diff options
author | James Morris <jmorris@namei.org> | 2008-08-28 04:47:34 +0400 |
---|---|---|
committer | James Morris <jmorris@namei.org> | 2008-08-28 04:47:34 +0400 |
commit | 86d688984deefa3ae5a802880c11f2b408b5d6cf (patch) | |
tree | 7ea5e8189b0a774626d3ed7c3c87df2495a4c4a0 /net | |
parent | 93c06cbbf9fea5d5be1778febb7fa9ab1a74e5f5 (diff) | |
parent | 4c246edd2550304df5b766cc841584b2bb058843 (diff) | |
download | linux-86d688984deefa3ae5a802880c11f2b408b5d6cf.tar.xz |
Merge branch 'master' into next
Diffstat (limited to 'net')
102 files changed, 1436 insertions, 988 deletions
diff --git a/net/ax25/sysctl_net_ax25.c b/net/ax25/sysctl_net_ax25.c index f597987b2424..f288fc4aef9b 100644 --- a/net/ax25/sysctl_net_ax25.c +++ b/net/ax25/sysctl_net_ax25.c @@ -36,6 +36,7 @@ static struct ctl_path ax25_path[] = { { .procname = "ax25", .ctl_name = NET_AX25, }, { } }; + static const ctl_table ax25_param_table[] = { { .ctl_name = NET_AX25_IP_DEFAULT_MODE, @@ -167,6 +168,7 @@ static const ctl_table ax25_param_table[] = { .extra1 = &min_proto, .extra2 = &max_proto }, +#ifdef CONFIG_AX25_DAMA_SLAVE { .ctl_name = NET_AX25_DAMA_SLAVE_TIMEOUT, .procname = "dama_slave_timeout", @@ -177,6 +179,8 @@ static const ctl_table ax25_param_table[] = { .extra1 = &min_ds_timeout, .extra2 = &max_ds_timeout }, +#endif + { .ctl_name = 0 } /* that's all, folks! */ }; @@ -210,16 +214,6 @@ void ax25_register_sysctl(void) ax25_table[n].procname = ax25_dev->dev->name; ax25_table[n].mode = 0555; -#ifndef CONFIG_AX25_DAMA_SLAVE - /* - * We do not wish to have a representation of this parameter - * in /proc/sys/ when configured *not* to include the - * AX.25 DAMA slave code, do we? - */ - - child[AX25_VALUES_DS_TIMEOUT].procname = NULL; -#endif - child[AX25_MAX_VALUES].ctl_name = 0; /* just in case... */ for (k = 0; k < AX25_MAX_VALUES; k++) diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 4e59df5f8e05..1edfdf4c095b 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -456,7 +456,7 @@ static void __exit bt_exit(void) subsys_initcall(bt_init); module_exit(bt_exit); -MODULE_AUTHOR("Maxim Krasnyansky <maxk@qualcomm.com>, Marcel Holtmann <marcel@holtmann.org>"); +MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth Core ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 021172c0e666..80ba30cf4b68 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -57,7 +57,10 @@ #define BT_DBG(D...) #endif -#define VERSION "1.2" +#define VERSION "1.3" + +static int compress_src = 1; +static int compress_dst = 1; static LIST_HEAD(bnep_session_list); static DECLARE_RWSEM(bnep_session_sem); @@ -418,10 +421,10 @@ static inline int bnep_tx_frame(struct bnep_session *s, struct sk_buff *skb) iv[il++] = (struct kvec) { &type, 1 }; len++; - if (!compare_ether_addr(eh->h_dest, s->eh.h_source)) + if (compress_src && !compare_ether_addr(eh->h_dest, s->eh.h_source)) type |= 0x01; - if (!compare_ether_addr(eh->h_source, s->eh.h_dest)) + if (compress_dst && !compare_ether_addr(eh->h_source, s->eh.h_dest)) type |= 0x02; if (type) @@ -727,7 +730,13 @@ static void __exit bnep_exit(void) module_init(bnep_init); module_exit(bnep_exit); -MODULE_AUTHOR("David Libault <david.libault@inventel.fr>, Maxim Krasnyansky <maxk@qualcomm.com>"); +module_param(compress_src, bool, 0644); +MODULE_PARM_DESC(compress_src, "Compress sources headers"); + +module_param(compress_dst, bool, 0644); +MODULE_PARM_DESC(compress_dst, "Compress destination headers"); + +MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth BNEP ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index c85bf8f678dc..f4f6615cad9f 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -3,8 +3,6 @@ #include <linux/kernel.h> #include <linux/init.h> -#include <linux/platform_device.h> - #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -12,10 +10,164 @@ #undef BT_DBG #define BT_DBG(D...) #endif + +struct class *bt_class = NULL; +EXPORT_SYMBOL_GPL(bt_class); + static struct workqueue_struct *btaddconn; static struct workqueue_struct *btdelconn; -static inline char *typetostr(int type) +static inline char *link_typetostr(int type) +{ + switch (type) { + case ACL_LINK: + return "ACL"; + case SCO_LINK: + return "SCO"; + case ESCO_LINK: + return "eSCO"; + default: + return "UNKNOWN"; + } +} + +static ssize_t show_link_type(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hci_conn *conn = dev_get_drvdata(dev); + return sprintf(buf, "%s\n", link_typetostr(conn->type)); +} + +static ssize_t show_link_address(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hci_conn *conn = dev_get_drvdata(dev); + bdaddr_t bdaddr; + baswap(&bdaddr, &conn->dst); + return sprintf(buf, "%s\n", batostr(&bdaddr)); +} + +static ssize_t show_link_features(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hci_conn *conn = dev_get_drvdata(dev); + + return sprintf(buf, "0x%02x%02x%02x%02x%02x%02x%02x%02x\n", + conn->features[0], conn->features[1], + conn->features[2], conn->features[3], + conn->features[4], conn->features[5], + conn->features[6], conn->features[7]); +} + +#define LINK_ATTR(_name,_mode,_show,_store) \ +struct device_attribute link_attr_##_name = __ATTR(_name,_mode,_show,_store) + +static LINK_ATTR(type, S_IRUGO, show_link_type, NULL); +static LINK_ATTR(address, S_IRUGO, show_link_address, NULL); +static LINK_ATTR(features, S_IRUGO, show_link_features, NULL); + +static struct attribute *bt_link_attrs[] = { + &link_attr_type.attr, + &link_attr_address.attr, + &link_attr_features.attr, + NULL +}; + +static struct attribute_group bt_link_group = { + .attrs = bt_link_attrs, +}; + +static struct attribute_group *bt_link_groups[] = { + &bt_link_group, + NULL +}; + +static void bt_link_release(struct device *dev) +{ + void *data = dev_get_drvdata(dev); + kfree(data); +} + +static struct device_type bt_link = { + .name = "link", + .groups = bt_link_groups, + .release = bt_link_release, +}; + +static void add_conn(struct work_struct *work) +{ + struct hci_conn *conn = container_of(work, struct hci_conn, work); + + flush_workqueue(btdelconn); + + if (device_add(&conn->dev) < 0) { + BT_ERR("Failed to register connection device"); + return; + } +} + +void hci_conn_add_sysfs(struct hci_conn *conn) +{ + struct hci_dev *hdev = conn->hdev; + + BT_DBG("conn %p", conn); + + conn->dev.type = &bt_link; + conn->dev.class = bt_class; + conn->dev.parent = &hdev->dev; + + snprintf(conn->dev.bus_id, BUS_ID_SIZE, "%s:%d", + hdev->name, conn->handle); + + dev_set_drvdata(&conn->dev, conn); + + device_initialize(&conn->dev); + + INIT_WORK(&conn->work, add_conn); + + queue_work(btaddconn, &conn->work); +} + +/* + * The rfcomm tty device will possibly retain even when conn + * is down, and sysfs doesn't support move zombie device, + * so we should move the device before conn device is destroyed. + */ +static int __match_tty(struct device *dev, void *data) +{ + return !strncmp(dev->bus_id, "rfcomm", 6); +} + +static void del_conn(struct work_struct *work) +{ + struct hci_conn *conn = container_of(work, struct hci_conn, work); + struct hci_dev *hdev = conn->hdev; + + while (1) { + struct device *dev; + + dev = device_find_child(&conn->dev, NULL, __match_tty); + if (!dev) + break; + device_move(dev, NULL); + put_device(dev); + } + + device_del(&conn->dev); + put_device(&conn->dev); + hci_dev_put(hdev); +} + +void hci_conn_del_sysfs(struct hci_conn *conn) +{ + BT_DBG("conn %p", conn); + + if (!device_is_registered(&conn->dev)) + return; + + INIT_WORK(&conn->work, del_conn); + + queue_work(btdelconn, &conn->work); +} + +static inline char *host_typetostr(int type) { switch (type) { case HCI_VIRTUAL: @@ -40,7 +192,7 @@ static inline char *typetostr(int type) static ssize_t show_type(struct device *dev, struct device_attribute *attr, char *buf) { struct hci_dev *hdev = dev_get_drvdata(dev); - return sprintf(buf, "%s\n", typetostr(hdev->type)); + return sprintf(buf, "%s\n", host_typetostr(hdev->type)); } static ssize_t show_name(struct device *dev, struct device_attribute *attr, char *buf) @@ -221,183 +373,62 @@ static DEVICE_ATTR(sniff_max_interval, S_IRUGO | S_IWUSR, static DEVICE_ATTR(sniff_min_interval, S_IRUGO | S_IWUSR, show_sniff_min_interval, store_sniff_min_interval); -static struct device_attribute *bt_attrs[] = { - &dev_attr_type, - &dev_attr_name, - &dev_attr_class, - &dev_attr_address, - &dev_attr_features, - &dev_attr_manufacturer, - &dev_attr_hci_version, - &dev_attr_hci_revision, - &dev_attr_inquiry_cache, - &dev_attr_idle_timeout, - &dev_attr_sniff_max_interval, - &dev_attr_sniff_min_interval, +static struct attribute *bt_host_attrs[] = { + &dev_attr_type.attr, + &dev_attr_name.attr, + &dev_attr_class.attr, + &dev_attr_address.attr, + &dev_attr_features.attr, + &dev_attr_manufacturer.attr, + &dev_attr_hci_version.attr, + &dev_attr_hci_revision.attr, + &dev_attr_inquiry_cache.attr, + &dev_attr_idle_timeout.attr, + &dev_attr_sniff_max_interval.attr, + &dev_attr_sniff_min_interval.attr, NULL }; -static ssize_t show_conn_type(struct device *dev, struct device_attribute *attr, char *buf) -{ - struct hci_conn *conn = dev_get_drvdata(dev); - return sprintf(buf, "%s\n", conn->type == ACL_LINK ? "ACL" : "SCO"); -} - -static ssize_t show_conn_address(struct device *dev, struct device_attribute *attr, char *buf) -{ - struct hci_conn *conn = dev_get_drvdata(dev); - bdaddr_t bdaddr; - baswap(&bdaddr, &conn->dst); - return sprintf(buf, "%s\n", batostr(&bdaddr)); -} - -static ssize_t show_conn_features(struct device *dev, struct device_attribute *attr, char *buf) -{ - struct hci_conn *conn = dev_get_drvdata(dev); - - return sprintf(buf, "0x%02x%02x%02x%02x%02x%02x%02x%02x\n", - conn->features[0], conn->features[1], - conn->features[2], conn->features[3], - conn->features[4], conn->features[5], - conn->features[6], conn->features[7]); -} - -#define CONN_ATTR(_name,_mode,_show,_store) \ -struct device_attribute conn_attr_##_name = __ATTR(_name,_mode,_show,_store) - -static CONN_ATTR(type, S_IRUGO, show_conn_type, NULL); -static CONN_ATTR(address, S_IRUGO, show_conn_address, NULL); -static CONN_ATTR(features, S_IRUGO, show_conn_features, NULL); - -static struct device_attribute *conn_attrs[] = { - &conn_attr_type, - &conn_attr_address, - &conn_attr_features, - NULL +static struct attribute_group bt_host_group = { + .attrs = bt_host_attrs, }; -struct class *bt_class = NULL; -EXPORT_SYMBOL_GPL(bt_class); - -static struct bus_type bt_bus = { - .name = "bluetooth", +static struct attribute_group *bt_host_groups[] = { + &bt_host_group, + NULL }; -static struct platform_device *bt_platform; - -static void bt_release(struct device *dev) +static void bt_host_release(struct device *dev) { void *data = dev_get_drvdata(dev); kfree(data); } -static void add_conn(struct work_struct *work) -{ - struct hci_conn *conn = container_of(work, struct hci_conn, work); - int i; - - flush_workqueue(btdelconn); - - if (device_add(&conn->dev) < 0) { - BT_ERR("Failed to register connection device"); - return; - } - - for (i = 0; conn_attrs[i]; i++) - if (device_create_file(&conn->dev, conn_attrs[i]) < 0) - BT_ERR("Failed to create connection attribute"); -} - -void hci_conn_add_sysfs(struct hci_conn *conn) -{ - struct hci_dev *hdev = conn->hdev; - - BT_DBG("conn %p", conn); - - conn->dev.bus = &bt_bus; - conn->dev.parent = &hdev->dev; - - conn->dev.release = bt_release; - - snprintf(conn->dev.bus_id, BUS_ID_SIZE, "%s:%d", - hdev->name, conn->handle); - - dev_set_drvdata(&conn->dev, conn); - - device_initialize(&conn->dev); - - INIT_WORK(&conn->work, add_conn); - - queue_work(btaddconn, &conn->work); -} - -/* - * The rfcomm tty device will possibly retain even when conn - * is down, and sysfs doesn't support move zombie device, - * so we should move the device before conn device is destroyed. - */ -static int __match_tty(struct device *dev, void *data) -{ - return !strncmp(dev->bus_id, "rfcomm", 6); -} - -static void del_conn(struct work_struct *work) -{ - struct hci_conn *conn = container_of(work, struct hci_conn, work); - struct hci_dev *hdev = conn->hdev; - - while (1) { - struct device *dev; - - dev = device_find_child(&conn->dev, NULL, __match_tty); - if (!dev) - break; - device_move(dev, NULL); - put_device(dev); - } - - device_del(&conn->dev); - put_device(&conn->dev); - hci_dev_put(hdev); -} - -void hci_conn_del_sysfs(struct hci_conn *conn) -{ - BT_DBG("conn %p", conn); - - if (!device_is_registered(&conn->dev)) - return; - - INIT_WORK(&conn->work, del_conn); - - queue_work(btdelconn, &conn->work); -} +static struct device_type bt_host = { + .name = "host", + .groups = bt_host_groups, + .release = bt_host_release, +}; int hci_register_sysfs(struct hci_dev *hdev) { struct device *dev = &hdev->dev; - unsigned int i; int err; BT_DBG("%p name %s type %d", hdev, hdev->name, hdev->type); - dev->bus = &bt_bus; + dev->type = &bt_host; + dev->class = bt_class; dev->parent = hdev->parent; strlcpy(dev->bus_id, hdev->name, BUS_ID_SIZE); - dev->release = bt_release; - dev_set_drvdata(dev, hdev); err = device_register(dev); if (err < 0) return err; - for (i = 0; bt_attrs[i]; i++) - if (device_create_file(dev, bt_attrs[i]) < 0) - BT_ERR("Failed to create device attribute"); - return 0; } @@ -410,59 +441,30 @@ void hci_unregister_sysfs(struct hci_dev *hdev) int __init bt_sysfs_init(void) { - int err; - btaddconn = create_singlethread_workqueue("btaddconn"); - if (!btaddconn) { - err = -ENOMEM; - goto out; - } + if (!btaddconn) + return -ENOMEM; btdelconn = create_singlethread_workqueue("btdelconn"); if (!btdelconn) { - err = -ENOMEM; - goto out_del; - } - - bt_platform = platform_device_register_simple("bluetooth", -1, NULL, 0); - if (IS_ERR(bt_platform)) { - err = PTR_ERR(bt_platform); - goto out_platform; + destroy_workqueue(btaddconn); + return -ENOMEM; } - err = bus_register(&bt_bus); - if (err < 0) - goto out_bus; - bt_class = class_create(THIS_MODULE, "bluetooth"); if (IS_ERR(bt_class)) { - err = PTR_ERR(bt_class); - goto out_class; + destroy_workqueue(btdelconn); + destroy_workqueue(btaddconn); + return PTR_ERR(bt_class); } return 0; - -out_class: - bus_unregister(&bt_bus); -out_bus: - platform_device_unregister(bt_platform); -out_platform: - destroy_workqueue(btdelconn); -out_del: - destroy_workqueue(btaddconn); -out: - return err; } void bt_sysfs_cleanup(void) { destroy_workqueue(btaddconn); - destroy_workqueue(btdelconn); class_destroy(bt_class); - - bus_unregister(&bt_bus); - - platform_device_unregister(bt_platform); } diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index c1239852834a..3396d5bdef1c 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -2516,7 +2516,7 @@ EXPORT_SYMBOL(l2cap_load); module_init(l2cap_init); module_exit(l2cap_exit); -MODULE_AUTHOR("Maxim Krasnyansky <maxk@qualcomm.com>, Marcel Holtmann <marcel@holtmann.org>"); +MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth L2CAP ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 6cfc7ba611b3..ba537fae0a4c 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -2115,7 +2115,7 @@ MODULE_PARM_DESC(channel_mtu, "Default MTU for the RFCOMM channel"); module_param(l2cap_mtu, uint, 0644); MODULE_PARM_DESC(l2cap_mtu, "Default MTU for the L2CAP connection"); -MODULE_AUTHOR("Maxim Krasnyansky <maxk@qualcomm.com>, Marcel Holtmann <marcel@holtmann.org>"); +MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth RFCOMM ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 8cda49874868..a16011fedc1d 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -1002,7 +1002,7 @@ module_exit(sco_exit); module_param(disable_esco, bool, 0644); MODULE_PARM_DESC(disable_esco, "Disable eSCO connection creation"); -MODULE_AUTHOR("Maxim Krasnyansky <maxk@qualcomm.com>, Marcel Holtmann <marcel@holtmann.org>"); +MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth SCO ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 9b58d70b0e7d..4f52c3d50ebe 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -148,11 +148,16 @@ static int br_set_tx_csum(struct net_device *dev, u32 data) } static struct ethtool_ops br_ethtool_ops = { - .get_drvinfo = br_getinfo, - .get_link = ethtool_op_get_link, - .set_sg = br_set_sg, - .set_tx_csum = br_set_tx_csum, - .set_tso = br_set_tso, + .get_drvinfo = br_getinfo, + .get_link = ethtool_op_get_link, + .get_tx_csum = ethtool_op_get_tx_csum, + .set_tx_csum = br_set_tx_csum, + .get_sg = ethtool_op_get_sg, + .set_sg = br_set_sg, + .get_tso = ethtool_op_get_tso, + .set_tso = br_set_tso, + .get_ufo = ethtool_op_get_ufo, + .get_flags = ethtool_op_get_flags, }; void br_dev_setup(struct net_device *dev) diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 6e280a8a31ee..6a9a6cd74b1e 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -113,7 +113,7 @@ void br_netfilter_rtable_init(struct net_bridge *br) struct rtable *rt = &br->fake_rtable; atomic_set(&rt->u.dst.__refcnt, 1); - rt->u.dst.dev = &br->dev; + rt->u.dst.dev = br->dev; rt->u.dst.path = &rt->u.dst; rt->u.dst.metrics[RTAX_MTU - 1] = 1500; rt->u.dst.flags = DST_NOXFRM; diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 921bbe5cb94a..6e63ec3f1fcf 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -368,14 +368,25 @@ static void br_make_blocking(struct net_bridge_port *p) /* called under bridge lock */ static void br_make_forwarding(struct net_bridge_port *p) { - if (p->state == BR_STATE_BLOCKING) { - if (p->br->stp_enabled == BR_KERNEL_STP) - p->state = BR_STATE_LISTENING; - else - p->state = BR_STATE_LEARNING; + struct net_bridge *br = p->br; - br_log_state(p); - mod_timer(&p->forward_delay_timer, jiffies + p->br->forward_delay); } + if (p->state != BR_STATE_BLOCKING) + return; + + if (br->forward_delay == 0) { + p->state = BR_STATE_FORWARDING; + br_topology_change_detection(br); + del_timer(&p->forward_delay_timer); + } + else if (p->br->stp_enabled == BR_KERNEL_STP) + p->state = BR_STATE_LISTENING; + else + p->state = BR_STATE_LEARNING; + + br_log_state(p); + + if (br->forward_delay != 0) + mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay); } /* called under bridge lock */ diff --git a/net/core/datagram.c b/net/core/datagram.c index dd61dcad6019..52f577a0f544 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -339,6 +339,93 @@ fault: return -EFAULT; } +/** + * skb_copy_datagram_from_iovec - Copy a datagram from an iovec. + * @skb: buffer to copy + * @offset: offset in the buffer to start copying to + * @from: io vector to copy to + * @len: amount of data to copy to buffer from iovec + * + * Returns 0 or -EFAULT. + * Note: the iovec is modified during the copy. + */ +int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, + struct iovec *from, int len) +{ + int start = skb_headlen(skb); + int i, copy = start - offset; + + /* Copy header. */ + if (copy > 0) { + if (copy > len) + copy = len; + if (memcpy_fromiovec(skb->data + offset, from, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + } + + /* Copy paged appendix. Hmm... why does this look so complicated? */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + int end; + + WARN_ON(start > offset + len); + + end = start + skb_shinfo(skb)->frags[i].size; + if ((copy = end - offset) > 0) { + int err; + u8 *vaddr; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct page *page = frag->page; + + if (copy > len) + copy = len; + vaddr = kmap(page); + err = memcpy_fromiovec(vaddr + frag->page_offset + + offset - start, from, copy); + kunmap(page); + if (err) + goto fault; + + if (!(len -= copy)) + return 0; + offset += copy; + } + start = end; + } + + if (skb_shinfo(skb)->frag_list) { + struct sk_buff *list = skb_shinfo(skb)->frag_list; + + for (; list; list = list->next) { + int end; + + WARN_ON(start > offset + len); + + end = start + list->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_datagram_from_iovec(list, + offset - start, + from, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + } + start = end; + } + } + if (!len) + return 0; + +fault: + return -EFAULT; +} +EXPORT_SYMBOL(skb_copy_datagram_from_iovec); + static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, u8 __user *to, int len, __wsum *csump) diff --git a/net/core/dev.c b/net/core/dev.c index 69320a56a084..60c51f765887 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1339,19 +1339,23 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) } -void __netif_schedule(struct Qdisc *q) +static inline void __netif_reschedule(struct Qdisc *q) { - if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) { - struct softnet_data *sd; - unsigned long flags; + struct softnet_data *sd; + unsigned long flags; - local_irq_save(flags); - sd = &__get_cpu_var(softnet_data); - q->next_sched = sd->output_queue; - sd->output_queue = q; - raise_softirq_irqoff(NET_TX_SOFTIRQ); - local_irq_restore(flags); - } + local_irq_save(flags); + sd = &__get_cpu_var(softnet_data); + q->next_sched = sd->output_queue; + sd->output_queue = q; + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); +} + +void __netif_schedule(struct Qdisc *q) +{ + if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) + __netif_reschedule(q); } EXPORT_SYMBOL(__netif_schedule); @@ -1796,16 +1800,19 @@ gso: skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS); #endif if (q->enqueue) { - spinlock_t *root_lock = qdisc_root_lock(q); + spinlock_t *root_lock = qdisc_lock(q); spin_lock(root_lock); - rc = qdisc_enqueue_root(skb, q); - qdisc_run(q); - + if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { + kfree_skb(skb); + rc = NET_XMIT_DROP; + } else { + rc = qdisc_enqueue_root(skb, q); + qdisc_run(q); + } spin_unlock(root_lock); - rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc; goto out; } @@ -1909,7 +1916,6 @@ int netif_rx(struct sk_buff *skb) if (queue->input_pkt_queue.qlen <= netdev_max_backlog) { if (queue->input_pkt_queue.qlen) { enqueue: - dev_hold(skb->dev); __skb_queue_tail(&queue->input_pkt_queue, skb); local_irq_restore(flags); return NET_RX_SUCCESS; @@ -1941,22 +1947,6 @@ int netif_rx_ni(struct sk_buff *skb) EXPORT_SYMBOL(netif_rx_ni); -static inline struct net_device *skb_bond(struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - - if (dev->master) { - if (skb_bond_should_drop(skb)) { - kfree_skb(skb); - return NULL; - } - skb->dev = dev->master; - } - - return dev; -} - - static void net_tx_action(struct softirq_action *h) { struct softnet_data *sd = &__get_cpu_var(softnet_data); @@ -1992,15 +1982,17 @@ static void net_tx_action(struct softirq_action *h) head = head->next_sched; - smp_mb__before_clear_bit(); - clear_bit(__QDISC_STATE_SCHED, &q->state); - - root_lock = qdisc_root_lock(q); + root_lock = qdisc_lock(q); if (spin_trylock(root_lock)) { + smp_mb__before_clear_bit(); + clear_bit(__QDISC_STATE_SCHED, + &q->state); qdisc_run(q); spin_unlock(root_lock); } else { - __netif_schedule(q); + if (!test_bit(__QDISC_STATE_DEACTIVATED, + &q->state)) + __netif_reschedule(q); } } } @@ -2102,7 +2094,8 @@ static int ing_filter(struct sk_buff *skb) q = rxq->qdisc; if (q != &noop_qdisc) { spin_lock(qdisc_lock(q)); - result = qdisc_enqueue_root(skb, q); + if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) + result = qdisc_enqueue_root(skb, q); spin_unlock(qdisc_lock(q)); } @@ -2183,6 +2176,7 @@ int netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; struct net_device *orig_dev; + struct net_device *null_or_orig; int ret = NET_RX_DROP; __be16 type; @@ -2196,10 +2190,14 @@ int netif_receive_skb(struct sk_buff *skb) if (!skb->iif) skb->iif = skb->dev->ifindex; - orig_dev = skb_bond(skb); - - if (!orig_dev) - return NET_RX_DROP; + null_or_orig = NULL; + orig_dev = skb->dev; + if (orig_dev->master) { + if (skb_bond_should_drop(skb)) + null_or_orig = orig_dev; /* deliver only exact match */ + else + skb->dev = orig_dev->master; + } __get_cpu_var(netdev_rx_stat).total++; @@ -2223,7 +2221,8 @@ int netif_receive_skb(struct sk_buff *skb) #endif list_for_each_entry_rcu(ptype, &ptype_all, list) { - if (!ptype->dev || ptype->dev == skb->dev) { + if (ptype->dev == null_or_orig || ptype->dev == skb->dev || + ptype->dev == orig_dev) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; @@ -2248,7 +2247,8 @@ ncls: list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { if (ptype->type == type && - (!ptype->dev || ptype->dev == skb->dev)) { + (ptype->dev == null_or_orig || ptype->dev == skb->dev || + ptype->dev == orig_dev)) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; @@ -2270,6 +2270,20 @@ out: return ret; } +/* Network device is going away, flush any packets still pending */ +static void flush_backlog(void *arg) +{ + struct net_device *dev = arg; + struct softnet_data *queue = &__get_cpu_var(softnet_data); + struct sk_buff *skb, *tmp; + + skb_queue_walk_safe(&queue->input_pkt_queue, skb, tmp) + if (skb->dev == dev) { + __skb_unlink(skb, &queue->input_pkt_queue); + kfree_skb(skb); + } +} + static int process_backlog(struct napi_struct *napi, int quota) { int work = 0; @@ -2279,7 +2293,6 @@ static int process_backlog(struct napi_struct *napi, int quota) napi->weight = weight_p; do { struct sk_buff *skb; - struct net_device *dev; local_irq_disable(); skb = __skb_dequeue(&queue->input_pkt_queue); @@ -2288,14 +2301,9 @@ static int process_backlog(struct napi_struct *napi, int quota) local_irq_enable(); break; } - local_irq_enable(); - dev = skb->dev; - netif_receive_skb(skb); - - dev_put(dev); } while (++work < quota && jiffies == start_time); return work; @@ -3988,6 +3996,10 @@ int register_netdevice(struct net_device *dev) } } + /* Enable software GSO if SG is supported. */ + if (dev->features & NETIF_F_SG) + dev->features |= NETIF_F_GSO; + netdev_initialize_kobject(dev); ret = netdev_register_kobject(dev); if (ret) @@ -4165,6 +4177,8 @@ void netdev_run_todo(void) dev->reg_state = NETREG_UNREGISTERED; + on_each_cpu(flush_backlog, dev, 1); + netdev_wait_allrefs(dev); /* paranoia */ diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f62c8af85d38..9d92e41826e7 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2281,6 +2281,7 @@ static struct neighbour *neigh_get_idx(struct seq_file *seq, loff_t *pos) struct neighbour *n = neigh_get_first(seq); if (n) { + --(*pos); while (*pos) { n = neigh_get_next(seq, n, pos); if (!n) @@ -2341,6 +2342,7 @@ static struct pneigh_entry *pneigh_get_idx(struct seq_file *seq, loff_t *pos) struct pneigh_entry *pn = pneigh_get_first(seq); if (pn) { + --(*pos); while (*pos) { pn = pneigh_get_next(seq, pn, pos); if (!pn) @@ -2354,10 +2356,11 @@ static void *neigh_get_idx_any(struct seq_file *seq, loff_t *pos) { struct neigh_seq_state *state = seq->private; void *rc; + loff_t idxpos = *pos; - rc = neigh_get_idx(seq, pos); + rc = neigh_get_idx(seq, &idxpos); if (!rc && !(state->flags & NEIGH_SEQ_NEIGH_ONLY)) - rc = pneigh_get_idx(seq, pos); + rc = pneigh_get_idx(seq, &idxpos); return rc; } @@ -2366,7 +2369,6 @@ void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl __acquires(tbl->lock) { struct neigh_seq_state *state = seq->private; - loff_t pos_minus_one; state->tbl = tbl; state->bucket = 0; @@ -2374,8 +2376,7 @@ void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl read_lock_bh(&tbl->lock); - pos_minus_one = *pos - 1; - return *pos ? neigh_get_idx_any(seq, &pos_minus_one) : SEQ_START_TOKEN; + return *pos ? neigh_get_idx_any(seq, pos) : SEQ_START_TOKEN; } EXPORT_SYMBOL(neigh_seq_start); @@ -2385,7 +2386,7 @@ void *neigh_seq_next(struct seq_file *seq, void *v, loff_t *pos) void *rc; if (v == SEQ_START_TOKEN) { - rc = neigh_get_idx(seq, pos); + rc = neigh_get_first(seq); goto out; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 3284605f2ec7..a756847e3814 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -168,7 +168,7 @@ #include <asm/div64.h> /* do_div */ #include <asm/timex.h> -#define VERSION "pktgen v2.69: Packet Generator for packet performance testing.\n" +#define VERSION "pktgen v2.70: Packet Generator for packet performance testing.\n" #define IP_NAME_SZ 32 #define MAX_MPLS_LABELS 16 /* This is the max label stack depth */ @@ -189,6 +189,7 @@ #define F_FLOW_SEQ (1<<11) /* Sequential flows */ #define F_IPSEC_ON (1<<12) /* ipsec on for flows */ #define F_QUEUE_MAP_RND (1<<13) /* queue map Random */ +#define F_QUEUE_MAP_CPU (1<<14) /* queue map mirrors smp_processor_id() */ /* Thread control flag bits */ #define T_TERMINATE (1<<0) @@ -621,6 +622,9 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->flags & F_QUEUE_MAP_RND) seq_printf(seq, "QUEUE_MAP_RND "); + if (pkt_dev->flags & F_QUEUE_MAP_CPU) + seq_printf(seq, "QUEUE_MAP_CPU "); + if (pkt_dev->cflows) { if (pkt_dev->flags & F_FLOW_SEQ) seq_printf(seq, "FLOW_SEQ "); /*in sequence flows*/ @@ -1134,6 +1138,12 @@ static ssize_t pktgen_if_write(struct file *file, else if (strcmp(f, "!QUEUE_MAP_RND") == 0) pkt_dev->flags &= ~F_QUEUE_MAP_RND; + + else if (strcmp(f, "QUEUE_MAP_CPU") == 0) + pkt_dev->flags |= F_QUEUE_MAP_CPU; + + else if (strcmp(f, "!QUEUE_MAP_CPU") == 0) + pkt_dev->flags &= ~F_QUEUE_MAP_CPU; #ifdef CONFIG_XFRM else if (strcmp(f, "IPSEC") == 0) pkt_dev->flags |= F_IPSEC_ON; @@ -1895,6 +1905,23 @@ static int pktgen_device_event(struct notifier_block *unused, return NOTIFY_DONE; } +static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev, const char *ifname) +{ + char b[IFNAMSIZ+5]; + int i = 0; + + for(i=0; ifname[i] != '@'; i++) { + if(i == IFNAMSIZ) + break; + + b[i] = ifname[i]; + } + b[i] = 0; + + return dev_get_by_name(&init_net, b); +} + + /* Associate pktgen_dev with a device. */ static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) @@ -1908,7 +1935,7 @@ static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) pkt_dev->odev = NULL; } - odev = dev_get_by_name(&init_net, ifname); + odev = pktgen_dev_get_by_name(pkt_dev, ifname); if (!odev) { printk(KERN_ERR "pktgen: no such netdevice: \"%s\"\n", ifname); return -ENODEV; @@ -1934,6 +1961,8 @@ static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) */ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) { + int ntxq; + if (!pkt_dev->odev) { printk(KERN_ERR "pktgen: ERROR: pkt_dev->odev == NULL in " "setup_inject.\n"); @@ -1942,6 +1971,33 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) return; } + /* make sure that we don't pick a non-existing transmit queue */ + ntxq = pkt_dev->odev->real_num_tx_queues; + if (ntxq <= num_online_cpus() && (pkt_dev->flags & F_QUEUE_MAP_CPU)) { + printk(KERN_WARNING "pktgen: WARNING: QUEUE_MAP_CPU " + "disabled because CPU count (%d) exceeds number ", + num_online_cpus()); + printk(KERN_WARNING "pktgen: WARNING: of tx queues " + "(%d) on %s \n", ntxq, pkt_dev->odev->name); + pkt_dev->flags &= ~F_QUEUE_MAP_CPU; + } + if (ntxq <= pkt_dev->queue_map_min) { + printk(KERN_WARNING "pktgen: WARNING: Requested " + "queue_map_min (%d) exceeds number of tx\n", + pkt_dev->queue_map_min); + printk(KERN_WARNING "pktgen: WARNING: queues (%d) on " + "%s, resetting\n", ntxq, pkt_dev->odev->name); + pkt_dev->queue_map_min = ntxq - 1; + } + if (ntxq <= pkt_dev->queue_map_max) { + printk(KERN_WARNING "pktgen: WARNING: Requested " + "queue_map_max (%d) exceeds number of tx\n", + pkt_dev->queue_map_max); + printk(KERN_WARNING "pktgen: WARNING: queues (%d) on " + "%s, resetting\n", ntxq, pkt_dev->odev->name); + pkt_dev->queue_map_max = ntxq - 1; + } + /* Default to the interface's mac if not explicitly set. */ if (is_zero_ether_addr(pkt_dev->src_mac)) @@ -2085,15 +2141,19 @@ static inline int f_pick(struct pktgen_dev *pkt_dev) if (pkt_dev->flows[flow].count >= pkt_dev->lflow) { /* reset time */ pkt_dev->flows[flow].count = 0; + pkt_dev->flows[flow].flags = 0; pkt_dev->curfl += 1; if (pkt_dev->curfl >= pkt_dev->cflows) pkt_dev->curfl = 0; /*reset */ } } else { flow = random32() % pkt_dev->cflows; + pkt_dev->curfl = flow; - if (pkt_dev->flows[flow].count > pkt_dev->lflow) + if (pkt_dev->flows[flow].count > pkt_dev->lflow) { pkt_dev->flows[flow].count = 0; + pkt_dev->flows[flow].flags = 0; + } } return pkt_dev->curfl; @@ -2125,7 +2185,11 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) #endif static void set_cur_queue_map(struct pktgen_dev *pkt_dev) { - if (pkt_dev->queue_map_min < pkt_dev->queue_map_max) { + + if (pkt_dev->flags & F_QUEUE_MAP_CPU) + pkt_dev->cur_queue_map = smp_processor_id(); + + else if (pkt_dev->queue_map_min < pkt_dev->queue_map_max) { __u16 t; if (pkt_dev->flags & F_QUEUE_MAP_RND) { t = random32() % @@ -2162,7 +2226,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) mc = random32() % pkt_dev->src_mac_count; else { mc = pkt_dev->cur_src_mac_offset++; - if (pkt_dev->cur_src_mac_offset > + if (pkt_dev->cur_src_mac_offset >= pkt_dev->src_mac_count) pkt_dev->cur_src_mac_offset = 0; } @@ -2189,7 +2253,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) else { mc = pkt_dev->cur_dst_mac_offset++; - if (pkt_dev->cur_dst_mac_offset > + if (pkt_dev->cur_dst_mac_offset >= pkt_dev->dst_mac_count) { pkt_dev->cur_dst_mac_offset = 0; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 84640172d65d..ca1ccdf1ef76 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2256,14 +2256,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) segs = nskb; tail = nskb; - nskb->dev = skb->dev; - skb_copy_queue_mapping(nskb, skb); - nskb->priority = skb->priority; - nskb->protocol = skb->protocol; - nskb->vlan_tci = skb->vlan_tci; - nskb->dst = dst_clone(skb->dst); - memcpy(nskb->cb, skb->cb, sizeof(skb->cb)); - nskb->pkt_type = skb->pkt_type; + __copy_skb_header(nskb, skb); nskb->mac_len = skb->mac_len; skb_reserve(nskb, headroom); @@ -2274,6 +2267,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) skb_copy_from_linear_data(skb, skb_put(nskb, doffset), doffset); if (!sg) { + nskb->ip_summed = CHECKSUM_NONE; nskb->csum = skb_copy_and_csum_bits(skb, offset, skb_put(nskb, len), len, 0); @@ -2283,8 +2277,6 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) frag = skb_shinfo(nskb)->frags; k = 0; - nskb->ip_summed = CHECKSUM_PARTIAL; - nskb->csum = skb->csum; skb_copy_from_linear_data_offset(skb, offset, skb_put(nskb, hsize), hsize); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 1c2e3ec2eb57..b4bc6e095a0e 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -229,7 +229,8 @@ extern void dccp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb); extern int dccp_retransmit_skb(struct sock *sk); extern void dccp_send_ack(struct sock *sk); -extern void dccp_reqsk_send_ack(struct sk_buff *sk, struct request_sock *rsk); +extern void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, + struct request_sock *rsk); extern void dccp_send_sync(struct sock *sk, const u64 seq, const enum dccp_pkt_type pkt_type); diff --git a/net/dccp/input.c b/net/dccp/input.c index df2f110df94a..803933ab396d 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -411,12 +411,6 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, struct dccp_sock *dp = dccp_sk(sk); long tstamp = dccp_timestamp(); - /* Stop the REQUEST timer */ - inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); - WARN_ON(sk->sk_send_head == NULL); - __kfree_skb(sk->sk_send_head); - sk->sk_send_head = NULL; - if (!between48(DCCP_SKB_CB(skb)->dccpd_ack_seq, dp->dccps_awl, dp->dccps_awh)) { dccp_pr_debug("invalid ackno: S.AWL=%llu, " @@ -441,6 +435,12 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, DCCP_ACKVEC_STATE_RECEIVED)) goto out_invalid_packet; /* FIXME: change error code */ + /* Stop the REQUEST timer */ + inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); + WARN_ON(sk->sk_send_head == NULL); + kfree_skb(sk->sk_send_head); + sk->sk_send_head = NULL; + dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq; dccp_update_gsr(sk, dp->dccps_isr); /* diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 66dca5bba858..b2804e2d1b8c 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -296,7 +296,8 @@ int dccp_child_process(struct sock *parent, struct sock *child, EXPORT_SYMBOL_GPL(dccp_child_process); -void dccp_reqsk_send_ack(struct sk_buff *skb, struct request_sock *rsk) +void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, + struct request_sock *rsk) { DCCP_BUG("DCCP-ACK packets are never sent in LISTEN/RESPOND state"); } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index b622d9744856..1ca3b26eed0f 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -474,6 +474,11 @@ static int dccp_setsockopt_change(struct sock *sk, int type, if (copy_from_user(&opt, optval, sizeof(opt))) return -EFAULT; + /* + * rfc4340: 6.1. Change Options + */ + if (opt.dccpsf_len < 1) + return -EINVAL; val = kmalloc(opt.dccpsf_len, GFP_KERNEL); if (!val) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 4e73e5708e70..21515d4c49eb 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -575,7 +575,7 @@ static int esp_init_state(struct xfrm_state *x) crypto_aead_ivsize(aead); if (x->props.mode == XFRM_MODE_TUNNEL) x->props.header_len += sizeof(struct iphdr); - else if (x->props.mode == XFRM_MODE_BEET) + else if (x->props.mode == XFRM_MODE_BEET && x->sel.family != AF_INET6) x->props.header_len += IPV4_BEET_PHMAXLEN; if (x->encap) { struct xfrm_encap_tmpl *encap = x->encap; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 860558633b2c..55c355e63234 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -204,18 +204,22 @@ static struct sock *icmp_sk(struct net *net) return net->ipv4.icmp_sk[smp_processor_id()]; } -static inline int icmp_xmit_lock(struct sock *sk) +static inline struct sock *icmp_xmit_lock(struct net *net) { + struct sock *sk; + local_bh_disable(); + sk = icmp_sk(net); + if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path signals a * dst_link_failure() for an outgoing ICMP packet. */ local_bh_enable(); - return 1; + return NULL; } - return 0; + return sk; } static inline void icmp_xmit_unlock(struct sock *sk) @@ -354,15 +358,17 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) struct ipcm_cookie ipc; struct rtable *rt = skb->rtable; struct net *net = dev_net(rt->u.dst.dev); - struct sock *sk = icmp_sk(net); - struct inet_sock *inet = inet_sk(sk); + struct sock *sk; + struct inet_sock *inet; __be32 daddr; if (ip_options_echo(&icmp_param->replyopts, skb)) return; - if (icmp_xmit_lock(sk)) + sk = icmp_xmit_lock(net); + if (sk == NULL) return; + inet = inet_sk(sk); icmp_param->data.icmph.checksum = 0; @@ -419,7 +425,6 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) if (!rt) goto out; net = dev_net(rt->u.dst.dev); - sk = icmp_sk(net); /* * Find the original header. It is expected to be valid, of course. @@ -483,7 +488,8 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) } } - if (icmp_xmit_lock(sk)) + sk = icmp_xmit_lock(net); + if (sk == NULL) return; /* diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6203ece53606..f70fac612596 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -289,6 +289,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) struct rtable *rt; struct iphdr *pip; struct igmpv3_report *pig; + struct net *net = dev_net(dev); skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev), GFP_ATOMIC); if (skb == NULL) @@ -299,7 +300,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) .nl_u = { .ip4_u = { .daddr = IGMPV3_ALL_MCR } }, .proto = IPPROTO_IGMP }; - if (ip_route_output_key(&init_net, &rt, &fl)) { + if (ip_route_output_key(net, &rt, &fl)) { kfree_skb(skb); return NULL; } @@ -629,6 +630,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, struct igmphdr *ih; struct rtable *rt; struct net_device *dev = in_dev->dev; + struct net *net = dev_net(dev); __be32 group = pmc ? pmc->multiaddr : 0; __be32 dst; @@ -643,7 +645,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, struct flowi fl = { .oif = dev->ifindex, .nl_u = { .ip4_u = { .daddr = dst } }, .proto = IPPROTO_IGMP }; - if (ip_route_output_key(&init_net, &rt, &fl)) + if (ip_route_output_key(net, &rt, &fl)) return -1; } if (rt->rt_src == 0) { @@ -1196,9 +1198,6 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) ASSERT_RTNL(); - if (!net_eq(dev_net(in_dev->dev), &init_net)) - return; - for (im=in_dev->mc_list; im; im=im->next) { if (im->multiaddr == addr) { im->users++; @@ -1278,9 +1277,6 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) ASSERT_RTNL(); - if (!net_eq(dev_net(in_dev->dev), &init_net)) - return; - for (ip=&in_dev->mc_list; (i=*ip)!=NULL; ip=&i->next) { if (i->multiaddr==addr) { if (--i->users == 0) { @@ -1308,9 +1304,6 @@ void ip_mc_down(struct in_device *in_dev) ASSERT_RTNL(); - if (!net_eq(dev_net(in_dev->dev), &init_net)) - return; - for (i=in_dev->mc_list; i; i=i->next) igmp_group_dropped(i); @@ -1331,9 +1324,6 @@ void ip_mc_init_dev(struct in_device *in_dev) { ASSERT_RTNL(); - if (!net_eq(dev_net(in_dev->dev), &init_net)) - return; - in_dev->mc_tomb = NULL; #ifdef CONFIG_IP_MULTICAST in_dev->mr_gq_running = 0; @@ -1357,9 +1347,6 @@ void ip_mc_up(struct in_device *in_dev) ASSERT_RTNL(); - if (!net_eq(dev_net(in_dev->dev), &init_net)) - return; - ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for (i=in_dev->mc_list; i; i=i->next) @@ -1376,9 +1363,6 @@ void ip_mc_destroy_dev(struct in_device *in_dev) ASSERT_RTNL(); - if (!net_eq(dev_net(in_dev->dev), &init_net)) - return; - /* Deactivate timers */ ip_mc_down(in_dev); @@ -1395,7 +1379,7 @@ void ip_mc_destroy_dev(struct in_device *in_dev) write_unlock_bh(&in_dev->mc_list_lock); } -static struct in_device * ip_mc_find_dev(struct ip_mreqn *imr) +static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) { struct flowi fl = { .nl_u = { .ip4_u = { .daddr = imr->imr_multiaddr.s_addr } } }; @@ -1404,19 +1388,19 @@ static struct in_device * ip_mc_find_dev(struct ip_mreqn *imr) struct in_device *idev = NULL; if (imr->imr_ifindex) { - idev = inetdev_by_index(&init_net, imr->imr_ifindex); + idev = inetdev_by_index(net, imr->imr_ifindex); if (idev) __in_dev_put(idev); return idev; } if (imr->imr_address.s_addr) { - dev = ip_dev_find(&init_net, imr->imr_address.s_addr); + dev = ip_dev_find(net, imr->imr_address.s_addr); if (!dev) return NULL; dev_put(dev); } - if (!dev && !ip_route_output_key(&init_net, &rt, &fl)) { + if (!dev && !ip_route_output_key(net, &rt, &fl)) { dev = rt->u.dst.dev; ip_rt_put(rt); } @@ -1754,18 +1738,16 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) struct ip_mc_socklist *iml=NULL, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); + struct net *net = sock_net(sk); int ifindex; int count = 0; if (!ipv4_is_multicast(addr)) return -EINVAL; - if (!net_eq(sock_net(sk), &init_net)) - return -EPROTONOSUPPORT; - rtnl_lock(); - in_dev = ip_mc_find_dev(imr); + in_dev = ip_mc_find_dev(net, imr); if (!in_dev) { iml = NULL; @@ -1827,15 +1809,13 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml, **imlp; struct in_device *in_dev; + struct net *net = sock_net(sk); __be32 group = imr->imr_multiaddr.s_addr; u32 ifindex; int ret = -EADDRNOTAVAIL; - if (!net_eq(sock_net(sk), &init_net)) - return -EPROTONOSUPPORT; - rtnl_lock(); - in_dev = ip_mc_find_dev(imr); + in_dev = ip_mc_find_dev(net, imr); ifindex = imr->imr_ifindex; for (imlp = &inet->mc_list; (iml = *imlp) != NULL; imlp = &iml->next) { if (iml->multi.imr_multiaddr.s_addr != group) @@ -1873,21 +1853,19 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct struct in_device *in_dev = NULL; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; + struct net *net = sock_net(sk); int leavegroup = 0; int i, j, rv; if (!ipv4_is_multicast(addr)) return -EINVAL; - if (!net_eq(sock_net(sk), &init_net)) - return -EPROTONOSUPPORT; - rtnl_lock(); imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr; imr.imr_address.s_addr = mreqs->imr_interface; imr.imr_ifindex = ifindex; - in_dev = ip_mc_find_dev(&imr); + in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; @@ -2007,6 +1985,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *newpsl, *psl; + struct net *net = sock_net(sk); int leavegroup = 0; if (!ipv4_is_multicast(addr)) @@ -2015,15 +1994,12 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; - if (!net_eq(sock_net(sk), &init_net)) - return -EPROTONOSUPPORT; - rtnl_lock(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = ifindex; - in_dev = ip_mc_find_dev(&imr); + in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; @@ -2094,19 +2070,17 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; + struct net *net = sock_net(sk); if (!ipv4_is_multicast(addr)) return -EINVAL; - if (!net_eq(sock_net(sk), &init_net)) - return -EPROTONOSUPPORT; - rtnl_lock(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = 0; - in_dev = ip_mc_find_dev(&imr); + in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; @@ -2163,9 +2137,6 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, if (!ipv4_is_multicast(addr)) return -EINVAL; - if (!net_eq(sock_net(sk), &init_net)) - return -EPROTONOSUPPORT; - rtnl_lock(); err = -EADDRNOTAVAIL; @@ -2246,19 +2217,17 @@ void ip_mc_drop_socket(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; + struct net *net = sock_net(sk); if (inet->mc_list == NULL) return; - if (!net_eq(sock_net(sk), &init_net)) - return; - rtnl_lock(); while ((iml = inet->mc_list) != NULL) { struct in_device *in_dev; inet->mc_list = iml->next; - in_dev = inetdev_by_index(&init_net, iml->multi.imr_ifindex); + in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); if (in_dev != NULL) { ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); diff --git a/net/ipv4/ipvs/ip_vs_app.c b/net/ipv4/ipvs/ip_vs_app.c index 1f1897a1a702..201b8ea3020d 100644 --- a/net/ipv4/ipvs/ip_vs_app.c +++ b/net/ipv4/ipvs/ip_vs_app.c @@ -608,7 +608,7 @@ int ip_vs_skb_replace(struct sk_buff *skb, gfp_t pri, } -int ip_vs_app_init(void) +int __init ip_vs_app_init(void) { /* we will replace it with proc_net_ipvs_create() soon */ proc_net_fops_create(&init_net, "ip_vs_app", 0, &ip_vs_app_fops); diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c index f8bdae47a77f..44a6872dc245 100644 --- a/net/ipv4/ipvs/ip_vs_conn.c +++ b/net/ipv4/ipvs/ip_vs_conn.c @@ -965,7 +965,7 @@ static void ip_vs_conn_flush(void) } -int ip_vs_conn_init(void) +int __init ip_vs_conn_init(void) { int idx; diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c index 9a5ace0b4dd6..6379705a8dcb 100644 --- a/net/ipv4/ipvs/ip_vs_ctl.c +++ b/net/ipv4/ipvs/ip_vs_ctl.c @@ -683,9 +683,22 @@ static void ip_vs_zero_stats(struct ip_vs_stats *stats) { spin_lock_bh(&stats->lock); - memset(stats, 0, (char *)&stats->lock - (char *)stats); - spin_unlock_bh(&stats->lock); + + stats->conns = 0; + stats->inpkts = 0; + stats->outpkts = 0; + stats->inbytes = 0; + stats->outbytes = 0; + + stats->cps = 0; + stats->inpps = 0; + stats->outpps = 0; + stats->inbps = 0; + stats->outbps = 0; + ip_vs_zero_estimator(stats); + + spin_unlock_bh(&stats->lock); } /* @@ -1589,7 +1602,7 @@ static struct ctl_table vs_vars[] = { { .ctl_name = 0 } }; -struct ctl_path net_vs_ctl_path[] = { +const struct ctl_path net_vs_ctl_path[] = { { .procname = "net", .ctl_name = CTL_NET, }, { .procname = "ipv4", .ctl_name = NET_IPV4, }, { .procname = "vs", }, @@ -1784,7 +1797,9 @@ static const struct file_operations ip_vs_info_fops = { #endif -struct ip_vs_stats ip_vs_stats; +struct ip_vs_stats ip_vs_stats = { + .lock = __SPIN_LOCK_UNLOCKED(ip_vs_stats.lock), +}; #ifdef CONFIG_PROC_FS static int ip_vs_stats_show(struct seq_file *seq, void *v) @@ -2306,7 +2321,7 @@ static struct nf_sockopt_ops ip_vs_sockopts = { }; -int ip_vs_control_init(void) +int __init ip_vs_control_init(void) { int ret; int idx; @@ -2333,8 +2348,6 @@ int ip_vs_control_init(void) INIT_LIST_HEAD(&ip_vs_rtable[idx]); } - memset(&ip_vs_stats, 0, sizeof(ip_vs_stats)); - spin_lock_init(&ip_vs_stats.lock); ip_vs_new_estimator(&ip_vs_stats); /* Hook the defense timer */ diff --git a/net/ipv4/ipvs/ip_vs_dh.c b/net/ipv4/ipvs/ip_vs_dh.c index 8afc1503ed20..fa66824d264f 100644 --- a/net/ipv4/ipvs/ip_vs_dh.c +++ b/net/ipv4/ipvs/ip_vs_dh.c @@ -233,6 +233,7 @@ static struct ip_vs_scheduler ip_vs_dh_scheduler = .name = "dh", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_dh_scheduler.n_list), .init_service = ip_vs_dh_init_svc, .done_service = ip_vs_dh_done_svc, .update_service = ip_vs_dh_update_svc, @@ -242,7 +243,6 @@ static struct ip_vs_scheduler ip_vs_dh_scheduler = static int __init ip_vs_dh_init(void) { - INIT_LIST_HEAD(&ip_vs_dh_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_dh_scheduler); } diff --git a/net/ipv4/ipvs/ip_vs_est.c b/net/ipv4/ipvs/ip_vs_est.c index bc04eedd6dbb..5a20f93bd7f9 100644 --- a/net/ipv4/ipvs/ip_vs_est.c +++ b/net/ipv4/ipvs/ip_vs_est.c @@ -17,6 +17,7 @@ #include <linux/types.h> #include <linux/interrupt.h> #include <linux/sysctl.h> +#include <linux/list.h> #include <net/ip_vs.h> @@ -44,28 +45,11 @@ */ -struct ip_vs_estimator -{ - struct ip_vs_estimator *next; - struct ip_vs_stats *stats; - - u32 last_conns; - u32 last_inpkts; - u32 last_outpkts; - u64 last_inbytes; - u64 last_outbytes; - - u32 cps; - u32 inpps; - u32 outpps; - u32 inbps; - u32 outbps; -}; - +static void estimation_timer(unsigned long arg); -static struct ip_vs_estimator *est_list = NULL; -static DEFINE_RWLOCK(est_lock); -static struct timer_list est_timer; +static LIST_HEAD(est_list); +static DEFINE_SPINLOCK(est_lock); +static DEFINE_TIMER(est_timer, estimation_timer, 0, 0); static void estimation_timer(unsigned long arg) { @@ -76,9 +60,9 @@ static void estimation_timer(unsigned long arg) u64 n_inbytes, n_outbytes; u32 rate; - read_lock(&est_lock); - for (e = est_list; e; e = e->next) { - s = e->stats; + spin_lock(&est_lock); + list_for_each_entry(e, &est_list, list) { + s = container_of(e, struct ip_vs_stats, est); spin_lock(&s->lock); n_conns = s->conns; @@ -114,19 +98,16 @@ static void estimation_timer(unsigned long arg) s->outbps = (e->outbps+0xF)>>5; spin_unlock(&s->lock); } - read_unlock(&est_lock); + spin_unlock(&est_lock); mod_timer(&est_timer, jiffies + 2*HZ); } -int ip_vs_new_estimator(struct ip_vs_stats *stats) +void ip_vs_new_estimator(struct ip_vs_stats *stats) { - struct ip_vs_estimator *est; + struct ip_vs_estimator *est = &stats->est; - est = kzalloc(sizeof(*est), GFP_KERNEL); - if (est == NULL) - return -ENOMEM; + INIT_LIST_HEAD(&est->list); - est->stats = stats; est->last_conns = stats->conns; est->cps = stats->cps<<10; @@ -142,59 +123,40 @@ int ip_vs_new_estimator(struct ip_vs_stats *stats) est->last_outbytes = stats->outbytes; est->outbps = stats->outbps<<5; - write_lock_bh(&est_lock); - est->next = est_list; - if (est->next == NULL) { - setup_timer(&est_timer, estimation_timer, 0); - est_timer.expires = jiffies + 2*HZ; - add_timer(&est_timer); - } - est_list = est; - write_unlock_bh(&est_lock); - return 0; + spin_lock_bh(&est_lock); + if (list_empty(&est_list)) + mod_timer(&est_timer, jiffies + 2 * HZ); + list_add(&est->list, &est_list); + spin_unlock_bh(&est_lock); } void ip_vs_kill_estimator(struct ip_vs_stats *stats) { - struct ip_vs_estimator *est, **pest; - int killed = 0; - - write_lock_bh(&est_lock); - pest = &est_list; - while ((est=*pest) != NULL) { - if (est->stats != stats) { - pest = &est->next; - continue; - } - *pest = est->next; - kfree(est); - killed++; + struct ip_vs_estimator *est = &stats->est; + + spin_lock_bh(&est_lock); + list_del(&est->list); + while (list_empty(&est_list) && try_to_del_timer_sync(&est_timer) < 0) { + spin_unlock_bh(&est_lock); + cpu_relax(); + spin_lock_bh(&est_lock); } - if (killed && est_list == NULL) - del_timer_sync(&est_timer); - write_unlock_bh(&est_lock); + spin_unlock_bh(&est_lock); } void ip_vs_zero_estimator(struct ip_vs_stats *stats) { - struct ip_vs_estimator *e; - - write_lock_bh(&est_lock); - for (e = est_list; e; e = e->next) { - if (e->stats != stats) - continue; - - /* set counters zero */ - e->last_conns = 0; - e->last_inpkts = 0; - e->last_outpkts = 0; - e->last_inbytes = 0; - e->last_outbytes = 0; - e->cps = 0; - e->inpps = 0; - e->outpps = 0; - e->inbps = 0; - e->outbps = 0; - } - write_unlock_bh(&est_lock); + struct ip_vs_estimator *est = &stats->est; + + /* set counters zero, caller must hold the stats->lock lock */ + est->last_inbytes = 0; + est->last_outbytes = 0; + est->last_conns = 0; + est->last_inpkts = 0; + est->last_outpkts = 0; + est->cps = 0; + est->inpps = 0; + est->outpps = 0; + est->inbps = 0; + est->outbps = 0; } diff --git a/net/ipv4/ipvs/ip_vs_lblc.c b/net/ipv4/ipvs/ip_vs_lblc.c index 0efa3db4b180..7a6a319f544a 100644 --- a/net/ipv4/ipvs/ip_vs_lblc.c +++ b/net/ipv4/ipvs/ip_vs_lblc.c @@ -539,6 +539,7 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler = .name = "lblc", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_lblc_scheduler.n_list), .init_service = ip_vs_lblc_init_svc, .done_service = ip_vs_lblc_done_svc, .update_service = ip_vs_lblc_update_svc, @@ -550,7 +551,6 @@ static int __init ip_vs_lblc_init(void) { int ret; - INIT_LIST_HEAD(&ip_vs_lblc_scheduler.n_list); sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table); ret = register_ip_vs_scheduler(&ip_vs_lblc_scheduler); if (ret) diff --git a/net/ipv4/ipvs/ip_vs_lblcr.c b/net/ipv4/ipvs/ip_vs_lblcr.c index 8e3bbeb45138..c234e73968a6 100644 --- a/net/ipv4/ipvs/ip_vs_lblcr.c +++ b/net/ipv4/ipvs/ip_vs_lblcr.c @@ -728,6 +728,7 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler = .name = "lblcr", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_lblcr_scheduler.n_list), .init_service = ip_vs_lblcr_init_svc, .done_service = ip_vs_lblcr_done_svc, .update_service = ip_vs_lblcr_update_svc, @@ -739,7 +740,6 @@ static int __init ip_vs_lblcr_init(void) { int ret; - INIT_LIST_HEAD(&ip_vs_lblcr_scheduler.n_list); sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table); ret = register_ip_vs_scheduler(&ip_vs_lblcr_scheduler); if (ret) diff --git a/net/ipv4/ipvs/ip_vs_lc.c b/net/ipv4/ipvs/ip_vs_lc.c index ac9f08e065d5..ebcdbf75ac65 100644 --- a/net/ipv4/ipvs/ip_vs_lc.c +++ b/net/ipv4/ipvs/ip_vs_lc.c @@ -98,6 +98,7 @@ static struct ip_vs_scheduler ip_vs_lc_scheduler = { .name = "lc", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_lc_scheduler.n_list), .init_service = ip_vs_lc_init_svc, .done_service = ip_vs_lc_done_svc, .update_service = ip_vs_lc_update_svc, @@ -107,7 +108,6 @@ static struct ip_vs_scheduler ip_vs_lc_scheduler = { static int __init ip_vs_lc_init(void) { - INIT_LIST_HEAD(&ip_vs_lc_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_lc_scheduler) ; } diff --git a/net/ipv4/ipvs/ip_vs_nq.c b/net/ipv4/ipvs/ip_vs_nq.c index a46bf258d420..92f3a6770031 100644 --- a/net/ipv4/ipvs/ip_vs_nq.c +++ b/net/ipv4/ipvs/ip_vs_nq.c @@ -136,6 +136,7 @@ static struct ip_vs_scheduler ip_vs_nq_scheduler = .name = "nq", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_nq_scheduler.n_list), .init_service = ip_vs_nq_init_svc, .done_service = ip_vs_nq_done_svc, .update_service = ip_vs_nq_update_svc, @@ -145,7 +146,6 @@ static struct ip_vs_scheduler ip_vs_nq_scheduler = static int __init ip_vs_nq_init(void) { - INIT_LIST_HEAD(&ip_vs_nq_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_nq_scheduler); } diff --git a/net/ipv4/ipvs/ip_vs_proto.c b/net/ipv4/ipvs/ip_vs_proto.c index 876714f23d65..6099a88fc200 100644 --- a/net/ipv4/ipvs/ip_vs_proto.c +++ b/net/ipv4/ipvs/ip_vs_proto.c @@ -43,7 +43,7 @@ static struct ip_vs_protocol *ip_vs_proto_table[IP_VS_PROTO_TAB_SIZE]; /* * register an ipvs protocol */ -static int __used register_ip_vs_protocol(struct ip_vs_protocol *pp) +static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp) { unsigned hash = IP_VS_PROTO_HASH(pp->protocol); @@ -190,7 +190,7 @@ ip_vs_tcpudp_debug_packet(struct ip_vs_protocol *pp, } -int ip_vs_protocol_init(void) +int __init ip_vs_protocol_init(void) { char protocols[64]; #define REGISTER_PROTOCOL(p) \ diff --git a/net/ipv4/ipvs/ip_vs_rr.c b/net/ipv4/ipvs/ip_vs_rr.c index c8db12d39e61..358110d17e59 100644 --- a/net/ipv4/ipvs/ip_vs_rr.c +++ b/net/ipv4/ipvs/ip_vs_rr.c @@ -94,6 +94,7 @@ static struct ip_vs_scheduler ip_vs_rr_scheduler = { .name = "rr", /* name */ .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_rr_scheduler.n_list), .init_service = ip_vs_rr_init_svc, .done_service = ip_vs_rr_done_svc, .update_service = ip_vs_rr_update_svc, @@ -102,7 +103,6 @@ static struct ip_vs_scheduler ip_vs_rr_scheduler = { static int __init ip_vs_rr_init(void) { - INIT_LIST_HEAD(&ip_vs_rr_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_rr_scheduler); } diff --git a/net/ipv4/ipvs/ip_vs_sched.c b/net/ipv4/ipvs/ip_vs_sched.c index b64767309855..a46ad9e35016 100644 --- a/net/ipv4/ipvs/ip_vs_sched.c +++ b/net/ipv4/ipvs/ip_vs_sched.c @@ -184,7 +184,7 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) write_lock_bh(&__ip_vs_sched_lock); - if (scheduler->n_list.next != &scheduler->n_list) { + if (!list_empty(&scheduler->n_list)) { write_unlock_bh(&__ip_vs_sched_lock); ip_vs_use_count_dec(); IP_VS_ERR("register_ip_vs_scheduler(): [%s] scheduler " @@ -229,7 +229,7 @@ int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) } write_lock_bh(&__ip_vs_sched_lock); - if (scheduler->n_list.next == &scheduler->n_list) { + if (list_empty(&scheduler->n_list)) { write_unlock_bh(&__ip_vs_sched_lock); IP_VS_ERR("unregister_ip_vs_scheduler(): [%s] scheduler " "is not in the list. failed\n", scheduler->name); diff --git a/net/ipv4/ipvs/ip_vs_sed.c b/net/ipv4/ipvs/ip_vs_sed.c index 2a7d31358181..77663d84cbd1 100644 --- a/net/ipv4/ipvs/ip_vs_sed.c +++ b/net/ipv4/ipvs/ip_vs_sed.c @@ -138,6 +138,7 @@ static struct ip_vs_scheduler ip_vs_sed_scheduler = .name = "sed", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_sed_scheduler.n_list), .init_service = ip_vs_sed_init_svc, .done_service = ip_vs_sed_done_svc, .update_service = ip_vs_sed_update_svc, @@ -147,7 +148,6 @@ static struct ip_vs_scheduler ip_vs_sed_scheduler = static int __init ip_vs_sed_init(void) { - INIT_LIST_HEAD(&ip_vs_sed_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_sed_scheduler); } diff --git a/net/ipv4/ipvs/ip_vs_sh.c b/net/ipv4/ipvs/ip_vs_sh.c index b8fdfac65001..7b979e228056 100644 --- a/net/ipv4/ipvs/ip_vs_sh.c +++ b/net/ipv4/ipvs/ip_vs_sh.c @@ -230,6 +230,7 @@ static struct ip_vs_scheduler ip_vs_sh_scheduler = .name = "sh", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_sh_scheduler.n_list), .init_service = ip_vs_sh_init_svc, .done_service = ip_vs_sh_done_svc, .update_service = ip_vs_sh_update_svc, @@ -239,7 +240,6 @@ static struct ip_vs_scheduler ip_vs_sh_scheduler = static int __init ip_vs_sh_init(void) { - INIT_LIST_HEAD(&ip_vs_sh_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_sh_scheduler); } diff --git a/net/ipv4/ipvs/ip_vs_sync.c b/net/ipv4/ipvs/ip_vs_sync.c index 45e9bd96c286..a652da2c3200 100644 --- a/net/ipv4/ipvs/ip_vs_sync.c +++ b/net/ipv4/ipvs/ip_vs_sync.c @@ -904,9 +904,9 @@ int stop_sync_thread(int state) * progress of stopping the master sync daemon. */ - spin_lock(&ip_vs_sync_lock); + spin_lock_bh(&ip_vs_sync_lock); ip_vs_sync_state &= ~IP_VS_STATE_MASTER; - spin_unlock(&ip_vs_sync_lock); + spin_unlock_bh(&ip_vs_sync_lock); kthread_stop(sync_master_thread); sync_master_thread = NULL; } else if (state == IP_VS_STATE_BACKUP) { diff --git a/net/ipv4/ipvs/ip_vs_wlc.c b/net/ipv4/ipvs/ip_vs_wlc.c index 772c3cb4eca1..9b0ef86bb1f7 100644 --- a/net/ipv4/ipvs/ip_vs_wlc.c +++ b/net/ipv4/ipvs/ip_vs_wlc.c @@ -126,6 +126,7 @@ static struct ip_vs_scheduler ip_vs_wlc_scheduler = .name = "wlc", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_wlc_scheduler.n_list), .init_service = ip_vs_wlc_init_svc, .done_service = ip_vs_wlc_done_svc, .update_service = ip_vs_wlc_update_svc, @@ -135,7 +136,6 @@ static struct ip_vs_scheduler ip_vs_wlc_scheduler = static int __init ip_vs_wlc_init(void) { - INIT_LIST_HEAD(&ip_vs_wlc_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_wlc_scheduler); } diff --git a/net/ipv4/ipvs/ip_vs_wrr.c b/net/ipv4/ipvs/ip_vs_wrr.c index 1d6932d7dc97..0d86a79b87b5 100644 --- a/net/ipv4/ipvs/ip_vs_wrr.c +++ b/net/ipv4/ipvs/ip_vs_wrr.c @@ -212,6 +212,7 @@ static struct ip_vs_scheduler ip_vs_wrr_scheduler = { .name = "wrr", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_wrr_scheduler.n_list), .init_service = ip_vs_wrr_init_svc, .done_service = ip_vs_wrr_done_svc, .update_service = ip_vs_wrr_update_svc, @@ -220,7 +221,6 @@ static struct ip_vs_scheduler ip_vs_wrr_scheduler = { static int __init ip_vs_wrr_init(void) { - INIT_LIST_HEAD(&ip_vs_wrr_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_wrr_scheduler) ; } diff --git a/net/ipv4/netfilter/ipt_addrtype.c b/net/ipv4/netfilter/ipt_addrtype.c index 49587a497229..462a22c97877 100644 --- a/net/ipv4/netfilter/ipt_addrtype.c +++ b/net/ipv4/netfilter/ipt_addrtype.c @@ -70,7 +70,7 @@ addrtype_mt_v1(const struct sk_buff *skb, const struct net_device *in, (info->flags & IPT_ADDRTYPE_INVERT_SOURCE); if (ret && info->dest) ret &= match_type(dev, iph->daddr, info->dest) ^ - (info->flags & IPT_ADDRTYPE_INVERT_DEST); + !!(info->flags & IPT_ADDRTYPE_INVERT_DEST); return ret; } diff --git a/net/ipv4/netfilter/nf_nat_proto_common.c b/net/ipv4/netfilter/nf_nat_proto_common.c index 91537f11273f..6c4f11f51446 100644 --- a/net/ipv4/netfilter/nf_nat_proto_common.c +++ b/net/ipv4/netfilter/nf_nat_proto_common.c @@ -73,9 +73,13 @@ bool nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple, range_size = ntohs(range->max.all) - min + 1; } - off = *rover; if (range->flags & IP_NAT_RANGE_PROTO_RANDOM) - off = net_random(); + off = secure_ipv4_port_ephemeral(tuple->src.u3.ip, tuple->dst.u3.ip, + maniptype == IP_NAT_MANIP_SRC + ? tuple->dst.u.all + : tuple->src.u.all); + else + off = *rover; for (i = 0; i < range_size; i++, off++) { *portptr = htons(min + off % range_size); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 1bfa078ddbd0..e91bafeb32f4 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1509,14 +1509,14 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, /* BSD 4.2 compatibility hack :-( */ if (mtu == 0 && - old_mtu >= dst_metric(&rth->u.dst, RTAX_MTU) && + old_mtu >= dst_mtu(&rth->u.dst) && old_mtu >= 68 + (iph->ihl << 2)) old_mtu -= iph->ihl << 2; mtu = guess_mtu(old_mtu); } - if (mtu <= dst_metric(&rth->u.dst, RTAX_MTU)) { - if (mtu < dst_metric(&rth->u.dst, RTAX_MTU)) { + if (mtu <= dst_mtu(&rth->u.dst)) { + if (mtu < dst_mtu(&rth->u.dst)) { dst_confirm(&rth->u.dst); if (mtu < ip_rt_min_pmtu) { mtu = ip_rt_min_pmtu; @@ -1538,7 +1538,7 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) { - if (dst_metric(dst, RTAX_MTU) > mtu && mtu >= 68 && + if (dst_mtu(dst) > mtu && mtu >= 68 && !(dst_metric_locked(dst, RTAX_MTU))) { if (mtu < ip_rt_min_pmtu) { mtu = ip_rt_min_pmtu; @@ -1667,7 +1667,7 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag) if (dst_metric(&rt->u.dst, RTAX_HOPLIMIT) == 0) rt->u.dst.metrics[RTAX_HOPLIMIT-1] = sysctl_ip_default_ttl; - if (dst_metric(&rt->u.dst, RTAX_MTU) > IP_MAX_MTU) + if (dst_mtu(&rt->u.dst) > IP_MAX_MTU) rt->u.dst.metrics[RTAX_MTU-1] = IP_MAX_MTU; if (dst_metric(&rt->u.dst, RTAX_ADVMSS) == 0) rt->u.dst.metrics[RTAX_ADVMSS-1] = max_t(unsigned int, rt->u.dst.dev->mtu - 40, @@ -2914,6 +2914,68 @@ static int ipv4_sysctl_rtcache_flush_strategy(ctl_table *table, return 0; } +static void rt_secret_reschedule(int old) +{ + struct net *net; + int new = ip_rt_secret_interval; + int diff = new - old; + + if (!diff) + return; + + rtnl_lock(); + for_each_net(net) { + int deleted = del_timer_sync(&net->ipv4.rt_secret_timer); + + if (!new) + continue; + + if (deleted) { + long time = net->ipv4.rt_secret_timer.expires - jiffies; + + if (time <= 0 || (time += diff) <= 0) + time = 0; + + net->ipv4.rt_secret_timer.expires = time; + } else + net->ipv4.rt_secret_timer.expires = new; + + net->ipv4.rt_secret_timer.expires += jiffies; + add_timer(&net->ipv4.rt_secret_timer); + } + rtnl_unlock(); +} + +static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write, + struct file *filp, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int old = ip_rt_secret_interval; + int ret = proc_dointvec_jiffies(ctl, write, filp, buffer, lenp, ppos); + + rt_secret_reschedule(old); + + return ret; +} + +static int ipv4_sysctl_rt_secret_interval_strategy(ctl_table *table, + int __user *name, + int nlen, + void __user *oldval, + size_t __user *oldlenp, + void __user *newval, + size_t newlen) +{ + int old = ip_rt_secret_interval; + int ret = sysctl_jiffies(table, name, nlen, oldval, oldlenp, newval, + newlen); + + rt_secret_reschedule(old); + + return ret; +} + static ctl_table ipv4_route_table[] = { { .ctl_name = NET_IPV4_ROUTE_GC_THRESH, @@ -3048,20 +3110,29 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_secret_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = &ipv4_sysctl_rt_secret_interval, + .strategy = &ipv4_sysctl_rt_secret_interval_strategy, }, { .ctl_name = 0 } }; -static __net_initdata struct ctl_path ipv4_route_path[] = { +static struct ctl_table empty[1]; + +static struct ctl_table ipv4_skeleton[] = +{ + { .procname = "route", .ctl_name = NET_IPV4_ROUTE, + .child = ipv4_route_table}, + { .procname = "neigh", .ctl_name = NET_IPV4_NEIGH, + .child = empty}, + { } +}; + +static __net_initdata struct ctl_path ipv4_path[] = { { .procname = "net", .ctl_name = CTL_NET, }, { .procname = "ipv4", .ctl_name = NET_IPV4, }, - { .procname = "route", .ctl_name = NET_IPV4_ROUTE, }, { }, }; - static struct ctl_table ipv4_route_flush_table[] = { { .ctl_name = NET_IPV4_ROUTE_FLUSH, @@ -3074,6 +3145,13 @@ static struct ctl_table ipv4_route_flush_table[] = { { .ctl_name = 0 }, }; +static __net_initdata struct ctl_path ipv4_route_path[] = { + { .procname = "net", .ctl_name = CTL_NET, }, + { .procname = "ipv4", .ctl_name = NET_IPV4, }, + { .procname = "route", .ctl_name = NET_IPV4_ROUTE, }, + { }, +}; + static __net_init int sysctl_route_net_init(struct net *net) { struct ctl_table *tbl; @@ -3126,10 +3204,12 @@ static __net_init int rt_secret_timer_init(struct net *net) net->ipv4.rt_secret_timer.data = (unsigned long)net; init_timer_deferrable(&net->ipv4.rt_secret_timer); - net->ipv4.rt_secret_timer.expires = - jiffies + net_random() % ip_rt_secret_interval + - ip_rt_secret_interval; - add_timer(&net->ipv4.rt_secret_timer); + if (ip_rt_secret_interval) { + net->ipv4.rt_secret_timer.expires = + jiffies + net_random() % ip_rt_secret_interval + + ip_rt_secret_interval; + add_timer(&net->ipv4.rt_secret_timer); + } return 0; } @@ -3223,9 +3303,7 @@ int __init ip_rt_init(void) */ void __init ip_static_sysctl_init(void) { -#ifdef CONFIG_SYSCTL - register_sysctl_paths(ipv4_route_path, ipv4_route_table); -#endif + register_sysctl_paths(ipv4_path, ipv4_skeleton); } #endif diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 770d827f5ab8..e0689fd7b798 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -232,6 +232,7 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = &ipv4_doint_and_flush, .strategy = &ipv4_doint_and_flush_strategy, + .extra2 = &init_net, }, { .ctl_name = NET_IPV4_NO_PMTU_DISC, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 91a8cfddf1c4..44c1e934824b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -687,14 +687,14 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) inet_twsk_put(tw); } -static void tcp_v4_reqsk_send_ack(struct sk_buff *skb, +static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent, 0, - tcp_v4_md5_do_lookup(skb->sk, ip_hdr(skb)->daddr)); + tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr)); } /* diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 204c42162660..f976fc57892c 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -609,7 +609,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, tcp_rsk(req)->rcv_isn + 1, tcp_rsk(req)->rcv_isn + 1 + req->rcv_wnd)) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST)) - req->rsk_ops->send_ack(skb, req); + req->rsk_ops->send_ack(sk, skb, req); if (paws_reject) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); return NULL; @@ -618,89 +618,87 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, /* In sequence, PAWS is OK. */ if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_isn + 1)) - req->ts_recent = tmp_opt.rcv_tsval; + req->ts_recent = tmp_opt.rcv_tsval; - if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { - /* Truncate SYN, it is out of window starting - at tcp_rsk(req)->rcv_isn + 1. */ - flg &= ~TCP_FLAG_SYN; - } + if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { + /* Truncate SYN, it is out of window starting + at tcp_rsk(req)->rcv_isn + 1. */ + flg &= ~TCP_FLAG_SYN; + } - /* RFC793: "second check the RST bit" and - * "fourth, check the SYN bit" - */ - if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN)) { - TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_ATTEMPTFAILS); - goto embryonic_reset; - } + /* RFC793: "second check the RST bit" and + * "fourth, check the SYN bit" + */ + if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN)) { + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_ATTEMPTFAILS); + goto embryonic_reset; + } - /* ACK sequence verified above, just make sure ACK is - * set. If ACK not set, just silently drop the packet. - */ - if (!(flg & TCP_FLAG_ACK)) - return NULL; - - /* If TCP_DEFER_ACCEPT is set, drop bare ACK. */ - if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && - TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { - inet_rsk(req)->acked = 1; - return NULL; - } + /* ACK sequence verified above, just make sure ACK is + * set. If ACK not set, just silently drop the packet. + */ + if (!(flg & TCP_FLAG_ACK)) + return NULL; - /* OK, ACK is valid, create big socket and - * feed this segment to it. It will repeat all - * the tests. THIS SEGMENT MUST MOVE SOCKET TO - * ESTABLISHED STATE. If it will be dropped after - * socket is created, wait for troubles. - */ - child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, - req, NULL); - if (child == NULL) - goto listen_overflow; + /* If TCP_DEFER_ACCEPT is set, drop bare ACK. */ + if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && + TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { + inet_rsk(req)->acked = 1; + return NULL; + } + + /* OK, ACK is valid, create big socket and + * feed this segment to it. It will repeat all + * the tests. THIS SEGMENT MUST MOVE SOCKET TO + * ESTABLISHED STATE. If it will be dropped after + * socket is created, wait for troubles. + */ + child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); + if (child == NULL) + goto listen_overflow; #ifdef CONFIG_TCP_MD5SIG - else { - /* Copy over the MD5 key from the original socket */ - struct tcp_md5sig_key *key; - struct tcp_sock *tp = tcp_sk(sk); - key = tp->af_specific->md5_lookup(sk, child); - if (key != NULL) { - /* - * We're using one, so create a matching key on the - * newsk structure. If we fail to get memory then we - * end up not copying the key across. Shucks. - */ - char *newkey = kmemdup(key->key, key->keylen, - GFP_ATOMIC); - if (newkey) { - if (!tcp_alloc_md5sig_pool()) - BUG(); - tp->af_specific->md5_add(child, child, - newkey, - key->keylen); - } + else { + /* Copy over the MD5 key from the original socket */ + struct tcp_md5sig_key *key; + struct tcp_sock *tp = tcp_sk(sk); + key = tp->af_specific->md5_lookup(sk, child); + if (key != NULL) { + /* + * We're using one, so create a matching key on the + * newsk structure. If we fail to get memory then we + * end up not copying the key across. Shucks. + */ + char *newkey = kmemdup(key->key, key->keylen, + GFP_ATOMIC); + if (newkey) { + if (!tcp_alloc_md5sig_pool()) + BUG(); + tp->af_specific->md5_add(child, child, newkey, + key->keylen); } } + } #endif - inet_csk_reqsk_queue_unlink(sk, req, prev); - inet_csk_reqsk_queue_removed(sk, req); + inet_csk_reqsk_queue_unlink(sk, req, prev); + inet_csk_reqsk_queue_removed(sk, req); - inet_csk_reqsk_queue_add(sk, req, child); - return child; + inet_csk_reqsk_queue_add(sk, req, child); + return child; - listen_overflow: - if (!sysctl_tcp_abort_on_overflow) { - inet_rsk(req)->acked = 1; - return NULL; - } +listen_overflow: + if (!sysctl_tcp_abort_on_overflow) { + inet_rsk(req)->acked = 1; + return NULL; + } - embryonic_reset: - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); - if (!(flg & TCP_FLAG_RST)) - req->rsk_ops->send_reset(sk, skb); +embryonic_reset: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); + if (!(flg & TCP_FLAG_RST)) + req->rsk_ops->send_reset(sk, skb); - inet_csk_reqsk_queue_drop(sk, req, prev); - return NULL; + inet_csk_reqsk_queue_drop(sk, req, prev); + return NULL; } /* diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 383d17359d01..8e42fbbd5761 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -989,7 +989,9 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) up->encap_rcv != NULL) { int ret; + bh_unlock_sock(sk); ret = (*up->encap_rcv)(sk, skb); + bh_lock_sock(sk); if (ret <= 0) { UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INDATAGRAMS, @@ -1092,7 +1094,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, if (skb1) { int ret = 0; - bh_lock_sock_nested(sk); + bh_lock_sock(sk); if (!sock_owned_by_user(sk)) ret = udp_queue_rcv_skb(sk, skb1); else @@ -1194,7 +1196,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], if (sk != NULL) { int ret = 0; - bh_lock_sock_nested(sk); + bh_lock_sock(sk); if (!sock_owned_by_user(sk)) ret = udp_queue_rcv_skb(sk, skb); else diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index 9c798abce736..63418185f524 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -47,8 +47,10 @@ static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb) if (unlikely(optlen)) hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4); - skb_set_network_header(skb, IPV4_BEET_PHMAXLEN - x->props.header_len - - hdrlen); + skb_set_network_header(skb, -x->props.header_len - + hdrlen + (XFRM_MODE_SKB_CB(skb)->ihl - sizeof(*top_iph))); + if (x->sel.family != AF_INET6) + skb->network_header += IPV4_BEET_PHMAXLEN; skb->mac_header = skb->network_header + offsetof(struct iphdr, protocol); skb->transport_header = skb->network_header + sizeof(*top_iph); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index a7842c54f58a..7b6a584b62dd 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1106,13 +1106,12 @@ out: return ret; } -int ipv6_dev_get_saddr(struct net_device *dst_dev, +int ipv6_dev_get_saddr(struct net *net, struct net_device *dst_dev, const struct in6_addr *daddr, unsigned int prefs, struct in6_addr *saddr) { struct ipv6_saddr_score scores[2], *score = &scores[0], *hiscore = &scores[1]; - struct net *net = dev_net(dst_dev); struct ipv6_saddr_dst dst; struct net_device *dev; int dst_type; @@ -1689,6 +1688,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, .fc_dst_len = plen, .fc_flags = RTF_UP | flags, .fc_nlinfo.nl_net = dev_net(dev), + .fc_protocol = RTPROT_KERNEL, }; ipv6_addr_copy(&cfg.fc_dst, pfx); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index c6bb4c6d24b3..b181b08fb761 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -521,6 +521,10 @@ static int esp6_init_state(struct xfrm_state *x) crypto_aead_ivsize(aead); switch (x->props.mode) { case XFRM_MODE_BEET: + if (x->sel.family != AF_INET6) + x->props.header_len += IPV4_BEET_PHMAXLEN + + (sizeof(struct ipv6hdr) - sizeof(struct iphdr)); + break; case XFRM_MODE_TRANSPORT: break; case XFRM_MODE_TUNNEL: diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 8d05527524e3..f5de3f9dc692 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -93,7 +93,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, if (flags & RT6_LOOKUP_F_SRCPREF_COA) srcprefs |= IPV6_PREFER_SRC_COA; - if (ipv6_dev_get_saddr(ip6_dst_idev(&rt->u.dst)->dev, + if (ipv6_dev_get_saddr(net, + ip6_dst_idev(&rt->u.dst)->dev, &flp->fl6_dst, srcprefs, &saddr)) goto again; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index abedf95fdf2d..b3157a0cc15d 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -91,19 +91,22 @@ static struct inet6_protocol icmpv6_protocol = { .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; -static __inline__ int icmpv6_xmit_lock(struct sock *sk) +static __inline__ struct sock *icmpv6_xmit_lock(struct net *net) { + struct sock *sk; + local_bh_disable(); + sk = icmpv6_sk(net); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path (f.e. SIT or * ip6ip6 tunnel) signals dst_link_failure() for an * outgoing ICMP6 packet. */ local_bh_enable(); - return 1; + return NULL; } - return 0; + return sk; } static __inline__ void icmpv6_xmit_unlock(struct sock *sk) @@ -392,11 +395,10 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, fl.fl_icmp_code = code; security_skb_classify_flow(skb, &fl); - sk = icmpv6_sk(net); - np = inet6_sk(sk); - - if (icmpv6_xmit_lock(sk)) + sk = icmpv6_xmit_lock(net); + if (sk == NULL) return; + np = inet6_sk(sk); if (!icmpv6_xrlim_allow(sk, type, &fl)) goto out; @@ -539,11 +541,10 @@ static void icmpv6_echo_reply(struct sk_buff *skb) fl.fl_icmp_type = ICMPV6_ECHO_REPLY; security_skb_classify_flow(skb, &fl); - sk = icmpv6_sk(net); - np = inet6_sk(sk); - - if (icmpv6_xmit_lock(sk)) + sk = icmpv6_xmit_lock(net); + if (sk == NULL) return; + np = inet6_sk(sk); if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) fl.oif = np->mcast_oif; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 52dddc25d3e6..29c7c99e69f7 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -378,6 +378,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) arg.skb = skb; arg.cb = cb; + arg.net = net; w->args = &arg; for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a027003d69a4..0e844c2736a7 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -269,7 +269,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, skb->mark = sk->sk_mark; mtu = dst_mtu(dst); - if ((skb->len <= mtu) || ipfragok || skb_is_gso(skb)) { + if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) { IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_OUTREQUESTS); return NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev, @@ -934,7 +934,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, goto out_err_release; if (ipv6_addr_any(&fl->fl6_src)) { - err = ipv6_dev_get_saddr(ip6_dst_idev(*dst)->dev, + err = ipv6_dev_get_saddr(net, ip6_dst_idev(*dst)->dev, &fl->fl6_dst, sk ? inet6_sk(sk)->srcprefs : 0, &fl->fl6_src); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index ea33b26512c2..4e5eac301f91 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -346,6 +346,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, */ if (optlen == 0) optval = NULL; + else if (optval == NULL) + goto e_inval; else if (optlen < sizeof(struct ipv6_opt_hdr) || optlen & 0x7 || optlen > 8 * 255) goto e_inval; @@ -909,7 +911,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, } else { if (np->rxopt.bits.rxinfo) { struct in6_pktinfo src_info; - src_info.ipi6_ifindex = np->mcast_oif; + src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : sk->sk_bound_dev_if; ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr); put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } @@ -919,7 +921,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, } if (np->rxopt.bits.rxoinfo) { struct in6_pktinfo src_info; - src_info.ipi6_ifindex = np->mcast_oif; + src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : sk->sk_bound_dev_if; ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr); put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index beb48e3f038a..f1c62ba0f56b 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -549,7 +549,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, override = 0; in6_ifa_put(ifp); } else { - if (ipv6_dev_get_saddr(dev, daddr, + if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr, inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs, &tmpaddr)) return; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 86540b24b27c..9af6115f0f50 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1249,7 +1249,7 @@ install_route: if (dst_metric(&rt->u.dst, RTAX_HOPLIMIT) == 0) rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1; - if (!dst_metric(&rt->u.dst, RTAX_MTU)) + if (!dst_mtu(&rt->u.dst)) rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(dev); if (!dst_metric(&rt->u.dst, RTAX_ADVMSS)) rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->u.dst)); @@ -2106,7 +2106,8 @@ static inline size_t rt6_nlmsg_size(void) + nla_total_size(sizeof(struct rta_cacheinfo)); } -static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, +static int rt6_fill_node(struct net *net, + struct sk_buff *skb, struct rt6_info *rt, struct in6_addr *dst, struct in6_addr *src, int iif, int type, u32 pid, u32 seq, int prefix, int nowait, unsigned int flags) @@ -2187,8 +2188,9 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, #endif NLA_PUT_U32(skb, RTA_IIF, iif); } else if (dst) { + struct inet6_dev *idev = ip6_dst_idev(&rt->u.dst); struct in6_addr saddr_buf; - if (ipv6_dev_get_saddr(ip6_dst_idev(&rt->u.dst)->dev, + if (ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, dst, 0, &saddr_buf) == 0) NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); } @@ -2233,7 +2235,8 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg) } else prefix = 0; - return rt6_fill_node(arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, + return rt6_fill_node(arg->net, + arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).pid, arg->cb->nlh->nlmsg_seq, prefix, 0, NLM_F_MULTI); } @@ -2299,7 +2302,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl); skb->dst = &rt->u.dst; - err = rt6_fill_node(skb, rt, &fl.fl6_dst, &fl.fl6_src, iif, + err = rt6_fill_node(net, skb, rt, &fl.fl6_dst, &fl.fl6_src, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, 0, 0, 0); if (err < 0) { @@ -2326,7 +2329,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) if (skb == NULL) goto errout; - err = rt6_fill_node(skb, rt, NULL, NULL, 0, + err = rt6_fill_node(net, skb, rt, NULL, NULL, 0, event, info->pid, seq, 0, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index a46badd1082d..ec394cf5a19b 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -199,10 +199,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq6 = inet6_rsk(req); treq = tcp_rsk(req); - if (security_inet_conn_request(sk, skb, req)) { - reqsk_free(req); - goto out; - } + if (security_inet_conn_request(sk, skb, req)) + goto out_free; req->mss = mss; ireq->rmt_port = th->source; @@ -255,14 +253,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_sk(sk)->sport; security_req_classify_flow(req, &fl); - if (ip6_dst_lookup(sk, &dst, &fl)) { - reqsk_free(req); - goto out; - } + if (ip6_dst_lookup(sk, &dst, &fl)) + goto out_free; + if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0) - goto out; + goto out_free; } req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); @@ -273,7 +270,10 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->rcv_wscale = rcv_wscale; ret = get_cookie_sock(sk, skb, req, dst); - -out: return ret; +out: + return ret; +out_free: + reqsk_free(req); + return NULL; } diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index e6dfaeac6be3..587f8f60c489 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -156,7 +156,7 @@ static struct ctl_table_header *ip6_base; int ipv6_static_sysctl_register(void) { static struct ctl_table empty[1]; - ip6_base = register_net_sysctl_rotable(net_ipv6_ctl_path, empty); + ip6_base = register_sysctl_paths(net_ipv6_ctl_path, empty); if (ip6_base == NULL) return -ENOMEM; return 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 78185a409212..5b90b369ccb2 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -69,7 +69,8 @@ #include <linux/scatterlist.h> static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb); -static void tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req); +static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, + struct request_sock *req); static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); @@ -1138,10 +1139,11 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) inet_twsk_put(tw); } -static void tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req) +static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, + struct request_sock *req) { tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent, - tcp_v6_md5_do_lookup(skb->sk, &ipv6_hdr(skb)->daddr)); + tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr)); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d1477b350f76..a6aecf76a71b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -379,7 +379,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, uh->source, saddr, dif))) { struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC); if (buff) { - bh_lock_sock_nested(sk2); + bh_lock_sock(sk2); if (!sock_owned_by_user(sk2)) udpv6_queue_rcv_skb(sk2, buff); else @@ -387,7 +387,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, bh_unlock_sock(sk2); } } - bh_lock_sock_nested(sk); + bh_lock_sock(sk); if (!sock_owned_by_user(sk)) udpv6_queue_rcv_skb(sk, skb); else @@ -508,7 +508,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], /* deliver */ - bh_lock_sock_nested(sk); + bh_lock_sock(sk); if (!sock_owned_by_user(sk)) udpv6_queue_rcv_skb(sk, skb); else diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index d6ce400f585f..bbd48b101bae 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -40,16 +40,39 @@ static void xfrm6_beet_make_header(struct sk_buff *skb) static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) { struct ipv6hdr *top_iph; - - skb_set_network_header(skb, -x->props.header_len); + struct ip_beet_phdr *ph; + struct iphdr *iphv4; + int optlen, hdr_len; + + iphv4 = ip_hdr(skb); + hdr_len = 0; + optlen = XFRM_MODE_SKB_CB(skb)->optlen; + if (unlikely(optlen)) + hdr_len += IPV4_BEET_PHMAXLEN - (optlen & 4); + + skb_set_network_header(skb, -x->props.header_len - hdr_len); + if (x->sel.family != AF_INET6) + skb->network_header += IPV4_BEET_PHMAXLEN; skb->mac_header = skb->network_header + offsetof(struct ipv6hdr, nexthdr); skb->transport_header = skb->network_header + sizeof(*top_iph); - __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl); + ph = (struct ip_beet_phdr *)__skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl-hdr_len); xfrm6_beet_make_header(skb); top_iph = ipv6_hdr(skb); + if (unlikely(optlen)) { + + BUG_ON(optlen < 0); + + ph->padlen = 4 - (optlen & 4); + ph->hdrlen = optlen / 8; + ph->nexthdr = top_iph->nexthdr; + if (ph->padlen) + memset(ph + 1, IPOPT_NOP, ph->padlen); + + top_iph->nexthdr = IPPROTO_BEETPH; + } ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr); ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 8f1e0543b3c4..08e4cbbe3f04 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -52,12 +52,14 @@ static struct dst_entry *xfrm6_dst_lookup(int tos, xfrm_address_t *saddr, static int xfrm6_get_saddr(xfrm_address_t *saddr, xfrm_address_t *daddr) { struct dst_entry *dst; + struct net_device *dev; dst = xfrm6_dst_lookup(0, NULL, daddr); if (IS_ERR(dst)) return -EHOSTUNREACH; - ipv6_dev_get_saddr(ip6_dst_idev(dst)->dev, + dev = ip6_dst_idev(dst)->dev; + ipv6_dev_get_saddr(dev_net(dev), dev, (struct in6_addr *)&daddr->a6, 0, (struct in6_addr *)&saddr->a6); dst_release(dst); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index a4f9a832722a..ec59345af65b 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -82,6 +82,7 @@ struct ieee80211_sta_bss { u8 bssid[ETH_ALEN]; u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 dtim_period; u16 capability; /* host byte order */ enum ieee80211_band band; int freq; @@ -586,6 +587,7 @@ struct ieee80211_local { struct timer_list sta_cleanup; unsigned long queues_pending[BITS_TO_LONGS(IEEE80211_MAX_QUEUES)]; + unsigned long queues_pending_run[BITS_TO_LONGS(IEEE80211_MAX_QUEUES)]; struct ieee80211_tx_stored_packet pending_packet[IEEE80211_MAX_QUEUES]; struct tasklet_struct tx_pending_tasklet; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index a4c5b90de769..aa5a191598c9 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -245,10 +245,13 @@ static int ieee80211_open(struct net_device *dev) case IEEE80211_IF_TYPE_AP: sdata->bss = &sdata->u.ap; break; + case IEEE80211_IF_TYPE_MESH_POINT: + /* mesh ifaces must set allmulti to forward mcast traffic */ + atomic_inc(&local->iff_allmultis); + break; case IEEE80211_IF_TYPE_STA: case IEEE80211_IF_TYPE_MNTR: case IEEE80211_IF_TYPE_IBSS: - case IEEE80211_IF_TYPE_MESH_POINT: /* no special treatment */ break; case IEEE80211_IF_TYPE_INVALID: @@ -495,6 +498,9 @@ static int ieee80211_stop(struct net_device *dev) netif_addr_unlock_bh(local->mdev); break; case IEEE80211_IF_TYPE_MESH_POINT: + /* allmulti is always set on mesh ifaces */ + atomic_dec(&local->iff_allmultis); + /* fall through */ case IEEE80211_IF_TYPE_STA: case IEEE80211_IF_TYPE_IBSS: sdata->u.sta.state = IEEE80211_DISABLED; @@ -1689,6 +1695,11 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (local->hw.conf.beacon_int < 10) local->hw.conf.beacon_int = 100; + if (local->hw.max_listen_interval == 0) + local->hw.max_listen_interval = 1; + + local->hw.conf.listen_interval = local->hw.max_listen_interval; + local->wstats_flags |= local->hw.flags & (IEEE80211_HW_SIGNAL_UNSPEC | IEEE80211_HW_SIGNAL_DB | IEEE80211_HW_SIGNAL_DBM) ? diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 669eafafe497..7495fbb0d211 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -214,8 +214,7 @@ void ieee80211s_stop(void); void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata); /* Mesh paths */ -int mesh_nexthop_lookup(u8 *next_hop, struct sk_buff *skb, - struct net_device *dev); +int mesh_nexthop_lookup(struct sk_buff *skb, struct net_device *dev); void mesh_path_start_discovery(struct net_device *dev); struct mesh_path *mesh_path_lookup(u8 *dst, struct net_device *dev); struct mesh_path *mesh_path_lookup_by_idx(int idx, struct net_device *dev); @@ -286,6 +285,4 @@ static inline void mesh_path_activate(struct mesh_path *mpath) #define mesh_allocated 0 #endif -#define MESH_PREQ(skb) (skb->cb + 30) - #endif /* IEEE80211S_H */ diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 7fa149e230e6..08aca446ca01 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -758,29 +758,30 @@ enddiscovery: /** * ieee80211s_lookup_nexthop - put the appropriate next hop on a mesh frame * - * @next_hop: output argument for next hop address - * @skb: frame to be sent + * @skb: 802.11 frame to be sent * @dev: network device the frame will be sent through + * @fwd_frame: true if this frame was originally from a different host * * Returns: 0 if the next hop was found. Nonzero otherwise. If no next hop is * found, the function will start a path discovery and queue the frame so it is * sent when the path is resolved. This means the caller must not free the skb * in this case. */ -int mesh_nexthop_lookup(u8 *next_hop, struct sk_buff *skb, - struct net_device *dev) +int mesh_nexthop_lookup(struct sk_buff *skb, struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct sk_buff *skb_to_free = NULL; struct mesh_path *mpath; + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + u8 *dst_addr = hdr->addr3; int err = 0; rcu_read_lock(); - mpath = mesh_path_lookup(skb->data, dev); + mpath = mesh_path_lookup(dst_addr, dev); if (!mpath) { - mesh_path_add(skb->data, dev); - mpath = mesh_path_lookup(skb->data, dev); + mesh_path_add(dst_addr, dev); + mpath = mesh_path_lookup(dst_addr, dev); if (!mpath) { dev_kfree_skb(skb); sdata->u.sta.mshstats.dropped_frames_no_route++; @@ -792,13 +793,13 @@ int mesh_nexthop_lookup(u8 *next_hop, struct sk_buff *skb, if (mpath->flags & MESH_PATH_ACTIVE) { if (time_after(jiffies, mpath->exp_time - msecs_to_jiffies(sdata->u.sta.mshcfg.path_refresh_time)) - && skb->pkt_type != PACKET_OTHERHOST + && !memcmp(dev->dev_addr, hdr->addr4, ETH_ALEN) && !(mpath->flags & MESH_PATH_RESOLVING) && !(mpath->flags & MESH_PATH_FIXED)) { mesh_queue_preq(mpath, PREQ_Q_F_START | PREQ_Q_F_REFRESH); } - memcpy(next_hop, mpath->next_hop->addr, + memcpy(hdr->addr1, mpath->next_hop->addr, ETH_ALEN); } else { if (!(mpath->flags & MESH_PATH_RESOLVING)) { diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 5f88a2e6ee50..838ee60492ad 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -388,18 +388,15 @@ void mesh_path_tx_pending(struct mesh_path *mpath) void mesh_path_discard_frame(struct sk_buff *skb, struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct mesh_path *mpath; u32 dsn = 0; - if (skb->pkt_type == PACKET_OTHERHOST) { - struct ieee80211s_hdr *prev_meshhdr; - int mshhdrlen; + if (memcmp(hdr->addr4, dev->dev_addr, ETH_ALEN) != 0) { u8 *ra, *da; - prev_meshhdr = ((struct ieee80211s_hdr *)skb->cb); - mshhdrlen = ieee80211_get_mesh_hdrlen(prev_meshhdr); - da = skb->data; - ra = MESH_PREQ(skb); + da = hdr->addr3; + ra = hdr->addr2; mpath = mesh_path_lookup(da, dev); if (mpath) dsn = ++mpath->dsn; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index acb04133a95d..1e97fb9fb34b 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -551,6 +551,7 @@ static void ieee80211_set_associated(struct net_device *dev, /* set timing information */ sdata->bss_conf.beacon_int = bss->beacon_int; sdata->bss_conf.timestamp = bss->timestamp; + sdata->bss_conf.dtim_period = bss->dtim_period; changed |= ieee80211_handle_bss_capability(sdata, bss); @@ -773,7 +774,8 @@ static void ieee80211_send_assoc(struct net_device *dev, mgmt->frame_control = IEEE80211_FC(IEEE80211_FTYPE_MGMT, IEEE80211_STYPE_REASSOC_REQ); mgmt->u.reassoc_req.capab_info = cpu_to_le16(capab); - mgmt->u.reassoc_req.listen_interval = cpu_to_le16(1); + mgmt->u.reassoc_req.listen_interval = + cpu_to_le16(local->hw.conf.listen_interval); memcpy(mgmt->u.reassoc_req.current_ap, ifsta->prev_bssid, ETH_ALEN); } else { @@ -781,7 +783,8 @@ static void ieee80211_send_assoc(struct net_device *dev, mgmt->frame_control = IEEE80211_FC(IEEE80211_FTYPE_MGMT, IEEE80211_STYPE_ASSOC_REQ); mgmt->u.assoc_req.capab_info = cpu_to_le16(capab); - mgmt->u.assoc_req.listen_interval = cpu_to_le16(1); + mgmt->u.reassoc_req.listen_interval = + cpu_to_le16(local->hw.conf.listen_interval); } /* SSID */ @@ -2100,6 +2103,8 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); return; } + /* update new sta with its last rx activity */ + sta->last_rx = jiffies; } /* @@ -2688,6 +2693,16 @@ static void ieee80211_rx_bss_info(struct net_device *dev, bss->beacon_int = le16_to_cpu(mgmt->u.beacon.beacon_int); bss->capability = le16_to_cpu(mgmt->u.beacon.capab_info); + if (elems->tim) { + struct ieee80211_tim_ie *tim_ie = + (struct ieee80211_tim_ie *)elems->tim; + bss->dtim_period = tim_ie->dtim_period; + } + + /* set default value for buggy APs */ + if (!elems->tim || bss->dtim_period == 0) + bss->dtim_period = 1; + bss->supp_rates_len = 0; if (elems->supp_rates) { clen = IEEE80211_MAX_SUPP_RATES - bss->supp_rates_len; @@ -3650,11 +3665,21 @@ static int ieee80211_sta_find_ibss(struct net_device *dev, "%s\n", print_mac(mac, bssid), print_mac(mac2, ifsta->bssid)); #endif /* CONFIG_MAC80211_IBSS_DEBUG */ - if (found && memcmp(ifsta->bssid, bssid, ETH_ALEN) != 0 && - (bss = ieee80211_rx_bss_get(dev, bssid, - local->hw.conf.channel->center_freq, - ifsta->ssid, ifsta->ssid_len))) { + + if (found && memcmp(ifsta->bssid, bssid, ETH_ALEN) != 0) { int ret; + int search_freq; + + if (ifsta->flags & IEEE80211_STA_AUTO_CHANNEL_SEL) + search_freq = bss->freq; + else + search_freq = local->hw.conf.channel->center_freq; + + bss = ieee80211_rx_bss_get(dev, bssid, search_freq, + ifsta->ssid, ifsta->ssid_len); + if (!bss) + goto dont_join; + printk(KERN_DEBUG "%s: Selected IBSS BSSID %s" " based on configured SSID\n", dev->name, print_mac(mac, bssid)); @@ -3662,6 +3687,8 @@ static int ieee80211_sta_find_ibss(struct net_device *dev, ieee80211_rx_bss_put(local, bss); return ret; } + +dont_join: #ifdef CONFIG_MAC80211_IBSS_DEBUG printk(KERN_DEBUG " did not try to join ibss\n"); #endif /* CONFIG_MAC80211_IBSS_DEBUG */ @@ -3895,7 +3922,7 @@ done: if (sdata->vif.type == IEEE80211_IF_TYPE_IBSS) { struct ieee80211_if_sta *ifsta = &sdata->u.sta; if (!(ifsta->flags & IEEE80211_STA_BSSID_SET) || - (!ifsta->state == IEEE80211_IBSS_JOINED && + (!(ifsta->state == IEEE80211_IBSS_JOINED) && !ieee80211_sta_active_ibss(dev))) ieee80211_sta_find_ibss(dev, ifsta); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 6d9ae67c27ca..6db854505193 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1109,20 +1109,9 @@ ieee80211_data_to_8023(struct ieee80211_rx_data *rx) hdrlen = ieee80211_get_hdrlen(fc); - if (ieee80211_vif_is_mesh(&sdata->vif)) { - int meshhdrlen = ieee80211_get_mesh_hdrlen( + if (ieee80211_vif_is_mesh(&sdata->vif)) + hdrlen += ieee80211_get_mesh_hdrlen( (struct ieee80211s_hdr *) (skb->data + hdrlen)); - /* Copy on cb: - * - mesh header: to be used for mesh forwarding - * decision. It will also be used as mesh header template at - * tx.c:ieee80211_subif_start_xmit() if interface - * type is mesh and skb->pkt_type == PACKET_OTHERHOST - * - ta: to be used if a RERR needs to be sent. - */ - memcpy(skb->cb, skb->data + hdrlen, meshhdrlen); - memcpy(MESH_PREQ(skb), hdr->addr2, ETH_ALEN); - hdrlen += meshhdrlen; - } /* convert IEEE 802.11 header + possible LLC headers into Ethernet * header @@ -1269,38 +1258,6 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) } } - /* Mesh forwarding */ - if (ieee80211_vif_is_mesh(&sdata->vif)) { - u8 *mesh_ttl = &((struct ieee80211s_hdr *)skb->cb)->ttl; - (*mesh_ttl)--; - - if (is_multicast_ether_addr(skb->data)) { - if (*mesh_ttl > 0) { - xmit_skb = skb_copy(skb, GFP_ATOMIC); - if (xmit_skb) - xmit_skb->pkt_type = PACKET_OTHERHOST; - else if (net_ratelimit()) - printk(KERN_DEBUG "%s: failed to clone " - "multicast frame\n", dev->name); - } else - IEEE80211_IFSTA_MESH_CTR_INC(&sdata->u.sta, - dropped_frames_ttl); - } else if (skb->pkt_type != PACKET_OTHERHOST && - compare_ether_addr(dev->dev_addr, skb->data) != 0) { - if (*mesh_ttl == 0) { - IEEE80211_IFSTA_MESH_CTR_INC(&sdata->u.sta, - dropped_frames_ttl); - dev_kfree_skb(skb); - skb = NULL; - } else { - xmit_skb = skb; - xmit_skb->pkt_type = PACKET_OTHERHOST; - if (!(dev->flags & IFF_PROMISC)) - skb = NULL; - } - } - } - if (skb) { /* deliver to local stack */ skb->protocol = eth_type_trans(skb, dev); @@ -1431,6 +1388,63 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) } static ieee80211_rx_result debug_noinline +ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) +{ + struct ieee80211_hdr *hdr; + struct ieee80211s_hdr *mesh_hdr; + unsigned int hdrlen; + struct sk_buff *skb = rx->skb, *fwd_skb; + + hdr = (struct ieee80211_hdr *) skb->data; + hdrlen = ieee80211_hdrlen(hdr->frame_control); + mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); + + if (!ieee80211_is_data(hdr->frame_control)) + return RX_CONTINUE; + + if (!mesh_hdr->ttl) + /* illegal frame */ + return RX_DROP_MONITOR; + + if (compare_ether_addr(rx->dev->dev_addr, hdr->addr3) == 0) + return RX_CONTINUE; + + mesh_hdr->ttl--; + + if (rx->flags & IEEE80211_RX_RA_MATCH) { + if (!mesh_hdr->ttl) + IEEE80211_IFSTA_MESH_CTR_INC(&rx->sdata->u.sta, + dropped_frames_ttl); + else { + struct ieee80211_hdr *fwd_hdr; + fwd_skb = skb_copy(skb, GFP_ATOMIC); + + if (!fwd_skb && net_ratelimit()) + printk(KERN_DEBUG "%s: failed to clone mesh frame\n", + rx->dev->name); + + fwd_hdr = (struct ieee80211_hdr *) fwd_skb->data; + /* + * Save TA to addr1 to send TA a path error if a + * suitable next hop is not found + */ + memcpy(fwd_hdr->addr1, fwd_hdr->addr2, ETH_ALEN); + memcpy(fwd_hdr->addr2, rx->dev->dev_addr, ETH_ALEN); + fwd_skb->dev = rx->local->mdev; + fwd_skb->iif = rx->dev->ifindex; + dev_queue_xmit(fwd_skb); + } + } + + if (is_multicast_ether_addr(hdr->addr3) || + rx->dev->flags & IFF_PROMISC) + return RX_CONTINUE; + else + return RX_DROP_MONITOR; +} + + +static ieee80211_rx_result debug_noinline ieee80211_rx_h_data(struct ieee80211_rx_data *rx) { struct net_device *dev = rx->dev; @@ -1663,10 +1677,12 @@ static void ieee80211_invoke_rx_handlers(struct ieee80211_sub_if_data *sdata, rx->sdata = sdata; rx->dev = sdata->dev; -#define CALL_RXH(rxh) \ - res = rxh(rx); \ - if (res != RX_CONTINUE) \ - goto rxh_done; +#define CALL_RXH(rxh) \ + do { \ + res = rxh(rx); \ + if (res != RX_CONTINUE) \ + goto rxh_done; \ + } while (0); CALL_RXH(ieee80211_rx_h_passive_scan) CALL_RXH(ieee80211_rx_h_check) @@ -1678,6 +1694,8 @@ static void ieee80211_invoke_rx_handlers(struct ieee80211_sub_if_data *sdata, /* must be after MMIC verify so header is counted in MPDU mic */ CALL_RXH(ieee80211_rx_h_remove_qos_control) CALL_RXH(ieee80211_rx_h_amsdu) + if (ieee80211_vif_is_mesh(&sdata->vif)) + CALL_RXH(ieee80211_rx_h_mesh_fwding); CALL_RXH(ieee80211_rx_h_data) CALL_RXH(ieee80211_rx_h_ctrl) CALL_RXH(ieee80211_rx_h_mgmt) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 69019e943873..4788f7b91f49 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1060,13 +1060,14 @@ static int ieee80211_tx_prepare(struct ieee80211_tx_data *tx, static int __ieee80211_tx(struct ieee80211_local *local, struct sk_buff *skb, struct ieee80211_tx_data *tx) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_tx_info *info; int ret, i; - if (netif_subqueue_stopped(local->mdev, skb)) - return IEEE80211_TX_AGAIN; - if (skb) { + if (netif_subqueue_stopped(local->mdev, skb)) + return IEEE80211_TX_AGAIN; + info = IEEE80211_SKB_CB(skb); + ieee80211_dump_frame(wiphy_name(local->hw.wiphy), "TX to low-level driver", skb); ret = local->ops->tx(local_to_hw(local), skb); @@ -1215,6 +1216,7 @@ retry: if (ret == IEEE80211_TX_FRAG_AGAIN) skb = NULL; + set_bit(queue, local->queues_pending); smp_mb(); /* @@ -1299,6 +1301,7 @@ int ieee80211_master_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct net_device *odev = NULL; struct ieee80211_sub_if_data *osdata; int headroom; @@ -1326,6 +1329,20 @@ int ieee80211_master_start_xmit(struct sk_buff *skb, osdata = IEEE80211_DEV_TO_SUB_IF(odev); + if (ieee80211_vif_is_mesh(&osdata->vif) && + ieee80211_is_data(hdr->frame_control)) { + if (ieee80211_is_data(hdr->frame_control)) { + if (is_multicast_ether_addr(hdr->addr3)) + memcpy(hdr->addr1, hdr->addr3, ETH_ALEN); + else + if (mesh_nexthop_lookup(skb, odev)) + return 0; + if (memcmp(odev->dev_addr, hdr->addr4, ETH_ALEN) != 0) + IEEE80211_IFSTA_MESH_CTR_INC(&osdata->u.sta, + fwded_frames); + } + } + may_encrypt = !skb->do_not_encrypt; headroom = osdata->local->tx_headroom; @@ -1470,30 +1487,17 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, case IEEE80211_IF_TYPE_MESH_POINT: fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS); /* RA TA DA SA */ - if (is_multicast_ether_addr(skb->data)) - memcpy(hdr.addr1, skb->data, ETH_ALEN); - else if (mesh_nexthop_lookup(hdr.addr1, skb, dev)) - return 0; + memset(hdr.addr1, 0, ETH_ALEN); memcpy(hdr.addr2, dev->dev_addr, ETH_ALEN); memcpy(hdr.addr3, skb->data, ETH_ALEN); memcpy(hdr.addr4, skb->data + ETH_ALEN, ETH_ALEN); - if (skb->pkt_type == PACKET_OTHERHOST) { - /* Forwarded frame, keep mesh ttl and seqnum */ - struct ieee80211s_hdr *prev_meshhdr; - prev_meshhdr = ((struct ieee80211s_hdr *)skb->cb); - meshhdrlen = ieee80211_get_mesh_hdrlen(prev_meshhdr); - memcpy(&mesh_hdr, prev_meshhdr, meshhdrlen); - sdata->u.sta.mshstats.fwded_frames++; - } else { - if (!sdata->u.sta.mshcfg.dot11MeshTTL) { - /* Do not send frames with mesh_ttl == 0 */ - sdata->u.sta.mshstats.dropped_frames_ttl++; - ret = 0; - goto fail; - } - meshhdrlen = ieee80211_new_mesh_header(&mesh_hdr, - sdata); + if (!sdata->u.sta.mshcfg.dot11MeshTTL) { + /* Do not send frames with mesh_ttl == 0 */ + sdata->u.sta.mshstats.dropped_frames_ttl++; + ret = 0; + goto fail; } + meshhdrlen = ieee80211_new_mesh_header(&mesh_hdr, sdata); hdrlen = 30; break; #endif @@ -1541,7 +1545,8 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, * Drop unicast frames to unauthorised stations unless they are * EAPOL frames from the local station. */ - if (unlikely(!is_multicast_ether_addr(hdr.addr1) && + if (!ieee80211_vif_is_mesh(&sdata->vif) && + unlikely(!is_multicast_ether_addr(hdr.addr1) && !(sta_flags & WLAN_STA_AUTHORIZED) && !(ethertype == ETH_P_PAE && compare_ether_addr(dev->dev_addr, @@ -1708,14 +1713,19 @@ void ieee80211_tx_pending(unsigned long data) netif_tx_lock_bh(dev); for (i = 0; i < ieee80211_num_regular_queues(&local->hw); i++) { /* Check that this queue is ok */ - if (__netif_subqueue_stopped(local->mdev, i)) + if (__netif_subqueue_stopped(local->mdev, i) && + !test_bit(i, local->queues_pending_run)) continue; if (!test_bit(i, local->queues_pending)) { + clear_bit(i, local->queues_pending_run); ieee80211_wake_queue(&local->hw, i); continue; } + clear_bit(i, local->queues_pending_run); + netif_start_subqueue(local->mdev, i); + store = &local->pending_packet[i]; tx.extra_frag = store->extra_frag; tx.num_extra_frag = store->num_extra_frag; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 19f85e1b3695..0d463c80c404 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -361,6 +361,7 @@ void ieee80211_wake_queue(struct ieee80211_hw *hw, int queue) struct ieee80211_local *local = hw_to_local(hw); if (test_bit(queue, local->queues_pending)) { + set_bit(queue, local->queues_pending_run); tasklet_schedule(&local->tx_pending_tasklet); } else { netif_wake_subqueue(local->mdev, queue); diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 28437f0001db..4310e2f65661 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -241,12 +241,14 @@ void ieee80211_ht_agg_queue_remove(struct ieee80211_local *local, } else { struct netdev_queue *txq; spinlock_t *root_lock; + struct Qdisc *q; txq = netdev_get_tx_queue(local->mdev, agg_queue); - root_lock = qdisc_root_lock(txq->qdisc); + q = rcu_dereference(txq->qdisc); + root_lock = qdisc_lock(q); spin_lock_bh(root_lock); - qdisc_reset(txq->qdisc); + qdisc_reset(q); spin_unlock_bh(root_lock); } } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c519d090bdb9..9d1830da8e84 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1032,10 +1032,10 @@ void nf_conntrack_cleanup(void) nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_vmalloc, nf_conntrack_htable_size); - nf_conntrack_proto_fini(); - nf_conntrack_helper_fini(); - nf_conntrack_expect_fini(); nf_conntrack_acct_fini(); + nf_conntrack_expect_fini(); + nf_conntrack_helper_fini(); + nf_conntrack_proto_fini(); } struct hlist_head *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 105a616c5c78..a8752031adcb 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -968,7 +968,7 @@ ctnetlink_change_helper(struct nf_conn *ct, struct nlattr *cda[]) /* need to zero data of old helper */ memset(&help->help, 0, sizeof(help->help)); } else { - help = nf_ct_helper_ext_add(ct, GFP_KERNEL); + help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help == NULL) return -ENOMEM; } @@ -1136,16 +1136,33 @@ ctnetlink_create_conntrack(struct nlattr *cda[], ct->timeout.expires = jiffies + ct->timeout.expires * HZ; ct->status |= IPS_CONFIRMED; + rcu_read_lock(); + helper = __nf_ct_helper_find(rtuple); + if (helper) { + help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); + if (help == NULL) { + rcu_read_unlock(); + err = -ENOMEM; + goto err; + } + /* not in hash table yet so not strictly necessary */ + rcu_assign_pointer(help->helper, helper); + } + if (cda[CTA_STATUS]) { err = ctnetlink_change_status(ct, cda); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto err; + } } if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto err; + } } nf_ct_acct_ext_add(ct, GFP_KERNEL); @@ -1155,19 +1172,6 @@ ctnetlink_create_conntrack(struct nlattr *cda[], ct->mark = ntohl(nla_get_be32(cda[CTA_MARK])); #endif - rcu_read_lock(); - helper = __nf_ct_helper_find(rtuple); - if (helper) { - help = nf_ct_helper_ext_add(ct, GFP_KERNEL); - if (help == NULL) { - rcu_read_unlock(); - err = -ENOMEM; - goto err; - } - /* not in hash table yet so not strictly necessary */ - rcu_assign_pointer(help->helper, helper); - } - /* setup master conntrack: this is a confirmed expectation */ if (master_ct) { __set_bit(IPS_EXPECTED_BIT, &ct->status); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 869ef9349d0f..8509db14670b 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -324,6 +324,7 @@ static int log_invalid_proto_min = 0; static int log_invalid_proto_max = 255; static struct ctl_table_header *nf_ct_sysctl_header; +static struct ctl_table_header *nf_ct_netfilter_header; static ctl_table nf_ct_sysctl_table[] = { { @@ -384,12 +385,6 @@ static ctl_table nf_ct_sysctl_table[] = { static ctl_table nf_ct_netfilter_table[] = { { - .ctl_name = NET_NETFILTER, - .procname = "netfilter", - .mode = 0555, - .child = nf_ct_sysctl_table, - }, - { .ctl_name = NET_NF_CONNTRACK_MAX, .procname = "nf_conntrack_max", .data = &nf_conntrack_max, @@ -409,18 +404,29 @@ EXPORT_SYMBOL_GPL(nf_ct_log_invalid); static int nf_conntrack_standalone_init_sysctl(void) { - nf_ct_sysctl_header = + nf_ct_netfilter_header = register_sysctl_paths(nf_ct_path, nf_ct_netfilter_table); - if (nf_ct_sysctl_header == NULL) { - printk("nf_conntrack: can't register to sysctl.\n"); - return -ENOMEM; - } + if (!nf_ct_netfilter_header) + goto out; + + nf_ct_sysctl_header = + register_sysctl_paths(nf_net_netfilter_sysctl_path, + nf_ct_sysctl_table); + if (!nf_ct_sysctl_header) + goto out_unregister_netfilter; + return 0; +out_unregister_netfilter: + unregister_sysctl_table(nf_ct_netfilter_header); +out: + printk("nf_conntrack: can't register to sysctl.\n"); + return -ENOMEM; } static void nf_conntrack_standalone_fini_sysctl(void) { + unregister_sysctl_table(nf_ct_netfilter_header); unregister_sysctl_table(nf_ct_sysctl_header); } #else diff --git a/net/rfkill/rfkill-input.c b/net/rfkill/rfkill-input.c index 8aa822730145..e5b69556bb5b 100644 --- a/net/rfkill/rfkill-input.c +++ b/net/rfkill/rfkill-input.c @@ -109,6 +109,25 @@ static DEFINE_RFKILL_TASK(rfkill_uwb, RFKILL_TYPE_UWB); static DEFINE_RFKILL_TASK(rfkill_wimax, RFKILL_TYPE_WIMAX); static DEFINE_RFKILL_TASK(rfkill_wwan, RFKILL_TYPE_WWAN); +static void rfkill_schedule_evsw_rfkillall(int state) +{ + /* EVERY radio type. state != 0 means radios ON */ + /* handle EPO (emergency power off) through shortcut */ + if (state) { + rfkill_schedule_set(&rfkill_wwan, + RFKILL_STATE_UNBLOCKED); + rfkill_schedule_set(&rfkill_wimax, + RFKILL_STATE_UNBLOCKED); + rfkill_schedule_set(&rfkill_uwb, + RFKILL_STATE_UNBLOCKED); + rfkill_schedule_set(&rfkill_bt, + RFKILL_STATE_UNBLOCKED); + rfkill_schedule_set(&rfkill_wlan, + RFKILL_STATE_UNBLOCKED); + } else + rfkill_schedule_epo(); +} + static void rfkill_event(struct input_handle *handle, unsigned int type, unsigned int code, int data) { @@ -132,21 +151,7 @@ static void rfkill_event(struct input_handle *handle, unsigned int type, } else if (type == EV_SW) { switch (code) { case SW_RFKILL_ALL: - /* EVERY radio type. data != 0 means radios ON */ - /* handle EPO (emergency power off) through shortcut */ - if (data) { - rfkill_schedule_set(&rfkill_wwan, - RFKILL_STATE_UNBLOCKED); - rfkill_schedule_set(&rfkill_wimax, - RFKILL_STATE_UNBLOCKED); - rfkill_schedule_set(&rfkill_uwb, - RFKILL_STATE_UNBLOCKED); - rfkill_schedule_set(&rfkill_bt, - RFKILL_STATE_UNBLOCKED); - rfkill_schedule_set(&rfkill_wlan, - RFKILL_STATE_UNBLOCKED); - } else - rfkill_schedule_epo(); + rfkill_schedule_evsw_rfkillall(data); break; default: break; @@ -168,6 +173,7 @@ static int rfkill_connect(struct input_handler *handler, struct input_dev *dev, handle->handler = handler; handle->name = "rfkill"; + /* causes rfkill_start() to be called */ error = input_register_handle(handle); if (error) goto err_free_handle; @@ -185,6 +191,23 @@ static int rfkill_connect(struct input_handler *handler, struct input_dev *dev, return error; } +static void rfkill_start(struct input_handle *handle) +{ + /* Take event_lock to guard against configuration changes, we + * should be able to deal with concurrency with rfkill_event() + * just fine (which event_lock will also avoid). */ + spin_lock_irq(&handle->dev->event_lock); + + if (test_bit(EV_SW, handle->dev->evbit)) { + if (test_bit(SW_RFKILL_ALL, handle->dev->swbit)) + rfkill_schedule_evsw_rfkillall(test_bit(SW_RFKILL_ALL, + handle->dev->sw)); + /* add resync for further EV_SW events here */ + } + + spin_unlock_irq(&handle->dev->event_lock); +} + static void rfkill_disconnect(struct input_handle *handle) { input_close_device(handle); @@ -225,6 +248,7 @@ static struct input_handler rfkill_handler = { .event = rfkill_event, .connect = rfkill_connect, .disconnect = rfkill_disconnect, + .start = rfkill_start, .name = "rfkill", .id_table = rfkill_ids, }; diff --git a/net/rfkill/rfkill.c b/net/rfkill/rfkill.c index c6f2f388cb72..35a9994e2339 100644 --- a/net/rfkill/rfkill.c +++ b/net/rfkill/rfkill.c @@ -105,6 +105,16 @@ static void rfkill_led_trigger(struct rfkill *rfkill, #endif /* CONFIG_RFKILL_LEDS */ } +#ifdef CONFIG_RFKILL_LEDS +static void rfkill_led_trigger_activate(struct led_classdev *led) +{ + struct rfkill *rfkill = container_of(led->trigger, + struct rfkill, led_trigger); + + rfkill_led_trigger(rfkill, rfkill->state); +} +#endif /* CONFIG_RFKILL_LEDS */ + static void notify_rfkill_state_change(struct rfkill *rfkill) { blocking_notifier_call_chain(&rfkill_notifier_list, @@ -140,6 +150,8 @@ static void update_rfkill_state(struct rfkill *rfkill) * calls and handling all the red tape such as issuing notifications * if the call is successful. * + * Suspended devices are not touched at all, and -EAGAIN is returned. + * * Note that the @force parameter cannot override a (possibly cached) * state of RFKILL_STATE_HARD_BLOCKED. Any device making use of * RFKILL_STATE_HARD_BLOCKED implements either get_state() or @@ -158,6 +170,9 @@ static int rfkill_toggle_radio(struct rfkill *rfkill, int retval = 0; enum rfkill_state oldstate, newstate; + if (unlikely(rfkill->dev.power.power_state.event & PM_EVENT_SLEEP)) + return -EBUSY; + oldstate = rfkill->state; if (rfkill->get_state && !force && @@ -204,7 +219,7 @@ static int rfkill_toggle_radio(struct rfkill *rfkill, * * This function toggles the state of all switches of given type, * unless a specific switch is claimed by userspace (in which case, - * that switch is left alone). + * that switch is left alone) or suspended. */ void rfkill_switch_all(enum rfkill_type type, enum rfkill_state state) { @@ -229,8 +244,8 @@ EXPORT_SYMBOL(rfkill_switch_all); /** * rfkill_epo - emergency power off all transmitters * - * This kicks all rfkill devices to RFKILL_STATE_SOFT_BLOCKED, ignoring - * everything in its path but rfkill_mutex and rfkill->mutex. + * This kicks all non-suspended rfkill devices to RFKILL_STATE_SOFT_BLOCKED, + * ignoring everything in its path but rfkill_mutex and rfkill->mutex. */ void rfkill_epo(void) { @@ -448,13 +463,14 @@ static int rfkill_resume(struct device *dev) if (dev->power.power_state.event != PM_EVENT_ON) { mutex_lock(&rfkill->mutex); + dev->power.power_state.event = PM_EVENT_ON; + /* restore radio state AND notify everybody */ rfkill_toggle_radio(rfkill, rfkill->state, 1); mutex_unlock(&rfkill->mutex); } - dev->power.power_state = PMSG_ON; return 0; } #else @@ -589,7 +605,10 @@ static void rfkill_led_trigger_register(struct rfkill *rfkill) #ifdef CONFIG_RFKILL_LEDS int error; - rfkill->led_trigger.name = rfkill->dev.bus_id; + if (!rfkill->led_trigger.name) + rfkill->led_trigger.name = rfkill->dev.bus_id; + if (!rfkill->led_trigger.activate) + rfkill->led_trigger.activate = rfkill_led_trigger_activate; error = led_trigger_register(&rfkill->led_trigger); if (error) rfkill->led_trigger.name = NULL; diff --git a/net/rxrpc/ar-accept.c b/net/rxrpc/ar-accept.c index bdfb77417794..77228f28fa36 100644 --- a/net/rxrpc/ar-accept.c +++ b/net/rxrpc/ar-accept.c @@ -100,7 +100,7 @@ static int rxrpc_accept_incoming_call(struct rxrpc_local *local, trans = rxrpc_get_transport(local, peer, GFP_NOIO); rxrpc_put_peer(peer); - if (!trans) { + if (IS_ERR(trans)) { _debug("no trans"); ret = -EBUSY; goto error; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index d308c19aa3f9..9974b3f04f05 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -205,10 +205,9 @@ struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind, { struct tcf_common *p = NULL; if (index && (p = tcf_hash_lookup(index, hinfo)) != NULL) { - if (bind) { + if (bind) p->tcfc_bindcnt++; - p->tcfc_refcnt++; - } + p->tcfc_refcnt++; a->priv = p; } return p; @@ -752,7 +751,7 @@ static int tca_action_flush(struct nlattr *nla, struct nlmsghdr *n, u32 pid) struct nlattr *tb[TCA_ACT_MAX+1]; struct nlattr *kind; struct tc_action *a = create_a(0); - int err = -EINVAL; + int err = -ENOMEM; if (a == NULL) { printk("tca_action_flush: couldnt create tc_action\n"); @@ -763,7 +762,7 @@ static int tca_action_flush(struct nlattr *nla, struct nlmsghdr *n, u32 pid) if (!skb) { printk("tca_action_flush: failed skb alloc\n"); kfree(a); - return -ENOBUFS; + return err; } b = skb_tail_pointer(skb); @@ -791,6 +790,8 @@ static int tca_action_flush(struct nlattr *nla, struct nlmsghdr *n, u32 pid) err = a->ops->walk(skb, &dcb, RTM_DELACTION, a); if (err < 0) goto nla_put_failure; + if (err == 0) + goto noflush_out; nla_nest_end(skb, nest); @@ -808,6 +809,7 @@ nla_put_failure: nlmsg_failure: module_put(a->ops->owner); err_out: +noflush_out: kfree_skb(skb); kfree(a); return err; @@ -825,8 +827,10 @@ tca_action_gd(struct nlattr *nla, struct nlmsghdr *n, u32 pid, int event) return ret; if (event == RTM_DELACTION && n->nlmsg_flags&NLM_F_ROOT) { - if (tb[0] != NULL && tb[1] == NULL) - return tca_action_flush(tb[0], n, pid); + if (tb[1] != NULL) + return tca_action_flush(tb[1], n, pid); + else + return -EINVAL; } for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d2b6f54a6261..5cafdd4c8018 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -280,7 +280,7 @@ replay: if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { spin_lock_bh(root_lock); *back = tp->next; - spin_lock_bh(root_lock); + spin_unlock_bh(root_lock); tfilter_notify(skb, n, tp, fh, RTM_DELTFILTER); tcf_destroy(tp); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 4840aff47256..e7fb9e0d21b4 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -27,6 +27,7 @@ #include <linux/kmod.h> #include <linux/list.h> #include <linux/hrtimer.h> +#include <linux/lockdep.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -183,24 +184,68 @@ EXPORT_SYMBOL(unregister_qdisc); (root qdisc, all its children, children of children etc.) */ +struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) +{ + struct Qdisc *q; + + if (!(root->flags & TCQ_F_BUILTIN) && + root->handle == handle) + return root; + + list_for_each_entry(q, &root->list, list) { + if (q->handle == handle) + return q; + } + return NULL; +} + +/* + * This lock is needed until some qdiscs stop calling qdisc_tree_decrease_qlen() + * without rtnl_lock(); currently hfsc_dequeue(), netem_dequeue(), tbf_dequeue() + */ +static DEFINE_SPINLOCK(qdisc_list_lock); + +static void qdisc_list_add(struct Qdisc *q) +{ + if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { + spin_lock_bh(&qdisc_list_lock); + list_add_tail(&q->list, &qdisc_root_sleeping(q)->list); + spin_unlock_bh(&qdisc_list_lock); + } +} + +void qdisc_list_del(struct Qdisc *q) +{ + if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { + spin_lock_bh(&qdisc_list_lock); + list_del(&q->list); + spin_unlock_bh(&qdisc_list_lock); + } +} +EXPORT_SYMBOL(qdisc_list_del); + struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) { unsigned int i; + struct Qdisc *q; + + spin_lock_bh(&qdisc_list_lock); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - struct Qdisc *q, *txq_root = txq->qdisc; - - if (!(txq_root->flags & TCQ_F_BUILTIN) && - txq_root->handle == handle) - return txq_root; + struct Qdisc *txq_root = txq->qdisc_sleeping; - list_for_each_entry(q, &txq_root->list, list) { - if (q->handle == handle) - return q; - } + q = qdisc_match_from_root(txq_root, handle); + if (q) + goto unlock; } - return NULL; + + q = qdisc_match_from_root(dev->rx_queue.qdisc_sleeping, handle); + +unlock: + spin_unlock_bh(&qdisc_list_lock); + + return q; } static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) @@ -416,7 +461,7 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) wd->qdisc->flags &= ~TCQ_F_THROTTLED; smp_wmb(); - __netif_schedule(wd->qdisc); + __netif_schedule(qdisc_root(wd->qdisc)); return HRTIMER_NORESTART; } @@ -433,6 +478,10 @@ void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) { ktime_t time; + if (test_bit(__QDISC_STATE_DEACTIVATED, + &qdisc_root_sleeping(wd->qdisc)->state)) + return; + wd->qdisc->flags |= TCQ_F_THROTTLED; time = ktime_set(0, 0); time = ktime_add_ns(time, PSCHED_US2NS(expires)); @@ -627,11 +676,8 @@ static void notify_and_destroy(struct sk_buff *skb, struct nlmsghdr *n, u32 clid if (new || old) qdisc_notify(skb, n, clid, old, new); - if (old) { - spin_lock_bh(&old->q.lock); + if (old) qdisc_destroy(old); - spin_unlock_bh(&old->q.lock); - } } /* Graft qdisc "new" to class "classid" of qdisc "parent" or @@ -697,6 +743,10 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, return err; } +/* lockdep annotation is needed for ingress; egress gets it only for name */ +static struct lock_class_key qdisc_tx_lock; +static struct lock_class_key qdisc_rx_lock; + /* Allocate and initialize new qdisc. @@ -757,6 +807,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, if (handle == TC_H_INGRESS) { sch->flags |= TCQ_F_INGRESS; handle = TC_H_MAKE(TC_H_INGRESS, 0); + lockdep_set_class(qdisc_lock(sch), &qdisc_rx_lock); } else { if (handle == 0) { handle = qdisc_alloc_handle(dev); @@ -764,6 +815,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, if (handle == 0) goto err_out3; } + lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); } sch->handle = handle; @@ -792,8 +844,8 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, goto err_out3; } } - if (parent && !(sch->flags & TCQ_F_INGRESS)) - list_add_tail(&sch->list, &dev_queue->qdisc->list); + + qdisc_list_add(sch); return sch; } @@ -908,7 +960,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) return -ENOENT; q = qdisc_leaf(p, clid); } else { /* ingress */ - q = dev->rx_queue.qdisc; + q = dev->rx_queue.qdisc_sleeping; } } else { struct netdev_queue *dev_queue; @@ -978,7 +1030,7 @@ replay: return -ENOENT; q = qdisc_leaf(p, clid); } else { /*ingress */ - q = dev->rx_queue.qdisc; + q = dev->rx_queue.qdisc_sleeping; } } else { struct netdev_queue *dev_queue; @@ -1074,20 +1126,13 @@ create_n_graft: } graft: - if (1) { - spinlock_t *root_lock; - - err = qdisc_graft(dev, p, skb, n, clid, q, NULL); - if (err) { - if (q) { - root_lock = qdisc_root_lock(q); - spin_lock_bh(root_lock); - qdisc_destroy(q); - spin_unlock_bh(root_lock); - } - return err; - } + err = qdisc_graft(dev, p, skb, n, clid, q, NULL); + if (err) { + if (q) + qdisc_destroy(q); + return err; } + return 0; } @@ -1236,11 +1281,11 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) q_idx = 0; dev_queue = netdev_get_tx_queue(dev, 0); - if (tc_dump_qdisc_root(dev_queue->qdisc, skb, cb, &q_idx, s_q_idx) < 0) + if (tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, &q_idx, s_q_idx) < 0) goto done; dev_queue = &dev->rx_queue; - if (tc_dump_qdisc_root(dev_queue->qdisc, skb, cb, &q_idx, s_q_idx) < 0) + if (tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, &q_idx, s_q_idx) < 0) goto done; cont: @@ -1529,11 +1574,11 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) t = 0; dev_queue = netdev_get_tx_queue(dev, 0); - if (tc_dump_tclass_root(dev_queue->qdisc, skb, tcm, cb, &t, s_t) < 0) + if (tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, &t, s_t) < 0) goto done; dev_queue = &dev->rx_queue; - if (tc_dump_tclass_root(dev_queue->qdisc, skb, tcm, cb, &t, s_t) < 0) + if (tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, &t, s_t) < 0) goto done; done: diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 6b517b9dac5b..43d37256c15e 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -415,7 +415,7 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch) case TC_ACT_QUEUED: case TC_ACT_STOLEN: kfree_skb(skb); - return NET_XMIT_SUCCESS; + return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: kfree_skb(skb); goto drop; @@ -432,9 +432,11 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch) ret = qdisc_enqueue(skb, flow->q); if (ret != 0) { drop: __maybe_unused - sch->qstats.drops++; - if (flow) - flow->qstats.drops++; + if (net_xmit_drop_count(ret)) { + sch->qstats.drops++; + if (flow) + flow->qstats.drops++; + } return ret; } sch->bstats.bytes += qdisc_pkt_len(skb); @@ -455,7 +457,7 @@ drop: __maybe_unused return 0; } tasklet_schedule(&p->task); - return NET_XMIT_BYPASS; + return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; } /* @@ -530,7 +532,7 @@ static int atm_tc_requeue(struct sk_buff *skb, struct Qdisc *sch) if (!ret) { sch->q.qlen++; sch->qstats.requeues++; - } else { + } else if (net_xmit_drop_count(ret)) { sch->qstats.drops++; p->link.qstats.drops++; } diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 14954bf4a683..8fa90d68ec6d 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -230,7 +230,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) (cl = cbq_class_lookup(q, prio)) != NULL) return cl; - *qerr = NET_XMIT_BYPASS; + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; for (;;) { int result = 0; defmap = head->defaults; @@ -256,7 +256,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: - *qerr = NET_XMIT_SUCCESS; + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return NULL; case TC_ACT_RECLASSIFY: @@ -377,7 +377,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch) q->rx_class = cl; #endif if (cl == NULL) { - if (ret == NET_XMIT_BYPASS) + if (ret & __NET_XMIT_BYPASS) sch->qstats.drops++; kfree_skb(skb); return ret; @@ -397,9 +397,11 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch) return ret; } - sch->qstats.drops++; - cbq_mark_toplevel(q, cl); - cl->qstats.drops++; + if (net_xmit_drop_count(ret)) { + sch->qstats.drops++; + cbq_mark_toplevel(q, cl); + cl->qstats.drops++; + } return ret; } @@ -430,8 +432,10 @@ cbq_requeue(struct sk_buff *skb, struct Qdisc *sch) cbq_activate_class(cl); return 0; } - sch->qstats.drops++; - cl->qstats.drops++; + if (net_xmit_drop_count(ret)) { + sch->qstats.drops++; + cl->qstats.drops++; + } return ret; } @@ -517,6 +521,10 @@ static void cbq_ovl_delay(struct cbq_class *cl) struct cbq_sched_data *q = qdisc_priv(cl->qdisc); psched_tdiff_t delay = cl->undertime - q->now; + if (test_bit(__QDISC_STATE_DEACTIVATED, + &qdisc_root_sleeping(cl->qdisc)->state)) + return; + if (!cl->delayed) { psched_time_t sched = q->now; ktime_t expires; @@ -650,7 +658,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) } sch->flags &= ~TCQ_F_THROTTLED; - __netif_schedule(sch); + __netif_schedule(qdisc_root(sch)); return HRTIMER_NORESTART; } @@ -664,13 +672,15 @@ static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child) q->rx_class = NULL; if (cl && (cl = cbq_reclassify(skb, cl)) != NULL) { + int ret; cbq_mark_toplevel(q, cl); q->rx_class = cl; cl->q->__parent = sch; - if (qdisc_enqueue(skb, cl->q) == 0) { + ret = qdisc_enqueue(skb, cl->q); + if (ret == NET_XMIT_SUCCESS) { sch->q.qlen++; sch->bstats.packets++; sch->bstats.bytes += qdisc_pkt_len(skb); @@ -678,7 +688,8 @@ static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child) cbq_activate_class(cl); return 0; } - sch->qstats.drops++; + if (net_xmit_drop_count(ret)) + sch->qstats.drops++; return 0; } diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index a935676987e2..edd1298f85f6 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -236,7 +236,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch) case TC_ACT_QUEUED: case TC_ACT_STOLEN: kfree_skb(skb); - return NET_XMIT_SUCCESS; + return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: goto drop; @@ -254,7 +254,8 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch) err = qdisc_enqueue(skb, p->q); if (err != NET_XMIT_SUCCESS) { - sch->qstats.drops++; + if (net_xmit_drop_count(err)) + sch->qstats.drops++; return err; } @@ -267,7 +268,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch) drop: kfree_skb(skb); sch->qstats.drops++; - return NET_XMIT_BYPASS; + return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; } static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) @@ -321,7 +322,8 @@ static int dsmark_requeue(struct sk_buff *skb, struct Qdisc *sch) err = p->q->ops->requeue(skb, p->q); if (err != NET_XMIT_SUCCESS) { - sch->qstats.drops++; + if (net_xmit_drop_count(err)) + sch->qstats.drops++; return err; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 9c9cd4d94890..5f0ade7806a7 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -29,7 +29,7 @@ /* Main transmission queue. */ /* Modifications to data participating in scheduling must be protected with - * qdisc_root_lock(qdisc) spinlock. + * qdisc_lock(qdisc) spinlock. * * The idea is the following: * - enqueue, dequeue are serialized via qdisc root lock @@ -126,7 +126,7 @@ static inline int qdisc_restart(struct Qdisc *q) if (unlikely((skb = dequeue_skb(q)) == NULL)) return 0; - root_lock = qdisc_root_lock(q); + root_lock = qdisc_lock(q); /* And release qdisc */ spin_unlock(root_lock); @@ -507,7 +507,7 @@ errout: } EXPORT_SYMBOL(qdisc_create_dflt); -/* Under qdisc_root_lock(qdisc) and BH! */ +/* Under qdisc_lock(qdisc) and BH! */ void qdisc_reset(struct Qdisc *qdisc) { @@ -518,15 +518,17 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); -/* this is the rcu callback function to clean up a qdisc when there - * are no further references to it */ - -static void __qdisc_destroy(struct rcu_head *head) +void qdisc_destroy(struct Qdisc *qdisc) { - struct Qdisc *qdisc = container_of(head, struct Qdisc, q_rcu); const struct Qdisc_ops *ops = qdisc->ops; + if (qdisc->flags & TCQ_F_BUILTIN || + !atomic_dec_and_test(&qdisc->refcnt)) + return; + #ifdef CONFIG_NET_SCHED + qdisc_list_del(qdisc); + qdisc_put_stab(qdisc->stab); #endif gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est); @@ -542,20 +544,6 @@ static void __qdisc_destroy(struct rcu_head *head) kfree((char *) qdisc - qdisc->padded); } - -/* Under qdisc_root_lock(qdisc) and BH! */ - -void qdisc_destroy(struct Qdisc *qdisc) -{ - if (qdisc->flags & TCQ_F_BUILTIN || - !atomic_dec_and_test(&qdisc->refcnt)) - return; - - if (qdisc->parent) - list_del(&qdisc->list); - - call_rcu(&qdisc->q_rcu, __qdisc_destroy); -} EXPORT_SYMBOL(qdisc_destroy); static bool dev_all_qdisc_sleeping_noop(struct net_device *dev) @@ -597,6 +585,9 @@ static void transition_one_qdisc(struct net_device *dev, struct Qdisc *new_qdisc = dev_queue->qdisc_sleeping; int *need_watchdog_p = _need_watchdog; + if (!(new_qdisc->flags & TCQ_F_BUILTIN)) + clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state); + rcu_assign_pointer(dev_queue->qdisc, new_qdisc); if (need_watchdog_p && new_qdisc != &noqueue_qdisc) *need_watchdog_p = 1; @@ -640,6 +631,9 @@ static void dev_deactivate_queue(struct net_device *dev, if (qdisc) { spin_lock_bh(qdisc_lock(qdisc)); + if (!(qdisc->flags & TCQ_F_BUILTIN)) + set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); + dev_queue->qdisc = qdisc_default; qdisc_reset(qdisc); @@ -647,7 +641,7 @@ static void dev_deactivate_queue(struct net_device *dev, } } -static bool some_qdisc_is_running(struct net_device *dev, int lock) +static bool some_qdisc_is_busy(struct net_device *dev) { unsigned int i; @@ -658,16 +652,15 @@ static bool some_qdisc_is_running(struct net_device *dev, int lock) int val; dev_queue = netdev_get_tx_queue(dev, i); - q = dev_queue->qdisc; - root_lock = qdisc_root_lock(q); + q = dev_queue->qdisc_sleeping; + root_lock = qdisc_lock(q); - if (lock) - spin_lock_bh(root_lock); + spin_lock_bh(root_lock); - val = test_bit(__QDISC_STATE_RUNNING, &q->state); + val = (test_bit(__QDISC_STATE_RUNNING, &q->state) || + test_bit(__QDISC_STATE_SCHED, &q->state)); - if (lock) - spin_unlock_bh(root_lock); + spin_unlock_bh(root_lock); if (val) return true; @@ -677,8 +670,6 @@ static bool some_qdisc_is_running(struct net_device *dev, int lock) void dev_deactivate(struct net_device *dev) { - bool running; - netdev_for_each_tx_queue(dev, dev_deactivate_queue, &noop_qdisc); dev_deactivate_queue(dev, &dev->rx_queue, &noop_qdisc); @@ -688,25 +679,8 @@ void dev_deactivate(struct net_device *dev) synchronize_rcu(); /* Wait for outstanding qdisc_run calls. */ - do { - while (some_qdisc_is_running(dev, 0)) - yield(); - - /* - * Double-check inside queue lock to ensure that all effects - * of the queue run are visible when we return. - */ - running = some_qdisc_is_running(dev, 1); - - /* - * The running flag should never be set at this point because - * we've already set dev->qdisc to noop_qdisc *inside* the same - * pair of spin locks. That is, if any qdisc_run starts after - * our initial test it should see the noop_qdisc and then - * clear the RUNNING bit before dropping the queue lock. So - * if it is set here then we've found a bug. - */ - } while (WARN_ON_ONCE(running)); + while (some_qdisc_is_busy(dev)) + yield(); } static void dev_init_scheduler_queue(struct net_device *dev, @@ -735,14 +709,10 @@ static void shutdown_scheduler_queue(struct net_device *dev, struct Qdisc *qdisc_default = _qdisc_default; if (qdisc) { - spinlock_t *root_lock = qdisc_root_lock(qdisc); - dev_queue->qdisc = qdisc_default; dev_queue->qdisc_sleeping = qdisc_default; - spin_lock_bh(root_lock); qdisc_destroy(qdisc); - spin_unlock_bh(root_lock); } } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 0ae7d19dcba8..c2b8d9cce3d2 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1159,14 +1159,14 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) if (cl->level == 0) return cl; - *qerr = NET_XMIT_BYPASS; + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; tcf = q->root.filter_list; while (tcf && (result = tc_classify(skb, tcf, &res)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: - *qerr = NET_XMIT_SUCCESS; + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return NULL; } @@ -1578,7 +1578,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch) cl = hfsc_classify(skb, sch, &err); if (cl == NULL) { - if (err == NET_XMIT_BYPASS) + if (err & __NET_XMIT_BYPASS) sch->qstats.drops++; kfree_skb(skb); return err; @@ -1586,8 +1586,10 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch) err = qdisc_enqueue(skb, cl->qdisc); if (unlikely(err != NET_XMIT_SUCCESS)) { - cl->qstats.drops++; - sch->qstats.drops++; + if (net_xmit_drop_count(err)) { + cl->qstats.drops++; + sch->qstats.drops++; + } return err; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 75a40951c4f2..0df0df202ed0 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -214,14 +214,14 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, if ((cl = htb_find(skb->priority, sch)) != NULL && cl->level == 0) return cl; - *qerr = NET_XMIT_BYPASS; + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; tcf = q->filter_list; while (tcf && (result = tc_classify(skb, tcf, &res)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: - *qerr = NET_XMIT_SUCCESS; + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return NULL; } @@ -567,15 +567,17 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch) } #ifdef CONFIG_NET_CLS_ACT } else if (!cl) { - if (ret == NET_XMIT_BYPASS) + if (ret & __NET_XMIT_BYPASS) sch->qstats.drops++; kfree_skb(skb); return ret; #endif - } else if (qdisc_enqueue(skb, cl->un.leaf.q) != NET_XMIT_SUCCESS) { - sch->qstats.drops++; - cl->qstats.drops++; - return NET_XMIT_DROP; + } else if ((ret = qdisc_enqueue(skb, cl->un.leaf.q)) != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(ret)) { + sch->qstats.drops++; + cl->qstats.drops++; + } + return ret; } else { cl->bstats.packets += skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1; @@ -610,16 +612,18 @@ static int htb_requeue(struct sk_buff *skb, struct Qdisc *sch) } #ifdef CONFIG_NET_CLS_ACT } else if (!cl) { - if (ret == NET_XMIT_BYPASS) + if (ret & __NET_XMIT_BYPASS) sch->qstats.drops++; kfree_skb(skb); return ret; #endif - } else if (cl->un.leaf.q->ops->requeue(skb, cl->un.leaf.q) != + } else if ((ret = cl->un.leaf.q->ops->requeue(skb, cl->un.leaf.q)) != NET_XMIT_SUCCESS) { - sch->qstats.drops++; - cl->qstats.drops++; - return NET_XMIT_DROP; + if (net_xmit_drop_count(ret)) { + sch->qstats.drops++; + cl->qstats.drops++; + } + return ret; } else htb_activate(q, cl); @@ -1275,7 +1279,8 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) /* delete from hash and active; remainder in destroy_class */ qdisc_class_hash_remove(&q->clhash, &cl->common); - cl->parent->children--; + if (cl->parent) + cl->parent->children--; if (cl->prio_activity) htb_deactivate(q, cl); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index a59085700678..fb0294d0b55e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -176,7 +176,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (count == 0) { sch->qstats.drops++; kfree_skb(skb); - return NET_XMIT_BYPASS; + return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; } skb_orphan(skb); @@ -240,8 +240,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) sch->q.qlen++; sch->bstats.bytes += qdisc_pkt_len(skb); sch->bstats.packets++; - } else + } else if (net_xmit_drop_count(ret)) { sch->qstats.drops++; + } pr_debug("netem: enqueue ret %d\n", ret); return ret; diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index f849243eb095..a6697c686c7f 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -38,14 +38,14 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) struct tcf_result res; int err; - *qerr = NET_XMIT_BYPASS; + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; if (TC_H_MAJ(skb->priority) != sch->handle) { err = tc_classify(skb, q->filter_list, &res); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: - *qerr = NET_XMIT_SUCCESS; + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return NULL; } @@ -74,7 +74,7 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch) #ifdef CONFIG_NET_CLS_ACT if (qdisc == NULL) { - if (ret == NET_XMIT_BYPASS) + if (ret & __NET_XMIT_BYPASS) sch->qstats.drops++; kfree_skb(skb); return ret; @@ -88,7 +88,8 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch) sch->q.qlen++; return NET_XMIT_SUCCESS; } - sch->qstats.drops++; + if (net_xmit_drop_count(ret)) + sch->qstats.drops++; return ret; } @@ -102,7 +103,7 @@ prio_requeue(struct sk_buff *skb, struct Qdisc* sch) qdisc = prio_classify(skb, sch, &ret); #ifdef CONFIG_NET_CLS_ACT if (qdisc == NULL) { - if (ret == NET_XMIT_BYPASS) + if (ret & __NET_XMIT_BYPASS) sch->qstats.drops++; kfree_skb(skb); return ret; @@ -112,10 +113,11 @@ prio_requeue(struct sk_buff *skb, struct Qdisc* sch) if ((ret = qdisc->ops->requeue(skb, qdisc)) == NET_XMIT_SUCCESS) { sch->q.qlen++; sch->qstats.requeues++; - return 0; + return NET_XMIT_SUCCESS; } - sch->qstats.drops++; - return NET_XMIT_DROP; + if (net_xmit_drop_count(ret)) + sch->qstats.drops++; + return ret; } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 3f2d1d7f3bbd..5da05839e225 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -97,7 +97,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch) sch->bstats.bytes += qdisc_pkt_len(skb); sch->bstats.packets++; sch->q.qlen++; - } else { + } else if (net_xmit_drop_count(ret)) { q->stats.pdrop++; sch->qstats.drops++; } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 8589da666568..6e041d10dbdb 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -171,14 +171,14 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, if (!q->filter_list) return sfq_hash(q, skb) + 1; - *qerr = NET_XMIT_BYPASS; + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; result = tc_classify(skb, q->filter_list, &res); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: - *qerr = NET_XMIT_SUCCESS; + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; case TC_ACT_SHOT: return 0; } @@ -285,7 +285,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) hash = sfq_classify(skb, sch, &ret); if (hash == 0) { - if (ret == NET_XMIT_BYPASS) + if (ret & __NET_XMIT_BYPASS) sch->qstats.drops++; kfree_skb(skb); return ret; @@ -339,7 +339,7 @@ sfq_requeue(struct sk_buff *skb, struct Qdisc *sch) hash = sfq_classify(skb, sch, &ret); if (hash == 0) { - if (ret == NET_XMIT_BYPASS) + if (ret & __NET_XMIT_BYPASS) sch->qstats.drops++; kfree_skb(skb); return ret; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index b296672f7632..94c61598b86a 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -123,19 +123,13 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch) struct tbf_sched_data *q = qdisc_priv(sch); int ret; - if (qdisc_pkt_len(skb) > q->max_size) { - sch->qstats.drops++; -#ifdef CONFIG_NET_CLS_ACT - if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch)) -#endif - kfree_skb(skb); - - return NET_XMIT_DROP; - } + if (qdisc_pkt_len(skb) > q->max_size) + return qdisc_reshape_fail(skb, sch); ret = qdisc_enqueue(skb, q->qdisc); if (ret != 0) { - sch->qstats.drops++; + if (net_xmit_drop_count(ret)) + sch->qstats.drops++; return ret; } diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 675a5c3e68a6..1fcb4cf2f4c9 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -80,6 +80,10 @@ static struct sctp_auth_bytes *sctp_auth_create_key(__u32 key_len, gfp_t gfp) { struct sctp_auth_bytes *key; + /* Verify that we are not going to overflow INT_MAX */ + if ((INT_MAX - key_len) < sizeof(struct sctp_auth_bytes)) + return NULL; + /* Allocate the shared key */ key = kmalloc(sizeof(struct sctp_auth_bytes) + key_len, gfp); if (!key) diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index e39a0cdef184..4c8d9f45ce09 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -103,6 +103,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, /* Initialize the CHUNKS parameter */ auth_chunks->param_hdr.type = SCTP_PARAM_CHUNKS; + auth_chunks->param_hdr.length = htons(sizeof(sctp_paramhdr_t)); /* If the Add-IP functionality is enabled, we must * authenticate, ASCONF and ASCONF-ACK chunks @@ -110,8 +111,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, if (sctp_addip_enable) { auth_chunks->chunks[0] = SCTP_CID_ASCONF; auth_chunks->chunks[1] = SCTP_CID_ASCONF_ACK; - auth_chunks->param_hdr.length = - htons(sizeof(sctp_paramhdr_t) + 2); + auth_chunks->param_hdr.length += htons(2); } } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index a238d6834b33..47f91afa0211 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -195,8 +195,7 @@ out: } /* Based on tcp_v6_xmit() in tcp_ipv6.c. */ -static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport, - int ipfragok) +static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) { struct sock *sk = skb->sk; struct ipv6_pinfo *np = inet6_sk(sk); @@ -231,7 +230,10 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport, SCTP_INC_STATS(SCTP_MIB_OUTSCTPPACKS); - return ip6_xmit(sk, skb, &fl, np->opt, ipfragok); + if (!(transport->param_flags & SPP_PMTUD_ENABLE)) + skb->local_df = 1; + + return ip6_xmit(sk, skb, &fl, np->opt, 0); } /* Returns the dst cache entry for the given source and destination ip @@ -317,7 +319,8 @@ static void sctp_v6_get_saddr(struct sctp_sock *sk, __func__, asoc, dst, NIP6(daddr->v6.sin6_addr)); if (!asoc) { - ipv6_dev_get_saddr(dst ? ip6_dst_idev(dst)->dev : NULL, + ipv6_dev_get_saddr(sock_net(sctp_opt2sk(sk)), + dst ? ip6_dst_idev(dst)->dev : NULL, &daddr->v6.sin6_addr, inet6_sk(&sk->inet.sk)->srcprefs, &saddr->v6.sin6_addr); diff --git a/net/sctp/output.c b/net/sctp/output.c index 45684646b1db..0dc4a7dfb234 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -586,10 +586,8 @@ int sctp_packet_transmit(struct sctp_packet *packet) SCTP_DEBUG_PRINTK("***sctp_transmit_packet*** skb len %d\n", nskb->len); - if (tp->param_flags & SPP_PMTUD_ENABLE) - (*tp->af_specific->sctp_xmit)(nskb, tp, packet->ipfragok); - else - (*tp->af_specific->sctp_xmit)(nskb, tp, 1); + nskb->local_df = packet->ipfragok; + (*tp->af_specific->sctp_xmit)(nskb, tp); out: packet->size = packet->overhead; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index a6e0818bcff5..0b65354aaf64 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -862,16 +862,21 @@ static int sctp_inet_supported_addrs(const struct sctp_sock *opt, /* Wrapper routine that calls the ip transmit routine. */ static inline int sctp_v4_xmit(struct sk_buff *skb, - struct sctp_transport *transport, int ipfragok) + struct sctp_transport *transport) { + struct inet_sock *inet = inet_sk(skb->sk); + SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, " "src:%u.%u.%u.%u, dst:%u.%u.%u.%u\n", __func__, skb, skb->len, NIPQUAD(skb->rtable->rt_src), NIPQUAD(skb->rtable->rt_dst)); + inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ? + IP_PMTUDISC_DO : IP_PMTUDISC_DONT; + SCTP_INC_STATS(SCTP_MIB_OUTSCTPPACKS); - return ip_queue_xmit(skb, ipfragok); + return ip_queue_xmit(skb, 0); } static struct sctp_af sctp_af_inet; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index dbb79adf8f3c..afa952e726d7 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3055,6 +3055,9 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk, { struct sctp_authchunk val; + if (!sctp_auth_enable) + return -EACCES; + if (optlen != sizeof(struct sctp_authchunk)) return -EINVAL; if (copy_from_user(&val, optval, optlen)) @@ -3085,6 +3088,9 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk, struct sctp_hmacalgo *hmacs; int err; + if (!sctp_auth_enable) + return -EACCES; + if (optlen < sizeof(struct sctp_hmacalgo)) return -EINVAL; @@ -3123,6 +3129,9 @@ static int sctp_setsockopt_auth_key(struct sock *sk, struct sctp_association *asoc; int ret; + if (!sctp_auth_enable) + return -EACCES; + if (optlen <= sizeof(struct sctp_authkey)) return -EINVAL; @@ -3135,6 +3144,11 @@ static int sctp_setsockopt_auth_key(struct sock *sk, goto out; } + if (authkey->sca_keylength > optlen) { + ret = -EINVAL; + goto out; + } + asoc = sctp_id2assoc(sk, authkey->sca_assoc_id); if (!asoc && authkey->sca_assoc_id && sctp_style(sk, UDP)) { ret = -EINVAL; @@ -3160,6 +3174,9 @@ static int sctp_setsockopt_active_key(struct sock *sk, struct sctp_authkeyid val; struct sctp_association *asoc; + if (!sctp_auth_enable) + return -EACCES; + if (optlen != sizeof(struct sctp_authkeyid)) return -EINVAL; if (copy_from_user(&val, optval, optlen)) @@ -3185,6 +3202,9 @@ static int sctp_setsockopt_del_key(struct sock *sk, struct sctp_authkeyid val; struct sctp_association *asoc; + if (!sctp_auth_enable) + return -EACCES; + if (optlen != sizeof(struct sctp_authkeyid)) return -EINVAL; if (copy_from_user(&val, optval, optlen)) @@ -5197,19 +5217,29 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, char __user *optval, int __user *optlen) { + struct sctp_hmacalgo __user *p = (void __user *)optval; struct sctp_hmac_algo_param *hmacs; - __u16 param_len; + __u16 data_len = 0; + u32 num_idents; + + if (!sctp_auth_enable) + return -EACCES; hmacs = sctp_sk(sk)->ep->auth_hmacs_list; - param_len = ntohs(hmacs->param_hdr.length); + data_len = ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t); - if (len < param_len) + if (len < sizeof(struct sctp_hmacalgo) + data_len) return -EINVAL; + + len = sizeof(struct sctp_hmacalgo) + data_len; + num_idents = data_len / sizeof(u16); + if (put_user(len, optlen)) return -EFAULT; - if (copy_to_user(optval, hmacs->hmac_ids, len)) + if (put_user(num_idents, &p->shmac_num_idents)) + return -EFAULT; + if (copy_to_user(p->shmac_idents, hmacs->hmac_ids, data_len)) return -EFAULT; - return 0; } @@ -5219,6 +5249,9 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len, struct sctp_authkeyid val; struct sctp_association *asoc; + if (!sctp_auth_enable) + return -EACCES; + if (len < sizeof(struct sctp_authkeyid)) return -EINVAL; if (copy_from_user(&val, optval, sizeof(struct sctp_authkeyid))) @@ -5233,6 +5266,12 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len, else val.scact_keynumber = sctp_sk(sk)->ep->active_key_id; + len = sizeof(struct sctp_authkeyid); + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + return 0; } @@ -5243,13 +5282,16 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, struct sctp_authchunks val; struct sctp_association *asoc; struct sctp_chunks_param *ch; - u32 num_chunks; + u32 num_chunks = 0; char __user *to; - if (len <= sizeof(struct sctp_authchunks)) + if (!sctp_auth_enable) + return -EACCES; + + if (len < sizeof(struct sctp_authchunks)) return -EINVAL; - if (copy_from_user(&val, p, sizeof(struct sctp_authchunks))) + if (copy_from_user(&val, optval, sizeof(struct sctp_authchunks))) return -EFAULT; to = p->gauth_chunks; @@ -5258,20 +5300,21 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, return -EINVAL; ch = asoc->peer.peer_chunks; + if (!ch) + goto num; /* See if the user provided enough room for all the data */ num_chunks = ntohs(ch->param_hdr.length) - sizeof(sctp_paramhdr_t); if (len < num_chunks) return -EINVAL; - len = num_chunks; - if (put_user(len, optlen)) + if (copy_to_user(to, ch->chunks, num_chunks)) return -EFAULT; +num: + len = sizeof(struct sctp_authchunks) + num_chunks; + if (put_user(len, optlen)) return -EFAULT; if (put_user(num_chunks, &p->gauth_number_of_chunks)) return -EFAULT; - if (copy_to_user(to, ch->chunks, len)) - return -EFAULT; - return 0; } @@ -5282,13 +5325,16 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, struct sctp_authchunks val; struct sctp_association *asoc; struct sctp_chunks_param *ch; - u32 num_chunks; + u32 num_chunks = 0; char __user *to; - if (len <= sizeof(struct sctp_authchunks)) + if (!sctp_auth_enable) + return -EACCES; + + if (len < sizeof(struct sctp_authchunks)) return -EINVAL; - if (copy_from_user(&val, p, sizeof(struct sctp_authchunks))) + if (copy_from_user(&val, optval, sizeof(struct sctp_authchunks))) return -EFAULT; to = p->gauth_chunks; @@ -5301,17 +5347,21 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, else ch = sctp_sk(sk)->ep->auth_chunk_list; + if (!ch) + goto num; + num_chunks = ntohs(ch->param_hdr.length) - sizeof(sctp_paramhdr_t); - if (len < num_chunks) + if (len < sizeof(struct sctp_authchunks) + num_chunks) return -EINVAL; - len = num_chunks; + if (copy_to_user(to, ch->chunks, num_chunks)) + return -EFAULT; +num: + len = sizeof(struct sctp_authchunks) + num_chunks; if (put_user(len, optlen)) return -EFAULT; if (put_user(num_chunks, &p->gauth_number_of_chunks)) return -EFAULT; - if (copy_to_user(to, ch->chunks, len)) - return -EFAULT; return 0; } diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 0326d3060bc7..0747d8a9232f 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -85,7 +85,7 @@ static struct top_srv topsrv = { 0 }; static u32 htohl(u32 in, int swap) { - return swap ? (u32)___constant_swab32(in) : in; + return swap ? swab32(in) : in; } /** diff --git a/net/wanrouter/wanmain.c b/net/wanrouter/wanmain.c index b210a88d0960..7f07152bc109 100644 --- a/net/wanrouter/wanmain.c +++ b/net/wanrouter/wanmain.c @@ -57,7 +57,6 @@ #include <linux/vmalloc.h> /* vmalloc, vfree */ #include <asm/uaccess.h> /* copy_to/from_user */ #include <linux/init.h> /* __initfunc et al. */ -#include <net/syncppp.h> #define KMEM_SAFETYZONE 8 @@ -567,9 +566,6 @@ static int wanrouter_device_new_if(struct wan_device *wandev, { wanif_conf_t *cnf; struct net_device *dev = NULL; -#ifdef CONFIG_WANPIPE_MULTPPP - struct ppp_device *pppdev=NULL; -#endif int err; if ((wandev->state == WAN_UNCONFIGURED) || (wandev->new_if == NULL)) @@ -588,25 +584,10 @@ static int wanrouter_device_new_if(struct wan_device *wandev, goto out; if (cnf->config_id == WANCONFIG_MPPP) { -#ifdef CONFIG_WANPIPE_MULTPPP - pppdev = kzalloc(sizeof(struct ppp_device), GFP_KERNEL); - err = -ENOBUFS; - if (pppdev == NULL) - goto out; - pppdev->dev = kzalloc(sizeof(struct net_device), GFP_KERNEL); - if (pppdev->dev == NULL) { - kfree(pppdev); - err = -ENOBUFS; - goto out; - } - err = wandev->new_if(wandev, (struct net_device *)pppdev, cnf); - dev = pppdev->dev; -#else printk(KERN_INFO "%s: Wanpipe Mulit-Port PPP support has not been compiled in!\n", wandev->name); err = -EPROTONOSUPPORT; goto out; -#endif } else { dev = kzalloc(sizeof(struct net_device), GFP_KERNEL); err = -ENOBUFS; @@ -661,17 +642,9 @@ static int wanrouter_device_new_if(struct wan_device *wandev, kfree(dev->priv); dev->priv = NULL; -#ifdef CONFIG_WANPIPE_MULTPPP - if (cnf->config_id == WANCONFIG_MPPP) - kfree(pppdev); - else - kfree(dev); -#else /* Sync PPP is disabled */ if (cnf->config_id != WANCONFIG_MPPP) kfree(dev); -#endif - out: kfree(cnf); return err; diff --git a/net/wireless/wext.c b/net/wireless/wext.c index df5b3886c36b..d98ffb75119a 100644 --- a/net/wireless/wext.c +++ b/net/wireless/wext.c @@ -1277,6 +1277,7 @@ static int rtnetlink_fill_iwinfo(struct sk_buff *skb, struct net_device *dev, r->ifi_flags = dev_get_flags(dev); r->ifi_change = 0; /* Wireless changes don't affect those flags */ + NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); /* Add the wireless events in the netlink packet */ NLA_PUT(skb, IFLA_WIRELESS, event_len, event); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 3f964db908a7..ac25b4c0e982 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -112,16 +112,13 @@ error_nolock: int xfrm_output_resume(struct sk_buff *skb, int err) { while (likely((err = xfrm_output_one(skb, err)) == 0)) { - struct xfrm_state *x; - nf_reset(skb); err = skb->dst->ops->local_out(skb); if (unlikely(err != 1)) goto out; - x = skb->dst->xfrm; - if (!x) + if (!skb->dst->xfrm) return dst_output(skb); err = nf_hook(skb->dst->ops->family, |