diff options
Diffstat (limited to 'net')
34 files changed, 511 insertions, 369 deletions
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 4e59df5f8e0..1edfdf4c095 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 12bba6207a8..80ba30cf4b6 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -736,7 +736,7 @@ MODULE_PARM_DESC(compress_src, "Compress sources headers"); module_param(compress_dst, bool, 0644); MODULE_PARM_DESC(compress_dst, "Compress destination headers"); -MODULE_AUTHOR("David Libault <david.libault@inventel.fr>, Maxim Krasnyansky <maxk@qualcomm.com>"); +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 c85bf8f678d..f4f6615cad9 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 c1239852834..3396d5bdef1 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 6cfc7ba611b..ba537fae0a4 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 8cda4987486..a16011fedc1 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 9b58d70b0e7..4f52c3d50eb 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/core/datagram.c b/net/core/datagram.c index dd61dcad601..52f577a0f54 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 600bb23c4c2..60c51f76588 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); @@ -1800,9 +1804,13 @@ gso: 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); goto out; @@ -1974,15 +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_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); } } } @@ -2084,7 +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)); } diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index a89f32fa94f..57abe8266be 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -99,7 +99,7 @@ struct gen_estimator_head static struct gen_estimator_head elist[EST_MAX_INTERVAL+1]; -/* Protects against NULL dereference and RCU write-side */ +/* Protects against NULL dereference */ static DEFINE_RWLOCK(est_lock); static void est_timer(unsigned long arg) @@ -185,7 +185,6 @@ int gen_new_estimator(struct gnet_stats_basic *bstats, est->last_packets = bstats->packets; est->avpps = rate_est->pps<<10; - write_lock_bh(&est_lock); if (!elist[idx].timer.function) { INIT_LIST_HEAD(&elist[idx].list); setup_timer(&elist[idx].timer, est_timer, idx); @@ -195,7 +194,6 @@ int gen_new_estimator(struct gnet_stats_basic *bstats, mod_timer(&elist[idx].timer, jiffies + ((HZ/4) << idx)); list_add_rcu(&est->list, &elist[idx].list); - write_unlock_bh(&est_lock); return 0; } @@ -214,6 +212,7 @@ static void __gen_kill_estimator(struct rcu_head *head) * Removes the rate estimator specified by &bstats and &rate_est * and deletes the timer. * + * NOTE: Called under rtnl_mutex */ void gen_kill_estimator(struct gnet_stats_basic *bstats, struct gnet_stats_rate_est *rate_est) @@ -227,17 +226,17 @@ void gen_kill_estimator(struct gnet_stats_basic *bstats, if (!elist[idx].timer.function) continue; - write_lock_bh(&est_lock); list_for_each_entry_safe(e, n, &elist[idx].list, list) { if (e->rate_est != rate_est || e->bstats != bstats) continue; + write_lock_bh(&est_lock); e->bstats = NULL; + write_unlock_bh(&est_lock); list_del_rcu(&e->list); call_rcu(&e->e_rcu, __gen_kill_estimator); } - write_unlock_bh(&est_lock); } } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 84640172d65..ca1ccdf1ef7 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/input.c b/net/dccp/input.c index df2f110df94..803933ab396 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/ipv4/netfilter/ipt_addrtype.c b/net/ipv4/netfilter/ipt_addrtype.c index 49587a49722..462a22c9787 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 91537f11273..6c4f11f5144 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 16fc6f454a3..cca921ea855 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -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, @@ -3048,8 +3110,8 @@ 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 } }; @@ -3126,10 +3188,12 @@ 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; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index a7842c54f58..e2d3b7580b7 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; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 8d05527524e..f5de3f9dc69 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/ip6_fib.c b/net/ipv6/ip6_fib.c index 52dddc25d3e..29c7c99e69f 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 a4402de425d..0e844c2736a 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -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 741cfcd96f8..4e5eac301f9 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -911,7 +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); } @@ -921,7 +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 beb48e3f038..f1c62ba0f56 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 41b165ffb36..9af6115f0f5 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -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) @@ -2189,7 +2190,7 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, } else if (dst) { struct inet6_dev *idev = ip6_dst_idev(&rt->u.dst); struct in6_addr saddr_buf; - if (ipv6_dev_get_saddr(idev ? idev->dev : NULL, + if (ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, dst, 0, &saddr_buf) == 0) NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); } @@ -2234,7 +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); } @@ -2300,7 +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) { @@ -2327,7 +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/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 8f1e0543b3c..08e4cbbe3f0 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/mlme.c b/net/mac80211/mlme.c index e1d11c9b672..1e97fb9fb34 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2103,6 +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; } /* diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 105a616c5c7..a8752031adc 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/rfkill/rfkill.c b/net/rfkill/rfkill.c index d2d45655cd1..35a9994e233 100644 --- a/net/rfkill/rfkill.c +++ b/net/rfkill/rfkill.c @@ -150,6 +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 @@ -168,6 +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 && @@ -214,7 +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) { @@ -239,8 +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) { @@ -458,13 +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 diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d2b6f54a626..5cafdd4c801 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 c25465e5607..ef0efeca635 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> @@ -331,7 +332,7 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt) if (!s || tsize != s->tsize || (!tab && tsize > 0)) return ERR_PTR(-EINVAL); - spin_lock_bh(&qdisc_stab_lock); + spin_lock(&qdisc_stab_lock); list_for_each_entry(stab, &qdisc_stab_list, list) { if (memcmp(&stab->szopts, s, sizeof(*s))) @@ -339,11 +340,11 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt) if (tsize > 0 && memcmp(stab->data, tab, tsize * sizeof(u16))) continue; stab->refcnt++; - spin_unlock_bh(&qdisc_stab_lock); + spin_unlock(&qdisc_stab_lock); return stab; } - spin_unlock_bh(&qdisc_stab_lock); + spin_unlock(&qdisc_stab_lock); stab = kmalloc(sizeof(*stab) + tsize * sizeof(u16), GFP_KERNEL); if (!stab) @@ -354,9 +355,9 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt) if (tsize > 0) memcpy(stab->data, tab, tsize * sizeof(u16)); - spin_lock_bh(&qdisc_stab_lock); + spin_lock(&qdisc_stab_lock); list_add_tail(&stab->list, &qdisc_stab_list); - spin_unlock_bh(&qdisc_stab_lock); + spin_unlock(&qdisc_stab_lock); return stab; } @@ -366,14 +367,14 @@ void qdisc_put_stab(struct qdisc_size_table *tab) if (!tab) return; - spin_lock_bh(&qdisc_stab_lock); + spin_lock(&qdisc_stab_lock); if (--tab->refcnt == 0) { list_del(&tab->list); kfree(tab); } - spin_unlock_bh(&qdisc_stab_lock); + spin_unlock(&qdisc_stab_lock); } EXPORT_SYMBOL(qdisc_put_stab); @@ -426,7 +427,7 @@ 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; } @@ -637,11 +638,8 @@ 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 @@ -707,6 +705,10 @@ 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. @@ -767,6 +769,7 @@ 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); @@ -774,6 +777,7 @@ 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; @@ -1084,20 +1088,13 @@ 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; } diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 4e261ce62f4..47ef492c4ff 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -654,7 +654,7 @@ 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; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 468574682ca..c3ed4d44fc1 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -518,14 +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; + + if (qdisc->parent) + list_del(&qdisc->list); + #ifdef CONFIG_NET_SCHED qdisc_put_stab(qdisc->stab); #endif @@ -542,20 +545,6 @@ static void __qdisc_destroy(struct rcu_head *head) kfree((char *) qdisc - qdisc->padded); } - -/* Under qdisc_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 +586,9 @@ 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 +632,9 @@ 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 +642,7 @@ static void dev_deactivate_queue(struct net_device *dev, } } -static bool some_qdisc_is_busy(struct net_device *dev, int lock) +static bool some_qdisc_is_busy(struct net_device *dev) { unsigned int i; @@ -661,14 +656,12 @@ static bool some_qdisc_is_busy(struct net_device *dev, int lock) 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) || test_bit(__QDISC_STATE_SCHED, &q->state)); - if (lock) - spin_unlock_bh(root_lock); + spin_unlock_bh(root_lock); if (val) return true; @@ -678,8 +671,6 @@ static bool some_qdisc_is_busy(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); @@ -689,25 +680,8 @@ void dev_deactivate(struct net_device *dev) synchronize_rcu(); /* Wait for outstanding qdisc_run calls. */ - do { - while (some_qdisc_is_busy(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_busy(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, @@ -736,14 +710,10 @@ static void shutdown_scheduler_queue(struct net_device *dev, struct Qdisc *qdisc_default = _qdisc_default; if (qdisc) { - spinlock_t *root_lock = qdisc_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_htb.c b/net/sched/sch_htb.c index 6febd245e62..0df0df202ed 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -577,7 +577,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch) sch->qstats.drops++; cl->qstats.drops++; } - return NET_XMIT_DROP; + return ret; } else { cl->bstats.packets += skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1; @@ -623,7 +623,7 @@ static int htb_requeue(struct sk_buff *skb, struct Qdisc *sch) sch->qstats.drops++; cl->qstats.drops++; } - return NET_XMIT_DROP; + return ret; } else htb_activate(q, cl); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index eac197610ed..a6697c686c7 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -113,11 +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; } if (net_xmit_drop_count(ret)) sch->qstats.drops++; - return NET_XMIT_DROP; + return ret; } diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 7d3b7ff3bf0..94c61598b86 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -123,15 +123,8 @@ 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) { diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 483a01d0740..47f91afa021 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -319,7 +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); |