diff options
Diffstat (limited to '')
183 files changed, 2797 insertions, 2325 deletions
diff --git a/net/802/psnap.c b/net/802/psnap.c index ea4643931446..b3cfe5a14fca 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -31,11 +31,9 @@ static struct llc_sap *snap_sap; */ static struct datalink_proto *find_snap_client(unsigned char *desc) { - struct list_head *entry; struct datalink_proto *proto = NULL, *p; - list_for_each_rcu(entry, &snap_list) { - p = list_entry(entry, struct datalink_proto, node); + list_for_each_entry_rcu(p, &snap_list, node) { if (!memcmp(p->type, desc, 5)) { proto = p; break; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index f42bc2b26b85..4bf014e51f8c 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -569,6 +569,7 @@ static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) * separate class since they always nest. */ static struct lock_class_key vlan_netdev_xmit_lock_key; +static struct lock_class_key vlan_netdev_addr_lock_key; static void vlan_dev_set_lockdep_one(struct net_device *dev, struct netdev_queue *txq, @@ -581,6 +582,9 @@ static void vlan_dev_set_lockdep_one(struct net_device *dev, static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass) { + lockdep_set_class_and_subclass(&dev->addr_list_lock, + &vlan_netdev_addr_lock_key, + subclass); netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass); } diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 4507f744f44e..cdf137af7adc 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -1285,7 +1285,7 @@ static int p9_socket_open(struct p9_trans *trans, struct socket *csocket) int fd, ret; csocket->sk->sk_allocation = GFP_NOIO; - fd = sock_map_fd(csocket); + fd = sock_map_fd(csocket, 0); if (fd < 0) { P9_EPRINTK(KERN_ERR, "p9_socket_open: failed to map fd\n"); return fd; diff --git a/net/Kconfig b/net/Kconfig index b98668751749..7612cc8c337c 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -2,9 +2,7 @@ # Network configuration # -menu "Networking" - -config NET +menuconfig NET bool "Networking support" ---help--- Unless you really know what you are doing, you should say Y here. @@ -22,7 +20,6 @@ config NET recommended to read the NET-HOWTO, available from <http://www.tldp.org/docs.html#howto>. -# Make sure that all config symbols are dependent on NET if NET menu "Networking options" @@ -252,5 +249,3 @@ source "net/rfkill/Kconfig" source "net/9p/Kconfig" endif # if NET -endmenu # Networking - diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 07b5b82c5eab..0c850427a85b 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -959,7 +959,7 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + skb_shinfo(skb)->frags[i].size; if ((copy = end - offset) > 0) { @@ -986,7 +986,7 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset, for (; list; list = list->next) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + list->len; if ((copy = end - offset) > 0) { diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 4fccaa1e07be..11b16d16661c 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -62,11 +62,13 @@ static void MPOA_cache_impos_rcvd(struct k_message *msg, struct mpoa_client *mpc static void set_mpc_ctrl_addr_rcvd(struct k_message *mesg, struct mpoa_client *mpc); static void set_mps_mac_addr_rcvd(struct k_message *mesg, struct mpoa_client *mpc); -static uint8_t *copy_macs(struct mpoa_client *mpc, uint8_t *router_mac, - uint8_t *tlvs, uint8_t mps_macs, uint8_t device_type); +static const uint8_t *copy_macs(struct mpoa_client *mpc, + const uint8_t *router_mac, + const uint8_t *tlvs, uint8_t mps_macs, + uint8_t device_type); static void purge_egress_shortcut(struct atm_vcc *vcc, eg_cache_entry *entry); -static void send_set_mps_ctrl_addr(char *addr, struct mpoa_client *mpc); +static void send_set_mps_ctrl_addr(const char *addr, struct mpoa_client *mpc); static void mpoad_close(struct atm_vcc *vcc); static int msg_from_mpoad(struct atm_vcc *vcc, struct sk_buff *skb); @@ -351,12 +353,12 @@ static const char *mpoa_device_type_string(char type) * lec sees a TLV it uses the pointer to call this function. * */ -static void lane2_assoc_ind(struct net_device *dev, uint8_t *mac_addr, - uint8_t *tlvs, uint32_t sizeoftlvs) +static void lane2_assoc_ind(struct net_device *dev, const u8 *mac_addr, + const u8 *tlvs, u32 sizeoftlvs) { uint32_t type; uint8_t length, mpoa_device_type, number_of_mps_macs; - uint8_t *end_of_tlvs; + const uint8_t *end_of_tlvs; struct mpoa_client *mpc; mpoa_device_type = number_of_mps_macs = 0; /* silence gcc */ @@ -430,8 +432,10 @@ static void lane2_assoc_ind(struct net_device *dev, uint8_t *mac_addr, * plus the possible MAC address(es) to mpc->mps_macs. * For a freshly allocated MPOA client mpc->mps_macs == 0. */ -static uint8_t *copy_macs(struct mpoa_client *mpc, uint8_t *router_mac, - uint8_t *tlvs, uint8_t mps_macs, uint8_t device_type) +static const uint8_t *copy_macs(struct mpoa_client *mpc, + const uint8_t *router_mac, + const uint8_t *tlvs, uint8_t mps_macs, + uint8_t device_type) { int num_macs; num_macs = (mps_macs > 1) ? mps_macs : 1; @@ -811,7 +815,7 @@ static int atm_mpoa_mpoad_attach (struct atm_vcc *vcc, int arg) return arg; } -static void send_set_mps_ctrl_addr(char *addr, struct mpoa_client *mpc) +static void send_set_mps_ctrl_addr(const char *addr, struct mpoa_client *mpc) { struct k_message mesg; 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 844ca5f1b2d4..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) @@ -221,187 +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"); - - if (sysfs_create_link(&bt_class->subsys.kobj, - &dev->kobj, kobject_name(&dev->kobj)) < 0) - BT_ERR("Failed to create class symlink"); - return 0; } @@ -409,67 +436,35 @@ void hci_unregister_sysfs(struct hci_dev *hdev) { BT_DBG("%p name %s type %d", hdev, hdev->name, hdev->type); - sysfs_remove_link(&bt_class->subsys.kobj, - kobject_name(&hdev->dev.kobj)); - device_del(&hdev->dev); } 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 d9449df7cad5..4f52c3d50ebe 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -68,10 +68,17 @@ static int br_dev_stop(struct net_device *dev) static int br_change_mtu(struct net_device *dev, int new_mtu) { - if (new_mtu < 68 || new_mtu > br_min_mtu(netdev_priv(dev))) + struct net_bridge *br = netdev_priv(dev); + if (new_mtu < 68 || new_mtu > br_min_mtu(br)) return -EINVAL; dev->mtu = new_mtu; + +#ifdef CONFIG_BRIDGE_NETFILTER + /* remember the MTU in the rtable for PMTU */ + br->fake_rtable.u.dst.metrics[RTAX_MTU - 1] = new_mtu; +#endif + return 0; } @@ -141,11 +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_if.c b/net/bridge/br_if.c index a072ea5ca6f5..63c18aacde8c 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -202,6 +202,9 @@ static struct net_device *new_bridge_dev(const char *name) br->topology_change = 0; br->topology_change_detected = 0; br->ageing_time = 300 * HZ; + + br_netfilter_rtable_init(br); + INIT_LIST_HEAD(&br->age_list); br_stp_timer_init(br); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index bb90cd7bace3..6a9a6cd74b1e 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -101,33 +101,30 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb) pppoe_proto(skb) == htons(PPP_IPV6) && \ brnf_filter_pppoe_tagged) -/* We need these fake structures to make netfilter happy -- - * lots of places assume that skb->dst != NULL, which isn't - * all that unreasonable. - * +/* + * Initialize bogus route table used to keep netfilter happy. * Currently, we fill in the PMTU entry because netfilter * refragmentation needs it, and the rt_flags entry because * ipt_REJECT needs it. Future netfilter modules might - * require us to fill additional fields. */ -static struct net_device __fake_net_device = { - .hard_header_len = ETH_HLEN, -#ifdef CONFIG_NET_NS - .nd_net = &init_net, -#endif -}; + * require us to fill additional fields. + */ +void br_netfilter_rtable_init(struct net_bridge *br) +{ + struct rtable *rt = &br->fake_rtable; -static struct rtable __fake_rtable = { - .u = { - .dst = { - .__refcnt = ATOMIC_INIT(1), - .dev = &__fake_net_device, - .path = &__fake_rtable.u.dst, - .metrics = {[RTAX_MTU - 1] = 1500}, - .flags = DST_NOXFRM, - } - }, - .rt_flags = 0, -}; + atomic_set(&rt->u.dst.__refcnt, 1); + 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; +} + +static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) +{ + struct net_bridge_port *port = rcu_dereference(dev->br_port); + + return port ? &port->br->fake_rtable : NULL; +} static inline struct net_device *bridge_parent(const struct net_device *dev) { @@ -226,8 +223,12 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) } nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; - skb->rtable = &__fake_rtable; - dst_hold(&__fake_rtable.u.dst); + skb->rtable = bridge_parent_rtable(nf_bridge->physindev); + if (!skb->rtable) { + kfree_skb(skb); + return 0; + } + dst_hold(&skb->rtable->u.dst); skb->dev = nf_bridge->physindev; nf_bridge_push_encap_header(skb); @@ -391,8 +392,12 @@ bridged_dnat: skb->pkt_type = PACKET_HOST; } } else { - skb->rtable = &__fake_rtable; - dst_hold(&__fake_rtable.u.dst); + skb->rtable = bridge_parent_rtable(nf_bridge->physindev); + if (!skb->rtable) { + kfree_skb(skb); + return 0; + } + dst_hold(&skb->rtable->u.dst); } skb->dev = nf_bridge->physindev; @@ -611,8 +616,8 @@ static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - if (skb->rtable == &__fake_rtable) { - dst_release(&__fake_rtable.u.dst); + if (skb->rtable && skb->rtable == bridge_parent_rtable(in)) { + dst_release(&skb->rtable->u.dst); skb->rtable = NULL; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 815ed38925b2..c3dc18ddc043 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -15,6 +15,7 @@ #include <linux/netdevice.h> #include <linux/if_bridge.h> +#include <net/route.h> #define BR_HASH_BITS 8 #define BR_HASH_SIZE (1 << BR_HASH_BITS) @@ -92,6 +93,9 @@ struct net_bridge struct hlist_head hash[BR_HASH_SIZE]; struct list_head age_list; unsigned long feature_mask; +#ifdef CONFIG_BRIDGE_NETFILTER + struct rtable fake_rtable; +#endif unsigned long flags; #define BR_SET_MAC_ADDR 0x00000001 @@ -197,9 +201,11 @@ extern int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __us #ifdef CONFIG_BRIDGE_NETFILTER extern int br_netfilter_init(void); extern void br_netfilter_fini(void); +extern void br_netfilter_rtable_init(struct net_bridge *); #else #define br_netfilter_init() (0) #define br_netfilter_fini() do { } while(0) +#define br_netfilter_rtable_init(x) #endif /* br_stp.c */ 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/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 690bc3ab186c..1a58af51a2e2 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -93,28 +93,20 @@ static struct nf_hook_ops ebt_ops_filter[] __read_mostly = { static int __init ebtable_filter_init(void) { - int i, j, ret; + int ret; ret = ebt_register_table(&frame_filter); if (ret < 0) return ret; - for (i = 0; i < ARRAY_SIZE(ebt_ops_filter); i++) - if ((ret = nf_register_hook(&ebt_ops_filter[i])) < 0) - goto cleanup; - return ret; -cleanup: - for (j = 0; j < i; j++) - nf_unregister_hook(&ebt_ops_filter[j]); - ebt_unregister_table(&frame_filter); + ret = nf_register_hooks(ebt_ops_filter, ARRAY_SIZE(ebt_ops_filter)); + if (ret < 0) + ebt_unregister_table(&frame_filter); return ret; } static void __exit ebtable_filter_fini(void) { - int i; - - for (i = 0; i < ARRAY_SIZE(ebt_ops_filter); i++) - nf_unregister_hook(&ebt_ops_filter[i]); + nf_unregister_hooks(ebt_ops_filter, ARRAY_SIZE(ebt_ops_filter)); ebt_unregister_table(&frame_filter); } diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 5b495fe2d0b6..f60c1e78e575 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -100,28 +100,20 @@ static struct nf_hook_ops ebt_ops_nat[] __read_mostly = { static int __init ebtable_nat_init(void) { - int i, ret, j; + int ret; ret = ebt_register_table(&frame_nat); if (ret < 0) return ret; - for (i = 0; i < ARRAY_SIZE(ebt_ops_nat); i++) - if ((ret = nf_register_hook(&ebt_ops_nat[i])) < 0) - goto cleanup; - return ret; -cleanup: - for (j = 0; j < i; j++) - nf_unregister_hook(&ebt_ops_nat[j]); - ebt_unregister_table(&frame_nat); + ret = nf_register_hooks(ebt_ops_nat, ARRAY_SIZE(ebt_ops_nat)); + if (ret < 0) + ebt_unregister_table(&frame_nat); return ret; } static void __exit ebtable_nat_fini(void) { - int i; - - for (i = 0; i < ARRAY_SIZE(ebt_ops_nat); i++) - nf_unregister_hook(&ebt_ops_nat[i]); + nf_unregister_hooks(ebt_ops_nat, ARRAY_SIZE(ebt_ops_nat)); ebt_unregister_table(&frame_nat); } diff --git a/net/compat.c b/net/compat.c index 6e1b03b51933..67fb6a3834a3 100644 --- a/net/compat.c +++ b/net/compat.c @@ -722,9 +722,10 @@ EXPORT_SYMBOL(compat_mc_getsockopt); /* Argument list sizes for compat_sys_socketcall */ #define AL(x) ((x) * sizeof(u32)) -static unsigned char nas[18]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), +static unsigned char nas[19]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), AL(3),AL(3),AL(4),AL(4),AL(4),AL(6), - AL(6),AL(2),AL(5),AL(5),AL(3),AL(3)}; + AL(6),AL(2),AL(5),AL(5),AL(3),AL(3), + AL(6)}; #undef AL asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags) @@ -737,13 +738,52 @@ asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, uns return sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } +asmlinkage long compat_sys_paccept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize, int flags) +{ + compat_sigset_t ss32; + sigset_t ksigmask, sigsaved; + int ret; + + if (sigmask) { + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + if (copy_from_user(&ss32, sigmask, sizeof(ss32))) + return -EFAULT; + sigset_from_compat(&ksigmask, &ss32); + + sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + } + + ret = do_accept(fd, upeer_sockaddr, upeer_addrlen, flags); + + if (ret == -ERESTARTNOHAND) { + /* + * Don't restore the signal mask yet. Let do_signal() deliver + * the signal on the way back to userspace, before the signal + * mask is restored. + */ + if (sigmask) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_restore_sigmask(); + } + } else if (sigmask) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + + return ret; +} + asmlinkage long compat_sys_socketcall(int call, u32 __user *args) { int ret; u32 a[6]; u32 a0, a1; - if (call < SYS_SOCKET || call > SYS_RECVMSG) + if (call < SYS_SOCKET || call > SYS_PACCEPT) return -EINVAL; if (copy_from_user(a, args, nas[call])) return -EFAULT; @@ -764,7 +804,7 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args) ret = sys_listen(a0, a1); break; case SYS_ACCEPT: - ret = sys_accept(a0, compat_ptr(a1), compat_ptr(a[2])); + ret = do_accept(a0, compat_ptr(a1), compat_ptr(a[2]), 0); break; case SYS_GETSOCKNAME: ret = sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2])); @@ -804,6 +844,10 @@ asmlinkage long compat_sys_socketcall(int call, u32 __user *args) case SYS_RECVMSG: ret = compat_sys_recvmsg(a0, compat_ptr(a1), a[2]); break; + case SYS_PACCEPT: + ret = compat_sys_paccept(a0, compat_ptr(a1), compat_ptr(a[2]), + compat_ptr(a[3]), a[4], a[5]); + break; default: ret = -EINVAL; break; diff --git a/net/core/datagram.c b/net/core/datagram.c index 8a28fc93b724..52f577a0f544 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -285,7 +285,7 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + skb_shinfo(skb)->frags[i].size; if ((copy = end - offset) > 0) { @@ -315,7 +315,7 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, for (; list; list = list->next) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + list->len; if ((copy = end - offset) > 0) { @@ -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) @@ -366,7 +453,7 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + skb_shinfo(skb)->frags[i].size; if ((copy = end - offset) > 0) { @@ -402,7 +489,7 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, for (; list; list=list->next) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + list->len; if ((copy = end - offset) > 0) { diff --git a/net/core/dev.c b/net/core/dev.c index cbc34c0db376..60c51f765887 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -261,7 +261,7 @@ static RAW_NOTIFIER_HEAD(netdev_chain); DEFINE_PER_CPU(struct softnet_data, softnet_data); -#ifdef CONFIG_DEBUG_LOCK_ALLOC +#ifdef CONFIG_LOCKDEP /* * register_netdevice() inits txq->_xmit_lock and sets lockdep class * according to dev->type @@ -301,6 +301,7 @@ static const char *netdev_lock_name[] = "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; +static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; static inline unsigned short netdev_lock_pos(unsigned short dev_type) { @@ -313,8 +314,8 @@ static inline unsigned short netdev_lock_pos(unsigned short dev_type) return ARRAY_SIZE(netdev_lock_type) - 1; } -static inline void netdev_set_lockdep_class(spinlock_t *lock, - unsigned short dev_type) +static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, + unsigned short dev_type) { int i; @@ -322,9 +323,22 @@ static inline void netdev_set_lockdep_class(spinlock_t *lock, lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], netdev_lock_name[i]); } + +static inline void netdev_set_addr_lockdep_class(struct net_device *dev) +{ + int i; + + i = netdev_lock_pos(dev->type); + lockdep_set_class_and_name(&dev->addr_list_lock, + &netdev_addr_lock_key[i], + netdev_lock_name[i]); +} #else -static inline void netdev_set_lockdep_class(spinlock_t *lock, - unsigned short dev_type) +static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, + unsigned short dev_type) +{ +} +static inline void netdev_set_addr_lockdep_class(struct net_device *dev) { } #endif @@ -1325,22 +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 (WARN_ON_ONCE(q == &noop_qdisc)) - return; + struct softnet_data *sd; + unsigned long flags; - if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) { - 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); @@ -1645,32 +1660,6 @@ out_kfree_skb: return 0; } -/** - * dev_queue_xmit - transmit a buffer - * @skb: buffer to transmit - * - * Queue a buffer for transmission to a network device. The caller must - * have set the device and priority and built the buffer before calling - * this function. The function can be called from an interrupt. - * - * A negative errno code is returned on a failure. A success does not - * guarantee the frame will be transmitted as it may be dropped due - * to congestion or traffic shaping. - * - * ----------------------------------------------------------------------------------- - * I notice this method can also return errors from the queue disciplines, - * including NET_XMIT_DROP, which is a positive value. So, errors can also - * be positive. - * - * Regardless of the return value, the skb is consumed, so it is currently - * difficult to retry a send to this method. (You can bump the ref count - * before sending to hold a reference for retry if you are careful.) - * - * When calling this method, interrupts MUST be enabled. This is because - * the BH enable code must have IRQs enabled so that it will not deadlock. - * --BLG - */ - static u32 simple_tx_hashrnd; static int simple_tx_hashrnd_initialized = 0; @@ -1738,6 +1727,31 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, return netdev_get_tx_queue(dev, queue_index); } +/** + * dev_queue_xmit - transmit a buffer + * @skb: buffer to transmit + * + * Queue a buffer for transmission to a network device. The caller must + * have set the device and priority and built the buffer before calling + * this function. The function can be called from an interrupt. + * + * A negative errno code is returned on a failure. A success does not + * guarantee the frame will be transmitted as it may be dropped due + * to congestion or traffic shaping. + * + * ----------------------------------------------------------------------------------- + * I notice this method can also return errors from the queue disciplines, + * including NET_XMIT_DROP, which is a positive value. So, errors can also + * be positive. + * + * Regardless of the return value, the skb is consumed, so it is currently + * difficult to retry a send to this method. (You can bump the ref count + * before sending to hold a reference for retry if you are careful.) + * + * When calling this method, interrupts MUST be enabled. This is because + * the BH enable code must have IRQs enabled so that it will not deadlock. + * --BLG + */ int dev_queue_xmit(struct sk_buff *skb) { struct net_device *dev = skb->dev; @@ -1786,16 +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; } @@ -1899,7 +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; @@ -1931,22 +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); @@ -1963,7 +1963,7 @@ static void net_tx_action(struct softirq_action *h) struct sk_buff *skb = clist; clist = clist->next; - BUG_TRAP(!atomic_read(&skb->users)); + WARN_ON(atomic_read(&skb->users)); __kfree_skb(skb); } } @@ -1982,15 +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); } } } @@ -2090,9 +2092,10 @@ static int ing_filter(struct sk_buff *skb) rxq = &dev->rx_queue; q = rxq->qdisc; - if (q) { + 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)); } @@ -2103,7 +2106,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { - if (!skb->dev->rx_queue.qdisc) + if (skb->dev->rx_queue.qdisc == &noop_qdisc) goto out; if (*pt_prev) { @@ -2173,6 +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; @@ -2186,10 +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++; @@ -2213,7 +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; @@ -2238,7 +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; @@ -2260,6 +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; @@ -2269,7 +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); @@ -2278,14 +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; @@ -2385,7 +2403,7 @@ out: */ if (!cpus_empty(net_dma.channel_mask)) { int chan_idx; - for_each_cpu_mask(chan_idx, net_dma.channel_mask) { + for_each_cpu_mask_nr(chan_idx, net_dma.channel_mask) { struct dma_chan *chan = net_dma.channels[chan_idx]; if (chan) dma_async_memcpy_issue_pending(chan); @@ -3837,7 +3855,7 @@ static void rollback_registered(struct net_device *dev) dev->uninit(dev); /* Notifier chain MUST detach us from master device. */ - BUG_TRAP(!dev->master); + WARN_ON(dev->master); /* Remove entries from kobject tree */ netdev_unregister_kobject(dev); @@ -3852,7 +3870,7 @@ static void __netdev_init_queue_locks_one(struct net_device *dev, void *_unused) { spin_lock_init(&dev_queue->_xmit_lock); - netdev_set_lockdep_class(&dev_queue->_xmit_lock, dev->type); + netdev_set_xmit_lockdep_class(&dev_queue->_xmit_lock, dev->type); dev_queue->xmit_lock_owner = -1; } @@ -3897,6 +3915,7 @@ int register_netdevice(struct net_device *dev) net = dev_net(dev); spin_lock_init(&dev->addr_list_lock); + netdev_set_addr_lockdep_class(dev); netdev_init_queue_locks(dev); dev->iflink = -1; @@ -3977,6 +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) @@ -4154,13 +4177,15 @@ void netdev_run_todo(void) dev->reg_state = NETREG_UNREGISTERED; + on_each_cpu(flush_backlog, dev, 1); + netdev_wait_allrefs(dev); /* paranoia */ BUG_ON(atomic_read(&dev->refcnt)); - BUG_TRAP(!dev->ip_ptr); - BUG_TRAP(!dev->ip6_ptr); - BUG_TRAP(!dev->dn_ptr); + WARN_ON(dev->ip_ptr); + WARN_ON(dev->ip6_ptr); + WARN_ON(dev->dn_ptr); if (dev->destructor) dev->destructor(dev); @@ -4189,6 +4214,7 @@ static void netdev_init_queues(struct net_device *dev) { netdev_init_one_queue(dev, &dev->rx_queue, NULL); netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); + spin_lock_init(&dev->tx_global_lock); } /** @@ -4207,7 +4233,7 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, { struct netdev_queue *tx; struct net_device *dev; - int alloc_size; + size_t alloc_size; void *p; BUG_ON(strlen(name) >= sizeof(dev->name)); @@ -4227,7 +4253,7 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, return NULL; } - tx = kzalloc(sizeof(struct netdev_queue) * queue_count, GFP_KERNEL); + tx = kcalloc(queue_count, sizeof(struct netdev_queue), GFP_KERNEL); if (!tx) { printk(KERN_ERR "alloc_netdev: Unable to allocate " "tx qdiscs.\n"); @@ -4519,7 +4545,7 @@ static void net_dma_rebalance(struct net_dma *net_dma) i = 0; cpu = first_cpu(cpu_online_map); - for_each_cpu_mask(chan_idx, net_dma->channel_mask) { + for_each_cpu_mask_nr(chan_idx, net_dma->channel_mask) { chan = net_dma->channels[chan_idx]; n = ((num_online_cpus() / cpus_weight(net_dma->channel_mask)) @@ -4686,6 +4712,26 @@ err_name: return -ENOMEM; } +char *netdev_drivername(struct net_device *dev, char *buffer, int len) +{ + struct device_driver *driver; + struct device *parent; + + if (len <= 0 || !buffer) + return buffer; + buffer[0] = 0; + + parent = dev->dev.parent; + + if (!parent) + return buffer; + + driver = parent->driver; + if (driver && driver->name) + strlcpy(buffer, driver->name, len); + return buffer; +} + static void __net_exit netdev_exit(struct net *net) { kfree(net->dev_name_head); 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/netpoll.c b/net/core/netpoll.c index c12720895ecf..6c7af390be0a 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -70,6 +70,7 @@ static void queue_process(struct work_struct *work) local_irq_save(flags); __netif_tx_lock(txq, smp_processor_id()); if (netif_tx_queue_stopped(txq) || + netif_tx_queue_frozen(txq) || dev->hard_start_xmit(skb, dev) != NETDEV_TX_OK) { skb_queue_head(&npinfo->txq, skb); __netif_tx_unlock(txq); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index c7d484f7e1c4..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; } @@ -3305,6 +3369,7 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) txq = netdev_get_tx_queue(odev, queue_map); if (netif_tx_queue_stopped(txq) || + netif_tx_queue_frozen(txq) || need_resched()) { idle_start = getCurUs(); @@ -3320,7 +3385,8 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->idle_acc += getCurUs() - idle_start; - if (netif_tx_queue_stopped(txq)) { + if (netif_tx_queue_stopped(txq) || + netif_tx_queue_frozen(txq)) { pkt_dev->next_tx_us = getCurUs(); /* TODO */ pkt_dev->next_tx_ns = 0; goto out; /* Try the next interface */ @@ -3352,7 +3418,8 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) txq = netdev_get_tx_queue(odev, queue_map); __netif_tx_lock_bh(txq); - if (!netif_tx_queue_stopped(txq)) { + if (!netif_tx_queue_stopped(txq) && + !netif_tx_queue_frozen(txq)) { atomic_inc(&(pkt_dev->skb->users)); retry_now: diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 2d3035d3abd7..7552495aff7a 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -123,7 +123,7 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) } } - BUG_TRAP(lopt->qlen == 0); + WARN_ON(lopt->qlen != 0); if (lopt_size > PAGE_SIZE) vfree(lopt); else diff --git a/net/core/skbuff.c b/net/core/skbuff.c index e4115672b6cf..ca1ccdf1ef76 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -485,6 +485,9 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) C(head); C(data); C(truesize); +#if defined(CONFIG_MAC80211) || defined(CONFIG_MAC80211_MODULE) + C(do_not_encrypt); +#endif atomic_set(&n->users, 1); atomic_inc(&(skb_shinfo(skb)->dataref)); @@ -1200,7 +1203,7 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + skb_shinfo(skb)->frags[i].size; if ((copy = end - offset) > 0) { @@ -1229,7 +1232,7 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) for (; list; list = list->next) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + list->len; if ((copy = end - offset) > 0) { @@ -1475,7 +1478,7 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + frag->size; if ((copy = end - offset) > 0) { @@ -1503,7 +1506,7 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) for (; list; list = list->next) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + list->len; if ((copy = end - offset) > 0) { @@ -1552,7 +1555,7 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + skb_shinfo(skb)->frags[i].size; if ((copy = end - offset) > 0) { @@ -1581,7 +1584,7 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, for (; list; list = list->next) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + list->len; if ((copy = end - offset) > 0) { @@ -1629,7 +1632,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + skb_shinfo(skb)->frags[i].size; if ((copy = end - offset) > 0) { @@ -1662,7 +1665,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, __wsum csum2; int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + list->len; if ((copy = end - offset) > 0) { @@ -2253,14 +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); @@ -2271,6 +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); @@ -2280,8 +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); @@ -2373,7 +2368,7 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + skb_shinfo(skb)->frags[i].size; if ((copy = end - offset) > 0) { @@ -2397,7 +2392,7 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) for (; list; list = list->next) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + list->len; if ((copy = end - offset) > 0) { diff --git a/net/core/sock.c b/net/core/sock.c index 10a64d57078c..91f8bbc93526 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -180,7 +180,7 @@ static const char *af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_ASH" , "clock-AF_ECONET" , "clock-AF_ATMSVC" , "clock-21" , "clock-AF_SNA" , "clock-AF_IRDA" , "clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" , - "clock-27" , "clock-28" , "clock-29" , + "clock-27" , "clock-28" , "clock-AF_CAN" , "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , "clock-AF_RXRPC" , "clock-AF_MAX" }; diff --git a/net/core/stream.c b/net/core/stream.c index 4a0ad152c9c4..a6b3437ff082 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -192,13 +192,13 @@ void sk_stream_kill_queues(struct sock *sk) __skb_queue_purge(&sk->sk_error_queue); /* Next, the write queue. */ - BUG_TRAP(skb_queue_empty(&sk->sk_write_queue)); + WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); /* Account for returned memory. */ sk_mem_reclaim(sk); - BUG_TRAP(!sk->sk_wmem_queued); - BUG_TRAP(!sk->sk_forward_alloc); + WARN_ON(sk->sk_wmem_queued); + WARN_ON(sk->sk_forward_alloc); /* It is _impossible_ for the backlog to contain anything * when we get here. All user references to this socket diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index a570e2af22cb..f686467ff12b 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -67,7 +67,7 @@ static struct ctl_table net_core_table[] = { { .ctl_name = NET_CORE_MSG_COST, .procname = "message_cost", - .data = &net_msg_cost, + .data = &net_ratelimit_state.interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = &proc_dointvec_jiffies, @@ -76,7 +76,7 @@ static struct ctl_table net_core_table[] = { { .ctl_name = NET_CORE_MSG_BURST, .procname = "message_burst", - .data = &net_msg_burst, + .data = &net_ratelimit_state.burst, .maxlen = sizeof(int), .mode = 0644, .proc_handler = &proc_dointvec, diff --git a/net/core/user_dma.c b/net/core/user_dma.c index c77aff9c6eb3..164b090d5ac3 100644 --- a/net/core/user_dma.c +++ b/net/core/user_dma.c @@ -27,13 +27,13 @@ #include <linux/dmaengine.h> #include <linux/socket.h> -#include <linux/rtnetlink.h> /* for BUG_TRAP */ #include <net/tcp.h> #include <net/netdma.h> #define NET_DMA_DEFAULT_COPYBREAK 4096 int sysctl_tcp_dma_copybreak = NET_DMA_DEFAULT_COPYBREAK; +EXPORT_SYMBOL(sysctl_tcp_dma_copybreak); /** * dma_skb_copy_datagram_iovec - Copy a datagram to an iovec. @@ -71,7 +71,7 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + skb_shinfo(skb)->frags[i].size; copy = end - offset; @@ -100,7 +100,7 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, for (; list; list = list->next) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + list->len; copy = end - offset; diff --git a/net/core/utils.c b/net/core/utils.c index 8031eb59054e..72e0ebe964a0 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -31,17 +31,16 @@ #include <asm/system.h> #include <asm/uaccess.h> -int net_msg_cost __read_mostly = 5*HZ; -int net_msg_burst __read_mostly = 10; int net_msg_warn __read_mostly = 1; EXPORT_SYMBOL(net_msg_warn); +DEFINE_RATELIMIT_STATE(net_ratelimit_state, 5 * HZ, 10); /* * All net warning printk()s should be guarded by this function. */ int net_ratelimit(void) { - return __printk_ratelimit(net_msg_cost, net_msg_burst); + return __ratelimit(&net_ratelimit_state); } EXPORT_SYMBOL(net_ratelimit); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 32617e0576cb..b4bc6e095a0e 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -164,7 +164,7 @@ static inline bool dccp_loss_free(const u64 s1, const u64 s2, const u64 ndp) { s64 delta = dccp_delta_seqno(s1, s2); - BUG_TRAP(delta >= 0); + WARN_ON(delta < 0); return (u64)delta <= ndp + 1; } @@ -226,10 +226,11 @@ static inline void dccp_csum_outgoing(struct sk_buff *skb) extern void dccp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb); -extern int dccp_retransmit_skb(struct sock *sk, 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 08392ed86c25..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); - BUG_TRAP(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/ipv4.c b/net/dccp/ipv4.c index 2622ace17c46..882c5c4de69e 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -196,8 +196,8 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk, static void dccp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (struct iphdr *)skb->data; - const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + - (iph->ihl << 2)); + const u8 offset = iph->ihl << 2; + const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); struct dccp_sock *dp; struct inet_sock *inet; const int type = icmp_hdr(skb)->type; @@ -207,7 +207,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) int err; struct net *net = dev_net(skb->dev); - if (skb->len < (iph->ihl << 2) + 8) { + if (skb->len < offset + sizeof(*dh) || + skb->len < offset + __dccp_basic_hdr_len(dh)) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } @@ -238,7 +239,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) dp = dccp_sk(sk); seq = dccp_hdr_seq(dh); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && - !between48(seq, dp->dccps_swl, dp->dccps_swh)) { + !between48(seq, dp->dccps_awl, dp->dccps_awh)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -283,7 +284,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) * ICMPs are not backlogged, hence we cannot get an established * socket here. */ - BUG_TRAP(!req->sk); + WARN_ON(req->sk); if (seq != dccp_rsk(req)->dreq_iss) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index b74e8b2cbe55..5e1ee0da2c40 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -89,12 +89,19 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, { struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); + struct dccp_sock *dp; struct ipv6_pinfo *np; struct sock *sk; int err; __u64 seq; struct net *net = dev_net(skb->dev); + if (skb->len < offset + sizeof(*dh) || + skb->len < offset + __dccp_basic_hdr_len(dh)) { + ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); + return; + } + sk = inet6_lookup(net, &dccp_hashinfo, &hdr->daddr, dh->dccph_dport, &hdr->saddr, dh->dccph_sport, inet6_iif(skb)); @@ -116,6 +123,14 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (sk->sk_state == DCCP_CLOSED) goto out; + dp = dccp_sk(sk); + seq = dccp_hdr_seq(dh); + if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && + !between48(seq, dp->dccps_awl, dp->dccps_awh)) { + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); + goto out; + } + np = inet6_sk(sk); if (type == ICMPV6_PKT_TOOBIG) { @@ -168,7 +183,6 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, icmpv6_err_convert(type, code, &err); - seq = dccp_hdr_seq(dh); /* Might be for an request_sock */ switch (sk->sk_state) { struct request_sock *req, **prev; @@ -186,7 +200,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, * ICMPs are not backlogged, hence we cannot get an established * socket here. */ - BUG_TRAP(req->sk == NULL); + WARN_ON(req->sk != NULL); if (seq != dccp_rsk(req)->dreq_iss) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); 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/output.c b/net/dccp/output.c index fe20068c5d8e..d06945c7d3df 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -53,8 +53,11 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) dccp_packet_hdr_len(dcb->dccpd_type); int err, set_ack = 1; u64 ackno = dp->dccps_gsr; - - dccp_inc_seqno(&dp->dccps_gss); + /* + * Increment GSS here already in case the option code needs it. + * Update GSS for real only if option processing below succeeds. + */ + dcb->dccpd_seq = ADD48(dp->dccps_gss, 1); switch (dcb->dccpd_type) { case DCCP_PKT_DATA: @@ -66,6 +69,9 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) case DCCP_PKT_REQUEST: set_ack = 0; + /* Use ISS on the first (non-retransmitted) Request. */ + if (icsk->icsk_retransmits == 0) + dcb->dccpd_seq = dp->dccps_iss; /* fall through */ case DCCP_PKT_SYNC: @@ -84,8 +90,6 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) break; } - dcb->dccpd_seq = dp->dccps_gss; - if (dccp_insert_options(sk, skb)) { kfree_skb(skb); return -EPROTO; @@ -103,7 +107,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) /* XXX For now we're using only 48 bits sequence numbers */ dh->dccph_x = 1; - dp->dccps_awh = dp->dccps_gss; + dccp_update_gss(sk, dcb->dccpd_seq); dccp_hdr_set_seq(dh, dp->dccps_gss); if (set_ack) dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno); @@ -112,6 +116,11 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) case DCCP_PKT_REQUEST: dccp_hdr_request(skb)->dccph_req_service = dp->dccps_service; + /* + * Limit Ack window to ISS <= P.ackno <= GSS, so that + * only Responses to Requests we sent are considered. + */ + dp->dccps_awl = dp->dccps_iss; break; case DCCP_PKT_RESET: dccp_hdr_reset(skb)->dccph_reset_code = @@ -284,14 +293,26 @@ void dccp_write_xmit(struct sock *sk, int block) } } -int dccp_retransmit_skb(struct sock *sk, struct sk_buff *skb) +/** + * dccp_retransmit_skb - Retransmit Request, Close, or CloseReq packets + * There are only four retransmittable packet types in DCCP: + * - Request in client-REQUEST state (sec. 8.1.1), + * - CloseReq in server-CLOSEREQ state (sec. 8.3), + * - Close in node-CLOSING state (sec. 8.3), + * - Acks in client-PARTOPEN state (sec. 8.1.5, handled by dccp_delack_timer()). + * This function expects sk->sk_send_head to contain the original skb. + */ +int dccp_retransmit_skb(struct sock *sk) { + WARN_ON(sk->sk_send_head == NULL); + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk) != 0) return -EHOSTUNREACH; /* Routing failure or similar. */ - return dccp_transmit_skb(sk, (skb_cloned(skb) ? - pskb_copy(skb, GFP_ATOMIC): - skb_clone(skb, GFP_ATOMIC))); + /* this count is used to distinguish original and retransmitted skb */ + inet_csk(sk)->icsk_retransmits++; + + return dccp_transmit_skb(sk, skb_clone(sk->sk_send_head, GFP_ATOMIC)); } struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, @@ -437,19 +458,7 @@ static inline void dccp_connect_init(struct sock *sk) dccp_sync_mss(sk, dst_mtu(dst)); - /* - * SWL and AWL are initially adjusted so that they are not less than - * the initial Sequence Numbers received and sent, respectively: - * SWL := max(GSR + 1 - floor(W/4), ISR), - * AWL := max(GSS - W' + 1, ISS). - * These adjustments MUST be applied only at the beginning of the - * connection. - */ - dccp_update_gss(sk, dp->dccps_iss); - dccp_set_seqno(&dp->dccps_awl, max48(dp->dccps_awl, dp->dccps_iss)); - - /* S.GAR - greatest valid acknowledgement number received on a non-Sync; - * initialized to S.ISS (sec. 8.5) */ + /* Initialise GAR as per 8.5; AWL/AWH are set in dccp_transmit_skb() */ dp->dccps_gar = dp->dccps_iss; icsk->icsk_retransmits = 0; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index a0b56009611f..1ca3b26eed0f 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -327,7 +327,7 @@ int dccp_disconnect(struct sock *sk, int flags) inet_csk_delack_init(sk); __sk_dst_reset(sk); - BUG_TRAP(!inet->num || icsk->icsk_bind_hash); + WARN_ON(inet->num && !icsk->icsk_bind_hash); sk->sk_error_report(sk); return err; @@ -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) @@ -981,7 +986,7 @@ adjudge_to_death: */ local_bh_disable(); bh_lock_sock(sk); - BUG_TRAP(!sock_owned_by_user(sk)); + WARN_ON(sock_owned_by_user(sk)); /* Have we already been destroyed by a softirq or backlog? */ if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED) diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 3608d5342ca2..54b3c7e9e016 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -99,21 +99,11 @@ static void dccp_retransmit_timer(struct sock *sk) } /* - * sk->sk_send_head has to have one skb with - * DCCP_SKB_CB(skb)->dccpd_type set to one of the retransmittable DCCP - * packet types. The only packets eligible for retransmission are: - * -- Requests in client-REQUEST state (sec. 8.1.1) - * -- Acks in client-PARTOPEN state (sec. 8.1.5) - * -- CloseReq in server-CLOSEREQ state (sec. 8.3) - * -- Close in node-CLOSING state (sec. 8.3) */ - BUG_TRAP(sk->sk_send_head != NULL); - - /* * More than than 4MSL (8 minutes) has passed, a RESET(aborted) was * sent, no need to retransmit, this sock is dead. */ if (dccp_write_timeout(sk)) - goto out; + return; /* * We want to know the number of packets retransmitted, not the @@ -122,30 +112,28 @@ static void dccp_retransmit_timer(struct sock *sk) if (icsk->icsk_retransmits == 0) DCCP_INC_STATS_BH(DCCP_MIB_TIMEOUTS); - if (dccp_retransmit_skb(sk, sk->sk_send_head) < 0) { + if (dccp_retransmit_skb(sk) != 0) { /* * Retransmission failed because of local congestion, * do not backoff. */ - if (icsk->icsk_retransmits == 0) + if (--icsk->icsk_retransmits == 0) icsk->icsk_retransmits = 1; inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, min(icsk->icsk_rto, TCP_RESOURCE_PROBE_INTERVAL), DCCP_RTO_MAX); - goto out; + return; } backoff: icsk->icsk_backoff++; - icsk->icsk_retransmits++; icsk->icsk_rto = min(icsk->icsk_rto << 1, DCCP_RTO_MAX); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, DCCP_RTO_MAX); if (icsk->icsk_retransmits > sysctl_dccp_retries1) __sk_dst_reset(sk); -out:; } static void dccp_write_timer(unsigned long data) diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 4670683b4688..591ea23639ca 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -356,10 +356,8 @@ config INET_ESP config INET_IPCOMP tristate "IP: IPComp transformation" - select XFRM select INET_XFRM_TUNNEL - select CRYPTO - select CRYPTO_DEFLATE + select XFRM_IPCOMP ---help--- Support for IP Payload Compression Protocol (IPComp) (RFC3173), typically needed for IPsec. diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index dd919d84285f..8a3ac1fa71a9 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -148,10 +148,10 @@ void inet_sock_destruct(struct sock *sk) return; } - BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc)); - BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc)); - BUG_TRAP(!sk->sk_wmem_queued); - BUG_TRAP(!sk->sk_forward_alloc); + WARN_ON(atomic_read(&sk->sk_rmem_alloc)); + WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(sk->sk_wmem_queued); + WARN_ON(sk->sk_forward_alloc); kfree(inet->opt); dst_release(sk->sk_dst_cache); @@ -264,7 +264,6 @@ static inline int inet_netns_ok(struct net *net, int protocol) static int inet_create(struct net *net, struct socket *sock, int protocol) { struct sock *sk; - struct list_head *p; struct inet_protosw *answer; struct inet_sock *inet; struct proto *answer_prot; @@ -281,13 +280,12 @@ static int inet_create(struct net *net, struct socket *sock, int protocol) sock->state = SS_UNCONNECTED; /* Look for the requested type/protocol pair. */ - answer = NULL; lookup_protocol: err = -ESOCKTNOSUPPORT; rcu_read_lock(); - list_for_each_rcu(p, &inetsw[sock->type]) { - answer = list_entry(p, struct inet_protosw, list); + list_for_each_entry_rcu(answer, &inetsw[sock->type], list) { + err = 0; /* Check the non-wild match. */ if (protocol == answer->protocol) { if (protocol != IPPROTO_IP) @@ -302,10 +300,9 @@ lookup_protocol: break; } err = -EPROTONOSUPPORT; - answer = NULL; } - if (unlikely(answer == NULL)) { + if (unlikely(err)) { if (try_loading_module < 2) { rcu_read_unlock(); /* @@ -341,7 +338,7 @@ lookup_protocol: answer_flags = answer->flags; rcu_read_unlock(); - BUG_TRAP(answer_prot->slab != NULL); + WARN_ON(answer_prot->slab == NULL); err = -ENOBUFS; sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot); @@ -661,8 +658,8 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags) lock_sock(sk2); - BUG_TRAP((1 << sk2->sk_state) & - (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE)); + WARN_ON(!((1 << sk2->sk_state) & + (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE))); sock_graft(sk2, newsock); @@ -1442,6 +1439,10 @@ static int __init inet_init(void) (void)sock_register(&inet_family_ops); +#ifdef CONFIG_SYSCTL + ip_static_sysctl_init(); +#endif + /* * Add all the base protocols. */ diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 2e667e2f90df..91d3d96805d0 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -138,8 +138,8 @@ void in_dev_finish_destroy(struct in_device *idev) { struct net_device *dev = idev->dev; - BUG_TRAP(!idev->ifa_list); - BUG_TRAP(!idev->mc_list); + WARN_ON(idev->ifa_list); + WARN_ON(idev->mc_list); #ifdef NET_REFCNT_DEBUG printk(KERN_DEBUG "in_dev_finish_destroy: %p=%s\n", idev, dev ? dev->name : "NIL"); @@ -399,7 +399,7 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) } ipv4_devconf_setall(in_dev); if (ifa->ifa_dev != in_dev) { - BUG_TRAP(!ifa->ifa_dev); + WARN_ON(ifa->ifa_dev); in_dev_hold(in_dev); ifa->ifa_dev = in_dev; } 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/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/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index bb81c958b744..0c1ae68ee84b 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -167,7 +167,7 @@ tb_not_found: success: if (!inet_csk(sk)->icsk_bind_hash) inet_bind_hash(sk, tb, snum); - BUG_TRAP(inet_csk(sk)->icsk_bind_hash == tb); + WARN_ON(inet_csk(sk)->icsk_bind_hash != tb); ret = 0; fail_unlock: @@ -260,7 +260,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) } newsk = reqsk_queue_get_child(&icsk->icsk_accept_queue, sk); - BUG_TRAP(newsk->sk_state != TCP_SYN_RECV); + WARN_ON(newsk->sk_state == TCP_SYN_RECV); out: release_sock(sk); return newsk; @@ -386,7 +386,7 @@ struct request_sock *inet_csk_search_req(const struct sock *sk, ireq->rmt_addr == raddr && ireq->loc_addr == laddr && AF_INET_FAMILY(req->rsk_ops->family)) { - BUG_TRAP(!req->sk); + WARN_ON(req->sk); *prevp = prev; break; } @@ -539,14 +539,14 @@ EXPORT_SYMBOL_GPL(inet_csk_clone); */ void inet_csk_destroy_sock(struct sock *sk) { - BUG_TRAP(sk->sk_state == TCP_CLOSE); - BUG_TRAP(sock_flag(sk, SOCK_DEAD)); + WARN_ON(sk->sk_state != TCP_CLOSE); + WARN_ON(!sock_flag(sk, SOCK_DEAD)); /* It cannot be in hash table! */ - BUG_TRAP(sk_unhashed(sk)); + WARN_ON(!sk_unhashed(sk)); /* If it has not 0 inet_sk(sk)->num, it must be bound */ - BUG_TRAP(!inet_sk(sk)->num || inet_csk(sk)->icsk_bind_hash); + WARN_ON(inet_sk(sk)->num && !inet_csk(sk)->icsk_bind_hash); sk->sk_prot->destroy(sk); @@ -629,7 +629,7 @@ void inet_csk_listen_stop(struct sock *sk) local_bh_disable(); bh_lock_sock(child); - BUG_TRAP(!sock_owned_by_user(child)); + WARN_ON(sock_owned_by_user(child)); sock_hold(child); sk->sk_prot->disconnect(child, O_NONBLOCK); @@ -647,7 +647,7 @@ void inet_csk_listen_stop(struct sock *sk) sk_acceptq_removed(sk); __reqsk_free(req); } - BUG_TRAP(!sk->sk_ack_backlog); + WARN_ON(sk->sk_ack_backlog); } EXPORT_SYMBOL_GPL(inet_csk_listen_stop); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 0546a0bc97ea..6c52e08f786e 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -134,8 +134,8 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f, struct sk_buff *fp; struct netns_frags *nf; - BUG_TRAP(q->last_in & INET_FRAG_COMPLETE); - BUG_TRAP(del_timer(&q->timer) == 0); + WARN_ON(!(q->last_in & INET_FRAG_COMPLETE)); + WARN_ON(del_timer(&q->timer) != 0); /* Release all fragment data. */ fp = q->fragments; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 115f53722d20..44981906fb91 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -305,7 +305,7 @@ unique: inet->num = lport; inet->sport = htons(lport); sk->sk_hash = hash; - BUG_TRAP(sk_unhashed(sk)); + WARN_ON(!sk_unhashed(sk)); __sk_add_node(sk, &head->chain); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); write_unlock(lock); @@ -342,7 +342,7 @@ void __inet_hash_nolisten(struct sock *sk) rwlock_t *lock; struct inet_ehash_bucket *head; - BUG_TRAP(sk_unhashed(sk)); + WARN_ON(!sk_unhashed(sk)); sk->sk_hash = inet_sk_ehashfn(sk); head = inet_ehash_bucket(hashinfo, sk->sk_hash); @@ -367,7 +367,7 @@ static void __inet_hash(struct sock *sk) return; } - BUG_TRAP(sk_unhashed(sk)); + WARN_ON(!sk_unhashed(sk)); list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; lock = &hashinfo->lhash_lock; @@ -450,7 +450,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, */ inet_bind_bucket_for_each(tb, node, &head->chain) { if (tb->ib_net == net && tb->port == port) { - BUG_TRAP(!hlist_empty(&tb->owners)); + WARN_ON(hlist_empty(&tb->owners)); if (tb->fastreuse >= 0) goto next_port; if (!check_established(death_row, sk, diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 75c2def8f9a0..d985bd613d25 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -86,7 +86,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, hashinfo->bhash_size)]; spin_lock(&bhead->lock); tw->tw_tb = icsk->icsk_bind_hash; - BUG_TRAP(icsk->icsk_bind_hash); + WARN_ON(!icsk->icsk_bind_hash); inet_twsk_add_bind_node(tw, &tw->tw_tb->owners); spin_unlock(&bhead->lock); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 38d38f058018..2152d222b954 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -488,8 +488,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, qp->q.fragments = head; } - BUG_TRAP(head != NULL); - BUG_TRAP(FRAG_CB(head)->offset == 0); + WARN_ON(head == NULL); + WARN_ON(FRAG_CB(head)->offset != 0); /* Allocate a new buffer for the datagram. */ ihlen = ip_hdrlen(head); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 465544f6281a..d533a89e08de 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -118,7 +118,7 @@ static int ip_dev_loopback_xmit(struct sk_buff *newskb) __skb_pull(newskb, skb_network_offset(newskb)); newskb->pkt_type = PACKET_LOOPBACK; newskb->ip_summed = CHECKSUM_UNNECESSARY; - BUG_TRAP(newskb->dst); + WARN_ON(!newskb->dst); netif_rx(newskb); return 0; } diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index a75807b971b3..38ccb6dfb02e 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -14,153 +14,14 @@ * - Adaptive compression. */ #include <linux/module.h> -#include <linux/crypto.h> #include <linux/err.h> -#include <linux/pfkeyv2.h> -#include <linux/percpu.h> -#include <linux/smp.h> -#include <linux/list.h> -#include <linux/vmalloc.h> #include <linux/rtnetlink.h> -#include <linux/mutex.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/icmp.h> #include <net/ipcomp.h> #include <net/protocol.h> - -struct ipcomp_tfms { - struct list_head list; - struct crypto_comp **tfms; - int users; -}; - -static DEFINE_MUTEX(ipcomp_resource_mutex); -static void **ipcomp_scratches; -static int ipcomp_scratch_users; -static LIST_HEAD(ipcomp_tfms_list); - -static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb) -{ - struct ipcomp_data *ipcd = x->data; - const int plen = skb->len; - int dlen = IPCOMP_SCRATCH_SIZE; - const u8 *start = skb->data; - const int cpu = get_cpu(); - u8 *scratch = *per_cpu_ptr(ipcomp_scratches, cpu); - struct crypto_comp *tfm = *per_cpu_ptr(ipcd->tfms, cpu); - int err = crypto_comp_decompress(tfm, start, plen, scratch, &dlen); - - if (err) - goto out; - - if (dlen < (plen + sizeof(struct ip_comp_hdr))) { - err = -EINVAL; - goto out; - } - - err = pskb_expand_head(skb, 0, dlen - plen, GFP_ATOMIC); - if (err) - goto out; - - skb->truesize += dlen - plen; - __skb_put(skb, dlen - plen); - skb_copy_to_linear_data(skb, scratch, dlen); -out: - put_cpu(); - return err; -} - -static int ipcomp_input(struct xfrm_state *x, struct sk_buff *skb) -{ - int nexthdr; - int err = -ENOMEM; - struct ip_comp_hdr *ipch; - - if (skb_linearize_cow(skb)) - goto out; - - skb->ip_summed = CHECKSUM_NONE; - - /* Remove ipcomp header and decompress original payload */ - ipch = (void *)skb->data; - nexthdr = ipch->nexthdr; - - skb->transport_header = skb->network_header + sizeof(*ipch); - __skb_pull(skb, sizeof(*ipch)); - err = ipcomp_decompress(x, skb); - if (err) - goto out; - - err = nexthdr; - -out: - return err; -} - -static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb) -{ - struct ipcomp_data *ipcd = x->data; - const int plen = skb->len; - int dlen = IPCOMP_SCRATCH_SIZE; - u8 *start = skb->data; - const int cpu = get_cpu(); - u8 *scratch = *per_cpu_ptr(ipcomp_scratches, cpu); - struct crypto_comp *tfm = *per_cpu_ptr(ipcd->tfms, cpu); - int err; - - local_bh_disable(); - err = crypto_comp_compress(tfm, start, plen, scratch, &dlen); - local_bh_enable(); - if (err) - goto out; - - if ((dlen + sizeof(struct ip_comp_hdr)) >= plen) { - err = -EMSGSIZE; - goto out; - } - - memcpy(start + sizeof(struct ip_comp_hdr), scratch, dlen); - put_cpu(); - - pskb_trim(skb, dlen + sizeof(struct ip_comp_hdr)); - return 0; - -out: - put_cpu(); - return err; -} - -static int ipcomp_output(struct xfrm_state *x, struct sk_buff *skb) -{ - int err; - struct ip_comp_hdr *ipch; - struct ipcomp_data *ipcd = x->data; - - if (skb->len < ipcd->threshold) { - /* Don't bother compressing */ - goto out_ok; - } - - if (skb_linearize_cow(skb)) - goto out_ok; - - err = ipcomp_compress(x, skb); - - if (err) { - goto out_ok; - } - - /* Install ipcomp header, convert into ipcomp datagram. */ - ipch = ip_comp_hdr(skb); - ipch->nexthdr = *skb_mac_header(skb); - ipch->flags = 0; - ipch->cpi = htons((u16 )ntohl(x->id.spi)); - *skb_mac_header(skb) = IPPROTO_COMP; -out_ok: - skb_push(skb, -skb_network_offset(skb)); - return 0; -} +#include <net/sock.h> static void ipcomp4_err(struct sk_buff *skb, u32 info) { @@ -241,155 +102,9 @@ out: return err; } -static void ipcomp_free_scratches(void) -{ - int i; - void **scratches; - - if (--ipcomp_scratch_users) - return; - - scratches = ipcomp_scratches; - if (!scratches) - return; - - for_each_possible_cpu(i) - vfree(*per_cpu_ptr(scratches, i)); - - free_percpu(scratches); -} - -static void **ipcomp_alloc_scratches(void) -{ - int i; - void **scratches; - - if (ipcomp_scratch_users++) - return ipcomp_scratches; - - scratches = alloc_percpu(void *); - if (!scratches) - return NULL; - - ipcomp_scratches = scratches; - - for_each_possible_cpu(i) { - void *scratch = vmalloc(IPCOMP_SCRATCH_SIZE); - if (!scratch) - return NULL; - *per_cpu_ptr(scratches, i) = scratch; - } - - return scratches; -} - -static void ipcomp_free_tfms(struct crypto_comp **tfms) -{ - struct ipcomp_tfms *pos; - int cpu; - - list_for_each_entry(pos, &ipcomp_tfms_list, list) { - if (pos->tfms == tfms) - break; - } - - BUG_TRAP(pos); - - if (--pos->users) - return; - - list_del(&pos->list); - kfree(pos); - - if (!tfms) - return; - - for_each_possible_cpu(cpu) { - struct crypto_comp *tfm = *per_cpu_ptr(tfms, cpu); - crypto_free_comp(tfm); - } - free_percpu(tfms); -} - -static struct crypto_comp **ipcomp_alloc_tfms(const char *alg_name) -{ - struct ipcomp_tfms *pos; - struct crypto_comp **tfms; - int cpu; - - /* This can be any valid CPU ID so we don't need locking. */ - cpu = raw_smp_processor_id(); - - list_for_each_entry(pos, &ipcomp_tfms_list, list) { - struct crypto_comp *tfm; - - tfms = pos->tfms; - tfm = *per_cpu_ptr(tfms, cpu); - - if (!strcmp(crypto_comp_name(tfm), alg_name)) { - pos->users++; - return tfms; - } - } - - pos = kmalloc(sizeof(*pos), GFP_KERNEL); - if (!pos) - return NULL; - - pos->users = 1; - INIT_LIST_HEAD(&pos->list); - list_add(&pos->list, &ipcomp_tfms_list); - - pos->tfms = tfms = alloc_percpu(struct crypto_comp *); - if (!tfms) - goto error; - - for_each_possible_cpu(cpu) { - struct crypto_comp *tfm = crypto_alloc_comp(alg_name, 0, - CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) - goto error; - *per_cpu_ptr(tfms, cpu) = tfm; - } - - return tfms; - -error: - ipcomp_free_tfms(tfms); - return NULL; -} - -static void ipcomp_free_data(struct ipcomp_data *ipcd) +static int ipcomp4_init_state(struct xfrm_state *x) { - if (ipcd->tfms) - ipcomp_free_tfms(ipcd->tfms); - ipcomp_free_scratches(); -} - -static void ipcomp_destroy(struct xfrm_state *x) -{ - struct ipcomp_data *ipcd = x->data; - if (!ipcd) - return; - xfrm_state_delete_tunnel(x); - mutex_lock(&ipcomp_resource_mutex); - ipcomp_free_data(ipcd); - mutex_unlock(&ipcomp_resource_mutex); - kfree(ipcd); -} - -static int ipcomp_init_state(struct xfrm_state *x) -{ - int err; - struct ipcomp_data *ipcd; - struct xfrm_algo_desc *calg_desc; - - err = -EINVAL; - if (!x->calg) - goto out; - - if (x->encap) - goto out; + int err = -EINVAL; x->props.header_len = 0; switch (x->props.mode) { @@ -402,40 +117,22 @@ static int ipcomp_init_state(struct xfrm_state *x) goto out; } - err = -ENOMEM; - ipcd = kzalloc(sizeof(*ipcd), GFP_KERNEL); - if (!ipcd) + err = ipcomp_init_state(x); + if (err) goto out; - mutex_lock(&ipcomp_resource_mutex); - if (!ipcomp_alloc_scratches()) - goto error; - - ipcd->tfms = ipcomp_alloc_tfms(x->calg->alg_name); - if (!ipcd->tfms) - goto error; - mutex_unlock(&ipcomp_resource_mutex); - if (x->props.mode == XFRM_MODE_TUNNEL) { err = ipcomp_tunnel_attach(x); if (err) goto error_tunnel; } - calg_desc = xfrm_calg_get_byname(x->calg->alg_name, 0); - BUG_ON(!calg_desc); - ipcd->threshold = calg_desc->uinfo.comp.threshold; - x->data = ipcd; err = 0; out: return err; error_tunnel: - mutex_lock(&ipcomp_resource_mutex); -error: - ipcomp_free_data(ipcd); - mutex_unlock(&ipcomp_resource_mutex); - kfree(ipcd); + ipcomp_destroy(x); goto out; } @@ -443,7 +140,7 @@ static const struct xfrm_type ipcomp_type = { .description = "IPCOMP4", .owner = THIS_MODULE, .proto = IPPROTO_COMP, - .init_state = ipcomp_init_state, + .init_state = ipcomp4_init_state, .destructor = ipcomp_destroy, .input = ipcomp_input, .output = ipcomp_output @@ -481,7 +178,7 @@ module_init(ipcomp4_init); module_exit(ipcomp4_fini); MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("IP Payload Compression Protocol (IPComp) - RFC3173"); +MODULE_DESCRIPTION("IP Payload Compression Protocol (IPComp/IPv4) - RFC3173"); MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_COMP); 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/Kconfig b/net/ipv4/netfilter/Kconfig index f23e60c93ef9..90eb7cb47e77 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -369,7 +369,7 @@ config IP_NF_SECURITY tristate "Security table" depends on IP_NF_IPTABLES depends on SECURITY - default m if NETFILTER_ADVANCED=n + depends on NETFILTER_ADVANCED help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 3be4d07e7ed9..082f5dd3156c 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -55,32 +55,53 @@ static struct xt_table packet_filter = { }; /* The work comes in here from netfilter.c */ -static unsigned int arpt_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) +static unsigned int arpt_in_hook(unsigned int hook, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return arpt_do_table(skb, hook, in, out, init_net.ipv4.arptable_filter); + return arpt_do_table(skb, hook, in, out, + dev_net(in)->ipv4.arptable_filter); +} + +static unsigned int arpt_out_hook(unsigned int hook, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + return arpt_do_table(skb, hook, in, out, + dev_net(out)->ipv4.arptable_filter); +} + +static unsigned int arpt_forward_hook(unsigned int hook, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + return arpt_do_table(skb, hook, in, out, + dev_net(in)->ipv4.arptable_filter); } static struct nf_hook_ops arpt_ops[] __read_mostly = { { - .hook = arpt_hook, + .hook = arpt_in_hook, .owner = THIS_MODULE, .pf = NF_ARP, .hooknum = NF_ARP_IN, .priority = NF_IP_PRI_FILTER, }, { - .hook = arpt_hook, + .hook = arpt_out_hook, .owner = THIS_MODULE, .pf = NF_ARP, .hooknum = NF_ARP_OUT, .priority = NF_IP_PRI_FILTER, }, { - .hook = arpt_hook, + .hook = arpt_forward_hook, .owner = THIS_MODULE, .pf = NF_ARP, .hooknum = NF_ARP_FORWARD, diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 1819ad7ab910..fafe8ebb4c55 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -475,11 +475,10 @@ static void arp_print(struct arp_payload *payload) #define HBUFFERLEN 30 char hbuffer[HBUFFERLEN]; int j,k; - const char hexbuf[]= "0123456789abcdef"; for (k=0, j=0; k < HBUFFERLEN-3 && j < ETH_ALEN; j++) { - hbuffer[k++]=hexbuf[(payload->src_hw[j]>>4)&15]; - hbuffer[k++]=hexbuf[payload->src_hw[j]&15]; + hbuffer[k++] = hex_asc_hi(payload->src_hw[j]); + hbuffer[k++] = hex_asc_lo(payload->src_hw[j]); hbuffer[k++]=':'; } hbuffer[--k]='\0'; 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/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c index 21cb053f5d7d..3974d7cae5c0 100644 --- a/net/ipv4/netfilter/ipt_recent.c +++ b/net/ipv4/netfilter/ipt_recent.c @@ -305,10 +305,10 @@ static void recent_mt_destroy(const struct xt_match *match, void *matchinfo) spin_lock_bh(&recent_lock); list_del(&t->list); spin_unlock_bh(&recent_lock); - recent_table_flush(t); #ifdef CONFIG_PROC_FS remove_proc_entry(t->name, proc_dir); #endif + recent_table_flush(t); kfree(t); } mutex_unlock(&recent_mutex); diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 2b472ac2263a..db6d312128e1 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -32,7 +32,7 @@ static struct struct ipt_replace repl; struct ipt_standard entries[3]; struct ipt_error term; -} initial_table __initdata = { +} initial_table __net_initdata = { .repl = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, 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/proc.c b/net/ipv4/proc.c index 834356ea99df..8f5a403f6f6b 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -232,6 +232,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDSACKIgnoredOld", LINUX_MIB_TCPDSACKIGNOREDOLD), SNMP_MIB_ITEM("TCPDSACKIgnoredNoUndo", LINUX_MIB_TCPDSACKIGNOREDNOUNDO), SNMP_MIB_ITEM("TCPSpuriousRTOs", LINUX_MIB_TCPSPURIOUSRTOS), + SNMP_MIB_ITEM("TCPMD5NotFound", LINUX_MIB_TCPMD5NOTFOUND), + SNMP_MIB_ITEM("TCPMD5Unexpected", LINUX_MIB_TCPMD5UNEXPECTED), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e4ab0ac94f92..cca921ea8550 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1502,21 +1502,21 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, rth->fl.iif != 0 || dst_metric_locked(&rth->u.dst, RTAX_MTU) || !net_eq(dev_net(rth->u.dst.dev), net) || - !rt_is_expired(rth)) + rt_is_expired(rth)) continue; if (new_mtu < 68 || new_mtu >= old_mtu) { /* 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, @@ -2914,7 +2914,69 @@ static int ipv4_sysctl_rtcache_flush_strategy(ctl_table *table, return 0; } -ctl_table ipv4_route_table[] = { +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, .procname = "gc_thresh", @@ -3048,8 +3110,8 @@ 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; } @@ -3216,6 +3280,17 @@ int __init ip_rt_init(void) return rc; } +#ifdef CONFIG_SYSCTL +/* + * We really need to sanitize the damn ipv4 init order, then all + * this nonsense will go away. + */ +void __init ip_static_sysctl_init(void) +{ + register_sysctl_paths(ipv4_route_path, ipv4_route_table); +} +#endif + EXPORT_SYMBOL(__ip_select_ident); EXPORT_SYMBOL(ip_route_input); EXPORT_SYMBOL(ip_route_output_key); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 51bc24d3b8a7..9d38005abbac 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -299,6 +299,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->rmt_port = th->source; ireq->loc_addr = ip_hdr(skb)->daddr; ireq->rmt_addr = ip_hdr(skb)->saddr; + ireq->ecn_ok = 0; ireq->snd_wscale = tcp_opt.snd_wscale; ireq->rcv_wscale = tcp_opt.rcv_wscale; ireq->sack_ok = tcp_opt.sack_ok; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 14ef202a2254..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, @@ -401,13 +402,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = &ipv4_local_port_range, .strategy = &ipv4_sysctl_local_port_range, }, - { - .ctl_name = NET_IPV4_ROUTE, - .procname = "route", - .maxlen = 0, - .mode = 0555, - .child = ipv4_route_table - }, #ifdef CONFIG_IP_MULTICAST { .ctl_name = NET_IPV4_IGMP_MAX_MEMBERSHIPS, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0b491bf03db4..1ab341e5d3e0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1096,7 +1096,7 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) #if TCP_DEBUG struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); - BUG_TRAP(!skb || before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq)); + WARN_ON(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq)); #endif if (inet_csk_ack_scheduled(sk)) { @@ -1358,7 +1358,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, goto found_ok_skb; if (tcp_hdr(skb)->fin) goto found_fin_ok; - BUG_TRAP(flags & MSG_PEEK); + WARN_ON(!(flags & MSG_PEEK)); skb = skb->next; } while (skb != (struct sk_buff *)&sk->sk_receive_queue); @@ -1421,8 +1421,8 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, tp->ucopy.len = len; - BUG_TRAP(tp->copied_seq == tp->rcv_nxt || - (flags & (MSG_PEEK | MSG_TRUNC))); + WARN_ON(tp->copied_seq != tp->rcv_nxt && + !(flags & (MSG_PEEK | MSG_TRUNC))); /* Ugly... If prequeue is not empty, we have to * process it before releasing socket, otherwise @@ -1844,7 +1844,7 @@ adjudge_to_death: */ local_bh_disable(); bh_lock_sock(sk); - BUG_TRAP(!sock_owned_by_user(sk)); + WARN_ON(sock_owned_by_user(sk)); /* Have we already been destroyed by a softirq or backlog? */ if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE) @@ -1973,7 +1973,7 @@ int tcp_disconnect(struct sock *sk, int flags) memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); - BUG_TRAP(!inet->num || icsk->icsk_bind_hash); + WARN_ON(inet->num && !icsk->icsk_bind_hash); sk->sk_error_report(sk); return err; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1f5e6049883e..67ccce2a96bd 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1629,10 +1629,10 @@ advance_sp: out: #if FASTRETRANS_DEBUG > 0 - BUG_TRAP((int)tp->sacked_out >= 0); - BUG_TRAP((int)tp->lost_out >= 0); - BUG_TRAP((int)tp->retrans_out >= 0); - BUG_TRAP((int)tcp_packets_in_flight(tp) >= 0); + WARN_ON((int)tp->sacked_out < 0); + WARN_ON((int)tp->lost_out < 0); + WARN_ON((int)tp->retrans_out < 0); + WARN_ON((int)tcp_packets_in_flight(tp) < 0); #endif return flag; } @@ -2181,7 +2181,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets) int err; unsigned int mss; - BUG_TRAP(packets <= tp->packets_out); + WARN_ON(packets > tp->packets_out); if (tp->lost_skb_hint) { skb = tp->lost_skb_hint; cnt = tp->lost_cnt_hint; @@ -2610,7 +2610,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) /* E. Check state exit conditions. State can be terminated * when high_seq is ACKed. */ if (icsk->icsk_ca_state == TCP_CA_Open) { - BUG_TRAP(tp->retrans_out == 0); + WARN_ON(tp->retrans_out != 0); tp->retrans_stamp = 0; } else if (!before(tp->snd_una, tp->high_seq)) { switch (icsk->icsk_ca_state) { @@ -2972,9 +2972,9 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets) } #if FASTRETRANS_DEBUG > 0 - BUG_TRAP((int)tp->sacked_out >= 0); - BUG_TRAP((int)tp->lost_out >= 0); - BUG_TRAP((int)tp->retrans_out >= 0); + WARN_ON((int)tp->sacked_out < 0); + WARN_ON((int)tp->lost_out < 0); + WARN_ON((int)tp->retrans_out < 0); if (!tp->packets_out && tcp_is_sack(tp)) { icsk = inet_csk(sk); if (tp->lost_out) { @@ -3292,6 +3292,7 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) * log. Something worked... */ sk->sk_err_soft = 0; + icsk->icsk_probes_out = 0; tp->rcv_tstamp = tcp_time_stamp; prior_packets = tp->packets_out; if (!prior_packets) @@ -3324,8 +3325,6 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) return 1; no_queue: - icsk->icsk_probes_out = 0; - /* If this ack opens up a zero window, clear backoff. It was * being used to time the probes, and is probably far higher than * it needs to be for normal retransmission. @@ -3878,7 +3877,7 @@ static void tcp_sack_remove(struct tcp_sock *tp) int i; /* RCV.NXT must cover all the block! */ - BUG_TRAP(!before(tp->rcv_nxt, sp->end_seq)); + WARN_ON(before(tp->rcv_nxt, sp->end_seq)); /* Zap this SACK, by moving forward any other SACKS. */ for (i=this_sack+1; i < num_sacks; i++) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a82df6307567..44c1e934824b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -418,7 +418,7 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) /* ICMPs are not backlogged, hence we cannot get an established socket here. */ - BUG_TRAP(!req->sk); + WARN_ON(req->sk); if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); @@ -655,8 +655,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, rep.th.doff = arg.iov[0].iov_len/4; tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[offset], - key, ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr, &rep.th); + key, ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, &rep.th); } #endif arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr, @@ -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)); } /* @@ -1116,18 +1116,12 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb) return 0; if (hash_expected && !hash_location) { - LIMIT_NETDEBUG(KERN_INFO "MD5 Hash expected but NOT found " - "(" NIPQUAD_FMT ", %d)->(" NIPQUAD_FMT ", %d)\n", - NIPQUAD(iph->saddr), ntohs(th->source), - NIPQUAD(iph->daddr), ntohs(th->dest)); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); return 1; } if (!hash_expected && hash_location) { - LIMIT_NETDEBUG(KERN_INFO "MD5 Hash NOT expected but found " - "(" NIPQUAD_FMT ", %d)->(" NIPQUAD_FMT ", %d)\n", - NIPQUAD(iph->saddr), ntohs(th->source), - NIPQUAD(iph->daddr), ntohs(th->dest)); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); return 1; } 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/tcp_output.c b/net/ipv4/tcp_output.c index 1fa683c0ba9b..a00532de2a8c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -472,7 +472,7 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, } if (likely(sysctl_tcp_sack)) { opts->options |= OPTION_SACK_ADVERTISE; - if (unlikely(!OPTION_TS & opts->options)) + if (unlikely(!(OPTION_TS & opts->options))) size += TCPOLEN_SACKPERM_ALIGNED; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 328e0cf42b3c..5ab6ba19c3ce 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -287,7 +287,7 @@ static void tcp_retransmit_timer(struct sock *sk) if (!tp->packets_out) goto out; - BUG_TRAP(!tcp_write_queue_empty(sk)); + WARN_ON(tcp_write_queue_empty(sk)); if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) && !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index a751770947a3..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 @@ -1325,6 +1327,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; if (val != 0 && val < 8) /* Illegal coverage: use default (8) */ val = 8; + else if (val > USHORT_MAX) + val = USHORT_MAX; up->pcslen = val; up->pcflag |= UDPLITE_SEND_CC; break; @@ -1337,6 +1341,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; if (val != 0 && val < 8) /* Avoid silly minimal values. */ val = 8; + else if (val > USHORT_MAX) + val = USHORT_MAX; up->pcrlen = val; up->pcflag |= UDPLITE_RECV_CC; break; 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/Kconfig b/net/ipv6/Kconfig index 42814a2ec9d7..ec992159b5f8 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -96,10 +96,8 @@ config INET6_ESP config INET6_IPCOMP tristate "IPv6: IPComp transformation" - select XFRM select INET6_XFRM_TUNNEL - select CRYPTO - select CRYPTO_DEFLATE + select XFRM_IPCOMP ---help--- Support for IP Payload Compression Protocol (IPComp) (RFC3173), typically needed for IPsec. diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9f4fcce6379b..e2d3b7580b76 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -153,7 +153,7 @@ static int ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); -struct ipv6_devconf ipv6_devconf __read_mostly = { +static struct ipv6_devconf ipv6_devconf __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, .mtu6 = IPV6_MIN_MTU, @@ -313,8 +313,10 @@ static void in6_dev_finish_destroy_rcu(struct rcu_head *head) void in6_dev_finish_destroy(struct inet6_dev *idev) { struct net_device *dev = idev->dev; - BUG_TRAP(idev->addr_list==NULL); - BUG_TRAP(idev->mc_list==NULL); + + WARN_ON(idev->addr_list != NULL); + WARN_ON(idev->mc_list != NULL); + #ifdef NET_REFCNT_DEBUG printk(KERN_DEBUG "in6_dev_finish_destroy: %s\n", dev ? dev->name : "NIL"); #endif @@ -517,8 +519,9 @@ static void addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) { - BUG_TRAP(ifp->if_next==NULL); - BUG_TRAP(ifp->lst_next==NULL); + WARN_ON(ifp->if_next != NULL); + WARN_ON(ifp->lst_next != NULL); + #ifdef NET_REFCNT_DEBUG printk(KERN_DEBUG "inet6_ifa_finish_destroy\n"); #endif @@ -1103,13 +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/af_inet6.c b/net/ipv6/af_inet6.c index 3d828bc4b1cf..95055f8c3f35 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -83,7 +83,6 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol) struct inet_sock *inet; struct ipv6_pinfo *np; struct sock *sk; - struct list_head *p; struct inet_protosw *answer; struct proto *answer_prot; unsigned char answer_flags; @@ -97,13 +96,12 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol) build_ehash_secret(); /* Look for the requested type/protocol pair. */ - answer = NULL; lookup_protocol: err = -ESOCKTNOSUPPORT; rcu_read_lock(); - list_for_each_rcu(p, &inetsw6[sock->type]) { - answer = list_entry(p, struct inet_protosw, list); + list_for_each_entry_rcu(answer, &inetsw6[sock->type], list) { + err = 0; /* Check the non-wild match. */ if (protocol == answer->protocol) { if (protocol != IPPROTO_IP) @@ -118,10 +116,9 @@ lookup_protocol: break; } err = -EPROTONOSUPPORT; - answer = NULL; } - if (!answer) { + if (err) { if (try_loading_module < 2) { rcu_read_unlock(); /* @@ -153,7 +150,7 @@ lookup_protocol: answer_flags = answer->flags; rcu_read_unlock(); - BUG_TRAP(answer_prot->slab != NULL); + WARN_ON(answer_prot->slab == NULL); err = -ENOBUFS; sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot); @@ -937,6 +934,11 @@ static int __init inet6_init(void) if (err) goto out_unregister_sock; +#ifdef CONFIG_SYSCTL + err = ipv6_static_sysctl_register(); + if (err) + goto static_sysctl_fail; +#endif /* * ipngwg API draft makes clear that the correct semantics * for TCP and UDP is to consider one TCP and UDP instance @@ -1061,6 +1063,10 @@ ipmr_fail: icmp_fail: unregister_pernet_subsys(&inet6_net_ops); register_pernet_fail: +#ifdef CONFIG_SYSCTL + ipv6_static_sysctl_unregister(); +static_sysctl_fail: +#endif cleanup_ipv6_mibs(); out_unregister_sock: sock_unregister(PF_INET6); @@ -1116,6 +1122,9 @@ static void __exit inet6_exit(void) rawv6_exit(); unregister_pernet_subsys(&inet6_net_ops); +#ifdef CONFIG_SYSCTL + ipv6_static_sysctl_unregister(); +#endif cleanup_ipv6_mibs(); proto_unregister(&rawv6_prot); proto_unregister(&udplitev6_prot); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index f7b535dec860..410046a8cc91 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -732,7 +732,7 @@ int datagram_send_ctl(struct net *net, LIMIT_NETDEBUG(KERN_DEBUG "invalid cmsg type: %d\n", cmsg->cmsg_type); err = -EINVAL; - break; + goto exit_f; } } 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/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 87801cc1b2f8..16d43f20b32f 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -98,7 +98,7 @@ struct request_sock *inet6_csk_search_req(const struct sock *sk, ipv6_addr_equal(&treq->rmt_addr, raddr) && ipv6_addr_equal(&treq->loc_addr, laddr) && (!treq->iif || treq->iif == iif)) { - BUG_TRAP(req->sk == NULL); + WARN_ON(req->sk != NULL); *prevp = prev; return req; } diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 00a8a5f9380c..1646a5658255 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -28,7 +28,7 @@ void __inet6_hash(struct sock *sk) struct hlist_head *list; rwlock_t *lock; - BUG_TRAP(sk_unhashed(sk)); + WARN_ON(!sk_unhashed(sk)); if (sk->sk_state == TCP_LISTEN) { list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; @@ -202,7 +202,7 @@ unique: * in hash table socket with a funny identity. */ inet->num = lport; inet->sport = htons(lport); - BUG_TRAP(sk_unhashed(sk)); + WARN_ON(!sk_unhashed(sk)); __sk_add_node(sk, &head->chain); sk->sk_hash = hash; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 4de2b9efcacb..29c7c99e69f7 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -287,7 +287,7 @@ static int fib6_dump_node(struct fib6_walker_t *w) w->leaf = rt; return 1; } - BUG_TRAP(res!=0); + WARN_ON(res == 0); } w->leaf = NULL; return 0; @@ -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) { @@ -661,17 +662,17 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, static __inline__ void fib6_start_gc(struct net *net, struct rt6_info *rt) { - if (net->ipv6.ip6_fib_timer->expires == 0 && + if (!timer_pending(&net->ipv6.ip6_fib_timer) && (rt->rt6i_flags & (RTF_EXPIRES|RTF_CACHE))) - mod_timer(net->ipv6.ip6_fib_timer, jiffies + - net->ipv6.sysctl.ip6_rt_gc_interval); + mod_timer(&net->ipv6.ip6_fib_timer, + jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } void fib6_force_start_gc(struct net *net) { - if (net->ipv6.ip6_fib_timer->expires == 0) - mod_timer(net->ipv6.ip6_fib_timer, jiffies + - net->ipv6.sysctl.ip6_rt_gc_interval); + if (!timer_pending(&net->ipv6.ip6_fib_timer)) + mod_timer(&net->ipv6.ip6_fib_timer, + jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } /* @@ -778,7 +779,7 @@ out: pn->leaf = fib6_find_prefix(info->nl_net, pn); #if RT6_DEBUG >= 2 if (!pn->leaf) { - BUG_TRAP(pn->leaf != NULL); + WARN_ON(pn->leaf == NULL); pn->leaf = info->nl_net->ipv6.ip6_null_entry; } #endif @@ -942,7 +943,7 @@ struct fib6_node * fib6_locate(struct fib6_node *root, #ifdef CONFIG_IPV6_SUBTREES if (src_len) { - BUG_TRAP(saddr!=NULL); + WARN_ON(saddr == NULL); if (fn && fn->subtree) fn = fib6_locate_1(fn->subtree, saddr, src_len, offsetof(struct rt6_info, rt6i_src)); @@ -996,9 +997,9 @@ static struct fib6_node *fib6_repair_tree(struct net *net, RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; - BUG_TRAP(!(fn->fn_flags&RTN_RTINFO)); - BUG_TRAP(!(fn->fn_flags&RTN_TL_ROOT)); - BUG_TRAP(fn->leaf==NULL); + WARN_ON(fn->fn_flags & RTN_RTINFO); + WARN_ON(fn->fn_flags & RTN_TL_ROOT); + WARN_ON(fn->leaf != NULL); children = 0; child = NULL; @@ -1014,7 +1015,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net, fn->leaf = fib6_find_prefix(net, fn); #if RT6_DEBUG >= 2 if (fn->leaf==NULL) { - BUG_TRAP(fn->leaf); + WARN_ON(!fn->leaf); fn->leaf = net->ipv6.ip6_null_entry; } #endif @@ -1025,16 +1026,17 @@ static struct fib6_node *fib6_repair_tree(struct net *net, pn = fn->parent; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { - BUG_TRAP(fn->fn_flags&RTN_ROOT); + WARN_ON(!(fn->fn_flags & RTN_ROOT)); FIB6_SUBTREE(pn) = NULL; nstate = FWS_L; } else { - BUG_TRAP(!(fn->fn_flags&RTN_ROOT)); + WARN_ON(fn->fn_flags & RTN_ROOT); #endif if (pn->right == fn) pn->right = child; else if (pn->left == fn) pn->left = child; #if RT6_DEBUG >= 2 - else BUG_TRAP(0); + else + WARN_ON(1); #endif if (child) child->parent = pn; @@ -1154,14 +1156,14 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) #if RT6_DEBUG >= 2 if (rt->u.dst.obsolete>0) { - BUG_TRAP(fn==NULL); + WARN_ON(fn != NULL); return -ENOENT; } #endif if (fn == NULL || rt == net->ipv6.ip6_null_entry) return -ENOENT; - BUG_TRAP(fn->fn_flags&RTN_RTINFO); + WARN_ON(!(fn->fn_flags & RTN_RTINFO)); if (!(rt->rt6i_flags&RTF_CACHE)) { struct fib6_node *pn = fn; @@ -1266,7 +1268,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w) w->node = pn; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { - BUG_TRAP(fn->fn_flags&RTN_ROOT); + WARN_ON(!(fn->fn_flags & RTN_ROOT)); w->state = FWS_L; continue; } @@ -1281,7 +1283,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w) continue; } #if RT6_DEBUG >= 2 - BUG_TRAP(0); + WARN_ON(1); #endif } } @@ -1323,7 +1325,7 @@ static int fib6_clean_node(struct fib6_walker_t *w) } return 0; } - BUG_TRAP(res==0); + WARN_ON(res != 0); } w->leaf = rt; return 0; @@ -1447,27 +1449,23 @@ void fib6_run_gc(unsigned long expires, struct net *net) gc_args.timeout = expires ? (int)expires : net->ipv6.sysctl.ip6_rt_gc_interval; } else { - local_bh_disable(); - if (!spin_trylock(&fib6_gc_lock)) { - mod_timer(net->ipv6.ip6_fib_timer, jiffies + HZ); - local_bh_enable(); + if (!spin_trylock_bh(&fib6_gc_lock)) { + mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); return; } gc_args.timeout = net->ipv6.sysctl.ip6_rt_gc_interval; } - gc_args.more = 0; - icmp6_dst_gc(&gc_args.more); + gc_args.more = icmp6_dst_gc(); fib6_clean_all(net, fib6_age, 0, NULL); if (gc_args.more) - mod_timer(net->ipv6.ip6_fib_timer, jiffies + - net->ipv6.sysctl.ip6_rt_gc_interval); - else { - del_timer(net->ipv6.ip6_fib_timer); - net->ipv6.ip6_fib_timer->expires = 0; - } + mod_timer(&net->ipv6.ip6_fib_timer, + round_jiffies(jiffies + + net->ipv6.sysctl.ip6_rt_gc_interval)); + else + del_timer(&net->ipv6.ip6_fib_timer); spin_unlock_bh(&fib6_gc_lock); } @@ -1478,24 +1476,15 @@ static void fib6_gc_timer_cb(unsigned long arg) static int fib6_net_init(struct net *net) { - int ret; - struct timer_list *timer; - - ret = -ENOMEM; - timer = kzalloc(sizeof(*timer), GFP_KERNEL); - if (!timer) - goto out; - - setup_timer(timer, fib6_gc_timer_cb, (unsigned long)net); - net->ipv6.ip6_fib_timer = timer; + setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net); net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); if (!net->ipv6.rt6_stats) goto out_timer; - net->ipv6.fib_table_hash = - kzalloc(sizeof(*net->ipv6.fib_table_hash)*FIB_TABLE_HASHSZ, - GFP_KERNEL); + net->ipv6.fib_table_hash = kcalloc(FIB_TABLE_HASHSZ, + sizeof(*net->ipv6.fib_table_hash), + GFP_KERNEL); if (!net->ipv6.fib_table_hash) goto out_rt6_stats; @@ -1521,9 +1510,7 @@ static int fib6_net_init(struct net *net) #endif fib6_tables_init(net); - ret = 0; -out: - return ret; + return 0; #ifdef CONFIG_IPV6_MULTIPLE_TABLES out_fib6_main_tbl: @@ -1534,15 +1521,14 @@ out_fib_table_hash: out_rt6_stats: kfree(net->ipv6.rt6_stats); out_timer: - kfree(timer); - goto out; + return -ENOMEM; } static void fib6_net_exit(struct net *net) { rt6_ifdown(net, NULL); - del_timer_sync(net->ipv6.ip6_fib_timer); - kfree(net->ipv6.ip6_fib_timer); + del_timer_sync(&net->ipv6.ip6_fib_timer); + #ifdef CONFIG_IPV6_MULTIPLE_TABLES kfree(net->ipv6.fib6_local_tbl); #endif diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 6407c64ea4a5..0e844c2736a7 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -116,7 +116,7 @@ static int ip6_dev_loopback_xmit(struct sk_buff *newskb) __skb_pull(newskb, skb_network_offset(newskb)); newskb->pkt_type = PACKET_LOOPBACK; newskb->ip_summed = CHECKSUM_UNNECESSARY; - BUG_TRAP(newskb->dst); + WARN_ON(!newskb->dst); netif_rx(newskb); return 0; @@ -236,6 +236,10 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, skb_reset_network_header(skb); hdr = ipv6_hdr(skb); + /* Allow local fragmentation. */ + if (ipfragok) + skb->local_df = 1; + /* * Fill in the IPv6 header */ @@ -265,7 +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, @@ -930,7 +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/ipcomp6.c b/net/ipv6/ipcomp6.c index ee6de425ce6b..4545e4306862 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -50,125 +50,6 @@ #include <linux/icmpv6.h> #include <linux/mutex.h> -struct ipcomp6_tfms { - struct list_head list; - struct crypto_comp **tfms; - int users; -}; - -static DEFINE_MUTEX(ipcomp6_resource_mutex); -static void **ipcomp6_scratches; -static int ipcomp6_scratch_users; -static LIST_HEAD(ipcomp6_tfms_list); - -static int ipcomp6_input(struct xfrm_state *x, struct sk_buff *skb) -{ - int nexthdr; - int err = -ENOMEM; - struct ip_comp_hdr *ipch; - int plen, dlen; - struct ipcomp_data *ipcd = x->data; - u8 *start, *scratch; - struct crypto_comp *tfm; - int cpu; - - if (skb_linearize_cow(skb)) - goto out; - - skb->ip_summed = CHECKSUM_NONE; - - /* Remove ipcomp header and decompress original payload */ - ipch = (void *)skb->data; - nexthdr = ipch->nexthdr; - - skb->transport_header = skb->network_header + sizeof(*ipch); - __skb_pull(skb, sizeof(*ipch)); - - /* decompression */ - plen = skb->len; - dlen = IPCOMP_SCRATCH_SIZE; - start = skb->data; - - cpu = get_cpu(); - scratch = *per_cpu_ptr(ipcomp6_scratches, cpu); - tfm = *per_cpu_ptr(ipcd->tfms, cpu); - - err = crypto_comp_decompress(tfm, start, plen, scratch, &dlen); - if (err) - goto out_put_cpu; - - if (dlen < (plen + sizeof(*ipch))) { - err = -EINVAL; - goto out_put_cpu; - } - - err = pskb_expand_head(skb, 0, dlen - plen, GFP_ATOMIC); - if (err) { - goto out_put_cpu; - } - - skb->truesize += dlen - plen; - __skb_put(skb, dlen - plen); - skb_copy_to_linear_data(skb, scratch, dlen); - err = nexthdr; - -out_put_cpu: - put_cpu(); -out: - return err; -} - -static int ipcomp6_output(struct xfrm_state *x, struct sk_buff *skb) -{ - int err; - struct ip_comp_hdr *ipch; - struct ipcomp_data *ipcd = x->data; - int plen, dlen; - u8 *start, *scratch; - struct crypto_comp *tfm; - int cpu; - - /* check whether datagram len is larger than threshold */ - if (skb->len < ipcd->threshold) { - goto out_ok; - } - - if (skb_linearize_cow(skb)) - goto out_ok; - - /* compression */ - plen = skb->len; - dlen = IPCOMP_SCRATCH_SIZE; - start = skb->data; - - cpu = get_cpu(); - scratch = *per_cpu_ptr(ipcomp6_scratches, cpu); - tfm = *per_cpu_ptr(ipcd->tfms, cpu); - - local_bh_disable(); - err = crypto_comp_compress(tfm, start, plen, scratch, &dlen); - local_bh_enable(); - if (err || (dlen + sizeof(*ipch)) >= plen) { - put_cpu(); - goto out_ok; - } - memcpy(start + sizeof(struct ip_comp_hdr), scratch, dlen); - put_cpu(); - pskb_trim(skb, dlen + sizeof(struct ip_comp_hdr)); - - /* insert ipcomp header and replace datagram */ - ipch = ip_comp_hdr(skb); - ipch->nexthdr = *skb_mac_header(skb); - ipch->flags = 0; - ipch->cpi = htons((u16 )ntohl(x->id.spi)); - *skb_mac_header(skb) = IPPROTO_COMP; - -out_ok: - skb_push(skb, -skb_network_offset(skb)); - - return 0; -} - static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int type, int code, int offset, __be32 info) { @@ -251,160 +132,9 @@ out: return err; } -static void ipcomp6_free_scratches(void) -{ - int i; - void **scratches; - - if (--ipcomp6_scratch_users) - return; - - scratches = ipcomp6_scratches; - if (!scratches) - return; - - for_each_possible_cpu(i) { - void *scratch = *per_cpu_ptr(scratches, i); - - vfree(scratch); - } - - free_percpu(scratches); -} - -static void **ipcomp6_alloc_scratches(void) -{ - int i; - void **scratches; - - if (ipcomp6_scratch_users++) - return ipcomp6_scratches; - - scratches = alloc_percpu(void *); - if (!scratches) - return NULL; - - ipcomp6_scratches = scratches; - - for_each_possible_cpu(i) { - void *scratch = vmalloc(IPCOMP_SCRATCH_SIZE); - if (!scratch) - return NULL; - *per_cpu_ptr(scratches, i) = scratch; - } - - return scratches; -} - -static void ipcomp6_free_tfms(struct crypto_comp **tfms) -{ - struct ipcomp6_tfms *pos; - int cpu; - - list_for_each_entry(pos, &ipcomp6_tfms_list, list) { - if (pos->tfms == tfms) - break; - } - - BUG_TRAP(pos); - - if (--pos->users) - return; - - list_del(&pos->list); - kfree(pos); - - if (!tfms) - return; - - for_each_possible_cpu(cpu) { - struct crypto_comp *tfm = *per_cpu_ptr(tfms, cpu); - crypto_free_comp(tfm); - } - free_percpu(tfms); -} - -static struct crypto_comp **ipcomp6_alloc_tfms(const char *alg_name) -{ - struct ipcomp6_tfms *pos; - struct crypto_comp **tfms; - int cpu; - - /* This can be any valid CPU ID so we don't need locking. */ - cpu = raw_smp_processor_id(); - - list_for_each_entry(pos, &ipcomp6_tfms_list, list) { - struct crypto_comp *tfm; - - tfms = pos->tfms; - tfm = *per_cpu_ptr(tfms, cpu); - - if (!strcmp(crypto_comp_name(tfm), alg_name)) { - pos->users++; - return tfms; - } - } - - pos = kmalloc(sizeof(*pos), GFP_KERNEL); - if (!pos) - return NULL; - - pos->users = 1; - INIT_LIST_HEAD(&pos->list); - list_add(&pos->list, &ipcomp6_tfms_list); - - pos->tfms = tfms = alloc_percpu(struct crypto_comp *); - if (!tfms) - goto error; - - for_each_possible_cpu(cpu) { - struct crypto_comp *tfm = crypto_alloc_comp(alg_name, 0, - CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) - goto error; - *per_cpu_ptr(tfms, cpu) = tfm; - } - - return tfms; - -error: - ipcomp6_free_tfms(tfms); - return NULL; -} - -static void ipcomp6_free_data(struct ipcomp_data *ipcd) -{ - if (ipcd->tfms) - ipcomp6_free_tfms(ipcd->tfms); - ipcomp6_free_scratches(); -} - -static void ipcomp6_destroy(struct xfrm_state *x) -{ - struct ipcomp_data *ipcd = x->data; - if (!ipcd) - return; - xfrm_state_delete_tunnel(x); - mutex_lock(&ipcomp6_resource_mutex); - ipcomp6_free_data(ipcd); - mutex_unlock(&ipcomp6_resource_mutex); - kfree(ipcd); - - xfrm6_tunnel_free_spi((xfrm_address_t *)&x->props.saddr); -} - static int ipcomp6_init_state(struct xfrm_state *x) { - int err; - struct ipcomp_data *ipcd; - struct xfrm_algo_desc *calg_desc; - - err = -EINVAL; - if (!x->calg) - goto out; - - if (x->encap) - goto out; + int err = -EINVAL; x->props.header_len = 0; switch (x->props.mode) { @@ -417,39 +147,21 @@ static int ipcomp6_init_state(struct xfrm_state *x) goto out; } - err = -ENOMEM; - ipcd = kzalloc(sizeof(*ipcd), GFP_KERNEL); - if (!ipcd) + err = ipcomp_init_state(x); + if (err) goto out; - mutex_lock(&ipcomp6_resource_mutex); - if (!ipcomp6_alloc_scratches()) - goto error; - - ipcd->tfms = ipcomp6_alloc_tfms(x->calg->alg_name); - if (!ipcd->tfms) - goto error; - mutex_unlock(&ipcomp6_resource_mutex); - if (x->props.mode == XFRM_MODE_TUNNEL) { err = ipcomp6_tunnel_attach(x); if (err) goto error_tunnel; } - calg_desc = xfrm_calg_get_byname(x->calg->alg_name, 0); - BUG_ON(!calg_desc); - ipcd->threshold = calg_desc->uinfo.comp.threshold; - x->data = ipcd; err = 0; out: return err; error_tunnel: - mutex_lock(&ipcomp6_resource_mutex); -error: - ipcomp6_free_data(ipcd); - mutex_unlock(&ipcomp6_resource_mutex); - kfree(ipcd); + ipcomp_destroy(x); goto out; } @@ -460,9 +172,9 @@ static const struct xfrm_type ipcomp6_type = .owner = THIS_MODULE, .proto = IPPROTO_COMP, .init_state = ipcomp6_init_state, - .destructor = ipcomp6_destroy, - .input = ipcomp6_input, - .output = ipcomp6_output, + .destructor = ipcomp_destroy, + .input = ipcomp_input, + .output = ipcomp_output, .hdr_offset = xfrm6_find_1stfragopt, }; 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/mip6.c b/net/ipv6/mip6.c index ad1cc5bbf977..31295c8f6196 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -164,8 +164,8 @@ static int mip6_destopt_output(struct xfrm_state *x, struct sk_buff *skb) calc_padlen(sizeof(*dstopt), 6)); hao->type = IPV6_TLV_HAO; + BUILD_BUG_ON(sizeof(*hao) != 18); hao->length = sizeof(*hao) - 2; - BUG_TRAP(hao->length == 16); len = ((char *)hao - (char *)dstopt) + sizeof(*hao); @@ -174,7 +174,7 @@ static int mip6_destopt_output(struct xfrm_state *x, struct sk_buff *skb) memcpy(&iph->saddr, x->coaddr, sizeof(iph->saddr)); spin_unlock_bh(&x->lock); - BUG_TRAP(len == x->props.header_len); + WARN_ON(len != x->props.header_len); dstopt->hdrlen = (x->props.header_len >> 3) - 1; return 0; @@ -317,7 +317,7 @@ static int mip6_destopt_init_state(struct xfrm_state *x) x->props.header_len = sizeof(struct ipv6_destopt_hdr) + calc_padlen(sizeof(struct ipv6_destopt_hdr), 6) + sizeof(struct ipv6_destopt_hao); - BUG_TRAP(x->props.header_len == 24); + WARN_ON(x->props.header_len != 24); return 0; } @@ -380,7 +380,7 @@ static int mip6_rthdr_output(struct xfrm_state *x, struct sk_buff *skb) rt2->rt_hdr.segments_left = 1; memset(&rt2->reserved, 0, sizeof(rt2->reserved)); - BUG_TRAP(rt2->rt_hdr.hdrlen == 2); + WARN_ON(rt2->rt_hdr.hdrlen != 2); memcpy(&rt2->addr, &iph->daddr, sizeof(rt2->addr)); spin_lock_bh(&x->lock); 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/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 689dec899c57..0cfcce7b18d8 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -213,7 +213,7 @@ config IP6_NF_SECURITY tristate "Security table" depends on IP6_NF_IPTABLES depends on SECURITY - default m if NETFILTER_ADVANCED=n + depends on NETFILTER_ADVANCED help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index a07abee30497..6e7131036bc6 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -31,7 +31,7 @@ static struct struct ip6t_replace repl; struct ip6t_standard entries[3]; struct ip6t_error term; -} initial_table __initdata = { +} initial_table __net_initdata = { .repl = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index cf20bc4fd60d..52d06dd4b817 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -416,8 +416,8 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) fq_kill(fq); - BUG_TRAP(head != NULL); - BUG_TRAP(NFCT_FRAG6_CB(head)->offset == 0); + WARN_ON(head == NULL); + WARN_ON(NFCT_FRAG6_CB(head)->offset != 0); /* Unfragmented part is taken from the first segment. */ payload_len = ((head->data - skb_network_header(head)) - diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index f82f6074cf85..0179b66864f1 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -286,7 +286,6 @@ proc_net_fail: void ipv6_misc_proc_exit(void) { - proc_net_remove(&init_net, "sockstat6"); proc_net_remove(&init_net, "dev_snmp6"); proc_net_remove(&init_net, "snmp6"); unregister_pernet_subsys(&ipv6_proc_ops); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 6ab957ec2dd6..89184b576e23 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -473,8 +473,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, fq->q.fragments = head; } - BUG_TRAP(head != NULL); - BUG_TRAP(FRAG6_CB(head)->offset == 0); + WARN_ON(head == NULL); + WARN_ON(FRAG6_CB(head)->offset != 0); /* Unfragmented part is taken from the first segment. */ payload_len = ((head->data - skb_network_header(head)) - diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 615b328de251..9af6115f0f50 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -978,13 +978,12 @@ out: return &rt->u.dst; } -int icmp6_dst_gc(int *more) +int icmp6_dst_gc(void) { struct dst_entry *dst, *next, **pprev; - int freed; + int more = 0; next = NULL; - freed = 0; spin_lock_bh(&icmp6_dst_lock); pprev = &icmp6_dst_gc_list; @@ -993,16 +992,15 @@ int icmp6_dst_gc(int *more) if (!atomic_read(&dst->__refcnt)) { *pprev = dst->next; dst_free(dst); - freed++; } else { pprev = &dst->next; - (*more)++; + ++more; } } spin_unlock_bh(&icmp6_dst_lock); - return freed; + return more; } static int ip6_dst_gc(struct dst_ops *ops) @@ -1251,7 +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)); @@ -2108,7 +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) @@ -2189,8 +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); } @@ -2235,7 +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); } @@ -2301,7 +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) { @@ -2328,7 +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 6a68eeb7bbf8..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; @@ -223,6 +221,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) req->expires = 0UL; req->retrans = 0; + ireq->ecn_ok = 0; ireq->snd_wscale = tcp_opt.snd_wscale; ireq->rcv_wscale = tcp_opt.rcv_wscale; ireq->sack_ok = tcp_opt.sack_ok; @@ -254,14 +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); @@ -272,7 +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 5c99274558bf..e6dfaeac6be3 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -150,3 +150,19 @@ void ipv6_sysctl_unregister(void) unregister_net_sysctl_table(ip6_header); unregister_pernet_subsys(&ipv6_sysctl_net_ops); } + +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); + if (ip6_base == NULL) + return -ENOMEM; + return 0; +} + +void ipv6_static_sysctl_unregister(void) +{ + unregister_net_sysctl_table(ip6_base); +} diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ae45f9835014..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); @@ -421,7 +422,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* ICMPs are not backlogged, hence we cannot get * an established socket here. */ - BUG_TRAP(req->sk == NULL); + WARN_ON(req->sk != NULL); if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); @@ -748,7 +749,7 @@ static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, ipv6_addr_copy(&bp->saddr, saddr); ipv6_addr_copy(&bp->daddr, daddr); bp->protocol = cpu_to_be32(IPPROTO_TCP); - bp->len = cpu_to_be16(nbytes); + bp->len = cpu_to_be32(nbytes); sg_init_one(&sg, bp, sizeof(*bp)); return crypto_hash_update(&hp->md5_desc, &sg, sizeof(*bp)); @@ -849,28 +850,17 @@ static int tcp_v6_inbound_md5_hash (struct sock *sk, struct sk_buff *skb) hash_expected = tcp_v6_md5_do_lookup(sk, &ip6h->saddr); hash_location = tcp_parse_md5sig_option(th); - /* do we have a hash as expected? */ - if (!hash_expected) { - if (!hash_location) - return 0; - if (net_ratelimit()) { - printk(KERN_INFO "MD5 Hash NOT expected but found " - "(" NIP6_FMT ", %u)->" - "(" NIP6_FMT ", %u)\n", - NIP6(ip6h->saddr), ntohs(th->source), - NIP6(ip6h->daddr), ntohs(th->dest)); - } + /* We've parsed the options - do we have a hash? */ + if (!hash_expected && !hash_location) + return 0; + + if (hash_expected && !hash_location) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); return 1; } - if (!hash_location) { - if (net_ratelimit()) { - printk(KERN_INFO "MD5 Hash expected but NOT found " - "(" NIP6_FMT ", %u)->" - "(" NIP6_FMT ", %u)\n", - NIP6(ip6h->saddr), ntohs(th->source), - NIP6(ip6h->daddr), ntohs(th->dest)); - } + if (!hash_expected && hash_location) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); return 1; } @@ -1105,8 +1095,8 @@ static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); tcp_v6_md5_hash_hdr((__u8 *)topt, key, - &ipv6_hdr(skb)->daddr, - &ipv6_hdr(skb)->saddr, t1); + &ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, t1); } #endif @@ -1149,10 +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/iucv/iucv.c b/net/iucv/iucv.c index 265b1b289a32..705959b31e24 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -497,7 +497,7 @@ static void iucv_setmask_up(void) /* Disable all cpu but the first in cpu_irq_cpumask. */ cpumask = iucv_irq_cpumask; cpu_clear(first_cpu(iucv_irq_cpumask), cpumask); - for_each_cpu_mask(cpu, cpumask) + for_each_cpu_mask_nr(cpu, cpumask) smp_call_function_single(cpu, iucv_block_cpu, NULL, 1); } diff --git a/net/key/af_key.c b/net/key/af_key.c index f0fc46c8038d..d628df97e02e 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -96,8 +96,8 @@ static void pfkey_sock_destruct(struct sock *sk) return; } - BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc)); - BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(atomic_read(&sk->sk_rmem_alloc)); + WARN_ON(atomic_read(&sk->sk_wmem_alloc)); atomic_dec(&pfkey_socks_nr); } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 8e7ba0e62cf5..297c257864c7 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -81,6 +81,7 @@ static int ieee80211_change_iface(struct wiphy *wiphy, int ifindex, enum nl80211_iftype type, u32 *flags, struct vif_params *params) { + struct ieee80211_local *local = wiphy_priv(wiphy); struct net_device *dev; enum ieee80211_if_types itype; struct ieee80211_sub_if_data *sdata; @@ -95,6 +96,9 @@ static int ieee80211_change_iface(struct wiphy *wiphy, int ifindex, if (itype == IEEE80211_IF_TYPE_INVALID) return -EINVAL; + if (dev == local->mdev) + return -EOPNOTSUPP; + sdata = IEEE80211_DEV_TO_SUB_IF(dev); ret = ieee80211_if_change_type(sdata, itype); @@ -117,12 +121,16 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, u8 key_idx, u8 *mac_addr, struct key_params *params) { + struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; struct sta_info *sta = NULL; enum ieee80211_key_alg alg; struct ieee80211_key *key; int err; + if (dev == local->mdev) + return -EOPNOTSUPP; + sdata = IEEE80211_DEV_TO_SUB_IF(dev); switch (params->cipher) { @@ -167,10 +175,14 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_del_key(struct wiphy *wiphy, struct net_device *dev, u8 key_idx, u8 *mac_addr) { + struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; struct sta_info *sta; int ret; + if (dev == local->mdev) + return -EOPNOTSUPP; + sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); @@ -211,7 +223,8 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, void (*callback)(void *cookie, struct key_params *params)) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata; struct sta_info *sta = NULL; u8 seq[6] = {0}; struct key_params params; @@ -220,6 +233,11 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, u16 iv16; int err = -ENOENT; + if (dev == local->mdev) + return -EOPNOTSUPP; + + sdata = IEEE80211_DEV_TO_SUB_IF(dev); + rcu_read_lock(); if (mac_addr) { @@ -293,8 +311,12 @@ static int ieee80211_config_default_key(struct wiphy *wiphy, struct net_device *dev, u8 key_idx) { + struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; + if (dev == local->mdev) + return -EOPNOTSUPP; + rcu_read_lock(); sdata = IEEE80211_DEV_TO_SUB_IF(dev); @@ -475,9 +497,15 @@ static int ieee80211_config_beacon(struct ieee80211_sub_if_data *sdata, static int ieee80211_add_beacon(struct wiphy *wiphy, struct net_device *dev, struct beacon_parameters *params) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata; struct beacon_data *old; + if (dev == local->mdev) + return -EOPNOTSUPP; + + sdata = IEEE80211_DEV_TO_SUB_IF(dev); + if (sdata->vif.type != IEEE80211_IF_TYPE_AP) return -EINVAL; @@ -492,9 +520,15 @@ static int ieee80211_add_beacon(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_set_beacon(struct wiphy *wiphy, struct net_device *dev, struct beacon_parameters *params) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata; struct beacon_data *old; + if (dev == local->mdev) + return -EOPNOTSUPP; + + sdata = IEEE80211_DEV_TO_SUB_IF(dev); + if (sdata->vif.type != IEEE80211_IF_TYPE_AP) return -EINVAL; @@ -508,9 +542,15 @@ static int ieee80211_set_beacon(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_del_beacon(struct wiphy *wiphy, struct net_device *dev) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata; struct beacon_data *old; + if (dev == local->mdev) + return -EOPNOTSUPP; + + sdata = IEEE80211_DEV_TO_SUB_IF(dev); + if (sdata->vif.type != IEEE80211_IF_TYPE_AP) return -EINVAL; @@ -646,11 +686,14 @@ static void sta_apply_parameters(struct ieee80211_local *local, static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, u8 *mac, struct station_parameters *params) { - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); + struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; struct ieee80211_sub_if_data *sdata; int err; + if (dev == local->mdev || params->vlan == local->mdev) + return -EOPNOTSUPP; + /* Prevent a race with changing the rate control algorithm */ if (!netif_running(dev)) return -ENETDOWN; @@ -701,10 +744,15 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev, u8 *mac) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct ieee80211_local *local = sdata->local; + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata; struct sta_info *sta; + if (dev == local->mdev) + return -EOPNOTSUPP; + + sdata = IEEE80211_DEV_TO_SUB_IF(dev); + if (mac) { rcu_read_lock(); @@ -730,10 +778,13 @@ static int ieee80211_change_station(struct wiphy *wiphy, u8 *mac, struct station_parameters *params) { - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); + struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; struct ieee80211_sub_if_data *vlansdata; + if (dev == local->mdev || params->vlan == local->mdev) + return -EOPNOTSUPP; + rcu_read_lock(); /* XXX: get sta belonging to dev */ @@ -752,7 +803,7 @@ static int ieee80211_change_station(struct wiphy *wiphy, return -EINVAL; } - sta->sdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); + sta->sdata = vlansdata; ieee80211_send_layer2_update(sta); } @@ -767,15 +818,20 @@ static int ieee80211_change_station(struct wiphy *wiphy, static int ieee80211_add_mpath(struct wiphy *wiphy, struct net_device *dev, u8 *dst, u8 *next_hop) { - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; struct sta_info *sta; int err; + if (dev == local->mdev) + return -EOPNOTSUPP; + if (!netif_running(dev)) return -ENETDOWN; + sdata = IEEE80211_DEV_TO_SUB_IF(dev); + if (sdata->vif.type != IEEE80211_IF_TYPE_MESH_POINT) return -ENOTSUPP; @@ -817,14 +873,19 @@ static int ieee80211_change_mpath(struct wiphy *wiphy, struct net_device *dev, u8 *dst, u8 *next_hop) { - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; struct sta_info *sta; + if (dev == local->mdev) + return -EOPNOTSUPP; + if (!netif_running(dev)) return -ENETDOWN; + sdata = IEEE80211_DEV_TO_SUB_IF(dev); + if (sdata->vif.type != IEEE80211_IF_TYPE_MESH_POINT) return -ENOTSUPP; @@ -891,9 +952,15 @@ static int ieee80211_get_mpath(struct wiphy *wiphy, struct net_device *dev, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; + if (dev == local->mdev) + return -EOPNOTSUPP; + + sdata = IEEE80211_DEV_TO_SUB_IF(dev); + if (sdata->vif.type != IEEE80211_IF_TYPE_MESH_POINT) return -ENOTSUPP; @@ -913,9 +980,15 @@ static int ieee80211_dump_mpath(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; + if (dev == local->mdev) + return -EOPNOTSUPP; + + sdata = IEEE80211_DEV_TO_SUB_IF(dev); + if (sdata->vif.type != IEEE80211_IF_TYPE_MESH_POINT) return -ENOTSUPP; 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 f1a83d450ea0..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; @@ -1233,18 +1239,12 @@ static void ieee80211_tasklet_handler(unsigned long data) /* Remove added headers (e.g., QoS control), encryption header/MIC, etc. to * make a prepared TX frame (one that has been given to hw) to look like brand * new IEEE 802.11 frame that is ready to go through TX processing again. - * Also, tx_packet_data in cb is restored from tx_control. */ + */ static void ieee80211_remove_tx_extra(struct ieee80211_local *local, struct ieee80211_key *key, struct sk_buff *skb) { int hdrlen, iv_len, mic_len; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - - info->flags &= IEEE80211_TX_CTL_REQ_TX_STATUS | - IEEE80211_TX_CTL_DO_NOT_ENCRYPT | - IEEE80211_TX_CTL_REQUEUE | - IEEE80211_TX_CTL_EAPOL_FRAME; hdrlen = ieee80211_get_hdrlen_from_skb(skb); @@ -1695,6 +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) ? @@ -1731,8 +1736,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) result = ieee80211_wep_init(local); if (result < 0) { - printk(KERN_DEBUG "%s: Failed to initialize wep\n", - wiphy_name(local->hw.wiphy)); + printk(KERN_DEBUG "%s: Failed to initialize wep: %d\n", + wiphy_name(local->hw.wiphy), result); goto fail_wep; } 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 d7c371e36bf0..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); @@ -606,7 +607,6 @@ void ieee80211_sta_tx(struct net_device *dev, struct sk_buff *skb, int encrypt) { struct ieee80211_sub_if_data *sdata; - struct ieee80211_tx_info *info; sdata = IEEE80211_DEV_TO_SUB_IF(dev); skb->dev = sdata->local->mdev; @@ -614,11 +614,8 @@ void ieee80211_sta_tx(struct net_device *dev, struct sk_buff *skb, skb_set_network_header(skb, 0); skb_set_transport_header(skb, 0); - info = IEEE80211_SKB_CB(skb); - memset(info, 0, sizeof(struct ieee80211_tx_info)); - info->control.ifindex = sdata->dev->ifindex; - if (!encrypt) - info->flags |= IEEE80211_TX_CTL_DO_NOT_ENCRYPT; + skb->iif = sdata->dev->ifindex; + skb->do_not_encrypt = !encrypt; dev_queue_xmit(skb); } @@ -777,7 +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 { @@ -785,7 +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 */ @@ -2104,6 +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; } /* @@ -2692,6 +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; @@ -3303,6 +3314,7 @@ void ieee80211_start_mesh(struct net_device *dev) ifsta = &sdata->u.sta; ifsta->state = IEEE80211_MESH_UP; ieee80211_sta_timer((unsigned long)sdata); + ieee80211_if_config(sdata, IEEE80211_IFCC_BEACON); } #endif @@ -3653,11 +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)); @@ -3665,6 +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 */ @@ -3898,7 +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 0fbadd8b983c..4788f7b91f49 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -305,7 +305,7 @@ static void purge_old_ps_buffers(struct ieee80211_local *local) rcu_read_unlock(); local->total_ps_buffered = total; -#ifdef MAC80211_VERBOSE_PS_DEBUG +#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG printk(KERN_DEBUG "%s: PS buffers full - purged %d frames\n", wiphy_name(local->hw.wiphy), purged); #endif @@ -342,7 +342,7 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) purge_old_ps_buffers(tx->local); if (skb_queue_len(&tx->sdata->bss->ps_bc_buf) >= AP_MAX_BC_BUFFER) { -#ifdef MAC80211_VERBOSE_PS_DEBUG +#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG if (net_ratelimit()) { printk(KERN_DEBUG "%s: BC TX buffer full - " "dropping the oldest frame\n", @@ -389,7 +389,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) purge_old_ps_buffers(tx->local); if (skb_queue_len(&sta->ps_tx_buf) >= STA_MAX_TX_BUFFER) { struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf); -#ifdef MAC80211_VERBOSE_PS_DEBUG +#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG if (net_ratelimit()) { printk(KERN_DEBUG "%s: STA %s TX " "buffer full - dropping oldest frame\n", @@ -439,14 +439,14 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); u16 fc = tx->fc; - if (unlikely(info->flags & IEEE80211_TX_CTL_DO_NOT_ENCRYPT)) + if (unlikely(tx->skb->do_not_encrypt)) tx->key = NULL; else if (tx->sta && (key = rcu_dereference(tx->sta->key))) tx->key = key; else if ((key = rcu_dereference(tx->sdata->default_key))) tx->key = key; else if (tx->sdata->drop_unencrypted && - !(info->flags & IEEE80211_TX_CTL_EAPOL_FRAME) && + (tx->skb->protocol != cpu_to_be16(ETH_P_PAE)) && !(info->flags & IEEE80211_TX_CTL_INJECTED)) { I802_DEBUG_INC(tx->local->tx_handlers_drop_unencrypted); return TX_DROP; @@ -476,7 +476,7 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) } if (!tx->key || !(tx->key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) - info->flags |= IEEE80211_TX_CTL_DO_NOT_ENCRYPT; + tx->skb->do_not_encrypt = 1; return TX_CONTINUE; } @@ -732,6 +732,7 @@ ieee80211_tx_h_fragment(struct ieee80211_tx_data *tx) memcpy(skb_put(frag, copylen), pos, copylen); memcpy(frag->cb, first->cb, sizeof(frag->cb)); skb_copy_queue_mapping(frag, first); + frag->do_not_encrypt = first->do_not_encrypt; pos += copylen; left -= copylen; @@ -852,7 +853,7 @@ __ieee80211_parse_tx_radiotap(struct ieee80211_tx_data *tx, sband = tx->local->hw.wiphy->bands[tx->channel->band]; - info->flags |= IEEE80211_TX_CTL_DO_NOT_ENCRYPT; + skb->do_not_encrypt = 1; info->flags |= IEEE80211_TX_CTL_INJECTED; tx->flags &= ~IEEE80211_TX_FRAGMENTED; @@ -925,8 +926,7 @@ __ieee80211_parse_tx_radiotap(struct ieee80211_tx_data *tx, skb_trim(skb, skb->len - FCS_LEN); } if (*iterator.this_arg & IEEE80211_RADIOTAP_F_WEP) - info->flags &= - ~IEEE80211_TX_CTL_DO_NOT_ENCRYPT; + tx->skb->do_not_encrypt = 0; if (*iterator.this_arg & IEEE80211_RADIOTAP_F_FRAG) tx->flags |= IEEE80211_TX_FRAGMENTED; break; @@ -1042,10 +1042,9 @@ static int ieee80211_tx_prepare(struct ieee80211_tx_data *tx, struct sk_buff *skb, struct net_device *mdev) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct net_device *dev; - dev = dev_get_by_index(&init_net, info->control.ifindex); + dev = dev_get_by_index(&init_net, skb->iif); if (unlikely(dev && !is_ieee80211_device(dev, mdev))) { dev_put(dev); dev = NULL; @@ -1061,13 +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); @@ -1216,6 +1216,7 @@ retry: if (ret == IEEE80211_TX_FRAG_AGAIN) skb = NULL; + set_bit(queue, local->queues_pending); smp_mb(); /* @@ -1300,14 +1301,15 @@ 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; bool may_encrypt; int ret; - if (info->control.ifindex) - odev = dev_get_by_index(&init_net, info->control.ifindex); + if (skb->iif) + odev = dev_get_by_index(&init_net, skb->iif); if (unlikely(odev && !is_ieee80211_device(odev, dev))) { dev_put(odev); odev = NULL; @@ -1321,9 +1323,27 @@ int ieee80211_master_start_xmit(struct sk_buff *skb, return 0; } + memset(info, 0, sizeof(*info)); + + info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS; + osdata = IEEE80211_DEV_TO_SUB_IF(odev); - may_encrypt = !(info->flags & IEEE80211_TX_CTL_DO_NOT_ENCRYPT); + 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; if (may_encrypt) @@ -1348,7 +1368,6 @@ int ieee80211_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_radiotap_header *prthdr = (struct ieee80211_radiotap_header *)skb->data; u16 len_rthdr; @@ -1371,11 +1390,11 @@ int ieee80211_monitor_start_xmit(struct sk_buff *skb, skb->dev = local->mdev; /* needed because we set skb device to master */ - info->control.ifindex = dev->ifindex; + skb->iif = dev->ifindex; - info->flags |= IEEE80211_TX_CTL_DO_NOT_ENCRYPT; - /* Interfaces should always request a status report */ - info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS; + /* sometimes we do encrypt injected frames, will be fixed + * up in radiotap parser if not wanted */ + skb->do_not_encrypt = 0; /* * fix up the pointers accounting for the radiotap @@ -1419,7 +1438,6 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct ieee80211_tx_info *info; struct ieee80211_sub_if_data *sdata; int ret = 1, head_need; u16 ethertype, hdrlen, meshhdrlen = 0; @@ -1469,30 +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 @@ -1540,7 +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, @@ -1645,14 +1651,7 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, nh_pos += hdrlen; h_pos += hdrlen; - info = IEEE80211_SKB_CB(skb); - memset(info, 0, sizeof(*info)); - info->control.ifindex = dev->ifindex; - if (ethertype == ETH_P_PAE) - info->flags |= IEEE80211_TX_CTL_EAPOL_FRAME; - - /* Interfaces should always request a status report */ - info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS; + skb->iif = dev->ifindex; skb->dev = local->mdev; dev->stats.tx_packets++; @@ -1714,14 +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; @@ -1922,6 +1926,8 @@ struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, info = IEEE80211_SKB_CB(skb); + skb->do_not_encrypt = 1; + info->band = band; rate_control_get_rate(local->mdev, sband, skb, &rsel); @@ -1931,7 +1937,7 @@ struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, "no rate found\n", wiphy_name(local->hw.wiphy)); } - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); skb = NULL; goto out; } @@ -1940,7 +1946,6 @@ struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, info->tx_rate_idx = rsel.rate_idx; info->flags |= IEEE80211_TX_CTL_NO_ACK; - info->flags |= IEEE80211_TX_CTL_DO_NOT_ENCRYPT; info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT; info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ; if (sdata->bss_conf.use_short_preamble && 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/wep.c b/net/mac80211/wep.c index 872d2fcd1a5b..5c2bf0a3d4db 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -31,13 +31,13 @@ int ieee80211_wep_init(struct ieee80211_local *local) local->wep_tx_tfm = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(local->wep_tx_tfm)) - return -ENOMEM; + return PTR_ERR(local->wep_tx_tfm); local->wep_rx_tfm = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(local->wep_rx_tfm)) { crypto_free_blkcipher(local->wep_tx_tfm); - return -ENOMEM; + return PTR_ERR(local->wep_rx_tfm); } return 0; diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 07edda0b8a5c..4310e2f65661 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -188,6 +188,9 @@ int ieee80211_ht_agg_queue_add(struct ieee80211_local *local, { int i; + /* XXX: currently broken due to cb/requeue use */ + return -EPERM; + /* prepare the filter and save it for the SW queue * matching the received HW queue */ @@ -238,12 +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_extend.c b/net/netfilter/nf_conntrack_extend.c index 3469bc71a385..4b2c769d555f 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -95,7 +95,7 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) newlen = newoff + t->len; rcu_read_unlock(); - new = krealloc(ct->ext, newlen, gfp); + new = __krealloc(ct->ext, newlen, gfp); if (!new) return NULL; @@ -115,10 +115,10 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) ct->ext = new; } - ct->ext->offset[id] = newoff; - ct->ext->len = newlen; - memset((void *)ct->ext + newoff, 0, newlen - newoff); - return (void *)ct->ext + newoff; + new->offset[id] = newoff; + new->len = newlen; + memset((void *)new + newoff, 0, newlen - newoff); + return (void *)new + newoff; } EXPORT_SYMBOL(__nf_ct_ext_add); 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_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 420a10d8eb1e..6f61261888ef 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -67,7 +67,8 @@ static const char *const tcp_conntrack_names[] = { /* RFC1122 says the R2 limit should be at least 100 seconds. Linux uses 15 packets as limit, which corresponds to ~13-30min depending on RTO. */ -static unsigned int nf_ct_tcp_timeout_max_retrans __read_mostly = 5 MINS; +static unsigned int nf_ct_tcp_timeout_max_retrans __read_mostly = 5 MINS; +static unsigned int nf_ct_tcp_timeout_unacknowledged __read_mostly = 5 MINS; static unsigned int tcp_timeouts[TCP_CONNTRACK_MAX] __read_mostly = { [TCP_CONNTRACK_SYN_SENT] = 2 MINS, @@ -625,8 +626,10 @@ static bool tcp_in_window(const struct nf_conn *ct, swin = win + (sack - ack); if (sender->td_maxwin < swin) sender->td_maxwin = swin; - if (after(end, sender->td_end)) + if (after(end, sender->td_end)) { sender->td_end = end; + sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; + } /* * Update receiver data. */ @@ -637,6 +640,8 @@ static bool tcp_in_window(const struct nf_conn *ct, if (win == 0) receiver->td_maxend++; } + if (ack == receiver->td_end) + receiver->flags &= ~IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; /* * Check retransmissions. @@ -951,9 +956,16 @@ static int tcp_packet(struct nf_conn *ct, if (old_state != new_state && new_state == TCP_CONNTRACK_FIN_WAIT) ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT; - timeout = ct->proto.tcp.retrans >= nf_ct_tcp_max_retrans - && tcp_timeouts[new_state] > nf_ct_tcp_timeout_max_retrans - ? nf_ct_tcp_timeout_max_retrans : tcp_timeouts[new_state]; + + if (ct->proto.tcp.retrans >= nf_ct_tcp_max_retrans && + tcp_timeouts[new_state] > nf_ct_tcp_timeout_max_retrans) + timeout = nf_ct_tcp_timeout_max_retrans; + else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) & + IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED && + tcp_timeouts[new_state] > nf_ct_tcp_timeout_unacknowledged) + timeout = nf_ct_tcp_timeout_unacknowledged; + else + timeout = tcp_timeouts[new_state]; write_unlock_bh(&tcp_lock); nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, skb); @@ -1236,6 +1248,13 @@ static struct ctl_table tcp_sysctl_table[] = { .proc_handler = &proc_dointvec_jiffies, }, { + .procname = "nf_conntrack_tcp_timeout_unacknowledged", + .data = &nf_ct_tcp_timeout_unacknowledged, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + }, + { .ctl_name = NET_NF_CONNTRACK_TCP_LOOSE, .procname = "nf_conntrack_tcp_loose", .data = &nf_ct_tcp_loose, 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/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 6809af542a2c..d9418a267812 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -367,9 +367,7 @@ static void htable_gc(unsigned long htlong) static void htable_destroy(struct xt_hashlimit_htable *hinfo) { - /* remove timer, if it is pending */ - if (timer_pending(&hinfo->timer)) - del_timer(&hinfo->timer); + del_timer_sync(&hinfo->timer); /* remove proc entry */ remove_proc_entry(hinfo->pde->name, diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 98bfe277eab2..b0eacc0007cc 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -158,9 +158,10 @@ static void netlink_sock_destruct(struct sock *sk) printk(KERN_ERR "Freeing alive netlink socket %p\n", sk); return; } - BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc)); - BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc)); - BUG_TRAP(!nlk_sk(sk)->groups); + + WARN_ON(atomic_read(&sk->sk_rmem_alloc)); + WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(nlk_sk(sk)->groups); } /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index fccc250f95f5..532e4faa29f7 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -73,6 +73,7 @@ static const struct proto_ops nr_proto_ops; * separate class since they always nest. */ static struct lock_class_key nr_netdev_xmit_lock_key; +static struct lock_class_key nr_netdev_addr_lock_key; static void nr_set_lockdep_one(struct net_device *dev, struct netdev_queue *txq, @@ -83,6 +84,7 @@ static void nr_set_lockdep_one(struct net_device *dev, static void nr_set_lockdep_key(struct net_device *dev) { + lockdep_set_class(&dev->addr_list_lock, &nr_netdev_addr_lock_key); netdev_for_each_tx_queue(dev, nr_set_lockdep_one, NULL); } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d56cae112dc8..c718e7e3f7de 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -260,8 +260,8 @@ static inline struct packet_sock *pkt_sk(struct sock *sk) static void packet_sock_destruct(struct sock *sk) { - BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc)); - BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(atomic_read(&sk->sk_rmem_alloc)); + WARN_ON(atomic_read(&sk->sk_wmem_alloc)); if (!sock_flag(sk, SOCK_DEAD)) { printk("Attempt to release alive packet socket: %p\n", sk); 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 7a560b785097..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, @@ -130,7 +140,6 @@ static void update_rfkill_state(struct rfkill *rfkill) /** * rfkill_toggle_radio - wrapper for toggle_radio hook - * * @rfkill: the rfkill struct to use * @force: calls toggle_radio even if cache says it is not needed, * and also makes sure notifications of the state will be @@ -141,8 +150,10 @@ static void update_rfkill_state(struct rfkill *rfkill) * calls and handling all the red tape such as issuing notifications * if the call is successful. * - * Note that @force cannot override a (possibly cached) state of - * RFKILL_STATE_HARD_BLOCKED. Any device making use of + * 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 * rfkill_force_state(), so the cache either is bypassed or valid. * @@ -150,7 +161,7 @@ static void update_rfkill_state(struct rfkill *rfkill) * even if the radio is in RFKILL_STATE_HARD_BLOCKED state, so as to * give the driver a hint that it should double-BLOCK the transmitter. * - * Caller must have aquired rfkill_mutex. + * Caller must have acquired rfkill->mutex. */ static int rfkill_toggle_radio(struct rfkill *rfkill, enum rfkill_state state, @@ -159,6 +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 && @@ -200,12 +214,12 @@ static int rfkill_toggle_radio(struct rfkill *rfkill, /** * rfkill_switch_all - Toggle state of all switches of given type - * @type: type of interfaces to be affeceted + * @type: type of interfaces to be affected * @state: the new state * - * This function toggles state of all switches of given type unless - * a specific switch is claimed by userspace in which case it is - * left alone. + * 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) or suspended. */ void rfkill_switch_all(enum rfkill_type type, enum rfkill_state state) { @@ -216,8 +230,11 @@ void rfkill_switch_all(enum rfkill_type type, enum rfkill_state state) rfkill_states[type] = state; list_for_each_entry(rfkill, &rfkill_list, node) { - if ((!rfkill->user_claim) && (rfkill->type == type)) + if ((!rfkill->user_claim) && (rfkill->type == type)) { + mutex_lock(&rfkill->mutex); rfkill_toggle_radio(rfkill, state, 0); + mutex_unlock(&rfkill->mutex); + } } mutex_unlock(&rfkill_mutex); @@ -227,8 +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. + * 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) { @@ -236,7 +253,9 @@ void rfkill_epo(void) mutex_lock(&rfkill_mutex); list_for_each_entry(rfkill, &rfkill_list, node) { + mutex_lock(&rfkill->mutex); rfkill_toggle_radio(rfkill, RFKILL_STATE_SOFT_BLOCKED, 1); + mutex_unlock(&rfkill->mutex); } mutex_unlock(&rfkill_mutex); } @@ -252,7 +271,12 @@ EXPORT_SYMBOL_GPL(rfkill_epo); * a notification by the firmware/hardware of the current *real* * state of the radio rfkill switch. * - * It may not be called from an atomic context. + * Devices which are subject to external changes on their rfkill + * state (such as those caused by a hardware rfkill line) MUST + * have their driver arrange to call rfkill_force_state() as soon + * as possible after such a change. + * + * This function may not be called from an atomic context. */ int rfkill_force_state(struct rfkill *rfkill, enum rfkill_state state) { @@ -367,6 +391,9 @@ static ssize_t rfkill_claim_store(struct device *dev, if (!capable(CAP_NET_ADMIN)) return -EPERM; + if (rfkill->user_claim_unsupported) + return -EOPNOTSUPP; + /* * Take the global lock to make sure the kernel is not in * the middle of rfkill_switch_all @@ -375,19 +402,17 @@ static ssize_t rfkill_claim_store(struct device *dev, if (error) return error; - if (rfkill->user_claim_unsupported) { - error = -EOPNOTSUPP; - goto out_unlock; - } if (rfkill->user_claim != claim) { - if (!claim) + if (!claim) { + mutex_lock(&rfkill->mutex); rfkill_toggle_radio(rfkill, rfkill_states[rfkill->type], 0); + mutex_unlock(&rfkill->mutex); + } rfkill->user_claim = claim; } -out_unlock: mutex_unlock(&rfkill_mutex); return error ? error : count; @@ -438,13 +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 @@ -516,8 +542,11 @@ static void rfkill_remove_switch(struct rfkill *rfkill) { mutex_lock(&rfkill_mutex); list_del_init(&rfkill->node); - rfkill_toggle_radio(rfkill, RFKILL_STATE_SOFT_BLOCKED, 1); mutex_unlock(&rfkill_mutex); + + mutex_lock(&rfkill->mutex); + rfkill_toggle_radio(rfkill, RFKILL_STATE_SOFT_BLOCKED, 1); + mutex_unlock(&rfkill->mutex); } /** @@ -526,9 +555,10 @@ static void rfkill_remove_switch(struct rfkill *rfkill) * @type: type of the switch (RFKILL_TYPE_*) * * This function should be called by the network driver when it needs - * rfkill structure. Once the structure is allocated the driver shoud - * finish its initialization by setting name, private data, enable_radio + * rfkill structure. Once the structure is allocated the driver should + * finish its initialization by setting the name, private data, enable_radio * and disable_radio methods and then register it with rfkill_register(). + * * NOTE: If registration fails the structure shoudl be freed by calling * rfkill_free() otherwise rfkill_unregister() should be used. */ @@ -560,7 +590,7 @@ EXPORT_SYMBOL(rfkill_allocate); * rfkill_free - Mark rfkill structure for deletion * @rfkill: rfkill structure to be destroyed * - * Decrements reference count of rfkill structure so it is destroyed. + * Decrements reference count of the rfkill structure so it is destroyed. * Note that rfkill_free() should _not_ be called after rfkill_unregister(). */ void rfkill_free(struct rfkill *rfkill) @@ -575,7 +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; @@ -585,8 +618,10 @@ static void rfkill_led_trigger_register(struct rfkill *rfkill) static void rfkill_led_trigger_unregister(struct rfkill *rfkill) { #ifdef CONFIG_RFKILL_LEDS - if (rfkill->led_trigger.name) + if (rfkill->led_trigger.name) { led_trigger_unregister(&rfkill->led_trigger); + rfkill->led_trigger.name = NULL; + } #endif } @@ -622,8 +657,8 @@ int rfkill_register(struct rfkill *rfkill) error = device_add(dev); if (error) { - rfkill_led_trigger_unregister(rfkill); rfkill_remove_switch(rfkill); + rfkill_led_trigger_unregister(rfkill); return error; } diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index dbc963b4f5fb..a7f1ce11bc22 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -74,6 +74,7 @@ ax25_address rose_callsign; * separate class since they always nest. */ static struct lock_class_key rose_netdev_xmit_lock_key; +static struct lock_class_key rose_netdev_addr_lock_key; static void rose_set_lockdep_one(struct net_device *dev, struct netdev_queue *txq, @@ -84,6 +85,7 @@ static void rose_set_lockdep_one(struct net_device *dev, static void rose_set_lockdep_key(struct net_device *dev) { + lockdep_set_class(&dev->addr_list_lock, &rose_netdev_addr_lock_key); netdev_for_each_tx_queue(dev, rose_set_lockdep_one, NULL); } diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 4b2682feeedc..32e489118beb 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -660,9 +660,9 @@ static void rxrpc_sock_destructor(struct sock *sk) rxrpc_purge_queue(&sk->sk_receive_queue); - BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc)); - BUG_TRAP(sk_unhashed(sk)); - BUG_TRAP(!sk->sk_socket); + WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(!sk_unhashed(sk)); + WARN_ON(sk->sk_socket); if (!sock_flag(sk, SOCK_DEAD)) { printk("Attempt to release alive rxrpc socket: %p\n", sk); 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 74e662cbb2c5..9974b3f04f05 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -41,7 +41,7 @@ void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo) return; } } - BUG_TRAP(0); + WARN_ON(1); } EXPORT_SYMBOL(tcf_hash_destroy); @@ -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/act_police.c b/net/sched/act_police.c index 32c3f9d9fb7a..38015b493947 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -116,7 +116,7 @@ static void tcf_police_destroy(struct tcf_police *p) return; } } - BUG_TRAP(0); + WARN_ON(1); } static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { 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/cls_u32.c b/net/sched/cls_u32.c index 527db2559dd2..246f9065ce34 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -345,7 +345,7 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode* key) } } } - BUG_TRAP(0); + WARN_ON(1); return 0; } @@ -368,7 +368,7 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) struct tc_u_common *tp_c = tp->data; struct tc_u_hnode **hn; - BUG_TRAP(!ht->refcnt); + WARN_ON(ht->refcnt); u32_clear_hnode(tp, ht); @@ -380,7 +380,7 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) } } - BUG_TRAP(0); + WARN_ON(1); return -ENOENT; } @@ -389,7 +389,7 @@ static void u32_destroy(struct tcf_proto *tp) struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *root_ht = xchg(&tp->root, NULL); - BUG_TRAP(root_ht != NULL); + WARN_ON(root_ht == NULL); if (root_ht && --root_ht->refcnt == 0) u32_destroy_hnode(tp, root_ht); @@ -407,7 +407,7 @@ static void u32_destroy(struct tcf_proto *tp) while ((ht = tp_c->hlist) != NULL) { tp_c->hlist = ht->next; - BUG_TRAP(ht->refcnt == 0); + WARN_ON(ht->refcnt != 0); kfree(ht); } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 5219d5f9d754..ef0efeca6352 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 +184,34 @@ 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; +} + struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) { unsigned int i; 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 *q, *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) + return q; } - return NULL; + return qdisc_match_from_root(dev->rx_queue.qdisc_sleeping, handle); } static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) @@ -416,7 +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; } @@ -447,7 +458,7 @@ void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) } EXPORT_SYMBOL(qdisc_watchdog_cancel); -struct hlist_head *qdisc_class_hash_alloc(unsigned int n) +static struct hlist_head *qdisc_class_hash_alloc(unsigned int n) { unsigned int size = n * sizeof(struct hlist_head), i; struct hlist_head *h; @@ -572,44 +583,21 @@ static u32 qdisc_alloc_handle(struct net_device *dev) static struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc) { + struct Qdisc *oqdisc = dev_queue->qdisc_sleeping; spinlock_t *root_lock; - struct Qdisc *oqdisc; - int ingress; - - ingress = 0; - if (qdisc && qdisc->flags&TCQ_F_INGRESS) - ingress = 1; - - if (ingress) { - oqdisc = dev_queue->qdisc; - } else { - oqdisc = dev_queue->qdisc_sleeping; - } root_lock = qdisc_root_lock(oqdisc); spin_lock_bh(root_lock); - if (ingress) { - /* Prune old scheduler */ - if (oqdisc && atomic_read(&oqdisc->refcnt) <= 1) { - /* delete */ - qdisc_reset(oqdisc); - dev_queue->qdisc = NULL; - } else { /* new */ - dev_queue->qdisc = qdisc; - } + /* Prune old scheduler */ + if (oqdisc && atomic_read(&oqdisc->refcnt) <= 1) + qdisc_reset(oqdisc); - } else { - /* Prune old scheduler */ - if (oqdisc && atomic_read(&oqdisc->refcnt) <= 1) - qdisc_reset(oqdisc); - - /* ... and graft new one */ - if (qdisc == NULL) - qdisc = &noop_qdisc; - dev_queue->qdisc_sleeping = qdisc; - dev_queue->qdisc = &noop_qdisc; - } + /* ... and graft new one */ + if (qdisc == NULL) + qdisc = &noop_qdisc; + dev_queue->qdisc_sleeping = qdisc; + dev_queue->qdisc = &noop_qdisc; spin_unlock_bh(root_lock); @@ -650,11 +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 @@ -678,7 +663,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, ingress = 0; num_q = dev->num_tx_queues; - if (q && q->flags & TCQ_F_INGRESS) { + if ((q && q->flags & TCQ_F_INGRESS) || + (new && new->flags & TCQ_F_INGRESS)) { num_q = 1; ingress = 1; } @@ -692,13 +678,10 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if (!ingress) dev_queue = netdev_get_tx_queue(dev, i); - if (ingress) { - old = dev_graft_qdisc(dev_queue, q); - } else { - old = dev_graft_qdisc(dev_queue, new); - if (new && i > 0) - atomic_inc(&new->refcnt); - } + old = dev_graft_qdisc(dev_queue, new); + if (new && i > 0) + atomic_inc(&new->refcnt); + notify_and_destroy(skb, n, classid, old, new); } @@ -722,6 +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. @@ -782,6 +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); @@ -789,6 +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; @@ -817,8 +806,8 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, goto err_out3; } } - if (parent) - list_add_tail(&sch->list, &dev_queue->qdisc->list); + if ((parent != TC_H_ROOT) && !(sch->flags & TCQ_F_INGRESS)) + list_add_tail(&sch->list, &dev_queue->qdisc_sleeping->list); return sch; } @@ -933,7 +922,7 @@ 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; @@ -1003,7 +992,7 @@ 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; @@ -1099,20 +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; } @@ -1261,11 +1243,11 @@ 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: @@ -1554,11 +1536,11 @@ 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 04faa835be17..43d37256c15e 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -162,7 +162,7 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl) qdisc_destroy(flow->q); tcf_destroy_chain(&flow->filter_list); if (flow->sock) { - pr_debug("atm_tc_put: f_count %d\n", + pr_debug("atm_tc_put: f_count %ld\n", file_count(flow->sock->file)); flow->vcc->pop = flow->old_pop; sockfd_put(flow->sock); @@ -259,7 +259,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, sock = sockfd_lookup(fd, &error); if (!sock) return error; /* f_count++ */ - pr_debug("atm_tc_change: f_count %d\n", file_count(sock->file)); + pr_debug("atm_tc_change: f_count %ld\n", file_count(sock->file)); if (sock->ops->family != PF_ATMSVC && sock->ops->family != PF_ATMPVC) { error = -EPROTOTYPE; goto err_out; @@ -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 f1d2f8ec8b4c..47ef492c4ff4 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; } @@ -650,7 +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; } @@ -664,13 +668,15 @@ 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 +684,8 @@ 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; } @@ -1175,7 +1182,7 @@ static void cbq_unlink_class(struct cbq_class *this) this->tparent->children = NULL; } } else { - BUG_TRAP(this->sibling == this); + WARN_ON(this->sibling != this); } } @@ -1699,7 +1706,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) { struct cbq_sched_data *q = qdisc_priv(sch); - BUG_TRAP(!cl->filters); + WARN_ON(cl->filters); tcf_destroy_chain(&cl->filter_list); qdisc_destroy(cl->q); 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 cb625b4d6da5..c3ed4d44fc14 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); @@ -135,7 +135,8 @@ static inline int qdisc_restart(struct Qdisc *q) txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); HARD_TX_LOCK(dev, txq, smp_processor_id()); - if (!netif_subqueue_stopped(dev, skb)) + if (!netif_tx_queue_stopped(txq) && + !netif_tx_queue_frozen(txq)) ret = dev_hard_start_xmit(skb, dev, txq); HARD_TX_UNLOCK(dev, txq); @@ -162,7 +163,8 @@ static inline int qdisc_restart(struct Qdisc *q) break; } - if (ret && netif_tx_queue_stopped(txq)) + if (ret && (netif_tx_queue_stopped(txq) || + netif_tx_queue_frozen(txq))) ret = 0; return ret; @@ -212,9 +214,9 @@ static void dev_watchdog(unsigned long arg) if (some_queue_stopped && time_after(jiffies, (dev->trans_start + dev->watchdog_timeo))) { - printk(KERN_INFO "NETDEV WATCHDOG: %s: " - "transmit timed out\n", - dev->name); + char drivername[64]; + printk(KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit timed out\n", + dev->name, netdev_drivername(dev, drivername, 64)); dev->tx_timeout(dev); WARN_ON_ONCE(1); } @@ -505,7 +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) { @@ -516,14 +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 @@ -540,20 +545,6 @@ 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) @@ -595,8 +586,11 @@ 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 (new_qdisc != &noqueue_qdisc) + if (need_watchdog_p && new_qdisc != &noqueue_qdisc) *need_watchdog_p = 1; } @@ -619,6 +613,7 @@ void dev_activate(struct net_device *dev) need_watchdog = 0; netdev_for_each_tx_queue(dev, transition_one_qdisc, &need_watchdog); + transition_one_qdisc(dev, &dev->rx_queue, NULL); if (need_watchdog) { dev->trans_start = jiffies; @@ -637,6 +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); @@ -644,7 +642,7 @@ 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; @@ -655,16 +653,15 @@ 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; @@ -674,9 +671,8 @@ 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); dev_watchdog_down(dev); @@ -684,25 +680,8 @@ 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, @@ -718,7 +697,7 @@ static void dev_init_scheduler_queue(struct net_device *dev, void dev_init_scheduler(struct net_device *dev) { netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc); - dev_init_scheduler_queue(dev, &dev->rx_queue, NULL); + dev_init_scheduler_queue(dev, &dev->rx_queue, &noop_qdisc); setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev); } @@ -731,20 +710,16 @@ 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(root_lock); qdisc_destroy(qdisc); - spin_unlock(root_lock); } } void dev_shutdown(struct net_device *dev) { netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); - shutdown_scheduler_queue(dev, &dev->rx_queue, NULL); - BUG_TRAP(!timer_pending(&dev->watchdog_timer)); + shutdown_scheduler_queue(dev, &dev->rx_queue, &noop_qdisc); + WARN_ON(timer_pending(&dev->watchdog_timer)); } 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 30c999c61b01..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; } @@ -524,7 +524,7 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, long *diff) */ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) { - BUG_TRAP(!cl->level && cl->un.leaf.q && cl->un.leaf.q->q.qlen); + WARN_ON(cl->level || !cl->un.leaf.q || !cl->un.leaf.q->q.qlen); if (!cl->prio_activity) { cl->prio_activity = 1 << (cl->un.leaf.aprio = cl->un.leaf.prio); @@ -542,7 +542,7 @@ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) */ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) { - BUG_TRAP(cl->prio_activity); + WARN_ON(!cl->prio_activity); htb_deactivate_prios(q, cl); cl->prio_activity = 0; @@ -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); @@ -757,7 +761,7 @@ static struct htb_class *htb_lookup_leaf(struct rb_root *tree, int prio, u32 *pid; } stk[TC_HTB_MAXDEPTH], *sp = stk; - BUG_TRAP(tree->rb_node); + WARN_ON(!tree->rb_node); sp->root = tree->rb_node; sp->pptr = pptr; sp->pid = pid; @@ -777,7 +781,7 @@ static struct htb_class *htb_lookup_leaf(struct rb_root *tree, int prio, *sp->pptr = (*sp->pptr)->rb_left; if (sp > stk) { sp--; - BUG_TRAP(*sp->pptr); + WARN_ON(!*sp->pptr); if (!*sp->pptr) return NULL; htb_next_rb_node(sp->pptr); @@ -792,7 +796,7 @@ static struct htb_class *htb_lookup_leaf(struct rb_root *tree, int prio, sp->pid = cl->un.inner.last_ptr_id + prio; } } - BUG_TRAP(0); + WARN_ON(1); return NULL; } @@ -810,7 +814,7 @@ static struct sk_buff *htb_dequeue_tree(struct htb_sched *q, int prio, do { next: - BUG_TRAP(cl); + WARN_ON(!cl); if (!cl) return NULL; @@ -1185,7 +1189,7 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, { struct htb_class *parent = cl->parent; - BUG_TRAP(!cl->level && cl->un.leaf.q && !cl->prio_activity); + WARN_ON(cl->level || !cl->un.leaf.q || cl->prio_activity); if (parent->cmode != HTB_CAN_SEND) htb_safe_rb_erase(&parent->pq_node, q->wait_pq + parent->level); @@ -1205,7 +1209,7 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) { if (!cl->level) { - BUG_TRAP(cl->un.leaf.q); + WARN_ON(!cl->un.leaf.q); qdisc_destroy(cl->un.leaf.q); } gen_kill_estimator(&cl->bstats, &cl->rate_est); @@ -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/sched/sch_teql.c b/net/sched/sch_teql.c index 537223642b6e..2c35c678563b 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -305,10 +305,11 @@ restart: switch (teql_resolve(skb, skb_res, slave)) { case 0: - if (netif_tx_trylock(slave)) { - if (!__netif_subqueue_stopped(slave, subq) && + if (__netif_tx_trylock(slave_txq)) { + if (!netif_tx_queue_stopped(slave_txq) && + !netif_tx_queue_frozen(slave_txq) && slave->hard_start_xmit(skb, slave) == 0) { - netif_tx_unlock(slave); + __netif_tx_unlock(slave_txq); master->slaves = NEXT_SLAVE(q); netif_wake_queue(dev); master->stats.tx_packets++; @@ -316,7 +317,7 @@ restart: qdisc_pkt_len(skb); return 0; } - netif_tx_unlock(slave); + __netif_tx_unlock(slave_txq); } if (netif_queue_stopped(dev)) busy = 1; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index ec2a0a33fd78..8472b8b349c4 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -464,7 +464,7 @@ static void sctp_association_destroy(struct sctp_association *asoc) spin_unlock_bh(&sctp_assocs_id_lock); } - BUG_TRAP(!atomic_read(&asoc->rmem_alloc)); + WARN_ON(atomic_read(&asoc->rmem_alloc)); if (asoc->base.malloced) { kfree(asoc); 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/outqueue.c b/net/sctp/outqueue.c index 70ead8dc3485..4328ad5439c9 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -71,6 +71,8 @@ static void sctp_mark_missing(struct sctp_outq *q, static void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 sack_ctsn); +static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout); + /* Add data to the front of the queue. */ static inline void sctp_outq_head_data(struct sctp_outq *q, struct sctp_chunk *ch) @@ -712,7 +714,7 @@ int sctp_outq_uncork(struct sctp_outq *q) * locking concerns must be made. Today we use the sock lock to protect * this function. */ -int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) +static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) { struct sctp_packet *packet; struct sctp_packet singleton; diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 5dd89831eceb..f268910620be 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -519,8 +519,3 @@ int __init sctp_remaddr_proc_init(void) return 0; } - -void sctp_assoc_proc_exit(void) -{ - remove_proc_entry("remaddr", proc_net_sctp); -} 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 79bece16aede..dbb79adf8f3c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3910,7 +3910,7 @@ static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval goto out; /* Map the socket to an unused fd that can be returned to the user. */ - retval = sock_map_fd(newsock); + retval = sock_map_fd(newsock, 0); if (retval < 0) { sock_release(newsock); goto out; diff --git a/net/socket.c b/net/socket.c index 1ba57d888981..8ef8ba81b9e2 100644 --- a/net/socket.c +++ b/net/socket.c @@ -63,11 +63,13 @@ #include <linux/file.h> #include <linux/net.h> #include <linux/interrupt.h> +#include <linux/thread_info.h> #include <linux/rcupdate.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/mutex.h> +#include <linux/thread_info.h> #include <linux/wanrouter.h> #include <linux/if_bridge.h> #include <linux/if_frad.h> @@ -263,7 +265,7 @@ static void sock_destroy_inode(struct inode *inode) container_of(inode, struct socket_alloc, vfs_inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct socket_alloc *ei = (struct socket_alloc *)foo; @@ -349,11 +351,11 @@ static struct dentry_operations sockfs_dentry_operations = { * but we take care of internal coherence yet. */ -static int sock_alloc_fd(struct file **filep) +static int sock_alloc_fd(struct file **filep, int flags) { int fd; - fd = get_unused_fd(); + fd = get_unused_fd_flags(flags); if (likely(fd >= 0)) { struct file *file = get_empty_filp(); @@ -367,7 +369,7 @@ static int sock_alloc_fd(struct file **filep) return fd; } -static int sock_attach_fd(struct socket *sock, struct file *file) +static int sock_attach_fd(struct socket *sock, struct file *file, int flags) { struct dentry *dentry; struct qstr name = { .name = "" }; @@ -389,20 +391,20 @@ static int sock_attach_fd(struct socket *sock, struct file *file) init_file(file, sock_mnt, dentry, FMODE_READ | FMODE_WRITE, &socket_file_ops); SOCK_INODE(sock)->i_fop = &socket_file_ops; - file->f_flags = O_RDWR; + file->f_flags = O_RDWR | (flags & O_NONBLOCK); file->f_pos = 0; file->private_data = sock; return 0; } -int sock_map_fd(struct socket *sock) +int sock_map_fd(struct socket *sock, int flags) { struct file *newfile; - int fd = sock_alloc_fd(&newfile); + int fd = sock_alloc_fd(&newfile, flags); if (likely(fd >= 0)) { - int err = sock_attach_fd(sock, newfile); + int err = sock_attach_fd(sock, newfile, flags); if (unlikely(err < 0)) { put_filp(newfile); @@ -1218,12 +1220,27 @@ asmlinkage long sys_socket(int family, int type, int protocol) { int retval; struct socket *sock; + int flags; + + /* Check the SOCK_* constants for consistency. */ + BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); + BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK); + BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK); + BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK); + + flags = type & ~SOCK_TYPE_MASK; + if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + type &= SOCK_TYPE_MASK; + + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; retval = sock_create(family, type, protocol, &sock); if (retval < 0) goto out; - retval = sock_map_fd(sock); + retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); if (retval < 0) goto out_release; @@ -1246,6 +1263,15 @@ asmlinkage long sys_socketpair(int family, int type, int protocol, struct socket *sock1, *sock2; int fd1, fd2, err; struct file *newfile1, *newfile2; + int flags; + + flags = type & ~SOCK_TYPE_MASK; + if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + type &= SOCK_TYPE_MASK; + + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; /* * Obtain the first socket and check if the underlying protocol @@ -1264,13 +1290,13 @@ asmlinkage long sys_socketpair(int family, int type, int protocol, if (err < 0) goto out_release_both; - fd1 = sock_alloc_fd(&newfile1); + fd1 = sock_alloc_fd(&newfile1, flags & O_CLOEXEC); if (unlikely(fd1 < 0)) { err = fd1; goto out_release_both; } - fd2 = sock_alloc_fd(&newfile2); + fd2 = sock_alloc_fd(&newfile2, flags & O_CLOEXEC); if (unlikely(fd2 < 0)) { err = fd2; put_filp(newfile1); @@ -1278,12 +1304,12 @@ asmlinkage long sys_socketpair(int family, int type, int protocol, goto out_release_both; } - err = sock_attach_fd(sock1, newfile1); + err = sock_attach_fd(sock1, newfile1, flags & O_NONBLOCK); if (unlikely(err < 0)) { goto out_fd2; } - err = sock_attach_fd(sock2, newfile2); + err = sock_attach_fd(sock2, newfile2, flags & O_NONBLOCK); if (unlikely(err < 0)) { fput(newfile1); goto out_fd1; @@ -1401,14 +1427,20 @@ asmlinkage long sys_listen(int fd, int backlog) * clean when we restucture accept also. */ -asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen) +long do_accept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; int err, len, newfd, fput_needed; struct sockaddr_storage address; + if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -1426,14 +1458,14 @@ asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, */ __module_get(newsock->ops->owner); - newfd = sock_alloc_fd(&newfile); + newfd = sock_alloc_fd(&newfile, flags & O_CLOEXEC); if (unlikely(newfd < 0)) { err = newfd; sock_release(newsock); goto out_put; } - err = sock_attach_fd(newsock, newfile); + err = sock_attach_fd(newsock, newfile, flags & O_NONBLOCK); if (err < 0) goto out_fd_simple; @@ -1479,6 +1511,66 @@ out_fd: goto out_put; } +#ifdef HAVE_SET_RESTORE_SIGMASK +asmlinkage long sys_paccept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, + const sigset_t __user *sigmask, + size_t sigsetsize, int flags) +{ + sigset_t ksigmask, sigsaved; + int ret; + + if (sigmask) { + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask))) + return -EFAULT; + + sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + } + + ret = do_accept(fd, upeer_sockaddr, upeer_addrlen, flags); + + if (ret < 0 && signal_pending(current)) { + /* + * Don't restore the signal mask yet. Let do_signal() deliver + * the signal on the way back to userspace, before the signal + * mask is restored. + */ + if (sigmask) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_restore_sigmask(); + } + } else if (sigmask) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + + return ret; +} +#else +asmlinkage long sys_paccept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, + const sigset_t __user *sigmask, + size_t sigsetsize, int flags) +{ + /* The platform does not support restoring the signal mask in the + * return path. So we do not allow using paccept() with a signal + * mask. */ + if (sigmask) + return -EINVAL; + + return do_accept(fd, upeer_sockaddr, upeer_addrlen, flags); +} +#endif + +asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen) +{ + return do_accept(fd, upeer_sockaddr, upeer_addrlen, 0); +} + /* * Attempt to connect to a socket with the server address. The address * is in user space so we verify it is OK and move it to kernel space. @@ -1999,10 +2091,11 @@ out: /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) -static const unsigned char nargs[18]={ +static const unsigned char nargs[19]={ AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), AL(3),AL(3),AL(4),AL(4),AL(4),AL(6), - AL(6),AL(2),AL(5),AL(5),AL(3),AL(3) + AL(6),AL(2),AL(5),AL(5),AL(3),AL(3), + AL(6) }; #undef AL @@ -2021,7 +2114,7 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) unsigned long a0, a1; int err; - if (call < 1 || call > SYS_RECVMSG) + if (call < 1 || call > SYS_PACCEPT) return -EINVAL; /* copy_from_user should be SMP safe. */ @@ -2050,8 +2143,8 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) break; case SYS_ACCEPT: err = - sys_accept(a0, (struct sockaddr __user *)a1, - (int __user *)a[2]); + do_accept(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], 0); break; case SYS_GETSOCKNAME: err = @@ -2098,6 +2191,13 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) case SYS_RECVMSG: err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]); break; + case SYS_PACCEPT: + err = + sys_paccept(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], + (const sigset_t __user *) a[3], + a[4], a[5]); + break; default: err = -EINVAL; break; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 5a9b0e7828cd..23a2b8f6dc49 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -897,7 +897,7 @@ static struct file_system_type rpc_pipe_fs_type = { }; static void -init_once(struct kmem_cache * cachep, void *foo) +init_once(void *foo) { struct rpc_inode *rpci = (struct rpc_inode *) foo; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index a19b22b452a3..84d328329d98 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -169,7 +169,8 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, (void *) vec->sge[xdr_sge_no].iov_base + sge_off, sge_bytes, DMA_TO_DEVICE); - if (dma_mapping_error(sge[sge_no].addr)) + if (dma_mapping_error(xprt->sc_cm_id->device->dma_device, + sge[sge_no].addr)) goto err; sge_off = 0; sge_no++; diff --git a/net/sysctl_net.c b/net/sysctl_net.c index 007c1a6708ee..972201cd5fa7 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -29,23 +29,35 @@ #include <linux/if_tr.h> #endif -static struct list_head * +static struct ctl_table_set * net_ctl_header_lookup(struct ctl_table_root *root, struct nsproxy *namespaces) { - return &namespaces->net_ns->sysctl_table_headers; + return &namespaces->net_ns->sysctls; } -static struct ctl_table_root net_sysctl_root = { - .lookup = net_ctl_header_lookup, -}; +static int is_seen(struct ctl_table_set *set) +{ + return ¤t->nsproxy->net_ns->sysctls == set; +} -static LIST_HEAD(net_sysctl_ro_tables); -static struct list_head *net_ctl_ro_header_lookup(struct ctl_table_root *root, - struct nsproxy *namespaces) +/* Return standard mode bits for table entry. */ +static int net_ctl_permissions(struct ctl_table_root *root, + struct nsproxy *nsproxy, + struct ctl_table *table) { - return &net_sysctl_ro_tables; + /* Allow network administrator to have same access as root. */ + if (capable(CAP_NET_ADMIN)) { + int mode = (table->mode >> 6) & 7; + return (mode << 6) | (mode << 3) | mode; + } + return table->mode; } +static struct ctl_table_root net_sysctl_root = { + .lookup = net_ctl_header_lookup, + .permissions = net_ctl_permissions, +}; + static int net_ctl_ro_header_perms(struct ctl_table_root *root, struct nsproxy *namespaces, struct ctl_table *table) { @@ -56,19 +68,20 @@ static int net_ctl_ro_header_perms(struct ctl_table_root *root, } static struct ctl_table_root net_sysctl_ro_root = { - .lookup = net_ctl_ro_header_lookup, .permissions = net_ctl_ro_header_perms, }; static int sysctl_net_init(struct net *net) { - INIT_LIST_HEAD(&net->sysctl_table_headers); + setup_sysctl_set(&net->sysctls, + &net_sysctl_ro_root.default_set, + is_seen); return 0; } static void sysctl_net_exit(struct net *net) { - WARN_ON(!list_empty(&net->sysctl_table_headers)); + WARN_ON(!list_empty(&net->sysctls.list)); return; } @@ -84,6 +97,7 @@ static __init int sysctl_init(void) if (ret) goto out; register_sysctl_root(&net_sysctl_root); + setup_sysctl_set(&net_sysctl_ro_root.default_set, NULL, NULL); register_sysctl_root(&net_sysctl_ro_root); out: return ret; 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/unix/af_unix.c b/net/unix/af_unix.c index 70ceb1604ad8..015606b54d9b 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -227,7 +227,7 @@ static void __unix_remove_socket(struct sock *sk) static void __unix_insert_socket(struct hlist_head *list, struct sock *sk) { - BUG_TRAP(sk_unhashed(sk)); + WARN_ON(!sk_unhashed(sk)); sk_add_node(sk, list); } @@ -350,9 +350,9 @@ static void unix_sock_destructor(struct sock *sk) skb_queue_purge(&sk->sk_receive_queue); - BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc)); - BUG_TRAP(sk_unhashed(sk)); - BUG_TRAP(!sk->sk_socket); + WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(!sk_unhashed(sk)); + WARN_ON(sk->sk_socket); if (!sock_flag(sk, SOCK_DEAD)) { printk("Attempt to release alive unix socket: %p\n", sk); return; @@ -603,7 +603,7 @@ static struct sock * unix_create1(struct net *net, struct socket *sock) u->dentry = NULL; u->mnt = NULL; spin_lock_init(&u->lock); - atomic_set(&u->inflight, 0); + atomic_long_set(&u->inflight, 0); INIT_LIST_HEAD(&u->link); mutex_init(&u->readlock); /* single task reading lock */ init_waitqueue_head(&u->peer_wait); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index ebdff3d877a1..2a27b84f740b 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -127,7 +127,7 @@ void unix_inflight(struct file *fp) if(s) { struct unix_sock *u = unix_sk(s); spin_lock(&unix_gc_lock); - if (atomic_inc_return(&u->inflight) == 1) { + if (atomic_long_inc_return(&u->inflight) == 1) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); } else { @@ -145,7 +145,7 @@ void unix_notinflight(struct file *fp) struct unix_sock *u = unix_sk(s); spin_lock(&unix_gc_lock); BUG_ON(list_empty(&u->link)); - if (atomic_dec_and_test(&u->inflight)) + if (atomic_long_dec_and_test(&u->inflight)) list_del_init(&u->link); unix_tot_inflight--; spin_unlock(&unix_gc_lock); @@ -237,17 +237,17 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *), static void dec_inflight(struct unix_sock *usk) { - atomic_dec(&usk->inflight); + atomic_long_dec(&usk->inflight); } static void inc_inflight(struct unix_sock *usk) { - atomic_inc(&usk->inflight); + atomic_long_inc(&usk->inflight); } static void inc_inflight_move_tail(struct unix_sock *u) { - atomic_inc(&u->inflight); + atomic_long_inc(&u->inflight); /* * If this is still a candidate, move it to the end of the * list, so that it's checked even if it was already passed @@ -288,11 +288,11 @@ void unix_gc(void) * before the detach without atomicity guarantees. */ list_for_each_entry_safe(u, next, &gc_inflight_list, link) { - int total_refs; - int inflight_refs; + long total_refs; + long inflight_refs; total_refs = file_count(u->sk.sk_socket->file); - inflight_refs = atomic_read(&u->inflight); + inflight_refs = atomic_long_read(&u->inflight); BUG_ON(inflight_refs < 1); BUG_ON(total_refs < inflight_refs); @@ -324,7 +324,7 @@ void unix_gc(void) /* Move cursor to after the current position. */ list_move(&cursor, &u->link); - if (atomic_read(&u->inflight) > 0) { + if (atomic_long_read(&u->inflight) > 0) { list_move_tail(&u->link, &gc_inflight_list); u->gc_candidate = 0; scan_children(&u->sk, inc_inflight_move_tail, NULL); 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/nl80211.c b/net/wireless/nl80211.c index b7fefffd2d0d..59eb2cf42e5f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -29,16 +29,16 @@ static struct genl_family nl80211_fam = { }; /* internal helper: get drv and dev */ -static int get_drv_dev_by_info_ifindex(struct genl_info *info, +static int get_drv_dev_by_info_ifindex(struct nlattr **attrs, struct cfg80211_registered_device **drv, struct net_device **dev) { int ifindex; - if (!info->attrs[NL80211_ATTR_IFINDEX]) + if (!attrs[NL80211_ATTR_IFINDEX]) return -EINVAL; - ifindex = nla_get_u32(info->attrs[NL80211_ATTR_IFINDEX]); + ifindex = nla_get_u32(attrs[NL80211_ATTR_IFINDEX]); *dev = dev_get_by_index(&init_net, ifindex); if (!*dev) return -ENODEV; @@ -291,21 +291,31 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * mutex_lock(&cfg80211_drv_mutex); list_for_each_entry(dev, &cfg80211_drv_list, list) { - if (++wp_idx < wp_start) + if (wp_idx < wp_start) { + wp_idx++; continue; + } if_idx = 0; mutex_lock(&dev->devlist_mtx); list_for_each_entry(wdev, &dev->netdev_list, list) { - if (++if_idx < if_start) + if (if_idx < if_start) { + if_idx++; continue; + } if (nl80211_send_iface(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - wdev->netdev) < 0) - break; + wdev->netdev) < 0) { + mutex_unlock(&dev->devlist_mtx); + goto out; + } + if_idx++; } mutex_unlock(&dev->devlist_mtx); + + wp_idx++; } + out: mutex_unlock(&cfg80211_drv_mutex); cb->args[0] = wp_idx; @@ -321,7 +331,7 @@ static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info) struct net_device *netdev; int err; - err = get_drv_dev_by_info_ifindex(info, &dev, &netdev); + err = get_drv_dev_by_info_ifindex(info->attrs, &dev, &netdev); if (err) return err; @@ -392,7 +402,7 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) } else return -EINVAL; - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; ifindex = dev->ifindex; @@ -477,7 +487,7 @@ static int nl80211_del_interface(struct sk_buff *skb, struct genl_info *info) int ifindex, err; struct net_device *dev; - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; ifindex = dev->ifindex; @@ -545,7 +555,7 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; @@ -618,7 +628,7 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NL80211_ATTR_KEY_DEFAULT]) return -EINVAL; - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; @@ -699,7 +709,7 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; @@ -735,7 +745,7 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; @@ -764,7 +774,7 @@ static int nl80211_addset_beacon(struct sk_buff *skb, struct genl_info *info) struct beacon_parameters params; int haveinfo = 0; - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; @@ -843,7 +853,7 @@ static int nl80211_del_beacon(struct sk_buff *skb, struct genl_info *info) int err; struct net_device *dev; - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; @@ -937,67 +947,78 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, } static int nl80211_dump_station(struct sk_buff *skb, - struct netlink_callback *cb) + struct netlink_callback *cb) { - int wp_idx = 0; - int if_idx = 0; - int sta_idx = cb->args[2]; - int wp_start = cb->args[0]; - int if_start = cb->args[1]; struct station_info sinfo; struct cfg80211_registered_device *dev; - struct wireless_dev *wdev; + struct net_device *netdev; u8 mac_addr[ETH_ALEN]; + int ifidx = cb->args[0]; + int sta_idx = cb->args[1]; int err; - int exit = 0; - /* TODO: filter by device */ - mutex_lock(&cfg80211_drv_mutex); - list_for_each_entry(dev, &cfg80211_drv_list, list) { - if (exit) + if (!ifidx) { + err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, + nl80211_fam.attrbuf, nl80211_fam.maxattr, + nl80211_policy); + if (err) + return err; + + if (!nl80211_fam.attrbuf[NL80211_ATTR_IFINDEX]) + return -EINVAL; + + ifidx = nla_get_u32(nl80211_fam.attrbuf[NL80211_ATTR_IFINDEX]); + if (!ifidx) + return -EINVAL; + } + + netdev = dev_get_by_index(&init_net, ifidx); + if (!netdev) + return -ENODEV; + + dev = cfg80211_get_dev_from_ifindex(ifidx); + if (IS_ERR(dev)) { + err = PTR_ERR(dev); + goto out_put_netdev; + } + + if (!dev->ops->dump_station) { + err = -ENOSYS; + goto out_err; + } + + rtnl_lock(); + + while (1) { + err = dev->ops->dump_station(&dev->wiphy, netdev, sta_idx, + mac_addr, &sinfo); + if (err == -ENOENT) break; - if (++wp_idx < wp_start) - continue; - if_idx = 0; + if (err) + goto out_err_rtnl; - mutex_lock(&dev->devlist_mtx); - list_for_each_entry(wdev, &dev->netdev_list, list) { - if (exit) - break; - if (++if_idx < if_start) - continue; - if (!dev->ops->dump_station) - continue; + if (nl80211_send_station(skb, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + netdev, mac_addr, + &sinfo) < 0) + goto out; - for (;; ++sta_idx) { - rtnl_lock(); - err = dev->ops->dump_station(&dev->wiphy, - wdev->netdev, sta_idx, mac_addr, - &sinfo); - rtnl_unlock(); - if (err) { - sta_idx = 0; - break; - } - if (nl80211_send_station(skb, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - wdev->netdev, mac_addr, - &sinfo) < 0) { - exit = 1; - break; - } - } - } - mutex_unlock(&dev->devlist_mtx); + sta_idx++; } - mutex_unlock(&cfg80211_drv_mutex); - cb->args[0] = wp_idx; - cb->args[1] = if_idx; - cb->args[2] = sta_idx; - return skb->len; + out: + cb->args[1] = sta_idx; + err = skb->len; + out_err_rtnl: + rtnl_unlock(); + out_err: + cfg80211_put_dev(dev); + out_put_netdev: + dev_put(netdev); + + return err; } static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) @@ -1016,7 +1037,7 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; @@ -1112,7 +1133,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) params.plink_action = nla_get_u8(info->attrs[NL80211_ATTR_STA_PLINK_ACTION]); - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; @@ -1172,7 +1193,7 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) ¶ms.station_flags)) return -EINVAL; - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; @@ -1207,7 +1228,7 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; @@ -1277,68 +1298,78 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 pid, u32 seq, } static int nl80211_dump_mpath(struct sk_buff *skb, - struct netlink_callback *cb) + struct netlink_callback *cb) { - int wp_idx = 0; - int if_idx = 0; - int sta_idx = cb->args[2]; - int wp_start = cb->args[0]; - int if_start = cb->args[1]; struct mpath_info pinfo; struct cfg80211_registered_device *dev; - struct wireless_dev *wdev; + struct net_device *netdev; u8 dst[ETH_ALEN]; u8 next_hop[ETH_ALEN]; + int ifidx = cb->args[0]; + int path_idx = cb->args[1]; int err; - int exit = 0; - /* TODO: filter by device */ - mutex_lock(&cfg80211_drv_mutex); - list_for_each_entry(dev, &cfg80211_drv_list, list) { - if (exit) + if (!ifidx) { + err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, + nl80211_fam.attrbuf, nl80211_fam.maxattr, + nl80211_policy); + if (err) + return err; + + if (!nl80211_fam.attrbuf[NL80211_ATTR_IFINDEX]) + return -EINVAL; + + ifidx = nla_get_u32(nl80211_fam.attrbuf[NL80211_ATTR_IFINDEX]); + if (!ifidx) + return -EINVAL; + } + + netdev = dev_get_by_index(&init_net, ifidx); + if (!netdev) + return -ENODEV; + + dev = cfg80211_get_dev_from_ifindex(ifidx); + if (IS_ERR(dev)) { + err = PTR_ERR(dev); + goto out_put_netdev; + } + + if (!dev->ops->dump_mpath) { + err = -ENOSYS; + goto out_err; + } + + rtnl_lock(); + + while (1) { + err = dev->ops->dump_mpath(&dev->wiphy, netdev, path_idx, + dst, next_hop, &pinfo); + if (err == -ENOENT) break; - if (++wp_idx < wp_start) - continue; - if_idx = 0; + if (err) + goto out_err_rtnl; - mutex_lock(&dev->devlist_mtx); - list_for_each_entry(wdev, &dev->netdev_list, list) { - if (exit) - break; - if (++if_idx < if_start) - continue; - if (!dev->ops->dump_mpath) - continue; + if (nl80211_send_mpath(skb, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + netdev, dst, next_hop, + &pinfo) < 0) + goto out; - for (;; ++sta_idx) { - rtnl_lock(); - err = dev->ops->dump_mpath(&dev->wiphy, - wdev->netdev, sta_idx, dst, - next_hop, &pinfo); - rtnl_unlock(); - if (err) { - sta_idx = 0; - break; - } - if (nl80211_send_mpath(skb, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - wdev->netdev, dst, next_hop, - &pinfo) < 0) { - exit = 1; - break; - } - } - } - mutex_unlock(&dev->devlist_mtx); + path_idx++; } - mutex_unlock(&cfg80211_drv_mutex); - cb->args[0] = wp_idx; - cb->args[1] = if_idx; - cb->args[2] = sta_idx; - return skb->len; + out: + cb->args[1] = path_idx; + err = skb->len; + out_err_rtnl: + rtnl_unlock(); + out_err: + cfg80211_put_dev(dev); + out_put_netdev: + dev_put(netdev); + + return err; } static int nl80211_get_mpath(struct sk_buff *skb, struct genl_info *info) @@ -1358,7 +1389,7 @@ static int nl80211_get_mpath(struct sk_buff *skb, struct genl_info *info) dst = nla_data(info->attrs[NL80211_ATTR_MAC]); - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; @@ -1411,7 +1442,7 @@ static int nl80211_set_mpath(struct sk_buff *skb, struct genl_info *info) dst = nla_data(info->attrs[NL80211_ATTR_MAC]); next_hop = nla_data(info->attrs[NL80211_ATTR_MPATH_NEXT_HOP]); - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; @@ -1446,7 +1477,7 @@ static int nl80211_new_mpath(struct sk_buff *skb, struct genl_info *info) dst = nla_data(info->attrs[NL80211_ATTR_MAC]); next_hop = nla_data(info->attrs[NL80211_ATTR_MPATH_NEXT_HOP]); - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) return err; @@ -1475,7 +1506,7 @@ static int nl80211_del_mpath(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_MAC]) dst = nla_data(info->attrs[NL80211_ATTR_MAC]); - err = get_drv_dev_by_info_ifindex(info, &drv, &dev); + err = get_drv_dev_by_info_ifindex(info->attrs, &drv, &dev); if (err) 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/Kconfig b/net/xfrm/Kconfig index 9201ef8ad90e..6d081674515f 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -46,6 +46,12 @@ config XFRM_STATISTICS If unsure, say N. +config XFRM_IPCOMP + tristate + select XFRM + select CRYPTO + select CRYPTO_DEFLATE + config NET_KEY tristate "PF_KEY sockets" select XFRM diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 332cfb0ff566..0f439a72ccab 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -6,4 +6,5 @@ obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \ xfrm_input.o xfrm_output.o xfrm_algo.o obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o +obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 23a2cc04b8cd..96036cf2216d 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -718,7 +718,7 @@ int skb_icv_walk(const struct sk_buff *skb, struct hash_desc *desc, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + skb_shinfo(skb)->frags[i].size; if ((copy = end - offset) > 0) { @@ -748,7 +748,7 @@ int skb_icv_walk(const struct sk_buff *skb, struct hash_desc *desc, for (; list; list = list->next) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); end = start + list->len; if ((copy = end - offset) > 0) { diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c new file mode 100644 index 000000000000..c609a4b98e15 --- /dev/null +++ b/net/xfrm/xfrm_ipcomp.c @@ -0,0 +1,384 @@ +/* + * IP Payload Compression Protocol (IPComp) - RFC3173. + * + * Copyright (c) 2003 James Morris <jmorris@intercode.com.au> + * Copyright (c) 2003-2008 Herbert Xu <herbert@gondor.apana.org.au> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + * Todo: + * - Tunable compression parameters. + * - Compression stats. + * - Adaptive compression. + */ + +#include <linux/crypto.h> +#include <linux/err.h> +#include <linux/gfp.h> +#include <linux/list.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/percpu.h> +#include <linux/smp.h> +#include <linux/vmalloc.h> +#include <net/ip.h> +#include <net/ipcomp.h> +#include <net/xfrm.h> + +struct ipcomp_tfms { + struct list_head list; + struct crypto_comp **tfms; + int users; +}; + +static DEFINE_MUTEX(ipcomp_resource_mutex); +static void **ipcomp_scratches; +static int ipcomp_scratch_users; +static LIST_HEAD(ipcomp_tfms_list); + +static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipcomp_data *ipcd = x->data; + const int plen = skb->len; + int dlen = IPCOMP_SCRATCH_SIZE; + const u8 *start = skb->data; + const int cpu = get_cpu(); + u8 *scratch = *per_cpu_ptr(ipcomp_scratches, cpu); + struct crypto_comp *tfm = *per_cpu_ptr(ipcd->tfms, cpu); + int err = crypto_comp_decompress(tfm, start, plen, scratch, &dlen); + int len; + + if (err) + goto out; + + if (dlen < (plen + sizeof(struct ip_comp_hdr))) { + err = -EINVAL; + goto out; + } + + len = dlen - plen; + if (len > skb_tailroom(skb)) + len = skb_tailroom(skb); + + skb->truesize += len; + __skb_put(skb, len); + + len += plen; + skb_copy_to_linear_data(skb, scratch, len); + + while ((scratch += len, dlen -= len) > 0) { + skb_frag_t *frag; + + err = -EMSGSIZE; + if (WARN_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) + goto out; + + frag = skb_shinfo(skb)->frags + skb_shinfo(skb)->nr_frags; + frag->page = alloc_page(GFP_ATOMIC); + + err = -ENOMEM; + if (!frag->page) + goto out; + + len = PAGE_SIZE; + if (dlen < len) + len = dlen; + + memcpy(page_address(frag->page), scratch, len); + + frag->page_offset = 0; + frag->size = len; + skb->truesize += len; + skb->data_len += len; + skb->len += len; + + skb_shinfo(skb)->nr_frags++; + } + + err = 0; + +out: + put_cpu(); + return err; +} + +int ipcomp_input(struct xfrm_state *x, struct sk_buff *skb) +{ + int nexthdr; + int err = -ENOMEM; + struct ip_comp_hdr *ipch; + + if (skb_linearize_cow(skb)) + goto out; + + skb->ip_summed = CHECKSUM_NONE; + + /* Remove ipcomp header and decompress original payload */ + ipch = (void *)skb->data; + nexthdr = ipch->nexthdr; + + skb->transport_header = skb->network_header + sizeof(*ipch); + __skb_pull(skb, sizeof(*ipch)); + err = ipcomp_decompress(x, skb); + if (err) + goto out; + + err = nexthdr; + +out: + return err; +} +EXPORT_SYMBOL_GPL(ipcomp_input); + +static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipcomp_data *ipcd = x->data; + const int plen = skb->len; + int dlen = IPCOMP_SCRATCH_SIZE; + u8 *start = skb->data; + const int cpu = get_cpu(); + u8 *scratch = *per_cpu_ptr(ipcomp_scratches, cpu); + struct crypto_comp *tfm = *per_cpu_ptr(ipcd->tfms, cpu); + int err; + + local_bh_disable(); + err = crypto_comp_compress(tfm, start, plen, scratch, &dlen); + local_bh_enable(); + if (err) + goto out; + + if ((dlen + sizeof(struct ip_comp_hdr)) >= plen) { + err = -EMSGSIZE; + goto out; + } + + memcpy(start + sizeof(struct ip_comp_hdr), scratch, dlen); + put_cpu(); + + pskb_trim(skb, dlen + sizeof(struct ip_comp_hdr)); + return 0; + +out: + put_cpu(); + return err; +} + +int ipcomp_output(struct xfrm_state *x, struct sk_buff *skb) +{ + int err; + struct ip_comp_hdr *ipch; + struct ipcomp_data *ipcd = x->data; + + if (skb->len < ipcd->threshold) { + /* Don't bother compressing */ + goto out_ok; + } + + if (skb_linearize_cow(skb)) + goto out_ok; + + err = ipcomp_compress(x, skb); + + if (err) { + goto out_ok; + } + + /* Install ipcomp header, convert into ipcomp datagram. */ + ipch = ip_comp_hdr(skb); + ipch->nexthdr = *skb_mac_header(skb); + ipch->flags = 0; + ipch->cpi = htons((u16 )ntohl(x->id.spi)); + *skb_mac_header(skb) = IPPROTO_COMP; +out_ok: + skb_push(skb, -skb_network_offset(skb)); + return 0; +} +EXPORT_SYMBOL_GPL(ipcomp_output); + +static void ipcomp_free_scratches(void) +{ + int i; + void **scratches; + + if (--ipcomp_scratch_users) + return; + + scratches = ipcomp_scratches; + if (!scratches) + return; + + for_each_possible_cpu(i) + vfree(*per_cpu_ptr(scratches, i)); + + free_percpu(scratches); +} + +static void **ipcomp_alloc_scratches(void) +{ + int i; + void **scratches; + + if (ipcomp_scratch_users++) + return ipcomp_scratches; + + scratches = alloc_percpu(void *); + if (!scratches) + return NULL; + + ipcomp_scratches = scratches; + + for_each_possible_cpu(i) { + void *scratch = vmalloc(IPCOMP_SCRATCH_SIZE); + if (!scratch) + return NULL; + *per_cpu_ptr(scratches, i) = scratch; + } + + return scratches; +} + +static void ipcomp_free_tfms(struct crypto_comp **tfms) +{ + struct ipcomp_tfms *pos; + int cpu; + + list_for_each_entry(pos, &ipcomp_tfms_list, list) { + if (pos->tfms == tfms) + break; + } + + WARN_ON(!pos); + + if (--pos->users) + return; + + list_del(&pos->list); + kfree(pos); + + if (!tfms) + return; + + for_each_possible_cpu(cpu) { + struct crypto_comp *tfm = *per_cpu_ptr(tfms, cpu); + crypto_free_comp(tfm); + } + free_percpu(tfms); +} + +static struct crypto_comp **ipcomp_alloc_tfms(const char *alg_name) +{ + struct ipcomp_tfms *pos; + struct crypto_comp **tfms; + int cpu; + + /* This can be any valid CPU ID so we don't need locking. */ + cpu = raw_smp_processor_id(); + + list_for_each_entry(pos, &ipcomp_tfms_list, list) { + struct crypto_comp *tfm; + + tfms = pos->tfms; + tfm = *per_cpu_ptr(tfms, cpu); + + if (!strcmp(crypto_comp_name(tfm), alg_name)) { + pos->users++; + return tfms; + } + } + + pos = kmalloc(sizeof(*pos), GFP_KERNEL); + if (!pos) + return NULL; + + pos->users = 1; + INIT_LIST_HEAD(&pos->list); + list_add(&pos->list, &ipcomp_tfms_list); + + pos->tfms = tfms = alloc_percpu(struct crypto_comp *); + if (!tfms) + goto error; + + for_each_possible_cpu(cpu) { + struct crypto_comp *tfm = crypto_alloc_comp(alg_name, 0, + CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm)) + goto error; + *per_cpu_ptr(tfms, cpu) = tfm; + } + + return tfms; + +error: + ipcomp_free_tfms(tfms); + return NULL; +} + +static void ipcomp_free_data(struct ipcomp_data *ipcd) +{ + if (ipcd->tfms) + ipcomp_free_tfms(ipcd->tfms); + ipcomp_free_scratches(); +} + +void ipcomp_destroy(struct xfrm_state *x) +{ + struct ipcomp_data *ipcd = x->data; + if (!ipcd) + return; + xfrm_state_delete_tunnel(x); + mutex_lock(&ipcomp_resource_mutex); + ipcomp_free_data(ipcd); + mutex_unlock(&ipcomp_resource_mutex); + kfree(ipcd); +} +EXPORT_SYMBOL_GPL(ipcomp_destroy); + +int ipcomp_init_state(struct xfrm_state *x) +{ + int err; + struct ipcomp_data *ipcd; + struct xfrm_algo_desc *calg_desc; + + err = -EINVAL; + if (!x->calg) + goto out; + + if (x->encap) + goto out; + + err = -ENOMEM; + ipcd = kzalloc(sizeof(*ipcd), GFP_KERNEL); + if (!ipcd) + goto out; + + mutex_lock(&ipcomp_resource_mutex); + if (!ipcomp_alloc_scratches()) + goto error; + + ipcd->tfms = ipcomp_alloc_tfms(x->calg->alg_name); + if (!ipcd->tfms) + goto error; + mutex_unlock(&ipcomp_resource_mutex); + + calg_desc = xfrm_calg_get_byname(x->calg->alg_name, 0); + BUG_ON(!calg_desc); + ipcd->threshold = calg_desc->uinfo.comp.threshold; + x->data = ipcd; + err = 0; +out: + return err; + +error: + ipcomp_free_data(ipcd); + mutex_unlock(&ipcomp_resource_mutex); + kfree(ipcd); + goto out; +} +EXPORT_SYMBOL_GPL(ipcomp_init_state); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("IP Payload Compression Protocol (IPComp) - RFC3173"); +MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); 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, diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 72fddafd891a..4c6914ef7d92 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -538,7 +538,7 @@ EXPORT_SYMBOL(xfrm_state_alloc); void __xfrm_state_destroy(struct xfrm_state *x) { - BUG_TRAP(x->km.state == XFRM_STATE_DEAD); + WARN_ON(x->km.state != XFRM_STATE_DEAD); spin_lock_bh(&xfrm_state_lock); list_del(&x->all); |