diff options
author | Jiri Kosina <jkosina@suse.cz> | 2011-09-15 15:08:05 +0200 |
---|---|---|
committer | Jiri Kosina <jkosina@suse.cz> | 2011-09-15 15:08:18 +0200 |
commit | e060c38434b2caa78efe7cedaff4191040b65a15 (patch) | |
tree | 407361230bf6733f63d8e788e4b5e6566ee04818 /net | |
parent | 10e4ac572eeffe5317019bd7330b6058a400dfc2 (diff) | |
parent | cc39c6a9bbdebfcf1a7dee64d83bf302bc38d941 (diff) | |
download | linux-e060c38434b2caa78efe7cedaff4191040b65a15.tar.gz linux-e060c38434b2caa78efe7cedaff4191040b65a15.tar.bz2 linux-e060c38434b2caa78efe7cedaff4191040b65a15.zip |
Merge branch 'master' into for-next
Fast-forward merge with Linus to be able to merge patches
based on more recent version of the tree.
Diffstat (limited to 'net')
119 files changed, 940 insertions, 447 deletions
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 5f27f8e30254..f1f2f7bb6661 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -167,6 +167,8 @@ struct sk_buff *vlan_untag(struct sk_buff *skb) if (unlikely(!skb)) goto err_free; + skb_reset_network_header(skb); + skb_reset_transport_header(skb); return skb; err_free: diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 934e221c1d07..9d40a071d038 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -695,7 +695,7 @@ void vlan_setup(struct net_device *dev) ether_setup(dev); dev->priv_flags |= IFF_802_1Q_VLAN; - dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); dev->tx_queue_len = 0; dev->netdev_ops = &vlan_netdev_ops; diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 175b5135bdcf..e317583fcc73 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -263,7 +263,6 @@ p9_virtio_request(struct p9_client *client, struct p9_req_t *req) { int in, out, inp, outp; struct virtio_chan *chan = client->trans; - char *rdata = (char *)req->rc+sizeof(struct p9_fcall); unsigned long flags; size_t pdata_off = 0; struct trans_rpage_info *rpinfo = NULL; @@ -346,7 +345,8 @@ req_retry_pinned: * Arrange in such a way that server places header in the * alloced memory and payload onto the user buffer. */ - inp = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, rdata, 11); + inp = pack_sg_list(chan->sg, out, + VIRTQUEUE_NUM, req->rc->sdata, 11); /* * Running executables in the filesystem may result in * a read request with kernel buffer as opposed to user buffer. @@ -366,8 +366,8 @@ req_retry_pinned: } in += inp; } else { - in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, rdata, - req->rc->capacity); + in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, + req->rc->sdata, req->rc->capacity); } err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc); @@ -592,7 +592,14 @@ static struct p9_trans_module p9_virtio_trans = { .close = p9_virtio_close, .request = p9_virtio_request, .cancel = p9_virtio_cancel, - .maxsize = PAGE_SIZE*VIRTQUEUE_NUM, + + /* + * We leave one entry for input and one entry for response + * headers. We also skip one more entry to accomodate, address + * that are not at page boundary, that can result in an extra + * page in zero copy. + */ + .maxsize = PAGE_SIZE * (VIRTQUEUE_NUM - 3), .pref = P9_TRANS_PREF_PAYLOAD_SEP, .def = 0, .owner = THIS_MODULE, diff --git a/net/atm/atm_misc.c b/net/atm/atm_misc.c index fc63526d8695..f41f02656ff4 100644 --- a/net/atm/atm_misc.c +++ b/net/atm/atm_misc.c @@ -9,7 +9,7 @@ #include <linux/sonet.h> #include <linux/bitops.h> #include <linux/errno.h> -#include <asm/atomic.h> +#include <linux/atomic.h> int atm_charge(struct atm_vcc *vcc, int truesize) { diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 2252c2085dac..d07223c834af 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -242,8 +242,6 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev, if (brdev->payload == p_bridged) { skb_push(skb, 2); memset(skb->data, 0, 2); - } else { /* p_routed */ - skb_pull(skb, ETH_HLEN); } } skb_debug(skb); @@ -560,12 +558,13 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) spin_unlock_irqrestore(&rq->lock, flags); skb_queue_walk_safe(&queue, skb, tmp) { - struct net_device *dev = skb->dev; + struct net_device *dev; + + br2684_push(atmvcc, skb); + dev = skb->dev; dev->stats.rx_bytes -= skb->len; dev->stats.rx_packets--; - - br2684_push(atmvcc, skb); } /* initialize netdev carrier state */ diff --git a/net/atm/clip.c b/net/atm/clip.c index 4bc8c67ecb14..852394072fa1 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -37,7 +37,7 @@ #include <linux/uaccess.h> #include <asm/byteorder.h> /* for htons etc. */ #include <asm/system.h> /* save/restore_flags */ -#include <asm/atomic.h> +#include <linux/atomic.h> #include "common.h" #include "resources.h" diff --git a/net/atm/common.c b/net/atm/common.c index 22b963d06a10..14ff9fe39989 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -23,7 +23,7 @@ #include <linux/uaccess.h> #include <linux/poll.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include "resources.h" /* atm_find_dev */ #include "common.h" /* prototypes */ diff --git a/net/atm/lec.c b/net/atm/lec.c index ba48daa68c1f..215c9fad7cdf 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1335,7 +1335,7 @@ static void lane2_associate_ind(struct net_device *dev, const u8 *mac_addr, #include <linux/types.h> #include <linux/timer.h> #include <linux/param.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <linux/inetdevice.h> #include <net/route.h> diff --git a/net/atm/proc.c b/net/atm/proc.c index be3afdefec58..0d020de8d233 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -27,7 +27,7 @@ #include <net/atmclip.h> #include <linux/uaccess.h> #include <linux/param.h> /* for HZ */ -#include <asm/atomic.h> +#include <linux/atomic.h> #include "resources.h" #include "common.h" /* atm_proc_init prototype */ #include "signaling.h" /* to get sigd - ugly too */ diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 8add9b499912..117e0d161780 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -494,9 +494,8 @@ int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo) BT_DBG("sk %p", sk); add_wait_queue(sk_sleep(sk), &wait); + set_current_state(TASK_INTERRUPTIBLE); while (sk->sk_state != state) { - set_current_state(TASK_INTERRUPTIBLE); - if (!timeo) { err = -EINPROGRESS; break; @@ -510,12 +509,13 @@ int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo) release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); + set_current_state(TASK_INTERRUPTIBLE); err = sock_error(sk); if (err) break; } - set_current_state(TASK_RUNNING); + __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); return err; } diff --git a/net/bluetooth/bnep/bnep.h b/net/bluetooth/bnep/bnep.h index 8e6c06158f8e..e7ee5314f39a 100644 --- a/net/bluetooth/bnep/bnep.h +++ b/net/bluetooth/bnep/bnep.h @@ -155,6 +155,7 @@ struct bnep_session { unsigned int role; unsigned long state; unsigned long flags; + atomic_t terminate; struct task_struct *task; struct ethhdr eh; diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index ca39fcf010ce..d9edfe8bf9d6 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -484,9 +484,11 @@ static int bnep_session(void *arg) init_waitqueue_entry(&wait, current); add_wait_queue(sk_sleep(sk), &wait); - while (!kthread_should_stop()) { + while (1) { set_current_state(TASK_INTERRUPTIBLE); + if (atomic_read(&s->terminate)) + break; /* RX */ while ((skb = skb_dequeue(&sk->sk_receive_queue))) { skb_orphan(skb); @@ -504,7 +506,7 @@ static int bnep_session(void *arg) schedule(); } - set_current_state(TASK_RUNNING); + __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); /* Cleanup session */ @@ -640,9 +642,10 @@ int bnep_del_connection(struct bnep_conndel_req *req) down_read(&bnep_session_sem); s = __bnep_get_session(req->dst); - if (s) - kthread_stop(s->task); - else + if (s) { + atomic_inc(&s->terminate); + wake_up_process(s->task); + } else err = -ENOENT; up_read(&bnep_session_sem); diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index 8c100c9dae28..d4f5dff7c955 100644 --- a/net/bluetooth/bnep/netdev.c +++ b/net/bluetooth/bnep/netdev.c @@ -231,6 +231,7 @@ void bnep_net_setup(struct net_device *dev) dev->addr_len = ETH_ALEN; ether_setup(dev); + dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->netdev_ops = &bnep_netdev_ops; dev->watchdog_timeo = HZ * 2; diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c index 040f67b12978..50f0d135eb8f 100644 --- a/net/bluetooth/cmtp/capi.c +++ b/net/bluetooth/cmtp/capi.c @@ -386,7 +386,8 @@ static void cmtp_reset_ctr(struct capi_ctr *ctrl) capi_ctr_down(ctrl); - kthread_stop(session->task); + atomic_inc(&session->terminate); + wake_up_process(session->task); } static void cmtp_register_appl(struct capi_ctr *ctrl, __u16 appl, capi_register_params *rp) diff --git a/net/bluetooth/cmtp/cmtp.h b/net/bluetooth/cmtp/cmtp.h index db43b54ac9af..c32638dddbf9 100644 --- a/net/bluetooth/cmtp/cmtp.h +++ b/net/bluetooth/cmtp/cmtp.h @@ -81,6 +81,7 @@ struct cmtp_session { char name[BTNAMSIZ]; + atomic_t terminate; struct task_struct *task; wait_queue_head_t wait; diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index c5b11af908be..521baa4fe835 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -292,9 +292,11 @@ static int cmtp_session(void *arg) init_waitqueue_entry(&wait, current); add_wait_queue(sk_sleep(sk), &wait); - while (!kthread_should_stop()) { + while (1) { set_current_state(TASK_INTERRUPTIBLE); + if (atomic_read(&session->terminate)) + break; if (sk->sk_state != BT_CONNECTED) break; @@ -307,7 +309,7 @@ static int cmtp_session(void *arg) schedule(); } - set_current_state(TASK_RUNNING); + __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); down_write(&cmtp_session_sem); @@ -380,16 +382,17 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) if (!(session->flags & (1 << CMTP_LOOPBACK))) { err = cmtp_attach_device(session); - if (err < 0) - goto detach; + if (err < 0) { + atomic_inc(&session->terminate); + wake_up_process(session->task); + up_write(&cmtp_session_sem); + return err; + } } up_write(&cmtp_session_sem); return 0; -detach: - cmtp_detach_device(session); - unlink: __cmtp_unlink_session(session); @@ -414,7 +417,8 @@ int cmtp_del_connection(struct cmtp_conndel_req *req) skb_queue_purge(&session->transmit); /* Stop session thread */ - kthread_stop(session->task); + atomic_inc(&session->terminate); + wake_up_process(session->task); } else err = -ENOENT; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index ec0bc3f60f2e..56943add45cc 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1209,7 +1209,6 @@ static void hci_cmd_timer(unsigned long arg) BT_ERR("%s command tx timeout", hdev->name); atomic_set(&hdev->cmd_cnt, 1); - clear_bit(HCI_RESET, &hdev->flags); tasklet_schedule(&hdev->cmd_task); } @@ -1327,7 +1326,7 @@ int hci_blacklist_add(struct hci_dev *hdev, bdaddr_t *bdaddr) entry = kzalloc(sizeof(struct bdaddr_list), GFP_KERNEL); if (!entry) { - return -ENOMEM; + err = -ENOMEM; goto err; } @@ -2408,7 +2407,10 @@ static void hci_cmd_task(unsigned long arg) if (hdev->sent_cmd) { atomic_dec(&hdev->cmd_cnt); hci_send_frame(skb); - mod_timer(&hdev->cmd_timer, + if (test_bit(HCI_RESET, &hdev->flags)) + del_timer(&hdev->cmd_timer); + else + mod_timer(&hdev->cmd_timer, jiffies + msecs_to_jiffies(HCI_CMD_TIMEOUT)); } else { skb_queue_head(&hdev->cmd_q, skb); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 43b4c2deb7cc..fb68f344c34a 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -764,6 +764,7 @@ static int hidp_session(void *arg) up_write(&hidp_session_sem); + kfree(session->rd_data); kfree(session); return 0; } @@ -841,7 +842,8 @@ static int hidp_setup_input(struct hidp_session *session, err = input_register_device(input); if (err < 0) { - hci_conn_put_device(session->conn); + input_free_device(input); + session->input = NULL; return err; } @@ -1044,8 +1046,12 @@ int hidp_add_connection(struct hidp_connadd_req *req, struct socket *ctrl_sock, } err = hid_add_device(session->hid); - if (err < 0) - goto err_add_device; + if (err < 0) { + atomic_inc(&session->terminate); + wake_up_process(session->task); + up_write(&hidp_session_sem); + return err; + } if (session->input) { hidp_send_ctrl_message(session, @@ -1059,12 +1065,6 @@ int hidp_add_connection(struct hidp_connadd_req *req, struct socket *ctrl_sock, up_write(&hidp_session_sem); return 0; -err_add_device: - hid_destroy_device(session->hid); - session->hid = NULL; - atomic_inc(&session->terminate); - wake_up_process(session->task); - unlink: hidp_del_timer(session); @@ -1090,7 +1090,6 @@ purge: failed: up_write(&hidp_session_sem); - input_free_device(session->input); kfree(session); return err; } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 3204ba8a701c..b3bdb482bbe6 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1159,9 +1159,8 @@ int __l2cap_wait_ack(struct sock *sk) int timeo = HZ/5; add_wait_queue(sk_sleep(sk), &wait); - while ((chan->unacked_frames > 0 && chan->conn)) { - set_current_state(TASK_INTERRUPTIBLE); - + set_current_state(TASK_INTERRUPTIBLE); + while (chan->unacked_frames > 0 && chan->conn) { if (!timeo) timeo = HZ/5; @@ -1173,6 +1172,7 @@ int __l2cap_wait_ack(struct sock *sk) release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); + set_current_state(TASK_INTERRUPTIBLE); err = sock_error(sk); if (err) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 5c36b3e8739c..61f1f623091d 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -235,30 +235,26 @@ static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int fl lock_sock_nested(sk, SINGLE_DEPTH_NESTING); - if (sk->sk_state != BT_LISTEN) { - err = -EBADFD; - goto done; - } - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); BT_DBG("sk %p timeo %ld", sk, timeo); /* Wait for an incoming connection. (wake-one). */ add_wait_queue_exclusive(sk_sleep(sk), &wait); - while (!(nsk = bt_accept_dequeue(sk, newsock))) { + while (1) { set_current_state(TASK_INTERRUPTIBLE); - if (!timeo) { - err = -EAGAIN; + + if (sk->sk_state != BT_LISTEN) { + err = -EBADFD; break; } - release_sock(sk); - timeo = schedule_timeout(timeo); - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); + nsk = bt_accept_dequeue(sk, newsock); + if (nsk) + break; - if (sk->sk_state != BT_LISTEN) { - err = -EBADFD; + if (!timeo) { + err = -EAGAIN; break; } @@ -266,8 +262,12 @@ static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int fl err = sock_intr_errno(timeo); break; } + + release_sock(sk); + timeo = schedule_timeout(timeo); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); } - set_current_state(TASK_RUNNING); + __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); if (err) @@ -993,7 +993,7 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int p INIT_LIST_HEAD(&bt_sk(sk)->accept_q); sk->sk_destruct = l2cap_sock_destruct; - sk->sk_sndtimeo = msecs_to_jiffies(L2CAP_CONN_TIMEOUT); + sk->sk_sndtimeo = L2CAP_CONN_TIMEOUT; sock_reset_flag(sk, SOCK_ZAPPED); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 5759bb7054f7..5ba3f6df665c 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -62,7 +62,6 @@ static DEFINE_MUTEX(rfcomm_mutex); #define rfcomm_lock() mutex_lock(&rfcomm_mutex) #define rfcomm_unlock() mutex_unlock(&rfcomm_mutex) -static unsigned long rfcomm_event; static LIST_HEAD(session_list); @@ -120,7 +119,6 @@ static inline void rfcomm_schedule(void) { if (!rfcomm_thread) return; - set_bit(RFCOMM_SCHED_WAKEUP, &rfcomm_event); wake_up_process(rfcomm_thread); } @@ -2038,19 +2036,18 @@ static int rfcomm_run(void *unused) rfcomm_add_listener(BDADDR_ANY); - while (!kthread_should_stop()) { + while (1) { set_current_state(TASK_INTERRUPTIBLE); - if (!test_bit(RFCOMM_SCHED_WAKEUP, &rfcomm_event)) { - /* No pending events. Let's sleep. - * Incoming connections and data will wake us up. */ - schedule(); - } - set_current_state(TASK_RUNNING); + + if (kthread_should_stop()) + break; /* Process stuff */ - clear_bit(RFCOMM_SCHED_WAKEUP, &rfcomm_event); rfcomm_process_sessions(); + + schedule(); } + __set_current_state(TASK_RUNNING); rfcomm_kill_listener(); diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 8f01e6b11a70..482722bbc7a0 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -485,11 +485,6 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f lock_sock(sk); - if (sk->sk_state != BT_LISTEN) { - err = -EBADFD; - goto done; - } - if (sk->sk_type != SOCK_STREAM) { err = -EINVAL; goto done; @@ -501,19 +496,20 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f /* Wait for an incoming connection. (wake-one). */ add_wait_queue_exclusive(sk_sleep(sk), &wait); - while (!(nsk = bt_accept_dequeue(sk, newsock))) { + while (1) { set_current_state(TASK_INTERRUPTIBLE); - if (!timeo) { - err = -EAGAIN; + + if (sk->sk_state != BT_LISTEN) { + err = -EBADFD; break; } - release_sock(sk); - timeo = schedule_timeout(timeo); - lock_sock(sk); + nsk = bt_accept_dequeue(sk, newsock); + if (nsk) + break; - if (sk->sk_state != BT_LISTEN) { - err = -EBADFD; + if (!timeo) { + err = -EAGAIN; break; } @@ -521,8 +517,12 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f err = sock_intr_errno(timeo); break; } + + release_sock(sk); + timeo = schedule_timeout(timeo); + lock_sock(sk); } - set_current_state(TASK_RUNNING); + __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); if (err) diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 4c3621b5e0aa..8270f05e3f1f 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -564,30 +564,26 @@ static int sco_sock_accept(struct socket *sock, struct socket *newsock, int flag lock_sock(sk); - if (sk->sk_state != BT_LISTEN) { - err = -EBADFD; - goto done; - } - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); BT_DBG("sk %p timeo %ld", sk, timeo); /* Wait for an incoming connection. (wake-one). */ add_wait_queue_exclusive(sk_sleep(sk), &wait); - while (!(ch = bt_accept_dequeue(sk, newsock))) { + while (1) { set_current_state(TASK_INTERRUPTIBLE); - if (!timeo) { - err = -EAGAIN; + + if (sk->sk_state != BT_LISTEN) { + err = -EBADFD; break; } - release_sock(sk); - timeo = schedule_timeout(timeo); - lock_sock(sk); + ch = bt_accept_dequeue(sk, newsock); + if (ch) + break; - if (sk->sk_state != BT_LISTEN) { - err = -EBADFD; + if (!timeo) { + err = -EAGAIN; break; } @@ -595,8 +591,12 @@ static int sco_sock_accept(struct socket *sock, struct socket *newsock, int flag err = sock_intr_errno(timeo); break; } + + release_sock(sk); + timeo = schedule_timeout(timeo); + lock_sock(sk); } - set_current_state(TASK_RUNNING); + __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); if (err) diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index e0dfbc151dd7..68def3b7fb49 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -21,7 +21,7 @@ #include <linux/jhash.h> #include <linux/random.h> #include <linux/slab.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/unaligned.h> #include "br_private.h" diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 3176e2e13d9b..e73815456adf 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -231,6 +231,7 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br, int br_add_bridge(struct net *net, const char *name) { struct net_device *dev; + int res; dev = alloc_netdev(sizeof(struct net_bridge), name, br_dev_setup); @@ -240,7 +241,10 @@ int br_add_bridge(struct net *net, const char *name) dev_net_set(dev, net); - return register_netdev(dev); + res = register_netdev(dev); + if (res) + free_netdev(dev); + return res; } int br_del_bridge(struct net *net, const char *name) @@ -417,6 +421,7 @@ put_back: int br_del_if(struct net_bridge *br, struct net_device *dev) { struct net_bridge_port *p; + bool changed_addr; p = br_port_get_rtnl(dev); if (!p || p->br != br) @@ -425,9 +430,12 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) del_nbp(p); spin_lock_bh(&br->lock); - br_stp_recalculate_bridge_id(br); + changed_addr = br_stp_recalculate_bridge_id(br); spin_unlock_bh(&br->lock); + if (changed_addr) + call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); + netdev_update_features(br->dev); return 0; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 2d85ca7111d3..995cbe0ac0b2 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1456,7 +1456,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, { struct sk_buff *skb2; const struct ipv6hdr *ip6h; - struct icmp6hdr *icmp6h; + u8 icmp6_type; u8 nexthdr; unsigned len; int offset; @@ -1502,9 +1502,9 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, __skb_pull(skb2, offset); skb_reset_transport_header(skb2); - icmp6h = icmp6_hdr(skb2); + icmp6_type = icmp6_hdr(skb2)->icmp6_type; - switch (icmp6h->icmp6_type) { + switch (icmp6_type) { case ICMPV6_MGM_QUERY: case ICMPV6_MGM_REPORT: case ICMPV6_MGM_REDUCTION: @@ -1520,16 +1520,23 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, err = pskb_trim_rcsum(skb2, len); if (err) goto out; + err = -EINVAL; } + ip6h = ipv6_hdr(skb2); + switch (skb2->ip_summed) { case CHECKSUM_COMPLETE: - if (!csum_fold(skb2->csum)) + if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, skb2->len, + IPPROTO_ICMPV6, skb2->csum)) break; /*FALLTHROUGH*/ case CHECKSUM_NONE: - skb2->csum = 0; - if (skb_checksum_complete(skb2)) + skb2->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr, + &ip6h->daddr, + skb2->len, + IPPROTO_ICMPV6, 0)); + if (__skb_checksum_complete(skb2)) goto out; } @@ -1537,7 +1544,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, BR_INPUT_SKB_CB(skb)->igmp = 1; - switch (icmp6h->icmp6_type) { + switch (icmp6_type) { case ICMPV6_MGM_REPORT: { struct mld_msg *mld; diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c index 6545ee9591d1..a76b62135558 100644 --- a/net/bridge/br_notify.c +++ b/net/bridge/br_notify.c @@ -34,6 +34,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v struct net_device *dev = ptr; struct net_bridge_port *p; struct net_bridge *br; + bool changed_addr; int err; /* register of bridge completed, add sysfs entries */ @@ -57,8 +58,12 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v case NETDEV_CHANGEADDR: spin_lock_bh(&br->lock); br_fdb_changeaddr(p, dev->dev_addr); - br_stp_recalculate_bridge_id(br); + changed_addr = br_stp_recalculate_bridge_id(br); spin_unlock_bh(&br->lock); + + if (changed_addr) + call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); + break; case NETDEV_CHANGE: diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 2b5ca1a0054d..5864cc491369 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1198,7 +1198,8 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table) if (table->check && table->check(newinfo, table->valid_hooks)) { BUGPRINT("The table doesn't like its own initial data, lol\n"); - return ERR_PTR(-EINVAL); + ret = -EINVAL; + goto free_chainstack; } table->private = newinfo; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 78b55f49de7c..c340e2e0765b 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -486,13 +486,10 @@ static void prepare_write_message(struct ceph_connection *con) m = list_first_entry(&con->out_queue, struct ceph_msg, list_head); con->out_msg = m; - if (test_bit(LOSSYTX, &con->state)) { - list_del_init(&m->list_head); - } else { - /* put message on sent list */ - ceph_msg_get(m); - list_move_tail(&m->list_head, &con->out_sent); - } + + /* put message on sent list */ + ceph_msg_get(m); + list_move_tail(&m->list_head, &con->out_sent); /* * only assign outgoing seq # if we haven't sent this message @@ -1399,6 +1396,7 @@ static void process_ack(struct ceph_connection *con) break; dout("got ack for seq %llu type %d at %p\n", seq, le16_to_cpu(m->hdr.type), m); + m->ack_stamp = jiffies; ceph_msg_remove(m); } prepare_read_tag(con); diff --git a/net/ceph/msgpool.c b/net/ceph/msgpool.c index d5f2d97ac05c..1f4cb30a42c5 100644 --- a/net/ceph/msgpool.c +++ b/net/ceph/msgpool.c @@ -7,27 +7,37 @@ #include <linux/ceph/msgpool.h> -static void *alloc_fn(gfp_t gfp_mask, void *arg) +static void *msgpool_alloc(gfp_t gfp_mask, void *arg) { struct ceph_msgpool *pool = arg; - void *p; + struct ceph_msg *msg; - p = ceph_msg_new(0, pool->front_len, gfp_mask); - if (!p) - pr_err("msgpool %s alloc failed\n", pool->name); - return p; + msg = ceph_msg_new(0, pool->front_len, gfp_mask); + if (!msg) { + dout("msgpool_alloc %s failed\n", pool->name); + } else { + dout("msgpool_alloc %s %p\n", pool->name, msg); + msg->pool = pool; + } + return msg; } -static void free_fn(void *element, void *arg) +static void msgpool_free(void *element, void *arg) { - ceph_msg_put(element); + struct ceph_msgpool *pool = arg; + struct ceph_msg *msg = element; + + dout("msgpool_release %s %p\n", pool->name, msg); + msg->pool = NULL; + ceph_msg_put(msg); } int ceph_msgpool_init(struct ceph_msgpool *pool, int front_len, int size, bool blocking, const char *name) { + dout("msgpool %s init\n", name); pool->front_len = front_len; - pool->pool = mempool_create(size, alloc_fn, free_fn, pool); + pool->pool = mempool_create(size, msgpool_alloc, msgpool_free, pool); if (!pool->pool) return -ENOMEM; pool->name = name; @@ -36,14 +46,17 @@ int ceph_msgpool_init(struct ceph_msgpool *pool, void ceph_msgpool_destroy(struct ceph_msgpool *pool) { + dout("msgpool %s destroy\n", pool->name); mempool_destroy(pool->pool); } struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, int front_len) { + struct ceph_msg *msg; + if (front_len > pool->front_len) { - pr_err("msgpool_get pool %s need front %d, pool size is %d\n", + dout("msgpool_get %s need front %d, pool size is %d\n", pool->name, front_len, pool->front_len); WARN_ON(1); @@ -51,14 +64,19 @@ struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, return ceph_msg_new(0, front_len, GFP_NOFS); } - return mempool_alloc(pool->pool, GFP_NOFS); + msg = mempool_alloc(pool->pool, GFP_NOFS); + dout("msgpool_get %s %p\n", pool->name, msg); + return msg; } void ceph_msgpool_put(struct ceph_msgpool *pool, struct ceph_msg *msg) { + dout("msgpool_put %s %p\n", pool->name, msg); + /* reset msg front_len; user may have changed it */ msg->front.iov_len = pool->front_len; msg->hdr.front_len = cpu_to_le32(pool->front_len); kref_init(&msg->kref); /* retake single ref */ + mempool_free(msg, pool->pool); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 7330c2757c0c..16836a7df7a6 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -685,6 +685,18 @@ static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) put_osd(osd); } +static void remove_all_osds(struct ceph_osd_client *osdc) +{ + dout("__remove_old_osds %p\n", osdc); + mutex_lock(&osdc->request_mutex); + while (!RB_EMPTY_ROOT(&osdc->osds)) { + struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds), + struct ceph_osd, o_node); + __remove_osd(osdc, osd); + } + mutex_unlock(&osdc->request_mutex); +} + static void __move_osd_to_lru(struct ceph_osd_client *osdc, struct ceph_osd *osd) { @@ -701,14 +713,14 @@ static void __remove_osd_from_lru(struct ceph_osd *osd) list_del_init(&osd->o_osd_lru); } -static void remove_old_osds(struct ceph_osd_client *osdc, int remove_all) +static void remove_old_osds(struct ceph_osd_client *osdc) { struct ceph_osd *osd, *nosd; dout("__remove_old_osds %p\n", osdc); mutex_lock(&osdc->request_mutex); list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) { - if (!remove_all && time_before(jiffies, osd->lru_ttl)) + if (time_before(jiffies, osd->lru_ttl)) break; __remove_osd(osdc, osd); } @@ -751,6 +763,7 @@ static void __insert_osd(struct ceph_osd_client *osdc, struct ceph_osd *new) struct rb_node *parent = NULL; struct ceph_osd *osd = NULL; + dout("__insert_osd %p osd%d\n", new, new->o_osd); while (*p) { parent = *p; osd = rb_entry(parent, struct ceph_osd, o_node); @@ -1085,9 +1098,15 @@ static void handle_timeout(struct work_struct *work) req = list_entry(osdc->req_lru.next, struct ceph_osd_request, r_req_lru_item); + /* hasn't been long enough since we sent it? */ if (time_before(jiffies, req->r_stamp + timeout)) break; + /* hasn't been long enough since it was acked? */ + if (req->r_request->ack_stamp == 0 || + time_before(jiffies, req->r_request->ack_stamp + timeout)) + break; + BUG_ON(req == last_req && req->r_stamp == last_stamp); last_req = req; last_stamp = req->r_stamp; @@ -1138,7 +1157,7 @@ static void handle_osds_timeout(struct work_struct *work) dout("osds timeout\n"); down_read(&osdc->map_sem); - remove_old_osds(osdc, 0); + remove_old_osds(osdc); up_read(&osdc->map_sem); schedule_delayed_work(&osdc->osds_timeout_work, @@ -1856,8 +1875,7 @@ void ceph_osdc_stop(struct ceph_osd_client *osdc) ceph_osdmap_destroy(osdc->osdmap); osdc->osdmap = NULL; } - remove_old_osds(osdc, 1); - WARN_ON(!RB_EMPTY_ROOT(&osdc->osds)); + remove_all_osds(osdc); mempool_destroy(osdc->req_mempool); ceph_msgpool_destroy(&osdc->msgpool_op); ceph_msgpool_destroy(&osdc->msgpool_op_reply); diff --git a/net/core/Makefile b/net/core/Makefile index 8a04dd22cf77..0d357b1c4e57 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -3,7 +3,7 @@ # obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ - gen_stats.o gen_estimator.o net_namespace.o + gen_stats.o gen_estimator.o net_namespace.o secure_seq.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o diff --git a/net/core/dev.c b/net/core/dev.c index 9444c5cb4137..17d67b579beb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4497,10 +4497,10 @@ void __dev_set_rx_mode(struct net_device *dev) */ if (!netdev_uc_empty(dev) && !dev->uc_promisc) { __dev_set_promiscuity(dev, 1); - dev->uc_promisc = 1; + dev->uc_promisc = true; } else if (netdev_uc_empty(dev) && dev->uc_promisc) { __dev_set_promiscuity(dev, -1); - dev->uc_promisc = 0; + dev->uc_promisc = false; } if (ops->ndo_set_multicast_list) diff --git a/net/core/flow.c b/net/core/flow.c index 990703b8863b..bf32c33cad3b 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -22,7 +22,7 @@ #include <linux/cpumask.h> #include <linux/mutex.h> #include <net/flow.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <linux/security.h> struct flow_cache_entry { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8fab9b0bb203..1334d7e56f02 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1319,11 +1319,15 @@ static void neigh_proxy_process(unsigned long arg) if (tdif <= 0) { struct net_device *dev = skb->dev; + __skb_unlink(skb, &tbl->proxy_queue); - if (tbl->proxy_redo && netif_running(dev)) + if (tbl->proxy_redo && netif_running(dev)) { + rcu_read_lock(); tbl->proxy_redo(skb); - else + rcu_read_unlock(); + } else { kfree_skb(skb); + } dev_put(dev); } else if (!sched_next || tdif < sched_next) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index adf84dd8c7b5..52622517e0d8 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -558,13 +558,14 @@ int __netpoll_rx(struct sk_buff *skb) if (skb_shared(skb)) goto out; - iph = (struct iphdr *)skb->data; if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; + iph = (struct iphdr *)skb->data; if (iph->ihl < 5 || iph->version != 4) goto out; if (!pskb_may_pull(skb, iph->ihl*4)) goto out; + iph = (struct iphdr *)skb->data; if (ip_fast_csum((u8 *)iph, iph->ihl) != 0) goto out; @@ -579,6 +580,7 @@ int __netpoll_rx(struct sk_buff *skb) if (pskb_trim_rcsum(skb, len)) goto out; + iph = (struct iphdr *)skb->data; if (iph->protocol != IPPROTO_UDP) goto out; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index f76079cd750c..e35a6fbb8110 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1070,7 +1070,9 @@ static ssize_t pktgen_if_write(struct file *file, len = num_arg(&user_buffer[i], 10, &value); if (len < 0) return len; - + if ((value > 0) && + (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))) + return -ENOTSUPP; i += len; pkt_dev->clone_skb = value; @@ -3555,7 +3557,6 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->min_pkt_size = ETH_ZLEN; pkt_dev->max_pkt_size = ETH_ZLEN; pkt_dev->nfrags = 0; - pkt_dev->clone_skb = pg_clone_skb_d; pkt_dev->delay = pg_delay_d; pkt_dev->count = pg_count_d; pkt_dev->sofar = 0; @@ -3563,7 +3564,6 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->udp_src_max = 9; pkt_dev->udp_dst_min = 9; pkt_dev->udp_dst_max = 9; - pkt_dev->vlan_p = 0; pkt_dev->vlan_cfi = 0; pkt_dev->vlan_id = 0xffff; @@ -3575,6 +3575,8 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) err = pktgen_setup_dev(pkt_dev, ifname); if (err) goto out1; + if (pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING) + pkt_dev->clone_skb = pg_clone_skb_d; pkt_dev->entry = proc_create_data(ifname, 0600, pg_proc_dir, &pktgen_if_fops, pkt_dev); diff --git a/net/core/scm.c b/net/core/scm.c index 4c1ef026d695..811b53fb330e 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -192,7 +192,7 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) goto error; cred->uid = cred->euid = p->creds.uid; - cred->gid = cred->egid = p->creds.uid; + cred->gid = cred->egid = p->creds.gid; put_cred(p->cred); p->cred = cred; } diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c new file mode 100644 index 000000000000..45329d7c9dd9 --- /dev/null +++ b/net/core/secure_seq.c @@ -0,0 +1,184 @@ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/cryptohash.h> +#include <linux/module.h> +#include <linux/cache.h> +#include <linux/random.h> +#include <linux/hrtimer.h> +#include <linux/ktime.h> +#include <linux/string.h> + +#include <net/secure_seq.h> + +static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned; + +static int __init net_secret_init(void) +{ + get_random_bytes(net_secret, sizeof(net_secret)); + return 0; +} +late_initcall(net_secret_init); + +static u32 seq_scale(u32 seq) +{ + /* + * As close as possible to RFC 793, which + * suggests using a 250 kHz clock. + * Further reading shows this assumes 2 Mb/s networks. + * For 10 Mb/s Ethernet, a 1 MHz clock is appropriate. + * For 10 Gb/s Ethernet, a 1 GHz clock should be ok, but + * we also need to limit the resolution so that the u32 seq + * overlaps less than one time per MSL (2 minutes). + * Choosing a clock of 64 ns period is OK. (period of 274 s) + */ + return seq + (ktime_to_ns(ktime_get_real()) >> 6); +} + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +__u32 secure_tcpv6_sequence_number(__be32 *saddr, __be32 *daddr, + __be16 sport, __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u32 i; + + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + daddr[i]; + secret[4] = net_secret[4] + + (((__force u16)sport << 16) + (__force u16)dport); + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + return seq_scale(hash[0]); +} +EXPORT_SYMBOL(secure_tcpv6_sequence_number); + +u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, + __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u32 i; + + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + (__force u32) daddr[i]; + secret[4] = net_secret[4] + (__force u32)dport; + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + return hash[0]; +} +#endif + +#ifdef CONFIG_INET +__u32 secure_ip_id(__be32 daddr) +{ + u32 hash[MD5_DIGEST_WORDS]; + + hash[0] = (__force __u32) daddr; + hash[1] = net_secret[13]; + hash[2] = net_secret[14]; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + return hash[0]; +} + +__u32 secure_ipv6_id(const __be32 daddr[4]) +{ + __u32 hash[4]; + + memcpy(hash, daddr, 16); + md5_transform(hash, net_secret); + + return hash[0]; +} + +__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = ((__force u16)sport << 16) + (__force u16)dport; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + return seq_scale(hash[0]); +} + +u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = (__force u32)dport ^ net_secret[14]; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + return hash[0]; +} +EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); +#endif + +#if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE) +u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + u64 seq; + + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = ((__force u16)sport << 16) + (__force u16)dport; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + seq = hash[0] | (((u64)hash[1]) << 32); + seq += ktime_to_ns(ktime_get_real()); + seq &= (1ull << 48) - 1; + + return seq; +} +EXPORT_SYMBOL(secure_dccp_sequence_number); + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, + __be16 sport, __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u64 seq; + u32 i; + + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + daddr[i]; + secret[4] = net_secret[4] + + (((__force u16)sport << 16) + (__force u16)dport); + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + seq = hash[0] | (((u64)hash[1]) << 32); + seq += ktime_to_ns(ktime_get_real()); + seq &= (1ull << 48) - 1; + + return seq; +} +EXPORT_SYMBOL(secure_dccpv6_sequence_number); +#endif +#endif diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2beda824636e..27002dffe7ed 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1369,8 +1369,21 @@ pull_pages: } EXPORT_SYMBOL(__pskb_pull_tail); -/* Copy some data bits from skb to kernel buffer. */ - +/** + * skb_copy_bits - copy bits from skb to kernel buffer + * @skb: source skb + * @offset: offset in source + * @to: destination buffer + * @len: number of bytes to copy + * + * Copy the specified number of bytes from the source skb to the + * destination buffer. + * + * CAUTION ! : + * If its prototype is ever changed, + * check arch/{*}/net/{*}.S files, + * since it is called from BPF assembly code. + */ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { int start = skb_headlen(skb); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 8c36adfd1919..332639b56f4d 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -26,6 +26,7 @@ #include <net/timewait_sock.h> #include <net/tcp_states.h> #include <net/xfrm.h> +#include <net/secure_seq.h> #include "ackvec.h" #include "ccid.h" diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 8dc4348774a5..b74f76117dcf 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -29,6 +29,7 @@ #include <net/transp_v6.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> +#include <net/secure_seq.h> #include "dccp.h" #include "ipv6.h" @@ -69,13 +70,7 @@ static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb) dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &np->daddr); } -static inline __u32 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, - __be16 sport, __be16 dport ) -{ - return secure_tcpv6_sequence_number(saddr, daddr, sport, dport); -} - -static inline __u32 dccp_v6_init_sequence(struct sk_buff *skb) +static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb) { return secure_dccpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 2bd8e53d7774..9e885f180b60 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -30,7 +30,7 @@ #include <linux/netdevice.h> #include <linux/timer.h> #include <linux/spinlock.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/uaccess.h> #include <net/neighbour.h> #include <net/dst.h> diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 0dc3fe61085b..7f0eb087dc11 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -38,7 +38,7 @@ #include <linux/seq_file.h> #include <linux/rcupdate.h> #include <linux/jhash.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <net/net_namespace.h> #include <net/neighbour.h> #include <net/dst.h> diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index cd0354e9bdb3..a9a62f225a6b 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -25,7 +25,7 @@ #include <linux/netdevice.h> #include <linux/timer.h> #include <linux/spinlock.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/uaccess.h> #include <linux/route.h> /* RTF_xxx */ #include <net/neighbour.h> diff --git a/net/decnet/dn_timer.c b/net/decnet/dn_timer.c index 09825711d58a..67f691bd4acf 100644 --- a/net/decnet/dn_timer.c +++ b/net/decnet/dn_timer.c @@ -22,7 +22,7 @@ #include <linux/timer.h> #include <linux/spinlock.h> #include <net/sock.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <net/flow.h> #include <net/dn.h> diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 5cffb63f481a..27997d35ebd3 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -231,6 +231,7 @@ EXPORT_SYMBOL(eth_header_parse); * eth_header_cache - fill cache entry from neighbour * @neigh: source neighbour * @hh: destination cache entry + * @type: Ethernet type field * Create an Ethernet header template from the neighbour. */ int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type) @@ -339,6 +340,7 @@ void ether_setup(struct net_device *dev) dev->addr_len = ETH_ALEN; dev->tx_queue_len = 1000; /* Ethernet wants good queues */ dev->flags = IFF_BROADCAST|IFF_MULTICAST; + dev->priv_flags = IFF_TX_SKB_SHARING; memset(dev->broadcast, 0xFF, ETH_ALEN); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 2b3c23c287cd..2c2a98e402e7 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -50,7 +50,7 @@ #include <net/tcp.h> #include <net/netlabel.h> #include <net/cipso_ipv4.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/bug.h> #include <asm/unaligned.h> diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 37b3c188d8b3..bc19bd06dd00 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1134,15 +1134,15 @@ static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) { - struct in_ifaddr *ifa = in_dev->ifa_list; - - if (!ifa) - return; + struct in_ifaddr *ifa; - arp_send(ARPOP_REQUEST, ETH_P_ARP, - ifa->ifa_local, dev, - ifa->ifa_local, NULL, - dev->dev_addr, NULL); + for (ifa = in_dev->ifa_list; ifa; + ifa = ifa->ifa_next) { + arp_send(ARPOP_REQUEST, ETH_P_ARP, + ifa->ifa_local, dev, + ifa->ifa_local, NULL, + dev->dev_addr, NULL); + } } /* Called only under RTNL semaphore */ diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index f1d27f6c9351..d577199eabd5 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -767,7 +767,7 @@ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) break; for (i=0; i<nsrcs; i++) { /* skip inactive filters */ - if (pmc->sfcount[MCAST_INCLUDE] || + if (psf->sf_count[MCAST_INCLUDE] || pmc->sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) continue; @@ -1718,7 +1718,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->sfcount[sfmode]--; for (j=0; j<i; j++) - (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[i]); + (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 3c0369a3a663..984ec656b03b 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -21,6 +21,7 @@ #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> +#include <net/secure_seq.h> #include <net/ip.h> /* diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e38213817d0a..86f13c67ea85 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -19,6 +19,7 @@ #include <linux/net.h> #include <net/ip.h> #include <net/inetpeer.h> +#include <net/secure_seq.h> /* * Theory of operations. diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index ccaaa851ab42..8c6563361ab5 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -122,6 +122,7 @@ static int ip_dev_loopback_xmit(struct sk_buff *newskb) newskb->pkt_type = PACKET_LOOPBACK; newskb->ip_summed = CHECKSUM_UNNECESSARY; WARN_ON(!skb_dst(newskb)); + skb_dst_force(newskb); netif_rx_ni(newskb); return 0; } @@ -204,9 +205,15 @@ static inline int ip_finish_output2(struct sk_buff *skb) skb = skb2; } + rcu_read_lock(); neigh = dst_get_neighbour(dst); - if (neigh) - return neigh_output(neigh, skb); + if (neigh) { + int res = neigh_output(neigh, skb); + + rcu_read_unlock(); + return res; + } + rcu_read_unlock(); if (net_ratelimit()) printk(KERN_DEBUG "ip_finish_output2: No header cache and no neighbour!\n"); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ab0c9efd1efa..8905e92f896a 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1067,7 +1067,7 @@ EXPORT_SYMBOL(compat_ip_setsockopt); */ static int do_ip_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) + char __user *optval, int __user *optlen, unsigned flags) { struct inet_sock *inet = inet_sk(sk); int val; @@ -1240,7 +1240,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, msg.msg_control = optval; msg.msg_controllen = len; - msg.msg_flags = 0; + msg.msg_flags = flags; if (inet->cmsg_flags & IP_CMSG_PKTINFO) { struct in_pktinfo info; @@ -1294,7 +1294,7 @@ int ip_getsockopt(struct sock *sk, int level, { int err; - err = do_ip_getsockopt(sk, level, optname, optval, optlen); + err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS && @@ -1327,7 +1327,8 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, return compat_mc_getsockopt(sk, level, optname, optval, optlen, ip_getsockopt); - err = do_ip_getsockopt(sk, level, optname, optval, optlen); + err = do_ip_getsockopt(sk, level, optname, optval, optlen, + MSG_CMSG_COMPAT); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 2e97e3ec1eb7..929b27bdeb79 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -18,17 +18,15 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) struct rtable *rt; struct flowi4 fl4 = {}; __be32 saddr = iph->saddr; - __u8 flags = 0; + __u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0; unsigned int hh_len; - if (!skb->sk && addr_type != RTN_LOCAL) { - if (addr_type == RTN_UNSPEC) - addr_type = inet_addr_type(net, saddr); - if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) - flags |= FLOWI_FLAG_ANYSRC; - else - saddr = 0; - } + if (addr_type == RTN_UNSPEC) + addr_type = inet_addr_type(net, saddr); + if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) + flags |= FLOWI_FLAG_ANYSRC; + else + saddr = 0; /* some non-standard hacks like ipt_REJECT.c:send_reset() can cause * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook. @@ -38,7 +36,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) fl4.flowi4_tos = RT_TOS(iph->tos); fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; fl4.flowi4_mark = skb->mark; - fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : flags; + fl4.flowi4_flags = flags; rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) return -1; diff --git a/net/ipv4/netfilter/nf_nat_proto_common.c b/net/ipv4/netfilter/nf_nat_proto_common.c index 3e61faf23a9a..f52d41ea0690 100644 --- a/net/ipv4/netfilter/nf_nat_proto_common.c +++ b/net/ipv4/netfilter/nf_nat_proto_common.c @@ -12,6 +12,7 @@ #include <linux/ip.h> #include <linux/netfilter.h> +#include <net/secure_seq.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_rule.h> diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 08526786dc39..61714bd52925 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -38,7 +38,7 @@ */ #include <linux/types.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/byteorder.h> #include <asm/current.h> #include <asm/uaccess.h> @@ -563,7 +563,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, - FLOWI_FLAG_CAN_SLEEP, daddr, saddr, 0, 0); + inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP, + daddr, saddr, 0, 0); if (!inet->hdrincl) { err = raw_probe_proto_opt(&fl4, msg); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 1730689f560e..075212e41b83 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -109,6 +109,7 @@ #include <linux/sysctl.h> #endif #include <net/atmclip.h> +#include <net/secure_seq.h> #define RT_FL_TOS(oldflp4) \ ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))) @@ -721,7 +722,7 @@ static inline bool compare_hash_inputs(const struct rtable *rt1, { return ((((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) | ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) | - (rt1->rt_iif ^ rt2->rt_iif)) == 0); + (rt1->rt_route_iif ^ rt2->rt_route_iif)) == 0); } static inline int compare_keys(struct rtable *rt1, struct rtable *rt2) @@ -730,8 +731,8 @@ static inline int compare_keys(struct rtable *rt1, struct rtable *rt2) ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) | (rt1->rt_mark ^ rt2->rt_mark) | (rt1->rt_key_tos ^ rt2->rt_key_tos) | - (rt1->rt_oif ^ rt2->rt_oif) | - (rt1->rt_iif ^ rt2->rt_iif)) == 0; + (rt1->rt_route_iif ^ rt2->rt_route_iif) | + (rt1->rt_oif ^ rt2->rt_oif)) == 0; } static inline int compare_netns(struct rtable *rt1, struct rtable *rt2) @@ -1628,16 +1629,18 @@ static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) { struct rtable *rt = (struct rtable *) dst; __be32 orig_gw = rt->rt_gateway; - struct neighbour *n; + struct neighbour *n, *old_n; dst_confirm(&rt->dst); - neigh_release(dst_get_neighbour(&rt->dst)); - dst_set_neighbour(&rt->dst, NULL); - rt->rt_gateway = peer->redirect_learned.a4; - rt_bind_neighbour(rt); - n = dst_get_neighbour(&rt->dst); + + n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); + if (IS_ERR(n)) + return PTR_ERR(n); + old_n = xchg(&rt->dst._neighbour, n); + if (old_n) + neigh_release(old_n); if (!n || !(n->nud_state & NUD_VALID)) { if (n) neigh_event_send(n, NULL); @@ -2317,8 +2320,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth = rcu_dereference(rth->dst.rt_next)) { if ((((__force u32)rth->rt_key_dst ^ (__force u32)daddr) | ((__force u32)rth->rt_key_src ^ (__force u32)saddr) | - (rth->rt_iif ^ iif) | - rth->rt_oif | + (rth->rt_route_iif ^ iif) | (rth->rt_key_tos ^ tos)) == 0 && rth->rt_mark == skb->mark && net_eq(dev_net(rth->dst.dev), net) && diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 92bb9434b338..3bc5c8f7c71b 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -276,7 +276,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, int mss; struct rtable *rt; __u8 rcv_wscale; - bool ecn_ok; + bool ecn_ok = false; if (!sysctl_tcp_syncookies || !th->ack || th->rst) goto out; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 955b8e65b69e..1c12b8ec849d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -72,6 +72,7 @@ #include <net/timewait_sock.h> #include <net/xfrm.h> #include <net/netdma.h> +#include <net/secure_seq.h> #include <linux/inet.h> #include <linux/ipv6.h> diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index a06c53c14d84..f012ebd87b43 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -656,7 +656,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, * layer address of our nexhop router */ - if (dst_get_neighbour(&rt->dst) == NULL) + if (dst_get_neighbour_raw(&rt->dst) == NULL) ifa->flags &= ~IFA_F_OPTIMISTIC; ifa->idev = idev; @@ -1481,6 +1481,8 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; + if (ifp->prefix_len == 127) /* RFC 6164 */ + return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); if (ipv6_addr_any(&addr)) return; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 16560336eb72..9ef1831746ef 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -33,6 +33,11 @@ #include <linux/errqueue.h> #include <asm/uaccess.h> +static inline int ipv6_mapped_addr_any(const struct in6_addr *a) +{ + return (ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0)); +} + int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; @@ -102,10 +107,12 @@ ipv4_connected: ipv6_addr_set_v4mapped(inet->inet_daddr, &np->daddr); - if (ipv6_addr_any(&np->saddr)) + if (ipv6_addr_any(&np->saddr) || + ipv6_mapped_addr_any(&np->saddr)) ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - if (ipv6_addr_any(&np->rcv_saddr)) { + if (ipv6_addr_any(&np->rcv_saddr) || + ipv6_mapped_addr_any(&np->rcv_saddr)) { ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_saddr); if (sk->sk_prot->rehash) diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b53197233709..73f1a00a96af 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -20,6 +20,7 @@ #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> +#include <net/secure_seq.h> #include <net/ip.h> int __inet6_hash(struct sock *sk, struct inet_timewait_sock *tw) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 54a4678955bf..320d91d20ad7 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1455,7 +1455,7 @@ static int fib6_age(struct rt6_info *rt, void *arg) RT6_TRACE("aging clone %p\n", rt); return -1; } else if ((rt->rt6i_flags & RTF_GATEWAY) && - (!(dst_get_neighbour(&rt->dst)->flags & NTF_ROUTER))) { + (!(dst_get_neighbour_raw(&rt->dst)->flags & NTF_ROUTER))) { RT6_TRACE("purging route %p via non-router but gateway\n", rt); return -1; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 32e5339db0c8..4c882cf4e8a1 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -135,10 +135,15 @@ static int ip6_finish_output2(struct sk_buff *skb) skb->len); } + rcu_read_lock(); neigh = dst_get_neighbour(dst); - if (neigh) - return neigh_output(neigh, skb); + if (neigh) { + int res = neigh_output(neigh, skb); + rcu_read_unlock(); + return res; + } + rcu_read_unlock(); IP6_INC_STATS_BH(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); @@ -975,12 +980,14 @@ static int ip6_dst_lookup_tail(struct sock *sk, * dst entry and replace it instead with the * dst entry of the nexthop router */ + rcu_read_lock(); n = dst_get_neighbour(*dst); if (n && !(n->nud_state & NUD_VALID)) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; int redirect; + rcu_read_unlock(); ifp = ipv6_get_ifaddr(net, &fl6->saddr, (*dst)->dev, 1); @@ -1000,6 +1007,8 @@ static int ip6_dst_lookup_tail(struct sock *sk, if ((err = (*dst)->error)) goto out_err_release; } + } else { + rcu_read_unlock(); } #endif diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 36c2842a86b2..0bc98886c383 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -40,7 +40,7 @@ #include <linux/slab.h> #include <asm/uaccess.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <net/icmp.h> #include <net/ip.h> diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 9cb191ecaba8..147ede38ab48 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -913,7 +913,7 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt, } static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) + char __user *optval, int __user *optlen, unsigned flags) { struct ipv6_pinfo *np = inet6_sk(sk); int len; @@ -962,7 +962,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, msg.msg_control = optval; msg.msg_controllen = len; - msg.msg_flags = 0; + msg.msg_flags = flags; lock_sock(sk); skb = np->pktoptions; @@ -1222,7 +1222,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, if(level != SOL_IPV6) return -ENOPROTOOPT; - err = do_ipv6_getsockopt(sk, level, optname, optval, optlen); + err = do_ipv6_getsockopt(sk, level, optname, optval, optlen, 0); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IPV6_2292PKTOPTIONS) { @@ -1264,7 +1264,8 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, return compat_mc_getsockopt(sk, level, optname, optval, optlen, ipv6_getsockopt); - err = do_ipv6_getsockopt(sk, level, optname, optval, optlen); + err = do_ipv6_getsockopt(sk, level, optname, optval, optlen, + MSG_CMSG_COMPAT); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IPV6_2292PKTOPTIONS) { diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 3e6ebcdb4779..ee7839f4d6e3 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1059,7 +1059,7 @@ static int mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, break; for (i=0; i<nsrcs; i++) { /* skip inactive filters */ - if (pmc->mca_sfcount[MCAST_INCLUDE] || + if (psf->sf_count[MCAST_INCLUDE] || pmc->mca_sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) continue; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e8987da06667..9e69eb0ec6dd 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -364,7 +364,7 @@ out: #ifdef CONFIG_IPV6_ROUTER_PREF static void rt6_probe(struct rt6_info *rt) { - struct neighbour *neigh = rt ? dst_get_neighbour(&rt->dst) : NULL; + struct neighbour *neigh; /* * Okay, this does not seem to be appropriate * for now, however, we need to check if it @@ -373,8 +373,10 @@ static void rt6_probe(struct rt6_info *rt) * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ + rcu_read_lock(); + neigh = rt ? dst_get_neighbour(&rt->dst) : NULL; if (!neigh || (neigh->nud_state & NUD_VALID)) - return; + goto out; read_lock_bh(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { @@ -387,8 +389,11 @@ static void rt6_probe(struct rt6_info *rt) target = (struct in6_addr *)&neigh->primary_key; addrconf_addr_solict_mult(target, &mcaddr); ndisc_send_ns(rt->rt6i_dev, NULL, target, &mcaddr, NULL); - } else + } else { read_unlock_bh(&neigh->lock); + } +out: + rcu_read_unlock(); } #else static inline void rt6_probe(struct rt6_info *rt) @@ -412,8 +417,11 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif) static inline int rt6_check_neigh(struct rt6_info *rt) { - struct neighbour *neigh = dst_get_neighbour(&rt->dst); + struct neighbour *neigh; int m; + + rcu_read_lock(); + neigh = dst_get_neighbour(&rt->dst); if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) m = 1; @@ -430,6 +438,7 @@ static inline int rt6_check_neigh(struct rt6_info *rt) read_unlock_bh(&neigh->lock); } else m = 0; + rcu_read_unlock(); return m; } @@ -769,7 +778,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, rt->rt6i_dst.plen = 128; rt->rt6i_flags |= RTF_CACHE; rt->dst.flags |= DST_HOST; - dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour(&ort->dst))); + dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_raw(&ort->dst))); } return rt; } @@ -803,7 +812,7 @@ restart: dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); - if (!dst_get_neighbour(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); else if (!(rt->dst.flags & DST_HOST)) nrt = rt6_alloc_clone(rt, &fl6->daddr); @@ -1587,7 +1596,7 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, dst_confirm(&rt->dst); /* Duplicate redirect: silently ignore. */ - if (neigh == dst_get_neighbour(&rt->dst)) + if (neigh == dst_get_neighbour_raw(&rt->dst)) goto out; nrt = ip6_rt_copy(rt, dest); @@ -1682,7 +1691,7 @@ again: 1. It is connected route. Action: COW 2. It is gatewayed route or NONEXTHOP route. Action: clone it. */ - if (!dst_get_neighbour(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, daddr, saddr); else nrt = rt6_alloc_clone(rt, daddr); @@ -2326,6 +2335,7 @@ static int rt6_fill_node(struct net *net, struct nlmsghdr *nlh; long expires; u32 table; + struct neighbour *n; if (prefix) { /* user wants prefix routes only */ if (!(rt->rt6i_flags & RTF_PREFIX_RT)) { @@ -2414,8 +2424,11 @@ static int rt6_fill_node(struct net *net, if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; - if (dst_get_neighbour(&rt->dst)) - NLA_PUT(skb, RTA_GATEWAY, 16, &dst_get_neighbour(&rt->dst)->primary_key); + rcu_read_lock(); + n = dst_get_neighbour(&rt->dst); + if (n) + NLA_PUT(skb, RTA_GATEWAY, 16, &n->primary_key); + rcu_read_unlock(); if (rt->dst.dev) NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex); @@ -2608,12 +2621,14 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) #else seq_puts(m, "00000000000000000000000000000000 00 "); #endif + rcu_read_lock(); n = dst_get_neighbour(&rt->dst); if (n) { seq_printf(m, "%pi6", n->primary_key); } else { seq_puts(m, "00000000000000000000000000000000"); } + rcu_read_unlock(); seq_printf(m, " %08x %08x %08x %08x %8s\n", rt->rt6i_metric, atomic_read(&rt->dst.__refcnt), rt->dst.__use, rt->rt6i_flags, diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 07bf1085458f..00b15ac7a702 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -672,6 +672,9 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if (skb->protocol != htons(ETH_P_IPV6)) goto tx_error; + if (tos == 1) + tos = ipv6_get_dsfield(iph6); + /* ISATAP (RFC4214) - must come before 6to4 */ if (dev->priv_flags & IFF_ISATAP) { struct neighbour *neigh = NULL; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 89d5bf806222..ac838965ff34 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -165,7 +165,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) int mss; struct dst_entry *dst; __u8 rcv_wscale; - bool ecn_ok; + bool ecn_ok = false; if (!sysctl_tcp_syncookies || !th->ack || th->rst) goto out; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 78aa53492b3e..d1fb63f4aeb7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -61,6 +61,7 @@ #include <net/timewait_sock.h> #include <net/netdma.h> #include <net/inet_common.h> +#include <net/secure_seq.h> #include <asm/uaccess.h> diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index f2b713847b45..075a3808aa40 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -51,7 +51,7 @@ #include <linux/cpu.h> #include <linux/reboot.h> #include <net/iucv/iucv.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/ebcdic.h> #include <asm/io.h> #include <asm/irq.h> diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index ed8a2335442f..ad4ac2601a56 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -55,7 +55,7 @@ #include <net/protocol.h> #include <asm/byteorder.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include "l2tp_core.h" diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index a8193f52c13c..d2726a74597d 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -103,7 +103,7 @@ static struct net_device_ops l2tp_eth_netdev_ops = { static void l2tp_eth_dev_setup(struct net_device *dev) { ether_setup(dev); - + dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->netdev_ops = &l2tp_eth_netdev_ops; dev->destructor = free_netdev; } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 39a21d0c61c4..f42cd0915966 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -97,7 +97,7 @@ #include <net/xfrm.h> #include <asm/byteorder.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include "l2tp_core.h" diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index cd5fb40d3fd4..556e7e6ddf0a 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -698,6 +698,7 @@ static const struct net_device_ops ieee80211_monitorif_ops = { static void ieee80211_if_setup(struct net_device *dev) { ether_setup(dev); + dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->netdev_ops = &ieee80211_dataif_ops; dev->destructor = free_netdev; } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 866f269183cf..acb44230b251 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1012,7 +1012,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) cancel_work_sync(&local->reconfig_filter); ieee80211_clear_tx_pending(local); - sta_info_stop(local); rate_control_deinitialize(local); if (skb_queue_len(&local->skb_queue) || @@ -1024,6 +1023,7 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) destroy_workqueue(local->workqueue); wiphy_unregister(local->hw.wiphy); + sta_info_stop(local); ieee80211_wep_free(local); ieee80211_led_exit(local); kfree(local->int_scan_req); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index be43fd805bd0..2b771dc708a3 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3771,6 +3771,7 @@ err_sock: void ip_vs_control_cleanup(void) { EnterFunction(2); + unregister_netdevice_notifier(&ip_vs_dst_notifier); ip_vs_genl_unregister(); nf_unregister_sockopt(&ip_vs_sockopts); LeaveFunction(2); diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 5b466cd1272f..84d0fd47636a 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -312,6 +312,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) } break; case NF_STOLEN: + break; default: kfree_skb(skb); } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 2e7ccbb43ddb..2d8158acf6fa 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -33,7 +33,7 @@ #include <net/netfilter/nf_log.h> #include <net/netfilter/nfnetlink_log.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #ifdef CONFIG_BRIDGE_NETFILTER #include "../bridge/br_private.h" diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 49132bddd73e..00bd475eab4b 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -31,7 +31,7 @@ #include <net/sock.h> #include <net/netfilter/nf_queue.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #ifdef CONFIG_BRIDGE_NETFILTER #include "../bridge/br_private.h" diff --git a/net/netlabel/Makefile b/net/netlabel/Makefile index ea750e9df65f..d2732fc952e2 100644 --- a/net/netlabel/Makefile +++ b/net/netlabel/Makefile @@ -1,8 +1,6 @@ # # Makefile for the NetLabel subsystem. # -# Feb 9, 2006, Paul Moore <paul.moore@hp.com> -# # base objects obj-y := netlabel_user.o netlabel_kapi.o diff --git a/net/netlabel/netlabel_addrlist.c b/net/netlabel/netlabel_addrlist.c index c0519139679e..96b749dacc34 100644 --- a/net/netlabel/netlabel_addrlist.c +++ b/net/netlabel/netlabel_addrlist.c @@ -6,7 +6,7 @@ * system manages static and dynamic label mappings for network protocols such * as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_addrlist.h b/net/netlabel/netlabel_addrlist.h index 2b9644e19de0..fdbc1d2c7352 100644 --- a/net/netlabel/netlabel_addrlist.h +++ b/net/netlabel/netlabel_addrlist.h @@ -6,7 +6,7 @@ * system manages static and dynamic label mappings for network protocols such * as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index bae5756b1626..6bf878335d94 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -5,7 +5,7 @@ * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ @@ -39,7 +39,7 @@ #include <net/genetlink.h> #include <net/netlabel.h> #include <net/cipso_ipv4.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include "netlabel_user.h" #include "netlabel_cipso_v4.h" diff --git a/net/netlabel/netlabel_cipso_v4.h b/net/netlabel/netlabel_cipso_v4.h index af7f3355103e..d24d774bfd62 100644 --- a/net/netlabel/netlabel_cipso_v4.h +++ b/net/netlabel/netlabel_cipso_v4.h @@ -5,7 +5,7 @@ * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index 2aa975e5452d..7d8083cde34f 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -6,7 +6,7 @@ * system manages static and dynamic label mappings for network protocols such * as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_domainhash.h b/net/netlabel/netlabel_domainhash.h index 0261dda3f2d2..bfcc0f7024c5 100644 --- a/net/netlabel/netlabel_domainhash.h +++ b/net/netlabel/netlabel_domainhash.h @@ -6,7 +6,7 @@ * system manages static and dynamic label mappings for network protocols such * as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 1b83e0009d8d..9c24de10a657 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -5,7 +5,7 @@ * system manages static and dynamic label mappings for network protocols such * as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ @@ -39,7 +39,7 @@ #include <net/netlabel.h> #include <net/cipso_ipv4.h> #include <asm/bug.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include "netlabel_domainhash.h" #include "netlabel_unlabeled.h" @@ -341,11 +341,11 @@ int netlbl_cfg_cipsov4_map_add(u32 doi, entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (entry == NULL) - return -ENOMEM; + goto out_entry; if (domain != NULL) { entry->domain = kstrdup(domain, GFP_ATOMIC); if (entry->domain == NULL) - goto cfg_cipsov4_map_add_failure; + goto out_domain; } if (addr == NULL && mask == NULL) { @@ -354,13 +354,13 @@ int netlbl_cfg_cipsov4_map_add(u32 doi, } else if (addr != NULL && mask != NULL) { addrmap = kzalloc(sizeof(*addrmap), GFP_ATOMIC); if (addrmap == NULL) - goto cfg_cipsov4_map_add_failure; + goto out_addrmap; INIT_LIST_HEAD(&addrmap->list4); INIT_LIST_HEAD(&addrmap->list6); addrinfo = kzalloc(sizeof(*addrinfo), GFP_ATOMIC); if (addrinfo == NULL) - goto cfg_cipsov4_map_add_failure; + goto out_addrinfo; addrinfo->type_def.cipsov4 = doi_def; addrinfo->type = NETLBL_NLTYPE_CIPSOV4; addrinfo->list.addr = addr->s_addr & mask->s_addr; @@ -374,7 +374,7 @@ int netlbl_cfg_cipsov4_map_add(u32 doi, entry->type = NETLBL_NLTYPE_ADDRSELECT; } else { ret_val = -EINVAL; - goto cfg_cipsov4_map_add_failure; + goto out_addrmap; } ret_val = netlbl_domhsh_add(entry, audit_info); @@ -384,11 +384,15 @@ int netlbl_cfg_cipsov4_map_add(u32 doi, return 0; cfg_cipsov4_map_add_failure: - cipso_v4_doi_putdef(doi_def); + kfree(addrinfo); +out_addrinfo: + kfree(addrmap); +out_addrmap: kfree(entry->domain); +out_domain: kfree(entry); - kfree(addrmap); - kfree(addrinfo); +out_entry: + cipso_v4_doi_putdef(doi_def); return ret_val; } diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 4f251b19fbcc..bfa555869775 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -5,7 +5,7 @@ * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ @@ -42,7 +42,7 @@ #include <net/ipv6.h> #include <net/netlabel.h> #include <net/cipso_ipv4.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include "netlabel_domainhash.h" #include "netlabel_user.h" diff --git a/net/netlabel/netlabel_mgmt.h b/net/netlabel/netlabel_mgmt.h index 0a25838bcf45..5a9f31ce5799 100644 --- a/net/netlabel/netlabel_mgmt.h +++ b/net/netlabel/netlabel_mgmt.h @@ -5,7 +5,7 @@ * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ @@ -32,7 +32,7 @@ #define _NETLABEL_MGMT_H #include <net/netlabel.h> -#include <asm/atomic.h> +#include <linux/atomic.h> /* * The following NetLabel payloads are supported by the management interface. diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 9a290ef5c175..e6e823656f9d 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -5,7 +5,7 @@ * NetLabel system. The NetLabel system manages static and dynamic label * mappings for network protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ @@ -52,7 +52,7 @@ #include <net/net_namespace.h> #include <net/netlabel.h> #include <asm/bug.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include "netlabel_user.h" #include "netlabel_addrlist.h" diff --git a/net/netlabel/netlabel_unlabeled.h b/net/netlabel/netlabel_unlabeled.h index 0bc8dc3f9e3c..700af49022a0 100644 --- a/net/netlabel/netlabel_unlabeled.h +++ b/net/netlabel/netlabel_unlabeled.h @@ -5,7 +5,7 @@ * NetLabel system. The NetLabel system manages static and dynamic label * mappings for network protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_user.c b/net/netlabel/netlabel_user.c index a3fd75ac3fa5..9fae63f10298 100644 --- a/net/netlabel/netlabel_user.c +++ b/net/netlabel/netlabel_user.c @@ -5,7 +5,7 @@ * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_user.h b/net/netlabel/netlabel_user.h index f4fc4c9ad567..81969785e279 100644 --- a/net/netlabel/netlabel_user.h +++ b/net/netlabel/netlabel_user.h @@ -5,7 +5,7 @@ * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 102fc212cd64..e051398fdf6b 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -196,8 +196,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, skb2->skb_iif = skb->dev->ifindex; skb2->dev = dev; - dev_queue_xmit(skb2); - err = 0; + err = dev_queue_xmit(skb2); out: if (err) { diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 2a318f2dc3e5..b5d56a22b1d2 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -112,7 +112,7 @@ static struct sk_buff *prio_dequeue(struct Qdisc *sch) for (prio = 0; prio < q->bands; prio++) { struct Qdisc *qdisc = q->queues[prio]; - struct sk_buff *skb = qdisc->dequeue(qdisc); + struct sk_buff *skb = qdisc_dequeue_peeked(qdisc); if (skb) { qdisc_bstats_update(sch, skb); sch->q.qlen--; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 4536ee64383e..4f5510e2bd6f 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -410,7 +410,12 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) /* Return Congestion Notification only if we dropped a packet * from this flow. */ - return (qlen != slot->qlen) ? NET_XMIT_CN : NET_XMIT_SUCCESS; + if (qlen != slot->qlen) + return NET_XMIT_CN; + + /* As we dropped a packet, better let upper stack know this */ + qdisc_tree_decrease_qlen(sch, 1); + return NET_XMIT_SUCCESS; } static struct sk_buff * diff --git a/net/socket.c b/net/socket.c index 02dc82db3d23..ffe92ca32f2a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -467,7 +467,7 @@ static struct socket *sock_alloc(void) struct inode *inode; struct socket *sock; - inode = new_inode(sock_mnt->mnt_sb); + inode = new_inode_pseudo(sock_mnt->mnt_sb); if (!inode) return NULL; @@ -580,7 +580,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) } EXPORT_SYMBOL(sock_sendmsg); -int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg, size_t size) +static int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg, size_t size) { struct kiocb iocb; struct sock_iocb siocb; @@ -1871,8 +1871,14 @@ SYSCALL_DEFINE2(shutdown, int, fd, int, how) #define COMPAT_NAMELEN(msg) COMPAT_MSG(msg, msg_namelen) #define COMPAT_FLAGS(msg) COMPAT_MSG(msg, msg_flags) +struct used_address { + struct sockaddr_storage name; + unsigned int name_len; +}; + static int __sys_sendmsg(struct socket *sock, struct msghdr __user *msg, - struct msghdr *msg_sys, unsigned flags, int nosec) + struct msghdr *msg_sys, unsigned flags, + struct used_address *used_address) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; @@ -1953,8 +1959,30 @@ static int __sys_sendmsg(struct socket *sock, struct msghdr __user *msg, if (sock->file->f_flags & O_NONBLOCK) msg_sys->msg_flags |= MSG_DONTWAIT; - err = (nosec ? sock_sendmsg_nosec : sock_sendmsg)(sock, msg_sys, - total_len); + /* + * If this is sendmmsg() and current destination address is same as + * previously succeeded address, omit asking LSM's decision. + * used_address->name_len is initialized to UINT_MAX so that the first + * destination address never matches. + */ + if (used_address && msg_sys->msg_name && + used_address->name_len == msg_sys->msg_namelen && + !memcmp(&used_address->name, msg_sys->msg_name, + used_address->name_len)) { + err = sock_sendmsg_nosec(sock, msg_sys, total_len); + goto out_freectl; + } + err = sock_sendmsg(sock, msg_sys, total_len); + /* + * If this is sendmmsg() and sending to current destination address was + * successful, remember it. + */ + if (used_address && err >= 0) { + used_address->name_len = msg_sys->msg_namelen; + if (msg_sys->msg_name) + memcpy(&used_address->name, msg_sys->msg_name, + used_address->name_len); + } out_freectl: if (ctl_buf != ctl) @@ -1979,7 +2007,7 @@ SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned, flags) if (!sock) goto out; - err = __sys_sendmsg(sock, msg, &msg_sys, flags, 0); + err = __sys_sendmsg(sock, msg, &msg_sys, flags, NULL); fput_light(sock->file, fput_needed); out: @@ -1998,6 +2026,10 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, struct mmsghdr __user *entry; struct compat_mmsghdr __user *compat_entry; struct msghdr msg_sys; + struct used_address used_address; + + if (vlen > UIO_MAXIOV) + vlen = UIO_MAXIOV; datagrams = 0; @@ -2005,27 +2037,22 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, if (!sock) return err; - err = sock_error(sock->sk); - if (err) - goto out_put; - + used_address.name_len = UINT_MAX; entry = mmsg; compat_entry = (struct compat_mmsghdr __user *)mmsg; + err = 0; while (datagrams < vlen) { - /* - * No need to ask LSM for more than the first datagram. - */ if (MSG_CMSG_COMPAT & flags) { err = __sys_sendmsg(sock, (struct msghdr __user *)compat_entry, - &msg_sys, flags, datagrams); + &msg_sys, flags, &used_address); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { err = __sys_sendmsg(sock, (struct msghdr __user *)entry, - &msg_sys, flags, datagrams); + &msg_sys, flags, &used_address); if (err < 0) break; err = put_user(err, &entry->msg_len); @@ -2037,29 +2064,11 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, ++datagrams; } -out_put: fput_light(sock->file, fput_needed); - if (err == 0) - return datagrams; - - if (datagrams != 0) { - /* - * We may send less entries than requested (vlen) if the - * sock is non blocking... - */ - if (err != -EAGAIN) { - /* - * ... or if sendmsg returns an error after we - * send some datagrams, where we record the - * error to return on the next call or if the - * app asks about it using getsockopt(SO_ERROR). - */ - sock->sk->sk_err = -err; - } - + /* We only return an error if no datagrams were able to be sent */ + if (datagrams != 0) return datagrams; - } return err; } diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index b2198e65d8bb..ffd243d09188 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -4,6 +4,10 @@ config SUNRPC config SUNRPC_GSS tristate +config SUNRPC_BACKCHANNEL + bool + depends on SUNRPC + config SUNRPC_XPRT_RDMA tristate depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS && EXPERIMENTAL diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index 9d2fca5ad14a..8209a0411bca 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -13,6 +13,6 @@ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ addr.o rpcb_clnt.o timer.o xdr.o \ sunrpc_syms.o cache.o rpc_pipe.o \ svc_xprt.o -sunrpc-$(CONFIG_NFS_V4_1) += backchannel_rqst.o bc_svc.o +sunrpc-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel_rqst.o bc_svc.o sunrpc-$(CONFIG_PROC_FS) += stats.o sunrpc-$(CONFIG_SYSCTL) += sysctl.o diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index cf06af3b63c6..91eaa26e4c42 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -29,8 +29,6 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. #define RPCDBG_FACILITY RPCDBG_TRANS #endif -#if defined(CONFIG_NFS_V4_1) - /* * Helper routines that track the number of preallocation elements * on the transport. @@ -174,7 +172,7 @@ out_free: dprintk("RPC: setup backchannel transport failed\n"); return -1; } -EXPORT_SYMBOL(xprt_setup_backchannel); +EXPORT_SYMBOL_GPL(xprt_setup_backchannel); /* * Destroys the backchannel preallocated structures. @@ -204,7 +202,7 @@ void xprt_destroy_backchannel(struct rpc_xprt *xprt, unsigned int max_reqs) dprintk("RPC: backchannel list empty= %s\n", list_empty(&xprt->bc_pa_list) ? "true" : "false"); } -EXPORT_SYMBOL(xprt_destroy_backchannel); +EXPORT_SYMBOL_GPL(xprt_destroy_backchannel); /* * One or more rpc_rqst structure have been preallocated during the @@ -279,4 +277,3 @@ void xprt_free_bc_request(struct rpc_rqst *req) spin_unlock_bh(&xprt->bc_pa_lock); } -#endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/bc_svc.c b/net/sunrpc/bc_svc.c index 1dd1a6890007..0b2eb388cbda 100644 --- a/net/sunrpc/bc_svc.c +++ b/net/sunrpc/bc_svc.c @@ -27,8 +27,6 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * reply over an existing open connection previously established by the client. */ -#if defined(CONFIG_NFS_V4_1) - #include <linux/module.h> #include <linux/sunrpc/xprt.h> @@ -63,4 +61,3 @@ int bc_send(struct rpc_rqst *req) return ret; } -#endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index c50818f0473b..c5347d29cfb7 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -64,9 +64,9 @@ static void call_decode(struct rpc_task *task); static void call_bind(struct rpc_task *task); static void call_bind_status(struct rpc_task *task); static void call_transmit(struct rpc_task *task); -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) static void call_bc_transmit(struct rpc_task *task); -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ static void call_status(struct rpc_task *task); static void call_transmit_status(struct rpc_task *task); static void call_refresh(struct rpc_task *task); @@ -715,7 +715,7 @@ rpc_call_async(struct rpc_clnt *clnt, const struct rpc_message *msg, int flags, } EXPORT_SYMBOL_GPL(rpc_call_async); -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) /** * rpc_run_bc_task - Allocate a new RPC task for backchannel use, then run * rpc_execute against it @@ -758,7 +758,7 @@ out: dprintk("RPC: rpc_run_bc_task: task= %p\n", task); return task; } -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ void rpc_call_start(struct rpc_task *task) @@ -1361,7 +1361,7 @@ call_transmit_status(struct rpc_task *task) } } -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) /* * 5b. Send the backchannel RPC reply. On error, drop the reply. In * addition, disconnect on connectivity errors. @@ -1425,7 +1425,7 @@ call_bc_transmit(struct rpc_task *task) } rpc_wake_up_queued_task(&req->rq_xprt->pending, task); } -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ /* * 6. Sort out the RPC call status @@ -1550,8 +1550,7 @@ call_decode(struct rpc_task *task) kxdrdproc_t decode = task->tk_msg.rpc_proc->p_decode; __be32 *p; - dprintk("RPC: %5u call_decode (status %d)\n", - task->tk_pid, task->tk_status); + dprint_status(task); if (task->tk_flags & RPC_CALL_MAJORSEEN) { if (clnt->cl_chatty) diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 4814e246a874..d12ffa545811 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -97,14 +97,16 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task) /* * Add new request to a priority queue. */ -static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue, struct rpc_task *task) +static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue, + struct rpc_task *task, + unsigned char queue_priority) { struct list_head *q; struct rpc_task *t; INIT_LIST_HEAD(&task->u.tk_wait.links); - q = &queue->tasks[task->tk_priority]; - if (unlikely(task->tk_priority > queue->maxpriority)) + q = &queue->tasks[queue_priority]; + if (unlikely(queue_priority > queue->maxpriority)) q = &queue->tasks[queue->maxpriority]; list_for_each_entry(t, q, u.tk_wait.list) { if (t->tk_owner == task->tk_owner) { @@ -123,12 +125,14 @@ static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue, struct r * improve overall performance. * Everyone else gets appended to the queue to ensure proper FIFO behavior. */ -static void __rpc_add_wait_queue(struct rpc_wait_queue *queue, struct rpc_task *task) +static void __rpc_add_wait_queue(struct rpc_wait_queue *queue, + struct rpc_task *task, + unsigned char queue_priority) { BUG_ON (RPC_IS_QUEUED(task)); if (RPC_IS_PRIORITY(queue)) - __rpc_add_wait_queue_priority(queue, task); + __rpc_add_wait_queue_priority(queue, task, queue_priority); else if (RPC_IS_SWAPPER(task)) list_add(&task->u.tk_wait.list, &queue->tasks[0]); else @@ -311,13 +315,15 @@ static void rpc_make_runnable(struct rpc_task *task) * NB: An RPC task will only receive interrupt-driven events as long * as it's on a wait queue. */ -static void __rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task, - rpc_action action) +static void __rpc_sleep_on_priority(struct rpc_wait_queue *q, + struct rpc_task *task, + rpc_action action, + unsigned char queue_priority) { dprintk("RPC: %5u sleep_on(queue \"%s\" time %lu)\n", task->tk_pid, rpc_qname(q), jiffies); - __rpc_add_wait_queue(q, task); + __rpc_add_wait_queue(q, task, queue_priority); BUG_ON(task->tk_callback != NULL); task->tk_callback = action; @@ -334,11 +340,25 @@ void rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task, * Protect the queue operations. */ spin_lock_bh(&q->lock); - __rpc_sleep_on(q, task, action); + __rpc_sleep_on_priority(q, task, action, task->tk_priority); spin_unlock_bh(&q->lock); } EXPORT_SYMBOL_GPL(rpc_sleep_on); +void rpc_sleep_on_priority(struct rpc_wait_queue *q, struct rpc_task *task, + rpc_action action, int priority) +{ + /* We shouldn't ever put an inactive task to sleep */ + BUG_ON(!RPC_IS_ACTIVATED(task)); + + /* + * Protect the queue operations. + */ + spin_lock_bh(&q->lock); + __rpc_sleep_on_priority(q, task, action, priority - RPC_PRIORITY_LOW); + spin_unlock_bh(&q->lock); +} + /** * __rpc_do_wake_up_task - wake up a single rpc_task * @queue: wait queue diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 2b90292e9505..6a69a1131fb7 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1252,7 +1252,7 @@ svc_process(struct svc_rqst *rqstp) } } -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) /* * Process a backchannel RPC request that arrived over an existing * outbound connection @@ -1300,8 +1300,8 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req, return 0; } } -EXPORT_SYMBOL(bc_svc_process); -#endif /* CONFIG_NFS_V4_1 */ +EXPORT_SYMBOL_GPL(bc_svc_process); +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ /* * Return (transport-specific) limit on the rpc payload. diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index f2cb5b881dea..767d494de7a2 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -68,12 +68,12 @@ static void svc_sock_free(struct svc_xprt *); static struct svc_xprt *svc_create_socket(struct svc_serv *, int, struct net *, struct sockaddr *, int, int); -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int, struct net *, struct sockaddr *, int, int); static void svc_bc_sock_free(struct svc_xprt *xprt); -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key svc_key[2]; @@ -1243,7 +1243,7 @@ static struct svc_xprt *svc_tcp_create(struct svc_serv *serv, return svc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags); } -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int, struct net *, struct sockaddr *, int, int); @@ -1284,7 +1284,7 @@ static void svc_cleanup_bc_xprt_sock(void) { svc_unreg_xprt_class(&svc_tcp_bc_class); } -#else /* CONFIG_NFS_V4_1 */ +#else /* CONFIG_SUNRPC_BACKCHANNEL */ static void svc_init_bc_xprt_sock(void) { } @@ -1292,7 +1292,7 @@ static void svc_init_bc_xprt_sock(void) static void svc_cleanup_bc_xprt_sock(void) { } -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ static struct svc_xprt_ops svc_tcp_ops = { .xpo_create = svc_tcp_create, @@ -1623,7 +1623,7 @@ static void svc_sock_free(struct svc_xprt *xprt) kfree(svsk); } -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) /* * Create a back channel svc_xprt which shares the fore channel socket. */ @@ -1662,4 +1662,4 @@ static void svc_bc_sock_free(struct svc_xprt *xprt) if (xprt) kfree(container_of(xprt, struct svc_sock, sk_xprt)); } -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index f008c14ad34c..277ebd4bf095 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -126,7 +126,7 @@ xdr_terminate_string(struct xdr_buf *buf, const u32 len) kaddr[buf->page_base + len] = '\0'; kunmap_atomic(kaddr, KM_USER0); } -EXPORT_SYMBOL(xdr_terminate_string); +EXPORT_SYMBOL_GPL(xdr_terminate_string); void xdr_encode_pages(struct xdr_buf *xdr, struct page **pages, unsigned int base, diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index ce5eb68a9664..f4385e45a5fc 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -62,6 +62,7 @@ /* * Local functions */ +static void xprt_init(struct rpc_xprt *xprt, struct net *net); static void xprt_request_init(struct rpc_task *, struct rpc_xprt *); static void xprt_connect_status(struct rpc_task *task); static int __xprt_get_cong(struct rpc_xprt *, struct rpc_task *); @@ -186,15 +187,16 @@ EXPORT_SYMBOL_GPL(xprt_load_transport); /** * xprt_reserve_xprt - serialize write access to transports * @task: task that is requesting access to the transport + * @xprt: pointer to the target transport * * This prevents mixing the payload of separate requests, and prevents * transport connects from colliding with writes. No congestion control * is provided. */ -int xprt_reserve_xprt(struct rpc_task *task) +int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; - struct rpc_xprt *xprt = req->rq_xprt; + int priority; if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) { if (task == xprt->snd_task) @@ -202,8 +204,10 @@ int xprt_reserve_xprt(struct rpc_task *task) goto out_sleep; } xprt->snd_task = task; - req->rq_bytes_sent = 0; - req->rq_ntrans++; + if (req != NULL) { + req->rq_bytes_sent = 0; + req->rq_ntrans++; + } return 1; @@ -212,10 +216,13 @@ out_sleep: task->tk_pid, xprt); task->tk_timeout = 0; task->tk_status = -EAGAIN; - if (req->rq_ntrans) - rpc_sleep_on(&xprt->resend, task, NULL); + if (req == NULL) + priority = RPC_PRIORITY_LOW; + else if (!req->rq_ntrans) + priority = RPC_PRIORITY_NORMAL; else - rpc_sleep_on(&xprt->sending, task, NULL); + priority = RPC_PRIORITY_HIGH; + rpc_sleep_on_priority(&xprt->sending, task, NULL, priority); return 0; } EXPORT_SYMBOL_GPL(xprt_reserve_xprt); @@ -239,22 +246,24 @@ static void xprt_clear_locked(struct rpc_xprt *xprt) * integrated into the decision of whether a request is allowed to be * woken up and given access to the transport. */ -int xprt_reserve_xprt_cong(struct rpc_task *task) +int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) { - struct rpc_xprt *xprt = task->tk_xprt; struct rpc_rqst *req = task->tk_rqstp; + int priority; if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) { if (task == xprt->snd_task) return 1; goto out_sleep; } + if (req == NULL) { + xprt->snd_task = task; + return 1; + } if (__xprt_get_cong(xprt, task)) { xprt->snd_task = task; - if (req) { - req->rq_bytes_sent = 0; - req->rq_ntrans++; - } + req->rq_bytes_sent = 0; + req->rq_ntrans++; return 1; } xprt_clear_locked(xprt); @@ -262,10 +271,13 @@ out_sleep: dprintk("RPC: %5u failed to lock transport %p\n", task->tk_pid, xprt); task->tk_timeout = 0; task->tk_status = -EAGAIN; - if (req && req->rq_ntrans) - rpc_sleep_on(&xprt->resend, task, NULL); + if (req == NULL) + priority = RPC_PRIORITY_LOW; + else if (!req->rq_ntrans) + priority = RPC_PRIORITY_NORMAL; else - rpc_sleep_on(&xprt->sending, task, NULL); + priority = RPC_PRIORITY_HIGH; + rpc_sleep_on_priority(&xprt->sending, task, NULL, priority); return 0; } EXPORT_SYMBOL_GPL(xprt_reserve_xprt_cong); @@ -275,7 +287,7 @@ static inline int xprt_lock_write(struct rpc_xprt *xprt, struct rpc_task *task) int retval; spin_lock_bh(&xprt->transport_lock); - retval = xprt->ops->reserve_xprt(task); + retval = xprt->ops->reserve_xprt(xprt, task); spin_unlock_bh(&xprt->transport_lock); return retval; } @@ -288,12 +300,9 @@ static void __xprt_lock_write_next(struct rpc_xprt *xprt) if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) return; - task = rpc_wake_up_next(&xprt->resend); - if (!task) { - task = rpc_wake_up_next(&xprt->sending); - if (!task) - goto out_unlock; - } + task = rpc_wake_up_next(&xprt->sending); + if (task == NULL) + goto out_unlock; req = task->tk_rqstp; xprt->snd_task = task; @@ -310,24 +319,25 @@ out_unlock: static void __xprt_lock_write_next_cong(struct rpc_xprt *xprt) { struct rpc_task *task; + struct rpc_rqst *req; if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) return; if (RPCXPRT_CONGESTED(xprt)) goto out_unlock; - task = rpc_wake_up_next(&xprt->resend); - if (!task) { - task = rpc_wake_up_next(&xprt->sending); - if (!task) - goto out_unlock; + task = rpc_wake_up_next(&xprt->sending); + if (task == NULL) + goto out_unlock; + + req = task->tk_rqstp; + if (req == NULL) { + xprt->snd_task = task; + return; } if (__xprt_get_cong(xprt, task)) { - struct rpc_rqst *req = task->tk_rqstp; xprt->snd_task = task; - if (req) { - req->rq_bytes_sent = 0; - req->rq_ntrans++; - } + req->rq_bytes_sent = 0; + req->rq_ntrans++; return; } out_unlock: @@ -852,7 +862,7 @@ int xprt_prepare_transmit(struct rpc_task *task) err = req->rq_reply_bytes_recvd; goto out_unlock; } - if (!xprt->ops->reserve_xprt(task)) + if (!xprt->ops->reserve_xprt(xprt, task)) err = -EAGAIN; out_unlock: spin_unlock_bh(&xprt->transport_lock); @@ -928,28 +938,66 @@ void xprt_transmit(struct rpc_task *task) spin_unlock_bh(&xprt->transport_lock); } +static struct rpc_rqst *xprt_dynamic_alloc_slot(struct rpc_xprt *xprt, gfp_t gfp_flags) +{ + struct rpc_rqst *req = ERR_PTR(-EAGAIN); + + if (!atomic_add_unless(&xprt->num_reqs, 1, xprt->max_reqs)) + goto out; + req = kzalloc(sizeof(struct rpc_rqst), gfp_flags); + if (req != NULL) + goto out; + atomic_dec(&xprt->num_reqs); + req = ERR_PTR(-ENOMEM); +out: + return req; +} + +static bool xprt_dynamic_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) +{ + if (atomic_add_unless(&xprt->num_reqs, -1, xprt->min_reqs)) { + kfree(req); + return true; + } + return false; +} + static void xprt_alloc_slot(struct rpc_task *task) { struct rpc_xprt *xprt = task->tk_xprt; + struct rpc_rqst *req; - task->tk_status = 0; - if (task->tk_rqstp) - return; if (!list_empty(&xprt->free)) { - struct rpc_rqst *req = list_entry(xprt->free.next, struct rpc_rqst, rq_list); - list_del_init(&req->rq_list); - task->tk_rqstp = req; - xprt_request_init(task, xprt); - return; + req = list_entry(xprt->free.next, struct rpc_rqst, rq_list); + list_del(&req->rq_list); + goto out_init_req; + } + req = xprt_dynamic_alloc_slot(xprt, GFP_NOWAIT); + if (!IS_ERR(req)) + goto out_init_req; + switch (PTR_ERR(req)) { + case -ENOMEM: + rpc_delay(task, HZ >> 2); + dprintk("RPC: dynamic allocation of request slot " + "failed! Retrying\n"); + break; + case -EAGAIN: + rpc_sleep_on(&xprt->backlog, task, NULL); + dprintk("RPC: waiting for request slot\n"); } - dprintk("RPC: waiting for request slot\n"); task->tk_status = -EAGAIN; - task->tk_timeout = 0; - rpc_sleep_on(&xprt->backlog, task, NULL); + return; +out_init_req: + task->tk_status = 0; + task->tk_rqstp = req; + xprt_request_init(task, xprt); } static void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) { + if (xprt_dynamic_free_slot(xprt, req)) + return; + memset(req, 0, sizeof(*req)); /* mark unused */ spin_lock(&xprt->reserve_lock); @@ -958,25 +1006,49 @@ static void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) spin_unlock(&xprt->reserve_lock); } -struct rpc_xprt *xprt_alloc(struct net *net, int size, int max_req) +static void xprt_free_all_slots(struct rpc_xprt *xprt) +{ + struct rpc_rqst *req; + while (!list_empty(&xprt->free)) { + req = list_first_entry(&xprt->free, struct rpc_rqst, rq_list); + list_del(&req->rq_list); + kfree(req); + } +} + +struct rpc_xprt *xprt_alloc(struct net *net, size_t size, + unsigned int num_prealloc, + unsigned int max_alloc) { struct rpc_xprt *xprt; + struct rpc_rqst *req; + int i; xprt = kzalloc(size, GFP_KERNEL); if (xprt == NULL) goto out; - atomic_set(&xprt->count, 1); - xprt->max_reqs = max_req; - xprt->slot = kcalloc(max_req, sizeof(struct rpc_rqst), GFP_KERNEL); - if (xprt->slot == NULL) + xprt_init(xprt, net); + + for (i = 0; i < num_prealloc; i++) { + req = kzalloc(sizeof(struct rpc_rqst), GFP_KERNEL); + if (!req) + break; + list_add(&req->rq_list, &xprt->free); + } + if (i < num_prealloc) goto out_free; + if (max_alloc > num_prealloc) + xprt->max_reqs = max_alloc; + else + xprt->max_reqs = num_prealloc; + xprt->min_reqs = num_prealloc; + atomic_set(&xprt->num_reqs, num_prealloc); - xprt->xprt_net = get_net(net); return xprt; out_free: - kfree(xprt); + xprt_free(xprt); out: return NULL; } @@ -985,7 +1057,7 @@ EXPORT_SYMBOL_GPL(xprt_alloc); void xprt_free(struct rpc_xprt *xprt) { put_net(xprt->xprt_net); - kfree(xprt->slot); + xprt_free_all_slots(xprt); kfree(xprt); } EXPORT_SYMBOL_GPL(xprt_free); @@ -1001,10 +1073,24 @@ void xprt_reserve(struct rpc_task *task) { struct rpc_xprt *xprt = task->tk_xprt; - task->tk_status = -EIO; + task->tk_status = 0; + if (task->tk_rqstp != NULL) + return; + + /* Note: grabbing the xprt_lock_write() here is not strictly needed, + * but ensures that we throttle new slot allocation if the transport + * is congested (e.g. if reconnecting or if we're out of socket + * write buffer space). + */ + task->tk_timeout = 0; + task->tk_status = -EAGAIN; + if (!xprt_lock_write(xprt, task)) + return; + spin_lock(&xprt->reserve_lock); xprt_alloc_slot(task); spin_unlock(&xprt->reserve_lock); + xprt_release_write(xprt, task); } static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt) @@ -1021,6 +1107,7 @@ static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt) { struct rpc_rqst *req = task->tk_rqstp; + INIT_LIST_HEAD(&req->rq_list); req->rq_timeout = task->tk_client->cl_timeout->to_initval; req->rq_task = task; req->rq_xprt = xprt; @@ -1073,6 +1160,34 @@ void xprt_release(struct rpc_task *task) xprt_free_bc_request(req); } +static void xprt_init(struct rpc_xprt *xprt, struct net *net) +{ + atomic_set(&xprt->count, 1); + + spin_lock_init(&xprt->transport_lock); + spin_lock_init(&xprt->reserve_lock); + + INIT_LIST_HEAD(&xprt->free); + INIT_LIST_HEAD(&xprt->recv); +#if defined(CONFIG_SUNRPC_BACKCHANNEL) + spin_lock_init(&xprt->bc_pa_lock); + INIT_LIST_HEAD(&xprt->bc_pa_list); +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ + + xprt->last_used = jiffies; + xprt->cwnd = RPC_INITCWND; + xprt->bind_index = 0; + + rpc_init_wait_queue(&xprt->binding, "xprt_binding"); + rpc_init_wait_queue(&xprt->pending, "xprt_pending"); + rpc_init_priority_wait_queue(&xprt->sending, "xprt_sending"); + rpc_init_priority_wait_queue(&xprt->backlog, "xprt_backlog"); + + xprt_init_xid(xprt); + + xprt->xprt_net = get_net(net); +} + /** * xprt_create_transport - create an RPC transport * @args: rpc transport creation arguments @@ -1081,7 +1196,6 @@ void xprt_release(struct rpc_task *task) struct rpc_xprt *xprt_create_transport(struct xprt_create *args) { struct rpc_xprt *xprt; - struct rpc_rqst *req; struct xprt_class *t; spin_lock(&xprt_list_lock); @@ -1100,46 +1214,17 @@ found: if (IS_ERR(xprt)) { dprintk("RPC: xprt_create_transport: failed, %ld\n", -PTR_ERR(xprt)); - return xprt; + goto out; } - if (test_and_set_bit(XPRT_INITIALIZED, &xprt->state)) - /* ->setup returned a pre-initialized xprt: */ - return xprt; - - spin_lock_init(&xprt->transport_lock); - spin_lock_init(&xprt->reserve_lock); - - INIT_LIST_HEAD(&xprt->free); - INIT_LIST_HEAD(&xprt->recv); -#if defined(CONFIG_NFS_V4_1) - spin_lock_init(&xprt->bc_pa_lock); - INIT_LIST_HEAD(&xprt->bc_pa_list); -#endif /* CONFIG_NFS_V4_1 */ - INIT_WORK(&xprt->task_cleanup, xprt_autoclose); if (xprt_has_timer(xprt)) setup_timer(&xprt->timer, xprt_init_autodisconnect, (unsigned long)xprt); else init_timer(&xprt->timer); - xprt->last_used = jiffies; - xprt->cwnd = RPC_INITCWND; - xprt->bind_index = 0; - - rpc_init_wait_queue(&xprt->binding, "xprt_binding"); - rpc_init_wait_queue(&xprt->pending, "xprt_pending"); - rpc_init_wait_queue(&xprt->sending, "xprt_sending"); - rpc_init_wait_queue(&xprt->resend, "xprt_resend"); - rpc_init_priority_wait_queue(&xprt->backlog, "xprt_backlog"); - - /* initialize free list */ - for (req = &xprt->slot[xprt->max_reqs-1]; req >= &xprt->slot[0]; req--) - list_add(&req->rq_list, &xprt->free); - - xprt_init_xid(xprt); - dprintk("RPC: created transport %p with %u slots\n", xprt, xprt->max_reqs); +out: return xprt; } @@ -1157,7 +1242,6 @@ static void xprt_destroy(struct rpc_xprt *xprt) rpc_destroy_wait_queue(&xprt->binding); rpc_destroy_wait_queue(&xprt->pending); rpc_destroy_wait_queue(&xprt->sending); - rpc_destroy_wait_queue(&xprt->resend); rpc_destroy_wait_queue(&xprt->backlog); cancel_work_sync(&xprt->task_cleanup); /* diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 0867070bb5ca..b446e100286f 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -283,6 +283,7 @@ xprt_setup_rdma(struct xprt_create *args) } xprt = xprt_alloc(args->net, sizeof(struct rpcrdma_xprt), + xprt_rdma_slot_table_entries, xprt_rdma_slot_table_entries); if (xprt == NULL) { dprintk("RPC: %s: couldn't allocate rpcrdma_xprt\n", @@ -452,9 +453,8 @@ xprt_rdma_connect(struct rpc_task *task) } static int -xprt_rdma_reserve_xprt(struct rpc_task *task) +xprt_rdma_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task) { - struct rpc_xprt *xprt = task->tk_xprt; struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); int credits = atomic_read(&r_xprt->rx_buf.rb_credits); @@ -466,7 +466,7 @@ xprt_rdma_reserve_xprt(struct rpc_task *task) BUG_ON(r_xprt->rx_buf.rb_cwndscale <= 0); } xprt->cwnd = credits * r_xprt->rx_buf.rb_cwndscale; - return xprt_reserve_xprt_cong(task); + return xprt_reserve_xprt_cong(xprt, task); } /* diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index cae761a8536c..08c5d5a128fc 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -42,7 +42,7 @@ #include <linux/wait.h> /* wait_queue_head_t, etc */ #include <linux/spinlock.h> /* spinlock_t, etc */ -#include <asm/atomic.h> /* atomic_t, etc */ +#include <linux/atomic.h> /* atomic_t, etc */ #include <rdma/rdma_cm.h> /* RDMA connection api */ #include <rdma/ib_verbs.h> /* RDMA verbs api */ @@ -109,7 +109,7 @@ struct rpcrdma_ep { */ /* temporary static scatter/gather max */ -#define RPCRDMA_MAX_DATA_SEGS (8) /* max scatter/gather */ +#define RPCRDMA_MAX_DATA_SEGS (64) /* max scatter/gather */ #define RPCRDMA_MAX_SEGS (RPCRDMA_MAX_DATA_SEGS + 2) /* head+tail = 2 */ #define MAX_RPCRDMAHDR (\ /* max supported RPC/RDMA header */ \ diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 72abb7358933..d7f97ef26590 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -37,7 +37,7 @@ #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/xprtsock.h> #include <linux/file.h> -#ifdef CONFIG_NFS_V4_1 +#ifdef CONFIG_SUNRPC_BACKCHANNEL #include <linux/sunrpc/bc_xprt.h> #endif @@ -54,7 +54,8 @@ static void xs_close(struct rpc_xprt *xprt); * xprtsock tunables */ unsigned int xprt_udp_slot_table_entries = RPC_DEF_SLOT_TABLE; -unsigned int xprt_tcp_slot_table_entries = RPC_DEF_SLOT_TABLE; +unsigned int xprt_tcp_slot_table_entries = RPC_MIN_SLOT_TABLE; +unsigned int xprt_max_tcp_slot_table_entries = RPC_MAX_SLOT_TABLE; unsigned int xprt_min_resvport = RPC_DEF_MIN_RESVPORT; unsigned int xprt_max_resvport = RPC_DEF_MAX_RESVPORT; @@ -75,6 +76,7 @@ static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO; static unsigned int min_slot_table_size = RPC_MIN_SLOT_TABLE; static unsigned int max_slot_table_size = RPC_MAX_SLOT_TABLE; +static unsigned int max_tcp_slot_table_limit = RPC_MAX_SLOT_TABLE_LIMIT; static unsigned int xprt_min_resvport_limit = RPC_MIN_RESVPORT; static unsigned int xprt_max_resvport_limit = RPC_MAX_RESVPORT; @@ -104,6 +106,15 @@ static ctl_table xs_tunables_table[] = { .extra2 = &max_slot_table_size }, { + .procname = "tcp_max_slot_table_entries", + .data = &xprt_max_tcp_slot_table_entries, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &min_slot_table_size, + .extra2 = &max_tcp_slot_table_limit + }, + { .procname = "min_resvport", .data = &xprt_min_resvport, .maxlen = sizeof(unsigned int), @@ -755,6 +766,8 @@ static void xs_tcp_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task) if (task == NULL) goto out_release; req = task->tk_rqstp; + if (req == NULL) + goto out_release; if (req->rq_bytes_sent == 0) goto out_release; if (req->rq_bytes_sent == req->rq_snd_buf.len) @@ -1236,7 +1249,7 @@ static inline int xs_tcp_read_reply(struct rpc_xprt *xprt, return 0; } -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_SUNRPC_BACKCHANNEL) /* * Obtains an rpc_rqst previously allocated and invokes the common * tcp read code to read the data. The result is placed in the callback @@ -1299,7 +1312,7 @@ static inline int _xs_tcp_read_data(struct rpc_xprt *xprt, { return xs_tcp_read_reply(xprt, desc); } -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ /* * Read data off the transport. This can be either an RPC_CALL or an @@ -2489,7 +2502,8 @@ static int xs_init_anyaddr(const int family, struct sockaddr *sap) } static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args, - unsigned int slot_table_size) + unsigned int slot_table_size, + unsigned int max_slot_table_size) { struct rpc_xprt *xprt; struct sock_xprt *new; @@ -2499,7 +2513,8 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args, return ERR_PTR(-EBADF); } - xprt = xprt_alloc(args->net, sizeof(*new), slot_table_size); + xprt = xprt_alloc(args->net, sizeof(*new), slot_table_size, + max_slot_table_size); if (xprt == NULL) { dprintk("RPC: xs_setup_xprt: couldn't allocate " "rpc_xprt\n"); @@ -2541,7 +2556,8 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) struct rpc_xprt *xprt; struct rpc_xprt *ret; - xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries); + xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries, + xprt_max_tcp_slot_table_entries); if (IS_ERR(xprt)) return xprt; transport = container_of(xprt, struct sock_xprt, xprt); @@ -2605,7 +2621,8 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) struct sock_xprt *transport; struct rpc_xprt *ret; - xprt = xs_setup_xprt(args, xprt_udp_slot_table_entries); + xprt = xs_setup_xprt(args, xprt_udp_slot_table_entries, + xprt_udp_slot_table_entries); if (IS_ERR(xprt)) return xprt; transport = container_of(xprt, struct sock_xprt, xprt); @@ -2681,7 +2698,8 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) struct sock_xprt *transport; struct rpc_xprt *ret; - xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries); + xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries, + xprt_max_tcp_slot_table_entries); if (IS_ERR(xprt)) return xprt; transport = container_of(xprt, struct sock_xprt, xprt); @@ -2760,7 +2778,8 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) */ return args->bc_xprt->xpt_bc_xprt; } - xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries); + xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries, + xprt_tcp_slot_table_entries); if (IS_ERR(xprt)) return xprt; transport = container_of(xprt, struct sock_xprt, xprt); @@ -2947,8 +2966,26 @@ static struct kernel_param_ops param_ops_slot_table_size = { #define param_check_slot_table_size(name, p) \ __param_check(name, p, unsigned int); +static int param_set_max_slot_table_size(const char *val, + const struct kernel_param *kp) +{ + return param_set_uint_minmax(val, kp, + RPC_MIN_SLOT_TABLE, + RPC_MAX_SLOT_TABLE_LIMIT); +} + +static struct kernel_param_ops param_ops_max_slot_table_size = { + .set = param_set_max_slot_table_size, + .get = param_get_uint, +}; + +#define param_check_max_slot_table_size(name, p) \ + __param_check(name, p, unsigned int); + module_param_named(tcp_slot_table_entries, xprt_tcp_slot_table_entries, slot_table_size, 0644); +module_param_named(tcp_max_slot_table_entries, xprt_max_tcp_slot_table_entries, + max_slot_table_size, 0644); module_param_named(udp_slot_table_entries, xprt_udp_slot_table_entries, slot_table_size, 0644); diff --git a/net/tipc/core.h b/net/tipc/core.h index d234a98a460a..2761af36d141 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -47,7 +47,7 @@ #include <linux/string.h> #include <asm/uaccess.h> #include <linux/interrupt.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/hardirq.h> #include <linux/netdevice.h> #include <linux/in.h> diff --git a/net/wireless/core.c b/net/wireless/core.c index 645437cfc464..c14865172da7 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -616,6 +616,9 @@ int wiphy_register(struct wiphy *wiphy) if (res) goto out_rm_dev; + rtnl_lock(); + rdev->wiphy.registered = true; + rtnl_unlock(); return 0; out_rm_dev: @@ -647,6 +650,10 @@ void wiphy_unregister(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + rtnl_lock(); + rdev->wiphy.registered = false; + rtnl_unlock(); + rfkill_unregister(rdev->rfkill); /* protect the device list */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 28d2aa109bee..e83e7fee3bc0 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3464,7 +3464,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) tmp) { enum ieee80211_band band = nla_type(attr); - if (band < 0 || band > IEEE80211_NUM_BANDS) { + if (band < 0 || band >= IEEE80211_NUM_BANDS) { err = -EINVAL; goto out_free; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 1ad0f39fe091..02751dbc5a97 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -903,7 +903,7 @@ static bool ignore_reg_update(struct wiphy *wiphy, initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE && !is_world_regdom(last_request->alpha2)) { REG_DBG_PRINT("Ignoring regulatory request %s " - "since the driver requires its own regulaotry " + "since the driver requires its own regulatory " "domain to be set first", reg_initiator_name(initiator)); return true; @@ -1125,12 +1125,13 @@ void wiphy_update_regulatory(struct wiphy *wiphy, enum ieee80211_band band; if (ignore_reg_update(wiphy, initiator)) - goto out; + return; + for (band = 0; band < IEEE80211_NUM_BANDS; band++) { if (wiphy->bands[band]) handle_band(wiphy, band, initiator); } -out: + reg_process_beacons(wiphy); reg_process_ht_flags(wiphy); if (wiphy->reg_notifier) diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index c6e4ca6a7d2e..ff574597a854 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -93,7 +93,8 @@ static int wiphy_suspend(struct device *dev, pm_message_t state) if (rdev->ops->suspend) { rtnl_lock(); - ret = rdev->ops->suspend(&rdev->wiphy, rdev->wowlan); + if (rdev->wiphy.registered) + ret = rdev->ops->suspend(&rdev->wiphy, rdev->wowlan); rtnl_unlock(); } @@ -112,7 +113,8 @@ static int wiphy_resume(struct device *dev) if (rdev->ops->resume) { rtnl_lock(); - ret = rdev->ops->resume(&rdev->wiphy); + if (rdev->wiphy.registered) + ret = rdev->ops->resume(&rdev->wiphy); rtnl_unlock(); } diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 58064d9e565d..791ab2e77f3f 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -462,8 +462,8 @@ static struct xfrm_algo_desc ealg_list[] = { .desc = { .sadb_alg_id = SADB_X_EALG_AESCTR, .sadb_alg_ivlen = 8, - .sadb_alg_minbits = 128, - .sadb_alg_maxbits = 256 + .sadb_alg_minbits = 160, + .sadb_alg_maxbits = 288 } }, }; |