diff options
author | Benjamin Herrenschmidt <benh@kernel.crashing.org> | 2011-01-11 15:10:08 +1100 |
---|---|---|
committer | Benjamin Herrenschmidt <benh@kernel.crashing.org> | 2011-01-11 15:10:08 +1100 |
commit | eed0ba0b4ab2d1668588219a8efa81bf8636a12d (patch) | |
tree | f5aa3c732e7830a1b24e6071f8bed0f799881187 /net | |
parent | 98b14d6b290d96b24ae993ceaccc59b2aa4b130c (diff) | |
parent | c9de9333f5a860cab82052bce6ac28bcac9b2c26 (diff) | |
download | blackbird-op-linux-eed0ba0b4ab2d1668588219a8efa81bf8636a12d.tar.gz blackbird-op-linux-eed0ba0b4ab2d1668588219a8efa81bf8636a12d.zip |
Merge remote branch 'gcl/next' into next
Diffstat (limited to 'net')
51 files changed, 357 insertions, 208 deletions
diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c index 799c631f0fed..f7fa67c78766 100644 --- a/net/atm/atm_sysfs.c +++ b/net/atm/atm_sysfs.c @@ -143,12 +143,13 @@ static struct class atm_class = { .dev_uevent = atm_uevent, }; -int atm_register_sysfs(struct atm_dev *adev) +int atm_register_sysfs(struct atm_dev *adev, struct device *parent) { struct device *cdev = &adev->class_dev; int i, j, err; cdev->class = &atm_class; + cdev->parent = parent; dev_set_drvdata(cdev, adev); dev_set_name(cdev, "%s%d", adev->type, adev->number); diff --git a/net/atm/resources.c b/net/atm/resources.c index d29e58261511..23f45ce6f351 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -74,8 +74,9 @@ struct atm_dev *atm_dev_lookup(int number) } EXPORT_SYMBOL(atm_dev_lookup); -struct atm_dev *atm_dev_register(const char *type, const struct atmdev_ops *ops, - int number, unsigned long *flags) +struct atm_dev *atm_dev_register(const char *type, struct device *parent, + const struct atmdev_ops *ops, int number, + unsigned long *flags) { struct atm_dev *dev, *inuse; @@ -115,7 +116,7 @@ struct atm_dev *atm_dev_register(const char *type, const struct atmdev_ops *ops, goto out_fail; } - if (atm_register_sysfs(dev) < 0) { + if (atm_register_sysfs(dev, parent) < 0) { pr_err("atm_register_sysfs failed for dev %s\n", type); atm_proc_dev_deregister(dev); goto out_fail; diff --git a/net/atm/resources.h b/net/atm/resources.h index 126fb1840dfb..521431e30507 100644 --- a/net/atm/resources.h +++ b/net/atm/resources.h @@ -42,6 +42,6 @@ static inline void atm_proc_dev_deregister(struct atm_dev *dev) #endif /* CONFIG_PROC_FS */ -int atm_register_sysfs(struct atm_dev *adev); +int atm_register_sysfs(struct atm_dev *adev, struct device *parent); void atm_unregister_sysfs(struct atm_dev *adev); #endif diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index fa642aa652bd..432a9a633e8d 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -311,6 +311,7 @@ static void rfcomm_dlc_clear_state(struct rfcomm_dlc *d) d->state = BT_OPEN; d->flags = 0; d->mscex = 0; + d->sec_level = BT_SECURITY_LOW; d->mtu = RFCOMM_DEFAULT_MTU; d->v24_sig = RFCOMM_V24_RTC | RFCOMM_V24_RTR | RFCOMM_V24_DV; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index d0927d1fdada..66b9e5c0523a 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -882,7 +882,7 @@ static int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 type) int lm = 0; if (type != SCO_LINK && type != ESCO_LINK) - return 0; + return -EINVAL; BT_DBG("hdev %s, bdaddr %s", hdev->name, batostr(bdaddr)); @@ -908,7 +908,7 @@ static int sco_connect_cfm(struct hci_conn *hcon, __u8 status) BT_DBG("hcon %p bdaddr %s status %d", hcon, batostr(&hcon->dst), status); if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) - return 0; + return -EINVAL; if (!status) { struct sco_conn *conn; @@ -927,7 +927,7 @@ static int sco_disconn_cfm(struct hci_conn *hcon, __u8 reason) BT_DBG("hcon %p reason %d", hcon, reason); if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) - return 0; + return -EINVAL; sco_conn_del(hcon, bt_err(reason)); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index eb5b256ffc88..f19e347f56f6 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -437,7 +437,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, ip6h = ipv6_hdr(skb); *(__force __be32 *)ip6h = htonl(0x60000000); - ip6h->payload_len = 8 + sizeof(*mldq); + ip6h->payload_len = htons(8 + sizeof(*mldq)); ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; ipv6_addr_set(&ip6h->saddr, 0, 0, 0, 0); diff --git a/net/ceph/Makefile b/net/ceph/Makefile index aab1cabb8035..5f19415ec9c0 100644 --- a/net/ceph/Makefile +++ b/net/ceph/Makefile @@ -1,9 +1,6 @@ # # Makefile for CEPH filesystem. # - -ifneq ($(KERNELRELEASE),) - obj-$(CONFIG_CEPH_LIB) += libceph.o libceph-objs := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \ @@ -16,22 +13,3 @@ libceph-objs := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \ ceph_fs.o ceph_strings.o ceph_hash.o \ pagevec.o -else -#Otherwise we were called directly from the command -# line; invoke the kernel build system. - -KERNELDIR ?= /lib/modules/$(shell uname -r)/build -PWD := $(shell pwd) - -default: all - -all: - $(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules - -modules_install: - $(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules_install - -clean: - $(MAKE) -C $(KERNELDIR) M=$(PWD) clean - -endif diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 1c7a2ec4f3cc..b6ff4a1519ab 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -97,11 +97,9 @@ struct workqueue_struct *ceph_msgr_wq; int ceph_msgr_init(void) { ceph_msgr_wq = create_workqueue("ceph-msgr"); - if (IS_ERR(ceph_msgr_wq)) { - int ret = PTR_ERR(ceph_msgr_wq); - pr_err("msgr_init failed to create workqueue: %d\n", ret); - ceph_msgr_wq = NULL; - return ret; + if (!ceph_msgr_wq) { + pr_err("msgr_init failed to create workqueue\n"); + return -ENOMEM; } return 0; } diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c index ac34feeb2b3a..1a040e64c69f 100644 --- a/net/ceph/pagevec.c +++ b/net/ceph/pagevec.c @@ -13,7 +13,7 @@ * build a vector of user pages */ struct page **ceph_get_direct_page_vector(const char __user *data, - int num_pages) + int num_pages, bool write_page) { struct page **pages; int rc; @@ -24,24 +24,27 @@ struct page **ceph_get_direct_page_vector(const char __user *data, down_read(¤t->mm->mmap_sem); rc = get_user_pages(current, current->mm, (unsigned long)data, - num_pages, 0, 0, pages, NULL); + num_pages, write_page, 0, pages, NULL); up_read(¤t->mm->mmap_sem); - if (rc < 0) + if (rc < num_pages) goto fail; return pages; fail: - kfree(pages); + ceph_put_page_vector(pages, rc > 0 ? rc : 0, false); return ERR_PTR(rc); } EXPORT_SYMBOL(ceph_get_direct_page_vector); -void ceph_put_page_vector(struct page **pages, int num_pages) +void ceph_put_page_vector(struct page **pages, int num_pages, bool dirty) { int i; - for (i = 0; i < num_pages; i++) + for (i = 0; i < num_pages; i++) { + if (dirty) + set_page_dirty_lock(pages[i]); put_page(pages[i]); + } kfree(pages); } EXPORT_SYMBOL(ceph_put_page_vector); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 82a4369ae150..a20e5d3bbfa0 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -181,8 +181,7 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, { int ret = 0; - if (rule->iifindex && (rule->iifindex != fl->iif) && - !(fl->flags & FLOWI_FLAG_MATCH_ANY_IIF)) + if (rule->iifindex && (rule->iifindex != fl->iif)) goto out; if (rule->oifindex && (rule->oifindex != fl->oif)) diff --git a/net/core/filter.c b/net/core/filter.c index c1ee800bc080..ae21a0d3c4a2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -589,23 +589,16 @@ int sk_chk_filter(struct sock_filter *filter, int flen) EXPORT_SYMBOL(sk_chk_filter); /** - * sk_filter_rcu_release - Release a socket filter by rcu_head + * sk_filter_release_rcu - Release a socket filter by rcu_head * @rcu: rcu_head that contains the sk_filter to free */ -static void sk_filter_rcu_release(struct rcu_head *rcu) +void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); - sk_filter_release(fp); -} - -static void sk_filter_delayed_uncharge(struct sock *sk, struct sk_filter *fp) -{ - unsigned int size = sk_filter_len(fp); - - atomic_sub(size, &sk->sk_omem_alloc); - call_rcu_bh(&fp->rcu, sk_filter_rcu_release); + kfree(fp); } +EXPORT_SYMBOL(sk_filter_release_rcu); /** * sk_attach_filter - attach a socket filter @@ -649,7 +642,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) rcu_assign_pointer(sk->sk_filter, fp); if (old_fp) - sk_filter_delayed_uncharge(sk, old_fp); + sk_filter_uncharge(sk, old_fp); return 0; } EXPORT_SYMBOL_GPL(sk_attach_filter); @@ -663,7 +656,7 @@ int sk_detach_filter(struct sock *sk) sock_owned_by_user(sk)); if (filter) { rcu_assign_pointer(sk->sk_filter, NULL); - sk_filter_delayed_uncharge(sk, filter); + sk_filter_uncharge(sk, filter); ret = 0; } return ret; diff --git a/net/core/sock.c b/net/core/sock.c index fb6080111461..e5af8d5d5b50 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1009,6 +1009,36 @@ static void sock_copy(struct sock *nsk, const struct sock *osk) #endif } +/* + * caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes + * un-modified. Special care is taken when initializing object to zero. + */ +static inline void sk_prot_clear_nulls(struct sock *sk, int size) +{ + if (offsetof(struct sock, sk_node.next) != 0) + memset(sk, 0, offsetof(struct sock, sk_node.next)); + memset(&sk->sk_node.pprev, 0, + size - offsetof(struct sock, sk_node.pprev)); +} + +void sk_prot_clear_portaddr_nulls(struct sock *sk, int size) +{ + unsigned long nulls1, nulls2; + + nulls1 = offsetof(struct sock, __sk_common.skc_node.next); + nulls2 = offsetof(struct sock, __sk_common.skc_portaddr_node.next); + if (nulls1 > nulls2) + swap(nulls1, nulls2); + + if (nulls1 != 0) + memset((char *)sk, 0, nulls1); + memset((char *)sk + nulls1 + sizeof(void *), 0, + nulls2 - nulls1 - sizeof(void *)); + memset((char *)sk + nulls2 + sizeof(void *), 0, + size - nulls2 - sizeof(void *)); +} +EXPORT_SYMBOL(sk_prot_clear_portaddr_nulls); + static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, int family) { @@ -1021,19 +1051,12 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, if (!sk) return sk; if (priority & __GFP_ZERO) { - /* - * caches using SLAB_DESTROY_BY_RCU should let - * sk_node.next un-modified. Special care is taken - * when initializing object to zero. - */ - if (offsetof(struct sock, sk_node.next) != 0) - memset(sk, 0, offsetof(struct sock, sk_node.next)); - memset(&sk->sk_node.pprev, 0, - prot->obj_size - offsetof(struct sock, - sk_node.pprev)); + if (prot->clear_sk) + prot->clear_sk(sk, prot->obj_size); + else + sk_prot_clear_nulls(sk, prot->obj_size); } - } - else + } else sk = kmalloc(prot->obj_size, priority); if (sk != NULL) { diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 0ae6c22da85b..c19bb4ee405e 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -96,11 +96,13 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) struct phy_device *phydev; unsigned int type; - skb_push(skb, ETH_HLEN); + if (skb_headroom(skb) < ETH_HLEN) + return false; + __skb_push(skb, ETH_HLEN); type = classify(skb); - skb_pull(skb, ETH_HLEN); + __skb_pull(skb, ETH_HLEN); switch (type) { case PTP_CLASS_V1_IPV4: diff --git a/net/dccp/input.c b/net/dccp/input.c index 265985370fa1..e424a09e83f6 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -239,7 +239,8 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb) dccp_update_gsr(sk, seqno); if (dh->dccph_type != DCCP_PKT_SYNC && - (ackno != DCCP_PKT_WITHOUT_ACK_SEQ)) + ackno != DCCP_PKT_WITHOUT_ACK_SEQ && + after48(ackno, dp->dccps_gar)) dp->dccps_gar = ackno; } else { unsigned long now = jiffies; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index a76b78de679f..6f97268ed85f 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1556,6 +1556,8 @@ static int __dn_getsockopt(struct socket *sock, int level,int optname, char __us if (r_len > sizeof(struct linkinfo_dn)) r_len = sizeof(struct linkinfo_dn); + memset(&link, 0, sizeof(link)); + switch(sock->state) { case SS_CONNECTING: link.idn_linkstate = LL_CONNECTING; diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index f8c1ae4b41f0..15dcc1a586b4 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -31,6 +31,7 @@ #include <linux/skbuff.h> #include <linux/udp.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <net/sock.h> #include <net/inet_common.h> #include <linux/stat.h> @@ -276,12 +277,12 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, #endif #ifdef CONFIG_ECONET_AUNUDP struct msghdr udpmsg; - struct iovec iov[msg->msg_iovlen+1]; + struct iovec iov[2]; struct aunhdr ah; struct sockaddr_in udpdest; __kernel_size_t size; - int i; mm_segment_t oldfs; + char *userbuf; #endif /* @@ -297,23 +298,14 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, mutex_lock(&econet_mutex); - if (saddr == NULL) { - struct econet_sock *eo = ec_sk(sk); - - addr.station = eo->station; - addr.net = eo->net; - port = eo->port; - cb = eo->cb; - } else { - if (msg->msg_namelen < sizeof(struct sockaddr_ec)) { - mutex_unlock(&econet_mutex); - return -EINVAL; - } - addr.station = saddr->addr.station; - addr.net = saddr->addr.net; - port = saddr->port; - cb = saddr->cb; - } + if (saddr == NULL || msg->msg_namelen < sizeof(struct sockaddr_ec)) { + mutex_unlock(&econet_mutex); + return -EINVAL; + } + addr.station = saddr->addr.station; + addr.net = saddr->addr.net; + port = saddr->port; + cb = saddr->cb; /* Look for a device with the right network number. */ dev = net2dev_map[addr.net]; @@ -328,17 +320,17 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, } } - if (len + 15 > dev->mtu) { - mutex_unlock(&econet_mutex); - return -EMSGSIZE; - } - if (dev->type == ARPHRD_ECONET) { /* Real hardware Econet. We're not worthy etc. */ #ifdef CONFIG_ECONET_NATIVE unsigned short proto = 0; int res; + if (len + 15 > dev->mtu) { + mutex_unlock(&econet_mutex); + return -EMSGSIZE; + } + dev_hold(dev); skb = sock_alloc_send_skb(sk, len+LL_ALLOCATED_SPACE(dev), @@ -351,7 +343,6 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, eb = (struct ec_cb *)&skb->cb; - /* BUG: saddr may be NULL */ eb->cookie = saddr->cookie; eb->sec = *saddr; eb->sent = ec_tx_done; @@ -415,6 +406,11 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, return -ENETDOWN; /* No socket - can't send */ } + if (len > 32768) { + err = -E2BIG; + goto error; + } + /* Make up a UDP datagram and hand it off to some higher intellect. */ memset(&udpdest, 0, sizeof(udpdest)); @@ -446,36 +442,26 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, /* tack our header on the front of the iovec */ size = sizeof(struct aunhdr); - /* - * XXX: that is b0rken. We can't mix userland and kernel pointers - * in iovec, since on a lot of platforms copy_from_user() will - * *not* work with the kernel and userland ones at the same time, - * regardless of what we do with set_fs(). And we are talking about - * econet-over-ethernet here, so "it's only ARM anyway" doesn't - * apply. Any suggestions on fixing that code? -- AV - */ iov[0].iov_base = (void *)&ah; iov[0].iov_len = size; - for (i = 0; i < msg->msg_iovlen; i++) { - void __user *base = msg->msg_iov[i].iov_base; - size_t iov_len = msg->msg_iov[i].iov_len; - /* Check it now since we switch to KERNEL_DS later. */ - if (!access_ok(VERIFY_READ, base, iov_len)) { - mutex_unlock(&econet_mutex); - return -EFAULT; - } - iov[i+1].iov_base = base; - iov[i+1].iov_len = iov_len; - size += iov_len; + + userbuf = vmalloc(len); + if (userbuf == NULL) { + err = -ENOMEM; + goto error; } + iov[1].iov_base = userbuf; + iov[1].iov_len = len; + err = memcpy_fromiovec(userbuf, msg->msg_iov, len); + if (err) + goto error_free_buf; + /* Get a skbuff (no data, just holds our cb information) */ if ((skb = sock_alloc_send_skb(sk, 0, msg->msg_flags & MSG_DONTWAIT, - &err)) == NULL) { - mutex_unlock(&econet_mutex); - return err; - } + &err)) == NULL) + goto error_free_buf; eb = (struct ec_cb *)&skb->cb; @@ -491,7 +477,7 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, udpmsg.msg_name = (void *)&udpdest; udpmsg.msg_namelen = sizeof(udpdest); udpmsg.msg_iov = &iov[0]; - udpmsg.msg_iovlen = msg->msg_iovlen + 1; + udpmsg.msg_iovlen = 2; udpmsg.msg_control = NULL; udpmsg.msg_controllen = 0; udpmsg.msg_flags=0; @@ -499,9 +485,13 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, oldfs = get_fs(); set_fs(KERNEL_DS); /* More privs :-) */ err = sock_sendmsg(udpsock, &udpmsg, size); set_fs(oldfs); + +error_free_buf: + vfree(userbuf); #else err = -EPROTOTYPE; #endif + error: mutex_unlock(&econet_mutex); return err; @@ -671,6 +661,11 @@ static int ec_dev_ioctl(struct socket *sock, unsigned int cmd, void __user *arg) err = 0; switch (cmd) { case SIOCSIFADDR: + if (!capable(CAP_NET_ADMIN)) { + err = -EPERM; + break; + } + edev = dev->ec_ptr; if (edev == NULL) { /* Magic up a new one. */ @@ -856,9 +851,13 @@ static void aun_incoming(struct sk_buff *skb, struct aunhdr *ah, size_t len) { struct iphdr *ip = ip_hdr(skb); unsigned char stn = ntohl(ip->saddr) & 0xff; + struct dst_entry *dst = skb_dst(skb); + struct ec_device *edev = NULL; struct sock *sk = NULL; struct sk_buff *newskb; - struct ec_device *edev = skb->dev->ec_ptr; + + if (dst) + edev = dst->dev->ec_ptr; if (! edev) goto bad; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index eb6f69a8f27a..c19c1f739fba 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -163,13 +163,19 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) .daddr = addr } }, - .flags = FLOWI_FLAG_MATCH_ANY_IIF }; struct fib_result res = { 0 }; struct net_device *dev = NULL; + struct fib_table *local_table; + +#ifdef CONFIG_IP_MULTIPLE_TABLES + res.r = NULL; +#endif rcu_read_lock(); - if (fib_lookup(net, &fl, &res)) { + local_table = fib_get_table(net, RT_TABLE_LOCAL); + if (!local_table || + fib_table_lookup(local_table, &fl, &res, FIB_LOOKUP_NOREF)) { rcu_read_unlock(); return NULL; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 1b344f30b463..3c0369a3a663 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -133,8 +133,7 @@ int __inet_inherit_port(struct sock *sk, struct sock *child) } } } - sk_add_bind_node(child, &tb->owners); - inet_csk(child)->icsk_bind_hash = tb; + inet_bind_hash(child, tb, port); spin_unlock(&head->lock); return 0; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 1b48eb1ed453..b14ec7d03b6e 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -253,6 +253,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPMinTTLDrop", LINUX_MIB_TCPMINTTLDROP), SNMP_MIB_ITEM("TCPDeferAcceptDrop", LINUX_MIB_TCPDEFERACCEPTDROP), SNMP_MIB_ITEM("IPReversePathFilter", LINUX_MIB_IPRPFILTER), + SNMP_MIB_ITEM("TCPTimeWaitOverflow", LINUX_MIB_TCPTIMEWAITOVERFLOW), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 987bf9adb318..df948b0f1ac9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2585,9 +2585,10 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, goto out; /* RACE: Check return value of inet_select_addr instead. */ - if (rcu_dereference(dev_out->ip_ptr) == NULL) - goto out; /* Wrong error code */ - + if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) { + err = -ENETUNREACH; + goto out; + } if (ipv4_is_local_multicast(oldflp->fl4_dst) || ipv4_is_lbcast(oldflp->fl4_dst)) { if (!fl.fl4_src) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index e91911d7aae2..1b4ec21497a4 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -26,6 +26,8 @@ static int zero; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; +static int tcp_adv_win_scale_min = -31; +static int tcp_adv_win_scale_max = 31; /* Update system visible IP port range */ static void set_local_port_range(int range[2]) @@ -426,7 +428,9 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_adv_win_scale, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &tcp_adv_win_scale_min, + .extra2 = &tcp_adv_win_scale_max, }, { .procname = "tcp_tw_reuse", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 081419969485..f15c36a706ec 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2246,7 +2246,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet * know which interface is going to be used */ - if (val < 64 || val > MAX_TCP_WINDOW) { + if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) { err = -EINVAL; break; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 69ccbc1dde9c..d978bb2f748b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2030,7 +2030,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur) get_req: req = icsk->icsk_accept_queue.listen_opt->syn_table[st->sbucket]; } - sk = sk_next(st->syn_wait_sk); + sk = sk_nulls_next(st->syn_wait_sk); st->state = TCP_SEQ_STATE_LISTENING; read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); } else { @@ -2039,11 +2039,13 @@ get_req: if (reqsk_queue_len(&icsk->icsk_accept_queue)) goto start_req; read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); - sk = sk_next(sk); + sk = sk_nulls_next(sk); } get_sk: sk_nulls_for_each_from(sk, node) { - if (sk->sk_family == st->family && net_eq(sock_net(sk), net)) { + if (!net_eq(sock_net(sk), net)) + continue; + if (sk->sk_family == st->family) { cur = sk; goto out; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 43cf901d7659..a66735f75963 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -347,7 +347,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) * socket up. We've got bigger problems than * non-graceful socket closings. */ - LIMIT_NETDEBUG(KERN_INFO "TCP: time wait bucket table overflow\n"); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEWAITOVERFLOW); } tcp_update_metrics(sk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 05b1ecf36763..61c2463e2753 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -231,11 +231,10 @@ void tcp_select_initial_window(int __space, __u32 mss, /* when initializing use the value from init_rcv_wnd * rather than the default from above */ - if (init_rcv_wnd && - (*rcv_wnd > init_rcv_wnd * mss)) - *rcv_wnd = init_rcv_wnd * mss; - else if (*rcv_wnd > init_cwnd * mss) - *rcv_wnd = init_cwnd * mss; + if (init_rcv_wnd) + *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); + else + *rcv_wnd = min(*rcv_wnd, init_cwnd * mss); } /* Set the clamp no higher than max representable value */ @@ -386,27 +385,30 @@ struct tcp_out_options { */ static u8 tcp_cookie_size_check(u8 desired) { - if (desired > 0) { + int cookie_size; + + if (desired > 0) /* previously specified */ return desired; - } - if (sysctl_tcp_cookie_size <= 0) { + + cookie_size = ACCESS_ONCE(sysctl_tcp_cookie_size); + if (cookie_size <= 0) /* no default specified */ return 0; - } - if (sysctl_tcp_cookie_size <= TCP_COOKIE_MIN) { + + if (cookie_size <= TCP_COOKIE_MIN) /* value too small, specify minimum */ return TCP_COOKIE_MIN; - } - if (sysctl_tcp_cookie_size >= TCP_COOKIE_MAX) { + + if (cookie_size >= TCP_COOKIE_MAX) /* value too large, specify maximum */ return TCP_COOKIE_MAX; - } - if (0x1 & sysctl_tcp_cookie_size) { + + if (cookie_size & 1) /* 8-bit multiple, illegal, fix it */ - return (u8)(sysctl_tcp_cookie_size + 0x1); - } - return (u8)sysctl_tcp_cookie_size; + cookie_size++; + + return (u8)cookie_size; } /* Write previously computed TCP options to the packet. @@ -1513,6 +1515,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); u32 send_win, cong_win, limit, in_flight; + int win_divisor; if (TCP_SKB_CB(skb)->flags & TCPHDR_FIN) goto send_now; @@ -1544,13 +1547,14 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len)) goto send_now; - if (sysctl_tcp_tso_win_divisor) { + win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor); + if (win_divisor) { u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache); /* If at least some fraction of a window is available, * just use it. */ - chunk /= sysctl_tcp_tso_win_divisor; + chunk /= win_divisor; if (limit >= chunk) goto send_now; } else { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5e0a3a582a59..2d3ded4d0786 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1899,6 +1899,7 @@ struct proto udp_prot = { .compat_setsockopt = compat_udp_setsockopt, .compat_getsockopt = compat_udp_getsockopt, #endif + .clear_sk = sk_prot_clear_portaddr_nulls, }; EXPORT_SYMBOL(udp_prot); diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index ab76aa928fa9..aee9963f7f5a 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -57,6 +57,7 @@ struct proto udplite_prot = { .compat_setsockopt = compat_udp_setsockopt, .compat_getsockopt = compat_udp_getsockopt, #endif + .clear_sk = sk_prot_clear_portaddr_nulls, }; EXPORT_SYMBOL(udplite_prot); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 23cc8e1ce8d4..848b35591042 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2669,7 +2669,9 @@ static int addrconf_ifdown(struct net_device *dev, int how) ASSERT_RTNL(); - rt6_ifdown(net, dev); + /* Flush routes if device is being removed or it is not loopback */ + if (how || !(dev->flags & IFF_LOOPBACK)) + rt6_ifdown(net, dev); neigh_ifdown(&nd_tbl, dev); idev = __in6_dev_get(dev); @@ -4021,11 +4023,11 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev) kfree_skb(skb); goto errout; } - rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFINFO, NULL, GFP_ATOMIC); return; errout: if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_IFINFO, err); } static inline size_t inet6_prefix_nlmsg_size(void) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 99157b4cd56e..94b5bf132b2e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -56,7 +56,7 @@ #include <net/checksum.h> #include <linux/mroute6.h> -static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); +int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); int __ip6_local_out(struct sk_buff *skb) { @@ -145,14 +145,6 @@ static int ip6_finish_output2(struct sk_buff *skb) return -EINVAL; } -static inline int ip6_skb_dst_mtu(struct sk_buff *skb) -{ - struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; - - return (np && np->pmtudisc == IPV6_PMTUDISC_PROBE) ? - skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); -} - static int ip6_finish_output(struct sk_buff *skb) { if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || @@ -601,7 +593,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) return offset; } -static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) +int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = (struct rt6_info*)skb_dst(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 2a59610c2a58..70e891a20fb9 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1175,6 +1175,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) sizeof (struct ipv6hdr); dev->mtu = rt->rt6i_dev->mtu - sizeof (struct ipv6hdr); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + dev->mtu-=8; if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; @@ -1363,12 +1365,17 @@ static const struct net_device_ops ip6_tnl_netdev_ops = { static void ip6_tnl_dev_setup(struct net_device *dev) { + struct ip6_tnl *t; + dev->netdev_ops = &ip6_tnl_netdev_ops; dev->destructor = ip6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->hard_header_len = LL_MAX_HEADER + sizeof (struct ipv6hdr); dev->mtu = ETH_DATA_LEN - sizeof (struct ipv6hdr); + t = netdev_priv(dev); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) + dev->mtu-=8; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); dev->features |= NETIF_F_NETNS_LOCAL; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 96455ffb76fb..7659d6f16e6b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1565,11 +1565,16 @@ static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr, { struct rt6_info *rt, *nrt; int allfrag = 0; - +again: rt = rt6_lookup(net, daddr, saddr, ifindex, 0); if (rt == NULL) return; + if (rt6_check_expired(rt)) { + ip6_del_rt(rt); + goto again; + } + if (pmtu >= dst_mtu(&rt->dst)) goto out; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index d6bfaec3bbbf..8c4d00c7cd2b 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -606,8 +606,9 @@ static int ipip6_rcv(struct sk_buff *skb) return 0; } - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + /* no tunnel matched, let upstream know, ipsec may handle it */ rcu_read_unlock(); + return 1; out: kfree_skb(skb); return 0; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 91def93bec85..cd6cb7c3e563 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1477,6 +1477,7 @@ struct proto udpv6_prot = { .compat_setsockopt = compat_udpv6_setsockopt, .compat_getsockopt = compat_udpv6_getsockopt, #endif + .clear_sk = sk_prot_clear_portaddr_nulls, }; static struct inet_protosw udpv6_protosw = { diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 5f48fadc27f7..986c4de5292e 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -55,6 +55,7 @@ struct proto udplitev6_prot = { .compat_setsockopt = compat_udpv6_setsockopt, .compat_getsockopt = compat_udpv6_getsockopt, #endif + .clear_sk = sk_prot_clear_portaddr_nulls, }; static struct inet_protosw udplite6_protosw = { diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 6434bd5ce088..8e688b3de9ab 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -17,6 +17,7 @@ #include <linux/netfilter_ipv6.h> #include <net/dst.h> #include <net/ipv6.h> +#include <net/ip6_route.h> #include <net/xfrm.h> int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, @@ -88,8 +89,21 @@ static int xfrm6_output_finish(struct sk_buff *skb) return xfrm_output(skb); } +static int __xfrm6_output(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct xfrm_state *x = dst->xfrm; + + if ((x && x->props.mode == XFRM_MODE_TUNNEL) && + ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || + dst_allfrag(skb_dst(skb)))) { + return ip6_fragment(skb, xfrm6_output_finish); + } + return xfrm6_output_finish(skb); +} + int xfrm6_output(struct sk_buff *skb) { return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, - skb_dst(skb)->dev, xfrm6_output_finish); + skb_dst(skb)->dev, __xfrm6_output); } diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index a6de3059746d..c9890e25cd4c 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -2280,6 +2280,16 @@ static int irda_getsockopt(struct socket *sock, int level, int optname, switch (optname) { case IRLMP_ENUMDEVICES: + + /* Offset to first device entry */ + offset = sizeof(struct irda_device_list) - + sizeof(struct irda_device_info); + + if (len < offset) { + err = -EINVAL; + goto out; + } + /* Ask lmp for the current discovery log */ discoveries = irlmp_get_discoveries(&list.len, self->mask.word, self->nslots); @@ -2290,15 +2300,9 @@ static int irda_getsockopt(struct socket *sock, int level, int optname, } /* Write total list length back to client */ - if (copy_to_user(optval, &list, - sizeof(struct irda_device_list) - - sizeof(struct irda_device_info))) + if (copy_to_user(optval, &list, offset)) err = -EFAULT; - /* Offset to first device entry */ - offset = sizeof(struct irda_device_list) - - sizeof(struct irda_device_info); - /* Copy the list itself - watch for overflow */ if (list.len > 2048) { err = -EINVAL; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 0bf6a59545ab..522e219f3558 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -674,4 +674,8 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP over IP"); MODULE_VERSION("1.0"); -MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, SOCK_DGRAM, IPPROTO_L2TP); + +/* Use the value of SOCK_DGRAM (2) directory, because __stringify does't like + * enums + */ +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 2, IPPROTO_L2TP); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 582612998211..e35dbe55f520 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -317,8 +317,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) goto out; rc = -ENODEV; rtnl_lock(); + rcu_read_lock(); if (sk->sk_bound_dev_if) { - llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); + llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); if (llc->dev) { if (!addr->sllc_arphrd) addr->sllc_arphrd = llc->dev->type; @@ -329,13 +330,13 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) !llc_mac_match(addr->sllc_mac, llc->dev->dev_addr)) { rc = -EINVAL; - dev_put(llc->dev); llc->dev = NULL; } } } else llc->dev = dev_getbyhwaddr(&init_net, addr->sllc_arphrd, addr->sllc_mac); + rcu_read_unlock(); rtnl_unlock(); if (!llc->dev) goto out; diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 4d6f8653ec88..8e8ea9cb7093 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -92,7 +92,7 @@ config MAC80211_MESH config MAC80211_LEDS bool "Enable LED triggers" depends on MAC80211 - select NEW_LEDS + depends on LEDS_CLASS select LEDS_TRIGGERS ---help--- This option enables a few LED triggers for different diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 239c4836a946..077a93dd1671 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -780,6 +780,9 @@ void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, mutex_lock(&sdata->u.ibss.mtx); + if (!sdata->u.ibss.ssid_len) + goto mgmt_out; /* not ready to merge yet */ + switch (fc & IEEE80211_FCTL_STYPE) { case IEEE80211_STYPE_PROBE_REQ: ieee80211_rx_mgmt_probe_req(sdata, mgmt, skb->len); @@ -797,6 +800,7 @@ void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, break; } + mgmt_out: mutex_unlock(&sdata->u.ibss.mtx); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 902b03ee8f60..b01e467b76c6 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1788,9 +1788,11 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) fwd_skb = skb_copy(skb, GFP_ATOMIC); - if (!fwd_skb && net_ratelimit()) + if (!fwd_skb && net_ratelimit()) { printk(KERN_DEBUG "%s: failed to clone mesh frame\n", sdata->name); + goto out; + } fwd_hdr = (struct ieee80211_hdr *) fwd_skb->data; memcpy(fwd_hdr->addr2, sdata->vif.addr, ETH_ALEN); @@ -1828,6 +1830,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) } } + out: if (is_multicast_ether_addr(hdr->addr1) || sdata->dev->flags & IFF_PROMISC) return RX_CONTINUE; @@ -2247,6 +2250,10 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx) break; case cpu_to_le16(IEEE80211_STYPE_DEAUTH): case cpu_to_le16(IEEE80211_STYPE_DISASSOC): + if (is_multicast_ether_addr(mgmt->da) && + !is_broadcast_ether_addr(mgmt->da)) + return RX_DROP_MONITOR; + /* process only for station */ if (sdata->vif.type != NL80211_IFTYPE_STATION) return RX_DROP_MONITOR; @@ -2741,6 +2748,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, if (ieee80211_prepare_and_rx_handle(&rx, skb, true)) return; + goto out; } } @@ -2780,6 +2788,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, return; } + out: dev_kfree_skb(skb); } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 96c594309506..7a637b80a62e 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1587,7 +1587,12 @@ static void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, list) { if (!ieee80211_sdata_running(tmp_sdata)) continue; - if (tmp_sdata->vif.type != NL80211_IFTYPE_AP) + if (tmp_sdata->vif.type == + NL80211_IFTYPE_MONITOR || + tmp_sdata->vif.type == + NL80211_IFTYPE_AP_VLAN || + tmp_sdata->vif.type == + NL80211_IFTYPE_WDS) continue; if (compare_ether_addr(tmp_sdata->vif.addr, hdr->addr2) == 0) { @@ -1732,15 +1737,13 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, int nh_pos, h_pos; struct sta_info *sta = NULL; u32 sta_flags = 0; + struct sk_buff *tmp_skb; if (unlikely(skb->len < ETH_HLEN)) { ret = NETDEV_TX_OK; goto fail; } - nh_pos = skb_network_header(skb) - skb->data; - h_pos = skb_transport_header(skb) - skb->data; - /* convert Ethernet header to proper 802.11 header (based on * operation mode) */ ethertype = (skb->data[12] << 8) | skb->data[13]; @@ -1913,6 +1916,20 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, goto fail; } + /* + * If the skb is shared we need to obtain our own copy. + */ + if (skb_shared(skb)) { + tmp_skb = skb; + skb = skb_copy(skb, GFP_ATOMIC); + kfree_skb(tmp_skb); + + if (!skb) { + ret = NETDEV_TX_OK; + goto fail; + } + } + hdr.frame_control = fc; hdr.duration_id = 0; hdr.seq_ctrl = 0; @@ -1931,6 +1948,9 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, encaps_len = 0; } + nh_pos = skb_network_header(skb) - skb->data; + h_pos = skb_transport_header(skb) - skb->data; + skb_pull(skb, skip_header_bytes); nh_pos -= skip_header_bytes; h_pos -= skip_header_bytes; diff --git a/net/mac80211/work.c b/net/mac80211/work.c index ae344d1ba056..146097cb43a7 100644 --- a/net/mac80211/work.c +++ b/net/mac80211/work.c @@ -1051,11 +1051,13 @@ void ieee80211_work_purge(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; struct ieee80211_work *wk; + bool cleanup = false; mutex_lock(&local->mtx); list_for_each_entry(wk, &local->work_list, list) { if (wk->sdata != sdata) continue; + cleanup = true; wk->type = IEEE80211_WORK_ABORT; wk->started = true; wk->timeout = jiffies; @@ -1063,7 +1065,8 @@ void ieee80211_work_purge(struct ieee80211_sub_if_data *sdata) mutex_unlock(&local->mtx); /* run cleanups etc. */ - ieee80211_work_work(&local->work_work); + if (cleanup) + ieee80211_work_work(&local->work_work); mutex_lock(&local->mtx); list_for_each_entry(wk, &local->work_list, list) { diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 3cf478d012dd..7150705f1d0b 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -270,7 +270,6 @@ static unsigned int sfq_drop(struct Qdisc *sch) /* It is difficult to believe, but ALL THE SLOTS HAVE LENGTH 1. */ d = q->next[q->tail]; q->next[q->tail] = q->next[d]; - q->allot[q->next[d]] += q->quantum; skb = q->qs[d].prev; len = qdisc_pkt_len(skb); __skb_unlink(skb, &q->qs[d]); @@ -321,14 +320,13 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) sfq_inc(q, x); if (q->qs[x].qlen == 1) { /* The flow is new */ if (q->tail == SFQ_DEPTH) { /* It is the first flow */ - q->tail = x; q->next[x] = x; - q->allot[x] = q->quantum; } else { q->next[x] = q->next[q->tail]; q->next[q->tail] = x; - q->tail = x; } + q->tail = x; + q->allot[x] = q->quantum; } if (++sch->q.qlen <= q->limit) { sch->bstats.bytes += qdisc_pkt_len(skb); @@ -359,13 +357,13 @@ sfq_dequeue(struct Qdisc *sch) { struct sfq_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; - sfq_index a, old_a; + sfq_index a, next_a; /* No active slots */ if (q->tail == SFQ_DEPTH) return NULL; - a = old_a = q->next[q->tail]; + a = q->next[q->tail]; /* Grab packet */ skb = __skb_dequeue(&q->qs[a]); @@ -376,17 +374,15 @@ sfq_dequeue(struct Qdisc *sch) /* Is the slot empty? */ if (q->qs[a].qlen == 0) { q->ht[q->hash[a]] = SFQ_DEPTH; - a = q->next[a]; - if (a == old_a) { + next_a = q->next[a]; + if (a == next_a) { q->tail = SFQ_DEPTH; return skb; } - q->next[q->tail] = a; - q->allot[a] += q->quantum; + q->next[q->tail] = next_a; } else if ((q->allot[a] -= qdisc_pkt_len(skb)) <= 0) { - q->tail = a; - a = q->next[a]; q->allot[a] += q->quantum; + q->tail = a; } return skb; } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6bd554323a34..fff0926b1111 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2932,6 +2932,7 @@ static int sctp_setsockopt_peer_primary_addr(struct sock *sk, char __user *optva struct sctp_association *asoc = NULL; struct sctp_setpeerprim prim; struct sctp_chunk *chunk; + struct sctp_af *af; int err; sp = sctp_sk(sk); @@ -2959,6 +2960,13 @@ static int sctp_setsockopt_peer_primary_addr(struct sock *sk, char __user *optva if (!sctp_state(asoc, ESTABLISHED)) return -ENOTCONN; + af = sctp_get_af_specific(prim.sspp_addr.ss_family); + if (!af) + return -EINVAL; + + if (!af->addr_valid((union sctp_addr *)&prim.sspp_addr, sp, NULL)) + return -EADDRNOTAVAIL; + if (!sctp_assoc_lookup_laddr(asoc, (union sctp_addr *)&prim.sspp_addr)) return -EADDRNOTAVAIL; @@ -5045,7 +5053,7 @@ static int sctp_getsockopt_partial_delivery_point(struct sock *sk, int len, if (copy_to_user(optval, &val, len)) return -EFAULT; - return -ENOTSUPP; + return 0; } /* diff --git a/net/socket.c b/net/socket.c index 3ca2fd9e3720..088fb3fd45e0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -732,6 +732,21 @@ static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, return ret; } +/** + * kernel_recvmsg - Receive a message from a socket (kernel space) + * @sock: The socket to receive the message from + * @msg: Received message + * @vec: Input s/g array for message data + * @num: Size of input s/g array + * @size: Number of bytes to read + * @flags: Message flags (MSG_DONTWAIT, etc...) + * + * On return the msg structure contains the scatter/gather array passed in the + * vec argument. The array is modified so that it consists of the unfilled + * portion of the original array. + * + * The returned value is the total number of bytes received, or an error. + */ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size, int flags) { diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index ea2ff78dcf7b..3f2c5559ca1a 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -212,6 +212,7 @@ int svc_create_xprt(struct svc_serv *serv, const char *xprt_name, spin_lock(&svc_xprt_class_lock); list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) { struct svc_xprt *newxprt; + unsigned short newport; if (strcmp(xprt_name, xcl->xcl_name)) continue; @@ -230,8 +231,9 @@ int svc_create_xprt(struct svc_serv *serv, const char *xprt_name, spin_lock_bh(&serv->sv_lock); list_add(&newxprt->xpt_list, &serv->sv_permsocks); spin_unlock_bh(&serv->sv_lock); + newport = svc_xprt_local_port(newxprt); clear_bit(XPT_BUSY, &newxprt->xpt_flags); - return svc_xprt_local_port(newxprt); + return newport; } err: spin_unlock(&svc_xprt_class_lock); @@ -425,8 +427,13 @@ void svc_xprt_received(struct svc_xprt *xprt) { BUG_ON(!test_bit(XPT_BUSY, &xprt->xpt_flags)); xprt->xpt_pool = NULL; + /* As soon as we clear busy, the xprt could be closed and + * 'put', so we need a reference to call svc_xprt_enqueue with: + */ + svc_xprt_get(xprt); clear_bit(XPT_BUSY, &xprt->xpt_flags); svc_xprt_enqueue(xprt); + svc_xprt_put(xprt); } EXPORT_SYMBOL_GPL(svc_xprt_received); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3c95304a0817..2268e6798124 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1343,9 +1343,25 @@ static void unix_destruct_scm(struct sk_buff *skb) sock_wfree(skb); } +#define MAX_RECURSION_LEVEL 4 + static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) { int i; + unsigned char max_level = 0; + int unix_sock_count = 0; + + for (i = scm->fp->count - 1; i >= 0; i--) { + struct sock *sk = unix_get_socket(scm->fp->fp[i]); + + if (sk) { + unix_sock_count++; + max_level = max(max_level, + unix_sk(sk)->recursion_level); + } + } + if (unlikely(max_level > MAX_RECURSION_LEVEL)) + return -ETOOMANYREFS; /* * Need to duplicate file references for the sake of garbage @@ -1356,9 +1372,11 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) if (!UNIXCB(skb).fp) return -ENOMEM; - for (i = scm->fp->count-1; i >= 0; i--) - unix_inflight(scm->fp->fp[i]); - return 0; + if (unix_sock_count) { + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->fp[i]); + } + return max_level; } static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) @@ -1393,6 +1411,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, struct sk_buff *skb; long timeo; struct scm_cookie tmp_scm; + int max_level; if (NULL == siocb->scm) siocb->scm = &tmp_scm; @@ -1431,8 +1450,9 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, goto out; err = unix_scm_to_skb(siocb->scm, skb, true); - if (err) + if (err < 0) goto out_free; + max_level = err + 1; unix_get_secdata(siocb->scm, skb); skb_reset_transport_header(skb); @@ -1514,6 +1534,8 @@ restart: if (sock_flag(other, SOCK_RCVTSTAMP)) __net_timestamp(skb); skb_queue_tail(&other->sk_receive_queue, skb); + if (max_level > unix_sk(other)->recursion_level) + unix_sk(other)->recursion_level = max_level; unix_state_unlock(other); other->sk_data_ready(other, len); sock_put(other); @@ -1544,6 +1566,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, int sent = 0; struct scm_cookie tmp_scm; bool fds_sent = false; + int max_level; if (NULL == siocb->scm) siocb->scm = &tmp_scm; @@ -1607,10 +1630,11 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, /* Only send the fds in the first buffer */ err = unix_scm_to_skb(siocb->scm, skb, !fds_sent); - if (err) { + if (err < 0) { kfree_skb(skb); goto out_err; } + max_level = err + 1; fds_sent = true; err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size); @@ -1626,6 +1650,8 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, goto pipe_err_free; skb_queue_tail(&other->sk_receive_queue, skb); + if (max_level > unix_sk(other)->recursion_level) + unix_sk(other)->recursion_level = max_level; unix_state_unlock(other); other->sk_data_ready(other, size); sent += size; @@ -1845,6 +1871,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, unix_state_lock(sk); skb = skb_dequeue(&sk->sk_receive_queue); if (skb == NULL) { + unix_sk(sk)->recursion_level = 0; if (copied >= target) goto unlock; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index c8df6fda0b1f..f89f83bf828e 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -96,7 +96,7 @@ static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); unsigned int unix_tot_inflight; -static struct sock *unix_get_socket(struct file *filp) +struct sock *unix_get_socket(struct file *filp) { struct sock *u_sock = NULL; struct inode *inode = filp->f_path.dentry->d_inode; @@ -259,9 +259,16 @@ static void inc_inflight_move_tail(struct unix_sock *u) } static bool gc_in_progress = false; +#define UNIX_INFLIGHT_TRIGGER_GC 16000 void wait_for_unix_gc(void) { + /* + * If number of inflight sockets is insane, + * force a garbage collect right now. + */ + if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress) + unix_gc(); wait_event(unix_gc_wait, gc_in_progress == false); } diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index 73e7b954ad28..b25c6463c3e9 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -394,6 +394,7 @@ void __exit x25_link_free(void) list_for_each_safe(entry, tmp, &x25_neigh_list) { nb = list_entry(entry, struct x25_neigh, node); __x25_remove_neigh(nb); + dev_put(nb->dev); } write_unlock_bh(&x25_neigh_list_lock); } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index eb96ce52f178..220ebc05c7af 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1268,7 +1268,7 @@ struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x, return xc; error: - kfree(xc); + xfrm_state_put(xc); return NULL; } EXPORT_SYMBOL(xfrm_state_migrate); |