diff options
Diffstat (limited to 'net')
68 files changed, 582 insertions, 342 deletions
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 26eaebf..bb86d29 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1392,6 +1392,7 @@ static int ax25_getname(struct socket *sock, struct sockaddr *uaddr, ax25_cb *ax25; int err = 0; + memset(fsa, 0, sizeof(fsa)); lock_sock(sk); ax25 = ax25_sk(sk); @@ -1403,7 +1404,6 @@ static int ax25_getname(struct socket *sock, struct sockaddr *uaddr, fsa->fsa_ax25.sax25_family = AF_AX25; fsa->fsa_ax25.sax25_call = ax25->dest_addr; - fsa->fsa_ax25.sax25_ndigis = 0; if (ax25->digipeat != NULL) { ndigi = ax25->digipeat->ndigi; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index bfef5ba..84093b0 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1175,6 +1175,12 @@ static inline void hci_remote_features_evt(struct hci_dev *hdev, struct sk_buff hci_send_cmd(hdev, HCI_OP_READ_REMOTE_EXT_FEATURES, sizeof(cp), &cp); + } else if (!ev->status && conn->out && + conn->sec_level == BT_SECURITY_HIGH) { + struct hci_cp_auth_requested cp; + cp.handle = ev->handle; + hci_send_cmd(hdev, HCI_OP_AUTH_REQUESTED, + sizeof(cp), &cp); } else { conn->state = BT_CONNECTED; hci_proto_connect_cfm(conn, ev->status); diff --git a/net/bluetooth/hidp/Kconfig b/net/bluetooth/hidp/Kconfig index 98fdfa1..86a9154 100644 --- a/net/bluetooth/hidp/Kconfig +++ b/net/bluetooth/hidp/Kconfig @@ -1,6 +1,6 @@ config BT_HIDP tristate "HIDP protocol support" - depends on BT && BT_L2CAP && INPUT + depends on BT && BT_L2CAP && INPUT && HID_SUPPORT select HID help HIDP (Human Interface Device Protocol) is a transport layer diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index daa7a98..cd8f6ea 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -2421,11 +2421,11 @@ static inline int l2cap_get_conf_opt(void **ptr, int *type, int *olen, unsigned break; case 2: - *val = __le16_to_cpu(*((__le16 *) opt->val)); + *val = get_unaligned_le16(opt->val); break; case 4: - *val = __le32_to_cpu(*((__le32 *) opt->val)); + *val = get_unaligned_le32(opt->val); break; default: @@ -2452,11 +2452,11 @@ static void l2cap_add_conf_opt(void **ptr, u8 type, u8 len, unsigned long val) break; case 2: - *((__le16 *) opt->val) = cpu_to_le16(val); + put_unaligned_le16(val, opt->val); break; case 4: - *((__le32 *) opt->val) = cpu_to_le32(val); + put_unaligned_le32(val, opt->val); break; default: diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 39a5d87..fa642aa 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -79,7 +79,10 @@ static void rfcomm_make_uih(struct sk_buff *skb, u8 addr); static void rfcomm_process_connect(struct rfcomm_session *s); -static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bdaddr_t *dst, int *err); +static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, + bdaddr_t *dst, + u8 sec_level, + int *err); static struct rfcomm_session *rfcomm_session_get(bdaddr_t *src, bdaddr_t *dst); static void rfcomm_session_del(struct rfcomm_session *s); @@ -401,7 +404,7 @@ static int __rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, s = rfcomm_session_get(src, dst); if (!s) { - s = rfcomm_session_create(src, dst, &err); + s = rfcomm_session_create(src, dst, d->sec_level, &err); if (!s) return err; } @@ -679,7 +682,10 @@ static void rfcomm_session_close(struct rfcomm_session *s, int err) rfcomm_session_put(s); } -static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bdaddr_t *dst, int *err) +static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, + bdaddr_t *dst, + u8 sec_level, + int *err) { struct rfcomm_session *s = NULL; struct sockaddr_l2 addr; @@ -704,6 +710,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bdaddr_t *dst sk = sock->sk; lock_sock(sk); l2cap_pi(sk)->imtu = l2cap_mtu; + l2cap_pi(sk)->sec_level = sec_level; if (l2cap_ertm) l2cap_pi(sk)->mode = L2CAP_MODE_ERTM; release_sock(sk); diff --git a/net/caif/caif_config_util.c b/net/caif/caif_config_util.c index 76ae683..d522d8c 100644 --- a/net/caif/caif_config_util.c +++ b/net/caif/caif_config_util.c @@ -16,11 +16,18 @@ int connect_req_to_link_param(struct cfcnfg *cnfg, { struct dev_info *dev_info; enum cfcnfg_phy_preference pref; + int res; + memset(l, 0, sizeof(*l)); - l->priority = s->priority; + /* In caif protocol low value is high priority */ + l->priority = CAIF_PRIO_MAX - s->priority + 1; - if (s->link_name[0] != '\0') - l->phyid = cfcnfg_get_named(cnfg, s->link_name); + if (s->ifindex != 0){ + res = cfcnfg_get_id_from_ifi(cnfg, s->ifindex); + if (res < 0) + return res; + l->phyid = res; + } else { switch (s->link_selector) { case CAIF_LINK_HIGH_BANDW: diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index b99369a..a42a408 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -307,6 +307,8 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what, case NETDEV_UNREGISTER: caifd = caif_get(dev); + if (caifd == NULL) + break; netdev_info(dev, "unregister\n"); atomic_set(&caifd->state, what); caif_device_destroy(dev); diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 2eca2dd..1bf0cf5 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -716,8 +716,7 @@ static int setsockopt(struct socket *sock, { struct sock *sk = sock->sk; struct caifsock *cf_sk = container_of(sk, struct caifsock, sk); - int prio, linksel; - struct ifreq ifreq; + int linksel; if (cf_sk->sk.sk_socket->state != SS_UNCONNECTED) return -ENOPROTOOPT; @@ -735,33 +734,6 @@ static int setsockopt(struct socket *sock, release_sock(&cf_sk->sk); return 0; - case SO_PRIORITY: - if (lvl != SOL_SOCKET) - goto bad_sol; - if (ol < sizeof(int)) - return -EINVAL; - if (copy_from_user(&prio, ov, sizeof(int))) - return -EINVAL; - lock_sock(&(cf_sk->sk)); - cf_sk->conn_req.priority = prio; - release_sock(&cf_sk->sk); - return 0; - - case SO_BINDTODEVICE: - if (lvl != SOL_SOCKET) - goto bad_sol; - if (ol < sizeof(struct ifreq)) - return -EINVAL; - if (copy_from_user(&ifreq, ov, sizeof(ifreq))) - return -EFAULT; - lock_sock(&(cf_sk->sk)); - strncpy(cf_sk->conn_req.link_name, ifreq.ifr_name, - sizeof(cf_sk->conn_req.link_name)); - cf_sk->conn_req.link_name - [sizeof(cf_sk->conn_req.link_name)-1] = 0; - release_sock(&cf_sk->sk); - return 0; - case CAIFSO_REQ_PARAM: if (lvl != SOL_CAIF) goto bad_sol; @@ -880,6 +852,18 @@ static int caif_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTING; sk->sk_state = CAIF_CONNECTING; + /* Check priority value comming from socket */ + /* if priority value is out of range it will be ajusted */ + if (cf_sk->sk.sk_priority > CAIF_PRIO_MAX) + cf_sk->conn_req.priority = CAIF_PRIO_MAX; + else if (cf_sk->sk.sk_priority < CAIF_PRIO_MIN) + cf_sk->conn_req.priority = CAIF_PRIO_MIN; + else + cf_sk->conn_req.priority = cf_sk->sk.sk_priority; + + /*ifindex = id of the interface.*/ + cf_sk->conn_req.ifindex = cf_sk->sk.sk_bound_dev_if; + dbfs_atomic_inc(&cnt.num_connect_req); cf_sk->layer.receive = caif_sktrecv_cb; err = caif_connect_client(&cf_sk->conn_req, @@ -905,6 +889,7 @@ static int caif_connect(struct socket *sock, struct sockaddr *uaddr, cf_sk->maxframe = mtu - (headroom + tailroom); if (cf_sk->maxframe < 1) { pr_warn("CAIF Interface MTU too small (%d)\n", dev->mtu); + err = -ENODEV; goto out; } @@ -1142,7 +1127,7 @@ static int caif_create(struct net *net, struct socket *sock, int protocol, set_rx_flow_on(cf_sk); /* Set default options on configuration */ - cf_sk->conn_req.priority = CAIF_PRIO_NORMAL; + cf_sk->sk.sk_priority= CAIF_PRIO_NORMAL; cf_sk->conn_req.link_selector = CAIF_LINK_LOW_LATENCY; cf_sk->conn_req.protocol = protocol; /* Increase the number of sockets created. */ diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index 41adafd1..21ede14 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -173,18 +173,15 @@ static struct cfcnfg_phyinfo *cfcnfg_get_phyinfo(struct cfcnfg *cnfg, return NULL; } -int cfcnfg_get_named(struct cfcnfg *cnfg, char *name) + +int cfcnfg_get_id_from_ifi(struct cfcnfg *cnfg, int ifi) { int i; - - /* Try to match with specified name */ - for (i = 0; i < MAX_PHY_LAYERS; i++) { - if (cnfg->phy_layers[i].frm_layer != NULL - && strcmp(cnfg->phy_layers[i].phy_layer->name, - name) == 0) - return cnfg->phy_layers[i].frm_layer->id; - } - return 0; + for (i = 0; i < MAX_PHY_LAYERS; i++) + if (cnfg->phy_layers[i].frm_layer != NULL && + cnfg->phy_layers[i].ifindex == ifi) + return i; + return -ENODEV; } int cfcnfg_disconn_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer) diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index 08f267a..3cd8f97 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -361,11 +361,10 @@ void cfctrl_cancel_req(struct cflayer *layr, struct cflayer *adap_layer) struct cfctrl_request_info *p, *tmp; struct cfctrl *ctrl = container_obj(layr); spin_lock(&ctrl->info_list_lock); - pr_warn("enter\n"); list_for_each_entry_safe(p, tmp, &ctrl->list, list) { if (p->client_layer == adap_layer) { - pr_warn("cancel req :%d\n", p->sequence_no); + pr_debug("cancel req :%d\n", p->sequence_no); list_del(&p->list); kfree(p); } diff --git a/net/caif/cfdbgl.c b/net/caif/cfdbgl.c index 496fda9..11a2af4 100644 --- a/net/caif/cfdbgl.c +++ b/net/caif/cfdbgl.c @@ -12,6 +12,8 @@ #include <net/caif/cfsrvl.h> #include <net/caif/cfpkt.h> +#define container_obj(layr) ((struct cfsrvl *) layr) + static int cfdbgl_receive(struct cflayer *layr, struct cfpkt *pkt); static int cfdbgl_transmit(struct cflayer *layr, struct cfpkt *pkt); @@ -38,5 +40,17 @@ static int cfdbgl_receive(struct cflayer *layr, struct cfpkt *pkt) static int cfdbgl_transmit(struct cflayer *layr, struct cfpkt *pkt) { + struct cfsrvl *service = container_obj(layr); + struct caif_payload_info *info; + int ret; + + if (!cfsrvl_ready(service, &ret)) + return ret; + + /* Add info for MUX-layer to route the packet out */ + info = cfpkt_info(pkt); + info->channel_id = service->layer.id; + info->dev_info = &service->dev_info; + return layr->dn->transmit(layr->dn, pkt); } diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index bde8481..e2fb5fa 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -193,7 +193,7 @@ out: static int cfrfml_transmit_segment(struct cfrfml *rfml, struct cfpkt *pkt) { - caif_assert(cfpkt_getlen(pkt) >= rfml->fragment_size); + caif_assert(cfpkt_getlen(pkt) < rfml->fragment_size); /* Add info for MUX-layer to route the packet out. */ cfpkt_info(pkt)->channel_id = rfml->serv.layer.id; diff --git a/net/compat.c b/net/compat.c index 63d260e..3649d58 100644 --- a/net/compat.c +++ b/net/compat.c @@ -41,10 +41,12 @@ static inline int iov_from_user_compat_to_kern(struct iovec *kiov, compat_size_t len; if (get_user(len, &uiov32->iov_len) || - get_user(buf, &uiov32->iov_base)) { - tot_len = -EFAULT; - break; - } + get_user(buf, &uiov32->iov_base)) + return -EFAULT; + + if (len > INT_MAX - tot_len) + len = INT_MAX - tot_len; + tot_len += len; kiov->iov_base = compat_ptr(buf); kiov->iov_len = (__kernel_size_t) len; diff --git a/net/core/dev.c b/net/core/dev.c index 35dfb83..0dd54a6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2131,7 +2131,7 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, } else { struct sock *sk = skb->sk; queue_index = sk_tx_queue_get(sk); - if (queue_index < 0) { + if (queue_index < 0 || queue_index >= dev->real_num_tx_queues) { queue_index = 0; if (dev->real_num_tx_queues > 1) diff --git a/net/core/dst.c b/net/core/dst.c index 8abe628..b99c7c7 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -370,6 +370,7 @@ static int dst_dev_event(struct notifier_block *this, unsigned long event, static struct notifier_block dst_dev_notifier = { .notifier_call = dst_dev_event, + .priority = -10, /* must be called after other network notifiers */ }; void __init dst_init(void) diff --git a/net/core/filter.c b/net/core/filter.c index 7beaec3..23e9b2a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -112,39 +112,41 @@ EXPORT_SYMBOL(sk_filter); */ unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int flen) { - struct sock_filter *fentry; /* We walk down these */ void *ptr; u32 A = 0; /* Accumulator */ u32 X = 0; /* Index Register */ u32 mem[BPF_MEMWORDS]; /* Scratch Memory Store */ + unsigned long memvalid = 0; u32 tmp; int k; int pc; + BUILD_BUG_ON(BPF_MEMWORDS > BITS_PER_LONG); /* * Process array of filter instructions. */ for (pc = 0; pc < flen; pc++) { - fentry = &filter[pc]; + const struct sock_filter *fentry = &filter[pc]; + u32 f_k = fentry->k; switch (fentry->code) { case BPF_S_ALU_ADD_X: A += X; continue; case BPF_S_ALU_ADD_K: - A += fentry->k; + A += f_k; continue; case BPF_S_ALU_SUB_X: A -= X; continue; case BPF_S_ALU_SUB_K: - A -= fentry->k; + A -= f_k; continue; case BPF_S_ALU_MUL_X: A *= X; continue; case BPF_S_ALU_MUL_K: - A *= fentry->k; + A *= f_k; continue; case BPF_S_ALU_DIV_X: if (X == 0) @@ -152,49 +154,49 @@ unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int A /= X; continue; case BPF_S_ALU_DIV_K: - A /= fentry->k; + A /= f_k; continue; case BPF_S_ALU_AND_X: A &= X; continue; case BPF_S_ALU_AND_K: - A &= fentry->k; + A &= f_k; continue; case BPF_S_ALU_OR_X: A |= X; continue; case BPF_S_ALU_OR_K: - A |= fentry->k; + A |= f_k; continue; case BPF_S_ALU_LSH_X: A <<= X; continue; case BPF_S_ALU_LSH_K: - A <<= fentry->k; + A <<= f_k; continue; case BPF_S_ALU_RSH_X: A >>= X; continue; case BPF_S_ALU_RSH_K: - A >>= fentry->k; + A >>= f_k; continue; case BPF_S_ALU_NEG: A = -A; continue; case BPF_S_JMP_JA: - pc += fentry->k; + pc += f_k; continue; case BPF_S_JMP_JGT_K: - pc += (A > fentry->k) ? fentry->jt : fentry->jf; + pc += (A > f_k) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JGE_K: - pc += (A >= fentry->k) ? fentry->jt : fentry->jf; + pc += (A >= f_k) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JEQ_K: - pc += (A == fentry->k) ? fentry->jt : fentry->jf; + pc += (A == f_k) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JSET_K: - pc += (A & fentry->k) ? fentry->jt : fentry->jf; + pc += (A & f_k) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JGT_X: pc += (A > X) ? fentry->jt : fentry->jf; @@ -209,7 +211,7 @@ unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int pc += (A & X) ? fentry->jt : fentry->jf; continue; case BPF_S_LD_W_ABS: - k = fentry->k; + k = f_k; load_w: ptr = load_pointer(skb, k, 4, &tmp); if (ptr != NULL) { @@ -218,7 +220,7 @@ load_w: } break; case BPF_S_LD_H_ABS: - k = fentry->k; + k = f_k; load_h: ptr = load_pointer(skb, k, 2, &tmp); if (ptr != NULL) { @@ -227,7 +229,7 @@ load_h: } break; case BPF_S_LD_B_ABS: - k = fentry->k; + k = f_k; load_b: ptr = load_pointer(skb, k, 1, &tmp); if (ptr != NULL) { @@ -242,32 +244,34 @@ load_b: X = skb->len; continue; case BPF_S_LD_W_IND: - k = X + fentry->k; + k = X + f_k; goto load_w; case BPF_S_LD_H_IND: - k = X + fentry->k; + k = X + f_k; goto load_h; case BPF_S_LD_B_IND: - k = X + fentry->k; + k = X + f_k; goto load_b; case BPF_S_LDX_B_MSH: - ptr = load_pointer(skb, fentry->k, 1, &tmp); + ptr = load_pointer(skb, f_k, 1, &tmp); if (ptr != NULL) { X = (*(u8 *)ptr & 0xf) << 2; continue; } return 0; case BPF_S_LD_IMM: - A = fentry->k; + A = f_k; continue; case BPF_S_LDX_IMM: - X = fentry->k; + X = f_k; continue; case BPF_S_LD_MEM: - A = mem[fentry->k]; + A = (memvalid & (1UL << f_k)) ? + mem[f_k] : 0; continue; case BPF_S_LDX_MEM: - X = mem[fentry->k]; + X = (memvalid & (1UL << f_k)) ? + mem[f_k] : 0; continue; case BPF_S_MISC_TAX: X = A; @@ -276,14 +280,16 @@ load_b: A = X; continue; case BPF_S_RET_K: - return fentry->k; + return f_k; case BPF_S_RET_A: return A; case BPF_S_ST: - mem[fentry->k] = A; + memvalid |= 1UL << f_k; + mem[f_k] = A; continue; case BPF_S_STX: - mem[fentry->k] = X; + memvalid |= 1UL << f_k; + mem[f_k] = X; continue; default: WARN_ON(1); diff --git a/net/core/iovec.c b/net/core/iovec.c index 72aceb1..c40f27e 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -35,10 +35,9 @@ * in any case. */ -long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) +int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) { - int size, ct; - long err; + int size, ct, err; if (m->msg_namelen) { if (mode == VERIFY_READ) { @@ -62,14 +61,13 @@ long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, err = 0; for (ct = 0; ct < m->msg_iovlen; ct++) { - err += iov[ct].iov_len; - /* - * Goal is not to verify user data, but to prevent returning - * negative value, which is interpreted as errno. - * Overflow is still possible, but it is harmless. - */ - if (err < 0) - return -EMSGSIZE; + size_t len = iov[ct].iov_len; + + if (len > INT_MAX - err) { + len = INT_MAX - err; + iov[ct].iov_len = len; + } + err += len; } return err; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 679b797..33bc382 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -887,10 +887,11 @@ static ssize_t pktgen_if_write(struct file *file, i += len; if (debug) { - char tb[count + 1]; - if (copy_from_user(tb, user_buffer, count)) + size_t copy = min_t(size_t, count, 1023); + char tb[copy + 1]; + if (copy_from_user(tb, user_buffer, copy)) return -EFAULT; - tb[count] = 0; + tb[copy] = 0; printk(KERN_DEBUG "pktgen: %s,%lu buffer -:%s:-\n", name, (unsigned long)count, tb); } @@ -2611,8 +2612,8 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, /* Update any of the values, used when we're incrementing various * fields. */ - queue_map = pkt_dev->cur_queue_map; mod_cur_headers(pkt_dev); + queue_map = pkt_dev->cur_queue_map; datalen = (odev->hard_header_len + 16) & ~0xf; @@ -2975,8 +2976,8 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, /* Update any of the values, used when we're incrementing various * fields. */ - queue_map = pkt_dev->cur_queue_map; mod_cur_headers(pkt_dev); + queue_map = pkt_dev->cur_queue_map; skb = __netdev_alloc_skb(odev, pkt_dev->cur_pkt_size + 64 diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8121268..841c287 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -347,16 +347,17 @@ static size_t rtnl_link_get_size(const struct net_device *dev) if (!ops) return 0; - size = nlmsg_total_size(sizeof(struct nlattr)) + /* IFLA_LINKINFO */ - nlmsg_total_size(strlen(ops->kind) + 1); /* IFLA_INFO_KIND */ + size = nla_total_size(sizeof(struct nlattr)) + /* IFLA_LINKINFO */ + nla_total_size(strlen(ops->kind) + 1); /* IFLA_INFO_KIND */ if (ops->get_size) /* IFLA_INFO_DATA + nested data */ - size += nlmsg_total_size(sizeof(struct nlattr)) + + size += nla_total_size(sizeof(struct nlattr)) + ops->get_size(dev); if (ops->get_xstats_size) - size += ops->get_xstats_size(dev); /* IFLA_INFO_XSTATS */ + /* IFLA_INFO_XSTATS */ + size += nla_total_size(ops->get_xstats_size(dev)); return size; } diff --git a/net/core/sock.c b/net/core/sock.c index 3eed542..fb60801 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1653,10 +1653,10 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) { struct proto *prot = sk->sk_prot; int amt = sk_mem_pages(size); - int allocated; + long allocated; sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; - allocated = atomic_add_return(amt, prot->memory_allocated); + allocated = atomic_long_add_return(amt, prot->memory_allocated); /* Under limit. */ if (allocated <= prot->sysctl_mem[0]) { @@ -1714,7 +1714,7 @@ suppress_allocation: /* Alas. Undo changes. */ sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM; - atomic_sub(amt, prot->memory_allocated); + atomic_long_sub(amt, prot->memory_allocated); return 0; } EXPORT_SYMBOL(__sk_mem_schedule); @@ -1727,12 +1727,12 @@ void __sk_mem_reclaim(struct sock *sk) { struct proto *prot = sk->sk_prot; - atomic_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT, + atomic_long_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT, prot->memory_allocated); sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1; if (prot->memory_pressure && *prot->memory_pressure && - (atomic_read(prot->memory_allocated) < prot->sysctl_mem[0])) + (atomic_long_read(prot->memory_allocated) < prot->sysctl_mem[0])) *prot->memory_pressure = 0; } EXPORT_SYMBOL(__sk_mem_reclaim); @@ -2452,12 +2452,12 @@ static char proto_method_implemented(const void *method) static void proto_seq_printf(struct seq_file *seq, struct proto *proto) { - seq_printf(seq, "%-9s %4u %6d %6d %-3s %6u %-3s %-10s " + seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s " "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n", proto->name, proto->obj_size, sock_prot_inuse_get(seq_file_net(seq), proto), - proto->memory_allocated != NULL ? atomic_read(proto->memory_allocated) : -1, + proto->memory_allocated != NULL ? atomic_long_read(proto->memory_allocated) : -1L, proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI", proto->max_header, proto->slab == NULL ? "no" : "yes", diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 117fb09..75c3582 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -134,13 +134,41 @@ static inline int ccid_get_current_tx_ccid(struct dccp_sock *dp) extern void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk); extern void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk); +/* + * Congestion control of queued data packets via CCID decision. + * + * The TX CCID performs its congestion-control by indicating whether and when a + * queued packet may be sent, using the return code of ccid_hc_tx_send_packet(). + * The following modes are supported via the symbolic constants below: + * - timer-based pacing (CCID returns a delay value in milliseconds); + * - autonomous dequeueing (CCID internally schedules dccps_xmitlet). + */ + +enum ccid_dequeueing_decision { + CCID_PACKET_SEND_AT_ONCE = 0x00000, /* "green light": no delay */ + CCID_PACKET_DELAY_MAX = 0x0FFFF, /* maximum delay in msecs */ + CCID_PACKET_DELAY = 0x10000, /* CCID msec-delay mode */ + CCID_PACKET_WILL_DEQUEUE_LATER = 0x20000, /* CCID autonomous mode */ + CCID_PACKET_ERR = 0xF0000, /* error condition */ +}; + +static inline int ccid_packet_dequeue_eval(const int return_code) +{ + if (return_code < 0) + return CCID_PACKET_ERR; + if (return_code == 0) + return CCID_PACKET_SEND_AT_ONCE; + if (return_code <= CCID_PACKET_DELAY_MAX) + return CCID_PACKET_DELAY; + return return_code; +} + static inline int ccid_hc_tx_send_packet(struct ccid *ccid, struct sock *sk, struct sk_buff *skb) { - int rc = 0; if (ccid->ccid_ops->ccid_hc_tx_send_packet != NULL) - rc = ccid->ccid_ops->ccid_hc_tx_send_packet(sk, skb); - return rc; + return ccid->ccid_ops->ccid_hc_tx_send_packet(sk, skb); + return CCID_PACKET_SEND_AT_ONCE; } static inline void ccid_hc_tx_packet_sent(struct ccid *ccid, struct sock *sk, diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index d850e29..6576eae 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -78,12 +78,9 @@ static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hc) static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) { - struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - - if (hc->tx_pipe < hc->tx_cwnd) - return 0; - - return 1; /* XXX CCID should dequeue when ready instead of polling */ + if (ccid2_cwnd_network_limited(ccid2_hc_tx_sk(sk))) + return CCID_PACKET_WILL_DEQUEUE_LATER; + return CCID_PACKET_SEND_AT_ONCE; } static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val) @@ -115,6 +112,7 @@ static void ccid2_hc_tx_rto_expire(unsigned long data) { struct sock *sk = (struct sock *)data; struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + const bool sender_was_blocked = ccid2_cwnd_network_limited(hc); bh_lock_sock(sk); if (sock_owned_by_user(sk)) { @@ -129,8 +127,6 @@ static void ccid2_hc_tx_rto_expire(unsigned long data) if (hc->tx_rto > DCCP_RTO_MAX) hc->tx_rto = DCCP_RTO_MAX; - sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); - /* adjust pipe, cwnd etc */ hc->tx_ssthresh = hc->tx_cwnd / 2; if (hc->tx_ssthresh < 2) @@ -146,6 +142,12 @@ static void ccid2_hc_tx_rto_expire(unsigned long data) hc->tx_rpseq = 0; hc->tx_rpdupack = -1; ccid2_change_l_ack_ratio(sk, 1); + + /* if we were blocked before, we may now send cwnd=1 packet */ + if (sender_was_blocked) + tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet); + /* restart backed-off timer */ + sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); out: bh_unlock_sock(sk); sock_put(sk); @@ -434,6 +436,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + const bool sender_was_blocked = ccid2_cwnd_network_limited(hc); u64 ackno, seqno; struct ccid2_seq *seqp; unsigned char *vector; @@ -631,6 +634,10 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) sk_stop_timer(sk, &hc->tx_rtotimer); else sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); + + /* check if incoming Acks allow pending packets to be sent */ + if (sender_was_blocked && !ccid2_cwnd_network_limited(hc)) + tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet); } static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h index 9731c2d..25cb6b2 100644 --- a/net/dccp/ccids/ccid2.h +++ b/net/dccp/ccids/ccid2.h @@ -81,6 +81,11 @@ struct ccid2_hc_tx_sock { u64 tx_high_ack; }; +static inline bool ccid2_cwnd_network_limited(struct ccid2_hc_tx_sock *hc) +{ + return hc->tx_pipe >= hc->tx_cwnd; +} + struct ccid2_hc_rx_sock { int rx_data; }; diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 3060a60..3d604e1 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -268,11 +268,11 @@ out: sock_put(sk); } -/* - * returns - * > 0: delay (in msecs) that should pass before actually sending - * = 0: can send immediately - * < 0: error condition; do not send packet +/** + * ccid3_hc_tx_send_packet - Delay-based dequeueing of TX packets + * @skb: next packet candidate to send on @sk + * This function uses the convention of ccid_packet_dequeue_eval() and + * returns a millisecond-delay value between 0 and t_mbi = 64000 msec. */ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) { @@ -348,7 +348,7 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) /* set the nominal send time for the next following packet */ hc->tx_t_nom = ktime_add_us(hc->tx_t_nom, hc->tx_t_ipi); - return 0; + return CCID_PACKET_SEND_AT_ONCE; } static void ccid3_hc_tx_packet_sent(struct sock *sk, unsigned int len) diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 3eb264b..a8ed459 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -243,8 +243,9 @@ extern void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, extern void dccp_send_sync(struct sock *sk, const u64 seq, const enum dccp_pkt_type pkt_type); -extern void dccp_write_xmit(struct sock *sk, int block); -extern void dccp_write_space(struct sock *sk); +extern void dccp_write_xmit(struct sock *sk); +extern void dccp_write_space(struct sock *sk); +extern void dccp_flush_write_queue(struct sock *sk, long *time_budget); extern void dccp_init_xmit_timers(struct sock *sk); static inline void dccp_clear_xmit_timers(struct sock *sk) diff --git a/net/dccp/output.c b/net/dccp/output.c index a988fe9..45b9185 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -209,108 +209,150 @@ void dccp_write_space(struct sock *sk) } /** - * dccp_wait_for_ccid - Wait for ccid to tell us we can send a packet + * dccp_wait_for_ccid - Await CCID send permission * @sk: socket to wait for - * @skb: current skb to pass on for waiting - * @delay: sleep timeout in milliseconds (> 0) - * This function is called by default when the socket is closed, and - * when a non-zero linger time is set on the socket. For consistency + * @delay: timeout in jiffies + * This is used by CCIDs which need to delay the send time in process context. */ -static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb, int delay) +static int dccp_wait_for_ccid(struct sock *sk, unsigned long delay) { - struct dccp_sock *dp = dccp_sk(sk); DEFINE_WAIT(wait); - unsigned long jiffdelay; - int rc; + long remaining; + + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + sk->sk_write_pending++; + release_sock(sk); + + remaining = schedule_timeout(delay); + + lock_sock(sk); + sk->sk_write_pending--; + finish_wait(sk_sleep(sk), &wait); + + if (signal_pending(current) || sk->sk_err) + return -1; + return remaining; +} + +/** + * dccp_xmit_packet - Send data packet under control of CCID + * Transmits next-queued payload and informs CCID to account for the packet. + */ +static void dccp_xmit_packet(struct sock *sk) +{ + int err, len; + struct dccp_sock *dp = dccp_sk(sk); + struct sk_buff *skb = skb_dequeue(&sk->sk_write_queue); - do { - dccp_pr_debug("delayed send by %d msec\n", delay); - jiffdelay = msecs_to_jiffies(delay); + if (unlikely(skb == NULL)) + return; + len = skb->len; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + if (sk->sk_state == DCCP_PARTOPEN) { + const u32 cur_mps = dp->dccps_mss_cache - DCCP_FEATNEG_OVERHEAD; + /* + * See 8.1.5 - Handshake Completion. + * + * For robustness we resend Confirm options until the client has + * entered OPEN. During the initial feature negotiation, the MPS + * is smaller than usual, reduced by the Change/Confirm options. + */ + if (!list_empty(&dp->dccps_featneg) && len > cur_mps) { + DCCP_WARN("Payload too large (%d) for featneg.\n", len); + dccp_send_ack(sk); + dccp_feat_list_purge(&dp->dccps_featneg); + } - sk->sk_write_pending++; - release_sock(sk); - schedule_timeout(jiffdelay); - lock_sock(sk); - sk->sk_write_pending--; + inet_csk_schedule_ack(sk); + inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, + inet_csk(sk)->icsk_rto, + DCCP_RTO_MAX); + DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK; + } else if (dccp_ack_pending(sk)) { + DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK; + } else { + DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATA; + } + + err = dccp_transmit_skb(sk, skb); + if (err) + dccp_pr_debug("transmit_skb() returned err=%d\n", err); + /* + * Register this one as sent even if an error occurred. To the remote + * end a local packet drop is indistinguishable from network loss, i.e. + * any local drop will eventually be reported via receiver feedback. + */ + ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, len); +} - if (sk->sk_err) - goto do_error; - if (signal_pending(current)) - goto do_interrupted; +/** + * dccp_flush_write_queue - Drain queue at end of connection + * Since dccp_sendmsg queues packets without waiting for them to be sent, it may + * happen that the TX queue is not empty at the end of a connection. We give the + * HC-sender CCID a grace period of up to @time_budget jiffies. If this function + * returns with a non-empty write queue, it will be purged later. + */ +void dccp_flush_write_queue(struct sock *sk, long *time_budget) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct sk_buff *skb; + long delay, rc; + while (*time_budget > 0 && (skb = skb_peek(&sk->sk_write_queue))) { rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb); - } while ((delay = rc) > 0); -out: - finish_wait(sk_sleep(sk), &wait); - return rc; - -do_error: - rc = -EPIPE; - goto out; -do_interrupted: - rc = -EINTR; - goto out; + + switch (ccid_packet_dequeue_eval(rc)) { + case CCID_PACKET_WILL_DEQUEUE_LATER: + /* + * If the CCID determines when to send, the next sending + * time is unknown or the CCID may not even send again + * (e.g. remote host crashes or lost Ack packets). + */ + DCCP_WARN("CCID did not manage to send all packets\n"); + return; + case CCID_PACKET_DELAY: + delay = msecs_to_jiffies(rc); + if (delay > *time_budget) + return; + rc = dccp_wait_for_ccid(sk, delay); + if (rc < 0) + return; + *time_budget -= (delay - rc); + /* check again if we can send now */ + break; + case CCID_PACKET_SEND_AT_ONCE: + dccp_xmit_packet(sk); + break; + case CCID_PACKET_ERR: + skb_dequeue(&sk->sk_write_queue); + kfree_skb(skb); + dccp_pr_debug("packet discarded due to err=%ld\n", rc); + } + } } -void dccp_write_xmit(struct sock *sk, int block) +void dccp_write_xmit(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); struct sk_buff *skb; while ((skb = skb_peek(&sk->sk_write_queue))) { - int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb); - - if (err > 0) { - if (!block) { - sk_reset_timer(sk, &dp->dccps_xmit_timer, - msecs_to_jiffies(err)+jiffies); - break; - } else - err = dccp_wait_for_ccid(sk, skb, err); - if (err && err != -EINTR) - DCCP_BUG("err=%d after dccp_wait_for_ccid", err); - } + int rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb); - skb_dequeue(&sk->sk_write_queue); - if (err == 0) { - struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); - const int len = skb->len; - - if (sk->sk_state == DCCP_PARTOPEN) { - const u32 cur_mps = dp->dccps_mss_cache - DCCP_FEATNEG_OVERHEAD; - /* - * See 8.1.5 - Handshake Completion. - * - * For robustness we resend Confirm options until the client has - * entered OPEN. During the initial feature negotiation, the MPS - * is smaller than usual, reduced by the Change/Confirm options. - */ - if (!list_empty(&dp->dccps_featneg) && len > cur_mps) { - DCCP_WARN("Payload too large (%d) for featneg.\n", len); - dccp_send_ack(sk); - dccp_feat_list_purge(&dp->dccps_featneg); - } - - inet_csk_schedule_ack(sk); - inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, - inet_csk(sk)->icsk_rto, - DCCP_RTO_MAX); - dcb->dccpd_type = DCCP_PKT_DATAACK; - } else if (dccp_ack_pending(sk)) - dcb->dccpd_type = DCCP_PKT_DATAACK; - else - dcb->dccpd_type = DCCP_PKT_DATA; - - err = dccp_transmit_skb(sk, skb); - ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, len); - if (err) - DCCP_BUG("err=%d after ccid_hc_tx_packet_sent", - err); - } else { - dccp_pr_debug("packet discarded due to err=%d\n", err); + switch (ccid_packet_dequeue_eval(rc)) { + case CCID_PACKET_WILL_DEQUEUE_LATER: + return; + case CCID_PACKET_DELAY: + sk_reset_timer(sk, &dp->dccps_xmit_timer, + jiffies + msecs_to_jiffies(rc)); + return; + case CCID_PACKET_SEND_AT_ONCE: + dccp_xmit_packet(sk); + break; + case CCID_PACKET_ERR: + skb_dequeue(&sk->sk_write_queue); kfree_skb(skb); + dccp_pr_debug("packet discarded due to err=%d\n", rc); } } } @@ -622,7 +664,6 @@ void dccp_send_close(struct sock *sk, const int active) DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSE; if (active) { - dccp_write_xmit(sk, 1); dccp_skb_entail(sk, skb); dccp_transmit_skb(sk, skb_clone(skb, prio)); /* diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 7e5fc04..ef343d5 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -726,7 +726,13 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, goto out_discard; skb_queue_tail(&sk->sk_write_queue, skb); - dccp_write_xmit(sk,0); + /* + * The xmit_timer is set if the TX CCID is rate-based and will expire + * when congestion control permits to release further packets into the + * network. Window-based CCIDs do not use this timer. + */ + if (!timer_pending(&dp->dccps_xmit_timer)) + dccp_write_xmit(sk); out_release: release_sock(sk); return rc ? : len; @@ -951,9 +957,22 @@ void dccp_close(struct sock *sk, long timeout) /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); } else if (sk->sk_state != DCCP_CLOSED) { + /* + * Normal connection termination. May need to wait if there are + * still packets in the TX queue that are delayed by the CCID. + */ + dccp_flush_write_queue(sk, &timeout); dccp_terminate_connection(sk); } + /* + * Flush write queue. This may be necessary in several cases: + * - we have been closed by the peer but still have application data; + * - abortive termination (unread data or zero linger time), + * - normal termination but queue could not be flushed within time limit + */ + __skb_queue_purge(&sk->sk_write_queue); + sk_stream_wait_close(sk, timeout); adjudge_to_death: diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 1a9aa05d..7587870 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -237,32 +237,35 @@ out: sock_put(sk); } -/* Transmit-delay timer: used by the CCIDs to delay actual send time */ -static void dccp_write_xmit_timer(unsigned long data) +/** + * dccp_write_xmitlet - Workhorse for CCID packet dequeueing interface + * See the comments above %ccid_dequeueing_decision for supported modes. + */ +static void dccp_write_xmitlet(unsigned long data) { struct sock *sk = (struct sock *)data; - struct dccp_sock *dp = dccp_sk(sk); bh_lock_sock(sk); if (sock_owned_by_user(sk)) - sk_reset_timer(sk, &dp->dccps_xmit_timer, jiffies+1); + sk_reset_timer(sk, &dccp_sk(sk)->dccps_xmit_timer, jiffies + 1); else - dccp_write_xmit(sk, 0); + dccp_write_xmit(sk); bh_unlock_sock(sk); - sock_put(sk); } -static void dccp_init_write_xmit_timer(struct sock *sk) +static void dccp_write_xmit_timer(unsigned long data) { - struct dccp_sock *dp = dccp_sk(sk); - - setup_timer(&dp->dccps_xmit_timer, dccp_write_xmit_timer, - (unsigned long)sk); + dccp_write_xmitlet(data); + sock_put((struct sock *)data); } void dccp_init_xmit_timers(struct sock *sk) { - dccp_init_write_xmit_timer(sk); + struct dccp_sock *dp = dccp_sk(sk); + + tasklet_init(&dp->dccps_xmitlet, dccp_write_xmitlet, (unsigned long)sk); + setup_timer(&dp->dccps_xmit_timer, dccp_write_xmit_timer, + (unsigned long)sk); inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer, &dccp_keepalive_timer); } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index d6b93d1..a76b78d 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -155,7 +155,7 @@ static const struct proto_ops dn_proto_ops; static DEFINE_RWLOCK(dn_hash_lock); static struct hlist_head dn_sk_hash[DN_SK_HASH_SIZE]; static struct hlist_head dn_wild_sk; -static atomic_t decnet_memory_allocated; +static atomic_long_t decnet_memory_allocated; static int __dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen, int flags); static int __dn_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen, int flags); diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c index be3eb8e..28f8b5e 100644 --- a/net/decnet/sysctl_net_decnet.c +++ b/net/decnet/sysctl_net_decnet.c @@ -38,7 +38,7 @@ int decnet_log_martians = 1; int decnet_no_fc_max_cwnd = NSP_MIN_WINDOW; /* Reasonable defaults, I hope, based on tcp's defaults */ -int sysctl_decnet_mem[3] = { 768 << 3, 1024 << 3, 1536 << 3 }; +long sysctl_decnet_mem[3] = { 768 << 3, 1024 << 3, 1536 << 3 }; int sysctl_decnet_wmem[3] = { 4 * 1024, 16 * 1024, 128 * 1024 }; int sysctl_decnet_rmem[3] = { 4 * 1024, 87380, 87380 * 2 }; @@ -324,7 +324,7 @@ static ctl_table dn_table[] = { .data = &sysctl_decnet_mem, .maxlen = sizeof(sysctl_decnet_mem), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_doulongvec_minmax }, { .procname = "decnet_rmem", diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 36e27c2..eb6f69a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1052,7 +1052,7 @@ static void ip_fib_net_exit(struct net *net) hlist_for_each_entry_safe(tb, node, tmp, head, tb_hlist) { hlist_del(node); fib_table_flush(tb); - kfree(tb); + fib_free_table(tb); } } kfree(net->ipv4.fib_table_hash); diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index b232375..b3acb04 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -716,6 +716,24 @@ int fib_table_flush(struct fib_table *tb) return found; } +void fib_free_table(struct fib_table *tb) +{ + struct fn_hash *table = (struct fn_hash *) tb->tb_data; + struct fn_zone *fz, *next; + + next = table->fn_zone_list; + while (next != NULL) { + fz = next; + next = fz->fz_next; + + if (fz->fz_hash != fz->fz_embedded_hash) + fz_hash_free(fz->fz_hash, fz->fz_divisor); + + kfree(fz); + } + + kfree(tb); +} static inline int fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb, diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index a29edf2..c079cc0 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -47,11 +47,8 @@ extern int fib_detect_death(struct fib_info *fi, int order, static inline void fib_result_assign(struct fib_result *res, struct fib_info *fi) { - if (res->fi != NULL) - fib_info_put(res->fi); + /* we used to play games with refcounts, but we now use RCU */ res->fi = fi; - if (fi != NULL) - atomic_inc(&fi->fib_clntref); } #endif /* _FIB_LOOKUP_H */ diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index b144508..200eb53 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1797,6 +1797,11 @@ int fib_table_flush(struct fib_table *tb) return found; } +void fib_free_table(struct fib_table *tb) +{ + kfree(tb); +} + void fib_table_select_default(struct fib_table *tb, const struct flowi *flp, struct fib_result *res) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index c8877c6..3c53c2d 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2306,10 +2306,8 @@ void ip_mc_drop_socket(struct sock *sk) in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); - if (in_dev != NULL) { + if (in_dev != NULL) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); - in_dev_put(in_dev); - } /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); call_rcu(&iml->rcu, ip_mc_socklist_reclaim); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index ba80426..2ada171 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -490,9 +490,11 @@ static int inet_csk_diag_dump(struct sock *sk, { struct inet_diag_req *r = NLMSG_DATA(cb->nlh); - if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) { + if (nlmsg_attrlen(cb->nlh, sizeof(*r))) { struct inet_diag_entry entry; - struct rtattr *bc = (struct rtattr *)(r + 1); + const struct nlattr *bc = nlmsg_find_attr(cb->nlh, + sizeof(*r), + INET_DIAG_REQ_BYTECODE); struct inet_sock *inet = inet_sk(sk); entry.family = sk->sk_family; @@ -512,7 +514,7 @@ static int inet_csk_diag_dump(struct sock *sk, entry.dport = ntohs(inet->inet_dport); entry.userlocks = sk->sk_userlocks; - if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry)) + if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry)) return 0; } @@ -527,9 +529,11 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw, { struct inet_diag_req *r = NLMSG_DATA(cb->nlh); - if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) { + if (nlmsg_attrlen(cb->nlh, sizeof(*r))) { struct inet_diag_entry entry; - struct rtattr *bc = (struct rtattr *)(r + 1); + const struct nlattr *bc = nlmsg_find_attr(cb->nlh, + sizeof(*r), + INET_DIAG_REQ_BYTECODE); entry.family = tw->tw_family; #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) @@ -548,7 +552,7 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw, entry.dport = ntohs(tw->tw_dport); entry.userlocks = 0; - if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry)) + if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry)) return 0; } @@ -618,7 +622,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, struct inet_diag_req *r = NLMSG_DATA(cb->nlh); struct inet_connection_sock *icsk = inet_csk(sk); struct listen_sock *lopt; - struct rtattr *bc = NULL; + const struct nlattr *bc = NULL; struct inet_sock *inet = inet_sk(sk); int j, s_j; int reqnum, s_reqnum; @@ -638,8 +642,9 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, if (!lopt || !lopt->qlen) goto out; - if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) { - bc = (struct rtattr *)(r + 1); + if (nlmsg_attrlen(cb->nlh, sizeof(*r))) { + bc = nlmsg_find_attr(cb->nlh, sizeof(*r), + INET_DIAG_REQ_BYTECODE); entry.sport = inet->inet_num; entry.userlocks = sk->sk_userlocks; } @@ -672,8 +677,8 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, &ireq->rmt_addr; entry.dport = ntohs(ireq->rmt_port); - if (!inet_diag_bc_run(RTA_DATA(bc), - RTA_PAYLOAD(bc), &entry)) + if (!inet_diag_bc_run(nla_data(bc), + nla_len(bc), &entry)) continue; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 01087e0..70ff77f 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1325,7 +1325,6 @@ static void ipgre_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; - struct ipgre_net *ign = net_generic(dev_net(dev), ipgre_net_id); tunnel->dev = dev; strcpy(tunnel->parms.name, dev->name); @@ -1336,7 +1335,6 @@ static void ipgre_fb_tunnel_init(struct net_device *dev) tunnel->hlen = sizeof(struct iphdr) + 4; dev_hold(dev); - rcu_assign_pointer(ign->tunnels_wc[0], tunnel); } @@ -1383,10 +1381,12 @@ static int __net_init ipgre_init_net(struct net *net) if ((err = register_netdev(ign->fb_tunnel_dev))) goto err_reg_dev; + rcu_assign_pointer(ign->tunnels_wc[0], + netdev_priv(ign->fb_tunnel_dev)); return 0; err_reg_dev: - free_netdev(ign->fb_tunnel_dev); + ipgre_dev_free(ign->fb_tunnel_dev); err_alloc_dev: return err; } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 4ae1f20..1b48eb1 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -59,13 +59,13 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) local_bh_enable(); socket_seq_show(seq); - seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n", + seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n", sock_prot_inuse_get(net, &tcp_prot), orphans, tcp_death_row.tw_count, sockets, - atomic_read(&tcp_memory_allocated)); - seq_printf(seq, "UDP: inuse %d mem %d\n", + atomic_long_read(&tcp_memory_allocated)); + seq_printf(seq, "UDP: inuse %d mem %ld\n", sock_prot_inuse_get(net, &udp_prot), - atomic_read(&udp_memory_allocated)); + atomic_long_read(&udp_memory_allocated)); seq_printf(seq, "UDPLITE: inuse %d\n", sock_prot_inuse_get(net, &udplite_prot)); seq_printf(seq, "RAW: inuse %d\n", diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d96c1da..e91911d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -398,7 +398,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_mem, .maxlen = sizeof(sysctl_tcp_mem), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_doulongvec_minmax }, { .procname = "tcp_wmem", @@ -602,8 +602,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .proc_handler = proc_doulongvec_minmax, }, { .procname = "udp_rmem_min", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1664a05..0814199 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -282,7 +282,7 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); -int sysctl_tcp_mem[3] __read_mostly; +long sysctl_tcp_mem[3] __read_mostly; int sysctl_tcp_wmem[3] __read_mostly; int sysctl_tcp_rmem[3] __read_mostly; @@ -290,7 +290,7 @@ EXPORT_SYMBOL(sysctl_tcp_mem); EXPORT_SYMBOL(sysctl_tcp_rmem); EXPORT_SYMBOL(sysctl_tcp_wmem); -atomic_t tcp_memory_allocated; /* Current allocated memory. */ +atomic_long_t tcp_memory_allocated; /* Current allocated memory. */ EXPORT_SYMBOL(tcp_memory_allocated); /* @@ -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 < 8 || val > MAX_TCP_WINDOW) { + if (val < 64 || val > MAX_TCP_WINDOW) { err = -EINVAL; break; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3357f69..6d8ab1c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -259,8 +259,11 @@ static void tcp_fixup_sndbuf(struct sock *sk) int sndmem = tcp_sk(sk)->rx_opt.mss_clamp + MAX_TCP_HEADER + 16 + sizeof(struct sk_buff); - if (sk->sk_sndbuf < 3 * sndmem) - sk->sk_sndbuf = min(3 * sndmem, sysctl_tcp_wmem[2]); + if (sk->sk_sndbuf < 3 * sndmem) { + sk->sk_sndbuf = 3 * sndmem; + if (sk->sk_sndbuf > sysctl_tcp_wmem[2]) + sk->sk_sndbuf = sysctl_tcp_wmem[2]; + } } /* 2. Tuning advertised window (window_clamp, rcv_ssthresh) @@ -396,7 +399,7 @@ static void tcp_clamp_window(struct sock *sk) if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && !tcp_memory_pressure && - atomic_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) { + atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) { sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), sysctl_tcp_rmem[2]); } @@ -4861,7 +4864,7 @@ static int tcp_should_expand_sndbuf(struct sock *sk) return 0; /* If we are under soft global TCP memory pressure, do not expand. */ - if (atomic_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0]) + if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0]) return 0; /* If we filled the congestion window, do not expand. */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 28cb2d7..5e0a3a5 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -110,7 +110,7 @@ struct udp_table udp_table __read_mostly; EXPORT_SYMBOL(udp_table); -int sysctl_udp_mem[3] __read_mostly; +long sysctl_udp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_udp_mem); int sysctl_udp_rmem_min __read_mostly; @@ -119,7 +119,7 @@ EXPORT_SYMBOL(sysctl_udp_rmem_min); int sysctl_udp_wmem_min __read_mostly; EXPORT_SYMBOL(sysctl_udp_wmem_min); -atomic_t udp_memory_allocated; +atomic_long_t udp_memory_allocated; EXPORT_SYMBOL(udp_memory_allocated); #define MAX_UDP_PORTS 65536 diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 51df035..4555823 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1137,6 +1137,7 @@ static int get_info(struct net *net, void __user *user, private = &tmp; } #endif + memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index d082eae..24b3558 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -126,6 +126,8 @@ static const struct snmp_mib snmp6_udp6_list[] = { SNMP_MIB_ITEM("Udp6NoPorts", UDP_MIB_NOPORTS), SNMP_MIB_ITEM("Udp6InErrors", UDP_MIB_INERRORS), SNMP_MIB_ITEM("Udp6OutDatagrams", UDP_MIB_OUTDATAGRAMS), + SNMP_MIB_ITEM("Udp6RcvbufErrors", UDP_MIB_RCVBUFERRORS), + SNMP_MIB_ITEM("Udp6SndbufErrors", UDP_MIB_SNDBUFERRORS), SNMP_MIB_SENTINEL }; @@ -134,6 +136,8 @@ static const struct snmp_mib snmp6_udplite6_list[] = { SNMP_MIB_ITEM("UdpLite6NoPorts", UDP_MIB_NOPORTS), SNMP_MIB_ITEM("UdpLite6InErrors", UDP_MIB_INERRORS), SNMP_MIB_ITEM("UdpLite6OutDatagrams", UDP_MIB_OUTDATAGRAMS), + SNMP_MIB_ITEM("UdpLite6RcvbufErrors", UDP_MIB_RCVBUFERRORS), + SNMP_MIB_ITEM("UdpLite6SndbufErrors", UDP_MIB_SNDBUFERRORS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index c7ba314..0f27664 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -349,7 +349,7 @@ found: /* Check for overlap with preceding fragment. */ if (prev && - (FRAG6_CB(prev)->offset + prev->len) - offset > 0) + (FRAG6_CB(prev)->offset + prev->len) > offset) goto discard_fq; /* Look for overlap with succeeding segment. */ diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 25661f9..fc32833 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2741,6 +2741,7 @@ static void __net_exit ip6_route_net_exit(struct net *net) kfree(net->ipv6.ip6_prohibit_entry); kfree(net->ipv6.ip6_blk_hole_entry); #endif + dst_entries_destroy(&net->ipv6.ip6_dst_ops); } static struct pernet_operations ip6_route_net_ops = { @@ -2832,5 +2833,6 @@ void ip6_route_cleanup(void) xfrm6_fini(); fib6_gc_cleanup(); unregister_pernet_subsys(&ip6_route_net_ops); + dst_entries_destroy(&ip6_dst_blackhole_ops); kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); } diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 104ec3b..b8dbae8 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -249,7 +249,7 @@ static int l2tp_dfs_seq_open(struct inode *inode, struct file *file) struct seq_file *seq; int rc = -ENOMEM; - pd = kzalloc(GFP_KERNEL, sizeof(*pd)); + pd = kzalloc(sizeof(*pd), GFP_KERNEL); if (pd == NULL) goto out; diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index 4aa47d0..1243d1d 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -203,9 +203,13 @@ static ssize_t key_key_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; - int i, res, bufsize = 2 * key->conf.keylen + 2; + int i, bufsize = 2 * key->conf.keylen + 2; char *buf = kmalloc(bufsize, GFP_KERNEL); char *p = buf; + ssize_t res; + + if (!buf) + return -ENOMEM; for (i = 0; i < key->conf.keylen; i++) p += scnprintf(p, bufsize + buf - p, "%02x", key->conf.key[i]); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index f9163b1..7aa8559 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -391,6 +391,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, u32 hw_reconf_flags = 0; int i; + if (local->scan_sdata == sdata) + ieee80211_scan_cancel(local); + clear_bit(SDATA_STATE_RUNNING, &sdata->state); /* @@ -523,9 +526,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, synchronize_rcu(); skb_queue_purge(&sdata->skb_queue); - if (local->scan_sdata == sdata) - ieee80211_scan_cancel(local); - /* * Disable beaconing here for mesh only, AP and IBSS * are already taken care of. diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 6b322fa..107a0cb 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -677,10 +677,11 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) /* * Calculate scan IE length -- we need this to alloc * memory and to subtract from the driver limit. It - * includes the (extended) supported rates and HT + * includes the DS Params, (extended) supported rates, and HT * information -- SSID is the driver's responsibility. */ - local->scan_ies_len = 4 + max_bitrates; /* (ext) supp rates */ + local->scan_ies_len = 4 + max_bitrates /* (ext) supp rates */ + + 3 /* DS Params */; if (supp_ht) local->scan_ies_len += 2 + sizeof(struct ieee80211_ht_cap); diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index d94a858..00d6ae83 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -195,7 +195,7 @@ socket_mt4_v1(const struct sk_buff *skb, struct xt_action_param *par) static int extract_icmp6_fields(const struct sk_buff *skb, unsigned int outside_hdrlen, - u8 *protocol, + int *protocol, struct in6_addr **raddr, struct in6_addr **laddr, __be16 *rport, @@ -252,8 +252,7 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) struct sock *sk; struct in6_addr *daddr, *saddr; __be16 dport, sport; - int thoff; - u8 tproto; + int thoff, tproto; const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; tproto = ipv6_find_hdr(skb, &thoff, -1, NULL); @@ -305,7 +304,7 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) sk = NULL; } - pr_debug("proto %hhu %pI6:%hu -> %pI6:%hu " + pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu " "(orig %pI6:%hu) sock %p\n", tproto, saddr, ntohs(sport), daddr, ntohs(dport), diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 3616f27..0856a13 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1719,7 +1719,7 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex); if (dev) - strlcpy(uaddr->sa_data, dev->name, 15); + strncpy(uaddr->sa_data, dev->name, 14); else memset(uaddr->sa_data, 0, 14); rcu_read_unlock(); @@ -1742,6 +1742,7 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, sll->sll_family = AF_PACKET; sll->sll_ifindex = po->ifindex; sll->sll_protocol = po->num; + sll->sll_pkttype = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), po->ifindex); if (dev) { diff --git a/net/rds/loop.c b/net/rds/loop.c index c390156..aeec1d4 100644 --- a/net/rds/loop.c +++ b/net/rds/loop.c @@ -134,8 +134,12 @@ static int rds_loop_conn_alloc(struct rds_connection *conn, gfp_t gfp) static void rds_loop_conn_free(void *arg) { struct rds_loop_connection *lc = arg; + unsigned long flags; + rdsdebug("lc %p\n", lc); + spin_lock_irqsave(&loop_conns_lock, flags); list_del(&lc->loop_node); + spin_unlock_irqrestore(&loop_conns_lock, flags); kfree(lc); } diff --git a/net/rds/message.c b/net/rds/message.c index a84545d..1fd3d29 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -224,6 +224,9 @@ struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents) WARN_ON(rm->m_used_sgs + nents > rm->m_total_sgs); WARN_ON(!nents); + if (rm->m_used_sgs + nents > rm->m_total_sgs) + return NULL; + sg_ret = &sg_first[rm->m_used_sgs]; sg_init_table(sg_ret, nents); rm->m_used_sgs += nents; @@ -246,6 +249,10 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in rm->m_inc.i_hdr.h_len = cpu_to_be32(total_len); rm->data.op_nents = ceil(total_len, PAGE_SIZE); rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); + if (!rm->data.op_sg) { + rds_message_put(rm); + return ERR_PTR(-ENOMEM); + } for (i = 0; i < rm->data.op_nents; ++i) { sg_set_page(&rm->data.op_sg[i], diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 1a41deb..8920f2a 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -479,13 +479,38 @@ void rds_atomic_free_op(struct rm_atomic_op *ao) /* - * Count the number of pages needed to describe an incoming iovec. + * Count the number of pages needed to describe an incoming iovec array. */ -static int rds_rdma_pages(struct rds_rdma_args *args) +static int rds_rdma_pages(struct rds_iovec iov[], int nr_iovecs) +{ + int tot_pages = 0; + unsigned int nr_pages; + unsigned int i; + + /* figure out the number of pages in the vector */ + for (i = 0; i < nr_iovecs; i++) { + nr_pages = rds_pages_in_vec(&iov[i]); + if (nr_pages == 0) + return -EINVAL; + + tot_pages += nr_pages; + + /* + * nr_pages for one entry is limited to (UINT_MAX>>PAGE_SHIFT)+1, + * so tot_pages cannot overflow without first going negative. + */ + if (tot_pages < 0) + return -EINVAL; + } + + return tot_pages; +} + +int rds_rdma_extra_size(struct rds_rdma_args *args) { struct rds_iovec vec; struct rds_iovec __user *local_vec; - unsigned int tot_pages = 0; + int tot_pages = 0; unsigned int nr_pages; unsigned int i; @@ -502,14 +527,16 @@ static int rds_rdma_pages(struct rds_rdma_args *args) return -EINVAL; tot_pages += nr_pages; - } - return tot_pages; -} + /* + * nr_pages for one entry is limited to (UINT_MAX>>PAGE_SHIFT)+1, + * so tot_pages cannot overflow without first going negative. + */ + if (tot_pages < 0) + return -EINVAL; + } -int rds_rdma_extra_size(struct rds_rdma_args *args) -{ - return rds_rdma_pages(args) * sizeof(struct scatterlist); + return tot_pages * sizeof(struct scatterlist); } /* @@ -520,13 +547,12 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { struct rds_rdma_args *args; - struct rds_iovec vec; struct rm_rdma_op *op = &rm->rdma; int nr_pages; unsigned int nr_bytes; struct page **pages = NULL; - struct rds_iovec __user *local_vec; - unsigned int nr; + struct rds_iovec iovstack[UIO_FASTIOV], *iovs = iovstack; + int iov_size; unsigned int i, j; int ret = 0; @@ -546,9 +572,26 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, goto out; } - nr_pages = rds_rdma_pages(args); - if (nr_pages < 0) + /* Check whether to allocate the iovec area */ + iov_size = args->nr_local * sizeof(struct rds_iovec); + if (args->nr_local > UIO_FASTIOV) { + iovs = sock_kmalloc(rds_rs_to_sk(rs), iov_size, GFP_KERNEL); + if (!iovs) { + ret = -ENOMEM; + goto out; + } + } + + if (copy_from_user(iovs, (struct rds_iovec __user *)(unsigned long) args->local_vec_addr, iov_size)) { + ret = -EFAULT; + goto out; + } + + nr_pages = rds_rdma_pages(iovs, args->nr_local); + if (nr_pages < 0) { + ret = -EINVAL; goto out; + } pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) { @@ -564,6 +607,10 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_recverr = rs->rs_recverr; WARN_ON(!nr_pages); op->op_sg = rds_message_alloc_sgs(rm, nr_pages); + if (!op->op_sg) { + ret = -ENOMEM; + goto out; + } if (op->op_notify || op->op_recverr) { /* We allocate an uninitialized notifier here, because @@ -597,50 +644,40 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, (unsigned long long)args->remote_vec.addr, op->op_rkey); - local_vec = (struct rds_iovec __user *)(unsigned long) args->local_vec_addr; - for (i = 0; i < args->nr_local; i++) { - if (copy_from_user(&vec, &local_vec[i], - sizeof(struct rds_iovec))) { - ret = -EFAULT; - goto out; - } - - nr = rds_pages_in_vec(&vec); - if (nr == 0) { - ret = -EINVAL; - goto out; - } + struct rds_iovec *iov = &iovs[i]; + /* don't need to check, rds_rdma_pages() verified nr will be +nonzero */ + unsigned int nr = rds_pages_in_vec(iov); - rs->rs_user_addr = vec.addr; - rs->rs_user_bytes = vec.bytes; + rs->rs_user_addr = iov->addr; + rs->rs_user_bytes = iov->bytes; /* If it's a WRITE operation, we want to pin the pages for reading. * If it's a READ operation, we need to pin the pages for writing. */ - ret = rds_pin_pages(vec.addr, nr, pages, !op->op_write); + ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write); if (ret < 0) goto out; - rdsdebug("RDS: nr_bytes %u nr %u vec.bytes %llu vec.addr %llx\n", - nr_bytes, nr, vec.bytes, vec.addr); + rdsdebug("RDS: nr_bytes %u nr %u iov->bytes %llu iov->addr %llx\n", + nr_bytes, nr, iov->bytes, iov->addr); - nr_bytes += vec.bytes; + nr_bytes += iov->bytes; for (j = 0; j < nr; j++) { - unsigned int offset = vec.addr & ~PAGE_MASK; + unsigned int offset = iov->addr & ~PAGE_MASK; struct scatterlist *sg; sg = &op->op_sg[op->op_nents + j]; sg_set_page(sg, pages[j], - min_t(unsigned int, vec.bytes, PAGE_SIZE - offset), + min_t(unsigned int, iov->bytes, PAGE_SIZE - offset), offset); - rdsdebug("RDS: sg->offset %x sg->len %x vec.addr %llx vec.bytes %llu\n", - sg->offset, sg->length, vec.addr, vec.bytes); + rdsdebug("RDS: sg->offset %x sg->len %x iov->addr %llx iov->bytes %llu\n", + sg->offset, sg->length, iov->addr, iov->bytes); - vec.addr += sg->length; - vec.bytes -= sg->length; + iov->addr += sg->length; + iov->bytes -= sg->length; } op->op_nents += nr; @@ -655,13 +692,14 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, } op->op_bytes = nr_bytes; - ret = 0; out: + if (iovs != iovstack) + sock_kfree_s(rds_rs_to_sk(rs), iovs, iov_size); kfree(pages); if (ret) rds_rdma_free_op(op); - - rds_stats_inc(s_send_rdma); + else + rds_stats_inc(s_send_rdma); return ret; } @@ -773,6 +811,10 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, rm->atomic.op_active = 1; rm->atomic.op_recverr = rs->rs_recverr; rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1); + if (!rm->atomic.op_sg) { + ret = -ENOMEM; + goto err; + } /* verify 8 byte-aligned */ if (args->local_addr & 0x7) { diff --git a/net/rds/send.c b/net/rds/send.c index 0bc9db1..35b9c2e 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -973,6 +973,10 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, /* Attach data to the rm */ if (payload_len) { rm->data.op_sg = rds_message_alloc_sgs(rm, ceil(payload_len, PAGE_SIZE)); + if (!rm->data.op_sg) { + ret = -ENOMEM; + goto out; + } ret = rds_message_copy_from_user(rm, msg->msg_iov, payload_len); if (ret) goto out; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 08a8c6c..8e0a320 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -221,7 +221,13 @@ static int rds_tcp_conn_alloc(struct rds_connection *conn, gfp_t gfp) static void rds_tcp_conn_free(void *arg) { struct rds_tcp_connection *tc = arg; + unsigned long flags; rdsdebug("freeing tc %p\n", tc); + + spin_lock_irqsave(&rds_tcp_conn_lock, flags); + list_del(&tc->t_tcp_node); + spin_unlock_irqrestore(&rds_tcp_conn_lock, flags); + kmem_cache_free(rds_tcp_conn_slab, tc); } diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index efd4f95..f23d915 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -268,6 +268,10 @@ static int basic_dump(struct tcf_proto *tp, unsigned long fh, goto nla_put_failure; nla_nest_end(skb, nest); + + if (tcf_exts_dump_stats(skb, &f->exts, &basic_ext_map) < 0) + goto nla_put_failure; + return skb->len; nla_put_failure: diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 37dff78..d49c40f 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -34,8 +34,6 @@ struct cgroup_subsys net_cls_subsys = { .populate = cgrp_populate, #ifdef CONFIG_NET_CLS_CGROUP .subsys_id = net_cls_subsys_id, -#else -#define net_cls_subsys_id net_cls_subsys.subsys_id #endif .module = THIS_MODULE, }; diff --git a/net/sched/em_text.c b/net/sched/em_text.c index 7632532..ea8f566 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -103,7 +103,8 @@ retry: static void em_text_destroy(struct tcf_proto *tp, struct tcf_ematch *m) { - textsearch_destroy(EM_TEXT_PRIV(m)->config); + if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) + textsearch_destroy(EM_TEXT_PRIV(m)->config); } static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m) diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 1ef29c7..e58f947 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -92,7 +92,7 @@ static struct sctp_af *sctp_af_v6_specific; struct kmem_cache *sctp_chunk_cachep __read_mostly; struct kmem_cache *sctp_bucket_cachep __read_mostly; -int sysctl_sctp_mem[3]; +long sysctl_sctp_mem[3]; int sysctl_sctp_rmem[3]; int sysctl_sctp_wmem[3]; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e34ca9c..6bd5543 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -111,12 +111,12 @@ static void sctp_sock_migrate(struct sock *, struct sock *, static char *sctp_hmac_alg = SCTP_COOKIE_HMAC_ALG; extern struct kmem_cache *sctp_bucket_cachep; -extern int sysctl_sctp_mem[3]; +extern long sysctl_sctp_mem[3]; extern int sysctl_sctp_rmem[3]; extern int sysctl_sctp_wmem[3]; static int sctp_memory_pressure; -static atomic_t sctp_memory_allocated; +static atomic_long_t sctp_memory_allocated; struct percpu_counter sctp_sockets_allocated; static void sctp_enter_memory_pressure(struct sock *sk) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 832590b..50cb57f 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -54,7 +54,7 @@ static int sack_timer_max = 500; static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */ static int rwnd_scale_max = 16; -extern int sysctl_sctp_mem[3]; +extern long sysctl_sctp_mem[3]; extern int sysctl_sctp_rmem[3]; extern int sysctl_sctp_wmem[3]; @@ -203,7 +203,7 @@ static ctl_table sctp_table[] = { .data = &sysctl_sctp_mem, .maxlen = sizeof(sysctl_sctp_mem), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_doulongvec_minmax }, { .procname = "sctp_rmem", diff --git a/net/socket.c b/net/socket.c index abf3e25..2808b4d 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1652,6 +1652,8 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, struct iovec iov; int fput_needed; + if (len > INT_MAX) + len = INT_MAX; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -1709,6 +1711,8 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, int err, err2; int fput_needed; + if (size > INT_MAX) + size = INT_MAX; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 33217fc..e9f0d50 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -396,6 +396,7 @@ static int get_name(struct socket *sock, struct sockaddr *uaddr, struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; struct tipc_sock *tsock = tipc_sk(sock->sk); + memset(addr, 0, sizeof(*addr)); if (peer) { if ((sock->state != SS_CONNECTED) && ((peer != 2) || (sock->state != SS_DISCONNECTING))) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c506241..4e78e3f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -224,8 +224,8 @@ static int nl80211_prepare_netdev_dump(struct sk_buff *skb, } *rdev = cfg80211_get_dev_from_ifindex(sock_net(skb->sk), ifidx); - if (IS_ERR(dev)) { - err = PTR_ERR(dev); + if (IS_ERR(*rdev)) { + err = PTR_ERR(*rdev); goto out_rtnl; } diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index 771bab0..3a8c4c4 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -134,15 +134,15 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, case X25_FAC_CLASS_D: switch (*p) { case X25_FAC_CALLING_AE: - if (p[1] > X25_MAX_DTE_FACIL_LEN) - break; + if (p[1] > X25_MAX_DTE_FACIL_LEN || p[1] <= 1) + return 0; dte_facs->calling_len = p[2]; memcpy(dte_facs->calling_ae, &p[3], p[1] - 1); *vc_fac_mask |= X25_MASK_CALLING_AE; break; case X25_FAC_CALLED_AE: - if (p[1] > X25_MAX_DTE_FACIL_LEN) - break; + if (p[1] > X25_MAX_DTE_FACIL_LEN || p[1] <= 1) + return 0; dte_facs->called_len = p[2]; memcpy(dte_facs->called_ae, &p[3], p[1] - 1); *vc_fac_mask |= X25_MASK_CALLED_AE; diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index 6317896..f729f02 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -119,6 +119,8 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp &x25->vc_facil_mask); if (len > 0) skb_pull(skb, len); + else + return -1; /* * Copy any Call User Data. */ |