diff options
Diffstat (limited to 'net')
40 files changed, 611 insertions, 132 deletions
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 476709b..4663c3d 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1557,7 +1557,8 @@ static int hci_dev_do_close(struct hci_dev *hdev) { BT_DBG("%s %p", hdev->name, hdev); - if (!hci_dev_test_flag(hdev, HCI_UNREGISTER)) { + if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) && + test_bit(HCI_UP, &hdev->flags)) { /* Execute vendor specific shutdown routine */ if (hdev->shutdown) hdev->shutdown(hdev); diff --git a/net/core/dev.c b/net/core/dev.c index c7ba038..2c1c67f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5209,7 +5209,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper)) return -EBUSY; - if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper)) + if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper)) return -EEXIST; if (master && netdev_master_upper_dev_get(dev)) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 78fc04a..572af00 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -601,7 +601,7 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh) } err = rtnl_net_fill(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, - RTM_GETNSID, net, peer, -1); + RTM_NEWNSID, net, peer, -1); if (err < 0) goto err_out; diff --git a/net/core/sock.c b/net/core/sock.c index e891bcf..292f422 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1474,8 +1474,8 @@ void sk_release_kernel(struct sock *sk) return; sock_hold(sk); - sock_net_set(sk, get_net(&init_net)); sock_release(sk->sk_socket); + sock_net_set(sk, get_net(&init_net)); sock_put(sk); } EXPORT_SYMBOL(sk_release_kernel); diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile index 05dab29..4adfd4d 100644 --- a/net/ieee802154/Makefile +++ b/net/ieee802154/Makefile @@ -3,7 +3,9 @@ obj-$(CONFIG_IEEE802154_SOCKET) += ieee802154_socket.o obj-y += 6lowpan/ ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o core.o \ - header_ops.o sysfs.o nl802154.o + header_ops.o sysfs.o nl802154.o trace.o ieee802154_socket-y := socket.o +CFLAGS_trace.o := -I$(src) + ccflags-y += -D__CHECK_ENDIAN__ diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index 1b9d25f6..346c666 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -175,6 +175,7 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info) int rc = -ENOBUFS; struct net_device *dev; int type = __IEEE802154_DEV_INVALID; + unsigned char name_assign_type; pr_debug("%s\n", __func__); @@ -190,8 +191,10 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info) if (devname[nla_len(info->attrs[IEEE802154_ATTR_DEV_NAME]) - 1] != '\0') return -EINVAL; /* phy name should be null-terminated */ + name_assign_type = NET_NAME_USER; } else { devname = "wpan%d"; + name_assign_type = NET_NAME_ENUM; } if (strlen(devname) >= IFNAMSIZ) @@ -221,7 +224,7 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info) } dev = rdev_add_virtual_intf_deprecated(wpan_phy_to_rdev(phy), devname, - type); + name_assign_type, type); if (IS_ERR(dev)) { rc = PTR_ERR(dev); goto nla_put_failure; diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index a4daf91..f3c12f6 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -589,7 +589,7 @@ static int nl802154_new_interface(struct sk_buff *skb, struct genl_info *info) return rdev_add_virtual_intf(rdev, nla_data(info->attrs[NL802154_ATTR_IFNAME]), - type, extended_addr); + NET_NAME_USER, type, extended_addr); } static int nl802154_del_interface(struct sk_buff *skb, struct genl_info *info) diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h index 7c46732..7b5a9dd 100644 --- a/net/ieee802154/rdev-ops.h +++ b/net/ieee802154/rdev-ops.h @@ -4,13 +4,16 @@ #include <net/cfg802154.h> #include "core.h" +#include "trace.h" static inline struct net_device * rdev_add_virtual_intf_deprecated(struct cfg802154_registered_device *rdev, - const char *name, int type) + const char *name, + unsigned char name_assign_type, + int type) { return rdev->ops->add_virtual_intf_deprecated(&rdev->wpan_phy, name, - type); + name_assign_type, type); } static inline void @@ -22,75 +25,131 @@ rdev_del_virtual_intf_deprecated(struct cfg802154_registered_device *rdev, static inline int rdev_add_virtual_intf(struct cfg802154_registered_device *rdev, char *name, + unsigned char name_assign_type, enum nl802154_iftype type, __le64 extended_addr) { - return rdev->ops->add_virtual_intf(&rdev->wpan_phy, name, type, + int ret; + + trace_802154_rdev_add_virtual_intf(&rdev->wpan_phy, name, type, extended_addr); + ret = rdev->ops->add_virtual_intf(&rdev->wpan_phy, name, + name_assign_type, type, + extended_addr); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; } static inline int rdev_del_virtual_intf(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev) { - return rdev->ops->del_virtual_intf(&rdev->wpan_phy, wpan_dev); + int ret; + + trace_802154_rdev_del_virtual_intf(&rdev->wpan_phy, wpan_dev); + ret = rdev->ops->del_virtual_intf(&rdev->wpan_phy, wpan_dev); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; } static inline int rdev_set_channel(struct cfg802154_registered_device *rdev, u8 page, u8 channel) { - return rdev->ops->set_channel(&rdev->wpan_phy, page, channel); + int ret; + + trace_802154_rdev_set_channel(&rdev->wpan_phy, page, channel); + ret = rdev->ops->set_channel(&rdev->wpan_phy, page, channel); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; } static inline int rdev_set_cca_mode(struct cfg802154_registered_device *rdev, const struct wpan_phy_cca *cca) { - return rdev->ops->set_cca_mode(&rdev->wpan_phy, cca); + int ret; + + trace_802154_rdev_set_cca_mode(&rdev->wpan_phy, cca); + ret = rdev->ops->set_cca_mode(&rdev->wpan_phy, cca); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; } static inline int rdev_set_pan_id(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, __le16 pan_id) { - return rdev->ops->set_pan_id(&rdev->wpan_phy, wpan_dev, pan_id); + int ret; + + trace_802154_rdev_set_pan_id(&rdev->wpan_phy, wpan_dev, pan_id); + ret = rdev->ops->set_pan_id(&rdev->wpan_phy, wpan_dev, pan_id); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; } static inline int rdev_set_short_addr(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, __le16 short_addr) { - return rdev->ops->set_short_addr(&rdev->wpan_phy, wpan_dev, short_addr); + int ret; + + trace_802154_rdev_set_short_addr(&rdev->wpan_phy, wpan_dev, short_addr); + ret = rdev->ops->set_short_addr(&rdev->wpan_phy, wpan_dev, short_addr); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; } static inline int rdev_set_backoff_exponent(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, u8 min_be, u8 max_be) { - return rdev->ops->set_backoff_exponent(&rdev->wpan_phy, wpan_dev, + int ret; + + trace_802154_rdev_set_backoff_exponent(&rdev->wpan_phy, wpan_dev, min_be, max_be); + ret = rdev->ops->set_backoff_exponent(&rdev->wpan_phy, wpan_dev, + min_be, max_be); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; } static inline int rdev_set_max_csma_backoffs(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, u8 max_csma_backoffs) { - return rdev->ops->set_max_csma_backoffs(&rdev->wpan_phy, wpan_dev, - max_csma_backoffs); + int ret; + + trace_802154_rdev_set_csma_backoffs(&rdev->wpan_phy, wpan_dev, + max_csma_backoffs); + ret = rdev->ops->set_max_csma_backoffs(&rdev->wpan_phy, wpan_dev, + max_csma_backoffs); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; } static inline int rdev_set_max_frame_retries(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, s8 max_frame_retries) { - return rdev->ops->set_max_frame_retries(&rdev->wpan_phy, wpan_dev, + int ret; + + trace_802154_rdev_set_max_frame_retries(&rdev->wpan_phy, wpan_dev, max_frame_retries); + ret = rdev->ops->set_max_frame_retries(&rdev->wpan_phy, wpan_dev, + max_frame_retries); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; } static inline int rdev_set_lbt_mode(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, bool mode) { - return rdev->ops->set_lbt_mode(&rdev->wpan_phy, wpan_dev, mode); + int ret; + + trace_802154_rdev_set_lbt_mode(&rdev->wpan_phy, wpan_dev, mode); + ret = rdev->ops->set_lbt_mode(&rdev->wpan_phy, wpan_dev, mode); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; } #endif /* __CFG802154_RDEV_OPS */ diff --git a/net/ieee802154/trace.c b/net/ieee802154/trace.c new file mode 100644 index 0000000..95f997f --- /dev/null +++ b/net/ieee802154/trace.c @@ -0,0 +1,7 @@ +#include <linux/module.h> + +#ifndef __CHECKER__ +#define CREATE_TRACE_POINTS +#include "trace.h" + +#endif diff --git a/net/ieee802154/trace.h b/net/ieee802154/trace.h new file mode 100644 index 0000000..5ac25eb --- /dev/null +++ b/net/ieee802154/trace.h @@ -0,0 +1,247 @@ +/* Based on net/wireless/tracing.h */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM cfg802154 + +#if !defined(__RDEV_CFG802154_OPS_TRACE) || defined(TRACE_HEADER_MULTI_READ) +#define __RDEV_CFG802154_OPS_TRACE + +#include <linux/tracepoint.h> + +#include <net/cfg802154.h> + +#define MAXNAME 32 +#define WPAN_PHY_ENTRY __array(char, wpan_phy_name, MAXNAME) +#define WPAN_PHY_ASSIGN strlcpy(__entry->wpan_phy_name, \ + wpan_phy_name(wpan_phy), \ + MAXNAME) +#define WPAN_PHY_PR_FMT "%s" +#define WPAN_PHY_PR_ARG __entry->wpan_phy_name + +#define WPAN_DEV_ENTRY __field(u32, identifier) +#define WPAN_DEV_ASSIGN (__entry->identifier) = (!IS_ERR_OR_NULL(wpan_dev) \ + ? wpan_dev->identifier : 0) +#define WPAN_DEV_PR_FMT "wpan_dev(%u)" +#define WPAN_DEV_PR_ARG (__entry->identifier) + +#define WPAN_CCA_ENTRY __field(enum nl802154_cca_modes, cca_mode) \ + __field(enum nl802154_cca_opts, cca_opt) +#define WPAN_CCA_ASSIGN \ + do { \ + (__entry->cca_mode) = cca->mode; \ + (__entry->cca_opt) = cca->opt; \ + } while (0) +#define WPAN_CCA_PR_FMT "cca_mode: %d, cca_opt: %d" +#define WPAN_CCA_PR_ARG __entry->cca_mode, __entry->cca_opt + +#define BOOL_TO_STR(bo) (bo) ? "true" : "false" + +/************************************************************* + * rdev->ops traces * + *************************************************************/ + +TRACE_EVENT(802154_rdev_add_virtual_intf, + TP_PROTO(struct wpan_phy *wpan_phy, char *name, + enum nl802154_iftype type, __le64 extended_addr), + TP_ARGS(wpan_phy, name, type, extended_addr), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + __string(vir_intf_name, name ? name : "<noname>") + __field(enum nl802154_iftype, type) + __field(__le64, extended_addr) + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + __assign_str(vir_intf_name, name ? name : "<noname>"); + __entry->type = type; + __entry->extended_addr = extended_addr; + ), + TP_printk(WPAN_PHY_PR_FMT ", virtual intf name: %s, type: %d, ea %llx", + WPAN_PHY_PR_ARG, __get_str(vir_intf_name), __entry->type, + __le64_to_cpu(__entry->extended_addr)) +); + +TRACE_EVENT(802154_rdev_del_virtual_intf, + TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev), + TP_ARGS(wpan_phy, wpan_dev), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + WPAN_DEV_ENTRY + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + WPAN_DEV_ASSIGN; + ), + TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT, WPAN_PHY_PR_ARG, + WPAN_DEV_PR_ARG) +); + +TRACE_EVENT(802154_rdev_set_channel, + TP_PROTO(struct wpan_phy *wpan_phy, u8 page, u8 channel), + TP_ARGS(wpan_phy, page, channel), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + __field(u8, page) + __field(u8, channel) + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + __entry->page = page; + __entry->channel = channel; + ), + TP_printk(WPAN_PHY_PR_FMT ", page: %d, channel: %d", WPAN_PHY_PR_ARG, + __entry->page, __entry->channel) +); + +TRACE_EVENT(802154_rdev_set_cca_mode, + TP_PROTO(struct wpan_phy *wpan_phy, const struct wpan_phy_cca *cca), + TP_ARGS(wpan_phy, cca), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + WPAN_CCA_ENTRY + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + WPAN_CCA_ASSIGN; + ), + TP_printk(WPAN_PHY_PR_FMT ", " WPAN_CCA_PR_FMT, WPAN_PHY_PR_ARG, + WPAN_CCA_PR_ARG) +); + +DECLARE_EVENT_CLASS(802154_le16_template, + TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + __le16 le16arg), + TP_ARGS(wpan_phy, wpan_dev, le16arg), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + WPAN_DEV_ENTRY + __field(__le16, le16arg) + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + WPAN_DEV_ASSIGN; + __entry->le16arg = le16arg; + ), + TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", pan id: 0x%04x", + WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, + __le16_to_cpu(__entry->le16arg)) +); + +DEFINE_EVENT(802154_le16_template, 802154_rdev_set_pan_id, + TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + __le16 le16arg), + TP_ARGS(wpan_phy, wpan_dev, le16arg) +); + +DEFINE_EVENT_PRINT(802154_le16_template, 802154_rdev_set_short_addr, + TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + __le16 le16arg), + TP_ARGS(wpan_phy, wpan_dev, le16arg), + TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", sa: 0x%04x", + WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, + __le16_to_cpu(__entry->le16arg)) +); + +TRACE_EVENT(802154_rdev_set_backoff_exponent, + TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + u8 min_be, u8 max_be), + TP_ARGS(wpan_phy, wpan_dev, min_be, max_be), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + WPAN_DEV_ENTRY + __field(u8, min_be) + __field(u8, max_be) + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + WPAN_DEV_ASSIGN; + __entry->min_be = min_be; + __entry->max_be = max_be; + ), + + TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT + ", min be: %d, max_be: %d", WPAN_PHY_PR_ARG, + WPAN_DEV_PR_ARG, __entry->min_be, __entry->max_be) +); + +TRACE_EVENT(802154_rdev_set_csma_backoffs, + TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + u8 max_csma_backoffs), + TP_ARGS(wpan_phy, wpan_dev, max_csma_backoffs), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + WPAN_DEV_ENTRY + __field(u8, max_csma_backoffs) + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + WPAN_DEV_ASSIGN; + __entry->max_csma_backoffs = max_csma_backoffs; + ), + + TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT + ", max csma backoffs: %d", WPAN_PHY_PR_ARG, + WPAN_DEV_PR_ARG, __entry->max_csma_backoffs) +); + +TRACE_EVENT(802154_rdev_set_max_frame_retries, + TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + s8 max_frame_retries), + TP_ARGS(wpan_phy, wpan_dev, max_frame_retries), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + WPAN_DEV_ENTRY + __field(s8, max_frame_retries) + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + WPAN_DEV_ASSIGN; + __entry->max_frame_retries = max_frame_retries; + ), + + TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT + ", max frame retries: %d", WPAN_PHY_PR_ARG, + WPAN_DEV_PR_ARG, __entry->max_frame_retries) +); + +TRACE_EVENT(802154_rdev_set_lbt_mode, + TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + bool mode), + TP_ARGS(wpan_phy, wpan_dev, mode), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + WPAN_DEV_ENTRY + __field(bool, mode) + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + WPAN_DEV_ASSIGN; + __entry->mode = mode; + ), + TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT + ", lbt mode: %s", WPAN_PHY_PR_ARG, + WPAN_DEV_PR_ARG, BOOL_TO_STR(__entry->mode)) +); + +TRACE_EVENT(802154_rdev_return_int, + TP_PROTO(struct wpan_phy *wpan_phy, int ret), + TP_ARGS(wpan_phy, ret), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + __field(int, ret) + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + __entry->ret = ret; + ), + TP_printk(WPAN_PHY_PR_FMT ", returned: %d", WPAN_PHY_PR_ARG, + __entry->ret) +); + +#endif /* !__RDEV_CFG802154_OPS_TRACE || TRACE_HEADER_MULTI_READ */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace +#include <trace/define_trace.h> diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index bb77ebd..4d32262 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -224,14 +224,16 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, handler->idiag_get_info(sk, r, info); if (sk->sk_state < TCP_TIME_WAIT) { - int err = 0; + union tcp_cc_info info; + size_t sz = 0; + int attr; rcu_read_lock(); ca_ops = READ_ONCE(icsk->icsk_ca_ops); if (ca_ops && ca_ops->get_info) - err = ca_ops->get_info(sk, ext, skb); + sz = ca_ops->get_info(sk, ext, &attr, &info); rcu_read_unlock(); - if (err < 0) + if (sz && nla_put(skb, attr, sz, &info) < 0) goto errout; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8c5cd9e..46efa03 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -252,6 +252,7 @@ #include <linux/types.h> #include <linux/fcntl.h> #include <linux/poll.h> +#include <linux/inet_diag.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/skbuff.h> @@ -2592,7 +2593,7 @@ EXPORT_SYMBOL(compat_tcp_setsockopt); #endif /* Return information about state of tcp endpoint in API format. */ -void tcp_get_info(const struct sock *sk, struct tcp_info *info) +void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -2663,6 +2664,11 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info) rate = READ_ONCE(sk->sk_max_pacing_rate); info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL; + + spin_lock_bh(&sk->sk_lock.slock); + info->tcpi_bytes_acked = tp->bytes_acked; + info->tcpi_bytes_received = tp->bytes_received; + spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -2734,6 +2740,26 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EFAULT; return 0; } + case TCP_CC_INFO: { + const struct tcp_congestion_ops *ca_ops; + union tcp_cc_info info; + size_t sz = 0; + int attr; + + if (get_user(len, optlen)) + return -EFAULT; + + ca_ops = icsk->icsk_ca_ops; + if (ca_ops && ca_ops->get_info) + sz = ca_ops->get_info(sk, ~0U, &attr, &info); + + len = min_t(unsigned int, len, sz); + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &info, len)) + return -EFAULT; + return 0; + } case TCP_QUICKACK: val = !icsk->icsk_ack.pingpong; break; diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 4376016..4c41c12 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -277,7 +277,8 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) } } -static int dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb) +static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, + union tcp_cc_info *info) { const struct dctcp *ca = inet_csk_ca(sk); @@ -286,18 +287,17 @@ static int dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb) */ if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) || ext & (1 << (INET_DIAG_VEGASINFO - 1))) { - struct tcp_dctcp_info info; - - memset(&info, 0, sizeof(info)); + memset(info, 0, sizeof(struct tcp_dctcp_info)); if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) { - info.dctcp_enabled = 1; - info.dctcp_ce_state = (u16) ca->ce_state; - info.dctcp_alpha = ca->dctcp_alpha; - info.dctcp_ab_ecn = ca->acked_bytes_ecn; - info.dctcp_ab_tot = ca->acked_bytes_total; + info->dctcp.dctcp_enabled = 1; + info->dctcp.dctcp_ce_state = (u16) ca->ce_state; + info->dctcp.dctcp_alpha = ca->dctcp_alpha; + info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn; + info->dctcp.dctcp_ab_tot = ca->acked_bytes_total; } - return nla_put(skb, INET_DIAG_DCTCPINFO, sizeof(info), &info); + *attr = INET_DIAG_DCTCPINFO; + return sizeof(*info); } return 0; } diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index e3d87ac..3c673d5 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -206,6 +206,7 @@ static bool tcp_fastopen_create_child(struct sock *sk, skb_set_owner_r(skb2, child); __skb_queue_tail(&child->sk_receive_queue, skb2); tp->syn_data_acked = 1; + tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1; } else { end_seq = TCP_SKB_CB(skb)->seq + 1; } diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 67476f0..f71002e 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -300,24 +300,25 @@ static u32 tcp_illinois_ssthresh(struct sock *sk) } /* Extract info for Tcp socket info provided via netlink. */ -static int tcp_illinois_info(struct sock *sk, u32 ext, struct sk_buff *skb) +static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr, + union tcp_cc_info *info) { const struct illinois *ca = inet_csk_ca(sk); if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { - struct tcpvegas_info info = { - .tcpv_enabled = 1, - .tcpv_rttcnt = ca->cnt_rtt, - .tcpv_minrtt = ca->base_rtt, - }; + info->vegas.tcpv_enabled = 1; + info->vegas.tcpv_rttcnt = ca->cnt_rtt; + info->vegas.tcpv_minrtt = ca->base_rtt; + info->vegas.tcpv_rtt = 0; - if (info.tcpv_rttcnt > 0) { + if (info->vegas.tcpv_rttcnt > 0) { u64 t = ca->sum_rtt; - do_div(t, info.tcpv_rttcnt); - info.tcpv_rtt = t; + do_div(t, info->vegas.tcpv_rttcnt); + info->vegas.tcpv_rtt = t; } - return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info); + *attr = INET_DIAG_VEGASINFO; + return sizeof(struct tcpvegas_info); } return 0; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3a4d9b34..bc790ea 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1820,14 +1820,12 @@ advance_sp: for (j = 0; j < used_sacks; j++) tp->recv_sack_cache[i++] = sp[j]; - tcp_mark_lost_retrans(sk); - - tcp_verify_left_out(tp); - if ((state.reord < tp->fackets_out) && ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker)) tcp_update_reordering(sk, tp->fackets_out - state.reord, 0); + tcp_mark_lost_retrans(sk); + tcp_verify_left_out(tp); out: #if FASTRETRANS_DEBUG > 0 @@ -3280,6 +3278,24 @@ static inline bool tcp_may_update_window(const struct tcp_sock *tp, (ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd); } +/* If we update tp->snd_una, also update tp->bytes_acked */ +static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack) +{ + u32 delta = ack - tp->snd_una; + + tp->bytes_acked += delta; + tp->snd_una = ack; +} + +/* If we update tp->rcv_nxt, also update tp->bytes_received */ +static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) +{ + u32 delta = seq - tp->rcv_nxt; + + tp->bytes_received += delta; + tp->rcv_nxt = seq; +} + /* Update our send window. * * Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2 @@ -3315,7 +3331,7 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 } } - tp->snd_una = ack; + tcp_snd_una_update(tp, ack); return flag; } @@ -3497,7 +3513,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) * Note, we use the fact that SND.UNA>=SND.WL2. */ tcp_update_wl(tp, ack_seq); - tp->snd_una = ack; + tcp_snd_una_update(tp, ack); flag |= FLAG_WIN_UPDATE; tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE); @@ -4236,7 +4252,7 @@ static void tcp_ofo_queue(struct sock *sk) tail = skb_peek_tail(&sk->sk_receive_queue); eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen); - tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); if (!eaten) __skb_queue_tail(&sk->sk_receive_queue, skb); if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) @@ -4404,7 +4420,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int __skb_pull(skb, hdrlen); eaten = (tail && tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0; - tcp_sk(sk)->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq); if (!eaten) { __skb_queue_tail(&sk->sk_receive_queue, skb); skb_set_owner_r(skb, sk); @@ -4497,7 +4513,7 @@ queue_and_out: eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); } - tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); if (skb->len) tcp_event_data_recv(sk, skb); if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) @@ -5245,7 +5261,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, tcp_rcv_rtt_measure_ts(sk, skb); __skb_pull(skb, tcp_header_len); - tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITSTOUSER); eaten = 1; } diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index c71a1b8..a6cea1d 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -286,18 +286,19 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) } /* Extract info for Tcp socket info provided via netlink. */ -int tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb) +size_t tcp_vegas_get_info(struct sock *sk, u32 ext, int *attr, + union tcp_cc_info *info) { const struct vegas *ca = inet_csk_ca(sk); + if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { - struct tcpvegas_info info = { - .tcpv_enabled = ca->doing_vegas_now, - .tcpv_rttcnt = ca->cntRTT, - .tcpv_rtt = ca->baseRTT, - .tcpv_minrtt = ca->minRTT, - }; - - return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info); + info->vegas.tcpv_enabled = ca->doing_vegas_now, + info->vegas.tcpv_rttcnt = ca->cntRTT, + info->vegas.tcpv_rtt = ca->baseRTT, + info->vegas.tcpv_minrtt = ca->minRTT, + + *attr = INET_DIAG_VEGASINFO; + return sizeof(struct tcpvegas_info); } return 0; } diff --git a/net/ipv4/tcp_vegas.h b/net/ipv4/tcp_vegas.h index e8a6b33..ef9da53 100644 --- a/net/ipv4/tcp_vegas.h +++ b/net/ipv4/tcp_vegas.h @@ -19,6 +19,7 @@ void tcp_vegas_init(struct sock *sk); void tcp_vegas_state(struct sock *sk, u8 ca_state); void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us); void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event); -int tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb); +size_t tcp_vegas_get_info(struct sock *sk, u32 ext, int *attr, + union tcp_cc_info *info); #endif /* __TCP_VEGAS_H */ diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index b3c57cc..c10732e 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -256,18 +256,19 @@ static void tcp_westwood_event(struct sock *sk, enum tcp_ca_event event) } /* Extract info for Tcp socket info provided via netlink. */ -static int tcp_westwood_info(struct sock *sk, u32 ext, struct sk_buff *skb) +static size_t tcp_westwood_info(struct sock *sk, u32 ext, int *attr, + union tcp_cc_info *info) { const struct westwood *ca = inet_csk_ca(sk); if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { - struct tcpvegas_info info = { - .tcpv_enabled = 1, - .tcpv_rtt = jiffies_to_usecs(ca->rtt), - .tcpv_minrtt = jiffies_to_usecs(ca->rtt_min), - }; + info->vegas.tcpv_enabled = 1; + info->vegas.tcpv_rttcnt = 0; + info->vegas.tcpv_rtt = jiffies_to_usecs(ca->rtt), + info->vegas.tcpv_minrtt = jiffies_to_usecs(ca->rtt_min), - return nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info); + *attr = INET_DIAG_VEGASINFO; + return sizeof(struct tcpvegas_info); } return 0; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 7fde1f2..c217775 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -886,22 +886,45 @@ static int ip6_dst_lookup_tail(struct sock *sk, #endif int err; - if (!*dst) - *dst = ip6_route_output(net, sk, fl6); - - err = (*dst)->error; - if (err) - goto out_err_release; + /* The correct way to handle this would be to do + * ip6_route_get_saddr, and then ip6_route_output; however, + * the route-specific preferred source forces the + * ip6_route_output call _before_ ip6_route_get_saddr. + * + * In source specific routing (no src=any default route), + * ip6_route_output will fail given src=any saddr, though, so + * that's why we try it again later. + */ + if (ipv6_addr_any(&fl6->saddr) && (!*dst || !(*dst)->error)) { + struct rt6_info *rt; + bool had_dst = *dst != NULL; - if (ipv6_addr_any(&fl6->saddr)) { - struct rt6_info *rt = (struct rt6_info *) *dst; + if (!had_dst) + *dst = ip6_route_output(net, sk, fl6); + rt = (*dst)->error ? NULL : (struct rt6_info *)*dst; err = ip6_route_get_saddr(net, rt, &fl6->daddr, sk ? inet6_sk(sk)->srcprefs : 0, &fl6->saddr); if (err) goto out_err_release; + + /* If we had an erroneous initial result, pretend it + * never existed and let the SA-enabled version take + * over. + */ + if (!had_dst && (*dst)->error) { + dst_release(*dst); + *dst = NULL; + } } + if (!*dst) + *dst = ip6_route_output(net, sk, fl6); + + err = (*dst)->error; + if (err) + goto out_err_release; + #ifdef CONFIG_IPV6_OPTIMISTIC_DAD /* * Here if the dst entry we've looked up diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 5c48293..d358888 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2245,9 +2245,10 @@ int ip6_route_get_saddr(struct net *net, unsigned int prefs, struct in6_addr *saddr) { - struct inet6_dev *idev = ip6_dst_idev((struct dst_entry *)rt); + struct inet6_dev *idev = + rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL; int err = 0; - if (rt->rt6i_prefsrc.plen) + if (rt && rt->rt6i_prefsrc.plen) *saddr = rt->rt6i_prefsrc.addr; else err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index b4ac596..bab5c63 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -819,13 +819,15 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, * (because if we remove a STA after ops->remove_interface() * the driver will have removed the vif info already!) * - * This is relevant only in WDS mode, in all other modes we've - * already removed all stations when disconnecting or similar, - * so warn otherwise. + * In WDS mode a station must exist here and be flushed, for + * AP_VLANs stations may exist since there's nothing else that + * would have removed them, but in other modes there shouldn't + * be any stations. */ flushed = sta_info_flush(sdata); - WARN_ON_ONCE((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) || - (sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1)); + WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP_VLAN && + ((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) || + (sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1))); /* don't count this interface for promisc/allmulti while it is down */ if (sdata->flags & IEEE80211_SDATA_ALLMULTI) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 12971b7..2880f2a 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -66,6 +66,7 @@ static const struct rhashtable_params sta_rht_params = { .nelem_hint = 3, /* start small */ + .automatic_shrinking = true, .head_offset = offsetof(struct sta_info, hash_node), .key_offset = offsetof(struct sta_info, sta.addr), .key_len = ETH_ALEN, @@ -157,8 +158,24 @@ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata, const u8 *addr) { struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + struct rhash_head *tmp; + const struct bucket_table *tbl; + + rcu_read_lock(); + tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash); - return rhashtable_lookup_fast(&local->sta_hash, addr, sta_rht_params); + for_each_sta_info(local, tbl, addr, sta, tmp) { + if (sta->sdata == sdata) { + rcu_read_unlock(); + /* this is safe as the caller must already hold + * another rcu read section or the mutex + */ + return sta; + } + } + rcu_read_unlock(); + return NULL; } /* diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c index 5d9f68c..70be9c7 100644 --- a/net/mac802154/cfg.c +++ b/net/mac802154/cfg.c @@ -22,13 +22,14 @@ static struct net_device * ieee802154_add_iface_deprecated(struct wpan_phy *wpan_phy, - const char *name, int type) + const char *name, + unsigned char name_assign_type, int type) { struct ieee802154_local *local = wpan_phy_priv(wpan_phy); struct net_device *dev; rtnl_lock(); - dev = ieee802154_if_add(local, name, type, + dev = ieee802154_if_add(local, name, name_assign_type, type, cpu_to_le64(0x0000000000000000ULL)); rtnl_unlock(); @@ -45,12 +46,14 @@ static void ieee802154_del_iface_deprecated(struct wpan_phy *wpan_phy, static int ieee802154_add_iface(struct wpan_phy *phy, const char *name, + unsigned char name_assign_type, enum nl802154_iftype type, __le64 extended_addr) { struct ieee802154_local *local = wpan_phy_priv(phy); struct net_device *err; - err = ieee802154_if_add(local, name, type, extended_addr); + err = ieee802154_if_add(local, name, name_assign_type, type, + extended_addr); return PTR_ERR_OR_ZERO(err); } diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index bebd70f..127ba18 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -182,7 +182,8 @@ void ieee802154_iface_exit(void); void ieee802154_if_remove(struct ieee802154_sub_if_data *sdata); struct net_device * ieee802154_if_add(struct ieee802154_local *local, const char *name, - enum nl802154_iftype type, __le64 extended_addr); + unsigned char name_assign_type, enum nl802154_iftype type, + __le64 extended_addr); void ieee802154_remove_interfaces(struct ieee802154_local *local); #endif /* __IEEE802154_I_H */ diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 38b56f9..91b75ab 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -522,7 +522,8 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, struct net_device * ieee802154_if_add(struct ieee802154_local *local, const char *name, - enum nl802154_iftype type, __le64 extended_addr) + unsigned char name_assign_type, enum nl802154_iftype type, + __le64 extended_addr) { struct net_device *ndev = NULL; struct ieee802154_sub_if_data *sdata = NULL; @@ -531,7 +532,7 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name, ASSERT_RTNL(); ndev = alloc_netdev(sizeof(*sdata) + local->hw.vif_data_size, name, - NET_NAME_UNKNOWN, ieee802154_if_setup); + name_assign_type, ieee802154_if_setup); if (!ndev) return ERR_PTR(-ENOMEM); diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index dcf7395..5b2be12 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -134,7 +134,7 @@ llsec_key_alloc(const struct ieee802154_llsec_key *template) for (i = 0; i < ARRAY_SIZE(key->tfm); i++) { key->tfm[i] = crypto_alloc_aead("ccm(aes)", 0, CRYPTO_ALG_ASYNC); - if (!key->tfm[i]) + if (IS_ERR(key->tfm[i])) goto err_tfm; if (crypto_aead_setkey(key->tfm[i], template->key, IEEE802154_LLSEC_KEY_SIZE)) @@ -144,7 +144,7 @@ llsec_key_alloc(const struct ieee802154_llsec_key *template) } key->tfm0 = crypto_alloc_blkcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC); - if (!key->tfm0) + if (IS_ERR(key->tfm0)) goto err_tfm; if (crypto_blkcipher_setkey(key->tfm0, template->key, diff --git a/net/mac802154/main.c b/net/mac802154/main.c index 8500378..08cb32d 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -161,18 +161,21 @@ int ieee802154_register_hw(struct ieee802154_hw *hw) rtnl_lock(); - dev = ieee802154_if_add(local, "wpan%d", NL802154_IFTYPE_NODE, + dev = ieee802154_if_add(local, "wpan%d", NET_NAME_ENUM, + NL802154_IFTYPE_NODE, cpu_to_le64(0x0000000000000000ULL)); if (IS_ERR(dev)) { rtnl_unlock(); rc = PTR_ERR(dev); - goto out_wq; + goto out_phy; } rtnl_unlock(); return 0; +out_phy: + wpan_phy_unregister(local->phy); out_wq: destroy_workqueue(local->workqueue); out: diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 954810c..7b3f732 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -647,7 +647,7 @@ int nla_get_labels(const struct nlattr *nla, return -EINVAL; switch (dec.label) { - case LABEL_IMPLICIT_NULL: + case MPLS_LABEL_IMPLNULL: /* RFC3032: This is a label that an LSR may * assign and distribute, but which never * actually appears in the encapsulation. @@ -935,7 +935,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) } /* In case the predefined labels need to be populated */ - if (limit > LABEL_IPV4_EXPLICIT_NULL) { + if (limit > MPLS_LABEL_IPV4NULL) { struct net_device *lo = net->loopback_dev; rt0 = mpls_rt_alloc(lo->addr_len); if (!rt0) @@ -945,7 +945,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) rt0->rt_via_table = NEIGH_LINK_TABLE; memcpy(rt0->rt_via, lo->dev_addr, lo->addr_len); } - if (limit > LABEL_IPV6_EXPLICIT_NULL) { + if (limit > MPLS_LABEL_IPV6NULL) { struct net_device *lo = net->loopback_dev; rt2 = mpls_rt_alloc(lo->addr_len); if (!rt2) @@ -973,15 +973,15 @@ static int resize_platform_label_table(struct net *net, size_t limit) memcpy(labels, old, cp_size); /* If needed set the predefined labels */ - if ((old_limit <= LABEL_IPV6_EXPLICIT_NULL) && - (limit > LABEL_IPV6_EXPLICIT_NULL)) { - RCU_INIT_POINTER(labels[LABEL_IPV6_EXPLICIT_NULL], rt2); + if ((old_limit <= MPLS_LABEL_IPV6NULL) && + (limit > MPLS_LABEL_IPV6NULL)) { + RCU_INIT_POINTER(labels[MPLS_LABEL_IPV6NULL], rt2); rt2 = NULL; } - if ((old_limit <= LABEL_IPV4_EXPLICIT_NULL) && - (limit > LABEL_IPV4_EXPLICIT_NULL)) { - RCU_INIT_POINTER(labels[LABEL_IPV4_EXPLICIT_NULL], rt0); + if ((old_limit <= MPLS_LABEL_IPV4NULL) && + (limit > MPLS_LABEL_IPV4NULL)) { + RCU_INIT_POINTER(labels[MPLS_LABEL_IPV4NULL], rt0); rt0 = NULL; } diff --git a/net/mpls/internal.h b/net/mpls/internal.h index 693877d..b064c34 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -1,16 +1,6 @@ #ifndef MPLS_INTERNAL_H #define MPLS_INTERNAL_H -#define LABEL_IPV4_EXPLICIT_NULL 0 /* RFC3032 */ -#define LABEL_ROUTER_ALERT_LABEL 1 /* RFC3032 */ -#define LABEL_IPV6_EXPLICIT_NULL 2 /* RFC3032 */ -#define LABEL_IMPLICIT_NULL 3 /* RFC3032 */ -#define LABEL_ENTROPY_INDICATOR 7 /* RFC6790 */ -#define LABEL_GAL 13 /* RFC5586 */ -#define LABEL_OAM_ALERT 14 /* RFC3429 */ -#define LABEL_EXTENSION 15 /* RFC7274 */ - - struct mpls_shim_hdr { __be32 label_stack_entry; }; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index ec4adbd..daa0b81 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -3139,7 +3139,6 @@ static const struct rhashtable_params netlink_rhashtable_params = { .key_len = netlink_compare_arg_len, .obj_hashfn = netlink_hash, .obj_cmpfn = netlink_compare, - .max_size = 65536, .automatic_shrinking = true, }; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 5102c3c..b5989c6 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2311,11 +2311,14 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) tlen = dev->needed_tailroom; skb = sock_alloc_send_skb(&po->sk, hlen + tlen + sizeof(struct sockaddr_ll), - 0, &err); + !need_wait, &err); - if (unlikely(skb == NULL)) + if (unlikely(skb == NULL)) { + /* we assume the socket was initially writeable ... */ + if (likely(len_sum > 0)) + err = len_sum; goto out_status; - + } tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, addr, hlen); if (tp_len > dev->mtu + dev->hard_header_len) { diff --git a/net/rds/connection.c b/net/rds/connection.c index 14f04139..da6da57 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -126,7 +126,10 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr, struct rds_transport *loop_trans; unsigned long flags; int ret; + struct rds_transport *otrans = trans; + if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP) + goto new_conn; rcu_read_lock(); conn = rds_conn_lookup(head, laddr, faddr, trans); if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport && @@ -142,6 +145,7 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr, if (conn) goto out; +new_conn: conn = kmem_cache_zalloc(rds_conn_slab, gfp); if (!conn) { conn = ERR_PTR(-ENOMEM); @@ -230,13 +234,22 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr, /* Creating normal conn */ struct rds_connection *found; - found = rds_conn_lookup(head, laddr, faddr, trans); + if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP) + found = NULL; + else + found = rds_conn_lookup(head, laddr, faddr, trans); if (found) { trans->conn_free(conn->c_transport_data); kmem_cache_free(rds_conn_slab, conn); conn = found; } else { - hlist_add_head_rcu(&conn->c_hash_node, head); + if ((is_outgoing && otrans->t_type == RDS_TRANS_TCP) || + (otrans->t_type != RDS_TRANS_TCP)) { + /* Only the active side should be added to + * reconnect list for TCP. + */ + hlist_add_head_rcu(&conn->c_hash_node, head); + } rds_cong_add_conn(conn); rds_conn_count++; } diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 31b74f5..8a09ee7 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -183,8 +183,17 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even /* If the peer gave us the last packet it saw, process this as if * we had received a regular ACK. */ - if (dp && dp->dp_ack_seq) - rds_send_drop_acked(conn, be64_to_cpu(dp->dp_ack_seq), NULL); + if (dp) { + /* dp structure start is not guaranteed to be 8 bytes aligned. + * Since dp_ack_seq is 64-bit extended load operations can be + * used so go through get_unaligned to avoid unaligned errors. + */ + __be64 dp_ack_seq = get_unaligned(&dp->dp_ack_seq); + + if (dp_ack_seq) + rds_send_drop_acked(conn, be64_to_cpu(dp_ack_seq), + NULL); + } rds_connect_complete(conn); } diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index f9f564a..973109c7 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -62,6 +62,7 @@ void rds_tcp_state_change(struct sock *sk) case TCP_ESTABLISHED: rds_connect_complete(conn); break; + case TCP_CLOSE_WAIT: case TCP_CLOSE: rds_conn_drop(conn); default: diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 23ab4dcd..0da49e3 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -45,12 +45,45 @@ static void rds_tcp_accept_worker(struct work_struct *work); static DECLARE_WORK(rds_tcp_listen_work, rds_tcp_accept_worker); static struct socket *rds_tcp_listen_sock; +static int rds_tcp_keepalive(struct socket *sock) +{ + /* values below based on xs_udp_default_timeout */ + int keepidle = 5; /* send a probe 'keepidle' secs after last data */ + int keepcnt = 5; /* number of unack'ed probes before declaring dead */ + int keepalive = 1; + int ret = 0; + + ret = kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, + (char *)&keepalive, sizeof(keepalive)); + if (ret < 0) + goto bail; + + ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPCNT, + (char *)&keepcnt, sizeof(keepcnt)); + if (ret < 0) + goto bail; + + ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPIDLE, + (char *)&keepidle, sizeof(keepidle)); + if (ret < 0) + goto bail; + + /* KEEPINTVL is the interval between successive probes. We follow + * the model in xs_tcp_finish_connecting() and re-use keepidle. + */ + ret = kernel_setsockopt(sock, IPPROTO_TCP, TCP_KEEPINTVL, + (char *)&keepidle, sizeof(keepidle)); +bail: + return ret; +} + static int rds_tcp_accept_one(struct socket *sock) { struct socket *new_sock = NULL; struct rds_connection *conn; int ret; struct inet_sock *inet; + struct rds_tcp_connection *rs_tcp; ret = sock_create_lite(sock->sk->sk_family, sock->sk->sk_type, sock->sk->sk_protocol, &new_sock); @@ -63,6 +96,10 @@ static int rds_tcp_accept_one(struct socket *sock) if (ret < 0) goto out; + ret = rds_tcp_keepalive(new_sock); + if (ret < 0) + goto out; + rds_tcp_tune(new_sock); inet = inet_sk(new_sock->sk); @@ -77,6 +114,15 @@ static int rds_tcp_accept_one(struct socket *sock) ret = PTR_ERR(conn); goto out; } + /* An incoming SYN request came in, and TCP just accepted it. + * We always create a new conn for listen side of TCP, and do not + * add it to the c_hash_list. + * + * If the client reboots, this conn will need to be cleaned up. + * rds_tcp_state_change() will do that cleanup + */ + rs_tcp = (struct rds_tcp_connection *)conn->c_transport_data; + WARN_ON(!rs_tcp || rs_tcp->t_sock); /* * see the comment above rds_queue_delayed_reconnect() diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 8b0470e..b6ef9a0 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -308,12 +308,11 @@ replay: case RTM_DELTFILTER: err = tp->ops->delete(tp, fh); if (err == 0) { - tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER); - if (tcf_destroy(tp, false)) { - struct tcf_proto *next = rtnl_dereference(tp->next); + struct tcf_proto *next = rtnl_dereference(tp->next); + tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER); + if (tcf_destroy(tp, false)) RCU_INIT_POINTER(*back, next); - } } goto errout; case RTM_GETTFILTER: diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index de28f8e..7a0bdb1 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -164,7 +164,7 @@ static int codel_init(struct Qdisc *sch, struct nlattr *opt) sch->limit = DEFAULT_CODEL_LIMIT; - codel_params_init(&q->params); + codel_params_init(&q->params, sch); codel_vars_init(&q->vars); codel_stats_init(&q->stats); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 1e52dec..c244c45b 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -391,7 +391,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) q->perturbation = prandom_u32(); INIT_LIST_HEAD(&q->new_flows); INIT_LIST_HEAD(&q->old_flows); - codel_params_init(&q->cparams); + codel_params_init(&q->cparams, sch); codel_stats_init(&q->cstats); q->cparams.ecn = true; diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index a4ca451..634529e 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -229,7 +229,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch) break; } - if (q->backlog + qdisc_pkt_len(skb) <= q->limit) { + if (gred_backlog(t, q, sch) + qdisc_pkt_len(skb) <= q->limit) { q->backlog += qdisc_pkt_len(skb); return qdisc_enqueue_tail(skb, sch); } @@ -553,7 +553,7 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb) opt.limit = q->limit; opt.DP = q->DP; - opt.backlog = q->backlog; + opt.backlog = gred_backlog(table, q, sch); opt.prio = q->prio; opt.qth_min = q->parms.qth_min >> q->parms.Wlog; opt.qth_max = q->parms.qth_max >> q->parms.Wlog; |