diff options
Diffstat (limited to 'net/dccp')
-rw-r--r-- | net/dccp/Kconfig | 6 | ||||
-rw-r--r-- | net/dccp/ackvec.c | 7 | ||||
-rw-r--r-- | net/dccp/ccid.c | 2 | ||||
-rw-r--r-- | net/dccp/ccid.h | 2 | ||||
-rw-r--r-- | net/dccp/ccids/Kconfig | 10 | ||||
-rw-r--r-- | net/dccp/ccids/ccid2.c | 5 | ||||
-rw-r--r-- | net/dccp/ccids/ccid3.c | 10 | ||||
-rw-r--r-- | net/dccp/ccids/ccid3.h | 2 | ||||
-rw-r--r-- | net/dccp/ccids/lib/loss_interval.c | 3 | ||||
-rw-r--r-- | net/dccp/ccids/lib/packet_history.c | 7 | ||||
-rw-r--r-- | net/dccp/ccids/lib/packet_history.h | 2 | ||||
-rw-r--r-- | net/dccp/ccids/lib/tfrc_equation.c | 1 | ||||
-rw-r--r-- | net/dccp/dccp.h | 30 | ||||
-rw-r--r-- | net/dccp/diag.c | 9 | ||||
-rw-r--r-- | net/dccp/feat.c | 17 | ||||
-rw-r--r-- | net/dccp/input.c | 11 | ||||
-rw-r--r-- | net/dccp/ipv4.c | 91 | ||||
-rw-r--r-- | net/dccp/ipv6.c | 80 | ||||
-rw-r--r-- | net/dccp/minisocks.c | 4 | ||||
-rw-r--r-- | net/dccp/options.c | 8 | ||||
-rw-r--r-- | net/dccp/output.c | 17 | ||||
-rw-r--r-- | net/dccp/proto.c | 163 | ||||
-rw-r--r-- | net/dccp/qpolicy.c | 6 | ||||
-rw-r--r-- | net/dccp/timer.c | 17 | ||||
-rw-r--r-- | net/dccp/trace.h | 4 |
25 files changed, 303 insertions, 211 deletions
diff --git a/net/dccp/Kconfig b/net/dccp/Kconfig index f7c7495677b0..0c7d2f66ba27 100644 --- a/net/dccp/Kconfig +++ b/net/dccp/Kconfig @@ -2,10 +2,10 @@ menuconfig IP_DCCP tristate "The DCCP Protocol" depends on INET - ---help--- + help Datagram Congestion Control Protocol (RFC 4340) - From http://www.ietf.org/rfc/rfc4340.txt: + From https://www.ietf.org/rfc/rfc4340.txt: The Datagram Congestion Control Protocol (DCCP) is a transport protocol that implements bidirectional, unicast connections of @@ -32,7 +32,7 @@ menu "DCCP Kernel Hacking" config IP_DCCP_DEBUG bool "DCCP debug messages" - ---help--- + help Only use this if you're hacking DCCP. When compiling DCCP as a module, this debugging output can be toggled diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 0a72510d5de1..c4bbac99740d 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -242,6 +242,8 @@ static void dccp_ackvec_add_new(struct dccp_ackvec *av, u32 num_packets, /** * dccp_ackvec_input - Register incoming packet in the buffer + * @av: Ack Vector to register packet to + * @skb: Packet to register */ void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb) { @@ -273,8 +275,11 @@ void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb) /** * dccp_ackvec_clear_state - Perform house-keeping / garbage-collection + * @av: Ack Vector record to clean + * @ackno: last Ack Vector which has been acknowledged + * * This routine is called when the peer acknowledges the receipt of Ack Vectors - * up to and including @ackno. While based on on section A.3 of RFC 4340, here + * up to and including @ackno. While based on section A.3 of RFC 4340, here * are additional precautions to prevent corrupted buffer state. In particular, * we use tail_ackno to identify outdated records; it always marks the earliest * packet of group (2) in 11.4.2. diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index 1e9bb121ba72..6beac5d348e2 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -76,7 +76,7 @@ int ccid_getsockopt_builtin_ccids(struct sock *sk, int len, return err; } -static struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_fmt, const char *fmt,...) +static __printf(3, 4) struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_fmt, const char *fmt,...) { struct kmem_cache *slab; va_list args; diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 70f88f2b4456..105f3734dadb 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -95,7 +95,7 @@ void ccid_cleanup_builtins(void); struct ccid { struct ccid_operations *ccid_ops; - char ccid_priv[0]; + char ccid_priv[]; }; static inline void *ccid_priv(const struct ccid *ccid) diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig index 4a358e6847a8..a3eeb84d16f9 100644 --- a/net/dccp/ccids/Kconfig +++ b/net/dccp/ccids/Kconfig @@ -3,7 +3,7 @@ menu "DCCP CCIDs Configuration" config IP_DCCP_CCID2_DEBUG bool "CCID-2 debugging messages" - ---help--- + help Enable CCID-2 specific debugging messages. The debugging output can additionally be toggled by setting the @@ -14,7 +14,7 @@ config IP_DCCP_CCID2_DEBUG config IP_DCCP_CCID3 bool "CCID-3 (TCP-Friendly)" def_bool y if (IP_DCCP = y || IP_DCCP = m) - ---help--- + help CCID-3 denotes TCP-Friendly Rate Control (TFRC), an equation-based rate-controlled congestion control mechanism. TFRC is designed to be reasonably fair when competing for bandwidth with TCP-like flows, @@ -26,20 +26,20 @@ config IP_DCCP_CCID3 relatively smooth sending rate is of importance. CCID-3 is further described in RFC 4342, - http://www.ietf.org/rfc/rfc4342.txt + https://www.ietf.org/rfc/rfc4342.txt The TFRC congestion control algorithms were initially described in RFC 5348. This text was extracted from RFC 4340 (sec. 10.2), - http://www.ietf.org/rfc/rfc4340.txt + https://www.ietf.org/rfc/rfc4340.txt If in doubt, say N. config IP_DCCP_CCID3_DEBUG bool "CCID-3 debugging messages" depends on IP_DCCP_CCID3 - ---help--- + help Enable CCID-3 specific debugging messages. The debugging output can additionally be toggled by setting the diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 3da1f77bd039..4d9823d6dced 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -181,6 +181,9 @@ MODULE_PARM_DESC(ccid2_do_cwv, "Perform RFC2861 Congestion Window Validation"); /** * ccid2_update_used_window - Track how much of cwnd is actually used + * @hc: socket to update window + * @new_wnd: new window values to add into the filter + * * This is done in addition to CWV. The sender needs to have an idea of how many * packets may be in flight, to set the local Sequence Window value accordingly * (RFC 4340, 7.5.2). The CWV mechanism is exploited to keep track of the @@ -349,6 +352,8 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len) /** * ccid2_rtt_estimator - Sample RTT and compute RTO using RFC2988 algorithm + * @sk: socket to perform estimator on + * * This code is almost identical with TCP's tcp_rtt_estimator(), since * - it has a higher sampling frequency (recommended by RFC 1323), * - the RTO does not collapse into RTT due to RTTVAR going towards zero, diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 9ef9bee9610f..ca8670f78ac6 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -7,7 +7,7 @@ * An implementation of the DCCP protocol * * This code has been developed by the University of Waikato WAND - * research group. For further information please see http://www.wand.net.nz/ + * research group. For further information please see https://www.wand.net.nz/ * * This code also uses code from Lulea University, rereleased as GPL by its * authors: @@ -79,6 +79,8 @@ static inline u64 rfc3390_initial_rate(struct sock *sk) /** * ccid3_update_send_interval - Calculate new t_ipi = s / X_inst + * @hc: socket to have the send interval updated + * * This respects the granularity of X_inst (64 * bytes/second). */ static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hc) @@ -99,6 +101,7 @@ static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now) /** * ccid3_hc_tx_update_x - Update allowed sending rate X + * @sk: socket to be updated * @stamp: most recent time if available - can be left NULL. * * This function tracks draft rfc3448bis, check there for latest details. @@ -151,6 +154,7 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) /** * ccid3_hc_tx_update_s - Track the mean packet size `s' + * @hc: socket to be updated * @len: DCCP packet payload size in bytes * * cf. RFC 4342, 5.3 and RFC 3448, 4.1 @@ -259,6 +263,7 @@ out: /** * ccid3_hc_tx_send_packet - Delay-based dequeueing of TX packets + * @sk: socket to send packet from * @skb: next packet candidate to send on @sk * * This function uses the convention of ccid_packet_dequeue_eval() and @@ -608,7 +613,7 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, */ if (hc->rx_x_recv > 0) break; - /* fall through */ + fallthrough; case CCID3_FBACK_PERIODIC: delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback); if (delta <= 0) @@ -655,6 +660,7 @@ static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) /** * ccid3_first_li - Implements [RFC 5348, 6.3.1] + * @sk: socket to calculate loss interval for * * Determine the length of the first loss interval via inverse lookup. * Assume that X_recv can be computed by the throughput equation diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h index 081c195e7f7d..02e0fc9f6334 100644 --- a/net/dccp/ccids/ccid3.h +++ b/net/dccp/ccids/ccid3.h @@ -6,7 +6,7 @@ * An implementation of the DCCP protocol * * This code has been developed by the University of Waikato WAND - * research group. For further information please see http://www.wand.net.nz/ + * research group. For further information please see https://www.wand.net.nz/ * or e-mail Ian McDonald - ian.mcdonald@jandi.co.nz * * This code also uses code from Lulea University, rereleased as GPL by its diff --git a/net/dccp/ccids/lib/loss_interval.c b/net/dccp/ccids/lib/loss_interval.c index 67abad695e66..da95319842bb 100644 --- a/net/dccp/ccids/lib/loss_interval.c +++ b/net/dccp/ccids/lib/loss_interval.c @@ -79,6 +79,9 @@ static void tfrc_lh_calc_i_mean(struct tfrc_loss_hist *lh) /** * tfrc_lh_update_i_mean - Update the `open' loss interval I_0 + * @lh: histogram to update + * @skb: received socket triggering loss interval update + * * For recomputing p: returns `true' if p > p_prev <=> 1/p < 1/p_prev */ u8 tfrc_lh_update_i_mean(struct tfrc_loss_hist *lh, struct sk_buff *skb) diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c index 2d41bb036271..0cdda3c66fb5 100644 --- a/net/dccp/ccids/lib/packet_history.c +++ b/net/dccp/ccids/lib/packet_history.c @@ -6,7 +6,7 @@ * An implementation of the DCCP protocol * * This code has been developed by the University of Waikato WAND - * research group. For further information please see http://www.wand.net.nz/ + * research group. For further information please see https://www.wand.net.nz/ * or e-mail Ian McDonald - ian.mcdonald@jandi.co.nz * * This code also uses code from Lulea University, rereleased as GPL by its @@ -365,6 +365,7 @@ void tfrc_rx_hist_purge(struct tfrc_rx_hist *h) /** * tfrc_rx_hist_rtt_last_s - reference entry to compute RTT samples against + * @h: The non-empty RX history object */ static inline struct tfrc_rx_hist_entry * tfrc_rx_hist_rtt_last_s(const struct tfrc_rx_hist *h) @@ -374,6 +375,7 @@ static inline struct tfrc_rx_hist_entry * /** * tfrc_rx_hist_rtt_prev_s - previously suitable (wrt rtt_last_s) RTT-sampling entry + * @h: The non-empty RX history object */ static inline struct tfrc_rx_hist_entry * tfrc_rx_hist_rtt_prev_s(const struct tfrc_rx_hist *h) @@ -383,6 +385,9 @@ static inline struct tfrc_rx_hist_entry * /** * tfrc_rx_hist_sample_rtt - Sample RTT from timestamp / CCVal + * @h: receive histogram + * @skb: packet containing timestamp. + * * Based on ideas presented in RFC 4342, 8.1. Returns 0 if it was not able * to compute a sample with given data - calling function should check this. */ diff --git a/net/dccp/ccids/lib/packet_history.h b/net/dccp/ccids/lib/packet_history.h index a157d874840b..159cc9326eab 100644 --- a/net/dccp/ccids/lib/packet_history.h +++ b/net/dccp/ccids/lib/packet_history.h @@ -6,7 +6,7 @@ * Copyright (c) 2005-6 The University of Waikato, Hamilton, New Zealand. * * This code has been developed by the University of Waikato WAND - * research group. For further information please see http://www.wand.net.nz/ + * research group. For further information please see https://www.wand.net.nz/ * or e-mail Ian McDonald - ian.mcdonald@jandi.co.nz * * This code also uses code from Lulea University, rereleased as GPL by its diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c index e2a337fa9ff7..92a8c6bea316 100644 --- a/net/dccp/ccids/lib/tfrc_equation.c +++ b/net/dccp/ccids/lib/tfrc_equation.c @@ -688,6 +688,7 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) /** * tfrc_invert_loss_event_rate - Compute p so that 10^6 corresponds to 100% + * @loss_event_rate: loss event rate to invert * When @loss_event_rate is large, there is a chance that p is truncated to 0. * To avoid re-entering slow-start in that case, we set p = TFRC_SMALLEST_P > 0. */ diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 9c3b27c257bb..7dfc00c9fb32 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -41,14 +41,14 @@ extern bool dccp_debug; #define dccp_pr_debug_cat(format, a...) DCCP_PRINTK(dccp_debug, format, ##a) #define dccp_debug(fmt, a...) dccp_pr_debug_cat(KERN_DEBUG fmt, ##a) #else -#define dccp_pr_debug(format, a...) -#define dccp_pr_debug_cat(format, a...) -#define dccp_debug(format, a...) +#define dccp_pr_debug(format, a...) do {} while (0) +#define dccp_pr_debug_cat(format, a...) do {} while (0) +#define dccp_debug(format, a...) do {} while (0) #endif extern struct inet_hashinfo dccp_hashinfo; -extern struct percpu_counter dccp_orphan_count; +DECLARE_PER_CPU(unsigned int, dccp_orphan_count); void dccp_time_wait(struct sock *sk, int state, int timeo); @@ -108,11 +108,6 @@ extern int sysctl_dccp_sync_ratelimit; #define ADD48(a, b) (((a) + (b)) & UINT48_MAX) #define SUB48(a, b) ADD48((a), COMPLEMENT48(b)) -static inline void dccp_set_seqno(u64 *seqno, u64 value) -{ - *seqno = value & UINT48_MAX; -} - static inline void dccp_inc_seqno(u64 *seqno) { *seqno = ADD48(*seqno, 1); @@ -141,11 +136,6 @@ static inline int between48(const u64 seq1, const u64 seq2, const u64 seq3) return (seq3 << 16) - (seq2 << 16) >= (seq1 << 16) - (seq2 << 16); } -static inline u64 max48(const u64 seq1, const u64 seq2) -{ - return after48(seq1, seq2) ? seq1 : seq2; -} - /** * dccp_loss_count - Approximate the number of lost data packets in a burst loss * @s1: last known sequence number before the loss ('hole') @@ -300,17 +290,11 @@ int dccp_disconnect(struct sock *sk, int flags); int dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen); -#ifdef CONFIG_COMPAT -int compat_dccp_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen); -int compat_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen); -#endif + sockptr_t optval, unsigned int optlen); int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg); int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); -int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, - int flags, int *addr_len); +int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, + int *addr_len); void dccp_shutdown(struct sock *sk, int how); int inet_dccp_listen(struct socket *sock, int backlog); __poll_t dccp_poll(struct file *file, struct socket *sock, diff --git a/net/dccp/diag.c b/net/dccp/diag.c index 73ef73a218ff..8a82c5a2c5a8 100644 --- a/net/dccp/diag.c +++ b/net/dccp/diag.c @@ -46,16 +46,15 @@ static void dccp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, } static void dccp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, struct nlattr *bc) + const struct inet_diag_req_v2 *r) { - inet_diag_dump_icsk(&dccp_hashinfo, skb, cb, r, bc); + inet_diag_dump_icsk(&dccp_hashinfo, skb, cb, r); } -static int dccp_diag_dump_one(struct sk_buff *in_skb, - const struct nlmsghdr *nlh, +static int dccp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { - return inet_diag_dump_one_icsk(&dccp_hashinfo, in_skb, nlh, req); + return inet_diag_dump_one_icsk(&dccp_hashinfo, cb, req); } static const struct inet_diag_handler dccp_diag_handler = { diff --git a/net/dccp/feat.c b/net/dccp/feat.c index 9c3b5e056234..54086bb05c42 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -165,6 +165,8 @@ static const struct { /** * dccp_feat_index - Hash function to map feature number into array position + * @feat_num: feature to hash, one of %dccp_feature_numbers + * * Returns consecutive array index or -1 if the feature is not understood. */ static int dccp_feat_index(u8 feat_num) @@ -369,7 +371,7 @@ static int dccp_feat_clone_sp_val(dccp_feat_val *fval, u8 const *val, u8 len) fval->sp.vec = kmemdup(val, len, gfp_any()); if (fval->sp.vec == NULL) { fval->sp.len = 0; - return -ENOBUFS; + return -ENOMEM; } } return 0; @@ -567,6 +569,8 @@ cloning_failed: /** * dccp_feat_valid_nn_length - Enforce length constraints on NN options + * @feat_num: feature to return length of, one of %dccp_feature_numbers + * * Length is between 0 and %DCCP_OPTVAL_MAXLEN. Used for outgoing packets only, * incoming options are accepted as long as their values are valid. */ @@ -992,6 +996,8 @@ int dccp_feat_finalise_settings(struct dccp_sock *dp) /** * dccp_feat_server_ccid_dependencies - Resolve CCID-dependent features + * @dreq: server socket to resolve + * * It is the server which resolves the dependencies once the CCID has been * fully negotiated. If no CCID has been negotiated, it uses the default CCID. */ @@ -1029,6 +1035,10 @@ static int dccp_feat_preflist_match(u8 *servlist, u8 slen, u8 *clilist, u8 clen) /** * dccp_feat_prefer - Move preferred entry to the start of array + * @preferred_value: entry to move to start of array + * @array: array of preferred entries + * @array_len: size of the array + * * Reorder the @array_len elements in @array so that @preferred_value comes * first. Returns >0 to indicate that @preferred_value does occur in @array. */ @@ -1403,7 +1413,8 @@ int dccp_feat_parse_options(struct sock *sk, struct dccp_request_sock *dreq, * Negotiation during connection setup */ case DCCP_LISTEN: - server = true; /* fall through */ + server = true; + fallthrough; case DCCP_REQUESTING: switch (opt) { case DCCPO_CHANGE_L: @@ -1429,6 +1440,8 @@ int dccp_feat_parse_options(struct sock *sk, struct dccp_request_sock *dreq, /** * dccp_feat_init - Seed feature negotiation with host-specific defaults + * @sk: Socket to initialize. + * * This initialises global defaults, depending on the value of the sysctls. * These can later be overridden by registering changes via setsockopt calls. * The last link in the chain is finalise_settings, to make sure that between diff --git a/net/dccp/input.c b/net/dccp/input.c index 6dce68a55964..2cbb757a894f 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -64,7 +64,7 @@ static int dccp_rcv_close(struct sock *sk, struct sk_buff *skb) */ if (dccp_sk(sk)->dccps_role != DCCP_ROLE_CLIENT) break; - /* fall through */ + fallthrough; case DCCP_REQUESTING: case DCCP_ACTIVE_CLOSEREQ: dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED); @@ -76,7 +76,7 @@ static int dccp_rcv_close(struct sock *sk, struct sk_buff *skb) queued = 1; dccp_fin(sk, skb); dccp_set_state(sk, DCCP_PASSIVE_CLOSE); - /* fall through */ + fallthrough; case DCCP_PASSIVE_CLOSE: /* * Retransmitted Close: we have already enqueued the first one. @@ -113,7 +113,7 @@ static int dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb) queued = 1; dccp_fin(sk, skb); dccp_set_state(sk, DCCP_PASSIVE_CLOSEREQ); - /* fall through */ + fallthrough; case DCCP_PASSIVE_CLOSEREQ: sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); } @@ -530,7 +530,7 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk, case DCCP_PKT_DATA: if (sk->sk_state == DCCP_RESPOND) break; - /* fall through */ + fallthrough; case DCCP_PKT_DATAACK: case DCCP_PKT_ACK: /* @@ -684,7 +684,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, /* Step 8: if using Ack Vectors, mark packet acknowledgeable */ dccp_handle_ackvec_processing(sk, skb); dccp_deliver_input_to_ccids(sk, skb); - /* fall through */ + fallthrough; case DCCP_RESPOND: queued = dccp_rcv_respond_partopen_state_process(sk, skb, dh, len); @@ -715,6 +715,7 @@ EXPORT_SYMBOL_GPL(dccp_rcv_state_process); /** * dccp_sample_rtt - Validate and finalise computation of RTT sample + * @sk: socket structure * @delta: number of microseconds between packet and acknowledgment * * The routine is kept generic to work in different contexts. It should be diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index d19557c6d04b..713b7b8dad7e 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -23,14 +23,21 @@ #include <net/tcp_states.h> #include <net/xfrm.h> #include <net/secure_seq.h> +#include <net/netns/generic.h> #include "ackvec.h" #include "ccid.h" #include "dccp.h" #include "feat.h" +struct dccp_v4_pernet { + struct sock *v4_ctl_sk; +}; + +static unsigned int dccp_v4_pernet_id __read_mostly; + /* - * The per-net dccp.v4_ctl_sk socket is used for responding to + * The per-net v4_ctl_sk socket is used for responding to * the Out-of-the-blue (OOTB) packets. A control sock will be created * for this socket at the initialization time. */ @@ -38,10 +45,11 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; + struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; + __be32 daddr, nexthop, prev_sk_rcv_saddr; struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); __be16 orig_sport, orig_dport; - __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; @@ -69,9 +77,8 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) orig_dport = usin->sin_port; fl4 = &inet->cork.fl.u.ip4; rt = ip_route_connect(fl4, nexthop, inet->inet_saddr, - RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, - IPPROTO_DCCP, - orig_sport, orig_dport, sk); + sk->sk_bound_dev_if, IPPROTO_DCCP, orig_sport, + orig_dport, sk); if (IS_ERR(rt)) return PTR_ERR(rt); @@ -83,9 +90,29 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (inet_opt == NULL || !inet_opt->opt.srr) daddr = fl4->daddr; - if (inet->inet_saddr == 0) + if (inet->inet_saddr == 0) { + if (inet_csk(sk)->icsk_bind2_hash) { + prev_addr_hashbucket = + inet_bhashfn_portaddr(&dccp_hashinfo, sk, + sock_net(sk), + inet->inet_num); + prev_sk_rcv_saddr = sk->sk_rcv_saddr; + } inet->inet_saddr = fl4->saddr; + } + sk_rcv_saddr_set(sk, inet->inet_saddr); + + if (prev_addr_hashbucket) { + err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + if (err) { + inet->inet_saddr = 0; + sk_rcv_saddr_set(sk, prev_sk_rcv_saddr); + ip_rt_put(rt); + return err; + } + } + inet->inet_dport = usin->sin_port; sk_daddr_set(sk, daddr); @@ -117,7 +144,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, inet->inet_dport); - inet->inet_id = prandom_u32(); + inet->inet_id = get_random_u16(); err = dccp_connect(sk); rt = NULL; @@ -322,7 +349,7 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) __DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); dccp_done(sk); } else @@ -349,7 +376,7 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) inet = inet_sk(sk); if (!sock_owned_by_user(sk) && inet->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else /* Only an error on timeout */ sk->sk_err_soft = err; out: @@ -416,7 +443,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - newinet->inet_id = prandom_u32(); + newinet->inet_id = get_random_u16(); if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) goto put_and_exit; @@ -427,7 +454,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); if (*own_req) ireq->ireq_opt = NULL; else @@ -464,7 +491,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, .fl4_dport = dccp_hdr(skb)->dccph_sport, }; - security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); + security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) { IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); @@ -495,7 +522,8 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - rcu_dereference(ireq->ireq_opt)); + rcu_dereference(ireq->ireq_opt), + inet_sk(sk)->tos); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -512,7 +540,8 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) struct sk_buff *skb; struct dst_entry *dst; struct net *net = dev_net(skb_dst(rxskb)->dev); - struct sock *ctl_sk = net->dccp.v4_ctl_sk; + struct dccp_v4_pernet *pn; + struct sock *ctl_sk; /* Never send a reset in response to a reset. */ if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET) @@ -521,6 +550,8 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) if (skb_rtable(rxskb)->rt_type != RTN_LOCAL) return; + pn = net_generic(net, dccp_v4_pernet_id); + ctl_sk = pn->v4_ctl_sk; dst = dccp_v4_route_skb(net, ctl_sk, rxskb); if (dst == NULL) return; @@ -537,7 +568,8 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) local_bh_disable(); bh_lock_sock(ctl_sk); err = ip_build_and_send_pkt(skb, ctl_sk, - rxiph->daddr, rxiph->saddr, NULL); + rxiph->daddr, rxiph->saddr, NULL, + inet_sk(ctl_sk)->tos); bh_unlock_sock(ctl_sk); if (net_xmit_eval(err) == 0) { @@ -617,7 +649,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); ireq->ir_mark = inet_request_mark(sk, skb); ireq->ireq_family = AF_INET; - ireq->ir_iif = sk->sk_bound_dev_if; + ireq->ir_iif = READ_ONCE(sk->sk_bound_dev_if); /* * Step 3: Process LISTEN state @@ -694,6 +726,8 @@ EXPORT_SYMBOL_GPL(dccp_v4_do_rcv); /** * dccp_invalid_packet - check for malformed packets + * @skb: Packet to validate + * * Implements RFC 4340, 8.5: Step 1: Check header basics * Packets that fail these checks are ignored and do not receive Resets. */ @@ -729,7 +763,7 @@ int dccp_invalid_packet(struct sk_buff *skb) return 1; } /* - * If P.Data Offset is too too large for packet, drop packet and return + * If P.Data Offset is too large for packet, drop packet and return */ if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) { DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff); @@ -911,10 +945,6 @@ static const struct inet_connection_sock_af_ops dccp_ipv4_af_ops = { .getsockopt = ip_getsockopt, .addr2sockaddr = inet_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in), -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_ip_setsockopt, - .compat_getsockopt = compat_ip_getsockopt, -#endif }; static int dccp_v4_init_sock(struct sock *sk) @@ -961,17 +991,12 @@ static struct proto dccp_v4_prot = { .rsk_prot = &dccp_request_sock_ops, .twsk_prot = &dccp_timewait_sock_ops, .h.hashinfo = &dccp_hashinfo, -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_dccp_setsockopt, - .compat_getsockopt = compat_dccp_getsockopt, -#endif }; static const struct net_protocol dccp_v4_protocol = { .handler = dccp_v4_rcv, .err_handler = dccp_v4_err, .no_policy = 1, - .netns_ok = 1, .icmp_strict_tag_validation = 1, }; @@ -997,10 +1022,6 @@ static const struct proto_ops inet_dccp_ops = { .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_sock_common_setsockopt, - .compat_getsockopt = compat_sock_common_getsockopt, -#endif }; static struct inet_protosw dccp_v4_protosw = { @@ -1013,16 +1034,20 @@ static struct inet_protosw dccp_v4_protosw = { static int __net_init dccp_v4_init_net(struct net *net) { + struct dccp_v4_pernet *pn = net_generic(net, dccp_v4_pernet_id); + if (dccp_hashinfo.bhash == NULL) return -ESOCKTNOSUPPORT; - return inet_ctl_sock_create(&net->dccp.v4_ctl_sk, PF_INET, + return inet_ctl_sock_create(&pn->v4_ctl_sk, PF_INET, SOCK_DCCP, IPPROTO_DCCP, net); } static void __net_exit dccp_v4_exit_net(struct net *net) { - inet_ctl_sock_destroy(net->dccp.v4_ctl_sk); + struct dccp_v4_pernet *pn = net_generic(net, dccp_v4_pernet_id); + + inet_ctl_sock_destroy(pn->v4_ctl_sk); } static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list) @@ -1034,6 +1059,8 @@ static struct pernet_operations dccp_v4_ops = { .init = dccp_v4_init_net, .exit = dccp_v4_exit_net, .exit_batch = dccp_v4_exit_batch, + .id = &dccp_v4_pernet_id, + .size = sizeof(struct dccp_v4_pernet), }; static int __init dccp_v4_init(void) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 1e5e08cc0bfc..e57b43006074 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -27,13 +27,20 @@ #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/secure_seq.h> +#include <net/netns/generic.h> #include <net/sock.h> #include "dccp.h" #include "ipv6.h" #include "feat.h" -/* The per-net dccp.v6_ctl_sk is used for sending RSTs and ACKs */ +struct dccp_v6_pernet { + struct sock *v6_ctl_sk; +}; + +static unsigned int dccp_v6_pernet_id __read_mostly; + +/* The per-net v6_ctl_sk is used for sending RSTs and ACKs */ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped; static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops; @@ -165,7 +172,7 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, * Wake people up to see the error * (see connect in sock.c) */ - sk->sk_error_report(sk); + sk_error_report(sk); dccp_done(sk); } else sk->sk_err_soft = err; @@ -174,7 +181,7 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else sk->sk_err_soft = err; @@ -203,7 +210,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req fl6.flowi6_oif = ireq->ir_iif; fl6.fl6_dport = ireq->ir_rmt_port; fl6.fl6_sport = htons(ireq->ir_num); - security_req_classify_flow(req, flowi6_to_flowi(&fl6)); + security_req_classify_flow(req, flowi6_to_flowi_common(&fl6)); rcu_read_lock(); @@ -254,7 +261,8 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) struct sk_buff *skb; struct flowi6 fl6; struct net *net = dev_net(skb_dst(rxskb)->dev); - struct sock *ctl_sk = net->dccp.v6_ctl_sk; + struct dccp_v6_pernet *pn; + struct sock *ctl_sk; struct dst_entry *dst; if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET) @@ -263,6 +271,8 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) if (!ipv6_unicast_destination(rxskb)) return; + pn = net_generic(net, dccp_v6_pernet_id); + ctl_sk = pn->v6_ctl_sk; skb = dccp_ctl_make_reset(ctl_sk, rxskb); if (skb == NULL) return; @@ -279,7 +289,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) fl6.flowi6_oif = inet6_iif(rxskb); fl6.fl6_dport = dccp_hdr(skb)->dccph_dport; fl6.fl6_sport = dccp_hdr(skb)->dccph_sport; - security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6)); + security_skb_classify_flow(rxskb, flowi6_to_flowi_common(&fl6)); /* sk = NULL, but it is safe for now. RST socket required. */ dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); @@ -319,6 +329,11 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) return 0; /* discard, don't send a reset here */ + if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { + __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); + return 0; + } + if (dccp_bad_service_code(sk, service)) { dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE; goto drop; @@ -359,10 +374,10 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) refcount_inc(&skb->users); ireq->pktopts = skb; } - ireq->ir_iif = sk->sk_bound_dev_if; + ireq->ir_iif = READ_ONCE(sk->sk_bound_dev_if); /* So that link locals have meaning */ - if (!sk->sk_bound_dev_if && + if (!ireq->ir_iif && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = inet6_iif(skb); @@ -533,7 +548,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, dccp_done(newsk); goto out; } - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); /* Clone pktoptions received with SYN, if we own the req */ if (*own_req && ireq->pktopts) { newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC); @@ -877,7 +892,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, SOCK_DEBUG(sk, "connect: ipv4 mapped\n"); - if (__ipv6_only_sock(sk)) + if (ipv6_only_sock(sk)) return -ENETUNREACH; sin.sin_family = AF_INET; @@ -907,7 +922,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.fl6_dport = usin->sin6_port; fl6.fl6_sport = inet->inet_sport; - security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(&fl6, opt, &final); @@ -919,8 +934,26 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, } if (saddr == NULL) { + struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; + struct in6_addr prev_v6_rcv_saddr; + + if (icsk->icsk_bind2_hash) { + prev_addr_hashbucket = inet_bhashfn_portaddr(&dccp_hashinfo, + sk, sock_net(sk), + inet->inet_num); + prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr; + } + saddr = &fl6.saddr; sk->sk_v6_rcv_saddr = *saddr; + + if (prev_addr_hashbucket) { + err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + if (err) { + sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr; + goto failure; + } + } } /* set the source address */ @@ -970,10 +1003,6 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6), -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_ipv6_setsockopt, - .compat_getsockopt = compat_ipv6_getsockopt, -#endif }; /* @@ -990,10 +1019,6 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = { .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6), -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_ipv6_setsockopt, - .compat_getsockopt = compat_ipv6_getsockopt, -#endif }; /* NOTE: A lot of things set to zero explicitly by call to @@ -1049,10 +1074,6 @@ static struct proto dccp_v6_prot = { .rsk_prot = &dccp6_request_sock_ops, .twsk_prot = &dccp6_timewait_sock_ops, .h.hashinfo = &dccp_hashinfo, -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_dccp_setsockopt, - .compat_getsockopt = compat_dccp_getsockopt, -#endif }; static const struct inet6_protocol dccp_v6_protocol = { @@ -1082,8 +1103,7 @@ static const struct proto_ops inet6_dccp_ops = { .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, #ifdef CONFIG_COMPAT - .compat_setsockopt = compat_sock_common_setsockopt, - .compat_getsockopt = compat_sock_common_getsockopt, + .compat_ioctl = inet6_compat_ioctl, #endif }; @@ -1097,16 +1117,20 @@ static struct inet_protosw dccp_v6_protosw = { static int __net_init dccp_v6_init_net(struct net *net) { + struct dccp_v6_pernet *pn = net_generic(net, dccp_v6_pernet_id); + if (dccp_hashinfo.bhash == NULL) return -ESOCKTNOSUPPORT; - return inet_ctl_sock_create(&net->dccp.v6_ctl_sk, PF_INET6, + return inet_ctl_sock_create(&pn->v6_ctl_sk, PF_INET6, SOCK_DCCP, IPPROTO_DCCP, net); } static void __net_exit dccp_v6_exit_net(struct net *net) { - inet_ctl_sock_destroy(net->dccp.v6_ctl_sk); + struct dccp_v6_pernet *pn = net_generic(net, dccp_v6_pernet_id); + + inet_ctl_sock_destroy(pn->v6_ctl_sk); } static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list) @@ -1118,6 +1142,8 @@ static struct pernet_operations dccp_v6_ops = { .init = dccp_v6_init_net, .exit = dccp_v6_exit_net, .exit_batch = dccp_v6_exit_batch, + .id = &dccp_v6_pernet_id, + .size = sizeof(struct dccp_v6_pernet), }; static int __init dccp_v6_init(void) diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 25187528c308..64d805b27add 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -22,6 +22,7 @@ #include "feat.h" struct inet_timewait_death_row dccp_death_row = { + .tw_refcount = REFCOUNT_INIT(1), .sysctl_max_tw_buckets = NR_FILE * 2, .hashinfo = &dccp_hashinfo, }; @@ -94,6 +95,8 @@ struct sock *dccp_create_openreq_child(const struct sock *sk, newdp->dccps_role = DCCP_ROLE_SERVER; newdp->dccps_hc_rx_ackvec = NULL; newdp->dccps_service_list = NULL; + newdp->dccps_hc_rx_ccid = NULL; + newdp->dccps_hc_tx_ccid = NULL; newdp->dccps_service = dreq->dreq_service; newdp->dccps_timestamp_echo = dreq->dreq_timestamp_echo; newdp->dccps_timestamp_time = dreq->dreq_timestamp_time; @@ -216,6 +219,7 @@ EXPORT_SYMBOL_GPL(dccp_check_req); */ int dccp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb) + __releases(child) { int ret = 0; const int state = child->sk_state; diff --git a/net/dccp/options.c b/net/dccp/options.c index 3b42f5c6a63d..d24cad05001e 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -43,6 +43,7 @@ u64 dccp_decode_value_var(const u8 *bf, const u8 len) * dccp_parse_options - Parse DCCP options present in @skb * @sk: client|server|listening dccp socket (when @dreq != NULL) * @dreq: request socket to use during connection setup, or NULL + * @skb: frame to parse */ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, struct sk_buff *skb) @@ -56,7 +57,7 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, (dh->dccph_doff * 4); struct dccp_options_received *opt_recv = &dp->dccps_options_received; unsigned char opt, len; - unsigned char *uninitialized_var(value); + unsigned char *value; u32 elapsed_time; __be32 opt_val; int rc; @@ -224,7 +225,7 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, * interested. The RX CCID need not parse Ack Vectors, * since it is only interested in clearing old state. */ - /* fall through */ + fallthrough; case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC: if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk, pkt_type, opt, value, len)) @@ -471,6 +472,8 @@ static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) /** * dccp_insert_option_mandatory - Mandatory option (5.8.2) + * @skb: frame into which to insert option + * * Note that since we are using skb_push, this function needs to be called * _after_ inserting the option it is supposed to influence (stack order). */ @@ -486,6 +489,7 @@ int dccp_insert_option_mandatory(struct sk_buff *skb) /** * dccp_insert_fn_opt - Insert single Feature-Negotiation option into @skb + * @skb: frame to insert feature negotiation option into * @type: %DCCPO_CHANGE_L, %DCCPO_CHANGE_R, %DCCPO_CONFIRM_L, %DCCPO_CONFIRM_R * @feat: one out of %dccp_feature_numbers * @val: NN value or SP array (preferred element first) to copy diff --git a/net/dccp/output.c b/net/dccp/output.c index 6433187a5cc4..b8a24734385e 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -62,7 +62,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) switch (dcb->dccpd_type) { case DCCP_PKT_DATA: set_ack = 0; - /* fall through */ + fallthrough; case DCCP_PKT_DATAACK: case DCCP_PKT_RESET: break; @@ -72,12 +72,12 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) /* Use ISS on the first (non-retransmitted) Request. */ if (icsk->icsk_retransmits == 0) dcb->dccpd_seq = dp->dccps_iss; - /* fall through */ + fallthrough; case DCCP_PKT_SYNC: case DCCP_PKT_SYNCACK: ackno = dcb->dccpd_ack_seq; - /* fall through */ + fallthrough; default: /* * Set owner/destructor: some skbs are allocated via @@ -143,6 +143,8 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) /** * dccp_determine_ccmps - Find out about CCID-specific packet-size limits + * @dp: socket to find packet size limits of + * * We only consider the HC-sender CCID for setting the CCMPS (RFC 4340, 14.), * since the RX CCID is restricted to feedback packets (Acks), which are small * in comparison with the data traffic. A value of 0 means "no current CCMPS". @@ -236,6 +238,8 @@ static int dccp_wait_for_ccid(struct sock *sk, unsigned long delay) /** * dccp_xmit_packet - Send data packet under control of CCID + * @sk: socket to send data packet on + * * Transmits next-queued payload and informs CCID to account for the packet. */ static void dccp_xmit_packet(struct sock *sk) @@ -296,6 +300,9 @@ static void dccp_xmit_packet(struct sock *sk) /** * dccp_flush_write_queue - Drain queue at end of connection + * @sk: socket to be drained + * @time_budget: time allowed to drain the queue + * * 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 @@ -367,6 +374,8 @@ void dccp_write_xmit(struct sock *sk) /** * dccp_retransmit_skb - Retransmit Request, Close, or CloseReq packets + * @sk: socket to perform retransmit on + * * There are only four retransmittable packet types in DCCP: * - Request in client-REQUEST state (sec. 8.1.1), * - CloseReq in server-CLOSEREQ state (sec. 8.3), @@ -481,7 +490,7 @@ struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *rcv_skb) case DCCP_RESET_CODE_PACKET_ERROR: dhr->dccph_reset_data[0] = rxdh->dccph_type; break; - case DCCP_RESET_CODE_OPTION_ERROR: /* fall through */ + case DCCP_RESET_CODE_OPTION_ERROR: case DCCP_RESET_CODE_MANDATORY_ERROR: memcpy(dhr->dccph_reset_data, dcb->dccpd_reset_data, 3); break; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 4af8a98fe784..c548ca3e9b0e 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -42,8 +42,8 @@ DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly; EXPORT_SYMBOL_GPL(dccp_statistics); -struct percpu_counter dccp_orphan_count; -EXPORT_SYMBOL_GPL(dccp_orphan_count); +DEFINE_PER_CPU(unsigned int, dccp_orphan_count); +EXPORT_PER_CPU_SYMBOL_GPL(dccp_orphan_count); struct inet_hashinfo dccp_hashinfo; EXPORT_SYMBOL_GPL(dccp_hashinfo); @@ -101,7 +101,7 @@ void dccp_set_state(struct sock *sk, const int state) if (inet_csk(sk)->icsk_bind_hash != NULL && !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) inet_put_port(sk); - /* fall through */ + fallthrough; default: if (oldstate == DCCP_OPEN) DCCP_DEC_STATS(DCCP_MIB_CURRESTAB); @@ -238,17 +238,6 @@ void dccp_destroy_sock(struct sock *sk) EXPORT_SYMBOL_GPL(dccp_destroy_sock); -static inline int dccp_listen_start(struct sock *sk, int backlog) -{ - struct dccp_sock *dp = dccp_sk(sk); - - dp->dccps_role = DCCP_ROLE_LISTEN; - /* do not start to listen if feature negotiation setup fails */ - if (dccp_feat_finalise_settings(dp)) - return -EPROTO; - return inet_csk_listen_start(sk, backlog); -} - static inline int dccp_need_reset(int state) { return state != DCCP_CLOSED && state != DCCP_LISTEN && @@ -302,7 +291,7 @@ int dccp_disconnect(struct sock *sk, int flags) WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); - sk->sk_error_report(sk); + sk_error_report(sk); return 0; } @@ -375,6 +364,15 @@ int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg) goto out; switch (cmd) { + case SIOCOUTQ: { + int amount = sk_wmem_alloc_get(sk); + /* Using sk_wmem_alloc here because sk_wmem_queued is not used by DCCP and + * always 0, comparably to UDP. + */ + + rc = put_user(amount, (int __user *)arg); + } + break; case SIOCINQ: { struct sk_buff *skb; unsigned long amount = 0; @@ -402,7 +400,7 @@ out: EXPORT_SYMBOL_GPL(dccp_ioctl); static int dccp_setsockopt_service(struct sock *sk, const __be32 service, - char __user *optval, unsigned int optlen) + sockptr_t optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_service_list *sl = NULL; @@ -417,9 +415,8 @@ static int dccp_setsockopt_service(struct sock *sk, const __be32 service, return -ENOMEM; sl->dccpsl_nr = optlen / sizeof(u32) - 1; - if (copy_from_user(sl->dccpsl_list, - optval + sizeof(service), - optlen - sizeof(service)) || + if (copy_from_sockptr_offset(sl->dccpsl_list, optval, + sizeof(service), optlen - sizeof(service)) || dccp_list_has_service(sl, DCCP_SERVICE_INVALID_VALUE)) { kfree(sl); return -EFAULT; @@ -473,7 +470,7 @@ static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx) } static int dccp_setsockopt_ccid(struct sock *sk, int type, - char __user *optval, unsigned int optlen) + sockptr_t optval, unsigned int optlen) { u8 *val; int rc = 0; @@ -481,7 +478,7 @@ static int dccp_setsockopt_ccid(struct sock *sk, int type, if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS) return -EINVAL; - val = memdup_user(optval, optlen); + val = memdup_sockptr(optval, optlen); if (IS_ERR(val)) return PTR_ERR(val); @@ -498,7 +495,7 @@ static int dccp_setsockopt_ccid(struct sock *sk, int type, } static int do_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) + sockptr_t optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); int val, err = 0; @@ -520,7 +517,7 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname, if (optlen < (int)sizeof(int)) return -EINVAL; - if (get_user(val, (int __user *)optval)) + if (copy_from_sockptr(&val, optval, sizeof(int))) return -EFAULT; if (optname == DCCP_SOCKOPT_SERVICE) @@ -563,8 +560,8 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname, return err; } -int dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) +int dccp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, + unsigned int optlen) { if (level != SOL_DCCP) return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level, @@ -575,19 +572,6 @@ int dccp_setsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL_GPL(dccp_setsockopt); -#ifdef CONFIG_COMPAT -int compat_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) -{ - if (level != SOL_DCCP) - return inet_csk_compat_setsockopt(sk, level, optname, - optval, optlen); - return do_dccp_setsockopt(sk, level, optname, optval, optlen); -} - -EXPORT_SYMBOL_GPL(compat_dccp_setsockopt); -#endif - static int dccp_getsockopt_service(struct sock *sk, int len, __be32 __user *optval, int __user *optlen) @@ -696,19 +680,6 @@ int dccp_getsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL_GPL(dccp_getsockopt); -#ifdef CONFIG_COMPAT -int compat_dccp_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) -{ - if (level != SOL_DCCP) - return inet_csk_compat_getsockopt(sk, level, optname, - optval, optlen); - return do_dccp_getsockopt(sk, level, optname, optval, optlen); -} - -EXPORT_SYMBOL_GPL(compat_dccp_getsockopt); -#endif - static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb) { struct cmsghdr *cmsg; @@ -765,11 +736,6 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) lock_sock(sk); - if (dccp_qpolicy_full(sk)) { - rc = -EAGAIN; - goto out_release; - } - timeo = sock_sndtimeo(sk, noblock); /* @@ -788,6 +754,11 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (skb == NULL) goto out_release; + if (dccp_qpolicy_full(sk)) { + rc = -EAGAIN; + goto out_discard; + } + if (sk->sk_state == DCCP_CLOSED) { rc = -ENOTCONN; goto out_discard; @@ -820,8 +791,8 @@ out_discard: EXPORT_SYMBOL_GPL(dccp_sendmsg); -int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, - int flags, int *addr_len) +int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, + int *addr_len) { const struct dccp_hdr *dh; long timeo; @@ -833,7 +804,7 @@ int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, goto out; } - timeo = sock_rcvtimeo(sk, nonblock); + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); @@ -852,7 +823,7 @@ int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, case DCCP_PKT_CLOSEREQ: if (!(flags & MSG_PEEK)) dccp_finish_passive_close(sk); - /* fall through */ + fallthrough; case DCCP_PKT_RESET: dccp_pr_debug("found fin (%s) ok!\n", dccp_packet_name(dh->dccph_type)); @@ -949,11 +920,17 @@ int inet_dccp_listen(struct socket *sock, int backlog) * we can only allow the backlog to be adjusted. */ if (old_state != DCCP_LISTEN) { - /* - * FIXME: here it probably should be sk->sk_prot->listen_start - * see tcp_listen_start - */ - err = dccp_listen_start(sk, backlog); + struct dccp_sock *dp = dccp_sk(sk); + + dp->dccps_role = DCCP_ROLE_LISTEN; + + /* do not start to listen if feature negotiation setup fails */ + if (dccp_feat_finalise_settings(dp)) { + err = -EPROTO; + goto out; + } + + err = inet_csk_listen_start(sk); if (err) goto out; } @@ -978,7 +955,7 @@ static void dccp_terminate_connection(struct sock *sk) case DCCP_PARTOPEN: dccp_pr_debug("Stop PARTOPEN timer (%p)\n", sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); - /* fall through */ + fallthrough; case DCCP_OPEN: dccp_send_close(sk, 1); @@ -987,7 +964,7 @@ static void dccp_terminate_connection(struct sock *sk) next_state = DCCP_ACTIVE_CLOSEREQ; else next_state = DCCP_CLOSING; - /* fall through */ + fallthrough; default: dccp_set_state(sk, next_state); } @@ -1073,7 +1050,7 @@ adjudge_to_death: bh_lock_sock(sk); WARN_ON(sock_owned_by_user(sk)); - percpu_counter_inc(sk->sk_prot->orphan_count); + this_cpu_inc(dccp_orphan_count); /* Have we already been destroyed by a softirq or backlog? */ if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED) @@ -1133,10 +1110,6 @@ static int __init dccp_init(void) BUILD_BUG_ON(sizeof(struct dccp_skb_cb) > sizeof_field(struct sk_buff, cb)); - rc = percpu_counter_init(&dccp_orphan_count, 0, GFP_KERNEL); - if (rc) - goto out_fail; - inet_hashinfo_init(&dccp_hashinfo); rc = inet_hashinfo2_init_mod(&dccp_hashinfo); if (rc) goto out_fail; @@ -1144,9 +1117,15 @@ static int __init dccp_init(void) dccp_hashinfo.bind_bucket_cachep = kmem_cache_create("dccp_bind_bucket", sizeof(struct inet_bind_bucket), 0, - SLAB_HWCACHE_ALIGN, NULL); + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!dccp_hashinfo.bind_bucket_cachep) - goto out_free_percpu; + goto out_free_hashinfo2; + dccp_hashinfo.bind2_bucket_cachep = + kmem_cache_create("dccp_bind2_bucket", + sizeof(struct inet_bind2_bucket), 0, + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); + if (!dccp_hashinfo.bind2_bucket_cachep) + goto out_free_bind_bucket_cachep; /* * Size and allocate the main established and bind bucket @@ -1177,7 +1156,7 @@ static int __init dccp_init(void) if (!dccp_hashinfo.ehash) { DCCP_CRIT("Failed to allocate DCCP established hash table"); - goto out_free_bind_bucket_cachep; + goto out_free_bind2_bucket_cachep; } for (i = 0; i <= dccp_hashinfo.ehash_mask; i++) @@ -1203,14 +1182,26 @@ static int __init dccp_init(void) goto out_free_dccp_locks; } + dccp_hashinfo.bhash2 = (struct inet_bind_hashbucket *) + __get_free_pages(GFP_ATOMIC | __GFP_NOWARN, bhash_order); + + if (!dccp_hashinfo.bhash2) { + DCCP_CRIT("Failed to allocate DCCP bind2 hash table"); + goto out_free_dccp_bhash; + } + for (i = 0; i < dccp_hashinfo.bhash_size; i++) { spin_lock_init(&dccp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain); + spin_lock_init(&dccp_hashinfo.bhash2[i].lock); + INIT_HLIST_HEAD(&dccp_hashinfo.bhash2[i].chain); } + dccp_hashinfo.pernet = false; + rc = dccp_mib_init(); if (rc) - goto out_free_dccp_bhash; + goto out_free_dccp_bhash2; rc = dccp_ackvec_init(); if (rc) @@ -1234,30 +1225,38 @@ out_ackvec_exit: dccp_ackvec_exit(); out_free_dccp_mib: dccp_mib_exit(); +out_free_dccp_bhash2: + free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order); out_free_dccp_bhash: free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); out_free_dccp_locks: inet_ehash_locks_free(&dccp_hashinfo); out_free_dccp_ehash: free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order); +out_free_bind2_bucket_cachep: + kmem_cache_destroy(dccp_hashinfo.bind2_bucket_cachep); out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); -out_free_percpu: - percpu_counter_destroy(&dccp_orphan_count); +out_free_hashinfo2: + inet_hashinfo2_free_mod(&dccp_hashinfo); out_fail: dccp_hashinfo.bhash = NULL; + dccp_hashinfo.bhash2 = NULL; dccp_hashinfo.ehash = NULL; dccp_hashinfo.bind_bucket_cachep = NULL; + dccp_hashinfo.bind2_bucket_cachep = NULL; return rc; } static void __exit dccp_fini(void) { + int bhash_order = get_order(dccp_hashinfo.bhash_size * + sizeof(struct inet_bind_hashbucket)); + ccid_cleanup_builtins(); dccp_mib_exit(); - free_pages((unsigned long)dccp_hashinfo.bhash, - get_order(dccp_hashinfo.bhash_size * - sizeof(struct inet_bind_hashbucket))); + free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); + free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order); free_pages((unsigned long)dccp_hashinfo.ehash, get_order((dccp_hashinfo.ehash_mask + 1) * sizeof(struct inet_ehash_bucket))); @@ -1265,7 +1264,7 @@ static void __exit dccp_fini(void) kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_ackvec_exit(); dccp_sysctl_exit(); - percpu_counter_destroy(&dccp_orphan_count); + inet_hashinfo2_free_mod(&dccp_hashinfo); } module_init(dccp_init); diff --git a/net/dccp/qpolicy.c b/net/dccp/qpolicy.c index db2448c33a62..5ba204ec0aca 100644 --- a/net/dccp/qpolicy.c +++ b/net/dccp/qpolicy.c @@ -65,14 +65,16 @@ static bool qpolicy_prio_full(struct sock *sk) * @push: add a new @skb to the write queue * @full: indicates that no more packets will be admitted * @top: peeks at whatever the queueing policy defines as its `top' + * @params: parameter passed to policy operation */ -static struct dccp_qpolicy_operations { +struct dccp_qpolicy_operations { void (*push) (struct sock *sk, struct sk_buff *skb); bool (*full) (struct sock *sk); struct sk_buff* (*top) (struct sock *sk); __be32 params; +}; -} qpol_table[DCCPQ_POLICY_MAX] = { +static struct dccp_qpolicy_operations qpol_table[DCCPQ_POLICY_MAX] = { [DCCPQ_POLICY_SIMPLE] = { .push = qpolicy_simple_push, .full = qpolicy_simple_full, diff --git a/net/dccp/timer.c b/net/dccp/timer.c index c0b3672637c4..27a3b37acd2e 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -20,7 +20,7 @@ int sysctl_dccp_retries2 __read_mostly = TCP_RETR2; static void dccp_write_err(struct sock *sk) { sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; - sk->sk_error_report(sk); + sk_error_report(sk); dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); dccp_done(sk); @@ -85,7 +85,7 @@ static void dccp_retransmit_timer(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); /* - * More than than 4MSL (8 minutes) has passed, a RESET(aborted) was + * More than 4MSL (8 minutes) has passed, a RESET(aborted) was * sent, no need to retransmit, this sock is dead. */ if (dccp_write_timeout(sk)) @@ -176,7 +176,6 @@ static void dccp_delack_timer(struct timer_list *t) bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* Try again later. */ - icsk->icsk_ack.blocked = 1; __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); sk_reset_timer(sk, &icsk->icsk_delack_timer, jiffies + TCP_DELACK_MIN); @@ -216,11 +215,14 @@ out: /** * dccp_write_xmitlet - Workhorse for CCID packet dequeueing interface + * @t: pointer to the tasklet associated with this handler + * * See the comments above %ccid_dequeueing_decision for supported modes. */ -static void dccp_write_xmitlet(unsigned long data) +static void dccp_write_xmitlet(struct tasklet_struct *t) { - struct sock *sk = (struct sock *)data; + struct dccp_sock *dp = from_tasklet(dp, t, dccps_xmitlet); + struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk; bh_lock_sock(sk); if (sock_owned_by_user(sk)) @@ -234,16 +236,15 @@ static void dccp_write_xmitlet(unsigned long data) static void dccp_write_xmit_timer(struct timer_list *t) { struct dccp_sock *dp = from_timer(dp, t, dccps_xmit_timer); - struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk; - dccp_write_xmitlet((unsigned long)sk); + dccp_write_xmitlet(&dp->dccps_xmitlet); } void dccp_init_xmit_timers(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); - tasklet_init(&dp->dccps_xmitlet, dccp_write_xmitlet, (unsigned long)sk); + tasklet_setup(&dp->dccps_xmitlet, dccp_write_xmitlet); timer_setup(&dp->dccps_xmit_timer, dccp_write_xmit_timer, 0); inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer, &dccp_keepalive_timer); diff --git a/net/dccp/trace.h b/net/dccp/trace.h index 5062421beee9..5a43b3508c7f 100644 --- a/net/dccp/trace.h +++ b/net/dccp/trace.h @@ -60,9 +60,7 @@ TRACE_EVENT(dccp_probe, __entry->tx_t_ipi = hc->tx_t_ipi; } else { __entry->tx_s = 0; - memset(&__entry->tx_rtt, 0, (void *)&__entry->tx_t_ipi - - (void *)&__entry->tx_rtt + - sizeof(__entry->tx_t_ipi)); + memset_startat(__entry, 0, tx_rtt); } ), |