diff options
Diffstat (limited to 'net')
-rw-r--r-- | net/core/dev.c | 3 | ||||
-rw-r--r-- | net/dccp/ackvec.c | 251 | ||||
-rw-r--r-- | net/dccp/ackvec.h | 115 | ||||
-rw-r--r-- | net/dccp/ccids/ccid2.c | 13 | ||||
-rw-r--r-- | net/dccp/dccp.h | 11 | ||||
-rw-r--r-- | net/dccp/input.c | 6 | ||||
-rw-r--r-- | net/dccp/options.c | 65 | ||||
-rw-r--r-- | net/decnet/af_decnet.c | 2 | ||||
-rw-r--r-- | net/decnet/dn_dev.c | 100 | ||||
-rw-r--r-- | net/decnet/dn_fib.c | 6 | ||||
-rw-r--r-- | net/decnet/dn_neigh.c | 2 | ||||
-rw-r--r-- | net/decnet/dn_route.c | 72 | ||||
-rw-r--r-- | net/ipv4/icmp.c | 4 | ||||
-rw-r--r-- | net/ipv4/igmp.c | 225 | ||||
-rw-r--r-- | net/ipv4/ip_gre.c | 2 | ||||
-rw-r--r-- | net/ipv4/ipmr.c | 2 | ||||
-rw-r--r-- | net/ipv4/route.c | 57 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 16 | ||||
-rw-r--r-- | net/ipv4/xfrm4_policy.c | 24 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_xmit.c | 8 | ||||
-rw-r--r-- | net/socket.c | 11 | ||||
-rw-r--r-- | net/unix/af_unix.c | 34 |
22 files changed, 490 insertions, 539 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 0dd54a6..5968c82 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1817,8 +1817,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo) dev->ethtool_ops->get_drvinfo(dev, &info); - WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d " - "ip_summed=%d", + WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d ip_summed=%d\n", info.driver, dev ? dev->features : 0L, skb->sk ? skb->sk->sk_route_caps : 0L, skb->len, skb->data_len, skb->ip_summed); diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 92a6fcb..abaf241c 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -1,7 +1,8 @@ /* * net/dccp/ackvec.c * - * An implementation of the DCCP protocol + * An implementation of Ack Vectors for the DCCP protocol + * Copyright (c) 2007 University of Aberdeen, Scotland, UK * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@ghostprotocols.net> * * This program is free software; you can redistribute it and/or modify it @@ -23,173 +24,93 @@ static struct kmem_cache *dccp_ackvec_slab; static struct kmem_cache *dccp_ackvec_record_slab; -static struct dccp_ackvec_record *dccp_ackvec_record_new(void) +struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) { - struct dccp_ackvec_record *avr = - kmem_cache_alloc(dccp_ackvec_record_slab, GFP_ATOMIC); - - if (avr != NULL) - INIT_LIST_HEAD(&avr->avr_node); + struct dccp_ackvec *av = kmem_cache_zalloc(dccp_ackvec_slab, priority); - return avr; + if (av != NULL) { + av->av_buf_head = av->av_buf_tail = DCCPAV_MAX_ACKVEC_LEN - 1; + INIT_LIST_HEAD(&av->av_records); + } + return av; } -static void dccp_ackvec_record_delete(struct dccp_ackvec_record *avr) +static void dccp_ackvec_purge_records(struct dccp_ackvec *av) { - if (unlikely(avr == NULL)) - return; - /* Check if deleting a linked record */ - WARN_ON(!list_empty(&avr->avr_node)); - kmem_cache_free(dccp_ackvec_record_slab, avr); + struct dccp_ackvec_record *cur, *next; + + list_for_each_entry_safe(cur, next, &av->av_records, avr_node) + kmem_cache_free(dccp_ackvec_record_slab, cur); + INIT_LIST_HEAD(&av->av_records); } -static void dccp_ackvec_insert_avr(struct dccp_ackvec *av, - struct dccp_ackvec_record *avr) +void dccp_ackvec_free(struct dccp_ackvec *av) { - /* - * AVRs are sorted by seqno. Since we are sending them in order, we - * just add the AVR at the head of the list. - * -sorbo. - */ - if (!list_empty(&av->av_records)) { - const struct dccp_ackvec_record *head = - list_entry(av->av_records.next, - struct dccp_ackvec_record, - avr_node); - BUG_ON(before48(avr->avr_ack_seqno, head->avr_ack_seqno)); + if (likely(av != NULL)) { + dccp_ackvec_purge_records(av); + kmem_cache_free(dccp_ackvec_slab, av); } - - list_add(&avr->avr_node, &av->av_records); } -int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) +/** + * dccp_ackvec_update_records - Record information about sent Ack Vectors + * @av: Ack Vector records to update + * @seqno: Sequence number of the packet carrying the Ack Vector just sent + * @nonce_sum: The sum of all buffer nonces contained in the Ack Vector + */ +int dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seqno, u8 nonce_sum) { - struct dccp_sock *dp = dccp_sk(sk); - struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; - /* Figure out how many options do we need to represent the ackvec */ - const u8 nr_opts = DIV_ROUND_UP(av->av_vec_len, DCCP_SINGLE_OPT_MAXLEN); - u16 len = av->av_vec_len + 2 * nr_opts, i; - u32 elapsed_time; - const unsigned char *tail, *from; - unsigned char *to; struct dccp_ackvec_record *avr; - suseconds_t delta; - - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) - return -1; - - delta = ktime_us_delta(ktime_get_real(), av->av_time); - elapsed_time = delta / 10; - if (elapsed_time != 0 && - dccp_insert_option_elapsed_time(skb, elapsed_time)) - return -1; - - avr = dccp_ackvec_record_new(); + avr = kmem_cache_alloc(dccp_ackvec_record_slab, GFP_ATOMIC); if (avr == NULL) - return -1; - - DCCP_SKB_CB(skb)->dccpd_opt_len += len; - - to = skb_push(skb, len); - len = av->av_vec_len; - from = av->av_buf + av->av_buf_head; - tail = av->av_buf + DCCP_MAX_ACKVEC_LEN; - - for (i = 0; i < nr_opts; ++i) { - int copylen = len; - - if (len > DCCP_SINGLE_OPT_MAXLEN) - copylen = DCCP_SINGLE_OPT_MAXLEN; - - *to++ = DCCPO_ACK_VECTOR_0; - *to++ = copylen + 2; - - /* Check if buf_head wraps */ - if (from + copylen > tail) { - const u16 tailsize = tail - from; - - memcpy(to, from, tailsize); - to += tailsize; - len -= tailsize; - copylen -= tailsize; - from = av->av_buf; - } - - memcpy(to, from, copylen); - from += copylen; - to += copylen; - len -= copylen; - } + return -ENOBUFS; + avr->avr_ack_seqno = seqno; + avr->avr_ack_ptr = av->av_buf_head; + avr->avr_ack_ackno = av->av_buf_ackno; + avr->avr_ack_nonce = nonce_sum; + avr->avr_ack_runlen = dccp_ackvec_runlen(av->av_buf + av->av_buf_head); /* - * From RFC 4340, A.2: - * - * For each acknowledgement it sends, the HC-Receiver will add an - * acknowledgement record. ack_seqno will equal the HC-Receiver - * sequence number it used for the ack packet; ack_ptr will equal - * buf_head; ack_ackno will equal buf_ackno; and ack_nonce will - * equal buf_nonce. + * When the buffer overflows, we keep no more than one record. This is + * the simplest way of disambiguating sender-Acks dating from before the + * overflow from sender-Acks which refer to after the overflow; a simple + * solution is preferable here since we are handling an exception. */ - avr->avr_ack_seqno = DCCP_SKB_CB(skb)->dccpd_seq; - avr->avr_ack_ptr = av->av_buf_head; - avr->avr_ack_ackno = av->av_buf_ackno; - avr->avr_ack_nonce = av->av_buf_nonce; - avr->avr_sent_len = av->av_vec_len; - - dccp_ackvec_insert_avr(av, avr); + if (av->av_overflow) + dccp_ackvec_purge_records(av); + /* + * Since GSS is incremented for each packet, the list is automatically + * arranged in descending order of @ack_seqno. + */ + list_add(&avr->avr_node, &av->av_records); - dccp_pr_debug("%s ACK Vector 0, len=%d, ack_seqno=%llu, " - "ack_ackno=%llu\n", - dccp_role(sk), avr->avr_sent_len, + dccp_pr_debug("Added Vector, ack_seqno=%llu, ack_ackno=%llu (rl=%u)\n", (unsigned long long)avr->avr_ack_seqno, - (unsigned long long)avr->avr_ack_ackno); + (unsigned long long)avr->avr_ack_ackno, + avr->avr_ack_runlen); return 0; } -struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) -{ - struct dccp_ackvec *av = kmem_cache_alloc(dccp_ackvec_slab, priority); - - if (av != NULL) { - av->av_buf_head = DCCP_MAX_ACKVEC_LEN - 1; - av->av_buf_ackno = UINT48_MAX + 1; - av->av_buf_nonce = 0; - av->av_time = ktime_set(0, 0); - av->av_vec_len = 0; - INIT_LIST_HEAD(&av->av_records); - } - - return av; -} - -void dccp_ackvec_free(struct dccp_ackvec *av) +/* + * Buffer index and length computation using modulo-buffersize arithmetic. + * Note that, as pointers move from right to left, head is `before' tail. + */ +static inline u16 __ackvec_idx_add(const u16 a, const u16 b) { - if (unlikely(av == NULL)) - return; - - if (!list_empty(&av->av_records)) { - struct dccp_ackvec_record *avr, *next; - - list_for_each_entry_safe(avr, next, &av->av_records, avr_node) { - list_del_init(&avr->avr_node); - dccp_ackvec_record_delete(avr); - } - } - - kmem_cache_free(dccp_ackvec_slab, av); + return (a + b) % DCCPAV_MAX_ACKVEC_LEN; } -static inline u8 dccp_ackvec_state(const struct dccp_ackvec *av, - const u32 index) +static inline u16 __ackvec_idx_sub(const u16 a, const u16 b) { - return av->av_buf[index] & DCCP_ACKVEC_STATE_MASK; + return __ackvec_idx_add(a, DCCPAV_MAX_ACKVEC_LEN - b); } -static inline u8 dccp_ackvec_len(const struct dccp_ackvec *av, - const u32 index) +u16 dccp_ackvec_buflen(const struct dccp_ackvec *av) { - return av->av_buf[index] & DCCP_ACKVEC_LEN_MASK; + if (unlikely(av->av_overflow)) + return DCCPAV_MAX_ACKVEC_LEN; + return __ackvec_idx_sub(av->av_buf_tail, av->av_buf_head); } /* @@ -204,7 +125,7 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, long gap; long new_head; - if (av->av_vec_len + packets > DCCP_MAX_ACKVEC_LEN) + if (av->av_vec_len + packets > DCCPAV_MAX_ACKVEC_LEN) return -ENOBUFS; gap = packets - 1; @@ -212,18 +133,18 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, if (new_head < 0) { if (gap > 0) { - memset(av->av_buf, DCCP_ACKVEC_STATE_NOT_RECEIVED, + memset(av->av_buf, DCCPAV_NOT_RECEIVED, gap + new_head + 1); gap = -new_head; } - new_head += DCCP_MAX_ACKVEC_LEN; + new_head += DCCPAV_MAX_ACKVEC_LEN; } av->av_buf_head = new_head; if (gap > 0) memset(av->av_buf + av->av_buf_head + 1, - DCCP_ACKVEC_STATE_NOT_RECEIVED, gap); + DCCPAV_NOT_RECEIVED, gap); av->av_buf[av->av_buf_head] = state; av->av_vec_len += packets; @@ -236,6 +157,8 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, const u64 ackno, const u8 state) { + u8 *cur_head = av->av_buf + av->av_buf_head, + *buf_end = av->av_buf + DCCPAV_MAX_ACKVEC_LEN; /* * Check at the right places if the buffer is full, if it is, tell the * caller to start dropping packets till the HC-Sender acks our ACK @@ -260,7 +183,7 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, /* See if this is the first ackno being inserted */ if (av->av_vec_len == 0) { - av->av_buf[av->av_buf_head] = state; + *cur_head = state; av->av_vec_len = 1; } else if (after48(ackno, av->av_buf_ackno)) { const u64 delta = dccp_delta_seqno(av->av_buf_ackno, ackno); @@ -269,10 +192,9 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, * Look if the state of this packet is the same as the * previous ackno and if so if we can bump the head len. */ - if (delta == 1 && - dccp_ackvec_state(av, av->av_buf_head) == state && - dccp_ackvec_len(av, av->av_buf_head) < DCCP_ACKVEC_LEN_MASK) - av->av_buf[av->av_buf_head]++; + if (delta == 1 && dccp_ackvec_state(cur_head) == state && + dccp_ackvec_runlen(cur_head) < DCCPAV_MAX_RUNLEN) + *cur_head += 1; else if (dccp_ackvec_set_buf_head_state(av, delta, state)) return -ENOBUFS; } else { @@ -285,21 +207,17 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, * could reduce the complexity of this scan.) */ u64 delta = dccp_delta_seqno(ackno, av->av_buf_ackno); - u32 index = av->av_buf_head; while (1) { - const u8 len = dccp_ackvec_len(av, index); - const u8 av_state = dccp_ackvec_state(av, index); + const u8 len = dccp_ackvec_runlen(cur_head); /* * valid packets not yet in av_buf have a reserved * entry, with a len equal to 0. */ - if (av_state == DCCP_ACKVEC_STATE_NOT_RECEIVED && - len == 0 && delta == 0) { /* Found our - reserved seat! */ + if (*cur_head == DCCPAV_NOT_RECEIVED && delta == 0) { dccp_pr_debug("Found %llu reserved seat!\n", (unsigned long long)ackno); - av->av_buf[index] = state; + *cur_head = state; goto out; } /* len == 0 means one packet */ @@ -307,13 +225,12 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, goto out_duplicate; delta -= len + 1; - if (++index == DCCP_MAX_ACKVEC_LEN) - index = 0; + if (++cur_head == buf_end) + cur_head = av->av_buf; } } av->av_buf_ackno = ackno; - av->av_time = ktime_get_real(); out: return 0; @@ -333,13 +250,13 @@ static void dccp_ackvec_throw_record(struct dccp_ackvec *av, if (av->av_buf_head <= avr->avr_ack_ptr) av->av_vec_len = avr->avr_ack_ptr - av->av_buf_head; else - av->av_vec_len = DCCP_MAX_ACKVEC_LEN - 1 - + av->av_vec_len = DCCPAV_MAX_ACKVEC_LEN - 1 - av->av_buf_head + avr->avr_ack_ptr; /* free records */ list_for_each_entry_safe_from(avr, next, &av->av_records, avr_node) { - list_del_init(&avr->avr_node); - dccp_ackvec_record_delete(avr); + list_del(&avr->avr_node); + kmem_cache_free(dccp_ackvec_record_slab, avr); } } @@ -357,7 +274,7 @@ void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, struct sock *sk, if (ackno == avr->avr_ack_seqno) { dccp_pr_debug("%s ACK packet 0, len=%d, ack_seqno=%llu, " "ack_ackno=%llu, ACKED!\n", - dccp_role(sk), 1, + dccp_role(sk), avr->avr_ack_runlen, (unsigned long long)avr->avr_ack_seqno, (unsigned long long)avr->avr_ack_ackno); dccp_ackvec_throw_record(av, avr); @@ -387,7 +304,7 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, */ avr = list_entry(av->av_records.next, struct dccp_ackvec_record, avr_node); while (i--) { - const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; + const u8 rl = dccp_ackvec_runlen(vector); u64 ackno_end_rl; dccp_set_seqno(&ackno_end_rl, *ackno - rl); @@ -404,8 +321,7 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, break; found: if (between48(avr->avr_ack_seqno, ackno_end_rl, *ackno)) { - const u8 state = *vector & DCCP_ACKVEC_STATE_MASK; - if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED) { + if (dccp_ackvec_state(vector) != DCCPAV_NOT_RECEIVED) { dccp_pr_debug("%s ACK vector 0, len=%d, " "ack_seqno=%llu, ack_ackno=%llu, " "ACKED!\n", @@ -448,10 +364,9 @@ int __init dccp_ackvec_init(void) if (dccp_ackvec_slab == NULL) goto out_err; - dccp_ackvec_record_slab = - kmem_cache_create("dccp_ackvec_record", - sizeof(struct dccp_ackvec_record), - 0, SLAB_HWCACHE_ALIGN, NULL); + dccp_ackvec_record_slab = kmem_cache_create("dccp_ackvec_record", + sizeof(struct dccp_ackvec_record), + 0, SLAB_HWCACHE_ALIGN, NULL); if (dccp_ackvec_record_slab == NULL) goto out_destroy_slab; diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h index 7ea557b..23880be 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -3,9 +3,9 @@ /* * net/dccp/ackvec.h * - * An implementation of the DCCP protocol + * An implementation of Ack Vectors for the DCCP protocol + * Copyright (c) 2007 University of Aberdeen, Scotland, UK * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@mandriva.com> - * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. @@ -13,75 +13,89 @@ #include <linux/dccp.h> #include <linux/compiler.h> -#include <linux/ktime.h> #include <linux/list.h> #include <linux/types.h> -/* We can spread an ack vector across multiple options */ -#define DCCP_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * 2) +/* + * Ack Vector buffer space is static, in multiples of %DCCP_SINGLE_OPT_MAXLEN, + * the maximum size of a single Ack Vector. Setting %DCCPAV_NUM_ACKVECS to 1 + * will be sufficient for most cases of low Ack Ratios, using a value of 2 gives + * more headroom if Ack Ratio is higher or when the sender acknowledges slowly. + * The maximum value is bounded by the u16 types for indices and functions. + */ +#define DCCPAV_NUM_ACKVECS 2 +#define DCCPAV_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * DCCPAV_NUM_ACKVECS) /* Estimated minimum average Ack Vector length - used for updating MPS */ #define DCCPAV_MIN_OPTLEN 16 -#define DCCP_ACKVEC_STATE_RECEIVED 0 -#define DCCP_ACKVEC_STATE_ECN_MARKED (1 << 6) -#define DCCP_ACKVEC_STATE_NOT_RECEIVED (3 << 6) +enum dccp_ackvec_states { + DCCPAV_RECEIVED = 0x00, + DCCPAV_ECN_MARKED = 0x40, + DCCPAV_RESERVED = 0x80, + DCCPAV_NOT_RECEIVED = 0xC0 +}; +#define DCCPAV_MAX_RUNLEN 0x3F -#define DCCP_ACKVEC_STATE_MASK 0xC0 /* 11000000 */ -#define DCCP_ACKVEC_LEN_MASK 0x3F /* 00111111 */ +static inline u8 dccp_ackvec_runlen(const u8 *cell) +{ + return *cell & DCCPAV_MAX_RUNLEN; +} -/** struct dccp_ackvec - ack vector - * - * This data structure is the one defined in RFC 4340, Appendix A. - * - * @av_buf_head - circular buffer head - * @av_buf_tail - circular buffer tail - * @av_buf_ackno - ack # of the most recent packet acknowledgeable in the - * buffer (i.e. %av_buf_head) - * @av_buf_nonce - the one-bit sum of the ECN Nonces on all packets acked - * by the buffer with State 0 - * - * Additionally, the HC-Receiver must keep some information about the - * Ack Vectors it has recently sent. For each packet sent carrying an - * Ack Vector, it remembers four variables: +static inline u8 dccp_ackvec_state(const u8 *cell) +{ + return *cell & ~DCCPAV_MAX_RUNLEN; +} + +/** struct dccp_ackvec - Ack Vector main data structure * - * @av_records - list of dccp_ackvec_record - * @av_ack_nonce - the one-bit sum of the ECN Nonces for all State 0. + * This implements a fixed-size circular buffer within an array and is largely + * based on Appendix A of RFC 4340. * - * @av_time - the time in usecs - * @av_buf - circular buffer of acknowledgeable packets + * @av_buf: circular buffer storage area + * @av_buf_head: head index; begin of live portion in @av_buf + * @av_buf_tail: tail index; first index _after_ the live portion in @av_buf + * @av_buf_ackno: highest seqno of acknowledgeable packet recorded in @av_buf + * @av_tail_ackno: lowest seqno of acknowledgeable packet recorded in @av_buf + * @av_buf_nonce: ECN nonce sums, each covering subsequent segments of up to + * %DCCP_SINGLE_OPT_MAXLEN cells in the live portion of @av_buf + * @av_overflow: if 1 then buf_head == buf_tail indicates buffer wraparound + * @av_records: list of %dccp_ackvec_record (Ack Vectors sent previously) + * @av_veclen: length of the live portion of @av_buf */ struct dccp_ackvec { - u64 av_buf_ackno; - struct list_head av_records; - ktime_t av_time; + u8 av_buf[DCCPAV_MAX_ACKVEC_LEN]; u16 av_buf_head; + u16 av_buf_tail; + u64 av_buf_ackno:48; + u64 av_tail_ackno:48; + bool av_buf_nonce[DCCPAV_NUM_ACKVECS]; + u8 av_overflow:1; + struct list_head av_records; u16 av_vec_len; - u8 av_buf_nonce; - u8 av_ack_nonce; - u8 av_buf[DCCP_MAX_ACKVEC_LEN]; }; -/** struct dccp_ackvec_record - ack vector record +/** struct dccp_ackvec_record - Records information about sent Ack Vectors * - * ACK vector record as defined in Appendix A of spec. + * These list entries define the additional information which the HC-Receiver + * keeps about recently-sent Ack Vectors; again refer to RFC 4340, Appendix A. * - * The list is sorted by avr_ack_seqno + * @avr_node: the list node in @av_records + * @avr_ack_seqno: sequence number of the packet the Ack Vector was sent on + * @avr_ack_ackno: the Ack number that this record/Ack Vector refers to + * @avr_ack_ptr: pointer into @av_buf where this record starts + * @avr_ack_runlen: run length of @avr_ack_ptr at the time of sending + * @avr_ack_nonce: the sum of @av_buf_nonce's at the time this record was sent * - * @avr_node - node in av_records - * @avr_ack_seqno - sequence number of the packet this record was sent on - * @avr_ack_ackno - sequence number being acknowledged - * @avr_ack_ptr - pointer into av_buf where this record starts - * @avr_ack_nonce - av_ack_nonce at the time this record was sent - * @avr_sent_len - lenght of the record in av_buf + * The list as a whole is sorted in descending order by @avr_ack_seqno. */ struct dccp_ackvec_record { struct list_head avr_node; - u64 avr_ack_seqno; - u64 avr_ack_ackno; + u64 avr_ack_seqno:48; + u64 avr_ack_ackno:48; u16 avr_ack_ptr; - u16 avr_sent_len; - u8 avr_ack_nonce; + u8 avr_ack_runlen; + u8 avr_ack_nonce:1; }; struct sock; @@ -102,10 +116,11 @@ extern int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb, u64 *ackno, const u8 opt, const u8 *value, const u8 len); -extern int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb); +extern int dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seq, u8 sum); +extern u16 dccp_ackvec_buflen(const struct dccp_ackvec *av); -static inline int dccp_ackvec_pending(const struct dccp_ackvec *av) +static inline bool dccp_ackvec_is_empty(const struct dccp_ackvec *av) { - return av->av_vec_len; + return av->av_overflow == 0 && av->av_buf_head == av->av_buf_tail; } #endif /* _ACKVEC_H */ diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 6576eae..cb1b4a0 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -513,8 +513,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) &vector, &veclen)) != -1) { /* go through this ack vector */ while (veclen--) { - const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; - u64 ackno_end_rl = SUB48(ackno, rl); + u64 ackno_end_rl = SUB48(ackno, dccp_ackvec_runlen(vector)); ccid2_pr_debug("ackvec start:%llu end:%llu\n", (unsigned long long)ackno, @@ -537,17 +536,15 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) * run length */ while (between48(seqp->ccid2s_seq,ackno_end_rl,ackno)) { - const u8 state = *vector & - DCCP_ACKVEC_STATE_MASK; + const u8 state = dccp_ackvec_state(vector); /* new packet received or marked */ - if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED && + if (state != DCCPAV_NOT_RECEIVED && !seqp->ccid2s_acked) { - if (state == - DCCP_ACKVEC_STATE_ECN_MARKED) { + if (state == DCCPAV_ECN_MARKED) ccid2_congestion_event(sk, seqp); - } else + else ccid2_new_ack(sk, seqp, &maxincr); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index a8ed459..19fafd5 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -457,12 +457,15 @@ static inline void dccp_update_gss(struct sock *sk, u64 seq) dp->dccps_awh = dp->dccps_gss; } +static inline int dccp_ackvec_pending(const struct sock *sk) +{ + return dccp_sk(sk)->dccps_hc_rx_ackvec != NULL && + !dccp_ackvec_is_empty(dccp_sk(sk)->dccps_hc_rx_ackvec); +} + static inline int dccp_ack_pending(const struct sock *sk) { - const struct dccp_sock *dp = dccp_sk(sk); - return (dp->dccps_hc_rx_ackvec != NULL && - dccp_ackvec_pending(dp->dccps_hc_rx_ackvec)) || - inet_csk_ack_scheduled(sk); + return dccp_ackvec_pending(sk) || inet_csk_ack_scheduled(sk); } extern int dccp_feat_finalise_settings(struct dccp_sock *dp); diff --git a/net/dccp/input.c b/net/dccp/input.c index 2659853..c7aeeba 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -378,8 +378,7 @@ int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_seq, - DCCP_ACKVEC_STATE_RECEIVED)) + DCCP_SKB_CB(skb)->dccpd_seq, DCCPAV_RECEIVED)) goto discard; dccp_deliver_input_to_ccids(sk, skb); @@ -637,8 +636,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_seq, - DCCP_ACKVEC_STATE_RECEIVED)) + DCCP_SKB_CB(skb)->dccpd_seq, DCCPAV_RECEIVED)) goto discard; dccp_deliver_input_to_ccids(sk, skb); diff --git a/net/dccp/options.c b/net/dccp/options.c index cd30618..5adeeed 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -340,6 +340,7 @@ static inline int dccp_elapsed_time_len(const u32 elapsed_time) return elapsed_time == 0 ? 0 : elapsed_time <= 0xFFFF ? 2 : 4; } +/* FIXME: This function is currently not used anywhere */ int dccp_insert_option_elapsed_time(struct sk_buff *skb, u32 elapsed_time) { const int elapsed_time_len = dccp_elapsed_time_len(elapsed_time); @@ -424,6 +425,67 @@ static int dccp_insert_option_timestamp_echo(struct dccp_sock *dp, return 0; } +static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; + const u16 buflen = dccp_ackvec_buflen(av); + /* Figure out how many options do we need to represent the ackvec */ + const u8 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN); + u16 len = buflen + 2 * nr_opts; + u8 i, nonce = 0; + const unsigned char *tail, *from; + unsigned char *to; + + if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) + return -1; + + DCCP_SKB_CB(skb)->dccpd_opt_len += len; + + to = skb_push(skb, len); + len = buflen; + from = av->av_buf + av->av_buf_head; + tail = av->av_buf + DCCPAV_MAX_ACKVEC_LEN; + + for (i = 0; i < nr_opts; ++i) { + int copylen = len; + + if (len > DCCP_SINGLE_OPT_MAXLEN) + copylen = DCCP_SINGLE_OPT_MAXLEN; + + /* + * RFC 4340, 12.2: Encode the Nonce Echo for this Ack Vector via + * its type; ack_nonce is the sum of all individual buf_nonce's. + */ + nonce ^= av->av_buf_nonce[i]; + + *to++ = DCCPO_ACK_VECTOR_0 + av->av_buf_nonce[i]; + *to++ = copylen + 2; + + /* Check if buf_head wraps */ + if (from + copylen > tail) { + const u16 tailsize = tail - from; + + memcpy(to, from, tailsize); + to += tailsize; + len -= tailsize; + copylen -= tailsize; + from = av->av_buf; + } + + memcpy(to, from, copylen); + from += copylen; + to += copylen; + len -= copylen; + } + /* + * Each sent Ack Vector is recorded in the list, as per A.2 of RFC 4340. + */ + if (dccp_ackvec_update_records(av, DCCP_SKB_CB(skb)->dccpd_seq, nonce)) + return -ENOBUFS; + return 0; +} + /** * dccp_insert_option_mandatory - Mandatory option (5.8.2) * Note that since we are using skb_push, this function needs to be called @@ -519,8 +581,7 @@ int dccp_insert_options(struct sock *sk, struct sk_buff *skb) if (dccp_insert_option_timestamp(skb)) return -1; - } else if (dp->dccps_hc_rx_ackvec != NULL && - dccp_ackvec_pending(dp->dccps_hc_rx_ackvec) && + } else if (dccp_ackvec_pending(sk) && dccp_insert_option_ackvec(sk, skb)) { return -1; } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index a76b78d..9ecef99 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1848,7 +1848,7 @@ unsigned dn_mss_from_pmtu(struct net_device *dev, int mtu) { unsigned mss = 230 - DN_MAX_NSP_DATA_HEADER; if (dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); mtu -= LL_RESERVED_SPACE(dev); if (dn_db->use_long) mtu -= 21; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 4c409b4..0ba1563 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -267,7 +267,7 @@ static int dn_forwarding_proc(ctl_table *table, int write, if (table->extra1 == NULL) return -EINVAL; - dn_db = dev->dn_ptr; + dn_db = rcu_dereference_raw(dev->dn_ptr); old = dn_db->parms.forwarding; err = proc_dointvec(table, write, buffer, lenp, ppos); @@ -332,14 +332,19 @@ static struct dn_ifaddr *dn_dev_alloc_ifa(void) return ifa; } -static __inline__ void dn_dev_free_ifa(struct dn_ifaddr *ifa) +static void dn_dev_free_ifa_rcu(struct rcu_head *head) { - kfree(ifa); + kfree(container_of(head, struct dn_ifaddr, rcu)); } -static void dn_dev_del_ifa(struct dn_dev *dn_db, struct dn_ifaddr **ifap, int destroy) +static void dn_dev_free_ifa(struct dn_ifaddr *ifa) { - struct dn_ifaddr *ifa1 = *ifap; + call_rcu(&ifa->rcu, dn_dev_free_ifa_rcu); +} + +static void dn_dev_del_ifa(struct dn_dev *dn_db, struct dn_ifaddr __rcu **ifap, int destroy) +{ + struct dn_ifaddr *ifa1 = rtnl_dereference(*ifap); unsigned char mac_addr[6]; struct net_device *dev = dn_db->dev; @@ -373,7 +378,9 @@ static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) ASSERT_RTNL(); /* Check for duplicates */ - for(ifa1 = dn_db->ifa_list; ifa1; ifa1 = ifa1->ifa_next) { + for (ifa1 = rtnl_dereference(dn_db->ifa_list); + ifa1 != NULL; + ifa1 = rtnl_dereference(ifa1->ifa_next)) { if (ifa1->ifa_local == ifa->ifa_local) return -EEXIST; } @@ -386,7 +393,7 @@ static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) } ifa->ifa_next = dn_db->ifa_list; - dn_db->ifa_list = ifa; + rcu_assign_pointer(dn_db->ifa_list, ifa); dn_ifaddr_notify(RTM_NEWADDR, ifa); blocking_notifier_call_chain(&dnaddr_chain, NETDEV_UP, ifa); @@ -396,7 +403,7 @@ static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) static int dn_dev_set_ifa(struct net_device *dev, struct dn_ifaddr *ifa) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); int rv; if (dn_db == NULL) { @@ -425,7 +432,8 @@ int dn_dev_ioctl(unsigned int cmd, void __user *arg) struct sockaddr_dn *sdn = (struct sockaddr_dn *)&ifr->ifr_addr; struct dn_dev *dn_db; struct net_device *dev; - struct dn_ifaddr *ifa = NULL, **ifap = NULL; + struct dn_ifaddr *ifa = NULL; + struct dn_ifaddr __rcu **ifap = NULL; int ret = 0; if (copy_from_user(ifr, arg, DN_IFREQ_SIZE)) @@ -454,8 +462,10 @@ int dn_dev_ioctl(unsigned int cmd, void __user *arg) goto done; } - if ((dn_db = dev->dn_ptr) != NULL) { - for (ifap = &dn_db->ifa_list; (ifa=*ifap) != NULL; ifap = &ifa->ifa_next) + if ((dn_db = rtnl_dereference(dev->dn_ptr)) != NULL) { + for (ifap = &dn_db->ifa_list; + (ifa = rtnl_dereference(*ifap)) != NULL; + ifap = &ifa->ifa_next) if (strcmp(ifr->ifr_name, ifa->ifa_label) == 0) break; } @@ -558,7 +568,7 @@ static struct dn_dev *dn_dev_by_index(int ifindex) dev = __dev_get_by_index(&init_net, ifindex); if (dev) - dn_dev = dev->dn_ptr; + dn_dev = rtnl_dereference(dev->dn_ptr); return dn_dev; } @@ -576,7 +586,8 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct nlattr *tb[IFA_MAX+1]; struct dn_dev *dn_db; struct ifaddrmsg *ifm; - struct dn_ifaddr *ifa, **ifap; + struct dn_ifaddr *ifa; + struct dn_ifaddr __rcu **ifap; int err = -EINVAL; if (!net_eq(net, &init_net)) @@ -592,7 +603,9 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) goto errout; err = -EADDRNOTAVAIL; - for (ifap = &dn_db->ifa_list; (ifa = *ifap); ifap = &ifa->ifa_next) { + for (ifap = &dn_db->ifa_list; + (ifa = rtnl_dereference(*ifap)) != NULL; + ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && nla_memcmp(tb[IFA_LOCAL], &ifa->ifa_local, 2)) continue; @@ -632,7 +645,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if ((dev = __dev_get_by_index(&init_net, ifm->ifa_index)) == NULL) return -ENODEV; - if ((dn_db = dev->dn_ptr) == NULL) { + if ((dn_db = rtnl_dereference(dev->dn_ptr)) == NULL) { dn_db = dn_dev_create(dev, &err); if (!dn_db) return err; @@ -748,11 +761,11 @@ static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) skip_naddr = 0; } - if ((dn_db = dev->dn_ptr) == NULL) + if ((dn_db = rtnl_dereference(dev->dn_ptr)) == NULL) goto cont; - for (ifa = dn_db->ifa_list, dn_idx = 0; ifa; - ifa = ifa->ifa_next, dn_idx++) { + for (ifa = rtnl_dereference(dn_db->ifa_list), dn_idx = 0; ifa; + ifa = rtnl_dereference(ifa->ifa_next), dn_idx++) { if (dn_idx < skip_naddr) continue; @@ -773,21 +786,22 @@ done: static int dn_dev_get_first(struct net_device *dev, __le16 *addr) { - struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn_db; struct dn_ifaddr *ifa; int rv = -ENODEV; + rcu_read_lock(); + dn_db = rcu_dereference(dev->dn_ptr); if (dn_db == NULL) goto out; - rtnl_lock(); - ifa = dn_db->ifa_list; + ifa = rcu_dereference(dn_db->ifa_list); if (ifa != NULL) { *addr = ifa->ifa_local; rv = 0; } - rtnl_unlock(); out: + rcu_read_unlock(); return rv; } @@ -823,7 +837,7 @@ static void dn_send_endnode_hello(struct net_device *dev, struct dn_ifaddr *ifa) struct endnode_hello_message *msg; struct sk_buff *skb = NULL; __le16 *pktlen; - struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if ((skb = dn_alloc_skb(NULL, sizeof(*msg), GFP_ATOMIC)) == NULL) return; @@ -889,7 +903,7 @@ static int dn_am_i_a_router(struct dn_neigh *dn, struct dn_dev *dn_db, struct dn static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) { int n; - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); struct dn_neigh *dn = (struct dn_neigh *)dn_db->router; struct sk_buff *skb; size_t size; @@ -960,7 +974,7 @@ static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) static void dn_send_brd_hello(struct net_device *dev, struct dn_ifaddr *ifa) { - struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if (dn_db->parms.forwarding == 0) dn_send_endnode_hello(dev, ifa); @@ -998,7 +1012,7 @@ static void dn_send_ptp_hello(struct net_device *dev, struct dn_ifaddr *ifa) static int dn_eth_up(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if (dn_db->parms.forwarding == 0) dev_mc_add(dev, dn_rt_all_end_mcast); @@ -1012,7 +1026,7 @@ static int dn_eth_up(struct net_device *dev) static void dn_eth_down(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if (dn_db->parms.forwarding == 0) dev_mc_del(dev, dn_rt_all_end_mcast); @@ -1025,12 +1039,16 @@ static void dn_dev_set_timer(struct net_device *dev); static void dn_dev_timer_func(unsigned long arg) { struct net_device *dev = (struct net_device *)arg; - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db; struct dn_ifaddr *ifa; + rcu_read_lock(); + dn_db = rcu_dereference(dev->dn_ptr); if (dn_db->t3 <= dn_db->parms.t2) { if (dn_db->parms.timer3) { - for(ifa = dn_db->ifa_list; ifa; ifa = ifa->ifa_next) { + for (ifa = rcu_dereference(dn_db->ifa_list); + ifa; + ifa = rcu_dereference(ifa->ifa_next)) { if (!(ifa->ifa_flags & IFA_F_SECONDARY)) dn_db->parms.timer3(dev, ifa); } @@ -1039,13 +1057,13 @@ static void dn_dev_timer_func(unsigned long arg) } else { dn_db->t3 -= dn_db->parms.t2; } - + rcu_read_unlock(); dn_dev_set_timer(dev); } static void dn_dev_set_timer(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); if (dn_db->parms.t2 > dn_db->parms.t3) dn_db->parms.t2 = dn_db->parms.t3; @@ -1077,8 +1095,8 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) return NULL; memcpy(&dn_db->parms, p, sizeof(struct dn_dev_parms)); - smp_wmb(); - dev->dn_ptr = dn_db; + + rcu_assign_pointer(dev->dn_ptr, dn_db); dn_db->dev = dev; init_timer(&dn_db->timer); @@ -1086,7 +1104,7 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) dn_db->neigh_parms = neigh_parms_alloc(dev, &dn_neigh_table); if (!dn_db->neigh_parms) { - dev->dn_ptr = NULL; + rcu_assign_pointer(dev->dn_ptr, NULL); kfree(dn_db); return NULL; } @@ -1125,7 +1143,7 @@ void dn_dev_up(struct net_device *dev) struct dn_ifaddr *ifa; __le16 addr = decnet_address; int maybe_default = 0; - struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_LOOPBACK)) return; @@ -1176,7 +1194,7 @@ void dn_dev_up(struct net_device *dev) static void dn_dev_delete(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); if (dn_db == NULL) return; @@ -1204,13 +1222,13 @@ static void dn_dev_delete(struct net_device *dev) void dn_dev_down(struct net_device *dev) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); struct dn_ifaddr *ifa; if (dn_db == NULL) return; - while((ifa = dn_db->ifa_list) != NULL) { + while ((ifa = rtnl_dereference(dn_db->ifa_list)) != NULL) { dn_dev_del_ifa(dn_db, &dn_db->ifa_list, 0); dn_dev_free_ifa(ifa); } @@ -1270,7 +1288,7 @@ static inline int is_dn_dev(struct net_device *dev) } static void *dn_dev_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(rcu) + __acquires(RCU) { int i; struct net_device *dev; @@ -1313,7 +1331,7 @@ static void *dn_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void dn_dev_seq_stop(struct seq_file *seq, void *v) - __releases(rcu) + __releases(RCU) { rcu_read_unlock(); } @@ -1340,7 +1358,7 @@ static int dn_dev_seq_show(struct seq_file *seq, void *v) struct net_device *dev = v; char peer_buf[DN_ASCBUF_LEN]; char router_buf[DN_ASCBUF_LEN]; - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference(dev->dn_ptr); seq_printf(seq, "%-8s %1s %04u %04u %04lu %04lu" " %04hu %03d %02x %-10s %-7s %-7s\n", diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 4ab96c1..0ef0a81 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -610,10 +610,12 @@ static void dn_fib_del_ifaddr(struct dn_ifaddr *ifa) /* Scan device list */ rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { - dn_db = dev->dn_ptr; + dn_db = rcu_dereference(dev->dn_ptr); if (dn_db == NULL) continue; - for(ifa2 = dn_db->ifa_list; ifa2; ifa2 = ifa2->ifa_next) { + for (ifa2 = rcu_dereference(dn_db->ifa_list); + ifa2 != NULL; + ifa2 = rcu_dereference(ifa2->ifa_next)) { if (ifa2->ifa_local == ifa->ifa_local) { found_it = 1; break; diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index a085dbc..602dade 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -391,7 +391,7 @@ int dn_neigh_router_hello(struct sk_buff *skb) write_lock(&neigh->lock); neigh->used = jiffies; - dn_db = (struct dn_dev *)neigh->dev->dn_ptr; + dn_db = rcu_dereference(neigh->dev->dn_ptr); if (!(neigh->nud_state & NUD_PERMANENT)) { neigh->updated = jiffies; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index df0f3e5..474d54d 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -93,7 +93,7 @@ struct dn_rt_hash_bucket { - struct dn_route *chain; + struct dn_route __rcu *chain; spinlock_t lock; }; @@ -157,15 +157,17 @@ static inline void dnrt_drop(struct dn_route *rt) static void dn_dst_check_expire(unsigned long dummy) { int i; - struct dn_route *rt, **rtp; + struct dn_route *rt; + struct dn_route __rcu **rtp; unsigned long now = jiffies; unsigned long expire = 120 * HZ; - for(i = 0; i <= dn_rt_hash_mask; i++) { + for (i = 0; i <= dn_rt_hash_mask; i++) { rtp = &dn_rt_hash_table[i].chain; spin_lock(&dn_rt_hash_table[i].lock); - while((rt=*rtp) != NULL) { + while ((rt = rcu_dereference_protected(*rtp, + lockdep_is_held(&dn_rt_hash_table[i].lock))) != NULL) { if (atomic_read(&rt->dst.__refcnt) || (now - rt->dst.lastuse) < expire) { rtp = &rt->dst.dn_next; @@ -186,17 +188,19 @@ static void dn_dst_check_expire(unsigned long dummy) static int dn_dst_gc(struct dst_ops *ops) { - struct dn_route *rt, **rtp; + struct dn_route *rt; + struct dn_route __rcu **rtp; int i; unsigned long now = jiffies; unsigned long expire = 10 * HZ; - for(i = 0; i <= dn_rt_hash_mask; i++) { + for (i = 0; i <= dn_rt_hash_mask; i++) { spin_lock_bh(&dn_rt_hash_table[i].lock); rtp = &dn_rt_hash_table[i].chain; - while((rt=*rtp) != NULL) { + while ((rt = rcu_dereference_protected(*rtp, + lockdep_is_held(&dn_rt_hash_table[i].lock))) != NULL) { if (atomic_read(&rt->dst.__refcnt) || (now - rt->dst.lastuse) < expire) { rtp = &rt->dst.dn_next; @@ -227,7 +231,7 @@ static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu) { u32 min_mtu = 230; struct dn_dev *dn = dst->neighbour ? - (struct dn_dev *)dst->neighbour->dev->dn_ptr : NULL; + rcu_dereference_raw(dst->neighbour->dev->dn_ptr) : NULL; if (dn && dn->use_long == 0) min_mtu -= 6; @@ -277,13 +281,15 @@ static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) static int dn_insert_route(struct dn_route *rt, unsigned hash, struct dn_route **rp) { - struct dn_route *rth, **rthp; + struct dn_route *rth; + struct dn_route __rcu **rthp; unsigned long now = jiffies; rthp = &dn_rt_hash_table[hash].chain; spin_lock_bh(&dn_rt_hash_table[hash].lock); - while((rth = *rthp) != NULL) { + while ((rth = rcu_dereference_protected(*rthp, + lockdep_is_held(&dn_rt_hash_table[hash].lock))) != NULL) { if (compare_keys(&rth->fl, &rt->fl)) { /* Put it first */ *rthp = rth->dst.dn_next; @@ -315,15 +321,15 @@ static void dn_run_flush(unsigned long dummy) int i; struct dn_route *rt, *next; - for(i = 0; i < dn_rt_hash_mask; i++) { + for (i = 0; i < dn_rt_hash_mask; i++) { spin_lock_bh(&dn_rt_hash_table[i].lock); - if ((rt = xchg(&dn_rt_hash_table[i].chain, NULL)) == NULL) + if ((rt = xchg((struct dn_route **)&dn_rt_hash_table[i].chain, NULL)) == NULL) goto nothing_to_declare; - for(; rt; rt=next) { - next = rt->dst.dn_next; - rt->dst.dn_next = NULL; + for(; rt; rt = next) { + next = rcu_dereference_raw(rt->dst.dn_next); + RCU_INIT_POINTER(rt->dst.dn_next, NULL); dst_free((struct dst_entry *)rt); } @@ -458,15 +464,16 @@ static int dn_return_long(struct sk_buff *skb) */ static int dn_route_rx_packet(struct sk_buff *skb) { - struct dn_skb_cb *cb = DN_SKB_CB(skb); + struct dn_skb_cb *cb; int err; if ((err = dn_route_input(skb)) == 0) return dst_input(skb); + cb = DN_SKB_CB(skb); if (decnet_debug_level & 4) { char *devname = skb->dev ? skb->dev->name : "???"; - struct dn_skb_cb *cb = DN_SKB_CB(skb); + printk(KERN_DEBUG "DECnet: dn_route_rx_packet: rt_flags=0x%02x dev=%s len=%d src=0x%04hx dst=0x%04hx err=%d type=%d\n", (int)cb->rt_flags, devname, skb->len, @@ -573,7 +580,7 @@ int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type struct dn_skb_cb *cb; unsigned char flags = 0; __u16 len = le16_to_cpu(*(__le16 *)skb->data); - struct dn_dev *dn = (struct dn_dev *)dev->dn_ptr; + struct dn_dev *dn = rcu_dereference(dev->dn_ptr); unsigned char padlen = 0; if (!net_eq(dev_net(dev), &init_net)) @@ -728,7 +735,7 @@ static int dn_forward(struct sk_buff *skb) { struct dn_skb_cb *cb = DN_SKB_CB(skb); struct dst_entry *dst = skb_dst(skb); - struct dn_dev *dn_db = dst->dev->dn_ptr; + struct dn_dev *dn_db = rcu_dereference(dst->dev->dn_ptr); struct dn_route *rt; struct neighbour *neigh = dst->neighbour; int header_len; @@ -835,13 +842,16 @@ static inline int dn_match_addr(__le16 addr1, __le16 addr2) static __le16 dnet_select_source(const struct net_device *dev, __le16 daddr, int scope) { __le16 saddr = 0; - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db; struct dn_ifaddr *ifa; int best_match = 0; int ret; - read_lock(&dev_base_lock); - for(ifa = dn_db->ifa_list; ifa; ifa = ifa->ifa_next) { + rcu_read_lock(); + dn_db = rcu_dereference(dev->dn_ptr); + for (ifa = rcu_dereference(dn_db->ifa_list); + ifa != NULL; + ifa = rcu_dereference(ifa->ifa_next)) { if (ifa->ifa_scope > scope) continue; if (!daddr) { @@ -854,7 +864,7 @@ static __le16 dnet_select_source(const struct net_device *dev, __le16 daddr, int if (best_match == 0) saddr = ifa->ifa_local; } - read_unlock(&dev_base_lock); + rcu_read_unlock(); return saddr; } @@ -1020,7 +1030,7 @@ source_ok: err = -ENODEV; if (dev_out == NULL) goto out; - dn_db = dev_out->dn_ptr; + dn_db = rcu_dereference_raw(dev_out->dn_ptr); /* Possible improvement - check all devices for local addr */ if (dn_dev_islocal(dev_out, fl.fld_dst)) { dev_put(dev_out); @@ -1171,7 +1181,7 @@ static int __dn_route_output_key(struct dst_entry **pprt, const struct flowi *fl if ((flp->fld_dst == rt->fl.fld_dst) && (flp->fld_src == rt->fl.fld_src) && (flp->mark == rt->fl.mark) && - (rt->fl.iif == 0) && + dn_is_output_route(rt) && (rt->fl.oif == flp->oif)) { dst_use(&rt->dst, jiffies); rcu_read_unlock_bh(); @@ -1233,7 +1243,7 @@ static int dn_route_input_slow(struct sk_buff *skb) dev_hold(in_dev); - if ((dn_db = in_dev->dn_ptr) == NULL) + if ((dn_db = rcu_dereference(in_dev->dn_ptr)) == NULL) goto out; /* Zero source addresses are not allowed */ @@ -1502,7 +1512,7 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, if (rtnl_put_cacheinfo(skb, &rt->dst, 0, 0, 0, expires, rt->dst.error) < 0) goto rtattr_failure; - if (rt->fl.iif) + if (dn_is_input_route(rt)) RTA_PUT(skb, RTA_IIF, sizeof(int), &rt->fl.iif); nlh->nlmsg_len = skb_tail_pointer(skb) - b; @@ -1677,15 +1687,15 @@ static struct dn_route *dn_rt_cache_get_next(struct seq_file *seq, struct dn_rou { struct dn_rt_cache_iter_state *s = seq->private; - rt = rt->dst.dn_next; - while(!rt) { + rt = rcu_dereference_bh(rt->dst.dn_next); + while (!rt) { rcu_read_unlock_bh(); if (--s->bucket < 0) break; rcu_read_lock_bh(); - rt = dn_rt_hash_table[s->bucket].chain; + rt = rcu_dereference_bh(dn_rt_hash_table[s->bucket].chain); } - return rcu_dereference_bh(rt); + return rt; } static void *dn_rt_cache_seq_start(struct seq_file *seq, loff_t *pos) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 96bc7f9..c6e2aff 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -506,8 +506,8 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) struct net_device *dev = NULL; rcu_read_lock(); - if (rt->fl.iif && - net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) + if (rt_is_input_route(rt) && + net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) dev = dev_get_by_index_rcu(net, rt->fl.iif); if (dev) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 3c53c2d..0f0e0f0 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -149,11 +149,17 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc); static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta); + +static void ip_mc_list_reclaim(struct rcu_head *head) +{ + kfree(container_of(head, struct ip_mc_list, rcu)); +} + static void ip_ma_put(struct ip_mc_list *im) { if (atomic_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); - kfree(im); + call_rcu(&im->rcu, ip_mc_list_reclaim); } } @@ -163,7 +169,7 @@ static void ip_ma_put(struct ip_mc_list *im) * Timer management */ -static __inline__ void igmp_stop_timer(struct ip_mc_list *im) +static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); if (del_timer(&im->timer)) @@ -496,14 +502,24 @@ empty_source: return skb; } +#define for_each_pmc_rcu(in_dev, pmc) \ + for (pmc = rcu_dereference(in_dev->mc_list); \ + pmc != NULL; \ + pmc = rcu_dereference(pmc->next_rcu)) + +#define for_each_pmc_rtnl(in_dev, pmc) \ + for (pmc = rtnl_dereference(in_dev->mc_list); \ + pmc != NULL; \ + pmc = rtnl_dereference(pmc->next_rcu)) + static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) { struct sk_buff *skb = NULL; int type; if (!pmc) { - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; spin_lock_bh(&pmc->lock); @@ -514,7 +530,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } else { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) @@ -556,7 +572,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) struct sk_buff *skb = NULL; int type, dtype; - read_lock(&in_dev->mc_list_lock); + rcu_read_lock(); spin_lock_bh(&in_dev->mc_tomb_lock); /* deleted MCA's */ @@ -593,7 +609,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) spin_unlock_bh(&in_dev->mc_tomb_lock); /* change recs */ - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rcu(in_dev, pmc) { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) { type = IGMPV3_BLOCK_OLD_SOURCES; @@ -616,7 +632,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) } spin_unlock_bh(&pmc->lock); } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); if (!skb) return; @@ -813,14 +829,14 @@ static void igmp_heard_report(struct in_device *in_dev, __be32 group) if (group == IGMP_ALL_HOSTS) return; - read_lock(&in_dev->mc_list_lock); - for (im=in_dev->mc_list; im!=NULL; im=im->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == group) { igmp_stop_timer(im); break; } } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, @@ -906,8 +922,8 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, * - Use the igmp->igmp_code field as the maximum * delay possible */ - read_lock(&in_dev->mc_list_lock); - for (im=in_dev->mc_list; im!=NULL; im=im->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, im) { int changed; if (group && group != im->multiaddr) @@ -925,7 +941,7 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (changed) igmp_mod_timer(im, max_delay); } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } /* called in rcu_read_lock() section */ @@ -961,7 +977,7 @@ int igmp_rcv(struct sk_buff *skb) case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: /* Is it our report looped back? */ - if (skb_rtable(skb)->fl.iif == 0) + if (rt_is_output_route(skb_rtable(skb))) break; /* don't rely on MC router hearing unicast reports */ if (skb->pkt_type == PACKET_MULTICAST || @@ -1110,8 +1126,8 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) kfree(pmc); } /* clear dead sources, too */ - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { struct ip_sf_list *psf, *psf_next; spin_lock_bh(&pmc->lock); @@ -1123,7 +1139,7 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) kfree(psf); } } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } #endif @@ -1209,7 +1225,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) ASSERT_RTNL(); - for (im=in_dev->mc_list; im; im=im->next) { + for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) { im->users++; ip_mc_add_src(in_dev, &addr, MCAST_EXCLUDE, 0, NULL, 0); @@ -1217,7 +1233,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) } } - im = kmalloc(sizeof(*im), GFP_KERNEL); + im = kzalloc(sizeof(*im), GFP_KERNEL); if (!im) goto out; @@ -1227,26 +1243,18 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) im->multiaddr = addr; /* initial mode is (EX, empty) */ im->sfmode = MCAST_EXCLUDE; - im->sfcount[MCAST_INCLUDE] = 0; im->sfcount[MCAST_EXCLUDE] = 1; - im->sources = NULL; - im->tomb = NULL; - im->crcount = 0; atomic_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST - im->tm_running = 0; setup_timer(&im->timer, &igmp_timer_expire, (unsigned long)im); im->unsolicit_count = IGMP_Unsolicited_Report_Count; - im->reporter = 0; - im->gsquery = 0; #endif - im->loaded = 0; - write_lock_bh(&in_dev->mc_list_lock); - im->next = in_dev->mc_list; - in_dev->mc_list = im; + + im->next_rcu = in_dev->mc_list; in_dev->mc_count++; - write_unlock_bh(&in_dev->mc_list_lock); + rcu_assign_pointer(in_dev->mc_list, im); + #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im->multiaddr); #endif @@ -1287,17 +1295,18 @@ EXPORT_SYMBOL(ip_mc_rejoin_group); void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) { - struct ip_mc_list *i, **ip; + struct ip_mc_list *i; + struct ip_mc_list __rcu **ip; ASSERT_RTNL(); - for (ip=&in_dev->mc_list; (i=*ip)!=NULL; ip=&i->next) { + for (ip = &in_dev->mc_list; + (i = rtnl_dereference(*ip)) != NULL; + ip = &i->next_rcu) { if (i->multiaddr == addr) { if (--i->users == 0) { - write_lock_bh(&in_dev->mc_list_lock); - *ip = i->next; + *ip = i->next_rcu; in_dev->mc_count--; - write_unlock_bh(&in_dev->mc_list_lock); igmp_group_dropped(i); if (!in_dev->dead) @@ -1316,34 +1325,34 @@ EXPORT_SYMBOL(ip_mc_dec_group); void ip_mc_unmap(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); - for (i = in_dev->mc_list; i; i = i->next) - igmp_group_dropped(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_dropped(pmc); } void ip_mc_remap(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); - for (i = in_dev->mc_list; i; i = i->next) - igmp_group_added(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_added(pmc); } /* Device going down */ void ip_mc_down(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); - for (i=in_dev->mc_list; i; i=i->next) - igmp_group_dropped(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST in_dev->mr_ifc_count = 0; @@ -1374,7 +1383,6 @@ void ip_mc_init_dev(struct in_device *in_dev) in_dev->mr_qrv = IGMP_Unsolicited_Report_Count; #endif - rwlock_init(&in_dev->mc_list_lock); spin_lock_init(&in_dev->mc_tomb_lock); } @@ -1382,14 +1390,14 @@ void ip_mc_init_dev(struct in_device *in_dev) void ip_mc_up(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); - for (i=in_dev->mc_list; i; i=i->next) - igmp_group_added(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_added(pmc); } /* @@ -1405,17 +1413,13 @@ void ip_mc_destroy_dev(struct in_device *in_dev) /* Deactivate timers */ ip_mc_down(in_dev); - write_lock_bh(&in_dev->mc_list_lock); - while ((i = in_dev->mc_list) != NULL) { - in_dev->mc_list = i->next; + while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { + in_dev->mc_list = i->next_rcu; in_dev->mc_count--; - write_unlock_bh(&in_dev->mc_list_lock); + igmp_group_dropped(i); ip_ma_put(i); - - write_lock_bh(&in_dev->mc_list_lock); } - write_unlock_bh(&in_dev->mc_list_lock); } /* RTNL is locked */ @@ -1513,18 +1517,18 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (!in_dev) return -ENODEV; - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif @@ -1685,18 +1689,18 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (!in_dev) return -ENODEV; - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); @@ -1793,7 +1797,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) err = -EADDRINUSE; ifindex = imr->imr_ifindex; - for (i = inet->mc_list; i; i = i->next) { + for_each_pmc_rtnl(inet, i) { if (i->multi.imr_multiaddr.s_addr == addr && i->multi.imr_ifindex == ifindex) goto done; @@ -1807,7 +1811,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); - iml->next = inet->mc_list; + iml->next_rcu = inet->mc_list; iml->sflist = NULL; iml->sfmode = MCAST_EXCLUDE; rcu_assign_pointer(inet->mc_list, iml); @@ -1821,17 +1825,14 @@ EXPORT_SYMBOL(ip_mc_join_group); static void ip_sf_socklist_reclaim(struct rcu_head *rp) { - struct ip_sf_socklist *psf; - - psf = container_of(rp, struct ip_sf_socklist, rcu); + kfree(container_of(rp, struct ip_sf_socklist, rcu)); /* sk_omem_alloc should have been decreased by the caller*/ - kfree(psf); } static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { - struct ip_sf_socklist *psf = iml->sflist; + struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; if (psf == NULL) { @@ -1851,11 +1852,8 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, static void ip_mc_socklist_reclaim(struct rcu_head *rp) { - struct ip_mc_socklist *iml; - - iml = container_of(rp, struct ip_mc_socklist, rcu); + kfree(container_of(rp, struct ip_mc_socklist, rcu)); /* sk_omem_alloc should have been decreased by the caller*/ - kfree(iml); } @@ -1866,7 +1864,8 @@ static void ip_mc_socklist_reclaim(struct rcu_head *rp) int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); - struct ip_mc_socklist *iml, **imlp; + struct ip_mc_socklist *iml; + struct ip_mc_socklist __rcu **imlp; struct in_device *in_dev; struct net *net = sock_net(sk); __be32 group = imr->imr_multiaddr.s_addr; @@ -1876,7 +1875,9 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) rtnl_lock(); in_dev = ip_mc_find_dev(net, imr); ifindex = imr->imr_ifindex; - for (imlp = &inet->mc_list; (iml = *imlp) != NULL; imlp = &iml->next) { + for (imlp = &inet->mc_list; + (iml = rtnl_dereference(*imlp)) != NULL; + imlp = &iml->next_rcu) { if (iml->multi.imr_multiaddr.s_addr != group) continue; if (ifindex) { @@ -1888,7 +1889,7 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) (void) ip_mc_leave_src(sk, iml, in_dev); - rcu_assign_pointer(*imlp, iml->next); + *imlp = iml->next_rcu; if (in_dev) ip_mc_dec_group(in_dev, group); @@ -1934,7 +1935,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct } err = -EADDRNOTAVAIL; - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if ((pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr) && (pmc->multi.imr_ifindex == imr.imr_ifindex)) @@ -1958,7 +1959,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct pmc->sfmode = omode; } - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ @@ -2077,7 +2078,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) goto done; } - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; @@ -2107,7 +2108,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) (void) ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, 0, NULL, 0); } - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); if (psl) { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); @@ -2155,7 +2156,7 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, } err = -EADDRNOTAVAIL; - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; @@ -2163,7 +2164,7 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, if (!pmc) /* must have a prior join */ goto done; msf->imsf_fmode = pmc->sfmode; - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); rtnl_unlock(); if (!psl) { len = 0; @@ -2208,7 +2209,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, err = -EADDRNOTAVAIL; - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == addr && pmc->multi.imr_ifindex == gsf->gf_interface) break; @@ -2216,7 +2217,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, if (!pmc) /* must have a prior join */ goto done; gsf->gf_fmode = pmc->sfmode; - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); rtnl_unlock(); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; @@ -2257,7 +2258,7 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) goto out; rcu_read_lock(); - for (pmc=rcu_dereference(inet->mc_list); pmc; pmc=rcu_dereference(pmc->next)) { + for_each_pmc_rcu(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == loc_addr && pmc->multi.imr_ifindex == dif) break; @@ -2265,7 +2266,7 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) ret = inet->mc_all; if (!pmc) goto unlock; - psl = pmc->sflist; + psl = rcu_dereference(pmc->sflist); ret = (pmc->sfmode == MCAST_EXCLUDE); if (!psl) goto unlock; @@ -2300,10 +2301,10 @@ void ip_mc_drop_socket(struct sock *sk) return; rtnl_lock(); - while ((iml = inet->mc_list) != NULL) { + while ((iml = rtnl_dereference(inet->mc_list)) != NULL) { struct in_device *in_dev; - rcu_assign_pointer(inet->mc_list, iml->next); + inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); if (in_dev != NULL) @@ -2321,8 +2322,8 @@ int ip_check_mc(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 p struct ip_sf_list *psf; int rv = 0; - read_lock(&in_dev->mc_list_lock); - for (im=in_dev->mc_list; im; im=im->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == mc_addr) break; } @@ -2343,7 +2344,7 @@ int ip_check_mc(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 p } else rv = 1; /* unspecified source; tentatively allow */ } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); return rv; } @@ -2369,13 +2370,11 @@ static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) in_dev = __in_dev_get_rcu(state->dev); if (!in_dev) continue; - read_lock(&in_dev->mc_list_lock); - im = in_dev->mc_list; + im = rcu_dereference(in_dev->mc_list); if (im) { state->in_dev = in_dev; break; } - read_unlock(&in_dev->mc_list_lock); } return im; } @@ -2383,11 +2382,9 @@ static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_list *im) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); - im = im->next; - while (!im) { - if (likely(state->in_dev != NULL)) - read_unlock(&state->in_dev->mc_list_lock); + im = rcu_dereference(im->next_rcu); + while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->in_dev = NULL; @@ -2396,8 +2393,7 @@ static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_li state->in_dev = __in_dev_get_rcu(state->dev); if (!state->in_dev) continue; - read_lock(&state->in_dev->mc_list_lock); - im = state->in_dev->mc_list; + im = rcu_dereference(state->in_dev->mc_list); } return im; } @@ -2433,10 +2429,8 @@ static void igmp_mc_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); - if (likely(state->in_dev != NULL)) { - read_unlock(&state->in_dev->mc_list_lock); - state->in_dev = NULL; - } + + state->in_dev = NULL; state->dev = NULL; rcu_read_unlock(); } @@ -2458,7 +2452,7 @@ static int igmp_mc_seq_show(struct seq_file *seq, void *v) querier = "NONE"; #endif - if (state->in_dev->mc_list == im) { + if (rcu_dereference(state->in_dev->mc_list) == im) { seq_printf(seq, "%d\t%-10s: %5d %7s\n", state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } @@ -2517,8 +2511,7 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) idev = __in_dev_get_rcu(state->dev); if (unlikely(idev == NULL)) continue; - read_lock(&idev->mc_list_lock); - im = idev->mc_list; + im = rcu_dereference(idev->mc_list); if (likely(im != NULL)) { spin_lock_bh(&im->lock); psf = im->sources; @@ -2529,7 +2522,6 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) } spin_unlock_bh(&im->lock); } - read_unlock(&idev->mc_list_lock); } return psf; } @@ -2543,9 +2535,6 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l spin_unlock_bh(&state->im->lock); state->im = state->im->next; while (!state->im) { - if (likely(state->idev != NULL)) - read_unlock(&state->idev->mc_list_lock); - state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; @@ -2554,8 +2543,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l state->idev = __in_dev_get_rcu(state->dev); if (!state->idev) continue; - read_lock(&state->idev->mc_list_lock); - state->im = state->idev->mc_list; + state->im = rcu_dereference(state->idev->mc_list); } if (!state->im) break; @@ -2601,10 +2589,7 @@ static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) spin_unlock_bh(&state->im->lock); state->im = NULL; } - if (likely(state->idev != NULL)) { - read_unlock(&state->idev->mc_list_lock); - state->idev = NULL; - } + state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 70ff77f..cab2057 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -634,7 +634,7 @@ static int ipgre_rcv(struct sk_buff *skb) #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { /* Looped back packet, drop it! */ - if (skb_rtable(skb)->fl.iif == 0) + if (rt_is_output_route(skb_rtable(skb))) goto drop; tunnel->dev->stats.multicast++; skb->pkt_type = PACKET_BROADCAST; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 86dd569..ef2b008 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1654,7 +1654,7 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, if (mrt->vif_table[vif].dev != skb->dev) { int true_vifi; - if (skb_rtable(skb)->fl.iif == 0) { + if (rt_is_output_route(skb_rtable(skb))) { /* It is our own packet, looped back. * Very complicated situation... * diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 987bf9a..66610ea 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -140,13 +140,15 @@ static unsigned long expires_ljiffies; static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static void ipv4_dst_destroy(struct dst_entry *dst); -static void ipv4_dst_ifdown(struct dst_entry *dst, - struct net_device *dev, int how); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu); static int rt_garbage_collect(struct dst_ops *ops); +static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, + int how) +{ +} static struct dst_ops ipv4_dst_ops = { .family = AF_INET, @@ -621,7 +623,7 @@ static inline int rt_fast_clean(struct rtable *rth) /* Kill broadcast/multicast entries very aggresively, if they collide in hash table with more useful entries */ return (rth->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) && - rth->fl.iif && rth->dst.rt_next; + rt_is_input_route(rth) && rth->dst.rt_next; } static inline int rt_valuable(struct rtable *rth) @@ -666,7 +668,7 @@ static inline u32 rt_score(struct rtable *rt) if (rt_valuable(rt)) score |= (1<<31); - if (!rt->fl.iif || + if (rt_is_output_route(rt) || !(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL))) score |= (1<<30); @@ -1124,7 +1126,7 @@ restart: */ rt->dst.flags |= DST_NOCACHE; - if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) { + if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) { int err = arp_bind_neighbour(&rt->dst); if (err) { if (net_ratelimit()) @@ -1222,7 +1224,7 @@ restart: /* Try to bind route to arp only if it is output route or unicast forwarding path. */ - if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) { + if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) { int err = arp_bind_neighbour(&rt->dst); if (err) { spin_unlock_bh(rt_hash_lock_addr(hash)); @@ -1404,7 +1406,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, if (rth->fl.fl4_dst != daddr || rth->fl.fl4_src != skeys[i] || rth->fl.oif != ikeys[k] || - rth->fl.iif != 0 || + rt_is_input_route(rth) || rt_is_expired(rth) || !net_eq(dev_net(rth->dst.dev), net)) { rthp = &rth->dst.rt_next; @@ -1433,8 +1435,6 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, rt->dst.child = NULL; if (rt->dst.dev) dev_hold(rt->dst.dev); - if (rt->idev) - in_dev_hold(rt->idev); rt->dst.obsolete = -1; rt->dst.lastuse = jiffies; rt->dst.path = &rt->dst; @@ -1666,7 +1666,7 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, rth->rt_dst != daddr || rth->rt_src != iph->saddr || rth->fl.oif != ikeys[k] || - rth->fl.iif != 0 || + rt_is_input_route(rth) || dst_metric_locked(&rth->dst, RTAX_MTU) || !net_eq(dev_net(rth->dst.dev), net) || rt_is_expired(rth)) @@ -1728,33 +1728,13 @@ static void ipv4_dst_destroy(struct dst_entry *dst) { struct rtable *rt = (struct rtable *) dst; struct inet_peer *peer = rt->peer; - struct in_device *idev = rt->idev; if (peer) { rt->peer = NULL; inet_putpeer(peer); } - - if (idev) { - rt->idev = NULL; - in_dev_put(idev); - } } -static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, - int how) -{ - struct rtable *rt = (struct rtable *) dst; - struct in_device *idev = rt->idev; - if (dev != dev_net(dev)->loopback_dev && idev && idev->dev == dev) { - struct in_device *loopback_idev = - in_dev_get(dev_net(dev)->loopback_dev); - if (loopback_idev) { - rt->idev = loopback_idev; - in_dev_put(idev); - } - } -} static void ipv4_link_failure(struct sk_buff *skb) { @@ -1790,7 +1770,7 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt) __be32 src; struct fib_result res; - if (rt->fl.iif == 0) + if (rt_is_output_route(rt)) src = rt->rt_src; else { rcu_read_lock(); @@ -1910,7 +1890,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->fl.iif = dev->ifindex; rth->dst.dev = init_net.loopback_dev; dev_hold(rth->dst.dev); - rth->idev = in_dev_get(rth->dst.dev); rth->fl.oif = 0; rth->rt_gateway = daddr; rth->rt_spec_dst= spec_dst; @@ -2050,7 +2029,6 @@ static int __mkroute_input(struct sk_buff *skb, rth->fl.iif = in_dev->dev->ifindex; rth->dst.dev = (out_dev)->dev; dev_hold(rth->dst.dev); - rth->idev = in_dev_get(rth->dst.dev); rth->fl.oif = 0; rth->rt_spec_dst= spec_dst; @@ -2231,7 +2209,6 @@ local_input: rth->fl.iif = dev->ifindex; rth->dst.dev = net->loopback_dev; dev_hold(rth->dst.dev); - rth->idev = in_dev_get(rth->dst.dev); rth->rt_gateway = daddr; rth->rt_spec_dst= spec_dst; rth->dst.input= ip_local_deliver; @@ -2417,9 +2394,6 @@ static int __mkroute_output(struct rtable **result, if (!rth) return -ENOBUFS; - in_dev_hold(in_dev); - rth->idev = in_dev; - atomic_set(&rth->dst.__refcnt, 1); rth->dst.flags= DST_HOST; if (IN_DEV_CONF_GET(in_dev, NOXFRM)) @@ -2695,7 +2669,7 @@ int __ip_route_output_key(struct net *net, struct rtable **rp, rth = rcu_dereference_bh(rth->dst.rt_next)) { if (rth->fl.fl4_dst == flp->fl4_dst && rth->fl.fl4_src == flp->fl4_src && - rth->fl.iif == 0 && + rt_is_output_route(rth) && rth->fl.oif == flp->oif && rth->fl.mark == flp->mark && !((rth->fl.fl4_tos ^ flp->fl4_tos) & @@ -2759,9 +2733,6 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi rt->fl = ort->fl; - rt->idev = ort->idev; - if (rt->idev) - in_dev_hold(rt->idev); rt->rt_genid = rt_genid(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; @@ -2853,7 +2824,7 @@ static int rt_fill_info(struct net *net, if (rt->dst.tclassid) NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid); #endif - if (rt->fl.iif) + if (rt_is_input_route(rt)) NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst); else if (rt->rt_src != rt->fl.fl4_src) NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_src); @@ -2878,7 +2849,7 @@ static int rt_fill_info(struct net *net, } } - if (rt->fl.iif) { + if (rt_is_input_route(rt)) { #ifdef CONFIG_IP_MROUTE __be32 dst = rt->rt_dst; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0814199..2bb46d5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1193,7 +1193,7 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq), - KERN_INFO "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", + "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt); #endif @@ -1477,10 +1477,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, * shouldn't happen. */ if (WARN(before(*seq, TCP_SKB_CB(skb)->seq), - KERN_INFO "recvmsg bug: copied %X " - "seq %X rcvnxt %X fl %X\n", *seq, - TCP_SKB_CB(skb)->seq, tp->rcv_nxt, - flags)) + "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n", + *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, + flags)) break; offset = *seq - TCP_SKB_CB(skb)->seq; @@ -1490,10 +1489,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, goto found_ok_skb; if (tcp_hdr(skb)->fin) goto found_fin_ok; - WARN(!(flags & MSG_PEEK), KERN_INFO "recvmsg bug 2: " - "copied %X seq %X rcvnxt %X fl %X\n", - *seq, TCP_SKB_CB(skb)->seq, - tp->rcv_nxt, flags); + WARN(!(flags & MSG_PEEK), + "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n", + *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags); } /* Well, if we have backlog, try to process it now yet. */ diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 4464f3b..dd1fd8c 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -80,10 +80,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.dst.dev = dev; dev_hold(dev); - xdst->u.rt.idev = in_dev_get(dev); - if (!xdst->u.rt.idev) - return -ENODEV; - xdst->u.rt.peer = rt->peer; if (rt->peer) atomic_inc(&rt->peer->refcnt); @@ -189,8 +185,6 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - if (likely(xdst->u.rt.idev)) - in_dev_put(xdst->u.rt.idev); if (likely(xdst->u.rt.peer)) inet_putpeer(xdst->u.rt.peer); xfrm_dst_destroy(xdst); @@ -199,27 +193,9 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int unregister) { - struct xfrm_dst *xdst; - if (!unregister) return; - xdst = (struct xfrm_dst *)dst; - if (xdst->u.rt.idev->dev == dev) { - struct in_device *loopback_idev = - in_dev_get(dev_net(dev)->loopback_dev); - BUG_ON(!loopback_idev); - - do { - in_dev_put(xdst->u.rt.idev); - xdst->u.rt.idev = loopback_idev; - in_dev_hold(loopback_idev); - xdst = (struct xfrm_dst *)xdst->u.dst.child; - } while (xdst->u.dst.xfrm); - - __in_dev_put(loopback_idev); - } - xfrm_dst_ifdown(dst, dev); } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index de04ea3..10bd39c 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -169,7 +169,7 @@ __ip_vs_reroute_locally(struct sk_buff *skb) struct net *net = dev_net(dev); struct iphdr *iph = ip_hdr(skb); - if (rt->fl.iif) { + if (rt_is_input_route(rt)) { unsigned long orefdst = skb->_skb_refdst; if (ip_route_input(skb, iph->daddr, iph->saddr, @@ -552,7 +552,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #endif /* From world but DNAT to loopback address? */ - if (local && ipv4_is_loopback(rt->rt_dst) && skb_rtable(skb)->fl.iif) { + if (local && ipv4_is_loopback(rt->rt_dst) && + rt_is_input_route(skb_rtable(skb))) { IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): " "stopping DNAT to loopback address"); goto tx_error_put; @@ -1165,7 +1166,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #endif /* From world but DNAT to loopback address? */ - if (local && ipv4_is_loopback(rt->rt_dst) && skb_rtable(skb)->fl.iif) { + if (local && ipv4_is_loopback(rt->rt_dst) && + rt_is_input_route(skb_rtable(skb))) { IP_VS_DBG(1, "%s(): " "stopping DNAT to loopback %pI4\n", __func__, &cp->daddr.ip); diff --git a/net/socket.c b/net/socket.c index 3ca2fd9..c898df7 100644 --- a/net/socket.c +++ b/net/socket.c @@ -156,7 +156,7 @@ static const struct file_operations socket_file_ops = { */ static DEFINE_SPINLOCK(net_family_lock); -static const struct net_proto_family *net_families[NPROTO] __read_mostly; +static const struct net_proto_family __rcu *net_families[NPROTO] __read_mostly; /* * Statistics counters of the socket lists @@ -1200,7 +1200,7 @@ int __sock_create(struct net *net, int family, int type, int protocol, * requested real, full-featured networking support upon configuration. * Otherwise module support will break! */ - if (net_families[family] == NULL) + if (rcu_access_pointer(net_families[family]) == NULL) request_module("net-pf-%d", family); #endif @@ -2332,10 +2332,11 @@ int sock_register(const struct net_proto_family *ops) } spin_lock(&net_family_lock); - if (net_families[ops->family]) + if (rcu_dereference_protected(net_families[ops->family], + lockdep_is_held(&net_family_lock))) err = -EEXIST; else { - net_families[ops->family] = ops; + rcu_assign_pointer(net_families[ops->family], ops); err = 0; } spin_unlock(&net_family_lock); @@ -2363,7 +2364,7 @@ void sock_unregister(int family) BUG_ON(family < 0 || family >= NPROTO); spin_lock(&net_family_lock); - net_families[family] = NULL; + rcu_assign_pointer(net_families[family], NULL); spin_unlock(&net_family_lock); synchronize_rcu(); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3c95304..7ff31c6 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -316,7 +316,8 @@ static void unix_write_space(struct sock *sk) if (unix_writable(sk)) { wq = rcu_dereference(sk->sk_wq); if (wq_has_sleeper(wq)) - wake_up_interruptible_sync(&wq->wait); + wake_up_interruptible_sync_poll(&wq->wait, + POLLOUT | POLLWRNORM | POLLWRBAND); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); @@ -1710,7 +1711,8 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, goto out_unlock; } - wake_up_interruptible_sync(&u->peer_wait); + wake_up_interruptible_sync_poll(&u->peer_wait, + POLLOUT | POLLWRNORM | POLLWRBAND); if (msg->msg_name) unix_copy_addr(msg, skb->sk); @@ -2072,13 +2074,12 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) mask |= POLLERR; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP; + mask |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= POLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue) || - (sk->sk_shutdown & RCV_SHUTDOWN)) + if (!skb_queue_empty(&sk->sk_receive_queue)) mask |= POLLIN | POLLRDNORM; /* Connection-based need to check for termination and startup */ @@ -2090,20 +2091,19 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, return mask; } - /* writable? */ - writable = unix_writable(sk); - if (writable) { - other = unix_peer_get(sk); - if (other) { - if (unix_peer(other) != sk) { - sock_poll_wait(file, &unix_sk(other)->peer_wait, - wait); - if (unix_recvq_full(other)) - writable = 0; - } + /* No write status requested, avoid expensive OUT tests. */ + if (wait && !(wait->key & (POLLWRBAND | POLLWRNORM | POLLOUT))) + return mask; - sock_put(other); + writable = unix_writable(sk); + other = unix_peer_get(sk); + if (other) { + if (unix_peer(other) != sk) { + sock_poll_wait(file, &unix_sk(other)->peer_wait, wait); + if (unix_recvq_full(other)) + writable = 0; } + sock_put(other); } if (writable) |