diff options
Diffstat (limited to 'net/dccp')
-rw-r--r-- | net/dccp/Kconfig | 13 | ||||
-rw-r--r-- | net/dccp/Makefile | 9 | ||||
-rw-r--r-- | net/dccp/ackvec.c | 296 | ||||
-rw-r--r-- | net/dccp/ackvec.h | 53 | ||||
-rw-r--r-- | net/dccp/ccid.c | 189 | ||||
-rw-r--r-- | net/dccp/ccid.h | 129 | ||||
-rw-r--r-- | net/dccp/ccids/Kconfig | 43 | ||||
-rw-r--r-- | net/dccp/ccids/Makefile | 4 | ||||
-rw-r--r-- | net/dccp/ccids/ccid2.c | 779 | ||||
-rw-r--r-- | net/dccp/ccids/ccid2.h | 85 | ||||
-rw-r--r-- | net/dccp/ccids/ccid3.c | 112 | ||||
-rw-r--r-- | net/dccp/ccids/ccid3.h | 5 | ||||
-rw-r--r-- | net/dccp/dccp.h | 133 | ||||
-rw-r--r-- | net/dccp/diag.c | 2 | ||||
-rw-r--r-- | net/dccp/feat.c | 586 | ||||
-rw-r--r-- | net/dccp/feat.h | 29 | ||||
-rw-r--r-- | net/dccp/input.c | 28 | ||||
-rw-r--r-- | net/dccp/ipv4.c | 333 | ||||
-rw-r--r-- | net/dccp/ipv6.c | 371 | ||||
-rw-r--r-- | net/dccp/minisocks.c | 37 | ||||
-rw-r--r-- | net/dccp/options.c | 291 | ||||
-rw-r--r-- | net/dccp/output.c | 88 | ||||
-rw-r--r-- | net/dccp/proto.c | 440 | ||||
-rw-r--r-- | net/dccp/sysctl.c | 124 | ||||
-rw-r--r-- | net/dccp/timer.c | 14 |
25 files changed, 3154 insertions, 1039 deletions
diff --git a/net/dccp/Kconfig b/net/dccp/Kconfig index 187ac18..7e096ba 100644 --- a/net/dccp/Kconfig +++ b/net/dccp/Kconfig @@ -24,6 +24,10 @@ config INET_DCCP_DIAG def_tristate y if (IP_DCCP = y && INET_DIAG = y) def_tristate m +config IP_DCCP_ACKVEC + depends on IP_DCCP + def_bool N + source "net/dccp/ccids/Kconfig" menu "DCCP Kernel Hacking" @@ -36,15 +40,6 @@ config IP_DCCP_DEBUG Just say N. -config IP_DCCP_UNLOAD_HACK - depends on IP_DCCP=m && IP_DCCP_CCID3=m - bool "DCCP control sock unload hack" - ---help--- - Enable this to be able to unload the dccp module when the it - has only one refcount held, the control sock one. Just execute - "rmmod dccp_ccid3 dccp" - - Just say N. endmenu endmenu diff --git a/net/dccp/Makefile b/net/dccp/Makefile index 87b27ff..7696e21 100644 --- a/net/dccp/Makefile +++ b/net/dccp/Makefile @@ -2,15 +2,18 @@ obj-$(CONFIG_IPV6) += dccp_ipv6.o dccp_ipv6-y := ipv6.o -obj-$(CONFIG_IP_DCCP) += dccp.o +obj-$(CONFIG_IP_DCCP) += dccp.o dccp_ipv4.o -dccp-y := ccid.o input.o ipv4.o minisocks.o options.o output.o proto.o \ - timer.o +dccp-y := ccid.o feat.o input.o minisocks.o options.o output.o proto.o timer.o + +dccp_ipv4-y := ipv4.o dccp-$(CONFIG_IP_DCCP_ACKVEC) += ackvec.o obj-$(CONFIG_INET_DCCP_DIAG) += dccp_diag.o +dccp-$(CONFIG_SYSCTL) += sysctl.o + dccp_diag-y := diag.o obj-y += ccids/ diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 2c77daf..b5981e5 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -13,36 +13,83 @@ #include "dccp.h" #include <linux/dccp.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/kernel.h> #include <linux/skbuff.h> +#include <linux/slab.h> #include <net/sock.h> +static kmem_cache_t *dccp_ackvec_slab; +static kmem_cache_t *dccp_ackvec_record_slab; + +static struct dccp_ackvec_record *dccp_ackvec_record_new(void) +{ + struct dccp_ackvec_record *avr = + kmem_cache_alloc(dccp_ackvec_record_slab, GFP_ATOMIC); + + if (avr != NULL) + INIT_LIST_HEAD(&avr->dccpavr_node); + + return avr; +} + +static void dccp_ackvec_record_delete(struct dccp_ackvec_record *avr) +{ + if (unlikely(avr == NULL)) + return; + /* Check if deleting a linked record */ + WARN_ON(!list_empty(&avr->dccpavr_node)); + kmem_cache_free(dccp_ackvec_record_slab, avr); +} + +static void dccp_ackvec_insert_avr(struct dccp_ackvec *av, + struct dccp_ackvec_record *avr) +{ + /* + * 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->dccpav_records)) { + const struct dccp_ackvec_record *head = + list_entry(av->dccpav_records.next, + struct dccp_ackvec_record, + dccpavr_node); + BUG_ON(before48(avr->dccpavr_ack_seqno, + head->dccpavr_ack_seqno)); + } + + list_add(&avr->dccpavr_node, &av->dccpav_records); +} + int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); +#ifdef CONFIG_IP_DCCP_DEBUG + const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ? + "CLIENT tx: " : "server tx: "; +#endif struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; int len = av->dccpav_vec_len + 2; struct timeval now; u32 elapsed_time; unsigned char *to, *from; + struct dccp_ackvec_record *avr; + + if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) + return -1; dccp_timestamp(sk, &now); elapsed_time = timeval_delta(&now, &av->dccpav_time) / 10; - if (elapsed_time != 0) - dccp_insert_option_elapsed_time(sk, skb, elapsed_time); - - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) + if (elapsed_time != 0 && + dccp_insert_option_elapsed_time(sk, skb, elapsed_time)) return -1; - /* - * XXX: now we have just one ack vector sent record, so - * we have to wait for it to be cleared. - * - * Of course this is not acceptable, but this is just for - * basic testing now. - */ - if (av->dccpav_ack_seqno != DCCP_MAX_SEQNO + 1) + avr = dccp_ackvec_record_new(); + if (avr == NULL) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; @@ -55,8 +102,8 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) from = av->dccpav_buf + av->dccpav_buf_head; /* Check if buf_head wraps */ - if ((int)av->dccpav_buf_head + len > av->dccpav_vec_len) { - const u32 tailsize = av->dccpav_vec_len - av->dccpav_buf_head; + if ((int)av->dccpav_buf_head + len > DCCP_MAX_ACKVEC_LEN) { + const u32 tailsize = DCCP_MAX_ACKVEC_LEN - av->dccpav_buf_head; memcpy(to, from, tailsize); to += tailsize; @@ -73,45 +120,37 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) * 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. - * - * This implemention uses just one ack record for now. */ - av->dccpav_ack_seqno = DCCP_SKB_CB(skb)->dccpd_seq; - av->dccpav_ack_ptr = av->dccpav_buf_head; - av->dccpav_ack_ackno = av->dccpav_buf_ackno; - av->dccpav_ack_nonce = av->dccpav_buf_nonce; - av->dccpav_sent_len = av->dccpav_vec_len; + avr->dccpavr_ack_seqno = DCCP_SKB_CB(skb)->dccpd_seq; + avr->dccpavr_ack_ptr = av->dccpav_buf_head; + avr->dccpavr_ack_ackno = av->dccpav_buf_ackno; + avr->dccpavr_ack_nonce = av->dccpav_buf_nonce; + avr->dccpavr_sent_len = av->dccpav_vec_len; + + dccp_ackvec_insert_avr(av, avr); dccp_pr_debug("%sACK Vector 0, len=%d, ack_seqno=%llu, " "ack_ackno=%llu\n", - debug_prefix, av->dccpav_sent_len, - (unsigned long long)av->dccpav_ack_seqno, - (unsigned long long)av->dccpav_ack_ackno); - return -1; + debug_prefix, avr->dccpavr_sent_len, + (unsigned long long)avr->dccpavr_ack_seqno, + (unsigned long long)avr->dccpavr_ack_ackno); + return 0; } -struct dccp_ackvec *dccp_ackvec_alloc(const unsigned int len, - const gfp_t priority) +struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) { - struct dccp_ackvec *av; - - BUG_ON(len == 0); + struct dccp_ackvec *av = kmem_cache_alloc(dccp_ackvec_slab, priority); - if (len > DCCP_MAX_ACKVEC_LEN) - return NULL; - - av = kmalloc(sizeof(*av) + len, priority); if (av != NULL) { - av->dccpav_buf_len = len; av->dccpav_buf_head = - av->dccpav_buf_tail = av->dccpav_buf_len - 1; - av->dccpav_buf_ackno = - av->dccpav_ack_ackno = av->dccpav_ack_seqno = ~0LLU; + av->dccpav_buf_tail = DCCP_MAX_ACKVEC_LEN - 1; + av->dccpav_buf_ackno = DCCP_MAX_SEQNO + 1; av->dccpav_buf_nonce = av->dccpav_buf_nonce = 0; av->dccpav_ack_ptr = 0; av->dccpav_time.tv_sec = 0; av->dccpav_time.tv_usec = 0; av->dccpav_sent_len = av->dccpav_vec_len = 0; + INIT_LIST_HEAD(&av->dccpav_records); } return av; @@ -119,7 +158,20 @@ struct dccp_ackvec *dccp_ackvec_alloc(const unsigned int len, void dccp_ackvec_free(struct dccp_ackvec *av) { - kfree(av); + if (unlikely(av == NULL)) + return; + + if (!list_empty(&av->dccpav_records)) { + struct dccp_ackvec_record *avr, *next; + + list_for_each_entry_safe(avr, next, &av->dccpav_records, + dccpavr_node) { + list_del_init(&avr->dccpavr_node); + dccp_ackvec_record_delete(avr); + } + } + + kmem_cache_free(dccp_ackvec_slab, av); } static inline u8 dccp_ackvec_state(const struct dccp_ackvec *av, @@ -146,7 +198,7 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, unsigned int gap; long new_head; - if (av->dccpav_vec_len + packets > av->dccpav_buf_len) + if (av->dccpav_vec_len + packets > DCCP_MAX_ACKVEC_LEN) return -ENOBUFS; gap = packets - 1; @@ -158,7 +210,7 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, gap + new_head + 1); gap = -new_head; } - new_head += av->dccpav_buf_len; + new_head += DCCP_MAX_ACKVEC_LEN; } av->dccpav_buf_head = new_head; @@ -251,7 +303,7 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, goto out_duplicate; delta -= len + 1; - if (++index == av->dccpav_buf_len) + if (++index == DCCP_MAX_ACKVEC_LEN) index = 0; } } @@ -259,7 +311,6 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, av->dccpav_buf_ackno = ackno; dccp_timestamp(sk, &av->dccpav_time); out: - dccp_pr_debug(""); return 0; out_duplicate: @@ -297,44 +348,50 @@ void dccp_ackvec_print(const struct dccp_ackvec *av) } #endif -static void dccp_ackvec_throw_away_ack_record(struct dccp_ackvec *av) +static void dccp_ackvec_throw_record(struct dccp_ackvec *av, + struct dccp_ackvec_record *avr) { - /* - * As we're keeping track of the ack vector size (dccpav_vec_len) and - * the sent ack vector size (dccpav_sent_len) we don't need - * dccpav_buf_tail at all, but keep this code here as in the future - * we'll implement a vector of ack records, as suggested in - * draft-ietf-dccp-spec-11.txt Appendix A. -acme - */ -#if 0 - u32 new_buf_tail = av->dccpav_ack_ptr + 1; - if (new_buf_tail >= av->dccpav_vec_len) - new_buf_tail -= av->dccpav_vec_len; - av->dccpav_buf_tail = new_buf_tail; -#endif - av->dccpav_vec_len -= av->dccpav_sent_len; + struct dccp_ackvec_record *next; + + av->dccpav_buf_tail = avr->dccpavr_ack_ptr - 1; + if (av->dccpav_buf_tail == 0) + av->dccpav_buf_tail = DCCP_MAX_ACKVEC_LEN - 1; + + av->dccpav_vec_len -= avr->dccpavr_sent_len; + + /* free records */ + list_for_each_entry_safe_from(avr, next, &av->dccpav_records, + dccpavr_node) { + list_del_init(&avr->dccpavr_node); + dccp_ackvec_record_delete(avr); + } } void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, struct sock *sk, const u64 ackno) { - /* Check if we actually sent an ACK vector */ - if (av->dccpav_ack_seqno == DCCP_MAX_SEQNO + 1) - return; + struct dccp_ackvec_record *avr; - if (ackno == av->dccpav_ack_seqno) { + /* + * If we traverse backwards, it should be faster when we have large + * windows. We will be receiving ACKs for stuff we sent a while back + * -sorbo. + */ + list_for_each_entry_reverse(avr, &av->dccpav_records, dccpavr_node) { + if (ackno == avr->dccpavr_ack_seqno) { #ifdef CONFIG_IP_DCCP_DEBUG - struct dccp_sock *dp = dccp_sk(sk); - const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ? - "CLIENT rx ack: " : "server rx ack: "; + struct dccp_sock *dp = dccp_sk(sk); + const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ? + "CLIENT rx ack: " : "server rx ack: "; #endif - dccp_pr_debug("%sACK packet 0, len=%d, ack_seqno=%llu, " - "ack_ackno=%llu, ACKED!\n", - debug_prefix, 1, - (unsigned long long)av->dccpav_ack_seqno, - (unsigned long long)av->dccpav_ack_ackno); - dccp_ackvec_throw_away_ack_record(av); - av->dccpav_ack_seqno = DCCP_MAX_SEQNO + 1; + dccp_pr_debug("%sACK packet 0, len=%d, ack_seqno=%llu, " + "ack_ackno=%llu, ACKED!\n", + debug_prefix, 1, + (unsigned long long)avr->dccpavr_ack_seqno, + (unsigned long long)avr->dccpavr_ack_ackno); + dccp_ackvec_throw_record(av, avr); + break; + } } } @@ -344,28 +401,20 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, const unsigned char *vector) { unsigned char i; + struct dccp_ackvec_record *avr; /* Check if we actually sent an ACK vector */ - if (av->dccpav_ack_seqno == DCCP_MAX_SEQNO + 1) - return; - /* - * We're in the receiver half connection, so if the received an ACK - * vector ackno (e.g. 50) before dccpav_ack_seqno (e.g. 52), we're - * not interested. - * - * Extra explanation with example: - * - * if we received an ACK vector with ackno 50, it can only be acking - * 50, 49, 48, etc, not 52 (the seqno for the ACK vector we sent). - */ - /* dccp_pr_debug("is %llu < %llu? ", ackno, av->dccpav_ack_seqno); */ - if (before48(ackno, av->dccpav_ack_seqno)) { - /* dccp_pr_debug_cat("yes\n"); */ + if (list_empty(&av->dccpav_records)) return; - } - /* dccp_pr_debug_cat("no\n"); */ i = len; + /* + * XXX + * I think it might be more efficient to work backwards. See comment on + * rcv_ackno. -sorbo. + */ + avr = list_entry(av->dccpav_records.next, struct dccp_ackvec_record, + dccpavr_node); while (i--) { const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; u64 ackno_end_rl; @@ -373,14 +422,20 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, dccp_set_seqno(&ackno_end_rl, ackno - rl); /* - * dccp_pr_debug("is %llu <= %llu <= %llu? ", ackno_end_rl, - * av->dccpav_ack_seqno, ackno); + * If our AVR sequence number is greater than the ack, go + * forward in the AVR list until it is not so. */ - if (between48(av->dccpav_ack_seqno, ackno_end_rl, ackno)) { + list_for_each_entry_from(avr, &av->dccpav_records, + dccpavr_node) { + if (!after48(avr->dccpavr_ack_seqno, ackno)) + goto found; + } + /* End of the dccpav_records list, not found, exit */ + break; +found: + if (between48(avr->dccpavr_ack_seqno, ackno_end_rl, ackno)) { const u8 state = (*vector & DCCP_ACKVEC_STATE_MASK) >> 6; - /* dccp_pr_debug_cat("yes\n"); */ - if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED) { #ifdef CONFIG_IP_DCCP_DEBUG struct dccp_sock *dp = dccp_sk(sk); @@ -393,19 +448,16 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, "ACKED!\n", debug_prefix, len, (unsigned long long) - av->dccpav_ack_seqno, + avr->dccpavr_ack_seqno, (unsigned long long) - av->dccpav_ack_ackno); - dccp_ackvec_throw_away_ack_record(av); + avr->dccpavr_ack_ackno); + dccp_ackvec_throw_record(av, avr); } /* - * If dccpav_ack_seqno was not received, no problem - * we'll send another ACK vector. + * If it wasn't received, continue scanning... we might + * find another one. */ - av->dccpav_ack_seqno = DCCP_MAX_SEQNO + 1; - break; } - /* dccp_pr_debug_cat("no\n"); */ dccp_set_seqno(&ackno, ackno_end_rl - 1); ++vector; @@ -424,3 +476,43 @@ int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb, len, value); return 0; } + +static char dccp_ackvec_slab_msg[] __initdata = + KERN_CRIT "DCCP: Unable to create ack vectors slab caches\n"; + +int __init dccp_ackvec_init(void) +{ + dccp_ackvec_slab = kmem_cache_create("dccp_ackvec", + sizeof(struct dccp_ackvec), 0, + SLAB_HWCACHE_ALIGN, NULL, NULL); + 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, NULL); + if (dccp_ackvec_record_slab == NULL) + goto out_destroy_slab; + + return 0; + +out_destroy_slab: + kmem_cache_destroy(dccp_ackvec_slab); + dccp_ackvec_slab = NULL; +out_err: + printk(dccp_ackvec_slab_msg); + return -ENOBUFS; +} + +void dccp_ackvec_exit(void) +{ + if (dccp_ackvec_slab != NULL) { + kmem_cache_destroy(dccp_ackvec_slab); + dccp_ackvec_slab = NULL; + } + if (dccp_ackvec_record_slab != NULL) { + kmem_cache_destroy(dccp_ackvec_record_slab); + dccp_ackvec_record_slab = NULL; + } +} diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h index f7dfb5f..ec7a89b 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -13,6 +13,7 @@ #include <linux/config.h> #include <linux/compiler.h> +#include <linux/list.h> #include <linux/time.h> #include <linux/types.h> @@ -42,39 +43,57 @@ * Ack Vectors it has recently sent. For each packet sent carrying an * Ack Vector, it remembers four variables: * - * @dccpav_ack_seqno - the Sequence Number used for the packet - * (HC-Receiver seqno) * @dccpav_ack_ptr - the value of buf_head at the time of acknowledgement. - * @dccpav_ack_ackno - the Acknowledgement Number used for the packet - * (HC-Sender seqno) + * @dccpav_records - list of dccp_ackvec_record * @dccpav_ack_nonce - the one-bit sum of the ECN Nonces for all State 0. * - * @dccpav_buf_len - circular buffer length * @dccpav_time - the time in usecs * @dccpav_buf - circular buffer of acknowledgeable packets */ struct dccp_ackvec { u64 dccpav_buf_ackno; - u64 dccpav_ack_seqno; - u64 dccpav_ack_ackno; + struct list_head dccpav_records; struct timeval dccpav_time; u8 dccpav_buf_head; u8 dccpav_buf_tail; u8 dccpav_ack_ptr; u8 dccpav_sent_len; u8 dccpav_vec_len; - u8 dccpav_buf_len; u8 dccpav_buf_nonce; u8 dccpav_ack_nonce; - u8 dccpav_buf[0]; + u8 dccpav_buf[DCCP_MAX_ACKVEC_LEN]; +}; + +/** struct dccp_ackvec_record - ack vector record + * + * ACK vector record as defined in Appendix A of spec. + * + * The list is sorted by dccpavr_ack_seqno + * + * @dccpavr_node - node in dccpav_records + * @dccpavr_ack_seqno - sequence number of the packet this record was sent on + * @dccpavr_ack_ackno - sequence number being acknowledged + * @dccpavr_ack_ptr - pointer into dccpav_buf where this record starts + * @dccpavr_ack_nonce - dccpav_ack_nonce at the time this record was sent + * @dccpavr_sent_len - lenght of the record in dccpav_buf + */ +struct dccp_ackvec_record { + struct list_head dccpavr_node; + u64 dccpavr_ack_seqno; + u64 dccpavr_ack_ackno; + u8 dccpavr_ack_ptr; + u8 dccpavr_ack_nonce; + u8 dccpavr_sent_len; }; struct sock; struct sk_buff; #ifdef CONFIG_IP_DCCP_ACKVEC -extern struct dccp_ackvec *dccp_ackvec_alloc(unsigned int len, - const gfp_t priority); +extern int dccp_ackvec_init(void); +extern void dccp_ackvec_exit(void); + +extern struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority); extern void dccp_ackvec_free(struct dccp_ackvec *av); extern int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, @@ -92,8 +111,16 @@ static inline int dccp_ackvec_pending(const struct dccp_ackvec *av) return av->dccpav_sent_len != av->dccpav_vec_len; } #else /* CONFIG_IP_DCCP_ACKVEC */ -static inline struct dccp_ackvec *dccp_ackvec_alloc(unsigned int len, - const gfp_t priority) +static inline int dccp_ackvec_init(void) +{ + return 0; +} + +static inline void dccp_ackvec_exit(void) +{ +} + +static inline struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) { return NULL; } diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index 9d8fc0e..ff05e59 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -13,7 +13,7 @@ #include "ccid.h" -static struct ccid *ccids[CCID_MAX]; +static struct ccid_operations *ccids[CCID_MAX]; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT) static atomic_t ccids_lockct = ATOMIC_INIT(0); static DEFINE_SPINLOCK(ccids_lock); @@ -55,85 +55,202 @@ static inline void ccids_read_unlock(void) #define ccids_read_unlock() do { } while(0) #endif -int ccid_register(struct ccid *ccid) +static kmem_cache_t *ccid_kmem_cache_create(int obj_size, const char *fmt,...) { - int err; + kmem_cache_t *slab; + char slab_name_fmt[32], *slab_name; + va_list args; - if (ccid->ccid_init == NULL) - return -1; + va_start(args, fmt); + vsnprintf(slab_name_fmt, sizeof(slab_name_fmt), fmt, args); + va_end(args); + + slab_name = kstrdup(slab_name_fmt, GFP_KERNEL); + if (slab_name == NULL) + return NULL; + slab = kmem_cache_create(slab_name, sizeof(struct ccid) + obj_size, 0, + SLAB_HWCACHE_ALIGN, NULL, NULL); + if (slab == NULL) + kfree(slab_name); + return slab; +} + +static void ccid_kmem_cache_destroy(kmem_cache_t *slab) +{ + if (slab != NULL) { + const char *name = kmem_cache_name(slab); + + kmem_cache_destroy(slab); + kfree(name); + } +} + +int ccid_register(struct ccid_operations *ccid_ops) +{ + int err = -ENOBUFS; + + ccid_ops->ccid_hc_rx_slab = + ccid_kmem_cache_create(ccid_ops->ccid_hc_rx_obj_size, + "%s_hc_rx_sock", + ccid_ops->ccid_name); + if (ccid_ops->ccid_hc_rx_slab == NULL) + goto out; + + ccid_ops->ccid_hc_tx_slab = + ccid_kmem_cache_create(ccid_ops->ccid_hc_tx_obj_size, + "%s_hc_tx_sock", + ccid_ops->ccid_name); + if (ccid_ops->ccid_hc_tx_slab == NULL) + goto out_free_rx_slab; ccids_write_lock(); err = -EEXIST; - if (ccids[ccid->ccid_id] == NULL) { - ccids[ccid->ccid_id] = ccid; + if (ccids[ccid_ops->ccid_id] == NULL) { + ccids[ccid_ops->ccid_id] = ccid_ops; err = 0; } ccids_write_unlock(); - if (err == 0) - pr_info("CCID: Registered CCID %d (%s)\n", - ccid->ccid_id, ccid->ccid_name); + if (err != 0) + goto out_free_tx_slab; + + pr_info("CCID: Registered CCID %d (%s)\n", + ccid_ops->ccid_id, ccid_ops->ccid_name); +out: return err; +out_free_tx_slab: + ccid_kmem_cache_destroy(ccid_ops->ccid_hc_tx_slab); + ccid_ops->ccid_hc_tx_slab = NULL; + goto out; +out_free_rx_slab: + ccid_kmem_cache_destroy(ccid_ops->ccid_hc_rx_slab); + ccid_ops->ccid_hc_rx_slab = NULL; + goto out; } EXPORT_SYMBOL_GPL(ccid_register); -int ccid_unregister(struct ccid *ccid) +int ccid_unregister(struct ccid_operations *ccid_ops) { ccids_write_lock(); - ccids[ccid->ccid_id] = NULL; + ccids[ccid_ops->ccid_id] = NULL; ccids_write_unlock(); + + ccid_kmem_cache_destroy(ccid_ops->ccid_hc_tx_slab); + ccid_ops->ccid_hc_tx_slab = NULL; + ccid_kmem_cache_destroy(ccid_ops->ccid_hc_rx_slab); + ccid_ops->ccid_hc_rx_slab = NULL; + pr_info("CCID: Unregistered CCID %d (%s)\n", - ccid->ccid_id, ccid->ccid_name); + ccid_ops->ccid_id, ccid_ops->ccid_name); return 0; } EXPORT_SYMBOL_GPL(ccid_unregister); -struct ccid *ccid_init(unsigned char id, struct sock *sk) +struct ccid *ccid_new(unsigned char id, struct sock *sk, int rx, gfp_t gfp) { - struct ccid *ccid; + struct ccid_operations *ccid_ops; + struct ccid *ccid = NULL; + ccids_read_lock(); #ifdef CONFIG_KMOD - if (ccids[id] == NULL) + if (ccids[id] == NULL) { + /* We only try to load if in process context */ + ccids_read_unlock(); + if (gfp & GFP_ATOMIC) + goto out; request_module("net-dccp-ccid-%d", id); + ccids_read_lock(); + } #endif - ccids_read_lock(); + ccid_ops = ccids[id]; + if (ccid_ops == NULL) + goto out_unlock; - ccid = ccids[id]; - if (ccid == NULL) - goto out; + if (!try_module_get(ccid_ops->ccid_owner)) + goto out_unlock; - if (!try_module_get(ccid->ccid_owner)) - goto out_err; + ccids_read_unlock(); - if (ccid->ccid_init(sk) != 0) + ccid = kmem_cache_alloc(rx ? ccid_ops->ccid_hc_rx_slab : + ccid_ops->ccid_hc_tx_slab, gfp); + if (ccid == NULL) goto out_module_put; + ccid->ccid_ops = ccid_ops; + if (rx) { + memset(ccid + 1, 0, ccid_ops->ccid_hc_rx_obj_size); + if (ccid->ccid_ops->ccid_hc_rx_init != NULL && + ccid->ccid_ops->ccid_hc_rx_init(ccid, sk) != 0) + goto out_free_ccid; + } else { + memset(ccid + 1, 0, ccid_ops->ccid_hc_tx_obj_size); + if (ccid->ccid_ops->ccid_hc_tx_init != NULL && + ccid->ccid_ops->ccid_hc_tx_init(ccid, sk) != 0) + goto out_free_ccid; + } out: - ccids_read_unlock(); return ccid; -out_module_put: - module_put(ccid->ccid_owner); -out_err: +out_unlock: + ccids_read_unlock(); + goto out; +out_free_ccid: + kmem_cache_free(rx ? ccid_ops->ccid_hc_rx_slab : + ccid_ops->ccid_hc_tx_slab, ccid); ccid = NULL; +out_module_put: + module_put(ccid_ops->ccid_owner); goto out; } -EXPORT_SYMBOL_GPL(ccid_init); +EXPORT_SYMBOL_GPL(ccid_new); + +struct ccid *ccid_hc_rx_new(unsigned char id, struct sock *sk, gfp_t gfp) +{ + return ccid_new(id, sk, 1, gfp); +} + +EXPORT_SYMBOL_GPL(ccid_hc_rx_new); + +struct ccid *ccid_hc_tx_new(unsigned char id,struct sock *sk, gfp_t gfp) +{ + return ccid_new(id, sk, 0, gfp); +} + +EXPORT_SYMBOL_GPL(ccid_hc_tx_new); -void ccid_exit(struct ccid *ccid, struct sock *sk) +static void ccid_delete(struct ccid *ccid, struct sock *sk, int rx) { + struct ccid_operations *ccid_ops; + if (ccid == NULL) return; + ccid_ops = ccid->ccid_ops; + if (rx) { + if (ccid_ops->ccid_hc_rx_exit != NULL) + ccid_ops->ccid_hc_rx_exit(sk); + kmem_cache_free(ccid_ops->ccid_hc_rx_slab, ccid); + } else { + if (ccid_ops->ccid_hc_tx_exit != NULL) + ccid_ops->ccid_hc_tx_exit(sk); + kmem_cache_free(ccid_ops->ccid_hc_tx_slab, ccid); + } ccids_read_lock(); + if (ccids[ccid_ops->ccid_id] != NULL) + module_put(ccid_ops->ccid_owner); + ccids_read_unlock(); +} - if (ccids[ccid->ccid_id] != NULL) { - if (ccid->ccid_exit != NULL) - ccid->ccid_exit(sk); - module_put(ccid->ccid_owner); - } +void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk) +{ + ccid_delete(ccid, sk, 1); +} - ccids_read_unlock(); +EXPORT_SYMBOL_GPL(ccid_hc_rx_delete); + +void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk) +{ + ccid_delete(ccid, sk, 0); } -EXPORT_SYMBOL_GPL(ccid_exit); +EXPORT_SYMBOL_GPL(ccid_hc_tx_delete); diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index de681c6..f7eb6c6 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -23,14 +23,16 @@ struct tcp_info; -struct ccid { +struct ccid_operations { unsigned char ccid_id; const char *ccid_name; struct module *ccid_owner; - int (*ccid_init)(struct sock *sk); - void (*ccid_exit)(struct sock *sk); - int (*ccid_hc_rx_init)(struct sock *sk); - int (*ccid_hc_tx_init)(struct sock *sk); + kmem_cache_t *ccid_hc_rx_slab; + __u32 ccid_hc_rx_obj_size; + kmem_cache_t *ccid_hc_tx_slab; + __u32 ccid_hc_tx_obj_size; + int (*ccid_hc_rx_init)(struct ccid *ccid, struct sock *sk); + int (*ccid_hc_tx_init)(struct ccid *ccid, struct sock *sk); void (*ccid_hc_rx_exit)(struct sock *sk); void (*ccid_hc_tx_exit)(struct sock *sk); void (*ccid_hc_rx_packet_recv)(struct sock *sk, @@ -39,9 +41,9 @@ struct ccid { unsigned char option, unsigned char len, u16 idx, unsigned char* value); - void (*ccid_hc_rx_insert_options)(struct sock *sk, + int (*ccid_hc_rx_insert_options)(struct sock *sk, struct sk_buff *skb); - void (*ccid_hc_tx_insert_options)(struct sock *sk, + int (*ccid_hc_tx_insert_options)(struct sock *sk, struct sk_buff *skb); void (*ccid_hc_tx_packet_recv)(struct sock *sk, struct sk_buff *skb); @@ -67,75 +69,58 @@ struct ccid { int __user *optlen); }; -extern int ccid_register(struct ccid *ccid); -extern int ccid_unregister(struct ccid *ccid); +extern int ccid_register(struct ccid_operations *ccid_ops); +extern int ccid_unregister(struct ccid_operations *ccid_ops); -extern struct ccid *ccid_init(unsigned char id, struct sock *sk); -extern void ccid_exit(struct ccid *ccid, struct sock *sk); +struct ccid { + struct ccid_operations *ccid_ops; + char ccid_priv[0]; +}; -static inline void __ccid_get(struct ccid *ccid) +static inline void *ccid_priv(const struct ccid *ccid) { - __module_get(ccid->ccid_owner); + return (void *)ccid->ccid_priv; } +extern struct ccid *ccid_new(unsigned char id, struct sock *sk, int rx, + gfp_t gfp); + +extern struct ccid *ccid_hc_rx_new(unsigned char id, struct sock *sk, + gfp_t gfp); +extern struct ccid *ccid_hc_tx_new(unsigned char id, struct sock *sk, + gfp_t gfp); + +extern void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk); +extern void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk); + static inline int ccid_hc_tx_send_packet(struct ccid *ccid, struct sock *sk, struct sk_buff *skb, int len) { int rc = 0; - if (ccid->ccid_hc_tx_send_packet != NULL) - rc = ccid->ccid_hc_tx_send_packet(sk, skb, len); + if (ccid->ccid_ops->ccid_hc_tx_send_packet != NULL) + rc = ccid->ccid_ops->ccid_hc_tx_send_packet(sk, skb, len); return rc; } static inline void ccid_hc_tx_packet_sent(struct ccid *ccid, struct sock *sk, int more, int len) { - if (ccid->ccid_hc_tx_packet_sent != NULL) - ccid->ccid_hc_tx_packet_sent(sk, more, len); -} - -static inline int ccid_hc_rx_init(struct ccid *ccid, struct sock *sk) -{ - int rc = 0; - if (ccid->ccid_hc_rx_init != NULL) - rc = ccid->ccid_hc_rx_init(sk); - return rc; -} - -static inline int ccid_hc_tx_init(struct ccid *ccid, struct sock *sk) -{ - int rc = 0; - if (ccid->ccid_hc_tx_init != NULL) - rc = ccid->ccid_hc_tx_init(sk); - return rc; -} - -static inline void ccid_hc_rx_exit(struct ccid *ccid, struct sock *sk) -{ - if (ccid != NULL && ccid->ccid_hc_rx_exit != NULL && - dccp_sk(sk)->dccps_hc_rx_ccid_private != NULL) - ccid->ccid_hc_rx_exit(sk); -} - -static inline void ccid_hc_tx_exit(struct ccid *ccid, struct sock *sk) -{ - if (ccid != NULL && ccid->ccid_hc_tx_exit != NULL && - dccp_sk(sk)->dccps_hc_tx_ccid_private != NULL) - ccid->ccid_hc_tx_exit(sk); + if (ccid->ccid_ops->ccid_hc_tx_packet_sent != NULL) + ccid->ccid_ops->ccid_hc_tx_packet_sent(sk, more, len); } static inline void ccid_hc_rx_packet_recv(struct ccid *ccid, struct sock *sk, struct sk_buff *skb) { - if (ccid->ccid_hc_rx_packet_recv != NULL) - ccid->ccid_hc_rx_packet_recv(sk, skb); + if (ccid->ccid_ops->ccid_hc_rx_packet_recv != NULL) + ccid->ccid_ops->ccid_hc_rx_packet_recv(sk, skb); } static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk, struct sk_buff *skb) { - if (ccid->ccid_hc_tx_packet_recv != NULL) - ccid->ccid_hc_tx_packet_recv(sk, skb); + if (ccid->ccid_ops->ccid_hc_tx_packet_recv != NULL) + ccid->ccid_ops->ccid_hc_tx_packet_recv(sk, skb); } static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, @@ -144,8 +129,8 @@ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, unsigned char* value) { int rc = 0; - if (ccid->ccid_hc_tx_parse_options != NULL) - rc = ccid->ccid_hc_tx_parse_options(sk, option, len, idx, + if (ccid->ccid_ops->ccid_hc_tx_parse_options != NULL) + rc = ccid->ccid_ops->ccid_hc_tx_parse_options(sk, option, len, idx, value); return rc; } @@ -156,37 +141,39 @@ static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk, unsigned char* value) { int rc = 0; - if (ccid->ccid_hc_rx_parse_options != NULL) - rc = ccid->ccid_hc_rx_parse_options(sk, option, len, idx, value); + if (ccid->ccid_ops->ccid_hc_rx_parse_options != NULL) + rc = ccid->ccid_ops->ccid_hc_rx_parse_options(sk, option, len, idx, value); return rc; } -static inline void ccid_hc_tx_insert_options(struct ccid *ccid, struct sock *sk, - struct sk_buff *skb) +static inline int ccid_hc_tx_insert_options(struct ccid *ccid, struct sock *sk, + struct sk_buff *skb) { - if (ccid->ccid_hc_tx_insert_options != NULL) - ccid->ccid_hc_tx_insert_options(sk, skb); + if (ccid->ccid_ops->ccid_hc_tx_insert_options != NULL) + return ccid->ccid_ops->ccid_hc_tx_insert_options(sk, skb); + return 0; } -static inline void ccid_hc_rx_insert_options(struct ccid *ccid, struct sock *sk, - struct sk_buff *skb) +static inline int ccid_hc_rx_insert_options(struct ccid *ccid, struct sock *sk, + struct sk_buff *skb) { - if (ccid->ccid_hc_rx_insert_options != NULL) - ccid->ccid_hc_rx_insert_options(sk, skb); + if (ccid->ccid_ops->ccid_hc_rx_insert_options != NULL) + return ccid->ccid_ops->ccid_hc_rx_insert_options(sk, skb); + return 0; } static inline void ccid_hc_rx_get_info(struct ccid *ccid, struct sock *sk, struct tcp_info *info) { - if (ccid->ccid_hc_rx_get_info != NULL) - ccid->ccid_hc_rx_get_info(sk, info); + if (ccid->ccid_ops->ccid_hc_rx_get_info != NULL) + ccid->ccid_ops->ccid_hc_rx_get_info(sk, info); } static inline void ccid_hc_tx_get_info(struct ccid *ccid, struct sock *sk, struct tcp_info *info) { - if (ccid->ccid_hc_tx_get_info != NULL) - ccid->ccid_hc_tx_get_info(sk, info); + if (ccid->ccid_ops->ccid_hc_tx_get_info != NULL) + ccid->ccid_ops->ccid_hc_tx_get_info(sk, info); } static inline int ccid_hc_rx_getsockopt(struct ccid *ccid, struct sock *sk, @@ -194,8 +181,8 @@ static inline int ccid_hc_rx_getsockopt(struct ccid *ccid, struct sock *sk, u32 __user *optval, int __user *optlen) { int rc = -ENOPROTOOPT; - if (ccid->ccid_hc_rx_getsockopt != NULL) - rc = ccid->ccid_hc_rx_getsockopt(sk, optname, len, + if (ccid->ccid_ops->ccid_hc_rx_getsockopt != NULL) + rc = ccid->ccid_ops->ccid_hc_rx_getsockopt(sk, optname, len, optval, optlen); return rc; } @@ -205,8 +192,8 @@ static inline int ccid_hc_tx_getsockopt(struct ccid *ccid, struct sock *sk, u32 __user *optval, int __user *optlen) { int rc = -ENOPROTOOPT; - if (ccid->ccid_hc_tx_getsockopt != NULL) - rc = ccid->ccid_hc_tx_getsockopt(sk, optname, len, + if (ccid->ccid_ops->ccid_hc_tx_getsockopt != NULL) + rc = ccid->ccid_ops->ccid_hc_tx_getsockopt(sk, optname, len, optval, optlen); return rc; } diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig index 7684d83..ca00191 100644 --- a/net/dccp/ccids/Kconfig +++ b/net/dccp/ccids/Kconfig @@ -1,9 +1,39 @@ menu "DCCP CCIDs Configuration (EXPERIMENTAL)" depends on IP_DCCP && EXPERIMENTAL +config IP_DCCP_CCID2 + tristate "CCID2 (TCP-Like) (EXPERIMENTAL)" + depends on IP_DCCP + def_tristate IP_DCCP + select IP_DCCP_ACKVEC + ---help--- + CCID 2, TCP-like Congestion Control, denotes Additive Increase, + Multiplicative Decrease (AIMD) congestion control with behavior + modelled directly on TCP, including congestion window, slow start, + timeouts, and so forth [RFC 2581]. CCID 2 achieves maximum + bandwidth over the long term, consistent with the use of end-to-end + congestion control, but halves its congestion window in response to + each congestion event. This leads to the abrupt rate changes + typical of TCP. Applications should use CCID 2 if they prefer + maximum bandwidth utilization to steadiness of rate. This is often + the case for applications that are not playing their data directly + to the user. For example, a hypothetical application that + transferred files over DCCP, using application-level retransmissions + for lost packets, would prefer CCID 2 to CCID 3. On-line games may + also prefer CCID 2. + + CCID 2 is further described in: + http://www.icir.org/kohler/dccp/draft-ietf-dccp-ccid2-10.txt + + This text was extracted from: + http://www.icir.org/kohler/dccp/draft-ietf-dccp-spec-13.txt + + If in doubt, say M. + config IP_DCCP_CCID3 - tristate "CCID3 (TFRC) (EXPERIMENTAL)" + tristate "CCID3 (TCP-Friendly) (EXPERIMENTAL)" depends on IP_DCCP + def_tristate IP_DCCP ---help--- CCID 3 denotes TCP-Friendly Rate Control (TFRC), an equation-based rate-controlled congestion control mechanism. TFRC is designed to @@ -15,10 +45,15 @@ config IP_DCCP_CCID3 suitable than CCID 2 for applications such streaming media where a relatively smooth sending rate is of importance. - CCID 3 is further described in [CCID 3 PROFILE]. The TFRC - congestion control algorithms were initially described in RFC 3448. + CCID 3 is further described in: + + http://www.icir.org/kohler/dccp/draft-ietf-dccp-ccid3-11.txt. + + The TFRC congestion control algorithms were initially described in + RFC 3448. - This text was extracted from draft-ietf-dccp-spec-11.txt. + This text was extracted from: + http://www.icir.org/kohler/dccp/draft-ietf-dccp-spec-13.txt If in doubt, say M. diff --git a/net/dccp/ccids/Makefile b/net/dccp/ccids/Makefile index 956f79f..438f20b 100644 --- a/net/dccp/ccids/Makefile +++ b/net/dccp/ccids/Makefile @@ -2,4 +2,8 @@ obj-$(CONFIG_IP_DCCP_CCID3) += dccp_ccid3.o dccp_ccid3-y := ccid3.o +obj-$(CONFIG_IP_DCCP_CCID2) += dccp_ccid2.o + +dccp_ccid2-y := ccid2.o + obj-y += lib/ diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c new file mode 100644 index 0000000..d4f9e2d --- /dev/null +++ b/net/dccp/ccids/ccid2.c @@ -0,0 +1,779 @@ +/* + * net/dccp/ccids/ccid2.c + * + * Copyright (c) 2005, 2006 Andrea Bittau <a.bittau@cs.ucl.ac.uk> + * + * Changes to meet Linux coding standards, and DCCP infrastructure fixes. + * + * Copyright (c) 2006 Arnaldo Carvalho de Melo <acme@conectiva.com.br> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +/* + * This implementation should follow: draft-ietf-dccp-ccid2-10.txt + * + * BUGS: + * - sequence number wrapping + * - jiffies wrapping + */ + +#include <linux/config.h> +#include "../ccid.h" +#include "../dccp.h" +#include "ccid2.h" + +static int ccid2_debug; + +#undef CCID2_DEBUG +#ifdef CCID2_DEBUG +#define ccid2_pr_debug(format, a...) \ + do { if (ccid2_debug) \ + printk(KERN_DEBUG "%s: " format, __FUNCTION__, ##a); \ + } while (0) +#else +#define ccid2_pr_debug(format, a...) +#endif + +static const int ccid2_seq_len = 128; + +#ifdef CCID2_DEBUG +static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx) +{ + int len = 0; + int pipe = 0; + struct ccid2_seq *seqp = hctx->ccid2hctx_seqh; + + /* there is data in the chain */ + if (seqp != hctx->ccid2hctx_seqt) { + seqp = seqp->ccid2s_prev; + len++; + if (!seqp->ccid2s_acked) + pipe++; + + while (seqp != hctx->ccid2hctx_seqt) { + struct ccid2_seq *prev = seqp->ccid2s_prev; + + len++; + if (!prev->ccid2s_acked) + pipe++; + + /* packets are sent sequentially */ + BUG_ON(seqp->ccid2s_seq <= prev->ccid2s_seq); + BUG_ON(seqp->ccid2s_sent < prev->ccid2s_sent); + BUG_ON(len > ccid2_seq_len); + + seqp = prev; + } + } + + BUG_ON(pipe != hctx->ccid2hctx_pipe); + ccid2_pr_debug("len of chain=%d\n", len); + + do { + seqp = seqp->ccid2s_prev; + len++; + BUG_ON(len > ccid2_seq_len); + } while (seqp != hctx->ccid2hctx_seqh); + + BUG_ON(len != ccid2_seq_len); + ccid2_pr_debug("total len=%d\n", len); +} +#else +#define ccid2_hc_tx_check_sanity(hctx) do {} while (0) +#endif + +static int ccid2_hc_tx_send_packet(struct sock *sk, + struct sk_buff *skb, int len) +{ + struct ccid2_hc_tx_sock *hctx; + + switch (DCCP_SKB_CB(skb)->dccpd_type) { + case 0: /* XXX data packets from userland come through like this */ + case DCCP_PKT_DATA: + case DCCP_PKT_DATAACK: + break; + /* No congestion control on other packets */ + default: + return 0; + } + + hctx = ccid2_hc_tx_sk(sk); + + ccid2_pr_debug("pipe=%d cwnd=%d\n", hctx->ccid2hctx_pipe, + hctx->ccid2hctx_cwnd); + + if (hctx->ccid2hctx_pipe < hctx->ccid2hctx_cwnd) { + /* OK we can send... make sure previous packet was sent off */ + if (!hctx->ccid2hctx_sendwait) { + hctx->ccid2hctx_sendwait = 1; + return 0; + } + } + + return 100; /* XXX */ +} + +static void ccid2_change_l_ack_ratio(struct sock *sk, int val) +{ + struct dccp_sock *dp = dccp_sk(sk); + /* + * XXX I don't really agree with val != 2. If cwnd is 1, ack ratio + * should be 1... it shouldn't be allowed to become 2. + * -sorbo. + */ + if (val != 2) { + const struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + int max = hctx->ccid2hctx_cwnd / 2; + + /* round up */ + if (hctx->ccid2hctx_cwnd & 1) + max++; + + if (val > max) + val = max; + } + + ccid2_pr_debug("changing local ack ratio to %d\n", val); + WARN_ON(val <= 0); + dp->dccps_l_ack_ratio = val; +} + +static void ccid2_change_cwnd(struct sock *sk, int val) +{ + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + + if (val == 0) + val = 1; + + /* XXX do we need to change ack ratio? */ + ccid2_pr_debug("change cwnd to %d\n", val); + + BUG_ON(val < 1); + hctx->ccid2hctx_cwnd = val; +} + +static void ccid2_start_rto_timer(struct sock *sk); + +static void ccid2_hc_tx_rto_expire(unsigned long data) +{ + struct sock *sk = (struct sock *)data; + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + long s; + + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer, + jiffies + HZ / 5); + goto out; + } + + ccid2_pr_debug("RTO_EXPIRE\n"); + + ccid2_hc_tx_check_sanity(hctx); + + /* back-off timer */ + hctx->ccid2hctx_rto <<= 1; + + s = hctx->ccid2hctx_rto / HZ; + if (s > 60) + hctx->ccid2hctx_rto = 60 * HZ; + + ccid2_start_rto_timer(sk); + + /* adjust pipe, cwnd etc */ + hctx->ccid2hctx_pipe = 0; + hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd >> 1; + if (hctx->ccid2hctx_ssthresh < 2) + hctx->ccid2hctx_ssthresh = 2; + ccid2_change_cwnd(sk, 1); + + /* clear state about stuff we sent */ + hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqh; + hctx->ccid2hctx_ssacks = 0; + hctx->ccid2hctx_acks = 0; + hctx->ccid2hctx_sent = 0; + + /* clear ack ratio state. */ + hctx->ccid2hctx_arsent = 0; + hctx->ccid2hctx_ackloss = 0; + hctx->ccid2hctx_rpseq = 0; + hctx->ccid2hctx_rpdupack = -1; + ccid2_change_l_ack_ratio(sk, 1); + ccid2_hc_tx_check_sanity(hctx); +out: + bh_unlock_sock(sk); + sock_put(sk); +} + +static void ccid2_start_rto_timer(struct sock *sk) +{ + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + + ccid2_pr_debug("setting RTO timeout=%ld\n", hctx->ccid2hctx_rto); + + BUG_ON(timer_pending(&hctx->ccid2hctx_rtotimer)); + sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer, + jiffies + hctx->ccid2hctx_rto); +} + +static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, int len) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + u64 seq; + + ccid2_hc_tx_check_sanity(hctx); + + BUG_ON(!hctx->ccid2hctx_sendwait); + hctx->ccid2hctx_sendwait = 0; + hctx->ccid2hctx_pipe++; + BUG_ON(hctx->ccid2hctx_pipe < 0); + + /* There is an issue. What if another packet is sent between + * packet_send() and packet_sent(). Then the sequence number would be + * wrong. + * -sorbo. + */ + seq = dp->dccps_gss; + + hctx->ccid2hctx_seqh->ccid2s_seq = seq; + hctx->ccid2hctx_seqh->ccid2s_acked = 0; + hctx->ccid2hctx_seqh->ccid2s_sent = jiffies; + hctx->ccid2hctx_seqh = hctx->ccid2hctx_seqh->ccid2s_next; + + ccid2_pr_debug("cwnd=%d pipe=%d\n", hctx->ccid2hctx_cwnd, + hctx->ccid2hctx_pipe); + + if (hctx->ccid2hctx_seqh == hctx->ccid2hctx_seqt) { + /* XXX allocate more space */ + WARN_ON(1); + } + + hctx->ccid2hctx_sent++; + + /* Ack Ratio. Need to maintain a concept of how many windows we sent */ + hctx->ccid2hctx_arsent++; + /* We had an ack loss in this window... */ + if (hctx->ccid2hctx_ackloss) { + if (hctx->ccid2hctx_arsent >= hctx->ccid2hctx_cwnd) { + hctx->ccid2hctx_arsent = 0; + hctx->ccid2hctx_ackloss = 0; + } + } else { + /* No acks lost up to now... */ + /* decrease ack ratio if enough packets were sent */ + if (dp->dccps_l_ack_ratio > 1) { + /* XXX don't calculate denominator each time */ + int denom = dp->dccps_l_ack_ratio * dp->dccps_l_ack_ratio - + dp->dccps_l_ack_ratio; + + denom = hctx->ccid2hctx_cwnd * hctx->ccid2hctx_cwnd / denom; + + if (hctx->ccid2hctx_arsent >= denom) { + ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio - 1); + hctx->ccid2hctx_arsent = 0; + } + } else { + /* we can't increase ack ratio further [1] */ + hctx->ccid2hctx_arsent = 0; /* or maybe set it to cwnd*/ + } + } + + /* setup RTO timer */ + if (!timer_pending(&hctx->ccid2hctx_rtotimer)) + ccid2_start_rto_timer(sk); + +#ifdef CCID2_DEBUG + ccid2_pr_debug("pipe=%d\n", hctx->ccid2hctx_pipe); + ccid2_pr_debug("Sent: seq=%llu\n", seq); + do { + struct ccid2_seq *seqp = hctx->ccid2hctx_seqt; + + while (seqp != hctx->ccid2hctx_seqh) { + ccid2_pr_debug("out seq=%llu acked=%d time=%lu\n", + seqp->ccid2s_seq, seqp->ccid2s_acked, + seqp->ccid2s_sent); + seqp = seqp->ccid2s_next; + } + } while (0); + ccid2_pr_debug("=========\n"); + ccid2_hc_tx_check_sanity(hctx); +#endif +} + +/* XXX Lame code duplication! + * returns -1 if none was found. + * else returns the next offset to use in the function call. + */ +static int ccid2_ackvector(struct sock *sk, struct sk_buff *skb, int offset, + unsigned char **vec, unsigned char *veclen) +{ + const struct dccp_hdr *dh = dccp_hdr(skb); + unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb); + unsigned char *opt_ptr; + const unsigned char *opt_end = (unsigned char *)dh + + (dh->dccph_doff * 4); + unsigned char opt, len; + unsigned char *value; + + BUG_ON(offset < 0); + options += offset; + opt_ptr = options; + if (opt_ptr >= opt_end) + return -1; + + while (opt_ptr != opt_end) { + opt = *opt_ptr++; + len = 0; + value = NULL; + + /* Check if this isn't a single byte option */ + if (opt > DCCPO_MAX_RESERVED) { + if (opt_ptr == opt_end) + goto out_invalid_option; + + len = *opt_ptr++; + if (len < 3) + goto out_invalid_option; + /* + * Remove the type and len fields, leaving + * just the value size + */ + len -= 2; + value = opt_ptr; + opt_ptr += len; + + if (opt_ptr > opt_end) + goto out_invalid_option; + } + + switch (opt) { + case DCCPO_ACK_VECTOR_0: + case DCCPO_ACK_VECTOR_1: + *vec = value; + *veclen = len; + return offset + (opt_ptr - options); + } + } + + return -1; + +out_invalid_option: + BUG_ON(1); /* should never happen... options were previously parsed ! */ + return -1; +} + +static void ccid2_hc_tx_kill_rto_timer(struct sock *sk) +{ + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + + sk_stop_timer(sk, &hctx->ccid2hctx_rtotimer); + ccid2_pr_debug("deleted RTO timer\n"); +} + +static inline void ccid2_new_ack(struct sock *sk, + struct ccid2_seq *seqp, + unsigned int *maxincr) +{ + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + + /* slow start */ + if (hctx->ccid2hctx_cwnd < hctx->ccid2hctx_ssthresh) { + hctx->ccid2hctx_acks = 0; + + /* We can increase cwnd at most maxincr [ack_ratio/2] */ + if (*maxincr) { + /* increase every 2 acks */ + hctx->ccid2hctx_ssacks++; + if (hctx->ccid2hctx_ssacks == 2) { + ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd + 1); + hctx->ccid2hctx_ssacks = 0; + *maxincr = *maxincr - 1; + } + } else { + /* increased cwnd enough for this single ack */ + hctx->ccid2hctx_ssacks = 0; + } + } else { + hctx->ccid2hctx_ssacks = 0; + hctx->ccid2hctx_acks++; + + if (hctx->ccid2hctx_acks >= hctx->ccid2hctx_cwnd) { + ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd + 1); + hctx->ccid2hctx_acks = 0; + } + } + + /* update RTO */ + if (hctx->ccid2hctx_srtt == -1 || + (jiffies - hctx->ccid2hctx_lastrtt) >= hctx->ccid2hctx_srtt) { + unsigned long r = jiffies - seqp->ccid2s_sent; + int s; + + /* first measurement */ + if (hctx->ccid2hctx_srtt == -1) { + ccid2_pr_debug("R: %lu Time=%lu seq=%llu\n", + r, jiffies, seqp->ccid2s_seq); + hctx->ccid2hctx_srtt = r; + hctx->ccid2hctx_rttvar = r >> 1; + } else { + /* RTTVAR */ + long tmp = hctx->ccid2hctx_srtt - r; + if (tmp < 0) + tmp *= -1; + + tmp >>= 2; + hctx->ccid2hctx_rttvar *= 3; + hctx->ccid2hctx_rttvar >>= 2; + hctx->ccid2hctx_rttvar += tmp; + + /* SRTT */ + hctx->ccid2hctx_srtt *= 7; + hctx->ccid2hctx_srtt >>= 3; + tmp = r >> 3; + hctx->ccid2hctx_srtt += tmp; + } + s = hctx->ccid2hctx_rttvar << 2; + /* clock granularity is 1 when based on jiffies */ + if (!s) + s = 1; + hctx->ccid2hctx_rto = hctx->ccid2hctx_srtt + s; + + /* must be at least a second */ + s = hctx->ccid2hctx_rto / HZ; + /* DCCP doesn't require this [but I like it cuz my code sux] */ +#if 1 + if (s < 1) + hctx->ccid2hctx_rto = HZ; +#endif + /* max 60 seconds */ + if (s > 60) + hctx->ccid2hctx_rto = HZ * 60; + + hctx->ccid2hctx_lastrtt = jiffies; + + ccid2_pr_debug("srtt: %ld rttvar: %ld rto: %ld (HZ=%d) R=%lu\n", + hctx->ccid2hctx_srtt, hctx->ccid2hctx_rttvar, + hctx->ccid2hctx_rto, HZ, r); + hctx->ccid2hctx_sent = 0; + } + + /* we got a new ack, so re-start RTO timer */ + ccid2_hc_tx_kill_rto_timer(sk); + ccid2_start_rto_timer(sk); +} + +static void ccid2_hc_tx_dec_pipe(struct sock *sk) +{ + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + + hctx->ccid2hctx_pipe--; + BUG_ON(hctx->ccid2hctx_pipe < 0); + + if (hctx->ccid2hctx_pipe == 0) + ccid2_hc_tx_kill_rto_timer(sk); +} + +static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + u64 ackno, seqno; + struct ccid2_seq *seqp; + unsigned char *vector; + unsigned char veclen; + int offset = 0; + int done = 0; + int loss = 0; + unsigned int maxincr = 0; + + ccid2_hc_tx_check_sanity(hctx); + /* check reverse path congestion */ + seqno = DCCP_SKB_CB(skb)->dccpd_seq; + + /* XXX this whole "algorithm" is broken. Need to fix it to keep track + * of the seqnos of the dupacks so that rpseq and rpdupack are correct + * -sorbo. + */ + /* need to bootstrap */ + if (hctx->ccid2hctx_rpdupack == -1) { + hctx->ccid2hctx_rpdupack = 0; + hctx->ccid2hctx_rpseq = seqno; + } else { + /* check if packet is consecutive */ + if ((hctx->ccid2hctx_rpseq + 1) == seqno) + hctx->ccid2hctx_rpseq++; + /* it's a later packet */ + else if (after48(seqno, hctx->ccid2hctx_rpseq)) { + hctx->ccid2hctx_rpdupack++; + + /* check if we got enough dupacks */ + if (hctx->ccid2hctx_rpdupack >= + hctx->ccid2hctx_numdupack) { + hctx->ccid2hctx_rpdupack = -1; /* XXX lame */ + hctx->ccid2hctx_rpseq = 0; + + ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio << 1); + } + } + } + + /* check forward path congestion */ + /* still didn't send out new data packets */ + if (hctx->ccid2hctx_seqh == hctx->ccid2hctx_seqt) + return; + + switch (DCCP_SKB_CB(skb)->dccpd_type) { + case DCCP_PKT_ACK: + case DCCP_PKT_DATAACK: + break; + default: + return; + } + + ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq; + seqp = hctx->ccid2hctx_seqh->ccid2s_prev; + + /* If in slow-start, cwnd can increase at most Ack Ratio / 2 packets for + * this single ack. I round up. + * -sorbo. + */ + maxincr = dp->dccps_l_ack_ratio >> 1; + maxincr++; + + /* go through all ack vectors */ + while ((offset = ccid2_ackvector(sk, skb, offset, + &vector, &veclen)) != -1) { + /* go through this ack vector */ + while (veclen--) { + const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; + u64 ackno_end_rl; + + dccp_set_seqno(&ackno_end_rl, ackno - rl); + ccid2_pr_debug("ackvec start:%llu end:%llu\n", ackno, + ackno_end_rl); + /* if the seqno we are analyzing is larger than the + * current ackno, then move towards the tail of our + * seqnos. + */ + while (after48(seqp->ccid2s_seq, ackno)) { + if (seqp == hctx->ccid2hctx_seqt) { + done = 1; + break; + } + seqp = seqp->ccid2s_prev; + } + if (done) + break; + + /* check all seqnos in the range of the vector + * run length + */ + while (between48(seqp->ccid2s_seq,ackno_end_rl,ackno)) { + const u8 state = (*vector & + DCCP_ACKVEC_STATE_MASK) >> 6; + + /* new packet received or marked */ + if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED && + !seqp->ccid2s_acked) { + if (state == + DCCP_ACKVEC_STATE_ECN_MARKED) { + loss = 1; + } else + ccid2_new_ack(sk, seqp, + &maxincr); + + seqp->ccid2s_acked = 1; + ccid2_pr_debug("Got ack for %llu\n", + seqp->ccid2s_seq); + ccid2_hc_tx_dec_pipe(sk); + } + if (seqp == hctx->ccid2hctx_seqt) { + done = 1; + break; + } + seqp = seqp->ccid2s_next; + } + if (done) + break; + + + dccp_set_seqno(&ackno, ackno_end_rl - 1); + vector++; + } + if (done) + break; + } + + /* The state about what is acked should be correct now + * Check for NUMDUPACK + */ + seqp = hctx->ccid2hctx_seqh->ccid2s_prev; + done = 0; + while (1) { + if (seqp->ccid2s_acked) { + done++; + if (done == hctx->ccid2hctx_numdupack) + break; + } + if (seqp == hctx->ccid2hctx_seqt) + break; + seqp = seqp->ccid2s_prev; + } + + /* If there are at least 3 acknowledgements, anything unacknowledged + * below the last sequence number is considered lost + */ + if (done == hctx->ccid2hctx_numdupack) { + struct ccid2_seq *last_acked = seqp; + + /* check for lost packets */ + while (1) { + if (!seqp->ccid2s_acked) { + loss = 1; + ccid2_hc_tx_dec_pipe(sk); + } + if (seqp == hctx->ccid2hctx_seqt) + break; + seqp = seqp->ccid2s_prev; + } + + hctx->ccid2hctx_seqt = last_acked; + } + + /* trim acked packets in tail */ + while (hctx->ccid2hctx_seqt != hctx->ccid2hctx_seqh) { + if (!hctx->ccid2hctx_seqt->ccid2s_acked) + break; + + hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqt->ccid2s_next; + } + + if (loss) { + /* XXX do bit shifts guarantee a 0 as the new bit? */ + ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd >> 1); + hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd; + if (hctx->ccid2hctx_ssthresh < 2) + hctx->ccid2hctx_ssthresh = 2; + } + + ccid2_hc_tx_check_sanity(hctx); +} + +static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) +{ + struct ccid2_hc_tx_sock *hctx = ccid_priv(ccid); + int seqcount = ccid2_seq_len; + int i; + + /* XXX init variables with proper values */ + hctx->ccid2hctx_cwnd = 1; + hctx->ccid2hctx_ssthresh = 10; + hctx->ccid2hctx_numdupack = 3; + + /* XXX init ~ to window size... */ + hctx->ccid2hctx_seqbuf = kmalloc(sizeof(*hctx->ccid2hctx_seqbuf) * + seqcount, gfp_any()); + if (hctx->ccid2hctx_seqbuf == NULL) + return -ENOMEM; + + for (i = 0; i < (seqcount - 1); i++) { + hctx->ccid2hctx_seqbuf[i].ccid2s_next = + &hctx->ccid2hctx_seqbuf[i + 1]; + hctx->ccid2hctx_seqbuf[i + 1].ccid2s_prev = + &hctx->ccid2hctx_seqbuf[i]; + } + hctx->ccid2hctx_seqbuf[seqcount - 1].ccid2s_next = + hctx->ccid2hctx_seqbuf; + hctx->ccid2hctx_seqbuf->ccid2s_prev = + &hctx->ccid2hctx_seqbuf[seqcount - 1]; + + hctx->ccid2hctx_seqh = hctx->ccid2hctx_seqbuf; + hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqh; + hctx->ccid2hctx_sent = 0; + hctx->ccid2hctx_rto = 3 * HZ; + hctx->ccid2hctx_srtt = -1; + hctx->ccid2hctx_rttvar = -1; + hctx->ccid2hctx_lastrtt = 0; + hctx->ccid2hctx_rpdupack = -1; + + hctx->ccid2hctx_rtotimer.function = &ccid2_hc_tx_rto_expire; + hctx->ccid2hctx_rtotimer.data = (unsigned long)sk; + init_timer(&hctx->ccid2hctx_rtotimer); + + ccid2_hc_tx_check_sanity(hctx); + return 0; +} + +static void ccid2_hc_tx_exit(struct sock *sk) +{ + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + + ccid2_hc_tx_kill_rto_timer(sk); + kfree(hctx->ccid2hctx_seqbuf); + hctx->ccid2hctx_seqbuf = NULL; +} + +static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) +{ + const struct dccp_sock *dp = dccp_sk(sk); + struct ccid2_hc_rx_sock *hcrx = ccid2_hc_rx_sk(sk); + + switch (DCCP_SKB_CB(skb)->dccpd_type) { + case DCCP_PKT_DATA: + case DCCP_PKT_DATAACK: + hcrx->ccid2hcrx_data++; + if (hcrx->ccid2hcrx_data >= dp->dccps_r_ack_ratio) { + dccp_send_ack(sk); + hcrx->ccid2hcrx_data = 0; + } + break; + } +} + +static struct ccid_operations ccid2 = { + .ccid_id = 2, + .ccid_name = "ccid2", + .ccid_owner = THIS_MODULE, + .ccid_hc_tx_obj_size = sizeof(struct ccid2_hc_tx_sock), + .ccid_hc_tx_init = ccid2_hc_tx_init, + .ccid_hc_tx_exit = ccid2_hc_tx_exit, + .ccid_hc_tx_send_packet = ccid2_hc_tx_send_packet, + .ccid_hc_tx_packet_sent = ccid2_hc_tx_packet_sent, + .ccid_hc_tx_packet_recv = ccid2_hc_tx_packet_recv, + .ccid_hc_rx_obj_size = sizeof(struct ccid2_hc_rx_sock), + .ccid_hc_rx_packet_recv = ccid2_hc_rx_packet_recv, +}; + +module_param(ccid2_debug, int, 0444); +MODULE_PARM_DESC(ccid2_debug, "Enable debug messages"); + +static __init int ccid2_module_init(void) +{ + return ccid_register(&ccid2); +} +module_init(ccid2_module_init); + +static __exit void ccid2_module_exit(void) +{ + ccid_unregister(&ccid2); +} +module_exit(ccid2_module_exit); + +MODULE_AUTHOR("Andrea Bittau <a.bittau@cs.ucl.ac.uk>"); +MODULE_DESCRIPTION("DCCP TCP-Like (CCID2) CCID"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("net-dccp-ccid-2"); diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h new file mode 100644 index 0000000..451a874 --- /dev/null +++ b/net/dccp/ccids/ccid2.h @@ -0,0 +1,85 @@ +/* + * net/dccp/ccids/ccid2.h + * + * Copyright (c) 2005 Andrea Bittau <a.bittau@cs.ucl.ac.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ +#ifndef _DCCP_CCID2_H_ +#define _DCCP_CCID2_H_ + +#include <linux/dccp.h> +#include <linux/timer.h> +#include <linux/types.h> +#include "../ccid.h" + +struct sock; + +struct ccid2_seq { + u64 ccid2s_seq; + unsigned long ccid2s_sent; + int ccid2s_acked; + struct ccid2_seq *ccid2s_prev; + struct ccid2_seq *ccid2s_next; +}; + +/** struct ccid2_hc_tx_sock - CCID2 TX half connection + * + * @ccid2hctx_ssacks - ACKs recv in slow start + * @ccid2hctx_acks - ACKS recv in AI phase + * @ccid2hctx_sent - packets sent in this window + * @ccid2hctx_lastrtt -time RTT was last measured + * @ccid2hctx_arsent - packets sent [ack ratio] + * @ccid2hctx_ackloss - ack was lost in this win + * @ccid2hctx_rpseq - last consecutive seqno + * @ccid2hctx_rpdupack - dupacks since rpseq +*/ +struct ccid2_hc_tx_sock { + int ccid2hctx_cwnd; + int ccid2hctx_ssacks; + int ccid2hctx_acks; + int ccid2hctx_ssthresh; + int ccid2hctx_pipe; + int ccid2hctx_numdupack; + struct ccid2_seq *ccid2hctx_seqbuf; + struct ccid2_seq *ccid2hctx_seqh; + struct ccid2_seq *ccid2hctx_seqt; + long ccid2hctx_rto; + long ccid2hctx_srtt; + long ccid2hctx_rttvar; + int ccid2hctx_sent; + unsigned long ccid2hctx_lastrtt; + struct timer_list ccid2hctx_rtotimer; + unsigned long ccid2hctx_arsent; + int ccid2hctx_ackloss; + u64 ccid2hctx_rpseq; + int ccid2hctx_rpdupack; + int ccid2hctx_sendwait; +}; + +struct ccid2_hc_rx_sock { + int ccid2hcrx_data; +}; + +static inline struct ccid2_hc_tx_sock *ccid2_hc_tx_sk(const struct sock *sk) +{ + return ccid_priv(dccp_sk(sk)->dccps_hc_tx_ccid); +} + +static inline struct ccid2_hc_rx_sock *ccid2_hc_rx_sk(const struct sock *sk) +{ + return ccid_priv(dccp_sk(sk)->dccps_hc_rx_ccid); +} +#endif /* _DCCP_CCID2_H_ */ diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 35d1d34..b4a51d0 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -46,7 +46,7 @@ * Reason for maths here is to avoid 32 bit overflow when a is big. * With this we get close to the limit. */ -static inline u32 usecs_div(const u32 a, const u32 b) +static u32 usecs_div(const u32 a, const u32 b) { const u32 div = a < (UINT_MAX / (USEC_PER_SEC / 10)) ? 10 : a < (UINT_MAX / (USEC_PER_SEC / 50)) ? 50 : @@ -76,15 +76,6 @@ static struct dccp_tx_hist *ccid3_tx_hist; static struct dccp_rx_hist *ccid3_rx_hist; static struct dccp_li_hist *ccid3_li_hist; -static int ccid3_init(struct sock *sk) -{ - return 0; -} - -static void ccid3_exit(struct sock *sk) -{ -} - /* TFRC sender states */ enum ccid3_hc_tx_states { TFRC_SSTATE_NO_SENT = 1, @@ -107,8 +98,8 @@ static const char *ccid3_tx_state_name(enum ccid3_hc_tx_states state) } #endif -static inline void ccid3_hc_tx_set_state(struct sock *sk, - enum ccid3_hc_tx_states state) +static void ccid3_hc_tx_set_state(struct sock *sk, + enum ccid3_hc_tx_states state) { struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); enum ccid3_hc_tx_states oldstate = hctx->ccid3hctx_state; @@ -316,8 +307,6 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, switch (hctx->ccid3hctx_state) { case TFRC_SSTATE_NO_SENT: - hctx->ccid3hctx_no_feedback_timer.function = ccid3_hc_tx_no_feedback_timer; - hctx->ccid3hctx_no_feedback_timer.data = (unsigned long)sk; sk_reset_timer(sk, &hctx->ccid3hctx_no_feedback_timer, jiffies + usecs_to_jiffies(TFRC_INITIAL_TIMEOUT)); hctx->ccid3hctx_last_win_count = 0; @@ -585,16 +574,15 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) } } -static void ccid3_hc_tx_insert_options(struct sock *sk, struct sk_buff *skb) +static int ccid3_hc_tx_insert_options(struct sock *sk, struct sk_buff *skb) { const struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); BUG_ON(hctx == NULL); - if (!(sk->sk_state == DCCP_OPEN || sk->sk_state == DCCP_PARTOPEN)) - return; - - DCCP_SKB_CB(skb)->dccpd_ccval = hctx->ccid3hctx_last_win_count; + if (sk->sk_state == DCCP_OPEN || sk->sk_state == DCCP_PARTOPEN) + DCCP_SKB_CB(skb)->dccpd_ccval = hctx->ccid3hctx_last_win_count; + return 0; } static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option, @@ -626,7 +614,7 @@ static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option, __FUNCTION__, dccp_role(sk), sk); rc = -EINVAL; } else { - opt_recv->ccid3or_loss_event_rate = ntohl(*(u32 *)value); + opt_recv->ccid3or_loss_event_rate = ntohl(*(__be32 *)value); ccid3_pr_debug("%s, sk=%p, LOSS_EVENT_RATE=%u\n", dccp_role(sk), sk, opt_recv->ccid3or_loss_event_rate); @@ -647,7 +635,7 @@ static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option, __FUNCTION__, dccp_role(sk), sk); rc = -EINVAL; } else { - opt_recv->ccid3or_receive_rate = ntohl(*(u32 *)value); + opt_recv->ccid3or_receive_rate = ntohl(*(__be32 *)value); ccid3_pr_debug("%s, sk=%p, RECEIVE_RATE=%u\n", dccp_role(sk), sk, opt_recv->ccid3or_receive_rate); @@ -658,17 +646,10 @@ static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option, return rc; } -static int ccid3_hc_tx_init(struct sock *sk) +static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); - struct ccid3_hc_tx_sock *hctx; - - dp->dccps_hc_tx_ccid_private = kmalloc(sizeof(*hctx), gfp_any()); - if (dp->dccps_hc_tx_ccid_private == NULL) - return -ENOMEM; - - hctx = ccid3_hc_tx_sk(sk); - memset(hctx, 0, sizeof(*hctx)); + struct ccid3_hc_tx_sock *hctx = ccid_priv(ccid); if (dp->dccps_packet_size >= TFRC_MIN_PACKET_SIZE && dp->dccps_packet_size <= TFRC_MAX_PACKET_SIZE) @@ -681,6 +662,9 @@ static int ccid3_hc_tx_init(struct sock *sk) hctx->ccid3hctx_t_rto = USEC_PER_SEC; hctx->ccid3hctx_state = TFRC_SSTATE_NO_SENT; INIT_LIST_HEAD(&hctx->ccid3hctx_hist); + + hctx->ccid3hctx_no_feedback_timer.function = ccid3_hc_tx_no_feedback_timer; + hctx->ccid3hctx_no_feedback_timer.data = (unsigned long)sk; init_timer(&hctx->ccid3hctx_no_feedback_timer); return 0; @@ -688,7 +672,6 @@ static int ccid3_hc_tx_init(struct sock *sk) static void ccid3_hc_tx_exit(struct sock *sk) { - struct dccp_sock *dp = dccp_sk(sk); struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); BUG_ON(hctx == NULL); @@ -698,9 +681,6 @@ static void ccid3_hc_tx_exit(struct sock *sk) /* Empty packet history */ dccp_tx_hist_purge(ccid3_tx_hist, &hctx->ccid3hctx_hist); - - kfree(dp->dccps_hc_tx_ccid_private); - dp->dccps_hc_tx_ccid_private = NULL; } /* @@ -727,8 +707,8 @@ static const char *ccid3_rx_state_name(enum ccid3_hc_rx_states state) } #endif -static inline void ccid3_hc_rx_set_state(struct sock *sk, - enum ccid3_hc_rx_states state) +static void ccid3_hc_rx_set_state(struct sock *sk, + enum ccid3_hc_rx_states state) { struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); enum ccid3_hc_rx_states oldstate = hcrx->ccid3hcrx_state; @@ -793,31 +773,35 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk) dccp_send_ack(sk); } -static void ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) +static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) { const struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); - u32 x_recv, pinv; + __be32 x_recv, pinv; BUG_ON(hcrx == NULL); if (!(sk->sk_state == DCCP_OPEN || sk->sk_state == DCCP_PARTOPEN)) - return; + return 0; DCCP_SKB_CB(skb)->dccpd_ccval = hcrx->ccid3hcrx_last_counter; if (dccp_packet_without_ack(skb)) - return; - - if (hcrx->ccid3hcrx_elapsed_time != 0) - dccp_insert_option_elapsed_time(sk, skb, - hcrx->ccid3hcrx_elapsed_time); - dccp_insert_option_timestamp(sk, skb); + return 0; + x_recv = htonl(hcrx->ccid3hcrx_x_recv); pinv = htonl(hcrx->ccid3hcrx_pinv); - dccp_insert_option(sk, skb, TFRC_OPT_LOSS_EVENT_RATE, - &pinv, sizeof(pinv)); - dccp_insert_option(sk, skb, TFRC_OPT_RECEIVE_RATE, - &x_recv, sizeof(x_recv)); + + if ((hcrx->ccid3hcrx_elapsed_time != 0 && + dccp_insert_option_elapsed_time(sk, skb, + hcrx->ccid3hcrx_elapsed_time)) || + dccp_insert_option_timestamp(sk, skb) || + dccp_insert_option(sk, skb, TFRC_OPT_LOSS_EVENT_RATE, + &pinv, sizeof(pinv)) || + dccp_insert_option(sk, skb, TFRC_OPT_RECEIVE_RATE, + &x_recv, sizeof(x_recv))) + return -1; + + return 0; } /* calculate first loss interval @@ -1047,20 +1031,13 @@ static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) } } -static int ccid3_hc_rx_init(struct sock *sk) +static int ccid3_hc_rx_init(struct ccid *ccid, struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); - struct ccid3_hc_rx_sock *hcrx; + struct ccid3_hc_rx_sock *hcrx = ccid_priv(ccid); ccid3_pr_debug("%s, sk=%p\n", dccp_role(sk), sk); - dp->dccps_hc_rx_ccid_private = kmalloc(sizeof(*hcrx), gfp_any()); - if (dp->dccps_hc_rx_ccid_private == NULL) - return -ENOMEM; - - hcrx = ccid3_hc_rx_sk(sk); - memset(hcrx, 0, sizeof(*hcrx)); - if (dp->dccps_packet_size >= TFRC_MIN_PACKET_SIZE && dp->dccps_packet_size <= TFRC_MAX_PACKET_SIZE) hcrx->ccid3hcrx_s = dp->dccps_packet_size; @@ -1079,7 +1056,6 @@ static int ccid3_hc_rx_init(struct sock *sk) static void ccid3_hc_rx_exit(struct sock *sk) { struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); - struct dccp_sock *dp = dccp_sk(sk); BUG_ON(hcrx == NULL); @@ -1090,9 +1066,6 @@ static void ccid3_hc_rx_exit(struct sock *sk) /* Empty loss interval history */ dccp_li_hist_purge(ccid3_li_hist, &hcrx->ccid3hcrx_li_hist); - - kfree(dp->dccps_hc_rx_ccid_private); - dp->dccps_hc_rx_ccid_private = NULL; } static void ccid3_hc_rx_get_info(struct sock *sk, struct tcp_info *info) @@ -1178,12 +1151,11 @@ static int ccid3_hc_tx_getsockopt(struct sock *sk, const int optname, int len, return 0; } -static struct ccid ccid3 = { +static struct ccid_operations ccid3 = { .ccid_id = 3, .ccid_name = "ccid3", .ccid_owner = THIS_MODULE, - .ccid_init = ccid3_init, - .ccid_exit = ccid3_exit, + .ccid_hc_tx_obj_size = sizeof(struct ccid3_hc_tx_sock), .ccid_hc_tx_init = ccid3_hc_tx_init, .ccid_hc_tx_exit = ccid3_hc_tx_exit, .ccid_hc_tx_send_packet = ccid3_hc_tx_send_packet, @@ -1191,6 +1163,7 @@ static struct ccid ccid3 = { .ccid_hc_tx_packet_recv = ccid3_hc_tx_packet_recv, .ccid_hc_tx_insert_options = ccid3_hc_tx_insert_options, .ccid_hc_tx_parse_options = ccid3_hc_tx_parse_options, + .ccid_hc_rx_obj_size = sizeof(struct ccid3_hc_rx_sock), .ccid_hc_rx_init = ccid3_hc_rx_init, .ccid_hc_rx_exit = ccid3_hc_rx_exit, .ccid_hc_rx_insert_options = ccid3_hc_rx_insert_options, @@ -1241,15 +1214,6 @@ module_init(ccid3_module_init); static __exit void ccid3_module_exit(void) { -#ifdef CONFIG_IP_DCCP_UNLOAD_HACK - /* - * Hack to use while developing, so that we get rid of the control - * sock, that is what keeps a refcount on dccp.ko -acme - */ - extern void dccp_ctl_sock_exit(void); - - dccp_ctl_sock_exit(); -#endif ccid_unregister(&ccid3); if (ccid3_tx_hist != NULL) { diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h index 0bde458..f18b96d4 100644 --- a/net/dccp/ccids/ccid3.h +++ b/net/dccp/ccids/ccid3.h @@ -41,6 +41,7 @@ #include <linux/time.h> #include <linux/types.h> #include <linux/tfrc.h> +#include "../ccid.h" #define TFRC_MIN_PACKET_SIZE 16 #define TFRC_STD_PACKET_SIZE 256 @@ -135,12 +136,12 @@ struct ccid3_hc_rx_sock { static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk) { - return dccp_sk(sk)->dccps_hc_tx_ccid_private; + return ccid_priv(dccp_sk(sk)->dccps_hc_tx_ccid); } static inline struct ccid3_hc_rx_sock *ccid3_hc_rx_sk(const struct sock *sk) { - return dccp_sk(sk)->dccps_hc_rx_ccid_private; + return ccid_priv(dccp_sk(sk)->dccps_hc_rx_ccid); } #endif /* _DCCP_CCID3_H_ */ diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 93f26dd..1fe5091 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -59,8 +59,6 @@ extern void dccp_time_wait(struct sock *sk, int state, int timeo); #define DCCP_RTO_MAX ((unsigned)(120 * HZ)) /* FIXME: using TCP value */ -extern struct proto dccp_prot; - /* is seq1 < seq2 ? */ static inline int before48(const u64 seq1, const u64 seq2) { @@ -120,7 +118,6 @@ DECLARE_SNMP_STAT(struct dccp_mib, dccp_statistics); extern int dccp_retransmit_skb(struct sock *sk, struct sk_buff *skb); -extern int dccp_send_response(struct sock *sk); extern void dccp_send_ack(struct sock *sk); extern void dccp_send_delayed_ack(struct sock *sk); extern void dccp_send_sync(struct sock *sk, const u64 seq, @@ -140,53 +137,8 @@ extern unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu); extern const char *dccp_packet_name(const int type); extern const char *dccp_state_name(const int state); -static inline void dccp_set_state(struct sock *sk, const int state) -{ - const int oldstate = sk->sk_state; - - dccp_pr_debug("%s(%p) %-10.10s -> %s\n", - dccp_role(sk), sk, - dccp_state_name(oldstate), dccp_state_name(state)); - WARN_ON(state == oldstate); - - switch (state) { - case DCCP_OPEN: - if (oldstate != DCCP_OPEN) - DCCP_INC_STATS(DCCP_MIB_CURRESTAB); - break; - - case DCCP_CLOSED: - if (oldstate == DCCP_CLOSING || oldstate == DCCP_OPEN) - DCCP_INC_STATS(DCCP_MIB_ESTABRESETS); - - sk->sk_prot->unhash(sk); - if (inet_csk(sk)->icsk_bind_hash != NULL && - !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) - inet_put_port(&dccp_hashinfo, sk); - /* fall through */ - default: - if (oldstate == DCCP_OPEN) - DCCP_DEC_STATS(DCCP_MIB_CURRESTAB); - } - - /* Change state AFTER socket is unhashed to avoid closed - * socket sitting in hash tables. - */ - sk->sk_state = state; -} - -static inline void dccp_done(struct sock *sk) -{ - dccp_set_state(sk, DCCP_CLOSED); - dccp_clear_xmit_timers(sk); - - sk->sk_shutdown = SHUTDOWN_MASK; - - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); - else - inet_csk_destroy_sock(sk); -} +extern void dccp_set_state(struct sock *sk, const int state); +extern void dccp_done(struct sock *sk); static inline void dccp_openreq_init(struct request_sock *req, struct dccp_sock *dp, @@ -209,10 +161,6 @@ extern struct sock *dccp_create_openreq_child(struct sock *sk, extern int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); -extern void dccp_v4_err(struct sk_buff *skb, u32); - -extern int dccp_v4_rcv(struct sk_buff *skb); - extern struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, @@ -228,24 +176,30 @@ extern int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, extern int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct dccp_hdr *dh, const unsigned len); -extern int dccp_v4_init_sock(struct sock *sk); -extern int dccp_v4_destroy_sock(struct sock *sk); +extern int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized); +extern int dccp_destroy_sock(struct sock *sk); extern void dccp_close(struct sock *sk, long timeout); extern struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, struct request_sock *req); -extern struct sk_buff *dccp_make_reset(struct sock *sk, - struct dst_entry *dst, - enum dccp_reset_codes code); extern int dccp_connect(struct sock *sk); extern int dccp_disconnect(struct sock *sk, int flags); +extern void dccp_hash(struct sock *sk); extern void dccp_unhash(struct sock *sk); extern int dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int dccp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen); +#ifdef CONFIG_COMPAT +extern int compat_dccp_getsockopt(struct sock *sk, + int level, int optname, + char __user *optval, int __user *optlen); +extern int compat_dccp_setsockopt(struct sock *sk, + int level, int optname, + char __user *optval, int optlen); +#endif extern int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg); extern int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size); @@ -262,15 +216,14 @@ extern int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); extern int dccp_v4_checksum(const struct sk_buff *skb, - const u32 saddr, const u32 daddr); + const __be32 saddr, const __be32 daddr); -extern int dccp_v4_send_reset(struct sock *sk, - enum dccp_reset_codes code); +extern int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code); extern void dccp_send_close(struct sock *sk, const int active); extern int dccp_invalid_packet(struct sk_buff *skb); static inline int dccp_bad_service_code(const struct sock *sk, - const __u32 service) + const __be32 service) { const struct dccp_sock *dp = dccp_sk(sk); @@ -334,41 +287,29 @@ static inline void dccp_hdr_set_seq(struct dccp_hdr *dh, const u64 gss) { struct dccp_hdr_ext *dhx = (struct dccp_hdr_ext *)((void *)dh + sizeof(*dh)); - -#if defined(__LITTLE_ENDIAN_BITFIELD) - dh->dccph_seq = htonl((gss >> 32)) >> 8; -#elif defined(__BIG_ENDIAN_BITFIELD) - dh->dccph_seq = htonl((gss >> 32)); -#else -#error "Adjust your <asm/byteorder.h> defines" -#endif + dh->dccph_seq2 = 0; + dh->dccph_seq = htons((gss >> 32) & 0xfffff); dhx->dccph_seq_low = htonl(gss & 0xffffffff); } static inline void dccp_hdr_set_ack(struct dccp_hdr_ack_bits *dhack, const u64 gsr) { -#if defined(__LITTLE_ENDIAN_BITFIELD) - dhack->dccph_ack_nr_high = htonl((gsr >> 32)) >> 8; -#elif defined(__BIG_ENDIAN_BITFIELD) - dhack->dccph_ack_nr_high = htonl((gsr >> 32)); -#else -#error "Adjust your <asm/byteorder.h> defines" -#endif + dhack->dccph_reserved1 = 0; + dhack->dccph_ack_nr_high = htons(gsr >> 32); dhack->dccph_ack_nr_low = htonl(gsr & 0xffffffff); } static inline void dccp_update_gsr(struct sock *sk, u64 seq) { struct dccp_sock *dp = dccp_sk(sk); + const struct dccp_minisock *dmsk = dccp_msk(sk); dp->dccps_gsr = seq; dccp_set_seqno(&dp->dccps_swl, - (dp->dccps_gsr + 1 - - (dp->dccps_options.dccpo_sequence_window / 4))); + dp->dccps_gsr + 1 - (dmsk->dccpms_sequence_window / 4)); dccp_set_seqno(&dp->dccps_swh, - (dp->dccps_gsr + - (3 * dp->dccps_options.dccpo_sequence_window) / 4)); + dp->dccps_gsr + (3 * dmsk->dccpms_sequence_window) / 4); } static inline void dccp_update_gss(struct sock *sk, u64 seq) @@ -378,7 +319,7 @@ static inline void dccp_update_gss(struct sock *sk, u64 seq) dp->dccps_awh = dp->dccps_gss = seq; dccp_set_seqno(&dp->dccps_awl, (dp->dccps_gss - - dp->dccps_options.dccpo_sequence_window + 1)); + dccp_msk(sk)->dccpms_sequence_window + 1)); } static inline int dccp_ack_pending(const struct sock *sk) @@ -386,24 +327,22 @@ static inline int dccp_ack_pending(const struct sock *sk) const struct dccp_sock *dp = dccp_sk(sk); return dp->dccps_timestamp_echo != 0 || #ifdef CONFIG_IP_DCCP_ACKVEC - (dp->dccps_options.dccpo_send_ack_vector && + (dccp_msk(sk)->dccpms_send_ack_vector && dccp_ackvec_pending(dp->dccps_hc_rx_ackvec)) || #endif inet_csk_ack_scheduled(sk); } -extern void dccp_insert_options(struct sock *sk, struct sk_buff *skb); -extern void dccp_insert_option_elapsed_time(struct sock *sk, +extern int dccp_insert_options(struct sock *sk, struct sk_buff *skb); +extern int dccp_insert_option_elapsed_time(struct sock *sk, struct sk_buff *skb, u32 elapsed_time); -extern void dccp_insert_option_timestamp(struct sock *sk, +extern int dccp_insert_option_timestamp(struct sock *sk, struct sk_buff *skb); -extern void dccp_insert_option(struct sock *sk, struct sk_buff *skb, +extern int dccp_insert_option(struct sock *sk, struct sk_buff *skb, unsigned char option, const void *value, unsigned char len); -extern struct socket *dccp_ctl_socket; - extern void dccp_timestamp(const struct sock *sk, struct timeval *tv); static inline suseconds_t timeval_usecs(const struct timeval *tv) @@ -444,4 +383,18 @@ static inline void timeval_sub_usecs(struct timeval *tv, } } +#ifdef CONFIG_SYSCTL +extern int dccp_sysctl_init(void); +extern void dccp_sysctl_exit(void); +#else +static inline int dccp_sysctl_init(void) +{ + return 0; +} + +static inline void dccp_sysctl_exit(void) +{ +} +#endif + #endif /* _DCCP_H */ diff --git a/net/dccp/diag.c b/net/dccp/diag.c index 3f78c00..0f25dc3 100644 --- a/net/dccp/diag.c +++ b/net/dccp/diag.c @@ -30,7 +30,7 @@ static void dccp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_backoff = icsk->icsk_backoff; info->tcpi_pmtu = icsk->icsk_pmtu_cookie; - if (dp->dccps_options.dccpo_send_ack_vector) + if (dccp_msk(sk)->dccpms_send_ack_vector) info->tcpi_options |= TCPI_OPT_SACK; ccid_hc_rx_get_info(dp->dccps_hc_rx_ccid, sk, info); diff --git a/net/dccp/feat.c b/net/dccp/feat.c new file mode 100644 index 0000000..e3dd30d --- /dev/null +++ b/net/dccp/feat.c @@ -0,0 +1,586 @@ +/* + * net/dccp/feat.c + * + * An implementation of the DCCP protocol + * Andrea Bittau <a.bittau@cs.ucl.ac.uk> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/config.h> +#include <linux/module.h> + +#include "dccp.h" +#include "ccid.h" +#include "feat.h" + +#define DCCP_FEAT_SP_NOAGREE (-123) + +int dccp_feat_change(struct dccp_minisock *dmsk, u8 type, u8 feature, + u8 *val, u8 len, gfp_t gfp) +{ + struct dccp_opt_pend *opt; + + dccp_pr_debug("feat change type=%d feat=%d\n", type, feature); + + /* XXX sanity check feat change request */ + + /* check if that feature is already being negotiated */ + list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { + /* ok we found a negotiation for this option already */ + if (opt->dccpop_feat == feature && opt->dccpop_type == type) { + dccp_pr_debug("Replacing old\n"); + /* replace */ + BUG_ON(opt->dccpop_val == NULL); + kfree(opt->dccpop_val); + opt->dccpop_val = val; + opt->dccpop_len = len; + opt->dccpop_conf = 0; + return 0; + } + } + + /* negotiation for a new feature */ + opt = kmalloc(sizeof(*opt), gfp); + if (opt == NULL) + return -ENOMEM; + + opt->dccpop_type = type; + opt->dccpop_feat = feature; + opt->dccpop_len = len; + opt->dccpop_val = val; + opt->dccpop_conf = 0; + opt->dccpop_sc = NULL; + + BUG_ON(opt->dccpop_val == NULL); + + list_add_tail(&opt->dccpop_node, &dmsk->dccpms_pending); + return 0; +} + +EXPORT_SYMBOL_GPL(dccp_feat_change); + +static int dccp_feat_update_ccid(struct sock *sk, u8 type, u8 new_ccid_nr) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_minisock *dmsk = dccp_msk(sk); + /* figure out if we are changing our CCID or the peer's */ + const int rx = type == DCCPO_CHANGE_R; + const u8 ccid_nr = rx ? dmsk->dccpms_rx_ccid : dmsk->dccpms_tx_ccid; + struct ccid *new_ccid; + + /* Check if nothing is being changed. */ + if (ccid_nr == new_ccid_nr) + return 0; + + new_ccid = ccid_new(new_ccid_nr, sk, rx, GFP_ATOMIC); + if (new_ccid == NULL) + return -ENOMEM; + + if (rx) { + ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); + dp->dccps_hc_rx_ccid = new_ccid; + dmsk->dccpms_rx_ccid = new_ccid_nr; + } else { + ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); + dp->dccps_hc_tx_ccid = new_ccid; + dmsk->dccpms_tx_ccid = new_ccid_nr; + } + + return 0; +} + +/* XXX taking only u8 vals */ +static int dccp_feat_update(struct sock *sk, u8 type, u8 feat, u8 val) +{ + dccp_pr_debug("changing [%d] feat %d to %d\n", type, feat, val); + + switch (feat) { + case DCCPF_CCID: + return dccp_feat_update_ccid(sk, type, val); + default: + dccp_pr_debug("IMPLEMENT changing [%d] feat %d to %d\n", + type, feat, val); + break; + } + return 0; +} + +static int dccp_feat_reconcile(struct sock *sk, struct dccp_opt_pend *opt, + u8 *rpref, u8 rlen) +{ + struct dccp_sock *dp = dccp_sk(sk); + u8 *spref, slen, *res = NULL; + int i, j, rc, agree = 1; + + BUG_ON(rpref == NULL); + + /* check if we are the black sheep */ + if (dp->dccps_role == DCCP_ROLE_CLIENT) { + spref = rpref; + slen = rlen; + rpref = opt->dccpop_val; + rlen = opt->dccpop_len; + } else { + spref = opt->dccpop_val; + slen = opt->dccpop_len; + } + /* + * Now we have server preference list in spref and client preference in + * rpref + */ + BUG_ON(spref == NULL); + BUG_ON(rpref == NULL); + + /* FIXME sanity check vals */ + + /* Are values in any order? XXX Lame "algorithm" here */ + /* XXX assume values are 1 byte */ + for (i = 0; i < slen; i++) { + for (j = 0; j < rlen; j++) { + if (spref[i] == rpref[j]) { + res = &spref[i]; + break; + } + } + if (res) + break; + } + + /* we didn't agree on anything */ + if (res == NULL) { + /* confirm previous value */ + switch (opt->dccpop_feat) { + case DCCPF_CCID: + /* XXX did i get this right? =P */ + if (opt->dccpop_type == DCCPO_CHANGE_L) + res = &dccp_msk(sk)->dccpms_tx_ccid; + else + res = &dccp_msk(sk)->dccpms_rx_ccid; + break; + + default: + WARN_ON(1); /* XXX implement res */ + return -EFAULT; + } + + dccp_pr_debug("Don't agree... reconfirming %d\n", *res); + agree = 0; /* this is used for mandatory options... */ + } + + /* need to put result and our preference list */ + /* XXX assume 1 byte vals */ + rlen = 1 + opt->dccpop_len; + rpref = kmalloc(rlen, GFP_ATOMIC); + if (rpref == NULL) + return -ENOMEM; + + *rpref = *res; + memcpy(&rpref[1], opt->dccpop_val, opt->dccpop_len); + + /* put it in the "confirm queue" */ + if (opt->dccpop_sc == NULL) { + opt->dccpop_sc = kmalloc(sizeof(*opt->dccpop_sc), GFP_ATOMIC); + if (opt->dccpop_sc == NULL) { + kfree(rpref); + return -ENOMEM; + } + } else { + /* recycle the confirm slot */ + BUG_ON(opt->dccpop_sc->dccpoc_val == NULL); + kfree(opt->dccpop_sc->dccpoc_val); + dccp_pr_debug("recycling confirm slot\n"); + } + memset(opt->dccpop_sc, 0, sizeof(*opt->dccpop_sc)); + + opt->dccpop_sc->dccpoc_val = rpref; + opt->dccpop_sc->dccpoc_len = rlen; + + /* update the option on our side [we are about to send the confirm] */ + rc = dccp_feat_update(sk, opt->dccpop_type, opt->dccpop_feat, *res); + if (rc) { + kfree(opt->dccpop_sc->dccpoc_val); + kfree(opt->dccpop_sc); + opt->dccpop_sc = 0; + return rc; + } + + dccp_pr_debug("Will confirm %d\n", *rpref); + + /* say we want to change to X but we just got a confirm X, suppress our + * change + */ + if (!opt->dccpop_conf) { + if (*opt->dccpop_val == *res) + opt->dccpop_conf = 1; + dccp_pr_debug("won't ask for change of same feature\n"); + } + + return agree ? 0 : DCCP_FEAT_SP_NOAGREE; /* used for mandatory opts */ +} + +static int dccp_feat_sp(struct sock *sk, u8 type, u8 feature, u8 *val, u8 len) +{ + struct dccp_minisock *dmsk = dccp_msk(sk); + struct dccp_opt_pend *opt; + int rc = 1; + u8 t; + + /* + * We received a CHANGE. We gotta match it against our own preference + * list. If we got a CHANGE_R it means it's a change for us, so we need + * to compare our CHANGE_L list. + */ + if (type == DCCPO_CHANGE_L) + t = DCCPO_CHANGE_R; + else + t = DCCPO_CHANGE_L; + + /* find our preference list for this feature */ + list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { + if (opt->dccpop_type != t || opt->dccpop_feat != feature) + continue; + + /* find the winner from the two preference lists */ + rc = dccp_feat_reconcile(sk, opt, val, len); + break; + } + + /* We didn't deal with the change. This can happen if we have no + * preference list for the feature. In fact, it just shouldn't + * happen---if we understand a feature, we should have a preference list + * with at least the default value. + */ + BUG_ON(rc == 1); + + return rc; +} + +static int dccp_feat_nn(struct sock *sk, u8 type, u8 feature, u8 *val, u8 len) +{ + struct dccp_opt_pend *opt; + struct dccp_minisock *dmsk = dccp_msk(sk); + u8 *copy; + int rc; + + /* NN features must be change L */ + if (type == DCCPO_CHANGE_R) { + dccp_pr_debug("received CHANGE_R %d for NN feat %d\n", + type, feature); + return -EFAULT; + } + + /* XXX sanity check opt val */ + + /* copy option so we can confirm it */ + opt = kzalloc(sizeof(*opt), GFP_ATOMIC); + if (opt == NULL) + return -ENOMEM; + + copy = kmalloc(len, GFP_ATOMIC); + if (copy == NULL) { + kfree(opt); + return -ENOMEM; + } + memcpy(copy, val, len); + + opt->dccpop_type = DCCPO_CONFIRM_R; /* NN can only confirm R */ + opt->dccpop_feat = feature; + opt->dccpop_val = copy; + opt->dccpop_len = len; + + /* change feature */ + rc = dccp_feat_update(sk, type, feature, *val); + if (rc) { + kfree(opt->dccpop_val); + kfree(opt); + return rc; + } + + dccp_pr_debug("Confirming NN feature %d (val=%d)\n", feature, *copy); + list_add_tail(&opt->dccpop_node, &dmsk->dccpms_conf); + + return 0; +} + +static void dccp_feat_empty_confirm(struct dccp_minisock *dmsk, + u8 type, u8 feature) +{ + /* XXX check if other confirms for that are queued and recycle slot */ + struct dccp_opt_pend *opt = kzalloc(sizeof(*opt), GFP_ATOMIC); + + if (opt == NULL) { + /* XXX what do we do? Ignoring should be fine. It's a change + * after all =P + */ + return; + } + + opt->dccpop_type = type == DCCPO_CHANGE_L ? DCCPO_CONFIRM_R : + DCCPO_CONFIRM_L; + opt->dccpop_feat = feature; + opt->dccpop_val = 0; + opt->dccpop_len = 0; + + /* change feature */ + dccp_pr_debug("Empty confirm feature %d type %d\n", feature, type); + list_add_tail(&opt->dccpop_node, &dmsk->dccpms_conf); +} + +static void dccp_feat_flush_confirm(struct sock *sk) +{ + struct dccp_minisock *dmsk = dccp_msk(sk); + /* Check if there is anything to confirm in the first place */ + int yes = !list_empty(&dmsk->dccpms_conf); + + if (!yes) { + struct dccp_opt_pend *opt; + + list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { + if (opt->dccpop_conf) { + yes = 1; + break; + } + } + } + + if (!yes) + return; + + /* OK there is something to confirm... */ + /* XXX check if packet is in flight? Send delayed ack?? */ + if (sk->sk_state == DCCP_OPEN) + dccp_send_ack(sk); +} + +int dccp_feat_change_recv(struct sock *sk, u8 type, u8 feature, u8 *val, u8 len) +{ + int rc; + + dccp_pr_debug("got feat change type=%d feat=%d\n", type, feature); + + /* figure out if it's SP or NN feature */ + switch (feature) { + /* deal with SP features */ + case DCCPF_CCID: + rc = dccp_feat_sp(sk, type, feature, val, len); + break; + + /* deal with NN features */ + case DCCPF_ACK_RATIO: + rc = dccp_feat_nn(sk, type, feature, val, len); + break; + + /* XXX implement other features */ + default: + rc = -EFAULT; + break; + } + + /* check if there were problems changing features */ + if (rc) { + /* If we don't agree on SP, we sent a confirm for old value. + * However we propagate rc to caller in case option was + * mandatory + */ + if (rc != DCCP_FEAT_SP_NOAGREE) + dccp_feat_empty_confirm(dccp_msk(sk), type, feature); + } + + /* generate the confirm [if required] */ + dccp_feat_flush_confirm(sk); + + return rc; +} + +EXPORT_SYMBOL_GPL(dccp_feat_change_recv); + +int dccp_feat_confirm_recv(struct sock *sk, u8 type, u8 feature, + u8 *val, u8 len) +{ + u8 t; + struct dccp_opt_pend *opt; + struct dccp_minisock *dmsk = dccp_msk(sk); + int rc = 1; + int all_confirmed = 1; + + dccp_pr_debug("got feat confirm type=%d feat=%d\n", type, feature); + + /* XXX sanity check type & feat */ + + /* locate our change request */ + t = type == DCCPO_CONFIRM_L ? DCCPO_CHANGE_R : DCCPO_CHANGE_L; + + list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { + if (!opt->dccpop_conf && opt->dccpop_type == t && + opt->dccpop_feat == feature) { + /* we found it */ + /* XXX do sanity check */ + + opt->dccpop_conf = 1; + + /* We got a confirmation---change the option */ + dccp_feat_update(sk, opt->dccpop_type, + opt->dccpop_feat, *val); + + dccp_pr_debug("feat %d type %d confirmed %d\n", + feature, type, *val); + rc = 0; + break; + } + + if (!opt->dccpop_conf) + all_confirmed = 0; + } + + /* fix re-transmit timer */ + /* XXX gotta make sure that no option negotiation occurs during + * connection shutdown. Consider that the CLOSEREQ is sent and timer is + * on. if all options are confirmed it might kill timer which should + * remain alive until close is received. + */ + if (all_confirmed) { + dccp_pr_debug("clear feat negotiation timer %p\n", sk); + inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); + } + + if (rc) + dccp_pr_debug("feat %d type %d never requested\n", + feature, type); + return 0; +} + +EXPORT_SYMBOL_GPL(dccp_feat_confirm_recv); + +void dccp_feat_clean(struct dccp_minisock *dmsk) +{ + struct dccp_opt_pend *opt, *next; + + list_for_each_entry_safe(opt, next, &dmsk->dccpms_pending, + dccpop_node) { + BUG_ON(opt->dccpop_val == NULL); + kfree(opt->dccpop_val); + + if (opt->dccpop_sc != NULL) { + BUG_ON(opt->dccpop_sc->dccpoc_val == NULL); + kfree(opt->dccpop_sc->dccpoc_val); + kfree(opt->dccpop_sc); + } + + kfree(opt); + } + INIT_LIST_HEAD(&dmsk->dccpms_pending); + + list_for_each_entry_safe(opt, next, &dmsk->dccpms_conf, dccpop_node) { + BUG_ON(opt == NULL); + if (opt->dccpop_val != NULL) + kfree(opt->dccpop_val); + kfree(opt); + } + INIT_LIST_HEAD(&dmsk->dccpms_conf); +} + +EXPORT_SYMBOL_GPL(dccp_feat_clean); + +/* this is to be called only when a listening sock creates its child. It is + * assumed by the function---the confirm is not duplicated, but rather it is + * "passed on". + */ +int dccp_feat_clone(struct sock *oldsk, struct sock *newsk) +{ + struct dccp_minisock *olddmsk = dccp_msk(oldsk); + struct dccp_minisock *newdmsk = dccp_msk(newsk); + struct dccp_opt_pend *opt; + int rc = 0; + + INIT_LIST_HEAD(&newdmsk->dccpms_pending); + INIT_LIST_HEAD(&newdmsk->dccpms_conf); + + list_for_each_entry(opt, &olddmsk->dccpms_pending, dccpop_node) { + struct dccp_opt_pend *newopt; + /* copy the value of the option */ + u8 *val = kmalloc(opt->dccpop_len, GFP_ATOMIC); + + if (val == NULL) + goto out_clean; + memcpy(val, opt->dccpop_val, opt->dccpop_len); + + newopt = kmalloc(sizeof(*newopt), GFP_ATOMIC); + if (newopt == NULL) { + kfree(val); + goto out_clean; + } + + /* insert the option */ + memcpy(newopt, opt, sizeof(*newopt)); + newopt->dccpop_val = val; + list_add_tail(&newopt->dccpop_node, &newdmsk->dccpms_pending); + + /* XXX what happens with backlogs and multiple connections at + * once... + */ + /* the master socket no longer needs to worry about confirms */ + opt->dccpop_sc = 0; /* it's not a memleak---new socket has it */ + + /* reset state for a new socket */ + opt->dccpop_conf = 0; + } + + /* XXX not doing anything about the conf queue */ + +out: + return rc; + +out_clean: + dccp_feat_clean(newdmsk); + rc = -ENOMEM; + goto out; +} + +EXPORT_SYMBOL_GPL(dccp_feat_clone); + +static int __dccp_feat_init(struct dccp_minisock *dmsk, u8 type, u8 feat, + u8 *val, u8 len) +{ + int rc = -ENOMEM; + u8 *copy = kmalloc(len, GFP_KERNEL); + + if (copy != NULL) { + memcpy(copy, val, len); + rc = dccp_feat_change(dmsk, type, feat, copy, len, GFP_KERNEL); + if (rc) + kfree(copy); + } + return rc; +} + +int dccp_feat_init(struct dccp_minisock *dmsk) +{ + int rc; + + INIT_LIST_HEAD(&dmsk->dccpms_pending); + INIT_LIST_HEAD(&dmsk->dccpms_conf); + + /* CCID L */ + rc = __dccp_feat_init(dmsk, DCCPO_CHANGE_L, DCCPF_CCID, + &dmsk->dccpms_tx_ccid, 1); + if (rc) + goto out; + + /* CCID R */ + rc = __dccp_feat_init(dmsk, DCCPO_CHANGE_R, DCCPF_CCID, + &dmsk->dccpms_rx_ccid, 1); + if (rc) + goto out; + + /* Ack ratio */ + rc = __dccp_feat_init(dmsk, DCCPO_CHANGE_L, DCCPF_ACK_RATIO, + &dmsk->dccpms_ack_ratio, 1); +out: + return rc; +} + +EXPORT_SYMBOL_GPL(dccp_feat_init); diff --git a/net/dccp/feat.h b/net/dccp/feat.h new file mode 100644 index 0000000..6048373 --- /dev/null +++ b/net/dccp/feat.h @@ -0,0 +1,29 @@ +#ifndef _DCCP_FEAT_H +#define _DCCP_FEAT_H +/* + * net/dccp/feat.h + * + * An implementation of the DCCP protocol + * Copyright (c) 2005 Andrea Bittau <a.bittau@cs.ucl.ac.uk> + * + * 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. + */ + +#include <linux/types.h> + +struct sock; +struct dccp_minisock; + +extern int dccp_feat_change(struct dccp_minisock *dmsk, u8 type, u8 feature, + u8 *val, u8 len, gfp_t gfp); +extern int dccp_feat_change_recv(struct sock *sk, u8 type, u8 feature, + u8 *val, u8 len); +extern int dccp_feat_confirm_recv(struct sock *sk, u8 type, u8 feature, + u8 *val, u8 len); +extern void dccp_feat_clean(struct dccp_minisock *dmsk); +extern int dccp_feat_clone(struct sock *oldsk, struct sock *newsk); +extern int dccp_feat_init(struct dccp_minisock *dmsk); + +#endif /* _DCCP_FEAT_H */ diff --git a/net/dccp/input.c b/net/dccp/input.c index b6cba72..bfc5366 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -32,7 +32,7 @@ static void dccp_fin(struct sock *sk, struct sk_buff *skb) static void dccp_rcv_close(struct sock *sk, struct sk_buff *skb) { - dccp_v4_send_reset(sk, DCCP_RESET_CODE_CLOSED); + dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED); dccp_fin(sk, skb); dccp_set_state(sk, DCCP_CLOSED); sk_wake_async(sk, 1, POLL_HUP); @@ -56,11 +56,11 @@ static void dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb) dccp_send_close(sk, 0); } -static inline void dccp_event_ack_recv(struct sock *sk, struct sk_buff *skb) +static void dccp_event_ack_recv(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); - if (dp->dccps_options.dccpo_send_ack_vector) + if (dccp_msk(sk)->dccpms_send_ack_vector) dccp_ackvec_check_rcv_ackno(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_ack_seq); } @@ -151,9 +151,8 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb) return 0; } -static inline int __dccp_rcv_established(struct sock *sk, struct sk_buff *skb, - const struct dccp_hdr *dh, - const unsigned len) +static int __dccp_rcv_established(struct sock *sk, struct sk_buff *skb, + const struct dccp_hdr *dh, const unsigned len) { struct dccp_sock *dp = dccp_sk(sk); @@ -247,7 +246,7 @@ int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) dccp_event_ack_recv(sk, skb); - if (dp->dccps_options.dccpo_send_ack_vector && + if (dccp_msk(sk)->dccpms_send_ack_vector && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_ACKVEC_STATE_RECEIVED)) @@ -300,7 +299,10 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, goto out_invalid_packet; } - if (dp->dccps_options.dccpo_send_ack_vector && + if (dccp_parse_options(sk, skb)) + goto out_invalid_packet; + + if (dccp_msk(sk)->dccpms_send_ack_vector && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_ACKVEC_STATE_RECEIVED)) @@ -321,14 +323,6 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, dccp_set_seqno(&dp->dccps_swl, max48(dp->dccps_swl, dp->dccps_isr)); - if (ccid_hc_rx_init(dp->dccps_hc_rx_ccid, sk) != 0 || - ccid_hc_tx_init(dp->dccps_hc_tx_ccid, sk) != 0) { - ccid_hc_rx_exit(dp->dccps_hc_rx_ccid, sk); - ccid_hc_tx_exit(dp->dccps_hc_tx_ccid, sk); - /* FIXME: send appropriate RESET code */ - goto out_invalid_packet; - } - dccp_sync_mss(sk, icsk->icsk_pmtu_cookie); /* @@ -492,7 +486,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) dccp_event_ack_recv(sk, skb); - if (dp->dccps_options.dccpo_send_ack_vector && + if (dccp_msk(sk)->dccpms_send_ack_vector && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_ACKVEC_STATE_RECEIVED)) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index dc0487b..2904799 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -18,8 +18,10 @@ #include <linux/random.h> #include <net/icmp.h> +#include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/inet_sock.h> +#include <net/protocol.h> #include <net/sock.h> #include <net/timewait_sock.h> #include <net/tcp_states.h> @@ -28,14 +30,14 @@ #include "ackvec.h" #include "ccid.h" #include "dccp.h" +#include "feat.h" -struct inet_hashinfo __cacheline_aligned dccp_hashinfo = { - .lhash_lock = RW_LOCK_UNLOCKED, - .lhash_users = ATOMIC_INIT(0), - .lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(dccp_hashinfo.lhash_wait), -}; - -EXPORT_SYMBOL_GPL(dccp_hashinfo); +/* + * This is the global socket data structure used for responding to + * the Out-of-the-blue (OOTB) packets. A control sock will be created + * for this socket at the initialization time. + */ +static struct socket *dccp_v4_ctl_socket; static int dccp_v4_get_port(struct sock *sk, const unsigned short snum) { @@ -43,18 +45,6 @@ static int dccp_v4_get_port(struct sock *sk, const unsigned short snum) inet_csk_bind_conflict); } -static void dccp_v4_hash(struct sock *sk) -{ - inet_hash(&dccp_hashinfo, sk); -} - -void dccp_unhash(struct sock *sk) -{ - inet_unhash(&dccp_hashinfo, sk); -} - -EXPORT_SYMBOL_GPL(dccp_unhash); - int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); @@ -207,11 +197,12 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk, } /* else let the usual retransmit timer handle it */ } -static void dccp_v4_ctl_send_ack(struct sk_buff *rxskb) +static void dccp_v4_reqsk_send_ack(struct sk_buff *rxskb, + struct request_sock *req) { int err; struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh; - const int dccp_hdr_ack_len = sizeof(struct dccp_hdr) + + const u32 dccp_hdr_ack_len = sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext) + sizeof(struct dccp_hdr_ack_bits); struct sk_buff *skb; @@ -219,12 +210,12 @@ static void dccp_v4_ctl_send_ack(struct sk_buff *rxskb) if (((struct rtable *)rxskb->dst)->rt_type != RTN_LOCAL) return; - skb = alloc_skb(MAX_DCCP_HEADER + 15, GFP_ATOMIC); + skb = alloc_skb(dccp_v4_ctl_socket->sk->sk_prot->max_header, GFP_ATOMIC); if (skb == NULL) return; /* Reserve space for headers. */ - skb_reserve(skb, MAX_DCCP_HEADER); + skb_reserve(skb, dccp_v4_ctl_socket->sk->sk_prot->max_header); skb->dst = dst_clone(rxskb->dst); @@ -243,11 +234,11 @@ static void dccp_v4_ctl_send_ack(struct sk_buff *rxskb) dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), DCCP_SKB_CB(rxskb)->dccpd_seq); - bh_lock_sock(dccp_ctl_socket->sk); - err = ip_build_and_send_pkt(skb, dccp_ctl_socket->sk, + bh_lock_sock(dccp_v4_ctl_socket->sk); + err = ip_build_and_send_pkt(skb, dccp_v4_ctl_socket->sk, rxskb->nh.iph->daddr, rxskb->nh.iph->saddr, NULL); - bh_unlock_sock(dccp_ctl_socket->sk); + bh_unlock_sock(dccp_v4_ctl_socket->sk); if (err == NET_XMIT_CN || err == 0) { DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); @@ -255,12 +246,6 @@ static void dccp_v4_ctl_send_ack(struct sk_buff *rxskb) } } -static void dccp_v4_reqsk_send_ack(struct sk_buff *skb, - struct request_sock *req) -{ - dccp_v4_ctl_send_ack(skb); -} - static int dccp_v4_send_response(struct sock *sk, struct request_sock *req, struct dst_entry *dst) { @@ -275,7 +260,10 @@ static int dccp_v4_send_response(struct sock *sk, struct request_sock *req, skb = dccp_make_response(sk, dst, req); if (skb != NULL) { const struct inet_request_sock *ireq = inet_rsk(req); + struct dccp_hdr *dh = dccp_hdr(skb); + dh->dccph_checksum = dccp_v4_checksum(skb, ireq->loc_addr, + ireq->rmt_addr); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr, ireq->rmt_addr, @@ -301,7 +289,7 @@ out: * check at all. A more general error queue to queue errors for later handling * is probably better. */ -void dccp_v4_err(struct sk_buff *skb, u32 info) +static void dccp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (struct iphdr *)skb->data; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + @@ -456,32 +444,6 @@ void dccp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) EXPORT_SYMBOL_GPL(dccp_v4_send_check); -int dccp_v4_send_reset(struct sock *sk, enum dccp_reset_codes code) -{ - struct sk_buff *skb; - /* - * FIXME: what if rebuild_header fails? - * Should we be doing a rebuild_header here? - */ - int err = inet_sk_rebuild_header(sk); - - if (err != 0) - return err; - - skb = dccp_make_reset(sk, sk->sk_dst_cache, code); - if (skb != NULL) { - const struct inet_sock *inet = inet_sk(sk); - - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - err = ip_build_and_send_pkt(skb, sk, - inet->saddr, inet->daddr, NULL); - if (err == NET_XMIT_CN) - err = 0; - } - - return err; -} - static inline u64 dccp_v4_init_sequence(const struct sock *sk, const struct sk_buff *skb) { @@ -497,9 +459,9 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) struct dccp_sock dp; struct request_sock *req; struct dccp_request_sock *dreq; - const __u32 saddr = skb->nh.iph->saddr; - const __u32 daddr = skb->nh.iph->daddr; - const __u32 service = dccp_hdr_request(skb)->dccph_req_service; + const __be32 saddr = skb->nh.iph->saddr; + const __be32 daddr = skb->nh.iph->daddr; + const __be32 service = dccp_hdr_request(skb)->dccph_req_service; struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); __u8 reset_code = DCCP_RESET_CODE_TOO_BUSY; @@ -535,7 +497,8 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (req == NULL) goto drop; - /* FIXME: process options */ + if (dccp_parse_options(sk, skb)) + goto drop; dccp_openreq_init(req, &dp, skb); @@ -660,8 +623,8 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) return sk; } -int dccp_v4_checksum(const struct sk_buff *skb, const u32 saddr, - const u32 daddr) +int dccp_v4_checksum(const struct sk_buff *skb, const __be32 saddr, + const __be32 daddr) { const struct dccp_hdr* dh = dccp_hdr(skb); int checksum_len; @@ -680,8 +643,10 @@ int dccp_v4_checksum(const struct sk_buff *skb, const u32 saddr, IPPROTO_DCCP, tmp); } +EXPORT_SYMBOL_GPL(dccp_v4_checksum); + static int dccp_v4_verify_checksum(struct sk_buff *skb, - const u32 saddr, const u32 daddr) + const __be32 saddr, const __be32 daddr) { struct dccp_hdr *dh = dccp_hdr(skb); int checksum_len; @@ -741,16 +706,17 @@ static void dccp_v4_ctl_send_reset(struct sk_buff *rxskb) if (((struct rtable *)rxskb->dst)->rt_type != RTN_LOCAL) return; - dst = dccp_v4_route_skb(dccp_ctl_socket->sk, rxskb); + dst = dccp_v4_route_skb(dccp_v4_ctl_socket->sk, rxskb); if (dst == NULL) return; - skb = alloc_skb(MAX_DCCP_HEADER + 15, GFP_ATOMIC); + skb = alloc_skb(dccp_v4_ctl_socket->sk->sk_prot->max_header, + GFP_ATOMIC); if (skb == NULL) goto out; /* Reserve space for headers. */ - skb_reserve(skb, MAX_DCCP_HEADER); + skb_reserve(skb, dccp_v4_ctl_socket->sk->sk_prot->max_header); skb->dst = dst_clone(dst); skb->h.raw = skb_push(skb, dccp_hdr_reset_len); @@ -778,11 +744,11 @@ static void dccp_v4_ctl_send_reset(struct sk_buff *rxskb) dh->dccph_checksum = dccp_v4_checksum(skb, rxskb->nh.iph->saddr, rxskb->nh.iph->daddr); - bh_lock_sock(dccp_ctl_socket->sk); - err = ip_build_and_send_pkt(skb, dccp_ctl_socket->sk, + bh_lock_sock(dccp_v4_ctl_socket->sk); + err = ip_build_and_send_pkt(skb, dccp_v4_ctl_socket->sk, rxskb->nh.iph->daddr, rxskb->nh.iph->saddr, NULL); - bh_unlock_sock(dccp_ctl_socket->sk); + bh_unlock_sock(dccp_v4_ctl_socket->sk); if (err == NET_XMIT_CN || err == 0) { DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); @@ -912,7 +878,7 @@ int dccp_invalid_packet(struct sk_buff *skb) EXPORT_SYMBOL_GPL(dccp_invalid_packet); /* this is called when real data arrives */ -int dccp_v4_rcv(struct sk_buff *skb) +static int dccp_v4_rcv(struct sk_buff *skb) { const struct dccp_hdr *dh; struct sock *sk; @@ -1019,111 +985,37 @@ do_time_wait: goto no_dccp_socket; } -struct inet_connection_sock_af_ops dccp_ipv4_af_ops = { - .queue_xmit = ip_queue_xmit, - .send_check = dccp_v4_send_check, - .rebuild_header = inet_sk_rebuild_header, - .conn_request = dccp_v4_conn_request, - .syn_recv_sock = dccp_v4_request_recv_sock, - .net_header_len = sizeof(struct iphdr), - .setsockopt = ip_setsockopt, - .getsockopt = ip_getsockopt, - .addr2sockaddr = inet_csk_addr2sockaddr, - .sockaddr_len = sizeof(struct sockaddr_in), +static struct inet_connection_sock_af_ops dccp_ipv4_af_ops = { + .queue_xmit = ip_queue_xmit, + .send_check = dccp_v4_send_check, + .rebuild_header = inet_sk_rebuild_header, + .conn_request = dccp_v4_conn_request, + .syn_recv_sock = dccp_v4_request_recv_sock, + .net_header_len = sizeof(struct iphdr), + .setsockopt = ip_setsockopt, + .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 }; -int dccp_v4_init_sock(struct sock *sk) -{ - struct dccp_sock *dp = dccp_sk(sk); - struct inet_connection_sock *icsk = inet_csk(sk); - static int dccp_ctl_socket_init = 1; - - dccp_options_init(&dp->dccps_options); - do_gettimeofday(&dp->dccps_epoch); - - if (dp->dccps_options.dccpo_send_ack_vector) { - dp->dccps_hc_rx_ackvec = dccp_ackvec_alloc(DCCP_MAX_ACKVEC_LEN, - GFP_KERNEL); - if (dp->dccps_hc_rx_ackvec == NULL) - return -ENOMEM; - } - - /* - * FIXME: We're hardcoding the CCID, and doing this at this point makes - * the listening (master) sock get CCID control blocks, which is not - * necessary, but for now, to not mess with the test userspace apps, - * lets leave it here, later the real solution is to do this in a - * setsockopt(CCIDs-I-want/accept). -acme - */ - if (likely(!dccp_ctl_socket_init)) { - dp->dccps_hc_rx_ccid = ccid_init(dp->dccps_options.dccpo_rx_ccid, - sk); - dp->dccps_hc_tx_ccid = ccid_init(dp->dccps_options.dccpo_tx_ccid, - sk); - if (dp->dccps_hc_rx_ccid == NULL || - dp->dccps_hc_tx_ccid == NULL) { - ccid_exit(dp->dccps_hc_rx_ccid, sk); - ccid_exit(dp->dccps_hc_tx_ccid, sk); - if (dp->dccps_options.dccpo_send_ack_vector) { - dccp_ackvec_free(dp->dccps_hc_rx_ackvec); - dp->dccps_hc_rx_ackvec = NULL; - } - dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL; - return -ENOMEM; - } - } else - dccp_ctl_socket_init = 0; - - dccp_init_xmit_timers(sk); - icsk->icsk_rto = DCCP_TIMEOUT_INIT; - sk->sk_state = DCCP_CLOSED; - sk->sk_write_space = dccp_write_space; - icsk->icsk_af_ops = &dccp_ipv4_af_ops; - icsk->icsk_sync_mss = dccp_sync_mss; - dp->dccps_mss_cache = 536; - dp->dccps_role = DCCP_ROLE_UNDEFINED; - dp->dccps_service = DCCP_SERVICE_INVALID_VALUE; - - return 0; -} - -EXPORT_SYMBOL_GPL(dccp_v4_init_sock); - -int dccp_v4_destroy_sock(struct sock *sk) +static int dccp_v4_init_sock(struct sock *sk) { - struct dccp_sock *dp = dccp_sk(sk); + static __u8 dccp_v4_ctl_sock_initialized; + int err = dccp_init_sock(sk, dccp_v4_ctl_sock_initialized); - /* - * DCCP doesn't use sk_write_queue, just sk_send_head - * for retransmissions - */ - if (sk->sk_send_head != NULL) { - kfree_skb(sk->sk_send_head); - sk->sk_send_head = NULL; + if (err == 0) { + if (unlikely(!dccp_v4_ctl_sock_initialized)) + dccp_v4_ctl_sock_initialized = 1; + inet_csk(sk)->icsk_af_ops = &dccp_ipv4_af_ops; } - /* Clean up a referenced DCCP bind bucket. */ - if (inet_csk(sk)->icsk_bind_hash != NULL) - inet_put_port(&dccp_hashinfo, sk); - - kfree(dp->dccps_service_list); - dp->dccps_service_list = NULL; - - ccid_hc_rx_exit(dp->dccps_hc_rx_ccid, sk); - ccid_hc_tx_exit(dp->dccps_hc_tx_ccid, sk); - if (dp->dccps_options.dccpo_send_ack_vector) { - dccp_ackvec_free(dp->dccps_hc_rx_ackvec); - dp->dccps_hc_rx_ackvec = NULL; - } - ccid_exit(dp->dccps_hc_rx_ccid, sk); - ccid_exit(dp->dccps_hc_tx_ccid, sk); - dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL; - - return 0; + return err; } -EXPORT_SYMBOL_GPL(dccp_v4_destroy_sock); - static void dccp_v4_reqsk_destructor(struct request_sock *req) { kfree(inet_rsk(req)->opt); @@ -1142,7 +1034,7 @@ static struct timewait_sock_ops dccp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct inet_timewait_sock), }; -struct proto dccp_prot = { +static struct proto dccp_v4_prot = { .name = "DCCP", .owner = THIS_MODULE, .close = dccp_close, @@ -1155,17 +1047,110 @@ struct proto dccp_prot = { .sendmsg = dccp_sendmsg, .recvmsg = dccp_recvmsg, .backlog_rcv = dccp_v4_do_rcv, - .hash = dccp_v4_hash, + .hash = dccp_hash, .unhash = dccp_unhash, .accept = inet_csk_accept, .get_port = dccp_v4_get_port, .shutdown = dccp_shutdown, - .destroy = dccp_v4_destroy_sock, + .destroy = dccp_destroy_sock, .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp_sock), .rsk_prot = &dccp_request_sock_ops, .twsk_prot = &dccp_timewait_sock_ops, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_dccp_setsockopt, + .compat_getsockopt = compat_dccp_getsockopt, +#endif +}; + +static struct net_protocol dccp_v4_protocol = { + .handler = dccp_v4_rcv, + .err_handler = dccp_v4_err, + .no_policy = 1, +}; + +static const struct proto_ops inet_dccp_ops = { + .family = PF_INET, + .owner = THIS_MODULE, + .release = inet_release, + .bind = inet_bind, + .connect = inet_stream_connect, + .socketpair = sock_no_socketpair, + .accept = inet_accept, + .getname = inet_getname, + /* FIXME: work on tcp_poll to rename it to inet_csk_poll */ + .poll = dccp_poll, + .ioctl = inet_ioctl, + /* FIXME: work on inet_listen to rename it to sock_common_listen */ + .listen = inet_dccp_listen, + .shutdown = inet_shutdown, + .setsockopt = sock_common_setsockopt, + .getsockopt = sock_common_getsockopt, + .sendmsg = inet_sendmsg, + .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 }; -EXPORT_SYMBOL_GPL(dccp_prot); +static struct inet_protosw dccp_v4_protosw = { + .type = SOCK_DCCP, + .protocol = IPPROTO_DCCP, + .prot = &dccp_v4_prot, + .ops = &inet_dccp_ops, + .capability = -1, + .no_check = 0, + .flags = INET_PROTOSW_ICSK, +}; + +static int __init dccp_v4_init(void) +{ + int err = proto_register(&dccp_v4_prot, 1); + + if (err != 0) + goto out; + + err = inet_add_protocol(&dccp_v4_protocol, IPPROTO_DCCP); + if (err != 0) + goto out_proto_unregister; + + inet_register_protosw(&dccp_v4_protosw); + + err = inet_csk_ctl_sock_create(&dccp_v4_ctl_socket, PF_INET, + SOCK_DCCP, IPPROTO_DCCP); + if (err) + goto out_unregister_protosw; +out: + return err; +out_unregister_protosw: + inet_unregister_protosw(&dccp_v4_protosw); + inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP); +out_proto_unregister: + proto_unregister(&dccp_v4_prot); + goto out; +} + +static void __exit dccp_v4_exit(void) +{ + inet_unregister_protosw(&dccp_v4_protosw); + inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP); + proto_unregister(&dccp_v4_prot); +} + +module_init(dccp_v4_init); +module_exit(dccp_v4_exit); + +/* + * __stringify doesn't likes enums, so use SOCK_DCCP (6) and IPPROTO_DCCP (33) + * values directly, Also cover the case where the protocol is not specified, + * i.e. net-pf-PF_INET-proto-0-type-SOCK_DCCP + */ +MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-33-type-6"); +MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-0-type-6"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>"); +MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol"); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 80c4d04..65e2ab0 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1,6 +1,6 @@ /* * DCCP over IPv6 - * Linux INET6 implementation + * Linux INET6 implementation * * Based on net/dccp6/ipv6.c * @@ -33,6 +33,9 @@ #include "dccp.h" #include "ipv6.h" +/* Socket used for sending RSTs and ACKs */ +static struct socket *dccp_v6_ctl_socket; + static void dccp_v6_ctl_send_reset(struct sk_buff *skb); static void dccp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req); @@ -53,7 +56,7 @@ static void dccp_v6_hash(struct sock *sk) { if (sk->sk_state != DCCP_CLOSED) { if (inet_csk(sk)->icsk_af_ops == &dccp_ipv6_mapped) { - dccp_prot.hash(sk); + dccp_hash(sk); return; } local_bh_disable(); @@ -63,8 +66,8 @@ static void dccp_v6_hash(struct sock *sk) } static inline u16 dccp_v6_check(struct dccp_hdr *dh, int len, - struct in6_addr *saddr, - struct in6_addr *daddr, + struct in6_addr *saddr, + struct in6_addr *daddr, unsigned long base) { return csum_ipv6_magic(saddr, daddr, len, IPPROTO_DCCP, base); @@ -79,17 +82,17 @@ static __u32 dccp_v6_init_sequence(struct sock *sk, struct sk_buff *skb) skb->nh.ipv6h->saddr.s6_addr32, dh->dccph_dport, dh->dccph_sport); - else - return secure_dccp_sequence_number(skb->nh.iph->daddr, - skb->nh.iph->saddr, - dh->dccph_dport, - dh->dccph_sport); + + return secure_dccp_sequence_number(skb->nh.iph->daddr, + skb->nh.iph->saddr, + dh->dccph_dport, + dh->dccph_sport); } -static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, +static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; + struct sockaddr_in6 *usin = (struct sockaddr_in6 *)uaddr; struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -102,10 +105,10 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, dp->dccps_role = DCCP_ROLE_CLIENT; - if (addr_len < SIN6_LEN_RFC2133) + if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; - if (usin->sin6_family != AF_INET6) + if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; memset(&fl, 0, sizeof(fl)); @@ -122,17 +125,15 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl6_sock_release(flowlabel); } } - /* - * connect() to INADDR_ANY means loopback (BSD'ism). - */ - - if (ipv6_addr_any(&usin->sin6_addr)) - usin->sin6_addr.s6_addr[15] = 0x1; + * connect() to INADDR_ANY means loopback (BSD'ism). + */ + if (ipv6_addr_any(&usin->sin6_addr)) + usin->sin6_addr.s6_addr[15] = 1; addr_type = ipv6_addr_type(&usin->sin6_addr); - if(addr_type & IPV6_ADDR_MULTICAST) + if (addr_type & IPV6_ADDR_MULTICAST) return -ENETUNREACH; if (addr_type & IPV6_ADDR_LINKLOCAL) { @@ -157,9 +158,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, np->flow_label = fl.fl6_flowlabel; /* - * DCCP over IPv4 + * DCCP over IPv4 */ - if (addr_type == IPV6_ADDR_MAPPED) { u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; @@ -177,7 +177,6 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_backlog_rcv = dccp_v4_do_rcv; err = dccp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin)); - if (err) { icsk->icsk_ext_hdr_len = exthdrlen; icsk->icsk_af_ops = &dccp_ipv6_af_ops; @@ -203,8 +202,9 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl.fl_ip_dport = usin->sin6_port; fl.fl_ip_sport = inet->sport; - if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; + if (np->opt != NULL && np->opt->srcrt != NULL) { + const struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; + ipv6_addr_copy(&final, &fl.fl6_dst); ipv6_addr_copy(&fl.fl6_dst, rt0->addr); final_p = &final; @@ -213,10 +213,12 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, err = ip6_dst_lookup(sk, &dst, &fl); if (err) goto failure; + if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + err = xfrm_lookup(&dst, &fl, sk, 0); + if (err < 0) goto failure; if (saddr == NULL) { @@ -231,7 +233,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, ip6_dst_store(sk, dst, NULL); icsk->icsk_ext_hdr_len = 0; - if (np->opt) + if (np->opt != NULL) icsk->icsk_ext_hdr_len = (np->opt->opt_flen + np->opt->opt_nflen); @@ -264,7 +266,7 @@ failure: } static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) + int type, int code, int offset, __be32 info) { struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); @@ -305,7 +307,6 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* icmp should have updated the destination cache entry */ dst = __sk_dst_check(sk, np->dst_cookie); - if (dst == NULL) { struct inet_sock *inet = inet_sk(sk); struct flowi fl; @@ -322,16 +323,17 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, fl.fl_ip_dport = inet->dport; fl.fl_ip_sport = inet->sport; - if ((err = ip6_dst_lookup(sk, &dst, &fl))) { + err = ip6_dst_lookup(sk, &dst, &fl); + if (err) { sk->sk_err_soft = -err; goto out; } - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { + err = xfrm_lookup(&dst, &fl, sk, 0); + if (err < 0) { sk->sk_err_soft = -err; goto out; } - } else dst_hold(dst); @@ -355,11 +357,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, req = inet6_csk_search_req(sk, &prev, dh->dccph_dport, &hdr->daddr, &hdr->saddr, inet6_iif(skb)); - if (!req) + if (req == NULL) goto out; - /* ICMPs are not backlogged, hence we cannot get - * an established socket here. + /* + * ICMPs are not backlogged, hence we cannot get an established + * socket here. */ BUG_TRAP(req->sk == NULL); @@ -373,7 +376,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, case DCCP_REQUESTING: case DCCP_RESPOND: /* Cannot happen. - It can, it SYNs are crossed. --ANK */ + It can, it SYNs are crossed. --ANK */ if (!sock_owned_by_user(sk)) { DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; @@ -382,7 +385,6 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, * (see connect in sock.c) */ sk->sk_error_report(sk); - dccp_done(sk); } else sk->sk_err_soft = err; @@ -428,14 +430,16 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, ireq6->pktopts) { struct sk_buff *pktopts = ireq6->pktopts; struct inet6_skb_parm *rxopt = IP6CB(pktopts); + if (rxopt->srcrt) opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr *)(pktopts->nh.raw + rxopt->srcrt)); } - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt; + if (opt != NULL && opt->srcrt != NULL) { + const struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt; + ipv6_addr_copy(&final, &fl.fl6_dst); ipv6_addr_copy(&fl.fl6_dst, rt0->addr); final_p = &final; @@ -444,15 +448,19 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, err = ip6_dst_lookup(sk, &dst, &fl); if (err) goto done; + if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + + err = xfrm_lookup(&dst, &fl, sk, 0); + if (err < 0) goto done; } skb = dccp_make_response(sk, dst, req); if (skb != NULL) { struct dccp_hdr *dh = dccp_hdr(skb); + dh->dccph_checksum = dccp_v6_check(dh, skb->len, &ireq6->loc_addr, &ireq6->rmt_addr, @@ -466,7 +474,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, } done: - if (opt && opt != np->opt) + if (opt != NULL && opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); dst_release(dst); return err; @@ -497,7 +505,7 @@ static void dccp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) struct dccp_hdr *dh = dccp_hdr(skb); dh->dccph_checksum = csum_ipv6_magic(&np->saddr, &np->daddr, - len, IPPROTO_DCCP, + len, IPPROTO_DCCP, csum_partial((char *)dh, dh->dccph_doff << 2, skb->csum)); @@ -505,8 +513,8 @@ static void dccp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) static void dccp_v6_ctl_send_reset(struct sk_buff *rxskb) { - struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh; - const int dccp_hdr_reset_len = sizeof(struct dccp_hdr) + + struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh; + const u32 dccp_hdr_reset_len = sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext) + sizeof(struct dccp_hdr_reset); struct sk_buff *skb; @@ -517,20 +525,14 @@ static void dccp_v6_ctl_send_reset(struct sk_buff *rxskb) return; if (!ipv6_unicast_destination(rxskb)) - return; - - /* - * We need to grab some memory, and put together an RST, - * and then put it into the queue to be sent. - */ + return; - skb = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + - dccp_hdr_reset_len, GFP_ATOMIC); - if (skb == NULL) + skb = alloc_skb(dccp_v6_ctl_socket->sk->sk_prot->max_header, + GFP_ATOMIC); + if (skb == NULL) return; - skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr) + - dccp_hdr_reset_len); + skb_reserve(skb, dccp_v6_ctl_socket->sk->sk_prot->max_header); skb->h.raw = skb_push(skb, dccp_hdr_reset_len); dh = dccp_hdr(skb); @@ -568,7 +570,7 @@ static void dccp_v6_ctl_send_reset(struct sk_buff *rxskb) /* sk = NULL, but it is safe for now. RST socket required. */ if (!ip6_dst_lookup(NULL, &skb->dst, &fl)) { if (xfrm_lookup(&skb->dst, &fl, NULL, 0) >= 0) { - ip6_xmit(NULL, skb, &fl, NULL, 0); + ip6_xmit(dccp_v6_ctl_socket->sk, skb, &fl, NULL, 0); DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS); return; @@ -578,22 +580,22 @@ static void dccp_v6_ctl_send_reset(struct sk_buff *rxskb) kfree_skb(skb); } -static void dccp_v6_ctl_send_ack(struct sk_buff *rxskb) +static void dccp_v6_reqsk_send_ack(struct sk_buff *rxskb, + struct request_sock *req) { struct flowi fl; struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh; - const int dccp_hdr_ack_len = sizeof(struct dccp_hdr) + + const u32 dccp_hdr_ack_len = sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext) + sizeof(struct dccp_hdr_ack_bits); struct sk_buff *skb; - skb = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + - dccp_hdr_ack_len, GFP_ATOMIC); + skb = alloc_skb(dccp_v6_ctl_socket->sk->sk_prot->max_header, + GFP_ATOMIC); if (skb == NULL) return; - skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr) + - dccp_hdr_ack_len); + skb_reserve(skb, dccp_v6_ctl_socket->sk->sk_prot->max_header); skb->h.raw = skb_push(skb, dccp_hdr_ack_len); dh = dccp_hdr(skb); @@ -605,7 +607,7 @@ static void dccp_v6_ctl_send_ack(struct sk_buff *rxskb) dh->dccph_dport = rxdh->dccph_sport; dh->dccph_doff = dccp_hdr_ack_len / 4; dh->dccph_x = 1; - + dccp_hdr_set_seq(dh, DCCP_SKB_CB(rxskb)->dccpd_ack_seq); dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), DCCP_SKB_CB(rxskb)->dccpd_seq); @@ -623,7 +625,7 @@ static void dccp_v6_ctl_send_ack(struct sk_buff *rxskb) if (!ip6_dst_lookup(NULL, &skb->dst, &fl)) { if (xfrm_lookup(&skb->dst, &fl, NULL, 0) >= 0) { - ip6_xmit(NULL, skb, &fl, NULL, 0); + ip6_xmit(dccp_v6_ctl_socket->sk, skb, &fl, NULL, 0); DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); return; } @@ -632,12 +634,6 @@ static void dccp_v6_ctl_send_ack(struct sk_buff *rxskb) kfree_skb(skb); } -static void dccp_v6_reqsk_send_ack(struct sk_buff *skb, - struct request_sock *req) -{ - dccp_v6_ctl_send_ack(skb); -} - static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) { const struct dccp_hdr *dh = dccp_hdr(skb); @@ -657,7 +653,6 @@ static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) &iph->saddr, dh->dccph_sport, &iph->daddr, ntohs(dh->dccph_dport), inet6_iif(skb)); - if (nsk != NULL) { if (nsk->sk_state != DCCP_TIME_WAIT) { bh_lock_sock(nsk); @@ -678,7 +673,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) struct dccp_request_sock *dreq; struct inet6_request_sock *ireq6; struct ipv6_pinfo *np = inet6_sk(sk); - const __u32 service = dccp_hdr_request(skb)->dccph_req_service; + const __be32 service = dccp_hdr_request(skb)->dccph_req_service; struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); __u8 reset_code = DCCP_RESET_CODE_TOO_BUSY; @@ -686,17 +681,17 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) return dccp_v4_conn_request(sk, skb); if (!ipv6_unicast_destination(skb)) - goto drop; + goto drop; if (dccp_bad_service_code(sk, service)) { reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE; goto drop; } /* - * There are no SYN attacks on IPv6, yet... + * There are no SYN attacks on IPv6, yet... */ if (inet_csk_reqsk_queue_is_full(sk)) - goto drop; + goto drop; if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; @@ -730,7 +725,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq6->iif = inet6_iif(skb); - /* + /* * Step 3: Process LISTEN state * * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie @@ -774,9 +769,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, /* * v6 mapped */ - newsk = dccp_v4_request_recv_sock(sk, skb, req, dst); - if (newsk == NULL) + if (newsk == NULL) return NULL; newdp6 = (struct dccp6_sock *)newsk; @@ -822,9 +816,9 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, if (sk_acceptq_is_full(sk)) goto out_overflow; - if (np->rxopt.bits.osrcrt == 2 && - opt == NULL && ireq6->pktopts) { - struct inet6_skb_parm *rxopt = IP6CB(ireq6->pktopts); + if (np->rxopt.bits.osrcrt == 2 && opt == NULL && ireq6->pktopts) { + const struct inet6_skb_parm *rxopt = IP6CB(ireq6->pktopts); + if (rxopt->srcrt) opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr *)(ireq6->pktopts->nh.raw + @@ -838,8 +832,9 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, memset(&fl, 0, sizeof(fl)); fl.proto = IPPROTO_DCCP; ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; + if (opt != NULL && opt->srcrt != NULL) { + const struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt; + ipv6_addr_copy(&final, &fl.fl6_dst); ipv6_addr_copy(&fl.fl6_dst, rt0->addr); final_p = &final; @@ -857,7 +852,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0) goto out; - } + } newsk = dccp_create_openreq_child(sk, req, skb); if (newsk == NULL) @@ -870,9 +865,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, */ ip6_dst_store(newsk, dst, NULL); - newsk->sk_route_caps = dst->dev->features & - ~(NETIF_F_IP_CSUM | NETIF_F_TSO); - + newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM | + NETIF_F_TSO); newdp6 = (struct dccp6_sock *)newsk; newinet = inet_sk(newsk); newinet->pinet6 = &newdp6->inet6; @@ -886,7 +880,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, ipv6_addr_copy(&newnp->rcv_saddr, &ireq6->loc_addr); newsk->sk_bound_dev_if = ireq6->iif; - /* Now IPv6 options... + /* Now IPv6 options... First: no IPv4 options. */ @@ -908,20 +902,20 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = skb->nh.ipv6h->hop_limit; - /* Clone native IPv6 options from listening socket (if any) - - Yes, keeping reference count would be much more clever, - but we make one more one thing there: reattach optmem - to newsk. + /* + * Clone native IPv6 options from listening socket (if any) + * + * Yes, keeping reference count would be much more clever, but we make + * one more one thing there: reattach optmem to newsk. */ - if (opt) { + if (opt != NULL) { newnp->opt = ipv6_dup_options(newsk, opt); if (opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); } inet_csk(newsk)->icsk_ext_hdr_len = 0; - if (newnp->opt) + if (newnp->opt != NULL) inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen + newnp->opt->opt_flen); @@ -938,7 +932,7 @@ out_overflow: NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS); out: NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS); - if (opt && opt != np->opt) + if (opt != NULL && opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); dst_release(dst); return NULL; @@ -972,8 +966,8 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) goto discard; /* - * socket locking is here for SMP purposes as backlog rcv - * is currently called with bh processing disabled. + * socket locking is here for SMP purposes as backlog rcv is currently + * called with bh processing disabled. */ /* Do Stevens' IPV6_PKTOPTIONS. @@ -998,20 +992,20 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; } - if (sk->sk_state == DCCP_LISTEN) { + if (sk->sk_state == DCCP_LISTEN) { struct sock *nsk = dccp_v6_hnd_req(sk, skb); - if (!nsk) - goto discard; + if (nsk == NULL) + goto discard; /* * Queue it on the new socket if the new socket is active, * otherwise we just shortcircuit this and continue with * the new socket.. */ - if(nsk != sk) { + if (nsk != sk) { if (dccp_child_process(sk, nsk, skb)) goto reset; - if (opt_skb) + if (opt_skb != NULL) __kfree_skb(opt_skb); return 0; } @@ -1024,7 +1018,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) reset: dccp_v6_ctl_send_reset(skb); discard: - if (opt_skb) + if (opt_skb != NULL) __kfree_skb(opt_skb); kfree_skb(skb); return 0; @@ -1057,7 +1051,7 @@ static int dccp_v6_rcv(struct sk_buff **pskb) dh->dccph_sport, &skb->nh.ipv6h->daddr, ntohs(dh->dccph_dport), inet6_iif(skb)); - /* + /* * Step 2: * If no socket ... * Generate Reset(No Connection) unless P.type == Reset @@ -1066,15 +1060,14 @@ static int dccp_v6_rcv(struct sk_buff **pskb) if (sk == NULL) goto no_dccp_socket; - /* + /* * Step 2: * ... or S.state == TIMEWAIT, * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ - if (sk->sk_state == DCCP_TIME_WAIT) - goto do_time_wait; + goto do_time_wait; if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; @@ -1113,32 +1106,40 @@ do_time_wait: } static struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { - .queue_xmit = inet6_csk_xmit, - .send_check = dccp_v6_send_check, - .rebuild_header = inet6_sk_rebuild_header, - .conn_request = dccp_v6_conn_request, - .syn_recv_sock = dccp_v6_request_recv_sock, - .net_header_len = sizeof(struct ipv6hdr), - .setsockopt = ipv6_setsockopt, - .getsockopt = ipv6_getsockopt, - .addr2sockaddr = inet6_csk_addr2sockaddr, - .sockaddr_len = sizeof(struct sockaddr_in6) + .queue_xmit = inet6_csk_xmit, + .send_check = dccp_v6_send_check, + .rebuild_header = inet6_sk_rebuild_header, + .conn_request = dccp_v6_conn_request, + .syn_recv_sock = dccp_v6_request_recv_sock, + .net_header_len = sizeof(struct ipv6hdr), + .setsockopt = ipv6_setsockopt, + .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 }; /* * DCCP over IPv4 via INET6 API */ static struct inet_connection_sock_af_ops dccp_ipv6_mapped = { - .queue_xmit = ip_queue_xmit, - .send_check = dccp_v4_send_check, - .rebuild_header = inet_sk_rebuild_header, - .conn_request = dccp_v6_conn_request, - .syn_recv_sock = dccp_v6_request_recv_sock, - .net_header_len = sizeof(struct iphdr), - .setsockopt = ipv6_setsockopt, - .getsockopt = ipv6_getsockopt, - .addr2sockaddr = inet6_csk_addr2sockaddr, - .sockaddr_len = sizeof(struct sockaddr_in6) + .queue_xmit = ip_queue_xmit, + .send_check = dccp_v4_send_check, + .rebuild_header = inet_sk_rebuild_header, + .conn_request = dccp_v6_conn_request, + .syn_recv_sock = dccp_v6_request_recv_sock, + .net_header_len = sizeof(struct iphdr), + .setsockopt = ipv6_setsockopt, + .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 @@ -1146,71 +1147,83 @@ static struct inet_connection_sock_af_ops dccp_ipv6_mapped = { */ static int dccp_v6_init_sock(struct sock *sk) { - int err = dccp_v4_init_sock(sk); + static __u8 dccp_v6_ctl_sock_initialized; + int err = dccp_init_sock(sk, dccp_v6_ctl_sock_initialized); - if (err == 0) + if (err == 0) { + if (unlikely(!dccp_v6_ctl_sock_initialized)) + dccp_v6_ctl_sock_initialized = 1; inet_csk(sk)->icsk_af_ops = &dccp_ipv6_af_ops; + } return err; } static int dccp_v6_destroy_sock(struct sock *sk) { - dccp_v4_destroy_sock(sk); + dccp_destroy_sock(sk); return inet6_destroy_sock(sk); } static struct proto dccp_v6_prot = { - .name = "DCCPv6", - .owner = THIS_MODULE, - .close = dccp_close, - .connect = dccp_v6_connect, - .disconnect = dccp_disconnect, - .ioctl = dccp_ioctl, - .init = dccp_v6_init_sock, - .setsockopt = dccp_setsockopt, - .getsockopt = dccp_getsockopt, - .sendmsg = dccp_sendmsg, - .recvmsg = dccp_recvmsg, - .backlog_rcv = dccp_v6_do_rcv, - .hash = dccp_v6_hash, - .unhash = dccp_unhash, - .accept = inet_csk_accept, - .get_port = dccp_v6_get_port, - .shutdown = dccp_shutdown, - .destroy = dccp_v6_destroy_sock, - .orphan_count = &dccp_orphan_count, - .max_header = MAX_DCCP_HEADER, - .obj_size = sizeof(struct dccp6_sock), - .rsk_prot = &dccp6_request_sock_ops, - .twsk_prot = &dccp6_timewait_sock_ops, + .name = "DCCPv6", + .owner = THIS_MODULE, + .close = dccp_close, + .connect = dccp_v6_connect, + .disconnect = dccp_disconnect, + .ioctl = dccp_ioctl, + .init = dccp_v6_init_sock, + .setsockopt = dccp_setsockopt, + .getsockopt = dccp_getsockopt, + .sendmsg = dccp_sendmsg, + .recvmsg = dccp_recvmsg, + .backlog_rcv = dccp_v6_do_rcv, + .hash = dccp_v6_hash, + .unhash = dccp_unhash, + .accept = inet_csk_accept, + .get_port = dccp_v6_get_port, + .shutdown = dccp_shutdown, + .destroy = dccp_v6_destroy_sock, + .orphan_count = &dccp_orphan_count, + .max_header = MAX_DCCP_HEADER, + .obj_size = sizeof(struct dccp6_sock), + .rsk_prot = &dccp6_request_sock_ops, + .twsk_prot = &dccp6_timewait_sock_ops, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_dccp_setsockopt, + .compat_getsockopt = compat_dccp_getsockopt, +#endif }; static struct inet6_protocol dccp_v6_protocol = { - .handler = dccp_v6_rcv, - .err_handler = dccp_v6_err, - .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, + .handler = dccp_v6_rcv, + .err_handler = dccp_v6_err, + .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, }; static struct proto_ops inet6_dccp_ops = { - .family = PF_INET6, - .owner = THIS_MODULE, - .release = inet6_release, - .bind = inet6_bind, - .connect = inet_stream_connect, - .socketpair = sock_no_socketpair, - .accept = inet_accept, - .getname = inet6_getname, - .poll = dccp_poll, - .ioctl = inet6_ioctl, - .listen = inet_dccp_listen, - .shutdown = inet_shutdown, - .setsockopt = sock_common_setsockopt, - .getsockopt = sock_common_getsockopt, - .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, - .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, + .family = PF_INET6, + .owner = THIS_MODULE, + .release = inet6_release, + .bind = inet6_bind, + .connect = inet_stream_connect, + .socketpair = sock_no_socketpair, + .accept = inet_accept, + .getname = inet6_getname, + .poll = dccp_poll, + .ioctl = inet6_ioctl, + .listen = inet_dccp_listen, + .shutdown = inet_shutdown, + .setsockopt = sock_common_setsockopt, + .getsockopt = sock_common_getsockopt, + .sendmsg = inet_sendmsg, + .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_v6_protosw = { @@ -1234,8 +1247,16 @@ static int __init dccp_v6_init(void) goto out_unregister_proto; inet6_register_protosw(&dccp_v6_protosw); + + err = inet_csk_ctl_sock_create(&dccp_v6_ctl_socket, PF_INET6, + SOCK_DCCP, IPPROTO_DCCP); + if (err != 0) + goto out_unregister_protosw; out: return err; +out_unregister_protosw: + inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP); + inet6_unregister_protosw(&dccp_v6_protosw); out_unregister_proto: proto_unregister(&dccp_v6_prot); goto out; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 29261fc..c0349e5 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -22,6 +22,7 @@ #include "ackvec.h" #include "ccid.h" #include "dccp.h" +#include "feat.h" struct inet_timewait_death_row dccp_death_row = { .sysctl_max_tw_buckets = NR_FILE * 2, @@ -106,6 +107,7 @@ struct sock *dccp_create_openreq_child(struct sock *sk, const struct dccp_request_sock *dreq = dccp_rsk(req); struct inet_connection_sock *newicsk = inet_csk(sk); struct dccp_sock *newdp = dccp_sk(newsk); + struct dccp_minisock *newdmsk = dccp_msk(newsk); newdp->dccps_role = DCCP_ROLE_SERVER; newdp->dccps_hc_rx_ackvec = NULL; @@ -114,27 +116,27 @@ struct sock *dccp_create_openreq_child(struct sock *sk, newicsk->icsk_rto = DCCP_TIMEOUT_INIT; do_gettimeofday(&newdp->dccps_epoch); - if (newdp->dccps_options.dccpo_send_ack_vector) { + if (dccp_feat_clone(sk, newsk)) + goto out_free; + + if (newdmsk->dccpms_send_ack_vector) { newdp->dccps_hc_rx_ackvec = - dccp_ackvec_alloc(DCCP_MAX_ACKVEC_LEN, - GFP_ATOMIC); - /* - * XXX: We're using the same CCIDs set on the parent, - * i.e. sk_clone copied the master sock and left the - * CCID pointers for this child, that is why we do the - * __ccid_get calls. - */ + dccp_ackvec_alloc(GFP_ATOMIC); if (unlikely(newdp->dccps_hc_rx_ackvec == NULL)) goto out_free; } - if (unlikely(ccid_hc_rx_init(newdp->dccps_hc_rx_ccid, - newsk) != 0 || - ccid_hc_tx_init(newdp->dccps_hc_tx_ccid, - newsk) != 0)) { + newdp->dccps_hc_rx_ccid = + ccid_hc_rx_new(newdmsk->dccpms_rx_ccid, + newsk, GFP_ATOMIC); + newdp->dccps_hc_tx_ccid = + ccid_hc_tx_new(newdmsk->dccpms_tx_ccid, + newsk, GFP_ATOMIC); + if (unlikely(newdp->dccps_hc_rx_ccid == NULL || + newdp->dccps_hc_tx_ccid == NULL)) { dccp_ackvec_free(newdp->dccps_hc_rx_ackvec); - ccid_hc_rx_exit(newdp->dccps_hc_rx_ccid, newsk); - ccid_hc_tx_exit(newdp->dccps_hc_tx_ccid, newsk); + ccid_hc_rx_delete(newdp->dccps_hc_rx_ccid, newsk); + ccid_hc_tx_delete(newdp->dccps_hc_tx_ccid, newsk); out_free: /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ @@ -143,9 +145,6 @@ out_free: return NULL; } - __ccid_get(newdp->dccps_hc_rx_ccid); - __ccid_get(newdp->dccps_hc_tx_ccid); - /* * Step 3: Process LISTEN state * @@ -155,7 +154,7 @@ out_free: */ /* See dccp_v4_conn_request */ - newdp->dccps_options.dccpo_sequence_window = req->rcv_wnd; + newdmsk->dccpms_sequence_window = req->rcv_wnd; newdp->dccps_gar = newdp->dccps_isr = dreq->dreq_isr; dccp_update_gsr(newsk, dreq->dreq_isr); diff --git a/net/dccp/options.c b/net/dccp/options.c index 0a76426..e9feb2a 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -21,19 +21,23 @@ #include "ackvec.h" #include "ccid.h" #include "dccp.h" +#include "feat.h" -/* stores the default values for new connection. may be changed with sysctl */ -static const struct dccp_options dccpo_default_values = { - .dccpo_sequence_window = DCCPF_INITIAL_SEQUENCE_WINDOW, - .dccpo_rx_ccid = DCCPF_INITIAL_CCID, - .dccpo_tx_ccid = DCCPF_INITIAL_CCID, - .dccpo_send_ack_vector = DCCPF_INITIAL_SEND_ACK_VECTOR, - .dccpo_send_ndp_count = DCCPF_INITIAL_SEND_NDP_COUNT, -}; +int dccp_feat_default_sequence_window = DCCPF_INITIAL_SEQUENCE_WINDOW; +int dccp_feat_default_rx_ccid = DCCPF_INITIAL_CCID; +int dccp_feat_default_tx_ccid = DCCPF_INITIAL_CCID; +int dccp_feat_default_ack_ratio = DCCPF_INITIAL_ACK_RATIO; +int dccp_feat_default_send_ack_vector = DCCPF_INITIAL_SEND_ACK_VECTOR; +int dccp_feat_default_send_ndp_count = DCCPF_INITIAL_SEND_NDP_COUNT; -void dccp_options_init(struct dccp_options *dccpo) +void dccp_minisock_init(struct dccp_minisock *dmsk) { - memcpy(dccpo, &dccpo_default_values, sizeof(*dccpo)); + dmsk->dccpms_sequence_window = dccp_feat_default_sequence_window; + dmsk->dccpms_rx_ccid = dccp_feat_default_rx_ccid; + dmsk->dccpms_tx_ccid = dccp_feat_default_tx_ccid; + dmsk->dccpms_ack_ratio = dccp_feat_default_ack_ratio; + dmsk->dccpms_send_ack_vector = dccp_feat_default_send_ack_vector; + dmsk->dccpms_send_ndp_count = dccp_feat_default_send_ndp_count; } static u32 dccp_decode_value_var(const unsigned char *bf, const u8 len) @@ -69,9 +73,12 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) unsigned char opt, len; unsigned char *value; u32 elapsed_time; + int rc; + int mandatory = 0; memset(opt_recv, 0, sizeof(*opt_recv)); + opt = len = 0; while (opt_ptr != opt_end) { opt = *opt_ptr++; len = 0; @@ -100,6 +107,12 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) switch (opt) { case DCCPO_PADDING: break; + case DCCPO_MANDATORY: + if (mandatory) + goto out_invalid_option; + if (pkt_type != DCCP_PKT_DATA) + mandatory = 1; + break; case DCCPO_NDP_COUNT: if (len > 3) goto out_invalid_option; @@ -108,12 +121,37 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) dccp_pr_debug("%sNDP count=%d\n", debug_prefix, opt_recv->dccpor_ndp); break; + case DCCPO_CHANGE_L: + /* fall through */ + case DCCPO_CHANGE_R: + if (len < 2) + goto out_invalid_option; + rc = dccp_feat_change_recv(sk, opt, *value, value + 1, + len - 1); + /* + * When there is a change error, change_recv is + * responsible for dealing with it. i.e. reply with an + * empty confirm. + * If the change was mandatory, then we need to die. + */ + if (rc && mandatory) + goto out_invalid_option; + break; + case DCCPO_CONFIRM_L: + /* fall through */ + case DCCPO_CONFIRM_R: + if (len < 2) + goto out_invalid_option; + if (dccp_feat_confirm_recv(sk, opt, *value, + value + 1, len - 1)) + goto out_invalid_option; + break; case DCCPO_ACK_VECTOR_0: case DCCPO_ACK_VECTOR_1: if (pkt_type == DCCP_PKT_DATA) - continue; + break; - if (dp->dccps_options.dccpo_send_ack_vector && + if (dccp_msk(sk)->dccpms_send_ack_vector && dccp_ackvec_parse(sk, skb, opt, value, len)) goto out_invalid_option; break; @@ -121,7 +159,7 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) if (len != 4) goto out_invalid_option; - opt_recv->dccpor_timestamp = ntohl(*(u32 *)value); + opt_recv->dccpor_timestamp = ntohl(*(__be32 *)value); dp->dccps_timestamp_echo = opt_recv->dccpor_timestamp; dccp_timestamp(sk, &dp->dccps_timestamp_time); @@ -135,7 +173,7 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) if (len != 4 && len != 6 && len != 8) goto out_invalid_option; - opt_recv->dccpor_timestamp_echo = ntohl(*(u32 *)value); + opt_recv->dccpor_timestamp_echo = ntohl(*(__be32 *)value); dccp_pr_debug("%sTIMESTAMP_ECHO=%u, len=%d, ackno=%llu, ", debug_prefix, @@ -149,9 +187,9 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) break; if (len == 6) - elapsed_time = ntohs(*(u16 *)(value + 4)); + elapsed_time = ntohs(*(__be16 *)(value + 4)); else - elapsed_time = ntohl(*(u32 *)(value + 4)); + elapsed_time = ntohl(*(__be32 *)(value + 4)); /* Give precedence to the biggest ELAPSED_TIME */ if (elapsed_time > opt_recv->dccpor_elapsed_time) @@ -165,9 +203,9 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) continue; if (len == 2) - elapsed_time = ntohs(*(u16 *)value); + elapsed_time = ntohs(*(__be16 *)value); else - elapsed_time = ntohl(*(u32 *)value); + elapsed_time = ntohl(*(__be32 *)value); if (elapsed_time > opt_recv->dccpor_elapsed_time) opt_recv->dccpor_elapsed_time = elapsed_time; @@ -208,8 +246,15 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) sk, opt, len); break; } + + if (opt != DCCPO_MANDATORY) + mandatory = 0; } + /* mandatory was the last byte in option list -> reset connection */ + if (mandatory) + goto out_invalid_option; + return 0; out_invalid_option: @@ -219,6 +264,8 @@ out_invalid_option: return -1; } +EXPORT_SYMBOL_GPL(dccp_parse_options); + static void dccp_encode_value_var(const u32 value, unsigned char *to, const unsigned int len) { @@ -237,17 +284,14 @@ static inline int dccp_ndp_len(const int ndp) return likely(ndp <= 0xFF) ? 1 : ndp <= 0xFFFF ? 2 : 3; } -void dccp_insert_option(struct sock *sk, struct sk_buff *skb, +int dccp_insert_option(struct sock *sk, struct sk_buff *skb, const unsigned char option, const void *value, const unsigned char len) { unsigned char *to; - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 2 > DCCP_MAX_OPT_LEN) { - LIMIT_NETDEBUG(KERN_INFO "DCCP: packet too small to insert " - "%d option!\n", option); - return; - } + if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 2 > DCCP_MAX_OPT_LEN) + return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len + 2; @@ -256,11 +300,12 @@ void dccp_insert_option(struct sock *sk, struct sk_buff *skb, *to++ = len + 2; memcpy(to, value, len); + return 0; } EXPORT_SYMBOL_GPL(dccp_insert_option); -static void dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb) +static int dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); int ndp = dp->dccps_ndp_count; @@ -276,7 +321,7 @@ static void dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb) const int len = ndp_len + 2; if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) - return; + return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; @@ -285,6 +330,8 @@ static void dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb) *ptr++ = len; dccp_encode_value_var(ndp, ptr, ndp_len); } + + return 0; } static inline int dccp_elapsed_time_len(const u32 elapsed_time) @@ -292,27 +339,18 @@ static inline int dccp_elapsed_time_len(const u32 elapsed_time) return elapsed_time == 0 ? 0 : elapsed_time <= 0xFFFF ? 2 : 4; } -void dccp_insert_option_elapsed_time(struct sock *sk, - struct sk_buff *skb, - u32 elapsed_time) +int dccp_insert_option_elapsed_time(struct sock *sk, struct sk_buff *skb, + u32 elapsed_time) { -#ifdef CONFIG_IP_DCCP_DEBUG - struct dccp_sock *dp = dccp_sk(sk); - const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ? - "CLIENT TX opt: " : "server TX opt: "; -#endif const int elapsed_time_len = dccp_elapsed_time_len(elapsed_time); const int len = 2 + elapsed_time_len; unsigned char *to; if (elapsed_time_len == 0) - return; + return 0; - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) { - LIMIT_NETDEBUG(KERN_INFO "DCCP: packet too small to " - "insert elapsed time!\n"); - return; - } + if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) + return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; @@ -321,17 +359,14 @@ void dccp_insert_option_elapsed_time(struct sock *sk, *to++ = len; if (elapsed_time_len == 2) { - const u16 var16 = htons((u16)elapsed_time); + const __be16 var16 = htons((u16)elapsed_time); memcpy(to, &var16, 2); } else { - const u32 var32 = htonl(elapsed_time); + const __be32 var32 = htonl(elapsed_time); memcpy(to, &var32, 4); } - dccp_pr_debug("%sELAPSED_TIME=%u, len=%d, seqno=%llu\n", - debug_prefix, elapsed_time, - len, - (unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq); + return 0; } EXPORT_SYMBOL_GPL(dccp_insert_option_elapsed_time); @@ -352,32 +387,27 @@ void dccp_timestamp(const struct sock *sk, struct timeval *tv) EXPORT_SYMBOL_GPL(dccp_timestamp); -void dccp_insert_option_timestamp(struct sock *sk, struct sk_buff *skb) +int dccp_insert_option_timestamp(struct sock *sk, struct sk_buff *skb) { struct timeval tv; - u32 now; - + __be32 now; + dccp_timestamp(sk, &tv); - now = timeval_usecs(&tv) / 10; + now = htonl(timeval_usecs(&tv) / 10); /* yes this will overflow but that is the point as we want a * 10 usec 32 bit timer which mean it wraps every 11.9 hours */ - now = htonl(now); - dccp_insert_option(sk, skb, DCCPO_TIMESTAMP, &now, sizeof(now)); + return dccp_insert_option(sk, skb, DCCPO_TIMESTAMP, &now, sizeof(now)); } EXPORT_SYMBOL_GPL(dccp_insert_option_timestamp); -static void dccp_insert_option_timestamp_echo(struct sock *sk, - struct sk_buff *skb) +static int dccp_insert_option_timestamp_echo(struct sock *sk, + struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); -#ifdef CONFIG_IP_DCCP_DEBUG - const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ? - "CLIENT TX opt: " : "server TX opt: "; -#endif struct timeval now; - u32 tstamp_echo; + __be32 tstamp_echo; u32 elapsed_time; int len, elapsed_time_len; unsigned char *to; @@ -387,11 +417,8 @@ static void dccp_insert_option_timestamp_echo(struct sock *sk, elapsed_time_len = dccp_elapsed_time_len(elapsed_time); len = 6 + elapsed_time_len; - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) { - LIMIT_NETDEBUG(KERN_INFO "DCCP: packet too small to insert " - "timestamp echo!\n"); - return; - } + if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) + return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; @@ -402,51 +429,149 @@ static void dccp_insert_option_timestamp_echo(struct sock *sk, tstamp_echo = htonl(dp->dccps_timestamp_echo); memcpy(to, &tstamp_echo, 4); to += 4; - + if (elapsed_time_len == 2) { - const u16 var16 = htons((u16)elapsed_time); + const __be16 var16 = htons((u16)elapsed_time); memcpy(to, &var16, 2); } else if (elapsed_time_len == 4) { - const u32 var32 = htonl(elapsed_time); + const __be32 var32 = htonl(elapsed_time); memcpy(to, &var32, 4); } - dccp_pr_debug("%sTIMESTAMP_ECHO=%u, len=%d, seqno=%llu\n", - debug_prefix, dp->dccps_timestamp_echo, - len, - (unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq); - dp->dccps_timestamp_echo = 0; dp->dccps_timestamp_time.tv_sec = 0; dp->dccps_timestamp_time.tv_usec = 0; + return 0; } -void dccp_insert_options(struct sock *sk, struct sk_buff *skb) +static int dccp_insert_feat_opt(struct sk_buff *skb, u8 type, u8 feat, + u8 *val, u8 len) +{ + u8 *to; + + if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 3 > DCCP_MAX_OPT_LEN) { + LIMIT_NETDEBUG(KERN_INFO "DCCP: packet too small" + " to insert feature %d option!\n", feat); + return -1; + } + + DCCP_SKB_CB(skb)->dccpd_opt_len += len + 3; + + to = skb_push(skb, len + 3); + *to++ = type; + *to++ = len + 3; + *to++ = feat; + + if (len) + memcpy(to, val, len); + dccp_pr_debug("option %d feat %d len %d\n", type, feat, len); + + return 0; +} + +static int dccp_insert_options_feat(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); + struct dccp_minisock *dmsk = dccp_msk(sk); + struct dccp_opt_pend *opt, *next; + int change = 0; + + /* confirm any options [NN opts] */ + list_for_each_entry_safe(opt, next, &dmsk->dccpms_conf, dccpop_node) { + dccp_insert_feat_opt(skb, opt->dccpop_type, + opt->dccpop_feat, opt->dccpop_val, + opt->dccpop_len); + /* fear empty confirms */ + if (opt->dccpop_val) + kfree(opt->dccpop_val); + kfree(opt); + } + INIT_LIST_HEAD(&dmsk->dccpms_conf); + + /* see which features we need to send */ + list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { + /* see if we need to send any confirm */ + if (opt->dccpop_sc) { + dccp_insert_feat_opt(skb, opt->dccpop_type + 1, + opt->dccpop_feat, + opt->dccpop_sc->dccpoc_val, + opt->dccpop_sc->dccpoc_len); + + BUG_ON(!opt->dccpop_sc->dccpoc_val); + kfree(opt->dccpop_sc->dccpoc_val); + kfree(opt->dccpop_sc); + opt->dccpop_sc = NULL; + } + + /* any option not confirmed, re-send it */ + if (!opt->dccpop_conf) { + dccp_insert_feat_opt(skb, opt->dccpop_type, + opt->dccpop_feat, opt->dccpop_val, + opt->dccpop_len); + change++; + } + } + + /* Retransmit timer. + * If this is the master listening sock, we don't set a timer on it. It + * should be fine because if the dude doesn't receive our RESPONSE + * [which will contain the CHANGE] he will send another REQUEST which + * will "retrnasmit" the change. + */ + if (change && dp->dccps_role != DCCP_ROLE_LISTEN) { + dccp_pr_debug("reset feat negotiation timer %p\n", sk); + + /* XXX don't reset the timer on re-transmissions. I.e. reset it + * only when sending new stuff i guess. Currently the timer + * never backs off because on re-transmission it just resets it! + */ + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + inet_csk(sk)->icsk_rto, DCCP_RTO_MAX); + } + + return 0; +} + +int dccp_insert_options(struct sock *sk, struct sk_buff *skb) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_minisock *dmsk = dccp_msk(sk); DCCP_SKB_CB(skb)->dccpd_opt_len = 0; - if (dp->dccps_options.dccpo_send_ndp_count) - dccp_insert_option_ndp(sk, skb); + if (dmsk->dccpms_send_ndp_count && + dccp_insert_option_ndp(sk, skb)) + return -1; if (!dccp_packet_without_ack(skb)) { - if (dp->dccps_options.dccpo_send_ack_vector && - dccp_ackvec_pending(dp->dccps_hc_rx_ackvec)) - dccp_insert_option_ackvec(sk, skb); - if (dp->dccps_timestamp_echo != 0) - dccp_insert_option_timestamp_echo(sk, skb); + if (dmsk->dccpms_send_ack_vector && + dccp_ackvec_pending(dp->dccps_hc_rx_ackvec) && + dccp_insert_option_ackvec(sk, skb)) + return -1; + + if (dp->dccps_timestamp_echo != 0 && + dccp_insert_option_timestamp_echo(sk, skb)) + return -1; } if (dp->dccps_hc_rx_insert_options) { - ccid_hc_rx_insert_options(dp->dccps_hc_rx_ccid, sk, skb); + if (ccid_hc_rx_insert_options(dp->dccps_hc_rx_ccid, sk, skb)) + return -1; dp->dccps_hc_rx_insert_options = 0; } if (dp->dccps_hc_tx_insert_options) { - ccid_hc_tx_insert_options(dp->dccps_hc_tx_ccid, sk, skb); + if (ccid_hc_tx_insert_options(dp->dccps_hc_tx_ccid, sk, skb)) + return -1; dp->dccps_hc_tx_insert_options = 0; } + /* Feature negotiation */ + /* Data packets can't do feat negotiation */ + if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA && + DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATAACK && + dccp_insert_options_feat(sk, skb)) + return -1; + /* XXX: insert other options when appropriate */ if (DCCP_SKB_CB(skb)->dccpd_opt_len != 0) { @@ -459,4 +584,6 @@ void dccp_insert_options(struct sock *sk, struct sk_buff *skb) DCCP_SKB_CB(skb)->dccpd_opt_len += padding; } } + + return 0; } diff --git a/net/dccp/output.c b/net/dccp/output.c index efd7ffb..7409e4a 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -27,7 +27,7 @@ static inline void dccp_event_ack_sent(struct sock *sk) inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } -static inline void dccp_skb_entail(struct sock *sk, struct sk_buff *skb) +static void dccp_skb_entail(struct sock *sk, struct sk_buff *skb) { skb_set_owner_w(skb, sk); WARN_ON(sk->sk_send_head); @@ -49,7 +49,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); struct dccp_hdr *dh; /* XXX For now we're using only 48 bits sequence numbers */ - const int dccp_header_size = sizeof(*dh) + + const u32 dccp_header_size = sizeof(*dh) + sizeof(struct dccp_hdr_ext) + dccp_packet_hdr_len(dcb->dccpd_type); int err, set_ack = 1; @@ -64,6 +64,10 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) case DCCP_PKT_DATAACK: break; + case DCCP_PKT_REQUEST: + set_ack = 0; + /* fall through */ + case DCCP_PKT_SYNC: case DCCP_PKT_SYNCACK: ackno = dcb->dccpd_seq; @@ -79,7 +83,11 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) } dcb->dccpd_seq = dp->dccps_gss; - dccp_insert_options(sk, skb); + + if (dccp_insert_options(sk, skb)) { + kfree_skb(skb); + return -EPROTO; + } skb->h.raw = skb_push(skb, dccp_header_size); dh = dccp_hdr(skb); @@ -275,17 +283,16 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, { struct dccp_hdr *dh; struct dccp_request_sock *dreq; - const int dccp_header_size = sizeof(struct dccp_hdr) + + const u32 dccp_header_size = sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext) + sizeof(struct dccp_hdr_response); - struct sk_buff *skb = sock_wmalloc(sk, MAX_HEADER + DCCP_MAX_OPT_LEN + - dccp_header_size, 1, + struct sk_buff *skb = sock_wmalloc(sk, sk->sk_prot->max_header, 1, GFP_ATOMIC); if (skb == NULL) return NULL; /* Reserve space for headers. */ - skb_reserve(skb, MAX_HEADER + DCCP_MAX_OPT_LEN + dccp_header_size); + skb_reserve(skb, sk->sk_prot->max_header); skb->dst = dst_clone(dst); skb->csum = 0; @@ -293,7 +300,11 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, dreq = dccp_rsk(req); DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_RESPONSE; DCCP_SKB_CB(skb)->dccpd_seq = dreq->dreq_iss; - dccp_insert_options(sk, skb); + + if (dccp_insert_options(sk, skb)) { + kfree_skb(skb); + return NULL; + } skb->h.raw = skb_push(skb, dccp_header_size); @@ -310,32 +321,28 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), dreq->dreq_isr); dccp_hdr_response(skb)->dccph_resp_service = dreq->dreq_service; - dh->dccph_checksum = dccp_v4_checksum(skb, inet_rsk(req)->loc_addr, - inet_rsk(req)->rmt_addr); - DCCP_INC_STATS(DCCP_MIB_OUTSEGS); return skb; } EXPORT_SYMBOL_GPL(dccp_make_response); -struct sk_buff *dccp_make_reset(struct sock *sk, struct dst_entry *dst, - const enum dccp_reset_codes code) +static struct sk_buff *dccp_make_reset(struct sock *sk, struct dst_entry *dst, + const enum dccp_reset_codes code) { struct dccp_hdr *dh; struct dccp_sock *dp = dccp_sk(sk); - const int dccp_header_size = sizeof(struct dccp_hdr) + + const u32 dccp_header_size = sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext) + sizeof(struct dccp_hdr_reset); - struct sk_buff *skb = sock_wmalloc(sk, MAX_HEADER + DCCP_MAX_OPT_LEN + - dccp_header_size, 1, + struct sk_buff *skb = sock_wmalloc(sk, sk->sk_prot->max_header, 1, GFP_ATOMIC); if (skb == NULL) return NULL; /* Reserve space for headers. */ - skb_reserve(skb, MAX_HEADER + DCCP_MAX_OPT_LEN + dccp_header_size); + skb_reserve(skb, sk->sk_prot->max_header); skb->dst = dst_clone(dst); skb->csum = 0; @@ -345,7 +352,11 @@ struct sk_buff *dccp_make_reset(struct sock *sk, struct dst_entry *dst, DCCP_SKB_CB(skb)->dccpd_reset_code = code; DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_RESET; DCCP_SKB_CB(skb)->dccpd_seq = dp->dccps_gss; - dccp_insert_options(sk, skb); + + if (dccp_insert_options(sk, skb)) { + kfree_skb(skb); + return NULL; + } skb->h.raw = skb_push(skb, dccp_header_size); @@ -362,14 +373,34 @@ struct sk_buff *dccp_make_reset(struct sock *sk, struct dst_entry *dst, dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), dp->dccps_gsr); dccp_hdr_reset(skb)->dccph_reset_code = code; - - dh->dccph_checksum = dccp_v4_checksum(skb, inet_sk(sk)->saddr, - inet_sk(sk)->daddr); + inet_csk(sk)->icsk_af_ops->send_check(sk, skb->len, skb); DCCP_INC_STATS(DCCP_MIB_OUTSEGS); return skb; } +int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code) +{ + /* + * FIXME: what if rebuild_header fails? + * Should we be doing a rebuild_header here? + */ + int err = inet_sk_rebuild_header(sk); + + if (err == 0) { + struct sk_buff *skb = dccp_make_reset(sk, sk->sk_dst_cache, + code); + if (skb != NULL) { + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + err = inet_csk(sk)->icsk_af_ops->queue_xmit(skb, 0); + if (err == NET_XMIT_CN) + err = 0; + } + } + + return err; +} + /* * Do all connect socket setups that can be done AF independent. */ @@ -405,12 +436,12 @@ int dccp_connect(struct sock *sk) dccp_connect_init(sk); - skb = alloc_skb(MAX_DCCP_HEADER + 15, sk->sk_allocation); + skb = alloc_skb(sk->sk_prot->max_header, sk->sk_allocation); if (unlikely(skb == NULL)) return -ENOBUFS; /* Reserve space for headers. */ - skb_reserve(skb, MAX_DCCP_HEADER); + skb_reserve(skb, sk->sk_prot->max_header); DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_REQUEST; skb->csum = 0; @@ -431,7 +462,8 @@ void dccp_send_ack(struct sock *sk) { /* If we have been reset, we may not send again. */ if (sk->sk_state != DCCP_CLOSED) { - struct sk_buff *skb = alloc_skb(MAX_DCCP_HEADER, GFP_ATOMIC); + struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header, + GFP_ATOMIC); if (skb == NULL) { inet_csk_schedule_ack(sk); @@ -443,7 +475,7 @@ void dccp_send_ack(struct sock *sk) } /* Reserve space for headers */ - skb_reserve(skb, MAX_DCCP_HEADER); + skb_reserve(skb, sk->sk_prot->max_header); skb->csum = 0; DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_ACK; dccp_transmit_skb(sk, skb); @@ -490,14 +522,14 @@ void dccp_send_sync(struct sock *sk, const u64 seq, * dccp_transmit_skb() will set the ownership to this * sock. */ - struct sk_buff *skb = alloc_skb(MAX_DCCP_HEADER, GFP_ATOMIC); + struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header, GFP_ATOMIC); if (skb == NULL) /* FIXME: how to make sure the sync is sent? */ return; /* Reserve space for headers and prepare control bits. */ - skb_reserve(skb, MAX_DCCP_HEADER); + skb_reserve(skb, sk->sk_prot->max_header); skb->csum = 0; DCCP_SKB_CB(skb)->dccpd_type = pkt_type; DCCP_SKB_CB(skb)->dccpd_seq = seq; @@ -505,6 +537,8 @@ void dccp_send_sync(struct sock *sk, const u64 seq, dccp_transmit_skb(sk, skb); } +EXPORT_SYMBOL_GPL(dccp_send_sync); + /* * Send a DCCP_PKT_CLOSE/CLOSEREQ. The caller locks the socket for us. This * cannot be allowed to fail queueing a DCCP_PKT_CLOSE/CLOSEREQ frame under diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 65b11ea..d4b293e 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -23,9 +23,7 @@ #include <linux/random.h> #include <net/checksum.h> -#include <net/inet_common.h> #include <net/inet_sock.h> -#include <net/protocol.h> #include <net/sock.h> #include <net/xfrm.h> @@ -37,6 +35,7 @@ #include "ccid.h" #include "dccp.h" +#include "feat.h" DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly; @@ -46,12 +45,66 @@ atomic_t dccp_orphan_count = ATOMIC_INIT(0); EXPORT_SYMBOL_GPL(dccp_orphan_count); -static struct net_protocol dccp_protocol = { - .handler = dccp_v4_rcv, - .err_handler = dccp_v4_err, - .no_policy = 1, +struct inet_hashinfo __cacheline_aligned dccp_hashinfo = { + .lhash_lock = RW_LOCK_UNLOCKED, + .lhash_users = ATOMIC_INIT(0), + .lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(dccp_hashinfo.lhash_wait), }; +EXPORT_SYMBOL_GPL(dccp_hashinfo); + +void dccp_set_state(struct sock *sk, const int state) +{ + const int oldstate = sk->sk_state; + + dccp_pr_debug("%s(%p) %-10.10s -> %s\n", + dccp_role(sk), sk, + dccp_state_name(oldstate), dccp_state_name(state)); + WARN_ON(state == oldstate); + + switch (state) { + case DCCP_OPEN: + if (oldstate != DCCP_OPEN) + DCCP_INC_STATS(DCCP_MIB_CURRESTAB); + break; + + case DCCP_CLOSED: + if (oldstate == DCCP_CLOSING || oldstate == DCCP_OPEN) + DCCP_INC_STATS(DCCP_MIB_ESTABRESETS); + + sk->sk_prot->unhash(sk); + if (inet_csk(sk)->icsk_bind_hash != NULL && + !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) + inet_put_port(&dccp_hashinfo, sk); + /* fall through */ + default: + if (oldstate == DCCP_OPEN) + DCCP_DEC_STATS(DCCP_MIB_CURRESTAB); + } + + /* Change state AFTER socket is unhashed to avoid closed + * socket sitting in hash tables. + */ + sk->sk_state = state; +} + +EXPORT_SYMBOL_GPL(dccp_set_state); + +void dccp_done(struct sock *sk) +{ + dccp_set_state(sk, DCCP_CLOSED); + dccp_clear_xmit_timers(sk); + + sk->sk_shutdown = SHUTDOWN_MASK; + + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_state_change(sk); + else + inet_csk_destroy_sock(sk); +} + +EXPORT_SYMBOL_GPL(dccp_done); + const char *dccp_packet_name(const int type) { static const char *dccp_packet_names[] = { @@ -96,6 +149,120 @@ const char *dccp_state_name(const int state) EXPORT_SYMBOL_GPL(dccp_state_name); +void dccp_hash(struct sock *sk) +{ + inet_hash(&dccp_hashinfo, sk); +} + +EXPORT_SYMBOL_GPL(dccp_hash); + +void dccp_unhash(struct sock *sk) +{ + inet_unhash(&dccp_hashinfo, sk); +} + +EXPORT_SYMBOL_GPL(dccp_unhash); + +int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_minisock *dmsk = dccp_msk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + + dccp_minisock_init(&dp->dccps_minisock); + do_gettimeofday(&dp->dccps_epoch); + + /* + * FIXME: We're hardcoding the CCID, and doing this at this point makes + * the listening (master) sock get CCID control blocks, which is not + * necessary, but for now, to not mess with the test userspace apps, + * lets leave it here, later the real solution is to do this in a + * setsockopt(CCIDs-I-want/accept). -acme + */ + if (likely(ctl_sock_initialized)) { + int rc = dccp_feat_init(dmsk); + + if (rc) + return rc; + + if (dmsk->dccpms_send_ack_vector) { + dp->dccps_hc_rx_ackvec = dccp_ackvec_alloc(GFP_KERNEL); + if (dp->dccps_hc_rx_ackvec == NULL) + return -ENOMEM; + } + dp->dccps_hc_rx_ccid = ccid_hc_rx_new(dmsk->dccpms_rx_ccid, + sk, GFP_KERNEL); + dp->dccps_hc_tx_ccid = ccid_hc_tx_new(dmsk->dccpms_tx_ccid, + sk, GFP_KERNEL); + if (unlikely(dp->dccps_hc_rx_ccid == NULL || + dp->dccps_hc_tx_ccid == NULL)) { + ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); + ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); + if (dmsk->dccpms_send_ack_vector) { + dccp_ackvec_free(dp->dccps_hc_rx_ackvec); + dp->dccps_hc_rx_ackvec = NULL; + } + dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL; + return -ENOMEM; + } + } else { + /* control socket doesn't need feat nego */ + INIT_LIST_HEAD(&dmsk->dccpms_pending); + INIT_LIST_HEAD(&dmsk->dccpms_conf); + } + + dccp_init_xmit_timers(sk); + icsk->icsk_rto = DCCP_TIMEOUT_INIT; + sk->sk_state = DCCP_CLOSED; + sk->sk_write_space = dccp_write_space; + icsk->icsk_sync_mss = dccp_sync_mss; + dp->dccps_mss_cache = 536; + dp->dccps_role = DCCP_ROLE_UNDEFINED; + dp->dccps_service = DCCP_SERVICE_INVALID_VALUE; + dp->dccps_l_ack_ratio = dp->dccps_r_ack_ratio = 1; + + return 0; +} + +EXPORT_SYMBOL_GPL(dccp_init_sock); + +int dccp_destroy_sock(struct sock *sk) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_minisock *dmsk = dccp_msk(sk); + + /* + * DCCP doesn't use sk_write_queue, just sk_send_head + * for retransmissions + */ + if (sk->sk_send_head != NULL) { + kfree_skb(sk->sk_send_head); + sk->sk_send_head = NULL; + } + + /* Clean up a referenced DCCP bind bucket. */ + if (inet_csk(sk)->icsk_bind_hash != NULL) + inet_put_port(&dccp_hashinfo, sk); + + kfree(dp->dccps_service_list); + dp->dccps_service_list = NULL; + + if (dmsk->dccpms_send_ack_vector) { + dccp_ackvec_free(dp->dccps_hc_rx_ackvec); + dp->dccps_hc_rx_ackvec = NULL; + } + ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); + ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); + dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL; + + /* clean up feature negotiation state */ + dccp_feat_clean(dmsk); + + return 0; +} + +EXPORT_SYMBOL_GPL(dccp_destroy_sock); + static inline int dccp_listen_start(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); @@ -220,7 +387,7 @@ int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg) EXPORT_SYMBOL_GPL(dccp_ioctl); -static int dccp_setsockopt_service(struct sock *sk, const u32 service, +static int dccp_setsockopt_service(struct sock *sk, const __be32 service, char __user *optval, int optlen) { struct dccp_sock *dp = dccp_sk(sk); @@ -255,18 +422,46 @@ static int dccp_setsockopt_service(struct sock *sk, const u32 service, return 0; } -int dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) +/* byte 1 is feature. the rest is the preference list */ +static int dccp_setsockopt_change(struct sock *sk, int type, + struct dccp_so_feat __user *optval) +{ + struct dccp_so_feat opt; + u8 *val; + int rc; + + if (copy_from_user(&opt, optval, sizeof(opt))) + return -EFAULT; + + val = kmalloc(opt.dccpsf_len, GFP_KERNEL); + if (!val) + return -ENOMEM; + + if (copy_from_user(val, opt.dccpsf_val, opt.dccpsf_len)) { + rc = -EFAULT; + goto out_free_val; + } + + rc = dccp_feat_change(dccp_msk(sk), type, opt.dccpsf_feat, + val, opt.dccpsf_len, GFP_KERNEL); + if (rc) + goto out_free_val; + +out: + return rc; + +out_free_val: + kfree(val); + goto out; +} + +static int do_dccp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) { struct dccp_sock *dp; int err; int val; - if (level != SOL_DCCP) - return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level, - optname, optval, - optlen); - if (optlen < sizeof(int)) return -EINVAL; @@ -284,6 +479,25 @@ int dccp_setsockopt(struct sock *sk, int level, int optname, case DCCP_SOCKOPT_PACKET_SIZE: dp->dccps_packet_size = val; break; + + case DCCP_SOCKOPT_CHANGE_L: + if (optlen != sizeof(struct dccp_so_feat)) + err = -EINVAL; + else + err = dccp_setsockopt_change(sk, DCCPO_CHANGE_L, + (struct dccp_so_feat *) + optval); + break; + + case DCCP_SOCKOPT_CHANGE_R: + if (optlen != sizeof(struct dccp_so_feat)) + err = -EINVAL; + else + err = dccp_setsockopt_change(sk, DCCPO_CHANGE_R, + (struct dccp_so_feat *) + optval); + break; + default: err = -ENOPROTOOPT; break; @@ -293,10 +507,33 @@ int dccp_setsockopt(struct sock *sk, int level, int optname, return err; } +int dccp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + if (level != SOL_DCCP) + return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level, + optname, optval, + optlen); + return do_dccp_setsockopt(sk, level, optname, optval, optlen); +} + EXPORT_SYMBOL_GPL(dccp_setsockopt); +#ifdef CONFIG_COMPAT +int compat_dccp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, 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, - u32 __user *optval, + __be32 __user *optval, int __user *optlen) { const struct dccp_sock *dp = dccp_sk(sk); @@ -326,16 +563,12 @@ out: return err; } -int dccp_getsockopt(struct sock *sk, int level, int optname, +static int do_dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct dccp_sock *dp; int val, len; - if (level != SOL_DCCP) - return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level, - optname, optval, - optlen); if (get_user(len, optlen)) return -EFAULT; @@ -351,7 +584,7 @@ int dccp_getsockopt(struct sock *sk, int level, int optname, break; case DCCP_SOCKOPT_SERVICE: return dccp_getsockopt_service(sk, len, - (u32 __user *)optval, optlen); + (__be32 __user *)optval, optlen); case 128 ... 191: return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname, len, (u32 __user *)optval, optlen); @@ -368,8 +601,31 @@ int dccp_getsockopt(struct sock *sk, int level, int optname, return 0; } +int dccp_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level != SOL_DCCP) + return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level, + optname, optval, + optlen); + return do_dccp_getsockopt(sk, level, optname, optval, optlen); +} + 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 + int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) { @@ -679,84 +935,7 @@ void dccp_shutdown(struct sock *sk, int how) EXPORT_SYMBOL_GPL(dccp_shutdown); -static const struct proto_ops inet_dccp_ops = { - .family = PF_INET, - .owner = THIS_MODULE, - .release = inet_release, - .bind = inet_bind, - .connect = inet_stream_connect, - .socketpair = sock_no_socketpair, - .accept = inet_accept, - .getname = inet_getname, - /* FIXME: work on tcp_poll to rename it to inet_csk_poll */ - .poll = dccp_poll, - .ioctl = inet_ioctl, - /* FIXME: work on inet_listen to rename it to sock_common_listen */ - .listen = inet_dccp_listen, - .shutdown = inet_shutdown, - .setsockopt = sock_common_setsockopt, - .getsockopt = sock_common_getsockopt, - .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, - .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, -}; - -extern struct net_proto_family inet_family_ops; - -static struct inet_protosw dccp_v4_protosw = { - .type = SOCK_DCCP, - .protocol = IPPROTO_DCCP, - .prot = &dccp_prot, - .ops = &inet_dccp_ops, - .capability = -1, - .no_check = 0, - .flags = INET_PROTOSW_ICSK, -}; - -/* - * This is the global socket data structure used for responding to - * the Out-of-the-blue (OOTB) packets. A control sock will be created - * for this socket at the initialization time. - */ -struct socket *dccp_ctl_socket; - -static char dccp_ctl_socket_err_msg[] __initdata = - KERN_ERR "DCCP: Failed to create the control socket.\n"; - -static int __init dccp_ctl_sock_init(void) -{ - int rc = sock_create_kern(PF_INET, SOCK_DCCP, IPPROTO_DCCP, - &dccp_ctl_socket); - if (rc < 0) - printk(dccp_ctl_socket_err_msg); - else { - dccp_ctl_socket->sk->sk_allocation = GFP_ATOMIC; - inet_sk(dccp_ctl_socket->sk)->uc_ttl = -1; - - /* Unhash it so that IP input processing does not even - * see it, we do not wish this socket to see incoming - * packets. - */ - dccp_ctl_socket->sk->sk_prot->unhash(dccp_ctl_socket->sk); - } - - return rc; -} - -#ifdef CONFIG_IP_DCCP_UNLOAD_HACK -void dccp_ctl_sock_exit(void) -{ - if (dccp_ctl_socket != NULL) { - sock_release(dccp_ctl_socket); - dccp_ctl_socket = NULL; - } -} - -EXPORT_SYMBOL_GPL(dccp_ctl_sock_exit); -#endif - -static int __init init_dccp_v4_mibs(void) +static int __init dccp_mib_init(void) { int rc = -ENOMEM; @@ -778,6 +957,13 @@ out_free_one: } +static void dccp_mib_exit(void) +{ + free_percpu(dccp_statistics[0]); + free_percpu(dccp_statistics[1]); + dccp_statistics[0] = dccp_statistics[1] = NULL; +} + static int thash_entries; module_param(thash_entries, int, 0444); MODULE_PARM_DESC(thash_entries, "Number of ehash buckets"); @@ -794,17 +980,14 @@ static int __init dccp_init(void) { unsigned long goal; int ehash_order, bhash_order, i; - int rc = proto_register(&dccp_prot, 1); - - if (rc) - goto out; + int rc = -ENOBUFS; dccp_hashinfo.bind_bucket_cachep = kmem_cache_create("dccp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN, NULL, NULL); if (!dccp_hashinfo.bind_bucket_cachep) - goto out_proto_unregister; + goto out; /* * Size and allocate the main established and bind bucket @@ -866,27 +1049,23 @@ static int __init dccp_init(void) INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain); } - if (init_dccp_v4_mibs()) + rc = dccp_mib_init(); + if (rc) goto out_free_dccp_bhash; - rc = -EAGAIN; - if (inet_add_protocol(&dccp_protocol, IPPROTO_DCCP)) - goto out_free_dccp_v4_mibs; - - inet_register_protosw(&dccp_v4_protosw); + rc = dccp_ackvec_init(); + if (rc) + goto out_free_dccp_mib; - rc = dccp_ctl_sock_init(); + rc = dccp_sysctl_init(); if (rc) - goto out_unregister_protosw; + goto out_ackvec_exit; out: return rc; -out_unregister_protosw: - inet_unregister_protosw(&dccp_v4_protosw); - inet_del_protocol(&dccp_protocol, IPPROTO_DCCP); -out_free_dccp_v4_mibs: - free_percpu(dccp_statistics[0]); - free_percpu(dccp_statistics[1]); - dccp_statistics[0] = dccp_statistics[1] = NULL; +out_ackvec_exit: + dccp_ackvec_exit(); +out_free_dccp_mib: + dccp_mib_exit(); out_free_dccp_bhash: free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); dccp_hashinfo.bhash = NULL; @@ -896,23 +1075,12 @@ out_free_dccp_ehash: out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_hashinfo.bind_bucket_cachep = NULL; -out_proto_unregister: - proto_unregister(&dccp_prot); goto out; } -static const char dccp_del_proto_err_msg[] __exitdata = - KERN_ERR "can't remove dccp net_protocol\n"; - static void __exit dccp_fini(void) { - inet_unregister_protosw(&dccp_v4_protosw); - - if (inet_del_protocol(&dccp_protocol, IPPROTO_DCCP) < 0) - printk(dccp_del_proto_err_msg); - - free_percpu(dccp_statistics[0]); - free_percpu(dccp_statistics[1]); + dccp_mib_exit(); free_pages((unsigned long)dccp_hashinfo.bhash, get_order(dccp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket))); @@ -920,19 +1088,13 @@ static void __exit dccp_fini(void) get_order(dccp_hashinfo.ehash_size * sizeof(struct inet_ehash_bucket))); kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); - proto_unregister(&dccp_prot); + dccp_ackvec_exit(); + dccp_sysctl_exit(); } module_init(dccp_init); module_exit(dccp_fini); -/* - * __stringify doesn't likes enums, so use SOCK_DCCP (6) and IPPROTO_DCCP (33) - * values directly, Also cover the case where the protocol is not specified, - * i.e. net-pf-PF_INET-proto-0-type-SOCK_DCCP - */ -MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-33-type-6"); -MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-0-type-6"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@conectiva.com.br>"); MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol"); diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c new file mode 100644 index 0000000..64c89e9 --- /dev/null +++ b/net/dccp/sysctl.c @@ -0,0 +1,124 @@ +/* + * net/dccp/sysctl.c + * + * An implementation of the DCCP protocol + * 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 v2 + * as published by the Free Software Foundation. + */ + +#include <linux/config.h> +#include <linux/mm.h> +#include <linux/sysctl.h> + +#ifndef CONFIG_SYSCTL +#error This file should not be compiled without CONFIG_SYSCTL defined +#endif + +extern int dccp_feat_default_sequence_window; +extern int dccp_feat_default_rx_ccid; +extern int dccp_feat_default_tx_ccid; +extern int dccp_feat_default_ack_ratio; +extern int dccp_feat_default_send_ack_vector; +extern int dccp_feat_default_send_ndp_count; + +static struct ctl_table dccp_default_table[] = { + { + .ctl_name = NET_DCCP_DEFAULT_SEQ_WINDOW, + .procname = "seq_window", + .data = &dccp_feat_default_sequence_window, + .maxlen = sizeof(dccp_feat_default_sequence_window), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .ctl_name = NET_DCCP_DEFAULT_RX_CCID, + .procname = "rx_ccid", + .data = &dccp_feat_default_rx_ccid, + .maxlen = sizeof(dccp_feat_default_rx_ccid), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .ctl_name = NET_DCCP_DEFAULT_TX_CCID, + .procname = "tx_ccid", + .data = &dccp_feat_default_tx_ccid, + .maxlen = sizeof(dccp_feat_default_tx_ccid), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .ctl_name = NET_DCCP_DEFAULT_ACK_RATIO, + .procname = "ack_ratio", + .data = &dccp_feat_default_ack_ratio, + .maxlen = sizeof(dccp_feat_default_ack_ratio), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .ctl_name = NET_DCCP_DEFAULT_SEND_ACKVEC, + .procname = "send_ackvec", + .data = &dccp_feat_default_send_ack_vector, + .maxlen = sizeof(dccp_feat_default_send_ack_vector), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .ctl_name = NET_DCCP_DEFAULT_SEND_NDP, + .procname = "send_ndp", + .data = &dccp_feat_default_send_ndp_count, + .maxlen = sizeof(dccp_feat_default_send_ndp_count), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .ctl_name = 0, } +}; + +static struct ctl_table dccp_table[] = { + { + .ctl_name = NET_DCCP_DEFAULT, + .procname = "default", + .mode = 0555, + .child = dccp_default_table, + }, + { .ctl_name = 0, }, +}; + +static struct ctl_table dccp_dir_table[] = { + { + .ctl_name = NET_DCCP, + .procname = "dccp", + .mode = 0555, + .child = dccp_table, + }, + { .ctl_name = 0, }, +}; + +static struct ctl_table dccp_root_table[] = { + { + .ctl_name = CTL_NET, + .procname = "net", + .mode = 0555, + .child = dccp_dir_table, + }, + { .ctl_name = 0, }, +}; + +static struct ctl_table_header *dccp_table_header; + +int __init dccp_sysctl_init(void) +{ + dccp_table_header = register_sysctl_table(dccp_root_table, 1); + + return dccp_table_header != NULL ? 0 : -ENOMEM; +} + +void dccp_sysctl_exit(void) +{ + if (dccp_table_header != NULL) { + unregister_sysctl_table(dccp_table_header); + dccp_table_header = NULL; + } +} diff --git a/net/dccp/timer.c b/net/dccp/timer.c index aa34b57..5244415 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -31,7 +31,7 @@ static void dccp_write_err(struct sock *sk) sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; sk->sk_error_report(sk); - dccp_v4_send_reset(sk, DCCP_RESET_CODE_ABORTED); + dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); dccp_done(sk); DCCP_INC_STATS_BH(DCCP_MIB_ABORTONTIMEOUT); } @@ -141,6 +141,17 @@ static void dccp_retransmit_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + /* retransmit timer is used for feature negotiation throughout + * connection. In this case, no packet is re-transmitted, but rather an + * ack is generated and pending changes are splaced into its options. + */ + if (sk->sk_send_head == NULL) { + dccp_pr_debug("feat negotiation retransmit timeout %p\n", sk); + if (sk->sk_state == DCCP_OPEN) + dccp_send_ack(sk); + goto backoff; + } + /* * sk->sk_send_head has to have one skb with * DCCP_SKB_CB(skb)->dccpd_type set to one of the retransmittable DCCP @@ -177,6 +188,7 @@ static void dccp_retransmit_timer(struct sock *sk) goto out; } +backoff: icsk->icsk_backoff++; icsk->icsk_retransmits++; |