- 03 Dec, 2006 40 commits
-
-
Gerrit Renker authored
Problem:
-
Gerrit Renker authored
This corrects the setting of the nofeedback timer with regard to RFC 3448 - previously it was not set to max(4*R, 2*s/X) as specified. Using the maximum of 1 second as upper bound (as it was done before) can have detrimental effects, especially if R is small. Signed-off-by:
Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by:
Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by:
Arnaldo Carvalho de Melo <acme@mandriva.com>
-
Gerrit Renker authored
This is in response to a request sent earlier by Eric W. Biederman and replaces all sysctl numbers for net.dccp.default with CTL_UNNUMBERED. It has been tested to compile and to work. Commiter note: I've removed the use of CTL_UNNUMBERED, not setting .ctl_name sets it to 0, that is the what CTL_UNNUMBERED is, reason is to avoid unneeded source code cluttering. Signed-off-by: -
Arnaldo Carvalho de Melo authored
[acme@newtoy net-2.6.20]$ pahole /tmp/tcp_ipv6.o inet_protosw /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/net/protocol.h:69 */ struct inet_protosw { struct list_head list; /* 0 8 */ short unsigned int type; /* 8 2 */ /* XXX 2 bytes hole, try to pack */ int protocol; /* 12 4 */ struct proto * prot; /* 16 4 */ const struct proto_ops * ops; /* 20 4 */ int capability; /* 24 4 */ char no_check; /* 28 1 */ unsigned char flags; /* 29 1 */ }; /* size: 32, sum members: 28, holes: 1, sum holes: 2, padding: 2 */ So that we can kill that hole, protocol can only go all the way to 255 (RAW). Signed-off-by: -
Arnaldo Carvalho de Melo authored
As this struct is not userland visible at all. Signed-off-by: -
Arnaldo Carvalho de Melo authored
With this we eliminate the last hole in struct tcp_sock. End result: [acme@newtoy net-2.6.20]$ codiff -sV /tmp/tcp.o.before net/ipv4/tcp.o /pub/scm/linux/kernel/git/acme/net-2.6.20/net/ipv4/tcp.c: struct tcp_sock | -4 tcp_header_len; from: int /* 1000(0) 4(0) */ to: u16 /* 1000(0) 2(0) */ 1 struct changed [acme@newtoy net-2.6.20]$ Now sizeof(tcp_sock) is just... [acme@newtoy net-2.6.20]$ pahole --sizes ../OUTPUT/qemu/net-2.6.20/net/ipv4/tcp.o | grep -w tcp_sock struct tcp_sock: 1500 0 1500 bytes ;-) Signed-off-by: -
Gerrit Renker authored
This patch * removes setting t_RTO in ccid3_hc_tx_init (per [RFC 3448, 4.2], t_RTO is undefined until feedback has been received); * makes some trivial changes (updates of comments); * performs a small optimisation by exploiting that the feedback timeout uses the value of t_ipi. The way it is done is safe, because the timeouts appear after the changes to t_ipi, ensuring that up-to-date values are used; * in ccid3_hc_tx_packet_recv, moves the t_rto statement closer to the calculation of the next_tmout. This makes the code clearer to read and is also safe, since t_rto is not updated until the next call of ccid3_hc_tx_packet_recv, and is not read by the functions called via ccid_wait_for_ccid(); * removes a `max' statement in sk_reset_timer, this is not needed since the timeout value is always greater than 1E6 microseconds. * adds `XXX'es to highlight that currently the nofeedback timer is set in a non-standard way Signed-off-by:
-
Gerrit Renker authored
This patch: * consolidates updating of parameters (t_nom, t_ipi, t_delta) which need to be updated at the same time, since they are inter-dependent * removes two inline functions which are no longer needed as a result of the above consolidation * resolves a FIXME regarding the re-calculation of t_ipi within the nofeedback timer, in the state where no feedback has previously been received * ties updating these parameters to updating the sending rate X, exploiting that all three parameters in turn depend on X; and using a small optimisation which can reduce the number of required instructions: only update the three parameters when X really changes Signed-off-by:
-
Gerrit Renker authored
This patch concerns updating the value of the nofeedback timer when no feedback has been received so far. Since in this case the value of R is still undefined according to [RFC 3448, 4.2], we can not perform step (3) of [RFC 3448, 4.3]. A clarification is provided in [RFC 4342, sec. 5], which states that in these cases the nofeedback timer (still) expires "after two seconds". Many thanks to Ian McDonald for pointing this out and providing the clarification. The patch * implements [RFC 4342, sec. 5] with regard to the above case * consolidates handling timer restart by - adding an appropriate jump label and - initialising the timeout value Acked-by:
-
Jamal Hadi Salim authored
Caught by the EyeBalls(tm) of Thomas Graf Signed-off-by:
Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jamal Hadi Salim authored
Might as well make flush notifier prettier when subpolicy used Signed-off-by:
-
Arnaldo Carvalho de Melo authored
[acme@newtoy net-2.6.20]$ pahole net/ipv4/tcp.o xfrm_policy /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/linux/security.h:67 */ struct xfrm_policy { struct xfrm_policy * next; /* 0 4 */ struct hlist_node bydst; /* 4 8 */ struct hlist_node byidx; /* 12 8 */ rwlock_t lock; /* 20 36 */ atomic_t refcnt; /* 56 4 */ struct timer_list timer; /* 60 24 */ u8 type; /* 84 1 */ /* XXX 3 bytes hole, try to pack */ u32 priority; /* 88 4 */ u32 index; /* 92 4 */ struct xfrm_selector selector; /* 96 56 */ struct xfrm_lifetime_cfg lft; /* 152 64 */ struct xfrm_lifetime_cur curlft; /* 216 32 */ struct dst_entry * bundles; /* 248 4 */ __u16 family; /* 252 2 */ __u8 action; /* 254 1 */ __u8 flags; /* 255 1 */ __u8 dead; /* 256 1 */ __u8 xfrm_nr; /* 257 1 */ /* XXX 2 bytes hole, try to pack */ struct xfrm_sec_ctx * security; /* 260 4 */ struct xfrm_tmpl xfrm_vec[6]; /* 264 360 */ }; /* size: 624, sum members: 619, holes: 2, sum holes: 5 */ So lets have just one hole instead of two, by moving 'type' to just before 'action', end result: [acme@newtoy net-2.6.20]$ codiff -s /tmp/tcp.o.before net/ipv4/tcp.o /pub/scm/linux/kernel/git/acme/net-2.6.20/net/ipv4/tcp.c: struct xfrm_policy | -4 1 struct changed [acme@newtoy net-2.6.20]$ [acme@newtoy net-2.6.20]$ pahole -c 64 net/ipv4/tcp.o xfrm_policy /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/linux/security.h:67 */ struct xfrm_policy { struct xfrm_policy * next; /* 0 4 */ struct hlist_node bydst; /* 4 8 */ struct hlist_node byidx; /* 12 8 */ rwlock_t lock; /* 20 36 */ atomic_t refcnt; /* 56 4 */ struct timer_list timer; /* 60 24 */ u32 priority; /* 84 4 */ u32 index; /* 88 4 */ struct xfrm_selector selector; /* 92 56 */ struct xfrm_lifetime_cfg lft; /* 148 64 */ struct xfrm_lifetime_cur curlft; /* 212 32 */ struct dst_entry * bundles; /* 244 4 */ u16 family; /* 248 2 */ u8 type; /* 250 1 */ u8 action; /* 251 1 */ u8 flags; /* 252 1 */ u8 dead; /* 253 1 */ u8 xfrm_nr; /* 254 1 */ /* XXX 1 byte hole, try to pack */ struct xfrm_sec_ctx * security; /* 256 4 */ struct xfrm_tmpl xfrm_vec[6]; /* 260 360 */ }; /* size: 620, sum members: 619, holes: 1, sum holes: 1 */ Are there any fugly data dependencies here? None that I know. In the process changed the removed the __ prefixed types, that are just for userspace visible headers. Signed-off-by: -
Arnaldo Carvalho de Melo authored
[acme@newtoy net-2.6.20]$ pahole net/ipv4/tcp.o hh_cache /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/linux/netdevice.h:190 */ struct hh_cache { struct hh_cache * hh_next; /* 0 4 */ atomic_t hh_refcnt; /* 4 4 */ __be16 hh_type; /* 8 2 */ /* XXX 2 bytes hole, try to pack */ int hh_len; /* 12 4 */ int (*hh_output)(); /* 16 4 */ rwlock_t hh_lock; /* 20 36 */ long unsigned int hh_data[24]; /* 56 96 */ }; /* size: 152, sum members: 150, holes: 1, sum holes: 2 */ [acme@newtoy net-2.6.20]$ find net -name "*.[ch]" | xargs grep 'hh_len.\+=' | sort -u net/atm/br2684.c: hh->hh_len = PADLEN + ETH_HLEN; net/ethernet/eth.c: hh->hh_len = ETH_HLEN; net/ipv4/ipconfig.c: int hh_len = LL_RESERVED_SPACE(dev); net/ipv4/ip_output.c: hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); net/ipv4/ip_output.c: int hh_len = LL_RESERVED_SPACE(dev); net/ipv4/netfilter.c: hh_len = (*pskb)->dst->dev->hard_header_len; net/ipv4/raw.c: hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); net/ipv6/ip6_output.c: hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); net/ipv6/netfilter/ip6t_REJECT.c: hh_len = (dst->dev->hard_header_len + 15)&~15; net/ipv6/raw.c: hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); [acme@newtoy net-2.6.20]$ [acme@newtoy net-2.6.20]$ find include -name "*.h" | xargs grep 'define ETH_HLEN' include/linux/if_ether.h:#define ETH_HLEN 14 /* Total octets in header. */ (((dev)->hard_header_len&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) [acme@newtoy net-2.6.20]$ pahole net/ipv4/tcp.o net_device | grep hard_header_len short unsigned int hard_header_len; /* 106 2 */ [acme@newtoy net-2.6.20]$ So I think we're safe in turning hh_len an u16, end result: [acme@newtoy net-2.6.20]$ codiff -sV /tmp/tcp.o.before net/ipv4/tcp.o /pub/scm/linux/kernel/git/acme/net-2.6.20/net/ipv4/tcp.c: struct hh_cache | -4 hh_len; from: int /* 12(0) 4(0) */ to: u16 /* 10(0) 2(0) */ 1 struct changed [acme@newtoy net-2.6.20]$ Signed-off-by: -
Arnaldo Carvalho de Melo authored
We have a hole in: [acme@newtoy net-2.6.20]$ pahole net/ipv6/tcp_ipv6.o inet_connection_sock_af_ops /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/net/inet_connection_sock.h:38 */ struct inet_connection_sock_af_ops { int (*queue_xmit)(); /* 0 4 */ void (*send_check)(); /* 4 4 */ int (*rebuild_header)(); /* 8 4 */ int (*conn_request)(); /* 12 4 */ struct sock * (*syn_recv_sock)(); /* 16 4 */ int (*remember_stamp)(); /* 20 4 */ __u16 net_header_len; /* 24 2 */ /* XXX 2 bytes hole, try to pack */ int (*setsockopt)(); /* 28 4 */ int (*getsockopt)(); /* 32 4 */ int (*compat_setsockopt)(); /* 36 4 */ int (*compat_getsockopt)(); /* 40 4 */ void (*addr2sockaddr)(); /* 44 4 */ int sockaddr_len; /* 48 4 */ }; /* size: 52, sum members: 50, holes: 1, sum holes: 2 */ But we don't need sockaddr_len to be an int: [acme@newtoy net-2.6.20]$ find net -name "*.[ch]" | xargs grep '\.sockaddr_len.\+=' | sort -u net/dccp/ipv4.c: .sockaddr_len = sizeof(struct sockaddr_in), net/dccp/ipv6.c: .sockaddr_len = sizeof(struct sockaddr_in6), net/ipv4/tcp_ipv4.c: .sockaddr_len = sizeof(struct sockaddr_in), net/ipv6/tcp_ipv6.c: .sockaddr_len = sizeof(struct sockaddr_in6), net/sctp/ipv6.c: .sockaddr_len = sizeof(struct sockaddr_in6), net/sctp/protocol.c: .sockaddr_len = sizeof(struct sockaddr_in), [acme@newtoy net-2.6.20]$ pahole --sizes net/ipv6/tcp_ipv6.o | grep sockaddr_in struct sockaddr_in: 16 0 struct sockaddr_in6: 28 0 [acme@newtoy net-2.6.20]$ So I turned sockaddr_len a 'u16', and now: [acme@newtoy net-2.6.20]$ pahole net/ipv6/tcp_ipv6.o inet_connection_sock_af_ops /* /pub/scm/linux/kernel/git/acme/net-2.6.20/include/net/inet_connection_sock.h:38 */ struct inet_connection_sock_af_ops { int (*queue_xmit)(); /* 0 4 */ void (*send_check)(); /* 4 4 */ int (*rebuild_header)(); /* 8 4 */ int (*conn_request)(); /* 12 4 */ struct sock * (*syn_recv_sock)(); /* 16 4 */ int (*remember_stamp)(); /* 20 4 */ u16 net_header_len; /* 24 2 */ u16 sockaddr_len; /* 26 2 */ int (*setsockopt)(); /* 28 4 */ int (*getsockopt)(); /* 32 4 */ int (*compat_setsockopt)(); /* 36 4 */ int (*compat_getsockopt)(); /* 40 4 */ void (*addr2sockaddr)(); /* 44 4 */ }; /* size: 48 */ So we've saved 4 bytes: [acme@newtoy net-2.6.20]$ codiff -sV /tmp/tcp_ipv6.o.before net/ipv6/tcp_ipv6.o /pub/scm/linux/kernel/git/acme/net-2.6.20/net/ipv6/tcp_ipv6.c: struct inet_connection_sock_af_ops | -4 net_header_len; from: __u16 /* 24(0) 2(0) */ to: u16 /* 24(0) 2(0) */ sockaddr_len; from: int /* 48(0) 4(0) */ to: u16 /* 26(0) 2(0) */ 1 struct changed [acme@newtoy net-2.6.20]$ Signed-off-by: -
Gerrit Renker authored
This patch consolidates set/getsockopt code between UDP(-Lite) v4 and 6. The justification is that UDP(-Lite) is a transport-layer protocol and therefore the socket option code (at least in theory) should be AF-independent. Furthermore, there is the following code reduplication: * do_udp{,v6}_getsockopt is 100% identical between v4 and v6 * do_udp{,v6}_setsockopt is identical up to the following differerence --v4 in contrast to v4 additionally allows the experimental encapsulation types UDP_ENCAP_ESPINUDP and UDP_ENCAP_ESPINUDP_NON_IKE --the remainder is identical between v4 and v6 I believe that this difference is of little relevance. The advantages in not duplicating twice almost completely identical code. The patch further simplifies the interface of udp{,v6}_push_pending_frames, since for the second argument (struct udp_sock *up) it always holds that up = udp_sk(sk); where sk is the first function argument. Signed-off-by: -
Thomas Graf authored
IPv4, IPv6, and DECNet all use struct rta_cacheinfo in a similiar way, therefore rtnl_put_cacheinfo() is added to reuse code. Signed-off-by:
Thomas Graf <tgraf@suug.ch> Signed-off-by:
-
Thomas Graf authored
The destination PID is passed directly to netlink_unicast() respectively netlink_multicast(). Signed-off-by:
-
Gerrit Renker authored
This adds documentation for the TFRC structure fields. Signed-off-by:
-
Gerrit Renker authored
This considers the case - ACK received while no packet has been sent so far. Resolved by printing a (rate-limited) warning message. Further removes an unnecessary BUG_ON in ccid3_hc_tx_packet_recv, received feedback on a terminating connection is simply ignored. Signed-off-by:
-
Gerrit Renker authored
This patch removes a switch statement which is redundant since, * nothing is done in states TFRC_SSTATE_NO_SENT/TFRC_SSTATE_NO_FBACK * it is impossible that the function is called in the state TFRC_SSTATE_TERM, since --the function is called, in dccp_write_xmit, after ccid3_hc_tx_send_packet --if ccid3_hc_tx_send_packet is called in state TFRC_SSTATE_TERM, it returns -EINVAL, which means that ccid3_hc_tx_packet_sent will not be called (compare dccp_write_xmit) --> therefore, this case is logically impossible * the remaining state is TFRC_SSTATE_FBACK which conditionally updates t_ipi, t_nom, and t_delta. This is a no-op, since --t_ipi only changes when feedback is received --however, when feedback arrives via ccid3_hc_tx_packet_recv, there is an identical code block which performs the same set of operations --performing the same set of operations again in ccid3_hc_tx_packet_sent therefore does not change anything, since between the time of receiving the last feedback (and therefore update of t_ipi, t_nom, and t_delta), the value of t_ipi has not changed --since t_ipi has not changed, the values of t_delta and t_nom also do not change, they depend fully on t_ipi Signed-off-by: -
Gerrit Renker authored
This resolves an `XXX' in ccid3_hc_tx_send_packet(). The function is only called on Data and DataAck packets and returns a negative result on zero-sized messages. This is a reasonable policy since CCID 3 is a congestion-control module and congestion control on zero-sized Data(Ack) packets is in a way pathological. The patch uses a more suitable error code for this case, it returns the Posix.1 code `EBADMSG' ("Not a data message") instead of `ENOTCONN'. As a result of ignoring zero-sized packets, a the condition for a warning "First packet is data" in ccid3_hc_tx_packet_sent is always satisfied; this message has been removed since it will always be printed. Signed-off-by: -
Gerrit Renker authored
This makes some logically equivalent simplifications, by replacing rc - values plus goto's with direct return statements. Signed-off-by:
-
Gerrit Renker authored
Problem:
-
Gerrit Renker authored
This patch performs a simplifying (performance) optimisation: In each call of the inline function ccid3_calc_new_t_ipi(), the state is tested against TFRC_SSTATE_NO_FBACK. This is expensive when the function is called very often. A simpler solution, implemented by this patch, is to adapt the control flow. Background:
-
Gerrit Renker authored
Problem:
-
Andrea Bittau authored
Now that we can stuff bigger ack vectors into options. Signed-off-by:
Andrea Bittau <a.bittau@cs.ucl.ac.uk> Signed-off-by:
-
Andrea Bittau authored
Ack vectors grow proportional to the window size. If an ack vector does not fit into a single option, it must be spread across multiple options. This patch will allow for windows to grow larger. Committer note: Simplified the patch a bit, original algorithm kept. Signed-off-by:
-
Andrea Bittau authored
Commiter note: This was split from Andrea's original patch, in the process I changed the type of the ackvec index fields to u16 instead of to int and haven't folded dccp_ackvec_parse with dccp_ackvec_check_rcv_ackno. Next patch will actually do the insertion of more than one ackvec per packet, using, initially, up to a max of 2 ackvecs as per Andrea's original patch, then I'll work on support for larger ackvecs, be it using a sysctl or using setsockopt. Signed-off-by:
-
Andrea Bittau authored
Commiter note: original patch was splitted. Signed-off-by:
-
Thomas Graf authored
Extends the netlink interface to support the __le16 type and converts address addition, deletion and, dumping to use the new netlink interface. Fixes multiple occasions of possible illegal memory references due to not validated netlink attributes. Signed-off-by:
-
Thomas Graf authored
The name rtmsg_ifa is heavly overused and confusing. Signed-off-by:
-
Thomas Graf authored
Signed-off-by:
-
Ville Nuorvala authored
Log an error if the remote tunnel endpoint is unable to handle tunneled packets. Signed-off-by:
Ville Nuorvala <vnuorval@tcs.hut.fi> Signed-off-by:
-
Ville Nuorvala authored
Signed-off-by:
-
Ville Nuorvala authored
Allow link-local tunnel endpoints if the underlying link is defined. Signed-off-by:
-
Ville Nuorvala authored
Doing the mandatory tunnel endpoint checks when the tunnel is set up isn't enough as interfaces can go up or down and addresses can be added or deleted after this. The checks need to be done realtime when the tunnel is processing a packet. Signed-off-by:
-
Ville Nuorvala authored
A logic bug in tunnel lookup could result in duplicate tunnels when changing an existing device. Signed-off-by:
-
Thomas Graf authored
Based on Jamal's patch but compiled and even tested. :-) Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Signed-off-by: -
Arnaldo Carvalho de Melo authored
Signed-off-by:
-
