- 26 Apr, 2007 40 commits
-
-
YOSHIFUJI Hideaki authored
Signed-off-by:
YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
YOSHIFUJI Hideaki authored
Signed-off-by:
-
YOSHIFUJI Hideaki authored
Signed-off-by:
-
YOSHIFUJI Hideaki authored
Signed-off-by:
-
YOSHIFUJI Hideaki authored
Signed-off-by:
-
YOSHIFUJI Hideaki authored
Signed-off-by:
-
Herbert Xu authored
This patch eliminates some duplicate code for the verification of receive checksums between UDP-Lite and UDP. It does this by introducing __skb_checksum_complete_head which is identical to __skb_checksum_complete_head apart from the fact that it takes a length parameter rather than computing the first skb->len bytes. As a result UDP-Lite will be able to use hardware checksum offload for packets which do not use partial coverage checksums. It also means that UDP-Lite loopback no longer does unnecessary checksum verification. If any NICs start support UDP-Lite this would also start working automatically. This patch removes the assumption that msg_flags has MSG_TRUNC clear upon entry in recvmsg. Signed-off-by:
Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by:
-
Herbert Xu authored
This reverts the changeset [IPV6]: UDPv6 checksum. We always need to check UDPv6 checksum because it is mandatory. The sk_filter optimisation has nothing to do whether we verify the checksum. It simply postpones it to the point when the user calls recv or poll. Signed-off-by: -
Eric Dumazet authored
1) Some sysctl vars are declared __read_mostly 2) We can avoid updating stack[] when doing an AVL lookup only. lookup() macro is extended to receive a second parameter, that may be NULL in case of a pure lookup (no need to save the AVL path). This removes unnecessary instructions, because compiler knows if this _stack parameter is NULL or not. text size of net/ipv4/inetpeer.o is 2063 bytes instead of 2107 on x86_64 Signed-off-by:Eric Dumazet <dada1@cosmosbay.com> Signed-off-by:
-
Stephen Hemminger authored
Eliminate need for full 6/4/64 divide to compute queue. Variable maxqueue was really a constant. Fix indentation. Signed-off-by:
Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by:
-
Stephen Hemminger authored
The Newton-Raphson method is quadratically convergent so only a small fixed number of steps are necessary. Therefore it is faster to unroll the loop. Since div64_64 is no longer inline it won't cause code explosion. Also fixes a bug that can occur if x^2 was bigger than 32 bits. Signed-off-by:
-
YOSHIFUJI Hideaki authored
Signed-off-by:
-
David S. Miller authored
Signed-off-by: -
YOSHIFUJI Hideaki authored
The inet6_ifaddr for source address of RS is leaked if the address is not an optimistic address. Signed-off-by:
-
Neil Horman authored
Nominally an autoconfigured IPv6 address is added to an interface in the Tentative state (as per RFC 2462). Addresses in this state remain in this state while the Duplicate Address Detection process operates on them to determine their uniqueness on the network. During this period, these tentative addresses may not be used for communication, increasing the time before a node may be able to communicate on a network. Using Optimistic Duplicate Address Detection, autoconfigured addresses may be used immediately for communication on the network, as long as certain rules are followed to avoid conflicts with other nodes during the Duplicate Address Detection process. Signed-off-by:
Neil Horman <nhorman@tuxdriver.com> Signed-off-by:
-
Yasuyuki Kozakai authored
ip6_tunnel before supporting IPv4/IPv6 tunnel allows only IPPROTO_IPV6 in configurations from userland. This allows userland to set IPPROTO_IPIP and 0(wildcard). ip6_tunnel only handles allowed inner protocols. Signed-off-by:
Yasuyuki Kozakai <yasuyuki.kozakai@toshiba.co.jp> Signed-off-by:
-
Yasuyuki Kozakai authored
Signed-off-by:
-
Yasuyuki Kozakai authored
Some notes - Protocol number IPPROTO_IPIP is used for IPv4 over IPv6 packets. - If IP6_TNL_F_USE_ORIG_TCLASS is set, TOS in IPv4 header is copied to Traffic Class in outer IPv6 header on xmit. - IP6_TNL_F_USE_ORIG_FLOWLABEL is ignored on xmit of IPv4 packets, because IPv4 header does not have flow label. - Kernel sends ICMP error if IPv4 packet is too big on xmit, even if DF flag is not set. Signed-off-by:
-
Yasuyuki Kozakai authored
This enables to add IPv4/IPv6 specific handling later, Signed-off-by:
-
Yasuyuki Kozakai authored
This enables to add IPv4/IPv6 specific handling later, Signed-off-by:
-
Yasuyuki Kozakai authored
This enables to add IPv4/IPv6 specific error handling later, Signed-off-by:
-
YOSHIFUJI Hideaki authored
Signed-off-by: -
David S. Miller authored
If the user passes MSG_TRUNC in via msg_flags, return the full packet size not the truncated size. Idea from Herbert Xu and Thomas Graf. Signed-off-by: -
Eric Dumazet authored
We currently use a special structure (struct skb_timeval) and plain 'struct timeval' to store packet timestamps in sk_buffs and struct sock. This has some drawbacks : - Fixed resolution of micro second. - Waste of space on 64bit platforms where sizeof(struct timeval)=16 I suggest using ktime_t that is a nice abstraction of high resolution time services, currently capable of nanosecond resolution. As sizeof(ktime_t) is 8 bytes, using ktime_t in 'struct sock' permits a 8 byte shrink of this structure on 64bit architectures. Some other structures also benefit from this size reduction (struct ipq in ipv4/ip_fragment.c, struct frag_queue in ipv6/reassembly.c, ...) Once this ktime infrastructure adopted, we can more easily provide nanosecond resolution on top of it. (ioctl SIOCGSTAMPNS and/or SO_TIMESTAMPNS/SCM_TIMESTAMPNS) Note : this patch includes a bug correction in compat_sock_get_timestamp() where a "err = 0;" was missing (so this syscall returned -ENOENT instead of 0) Signed-off-by:
-
Stephen Hemminger authored
Here is the current version of the 64 bit divide common code. Signed-off-by:
-
James Morris authored
Where appropriate, convert references to xtime.tv_sec to the get_seconds() helper function. Signed-off-by:
James Morris <jmorris@namei.org> Signed-off-by:
-
Stephen Hemminger authored
Since devices can change name and other wierdness, don't hold onto a copy of device name, instead use pointer to output device. Fix a couple of leaks in error handling path as well. Signed-off-by:
Robert Olsson <robert.olsson@its.uu.se> Signed-off-by:
-
Stephen Hemminger authored
The existing htonl() macro is smart enough to do the same code as using __constant_htonl() and it looks cleaner. Signed-off-by:
-
Stephen Hemminger authored
Can use random32() now. Signed-off-by:
-
Stephen Hemminger authored
Remove private debug macro and replace with standard version Signed-off-by:
-
Eric Dumazet authored
sk_backlog is a critical field of struct sock. (known famous words) It is (ab)used in hot paths, in particular in release_sock(), tcp_recvmsg(), tcp_v4_rcv(), sk_receive_skb(). It really makes sense to place it next to sk_lock, because sk_backlog is only used after sk_lock locked (and thus memory cache line in L1 cache). This should reduce cache misses and sk_lock acquisition time. (In theory, we could only move the head pointer near sk_lock, and leaving tail far away, because 'tail' is normally not so hot, but keep it simple :) ) Signed-off-by:
-
Ilpo Järvinen authored
Undoing ssthresh is disabled in fastretrans_alert whenever FLAG_ECE is set by clearing prior_ssthresh. The clearing does not protect FRTO because FRTO operates before fastretrans_alert. Moving the clearing of prior_ssthresh earlier seems to be a suboptimal solution to the FRTO case because then FLAG_ECE will cause a second ssthresh reduction in try_to_open (the first occurred when FRTO was entered). So instead, FRTO falls back immediately to the rate halving response, which switches TCP to CA_CWR state preventing the latter reduction of ssthresh. If the first ECE arrived before the ACK after which FRTO is able to decide RTO as spurious, prior_ssthresh is already cleared. Thus no undoing for ssthresh occurs. Besides, FLAG_ECE should be set also in the following ACKs resulting in rate halving response that sees TCP is already in CA_CWR, which again prevents an extra ssthresh reduction on that round-trip. If the first ECE arrived before RTO, ssthresh has already been adapted and prior_ssthresh remains cleared on entry because TCP is in CA_CWR (the same applies also to a case where FRTO is entered more than once and ECE comes in the middle). High_seq must not be touched after tcp_enter_cwr because CWR round-trip calculation depends on it. I believe that after this patch, FRTO should be ECN-safe and even able to take advantage of synergy benefits. Signed-off-by:
Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by:
-
Ilpo Järvinen authored
A local variable for icsk was created but this change was missing. Spotted by Jarek Poplawski. Signed-off-by:
-
Ilpo Järvinen authored
In addition, fixed minor things in tcp_frto sysctl. Signed-off-by:
-
Ilpo Järvinen authored
New sysctl tcp_frto_response is added to select amongst these responses: - Rate halving based; reuses CA_CWR state (default) - Very conservative; used to be the only one available (=1) - Undo cwr; undoes ssthresh and cwnd reductions (=2) The response with rate halving requires a new parameter to tcp_enter_cwr because FRTO has already reduced ssthresh and doing a second reduction there has to be prevented. In addition, to keep things nice on 80 cols screen, a local variable was added. Signed-off-by:
-
Ilpo Järvinen authored
The reordering detection must work also when FRTO has not been used at all which was the original intention of mine, just the expression of the idea was flawed. Signed-off-by:
-
David S. Miller authored
Signed-off-by: -
Eric Dumazet authored
I noticed in oprofile study a cache miss in tcp_rcv_established() to read copied_seq. ffffffff80400a80 <tcp_rcv_established>: /* tcp_rcv_established total: 4034293 2.0400 */ 55493 0.0281 :ffffffff80400bc9: mov 0x4c8(%r12),%eax copied_seq 543103 0.2746 :ffffffff80400bd1: cmp 0x3e0(%r12),%eax rcv_nxt if (tp->copied_seq == tp->rcv_nxt && len - tcp_header_len <= tp->ucopy.len) { In this function, the cache line 0x4c0 -> 0x500 is used only for this reading 'copied_seq' field. rcv_wup and copied_seq should be next to rcv_nxt field, to lower number of active cache lines in hot paths. (tcp_rcv_established(), tcp_poll(), ...) As you suggested, I changed tcp_create_openreq_child() so that these fields are changed together, to avoid adding a new store buffer stall. Patch is 64bit friendly (no new hole because of alignment constraints) Signed-off-by: -
Ilpo Järvinen authored
In general, TCP code uses "sk" for struct sock pointer. Signed-off-by:
-
John Heffner authored
Signed-off-by:
John Heffner <jheffner@psc.edu> Signed-off-by:
-
