)]}' { "log": [ { "commit": "8243126c5e29030bf1a3fb75187a513966dcba62", "tree": "39750d44770efcdac150f041f71b7272c8da20f9", "parents": [ "f09484ff87f677056ce631aa3d8e486861501b51" ], "author": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jan 17 02:54:21 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jan 17 02:54:21 2006 -0800" }, "message": "[NET]: Make second arg to skb_reserved() signed.\n\nSome subsystems, such as PPP, can send negative values\nhere. It just happened to work correctly on 32-bit with\nan unsigned value, but on 64-bit this explodes.\n\nFigured out by Paul Mackerras based upon several PPP crash\nreports.\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "3e3850e989c5d2eb1aab6f0fd9257759f0f4cbc6", "tree": "fa05d1de4767bc30e77442ffbacfe8bd8dd2213d", "parents": [ "8cdfab8a43bb4b3da686ea503a702cb6f9f6a803" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Fri Jan 06 23:04:54 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Sat Jan 07 12:57:33 2006 -0800" }, "message": "[NETFILTER]: Fix xfrm lookup in ip_route_me_harder/ip6_route_me_harder\n\nip_route_me_harder doesn\u0027t use the port numbers of the xfrm lookup and\nuses ip_route_input for non-local addresses which doesn\u0027t do a xfrm\nlookup, ip6_route_me_harder doesn\u0027t do a xfrm lookup at all.\n\nUse xfrm_decode_session and do the lookup manually, make sure both\nonly do the lookup if the packet hasn\u0027t been transformed already.\n\nMakeing sure the lookup only happens once needs a new field in the\nIP6CB, which exceeds the size of skb-\u003ecb. The size of skb-\u003ecb is\nincreased to 48b. Apparently the IPv6 mobile extensions need some\nmore room anyway.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4947d3ef8de7b4f42aed6ea9ba689dc8fb45b5a5", "tree": "a4e77f0271702e4ff34a7a9e0c9598a3807204ee", "parents": [ "17ba15fb6264f27374bc87f4c3f8519b80289d85" ], "author": { "name": "Benjamin LaHaise", "email": "bcrl@kvack.org", "time": "Tue Jan 03 14:06:50 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 03 14:06:50 2006 -0800" }, "message": "[NET]: Speed up __alloc_skb()\n\nFrom: Benjamin LaHaise \u003cbcrl@kvack.org\u003e\n\nIn __alloc_skb(), the use of skb_shinfo() which casts a u8 * to the \nshared info structure results in gcc being forced to do a reload of the \npointer since it has no information on possible aliasing. Fix this by \nusing a pointer to refer to skb_shared_info.\n\nBy initializing skb_shared_info sequentially, the write combining buffers \ncan reduce the number of memory transactions to a single write. Reorder \nthe initialization in __alloc_skb() to match the structure definition. \nThere is also an alignment issue on 64 bit systems with skb_shared_info \nby converting nr_frags to a short everything packs up nicely.\n\nAlso, pass the slab cache pointer according to the fclone flag instead \nof using two almost identical function calls.\n\nThis raises bw_unix performance up to a peak of 707KB/s when combined \nwith the spinlock patch. It should help other networking protocols, too.\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "77d76ea310b50a9c8ff15bd290fcb4ed4961adf2", "tree": "7d6e8b2426d4b3debe5ddf838ab2a2ef13f1b106", "parents": [ "7708610b1bff4a0ba8a73733d3c7c4bda9f94b21" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Thu Dec 22 12:43:42 2005 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jan 03 13:11:14 2006 -0800" }, "message": "[NET]: Small cleanup to socket initialization\n\nsock_init can be done as a core_initcall instead of calling\nit directly in init/main.c\n\nAlso I removed an out of date #ifdef.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "3305b80c214c642b89cd5c21af83bc91ec13f8bd", "tree": "909ed75c500d0ac422738781f84a819c933703c5", "parents": [ "57cca05af1e20fdc65b55be52c042c234f86c866" ], "author": { "name": "Herbert Xu", "email": "herbert@gondor.apana.org.au", "time": "Tue Dec 13 23:16:37 2005 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jan 03 13:10:41 2006 -0800" }, "message": "[IP]: Simplify and consolidate MSG_PEEK error handling\n\nWhen a packet is obtained from skb_recv_datagram with MSG_PEEK enabled\nit is left on the socket receive queue. This means that when we detect\na checksum error we have to be careful when trying to free the packet\nas someone could have dequeued it in the time being.\n\nCurrently this delicate logic is duplicated three times between UDPv4,\nUDPv6 and RAWv6. This patch moves them into a one place and simplifies\nthe code somewhat.\n\nThis is based on a suggestion by Eric Dumazet.\n\nSigned-off-by: Herbert Xu \u003cherbert@gondor.apana.org.au\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "461ddf3b90bb149b99c3f675959c1bd6b11ed936", "tree": "12c7848560128e4344387eecdfc401369d46bb1c", "parents": [ "b84f4cc977ec4a1260dc8d9165efc9319a93c2a2" ], "author": { "name": "Randy Dunlap", "email": "rdunlap@xenotime.net", "time": "Sun Nov 20 21:25:15 2005 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 20 21:25:15 2005 -0800" }, "message": "[NET]: kernel-doc fixes\n\nFix kernel-doc warnings in network files.\n\nSigned-off-by: Randy Dunlap \u003crdunlap@xenotime.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b84f4cc977ec4a1260dc8d9165efc9319a93c2a2", "tree": "03e60bfcc51dfcb288fb2efe62e9ec805704c3d0", "parents": [ "a516b04950f62d36b33db00c0d3c69d09dae99a9" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sun Nov 20 21:19:21 2005 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 20 21:19:21 2005 -0800" }, "message": "[NET]: Use unused bit for ipvs_property field in struct sk_buff\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "fb286bb2990a107009dbf25f6ffebeb7df77f9be", "tree": "0eede2c37f1b3831e59601933eebf6b82be75ffc", "parents": [ "1064e944d03eb7a72c0fa11236d5e69cfd877a71" ], "author": { "name": "Herbert Xu", "email": "herbert@gondor.apana.org.au", "time": "Thu Nov 10 13:01:24 2005 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Nov 10 13:01:24 2005 -0800" }, "message": "[NET]: Detect hardware rx checksum faults correctly\n\nHere is the patch that introduces the generic skb_checksum_complete\nwhich also checks for hardware RX checksum faults. If that happens,\nit\u0027ll call netdev_rx_csum_fault which currently prints out a stack\ntrace with the device name. In future it can turn off RX checksum.\n\nI\u0027ve converted every spot under net/ that does RX checksum checks to\nuse skb_checksum_complete or __skb_checksum_complete with the\nexceptions of:\n\n* Those places where checksums are done bit by bit. These will call\nnetdev_rx_csum_fault directly.\n\n* The following have not been completely checked/converted:\n\nipmr\nip_vs\nnetfilter\ndccp\n\nThis patch is based on patches and suggestions from Stephen Hemminger\nand David S. Miller.\n\nSigned-off-by: Herbert Xu \u003cherbert@gondor.apana.org.au\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "9fb9cbb1082d6b31fb45aa1a14432449a0df6cf1", "tree": "c964a62bdd766eca436c30f51a9e33e2b798b0a6", "parents": [ "6730c3c14421b7c924d06e31bb66e0adad225547" ], "author": { "name": "Yasuyuki Kozakai", "email": "yasuyuki.kozakai@toshiba.co.jp", "time": "Wed Nov 09 16:38:16 2005 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Nov 09 16:38:16 2005 -0800" }, "message": "[NETFILTER]: Add nf_conntrack subsystem.\n\nThe existing connection tracking subsystem in netfilter can only\nhandle ipv4. There were basically two choices present to add\nconnection tracking support for ipv6. We could either duplicate all\nof the ipv4 connection tracking code into an ipv6 counterpart, or (the\nchoice taken by these patches) we could design a generic layer that\ncould handle both ipv4 and ipv6 and thus requiring only one sub-protocol\n(TCP, UDP, etc.) connection tracking helper module to be written.\n\nIn fact nf_conntrack is capable of working with any layer 3\nprotocol.\n\nThe existing ipv4 specific conntrack code could also not deal\nwith the pecularities of doing connection tracking on ipv6,\nwhich is also cured here. For example, these issues include:\n\n1) ICMPv6 handling, which is used for neighbour discovery in\n ipv6 thus some messages such as these should not participate\n in connection tracking since effectively they are like ARP\n messages\n\n2) fragmentation must be handled differently in ipv6, because\n the simplistic \"defrag, connection track and NAT, refrag\"\n (which the existing ipv4 connection tracking does) approach simply\n isn\u0027t feasible in ipv6\n\n3) ipv6 extension header parsing must occur at the correct spots\n before and after connection tracking decisions, and there were\n no provisions for this in the existing connection tracking\n design\n\n4) ipv6 has no need for stateful NAT\n\nThe ipv4 specific conntrack layer is kept around, until all of\nthe ipv4 specific conntrack helpers are ported over to nf_conntrack\nand it is feature complete. Once that occurs, the old conntrack\nstuff will get placed into the feature-removal-schedule and we will\nfully kill it off 6 months later.\n\nSigned-off-by: Yasuyuki Kozakai \u003cyasuyuki.kozakai@toshiba.co.jp\u003e\nSigned-off-by: Harald Welte \u003claforge@netfilter.org\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@mandriva.com\u003e\n" }, { "commit": "300ce174ebc2fcf2b5111a50fa42f79d891927dd", "tree": "ea7ac40eac2de90be9e5575759bab18029ae2fdf", "parents": [ "07aaa11540828f4482c09e1a936a1f63cdb9fc9d" ], "author": { "name": "Stephen Hemminger", "email": "shemminger@osdl.org", "time": "Sun Oct 30 13:47:34 2005 -0800" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@mandriva.com", "time": "Sat Nov 05 20:56:41 2005 -0200" }, "message": "[NETEM]: Support time based reordering\n\nChange netem to support packets getting reordered because of variations in\ndelay. Introduce a special case version of FIFO that queues packets in order\nbased on the netem delay.\n\nSince netem is classful, those users that don\u0027t want jitter based reordering\ncan just insert a pfifo instead of the default.\n\nThis required changes to generic skbuff code to allow finer grain manipulation\nof sk_buff_head. Insertion into the middle and reverse walk.\n\nSigned-off-by: Stephen Hemminger \u003cshemminger@osdl.org\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@mandriva.com\u003e\n" }, { "commit": "e89e9cf539a28df7d0eb1d0a545368e9920b34ac", "tree": "aae6a825f351ce931fcd30f1a865ebe65227c4b8", "parents": [ "de5144164f6242ccfa8c9b64eec570564f5eaf14" ], "author": { "name": "Ananda Raju", "email": "ananda.raju@neterion.com", "time": "Tue Oct 18 15:46:41 2005 -0700" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@mandriva.com", "time": "Fri Oct 28 16:30:00 2005 -0200" }, "message": "[IPv4/IPv6]: UFO Scatter-gather approach\n\nAttached is kernel patch for UDP Fragmentation Offload (UFO) feature.\n\n1. This patch incorporate the review comments by Jeff Garzik.\n2. Renamed USO as UFO (UDP Fragmentation Offload)\n3. udp sendfile support with UFO\n\nThis patches uses scatter-gather feature of skb to generate large UDP\ndatagram. Below is a \"how-to\" on changes required in network device\ndriver to use the UFO interface.\n\nUDP Fragmentation Offload (UFO) Interface:\n-------------------------------------------\nUFO is a feature wherein the Linux kernel network stack will offload the\nIP fragmentation functionality of large UDP datagram to hardware. This\nwill reduce the overhead of stack in fragmenting the large UDP datagram to\nMTU sized packets\n\n1) Drivers indicate their capability of UFO using\ndev-\u003efeatures |\u003d NETIF_F_UFO | NETIF_F_HW_CSUM | NETIF_F_SG\n\nNETIF_F_HW_CSUM is required for UFO over ipv6.\n\n2) UFO packet will be submitted for transmission using driver xmit routine.\nUFO packet will have a non-zero value for\n\n\"skb_shinfo(skb)-\u003eufo_size\"\n\nskb_shinfo(skb)-\u003eufo_size will indicate the length of data part in each IP\nfragment going out of the adapter after IP fragmentation by hardware.\n\nskb-\u003edata will contain MAC/IP/UDP header and skb_shinfo(skb)-\u003efrags[]\ncontains the data payload. The skb-\u003eip_summed will be set to CHECKSUM_HW\nindicating that hardware has to do checksum calculation. Hardware should\ncompute the UDP checksum of complete datagram and also ip header checksum of\neach fragmented IP packet.\n\nFor IPV6 the UFO provides the fragment identification-id in\nskb_shinfo(skb)-\u003eip6_frag_id. The adapter should use this ID for generating\nIPv6 fragments.\n\nSigned-off-by: Ananda Raju \u003cananda.raju@neterion.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e (forwarded)\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@mandriva.com\u003e\n" }, { "commit": "c83c24861882758b9731e8550225cd1e52a4cd1c", "tree": "a6161031466786ec726532a822fdb63104613b5f", "parents": [ "0d0d2bba97cb091218ea0bcb3d8debcc7bf48397" ], "author": { "name": "Randy Dunlap", "email": "rdunlap@xenotime.net", "time": "Tue Oct 18 22:07:41 2005 -0700" }, "committer": { "name": "Arnaldo Carvalho de Melo", "email": "acme@mandriva.com", "time": "Wed Oct 26 01:10:18 2005 -0200" }, "message": "[SK_BUFF] kernel-doc: fix skbuff warnings\n\nAdd kernel-doc to skbuff.h, skbuff.c to eliminate kernel-doc warnings.\n\nSigned-off-by: Randy Dunlap \u003crdunlap@xenotime.net\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@mandriva.com\u003e\n" }, { "commit": "dd0fc66fb33cd610bc1a5db8a5e232d34879b4d7", "tree": "51f96a9db96293b352e358f66032e1f4ff79fafb", "parents": [ "3b0e77bd144203a507eb191f7117d2c5004ea1de" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Fri Oct 07 07:46:04 2005 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sat Oct 08 15:00:57 2005 -0700" }, "message": "[PATCH] gfp flags annotations - part 1\n\n - added typedef unsigned int __nocast gfp_t;\n\n - replaced __nocast uses for gfp flags with gfp_t - it gives exactly\n the same warnings as far as sparse is concerned, doesn\u0027t change\n generated code (from gcc point of view we replaced unsigned int with\n typedef) and documents what\u0027s going on far better.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "325ed8239309cb29f10ea58c5a668058ead11479", "tree": "77386825b72ac44f4f42a942ef78bd1ff924b351", "parents": [ "ddea7be0ec8d1374f0b483a81566ed56ec9f3905" ], "author": { "name": "Herbert Xu", "email": "herbert@gondor.apana.org.au", "time": "Mon Oct 03 13:57:23 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Oct 03 13:57:23 2005 -0700" }, "message": "[NET]: Fix packet timestamping.\n\nI\u0027ve found the problem in general. It affects any 64-bit\narchitecture. The problem occurs when you change the system time.\n\nSuppose that when you boot your system clock is forward by a day.\nThis gets recorded down in skb_tv_base. You then wind the clock back\nby a day. From that point onwards the offset will be negative which\nessentially overflows the 32-bit variables they\u0027re stored in.\n\nIn fact, why don\u0027t we just store the real time stamp in those 32-bit\nvariables? After all, we\u0027re not going to overflow for quite a while\nyet.\n\nWhen we do overflow, we\u0027ll need a better solution of course.\n\nSigned-off-by: Herbert Xu \u003cherbert@gondor.apana.org.au\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0e4e4220f10bf8f58a8606f0cb28538088c64b1a", "tree": "5700dfd0ceab3b435a7fc91cc25e56bb911ce2a9", "parents": [ "1b11d78cf87a7014f96e5b7fa2e1233cc8081a00" ], "author": { "name": "Stephen Hemminger", "email": "shemminger@osdl.org", "time": "Thu Sep 08 12:32:03 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Sep 08 12:32:03 2005 -0700" }, "message": "[NET]: Optimize pskb_trim_rcsum()\n\nSince packets almost never contain extra garbage at the end, it is\nworthwhile to optimize for that case.\n\nSigned-off-by: Stephen Hemminger \u003cshemminger@osdl.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n\n" }, { "commit": "f2c383988d68c91a7d474b7cf26c0a2df49bbafe", "tree": "77981ee635498d88417ccb7742214cbbd3b1a466", "parents": [ "513c25000005257e5474f261bf27d4a3c1dff1e3" ], "author": { "name": "Stephen Hemminger", "email": "shemminger@osdl.org", "time": "Tue Sep 06 15:48:03 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Sep 06 15:48:03 2005 -0700" }, "message": "[NET]: skb_get/set_timestamp use const\n\nThe new timestamp get/set routines should have const attribute\non parameters (helps to indicate direction).\n\nSigned-off-by: Stephen Hemminger \u003cshemminger@osdl.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d179cd12928443f3ec29cfbc3567439644bd0afc", "tree": "0bfc57e73f0bf9f7bb9d5c8ce7d3d5afe550f94e", "parents": [ "e92ae93a8aa66aea12935420cb22d4df1c18d023" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Aug 17 14:57:30 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Mon Aug 29 16:01:54 2005 -0700" }, "message": "[NET]: Implement SKB fast cloning.\n\nProtocols that make extensive use of SKB cloning,\nfor example TCP, eat at least 2 allocations per\npacket sent as a result.\n\nTo cut the kmalloc() count in half, we implement\na pre-allocation scheme wherein we allocate\n2 sk_buff objects in advance, then use a simple\nreference count to free up the memory at the\ncorrect time.\n\nBased upon an initial patch by Thomas Graf and\nsuggestions from Herbert Xu.\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "20380731bc2897f2952ae055420972ded4cd786e", "tree": "abd31e5ebfadcf4f9024634eec8b11855029e512", "parents": [ "9deff7f2365958c5c5aa8cb5a0dd651c4dd83f8f" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@mandriva.com", "time": "Tue Aug 16 02:18:02 2005 -0300" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Mon Aug 29 16:01:32 2005 -0700" }, "message": "[NET]: Fix sparse warnings\n\nOf this type, mostly:\n\nCHECK net/ipv6/netfilter.c\nnet/ipv6/netfilter.c:96:12: warning: symbol \u0027ipv6_netfilter_init\u0027 was not declared. Should it be static?\nnet/ipv6/netfilter.c:101:6: warning: symbol \u0027ipv6_netfilter_fini\u0027 was not declared. Should it be static?\n\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@mandriva.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a61bbcf28a8cb0ba56f8193d512f7222e711a294", "tree": "33ae1976ab3b08aac516debb2742d2c6696d5436", "parents": [ "25ed891019b84498c83903ecf53df7ce35e9cff6" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sun Aug 14 17:24:31 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Mon Aug 29 15:58:24 2005 -0700" }, "message": "[NET]: Store skb-\u003etimestamp as offset to a base timestamp\n\nReduces skb size by 8 bytes on 64-bit.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f2ccd8fa06c8e302116e71df372f5c1f83432e03", "tree": "6e933f4bdc8899009edb33642b908779f123fb4a", "parents": [ "b6b99eb5409d75ae35390057cd28f3aedfbd4cf4" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Aug 09 19:34:12 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Mon Aug 29 15:32:25 2005 -0700" }, "message": "[NET]: Kill skb-\u003ereal_dev\n\nBonding just wants the device before the skb_bond()\ndecapsulation occurs, so simply pass that original\ndevice into packet_type-\u003efunc() as an argument.\n\nIt remains to be seen whether we can use this same\nexact thing to get rid of skb-\u003einput_dev as well.\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b6b99eb5409d75ae35390057cd28f3aedfbd4cf4", "tree": "d9bdbd412bec6474e6845480a806edd74c3a2808", "parents": [ "83e3609eba3818f6e18b8bf9442195169ac306b7" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Tue Aug 09 19:33:51 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Mon Aug 29 15:32:20 2005 -0700" }, "message": "[NET]: Reduce tc_index/tc_verd to u16\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "6f1cf16582160c4839f05007c978743911aa022b", "tree": "78c87b929e9c0469869db1c91a6691fe6ca689c6", "parents": [ "b0573dea1fb32ebc72ffa05980fd840df1d80860" ], "author": { "name": "Stephen Hemminger", "email": "shemminger@osdl.org", "time": "Tue Aug 09 19:31:17 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Mon Aug 29 15:31:42 2005 -0700" }, "message": "[NET]: Remove HIPPI private from skbuff.h\n\nThis removes the private element from skbuff, that is only used by\nHIPPI. Instead it uses skb-\u003ecb[] to hold the additional data that is\nneeded in the output path from hard_header to device driver.\n\nPS: The only qdisc that might potentially corrupt this cb[] is if\nnetem was used over HIPPI. I will take care of that by fixing netem\nto use skb-\u003estamp. I don\u0027t expect many users of netem over HIPPI\n\nSigned-off-by: Stephen Hemminger \u003cshemminger@osdl.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "abc3bc58047efa72ee9c2e208cbeb73d261ad703", "tree": "05701d5210afd76fded4bd4268a0e7e8c90a06bf", "parents": [ "8728b834b226ffcf2c94a58530090e292af2a7bf" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Tue Aug 09 19:25:56 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Mon Aug 29 15:31:18 2005 -0700" }, "message": "[NET]: Kill skb-\u003etc_classid\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "8728b834b226ffcf2c94a58530090e292af2a7bf", "tree": "2fd51ff3b7097eb3ffc41ea3a1d8b3ba04715b4c", "parents": [ "6869c4d8e066e21623c812c448a05f1ed931c9c6" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Aug 09 19:25:21 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Mon Aug 29 15:31:14 2005 -0700" }, "message": "[NET]: Kill skb-\u003elist\n\nRemove the \"list\" member of struct sk_buff, as it is entirely\nredundant. All SKB list removal callers know which list the\nSKB is on, so storing this in sk_buff does nothing other than\ntaking up some space.\n\nTwo tricky bits were SCTP, which I took care of, and two ATM\ndrivers which Francois Romieu \u003cromieu@fr.zoreil.com\u003e fixed\nup.\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: Francois Romieu \u003cromieu@fr.zoreil.com\u003e\n" }, { "commit": "6869c4d8e066e21623c812c448a05f1ed931c9c6", "tree": "ce18efc459e121e3a0b1bf5f85615567cdb30f68", "parents": [ "bf3a46aa9b96f6eb3a49a568f72a2801c3e830c0" ], "author": { "name": "Harald Welte", "email": "laforge@netfilter.org", "time": "Tue Aug 09 19:24:19 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Mon Aug 29 15:31:04 2005 -0700" }, "message": "[NETFILTER]: reduce netfilter sk_buff enlargement\n\nAs discussed at netconf\u002705, we\u0027re trying to save every bit in sk_buff.\nThe patch below makes sk_buff 8 bytes smaller. I did some basic\ntesting on my notebook and it seems to work.\n\nThe only real in-tree user of nfcache was IPVS, who only needs a\nsingle bit. Unfortunately I couldn\u0027t find some other free bit in\nsk_buff to stuff that bit into, so I introduced a separate field for\nthem. Maybe the IPVS guys can resolve that to further save space.\n\nInitially I wanted to shrink pkt_type to three bits (PACKET_HOST and\nalike are only 6 values defined), but unfortunately the bluetooth code\noverloads pkt_type :(\n\nThe conntrack-event-api (out-of-tree) uses nfcache, but Rusty just\ncame up with a way how to do it without any skb fields, so it\u0027s safe\nto remove it.\n\n- remove all never-implemented \u0027nfcache\u0027 code\n- don\u0027t have ipvs code abuse \u0027nfcache\u0027 field. currently get\u0027s their own\n compile-conditional skb-\u003eipvs_property field. IPVS maintainers can\n decide to move this bit elswhere, but nfcache needs to die.\n- remove skb-\u003enfcache field to save 4 bytes\n- move skb-\u003enfctinfo into three unused bits to save further 4 bytes\n\nSigned-off-by: Harald Welte \u003claforge@netfilter.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "bf3a46aa9b96f6eb3a49a568f72a2801c3e830c0", "tree": "4387ee7d8ef83348338a9d433c93139a4747dcb5", "parents": [ "8f3d17fb7bcb7c255197d11469fb5e9695c9d2f4" ], "author": { "name": "Harald Welte", "email": "laforge@netfilter.org", "time": "Tue Aug 09 19:22:01 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Mon Aug 29 15:29:31 2005 -0700" }, "message": "[NETFILTER]: convert nfmark and conntrack mark to 32bit\n\nAs discussed at netconf\u002705, we convert nfmark and conntrack-mark to be\n32bits even on 64bit architectures.\n\nSigned-off-by: Harald Welte \u003claforge@netfilter.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a0d3bea3cf6c7c1b53a46432bd490b5dc784ca42", "tree": "2c0f1d9e4c94f6b4052ca7f51442a3f5922124e3", "parents": [ "7d69fa6266770eeb6317eddd46b64456e8a515bf" ], "author": { "name": "Alexey Dobriyan", "email": "adobriyan@gmail.com", "time": "Thu Aug 11 16:05:50 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Aug 11 16:05:50 2005 -0700" }, "message": "[NET]: Make skb-\u003eprotocol __be16\n\nThere are many instances of\n\n\tskb-\u003eprotocol \u003d htons(ETH_P_*);\n\tskb-\u003eprotocol \u003d __constant_htons(ETH_P_*);\nand\n\tskb-\u003eprotocol \u003d *_type_trans(...);\n\nMost of *_type_trans() are already endian-annotated, so, let\u0027s shift\nattention on other warnings.\n\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "e2bf521d9728bfae9b6c3d484614e5962d0b5afd", "tree": "74a126835dc9e26fbca5080214f3cc1bb4f7c5ea", "parents": [ "37da647d994cdac7e0bc8d2a365fbda403939a2b" ], "author": { "name": "Victor Fusco", "email": "victor@cetuc.puc-rio.br", "time": "Mon Jul 18 13:36:38 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jul 18 13:36:38 2005 -0700" }, "message": "[NET]: Fix \"nocast type\" warnings in skbuff.h\n\nFrom: Victor Fusco \u003cvictor@cetuc.puc-rio.br\u003e\n\nFix the sparse warning \"implicit cast to nocast type\"\n\nSigned-off-by: Victor Fusco \u003cvictor@cetuc.puc-rio.br\u003e\nSigned-off-by: Domen Puncer \u003cdomen@coderock.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "86a76caf8705e3524e15f343f3c4806939a06dc8", "tree": "ac2022a6073b5af228e009178048bdab070d2230", "parents": [ "b03efcfb2180289718991bb984044ce6c5b7d1b0" ], "author": { "name": "Victor Fusco", "email": "victor@cetuc.puc-rio.br", "time": "Fri Jul 08 14:57:47 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Jul 08 14:57:47 2005 -0700" }, "message": "[NET]: Fix sparse warnings\n\nFrom: Victor Fusco \u003cvictor@cetuc.puc-rio.br\u003e\n\nFix the sparse warning \"implicit cast to nocast type\"\n\nSigned-off-by: Victor Fusco \u003cvictor@cetuc.puc-rio.br\u003e\nSigned-off-by: Domen Puncer \u003cdomen@coderock.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1cbb3380ef683f742876f48e3739b3df4ea9e168", "tree": "f1c65a6325068ea7baeec716adea5176cdbe6f20", "parents": [ "e176fe8954a5239c24afe79b1001ba3c29511963" ], "author": { "name": "Thomas Graf", "email": "tgraf@suug.ch", "time": "Tue Jul 05 14:13:41 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jul 05 14:13:41 2005 -0700" }, "message": "[NET]: Reduce size of sk_buff by 4 bytes\n\nReduce local_df to a bit field and ip_summed to a 2 bits\nfield thus saving 13 bits. Move bit fields, packet type,\nand protocol into the spare area between the priority\nand the destructor. Saves 4 bytes on both, 32bit and\n64bit architectures.\n\nSigned-off-by: Thomas Graf \u003ctgraf@suug.ch\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "e176fe8954a5239c24afe79b1001ba3c29511963", "tree": "418038ddda59950ac83decb708f25cd612d0ffe0", "parents": [ "3154e540e374bbfd62693d95bc8ed51da95efe75" ], "author": { "name": "Thomas Graf", "email": "tgraf@suug.ch", "time": "Tue Jul 05 14:12:44 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jul 05 14:12:44 2005 -0700" }, "message": "[NET]: Remove unused security member in sk_buff\n\nSigned-off-by: Thomas Graf \u003ctgraf@suug.ch\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "55820ee2f8c767a2833b21bd365e5753f50bd8ce", "tree": "fbf89b8f1365c18c5c2ee0fad15f61f6f3127af8", "parents": [ "17af691cd19765b782d891fc50c1568d0f1276b3" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Tue Jul 05 14:08:10 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jul 05 14:08:10 2005 -0700" }, "message": "[NET]: Fix signedness issues in net/core/filter.c\n\nThis is the code to load packet data into a register:\n\n k \u003d fentry-\u003ek;\n if (k \u003c 0) {\n...\n } else {\n u32 _tmp, *p;\n p \u003d skb_header_pointer(skb, k, 4, \u0026_tmp);\n if (p !\u003d NULL) {\n A \u003d ntohl(*p);\n continue;\n }\n }\n\nskb_header_pointer checks if the requested data is within the\nlinear area:\n\n int hlen \u003d skb_headlen(skb);\n\n if (offset + len \u003c\u003d hlen)\n return skb-\u003edata + offset;\n\nWhen offset is within [INT_MAX-len+1..INT_MAX] the addition will\nresult in a negative number which is \u003c\u003d hlen.\n\nI couldn\u0027t trigger a crash on my AMD64 with 2GB of memory, but a\ncoworker tried on his x86 machine and it crashed immediately.\n\nThis patch fixes the check in skb_header_pointer to handle large\npositive offsets similar to skb_copy_bits. Invalid data can still\nbe accessed using negative offsets (also similar to skb_copy_bits),\nanyone using negative offsets needs to verify them himself.\n\nThanks to Thomas Vögtle \u003cthomas.voegtle@coreworks.de\u003e for verifying the\nproblem by crashing his machine and providing me with an Oops.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nAcked-by: Herbert Xu \u003cherbert@gondor.apana.org.au\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "3fc7e8a6d842f72d16d2623b1022814a635ab961", "tree": "93f60c9af99b790c1d79bef1d3414fea3d7b9c5c", "parents": [ "677e90eda3bd8cfde0b748daaa46476162a03950" ], "author": { "name": "Thomas Graf", "email": "tgraf@suug.ch", "time": "Thu Jun 23 21:00:17 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jun 23 21:00:17 2005 -0700" }, "message": "[NET]: skb_find_text() - Find a text pattern in skb data\n\nFinds a pattern in the skb data according to the specified\ntextsearch configuration. Use textsearch_next() to retrieve\nsubsequent occurrences of the pattern. Returns the offset\nto the first occurrence or UINT_MAX if no match was found.\n\nSigned-off-by: Thomas Graf \u003ctgraf@suug.ch\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "677e90eda3bd8cfde0b748daaa46476162a03950", "tree": "4b40614cf9cd125883d0430467be9172997ca184", "parents": [ "6408f79cce401e1bfecf923e7156f84f96e021e3" ], "author": { "name": "Thomas Graf", "email": "tgraf@suug.ch", "time": "Thu Jun 23 20:59:51 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jun 23 20:59:51 2005 -0700" }, "message": "[NET]: Zerocopy sequential reading of skb data\n\nImplements sequential reading for both linear and non-linear\nskb data at zerocopy cost. The data is returned in chunks of\narbitary length, therefore random access is not possible.\n\nUsage:\n\tfrom\t :\u003d 0\n\tto\t :\u003d 128\n\tstate\t :\u003d undef\n\tdata\t :\u003d undef\n\tlen\t :\u003d undef\n\tconsumed :\u003d 0\n\n\tskb_prepare_seq_read(skb, from, to, \u0026state)\n\twhile (len \u003d skb_seq_read(consumed, \u0026data, \u0026state)) !\u003d 0 do\n\t\t/* do something with \u0027data\u0027 of length \u0027len\u0027 */\n\t\tif abort then\n\t\t\t/* abort read if we don\u0027t wait for\n\t\t\t * skb_seq_read() to return 0 */\n\t\t\tskb_abort_seq_read(\u0026state)\n\t\t\treturn\n\t\tendif\n\t\t/* not necessary to consume all of \u0027len\u0027 */\n\t\tconsumed +\u003d len\n\tdone\n\nSigned-off-by: Thomas Graf \u003ctgraf@suug.ch\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "18b8afc771102b1b6af97962808291a7d27f52af", "tree": "4d278a45ab07b5ba81dfa0b737f5174ad9ee7f79", "parents": [ "e45b1be8bcb3643808975a426fa3e201a2588e87" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Tue Jun 21 14:01:57 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jun 21 14:01:57 2005 -0700" }, "message": "[NETFILTER]: Kill nf_debug\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "67be2dd1bace0ec7ce2dbc1bba3f8df3d7be597e", "tree": "317d114a0288d3b19ef9902f94b536a5a8731dbd", "parents": [ "6013d5445f9a6d0b28090027868f455c5012d1cc" ], "author": { "name": "Martin Waitz", "email": "tali@admingilde.org", "time": "Sun May 01 08:59:26 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sun May 01 08:59:26 2005 -0700" }, "message": "[PATCH] DocBook: fix some descriptions\n\nSome KernelDoc descriptions are updated to match the current code.\nNo code changes.\n\nSigned-off-by: Martin Waitz \u003ctali@admingilde.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "4dc3b16ba18c0f967ad100c52fa65b01a4f76ff0", "tree": "fa038ad8969980eec6cef5b737872fda9feb4c6a", "parents": [ "333f981720d619e2038b980a55ad01b10580eb9f" ], "author": { "name": "Pavel Pisa", "email": "pisa@cmp.felk.cvut.cz", "time": "Sun May 01 08:59:25 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sun May 01 08:59:25 2005 -0700" }, "message": "[PATCH] DocBook: changes and extensions to the kernel documentation\n\nI have recompiled Linux kernel 2.6.11.5 documentation for me and our\nuniversity students again. The documentation could be extended for more\nsources which are equipped by structured comments for recent 2.6 kernels. I\nhave tried to proceed with that task. I have done that more times from 2.6.0\ntime and it gets boring to do same changes again and again. Linux kernel\ncompiles after changes for i386 and ARM targets. I have added references to\nsome more files into kernel-api book, I have added some section names as well.\n So please, check that changes do not break something and that categories are\nnot too much skewed.\n\nI have changed kernel-doc to accept \"fastcall\" and \"asmlinkage\" words reserved\nby kernel convention. Most of the other changes are modifications in the\ncomments to make kernel-doc happy, accept some parameters description and do\nnot bail out on errors. Changed \u003cpid\u003e to @pid in the description, moved some\n#ifdef before comments to correct function to comments bindings, etc.\n\nYou can see result of the modified documentation build at\n http://cmp.felk.cvut.cz/~pisa/linux/lkdb-2.6.11.tar.gz\n\nSome more sources are ready to be included into kernel-doc generated\ndocumentation. Sources has been added into kernel-api for now. Some more\nsection names added and probably some more chaos introduced as result of quick\ncleanup work.\n\nSigned-off-by: Pavel Pisa \u003cpisa@cmp.felk.cvut.cz\u003e\nSigned-off-by: Martin Waitz \u003ctali@admingilde.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "9c2b3328f74800bb370d08bb3a4255d5fe833e94", "tree": "9d3092a44b592a091c4818a20bd678d1191f7a88", "parents": [ "98f245e797a01611d6734c7d192240f1361439d3" ], "author": { "name": "Stephen Hemminger", "email": "shemminger@osdl.org", "time": "Tue Apr 19 22:39:42 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Apr 19 22:39:42 2005 -0700" }, "message": "[NET]: skbuff: remove old NET_CALLER macro\n\nHere is a revised alternative that uses BUG_ON/WARN_ON\n(as suggested by Herbert Xu) to eliminate NET_CALLER.\n\nSigned-off-by: Stephen Hemminger \u003cshemminger@osdl.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "357b40a18b04c699da1d45608436e9b76b50e251", "tree": "51c4480c9508a911d52a3f69bbe84ec1191fd202", "parents": [ "fd92833a52b972aafacced959f4a3f7541936a9b" ], "author": { "name": "Herbert Xu", "email": "herbert@gondor.apana.org.au", "time": "Tue Apr 19 22:30:14 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Apr 19 22:30:14 2005 -0700" }, "message": "[IPV6]: IPV6_CHECKSUM socket option can corrupt kernel memory\n\nSo here is a patch that introduces skb_store_bits -- the opposite of\nskb_copy_bits, and uses them to read/write the csum field in rawv6.\n\nSigned-off-by: Herbert Xu \u003cherbert@gondor.apana.org.au\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1da177e4c3f41524e886b7f1b8a0c1fc7321cac2", "tree": "0bba044c4ce775e45a88a51686b5d9f90697ea9d", "parents": [], "author": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "message": "Linux-2.6.12-rc2\n\nInitial git repository build. I\u0027m not bothering with the full history,\neven though we have it. We can create a separate \"historical\" git\narchive of that later if we want to, and in the meantime it\u0027s about\n3.2GB when imported into git - space that would just make the early\ngit days unnecessarily complicated, when we don\u0027t have a lot of good\ninfrastructure for it.\n\nLet it rip!\n" } ] }