)]}' { "log": [ { "commit": "58fc2ea4057511f84deaa182b1a3612327ecbf2d", "tree": "e618b9cb73831595a7bac9418497f8479ae2a790", "parents": [ "df149d70e1f34ec4995c8a703dbde38071ff4a05" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sat Jul 07 22:52:02 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:38 2007 -0700" }, "message": "[BNX2]: Print management firmware version.\n\nAdd management firmware version for ethtool -i.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "df149d70e1f34ec4995c8a703dbde38071ff4a05", "tree": "09103d4b997158202370619f5a1492a69f85e7af", "parents": [ "b8a7ce7bedb2134acb731e08e588ad92087a40ff" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sat Jul 07 22:51:36 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:36 2007 -0700" }, "message": "[BNX2]: Enhance the heartbeat.\n\nIn addition to the periodic heartbeat, we\u0027re adding a heartbeat\nrequest interrupt when the heartbeat is late. This is needed during\nnetpoll where the timer is not available. -rt kernels will also\nbenefit since the timer is not as accurate.\n\n[ We discussed this patch last time and we decided that the -rt\n kernel problem alone did not justify this patch. I think the\n netpoll problem makes this patch necessary. ]\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b8a7ce7bedb2134acb731e08e588ad92087a40ff", "tree": "2d18138f5c9697f71861c37f94aa2e7cbfc5228b", "parents": [ "9b1084b8f99a6b5e97c0c9bc1b4455db4fa51a07" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sat Jul 07 22:51:03 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:35 2007 -0700" }, "message": "[BNX2]: Reduce spurious INTA interrupts.\n\nSpurious interrupts are often encountered especially on systems\nusing the 8259 PIC mode. This is because the I/O write to deassert\nthe interrupt is posted and won\u0027t get to the chip immediately. As\na result, the IRQ may remain asserted after the IRQ handler exits,\ncausing spurious interrupts.\n\nAdd read back to flush the I/O write to deassert the IRQ immediately.\nWe also store the last_status_idx immediately in the IRQ handler to\nhelp detect whether the interrupt is ours or not when the IRQ is\nentered again before -\u003epoll gets called.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "9b1084b8f99a6b5e97c0c9bc1b4455db4fa51a07", "tree": "43db5eeb705032e8a4596d13d98c2ad6df92b56b", "parents": [ "7b6b83474cb9bdd07dadfb7497a29c3005ad9d1d" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sat Jul 07 22:50:37 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:34 2007 -0700" }, "message": "[BNX2]: Modify link up message.\n\nModify the link up dmesg to report remote copper or Serdes link.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "7b6b83474cb9bdd07dadfb7497a29c3005ad9d1d", "tree": "64fbf2a9c6a28f6f5e041b1da65b0cd12335a8c4", "parents": [ "0d8a6571051d23c214d7a316976138a6fd8bda1c" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sat Jul 07 22:50:15 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:33 2007 -0700" }, "message": "[BNX2]: Add ethtool support for remote PHY.\n\nModify the driver\u0027s ethtool_ops-\u003eget_settings and set_settings\nfunctions to support remote PHY. Users control the remote copper\nPHY settings by specifying link settings for the tp (twisted pair)\nport.\n\nThe nway_reset function is also modified to support remote PHY.\nmii-tool operations are not supported on remote PHY and we will\nreturn -EOPNOTSUPP.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0d8a6571051d23c214d7a316976138a6fd8bda1c", "tree": "cd69431666decde690d03970bc54b5cce9b36303", "parents": [ "9700e6befea505b03b6e625536a9a106811e9a14" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sat Jul 07 22:49:43 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:32 2007 -0700" }, "message": "[BNX2]: Add support for remote PHY.\n\nIn blade servers, the Serdes PHY in 5708S can control the remote\ncopper PHY through autonegotiation on the backplane. This patch adds\nthe logic to interface with the firmware to control the remote PHY\nautonegotiation and to handle remote PHY link events.\n\nWhen remote PHY is present, the 5708S Serdes device practically\nbecomes a copper device with full control over the 1000Base-T\nlink settings.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "9700e6befea505b03b6e625536a9a106811e9a14", "tree": "a3cb01457f6c060d16eab10752c074310ff46bae", "parents": [ "deaf391b4cc9d9f8e2b2793ebd56da776b54197a" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sat Jul 07 22:48:31 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:31 2007 -0700" }, "message": "[BNX2]: Add remote PHY bit definitions.\n\nAdd new fields in struct bnx2 and other bit definitions in shared\nmemory to support remote PHY.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "deaf391b4cc9d9f8e2b2793ebd56da776b54197a", "tree": "f834c1aae99c9d97eea7393286d91e5c3e43b13a", "parents": [ "5faf41535214b68c989a22302c8870f8758cbb8c" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sat Jul 07 22:48:00 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:30 2007 -0700" }, "message": "[BNX2]: Add bnx2_set_default_link().\n\nPut existing code to setup the default link settings in this new\nfunction. This makes it easier to support the remote PHY feature in\nthe next few patches.\n\nAlso change ETHTOOL_ALL_FIBRE_SPEED to include 2500Mbps if supported.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5faf41535214b68c989a22302c8870f8758cbb8c", "tree": "00a39404ff44b222436290193101651fb7ceed24", "parents": [ "585426fdc5b4cccaacf0afc8cf821ff763750ae8" ], "author": { "name": "Balazs Scheidler", "email": "bazsi@balabit.hu", "time": "Sat Jul 07 22:41:01 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:29 2007 -0700" }, "message": "[NETFILTER]: x_tables: add more detail to error message about match/target mask mismatch\n\nSigned-off-by: Balazs Scheidler \u003cbazsi@balabit.hu\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "585426fdc5b4cccaacf0afc8cf821ff763750ae8", "tree": "6dfaf7fc842003a33c89872cf6c1a96932c57f14", "parents": [ "ce7663d84a87bb4e1743f62950bf7dceed723a13" ], "author": { "name": "Yasuyuki Kozakai", "email": "yasuyuki.kozakai@toshiba.co.jp", "time": "Sat Jul 07 22:40:26 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:28 2007 -0700" }, "message": "[NETFILTER]: nf_queue: Use RCU and mutex for queue handlers\n\nQueue handlers are registered/unregistered in only process context.\n\nSigned-off-by: Yasuyuki Kozakai \u003cyasuyuki.kozakai@toshiba.co.jp\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ce7663d84a87bb4e1743f62950bf7dceed723a13", "tree": "3c1b16e33913199da3181b92ed7dc0fbb6e0aa64", "parents": [ "0d53778e81ac7af266dac8a20cc328328c327112" ], "author": { "name": "Yasuyuki Kozakai", "email": "yasuyuki.kozakai@toshiba.co.jp", "time": "Sat Jul 07 22:40:08 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:21 2007 -0700" }, "message": "[NETFILTER]: nfnetlink_queue: don\u0027t unregister handler of other subsystem\n\nThe queue handlers registered by ip[6]_queue.ko at initialization should\nnot be unregistered according to requests from userland program\nusing nfnetlink_queue. If we allow that, there is no way to register\nthe handlers of built-in ip[6]_queue again.\n\nSigned-off-by: Yasuyuki Kozakai \u003cyasuyuki.kozakai@toshiba.co.jp\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0d53778e81ac7af266dac8a20cc328328c327112", "tree": "034226154ea7c3466a31ef2d57b5a600d4a106e6", "parents": [ "342b7e3c8a3c84252799c4ac4d9a604b8903d2b4" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:39:38 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:20 2007 -0700" }, "message": "[NETFILTER]: Convert DEBUGP to pr_debug\n\nConvert DEBUGP to pr_debug and fix lots of non-compiling debug statements.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "342b7e3c8a3c84252799c4ac4d9a604b8903d2b4", "tree": "c61ffbcbf24287df26a6dfc58684630289669c7f", "parents": [ "91e8db80065d655ce1b6d74cadc921671e8d5285" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:39:16 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:19 2007 -0700" }, "message": "[NETFILTER]: xt_helper: use RCU\n\nThe -\u003ehelper pointer is protected by RCU, no need to take\nnf_conntrack_lock. Also remove excessive debugging.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "91e8db80065d655ce1b6d74cadc921671e8d5285", "tree": "c1368bd66a32c17cb7638082ca003ebf7461f63a", "parents": [ "d3c3f4243e135b3d8c41d98be0cb2f54a4141abf" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:38:54 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:18 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack_h323: turn some printks into DEBUGPs\n\nDon\u0027t spam the ringbuffer with decoding errors. The only printks remaining\nare for dropped packets when we\u0027re certain they are H.323.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d3c3f4243e135b3d8c41d98be0cb2f54a4141abf", "tree": "082b4108551892eecffa8ce9dab555827540183d", "parents": [ "3569b621ceba0a9cfb80e24c0bd19fd632ccee25" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:38:30 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:17 2007 -0700" }, "message": "[NETFILTER]: ipt_CLUSTERIP: add compat code\n\nAdjust structure size and don\u0027t expect pointers passed in from\nuserspace to be valid. Also replace an enum in an ABI structure\nby a fixed size type.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "3569b621ceba0a9cfb80e24c0bd19fd632ccee25", "tree": "becb6abd925950e4a57d98d3e42968c736a2def4", "parents": [ "7ae7730fd6d98be1afe8ad9ea77813de607ec970" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:38:07 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:16 2007 -0700" }, "message": "[NETFILTER]: ipt_SAME: add to feature-removal-schedule\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "7ae7730fd6d98be1afe8ad9ea77813de607ec970", "tree": "cb0cebe96de34a5d6116e4f76377e6ef4ca43547", "parents": [ "ec59a1110aee6846adada8979915cacae64042ce" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:37:38 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:15 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack: early_drop improvement\n\nWhen the maximum number of conntrack entries is reached and a new\none needs to be allocated, conntrack tries to drop an unassured\nconnection from the same hash bucket the new conntrack would hash\nto. Since with a properly sized hash the average number of entries\nper bucket is 1, the chances of actually finding one are not very\ngood. This patch makes it walk the hash until a minimum number of\n8 entries are checked.\n\nBased on patch by Vasily Averin \u003cvvs@sw.ru\u003e.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ec59a1110aee6846adada8979915cacae64042ce", "tree": "b4a19d1a84fd0f46e2f1f112f27ea716d819ff29", "parents": [ "b8a7fe6c10511fce10b20efa163123f4041f2550" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:37:03 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:14 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack: mark helpers __read_mostly\n\nMost are __read_mostly already, this changes the remaining ones.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b8a7fe6c10511fce10b20efa163123f4041f2550", "tree": "a2e864f2dee638a08a02801320dc3700b4ed9cad", "parents": [ "f264a7df08d50bb4a23be6a9aa06940e497ac1c4" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:36:46 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:13 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack_helper: use hashtable for conntrack helpers\n\nEliminate the last global list searched for every new connection.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f264a7df08d50bb4a23be6a9aa06940e497ac1c4", "tree": "c07c92616a50107c2dacc5836626d4b6a12c57ae", "parents": [ "b560580a13b180bc1e3cad7ffbc93388cc39be5d" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:36:24 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:12 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack_expect: introduce nf_conntrack_expect_max sysct\n\nAs a last step of preventing DoS by creating lots of expectations, this\npatch introduces a global maximum and a sysctl to control it. The default\nis initialized to 4 * the expectation hash table size, which results in\n1/64 of the default maxmimum of conntracks.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b560580a13b180bc1e3cad7ffbc93388cc39be5d", "tree": "9ad6fd7a93c75ef4776239b4f43bde27737aa04b", "parents": [ "31f15875c5ad98a13b528aaf19c839e22b43dc9a" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:35:56 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:02 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack_expect: maintain per conntrack expectation list\n\nThis patch brings back the per-conntrack expectation list that was\nremoved around 2.6.10 to avoid walking all expectations on expectation\neviction and conntrack destruction.\n\nAs these were the last users of the global expectation list, this patch\nalso kills that.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "31f15875c5ad98a13b528aaf19c839e22b43dc9a", "tree": "3ede173710f42917ed228a2494af3b891a7ff4cf", "parents": [ "5d08ad440feae11b8d6e7599147a8a20ac60f99a" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:35:21 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:01 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack_helper/nf_conntrack_netlink: convert to expectation hash\n\nConvert from the global expectation list to the hash table.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5d08ad440feae11b8d6e7599147a8a20ac60f99a", "tree": "41043588598c7dae1b1edecaac3764924f0cf3bf", "parents": [ "a71c085562bcc99e8b711cab4222bff1f6e955da" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:34:07 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:00 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack_expect: convert proc functions to hash\n\nConvert from the global expectation list to the hash table.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a71c085562bcc99e8b711cab4222bff1f6e955da", "tree": "7de563d406e8e9e44065b53c664f837f97f8b3fe", "parents": [ "e9c1b084e17ca225b6be731b819308ee0f9e04b8" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:33:47 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:59 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack: use hashtable for expectations\n\nCurrently all expectations are kept on a global list that\n\n- needs to be searched for every new conncetion\n- needs to be walked for evicting expectations when a master connection\n has reached its limit\n- needs to be walked on connection destruction for connections that\n have open expectations\n\nThis is obviously not good, especially when considering helpers like\nH.323 that register *lots* of expectations and can set up permanent\nexpectations, but it also allows for an easy DoS against firewalls\nusing connection tracking helpers.\n\nUse a hashtable for expectations to avoid incurring the search overhead\nfor every new connection. The default hash size is 1/256 of the conntrack\nhash table size, this can be overriden using a module parameter.\n\nThis patch only introduces the hash table for expectation lookups and\nkeeps other users to reduce the noise, the following patches will get\nrid of it completely.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "e9c1b084e17ca225b6be731b819308ee0f9e04b8", "tree": "f2cb1ee43873b5c6bc6eb54a9b450f0409afcf05", "parents": [ "cf6994c2b9812a9f02b99e89df411ffc5db9c779" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:32:53 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:58 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack: move expectaton related init code to nf_conntrack_expect.c\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cf6994c2b9812a9f02b99e89df411ffc5db9c779", "tree": "60cd51886db3d35080c6eea8b4b5ba437293bb42", "parents": [ "4e1d4e6c5a448bd114e0cef6311c974cb7c7385e" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:32:34 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:57 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack_netlink: sync expectation dumping with conntrack table dumping\n\nResync expectation table dumping code with conntrack dumping: don\u0027t\nrely on the unique ID anymore since that requires to walk the list\nbackwards, which doesn\u0027t work with the upcoming conversion to hlists.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4e1d4e6c5a448bd114e0cef6311c974cb7c7385e", "tree": "aa785c5d14b7796de154872a754ae9e25df6650b", "parents": [ "d4156e8cd93f5772483928aaf4960120caebd789" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:32:03 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:56 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack_expect: avoid useless list walking\n\nDon\u0027t walk the list when unexpecting an expectation, we already\nhave a reference and the timer check is enough to guarantee\nthat it still is on the list.\n\nThis comment suggests that it was copied there by mistake from\nexpectation eviction:\n\n/* choose the oldest expectation to evict */\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d4156e8cd93f5772483928aaf4960120caebd789", "tree": "e740e629df29d8ea1ad21244998851362b64a70e", "parents": [ "df43b4e7ca46952756b2fc039ed80469b1bff62d" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:31:32 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:55 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack: reduce masks to a subset of tuples\n\nSince conntrack currently allows to use masks for every bit of both\nhelper and expectation tuples, we can\u0027t hash them and have to keep\nthem on two global lists that are searched for every new connection.\n\nThis patch removes the never used ability to use masks for the\ndestination part of the expectation tuple and completely removes\nmasks from helpers since the only reasonable choice is a full\nmatch on l3num, protonum and src.u.all.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "df43b4e7ca46952756b2fc039ed80469b1bff62d", "tree": "84fed9a5fafb0dec8695985b1db150e9b879f9eb", "parents": [ "6823645d608541c2c69e8a99454936e058c294e0" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:31:07 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:54 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack_ftp: use nf_ct_expect_init\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "6823645d608541c2c69e8a99454936e058c294e0", "tree": "e7b8b9200b4b03b7b787fc55f92c37c19076c225", "parents": [ "53aba5979e1d964c0234816eda2316f1c2e7946d" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:30:49 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:53 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack_expect: function naming unification\n\nCurrently there is a wild mix of nf_conntrack_expect_, nf_ct_exp_,\nexpect_, exp_, ...\n\nConsistently use nf_ct_ as prefix for exported functions.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "53aba5979e1d964c0234816eda2316f1c2e7946d", "tree": "042b0528b82f119d2a452c0e2a448f1d4d04fb14", "parents": [ "ac565e5fc104fe1842a87f2206fcfb7b6dda903d" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:30:27 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:43 2007 -0700" }, "message": "[NETFILTER]: nf_nat: use hlists for bysource hash\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ac565e5fc104fe1842a87f2206fcfb7b6dda903d", "tree": "6d5241eb5b8061cfd2019977dcd619c2797a06ab", "parents": [ "330f7db5e578e1e298ba3a41748e5ea333a64a2b" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:30:08 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:42 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack: export hash allocation/destruction functions\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "330f7db5e578e1e298ba3a41748e5ea333a64a2b", "tree": "1557656cf800dcee7915cb41c94d4ce644947c61", "parents": [ "f205c5e0c28aa7e0fb6eaaa66e97928f9d9e6994" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:28:42 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:41 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack: remove \u0027ignore_conntrack\u0027 argument from nf_conntrack_find_get\n\nAll callers pass NULL, this also doesn\u0027t seem very useful for modules.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f205c5e0c28aa7e0fb6eaaa66e97928f9d9e6994", "tree": "7ad04d827c5c2d24ac804346d95853ebceab0bfd", "parents": [ "8e5105a0c36a059dfd0f0bb9e73ee7c97d306247" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:28:14 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:40 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack: use hlists for conntrack hash\n\nConvert conntrack hash to hlists to reduce its size and cache\nfootprint. Since the default hashsize to max. entries ratio\nsucks (1:16), this patch doesn\u0027t reduce the amount of memory\nused for the hash by default, but instead uses a better ratio\nof 1:8, which results in the same max. entries value.\n\nOne thing worth noting is early_drop. It really should use LRU,\nso it now has to iterate over the entire chain to find the last\nunconfirmed entry. Since chains shouldn\u0027t be very long and the\nentire operation is very rare this shouldn\u0027t be a problem.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "8e5105a0c36a059dfd0f0bb9e73ee7c97d306247", "tree": "b1bdbfeaa011544a3e1a5b3e44eca4bdd0bb8f7e", "parents": [ "61eb3107cd8e0302f95aae26206e552365daf290" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:27:33 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:39 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack: round up hashsize to next multiple of PAGE_SIZE\n\nDon\u0027t let the rest of the page go to waste.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "61eb3107cd8e0302f95aae26206e552365daf290", "tree": "611a85cac1cb7540944b7e1779cb4f4ab846cf69", "parents": [ "b6b84d4a94e95727a4c65841eea23ac60c6aa329" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:27:06 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:38 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack_extend: use __read_mostly for struct nf_ct_ext_type\n\nAlso make them static.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b6b84d4a94e95727a4c65841eea23ac60c6aa329", "tree": "b24f89ef0ea4542bf884a2a3eb73f7d479460eae", "parents": [ "d8a0509a696de60296a66ba4fe4f9eaade497103" ], "author": { "name": "Yasuyuki Kozakai", "email": "yasuyuki.kozakai@toshiba.co.jp", "time": "Sat Jul 07 22:26:35 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:37 2007 -0700" }, "message": "[NETFILTER]: nf_nat: merge nf_conn and nf_nat_info\n\nSigned-off-by: Yasuyuki Kozakai \u003cyasuyuki.kozakai@toshiba.co.jp\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d8a0509a696de60296a66ba4fe4f9eaade497103", "tree": "6aa00195176f8cd05221e356877ec83d0aa0536c", "parents": [ "dacd2a1a5cf621288833aa3c6e815b86a1536538" ], "author": { "name": "Yasuyuki Kozakai", "email": "yasuyuki.kozakai@toshiba.co.jp", "time": "Sat Jul 07 22:26:16 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:36 2007 -0700" }, "message": "[NETFILTER]: nf_nat: kill global \u0027destroy\u0027 operation\n\nThis kills the global \u0027destroy\u0027 operation which was used by NAT.\nInstead it uses the extension infrastructure so that multiple\nextensions can register own operations.\n\nSigned-off-by: Yasuyuki Kozakai \u003cyasuyuki.kozakai@toshiba.co.jp\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "dacd2a1a5cf621288833aa3c6e815b86a1536538", "tree": "c615b95aa1518c6518df35acd481ed4af19acd61", "parents": [ "ff09b7493c8f433d3ffd6a31ad58d190f82ef0c5" ], "author": { "name": "Yasuyuki Kozakai", "email": "yasuyuki.kozakai@toshiba.co.jp", "time": "Sat Jul 07 22:25:51 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:35 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack: remove old memory allocator of conntrack\n\nNow memory space for help and NAT are allocated by extension\ninfrastructure.\n\nSigned-off-by: Yasuyuki Kozakai \u003cyasuyuki.kozakai@toshiba.co.jp\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ff09b7493c8f433d3ffd6a31ad58d190f82ef0c5", "tree": "8c9f1b55f9f0d97543c3751220dc91ab75895072", "parents": [ "2d59e5ca8c7113ad91452f0f9259a4b55ee90323" ], "author": { "name": "Yasuyuki Kozakai", "email": "yasuyuki.kozakai@toshiba.co.jp", "time": "Sat Jul 07 22:25:28 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:34 2007 -0700" }, "message": "[NETFILTER]: nf_nat: remove unused nf_nat_module_is_loaded\n\nSigned-off-by: Yasuyuki Kozakai \u003cyasuyuki.kozakai@toshiba.co.jp\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "2d59e5ca8c7113ad91452f0f9259a4b55ee90323", "tree": "16ffd5284bb5462eaa3af285977389afefca54ca", "parents": [ "e54cbc1f91dea4f98b6209e693d3b5eae46321bd" ], "author": { "name": "Yasuyuki Kozakai", "email": "yasuyuki.kozakai@toshiba.co.jp", "time": "Sat Jul 07 22:24:28 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:20 2007 -0700" }, "message": "[NETFILTER]: nf_nat: use extension infrastructure\n\nSigned-off-by: Yasuyuki Kozakai \u003cyasuyuki.kozakai@toshiba.co.jp\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "e54cbc1f91dea4f98b6209e693d3b5eae46321bd", "tree": "4441dfea2c4cef6687fc9664d1b72683f5bc1ef0", "parents": [ "ceceae1b1555a9afcb8dacf90df5fa1f20fd5466" ], "author": { "name": "Yasuyuki Kozakai", "email": "yasuyuki.kozakai@toshiba.co.jp", "time": "Sat Jul 07 22:24:04 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:19 2007 -0700" }, "message": "[NETFILTER]: nf_nat: add reference to conntrack from entry of bysource list\n\nI will split \u0027struct nf_nat_info\u0027 out from conntrack. So I cannot use\n\u0027offsetof\u0027 to get the pointer to conntrack from it.\n\nSigned-off-by: Yasuyuki Kozakai \u003cyasuyuki.kozakai@toshiba.co.jp\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ceceae1b1555a9afcb8dacf90df5fa1f20fd5466", "tree": "008841923a297be92566c8da42f516ffe6c2cdc1", "parents": [ "ecfab2c9fe5597221c2b30dec48634a2361a0d08" ], "author": { "name": "Yasuyuki Kozakai", "email": "yasuyuki.kozakai@toshiba.co.jp", "time": "Sat Jul 07 22:23:42 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:18 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack: use extension infrastructure for helper\n\nSigned-off-by: Yasuyuki Kozakai \u003cyasuyuki.kozakai@toshiba.co.jp\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ecfab2c9fe5597221c2b30dec48634a2361a0d08", "tree": "5640796c698074105430c1c1bc24df87f4d0a6b4", "parents": [ "4ba887790ce2015e8c464809c0be902fb813ad15" ], "author": { "name": "Yasuyuki Kozakai", "email": "yasuyuki.kozakai@toshiba.co.jp", "time": "Sat Jul 07 22:23:21 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:17 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack: introduce extension infrastructure\n\nOld space allocator of conntrack had problems about extensibility.\n- It required slab cache per combination of extensions.\n- It expected what extensions would be assigned, but it was impossible\n to expect that completely, then we allocated bigger memory object than\n really required.\n- It needed to search helper twice due to lock issue.\n\nNow basic informations of a connection are stored in \u0027struct nf_conn\u0027.\nAnd a storage for extension (helper, NAT) is allocated by kmalloc.\n\nSigned-off-by: Yasuyuki Kozakai \u003cyasuyuki.kozakai@toshiba.co.jp\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4ba887790ce2015e8c464809c0be902fb813ad15", "tree": "0373b274e64a4b70415cd59f2cb6270762aa55b4", "parents": [ "9f15c5302de4e8b0aac7ca24c36bf26a7fe1a513" ], "author": { "name": "Yasuyuki Kozakai", "email": "yasuyuki.kozakai@toshiba.co.jp", "time": "Sat Jul 07 22:22:33 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:16 2007 -0700" }, "message": "[NETFILTER]: nf_nat: move NAT declarations from nf_conntrack_ipv4.h to nf_nat.h\n\nSigned-off-by: Yasuyuki Kozakai \u003cyasuyuki.kozakai@toshiba.co.jp\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "9f15c5302de4e8b0aac7ca24c36bf26a7fe1a513", "tree": "f9bf5883558941b1ad519f02106f53eefc90ba38", "parents": [ "ba9dda3ab5a865542e69dfe01edb2436857c9420" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jul 07 22:22:02 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:15 2007 -0700" }, "message": "[NETFILTER]: x_tables: mark matches and targets __read_mostly\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ba9dda3ab5a865542e69dfe01edb2436857c9420", "tree": "93f92442a8ad134d78b4d7cd8dc74e089baef3d7", "parents": [ "1b50b8a371e90a5e110f466e4ac02cf6b5f681de" ], "author": { "name": "Jozsef Kadlecsik", "email": "kadlec@blackhole.kfki.hu", "time": "Sat Jul 07 22:21:23 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:14 2007 -0700" }, "message": "[NETFILTER]: x_tables: add TRACE target\n\nThe TRACE target can be used to follow IP and IPv6 packets through\nthe ruleset.\n\nSigned-off-by: Jozsef Kadlecsik \u003ckadlec@blackhole.kfki.hu\u003e\nSigned-off-by: Patrick NcHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1b50b8a371e90a5e110f466e4ac02cf6b5f681de", "tree": "edf2513fbfd707a089691487c007c142417ad3a1", "parents": [ "f4a607bfae30d15aad46e75d2ed7a39f7ce7708b" ], "author": { "name": "Jan Engelhardt", "email": "jengelh@gmx.de", "time": "Sat Jul 07 22:20:36 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:13 2007 -0700" }, "message": "[NETFILTER]: Add u32 match\n\nAlong comes... xt_u32, a revamped ipt_u32 from POM-NG,\nPlus:\n\n *\t2007-06-02: added ipv6 support\n\n *\t2007-06-05: uses kmalloc for the big buffer\n\n * 2007-06-05: added inversion\n\n * 2007-06-20: use skb_copy_bits() and get rid of the big buffer\n and lock (suggested by Pablo Neira Ayuso)\n\nSigned-off-by: Jan Engelhardt \u003cjengelh@gmx.de\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f4a607bfae30d15aad46e75d2ed7a39f7ce7708b", "tree": "aefe93235430427833e0eed936ca80a991d9df0d", "parents": [ "7c4e36bc172ae1accde835b880fdc4a2c2a3df57" ], "author": { "name": "Jerome Borsboom", "email": "j.borsboom@erasmusmc.nl", "time": "Sat Jul 07 22:19:48 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:12 2007 -0700" }, "message": "[NETFILTER]: nf_nat_sip: only perform RTP DNAT if SIP session was SNATed\n\nDNAT of the the RTP session is only necessary if the SIP session has\nbeen SNATed.\n\nSigned-off-by: Jerome Borsboom \u003cj.borsboom@erasmusmc.nl\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "7c4e36bc172ae1accde835b880fdc4a2c2a3df57", "tree": "e89d34ec33180a75fd15cc07e7d81ec9a7d4f5a4", "parents": [ "170b197c0afc621179f0f82284e331e3c252b7cf" ], "author": { "name": "Jan Engelhardt", "email": "jengelh@gmx.de", "time": "Sat Jul 07 22:19:08 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:11 2007 -0700" }, "message": "[NETFILTER]: Remove redundant parentheses/braces\n\nRemoves redundant parentheses and braces (And add one pair in a\nxt_tcpudp.c macro).\n\nSigned-off-by: Jan Engelhardt \u003cjengelh@gmx.de\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "170b197c0afc621179f0f82284e331e3c252b7cf", "tree": "5a32d18b0c2251a0aec6eb2992c66739e2e2e3fa", "parents": [ "a47362a226456d8db8207e618324a2278d05d3a7" ], "author": { "name": "Jan Engelhardt", "email": "jengelh@gmx.de", "time": "Sat Jul 07 22:17:36 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:02 2007 -0700" }, "message": "[NETFILTER]: Remove incorrect inline markers\n\ndevice_cmp: the function\u0027s address is taken (call to nf_ct_iterate_cleanup)\nalloc_null_binding: referenced externally\n\nSigned-off-by: Jan Engelhardt \u003cjengelh@gmx.de\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a47362a226456d8db8207e618324a2278d05d3a7", "tree": "9431e971844582fd65a8cdd234cf89d72c6e4c6c", "parents": [ "e1931b784a8de324abf310fa3b5e3f25d3988233" ], "author": { "name": "Jan Engelhardt", "email": "jengelh@gmx.de", "time": "Sat Jul 07 22:16:55 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:17:01 2007 -0700" }, "message": "[NETFILTER]: add some consts, remove some casts\n\nMake a number of variables const and/or remove unneeded casts.\n\nSigned-off-by: Jan Engelhardt \u003cjengelh@gmx.de\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "e1931b784a8de324abf310fa3b5e3f25d3988233", "tree": "3f553c7fed76a21efc96cc0eb4fa7bd69722f94d", "parents": [ "ccb79bdce71f2c04cfa9bfcbaf4d37e2f963d684" ], "author": { "name": "Jan Engelhardt", "email": "jengelh@gmx.de", "time": "Sat Jul 07 22:16:26 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:59 2007 -0700" }, "message": "[NETFILTER]: x_tables: switch xt_target-\u003echeckentry to bool\n\nSwitch the return type of target checkentry functions to boolean.\n\nSigned-off-by: Jan Engelhardt \u003cjengelh@gmx.de\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ccb79bdce71f2c04cfa9bfcbaf4d37e2f963d684", "tree": "5f41d7d1daade309b96492301a6f973caba3a2a4", "parents": [ "1d93a9cbad608f6398ba6c5b588c504ccd35a2ca" ], "author": { "name": "Jan Engelhardt", "email": "jengelh@gmx.de", "time": "Sat Jul 07 22:16:00 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:58 2007 -0700" }, "message": "[NETFILTER]: x_tables: switch xt_match-\u003echeckentry to bool\n\nSwitch the return type of match functions to boolean\n\nSigned-off-by: Jan Engelhardt \u003cjengelh@gmx.de\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1d93a9cbad608f6398ba6c5b588c504ccd35a2ca", "tree": "df02632a70f0438efb0e5baab9900f4f2acf98a1", "parents": [ "cff533ac12494fa002e2c46acc94d670e5f636a2" ], "author": { "name": "Jan Engelhardt", "email": "jengelh@gmx.de", "time": "Sat Jul 07 22:15:35 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:57 2007 -0700" }, "message": "[NETFILTER]: x_tables: switch xt_match-\u003ematch to bool\n\nSwitch the return type of match functions to boolean\n\nSigned-off-by: Jan Engelhardt \u003cjengelh@gmx.de\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cff533ac12494fa002e2c46acc94d670e5f636a2", "tree": "ab159436fa3f5c282455afafcf136fd03fa8225a", "parents": [ "7bfe24611671ec76b44281e582b38535e21f01a9" ], "author": { "name": "Jan Engelhardt", "email": "jengelh@gmx.de", "time": "Sat Jul 07 22:15:12 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:56 2007 -0700" }, "message": "[NETFILTER]: x_tables: switch hotdrop to bool\n\nSwitch the \"hotdrop\" variables to boolean\n\nSigned-off-by: Jan Engelhardt \u003cjengelh@gmx.de\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "7bfe24611671ec76b44281e582b38535e21f01a9", "tree": "72b04c7220842c58b0f0da274eac78896a28d142", "parents": [ "558585aad0c0ef83d3d14a1c7576b1e404ca1fbc" ], "author": { "name": "Yasuyuki Kozakai", "email": "yasuyuki@netfilter.org", "time": "Sat Jul 07 22:14:23 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:55 2007 -0700" }, "message": "[NETFILTER]: ip6_tables: fix explanation of valid upper protocol number\n\nThis explains the allowed upper protocol numbers. IP6T_F_NOPROTO was\nintroduced to use 0 as Hop-by-Hop option header, not wildcard. But that\nseemed to be forgotten. 0 has been used as wildcard since 2002-08-23.\n\nSigned-off-by: Yasuyuki Kozakai \u003cyasuyuki@netfilter.org\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "558585aad0c0ef83d3d14a1c7576b1e404ca1fbc", "tree": "c0c196e304373addcb4562fd84067ecd29da5d44", "parents": [ "067b207b281db5e3f03f8d244286c20f61aa2343" ], "author": { "name": "Jing Min Zhao", "email": "zhaojingmin@vivecode.com", "time": "Sat Jul 07 22:13:17 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:54 2007 -0700" }, "message": "[NETFILTER]: nf_conntrack_h323: check range first in sequence extension\n\nCheck range before checking STOP flag. This optimization may save a\nnanosecond or less :)\n\nSigned-off-by: Jing Min Zhao \u003czhaojingmin@vivecode.com\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "067b207b281db5e3f03f8d244286c20f61aa2343", "tree": "a947ba1fdc03ca82fdb2c7d6f8334b995c1c5ab2", "parents": [ "93cce3d3657bfb5d04789afcd5104f8c48700f32" ], "author": { "name": "James Chapman", "email": "jchapman@katalix.com", "time": "Thu Jul 05 17:08:05 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:53 2007 -0700" }, "message": "[UDP]: Cleanup UDP encapsulation code\n\nThis cleanup fell out after adding L2TP support where a new encap_rcv\nfuncptr was added to struct udp_sock. Have XFRM use the new encap_rcv\nfuncptr, which allows us to move the XFRM encap code from udp.c into\nxfrm4_input.c.\n\nMake xfrm4_rcv_encap() static since it is no longer called externally.\n\nSigned-off-by: James Chapman \u003cjchapman@katalix.com\u003e\nAcked-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "93cce3d3657bfb5d04789afcd5104f8c48700f32", "tree": "03d9392aec25c4386c390d0b45f3ec3f50bd8702", "parents": [ "66f5e51ed5a300291b34bf3e2b1e22ac28ca3631" ], "author": { "name": "G. Liakhovetski", "email": "gl@dsa-ac.de", "time": "Mon Jul 02 22:56:57 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:52 2007 -0700" }, "message": "[IrDA]: tsap init routine factorisation.\n\nThis patch extracts common code from irttp_open_tsap() and irttp_dup()\ninto a new function to 1) avoid code duplication, 2) help avoid\nforgetting object initialization in the tsap duplication path in the\nfuture.\n\nSigned-off-by: G. Liakhovetski \u003cgl@dsa-ac.de\u003e\nSigned-off-by: Samuel Ortiz \u003csamuel@sortiz.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "66f5e51ed5a300291b34bf3e2b1e22ac28ca3631", "tree": "fe70bb70b332f27b8143905d5b2b5b7a999f1315", "parents": [ "411725280bd0058ebb83c0e32133b7a94902c3a6" ], "author": { "name": "Samuel Ortiz", "email": "samuel@sortiz.org", "time": "Mon Jul 02 22:56:15 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:45 2007 -0700" }, "message": "[IrDA]: kingsun-sir.c charset fix.\n\nSigned-off-by: Samuel Ortiz \u003csamuel@sortiz.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "411725280bd0058ebb83c0e32133b7a94902c3a6", "tree": "7fc21a6c4b07ad80cf426c466400ed4679834e98", "parents": [ "89da1ecf5483e6aa29b456a15ad6d05a6797c5a5" ], "author": { "name": "Samuel Ortiz", "email": "samuel@sortiz.org", "time": "Mon Jul 02 22:55:31 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:44 2007 -0700" }, "message": "[IrDA]: Monitor mode.\n\nThrough the IrDA netlink set mode command, we switch to IrDA monitor\nmode, where one IrLAP instance receives all the packets on the media,\nwithout ever responding to them.\n\nSigned-off-by: Samuel Ortiz \u003csamuel@sortiz.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "89da1ecf5483e6aa29b456a15ad6d05a6797c5a5", "tree": "f9c6305e9c230f90e9cc2f862527eb8943a9e89c", "parents": [ "8c644623fe7e41f59fe97cdf666cba3cb7ced7d8" ], "author": { "name": "Samuel Ortiz", "email": "samuel@sortiz.org", "time": "Mon Jul 02 22:54:18 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:43 2007 -0700" }, "message": "[IrDA]: Netlink layer.\n\nFirst IrDA configuration netlink layer implementation.\nCurrently, we only support the set/get mode commands.\n\nSigned-off-by: Samuel Ortiz \u003csamuel@sortiz.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "8c644623fe7e41f59fe97cdf666cba3cb7ced7d8", "tree": "42ed72e59e73b6ec840aa4ea97a34630f3544093", "parents": [ "0ba48053831d5b89ee2afaefaae1c06eae80cb05" ], "author": { "name": "Guido Guenther", "email": "agx@sigxcpu.org", "time": "Mon Jul 02 22:50:25 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:42 2007 -0700" }, "message": "[NET]: Allow group ownership of TUN/TAP devices.\n\nIntroduce a new syscall TUNSETGROUP for group ownership setting of tap\ndevices. The user now is allowed to send packages if either his euid or\nhis egid matches the one specified via tunctl (via -u or -g\nrespecitvely). If both, gid and uid, are set via tunctl, both have to\nmatch.\n\nSigned-off-by: Guido Guenther \u003cagx@sigxcpu.org\u003e\nSigned-off-by: Jeff Dike \u003cjdike@linux.intel.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0ba48053831d5b89ee2afaefaae1c06eae80cb05", "tree": "4da20f12b2d4e69cfa22ee74d0319141ddc39801", "parents": [ "ee39e10c27ca5293c72addb95bff864095e19904" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Mon Jul 02 22:49:07 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:41 2007 -0700" }, "message": "[NET_SCHED]: Remove unnecessary includes\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ee39e10c27ca5293c72addb95bff864095e19904", "tree": "ab88b149b0aee405933e55a1bdb3806b3253a481", "parents": [ "4bdf39911e7a887c4499161422423cbaf16684e8" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Mon Jul 02 22:48:13 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:39 2007 -0700" }, "message": "[NET_SCHED]: sch_htb: use generic estimator\n\nUse the generic estimator instead of reimplementing (parts of) it.\nFor compatibility always create a default estimator for new classes.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4bdf39911e7a887c4499161422423cbaf16684e8", "tree": "3bf1ac8b4ee1e2682d7aff722d41175a694d41dc", "parents": [ "876d48aabf30e4981653f1a0a7ae1e262b8c8b6f" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Mon Jul 02 22:47:37 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:38 2007 -0700" }, "message": "[NET_SCHED]: Remove unnecessary stats_lock pointers\n\nRemove stats_lock pointers from qdisc-internal structures, in all cases\nit points to dev-\u003equeue_lock. The only case where it is necessary is for\ntop-level qdiscs, where it might also point to dev-\u003eingress_lock in case\nof the ingress qdisc. Also remove it from actions completely, it always\npoints to the actions internal lock.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "876d48aabf30e4981653f1a0a7ae1e262b8c8b6f", "tree": "49dace46f70bc243605ecf73af4a3f06e607a2be", "parents": [ "a553e4a6317b2cfc7659542c10fe43184ffe53da" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Mon Jul 02 22:46:07 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:37 2007 -0700" }, "message": "[NET_SCHED]: Remove CONFIG_NET_ESTIMATOR option\n\nThe generic estimator is always built in anways and all the config options\ndoes is prevent including a minimal amount of code for setting it up.\nAdditionally the option is already automatically selected for most cases.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a553e4a6317b2cfc7659542c10fe43184ffe53da", "tree": "ac0f046c4e0a40513e0f8405c3e628a6e515b83f", "parents": [ "628529b6ee334fedc8d25ce56205bb99566572b9" ], "author": { "name": "Jamal Hadi Salim", "email": "hadi@cyberus.ca", "time": "Mon Jul 02 22:41:59 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:36 2007 -0700" }, "message": "[PKTGEN]: IPSEC support\n\nAdded transport mode ESP support for starters. I will send more of\nthese modes and types once i have resolved the tunnel mode isses.\n\nSigned-off-by: Jamal Hadi Salim \u003chadi@cyberus.ca\u003e\nSigned-off-by: Robert Olsson \u003crobert.olsson@its.uu.se\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "628529b6ee334fedc8d25ce56205bb99566572b9", "tree": "4545df6f7ecdec05c903bb2c11ba9fb4380ac71c", "parents": [ "007a531b0a0c902392a3deff730acd28ce6625c7" ], "author": { "name": "Jamal Hadi Salim", "email": "hadi@cyberus.ca", "time": "Mon Jul 02 22:41:14 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:35 2007 -0700" }, "message": "[XFRM] Introduce standalone SAD lookup\n\nThis allows other in-kernel functions to do SAD lookups.\nThe only known user at the moment is pktgen.\n\nSigned-off-by: Jamal Hadi Salim \u003chadi@cyberus.ca\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "007a531b0a0c902392a3deff730acd28ce6625c7", "tree": "4b8be9cdb0aa51f186f759d285f943284e40312d", "parents": [ "16dab72f65a6aab0aa72866e00c91b58a2794082" ], "author": { "name": "Jamal Hadi Salim", "email": "hadi@cyberus.ca", "time": "Mon Jul 02 22:40:36 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:27 2007 -0700" }, "message": "[PKTGEN]: Introduce sequential flows\n\nBy default all flows in pktgen are randomly selected.\nThis patch introduces ability to have all defined flows to\nbe sent sequentially. Robert defined randomness to be the\ndefault behavior.\n\nSigned-off-by: Jamal Hadi Salim \u003chadi@cyberus.ca\u003e\nSigned-off-by: Robert Olsson \u003crobert.olsson@its.uu.se\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "16dab72f65a6aab0aa72866e00c91b58a2794082", "tree": "2e0b5871e75b9b4cef7c38d2d783147b942086ae", "parents": [ "eef6caf8a916f32f8d9b2a02d4fa7674736c00ac" ], "author": { "name": "Jamal Hadi Salim", "email": "hadi@cyberus.ca", "time": "Mon Jul 02 22:39:50 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:26 2007 -0700" }, "message": "[PKTGEN]: Centralize packet overhead tracking\n\nTrack the extra packet overhead for VLAN tags, MPLS, IPSEC etc\n\nSigned-off-by: Jamal Hadi Salim \u003chadi@cyberus.ca\u003e\nSigned-off-by: Robert Olsson \u003crobert.olsson@its.uu.se\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "eef6caf8a916f32f8d9b2a02d4fa7674736c00ac", "tree": "d9ecce23fc7d8b2c4c94905bc43f42dc77424822", "parents": [ "d0410051164bbbc597e15f068b53c06a954ae0d4" ], "author": { "name": "Larry Finger", "email": "Larry.Finger@lwfinger.net", "time": "Mon Jul 02 22:36:38 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:25 2007 -0700" }, "message": "[MAC80211]: Set low initial rate in rc80211_simple\n\nThe initial rate for STA\u0027s using rc80211_simple is set to the last\nrate in the rate table. For situations for which the signal is weak,\nthe rate may be too high for authentication and association. Although\nthe rc80211_simple module will adjust the speed, the response may not\nbe fast enough for a successful connection. This modification sets the\ninitial rate to the lowest supported value.\n\nSigned-off-by: Larry Finger \u003cLarry.Finger@lwfinger.net\u003e\nSigned-off-by: Johannes Berg \u003cjohannes@sipsolutions.net\u003e\nSigned-off-by: John W. Linville \u003clinville@tuxdriver.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d0410051164bbbc597e15f068b53c06a954ae0d4", "tree": "9b3385d276eac1b33d7347934773c976cc2b4a81", "parents": [ "61cbc2fca6335be52788773b21efdc52a2750924" ], "author": { "name": "Ilpo Järvinen", "email": "ilpo.jarvinen@helsinki.fi", "time": "Mon Jul 02 22:07:22 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:24 2007 -0700" }, "message": "[TCP]: SACK fastpath did override adjusted fackets_out\n\nDo same adjustment to SACK fastpath counters provided that\nthey\u0027re valid.\n\nSigned-off-by: Ilpo Järvinen \u003cilpo.jarvinen@helsinki.fi\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "61cbc2fca6335be52788773b21efdc52a2750924", "tree": "489e6a9571c7fabd49dcff384dd634635fe66555", "parents": [ "d62733c8e437fdb58325617c4b3331769ba82d70" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Sat Jun 30 13:35:52 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:23 2007 -0700" }, "message": "[NET]: Fix secondary unicast/multicast address count maintenance\n\nWhen a reference to an existing address is increased or decreased without\nhitting zero, the address count is incorrectly adjusted.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d62733c8e437fdb58325617c4b3331769ba82d70", "tree": "fcbef07b66cda79b047092e7d53dfd005046838a", "parents": [ "f25f4e44808f0f6c9875d94ef1c41ef86c288eb2" ], "author": { "name": "Peter P Waskiewicz Jr", "email": "peter.p.waskiewicz.jr@intel.com", "time": "Thu Jun 28 21:04:31 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:22 2007 -0700" }, "message": "[SCHED]: Qdisc changes and sch_rr added for multiqueue\n\nAdd the new sch_rr qdisc for multiqueue network device support. Allow\nsch_prio and sch_rr to be compiled with or without multiqueue hardware\nsupport.\n\nsch_rr is part of sch_prio, and is referenced from MODULE_ALIAS. This\nwas done since sch_prio and sch_rr only differ in their dequeue\nroutine.\n\nSigned-off-by: Peter P Waskiewicz Jr \u003cpeter.p.waskiewicz.jr@intel.com\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f25f4e44808f0f6c9875d94ef1c41ef86c288eb2", "tree": "d7809dd5e957f1626185326d0c3438ff9a04d350", "parents": [ "a093bf006e09a305e95ff0938c0a18b7520aef67" ], "author": { "name": "Peter P Waskiewicz Jr", "email": "peter.p.waskiewicz.jr@intel.com", "time": "Fri Jul 06 13:36:20 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:21 2007 -0700" }, "message": "[CORE] Stack changes to add multiqueue hardware support API\n\nAdd the multiqueue hardware device support API to the core network\nstack. Allow drivers to allocate multiple queues and manage them at\nthe netdev level if they choose to do so.\n\nAdded a new field to sk_buff, namely queue_mapping, for drivers to\nknow which tx_ring to select based on OS classification of the flow.\n\nSigned-off-by: Peter P Waskiewicz Jr \u003cpeter.p.waskiewicz.jr@intel.com\u003e\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a093bf006e09a305e95ff0938c0a18b7520aef67", "tree": "034bb8195b9aec792a577d020341cfa83caec2bb", "parents": [ "a298830cd026b4c0cde45ef3679a5f68a17577e6" ], "author": { "name": "Peter P Waskiewicz Jr", "email": "peter.p.waskiewicz.jr@intel.com", "time": "Thu Jun 28 20:45:47 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:20 2007 -0700" }, "message": "[NET]: [DOC] Multiqueue hardware support documentation\n\nAdd a brief howto to Documentation/networking for multiqueue. It\nexplains how to use the multiqueue API in a driver to support\nmultiqueue paths from the stack, as well as the qdiscs to use for\nfeeding a multiqueue device.\n\nSigned-off-by: Peter P Waskiewicz Jr \u003cpeter.p.waskiewicz.jr@intel.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a298830cd026b4c0cde45ef3679a5f68a17577e6", "tree": "211a4d13360027e8136b32453ebc6d97a87b8ef7", "parents": [ "58e50a904ec78caf4ca938801c031413b0d3f962" ], "author": { "name": "Herbert Xu", "email": "herbert@gondor.apana.org.au", "time": "Thu Jun 28 13:44:37 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:19 2007 -0700" }, "message": "[NET]: Fix TX checksum feature check\n\nThis patch fixes a boolean error in the new TX checksum check\nthat causes bogus TSO packets to be generated.\n\nSigned-off-by: Herbert Xu \u003cherbert@gondor.apana.org.au\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "58e50a904ec78caf4ca938801c031413b0d3f962", "tree": "73a5443d31a5e0dbb3761fab4c20ce61f7545af5", "parents": [ "a6d2370b0839c228ae4e680e75263ecf0a73e251" ], "author": { "name": "James Chapman", "email": "jchapman@katalix.com", "time": "Wed Jun 27 15:53:49 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:18 2007 -0700" }, "message": "[L2TP]: Add PPPoL2TP in-kernel documentation\n\nSigned-off-by: James Chapman \u003cjchapman@katalix.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a6d2370b0839c228ae4e680e75263ecf0a73e251", "tree": "3f2941e6ccc50f01eeec9cc59dbb2c550967b33c", "parents": [ "38d15b656258b52a659fcf3e181f85b51bd1851f" ], "author": { "name": "James Chapman", "email": "jchapman@katalix.com", "time": "Wed Jun 27 15:53:17 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:01 2007 -0700" }, "message": "[L2TP]: Add PPPoL2TP maintainer\n\nSigned-off-by: James Chapman \u003cjchapman@katalix.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "38d15b656258b52a659fcf3e181f85b51bd1851f", "tree": "4fdd8b20afa4532d1a7ac4dc698c0ccc9361f3a2", "parents": [ "3557baabf28088f49bdf72a048fd33ab62e205b1" ], "author": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Wed Jun 27 15:52:25 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:16:00 2007 -0700" }, "message": "[PPPOL2TP]: Use proper printf format specifier for size_t.\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "3557baabf28088f49bdf72a048fd33ab62e205b1", "tree": "c0e2f8f03b037758a9fd790adf9bfa1580109910", "parents": [ "cf14a4d06742d59ecb2d837a3f53bb24d1ff9acb" ], "author": { "name": "James Chapman", "email": "jchapman@katalix.com", "time": "Wed Jun 27 15:49:24 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:59 2007 -0700" }, "message": "[L2TP]: PPP over L2TP driver core\n\nThis driver handles only L2TP data frames; control frames are handled\nby a userspace application. It implements L2TP using the PPPoX socket\nfamily. There is a PPPoX socket for each L2TP session in an L2TP\ntunnel. PPP data within each session is passed through the kernel\u0027s\nPPP subsystem via this driver. Kernel parameters of each socket can be\nread or modified using ioctl() or [gs]etsockopt() calls.\n\nSigned-off-by: James Chapman \u003cjchapman@katalix.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cf14a4d06742d59ecb2d837a3f53bb24d1ff9acb", "tree": "78b8058dd7bd8b1cfba243d7d478495e0ba9281b", "parents": [ "342f0234c71b40da785dd6a7ce1dd481ecbfdb81" ], "author": { "name": "James Chapman", "email": "jchapman@katalix.com", "time": "Wed Jun 27 15:43:43 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:58 2007 -0700" }, "message": "[L2TP]: Changes to existing ppp and socket kernel headers for L2TP\n\nAdd struct sockaddr_pppol2tp to carry L2TP-specific address\ninformation for the PPPoX (PPPoL2TP) socket. Unfortunately we can\u0027t\nuse the union inside struct sockaddr_pppox because the L2TP-specific\ndata is larger than the current size of the union and we must preserve\nthe size of struct sockaddr_pppox for binary compatibility.\n\nAlso add a PPPIOCGL2TPSTATS ioctl to allow userspace to obtain\nL2TP counters and state from the kernel.\n\nAdd new if_pppol2tp.h header.\n\n[ Modified to use aligned_u64 in statistics structure -DaveM ]\n\nSigned-off-by: James Chapman \u003cjchapman@katalix.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "342f0234c71b40da785dd6a7ce1dd481ecbfdb81", "tree": "b6d7295cd484449f3f6478fe3e796fc8988534a3", "parents": [ "4417da668c0021903464f92db278ddae348e0299" ], "author": { "name": "James Chapman", "email": "jchapman@katalix.com", "time": "Wed Jun 27 15:37:46 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:57 2007 -0700" }, "message": "[UDP]: Introduce UDP encapsulation type for L2TP\n\nThis patch adds a new UDP_ENCAP_L2TPINUDP encapsulation type for UDP\nsockets. When a UDP socket\u0027s encap_type is UDP_ENCAP_L2TPINUDP, the\nskb is delivered to a function pointed to by the udp_sock\u0027s\nencap_rcv funcptr. If the skb isn\u0027t wanted by L2TP, it returns \u003e0, which\ncauses it to be passed through to UDP.\n\nInclude padding to put the new encap_rcv field on a 4-byte boundary.\n\nPreviously, the only user of UDP encap sockets was ESP, so when\nCONFIG_XFRM was not defined, some of the encap code was compiled\nout. This patch changes that. As a result, udp_encap_rcv() will\nnow do a little more work when CONFIG_XFRM is not defined.\n\nSigned-off-by: James Chapman \u003cjchapman@katalix.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4417da668c0021903464f92db278ddae348e0299", "tree": "a4330cbc2e69a5714fee0a04bcfbabe97109de46", "parents": [ "3fba5a8b1e3df2384b90493538161e83cf15dd5f" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Wed Jun 27 01:28:10 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:56 2007 -0700" }, "message": "[NET]: dev: secondary unicast address support\n\nAdd support for configuring secondary unicast addresses on network\ndevices. To support this devices capable of filtering multiple\nunicast addresses need to change their set_multicast_list function\nto configure unicast filters as well and assign it to dev-\u003eset_rx_mode\ninstead of dev-\u003eset_multicast_list. Other devices are put into promiscous\nmode when secondary unicast addresses are present.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "3fba5a8b1e3df2384b90493538161e83cf15dd5f", "tree": "f38bb73c1bf2516c6c973c9e7cd18fd5a20b1c20", "parents": [ "bf742482d7a647c5c6f03f78eb35a862e159ecf5" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Wed Jun 27 01:26:58 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:55 2007 -0700" }, "message": "[NET]: dev_mcast: switch to generic net_device address lists\n\nUse generic net_device address lists for multicast list handling.\nSome defines are used to keep drivers working.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "bf742482d7a647c5c6f03f78eb35a862e159ecf5", "tree": "80a822df5fa5eb6b766489b1983c4dc83d4f7668", "parents": [ "75ebe8f73610636be8bbd8d73db883512850e6be" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Wed Jun 27 01:26:19 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:54 2007 -0700" }, "message": "[NET]: dev: introduce generic net_device address lists\n\nIntroduce struct dev_addr_list and list maintenance functions\nbased on dev_mc_list and the related functions. This will be\nused by follow-up patches for both multicast and secondary\nunicast addresses.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "75ebe8f73610636be8bbd8d73db883512850e6be", "tree": "60ea3cc1b5fa6a942667d0c9352df838b2f0094b", "parents": [ "d212f87b068c9d72065ef579d85b5ee6b8b59381" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Wed Jun 27 01:25:11 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:53 2007 -0700" }, "message": "[NET]: dev_mcast: unexport dev_mc_upload\n\ndev_mc_add/dev_mc_delete take care of uploading the list when\nnecessary and thats the only interface other code should use.\nAlso remove two incorrect calls in DECnet.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d212f87b068c9d72065ef579d85b5ee6b8b59381", "tree": "a194d5c667c277c7ea5392c9cf97857a0cd1d321", "parents": [ "d3d6dd3adaaad71eae20902ed81808a66a40a5b9" ], "author": { "name": "Stephen Hemminger", "email": "shemminger@linux-foundation.org", "time": "Wed Jun 27 00:47:37 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:52 2007 -0700" }, "message": "[NET]: IPV6 checksum offloading in network devices\n\nThe existing model for checksum offload does not correctly handle\ndevices that can offload IPV4 and IPV6 only. The NETIF_F_HW_CSUM flag\nimplies device can do any arbitrary protocol.\n\nThis patch:\n * adds NETIF_F_IPV6_CSUM for those devices\n * fixes bnx2 and tg3 devices that need it\n * add NETIF_F_IPV6_CSUM to ipv6 output (incl GSO)\n * fixes assumptions about NETIF_F_ALL_CSUM in nat\n * adjusts bridge union of checksumming computation\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d3d6dd3adaaad71eae20902ed81808a66a40a5b9", "tree": "b08faa2174867f3f589889695bfa8388d2237f1e", "parents": [ "59fbb3a61e02deaeaa4fb50792217921f3002d64" ], "author": { "name": "Masahide NAKAMURA", "email": "nakam@linux-ipv6.org", "time": "Tue Jun 26 23:57:49 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:43 2007 -0700" }, "message": "[XFRM]: Add module alias for transformation type.\n\nIt is clean-up for XFRM type modules and adds aliases with its\nprotocol:\n ESP, AH, IPCOMP, IPIP and IPv6 for IPsec\n ROUTING and DSTOPTS for MIPv6\n\nIt is almost the same thing as XFRM mode alias, but it is added\nnew defines XFRM_PROTO_XXX for preprocessing since some protocols\nare defined as enum.\n\nSigned-off-by: Masahide NAKAMURA \u003cnakam@linux-ipv6.org\u003e\nAcked-by: Ingo Oeser \u003cnetdev@axxeo.de\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "59fbb3a61e02deaeaa4fb50792217921f3002d64", "tree": "7455815c2566ba9b898cd6ea2c710159bbeb624f", "parents": [ "136ebf08b46f839e2dc9db34322b654e5d9b9936" ], "author": { "name": "Masahide NAKAMURA", "email": "nakam@linux-ipv6.org", "time": "Tue Jun 26 23:56:32 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:42 2007 -0700" }, "message": "[IPV6] MIP6: Loadable module support for MIPv6.\n\nThis patch makes MIPv6 loadable module named \"mip6\".\n\nHere is a modprobe.conf(5) example to load it automatically\nwhen user application uses XFRM state for MIPv6:\n\nalias xfrm-type-10-43 mip6\nalias xfrm-type-10-60 mip6\n\nSome MIPv6 feature is not included by this modular, however,\nit should not be affected to other features like either IPsec\nor IPv6 with and without the patch.\nWe may discuss XFRM, MH (RAW socket) and ancillary data/sockopt\nseparately for future work.\n\nLoadable features:\n* MH receiving check (to send ICMP error back)\n* RO header parsing and building (i.e. RH2 and HAO in DSTOPTS)\n* XFRM policy/state database handling for RO\n\nThese are NOT covered as loadable:\n* Home Address flags and its rule on source address selection\n* XFRM sub policy (depends on its own kernel option)\n* XFRM functions to receive RO as IPv6 extension header\n* MH sending/receiving through raw socket if user application\n opens it (since raw socket allows to do so)\n* RH2 sending as ancillary data\n* RH2 operation with setsockopt(2)\n\nSigned-off-by: Masahide NAKAMURA \u003cnakam@linux-ipv6.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "136ebf08b46f839e2dc9db34322b654e5d9b9936", "tree": "6a38a3c546def150ff73effcf4afd9c55881f49c", "parents": [ "2371baa4bdab3268b32009926f75e7a5d3a41506" ], "author": { "name": "Masahide NAKAMURA", "email": "nakam@linux-ipv6.org", "time": "Tue Jun 26 23:51:41 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:41 2007 -0700" }, "message": "[IPV6] MIP6: Kill unnecessary ifdefs.\n\nKill unnecessary CONFIG_IPV6_MIP6.\n\no It is redundant for RAW socket to keep MH out with the config then\n it can handle any protocol.\no Clean-up at AH.\n\nSigned-off-by: Masahide NAKAMURA \u003cnakam@linux-ipv6.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "2371baa4bdab3268b32009926f75e7a5d3a41506", "tree": "1c9d118ee17261b92da75550ef2a7b453bbe5bc9", "parents": [ "afdc3238ec948531205f5c5f77d2de7bae519c71" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Tue Jun 26 03:23:44 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:40 2007 -0700" }, "message": "[RTNETLINK]: Fix rtnetlink compat attribute patch\n\nSent the wrong patch previously.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "afdc3238ec948531205f5c5f77d2de7bae519c71", "tree": "ce69a6ed3095ba5049673340304672381068b3af", "parents": [ "1092cb219774a82b1f16781aec7b8d4ec727c981" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Mon Jun 25 14:30:16 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:39 2007 -0700" }, "message": "[RTNETLINK]: Add nested compat attribute\n\nAdd a nested compat attribute type that can be used to convert\nattributes that contain a structure to nested attributes in a\nbackwards compatible way.\n\nThe attribute looks like this:\n\nstruct {\n [ compat contents ]\n struct rtattr {\n .rta_len \u003d total size,\n .rta_type \u003d type,\n } rta;\n struct old_structure struct;\n\n [ nested top-level attribute ]\n struct rtattr {\n .rta_len \u003d nest size,\n .rta_type \u003d type,\n } nest_attr;\n\n [ optional 0 .. n nested attributes ]\n struct rtattr {\n .rta_len \u003d private attribute len,\n .rta_type \u003d private attribute typ,\n } nested_attr;\n struct nested_data data;\n};\n\nSince both userspace and kernel deal correctly with attributes that are\nlarger than expected old versions will just parse the compat part and\nignore the rest.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1092cb219774a82b1f16781aec7b8d4ec727c981", "tree": "dddd1d559e08c07b41715d8cf2678ff7d45d5230", "parents": [ "334a8132d9950f769f390f0f35c233d099688e7a" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Mon Jun 25 13:49:35 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:38 2007 -0700" }, "message": "[NETLINK]: attr: add nested compat attribute type\n\nAdd a nested compat attribute type that can be used to convert\nattributes that contain a structure to nested attributes in a\nbackwards compatible way.\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "334a8132d9950f769f390f0f35c233d099688e7a", "tree": "0a9e988971d4c20e720e99bccfa6f5feeca5d94a", "parents": [ "e50c41b53d7aa48152dd9c633b04fc7abd536f1f" ], "author": { "name": "Patrick McHardy", "email": "kaber@trash.net", "time": "Mon Jun 25 04:35:20 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:37 2007 -0700" }, "message": "[SKBUFF]: Keep track of writable header len of headerless clones\n\nCurrently NAT (and others) that want to modify cloned skbs copy them,\neven if in the vast majority of cases its not necessary because the\nskb is a clone made by TCP and the portion NAT wants to modify is\nactually writable because TCP release the header reference before\ncloning.\n\nThe problem is that there is no clean way for NAT to find out how\nlong the writable header area is, so this patch introduces skb-\u003ehdr_len\nto hold this length. When a headerless skb is cloned skb-\u003ehdr_len\nis set to the current headroom, for regular clones it is copied from\nthe original. A new function skb_clone_writable(skb, len) returns\nwhether the skb is writable up to len bytes from skb-\u003edata. To avoid\nenlarging the skb the mac_len field is reduced to 16 bit and the\nnew hdr_len field is put in the remaining 16 bit.\n\nI\u0027ve done a few rough benchmarks of NAT (not with this exact patch,\nbut a very similar one). As expected it saves huge amounts of system\ntime in case of sendfile, bringing it down to basically the same\namount as without NAT, with sendmsg it only helps on loopback,\nprobably because of the large MTU.\n\nTransmit a 1GB file using sendfile/sendmsg over eth0/lo with and\nwithout NAT:\n\n- sendfile eth0, no NAT:\tsys 0m0.388s\n- sendfile eth0, NAT:\t\tsys 0m1.835s\n- sendfile eth0: NAT + path:\tsys 0m0.370s\t(~ -80%)\n\n- sendfile lo, no NAT:\t\tsys 0m0.258s\n- sendfile lo, NAT:\t\tsys 0m2.609s\n- sendfile lo, NAT + patch:\tsys 0m0.260s\t(~ -90%)\n\n- sendmsg eth0, no NAT:\t\tsys 0m2.508s\n- sendmsg eth0, NAT:\t\tsys 0m2.539s\n- sendmsg eth0, NAT + patch:\tsys 0m2.445s\t(no change)\n\n- sendmsg lo, no NAT:\t\tsys\t0m2.151s\n- sendmsg lo, NAT:\t\tsys 0m3.557s\n- sendmsg lo, NAT + patch:\tsys 0m2.159s\t(~ -40%)\n\nI expect other users can see a similar performance improvement,\npacket mangling iptables targets, ipip and ip_gre come to mind ..\n\nSigned-off-by: Patrick McHardy \u003ckaber@trash.net\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "e50c41b53d7aa48152dd9c633b04fc7abd536f1f", "tree": "3f9ecdbf7a685820ad06321dadc73441e850ba10", "parents": [ "6c1361a6f285bf3df4b502651c0dd38d0eedc044" ], "author": { "name": "Krishna Kumar", "email": "krkumar2@in.ibm.com", "time": "Sun Jun 24 19:57:27 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:36 2007 -0700" }, "message": "[NET]: qdisc_restart - couple of optimizations.\n\nChanges :\n\n- netif_queue_stopped need not be called inside qdisc_restart as\n it has been called already in qdisc_run() before the first skb\n is sent, and in __qdisc_run() after each intermediate skb is\n sent (note : we are the only sender, so the queue cannot get\n stopped while the tx lock was got in the ~LLTX case).\n\n- BUG_ON((int) q-\u003eq.qlen \u003c 0) was a relic from old times when -1\n meant more packets are available, and __qdisc_run used to loop\n when qdisc_restart() returned -1. During those days, it was\n necessary to make sure that qlen is never less than zero, since\n __qdisc_run would get into an infinite loop if no packets are on\n the queue and this bug in qdisc was there (and worse - no more\n skbs could ever get queue\u0027d as we hold the queue lock too). With\n Herbert\u0027s recent change to return values, this check is not\n required. Hopefully Herbert can validate this change. If at all\n this is required, it should be added to skb_dequeue (in failure\n case), and not to qdisc_qlen.\n\nSigned-off-by: Krishna Kumar \u003ckrkumar2@in.ibm.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "6c1361a6f285bf3df4b502651c0dd38d0eedc044", "tree": "b0a89bc11d04bd32451b6b0637da6396fa1c8549", "parents": [ "49d66a70cf9fd94057aacd6055334299ab3a5eac" ], "author": { "name": "Krishna Kumar", "email": "krkumar2@in.ibm.com", "time": "Sun Jun 24 19:56:09 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:35 2007 -0700" }, "message": "[NET]: qdisc_restart - readability changes plus one bug fix.\n\nNew changes :\n\n- Incorporated Peter Waskiewicz\u0027s comments.\n- Re-added back one warning message (on driver returning wrong value).\n\nPrevious changes :\n\n- Converted to use switch/case code which looks neater.\n\n- \"if (ret \u003d\u003d NETDEV_TX_LOCKED \u0026\u0026 lockless)\" is buggy, and the lockless\n check should be removed, since driver will return NETDEV_TX_LOCKED only\n if lockless is true and driver has to do the locking. In the original\n code as well as the latest code, this code can result in a bug where\n if LLTX is not set for a driver (lockless \u003d\u003d 0) but the driver is written\n wrongly to do a trylock (despite LLTX being set), the driver returns\n LOCKED. But since lockless is zero, the packet is requeue\u0027d instead of\n calling collision code which will issue warning and free up the skb.\n Instead this skb will be retried with this driver next time, and the same\n result will ensue. Removing this check will catch these driver bugs instead\n of hiding the problem. I am keeping this change to readability section\n since :\n \ta. it is confusing to check two things as it is; and\n \tb. it is difficult to keep this check in the changed \u0027switch\u0027 code.\n\n- Changed some names, like try_get_tx_pkt to dev_dequeue_skb (as that is\n the work being done and easier to understand) and do_dev_requeue to\n dev_requeue_skb, merged handle_dev_cpu_collision and tx_islocked to\n dev_handle_collision (handle_dev_cpu_collision is a small routine with only\n one caller, so there is no need to have two separate routines which also\n results in getting rid of two macros, etc.\n\n- Removed an XXX comment as it should never fail (I suspect this was related\n to batch skb WIP, Jamal ?). Converted some functions to original coding\n style of having the return values and the function name on same line, eg\n prio2list.\n\nSigned-off-by: Krishna Kumar \u003ckrkumar2@in.ibm.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "49d66a70cf9fd94057aacd6055334299ab3a5eac", "tree": "2feed7f094e3b2a45b7d3a211c2a3b33c61cbfb1", "parents": [ "8132da4d412ad51c34bad11133a8f0941e2a1972" ], "author": { "name": "Gerrit Renker", "email": "gerrit@erg.abdn.ac.uk", "time": "Sat Jun 16 13:48:50 2007 -0300" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:15:34 2007 -0700" }, "message": "[CCID3]: Fix a bug in the send time processing\n\nccid3_hc_tx_send_packet currently returns 0 when the time difference between\ncurrent time and t_nom is less than 1000 microseconds.\n\nIn this case the packet is sent immediately; but, unlike other packets that can\nbe emitted on first attempt, it will not have its window counter updated and\nits options set as required. This is a bug.\n\nFix: Require the time difference to be at least 1000 microseconds. The\nalgorithm then converges: time differences \u003e 1000 microseconds trigger the\ntimer in dccp_write_xmit; after timer expiry this function is tried again; when\nthe time difference is less than 1000, the packet will have its options added\nand window counter updated as required.\n\nSigned-off-by: Gerrit Renker \u003cgerrit@erg.abdn.ac.uk\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@ghostprotocols.net\u003e\n" } ], "next": "8132da4d412ad51c34bad11133a8f0941e2a1972" }