)]}' { "log": [ { "commit": "2937391385807b3da9cd7a39345259caf550b032", "tree": "6b75733afd1c5eb9a847c72b0c745ffc24aef559", "parents": [ "26a414092353590ceaa5955bcb53f863d6ea7549" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Fri Oct 03 17:15:38 2008 -0400" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Sat Oct 04 17:12:27 2008 -0400" }, "message": "NLM: Remove unused argument from svc_addsock() function\n\nClean up: The svc_addsock() function no longer uses its \"proto\"\nargument, so remove it.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "b6632339e3afbcbb438a3c8935190ea22464fc99", "tree": "13fb088ceb8b18563c2eae311b0007783a612948", "parents": [ "c8ab5f2a13fb41a878863c61a1e27d78f1844b5e" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Aug 18 19:33:44 2008 -0400" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Mon Sep 29 18:13:37 2008 -0400" }, "message": "SUNRPC: Set V6ONLY socket option for RPC listener sockets\n\nMy plan is to use an AF_INET listener on systems that support only IPv4,\nand an AF_INET6 listener on systems that can support IPv6. Incoming\nIPv4 packets will be posted to an AF_INET6 listener with a mapped IPv4\naddress.\n\nMax Matveev \u003cmakc@sgi.com\u003e says:\n Creating a single listener can be dangerous - if net.ipv6.bindv6only\n is enabled then it\u0027s possible to create another listener in v4\n namespace on the same port and steal the traffic from the \"unifed\"\n listener. You need to disable V6ONLY explicitly via a sockopt to stop\n that.\n\nSet appropriate socket option on RPC server listener sockets to prevent\nthis.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "c0401ea008fb7c785a93428752d69dccafb127ec", "tree": "c24c8c6e8871ecba8906098c0360bf3980fedf73", "parents": [ "b7872fe86db78cc96c85a13338ea6e3fe1aef610" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Apr 14 12:27:30 2008 -0400" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Wed Apr 23 16:13:43 2008 -0400" }, "message": "SUNRPC: Update RPC server\u0027s TCP record marker decoder\n\nClean up: Update the RPC server\u0027s TCP record marker decoder to match the\nconstructs used by the RPC client\u0027s TCP socket transport.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "b7872fe86db78cc96c85a13338ea6e3fe1aef610", "tree": "2425138e8007ab93a8d46f6ab9c240a8214814a6", "parents": [ "f97c650dda24e48405399aa0676e90da52408515" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Apr 14 12:27:01 2008 -0400" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Wed Apr 23 16:13:43 2008 -0400" }, "message": "SUNRPC: RPC server still uses 2.4 method for disabling TCP Nagle\n\nUse the 2.6 method for disabling TCP Nagle in the kernel\u0027s RPC server.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "23d42ee278de1552d67daef5774ba59ff30925db", "tree": "9470458414cfaf370986283a4c388c9e652cf8f0", "parents": [ "1447d25eb3a7bbe5bf5e4e7489f09be13e1ec73a" ], "author": { "name": "Jeff Layton", "email": "jlayton@redhat.com", "time": "Thu Feb 07 16:34:53 2008 -0500" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Wed Apr 23 16:13:35 2008 -0400" }, "message": "SUNRPC: export svc_sock_update_bufs\n\nNeeded since the plan is to not have a svc_create_thread helper and to\nhave current users of that function just call kthread_run directly.\n\nSigned-off-by: Jeff Layton \u003cjlayton@redhat.com\u003e\nReviewed-by: NeilBrown \u003cneilb@suse.de\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "5216a8e70e25b01cbd2915cd0442fb96deb2c262", "tree": "f372bd3cb3fc2f4a2d3e4ad303e6c4d3f8f48865", "parents": [ "90dc7d2796edf94a9eaa838321a9734c8513e717" ], "author": { "name": "Pavel Emelyanov", "email": "xemul@openvz.org", "time": "Thu Feb 21 10:57:45 2008 +0300" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Thu Feb 21 18:42:29 2008 -0500" }, "message": "Wrap buffers used for rpc debug printks into RPC_IFDEBUG\n\nSorry for the noise, but here\u0027s the v3 of this compilation fix :)\n\nThere are some places, which declare the char buf[...] on the stack\nto push it later into dprintk(). Since the dprintk sometimes (if the\nCONFIG_SYSCTL\u003dn) becomes an empty do { } while (0) stub, these buffers\ncause gcc to produce appropriate warnings.\n\nWrap these buffers with RPC_IFDEBUG macro, as Trond proposed, to\ncompile them out when not needed.\n\nSigned-off-by: Pavel Emelyanov \u003cxemul@openvz.org\u003e\nAcked-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "260c1d1298f6703d38fdccd3dd5a310766327340", "tree": "95bf71a81a9bba5d1e69940ccba99943682029c5", "parents": [ "0f0257eaa5d29b80f6ab2c40ed21aa65bb4527f6" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:29 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:13 2008 -0500" }, "message": "svc: Add transport hdr size for defer/revisit\n\nSome transports have a header in front of the RPC header. The current\ndefer/revisit processing considers only the iov_len and arg_len to\ndetermine how much to back up when saving the original request\nto revisit. Add a field to the rqstp structure to save the size\nof the transport header so svc_defer can correctly compute\nthe start of a request.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "0f0257eaa5d29b80f6ab2c40ed21aa65bb4527f6", "tree": "542f64ec74fc045c06f5a1ffc0d48f823de12ccb", "parents": [ "18d19f949d5a9c927b2b88402630c5137971b619" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:27 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:13 2008 -0500" }, "message": "svc: Move the xprt independent code to the svc_xprt.c file\n\nThis functionally trivial patch moves all of the transport independent\nfunctions from the svcsock.c file to the transport independent svc_xprt.c\nfile.\n\nIn addition the following formatting changes were made:\n- White space cleanup\n- Function signatures on single line\n- The inline directive was removed\n- Lines over 80 columns were reformatted\n- The term \u0027socket\u0027 was changed to \u0027transport\u0027 in comments\n- The SMP comment was moved and updated.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "18d19f949d5a9c927b2b88402630c5137971b619", "tree": "f66d3366d322c2fa78166bf6a4164c7caf7d14bd", "parents": [ "57b1d3babaafea1c395c932914e38c2ff9493001" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:25 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:13 2008 -0500" }, "message": "svc: Make svc_check_conn_limits xprt independent\n\nThe svc_check_conn_limits function only manipulates xprt fields. Change references\nto svc_sock-\u003esk_xprt to svc_xprt directly.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "57b1d3babaafea1c395c932914e38c2ff9493001", "tree": "5580e5f084f4473ac6b7b00905d4abd0328e5617", "parents": [ "4e5caaa5f24b3df1fe01097e1e7576461e70d491" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:22 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:13 2008 -0500" }, "message": "svc: Removing remaining references to rq_sock in rqstp\n\nThis functionally empty patch removes rq_sock and unamed union\nfrom rqstp structure.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "4e5caaa5f24b3df1fe01097e1e7576461e70d491", "tree": "c682473e9a40f4e8a8a1317906a516b41d47ec30", "parents": [ "9f8bfae693c724120ffc8fb77564f6deb508daf3" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:20 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:13 2008 -0500" }, "message": "svc: Move create logic to common code\n\nMove the svc transport list logic into common transport creation code.\nRefactor this code path to make the flow of control easier to read.\n\nMove the setting and clearing of the BUSY_BIT during transport creation\nto common code.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "9f8bfae693c724120ffc8fb77564f6deb508daf3", "tree": "abcd5cad6a5a4e798d428a8568e5256adc8e1cb8", "parents": [ "c36adb2a7f9132b37d4b669b2e2c04e46d5188b2" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:18 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:13 2008 -0500" }, "message": "svc: Make svc_age_temp_sockets svc_age_temp_transports\n\nThis function is transport independent. Change it to use svc_xprt directly\nand change it\u0027s name to reflect this.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "c36adb2a7f9132b37d4b669b2e2c04e46d5188b2", "tree": "0047a71515d96cdd4085adbd1691232db42c2b9f", "parents": [ "eab996d4aca7a9d8621d2b98c00ce420df85eaed" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:16 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:12 2008 -0500" }, "message": "svc: Make svc_recv transport neutral\n\nAll of the transport field and functions used by svc_recv are now\ntransport independent. Change the svc_recv function to use the svc_xprt\nstructure directly instead of the transport specific svc_sock structure.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "eab996d4aca7a9d8621d2b98c00ce420df85eaed", "tree": "beee1815aebbb5e31628d939cd08330cf3417c3f", "parents": [ "9dbc240f199c16c3c0859c255ad52a663d8ee51d" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:14 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:12 2008 -0500" }, "message": "svc: Make svc_sock_release svc_xprt_release\n\nThe svc_sock_release function only touches transport independent fields.\nChange the function to manipulate svc_xprt directly instead of the transport\ndependent svc_sock structure.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "9dbc240f199c16c3c0859c255ad52a663d8ee51d", "tree": "0e81dd425c36590e65accfe9654d905632783c7f", "parents": [ "8c7b0172a1db8120d25ecb4eff69664c52ee7639" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:12 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:12 2008 -0500" }, "message": "svc: Move the sockaddr information to svc_xprt\n\nThis patch moves the transport sockaddr to the svc_xprt\nstructure. Convenience functions are added to set and\nget the local and remote addresses of a transport from\nthe transport provider as well as determine the length\nof a sockaddr.\n\nA transport is responsible for setting the xpt_local\nand xpt_remote addresses in the svc_xprt structure as\npart of transport creation and xpo_accept processing. This\ncannot be done in a generic way and in fact varies\nbetween TCP, UDP and RDMA. A set of xpo_ functions\n(e.g. getlocalname, getremotename) could have been\nadded but this would have resulted in additional\ncaching and copying of the addresses around. Note that\nthe xpt_local address should also be set on listening\nendpoints; for TCP/RDMA this is done as part of\nendpoint creation.\n\nFor connected transports like TCP and RDMA, the addresses\nnever change and can be set once and copied into the\nrqstp structure for each request. For UDP, however, the\nlocal and remote addresses may change for each request. In\nthis case, the address information is obtained from the\nUDP recvmsg info and copied into the rqstp structure from\nthere.\n\nA svc_xprt_local_port function was also added that returns\nthe local port given a transport. This is used by\nsvc_create_xprt when returning the port associated with\na newly created transport, and later when creating a\ngeneric find transport service to check if a service is\nalready listening on a given port.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "8c7b0172a1db8120d25ecb4eff69664c52ee7639", "tree": "d048ab4c5c378d2a90e5dd52a09dee4e24712cc9", "parents": [ "def13d7401e9b95bbd34c20057ebeb2972708b1b" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:10 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:12 2008 -0500" }, "message": "svc: Make deferral processing xprt independent\n\nThis patch moves the transport independent sk_deferred list to the svc_xprt\nstructure and updates the svc_deferred_req structure to keep pointers to\nsvc_xprt\u0027s directly. The deferral processing code is also moved out of the\ntransport dependent recvfrom functions and into the generic svc_recv path.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "def13d7401e9b95bbd34c20057ebeb2972708b1b", "tree": "afea72afdfe80c645eaf75aa828a49a6e1dec864", "parents": [ "4bc6c497b26a7984cac842a09e2e8f8c46242782" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:08 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:12 2008 -0500" }, "message": "svc: Move the authinfo cache to svc_xprt.\n\nMove the authinfo cache to svc_xprt. This allows both the TCP and RDMA\ntransports to share this logic. A flag bit is used to determine if\nauth information is to be cached or not. Previously, this code looked\nat the transport protocol.\n\nI\u0027ve also changed the spin_lock/unlock logic so that a lock is not taken for\ntransports that are not caching auth info.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "4bc6c497b26a7984cac842a09e2e8f8c46242782", "tree": "4b4d4d700ed6539e3b13bc2b66af4bdf179b35aa", "parents": [ "6bc5ab1367e43e59671d3fd19e6b0d2e4c138323" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:05 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:12 2008 -0500" }, "message": "svc: Remove sk_lastrecv\n\nWith the implementation of the new mark and sweep algorithm for shutting\ndown old connections, the sk_lastrecv field is no longer needed.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "6bc5ab1367e43e59671d3fd19e6b0d2e4c138323", "tree": "37b94ecc396a3e763677ad741c8b8b5f4fa36518", "parents": [ "a6046f71f2b598af241e7496a8ead90f2979224b" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:03 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:12 2008 -0500" }, "message": "svc: Move accept call to svc_xprt_received to common code\n\nNow that the svc_xprt_received function handles transports, the call\nto svc_xprt_received in the xpo_tcp_accept function can be moved to\ncommon code.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "a6046f71f2b598af241e7496a8ead90f2979224b", "tree": "bceb453e9c7aac478a86253528ff2a00b0726fcc", "parents": [ "a50fea26b9d2aa7b66fdd6d9579de10827ec086a" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:08:01 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:12 2008 -0500" }, "message": "svc: Change svc_sock_received to svc_xprt_received and export it\n\nAll fields touched by svc_sock_received are now transport independent.\nChange it to use svc_xprt directly. This function is called from\ntransport dependent code, so export it.\n\nUpdate the comment to clearly state the rules for calling this function.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "a50fea26b9d2aa7b66fdd6d9579de10827ec086a", "tree": "efb7893e6e45b417405e9320d3b82100b1684daf", "parents": [ "f6150c3cab6e788afacb07470be3c6b4a722f1ed" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:59 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:11 2008 -0500" }, "message": "svc: Make svc_send transport neutral\n\nMove the sk_mutex field to the transport independent svc_xprt structure.\nNow all the fields that svc_send touches are transport neutral. Change the\nsvc_send function to use the transport independent svc_xprt directly instead\nof the transport dependent svc_sock structure.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "f6150c3cab6e788afacb07470be3c6b4a722f1ed", "tree": "b770317b97975b5e3f12482d13873bd27cd2cb7e", "parents": [ "7a90e8cc21ad80529b3a3371dc97acc8832cc592" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:57 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:11 2008 -0500" }, "message": "svc: Make the enqueue service transport neutral and export it.\n\nThe svc_sock_enqueue function is now transport independent since all of\nthe fields it touches have been moved to the transport independent svc_xprt\nstructure. Change the function to use the svc_xprt structure directly\ninstead of the transport specific svc_sock structure.\n\nTransport specific data-ready handlers need to call this function, so\nexport it.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "7a90e8cc21ad80529b3a3371dc97acc8832cc592", "tree": "3a5527b0cce3c046067c72705d6acd5d6bc1184b", "parents": [ "7a18208383ab3f3ce4a1f4e0536acc9372523d81" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:55 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:11 2008 -0500" }, "message": "svc: Move sk_reserved to svc_xprt\n\nThis functionally trivial patch moves the sk_reserved field to the\ntransport independent svc_xprt structure.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "7a18208383ab3f3ce4a1f4e0536acc9372523d81", "tree": "851a1cc29d753297c2e7cf4cb4a95c4af7868427", "parents": [ "bb5cf160b282644c4491afbf76fbc66f5dc35030" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:53 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:11 2008 -0500" }, "message": "svc: Make close transport independent\n\nMove sk_list and sk_ready to svc_xprt. This involves close because these\nlists are walked by svcs when closing all their transports. So I combined\nthe moving of these lists to svc_xprt with making close transport independent.\n\nThe svc_force_sock_close has been changed to svc_close_all and takes a list\nas an argument. This removes some svc internals knowledge from the svcs.\n\nThis code races with module removal and transport addition.\n\nThanks to Simon Holm Thøgersen for a compile fix.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\nCc: Simon Holm Thøgersen \u003codie@cs.aau.dk\u003e\n" }, { "commit": "bb5cf160b282644c4491afbf76fbc66f5dc35030", "tree": "76443ea6f87faf4d2e039ca6d2e3a7008261a1d2", "parents": [ "02fc6c36188be0ad19502cfd39266150ffab7603" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:50 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:11 2008 -0500" }, "message": "svc: Move sk_server and sk_pool to svc_xprt\n\nThis is another incremental change that moves transport independent\nfields from svc_sock to the svc_xprt structure. The changes\nshould be functionally null.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "02fc6c36188be0ad19502cfd39266150ffab7603", "tree": "e1d85b49c18944209232bbb1ebaf51001b6af602", "parents": [ "e1b3157f9710622bad6c7747d3b08ed3d2394cf6" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:48 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:11 2008 -0500" }, "message": "svc: Move sk_flags to the svc_xprt structure\n\nThis functionally trivial change moves the transport independent sk_flags\nfield to the transport independent svc_xprt structure.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "e1b3157f9710622bad6c7747d3b08ed3d2394cf6", "tree": "e03687e0363fdb2307f7e4909a735e8d1331050a", "parents": [ "d7c9f1ed972b4a468dd24a2457721704dfe9ca70" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:46 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:11 2008 -0500" }, "message": "svc: Change sk_inuse to a kref\n\nChange the atomic_t reference count to a kref and move it to the\ntransport indepenent svc_xprt structure. Change the reference count\nwrapper names to be generic.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "d7c9f1ed972b4a468dd24a2457721704dfe9ca70", "tree": "40cd2b38db79df4d90753b58789c3e4bc274095f", "parents": [ "b700cbb11fced2a0e953fdd19eac07ffaad86598" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:44 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:09 2008 -0500" }, "message": "svc: Change services to use new svc_create_xprt service\n\nModify the various kernel RPC svcs to use the svc_create_xprt service.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "b700cbb11fced2a0e953fdd19eac07ffaad86598", "tree": "345028d75f049b63bcec574158b94e205e9684bc", "parents": [ "f9f3cc4fae04c87c815a4b473fb577cf74ef27da" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:42 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:09 2008 -0500" }, "message": "svc: Add a generic transport svc_create_xprt function\n\nThe svc_create_xprt function is a transport independent version\nof the svc_makesock function.\n\nSince transport instance creation contains transport dependent and\nindependent components, add an xpo_create transport function. The\ntransport implementation of this function allocates the memory for the\nendpoint, implements the transport dependent initialization logic, and\ncalls svc_xprt_init to initialize the transport independent field (svc_xprt)\nin it\u0027s data structure.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "f9f3cc4fae04c87c815a4b473fb577cf74ef27da", "tree": "906550a4f9db0bf79adea43b3b9ac1fbc2b2c4e6", "parents": [ "44a6995b32eb9b021ee71b279edb84728c9f5160" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:40 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:09 2008 -0500" }, "message": "svc: Move connection limit checking to its own function\n\nMove the code that poaches connections when the connection limit is hit\nto a subroutine to make the accept logic path easier to follow. Since this\nis in the new connection path, it should not be a performance issue.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "44a6995b32eb9b021ee71b279edb84728c9f5160", "tree": "fbe6492dc072aaf80cda94353e2bfce8738802e9", "parents": [ "38a417cc993f4535548e47207f9894e7c27e05e4" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:38 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:09 2008 -0500" }, "message": "svc: Remove unnecessary call to svc_sock_enqueue\n\nThe svc_tcp_accept function calls svc_sock_enqueue after setting the\nSK_CONN bit. This doesn\u0027t actually do anything because the SK_BUSY bit\nis still set. The call is unnecessary anyway because the generic code in\nsvc_recv calls svc_sock_received after calling the accept function.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "38a417cc993f4535548e47207f9894e7c27e05e4", "tree": "f8035bcf6bc9a4831b152f5556b14cb3b48a72b8", "parents": [ "d7979ae4a050a45b78af51832475001b68263d2a" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:36 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:08 2008 -0500" }, "message": "svc: Add xpo_accept transport function\n\nPreviously, the accept logic looked into the socket state to determine\nwhether to call accept or recv when data-ready was indicated on an endpoint.\nSince some transports don\u0027t use sockets, this logic now uses a flag\nbit (SK_LISTENER) to identify listening endpoints. A transport function\n(xpo_accept) allows each transport to define its own accept processing.\nA transport\u0027s initialization logic is reponsible for setting the\nSK_LISTENER bit. I didn\u0027t see any way to do this in transport independent\nlogic since the passive side of a UDP connection doesn\u0027t listen and\nalways recv\u0027s.\n\nIn the svc_recv function, if the SK_LISTENER bit is set, the transport\nxpo_accept function is called to handle accept processing.\n\nNote that all functions are defined even if they don\u0027t make sense\nfor a given transport. For example, accept doesn\u0027t mean anything for\nUDP. The function is defined anyway and bug checks if called. The\nUDP transport should never set the SK_LISTENER bit.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "d7979ae4a050a45b78af51832475001b68263d2a", "tree": "f76bf9dea36d03a1141824202015d26002000589", "parents": [ "323bee32e9bef14c6dd943ecc8e8cd373a9c94d9" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:34 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:08 2008 -0500" }, "message": "svc: Move close processing to a single place\n\nClose handling was duplicated in the UDP and TCP recvfrom\nmethods. This code has been moved to the transport independent\nsvc_recv function.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "323bee32e9bef14c6dd943ecc8e8cd373a9c94d9", "tree": "5779a724dfcbe3aee1f06d9eb989931d1dcfa163", "parents": [ "e831fe65b10199e1e301a7316c66d6ced133712d" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:31 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:08 2008 -0500" }, "message": "svc: Add a transport function that checks for write space\n\nIn order to avoid blocking a service thread, the receive side checks\nto see if there is sufficient write space to reply to the request.\nEach transport has a different mechanism for determining if there is\nenough write space to reply.\n\nThe code that checked for write space was coupled with code that\nchecked for CLOSE and CONN. These checks have been broken out into\nseparate statements to make the code easier to read.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "e831fe65b10199e1e301a7316c66d6ced133712d", "tree": "33436ef94e099e854c4824e78cd62f341e5f357a", "parents": [ "755cceaba7555027e61dfa79f1e55bdfc6906633" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:29 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:08 2008 -0500" }, "message": "svc: Add xpo_prep_reply_hdr\n\nSome transports add fields to the RPC header for replies, e.g. the TCP\nrecord length. This function is called when preparing the reply header\nto allow each transport to add whatever fields it requires.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "755cceaba7555027e61dfa79f1e55bdfc6906633", "tree": "13fa81b19e96af8130414b3535ced72b910a1aef", "parents": [ "5148bf4ebc1f59dc6a0ec43a220c55ff0771246e" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:27 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:08 2008 -0500" }, "message": "svc: Add per-transport delete functions\n\nAdd transport specific xpo_detach and xpo_free functions. The xpo_detach\nfunction causes the transport to stop delivering data-ready events\nand enqueing the transport for I/O.\n\nThe xpo_free function frees all resources associated with the particular\ntransport instance.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "5148bf4ebc1f59dc6a0ec43a220c55ff0771246e", "tree": "d7ba46947483308dc77736335b05d1124befa7c4", "parents": [ "5d137990f5860451a6e0428e0903f62933d05287" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:25 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:08 2008 -0500" }, "message": "svc: Add transport specific xpo_release function\n\nThe svc_sock_release function releases pages allocated to a thread. For\nUDP this frees the receive skb. For RDMA it will post a receive WR\nand bump the client credit count.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "5d137990f5860451a6e0428e0903f62933d05287", "tree": "71f57e8a13138530c8c82f9de19067687d0b428d", "parents": [ "490231558e058547da4ffab6d8ce8e28771749cc" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:23 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:08 2008 -0500" }, "message": "svc: Move sk_sendto and sk_recvfrom to svc_xprt_class\n\nThe sk_sendto and sk_recvfrom are function pointers that allow svc_sock\nto be used for both UDP and TCP. Move these function pointers to the\nsvc_xprt_ops structure.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "490231558e058547da4ffab6d8ce8e28771749cc", "tree": "aac2eef69dbd262a755ee1cafec34787faf5d2f0", "parents": [ "9f29868b491beee706931e0cf875a60cb4688754" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:21 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:08 2008 -0500" }, "message": "svc: Add a max payload value to the transport\n\nThe svc_max_payload function currently looks at the socket type\nto determine the max payload. Add a max payload value to svc_xprt_class\nso it can be returned directly.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "360d873864c8903a650b227758b49dd50e6ecc9f", "tree": "806631491e4848b194abd539293f124b366a49de", "parents": [ "1d8206b97a09e7ff2fbef17d8d1ea008d764eeaa" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Sun Dec 30 21:07:17 2007 -0600" }, "committer": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Fri Feb 01 16:42:07 2008 -0500" }, "message": "svc: Make svc_sock the tcp/udp transport\n\nMake TCP and UDP svc_sock transports, and register them\nwith the svc transport core.\n\nA transport type (svc_sock) has an svc_xprt as its first member,\nand calls svc_xprt_init to initialize this field.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nReviewed-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nReviewed-by: Greg Banks \u003cgnb@sgi.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\n" }, { "commit": "02b3d34631831a19ee691516e233756b270eac6d", "tree": "28ddf5beadfd1f1954ca5ada9ac9d337fa7ce9e2", "parents": [ "ab0049b4a2f66074dff6af851b35bba888f53972" ], "author": { "name": "John Heffner", "email": "jheffner@psc.edu", "time": "Wed Sep 12 10:42:12 2007 +0200" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Wed Oct 10 16:49:00 2007 -0700" }, "message": "[NET] Cleanup: Use sock_owned_by_user() macro\n\nChanges asserts in sunrpc to use sock_owned_by_user() macro instead of\nreferencing sock_lock.owner directly.\n\nSigned-off-by: John Heffner \u003cjheffner@psc.edu\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "172589ccdde41b59861c92c4a971b95514ef24e3", "tree": "ae775e6db4cb85aad1c74b6d93ba359f9dfe88ea", "parents": [ "c45248c70125cc374fdf264659643276c72801bf" ], "author": { "name": "Ilpo Järvinen", "email": "ilpo.jarvinen@helsinki.fi", "time": "Tue Aug 28 15:50:33 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Wed Oct 10 16:48:37 2007 -0700" }, "message": "[NET]: DIV_ROUND_UP cleanup (part two)\n\nHopefully captured all single statement cases under net/. I\u0027m\nnot too sure if there is some policy about #includes that are\n\"guaranteed\" (ie., in the current tree) to be available through\nsome other #included header, so I just added linux/kernel.h to\neach changed file that didn\u0027t #include it previously.\n\nSigned-off-by: Ilpo Järvinen \u003cilpo.jarvinen@helsinki.fi\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "9db619e66503494e41159de3c76fafabe80d016b", "tree": "8f7d2ba98c216a772b5a0e5ab89708dcaceaa1e3", "parents": [ "f685ddaf0fc9b9f53eb9346c858664776becf5d9" ], "author": { "name": "Wolfgang Walter", "email": "wolfgang.walter@studentenwerk.mhn.de", "time": "Thu Sep 20 15:51:46 2007 -0400" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Sep 20 13:15:57 2007 -0700" }, "message": "rpc: fix garbage in printk in svc_tcp_accept()\n\nwe upgraded the kernel of a nfs-server from 2.6.17.11 to 2.6.22.6. Since\nthen we get the message\n\nlockd: too many open TCP sockets, consider increasing the number of nfsd threads\nlockd: last TCP connect from ^\\\\236^\\É^D\n\nThese random characters in the second line are caused by a bug in\nsvc_tcp_accept.\n\n(Note: there are two previous __svc_print_addr(sin, buf, sizeof(buf))\ncalls in this function, either of which would initialize buf correctly;\nbut both are inside \"if\"\u0027s and are not necessarily executed. This is\nless obvious in the second case, which is inside a dprintk(), which is a\nmacro which expands to an if statement.)\n\nSigned-off-by: Wolfgang Walter \u003cwolfgang.walter@studentenwerk.mhn.de\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7a1fa065a0264f6b3d3003ba5635289f6583c478", "tree": "c8193e1c65a7b2ced3366a02668261a553150ff4", "parents": [ "2123a09f3f129f4d56f59026ec63e5990f86db2f" ], "author": { "name": "Neil Brown", "email": "neilb@suse.de", "time": "Fri Sep 14 10:28:08 2007 -0400" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Sep 14 13:58:11 2007 -0700" }, "message": "Correctly close old nfsd/lockd sockets.\n\nCommit aaf68cfbf2241d24d46583423f6bff5c47e088b3 added a bias\nto sk_inuse, so this test for an unused socket now fails. So no\nsockets get closed because they are old (they might get closed\nif the client closed them).\n\nThis bug has existed since 2.6.21-rc1.\n\nThanks to Wolfgang Walter for finding and reporting the bug.\n\nCc: Wolfgang Walter \u003cwolfgang.walter@studentenwerk.mhn.de\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "582ee43dad8e411513a74f2d801255dcffc6d29e", "tree": "bf822fd3dd9b889531134c7004e9f42b134485f1", "parents": [ "704eae1f32274c0435f7f3924077afdb811edd1d" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Thu Jul 26 17:33:39 2007 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Jul 26 11:11:56 2007 -0700" }, "message": "net/* misc endianness annotations\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a97476926ec061f90b77da478620ea6dc71a3237", "tree": "0b6ad42f5cca4484ce702cf3fcb016b52ec17cef", "parents": [ "96802a095171f5b35cf0e1e0d4be943e6696a253" ], "author": { "name": "Frank van Maarseveen", "email": "frankvm@frankvm.com", "time": "Mon Jul 09 22:21:39 2007 +0200" }, "committer": { "name": "Trond Myklebust", "email": "Trond.Myklebust@netapp.com", "time": "Tue Jul 10 23:40:49 2007 -0400" }, "message": "SUNRPC server: record the destination address of a request\n\nSave the destination address of an incoming request over TCP like is\ndone already for UDP. It is necessary later for callbacks by the server.\n\nSigned-off-by: Frank van Maarseveen \u003cfrankvm@frankvm.com\u003e\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\n" }, { "commit": "05ed690efbb28b54af79f97af8c9705e82a6fbd7", "tree": "f6c5a437cb8f8c0a666cd1f1a13e39d1fa354146", "parents": [ "c5e434c98b49f4877ea1614a629499e082b1a818" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed May 09 02:34:55 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed May 09 12:30:54 2007 -0700" }, "message": "knfsd: simplify a \u0027while\u0027 condition in svcsock.c\n\nThis while loop has an overly complex condition, which performs a couple of\nassignments. This hurts readability.\n\nWe don\u0027t really need a loop at all. We can just return -EAGAIN and (providing\nwe set SK_DATA), the function will be called again.\n\nSo discard the loop, make the complex conditional become a few clear function\ncalls, and hopefully improve readability.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7ac1bea5507218da03f6005d228789da5a831c3f", "tree": "43c0a68d468352f8ca1f42ada7970e3a97411f5b", "parents": [ "f34b95689d2ce001c157b1604289ff240b4bdee0" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed May 09 02:34:48 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed May 09 12:30:54 2007 -0700" }, "message": "knfsd: rename sk_defer_lock to sk_lock\n\nNow that sk_defer_lock protects two different things, make the name more\ngeneric.\n\nAlso don\u0027t bother with disabling _bh as the lock is only ever taken from\nprocess context.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b7aa0bf70c4afb9e38be25f5c0922498d0f8684c", "tree": "4bc9d61031f4eb40d73887d6bde09e7d6bf2b259", "parents": [ "3927f2e8f9afa3424bb51ca81f7abac01ffd0005" ], "author": { "name": "Eric Dumazet", "email": "dada1@cosmosbay.com", "time": "Thu Apr 19 16:16:32 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Wed Apr 25 22:23:34 2007 -0700" }, "message": "[NET]: convert network timestamps to ktime_t\n\nWe currently use a special structure (struct skb_timeval) and plain\n\u0027struct timeval\u0027 to store packet timestamps in sk_buffs and struct\nsock.\n\nThis has some drawbacks :\n- Fixed resolution of micro second.\n- Waste of space on 64bit platforms where sizeof(struct timeval)\u003d16\n\nI suggest using ktime_t that is a nice abstraction of high resolution\ntime services, currently capable of nanosecond resolution.\n\nAs sizeof(ktime_t) is 8 bytes, using ktime_t in \u0027struct sock\u0027 permits\na 8 byte shrink of this structure on 64bit architectures. Some other\nstructures also benefit from this size reduction (struct ipq in\nipv4/ip_fragment.c, struct frag_queue in ipv6/reassembly.c, ...)\n\nOnce this ktime infrastructure adopted, we can more easily provide\nnanosecond resolution on top of it. (ioctl SIOCGSTAMPNS and/or\nSO_TIMESTAMPNS/SCM_TIMESTAMPNS)\n\nNote : this patch includes a bug correction in\ncompat_sock_get_timestamp() where a \"err \u003d 0;\" was missing (so this\nsyscall returned -ENOENT instead of 0)\n\nSigned-off-by: Eric Dumazet \u003cdada1@cosmosbay.com\u003e\nCC: Stephen Hemminger \u003cshemminger@linux-foundation.org\u003e\nCC: John find \u003clinux.kernel@free.fr\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "bc375ea7efcda0450b7cba9b3514e76d2e1cea79", "tree": "321c7a881214991758b66d6877cae4cd0d2071c2", "parents": [ "1d51c69fb6e61054cd6cc485f9bef77d19d82751" ], "author": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Thu Apr 12 13:35:59 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Thu Apr 12 13:35:59 2007 -0700" }, "message": "[SUNRPC]: Make sure on-stack cmsg buffer is properly aligned.\n\nBased upon a report from Meelis Roos.\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "418106d6248618bca1add65168a82974c72206db", "tree": "fe8b9484c06814c8d11f4e114db460ebbe613f3c", "parents": [ "5792a2856a63cdc568e08a7d6f9b2413d9217b3e" ], "author": { "name": "Adrian Bunk", "email": "bunk@stusta.de", "time": "Wed Apr 04 19:08:21 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Apr 04 21:12:47 2007 -0700" }, "message": "[PATCH] net/sunrpc/svcsock.c: fix a check\n\nThe return value of kernel_recvmsg() should be assigned to \"err\", not\ncompared with the random value of a never initialized \"err\" (and the \"\u003c 0\"\ncheck wrongly always returned false since \u003d\u003d comparisons never have a\nresult \u003c 0).\n\nSpotted by the Coverity checker.\n\nSigned-off-by: Adrian Bunk \u003cbunk@stusta.de\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "cda1fd4abd773216a888487af0170d0cc3d50454", "tree": "aed6662bab1789a1698644f2e1d0db4255ecad67", "parents": [ "5a05ed73e1abfd7e0e7d474817245861deaa18af" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 06 01:42:22 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Mar 06 09:30:26 2007 -0800" }, "message": "[PATCH] knfsd: fix recently introduced problem with shutting down a busy NFS server\n\nWhen the last thread of nfsd exits, it shuts down all related sockets. It\ncurrently uses svc_close_socket to do this, but that only is immediately\neffective if the socket is not SK_BUSY.\n\nIf the socket is busy - i.e. if a request has arrived that has not yet been\nprocesses - svc_close_socket is not effective and the shutdown process spins.\n\nSo create a new svc_force_close_socket which removes the SK_BUSY flag is set\nand then calls svc_close_socket.\n\nAlso change some open-codes loops in svc_destroy to use\nlist_for_each_entry_safe.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "5a05ed73e1abfd7e0e7d474817245861deaa18af", "tree": "df2e9b2717719dc900be6a11db4cb33d4b237aae", "parents": [ "7a37f5787e76bf1765c1add3a9a7163f841a28bb" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 06 01:42:22 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Mar 06 09:30:26 2007 -0800" }, "message": "[PATCH] knfsd: remove CONFIG_IPV6 ifdefs from sunrpc server code\n\nThey don\u0027t really save that much, and aren\u0027t worth the hassle.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7a37f5787e76bf1765c1add3a9a7163f841a28bb", "tree": "f67e69f082bf6a6083e3b0cff089d1bba1d1da0c", "parents": [ "0e8cd28a084691587549630dce728661401d343b" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 06 01:42:21 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Mar 06 09:30:26 2007 -0800" }, "message": "[PATCH] knfsd: use recv_msg to get peer address for NFSD instead of code-copying\n\nThe sunrpc server code needs to know the source and destination address for\nUDP packets so it can reply properly. It currently copies code out of the\nnetwork stack to pick the pieces out of the skb. This is ugly and causes\ncompile problems with the IPv6 stuff.\n\nSo, rip that out and use recv_msg instead. This is a much cleaner interface,\nbut has a slight cost in that the checksum is now checked before the copy, so\nwe don\u0027t benefit from doing both at the same time. This can probably be\nfixed.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "77f1f67a1a56defa210c3d8857f3e5eee3990a99", "tree": "9d34af393db31a566c01f915074ff070c644ecc1", "parents": [ "95756482c9bfa375418c5a32455494a3042f65cd" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Feb 12 00:53:39 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:36 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: fix up svc_create_socket() to take a sockaddr struct + length\n\nReplace existing svc_create_socket() API to allow callers to pass addresses\nlarger than a sockaddr_in.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Aurelien Charbon \u003caurelien.charbon@ext.bull.net\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "95756482c9bfa375418c5a32455494a3042f65cd", "tree": "1c7583a43df17591cae77af601143509ab68c2b1", "parents": [ "cdd88b9f3ed5013de0f1085e0e2f9123c798609d" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Feb 12 00:53:38 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:36 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: support IPv6 addresses in RPC server\u0027s UDP receive path\n\nAdd support for IPv6 addresses in the RPC server\u0027s UDP receive path.\n\n[akpm@linux-foundation.org: cleanups]\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Aurelien Charbon \u003caurelien.charbon@ext.bull.net\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "cdd88b9f3ed5013de0f1085e0e2f9123c798609d", "tree": "2e2fba732f54c487461ad0da81bc8f11daea2786", "parents": [ "bcdb81ae29091f6a66369aabfd8324e4a53d05dc" ], "author": { "name": "akpm@linux-foundation.org", "email": "akpm@linux-foundation.org", "time": "Mon Feb 12 00:53:38 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:36 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: Support IPv6 addresses in svc_tcp_accept\n\nModify svc_tcp_accept to support connecting on IPv6 sockets.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Aurelien Charbon \u003caurelien.charbon@ext.bull.net\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "bcdb81ae29091f6a66369aabfd8324e4a53d05dc", "tree": "ce70eed085bd56c0b1eaffa838ca27bec94e1345", "parents": [ "b92503b25c3f794cff5f96626ea3ecba8d10d254" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Feb 12 00:53:37 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:36 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: add a \"generic\" function to see if the peer uses a secure port\n\nThe only reason svcsock.c looks at a sockaddr\u0027s port is to check whether the\nremote peer is connecting from a privileged port. Refactor this check to hide\nprocessing that is specific to address format.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Aurelien Charbon \u003caurelien.charbon@ext.bull.net\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b92503b25c3f794cff5f96626ea3ecba8d10d254", "tree": "a3bd2e04e1f748f0bdd1ce54b5ec79a393815efa", "parents": [ "73df0dbaff8d0853387e140f52b6250c486b18a1" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Feb 12 00:53:36 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:36 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: teach svc_sendto() to deal with IPv6 addresses\n\nCMSG_DATA comes in different sizes, depending on address family.\n\n[akpm@linux-foundation.org: remove unneeded do/while (0)]\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Aurelien Charbon \u003caurelien.charbon@ext.bull.net\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "73df0dbaff8d0853387e140f52b6250c486b18a1", "tree": "f1b3a669b47744b982ba5e25af329712abd36bf5", "parents": [ "27459f0940e16c68e080f5fc7e85aa9eb3f74528" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Feb 12 00:53:35 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:36 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: Make rq_daddr field address-version independent\n\nThe rq_daddr field must support larger addresses.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Aurelien Charbon \u003caurelien.charbon@ext.bull.net\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "27459f0940e16c68e080f5fc7e85aa9eb3f74528", "tree": "f13cd1f2005dda2b6115e2afbc49e1271b0d374b", "parents": [ "2442222283918c2d1c20ae651d95fe168757938b" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Feb 12 00:53:34 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:36 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: Provide room in svc_rqst for larger addresses\n\nExpand the rq_addr field to allow it to contain larger addresses.\n\nSpecifically, we replace a \u0027sockaddr_in\u0027 with a \u0027sockaddr_storage\u0027, then\neverywhere the \u0027sockaddr_in\u0027 was referenced, we use instead an accessor\nfunction (svc_addr_in) which safely casts the _storage to _in.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Aurelien Charbon \u003caurelien.charbon@ext.bull.net\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "2442222283918c2d1c20ae651d95fe168757938b", "tree": "f4e120320c5b9538b4626e576fce67db201c4cc7", "parents": [ "ad06e4bd62351bc569cca0f25d68c58dbd298146" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Feb 12 00:53:33 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:35 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: Use sockaddr_storage to store address in svc_deferred_req\n\nSockaddr_storage will allow us to store arbitrary socket addresses in the\nsvc_deferred_req struct.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Aurelien Charbon \u003caurelien.charbon@ext.bull.net\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ad06e4bd62351bc569cca0f25d68c58dbd298146", "tree": "82024c01e61de32af17d3b67eac0bb93138a2954", "parents": [ "1ba951053f07187f6e77be664a4b6f8bf0ba7ae4" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Feb 12 00:53:32 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:35 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: Add a function to format the address in an svc_rqst for printing\n\nThere are loads of places where the RPC server assumes that the rq_addr fields\ncontains an IPv4 address. Top among these are error and debugging messages\nthat display the server\u0027s IP address.\n\nLet\u0027s refactor the address printing into a separate function that\u0027s smart\nenough to figure out the difference between IPv4 and IPv6 addresses.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Aurelien Charbon \u003caurelien.charbon@ext.bull.net\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "1ba951053f07187f6e77be664a4b6f8bf0ba7ae4", "tree": "68e6e183de677269078de1b2ce6efc88249a3b33", "parents": [ "067d7817310569f7b76ca08c4d071ca95ad4c1d3" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Feb 12 00:53:31 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:35 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: Don\u0027t set msg_name and msg_namelen when calling sock_recvmsg\n\nClean-up: msg_name and msg_namelen are not used by sock_recvmsg, so don\u0027t\nbother to set them in svc_recvfrom.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "067d7817310569f7b76ca08c4d071ca95ad4c1d3", "tree": "ee931bac235a3f9d0083edd7c00340121fe32767", "parents": [ "e79eff1f90826b207b1152fc87aa97fa74fb7f9c" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Feb 12 00:53:30 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:35 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: Cache remote peer\u0027s address in svc_sock\n\nThe remote peer\u0027s address won\u0027t change after the socket has been accepted. We\ndon\u0027t need to call -\u003egetname on every incoming request.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Aurelien Charbon \u003caurelien.charbon@ext.bull.net\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e79eff1f90826b207b1152fc87aa97fa74fb7f9c", "tree": "8cd39c30c01fdbca8c93652512441b7dda666eea", "parents": [ "482fb94e1b0c2efe8258334aa2a68d4f4a91de9c" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Feb 12 00:53:30 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:35 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: aplit svc_sock_enqueue out of svc_setup_socket\n\nRather than calling svc_sock_enqueue at the end of svc_setup_socket, we now\ncall it (via svc_sock_recieved) after calling svc_setup_socket at each call\nsite.\n\nWe do this because a subsequent patch will insert some code between the two\ncalls at one call site.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "482fb94e1b0c2efe8258334aa2a68d4f4a91de9c", "tree": "84353b34bb5ea02df98b598fff037cf1da20d6b0", "parents": [ "6b174337e5126de834a971d3edc3681bbfa45e2c" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Feb 12 00:53:29 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:35 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: allow creating an RPC service without registering with portmapper\n\nSometimes we need to create an RPC service but not register it with the local\nportmapper. NFSv4 delegation callback, for example.\n\nChange the svc_makesock() API to allow optionally creating temporary or\npermanent sockets, optionally registering with the local portmapper, and make\nit return the ephemeral port of the new socket.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Aurelien Charbon \u003caurelien.charbon@ext.bull.net\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6b174337e5126de834a971d3edc3681bbfa45e2c", "tree": "b1dc3e0ecd82353896b07c433f98f547abc5adc2", "parents": [ "f85aaeba458fda1de199a73566c641516e9a935d" ], "author": { "name": "Chuck Lever", "email": "chuck.lever@oracle.com", "time": "Mon Feb 12 00:53:28 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 12 09:48:35 2007 -0800" }, "message": "[PATCH] knfsd: SUNRPC: update internal API: separate pmap register and temp sockets\n\nCurrently in the RPC server, registering with the local portmapper and\ncreating \"permanent\" sockets are tied together. Expand the internal APIs to\nallow these two socket characteristics to be separately specified.\n\nThis will be externalized in the next patch.\n\nSigned-off-by: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Aurelien Charbon \u003caurelien.charbon@ext.bull.net\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "cca5172a7ec10dfdb0b787cd8e9d5b0b8f179793", "tree": "1b9e86cf95ab5e1e2b3180ebe59be2a05ebbe1bf", "parents": [ "d808ad9ab8b1109239027c248c4652503b9d3029" ], "author": { "name": "YOSHIFUJI Hideaki", "email": "yoshfuji@linux-ipv6.org", "time": "Fri Feb 09 15:38:13 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Sat Feb 10 23:20:13 2007 -0800" }, "message": "[NET] SUNRPC: Fix whitespace errors.\n\nSigned-off-by: YOSHIFUJI Hideaki \u003cyoshfuji@linux-ipv6.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "aaf68cfbf2241d24d46583423f6bff5c47e088b3", "tree": "65ca14b85d28b12da097d7d187cebfef88b5ba3a", "parents": [ "387bb17374c5fa057462d00d4ba941d49f45de4d" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Feb 08 14:20:30 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Feb 09 09:25:47 2007 -0800" }, "message": "[PATCH] knfsd: fix a race in closing NFSd connections\n\nIf you lose this race, it can iput a socket inode twice and you get a BUG\nin fs/inode.c\n\nWhen I added the option for user-space to close a socket, I added some\ncruft to svc_delete_socket so that I could call that function when closing\na socket per user-space request.\n\nThis was the wrong thing to do. I should have just set SK_CLOSE and let\nnormal mechanisms do the work.\n\nNot only wrong, but buggy. The locking is all wrong and it openned up a\nrace where-by a socket could be closed twice.\n\nSo this patch:\n Introduces svc_close_socket which sets SK_CLOSE then either leave\n the close up to a thread, or calls svc_delete_socket if it can\n get SK_BUSY.\n\n Adds a bias to sk_busy which is removed when SK_DEAD is set,\n This avoid races around shutting down the socket.\n\n Changes several \u0027spin_lock\u0027 to \u0027spin_lock_bh\u0027 where the _bh\n was missing.\n\nBugzilla-url: http://bugzilla.kernel.org/show_bug.cgi?id\u003d7916\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "34e9a63b4f3e169b583f6ba2e26356ecbf932fba", "tree": "445562aa7159ef7ec3d29f8e1cc18d578d9bfcae", "parents": [ "d019bcf0eb9a55c51f1c57659f923d356b4675e1" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Jan 29 13:19:52 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Jan 30 08:26:45 2007 -0800" }, "message": "[PATCH] knfsd: ratelimit some nfsd messages that are triggered by external events\n\nAlso remove {NFSD,RPC}_PARANOIA as having the defines doesn\u0027t really add\nanything.\n\nThe printks covered by RPC_PARANOIA were triggered by badly formatted\npackets and so should be ratelimited.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "250f3915183d377d36e012bac9caa7345ce465b8", "tree": "e7fd20dfa79a8b4f6435083bf48f4cd3d1836cbf", "parents": [ "1a8eff6d977c28162c61c9532ca58634e7090b69" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Fri Jan 26 00:56:59 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Jan 26 13:50:59 2007 -0800" }, "message": "[PATCH] knfsd: fix an NFSD bug with full sized, non-page-aligned reads\n\nNFSd assumes that largest number of pages that will be needed for a\nrequest+response is 2+N where N pages is the size of the largest permitted\nread/write request. The \u00272\u0027 are 1 for the non-data part of the request, and 1\nfor the non-data part of the reply.\n\nHowever, when a read request is not page-aligned, and we choose to use\n-\u003esendfile to send it directly from the page cache, we may need N+1 pages to\nhold the whole reply. This can overflow and array and cause an Oops.\n\nThis patch increases size of the array for holding pages by one and makes sure\nthat entry is NULL when it is not in use.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ed07536ed6731775219c1df7fa26a7588753e693", "tree": "c539d80fe50f28d4e294850bb33be810f46fd515", "parents": [ "b9d85b08c689dbf54b9943a02f73cb54c2b0fccf" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Wed Dec 06 20:35:24 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Thu Dec 07 08:39:30 2006 -0800" }, "message": "[PATCH] lockdep: annotate nfs/nfsd in-kernel sockets\n\nStick NFS sockets in their own class to avoid some lockdep warnings. NFS\nsockets are never exposed to user-space, and will hence not trigger certain\ncode paths that would otherwise pose deadlock scenarios.\n\n[akpm@osdl.org: cleanups]\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Steven Dickson \u003cSteveD@redhat.com\u003e\nAcked-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Trond Myklebust \u003ctrond.myklebust@fys.uio.no\u003e\nAcked-by: Neil Brown \u003cneilb@suse.de\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\n[ Fixed patch corruption by quilt, pointed out by Peter Zijlstra ]\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "7dfb71030f7636a0d65200158113c37764552f93", "tree": "276b812903d377b16d8828e888552fd256f48aab", "parents": [ "8a05aac2631aa0e6494d9dc990f8c68ed8b8fde7" ], "author": { "name": "Nigel Cunningham", "email": "ncunningham@linuxmail.org", "time": "Wed Dec 06 20:34:23 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Thu Dec 07 08:39:27 2006 -0800" }, "message": "[PATCH] Add include/linux/freezer.h and move definitions from sched.h\n\nMove process freezing functions from include/linux/sched.h to freezer.h, so\nthat modifications to the freezer or the kernel configuration don\u0027t require\nrecompiling just about everything.\n\n[akpm@osdl.org: fix ueagle driver]\nSigned-off-by: Nigel Cunningham \u003cnigel@suspend2.net\u003e\nCc: \"Rafael J. Wysocki\" \u003crjw@sisk.pl\u003e\nCc: Pavel Machek \u003cpavel@ucw.cz\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "202dd450246cd658e298a86dddca5592fcb898cd", "tree": "3cea5cde79fcd87eaffaa4d38cb813aaf845ecf9", "parents": [ "3f4b23e9833f0816b57d07401eac5e184b627fd7" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Sun Oct 29 22:57:57 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Oct 30 12:12:21 2006 -0800" }, "message": "[PATCH] fix \"sunrpc: fix refcounting problems in rpc servers\"\n\n- printk should remain dprintk\n\n- fix coding-style.\n\nCc: Neil Brown \u003cneilb@suse.de\u003e\nCc: Trond Myklebust \u003ctrond.myklebust@fys.uio.no\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "d6740df98e12a8e49ef3a699dcc1e2913f22c51b", "tree": "ded79841a8570d3a3aa46154f3bfc4eaa21900d9", "parents": [ "2b52c9590d5ad2fb67b720ec12018dd2cf061480" ], "author": { "name": "Neil Brown", "email": "neilb@suse.de", "time": "Sun Oct 29 22:46:45 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Oct 30 12:08:42 2006 -0800" }, "message": "[PATCH] sunrpc: fix refcounting problems in rpc servers\n\nA recent patch fixed a problem which would occur when the refcount on an\nauth_domain reached zero. This problem has not been reported in practice\ndespite existing in two major kernel releases because the refcount can\nnever reach zero.\n\nThis patch fixes the problems that stop the refcount reaching zero.\n\n1/ We were adding to the refcount when inserting in the hash table,\n but only removing from the hashtable when the refcount reached zero.\n Obviously it never would. So don\u0027t count the implied reference of\n being in the hash table.\n\n2/ There are two paths on which a socket can be destroyed. One called\n svcauth_unix_info_release(). The other didn\u0027t. So when the other was\n taken, we can lose a reference to an ip_map which in-turn holds a\n reference to an auth_domain\n\n So unify the exit paths into svc_sock_put. This highlights the fact\n that svc_delete_socket has slightly odd semantics - it does not drop\n a reference but probably should. Fixing this need a bit more\n thought and testing.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nCc: Trond Myklebust \u003ctrond.myklebust@fys.uio.no\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1a047060a99f274a7c52cfea8159e4142a14b8a7", "tree": "5f9754ea24794b1346dc257b3a8702fa958785e8", "parents": [ "e05d722e4555cd54677b4c8431d9e81fd047ef7a" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Oct 19 23:29:13 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Oct 20 10:26:44 2006 -0700" }, "message": "[PATCH] knfsd: fix race that can disable NFS server\n\nThis patch is suitable for just about any 2.6 kernel. It should go in\n2.6.19 and 2.6.18.2 and possible even the .17 and .16 stable series.\n\nThis is a long standing bug that seems to have only recently become\napparent, presumably due to increasing use of NFS over TCP - many\ndistros seem to be making it the default.\n\nThe SK_CONN bit gets set when a listening socket may be ready\nfor an accept, just as SK_DATA is set when data may be available.\n\nIt is entirely possible for svc_tcp_accept to be called with neither\nof these set. It doesn\u0027t happen often but there is a small race in\nsvc_sock_enqueue as SK_CONN and SK_DATA are tested outside the\nspin_lock. They could be cleared immediately after the test and\nbefore the lock is gained.\n\nThis normally shouldn\u0027t be a problem. The sockets are non-blocking so\ntrying to read() or accept() when ther is nothing to do is not a problem.\n\nHowever: svc_tcp_recvfrom makes the decision \"Should I accept() or\nshould I read()\" based on whether SK_CONN is set or not. This usually\nworks but is not safe. The decision should be based on whether it is\na TCP_LISTEN socket or a TCP_CONNECTED socket.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nCc: Adrian Bunk \u003cbunk@stusta.de\u003e\nCc: \u003cstable@kernel.org\u003e\nCc: Trond Myklebust \u003ctrond.myklebust@fys.uio.no\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "c6b0a9f87b82f25fa35206ec04b5160372eabab4", "tree": "849ed55115c95a86a3d164d674c178f9504750a5", "parents": [ "5842730de179405d80649231faa0b3f254477434" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Fri Oct 06 00:44:05 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Oct 06 08:53:41 2006 -0700" }, "message": "[PATCH] knfsd: tidy up up meaning of \u0027buffer size\u0027 in nfsd/sunrpc\n\nThere is some confusion about the meaning of \u0027bufsz\u0027 for a sunrpc server.\nIn some cases it is the largest message that can be sent or received. In\nother cases it is the largest \u0027payload\u0027 that can be included in a NFS\nmessage.\n\nIn either case, it is not possible for both the request and the reply to be\nthis large. One of the request or reply may only be one page long, which\nfits nicely with NFS.\n\nSo we remove \u0027bufsz\u0027 and replace it with two numbers: \u0027max_payload\u0027 and\n\u0027max_mesg\u0027. Max_payload is the size that the server requests. It is used\nby the server to check the max size allowed on a particular connection:\ndepending on the protocol a lower limit might be used.\n\nmax_mesg is the largest single message that can be sent or received. It is\ncalculated as the max_payload, rounded up to a multiple of PAGE_SIZE, and\nwith PAGE_SIZE added to overhead. Only one of the request and reply may be\nthis size. The other must be at most one page.\n\nCc: Greg Banks \u003cgnb@sgi.com\u003e\nCc: \"J. Bruce Fields\" \u003cbfields@fieldses.org\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "7b2b1fee30df7e2165525cd03f7d1d01a3a56794", "tree": "71740fb9ea88465b54c52d998eadd012a6f8f4a6", "parents": [ "fce1456a19f5c08b688c29f00ef90fdfa074c79b" ], "author": { "name": "Greg Banks", "email": "gnb@melbourne.sgi.com", "time": "Wed Oct 04 02:15:50 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Oct 04 07:55:16 2006 -0700" }, "message": "[PATCH] knfsd: knfsd: cache ipmap per TCP socket\n\nSpeed up high call-rate workloads by caching the struct ip_map for the peer on\nthe connected struct svc_sock instead of looking it up in the ip_map cache\nhashtable on every call. This helps workloads using AUTH_SYS authentication\nover TCP.\n\nTesting was on a 4 CPU 4 NIC Altix using 4 IRIX clients, each with 16\nsynthetic client threads simulating an rsync (i.e. recursive directory\nlisting) workload reading from an i386 RH9 install image (161480 regular files\nin 10841 directories) on the server. That tree is small enough to fill in the\nserver\u0027s RAM so no disk traffic was involved. This setup gives a sustained\ncall rate in excess of 60000 calls/sec before being CPU-bound on the server.\n\nProfiling showed strcmp(), called from ip_map_match(), was taking 4.8% of each\nCPU, and ip_map_lookup() was taking 2.9%. This patch drops both contribution\ninto the profile noise.\n\nNote that the above result overstates this value of this patch for most\nworkloads. The synthetic clients are all using separate IP addresses, so\nthere are 64 entries in the ip_map cache hash. Because the kernel measured\ncontained the bug fixed in commit\n\ncommit 1f1e030bf75774b6a283518e1534d598e14147d4\n\nand was running on 64bit little-endian machine, probably all of those 64\nentries were on a single chain, thus increasing the cost of ip_map_lookup().\n\nWith a modern kernel you would need more clients to see the same amount of\nperformance improvement. This patch has helped to scale knfsd to handle a\ndeployment with 2000 NFS clients.\n\nSigned-off-by: Greg Banks \u003cgnb@melbourne.sgi.com\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "3cc03b164cf01c6f36e64720b58610d292fb26f7", "tree": "b558e11a087945ad5b9a1a25483aa2acc8d93fbb", "parents": [ "4452435948424e5322c2a2fefbdc2cf3732cc45d" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Oct 04 02:15:47 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Oct 04 07:55:15 2006 -0700" }, "message": "[PATCH] knfsd: Avoid excess stack usage in svc_tcp_recvfrom\n\n.. by allocating the array of \u0027kvec\u0027 in \u0027struct svc_rqst\u0027.\n\nAs we plan to increase RPCSVC_MAXPAGES from 8 upto 256, we can no longer\nallocate an array of this size on the stack. So we allocate it in \u0027struct\nsvc_rqst\u0027.\n\nHowever svc_rqst contains (indirectly) an array of the same type and size\n(actually several, but they are in a union). So rather than waste space, we\nmove those arrays out of the separately allocated union and into svc_rqst to\nshare with the kvec moved out of svc_tcp_recvfrom (various arrays are used at\ndifferent times, so there is no conflict).\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "4452435948424e5322c2a2fefbdc2cf3732cc45d", "tree": "d2082c68d33298e85298852cafde7999ccca3364", "parents": [ "5680c44632053a6c9464bca43083f01776d318da" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Oct 04 02:15:46 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Oct 04 07:55:15 2006 -0700" }, "message": "[PATCH] knfsd: Replace two page lists in struct svc_rqst with one\n\nWe are planning to increase RPCSVC_MAXPAGES from about 8 to about 256. This\nmeans we need to be a bit careful about arrays of size RPCSVC_MAXPAGES.\n\nstruct svc_rqst contains two such arrays. However the there are never more\nthat RPCSVC_MAXPAGES pages in the two arrays together, so only one array is\nneeded.\n\nThe two arrays are for the pages holding the request, and the pages holding\nthe reply. Instead of two arrays, we can simply keep an index into where the\nfirst reply page is.\n\nThis patch also removes a number of small inline functions that probably\nserver to obscure what is going on rather than clarify it, and opencode the\nneeded functionality.\n\nAlso remove the \u0027rq_restailpage\u0027 variable as it is *always* 0. i.e. if the\nresponse \u0027xdr\u0027 structure has a non-empty tail it is always in the same pages\nas the head.\n\n check counters are initilised and incr properly\n check for consistant usage of ++ etc\n maybe extra some inlines for common approach\n general review\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nCc: Magnus Maatta \u003cnovell@kiruna.se\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "5680c44632053a6c9464bca43083f01776d318da", "tree": "220f7bcb0168972bbc2ce804074f42b5470a1e15", "parents": [ "cda9e0cd8a6b30ccc32edced066c378fbd87003d" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Oct 04 02:15:45 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Oct 04 07:55:15 2006 -0700" }, "message": "[PATCH] knfsd: Fixed handling of lockd fail when adding nfsd socket\n\nArrgg.. We cannot \u0027lockd_up\u0027 before \u0027svc_addsock\u0027 as we don\u0027t know the\nprotocol yet.... So switch it around again and save the name of the created\nsockets so that it can be closed if lock_up fails.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "37a034729ae611295bbb8e925333d4d54d7c1ebc", "tree": "219882844fd21fc65eb8673677e7d37a1ff463a2", "parents": [ "7ed94296a660a61989b5d54f0c4bb804f30567d3" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Oct 04 02:15:44 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Oct 04 07:55:15 2006 -0700" }, "message": "[PATCH] knfsd: call lockd_down when closing a socket via a write to nfsd/portlist\n\nThe refcount that nfsd holds on lockd is based on the number of open sockets.\nSo when we close a socket, we should decrement the ref (with lockd_down).\n\nCurrently when a socket is closed via writing to the portlist file, that\ndoesn\u0027t happen.\n\nSo: make sure we get an error return if the socket that was requested does is\nnot found, and call lockd_down if it was.\n\nCc: \"J. Bruce Fields\" \u003cbfields@fieldses.org\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "bfd241600a3b0db4fe43c859f1460d0a958d924a", "tree": "7f04604adee7249e686d1db0cac93f1fee8bc5b6", "parents": [ "eec09661dc82e90a31051d045a94026a91aceb82" ], "author": { "name": "Greg Banks", "email": "gnb@melbourne.sgi.com", "time": "Mon Oct 02 02:18:01 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Oct 02 07:57:20 2006 -0700" }, "message": "[PATCH] knfsd: make rpc threads pools numa aware\n\nActually implement multiple pools. On NUMA machines, allocate a svc_pool per\nNUMA node; on SMP a svc_pool per CPU; otherwise a single global pool. Enqueue\nsockets on the svc_pool corresponding to the CPU on which the socket bh is run\n(i.e. the NIC interrupt CPU). Threads have their cpu mask set to limit them\nto the CPUs in the svc_pool that owns them.\n\nThis is the patch that allows an Altix to scale NFS traffic linearly\nbeyond 4 CPUs and 4 NICs.\n\nIncorporates changes and feedback from Neil Brown, Trond Myklebust, and\nChristoph Hellwig.\n\nSigned-off-by: Greg Banks \u003cgnb@melbourne.sgi.com\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "3262c816a3d7fb1eaabce633caa317887ed549ae", "tree": "5b635d8b62b9724ab2b1e5563aad37e35b894406", "parents": [ "c081a0c7cfe42adf8e8b9c2b8d0b2ec7f47603e8" ], "author": { "name": "Greg Banks", "email": "gnb@melbourne.sgi.com", "time": "Mon Oct 02 02:17:58 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Oct 02 07:57:19 2006 -0700" }, "message": "[PATCH] knfsd: split svc_serv into pools\n\nSplit out the list of idle threads and pending sockets from svc_serv into a\nnew svc_pool structure, and allocate a fixed number (in this patch, 1) of\npools per svc_serv. The new structure contains a lock which takes over\nseveral of the duties of svc_serv-\u003esv_lock, which is now relegated to\nprotecting only sv_tempsocks, sv_permsocks, and sv_tmpcnt in svc_serv.\n\nThe point is to move the hottest fields out of svc_serv and into svc_pool,\nallowing a following patch to arrange for a svc_pool per NUMA node or per CPU.\n This is a major step towards making the NFS server NUMA-friendly.\n\nSigned-off-by: Greg Banks \u003cgnb@melbourne.sgi.com\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "c081a0c7cfe42adf8e8b9c2b8d0b2ec7f47603e8", "tree": "b8be50680c576427f29195946332bacd56eb1055", "parents": [ "5685f0fa1c24b138d041ef129ed419c5effa40e1" ], "author": { "name": "Greg Banks", "email": "gnb@melbourne.sgi.com", "time": "Mon Oct 02 02:17:57 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Oct 02 07:57:19 2006 -0700" }, "message": "[PATCH] knfsd: test and set SK_BUSY atomically\n\nThe SK_BUSY bit in svc_sock-\u003esk_flags ensures that we do not attempt to\nenqueue a socket twice. Currently, setting and clearing the bit is protected\nby svc_serv-\u003esv_lock. As I intend to reduce the data that the lock protects\nso it\u0027s not held when svc_sock_enqueue() tests and sets SK_BUSY, that test and\nset needs to be atomic.\n\nSigned-off-by: Greg Banks \u003cgnb@melbourne.sgi.com\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "5685f0fa1c24b138d041ef129ed419c5effa40e1", "tree": "068c413c32cc7735a590d4ec16efe55894e67b80", "parents": [ "1a68d952af5f43032012d26dd0d5164c9e9986bc" ], "author": { "name": "Greg Banks", "email": "gnb@melbourne.sgi.com", "time": "Mon Oct 02 02:17:56 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Oct 02 07:57:19 2006 -0700" }, "message": "[PATCH] knfsd: convert sk_reserved to atomic_t\n\nConvert the svc_sock-\u003esk_reserved variable from an int protected by\nsvc_serv-\u003esv_lock, to an atomic. This reduces (by 1) the number of places we\nneed to take the (effectively global) svc_serv-\u003esv_lock.\n\nSigned-off-by: Greg Banks \u003cgnb@melbourne.sgi.com\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1a68d952af5f43032012d26dd0d5164c9e9986bc", "tree": "6c660f3ee27205a4c4f18883b2205f873cf396be", "parents": [ "c45c357d7dbc9e94338f44349e0035149da86b26" ], "author": { "name": "Greg Banks", "email": "gnb@melbourne.sgi.com", "time": "Mon Oct 02 02:17:55 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Oct 02 07:57:19 2006 -0700" }, "message": "[PATCH] knfsd: use new lock for svc_sock deferred list\n\nProtect the svc_sock-\u003esk_deferred list with a new lock svc_sock-\u003esk_defer_lock\ninstead of svc_serv-\u003esv_lock. Using the more fine-grained lock reduces the\nnumber of places we need to take the svc_serv lock.\n\nSigned-off-by: Greg Banks \u003cgnb@melbourne.sgi.com\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "c45c357d7dbc9e94338f44349e0035149da86b26", "tree": "b04388ccaccd5fb304b4bd8be57258d52e79f886", "parents": [ "36bdfc8bae51339aa27ef8e4ce148185293061ae" ], "author": { "name": "Greg Banks", "email": "gnb@melbourne.sgi.com", "time": "Mon Oct 02 02:17:54 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Oct 02 07:57:19 2006 -0700" }, "message": "[PATCH] knfsd: convert sk_inuse to atomic_t\n\nConvert the svc_sock-\u003esk_inuse counter from an int protected by\nsvc_serv-\u003esv_lock, to an atomic. This reduces the number of places we need to\ntake the (effectively global) svc_serv-\u003esv_lock.\n\nSigned-off-by: Greg Banks \u003cgnb@melbourne.sgi.com\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "36bdfc8bae51339aa27ef8e4ce148185293061ae", "tree": "deab54ff70d6991c1e5be0d9efe97d10f65375b0", "parents": [ "4a3ae42dc312dbdffee803efaf393421b79f997a" ], "author": { "name": "Greg Banks", "email": "gnb@melbourne.sgi.com", "time": "Mon Oct 02 02:17:54 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Oct 02 07:57:19 2006 -0700" }, "message": "[PATCH] knfsd: move tempsock aging to a timer\n\nFollowing are 11 patches from Greg Banks which combine to make knfsd more\nNuma-aware. They reduce hitting on \u0027global\u0027 data structures, and create some\ndata-structures that can be node-local.\n\nknfsd threads are bound to a particular node, and the thread to handle a new\nrequest is chosen from the threads that are attach to the node that received\nthe interrupt.\n\nThe distribution of threads across nodes can be controlled by a new file in\nthe \u0027nfsd\u0027 filesystem, though the default approach of an even spread is\nprobably fine for most sites.\n\nSome (old) numbers that show the efficacy of these patches: N \u003d\u003d number of\nNICs \u003d\u003d number of CPUs \u003d\u003d nmber of clients. Number of NUMA nodes \u003d\u003d N/2\n\nN\tThroughput, MiB/s\tCPU usage, % (max\u003dN*100)\n\tBefore\tAfter\t\tBefore\tAfter\n\t---\t------\t----\t\t-----\t-----\n\t4\t312\t435\t\t350\t228\n\t6\t500\t656\t\t501\t418\n\t8\t562\t804\t\t690\t589\n\nThis patch:\n\nMove the aging of RPC/TCP connection sockets from the main svc_recv() loop to\na timer which uses a mark-and-sweep algorithm every 6 minutes. This reduces\nthe amount of work that needs to be done in the main RPC loop and the length\nof time we need to hold the (effectively global) svc_serv-\u003esv_lock.\n\n[akpm@osdl.org: cleanup]\nSigned-off-by: Greg Banks \u003cgnb@melbourne.sgi.com\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "6fb2b47fa16c81317ec282248e6cff521cca31c2", "tree": "226d823e900aba03fb7ee55cab3a9137fd5d9077", "parents": [ "896440d560de3bca6813e83792f431edf5073318" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Oct 02 02:17:50 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Oct 02 07:57:18 2006 -0700" }, "message": "[PATCH] knfsd: Drop \u0027serv\u0027 option to svc_recv and svc_process\n\nIt isn\u0027t needed as it is available in rqstp-\u003erq_server, and dropping it allows\nsome local vars to be dropped.\n\n[akpm@osdl.org: build fix]\nCc: \"J. Bruce Fields\" \u003cbfields@fieldses.org\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "b41b66d63c730cc45a1024e1f1e67439e507e40f", "tree": "85f623c087a90ccf08a8264c638df5504f972c0d", "parents": [ "80212d59e32a8a8e030c2ddc5861d8ff70542c56" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Oct 02 02:17:48 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Oct 02 07:57:18 2006 -0700" }, "message": "[PATCH] knfsd: allow sockets to be passed to nfsd via \u0027portlist\u0027\n\nUserspace should create and bind a socket (but not connectted) and write the\n\u0027fd\u0027 to portlist. This will cause the nfs server to listen on that socket.\n\nTo close a socket, the name of the socket - as read from \u0027portlist\u0027 can be\nwritten to \u0027portlist\u0027 with a preceding \u0027-\u0027.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "80212d59e32a8a8e030c2ddc5861d8ff70542c56", "tree": "fb708f92e50ab8a1c13b68d4e6e3db8b50bd07a8", "parents": [ "02a375f0ac4bc2e9b767fabb6b2f9915547226a7" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Oct 02 02:17:47 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Oct 02 07:57:18 2006 -0700" }, "message": "[PATCH] knfsd: define new nfsdfs file: portlist - contains list of ports\n\nThis file will list all ports that nfsd has open.\nDefault when TCP enabled will be\n ipv4 udp 0.0.0.0 2049\n ipv4 tcp 0.0.0.0 2049\n\nLater, the list of ports will be settable.\n\n\u0027portlist\u0027 chosen rather than \u0027ports\u0027, to avoid unnecessary confusion with\nnon-mainline patches which created \u0027ports\u0027 with different semantics.\n\n[akpm@osdl.org: cleanups, build fix]\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1811474620d1986da45f7245168bf7c2d883d770", "tree": "dbd73019e333f8410b326a383854ef334393f703", "parents": [ "96d2ca4ec0bb8d0f344e5960224700be3dec3515" ], "author": { "name": "Eric Sesterhenn", "email": "snakebyte@gmx.de", "time": "Thu Sep 28 14:37:07 2006 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Thu Sep 28 18:03:06 2006 -0700" }, "message": "[SUNRPC]: Remove unnecessary check in net/sunrpc/svcsock.c\n\ncoverity spotted this one as possible dereference in the dprintk(),\nbut since there is only one caller of svc_create_socket(), which always\npasses a valid sin, we dont need this check.\n\nSigned-off-by: Eric Sesterhenn \u003csnakebyte@gmx.de\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d8ed029d6000ba2e2908d9286409e4833c091b4c", "tree": "732feaa2e3751df5c81032a30ff4761427492ac4", "parents": [ "7699431301b189fca7ccbb64fe54e5a5170f8497" ], "author": { "name": "Alexey Dobriyan", "email": "adobriyan@gmail.com", "time": "Tue Sep 26 22:29:38 2006 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Thu Sep 28 18:01:21 2006 -0700" }, "message": "[SUNRPC]: trivial endianness annotations\n\npure s/u32/__be32/\n\n[AV: large part based on Alexey\u0027s patches]\n\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "e6242e928ef1e4ed853f909a7479e4934f4bcb70", "tree": "f348f28e1993c73b2683f7edf87ef673ad2d5ec8", "parents": [ "ac5a488ef252ed673cb067843e411f8cc43f7ab9" ], "author": { "name": "Sridhar Samudrala", "email": "sri@us.ibm.com", "time": "Mon Aug 07 20:58:01 2006 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Fri Sep 22 14:54:06 2006 -0700" }, "message": "[SUNRPC]: Update to use in-kernel sockets API.\n\nSigned-off-by: Sridhar Samudrala \u003csri@us.ibm.com\u003e\nAcked-by: James Morris \u003cjmorris@namei.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0da974f4f303a6842516b764507e3c0a03f41e5a", "tree": "8872aec792f02040269c6769dd1009b20f71d186", "parents": [ "a0ee7c70b22f78593957f99faa06acb4747b8bc0" ], "author": { "name": "Panagiotis Issaris", "email": "takis@issaris.org", "time": "Fri Jul 21 14:51:30 2006 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Jul 21 14:51:30 2006 -0700" }, "message": "[NET]: Conversions from kmalloc+memset to k(z|c)alloc.\n\nSigned-off-by: Panagiotis Issaris \u003ctakis@issaris.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n\n" }, { "commit": "57b47a53ec4a67691ba32cff5768e8d78fa6c67f", "tree": "d735ae4734f7b386eefa508a0629715f45808d1d", "parents": [ "6613f82dd293b23f582a649b287fadbf8d23e6cf" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Mar 20 22:35:41 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 20 22:35:41 2006 -0800" }, "message": "[NET]: sem2mutex part 2\n\nSemaphore to mutex conversion.\n\nThe conversion was generated via scripts, and the result was validated\nautomatically via a script as well.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1918e341383ab787d6c5b17200f4ed901b10c777", "tree": "5644f3d1ecfbc104ed956ad674785ee69348df41", "parents": [ "7e8f05934d540aeb45c1cc3cc3a0e811bd61866b" ], "author": { "name": "J. Bruce Fields", "email": "bfields@citi.umich.edu", "time": "Wed Jan 18 17:43:16 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 18 19:20:24 2006 -0800" }, "message": "[PATCH] svcrpc: save and restore the daddr field when request deferred\n\nThe server code currently keeps track of the destination address on every\nrequest so that it can reply using the same address. However we forget to do\nthat in the case of a deferred request. Remedy this oversight. \u003eFrom folks\nat PolyServe.\n\nSigned-off-by: J. Bruce Fields \u003cbfields@citi.umich.edu\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "93fbf1a5de8afde08988dda3735669099dee84d0", "tree": "2be514a800662b94a6a879b7b53f5fab6b56dd0e", "parents": [ "f93ea411b73594f7d144855fd34278bcf34a9afc" ], "author": { "name": "Olaf Kirch", "email": "okir@suse.de", "time": "Fri Jan 06 00:19:56 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Jan 06 08:33:59 2006 -0800" }, "message": "[PATCH] Keep nfsd from exiting when seeing recv() errors\n\nI submitted this one previously - svc_tcp_recvfrom currently returns\nany errors to the caller, including ECONNRESET and the like.\n\nThis is something svc_recv isn\u0027t able to deal with:\n\n\tlen \u003d svsk-\u003esk_recvfrom(rqstp);\n\t[...]\n\tif (len \u003d\u003d 0 || len \u003d\u003d -EAGAIN) {\n\t\t[...]\n\t\treturn -EAGAIN;\n\t}\n\n\t[...]\n\treturn len;\n\nThe nfsd main loop will exit when it sees an error code other than\nEAGAIN.\n\nThe following patch fixes this problem\n\nsvc_recv is not equipped to deal with error codes other than EAGAIN,\nand will propagate anything else (such as ECONNRESET) up to nfsd,\ncausing it to exit.\n\nSigned-off-by: Olaf Kirch \u003cokir@suse.de\u003e\nCc: Trond Myklebust \u003ctrond.myklebust@fys.uio.no\u003e\nCc: Neil Brown \u003cneilb@cse.unsw.edu.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" } ], "next": "90ddc4f0470427df306f308ad03db6b6b21644b8" }