)]}' { "log": [ { "commit": "eedd5d0a707a8ad704e03bda5fbfe6b1a8e5f028", "tree": "eba3de380d915ea0eee92ac9fb007f18449e0a43", "parents": [ "a7e80ce26caa174b1caa5fdfbb3dbd740a87d33a", "c752c78275fbf3fcb1d6d0af9b03ac999fe1963d", "b9012e0a4255c93e1d81f1ccee591de6414b5955", "e441d6342890838bfc6d64ca2f0964aca08ae2a2", "943c246e9ba9078a61b6bcc5b4a8131ce8befb64", "7097228c54e7348d8c8c6dccc96e50191e39c2f8", "cd86f420614c1a2dea9c21d7f4f1acb5ec2465b2", "d57f5f72df1b0da501c4b55e56a1040b1631c1f3", "208dde28b0f73c0e2dc6be74040fa562e129a6e8", "fbcffcc6a0536544fa53cd5bd5c4913efe1a5982" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Oct 09 17:41:15 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Oct 09 17:41:15 2008 -0700" }, "message": "Merge branches \u0027cma\u0027, \u0027cxgb3\u0027, \u0027ehca\u0027, \u0027ipath\u0027, \u0027ipoib\u0027, \u0027mad\u0027, \u0027misc\u0027, \u0027mlx4\u0027, \u0027mthca\u0027 and \u0027nes\u0027 into for-next\n" }, { "commit": "fbcffcc6a0536544fa53cd5bd5c4913efe1a5982", "tree": "7d93347e1d86da8ea2ee5a89474d48621a7f89d2", "parents": [ "e2f5e7333a2fb51ef9e45280c3da9ca3bde65fde" ], "author": { "name": "Chien Tung", "email": "ctung@neteffect.com", "time": "Thu Oct 09 17:41:05 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Oct 09 17:41:05 2008 -0700" }, "message": "RDMA/nes: Fix slab corruption\n\nReferencing cm_node after it is freed via rem_ref_cm_node() causes a\nslab corruption. There is no need to set cm_node-\u003ecm_id to NULL in\nmini_cm_close().\n\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d57f5f72df1b0da501c4b55e56a1040b1631c1f3", "tree": "f383afb1c188425fe93b6acfb788a0ef14420246", "parents": [ "9824b8f11373b0df806c135a342da9319ef1d893" ], "author": { "name": "Vladimir Sokolovsky", "email": "vlad@mellanox.co.il", "time": "Wed Oct 08 20:09:01 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Oct 08 20:09:01 2008 -0700" }, "message": "IB/mlx4: Set RLKEY bit for kernel QPs\n\nSet RLKEY bit in the HW context for kernel QPs so that kernel QPs can\nuse the reserved L_Key for memory reference.\n\nSigned-off-by: Vladimir Sokolovsky \u003cvlad@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e2f5e7333a2fb51ef9e45280c3da9ca3bde65fde", "tree": "022a747dda261baa7a834c1c9a99ed49c2dfc9e5", "parents": [ "7191a0a18228c8da9abc7776433c6a3953ff1e4b" ], "author": { "name": "Chien Tung", "email": "ctung@neteffect.com", "time": "Wed Oct 08 14:43:29 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Oct 08 14:43:29 2008 -0700" }, "message": "RDMA/nes: Correct error_module bit mask\n\nerror_module is 5 bits wide not 4. The corresponding crit_error_count\narray is correct with 32 entries.\n\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\n--\n drivers/infiniband/hw/nes/nes_hw.c | 2 +-\n 1 files changed, 1 insertions(+), 1 deletions(-)\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7191a0a18228c8da9abc7776433c6a3953ff1e4b", "tree": "c7c103a900a033242fd0cfda4b7e1100428234cf", "parents": [ "7e36d3d732438de894802f87a0ca21372e00fb74" ], "author": { "name": "Bob Sharp", "email": "bsharp@neteffect.com", "time": "Fri Oct 03 12:21:19 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Oct 03 12:21:19 2008 -0700" }, "message": "RDMA/nes: Fix routed RDMA connections\n\nFix routed RDMA connections to destinations where the next hop is not\nthe final destination. Use neigh_*() to properly locate neighbor.\n\nSigned-off-by: Bob Sharp \u003cbsharp@neteffect.com\u003e\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\n" }, { "commit": "7e36d3d732438de894802f87a0ca21372e00fb74", "tree": "4f86671c059e8e8ef542a268ebb12813a2270a0f", "parents": [ "1bb28499979d926806139bbdef6969fc37621118" ], "author": { "name": "Vadim Makhervaks", "email": "vmakhervaks@neteffect.com", "time": "Fri Oct 03 12:21:18 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Oct 03 12:21:18 2008 -0700" }, "message": "RDMA/nes: Enhanced PFT management scheme\n\nChange management of perfect filter table to allow enhanced\nperformance applications.\n\nSigned-off-by: Vadim Makhervaks \u003cvmakhervaks@neteffect.com\u003e\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "1bb28499979d926806139bbdef6969fc37621118", "tree": "74b5edeb01621c78498707715e4ccebfff5ce7ed", "parents": [ "9d156947c734747065178331e0c95745cf3a55e1" ], "author": { "name": "Faisal Latif", "email": "flatif@neteffect.com", "time": "Fri Sep 26 15:08:10 2008 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 15:35:49 2008 -0700" }, "message": "RDMA/nes: Handle AE bounds violation\n\nHandle async error NES_AEQE_AEID_AMP_BOUNDS_VIOLATION.\n\nSigned-off-by: Faisal Latif \u003cflatif@neteffect.com\u003e\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "9d156947c734747065178331e0c95745cf3a55e1", "tree": "278e4509d89f16aa2405a950306b14c601bf6400", "parents": [ "068e80de6af2b920d2644bba3a2c060431834160" ], "author": { "name": "Chien Tung", "email": "ctung@neteffect.com", "time": "Fri Sep 26 15:08:10 2008 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 15:35:49 2008 -0700" }, "message": "RDMA/nes: Limit critical error interrupts\n\nMask off a critical error after 100 critical error interrupts to\nkeep the system \"sane\".\n\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "068e80de6af2b920d2644bba3a2c060431834160", "tree": "4808d69a2e1bbd988623132d36fc207a170e6364", "parents": [ "168ac8244df5af1a9ab03bf39e4a9d3161dd9f11" ], "author": { "name": "Chien Tung", "email": "ctung@neteffect.com", "time": "Fri Sep 26 15:08:10 2008 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 15:35:49 2008 -0700" }, "message": "RDMA/nes: Stop spurious MAC interrupts\n\nMask off MAC interrupts on netdev_stop to prevent spurious MAC interrupts\non unload/reload of iw_nes.\n\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "168ac8244df5af1a9ab03bf39e4a9d3161dd9f11", "tree": "60460460c69c41cc80931b382d258aae98049753", "parents": [ "0c93ae355ed7301249d932e509f8546977d53376" ], "author": { "name": "Chien Tung", "email": "ctung@neteffect.com", "time": "Fri Sep 26 15:08:10 2008 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 15:35:48 2008 -0700" }, "message": "RDMA/nes: Correct tso_wqe_length\n\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "0c93ae355ed7301249d932e509f8546977d53376", "tree": "9a4b72285b2a61768c2a79f64e2435fee971ecb3", "parents": [ "27ffed603f555ce0a644de6e550d3462ff51d64f" ], "author": { "name": "Chien Tung", "email": "ctung@neteffect.com", "time": "Fri Sep 26 15:08:10 2008 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 15:35:48 2008 -0700" }, "message": "RDMA/nes: Fill in firmware version for ethtool\n\nFill in firmware version for ethtool_drvinfo.\n\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "27ffed603f555ce0a644de6e550d3462ff51d64f", "tree": "59746ac5d97430664d2ad9216ec12c72bd83c9d5", "parents": [ "a06fd26d48eb3304db246f3f4a0aa5a50afb10ec" ], "author": { "name": "John Lacombe", "email": "jlacombe@neteffect.com", "time": "Fri Sep 26 15:08:10 2008 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 15:35:48 2008 -0700" }, "message": "RDMA/nes: Use ethtool timer value\n\nUse timer value set via ethtool intead of #defines.\n\nSigned-off-by: John Lacombe \u003cjlacombe@neteffect.com\u003e\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "a06fd26d48eb3304db246f3f4a0aa5a50afb10ec", "tree": "79828ed068f03a7608b8fc99b0a9330114a7e800", "parents": [ "e0e31afbf9a9bb6ca934d3c64ef321cb5f873efe" ], "author": { "name": "Bob Sharp", "email": "bsharp@neteffect.com", "time": "Fri Sep 26 15:08:10 2008 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 15:35:48 2008 -0700" }, "message": "RDMA/nes: Correct MAX TSO frags value\n\nUse correct define for max TSO fragments.\n\nSigned-off-by: Bob Sharp \u003cbsharp@neteffect.com\u003e\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e0e31afbf9a9bb6ca934d3c64ef321cb5f873efe", "tree": "4006d1e4495422ab3f397c5fe5e2c46b35265240", "parents": [ "7a8d14070b3e2d52d2b531434ed09fa1787ae7ca" ], "author": { "name": "Bob Sharp", "email": "bsharp@neteffect.com", "time": "Fri Sep 26 15:08:10 2008 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 15:35:47 2008 -0700" }, "message": "RDMA/nes: Enable MC/UC after changing MTU\n\nRe-enable multicast and unicast after changing MTU.\n\nSigned-off-by: Bob Sharp \u003cbsharp@neteffect.com\u003e\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7a8d14070b3e2d52d2b531434ed09fa1787ae7ca", "tree": "2a8849888a7c2e1ee6675428660f4c706368ac1f", "parents": [ "e88bd7b624133e0b07adb21c45c9e6f68f8fdda2" ], "author": { "name": "Bob Sharp", "email": "bsharp@neteffect.com", "time": "Fri Sep 26 15:08:10 2008 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 15:35:47 2008 -0700" }, "message": "RDMA/nes: Free NIC TX buffers when destroying NIC QP\n\nSigned-off-by: Bob Sharp \u003cbsharp@neteffect.com\u003e\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e88bd7b624133e0b07adb21c45c9e6f68f8fdda2", "tree": "17311ea7eec42c441a31be207705737a53aab9ce", "parents": [ "2b537c2824194d50072ab260f54d6fe4cb8d17e8" ], "author": { "name": "Chien Tung", "email": "ctung@neteffect.com", "time": "Fri Sep 26 15:08:10 2008 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 15:35:47 2008 -0700" }, "message": "RDMA/nes: Fix MDC setting\n\nClear MDC bits before setting them to a new value. Adjust MDC value\nfor 10G.\n\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2b537c2824194d50072ab260f54d6fe4cb8d17e8", "tree": "cbfaf2ecce497f8a51dc24bd93da1afa185af260", "parents": [ "de182149c31786b2b07fa408fb076599b29232a1" ], "author": { "name": "Chien Tung", "email": "ctung@neteffect.com", "time": "Fri Sep 26 15:08:10 2008 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 15:35:46 2008 -0700" }, "message": "RDMA/nes: Add wqm_quanta module option\n\nAdd a module parameter wqm_quanta. It controls the number of segments\ntransmitted at a time.\n\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "de182149c31786b2b07fa408fb076599b29232a1", "tree": "12ced882faf211896664eaefff466f5e372e6ba5", "parents": [ "fcb7ad31beda842804167f0645ca54660713bcd6" ], "author": { "name": "Chien Tung", "email": "ctung@neteffect.com", "time": "Fri Sep 26 15:08:10 2008 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 15:35:46 2008 -0700" }, "message": "RDMA/nes: Module parameter permissions\n\nChange permission to 0644 so root can set mpa_version, disable_mpa_crc,\nsend_first, and nes_drv_opt at runtime.\n\nSigned-off-by: Sweta Bhatt \u003csweta.bhatt@einfochips.com\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "c752c78275fbf3fcb1d6d0af9b03ac999fe1963d", "tree": "85c8332c2197b68e53fff1de31eb8dc912d9da11", "parents": [ "9824b8f11373b0df806c135a342da9319ef1d893" ], "author": { "name": "Jon Mason", "email": "jon@opengridcomputing.com", "time": "Tue Sep 30 14:51:19 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 14:51:19 2008 -0700" }, "message": "RDMA/cxgb3: Set active_mtu in ib_port_attr\n\nWhen running ibv_devinfo, the active_mtu returned is garbage. This is\ndue to the field not being populated in the query_port function in the\ndriver. The patch below populates the active_mtu field with a MTU of\n2k. It also zeros the struct, so that any new additions to it will\nreturn 0.\n\nSigned-off-by: Jon Mason \u003cjon@opengridcomputing.com\u003e\nAcked-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "fcb7ad31beda842804167f0645ca54660713bcd6", "tree": "9b8311500887491d74cff655593a102f77db38c1", "parents": [ "54c86a8c838301e8a619e454b686288578002300" ], "author": { "name": "Chien Tung", "email": "ctung@neteffect.com", "time": "Tue Sep 30 14:49:44 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 14:49:44 2008 -0700" }, "message": "RDMA/nes: Add support for 4-port 1G HP blade card\n\nAdd support for NetEffect 4 port 1G HP blade card. The mapping\nbetween physical port and MAC is different from the standup card.\n\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "54c86a8c838301e8a619e454b686288578002300", "tree": "ec6b4623731ce0454f6674d0fec0b42f0b3419c0", "parents": [ "9824b8f11373b0df806c135a342da9319ef1d893" ], "author": { "name": "Faisal Latif", "email": "flatif@neteffect.com", "time": "Tue Sep 30 14:47:27 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 30 14:47:27 2008 -0700" }, "message": "RDMA/nes: Make mini_cm_connect() static\n\nSigned-off-by: Faisal Latif \u003cflatif@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "208dde28b0f73c0e2dc6be74040fa562e129a6e8", "tree": "e4ef7fa60a3411fb6fba868ec1c8549c083e799c", "parents": [ "9824b8f11373b0df806c135a342da9319ef1d893" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Sep 29 21:37:33 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Sep 29 21:37:33 2008 -0700" }, "message": "IB/mthca: Use pci_request_regions()\n\nBack in prehistoric (pre-git!) days, the kernel\u0027s MSI-X support did\nrequest_mem_region() on a device\u0027s MSI-X tables, which meant that a\ndriver that enabled MSI-X couldn\u0027t use pci_request_regions() (since\nthat would clash with the PCI layer\u0027s MSI-X request).\n\nHowever, that was removed (by me!) years ago, so mthca can just use\npci_request_regions() and pci_release_regions() instead of its own\nmuch more complicated code that avoids requesting the MSI-X tables.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e441d6342890838bfc6d64ca2f0964aca08ae2a2", "tree": "94a3fa3aba43ddf3b7381435c347d1699e755ab1", "parents": [ "940358967599ba9057b3c51ba906e1cd5b984729" ], "author": { "name": "Yannick Cote", "email": "yannick.cote@qlogic.com", "time": "Mon Sep 29 21:24:04 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Sep 29 21:24:04 2008 -0700" }, "message": "IB/ipath: Fix hang on module unload\n\nHandle the case where posting a send is requested when the link is\ndown. This fixes \u003chttps://bugs.openfabrics.org/show_bug.cgi?id\u003d1117\u003e.\n\nSigned-off-by: Yannick Cote \u003cyannick.cote@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "cd86f420614c1a2dea9c21d7f4f1acb5ec2465b2", "tree": "547a46cfaaf6d1ec26e38b6eae2248f4d71fd60c", "parents": [ "9824b8f11373b0df806c135a342da9319ef1d893" ], "author": { "name": "Julia Lawall", "email": "julia@diku.dk", "time": "Sat Sep 20 20:06:32 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sat Sep 20 20:06:32 2008 -0700" }, "message": "IB: Drop code after return statement\n\nA break after a return serves no purpose, remove it.\n\nSigned-off-by: Julia Lawall \u003cjulia@diku.dk\u003e\nReviewed-by: Richard Genoud \u003crichard.genoud@gmail.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "940358967599ba9057b3c51ba906e1cd5b984729", "tree": "6e29b978beddbcc843be676732156e0b31d317c0", "parents": [ "9824b8f11373b0df806c135a342da9319ef1d893" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Sat Sep 20 20:05:51 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sat Sep 20 20:05:51 2008 -0700" }, "message": "IB/ipath: Fix SLID generation for RC/UC QPs when LMC \u003e 0\n\nThe code to set the source LID in the sent LRH was not setting the low\nbits if LMC !\u003d 0 for RC/UC QPs.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "b9012e0a4255c93e1d81f1ccee591de6414b5955", "tree": "f96df62a968eab98722256251914070fa7bb0c2c", "parents": [ "9824b8f11373b0df806c135a342da9319ef1d893" ], "author": { "name": "Alexander Schmidt", "email": "alexs@linux.vnet.ibm.com", "time": "Sat Sep 20 20:05:21 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sat Sep 20 20:05:21 2008 -0700" }, "message": "IB/ehca: Generate flush status CQ entries\n\nWhen a QP goes into error state, it is required that CQ entries with a\nflush error status are delivered to the application for any\noutstanding work requests. eHCA does not do this in hardware, so this\npatch adds software flush CQE generation to the ehca driver.\n\nWhenever a QP gets into error state, it is added to the QP error list\nof its respective CQ. If the error QP list of a CQ is not empty,\npoll_cq() generates flush CQEs before polling the actual CQ.\n\nSigned-off-by: Alexander Schmidt \u003calexs@linux.vnet.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "5a0cd4eb661fea095ff9962060c21c161a9ed43f", "tree": "7e1e7a044fc9d04d2da246a58a52bd07c4e5fef0", "parents": [ "b4df9d88a62c6db4cee0d96507a27527bf205dde", "7e2c23285454ecc8c8159b86d6343efe222ca3ae" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Sep 19 16:18:21 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Sep 19 16:18:21 2008 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:\n IPoIB: Fix deadlock on RTNL between bcast join comp and ipoib_stop()\n RDMA/nes: Fix client side QP destroy\n IB/mlx4: Fix up fast register page list format\n mlx4_core: Set RAE and init mtt_sz field in FRMR MPT entries\n" }, { "commit": "7e2c23285454ecc8c8159b86d6343efe222ca3ae", "tree": "d4bb840de3750e01f81a604b3e300e0c50597ee1", "parents": [ "e8224e4b804b4fd26723191c1891101a5959bb8a", "29bdc88384c2b24e37e5760df0dc898546083d6b", "d7ffd5076d4407d54b25bc4b25f3002f74fbafde" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 16 11:57:52 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 16 11:57:52 2008 -0700" }, "message": "Merge branches \u0027ipoib\u0027, \u0027mlx4\u0027 and \u0027nes\u0027 into for-linus\n" }, { "commit": "d7ffd5076d4407d54b25bc4b25f3002f74fbafde", "tree": "52c2bef856fe7357da30a16c308dc007ce83d262", "parents": [ "1941246dd98089dd637f44d3bd4f6cc1c61aa9e4" ], "author": { "name": "Faisal Latif", "email": "flatif@neteffect.com", "time": "Tue Sep 16 11:56:26 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Sep 16 11:56:26 2008 -0700" }, "message": "RDMA/nes: Fix client side QP destroy\n\nFix QP not being destroyed properly on the client, which leads to\nuserspace programs hanging on exit. This is a missing chunk from the\nconnection management rewrite in commit 6492cdf3 (\"RDMA/nes: CM\nconnection setup/teardown rework\").\n\nSigned-off-by: Faisal Latif \u003cflatif@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "29bdc88384c2b24e37e5760df0dc898546083d6b", "tree": "9d8fe16ac4728ab669f81a763effda21301d9ddf", "parents": [ "c9257433f2eaf8803a1f3d3be5d984232db41ffe" ], "author": { "name": "Vladimir Sokolovsky", "email": "vlad@mellanox.co.il", "time": "Mon Sep 15 14:25:23 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Sep 15 14:25:23 2008 -0700" }, "message": "IB/mlx4: Fix up fast register page list format\n\nByte swap the addresses in the page list for fast register work requests\nto big endian to match what the HCA expectx. Also, the addresses must\nhave the \"present\" bit set so that the HCA knows it can access them.\nOtherwise the HCA will fault the first time it accesses the memory\nregion.\n\nSigned-off-by: Vladimir Sokolovsky \u003cvlad@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "4c246edd2550304df5b766cc841584b2bb058843", "tree": "16f9a553226d256adc3f1969c1d966dbc6e646f9", "parents": [ "ee7cbabbd359b5d9a60de3d5f1693163e07987ca" ], "author": { "name": "Vladimir Sokolovsky", "email": "vlad@mellanox.co.il", "time": "Wed Aug 27 14:29:57 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Aug 27 14:40:38 2008 -0700" }, "message": "IB/mlx4: Actually return L_Key and R_Key for fast register MRs\n\nInitialize the L_Key and R_Key for memory regions returned from\nmlx4_ib_alloc_fast_reg_mr(). Otherwise callers just get garbage for\nthe memory keys and can\u0027t do anything useful with these MRs.\n\nSigned-off-by: Vladimir Sokolovsky \u003cvlad@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7a8fc9b248e77a4eab0613acf30a6811799786b3", "tree": "24b3beb8bc0633db27ffdb791f94dce95d51b1d0", "parents": [ "d3ee1b405872214609868f3cde631ac157026dd0" ], "author": { "name": "Adrian Bunk", "email": "bunk@kernel.org", "time": "Sun Aug 17 17:36:59 2008 +0300" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Aug 23 12:14:12 2008 -0700" }, "message": "removed unused #include \u003clinux/version.h\u003e\u0027s\n\nThis patch lets the files using linux/version.h match the files that\n#include it.\n\nSigned-off-by: Adrian Bunk \u003cbunk@kernel.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "24babadec0209e5f84c067cb89aca6515486d35c", "tree": "25740b4379e917f5bb01b5e5264a74653a05d98c", "parents": [ "7ec01ff950c455aa1f1ccfaf347eb1aa9ec160d5" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Fri Aug 15 11:25:20 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Aug 15 11:25:20 2008 -0700" }, "message": "IB/ipath: Fix incorrect check for max physical address in TID\n\nThe check for max physical address was incorrect, thus limiting the\nrange of allowed physical addresses.\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7ec01ff950c455aa1f1ccfaf347eb1aa9ec160d5", "tree": "3cde8a28f0c1418bc520b705c35d7c4b5de9ef10", "parents": [ "ffaa5b984a9322bbd5d9a7f0814ca2ce70feebe5" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Fri Aug 15 11:23:47 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Aug 15 11:23:47 2008 -0700" }, "message": "IB/ipath: Fix lost UD send work request\n\nIf a UD QP has some work requests queued to be sent by the DMA engine\nfollowed by a local loopback work request, we have to wait for the\nprevious work requests to finish or the completion for the local\nloopback work request would be generated out of order. The problem\nwas that the work request queue pointer was already updated so that\nthe request would not be processed when the DMA queue drained.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6773f079b72ab0200fe9afa9bb0c656a6af5400c", "tree": "92b3b86492965367f62c37a84414b892d50504cf", "parents": [ "129a10fb81309f455eeb444560ec38657d29c46f" ], "author": { "name": "Alexander Schmidt", "email": "alexs@linux.vnet.ibm.com", "time": "Tue Aug 12 15:46:30 2008 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Aug 12 11:34:59 2008 -0700" }, "message": "IB/ehca: Discard double CQE for one WR\n\nUnder rare circumstances, the ehca hardware might erroneously generate\ntwo CQEs for the same WQE, which is not compliant to the IB spec and\nwill cause unpredictable errors like memory being freed twice. To\navoid this problem, the driver needs to detect the second CQE and\ndiscard it.\n\nFor this purpose, introduce an array holding as many elements as the\nSQ of the QP, called sq_map. Each sq_map entry stores a \"reported\"\nflag for one WQE in the SQ. When a work request is posted to the SQ,\nthe respective \"reported\" flag is set to zero. After the arrival of a\nCQE, the flag is set to 1, which allows to detect the occurence of a\nsecond CQE.\n\nThe mapping between WQE / CQE and the corresponding sq_map element is\nimplemented by replacing the lowest 16 Bits of the wr_id with the\nindex in the queue map. The original 16 Bits are stored in the sq_map\nentry and are restored when the CQE is passed to the application.\n\nSigned-off-by: Alexander Schmidt \u003calexs@linux.vnet.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "129a10fb81309f455eeb444560ec38657d29c46f", "tree": "544d44f33452e74b86a0869d5d5c64a503ba872b", "parents": [ "17c2b53adbf1ebd7a8b6a63e2597199676426dbf" ], "author": { "name": "Alexander Schmidt", "email": "alexs@linux.vnet.ibm.com", "time": "Tue Aug 12 15:46:27 2008 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Aug 12 11:34:59 2008 -0700" }, "message": "IB/ehca: Check idr_find() return value\n\nThe idr_find() function may fail when trying to get the QP that is\nassociated with a CQE, e.g. when a QP has been destroyed between the\ngeneration of a CQE and the poll request for it. In consequence, the\nreturn value of idr_find() must be checked and the CQE must be\ndiscarded when the QP cannot be found.\n\nSigned-off-by: Alexander Schmidt \u003calexs@linux.vnet.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "17c2b53adbf1ebd7a8b6a63e2597199676426dbf", "tree": "7d14c632f1b587ca632520509c57fc82e947f6ad", "parents": [ "6c02eed9302e7c27ee150d7911b83843c2206148" ], "author": { "name": "Alexander Schmidt", "email": "alexs@linux.vnet.ibm.com", "time": "Tue Aug 12 15:46:20 2008 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Aug 12 11:34:58 2008 -0700" }, "message": "IB/ehca: Repoll CQ on invalid opcode\n\nWhen the ehca driver detects an invalid opcode in a CQE, it currently\npasses the CQE to the application and returns with success. This patch\nchanges the CQE handling to discard CQEs with invalid opcodes and to\ncontinue reading the next CQE from the CQ.\n\nSigned-off-by: Alexander Schmidt \u003calexs@linux.vnet.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6c02eed9302e7c27ee150d7911b83843c2206148", "tree": "370b5f239187e94bfd61fa4c8a2caf5d048e7e4e", "parents": [ "51ad241af45a0bfc02d1ed72a3ad58b46f8e30df" ], "author": { "name": "Alexander Schmidt", "email": "alexs@linux.vnet.ibm.com", "time": "Tue Aug 12 15:46:13 2008 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Aug 12 11:34:58 2008 -0700" }, "message": "IB/ehca: Rename goto label in ehca_poll_cq_one()\n\nRename the \"poll_cq_one_read_cqe\" goto label to what it actually does,\nnamely \"repoll\".\n\nSigned-off-by: Alexander Schmidt \u003calexs@linux.vnet.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "51ad241af45a0bfc02d1ed72a3ad58b46f8e30df", "tree": "53c427390b91a0430309668153d6f7994b970bbf", "parents": [ "f2d7499be1b1fe1cd8a5e6a01c1f44173894a241" ], "author": { "name": "Alexander Schmidt", "email": "alexs@linux.vnet.ibm.com", "time": "Tue Aug 12 15:46:07 2008 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Aug 12 11:34:58 2008 -0700" }, "message": "IB/ehca: Update qp_state on cached modify_qp()\n\nSince the introduction of the port auto-detect mode for ehca, calls to\nmodify_qp() may be cached in the device driver when the ports are not\nactivated yet. When a modify_qp() call is cached, the qp state remains\nuntouched until the port is activated, which will leave the qp in the\nreset state. In the reset state, however, it is not allowed to post SQ\nWQEs, which confuses applications like ib_mad.\n\nThe solution for this problem is to immediately set the qp state as\nrequested by modify_qp(), even when the call is cached.\n\nSigned-off-by: Alexander Schmidt \u003calexs@linux.vnet.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "273b2578392bbf6e5c47a8a3d1ee461ce6fc7182", "tree": "1b00bd21574b1f8db084be4f682d7251a3a0ff3e", "parents": [ "8e43e12d638f732fa32600c324711f4be8fe0b1d", "06a91a02e9b249695f964bb59c8b02152c21e90c" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Aug 07 18:14:07 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Aug 07 18:14:07 2008 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:\n IB/mad: Test ib_create_send_mad() return with IS_ERR(), not \u003d\u003d NULL\n IB/mlx4: Allow 4K messages for UD QPs\n mlx4_core: Add ethernet fields to CQE struct\n IB/ipath: Fix printk format warnings\n RDMA/cxgb3: Fix deadlock initializing iw_cxgb3 device\n RDMA/cxgb3: Fix up MW access rights\n RDMA/cxgb3: Fix QP capabilities\n RDMA/cma: Remove padding arrays by using struct sockaddr_storage\n IB/ipath: Use unsigned long for irq flags\n IPoIB/cm: Set correct SG list in ipoib_cm_init_rx_wr()\n" }, { "commit": "06a91a02e9b249695f964bb59c8b02152c21e90c", "tree": "f4a771f1876f7acb967ceb1033bbe2fc38234018", "parents": [ "3f44675439b136d51179d31eb5a498383cb38624", "be43324d8b316fe83a7b4027334f2825f1121c2c", "70117b9e866b1fdf7e4e84ffb6f38a7b3e9702f8", "e08198169ec5facb3d85bb455efa44a2f8327842", "cd55ef5a10d1a2ea09853bc5fa40aadaf9f80614", "6e0d733d921526e628107fb8b1aff5f7de870d6f" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Aug 07 14:12:03 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Aug 07 14:12:03 2008 -0700" }, "message": "Merge branches \u0027cma\u0027, \u0027cxgb3\u0027, \u0027ipath\u0027, \u0027ipoib\u0027, \u0027mad\u0027 and \u0027mlx4\u0027 into for-linus\n" }, { "commit": "6e0d733d921526e628107fb8b1aff5f7de870d6f", "tree": "357adc8727a6dea4277fbf5a38095c77855012c1", "parents": [ "f780a9f119caa48088b230836a7fa73d1096de7c" ], "author": { "name": "Alex Naslednikov", "email": "xalex@mellanox.co.il", "time": "Thu Aug 07 14:06:50 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Aug 07 14:06:50 2008 -0700" }, "message": "IB/mlx4: Allow 4K messages for UD QPs\n\nCurrent code limits the max message size to 2K for UD QPs, while MTU\nmight be as big as 4K. This patch sets the maximum message size to\n4K, which is needed for UD to work correctly on fabrics with a 4K MTU.\n\nSigned-off-by: Alex Naslednikov \u003cxalex@mellanox.co.il\u003e\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f780a9f119caa48088b230836a7fa73d1096de7c", "tree": "513fb3aa4342a481aa1f4101675ea2e9c41bc28a", "parents": [ "6e86841d05f371b5b9b86ce76c02aaee83352298" ], "author": { "name": "Yevgeny Petrilin", "email": "yevgenyp@mellanox.co.il", "time": "Wed Aug 06 20:14:06 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Aug 06 20:14:06 2008 -0700" }, "message": "mlx4_core: Add ethernet fields to CQE struct\n\nAdd ethernet-related fields to struct mlx4_cqe so that the mlx4_en\nethernet NIC driver can share the same definition.\n\nSigned-off-by: Yevgeny Petrilin \u003cyevgenyp@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "70117b9e866b1fdf7e4e84ffb6f38a7b3e9702f8", "tree": "65cd604d47b041ba203634a91b2a20d114b03354", "parents": [ "52fd8ca6ad4124c15952ded35cfcf6adbd7ae8d4" ], "author": { "name": "Alexander Beregalov", "email": "a.beregalov@gmail.com", "time": "Mon Aug 04 11:12:18 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Aug 04 11:12:18 2008 -0700" }, "message": "IB/ipath: Fix printk format warnings\n\n ipath_driver.c:1260: warning: format \u0027%Lx\u0027 expects type \u0027long long unsigned int\u0027, but argument 6 has type \u0027long unsigned int\u0027\n ipath_driver.c:1459: warning: format \u0027%Lx\u0027 expects type \u0027long long unsigned int\u0027, but argument 4 has type \u0027u64\u0027\n ipath_intr.c:358: warning: format \u0027%Lx\u0027 expects type \u0027long long unsigned int\u0027, but argument 3 has type \u0027u64\u0027\n ipath_intr.c:358: warning: format \u0027%Lu\u0027 expects type \u0027long long unsigned int\u0027, but argument 6 has type \u0027u64\u0027\n ipath_intr.c:1119: warning: format \u0027%Lx\u0027 expects type \u0027long long unsigned int\u0027, but argument 5 has type \u0027u64\u0027\n ipath_intr.c:1119: warning: format \u0027%Lx\u0027 expects type \u0027long long unsigned int\u0027, but argument 3 has type \u0027u64\u0027\n ipath_intr.c:1123: warning: format \u0027%Lx\u0027 expects type \u0027long long unsigned int\u0027, but argument 3 has type \u0027u64\u0027\n ipath_intr.c:1130: warning: format \u0027%Lx\u0027 expects type \u0027long long unsigned int\u0027, but argument 4 has type \u0027u64\u0027\n ipath_iba7220.c:1032: warning: format \u0027%llx\u0027 expects type \u0027long long unsigned int\u0027, but argument 4 has type \u0027u64\u0027\n ipath_iba7220.c:1045: warning: format \u0027%llX\u0027 expects type \u0027long long unsigned int\u0027, but argument 3 has type \u0027u64\u0027\n ipath_iba7220.c:2506: warning: format \u0027%Lu\u0027 expects type \u0027long long unsigned int\u0027, but argument 4 has type \u0027u64\u0027\n\nSigned-off-by: Alexander Beregalov \u003ca.beregalov@gmail.com\u003e\nCc: Sean Hefty \u003csean.hefty@intel.com\u003e\nCc: Hal Rosenstock \u003chal.rosenstock@gmail.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "be43324d8b316fe83a7b4027334f2825f1121c2c", "tree": "30d238ba31519d2c75c642f371754af2fa9ad236", "parents": [ "1c355a6e80fd08e623416138631e240f431385f2" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Aug 04 11:08:37 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Aug 04 11:08:37 2008 -0700" }, "message": "RDMA/cxgb3: Fix deadlock initializing iw_cxgb3 device\n\nRunning \u0027ifconfig up\u0027 on the cxgb3 interface with iw_cxgb3 loaded\ncauses a deadlock. The rtnl lock is already held in this path. The\nfunction fw_supports_fastreg() was introduced in 2.6.27 to\nconditionally set the IB_DEVICE_MEM_MGT_EXTENSIONS bit iff the\nfirmware was at 7.0 or greater, and this function also acquires the\nrtnl lock and which thus causes a deadlock. Further, if iw_cxgb3 is\nloaded _after_ the nic interface is brought up, then the deadlock does\nnot occur and therefore fw_supports_fastreg() does need to grab the\nrtnl lock in that path.\n\nIt turns out this code is all useless anyway. The low level driver\nwill NOT allow the open if the firmware isn\u0027t 7.0, so iw_cxgb3 can\nalways set the MEM_MGT_EXTENSIONS bit. Simplify...\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "1c355a6e80fd08e623416138631e240f431385f2", "tree": "923c13058b6c21836d8f4990f050c7511bc06ec9", "parents": [ "5f0f66b022ba607db0a083bf5cc13e4a4336e366" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Aug 04 11:05:43 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Aug 04 11:05:43 2008 -0700" }, "message": "RDMA/cxgb3: Fix up MW access rights\n\n- MWs don\u0027t have local read/write permissions.\n- Set the MW_BIND enabled bit if a MR has MW_BIND access.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "5f0f66b022ba607db0a083bf5cc13e4a4336e366", "tree": "9f65ea34150f6948cd1e798a430d7b9018f24b54", "parents": [ "6e86841d05f371b5b9b86ce76c02aaee83352298" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Aug 04 11:04:42 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Aug 04 11:04:42 2008 -0700" }, "message": "RDMA/cxgb3: Fix QP capabilities\n\n- Set the stag0 and fastreg capability bits only for kernel qps.\n- QP_PRIV flag is no longer used, so don\u0027t set it.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "b8b572e1015f81b4e748417be2629dfe51ab99f9", "tree": "7df58667d5ed71d6c8f8f4ce40ca16b6fb776d0b", "parents": [ "2b12a4c524812fb3f6ee590a02e65b95c8c32229" ], "author": { "name": "Stephen Rothwell", "email": "sfr@canb.auug.org.au", "time": "Fri Aug 01 15:20:30 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Aug 04 12:02:00 2008 +1000" }, "message": "powerpc: Move include files to arch/powerpc/include/asm\n\nfrom include/asm-powerpc. This is the result of a\n\nmkdir arch/powerpc/include/asm\ngit mv include/asm-powerpc/* arch/powerpc/include/asm\n\nFollowed by a few documentation/comment fixups and a couple of places\nwhere \u003casm-powepc/...\u003e was being used explicitly. Of the latter only\none was outside the arch code and it is a driver only built for powerpc.\n\nSigned-off-by: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "61a2d07d3fb1ac34d142b9b62d4cd60a0f8c229e", "tree": "f7ffe587767438bc0a4f4008a135e976e6264977", "parents": [ "3a4b7886ee59e122d359e1714ed89585a06645ad" ], "author": { "name": "Niels de Vos", "email": "niels@nixpanic.net", "time": "Thu Jul 31 00:07:23 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Aug 01 12:46:41 2008 -0700" }, "message": "Remove newline from the description of module parameters\n\nSome module parameters with only one line have the \u0027\\n\u0027 at the end of the\ndescription. This is not needed nor wanted as after the description the\ntype (i.e. int) is followed by a newline.\n\nSome modules contain a multi-line description, these are not affected\nby this patch.\n\nSigned-off-by: Niels de Vos \u003cniels.devos@wincor-nixdorf.com\u003e\nAcked-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nCc: John W. Linville \u003clinville@tuxdriver.com\u003e\nCc: Ed L. Cashin \u003cecashin@coraid.com\u003e\nCc: Dave Airlie \u003cairlied@linux.ie\u003e\nCc: Roland Dreier \u003crolandd@cisco.com\u003e\nAcked-by: Mauro Carvalho Chehab \u003cmchehab@infradead.org\u003e\nCc: Jeff Garzik \u003cjeff@garzik.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "52fd8ca6ad4124c15952ded35cfcf6adbd7ae8d4", "tree": "b798e9db426b0a78b86427e13ca2107e08d6f897", "parents": [ "6e86841d05f371b5b9b86ce76c02aaee83352298" ], "author": { "name": "Vegard Nossum", "email": "vegard.nossum@gmail.com", "time": "Wed Jul 30 09:29:06 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Jul 30 09:29:06 2008 -0700" }, "message": "IB/ipath: Use unsigned long for irq flags\n\nA few functions in the ipath driver incorrectly use unsigned int to\nhold irq flags for spin_lock_irqsave().\n\nThis patch was generated using the Coccinelle framework with the\nfollowing semantic patch:\n\nThe semantic patch I used was this:\n\n@@\nexpression lock;\nidentifier flags;\nexpression subclass;\n@@\n\n- unsigned int flags;\n+ unsigned long flags;\n\n...\n\n\u003c+...\n\n(\n spin_lock_irqsave(lock, flags)\n|\n _spin_lock_irqsave(lock)\n|\n spin_unlock_irqrestore(lock, flags)\n|\n _spin_unlock_irqrestore(lock, flags)\n|\n read_lock_irqsave(lock, flags)\n|\n _read_lock_irqsave(lock)\n|\n read_unlock_irqrestore(lock, flags)\n|\n _read_unlock_irqrestore(lock, flags)\n|\n write_lock_irqsave(lock, flags)\n|\n _write_lock_irqsave(lock)\n|\n write_unlock_irqrestore(lock, flags)\n|\n _write_unlock_irqrestore(lock, flags)\n|\n spin_lock_irqsave_nested(lock, flags, subclass)\n|\n _spin_lock_irqsave_nested(lock, subclass)\n|\n spin_unlock_irqrestore(lock, flags)\n|\n _spin_unlock_irqrestore(lock, flags)\n|\n _raw_spin_lock_flags(lock, flags)\n|\n __raw_spin_lock_flags(lock, flags)\n)\n\n...+\u003e\n\nCc: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nCc: Julia Lawall \u003cjulia@diku.dk\u003e\nCc: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nSigned-off-by: Vegard Nossum \u003cvegard.nossum@gmail.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "8be1a6d6c77ab4532e4476fdb8177030ef48b52c", "tree": "c94ff327a6291672e1f9071a79bf61d63f5f0cb9", "parents": [ "852fef69c0d9510a28a70221cfddd004efa02552", "cc9969c96765476db5e30c9e074a57838604c1d1" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jul 26 20:40:36 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jul 26 20:40:36 2008 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:\n mlx4: Update/add Mellanox Technologies copyright lines to mlx4 driver files\n mlx4_core: Add VLAN tag field to WQE control segment struct\n RDMA/nes: CM connection setup/teardown rework\n IPoIB: Correct help text for INFINIBAND_IPOIB_DEBUG\n IPoIB/cm: Connected mode is no longer EXPERIMENTAL\n RDMA/ucm: BKL is not needed for ib_ucm_open()\n RDMA/ucma: BKL is not needed for ucma_open()\n" }, { "commit": "cc9969c96765476db5e30c9e074a57838604c1d1", "tree": "919c8528ca998f037afb8a512ba0f9c81e70069c", "parents": [ "5ba18b186c979283a2bf75a28b7ea325184b0c08", "9905922446f6dc02fd4650c8f59114d6bdb5b777", "51a379d0c8f7a6db7c9e3c9c770d90a6d2d1ef9b", "6492cdf3a24fd620660c399745b5e169a0ed27d6" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sat Jul 26 13:59:47 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sat Jul 26 13:59:47 2008 -0700" }, "message": "Merge branches \u0027bkl-removal\u0027, \u0027ipoib\u0027, \u0027mlx4\u0027 and \u0027nes\u0027 into for-linus\n" }, { "commit": "8d8bb39b9eba32dd70e87fd5ad5c5dd4ba118e06", "tree": "64090a84f4c4466f9f30ff46c993e0cede379052", "parents": [ "c485b465a031b6f9b9a51300e0ee1f86efc6db87" ], "author": { "name": "FUJITA Tomonori", "email": "fujita.tomonori@lab.ntt.co.jp", "time": "Fri Jul 25 19:44:49 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jul 26 12:00:03 2008 -0700" }, "message": "dma-mapping: add the device argument to dma_mapping_error()\n\nAdd per-device dma_mapping_ops support for CONFIG_X86_64 as POWER\narchitecture does:\n\nThis enables us to cleanly fix the Calgary IOMMU issue that some devices\nare not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423).\n\nI think that per-device dma_mapping_ops support would be also helpful for\nKVM people to support PCI passthrough but Andi thinks that this makes it\ndifficult to support the PCI passthrough (see the above thread). So I\nCC\u0027ed this to KVM camp. Comments are appreciated.\n\nA pointer to dma_mapping_ops to struct dev_archdata is added. If the\npointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it\u0027s\nNULL, the system-wide dma_ops pointer is used as before.\n\nIf it\u0027s useful for KVM people, I plan to implement a mechanism to register\na hook called when a new pci (or dma capable) device is created (it works\nwith hot plugging). It enables IOMMUs to set up an appropriate\ndma_mapping_ops per device.\n\nThe major obstacle is that dma_mapping_error doesn\u0027t take a pointer to the\ndevice unlike other DMA operations. So x86 can\u0027t have dma_mapping_ops per\ndevice. Note all the POWER IOMMUs use the same dma_mapping_error function\nso this is not a problem for POWER but x86 IOMMUs use different\ndma_mapping_error functions.\n\nThe first patch adds the device argument to dma_mapping_error. The patch\nis trivial but large since it touches lots of drivers and dma-mapping.h in\nall the architecture.\n\nThis patch:\n\ndma_mapping_error() doesn\u0027t take a pointer to the device unlike other DMA\noperations. So we can\u0027t have dma_mapping_ops per device.\n\nNote that POWER already has dma_mapping_ops per device but all the POWER\nIOMMUs use the same dma_mapping_error function. x86 IOMMUs use device\nargument.\n\n[akpm@linux-foundation.org: fix sge]\n[akpm@linux-foundation.org: fix svc_rdma]\n[akpm@linux-foundation.org: build fix]\n[akpm@linux-foundation.org: fix bnx2x]\n[akpm@linux-foundation.org: fix s2io]\n[akpm@linux-foundation.org: fix pasemi_mac]\n[akpm@linux-foundation.org: fix sdhci]\n[akpm@linux-foundation.org: build fix]\n[akpm@linux-foundation.org: fix sparc]\n[akpm@linux-foundation.org: fix ibmvscsi]\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nCc: Muli Ben-Yehuda \u003cmuli@il.ibm.com\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Avi Kivity \u003cavi@qumranet.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "51a379d0c8f7a6db7c9e3c9c770d90a6d2d1ef9b", "tree": "c3f2aecdaaa8e528556f7eeeffd71b983a38bbbc", "parents": [ "25c94d010a8ae8605dc4d5453e0c82fa97da5d12" ], "author": { "name": "Jack Morgenstein", "email": "jackm@dev.mellanox.co.il", "time": "Fri Jul 25 10:32:52 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jul 25 10:32:52 2008 -0700" }, "message": "mlx4: Update/add Mellanox Technologies copyright lines to mlx4 driver files\n\nUpdate existing Mellanox copyright lines to 2008, and add such lines\nto files where they are missing.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@dev.mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6492cdf3a24fd620660c399745b5e169a0ed27d6", "tree": "474a0e937cda0b4cff70bc47a657d8338fb91d22", "parents": [ "fb2e405fc1fc8b20d9c78eaa1c7fd5a297efde43" ], "author": { "name": "Faisal Latif", "email": "flatif@neteffect.com", "time": "Thu Jul 24 20:50:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Jul 24 20:50:45 2008 -0700" }, "message": "RDMA/nes: CM connection setup/teardown rework\n\nMajor rework of CM connection setup/teardown. We had a number of issues\nwith MPI applications not starting/terminating properly over time.\nWith these changes we were able to run longer on larger clusters.\n\n* Remove memory allocation from nes_connect() and nes_cm_connect().\n* Fix mini_cm_dec_refcnt_listen() when destroying listener.\n* Remove unnecessary code from schedule_nes_timer() and nes_cm_timer_tick().\n* Functionalize mini_cm_recv_pkt() and process_packet().\n* Clean up cm_node-\u003eref_count usage.\n* Reuse skbs if available.\n\nSigned-off-by: Faisal Latif \u003cflatif@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "5c402355adf8f920531f02099f4ec0d2bccd4c64", "tree": "eba326f8df01efc0d384874839384040401f5b45", "parents": [ "ecc8b655b38a880b578146895e0e1e2d477ca2c0", "2cc177364e4746becdf421f926fb967c047ccc32" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 12:56:07 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 12:56:07 2008 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:\n MAINTAINERS: Remove Glenn Streiff from NetEffect entry\n mlx4_core: Improve error message when not enough UAR pages are available\n IB/mlx4: Add support for memory management extensions and local DMA L_Key\n IB/mthca: Keep free count for MTT buddy allocator\n mlx4_core: Keep free count for MTT buddy allocator\n mlx4_code: Add missing FW status return code\n IB/mlx4: Rename struct mlx4_lso_seg to mlx4_wqe_lso_seg\n mlx4_core: Add module parameter to enable QoS support\n RDMA/iwcm: Remove IB_ACCESS_LOCAL_WRITE from remote QP attributes\n IPoIB: Include err code in trace message for ib_sa_path_rec_get() failures\n IB/sa_query: Check if sm_ah is NULL in ib_sa_remove_one()\n IB/ehca: Release mutex in error path of alloc_small_queue_page()\n IB/ehca: Use default value for Local CA ACK Delay if FW returns 0\n IB/ehca: Filter PATH_MIG events if QP was never armed\n IB/iser: Add support for RDMA_CM_EVENT_ADDR_CHANGE event\n RDMA/cma: Add RDMA_CM_EVENT_TIMEWAIT_EXIT event\n RDMA/cma: Add RDMA_CM_EVENT_ADDR_CHANGE event\n" }, { "commit": "2cc177364e4746becdf421f926fb967c047ccc32", "tree": "189dca3793dae155d61fa960a35046f0334ed51a", "parents": [ "2f5de1512884da8c74bec2c76e8f114b972ab4be", "1a867c33bb65f2921351a9bdd98548bb96f0ff8c", "1ca8d15619f725e223c19137350b0336b9196193", "76442640829163d0cdb67c2bf0cb4b81a0fe537b", "e8bb4beb2b1f90d499134f2849727ed04c3bedc4", "1fa6d8181b7bb0361512170c30e436dcc95591ee" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Jul 24 08:38:47 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Jul 24 08:38:47 2008 -0700" }, "message": "Merge branches \u0027bkl-removal\u0027, \u0027cma\u0027, \u0027ehca\u0027, \u0027for-2.6.27\u0027, \u0027mlx4\u0027, \u0027mthca\u0027 and \u0027nes\u0027 into for-linus\n" }, { "commit": "26dcce0fabbef75ae426461edf21b5030bad60f3", "tree": "56c64fa47dc29f7ea5a8fd0cab0459fb0a05a2bc", "parents": [ "d7b6de14a0ef8a376f9d57b867545b47302b7bfb", "eb6a12c2428d21a9f3e0f1a50e927d5fd80fc3d0" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 23 18:37:44 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 23 18:37:44 2008 -0700" }, "message": "Merge branch \u0027cpus4096-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027cpus4096-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (31 commits)\n NR_CPUS: Replace NR_CPUS in speedstep-centrino.c\n cpumask: Provide a generic set of CPUMASK_ALLOC macros, FIXUP\n NR_CPUS: Replace NR_CPUS in cpufreq userspace routines\n NR_CPUS: Replace per_cpu(..., smp_processor_id()) with __get_cpu_var\n NR_CPUS: Replace NR_CPUS in arch/x86/kernel/genapic_flat_64.c\n NR_CPUS: Replace NR_CPUS in arch/x86/kernel/genx2apic_uv_x.c\n NR_CPUS: Replace NR_CPUS in arch/x86/kernel/cpu/proc.c\n NR_CPUS: Replace NR_CPUS in arch/x86/kernel/cpu/mcheck/mce_64.c\n cpumask: Optimize cpumask_of_cpu in lib/smp_processor_id.c, fix\n cpumask: Use optimized CPUMASK_ALLOC macros in the centrino_target\n cpumask: Provide a generic set of CPUMASK_ALLOC macros\n cpumask: Optimize cpumask_of_cpu in lib/smp_processor_id.c\n cpumask: Optimize cpumask_of_cpu in kernel/time/tick-common.c\n cpumask: Optimize cpumask_of_cpu in drivers/misc/sgi-xp/xpc_main.c\n cpumask: Optimize cpumask_of_cpu in arch/x86/kernel/ldt.c\n cpumask: Optimize cpumask_of_cpu in arch/x86/kernel/io_apic_64.c\n cpumask: Replace cpumask_of_cpu with cpumask_of_cpu_ptr\n Revert \"cpumask: introduce new APIs\"\n cpumask: make for_each_cpu_mask a bit smaller\n net: Pass reference to cpumask variable in net/sunrpc/svc.c\n ...\n\nFix up trivial conflicts in drivers/cpufreq/cpufreq.c manually\n" }, { "commit": "95d04f0735b4fc837bff9aedcc3f3efb20ddc3d1", "tree": "900cd7debae9827c3e20f5199307ae27e83ba862", "parents": [ "e4044cfc493338cd09870bd45dc646336bb66e9f" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Jul 23 08:12:26 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Jul 23 08:12:26 2008 -0700" }, "message": "IB/mlx4: Add support for memory management extensions and local DMA L_Key\n\nAdd support for the following operations to mlx4 when device firmware\nsupports them:\n\n - Send with invalidate and local invalidate send queue work requests;\n - Allocate/free fast register MRs;\n - Allocate/free fast register MR page lists;\n - Fast register MR send queue work requests;\n - Local DMA L_Key.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e8bb4beb2b1f90d499134f2849727ed04c3bedc4", "tree": "3c4be492134aa4a738d1eeef144642d3e2bc9509", "parents": [ "d35cb360c29956510b2fe1a953bd4968536f7216" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Jul 22 14:20:05 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Jul 22 14:20:05 2008 -0700" }, "message": "IB/mthca: Keep free count for MTT buddy allocator\n\nMTT entries are allocated with a buddy allocator, which just keeps\nbitmaps for each level of the buddy table. However, all free space\nstarts out at the highest order, and small allocations start scanning\nfrom the lowest order. When the lowest order tables have no free\nspace, this can lead to scanning potentially millions of bits before\nfinding a free entry at a higher order.\n\nWe can avoid this by just keeping a count of how many free entries\neach order has, and skipping the bitmap scan when an order is\ncompletely empty. This provides a nice performance boost for a\nnegligible increase in memory usage.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "47b374752aed1c029f995473c7c463ee3ae5fbaa", "tree": "ce6dfb09d0e0f359b49e31e70bbfe3a599beebb2", "parents": [ "51f5f0ee22b98980f7816d42647467cd5f4b3b45" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Jul 22 14:19:39 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Jul 22 14:19:39 2008 -0700" }, "message": "IB/mlx4: Rename struct mlx4_lso_seg to mlx4_wqe_lso_seg\n\nMake the struct name consistent with other WQE segment struct types\ndefined in \u003clinux/mlx4/qp.h\u003e.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "1a867c33bb65f2921351a9bdd98548bb96f0ff8c", "tree": "9daeb99a600105643d737be1b22bb916e3e6c5b0", "parents": [ "593e4d4a05c8263a6dbd5452c21d47c5bdadd40c" ], "author": { "name": "Julia Lawall", "email": "julia@diku.dk", "time": "Tue Jul 22 14:18:10 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Jul 22 14:18:10 2008 -0700" }, "message": "IB/ehca: Release mutex in error path of alloc_small_queue_page()\n\nThe pd-\u003elock mutex is released on a successful return, so it should be\nreleased on an error return as well.\n\nThe semantic patch that makes this change is as follows:\n(http://www.emn.fr/x-info/coccinelle/)\n\n// \u003csmpl\u003e\n@@\nexpression l;\n@@\n\nmutex_lock(l);\n... when !\u003d mutex_unlock(l)\n when any\n when strict\n(\nif (...) { ... when !\u003d mutex_unlock(l)\n+ mutex_unlock(l);\n return ...;\n}\n|\nmutex_unlock(l);\n)\n// \u003c/smpl\u003e\n\nSigned-off-by: Julia Lawall \u003cjulia@diku.dk\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "593e4d4a05c8263a6dbd5452c21d47c5bdadd40c", "tree": "a6ae65ec6d4a880c7238489d34d65b09ee46ac0a", "parents": [ "5b673b71c8ca0fbdb99dc1b1434cfb554212d6ff" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Tue Jul 22 14:18:08 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Jul 22 14:18:08 2008 -0700" }, "message": "IB/ehca: Use default value for Local CA ACK Delay if FW returns 0\n\nSome firmware versions report a Local CA ACK Delay of 0. In that\ncase, return a more sensible default value of 12 (-\u003e 16 msec) instead.\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "5b673b71c8ca0fbdb99dc1b1434cfb554212d6ff", "tree": "6ef6d830a63e9fe417f6f05e819e5af56979d422", "parents": [ "d35cb360c29956510b2fe1a953bd4968536f7216" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Tue Jul 22 14:18:07 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Jul 22 14:18:07 2008 -0700" }, "message": "IB/ehca: Filter PATH_MIG events if QP was never armed\n\nCertain firmware versions sometimes cause spurious PATH_MIG events to\noccur during QP creation. Filter these events by making sure PATH_MIG\nevents are only handed down when they actually make sense (i.e. when\nthe QP has been armed at least once).\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "c76d3d28c31a68f45d6b5acaa4813138dd7883b3", "tree": "765746c107a907176aa90b1e78e0f7d15b5fdad5", "parents": [ "f71674a09f374bb0b5371b3e7b943029867477c5" ], "author": { "name": "Greg Kroah-Hartman", "email": "gregkh@suse.de", "time": "Wed May 21 12:52:33 2008 -0700" }, "committer": { "name": "Greg Kroah-Hartman", "email": "gregkh@suse.de", "time": "Mon Jul 21 21:54:43 2008 -0700" }, "message": "device create: infiniband: convert device_create to device_create_drvdata\n\ndevice_create() is race-prone, so use the race-free\ndevice_create_drvdata() instead as device_create() is going away.\n\nCc: Roland Dreier \u003crolandd@cisco.com\u003e\nCc: Sean Hefty \u003csean.hefty@intel.com\u003e\nCc: Hal Rosenstock \u003chal.rosenstock@gmail.com\u003e\nSigned-off-by: Greg Kroah-Hartman \u003cgregkh@suse.de\u003e\n\n" }, { "commit": "82638844d9a8581bbf33201cc209a14876eca167", "tree": "961d7f9360194421a71aa644a9d0c176a960ce49", "parents": [ "9982fbface82893e77d211fbabfbd229da6bdde6", "63cf13b77ab785e87c867defa8545e6d4a989774" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Jul 16 00:29:07 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Jul 16 00:29:07 2008 +0200" }, "message": "Merge branch \u0027linus\u0027 into cpus4096\n\nConflicts:\n\n\tarch/x86/xen/smp.c\n\tkernel/sched_rt.c\n\tnet/iucv/iucv.c\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6c9fcaf2eec1b9f85226a694230dd957dd7926b3", "tree": "f8c824c6c64dc411752c844f116e693760768bcc", "parents": [ "b9d2252c1e44fa83a4e65fdc9eb93db6297c55af", "199a952876adbfc2b6c13b8b07adabebf4ff54b2" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jul 15 21:10:12 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jul 15 21:10:12 2008 +0200" }, "message": "Merge branch \u0027core/rcu\u0027 into core/rcu-for-linus\n" }, { "commit": "f507d28bff0601f1a8a96b7939fa3855c50d25b6", "tree": "cc123185fdd19bac8c6309adeef0e39b47ef9b04", "parents": [ "2d92865158d0e21ef4350703af64bc2a610d81d3" ], "author": { "name": "Eli Cohen", "email": "eli@mellanox.co.il", "time": "Mon Jul 14 23:48:53 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:53 2008 -0700" }, "message": "IB/mlx4: Use kzalloc() for new QPs so flags are initialized to 0\n\nCurrent code uses kmalloc() and then just does a bitwise OR operation on\nqp-\u003eflags in create_qp_common(), which means that qp-\u003eflags may\npotentially have some unintended bits set. This patch uses kzalloc()\nand avoids further explicit clearing of structure members, which also\nshrinks the code:\n\nadd/remove: 0/0 grow/shrink: 0/1 up/down: 0/-65 (-65)\nfunction old new delta\ncreate_qp_common 2024 1959 -65\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "4ab928f69208d240d3681336f34589e4b151824f", "tree": "aca612ffbf703870cac63efb5ec5d8955ac2bc3c", "parents": [ "96f15c03532282366364ecfd20f04e49b5d96f3a" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Jul 14 23:48:53 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:53 2008 -0700" }, "message": "RDMA/cxgb3: Fixes for zero STag\n\nHandling the zero STag in receive work request requires some extra\nlogic in the driver:\n\n - Only set the QP_PRIV bit for kernel mode QPs.\n\n- Add a zero STag build function for recv wrs. The uP needs a PBL\n allocated and passed down in the recv WR so it can construct a HW\n PBL for the zero STag S/G entries. Note: we need to place a few\n restrictions on zero STag usage because of this:\n\n 1) all SGEs in a recv WR must either be zero STag or not. No mixing.\n\n 2) an individual SGE length cannot exceed 128MB for a zero-stag SGE.\n This should be OK since it\u0027s not really practical to allocate\n such a large chunk of pinned contiguous DMA mapped memory.\n\n- Add an optimized non-zero-STag recv wr format for kernel users.\n This is needed to optimize both zero and non-zero STag cracking in\n the recv path for kernel users.\n\n - Remove the iwch_ prefix from the static build functions.\n\n - Bump required FW version.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\n" }, { "commit": "96f15c03532282366364ecfd20f04e49b5d96f3a", "tree": "cf3cdbd22a112c43807175045d4e02286b729de0", "parents": [ "aed012279d35e88e29fd55737d8821604433f50a" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Jul 14 23:48:53 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:53 2008 -0700" }, "message": "RDMA/core: Add local DMA L_Key support\n\n- Change the IB_DEVICE_ZERO_STAG flag to the transport-neutral name\n IB_DEVICE_LOCAL_DMA_LKEY, which is used by iWARP RNICs to indicate 0\n STag support and IB HCAs to indicate reserved L_Key support.\n\n- Add a u32 local_dma_lkey member to struct ib_device. Drivers fill\n this in with the appropriate local DMA L_Key (if they support it).\n\n- Fix up the drivers using this flag.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "aed012279d35e88e29fd55737d8821604433f50a", "tree": "48a1223fd53f471d61254d1eb2e3263bf0b33e99", "parents": [ "c036925ac0e940a4e8525b08e89d2c64fe282c51" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:52 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:52 2008 -0700" }, "message": "IB/mthca: Fix check of max_send_sge for special QPs\n\nThe MLX transport requires two extra gather entries for sends (one for\nthe header and one for the checksum at the end, as the comment says).\nHowever the code checked that max_recv_sge was not too big, instead of\nchecking max_send_sge as it should have. Fix the code to check the\ncorrect condition.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "c036925ac0e940a4e8525b08e89d2c64fe282c51", "tree": "01bf048b52e4ae808303077440672c6e6fd5bcb1", "parents": [ "4522e08ced48baaf28990e2674e940aae9940310" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:52 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:52 2008 -0700" }, "message": "IB/mthca: Use round_jiffies() for catastrophic error polling timer\n\nExactly when the catastrophic error polling timer function runs is not\nimportant, so use round_jiffies() to save unnecessary wakeups.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "4522e08ced48baaf28990e2674e940aae9940310", "tree": "9c17d3aadb4adcd757c58331cc6a20e4a133cb50", "parents": [ "bc3a290b51aaefc6a6af2d6e6d52ed32387c416c" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:52 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:52 2008 -0700" }, "message": "IB/mthca: Remove \"stop\" flag for catastrophic error polling timer\n\nSince we use del_timer_sync() anyway, there\u0027s no need for an\nadditional flag to tell the timer not to rearm.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "df8666198dd058b9498ebdbc52c61957206d30a5", "tree": "7d2c8cacb34aa9e518f77b7b16587e2406e1571a", "parents": [ "bd3606715effbf37df986548c43bbed0842b49d5" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Mon Jul 14 23:48:52 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:52 2008 -0700" }, "message": "IB/ipath: Use IEEE OUI for vendor_id reported by ibv_query_device()\n\nThe IB spe. for SubnGet(NodeInfo) and query HCA says that the vendor\nID field should be the IEEE OUI assigned to the vendor. The ipath\ndriver was returning the PCI vendor ID instead. This will affect\napplications which call ibv_query_device(). The old value was\n0x001fc1 or 0x001077, the new value is 0x001175.\n\nThe vendor ID doesn\u0027t appear to be exported via /sys so that should\nreduce possible compatibility issues. I\u0027m only aware of Open MPI as a\nmajor application which depends on this change, and they have made\nnecessary adjustments.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "70fe1796a5ebc5f955be39bba5c42eee9eb89e1f", "tree": "1d0b092919a50ba23a958cdad199ba5a5389d535", "parents": [ "8294f29767c53e97664a27db9974adea8e2ea95b" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Jul 14 23:48:49 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:49 2008 -0700" }, "message": "RDMA/cxgb3: Set rkey field for new memory windows in iwch_alloc_mw()\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "8294f29767c53e97664a27db9974adea8e2ea95b", "tree": "b2c2ab078539b486667fcb1464a02bedeb5b7c85", "parents": [ "52c8084b740c42af27d5bfa62cec7079d12fbc2b" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:49 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:49 2008 -0700" }, "message": "RDMA/nes: Get rid of ring_doorbell parameter of nes_post_cqp_request()\n\nEvery caller of nes_post_cqp_request() passed it NES_CQP_REQUEST_RING_DOORBELL,\nso just remove that parameter and always ring the doorbell.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\nAcked-by: Faisal Latif \u003cflatif@neteffect.com\u003e\n" }, { "commit": "52c8084b740c42af27d5bfa62cec7079d12fbc2b", "tree": "d6bbe61d127501b9d45a74fae7421c452cc2d084", "parents": [ "1ff66e8c1faee7c2711b84b9c89e1c5fcd767839" ], "author": { "name": "Jon Mason", "email": "jon@opengridcomputing.com", "time": "Mon Jul 14 23:48:49 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:49 2008 -0700" }, "message": "RDMA/cxgb3: Propagate HW page size capabilities\n\ncxgb3 does not currently report the page size capabilities, and\nincorrectly reports them internally.\n\nThis version changes the bit-shifting to a static value (per Steve\u0027s\nrequest).\n\nSigned-off-by: Jon Mason \u003cjon@opengridcomputing.com\u003e\nAcked-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "1ff66e8c1faee7c2711b84b9c89e1c5fcd767839", "tree": "7a42adc119605abd1acb54d16b8a93f1effd2069", "parents": [ "ee1e2c82c245a5fb2864e9dbcdaab3390fde3fcc" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:49 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:49 2008 -0700" }, "message": "RDMA/nes: Encapsulate logic nes_put_cqp_request()\n\nThe iw_nes driver repeats the logic\n\n\tif (atomic_dec_and_test(\u0026cqp_request-\u003erefcount)) {\n\t\tif (cqp_request-\u003edynamic) {\n\t\t\tkfree(cqp_request);\n\t\t} else {\n\t\t\tspin_lock_irqsave(\u0026nesdev-\u003ecqp.lock, flags);\n\t\t\tlist_add_tail(\u0026cqp_request-\u003elist, \u0026nesdev-\u003ecqp_avail_reqs);\n\t\t\tspin_unlock_irqrestore(\u0026nesdev-\u003ecqp.lock, flags);\n\t\t}\n\t}\n\nover and over. Wrap this up in functions nes_free_cqp_request() and\nnes_put_cqp_request() to simplify such code.\n\nIn addition to making the source smaller and more readable, this shrinks\nthe compiled code quite a bit:\n\nadd/remove: 2/0 grow/shrink: 0/13 up/down: 164/-1692 (-1528)\nfunction old new delta\nnes_free_cqp_request - 147 +147\nnes_put_cqp_request - 17 +17\nnes_modify_qp 2316 2293 -23\nnes_hw_modify_qp 737 657 -80\nnes_dereg_mr 945 860 -85\nflush_wqes 501 416 -85\nnes_manage_apbvt 648 560 -88\nnes_reg_mr 1117 1026 -91\nnes_cqp_ce_handler 927 769 -158\nnes_alloc_mw 1052 884 -168\nnes_create_qp 5314 5141 -173\nnes_alloc_fmr 2212 2035 -177\nnes_destroy_cq 1097 918 -179\nnes_create_cq 2787 2598 -189\nnes_dealloc_mw 762 566 -196\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\nAcked-by: Faisal Latif \u003cflatif@neteffect.com\u003e\n" }, { "commit": "038919f29682b00ea95506e959210fc72d1aaf64", "tree": "3631f2f0785968062a3b8b3a0005a3ad2a018866", "parents": [ "af40da894e96d5c826d38be3ea53ee00d9de0367" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Mon Jul 14 23:48:49 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:49 2008 -0700" }, "message": "IB/ehca: Make device table externally visible\n\nThis gives ehca an autogenerated modalias and therefore enables automatic loading.\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "521e575b9a7324a0bca762622139f69582a042bf", "tree": "5962695835c6d11b424d76c64421ebd436b52a34", "parents": [ "47ee1b9f2e7bf73950602efe0b74fa1a8481f222" ], "author": { "name": "Ron Livne", "email": "ronli@voltaire.com", "time": "Mon Jul 14 23:48:48 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:48 2008 -0700" }, "message": "IB/mlx4: Add support for blocking multicast loopback packets\n\nAdd support for handling the IB_QP_CREATE_MULTICAST_BLOCK_LOOPBACK\nflag by using the per-multicast group loopback blocking feature of\nmlx4 hardware.\n\nSigned-off-by: Ron Livne \u003cronli@voltaire.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "14cc180f7b032f8484c1a3d0533b1129ffe307fd", "tree": "0f544f596e00955f56cb38051c5e2ce3c40c0b40", "parents": [ "7f624d023b5fb150831e02c1e4c0f2619ade72c2" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Jul 14 23:48:48 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:48 2008 -0700" }, "message": "RDMA/cxgb3: Add support for protocol statistics\n\n- Add a new rdma ctl command called RDMA_GET_MIB to the cxgb3 low\n level driver to obtain the protocol mib from the rnic hardware.\n\n- Add new iw_cxgb3 provider method to get the MIB from the low level\n driver.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "eec8845d29504a12fbd434e192d61aed3d9d74fa", "tree": "d8332777dfce7af169db842de54cdfb74d6e825d", "parents": [ "97d1cc8055c7b3fbd35bf693775d61102e65d174" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:47 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:47 2008 -0700" }, "message": "RDMA/cxgb3: Remove write-only iwch_rnic_attributes fields\n\nThe members struct iwch_rnic_attributes.vendor_id and .vendor_part_id\nare write-only, so we might as well get rid of them.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\nAcked-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\n" }, { "commit": "97d1cc8055c7b3fbd35bf693775d61102e65d174", "tree": "e120b64dacf4a7b2dc3de88aefbe4888807fd7fb", "parents": [ "6f7bc01a7382641c61ec036d68ff3a9140b48a1c" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Jul 14 23:48:47 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:47 2008 -0700" }, "message": "RDMA/cxgb3: Fix up some ib_device_attr fields\n\n- set fw_ver\n- set hw_ver\n- set max_qp_wr to something reasonable\n- set max_cqe to something reasonable\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6f7bc01a7382641c61ec036d68ff3a9140b48a1c", "tree": "debf518649e7af08c42465f6683bc66322ba1554", "parents": [ "3e255eac561672cbc92844b9f16cae9304c2a783" ], "author": { "name": "Stefan Roscher", "email": "ossrosch@linux.vnet.ibm.com", "time": "Mon Jul 14 23:48:47 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:47 2008 -0700" }, "message": "IB/ehca: In case of lost interrupts, trigger EOI to reenable interrupts\n\nDuring corner case testing, we noticed that some versions of ehca do\nnot properly transition to interrupt done in special load situations.\nThis can be resolved by periodically triggering EOI through H_EOI, if\nEQEs are pending.\n\nSigned-off-by: Stefan Roscher \u003cstefan.roscher@de.ibm.com\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "3e255eac561672cbc92844b9f16cae9304c2a783", "tree": "2e3181032185920f569b3dcaa0b1ad881674545e", "parents": [ "7c27f358209a8ce7c57b584346d7b611e823f1b1" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Mon Jul 14 23:48:47 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:47 2008 -0700" }, "message": "IB/ehca: Reject receive work requests if QP is in RESET state\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7c27f358209a8ce7c57b584346d7b611e823f1b1", "tree": "2978eba94e5b3a7e64086291c58c9dff8a7d231b", "parents": [ "d3809ad0972297fbc7ef0585049ef465d9d8d79d" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:46 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:46 2008 -0700" }, "message": "IB/mlx4: Remove extra code for RESET-\u003eERR QP state transition\n\nCommit 65adfa91 (\"IB/mlx4: Fix RESET to RESET and RESET to ERROR\ntransitions\") added some extra code to handle a QP state transition\nfrom RESET to ERROR. However, the latest 1.2.1 version of the IB spec\nhas clarified that this transition is actually not allowed, so we can\nremove this extra code again.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d3809ad0972297fbc7ef0585049ef465d9d8d79d", "tree": "a565a23430de36a1b8f49cc9cf5267efc65218a7", "parents": [ "e5a5e7d59af5944a674b9cea420a1fedc60496f2" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:46 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:46 2008 -0700" }, "message": "IB/mthca: Remove extra code for RESET-\u003eERR QP state transition\n\nCommit b18aad71 (\"IB/mthca: Fix RESET to ERROR transition\") added some\nextra code to handle a QP state transition from RESET to ERROR.\nHowever, the latest 1.2.1 version of the IB spec has clarified that\nthis transition is actually not allowed, so we can remove this extra\ncode again.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6578cf33989a594bab37af988d45d87812b946b8", "tree": "59dd9f73c29443a5d1fa199418b7d5d982fe5341", "parents": [ "d1f2cd895f8733faa9d79d09d825a2ed80002ac7" ], "author": { "name": "Eli Cohen", "email": "eli@dev.mellanox.co.il", "time": "Mon Jul 14 23:48:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:45 2008 -0700" }, "message": "IB/mlx4: Pass congestion management class MADs to the HCA\n\nConnectX HCAs support the IB_MGMT_CLASS_CONG_MGMT management class, so\nprocess MADs of this class through the MAD_IFC firmware command.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d1f2cd895f8733faa9d79d09d825a2ed80002ac7", "tree": "45d8f35de710b091af17611f3362f82834b5630f", "parents": [ "e7e55829999deaab3f43e201a087731c02c54cf9" ], "author": { "name": "Eli Cohen", "email": "eli@dev.mellanox.co.il", "time": "Mon Jul 14 23:48:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:45 2008 -0700" }, "message": "IB/mlx4: Configure QPs\u0027 max message size based on real device capability\n\nConnectX returns the max message size it supports through the\nQUERY_DEV_CAP firmware command. When modifying a QP to RTR, the max\nmessage size for the QP must be specified. This value must not exceed\nthe value declared through QUERY_DEV_CAP. The current code ignores\nthe max allowed size and unconditionally sets the value to 2^31. This\npatch sets all QPs to the max value allowed as returned from firmware.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e7e55829999deaab3f43e201a087731c02c54cf9", "tree": "665f2ff291045af9469bbb929f99224e9707965b", "parents": [ "00f7ec36c9324928e4cd23f02e6d8550f30c32ca" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Jul 14 23:48:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:45 2008 -0700" }, "message": "RDMA/cxgb3: MEM_MGT_EXTENSIONS support\n\n- set IB_DEVICE_MEM_MGT_EXTENSIONS capability bit if fw supports it.\n- set max_fast_reg_page_list_len device attribute.\n- add iwch_alloc_fast_reg_mr function.\n- add iwch_alloc_fastreg_pbl\n- add iwch_free_fastreg_pbl\n- adjust the WQ depth for kernel mode work queues to account for\n fastreg possibly taking 2 WR slots.\n- add fastreg_mr work request support.\n- add local_inv work request support.\n- add send_with_inv and send_with_se_inv work request support.\n- removed useless duplicate enums/defines for TPT/MW/MR stuff.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "00f7ec36c9324928e4cd23f02e6d8550f30c32ca", "tree": "dd9bea0d7589d49b4eb7e264e5f318045fcee1fb", "parents": [ "f89271da32bc1a636cf4eb078e615930886cd013" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Jul 14 23:48:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:45 2008 -0700" }, "message": "RDMA/core: Add memory management extensions support\n\nThis patch adds support for the IB \"base memory management extension\"\n(BMME) and the equivalent iWARP operations (which the iWARP verbs\nmandates all devices must implement). The new operations are:\n\n - Allocate an ib_mr for use in fast register work requests.\n\n - Allocate/free a physical buffer lists for use in fast register work\n requests. This allows device drivers to allocate this memory as\n needed for use in posting send requests (eg via dma_alloc_coherent).\n\n - New send queue work requests:\n * send with remote invalidate\n * fast register memory region\n * local invalidate memory region\n * RDMA read with invalidate local memory region (iWARP only)\n\nConsumer interface details:\n\n - A new device capability flag IB_DEVICE_MEM_MGT_EXTENSIONS is added\n to indicate device support for these features.\n\n - New send work request opcodes IB_WR_FAST_REG_MR, IB_WR_LOCAL_INV,\n IB_WR_RDMA_READ_WITH_INV are added.\n\n - A new consumer API function, ib_alloc_mr() is added to allocate\n fast register memory regions.\n\n - New consumer API functions, ib_alloc_fast_reg_page_list() and\n ib_free_fast_reg_page_list() are added to allocate and free\n device-specific memory for fast registration page lists.\n\n - A new consumer API function, ib_update_fast_reg_key(), is added to\n allow the key portion of the R_Key and L_Key of a fast registration\n MR to be updated. Consumers call this if desired before posting\n a IB_WR_FAST_REG_MR work request.\n\nConsumers can use this as follows:\n\n - MR is allocated with ib_alloc_mr().\n\n - Page list memory is allocated with ib_alloc_fast_reg_page_list().\n\n - MR R_Key/L_Key \"key\" field is updated with ib_update_fast_reg_key().\n\n - MR made VALID and bound to a specific page list via\n ib_post_send(IB_WR_FAST_REG_MR)\n\n - MR made INVALID via ib_post_send(IB_WR_LOCAL_INV),\n ib_post_send(IB_WR_RDMA_READ_WITH_INV) or an incoming send with\n invalidate operation.\n\n - MR is deallocated with ib_dereg_mr()\n\n - page lists dealloced via ib_free_fast_reg_page_list().\n\nApplications can allocate a fast register MR once, and then can\nrepeatedly bind the MR to different physical block lists (PBLs) via\nposting work requests to a send queue (SQ). For each outstanding\nMR-to-PBL binding in the SQ pipe, a fast_reg_page_list needs to be\nallocated (the fast_reg_page_list is owned by the low-level driver\nfrom the consumer posting a work request until the request completes).\nThus pipelining can be achieved while still allowing device-specific\npage_list processing.\n\nThe 32-bit fast register memory key/STag is composed of a 24-bit index\nand an 8-bit key. The application can change the key each time it\nfast registers thus allowing more control over the peer\u0027s use of the\nkey/STag (ie it can effectively be changed each time the rkey is\nrebound to a page list).\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f3781d2e89f12dd5afa046dc56032af6e39bd116", "tree": "30d170dc1534daf283cfb9c7278c2c3926b31a0f", "parents": [ "4deccd6d95f1f1536dad3c842e39c1ace577329d" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:44 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:44 2008 -0700" }, "message": "RDMA: Remove subversion $Id tags\n\nThey don\u0027t get updated by git and so they\u0027re worse than useless.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "fd91b1bf1bb6fb443cb8c7600c7314f093b31f40", "tree": "80f9efa76189711965243f13fee1fb01d5ec3930", "parents": [ "9670e553915e67fb68f13258644342c68dc26b84" ], "author": { "name": "Robert P. J. Day", "email": "rpjday@crashcourse.ca", "time": "Mon Jul 14 23:48:44 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:44 2008 -0700" }, "message": "IB/ipath: Simplify code using ARRAY_SIZE() macro\n\nSigned-off-by: Robert P. J. Day \u003crpjday@crashcourse.ca\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "9670e553915e67fb68f13258644342c68dc26b84", "tree": "68730cafe26cdb14d591f5f9c80bdeb1d6c85642", "parents": [ "164ba0893c27a216557396320b6063fdac040392" ], "author": { "name": "Eli Cohen", "email": "eli@mellanox.co.il", "time": "Mon Jul 14 23:48:44 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:44 2008 -0700" }, "message": "IB/mlx4: Optimize QP stamping\n\nThe idea is that for QPs with fixed size work requests (eg selective\nsignaling QPs), before stamping the WQE, we read the value of the DS\nfield, which gives the effective size of the descriptor as used in the\nprevious post. Then we stamp only that area, since the rest of the\ndescriptor is already stamped.\n\nWhen initializing the send queue buffer, make sure the DS field is\ninitialized to the max descriptor size so that the subsequent stamping\nwill be done on the entire descriptor area.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "929555a2baed9b0b050d03532655bfd721a43c44", "tree": "fdef410bfe02bab41f71e982af8c5bc467f47df4", "parents": [ "969a60f9db3f879f95bd37026a3c3bf02cc2568f" ], "author": { "name": "Christophe Jaillet", "email": "christophe.jaillet@wanadoo.fr", "time": "Mon Jul 14 23:48:43 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jul 14 23:48:43 2008 -0700" }, "message": "RDMA/nes: Remove unnecessary memset()\n\nRemove an explicit memset(..., 0, ...) of a \u0027listener\u0027 structure\nallocated with kzalloc().\n\nSigned-off-by: Christophe Jaillet \u003cchristophe.jaillet@wanadoo.fr\u003e\nAcked-by: Faisal Latif \u003cfaisal@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2fceef397f9880b212a74c418290ce69e7ac00eb", "tree": "d9cc09ab992825ef7fede4a688103503e3caf655", "parents": [ "feae1ef116ed381625d3731c5ae4f4ebcb3fa302", "bce7f793daec3e65ec5c5705d2457b81fe7b5725" ], "author": { "name": "Jonathan Corbet", "email": "corbet@lwn.net", "time": "Mon Jul 14 15:29:34 2008 -0600" }, "committer": { "name": "Jonathan Corbet", "email": "corbet@lwn.net", "time": "Mon Jul 14 15:29:34 2008 -0600" }, "message": "Merge commit \u0027v2.6.26\u0027 into bkl-removal\n" }, { "commit": "0c81b2a1448bc6a2a9b2d6469fb0669fb4b25e5b", "tree": "6f82579cae6d6e39fa9f837a3c349ded51e19d14", "parents": [ "0729fbf3bc70870370b4f43d652f05a468dc68b8", "70ff05554f91a1edda1f11684da1dbde09e2feea" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 11 10:46:50 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 11 10:46:50 2008 +0200" }, "message": "Merge branch \u0027linus\u0027 into core/rcu\n\nConflicts:\n\n\tinclude/linux/rculist.h\n\tkernel/rcupreempt.c\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "5e19cf663be534c7c15a35a86fa7ddc9f797e4f4", "tree": "32fa3b0fdc33698a307c60289701d27282397f8e", "parents": [ "62786b9e81a2dbe9c073a2ade52d33a2627d6d85" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Tue Jul 08 14:40:05 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Jul 08 14:40:05 2008 -0700" }, "message": "RDMA/cxgb3: Fix regression caused by class_device -\u003e device conversion\n\nThe change to iwch_provider.c in commit f4e91eb4 (\"IB: convert struct\nclass_device to struct device\") undid the fix done in commit 7f049f2f\n(\"RDMA/cxgb3: Hold rtnl_lock() around ethtool get_drvinfo call\"). It\nremoved the calls to rtnl_lock() that serialized the iw_cxgb3 ethtool\nops calls into the cxgb3 driver. This locking is needed to avoid\nmessing up the internal state of the cxgb3 driver.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "68083e05d72d94f347293d8cc0067050ba904bfa", "tree": "842e71365bd90866be7add181661a4039d891564", "parents": [ "7baac8b91f9871ba8cb09af84de4ae1d86d07812", "b7279469d66b55119784b8b9529c99c1955fe747" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Jul 06 14:23:39 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Jul 06 14:23:39 2008 +0200" }, "message": "Merge commit \u0027v2.6.26-rc9\u0027 into cpus4096\n" }, { "commit": "9a13150109fb418c50fa400c012f90d0ce6f67c3", "tree": "237d8ee3b8b87984776b5aa0f05b92f84d372a1d", "parents": [ "3ccf79f4570acacfefc51772e8f9207895b35ad7", "543cf4cb3fe6f6cae3651ba918b9c56200b257d0" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jun 26 09:24:23 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jun 26 09:24:23 2008 +0200" }, "message": "Merge commit \u0027v2.6.26-rc8\u0027 into core/rcu\n" } ], "next": "87afd448b186c885d67a08b7417cd46253b6a9d6" }