)]}' { "log": [ { "commit": "59fef3b1e96217c6e736372ff8cc95cbcca1b6aa", "tree": "5373713d77df970b52e9dd968a69252d469433a9", "parents": [ "ce684df05a531904ea055d01aeee75321fa0db1e" ], "author": { "name": "Jack Morgenstein", "email": "jackm@mellanox.co.il", "time": "Tue Apr 11 18:16:27 2006 +0300" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 12 11:42:30 2006 -0700" }, "message": "IB/mthca: Fix max_srq_sge returned by ib_query_device for Tavor devices\n\nThe driver allocates SRQ WQEs size with a power of 2 size both for\nTavor and for memfree. For Tavor, however, the hardware only requires\nthe WQE size to be a multiple of 16, not a power of 2, and the max\nnumber of scatter-gather allowed is reported accordingly by the\nfirmware (and this is the value currently returned by\nib_query_device() and ibv_query_device()).\n\nIf the max number of scatter/gather entries reported by the FW is used\nwhen creating an SRQ, the creation will fail for Tavor, since the\nrequired WQE size will be increased to the next power of 2, which\nturns out to be larger than the device permitted max WQE size (which\nis not a power of 2).\n\nThis patch reduces the reported SRQ max wqe size so that it can be used\nsuccessfully in creating an SRQ on Tavor HCAs.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n\n" }, { "commit": "ce684df05a531904ea055d01aeee75321fa0db1e", "tree": "0190ad3a94d12efeed218abe8e69a9062a75c75c", "parents": [ "f697f74a6b189702474b2fd457e1f9365fa213e3" ], "author": { "name": "Michael S. Tsirkin", "email": "mst@mellanox.co.il", "time": "Mon Apr 10 13:17:43 2006 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 10 13:17:43 2006 -0700" }, "message": "IB/cache: Use correct pointer to calculate size\n\nWhen allocating gid_cache, use kmalloc(sizeof *gid_cache, ...) rather\nthan kmalloc(sizeof *pkey_cache, ...). It doesn\u0027t really matter which\none is used, since the size ends up the same either way, but it\u0027s much\nbetter to say what we mean.\n\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f697f74a6b189702474b2fd457e1f9365fa213e3", "tree": "2e01abf6b8f324b195c7d72e925b79e9eca9ab1f", "parents": [ "a30bb96c6f5aca6513e4dbd94962da03d14b20a9" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 10 09:43:59 2006 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 10 09:43:59 2006 -0700" }, "message": "IPoIB: Use spin_lock_irq() instead of spin_lock_irqsave()\n\nWe know ipoib_flush_paths() is called from plain process context with\ninterrupts enabled, since it does wait_for_completion(). So there\u0027s\nno need to use spin_lock_irqsave() -- spin_lock_irq() is fine.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "a30bb96c6f5aca6513e4dbd94962da03d14b20a9", "tree": "7314d0813071b9e1b808422c96e868c26e14245a", "parents": [ "abf45dbb5b256dab439ca3b6b71191ecfddf9cb6" ], "author": { "name": "Eli Cohen", "email": "eli@mellanox.co.il", "time": "Wed Apr 05 15:59:34 2006 +0300" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 10 09:43:59 2006 -0700" }, "message": "IPoIB: Close race in ipoib_flush_paths()\n\nib_sa_cancel_query() must be called with priv-\u003elock held since\na completion might arrive and set path-\u003equery to NULL.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "abf45dbb5b256dab439ca3b6b71191ecfddf9cb6", "tree": "c2b95e3e911f6c8649c84c196de8b399cf7db269", "parents": [ "0f4852513fb07405ce88da40d8c497060561246e" ], "author": { "name": "Michael S. Tsirkin", "email": "mst@mellanox.co.il", "time": "Wed Apr 05 15:47:16 2006 +0300" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 10 09:43:58 2006 -0700" }, "message": "IB/mthca: Disable tuning PCI read burst size\n\nThe PCI spec recommends against drivers playing with a device\u0027s PCI\nread burst size, and says that systems software should configure it.\nAnd we actually have users that report that changing it from the\ndefault set by BIOS hurts performance and/or stability for them. On\nthe other hand, the Mellanox Programmer\u0027s Reference Manual recommends\nturning it up all the way to the maximum value. Some tests conducted\nhere in the lab do not show performance improvement from this tuning,\nbut this might be just me.\n\nAs a work-around, make this tuning an option, off by default (safe\nvalue), with an eye towards removing it completely one day if no one\ncomplains.\n\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "0f4852513fb07405ce88da40d8c497060561246e", "tree": "4221d43a7868b0431d7564601017d8f1449cd13d", "parents": [ "f2de3b06126ddb07d0e4617225d74dce0855add3" ], "author": { "name": "Shirley Ma", "email": "xma@us.ibm.com", "time": "Mon Apr 10 09:43:58 2006 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 10 09:43:58 2006 -0700" }, "message": "IPoIB: Make send and receive queue sizes tunable\n\nMake IPoIB\u0027s send and receive queue sizes tunable via module\nparameters (\"send_queue_size\" and \"recv_queue_size\"). This allows the\nqueue sizes to be enlarged to fix disastrously bad performance on some\nplatforms and workloads, without bloating memory usage when large\nqueues aren\u0027t needed.\n\nSigned-off-by: Shirley Ma \u003cxma@us.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f2de3b06126ddb07d0e4617225d74dce0855add3", "tree": "21a62b2115804688d700c01ed2ede87413b5d9d1", "parents": [ "bf6a9e31cfa768ce0a8e18474b3ca808641d9243" ], "author": { "name": "Eli Cohen", "email": "eli@mellanox.co.il", "time": "Wed Apr 05 14:59:40 2006 +0300" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 10 09:43:58 2006 -0700" }, "message": "IPoIB: Wait for join to finish before freeing mcast struct\n\nipoib_mcast_restart_task() might free an mcast object while a join\nrequest is still outstanding, leading to an oops when the query\ncompletes. Fix this by waiting for query to complete, similar to what\nipoib_stop_thread() is doing. The wait for mcast completion code is\nconsolidated in wait_for_mcast_join().\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "bf6a9e31cfa768ce0a8e18474b3ca808641d9243", "tree": "a7ebdb5a10e528959ca1497e222975d3087a5eef", "parents": [ "d2e0655ede1d91c3a586455d03a4a2d57e659830" ], "author": { "name": "Jack Morgenstein", "email": "jackm@mellanox.co.il", "time": "Mon Apr 10 09:43:47 2006 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 10 09:43:47 2006 -0700" }, "message": "IB: simplify static rate encoding\n\nPush translation of static rate to HCA format into low-level drivers,\nwhere it belongs. For static rate encoding, use encoding of rate\nfield from IB standard PathRecord, with addition of value 0, for\nbackwards compatibility with current usage. The changes are:\n\n - Add enum ib_rate to midlayer includes.\n - Get rid of static rate translation in IPoIB; just use static rate\n directly from Path and MulticastGroup records.\n - Update mthca driver to translate absolute static rate into the\n format used by hardware. This also fixes mthca\u0027s static rate\n handling for HCAs that are capable of 4X DDR.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d2e0655ede1d91c3a586455d03a4a2d57e659830", "tree": "e507e7c6dee32cb7ea8ebe0fc2024f81cf0f9b0f", "parents": [ "ce1823f0323be9f38bbe0df229a5bba025404923" ], "author": { "name": "Michael S. Tsirkin", "email": "mst@mellanox.co.il", "time": "Tue Apr 04 19:59:40 2006 +0300" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 04 14:46:48 2006 -0700" }, "message": "IPoIB: Consolidate private neighbour data handling\n\nConsolidate IPoIB\u0027s private neighbour data handling into\nipoib_neigh_alloc() and ipoib_neigh_free(). This will make it easier\nto keep track of the neighbour structures that IPoIB is handling, and\nis a nice cleanup of the code:\n\nadd/remove: 2/1 grow/shrink: 1/8 up/down: 100/-178 (-78)\nfunction old new delta\nipoib_neigh_alloc - 61 +61\nipoib_neigh_free - 36 +36\nipoib_mcast_join_finish 1288 1291 +3\npath_rec_completion 575 573 -2\nipoib_mcast_join_task 664 660 -4\nipoib_neigh_destructor 101 92 -9\nipoib_neigh_setup_dev 14 3 -11\nipoib_neigh_setup 17 - -17\npath_free 238 215 -23\nipoib_mcast_free 329 306 -23\nipoib_mcast_send 718 684 -34\nneigh_add_path 705 650 -55\n\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "ce1823f0323be9f38bbe0df229a5bba025404923", "tree": "f3c896b952cf01fb81054f65f2861be0e2d4f437", "parents": [ "227c939b00cf786b5e2e95fc904518206f478421" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 03 09:31:04 2006 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 03 09:31:04 2006 -0700" }, "message": "IB/srp: Fix memory leak in options parsing\n\nFix memory leak if parsing destination GID fails.\n\nCoverity bug 1042\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "227c939b00cf786b5e2e95fc904518206f478421", "tree": "f62cd8a2f0663d3c9853eead57ba91dd9626a572", "parents": [ "f5545d24b8aa9fccd8071203e83bc9f4b26e17a6" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sun Apr 02 14:39:20 2006 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sun Apr 02 14:39:20 2006 -0700" }, "message": "IB/mthca: Always build debugging code unless CONFIG_EMBEDDED\u003dy\n\nChange the mthca debugging trace output code so that it can enabled\nand disabled at runtime with the debug_level module parameter in\nsysfs. Also, don\u0027t allow CONFIG_INFINIBAND_MTHCA_DEBUG to be disabled\nunless CONFIG_EMBEDDED is selected. We want users (and especially\ndistros) to have this turned on unless they really need to save space,\nbecause by the time we want debugging output, it\u0027s usually too late to\nrebuild a kernel.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f5545d24b8aa9fccd8071203e83bc9f4b26e17a6", "tree": "c58bc4967eb3eff701acba0e9ea295fbc4c68c89", "parents": [ "37289efe3ee0c0a00b5d8302df9a2b007e65c187" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sun Apr 02 14:39:19 2006 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sun Apr 02 14:39:19 2006 -0700" }, "message": "IPoIB: Always build debugging code unless CONFIG_EMBEDDED\u003dy\n\nDon\u0027t allow CONFIG_INFINIBAND_IPOIB_DEBUG to be disabled unless\nCONFIG_EMBEDDED is selected. We want users (and especially distros)\nto have this turned on unless they really need to save space, because\nby the time we want debugging output, it\u0027s usually too late to rebuild\na kernel. The debugging output can be controlled at runtime via the\ndebug_level module parameter in sysfs.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "37289efe3ee0c0a00b5d8302df9a2b007e65c187", "tree": "92abe35ea148d32c735c7a675fdb9640fe9cfb7f", "parents": [ "f27f0a045b79de5729d064497e21a70871f1d6fe" ], "author": { "name": "Michael S. Tsirkin", "email": "mst@mellanox.co.il", "time": "Thu Mar 30 15:52:54 2006 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sun Apr 02 14:39:19 2006 -0700" }, "message": "IB/mad: fix oops in cancel_mads\n\nWe have seen the following OOPs in cancel_mads, when restarting opensm\nmultiple times:\n\n Call Trace:\n [\u003cc010549b\u003e] show_stack+0x9b/0xb0\n [\u003cc01055ec\u003e] show_registers+0x11c/0x190\n [\u003cc01057cd\u003e] die+0xed/0x160\n [\u003cc031b966\u003e] do_page_fault+0x3f6/0x5d0\n [\u003cc010511f\u003e] error_code+0x4f/0x60\n [\u003cf8ac4e38\u003e] cancel_mads+0x128/0x150 [ib_mad]\n [\u003cf8ac2811\u003e] unregister_mad_agent+0x11/0x130 [ib_mad]\n [\u003cf8ac2a12\u003e] ib_unregister_mad_agent+0x12/0x20 [ib_mad]\n [\u003cf8b10f23\u003e] ib_umad_close+0xf3/0x130 [ib_umad]\n [\u003cc0162937\u003e] __fput+0x187/0x1c0\n [\u003cc01627a9\u003e] fput+0x19/0x20\n [\u003cc0160f7a\u003e] filp_close+0x3a/0x60\n [\u003cc0121ca8\u003e] put_files_struct+0x68/0xa0\n [\u003cc0103cf7\u003e] do_signal+0x47/0x100\n [\u003cc0103ded\u003e] do_notify_resume+0x3d/0x40\n [\u003cc0103f9e\u003e] work_notifysig+0x13/0x25\n\nWe traced this back to local_completions unlocking mad_agent_priv-\u003elock\nwhile still keeping a pointer into local_list. A later call to\nlist_del(\u0026local-\u003ecompletion_list) would then corrupt the list.\n\nTo fix this, remove the entry from local_list after looking it up but\nbefore releasing mad_agent_priv-\u003elock, to prevent cancel_mads from\nfinding and freeing it.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@mellanox.co.il\u003e\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "77d8798b554c856e21400bc8e761bc1b2ded8967", "tree": "ea5dd7ed3ccb4b7095c37d4633f6f6a7b0a6b38e", "parents": [ "6522108f19a998a5ded4d0c4d0f9eb9736398e31" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:39 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:21 2006 -0800" }, "message": "IB/ipath: kbuild infrastructure\n\nIntegrate the ipath core and OpenIB drivers into the kernel build\ninfrastructure. Add entry to MAINTAINERS.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6522108f19a998a5ded4d0c4d0f9eb9736398e31", "tree": "675eb475939abf9889edf7b76a49e383b7c6e7e5", "parents": [ "e28c00ad67164dba688c1d19c208c5fb554465f2" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:38 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:21 2006 -0800" }, "message": "IB/ipath: infiniband verbs support\n\nThe ipath_verbs.c file implements the driver-specific components of the\nkernel\u0027s Infiniband verbs layer.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e28c00ad67164dba688c1d19c208c5fb554465f2", "tree": "b127fbb9799cebf2c1fe2fa08ad5a2e567033d84", "parents": [ "cef1cce5c87d84f76e44f0e7b4de72ab3818ac3a" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:37 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:21 2006 -0800" }, "message": "IB/ipath: misc infiniband code, part 2\n\nManagement datagram support, queue pairs, and reliable and unreliable\nconnections.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "cef1cce5c87d84f76e44f0e7b4de72ab3818ac3a", "tree": "c9cb13413cae9dd636a699e3ec7d41882fd8e514", "parents": [ "97f9efbc47f0b1bc88abac8724b505f0794a48d0" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:36 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:20 2006 -0800" }, "message": "IB/ipath: misc infiniband code, part 1\n\nCompletion queues, local and remote memory keys, and memory region\nsupport.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "97f9efbc47f0b1bc88abac8724b505f0794a48d0", "tree": "569de983df250b3c782f97c65562c31708a22788", "parents": [ "74ed6b5eb133b4acae7c47bc23457e5f8e7c1125" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:35 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:20 2006 -0800" }, "message": "IB/ipath: infiniband RC protocol support\n\nThis is an implementation of the Infiniband RC (\"reliable connection\")\nprotocol.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "74ed6b5eb133b4acae7c47bc23457e5f8e7c1125", "tree": "3ab28b15184e2a28539fc81b53257a53fdb9fc6a", "parents": [ "aa735edf5dffbe43463c3d1218912fa54a8ec724" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:34 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:20 2006 -0800" }, "message": "IB/ipath: infiniband UC and UD protocol support\n\nThese files implement the Infiniband UC (\"unreliable connection\") and UD\n(\"unreliable datagram\") protocols.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "aa735edf5dffbe43463c3d1218912fa54a8ec724", "tree": "f5ac10f3ff06a3e7dfc6a2e68be0064fbd8a1847", "parents": [ "889ab795a34247c8085e65648051e34f9fec952c" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:33 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:20 2006 -0800" }, "message": "IB/ipath: infiniband header files\n\nThese header files are used by the layered Infiniband driver.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "889ab795a34247c8085e65648051e34f9fec952c", "tree": "7bfe86ff3105a92a68d9ebfed29c501f016db843", "parents": [ "7f510b46e4771cfb89af134b3aa827d46125a2ce" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:32 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:20 2006 -0800" }, "message": "IB/ipath: layering interfaces used by higher-level driver code\n\nThe layering interfaces are used to implement the Infiniband protocols\nand the ethernet emulation driver.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7f510b46e4771cfb89af134b3aa827d46125a2ce", "tree": "09eb48dbf5d81e94d778b44b004cb9b7f242ff0b", "parents": [ "3e9b4a5eb4ae4936feeea256c0105e078c7702cd" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:31 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:19 2006 -0800" }, "message": "IB/ipath: support for userspace apps using core driver\n\nThese files introduce a char device that userspace apps use to gain\ndirect memory-mapped access to the InfiniPath hardware, and routines for\npinning and unpinning user memory in cases where the hardware needs to\nDMA into the user address space.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "3e9b4a5eb4ae4936feeea256c0105e078c7702cd", "tree": "f2d8e2f82de310ec6c7d7d44d15c39e42a165f45", "parents": [ "108ecf0d90655055d5a7db8d3a7239133b4d52b7" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:30 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:19 2006 -0800" }, "message": "IB/ipath: sysfs and ipathfs support for core driver\n\nThe ipathfs filesystem contains files that are not appropriate for\nsysfs, because they contain binary data. The hierarchy is simple; the\ntop-level directory contains driver-wide attribute files, while numbered\nsubdirectories contain per-device attribute files.\n\nOur userspace code currently expects this filesystem to be mounted on\n/ipathfs, but a final location has not yet been chosen.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "108ecf0d90655055d5a7db8d3a7239133b4d52b7", "tree": "95e3a20828478e7e66f1aa7e88e3b5cf17b93dfe", "parents": [ "097709fea03140b567bde8369f3ffafe33dfc1c6" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:29 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:19 2006 -0800" }, "message": "IB/ipath: misc driver support code\n\nEEPROM support, interrupt handling, statistics gathering, and write\ncombining management for x86_64.\n\nA note regarding i2c: The Atmel EEPROM hardware we use looks like an\ni2c device electrically, but is not i2c compliant at all from a\nfunctional perspective. We tried using the kernel\u0027s i2c support to\ntalk to it, but failed.\n\nNormal i2c devices have a single 7-bit or 10-bit i2c address that they\nrespond to. Valid 7-bit addresses range from 0x03 to 0x77. Addresses\n0x00 to 0x02 and 0x78 to 0x7F are special reserved addresses\n(e.g. 0x00 is the \"general call\" address.) The Atmel device, on the\nother hand, responds to ALL addresses. It\u0027s designed to be the only\ndevice on a given i2c bus. A given i2c device address corresponds to\nthe memory address within the i2c device itself.\n\nAt least one reason why the linux core i2c stuff won\u0027t work for this\nis that it prohibits access to reserved addresses like 0x00, which are\nreally valid addresses on the Atmel devices.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "097709fea03140b567bde8369f3ffafe33dfc1c6", "tree": "98ef94e0abcf13798c6f416ba7a5318ab4b47d7d", "parents": [ "dc741bbd4f47080c623d243546dd4cb5ff6c9564" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:28 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:19 2006 -0800" }, "message": "IB/ipath: chip initialisation code, and diag support\n\nipath_init_chip.c sets up an InfiniPath device for use.\n\nipath_diag.c permits userspace diagnostic tools to read and write a\nchip\u0027s registers. It is different in purpose from the mmap interfaces\nto the /sys/bus/pci resource files.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "dc741bbd4f47080c623d243546dd4cb5ff6c9564", "tree": "99868cf1cd79198b3937a22319e84c7286f540bf", "parents": [ "cc533a5721b79d231c127fd56d55e6df23c19770" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:27 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:19 2006 -0800" }, "message": "IB/ipath: support for PCI Express devices\n\nThis file contains routines and definitions specific to InfiniPath\ndevices that have PCI Express interfaces.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "cc533a5721b79d231c127fd56d55e6df23c19770", "tree": "3b4f172b5c056b7b88005214f81f465391e4b8c5", "parents": [ "d41d3aeb76135a70bfda9cd6666290fee0700b70" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:26 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:18 2006 -0800" }, "message": "IB/ipath: support for HyperTransport devices\n\nThe ipath_ht400.c file contains routines and definitions specific to\nHyperTransport-based InfiniPath devices.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d41d3aeb76135a70bfda9cd6666290fee0700b70", "tree": "4534e7efe5d738ba96793490f07453d0e60d2214", "parents": [ "7bb206e3b20477c8bcbbdf20834d456b0b6d82c4" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:25 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:18 2006 -0800" }, "message": "IB/ipath: core driver header files\n\nipath_common.h and ips_common.h contain definitions shared between\nuserspace and the kernel.\n\nipath_kernel.h is the core driver header file.\n\nipath_debug.h contains mask values used for controlling driver debugging.\n\nipath_registers.h contains bitmask definitions used in chip registers.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7bb206e3b20477c8bcbbdf20834d456b0b6d82c4", "tree": "020464ec844664ebdcee40e05630751a20075afb", "parents": [ "064c94f9da8845f12446ab37142aa10f3c6f66ac" ], "author": { "name": "Bryan O\u0027Sullivan", "email": "bos@pathscale.com", "time": "Wed Mar 29 15:23:24 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 31 13:14:18 2006 -0800" }, "message": "IB/ipath: core device driver\n\nThe ipath driver is a low-level driver for PathScale InfiniPath host\nchannel adapters (HCAs) based on the HT-400 and PE-800 chips, including\nthe InfiniPath HT-460, the small form factor InfiniPath HT-460, the\nInfiniPath HT-470 and the Linux Networx LS/X.\n\nThe ipath_driver.c file contains much of the low-level device handling\ncode.\n\nSigned-off-by: Bryan O\u0027Sullivan \u003cbos@pathscale.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "618a3c03fcfdf1ac4543247c8ddfb0c9d775ff33", "tree": "9b3c0baf53f0fcab01848b7816aace785afd8a94", "parents": [ "fa9656bbd9af5b95adc43eaa0a143992346378cb" ], "author": { "name": "Hal Rosenstock", "email": "halr@voltaire.com", "time": "Tue Mar 28 16:40:04 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Mar 30 07:19:51 2006 -0800" }, "message": "IB/mad: RMPP support for additional classes\n\nAdd RMPP support for additional management classes that support it.\nAlso, validate RMPP is consistent with management class specified.\n\nSigned-off-by: Hal Rosenstock \u003chalr@voltaire.com\u003e\nSigned-off-by: Sean Hefty \u003csean.hefty@intel.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "fa9656bbd9af5b95adc43eaa0a143992346378cb", "tree": "100d516324208e1a4a65b77e86bcbc94f5ef0db9", "parents": [ "e1f7868c80947d40ef8e1fd37323d939a9bf311c" ], "author": { "name": "Jack Morgenstein", "email": "jackm@mellanox.co.il", "time": "Tue Mar 28 16:39:07 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Mar 30 07:19:48 2006 -0800" }, "message": "IB/mad: include GID/class when matching receives\n\nReceived responses are currently matched against sent requests based\non TID only. According to the spec, responses should match based on\nthe combination of TID, management class, and requester LID/GID.\n\nWithout the additional qualification, an agent that is responding to\ntwo requests, both of which have the same TID, can match RMPP ACKs\nwith the incorrect transaction. This problem can occur on the SM node\nwhen responding to SA queries.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@mellanox.co.il\u003e\nSigned-off-by: Sean Hefty \u003csean.hefty@intel.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e1f7868c80947d40ef8e1fd37323d939a9bf311c", "tree": "04ee4d31a49e563bbdca385b8d558d7fee2f0d47", "parents": [ "ef12d4561900d4af37f46a8f2d97dec3c4d59bf9" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Mar 29 09:36:46 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Mar 29 09:36:46 2006 -0800" }, "message": "IB/mthca: Fix section mismatch problems\n\nQuite a few cleanup functions in mthca were marked as __devexit.\nHowever, they could also be called from error paths during\ninitialization, so they cannot be marked that way. Just delete all of\nthe incorrect annotations.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "ef12d4561900d4af37f46a8f2d97dec3c4d59bf9", "tree": "29b849109170341a546fbe0bdb52a43741b0341c", "parents": [ "a07bacca7b4032dd361ad5c87b1c39ae229e6739" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Mar 29 09:36:46 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Mar 29 09:36:46 2006 -0800" }, "message": "IPoIB: Fix oops with raw sockets\n\nipoib_hard_header() needs to handle the case that daddr is NULL. This\ncan happen when packets are injected via a raw socket, and IPoIB\nshouldn\u0027t oops in this case.\n\nReported by Anton Blanchard \u003canton@samba.org\u003e\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "a07bacca7b4032dd361ad5c87b1c39ae229e6739", "tree": "1050a1f6a00ca18cb1dc188a0af26b4cdd699ce3", "parents": [ "3f89f834497c0f37f16a3b6c32b1d60782facbca" ], "author": { "name": "Jack Morgenstein", "email": "jackm@mellanox.co.il", "time": "Sun Mar 26 17:01:12 2006 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Mar 29 09:36:46 2006 -0800" }, "message": "IB/mthca: Fix check of size in SRQ creation\n\nThe previous patch for Tavor broke MemFree logic.\n\nThe driver should perform limit check only for Tavor. For MemFree,\nthe check is incorrect, since ds (WQE stride) is always a power-of-2\n(although the max_desc_size may not be).\n\nIn Tavor, however, WQE stride and desc_size are the same, and are not\nnecessarily power-of-2. The check was really for the WQE stride (and\nit Tavor, we use max_desc_size for the stride).\n\nSigned-off-by: Jack Morgenstein \u003cjackm@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "3f89f834497c0f37f16a3b6c32b1d60782facbca", "tree": "4a27d2b5ed847fd90678d3e7758fe08b493426e1", "parents": [ "e71ac6032edf77a1e4a81f3e3b260807e94b37a5" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Mar 29 09:36:45 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Mar 29 09:36:45 2006 -0800" }, "message": "IB/srp: Fix unmapping of fake scatterlist\n\nThe recently merged patch to create a fake scatterlist for non-SG SCSI\ncommands had a bug: the driver ended up doing dma_unmap_sg() on a\nscatterlist scmnd-\u003erequest_buffer rather than the fake scatter list it\ncreated. Fix this so that the driver unmaps the same thing it maps.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7a343d4c46bc59fe617f968e996ce2fd67c5d179", "tree": "bc58caefafd0e1228266a0928f5d70aa5f262cf4", "parents": [ "192daa18dd7bfcaeb092a2ef928135745f2e6883" ], "author": { "name": "Leonid Arsh", "email": "leonida@voltaire.com", "time": "Thu Mar 23 19:52:51 2006 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 24 15:47:30 2006 -0800" }, "message": "IPoIB: P_Key change event handling\n\nThis patch causes the network interface to respond to P_Key change\nevents correctly. As a result, you\u0027ll see a child interface in the\n\"RUNNING\" state (netif_carrier_on()) only when the corresponding P_Key\nis configured by the SM. When SM removes a P_Key, the \"RUNNING\" state\nwill be disabled for the corresponding network interface. To\nimplement this, I added IB_EVENT_PKEY_CHANGE event handling. To\nprevent flushing the device before the device is open by the \"delay\nopen\" mechanism, I added an additional device flag called\nIPOIB_FLAG_INITIALIZED.\n\nThis also prevents the child network interface from trying to join to\nmulticast groups until the PKEY is configured. We used to get error\nmessages like:\n\n ib0.f2f2: couldn\u0027t attach QP to multicast group ff12:401b:f2f2:0:0:0:ffff:ffff\n\nin this case. To fix this, I just check IPOIB_FLAG_OPER_UP flag in\nipoib_set_mcast_list().\n\nSigned-off-by: Leonid Arsh \u003cleonida@voltaire.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "192daa18dd7bfcaeb092a2ef928135745f2e6883", "tree": "f6bff7aac7acd0ec5935fa0ada2889d77f58d6f4", "parents": [ "4e37b956161c3a3b160972c11c55f07b38b9830c" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 24 15:47:30 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 24 15:47:30 2006 -0800" }, "message": "IB/mthca: Fix modify QP error path\n\nIf the call to mthca_MODIFY_QP() failed, then mthca_modify_qp() would\nstill do some things it shouldn\u0027t, such as store away attributes for\nspecial QPs. Fix this, and simplify the code, by simply jumping to\nthe exit path if mthca_MODIFY_QP() fails.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "4e37b956161c3a3b160972c11c55f07b38b9830c", "tree": "d3e18ea58a3375afd2920062ad454b5e3f7371ae", "parents": [ "b0b3a8e1939d18c9bd4caca0b4b859b118a4167e" ], "author": { "name": "Leonid Arsh", "email": "leonida@voltaire.com", "time": "Wed Mar 22 19:54:24 2006 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 24 15:47:29 2006 -0800" }, "message": "IPoIB: Fix network interface \"RUNNING\" status\n\nWith the current IPoIB driver, the status of network interfaces stays\n\"RUNNING\" even if the link goes down (for example because a cable is\nunplugged). Fix this by flushing the IPoIB interface when the link\ngoes down.\n\nSigned-off-by: Leonid Arsh \u003cleonida@voltaire.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "b0b3a8e1939d18c9bd4caca0b4b859b118a4167e", "tree": "c0fdd86f8b69c6b50983fc641bf4f232379b5253", "parents": [ "b3f64967fafad2d3487cdba18bc5166aec33a823" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 24 15:47:29 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 24 15:47:29 2006 -0800" }, "message": "IB/mthca: Fix indentation\n\nFix some whitespace damage (indenting with spaces) that snuck in.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "b3f64967fafad2d3487cdba18bc5166aec33a823", "tree": "a0beb8a5ef4e0b9a30e5f456abc887d7af0391b1", "parents": [ "d4301e2c6685c87206f24f54969120b182119ab0" ], "author": { "name": "Jack Morgenstein", "email": "jackm@mellanox.co.il", "time": "Wed Mar 22 09:52:31 2006 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 24 15:47:29 2006 -0800" }, "message": "IB/mthca: Fix uninitialized variable in mthca_alloc_qp()\n\nmthca_alloc_sqp() by mthca_set_qp_size() need to set qp-\u003etransport\nbefore calling mthca_set_qp_size(), since the value is used there.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d4301e2c6685c87206f24f54969120b182119ab0", "tree": "64cd469cae71b04ec426ee2b14289a53bb9c9f9f", "parents": [ "ded9ad721d220d47989177076a181ae1f1b93af5" ], "author": { "name": "Jack Morgenstein", "email": "jackm@mellanox.co.il", "time": "Mon Mar 20 17:32:43 2006 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 24 15:47:28 2006 -0800" }, "message": "IB/mthca: Check SRQ limit in modify SRQ operation\n\nWhen setting the shared receive queue (SRQ) watermark in a modify SRQ\noperation, make sure that the supplied value is not larger than the\nfull size of the SRQ.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "ded9ad721d220d47989177076a181ae1f1b93af5", "tree": "4cd58fe6bccaaa133fbba3f22729dda3e6cb213f", "parents": [ "0ef61db837c93d4377fabd37182bb6f83ea5ca70" ], "author": { "name": "Jack Morgenstein", "email": "jackm@mellanox.co.il", "time": "Mon Mar 20 12:35:34 2006 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 24 15:47:27 2006 -0800" }, "message": "IB/mthca: Check that SRQ WQE size does not exceed device\u0027s max value\n\nGuarantee the calculated work queue entry size does not exceed the max\nallowable WQE size when creating an SRQ. This is a problem with Arbel\nin Tavor-compatibility mode because the current WQE size computation\nmethod rounds up to next power of 2.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "0ef61db837c93d4377fabd37182bb6f83ea5ca70", "tree": "04e5d5db86c5b12e3879c8a7c8933a1b8300ceda", "parents": [ "cf368713a3f3b2eb737a92d1b7186dedcc51167c" ], "author": { "name": "Dotan Barak", "email": "dotanb@mellanox.co.il", "time": "Sun Mar 19 17:20:36 2006 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 24 15:47:27 2006 -0800" }, "message": "IB/mthca: Check that sgid_index and path_mtu are valid in modify_qp\n\nAdd a check that the modify QP parameters sgid_index and path_mtu are\nvalid, since they might come from userspace.\n\nSigned-off-by: Dotan Barak \u003cdotanb@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "cf368713a3f3b2eb737a92d1b7186dedcc51167c", "tree": "450791a25611cf98bde1540a3c366d0e2a6ba117", "parents": [ "6f633c8d69415aabbccfcc494008e8e1300a98c1" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 24 15:47:26 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 24 15:47:26 2006 -0800" }, "message": "IB/srp: Use a fake scatterlist for non-SG SCSI commands\n\nSince the SCSI midlayer is moving towards entirely getting rid of\ncommands with use_sg \u003d\u003d 0, we should treat this case as an exception.\nTherefore, change the IB SRP initiator to create a fake scatterlist\nfor these commands with sg_init_one(). This simplifies the flow of\nDMA mapping and unmapping, since SRP can just use dma_map_sg() and\ndma_unmap_sg() unconditionally, rather than having to choose between\nthe dma_{map,unmap}_sg() and dma_{map,unmap}_single() variants.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6f633c8d69415aabbccfcc494008e8e1300a98c1", "tree": "8c3ad3009e6c4e19b4670c883342a047d511e434", "parents": [ "b2fd16b4ff2508ac16ae994f4bcd941f97754c00" ], "author": { "name": "Leonid Arsh", "email": "leonida@voltaire.com", "time": "Fri Mar 24 15:47:25 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 24 15:47:25 2006 -0800" }, "message": "IPoIB: Pass correct pointer when flushing child interfaces\n\nipoib_ib_dev_flush() should get passed cpriv-\u003edev, not \u0026cpriv-\u003edev.\n\nSigned-off-by: Leonid Arsh \u003cleonida@voltaire.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "3d1f337b3e7378923c89f37afb573a918ef40be5", "tree": "386798378567a10d1c7b24f599cb50f70298694c", "parents": [ "2bf2154c6bb5599e3ec3f73c34861a0b12aa839e", "5e35941d990123f155b02d5663e51a24f816b6f3" ], "author": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Mar 21 09:31:48 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Mar 21 09:31:48 2006 -0800" }, "message": "Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6\n\n* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (235 commits)\n [NETFILTER]: Add H.323 conntrack/NAT helper\n [TG3]: Don\u0027t mark tg3_test_registers() as returning const.\n [IPV6]: Cleanups for net/ipv6/addrconf.c (kzalloc, early exit) v2\n [IPV6]: Nearly complete kzalloc cleanup for net/ipv6\n [IPV6]: Cleanup of net/ipv6/reassambly.c\n [BRIDGE]: Remove duplicate const from is_link_local() argument type.\n [DECNET]: net/decnet/dn_route.c: fix inconsequent NULL checking\n [TG3]: make drivers/net/tg3.c:tg3_request_irq() static\n [BRIDGE]: use LLC to send STP\n [LLC]: llc_mac_hdr_init const arguments\n [BRIDGE]: allow show/store of group multicast address\n [BRIDGE]: use llc for receiving STP packets\n [BRIDGE]: stp timer to jiffies cleanup\n [BRIDGE]: forwarding remove unneeded preempt and bh diasables\n [BRIDGE]: netfilter inline cleanup\n [BRIDGE]: netfilter VLAN macro cleanup\n [BRIDGE]: netfilter dont use __constant_htons\n [BRIDGE]: netfilter whitespace\n [BRIDGE]: optimize frame pass up\n [BRIDGE]: use kzalloc\n ...\n" }, { "commit": "e35fc385655ac584902edd98dd07ac488e986aa1", "tree": "aa50ab6de762a5edc7f699bb77fdb94009995c8d", "parents": [ "dec73ff0293d59076d1fd8f4a264898ecfc457ec" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@mandriva.com", "time": "Mon Mar 20 22:46:40 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 20 22:46:40 2006 -0800" }, "message": "[INFINIBAND] ipoib: Remove leftover use of neigh_ops-\u003edestructor\n\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@mandriva.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c5ecd62c25400a3c6856e009f84257d5bd03f03b", "tree": "a0aeb88552772396bba986cce176028348ec041f", "parents": [ "53dcb0e38c1786aa82ada4641b4607be315b610a" ], "author": { "name": "Michael S. Tsirkin", "email": "mst@mellanox.co.il", "time": "Mon Mar 20 22:25:41 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 20 22:25:41 2006 -0800" }, "message": "[NET]: Move destructor from neigh-\u003eops to neigh_params\n\nstruct neigh_ops currently has a destructor field, which no in-kernel\ndrivers outside of infiniband use. The infiniband/ulp/ipoib in-tree\ndriver stashes some info in the neighbour structure (the results of\nthe second-stage lookup from ARP results to real link-level path), and\nit uses neigh-\u003eops-\u003edestructor to get a callback so it can clean up\nthis extra info when a neighbour is freed. We\u0027ve run into problems\nwith this: since the destructor is in an ops field that is shared\nbetween neighbours that may belong to different net devices, there\u0027s\nno way to set/clear it safely.\n\nThe following patch moves this field to neigh_parms where it can be\nsafely set, together with its twin neigh_setup. Two additional\npatches in the patch series update ipoib to use this new interface.\n\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "fd02e8038eb943755e8727a0ea193c037a51714f", "tree": "597dc0e67899c445ac85fc5b7ae8a151ca4491ee", "parents": [ "bfef73fa78ca1e56175dcbd33aa11de4764f85a5" ], "author": { "name": "Eli Cohen", "email": "eli@mellanox.co.il", "time": "Mon Mar 13 14:33:01 2006 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:26 2006 -0800" }, "message": "IB/mthca: Query SRQ srq_limit fixes\n\nFix endianness handling of srq_limit: it is big-endian in the context\nstructure, so we need to swab it before returning it.\n\nAlso add support for srq_limit query for Tavor (non-MemFree) HCAs.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "bfef73fa78ca1e56175dcbd33aa11de4764f85a5", "tree": "4d0021bcdd8e27891f2e1e1caa2b0c97f7c91d1d", "parents": [ "e10e271bfd295bf805dc294460868e1deb938211" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:26 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:26 2006 -0800" }, "message": "IPoIB: Get rid of useless test of queue length\n\nIn neigh_add_path(), the queue of delayed packets can never be full,\nbecause the queue is always freshly created and cannot be found by any\nother code path. In fact, the test of the queue length is worse than\nuseless: if somehow the test ever triggered and path_rec_start() also\nfailed, then dev_kfree_skb_any() will be called twice on the same skb.\nFix this by deleting the useless test. Pointed out by Michael\nS. Tsirkin \u003cmst@mellanox.co.il\u003e.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e10e271bfd295bf805dc294460868e1deb938211", "tree": "d2821657636e831e602f86baeabc3523a8e41285", "parents": [ "dc05980dd736bfbe5b2524b463e5f098e67a64e9" ], "author": { "name": "Dotan Barak", "email": "dotanb@mellanox.co.il", "time": "Mon Mar 20 10:08:26 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:26 2006 -0800" }, "message": "IB/mthca: Correct reported SRQ size in MemFree case.\n\nMemFree devices need to reserve one shared receive queue (SRQ) work\nrequest for internal use, so the capacity returned from the create_srq\nand query_srq methods should be srq-\u003emax - 1.\n\nSigned-off-by: Dotan Barak \u003cdotanb@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "dc05980dd736bfbe5b2524b463e5f098e67a64e9", "tree": "87f212e24ee4362a5e670418b32bd0c959d3f1c6", "parents": [ "bf17c1c7cc9250d7c3c01b0ae898aefa1853535a" ], "author": { "name": "Michael S. Tsirkin", "email": "mst@mellanox.co.il", "time": "Mon Mar 20 10:08:25 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:25 2006 -0800" }, "message": "IB/mad: Fix oopsable race on device removal\n\nFix an oopsable race debugged by Eli Cohen \u003celi@mellanox.co.il\u003e:\nAfter removing the port from port_list, ib_mad_port_close flushes\nport_priv-\u003ewq before destroying the special QPs. This means that a\ncompletion event could arrive, and queue a new work in this work queue\nafter flush.\n\nThis patch also removes an unnecessary flush_workqueue():\ndestroy_workqueue() already includes a flush.\n\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "bf17c1c7cc9250d7c3c01b0ae898aefa1853535a", "tree": "95c534eed9c2b188c28681a87690a759c876c30c", "parents": [ "6b63e3015a69dd8aa5534e23af9f132a021da02e" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:25 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:25 2006 -0800" }, "message": "IB/srp: Coverity fix to srp_parse_options()\n\nFix leak found by Coverity: in the SRP_OPT_DGID case,\nsrp_parse_options() didn\u0027t free the result of match_strdup().\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6b63e3015a69dd8aa5534e23af9f132a021da02e", "tree": "58c8ffeaf4a46e4ac5af98ebbaae7543c43561a9", "parents": [ "048975ac580a771fc5bb96c6b454cba897ab1a73" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:25 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:25 2006 -0800" }, "message": "IB/mthca: Coverity fix to mthca_init_eq_table()\n\nFix bug found by coverity: the loop body never executed, because it\nwas doing for (i \u003d 0; i \u003c MTHCA_EQ_CMD; ++i), but MTHCA_EQ_CMD is 0.\nThe correct loop bound is MTHCA_NUM_EQ, to loop over all EQs.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "048975ac580a771fc5bb96c6b454cba897ab1a73", "tree": "32405003b3cb78a3e2ccf765868f60a273c1313b", "parents": [ "0b3ea0829cbcdaee6e018a83a2949ef458213f3b" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:25 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:25 2006 -0800" }, "message": "IB: Coverity fixes to sysfs.c\n\nFix two bugs found by coverity:\n - Memory leak in error path of alloc_group_attrs()\n - Fencepost error in state_show(): the test should be \u003c ARRAY_SIZE(),\n not \u003c\u003d ARRAY_SIZE().\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "0b3ea0829cbcdaee6e018a83a2949ef458213f3b", "tree": "3e86dc70e4b71b1de1e9ab2df319b014dd242f7c", "parents": [ "8b9ab02b690e988f19c9d740ef642d7d833d23d5" ], "author": { "name": "Jack Morgenstein", "email": "jackm@mellanox.co.il", "time": "Mon Mar 20 10:08:24 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:24 2006 -0800" }, "message": "IPoIB: Move ipoib_ib_dev_flush() to ipoib workqueue\n\nMove ipoib_ib_dev_flush() to ipoib\u0027s workqueue. This keeps it ordered\nwith respect to other work scheduled by the ipoib driver. This fixes\nproblems with races, for example:\n - ipoib_ib_dev_flush() has started running because of an IB event\n - user does ifconfig ib0 down\n - ipoib_mcast_stop_thread() gets called twice and waits for the same\n completion twice\n\nSigned-off-by: Jack Morgenstein \u003cjackm@mellanox.co.il\u003e\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "8b9ab02b690e988f19c9d740ef642d7d833d23d5", "tree": "e72a12094911f4c0c4fe5ed7769be047763bc103", "parents": [ "702b2aaccfbf0fa29c6ffb423a39a7a5573f793a" ], "author": { "name": "Roland Dreier", "email": "rdreier@cisco.com", "time": "Tue Mar 07 11:21:08 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:24 2006 -0800" }, "message": "IPoIB: Fix build now that neighbour destructor is in neigh_params\n\nFix the IPoIB build (which is broken in net-2.6.17 because of my\nscrew-up, which left out this chunk in ipoib_multicast.c). \nThe neighbour destructor is now in neigh_params, so we don\u0027t\nneed to clear it in the ops structure.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "702b2aaccfbf0fa29c6ffb423a39a7a5573f793a", "tree": "3e4863f5d4dc73d813b13e99d97cfd33c8789d03", "parents": [ "f36e1793e25513380cae5958a9164d4cc4458ad0" ], "author": { "name": "Ami Perlmutter", "email": "amip@mellanox.co.il", "time": "Mon Mar 20 10:08:24 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:24 2006 -0800" }, "message": "IB/uverbs: Use correct alt_pkey_index in modify QP\n\nThe old code incorrectly used the primary P_Key index as the alternate\nindex too.\n\nSigned-off-by: Ami Perlmutter \u003camip@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f36e1793e25513380cae5958a9164d4cc4458ad0", "tree": "aa31d34ee07971645af6f21068709166420caee2", "parents": [ "6ecb0c849625e830ab96495d473bb704812c30e1" ], "author": { "name": "Jack Morgenstein", "email": "jackm@mellanox.co.il", "time": "Fri Mar 03 21:54:13 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:23 2006 -0800" }, "message": "IB/umad: Add support for large RMPP transfers\n\nAdd support for sending and receiving large RMPP transfers. The old\ncode supports transfers only as large as a single contiguous kernel\nmemory allocation. This patch uses linked list of memory buffers when\nsending and receiving data to avoid needing contiguous pages for\nlarger transfers.\n\n Receive side: copy the arriving MADs in chunks instead of coalescing\n to one large buffer in kernel space.\n\n Send side: split a multipacket MAD buffer to a list of segments,\n (multipacket_list) and send these using a gather list of size 2.\n Also, save pointer to last sent segment, and retrieve requested\n segments by walking list starting at last sent segment. Finally,\n save pointer to last-acked segment. When retrying, retrieve\n segments for resending relative to this pointer. When updating last\n ack, start at this pointer.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@mellanox.co.il\u003e\nSigned-off-by: Sean Hefty \u003csean.hefty@intel.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6ecb0c849625e830ab96495d473bb704812c30e1", "tree": "7f482334cd05121ed96f8c17353f8a6ae73a85f9", "parents": [ "87fd1a11ae91ab42fac978467667c61fee9f01da" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:23 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:23 2006 -0800" }, "message": "IB/srp: Add SCSI host attributes to show target port\n\nAdd SCSI host attributes in sysfs that show the ID extension, IOC\nGUID, service ID, P_Key and destination GID for each target port that\nthe SRP initiator connects to.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "87fd1a11ae91ab42fac978467667c61fee9f01da", "tree": "856c3ca67426211ac229b87bea31d8b1a3154840", "parents": [ "6226bb570184eb6c645e047d2aecbce8c0442e3e" ], "author": { "name": "Sean Hefty", "email": "sean.hefty@intel.com", "time": "Thu Mar 02 16:50:37 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:23 2006 -0800" }, "message": "IB/cm: Check cm_id state before handling a REP\n\nMove checking the state of a cm_id before modifying it when handling a\nREP. This fixes a bug seen under MPI scale-up testing, where a NULL\ntimewait_info pointer is dereferenced if a request times out before a\nREP is received.\n\nSigned-off-by: Sean Hefty \u003csean.hefty@intel.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6226bb570184eb6c645e047d2aecbce8c0442e3e", "tree": "39e7e101fbaf1816d1280e1d9be9f08bb7ff60ba", "parents": [ "651eaac92894f8b6761c51b6637ea9cacea7fba2" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Mar 02 13:56:37 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:22 2006 -0800" }, "message": "IB/mthca: Update firmware versions\n\nUpdate known firmware versions in driver\u0027s table to the latest releases.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "651eaac92894f8b6761c51b6637ea9cacea7fba2", "tree": "8be06461ef870b7d130ebce39f55fe93af6ac542", "parents": [ "27d56300647f6e76847bc2407d7abc782fe87495" ], "author": { "name": "Eli Cohen", "email": "eli@mellanox.co.il", "time": "Thu Mar 02 12:40:46 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:22 2006 -0800" }, "message": "IB/mthca: Optimize large messages on Sinai HCAs\n\nSinai (one-port PCI Express) HCAs get improved throughput for messages\nbigger than 80 KB in DDR mode if memory keys are formatted in a\nspecific way. The enhancement only works if the memory key table is\nsmaller than 2^24 entries. For larger tables, the enhancement is off\nand a warning is printed (to avoid silent performance loss).\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Michael Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "27d56300647f6e76847bc2407d7abc782fe87495", "tree": "58e63c3f4271e65807e8508944306a7c227aa987", "parents": [ "4546d31d84beafe74c56651173ac4fe197c7de8b" ], "author": { "name": "Dotan Barak", "email": "dotanb@mellanox.co.il", "time": "Thu Mar 02 11:25:27 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:21 2006 -0800" }, "message": "IB/uverbs: Fix query QP return of sq_sig_all\n\nThe old code didn\u0027t convert from the kernel\u0027s enum correctly.\n\nSigned-off-by: Dotan Barak \u003cdotanb@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "4546d31d84beafe74c56651173ac4fe197c7de8b", "tree": "5196b616386b05c4a64ce8e70e78ca5e2b27fbb2", "parents": [ "9acf6a8570dcfc9f55724b8b71099fc8768e8c26" ], "author": { "name": "Dotan Barak", "email": "dotanb@mellanox.co.il", "time": "Thu Mar 02 11:22:28 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:20 2006 -0800" }, "message": "IB: Fix modify QP checking of \"current QP state\" attribute\n\nAccording to the IB spec version 1.2, section 11.2.4.2, the current\ntable has a couple of mistakes where it allows the current QP state\n(IB_QP_CUR_STATE) attribute. For the transitions:\n\n RTS -\u003e RTS: IB_QP_CUR_STATE should be allowed for all transports\n SQD -\u003e SQD: IB_QP_CUR_STATE should never be allowed\n\nSigned-off-by: Dotan Barak \u003cdotanb@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "9acf6a8570dcfc9f55724b8b71099fc8768e8c26", "tree": "5b265bf0474f321722d2690b5b5dc57cde80690e", "parents": [ "54d07e2a1ead2f093ce054cda2e0f5ec163c650c" ], "author": { "name": "Michael S. Tsirkin", "email": "mst@mellanox.co.il", "time": "Thu Mar 02 11:07:47 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:20 2006 -0800" }, "message": "IPoIB: Fix multicast race between canceling and completing\n\nipoib_mcast_stop_thread currently tests mcast-\u003equery and if it is\nNULL, does not perform wait_for_completion on the mcast and frees the\nmcast object directly.\n\nHowever, since both operations are done without locking, it is\npossible that ipoib_mcast_join_complete is in progress on this mcast\nobject and has set mcast-\u003equery to NULL already.\n\nSolve this by:\n- taking priv-\u003elock before we change mcast-\u003equery in ipoib_mcast_join_complete,\n and keeping it until we no longer need the mcast object\n- taking priv-\u003elock around mcast-\u003equery test in ipoib_mcast_stop_thread\n\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "54d07e2a1ead2f093ce054cda2e0f5ec163c650c", "tree": "0d5d495d25506839bd8bec0c8da092ca8b007202", "parents": [ "8d3ef29d6be1e750512e0a9dbea6225290b81d0a" ], "author": { "name": "Eli Cohen", "email": "eli@mellanox.co.il", "time": "Thu Mar 02 11:05:19 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:19 2006 -0800" }, "message": "IPoIB: Clean up if posting receives fails\n\nIf posting receives in ipoib_ib_dev_open() fails, call\nipoib_ib_dev_stop() to move the device\u0027s QP back to the RESET state so\nthat we can try again later.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "8d3ef29d6be1e750512e0a9dbea6225290b81d0a", "tree": "9384d9275d5122574665db18b5196f9c9a96d7ac", "parents": [ "67e7377661db4e341ed5e9a0358d11a55e532aa8" ], "author": { "name": "Ishai Rabinovitz", "email": "ishai@mellanox.co.il", "time": "Wed Mar 01 22:33:11 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:19 2006 -0800" }, "message": "IB/mthca: Use an enum for HCA page size\n\nUse a named enum for the HCA\u0027s internal page size, rather than having\nmagic values of 4096 and shifts by 12 all over the code. Also, fix\none minor bug in EQ handling: only one HCA page is mapped to the HCA\nduring initialization, but a full kernel page is unmapped during\ncleanup. This might cause problems when PAGE_SIZE !\u003d 4096.\n\nSigned-off-by: Ishai Rabinovitz \u003cishai@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "67e7377661db4e341ed5e9a0358d11a55e532aa8", "tree": "ccc47340a8a0be951b65aec8f90f099eecdb181d", "parents": [ "7667abd1528782003d8b83c54756523ec547af6e" ], "author": { "name": "Dotan Barak", "email": "dotanb@mellanox.co.il", "time": "Wed Mar 01 14:28:12 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:18 2006 -0800" }, "message": "IB/mthca: Check alternate P_Key index when setting alternate path\n\nCheck that the alternate P_Key index is in range when setting the\nalternate path for a QP. Also make a cosmetic touch up to the debug\nmessage printed when the main P_Key index is out of range.\n\nSigned-off-by: Dotan Barak \u003cdotanb@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7667abd1528782003d8b83c54756523ec547af6e", "tree": "c0f1bb5ff87388cc8be6ca6e23a7bc013b52d589", "parents": [ "7343b231f22cec11f069bcdbb0c9a417df2750d3" ], "author": { "name": "Dotan Barak", "email": "dotanb@mellanox.co.il", "time": "Mon Feb 27 21:02:00 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:18 2006 -0800" }, "message": "IB/mthca: Add support for send work request fence flag\n\nAdd support for IB_SEND_FENCE flag in post_send methods.\n\nSigned-off-by: Dotan Barak \u003cdotanb@mellanox.co.il\u003e\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7343b231f22cec11f069bcdbb0c9a417df2750d3", "tree": "3b72ba5f585fcab8271dc4be046b3bd447852847", "parents": [ "1d89b1ae6c203bc68a3f424be144abcdf62773c9" ], "author": { "name": "Eli Cohen", "email": "eli@mellanox.co.il", "time": "Mon Feb 27 20:47:43 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:18 2006 -0800" }, "message": "IPoIB: Close race in setting mcast-\u003eah\n\nipoib_mcast_send() tests mcast-\u003eah twice. If this value is changed\nbetween these two points, we leak an skb. However,\nipoib_mcast_join_finish() sets mcast-\u003eah with no locking, so it could\nrace against ipoib_mcast_send().\n\nAs a solution, take priv-\u003elock around assignment to mcast-\u003eah thus\nmaking sure ipoib_mcast_send() (which also takes priv-\u003elock) is not in\nflight.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "1d89b1ae6c203bc68a3f424be144abcdf62773c9", "tree": "9d1979c98843ba7d18f6272f13ea06c2591ee8d5", "parents": [ "14abdffcc0a0ca9c5bb3274648d073e09a6fd2ba" ], "author": { "name": "Jack Morgenstein", "email": "jackm@mellanox.co.il", "time": "Sun Feb 26 16:05:59 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:17 2006 -0800" }, "message": "IB/mthca: Implement query_ah method\n\nImplement query_ah (except for AVs which are in HCA memory). This is\nneeded to implement RMPP duplicate session detection on sending side\n(extraction of DGID/DLID and GRH flag from address handle).\n\nSigned-off-by: Jack Morgenstein \u003cjackm@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "14abdffcc0a0ca9c5bb3274648d073e09a6fd2ba", "tree": "fe934450412ed70f627e9d98bb881b03c7b31222", "parents": [ "ea88fd16d6e85f4bc71b6053180b64f04be1ff14" ], "author": { "name": "Eli Cohen", "email": "eli@mellanox.co.il", "time": "Sun Feb 26 14:36:06 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:17 2006 -0800" }, "message": "IB/mthca: Write FW commands through doorbell page\n\nThis patch is checks whether the HCA supports posting FW commands\nthrough a doorbell page (user access region 0, or \"UAR0\"). If this is\nsupported, the driver maps UAR0 and uses it for FW commands. This can\nbe controlled by the value of a writable module parameter\nfw_cmd_doorbell. When the parameter is 0, the commands are posted\nthrough HCR using the old method; otherwise if HCA is capable commands\ngo through UAR0.\n\nThis use of UAR0 to post commands eliminates the need for polling the\n\"go\" bit prior to posting a new command. Since reading from a PCI\ndevice is much more expensive then issuing a posted write, it is\nexpected that issuing FW commands this way will provide better CPU\nutilization.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "ea88fd16d6e85f4bc71b6053180b64f04be1ff14", "tree": "ea0f02aca9bb83f636e60002a9f98f9dab6d57e0", "parents": [ "abb6e9ba17eb133ab385d0f9017fa8afa809d52a" ], "author": { "name": "Dotan Barak", "email": "dotanb@mellanox.co.il", "time": "Thu Feb 23 12:36:18 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:16 2006 -0800" }, "message": "IB/uverbs: Return actual capacity from create SRQ operation\n\nPass actual capacity of created SRQ back to userspace, so that\nuserspace can report accurate capacities. This requires an ABI bump,\nto change struct ib_uverbs_create_srq_resp.\n\nSigned-off-by: Dotan Barak \u003cdotanb@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "abb6e9ba17eb133ab385d0f9017fa8afa809d52a", "tree": "6cab0a44a1cb439c3c204149d44e6295320e5de7", "parents": [ "44af79f9524c29d6850591cc972f2667a27234d4" ], "author": { "name": "Dotan Barak", "email": "dotanb@mellanox.co.il", "time": "Thu Feb 23 12:13:51 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:16 2006 -0800" }, "message": "IB/mthca: Return actual capacity from create_srq\n\nHave mthca\u0027s create_srq method return the actual capacity of the SRQ\nthat gets created. Also update comments in \u003crdma/ib_verbs.h\u003e to\nclarify that this is what is expected from ib_create_srq().\n\nSigned-off-by: Dotan Barak \u003cdotanb@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "44af79f9524c29d6850591cc972f2667a27234d4", "tree": "8d88bdbd7c3fd015c692792bf1fcd3600ba0c275", "parents": [ "4d9781c5ce1a517a07dbf03c37323c011037fe79" ], "author": { "name": "Michael S. Tsirkin", "email": "mst@mellanox.co.il", "time": "Mon Feb 20 21:50:39 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:16 2006 -0800" }, "message": "IPoIB: clarify to_ipoib_neigh()\n\nCosmetic change: make alignment explicit in to_ipoib_neigh.\n\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "00df1b2c8b1f07e02a74e2d10b176f29395ce7d2", "tree": "b31cb90c60b5abc91e0cff2e39538d1c6524834f", "parents": [ "8ebe5077e37a0cb0da527e397460188e6bfdd3ee" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 13 17:21:09 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:15 2006 -0800" }, "message": "IB/mthca: Bump driver version and release date\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "8ebe5077e37a0cb0da527e397460188e6bfdd3ee", "tree": "401491fb7a94516dfbeeee027d8eeb294117cb5b", "parents": [ "8bdb0e8632e0f5061bd18b6934346cb609490135" ], "author": { "name": "Eli Cohen", "email": "eli@mellanox.co.il", "time": "Mon Feb 13 16:40:21 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:15 2006 -0800" }, "message": "IB/mthca: Support for query QP and SRQ\n\nImplement the query_qp and query_srq methods in mthca.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "8bdb0e8632e0f5061bd18b6934346cb609490135", "tree": "baa94a9ad7c97f4c025452ffbba2b7f6d8cc0af2", "parents": [ "7ccc9a24e01258a31ee2b964215e4ddddd2a02c4" ], "author": { "name": "Dotan Barak", "email": "dotanb@mellanox.co.il", "time": "Mon Feb 13 16:31:57 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:14 2006 -0800" }, "message": "IB/uverbs: Support for query SRQ from userspace\n\nAdd support to uverbs to handle querying userspace SRQs (shared\nreceive queues), including adding an ABI for marshalling requests and\nresponses. The kernel midlayer already has the underlying\nib_query_srq() function.\n\nSigned-off-by: Dotan Barak \u003cdotanb@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7ccc9a24e01258a31ee2b964215e4ddddd2a02c4", "tree": "486ab72c62f42952309ea764bc6bd30f56e87522", "parents": [ "a74cd4af0bfa9578594acbb711a958104c93b772" ], "author": { "name": "Dotan Barak", "email": "dotanb@mellanox.co.il", "time": "Mon Feb 13 16:31:25 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:14 2006 -0800" }, "message": "IB/uverbs: Support for query QP from userspace\n\nAdd support to uverbs to handle querying userspace QPs (queue pairs),\nincluding adding an ABI for marshalling requests and responses. The\nkernel midlayer already has the underlying ib_query_qp() function.\n\nSigned-off-by: Dotan Barak \u003cdotanb@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "a74cd4af0bfa9578594acbb711a958104c93b772", "tree": "070e951014aa396b472d3b17df81e6665bd5a4c5", "parents": [ "d844183d9c7b103da1d7a1c753a1c171e9ce26b3" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 13 16:30:49 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:13 2006 -0800" }, "message": "IB: Whitespace cleanups\n\nRemove trailing whitespace and fix indentation that with spaces\ninstead of tabs.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d844183d9c7b103da1d7a1c753a1c171e9ce26b3", "tree": "5bd7ca0feaae115b2f487e20fcd0fa75f76a16d9", "parents": [ "8a51866f08103ba04894ce0f65eef567ddc3ed40" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 13 16:30:18 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:13 2006 -0800" }, "message": "IB/mthca: Convert to use ib_modify_qp_is_ok()\n\nUse ib_modify_qp_is_ok() in mthca, and delete the big table of\nattributes for queue pair state transitions.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "8a51866f08103ba04894ce0f65eef567ddc3ed40", "tree": "39af79ce5995900c14610acc768850a749961ee9", "parents": [ "3fa1fa3e809dc009a080ca9f052cee2e17836c63" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 13 12:48:12 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:12 2006 -0800" }, "message": "IB: Add ib_modify_qp_is_ok() library function\n\nThe in-kernel mthca driver contains a table of which attributes are\nvalid for each queue pair state transition. It turns out that both\nother IB drivers -- ipath and ehca -- which are being prepared for\nmerging have copied this table, errors and all.\n\nTo forestall this code duplication, move this table and the code to\ncheck parameters against it into a midlayer library function,\nib_modify_qp_is_ok().\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "3fa1fa3e809dc009a080ca9f052cee2e17836c63", "tree": "471bc486f70e8cd4d3950b0ff256f12db057b951", "parents": [ "5e9f71a16c56af7e2ff8b7ea251e0fd90b5de560" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Feb 03 14:53:28 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:12 2006 -0800" }, "message": "IB/mthca: Generate SQ drained events when requested\n\nAdd low-level driver support to ib_mthca so that consumers can request\na \"send queue drained\" event be generated when a transiton to the SQD\nstate completes.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "5e9f71a16c56af7e2ff8b7ea251e0fd90b5de560", "tree": "d3b6aba0640173d0ce760140650dad51a76f9501", "parents": [ "5f0b67e0d5c2807337b8fee4aa71b05f4f641534" ], "author": { "name": "Ralph Campbell", "email": "ralphc@pathscale.com", "time": "Fri Feb 03 14:32:01 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:11 2006 -0800" }, "message": "IB/mad: Simplify SMI by eliminating smi_check_local_dr_smp()\n\nThe call to ib_get_agent_port() shouldn\u0027t be possible to fail when\nsmi_check_local_dr_smp() is called from ib_mad_recv_done_handler().\nWhen it is called from handle_outgoing_dr_smp(), the device and\nport_num come from mad_agent_priv so I assume the call to\nib_get_agent_port() shouldn\u0027t fail either. In either case,\nsmi_check_local_smp() only uses the mad_agent pointer to check that\nmad_agent-\u003edevice-\u003eprocess_mad is not NULL. The device pointer would\nhave to be the same as the one passed to smi_check_local_dr_smp()\nsince that pointer is used later instead of the one checked in\nsmi_check_local_smp().\n\nSigned-off-by: Hal Rosenstock \u003chalr@voltaire.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "5f0b67e0d5c2807337b8fee4aa71b05f4f641534", "tree": "7fa82fdc250aa862366296adb3087e2f30f4d4a1", "parents": [ "d36f34aadf184d8cc4c240de2b6319ccea8334bb" ], "author": { "name": "Ralph Campbell", "email": "ralphc@pathscale.com", "time": "Fri Feb 03 14:30:24 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:11 2006 -0800" }, "message": "IB/mad: Remove redundant check from smi_check_local_dr_smp()\n\nsmi_check_local_dr_smp() is called only from two places in core/mad.c\nIt returns 0 or 1. In smi_check_local_dr_smp(), it checks for\na directed route SMP but this function is only called when the SMP\nis a directed route so this is a NOP.\n\nSigned-off-by: Hal Rosenstock \u003chalr@voltaire.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d36f34aadf184d8cc4c240de2b6319ccea8334bb", "tree": "20b7a77e03f3c75c9043a50ddd720a31048efa99", "parents": [ "6dfc3901b04d1b79fa982d6de6d5af3b50c6cea8" ], "author": { "name": "Or Gerlitz", "email": "ogerlitz@voltaire.com", "time": "Thu Feb 02 10:43:45 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:10 2006 -0800" }, "message": "IB: Enable FMR pool user to set page size\n\nThis patch allows the consumer to set the page size of \"pages\" mapped\nby the pool FMRs, which is a feature already existing in the base\nverbs API. On the cosmetic side it changes ib_fmr_attr.page_size field\nto be named page_shift.\n\nSigned-off-by: Or Gerlitz \u003cogerlitz@voltaire.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6dfc3901b04d1b79fa982d6de6d5af3b50c6cea8", "tree": "f4918637c0d7c4b5c7fe4a4deb84e44ed3663dc6", "parents": [ "c5bcbbb9fe00128d500c2f473d5ddc8d8c2c53a7" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Feb 02 10:04:19 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:10 2006 -0800" }, "message": "IB/mthca: Add modify_device method to set node description\n\nAdd a modify_device method to mthca, which implements setting the node\ndescription. This makes the writable \"node_desc\" sysfs attribute work\nfor Mellanox HCAs.\n\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "c5bcbbb9fe00128d500c2f473d5ddc8d8c2c53a7", "tree": "c4a6feac1bc1dfd9e2fbe88c8e6ad1db4a47a817", "parents": [ "2fa5e2ebbe2d81f741ba7bed9e07dc38cc734625" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Feb 02 09:47:14 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:09 2006 -0800" }, "message": "IB: Allow userspace to set node description\n\nExpose a writable \"node_desc\" sysfs attribute for InfiniBand devices.\nThis allows userspace to update the node description with information\nsuch as the node\u0027s hostname, so that IB network management software\ncan tie its view to the real world.\n\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2fa5e2ebbe2d81f741ba7bed9e07dc38cc734625", "tree": "6cb2693d8e10a903d78e236e90645fc6df28c9b3", "parents": [ "4885bf64bc2eb242ebebe67077cfe3688283b586" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Feb 01 13:38:24 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:09 2006 -0800" }, "message": "IB/mthca: Whitespace cleanups\n\nRemove trailing whitespace and fix indentation that with spaces\ninstead of tabs.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "4885bf64bc2eb242ebebe67077cfe3688283b586", "tree": "ed40e3eb7c05e923919f1e8ef2a9186b32c916a4", "parents": [ "33b9b3ee9709b19c4f02ab91571d53540d05c3d1" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jan 30 14:31:33 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:08 2006 -0800" }, "message": "IB/mthca: Add device-specific support for resizing CQs\n\nAdd low-level driver support for resizing CQs (both kernel and\nuserspace) to mthca.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "33b9b3ee9709b19c4f02ab91571d53540d05c3d1", "tree": "2d1019e9b8bf63e4235d7c73fd78ab294b993de2", "parents": [ "399d7921299fc4f146bd62bfa6312382a5429bcc" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Jan 30 14:29:21 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:07 2006 -0800" }, "message": "IB: Add userspace support for resizing CQs\n\nAdd support to uverbs to handle resizing userspace CQs (completion\nqueues), including adding an ABI for marshalling requests and\nresponses. The kernel midlayer already has ib_resize_cq().\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "399d7921299fc4f146bd62bfa6312382a5429bcc", "tree": "f7ddfa33ef532e887b3028fd5259b2ce5e26188e", "parents": [ "d9b98b0f11ee7dd39429001ba289f095b9d66917" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Jan 31 21:14:18 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:07 2006 -0800" }, "message": "IB/mthca: Get rid of might_sleep() annotations\n\nThe might_sleep() annotations in mthca are silly -- they all occur\nshortly before calls that will end up in core functions like kmalloc()\nthat will print the same warning in an unsafe context anyway. In\nfact, beyond cluttering the source, we\u0027re actually bloating text with\nCONFIG_DEBUG_SPINLOCK_SLEEP and/or CONFIG_PREEMPT_VOLUNTARY set.\n\nWith both options set, getting rid of the might_sleep()s saves a lot:\nadd/remove: 0/0 grow/shrink: 0/7 up/down: 0/-171 (-171)\nfunction old new delta\nmthca_pd_alloc 132 109 -23\nmthca_init_cq 969 946 -23\nmthca_mr_alloc 592 568 -24\nmthca_pd_free 67 42 -25\nmthca_free_mr 219 194 -25\nmthca_free_cq 570 545 -25\nmthca_fmr_alloc 742 716 -26\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d9b98b0f11ee7dd39429001ba289f095b9d66917", "tree": "c473a7b348640cb80c4584ef5ea8dd055efed577", "parents": [ "7705a8792b0fc82fd7d4dd923724606bbfd9fb20" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Jan 31 20:45:51 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Mar 20 10:08:07 2006 -0800" }, "message": "IB/mthca: Make functions that never fail return void\n\nThe function mthca_free_err_wqe() can never fail, so get rid of its\nreturn value. That means handle_error_cqe() doesn\u0027t have to check\nwhat mthca_free_err_wqe() returns, which means it can\u0027t fail either\nand doesn\u0027t have to return anything either. All this results in\nsimpler source code and a slight object code improvement:\n\nadd/remove: 0/0 grow/shrink: 0/2 up/down: 0/-10 (-10)\nfunction old new delta\nmthca_free_err_wqe 83 81 -2\nmthca_poll_cq 1758 1750 -8\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "1285b3a0b0aa2391ac6f6939e6737203c8220f68", "tree": "b0041f55811fcda35614e6c04cb67e251d05a51f", "parents": [ "c499ec24c31edf270e777a868ffd0daddcfe7ebd" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 03 15:47:25 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Mar 03 17:50:16 2006 -0800" }, "message": "IB/srp: Don\u0027t send task management commands after target removal\n\nJust fail abort and reset requests that come in after we\u0027ve already\ndecided to remove a target.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f78cf0dc7b7b13d0550d1e02cf221b65969ff926", "tree": "d2bb41e6edb5f70ccb09ed50f5cfb35eda22f844", "parents": [ "4cbf8767902c578481ff3df366c77d24fe68fd26", "7d2babc4874825027848db04d11784070da4456d" ], "author": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Feb 14 13:49:37 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Feb 14 13:49:37 2006 -0800" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband\n" }, { "commit": "7d2babc4874825027848db04d11784070da4456d", "tree": "e97b125497031f13b974db376df1b80e04dd166f", "parents": [ "20b83382d1c5d4d1a73fc5671261db5239d1dbb3" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 13 12:19:44 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 13 12:19:44 2006 -0800" }, "message": "IB/mthca: bump driver version and release date\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "20b83382d1c5d4d1a73fc5671261db5239d1dbb3", "tree": "331685789ab2d86b1e126b0eb7c997642150d5d8", "parents": [ "f295c79b6766b25fe8c1aad88211c54d1caa7e0b" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sat Feb 11 12:22:12 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sat Feb 11 12:22:12 2006 -0800" }, "message": "IPoIB: Yet another fix for send-only joins\n\nEven after the last fix, it\u0027s still possible for a send-only join to\nstart before the join for the broadcast group has finished. This\ncould cause us to create a multicast group using attributes from the\nbroadcast group that haven\u0027t been initialized yet, so we would use\ngarbage for the Q_Key, etc. Fix this by waiting until the broadcast\ngroup\u0027s attached flag is set before starting send-only joins.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f295c79b6766b25fe8c1aad88211c54d1caa7e0b", "tree": "116e8255895a00c133637b3b7aa9559daba02a94", "parents": [ "7bcb974ef6a0ae903888272c92c66ea779388c01" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Feb 10 18:02:44 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Feb 10 18:02:44 2006 -0800" }, "message": "IB/mthca: Don\u0027t print debugging info until we have all values\n\nWhen debugging is enabled, the mthca_QUERY_DEV_LIM() firmware command\nfunction prints out some of the device limits that it queries.\nHowever the debugging prints happen before all of the fields are\nextracted from the firmware response, so some of the values that get\nprinted are uninitialized junk. Move the prints to the end of the\nfunction to fix this.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7bcb974ef6a0ae903888272c92c66ea779388c01", "tree": "926245a2e120dd5884f3bab92020612fcfbd78bf", "parents": [ "479a079663bd4c5f3d2714643b1b8c406aaba3e0" ], "author": { "name": "Michael S. Tsirkin", "email": "mst@mellanox.co.il", "time": "Tue Feb 07 16:39:26 2006 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Feb 07 16:39:26 2006 -0800" }, "message": "IPoIB: Fix another send-only join race\n\nFurther, there\u0027s an additional issue that I saw in testing:\nipoib_mcast_send may get called when priv-\u003ebroadcast is NULL (e.g. if\nthe device was downed and then upped internally because of a port\nevent).\n\nIf this happends and the send-only join request gets completed before\npriv-\u003ebroadcast is set, we get an oops.\n\nSigned-off-by: Michael S. Tsirkin \u003cmst@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" } ], "next": "479a079663bd4c5f3d2714643b1b8c406aaba3e0" }