)]}' { "log": [ { "commit": "4b1cc7e7ca5715907d17619dcb49144db6efe1c9", "tree": "82e8617c051c3148d902476464e36b418cbe531c", "parents": [ "30da7cff87f0ffa169fe07b766c3d6a5f6d1f6ab" ], "author": { "name": "John Lacombe", "email": "jlacombe@neteffect.com", "time": "Thu Feb 21 08:34:58 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Feb 26 16:24:29 2008 -0800" }, "message": "RDMA/nes: Fix interrupt moderation low threshold\n\nInterrupt moderation low threshold value was incorrectly triggering,\nindicating that the threshold should be lowered.\n\nThe impact was the timer was likely to become 40usecs and get stuck\nthere. The biggest side effect was too many interrupts and nonoptimal\nperformance.\n\nSigned-off-by: John Lacombe \u003cjlacombe@neteffect.com\u003e\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "30da7cff87f0ffa169fe07b766c3d6a5f6d1f6ab", "tree": "e68206af4e17a9542b978ca97aaca1a373ba8349", "parents": [ "a2e9c384ce76993cd68d6de57eaa81985b4618e3" ], "author": { "name": "Faisal Latif", "email": "flatif@neteffect.com", "time": "Thu Feb 21 08:31:22 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Feb 26 16:24:29 2008 -0800" }, "message": "RDMA/nes: Fix CRC endianness for RDMA connection establishment on big-endian\n\nWith commit ef19454b (\"[LIB] crc32c: Keep intermediate crc state in\ncpu order\"), the behavior of crc32c changes on big-endian platforms.\n\nOur algorithm expects the previous behavior; otherwise we have RDMA\nconnection establishment failure on big-endian platforms like powerpc.\nApply cpu_to_le32() to value returned by crc32c() to get the previous\nbehavior.\n\nSigned-off-by: Faisal Latif \u003cflatif@neteffect.com\u003e\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "a2e9c384ce76993cd68d6de57eaa81985b4618e3", "tree": "adea958874e4289b400635633b4f6829270de8eb", "parents": [ "f84fba6f969065c6622669bbaa955c26fc1461ae" ], "author": { "name": "Faisal Latif", "email": "flatif@neteffect.com", "time": "Thu Feb 21 08:27:32 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Feb 26 16:24:29 2008 -0800" }, "message": "RDMA/nes: Fix use-after-free in mini_cm_dec_refcnt_listen()\n\nFix use-after-free spotted by Coverity checker flagged by Adrian Bunk.\n\nSigned-off-by: Faisal Latif \u003cflatif@neteffect.com\u003e\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f84fba6f969065c6622669bbaa955c26fc1461ae", "tree": "b562989918c69b271c04b83df7b27df786229d8a", "parents": [ "a4435febd4c0f14b25159dca249ecf91301c7c76" ], "author": { "name": "Glenn Streiff", "email": "gstreiff@neteffect.com", "time": "Thu Feb 21 08:17:54 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Feb 26 16:24:29 2008 -0800" }, "message": "RDMA/nes: Fix use-after-free in nes_create_cq()\n\nJust delete the debugging statement so we don\u0027t use cqp_request after\nfreeing it. Adrian Bunk flagged this use-after-free issue spotted by\nthe Coverity checker.\n\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "a4435febd4c0f14b25159dca249ecf91301c7c76", "tree": "c75976729afd4f9754517249b831abfd3aeb5ee1", "parents": [ "ed0ba33d64fb933f5fd985aa8f641984efd9d658" ], "author": { "name": "Adrian Bunk", "email": "bunk@kernel.org", "time": "Thu Feb 21 08:13:47 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Feb 26 16:24:29 2008 -0800" }, "message": "RDMA/nes: Fix a check-after-use in nes_probe()\n\nFix a check-after-use spotted by the Coverity checker.\n\nSigned-off-by: Adrian Bunk \u003cbunk@kernel.org\u003e\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "ed0ba33d64fb933f5fd985aa8f641984efd9d658", "tree": "12c45202489de5470f732080aa6ec0be540345a9", "parents": [ "65b07ec29354b345ff93914d064c2467aef4c862" ], "author": { "name": "Adrian Bunk", "email": "bunk@kernel.org", "time": "Thu Feb 21 08:12:06 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Feb 26 16:24:27 2008 -0800" }, "message": "RDMA/nes: Fix a memory leak in schedule_nes_timer()\n\nFix a memory leak spotted by the Coverity checker.\n\nSigned-off-by: Adrian Bunk \u003cbunk@kernel.org\u003e\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "65b07ec29354b345ff93914d064c2467aef4c862", "tree": "a82fe79c2b17a54e0ee5ca8419d5810b340caa74", "parents": [ "9300c0c06788a409a97d54bbe3360d2f385fc621" ], "author": { "name": "Adrian Bunk", "email": "bunk@kernel.org", "time": "Thu Feb 21 08:01:18 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 25 16:00:30 2008 -0800" }, "message": "RDMA/nes: Fix off-by-one\n\nFix an off-by-one spotted by the Coverity checker.\n\nSigned-off-by: Adrian Bunk \u003cbunk@kernel.org\u003e\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "9300c0c06788a409a97d54bbe3360d2f385fc621", "tree": "177ad00f8cbabaf84f561e3c98fca6b84f2dac1f", "parents": [ "82d416fffb5e8e39e899be7075dbeeac5fb8f0c2" ], "author": { "name": "Chien Tung", "email": "ctung@neteffect.com", "time": "Thu Feb 21 07:51:17 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 25 16:00:30 2008 -0800" }, "message": "RDMA/nes: Resurrect error path dead code\n\nAdrian Bunk pointed out that a Coverity scan found some apparently\ndead code in nes_verbs.c that really shouldn\u0027t have been dead.\n\nThe function nes_create_cq() was missing the assignment\n\n\terr \u003d 1;\n\njust prior to an iteration that conditionally set err \u003d 0 if a PBL was\nfound for a given virtual CQ. I also noticed we should have been\nreturning -EFAULT on a couple related error paths.\n\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "82d416fffb5e8e39e899be7075dbeeac5fb8f0c2", "tree": "6b09634809c71b5bbd1141413d5a324e0f4de7c4", "parents": [ "bfa274e2436fc7ef72ef51c878083647f1cfd429" ], "author": { "name": "Bryan Rosenburg", "email": "rosnbrg@us.ibm.com", "time": "Wed Feb 20 17:31:48 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 25 16:00:29 2008 -0800" }, "message": "RDMA/cxgb3: Fix shift calc in build_phys_page_list() for 1-entry page lists\n\nA single entry (addr 0x10001000, size 0x2000) will get converted to\npage address 0x10000000 with a page size of 0x4000. The code as it\nstands doesn\u0027t address the single buffer case, but in fact it allows\nthe subsequent single-buffer special case to be eliminated entirely.\nBecause the mask now includes the (page adjusted) starting and ending\naddresses, the general case works for the single buffer case as well.\n\nSigned-off-by: Bryan Rosenburg \u003crosnbrg@us.ibm.com\u003e\nAcked-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "b7f9c112a5e7f68d77a31c79f5942a3272ae9a3b", "tree": "23839936fc223e7076eb4a482e8720b81801f107", "parents": [ "ec229e5e81b3cf757e5e8b6a8bd0b4f32fe52f8c" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Feb 19 10:42:50 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Feb 19 10:42:50 2008 -0800" }, "message": "IB/mthca: Free correct MPT on error exit from mthca_fmr_alloc()\n\nWhen mthca_fmr_alloc() returns an error, it should free the MPT at the\nindex key, not mr-\u003eibmr.lkey, since the lkey has been mangled by\nhw_index_to_key() and no longer is the real index. This bug causes\ncorruption of the MPT table free bitmap when mthca_fmr_alloc() fails.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "51af33e8e45b845d8ee85446f58e31bc4c118048", "tree": "5d82fbb684c0adc0a01f2277f93fab7da2ac3810", "parents": [ "edd2fd643c500c812cae5b0d314ab9db9f959898" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 18 10:33:59 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 18 10:33:59 2008 -0800" }, "message": "RDMA/nes: Fix possible array overrun\n\nIn nes_create_qp(), the test\n\n\tif (nesqp-\u003emmap_sq_db_index \u003e NES_MAX_USER_WQ_REGIONS) {\n\nis used to error out if the db_index is too large; however, if the\ntest doesn\u0027t trigger, then the index is used as\n\n\tnes_ucontext-\u003emmap_nesqp[nesqp-\u003emmap_sq_db_index] \u003d nesqp;\n\nand mmap_nesqp is declared as\n\n\tstruct nes_qp *mmap_nesqp[NES_MAX_USER_WQ_REGIONS];\n\nwhich leads to an array overrun if the index is exactly equal to\nNES_MAX_USER_WQ_REGIONS. Fix this by bailing out if the index is\ngreater than or equal to NES_MAX_USER_WQ_REGIONS.\n\nThis was spotted by the Coverity checker (CID 2162).\n\nAcked-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "edd2fd643c500c812cae5b0d314ab9db9f959898", "tree": "46e7fb390f08cc58ca521c714742651cadf89098", "parents": [ "11e0704b7ec3abfeaee7e3a56f11c82024d1ae01" ], "author": { "name": "Chien Tung", "email": "ctung@neteffect.com", "time": "Fri Feb 15 21:00:36 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sat Feb 16 21:16:33 2008 -0800" }, "message": "RDMA/nes: Fix VLAN support\n\nWe need to account for the VLAN header size in nes_netdev_change_mtu()\nand nes_netdev_init(). Also, add spin lock/unlock during VLAN RX\nregistration so only one process can assign VLAN group for a given\ninterface at a time.\n\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "11e0704b7ec3abfeaee7e3a56f11c82024d1ae01", "tree": "b4929f77a34339c47ee4863fed47d8bca717c538", "parents": [ "c7482b81c8b524193d736488c149adbe27a7eb7f" ], "author": { "name": "Glenn Streiff", "email": "gstreiff@neteffect.com", "time": "Fri Feb 15 11:41:27 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Feb 15 15:05:05 2008 -0800" }, "message": "RDMA/nes: Fix MAC interrupt erroneously masked on ifdown\n\nOnly mask out MAC interrupt if necessary and re-enable on ifup. There\ncould be multiple netdevs going through the same MAC. MAC interrupts\nshould not be masked off until the last netdev is downed.\n\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e6028c0e004d334bb9ed75d4c918f4c763af1b9f", "tree": "9b83da3ad6221f4935f22459ddfaf6a1702588c2", "parents": [ "a9d1884925c80b96a621939a4fef5d74de58debe" ], "author": { "name": "Jack Morgenstein", "email": "jackm@dev.mellanox.co.il", "time": "Thu Feb 14 10:39:36 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Feb 14 10:39:36 2008 -0800" }, "message": "IB/mlx4: mlx4_ib_fmr_alloc() should call mlx4_fmr_enable()\n\nCurrently mlx4_ib_fmr_alloc() calls mlx4_mr_enable() instead of\nmlx4_fmr_enable(). The two functions are equivalent at the moment, but \nthis is not really correct (and the change is needed to fix a bug).\n\nSigned-off-by: Jack Morgenstein \u003cjackm@dev.mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "5163dc1a645bc9ed7984fa484f1a77378c166d23", "tree": "986189b025cacec7e736dae41de4737e05b76df4", "parents": [ "8704e9a8790cc9e394198663c1c9150c899fb9a2" ], "author": { "name": "Marcin Slusarz", "email": "marcin.slusarz@gmail.com", "time": "Wed Feb 13 00:06:08 2008 +0100" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Feb 13 07:47:47 2008 -0800" }, "message": "IB/mthca: Convert to use be16_add_cpu()\n\nreplace:\n\n\tbig_endian_variable \u003d cpu_to_beX(beX_to_cpu(big_endian_variable) +\n\t\t\t\t\t\texpression_in_cpu_byteorder);\n\nwith:\n\n\tbeX_add_cpu(\u0026big_endian_variable, expression_in_cpu_byteorder);\n\nGenerated with a semantic patch.\n\nSigned-off-by: Marcin Slusarz \u003cmarcin.slusarz@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": "8704e9a8790cc9e394198663c1c9150c899fb9a2", "tree": "68f6ba71227f445d2fb81d5385f22d36fc1ba895", "parents": [ "7c7a9bccd2ba9f17e4b588461f140578a0a7b073" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Tue Feb 12 16:09:29 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Feb 13 07:47:42 2008 -0800" }, "message": "RDMA/cxgb3: Fail loopback connections\n\nThe cxgb3 HW and driver don\u0027t support loopback RDMA connections. So\nfail any connection attempt where the destination address is local.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "fe174357eb2deb184c93269846c92adf5743115b", "tree": "f034fd33459be36d5d2f47d176fee8ed79b7c7af", "parents": [ "96b5a46e2a72dc1829370c87053e0cd558d58bc0" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Feb 12 14:38:22 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Feb 12 14:38:22 2008 -0800" }, "message": "IB/mthca: Add missing sg_init_table() in mthca_map_user_db()\n\nUsually harmless, since the scatterlist is always hard-coded to a length\nof 1, but it triggers a BUG() if CONFIG_DEBUG_SG\u003dy, so we better fix it.\nThis fixes \u003chttp://bugzilla.kernel.org/show_bug.cgi?id\u003d9934\u003e.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "ea54b10c7773007e173da31fe7adcc049da33331", "tree": "b13b77fb3807071a5b93ece7b564f6748d962bbc", "parents": [ "b57aacfa7a95328f469d0360e49289b023c47e9e" ], "author": { "name": "Jack Morgenstein", "email": "jackm@dev.mellanox.co.il", "time": "Mon Jan 28 10:40:59 2008 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Feb 08 13:30:02 2008 -0800" }, "message": "IB/mlx4: Use multiple WQ blocks to post smaller send WQEs\n\nConnectX HCA supports shrinking WQEs, so that a single work request\ncan be made of multiple units of wqe_shift. This way, WRs can differ\nin size, and do not have to be a power of 2 in size, saving memory and\nspeeding up send WR posting. Unfortunately, if we do this then the\nwqe_index field in CQEs can\u0027t be used to look up the WR ID anymore, so\nour implementation does this only if selective signaling is off.\n\nFurther, on 32-bit platforms, we can\u0027t use vmap() to make the QP\nbuffer virtually contigious. Thus we have to use constant-sized WRs to\nmake sure a WR is always fully within a single page-sized chunk.\n\nFinally, we use WRs with the NOP opcode to avoid wrapping around the\nqueue buffer in the middle of posting a WR, and we set the\nNoErrorCompletion bit to avoid getting completions with error for NOP\nWRs. However, NEC is only supported starting with firmware 2.2.232,\nso we use constant-sized WRs for older firmware. And, since MLX QPs\nonly support SEND, we use constant-sized WRs in this case.\n\nWhen stamping during NOP posting, do stamping following setting of the\nNOP WQE valid bit.\n\nSigned-off-by: Michael S. Tsirkin \u003cmst@dev.mellanox.co.il\u003e\nSigned-off-by: Jack Morgenstein \u003cjackm@dev.mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "1c69fc2a9012e160c8d459f63df74a6b01db8322", "tree": "a32a2be6b2c8b9f5c4e006bacebc1eeb723e2ff5", "parents": [ "21511abd0a248a3f225d3b611cfabb93124605a7" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Feb 06 21:07:54 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Feb 06 21:07:54 2008 -0800" }, "message": "IB/mlx4: Consolidate code to get an entry from a struct mlx4_buf\n\nWe use struct mlx4_buf for kernel QP, CQ and SRQ buffers, and the code\nto look up an entry is duplicated in get_cqe_from_buf() and the QP and\nSRQ versions of get_wqe(). Factor this out into mlx4_buf_offset().\n\nThis will also make it easier to switch over to using vmap() for buffers.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "3c2d774cad5bf4fad576363da77870e9e6530b7a", "tree": "344ae8167730ea361ff4bd4bf098ba64bfeef5e5", "parents": [ "2c78853472a36c7cf51a84a34edc370e21c93ce4" ], "author": { "name": "Glenn Streiff", "email": "gstreiff@neteffect.com", "time": "Mon Feb 04 20:20:45 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:45 2008 -0800" }, "message": "RDMA/nes: Add a driver for NetEffect RNICs\n\nAdd a standard NIC and RDMA/iWARP driver for NetEffect 1/10Gb ethernet adapters.\n\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2c78853472a36c7cf51a84a34edc370e21c93ce4", "tree": "a89ab43cc596415f80e434470595fcbb4f8e7544", "parents": [ "f33afc26dc03e6e0513e2e300f2aa0ad5463c2d2" ], "author": { "name": "Olaf Kirch", "email": "olaf.kirch@oracle.com", "time": "Mon Feb 04 20:20:44 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:44 2008 -0800" }, "message": "IB/mthca: Return proper error codes from mthca_fmr_alloc()\n\nIf the allocation of the MTT or the mailbox failed, mthca_fmr_alloc()\nwould return 0 (success) no matter what. This leads to crashes a\nlittle down the road, when we try to dereference eg mr-\u003emtt, which was\nreally ERR_PTR(-Ewhatever).\n\nSigned-off-by: Olaf Kirch \u003colaf.kirch@oracle.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f33afc26dc03e6e0513e2e300f2aa0ad5463c2d2", "tree": "8d4645dd7c20c466a1c421a2ed05d480497f629f", "parents": [ "68f3948dab39249d178eb007c071f87fb6481fc6" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:44 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:44 2008 -0800" }, "message": "IB: Avoid marking __devinitdata as const\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "68f3948dab39249d178eb007c071f87fb6481fc6", "tree": "c67659a811309d0e63d8570a64ce934c9febc2fd", "parents": [ "1d368c546566e249da8181e933c53788093965cf" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:44 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:44 2008 -0800" }, "message": "IB/mlx4: Actually print out the driver version\n\nThe string mlx4_ib_version was defined, but never used. Print out the\nversion once when the first device is initialized.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "1d368c546566e249da8181e933c53788093965cf", "tree": "08ea2e0280f125f2981ab7ada0d335b5928cc670", "parents": [ "1203c42e7be1aa0be641b701f42b6d38c2d94b39" ], "author": { "name": "Eli Cohen", "email": "eli at mellanox.co.il", "time": "Thu Jan 24 06:38:06 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:44 2008 -0800" }, "message": "IB/ib_mthca: Pre-link receive WQEs in Tavor mode\n\nWe have recently discovered that Tavor mode requires each WQE in a\nposted list of receive WQEs to have a valid NDA field at all times.\nThis requirement holds true for regular QPs as well as for SRQs. This\npatch prelinks the receive queue in a regular QP and keeps the free\nlist in SRQ always properly linked.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nReviewed-by: Jack Morgenstein \u003cjackm@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "1203c42e7be1aa0be641b701f42b6d38c2d94b39", "tree": "3f84fb72b8fb61d460f3207d21ddf06b4a78700f", "parents": [ "1d96354e617990799b1cb5d7ff8f7c467b8767c8" ], "author": { "name": "Eli Cohen", "email": "eli@mellanox.co.il", "time": "Mon Feb 04 20:20:44 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:44 2008 -0800" }, "message": "IB/mthca: Remove checks for srq-\u003efirst_free \u003c 0\n\nThe SRQ receive posting functions make sure that srq-\u003efirst_free never\nbecomes negative, so we can remove tests of whether it is negative.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "893da75956ab48545e8732b46e1cf4350bd25f9c", "tree": "fe5125ffd8ec7d84f3b4937f6ade9ee65f7a4913", "parents": [ "6ccef1de2c1718729dd1c7ee8bd98473519eb3b3" ], "author": { "name": "Jack Morgenstein", "email": "jackm@dev.mellanox.co.il", "time": "Sun Jan 27 18:13:25 2008 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:43 2008 -0800" }, "message": "mlx4_core: Don\u0027t read reserved fields in mlx4_QUERY_ADAPTER()\n\nThe firmware QUERY_ADAPTER command does not return vendor_id,\ndevice_id, and revision_id; eliminate these fields from the query.\n\nInitialize the rev_id field of the mlx4 device via init_node_data (MAD\nIFC query), as is done in the query_device verb implementation.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@dev.mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6ccef1de2c1718729dd1c7ee8bd98473519eb3b3", "tree": "7685f0b85ce22ae65ea95a4af9771e03ec6206ad", "parents": [ "7bc531dd883b955e6198c8e202161f22d2e8c472" ], "author": { "name": "Jack Morgenstein", "email": "jackm@dev.mellanox.co.il", "time": "Sun Jan 27 18:13:20 2008 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:43 2008 -0800" }, "message": "IB/mthca: Don\u0027t read reserved fields in mthca_QUERY_ADAPTER()\n\nFor memfree devices, the firmware QUERY_ADAPTER command does not\nreturn vendor_id, device_id, and revision_id; do not return these\nfields in the QUERY_ADAPTER function for memfree devices.\n\nInstead, for memfree devices, initialize the rev_id field of the mthca\ndevice via init_node_data (MAD IFC query), as is done in the\nquery_device verb implementation.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@dev.mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "0d89fe2c0ca12ad2ee4e35a0661319746af6e94a", "tree": "fcc5d6598121a4863740437baf10217b701ca153", "parents": [ "2b5e6b120e58d44cace68e6c7204b541a8b0b43f" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:42 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:42 2008 -0800" }, "message": "IB/mthca: Fix and simplify page size calculation in mthca_reg_phys_mr()\n \nIn mthca_reg_phys_mr(), we calculate the page size for the HCA\nhardware to use to map the buffer list passed in by the consumer.\nFor example, if the consumer passes in\n\n [0] addr 0x1000, size 0x1000\n [1] addr 0x2000, size 0x1000\n\nthen the algorithm would come up with a page size of 0x2000 and a list\nof two pages, at 0x0000 and 0x2000. Usually, this would work fine\nsince the memory region would start at an offset of 0x1000 and have a\nlength of 0x2000.\n\nHowever, the old code did not take into account the alignment of the\nIO virtual address passed in. For example, if the consumer passed in\na virtual address of 0x6000 for the above, then the offset of 0x1000\nwould not be used correctly because the page mask of 0x1fff would\nresult in an offset of 0.\n\nWe can fix this quite neatly by making sure that the page shift we use\nis no bigger than the first bit where the start of the first buffer\nand the IO virtual address differ. Also, we can further simplify the\ncode by removing the special case for a single buffer by noticing that\nit doesn\u0027t matter if we use a page size that is too big. This allows\nthe loop to compute the page shift to be replaced with __ffs().\n\nThanks to Bryan S Rosenburg \u003crosnbrg@us.ibm.com\u003e for pointing out the\noriginal bug and suggesting several ways to improve this patch.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2b5e6b120e58d44cace68e6c7204b541a8b0b43f", "tree": "fa2cb052b146b22ec285928a000f133da3e7d73c", "parents": [ "528b03f73247c30750b740dcad16ad1914e56e89" ], "author": { "name": "Hoang-Nam Nguyen", "email": "hnguyen@de.ibm.com", "time": "Fri Jan 25 21:18:27 2008 +0100" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:42 2008 -0800" }, "message": "IB/ehca: Add PMA support\n\nThis patch enables ehca to redirect any PMA queries to the\nactual PMA QP.\n\nSigned-off-by: Hoang-Nam Nguyen \u003chnguyen@de.ibm.com\u003e\nReviewed-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nReviewed-by: Christoph Raisch \u003craisch@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "528b03f73247c30750b740dcad16ad1914e56e89", "tree": "414d7724b9f111fc80909975f53f65f675b431c4", "parents": [ "2b7274c39228d7a8c81a411dc3969763e9069c56" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Fri Jan 25 21:12:39 2008 +0100" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:42 2008 -0800" }, "message": "IB/ehca: Update sma_attr also in case of disruptive config change\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2b7274c39228d7a8c81a411dc3969763e9069c56", "tree": "596f69786ab9957a69a1d1e5da82d2fc900602c1", "parents": [ "3971c9f6dbf26f077b929dbe14ced60a697ebcf0" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Thu Jan 24 17:59:08 2008 +0100" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Feb 04 20:20:42 2008 -0800" }, "message": "IB/ehca: Prevent sending UD packets to QP0\n\nThe IB spec doesn\u0027t allow packets to QP0 sent on any other VL than VL15.\nHardware doesn\u0027t filter those packets on the send side, so we need to do\nthis in the driver and firmware.\n\nAs eHCA doesn\u0027t support QP0, we can just filter out all traffic going to\nQP0, regardless of SL or VL.\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "0ba6c33bcddc64a54b5f1c25a696c4767dc76292", "tree": "62e616f97a4762d8e75bf732e4827af2d15d52c5", "parents": [ "21af0297c7e56024a5ccc4d8ad2a590f9ec371ba", "85040bcb4643cba578839e953f25e2d1965d83d0" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jan 29 22:54:01 2008 +1100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jan 29 22:54:01 2008 +1100" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.25\n\n* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6.25: (1470 commits)\n [IPV6] ADDRLABEL: Fix double free on label deletion.\n [PPP]: Sparse warning fixes.\n [IPV4] fib_trie: remove unneeded NULL check\n [IPV4] fib_trie: More whitespace cleanup.\n [NET_SCHED]: Use nla_policy for attribute validation in ematches\n [NET_SCHED]: Use nla_policy for attribute validation in actions\n [NET_SCHED]: Use nla_policy for attribute validation in classifiers\n [NET_SCHED]: Use nla_policy for attribute validation in packet schedulers\n [NET_SCHED]: sch_api: introduce constant for rate table size\n [NET_SCHED]: Use typeful attribute parsing helpers\n [NET_SCHED]: Use typeful attribute construction helpers\n [NET_SCHED]: Use NLA_PUT_STRING for string dumping\n [NET_SCHED]: Use nla_nest_start/nla_nest_end\n [NET_SCHED]: Propagate nla_parse return value\n [NET_SCHED]: act_api: use PTR_ERR in tcf_action_init/tcf_action_get\n [NET_SCHED]: act_api: use nlmsg_parse\n [NET_SCHED]: act_api: fix netlink API conversion bug\n [NET_SCHED]: sch_netem: use nla_parse_nested_compat\n [NET_SCHED]: sch_atm: fix format string warning\n [NETNS]: Add namespace for ICMP replying code.\n ...\n" }, { "commit": "f1b050bf7a88910f9f00c9c8989c1bf5a67dd140", "tree": "37e8dce4268cb657a75e5074a38db48264f1e42f", "parents": [ "611c183ebcb5af384df3a4ddb391034a1b6ac255" ], "author": { "name": "Denis V. Lunev", "email": "den@openvz.org", "time": "Tue Jan 22 22:07:10 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 15:11:06 2008 -0800" }, "message": "[NETNS]: Add namespace parameter to ip_route_output_flow.\n\nNeeded to propagate it down to the __ip_route_output_key.\n\nSigned_off_by: Denis V. Lunev \u003cden@openvz.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "aff5905778d2fb1826ec623e4b1da3a7ff048ca4", "tree": "81af31da314140408653c95b53401d7405eceb91", "parents": [ "42d71c44d5fc09ae47783b7e15fe0d6b60711230" ], "author": { "name": "WANG Cong", "email": "xiyou.wangcong@gmail.com", "time": "Tue Jan 01 21:41:08 2008 +0800" }, "committer": { "name": "Sam Ravnborg", "email": "sam@ravnborg.org", "time": "Mon Jan 28 23:14:37 2008 +0100" }, "message": "INFINIBAND: Remove \u0027TOPDIR\u0027 from Makefiles\n\nThis patch removes TOPDIR from infiniband Makefile and delete\none include statement pointing to a non-existing directory\n\nCc: Roland Dreier \u003crolandd@cisco.com\u003e\nCc: Sean Hefty \u003cmshefty@ichips.intel.com\u003e\nCc: Hal Rosenstock \u003chal.rosenstock@gmail.com\u003e\nSigned-off-by: WANG Cong \u003cxiyou.wangcong@gmail.com\u003e\nSigned-off-by: Sam Ravnborg \u003csam@ravnborg.org\u003e\n" }, { "commit": "8176d297c73a06e6076c9c31f6404047567f6324", "tree": "d3ea63287941d458f853dc06e1e28115025cab19", "parents": [ "f7fca1e8a8eeb6660396327b48995e3d9a7b6dc2" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Thu Jan 24 16:30:16 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:17:47 2008 -0800" }, "message": "RDMA/cxgb3: Fix the T3A workaround checks\n\nCorrectly work around T3A issues by checking \"hwtype !\u003d T3A\" instead of\n\"hwtype \u003d\u003d T3B\". This will be needed for new hardware types.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f7fca1e8a8eeb6660396327b48995e3d9a7b6dc2", "tree": "4c174030d1cd5a47660d1cb9d45396b74b49daef", "parents": [ "1cf18d5aab5144866cb5221250905623b03a32a9" ], "author": { "name": "Jan Engelhardt", "email": "jengelh@computergmbh.de", "time": "Tue Jan 22 20:45:30 2008 +0100" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:17:46 2008 -0800" }, "message": "IB/ipath: Remove unnecessary cast\n\nSigned-off-by: Jan Engelhardt \u003cjengelh@computergmbh.de\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "c6b5b5047417c1becb5e48e748e3acb3801079a1", "tree": "8a4efd832544869ec93646be2f5d409119b9b309", "parents": [ "d08ca26ceec4dfbcfdbada4ad728db742ccaecd1" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Jan 21 14:42:13 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:17:45 2008 -0800" }, "message": "RDMA/cxgb3: Mark QP as privileged based on user capabilities\n\nThis is needed to support zero-stag properly.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d08ca26ceec4dfbcfdbada4ad728db742ccaecd1", "tree": "15c79eb89ce17fcb2b96f1497e52c352d433b0ff", "parents": [ "856b5925047d73a85557203d124d62c5eea1fbd3" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Jan 21 14:42:11 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:17:45 2008 -0800" }, "message": "RDMA/cxgb3: Fix page shift calculation in build_phys_page_list()\n\nThe existing logic incorrectly maps this buffer list:\n\n 0: addr 0x10001000, size 0x1000\n 1: addr 0x10002000, size 0x1000\n\nTo this bogus page list:\n\n 0: 0x10000000\n 1: 0x10002000\n\nThe shift calculation must also take into account the address of the\nfirst entry masked by the page_mask as well as the last address+size\nrounded up to the next page size.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "856b5925047d73a85557203d124d62c5eea1fbd3", "tree": "a2cd5eaff8a758e41d4870c7f62c2c7cf8aca861", "parents": [ "4e1e93a4189a98cfb0e24865f7f44470ae5f805e" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Jan 21 14:42:09 2008 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:17:45 2008 -0800" }, "message": "RDMA/cxgb3: Flush the receive queue when closing\n\n- for kernel mode cqs, call event notification handler when flushing.\n- flush QP when moving from RTS -\u003e CLOSING.\n- fix logic to identify a kernel mode qp.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "4e1e93a4189a98cfb0e24865f7f44470ae5f805e", "tree": "b81f51543d0af51edcbac668d851bf053b84d271", "parents": [ "950529e5c6efda8a6d3090a8fef9b904c833397a" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Fri Jan 25 14:17:44 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:17:44 2008 -0800" }, "message": "IB/ipath: Trivial simplification of ipath_make_ud_req()\n\nMove the increment of s_hdrwords into the existing if block that tests \nif we\u0027re doing a send with immediate, to save one test of the opcode.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "950529e5c6efda8a6d3090a8fef9b904c833397a", "tree": "92061c141f77626d14d9bf16c91c6a489fb73ee7", "parents": [ "48fe5e594c979177b7f20affd027be56e8ea2767" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:17:44 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:17:44 2008 -0800" }, "message": "IB/mthca: Update latest \"native Arbel\" firmware revision\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "3d68ea32611095c7e09409ac1b2a56da22fd5eb7", "tree": "6713954de767902d74c6b8d9ac432efa3b86b6b9", "parents": [ "6ac50727bda29e961385e4c40318dadbb5730193" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Thu Jan 10 00:50:41 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:17:44 2008 -0800" }, "message": "IB/ipath: Add mappings from HW register to PortInfo port physical state\n\nAdd new mappings from port physical state (a HW register value) to the\nIB SubnGet(PortInfo) port physical state.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6ac50727bda29e961385e4c40318dadbb5730193", "tree": "522ff1a220c817d4ed00e1311e4cf23b24952b50", "parents": [ "ddb70c83a5ce439271f1699e52a97785a8b45b81" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Thu Aug 09 03:11:38 2007 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:17:43 2008 -0800" }, "message": "IB/ipath: Changes to support PIO bandwidth check on IBA7220\n\nThe IBA7220 uses a count-based triggering mechanism, and therefore\ncan\u0027t use the same bandwidth verification mechanism as older chips.\n\nTo support the 7220, allow enabling and disabling armlaunch errors on\napplication request. Minor robustness improvements as well.\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "ddb70c83a5ce439271f1699e52a97785a8b45b81", "tree": "dec9a6a75c595a5348c7970cadd40465b59a4fef", "parents": [ "359193ef433061515fe24d57e5bd5a1318d71bc3" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Tue Jan 08 01:51:46 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:17:43 2008 -0800" }, "message": "IB/ipath: Minor cleanup of unused fields and chip-specific errors\n\nClean up some unused header fields, minor related cleanup.\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "359193ef433061515fe24d57e5bd5a1318d71bc3", "tree": "270f18f7a3752bf1ac9f98f4a8e88eb9b95f8c71", "parents": [ "c4bce8032ef4368063c84d665b19804878d63e7c" ], "author": { "name": "Michael Albaugh", "email": "michael.albaugh@qlogic.com", "time": "Tue Jan 08 00:37:34 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:17:32 2008 -0800" }, "message": "IB/ipath: New sysfs entries to control 7220 features\n\nIBA7220 includes many more configurable IB settings. Getting/setting\nthese is now grouped into a pair of chip specific functions accessed via\nfunction pointers. Provide sysfs access to these settings.\n\nSigned-off-by: Michael Albaugh \u003cmichael.albaugh@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "c4bce8032ef4368063c84d665b19804878d63e7c", "tree": "29b7e0b7a97747982237a98f634a97d2111d1d8a", "parents": [ "7387273307139ebf8d7f7fb3bb79d1ca48bd71d6" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Tue Jan 08 02:36:46 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:45 2008 -0800" }, "message": "IB/ipath: Add new chip-specific functions to older chips, consistent init\n\nThis adds the new (sometimes empty) chip-specific functions to the older\nchips, and makes the initialization and related functions consistent across\nall 3 chips.\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7387273307139ebf8d7f7fb3bb79d1ca48bd71d6", "tree": "9d65581f68a0dd14589053aaafffa155193e5bf1", "parents": [ "2ec8e662416cc9a171cdfe3d75e1ff00ba757859" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Tue Jan 08 23:16:17 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:44 2008 -0800" }, "message": "IB/ipath: Remove unused MDIO interface code\n\nThis code has been unused for some time, but still had leftovers\nfrom when it was used.\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2ec8e662416cc9a171cdfe3d75e1ff00ba757859", "tree": "dbc881205c3177db9a7816385b4fdda762bdb04c", "parents": [ "bbdd267ef2796e96b461b8447b2026ce06e6ec4b" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Thu Jan 17 15:07:24 2008 +0100" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:44 2008 -0800" }, "message": "IB/ehca: Prevent RDMA-related connection failures on some eHCA2 hardware\n\nSome HW revisions of eHCA2 may cause an RC connection to break if they\nreceived RDMA Reads over that connection before. This can be\nprevented by assuring that, after the first RDMA Read, the QP receives\na new RDMA Read every few million link packets.\n\nInclude code into the driver that inserts an empty (size 0) RDMA Read\ninto the message stream every now and then if the consumer doesn\u0027t\npost them frequently enough.\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "bbdd267ef2796e96b461b8447b2026ce06e6ec4b", "tree": "45cea3f33acc271da83fcccca0c5626c0281da4e", "parents": [ "b8b50e353b85bc3c791dd2b99370ac300ebcd186" ], "author": { "name": "Hoang-Nam Nguyen", "email": "hnguyen@de.ibm.com", "time": "Thu Jan 17 15:05:45 2008 +0100" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:44 2008 -0800" }, "message": "IB/ehca: Add \"port connection autodetect mode\"\n\nThis patch enhances ehca with a capability to \"autodetect\" the ports\nbeing connected physically. In order to utilize that function the\nmodule option nr_ports must be set to -1 (default is 2 - two\nports). This feature is experimental and will made the default later.\n\nMore detail:\n\nIf the user connects only one port to the switch, current code requires\n 1) port one to be connected and\n 2) module option nr_ports\u003d1 to be given.\n\nIf autodetect is enabled, ehca will not wait at creation of the GSI QP\nfor the respective port to become active. Since firmware does not\naccept modify_qp() while the port is down at initialization, we need\nto cache all calls to modify_qp() for the SMI/GSI QP and just return a\ngood return code.\n\nWhen a port is activated and we get a PORT_ACTIVE event, we replay the\ncached modify-qp() parms and re-trigger any posted recv WRs. Only then\ndo we forward the PORT_ACTIVE event to registered clients.\n\nThe result of this autodetect patch is that all ports will be\naccessible by the users. Depending on their respective cabling only\nthose ports that are connected properly will become operable. If a\nuser tries to modify a regular QP of a non-connected port, modify_qp()\nwill fail. Furthermore, ibv_devinfo should show the port state\naccordingly.\n\nNote that this patch primarily improves the loading behaviour of\nehca. If the cable is removed while the driver is operating and\nplugged in again, firmware will handle that properly by sending an\nappropriate async event.\n\nSigned-off-by: Hoang-Nam Nguyen \u003chnguyen@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "b8b50e353b85bc3c791dd2b99370ac300ebcd186", "tree": "80b6706a9601b3ce61c1d9caa049eb06520ed87a", "parents": [ "0c86e280fe8a08d4ae30b77e46a1e7da28d756c9" ], "author": { "name": "Hoang-Nam Nguyen", "email": "hnguyen at de.ibm.com", "time": "Thu Jan 17 15:04:32 2008 +0100" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:44 2008 -0800" }, "message": "IB/ehca: Define array to store SMI/GSI QPs\n\nSigned-off-by: Hoang-Nam Nguyen \u003chnguyen@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "0c86e280fe8a08d4ae30b77e46a1e7da28d756c9", "tree": "422504ced2506b3b84a13bb2924f8256c6d3ad90", "parents": [ "6410627eb9804e541b83d220c8e914ce64475b31" ], "author": { "name": "Hoang-Nam Nguyen", "email": "hnguyen at de.ibm.com", "time": "Thu Jan 17 15:03:55 2008 +0100" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:43 2008 -0800" }, "message": "IB/ehca: Remove CQ-QP-link before destroying QP in error path of create_qp()\n\nSigned-off-by: Hoang-Nam Nguyen \u003chnguyen@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "cf9542aa923982428fbf6a6f815c32ae2c3da8c7", "tree": "9e10e3b4920f1a98df8853fa59a52a20ac7ce8ec", "parents": [ "1d6e658e8e3247fcf0fa90c40fdfebf2e85a610e" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:42 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:42 2008 -0800" }, "message": "IB/ipath: Fix some sparse warnings about shadowed symbols\n\nThere are a few places in the ipath driver where a variable is\nre-declared within a block where it is already in scope. Most of these\nextra declarations can simply be removed, since the variable from the\nouter scope is used in a way so that it does not need to keep its\nvariable across the block with the re-declaration.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "1d6e658e8e3247fcf0fa90c40fdfebf2e85a610e", "tree": "fed64880f5886d4991d9e6910985054faefee4f6", "parents": [ "1a7d2dce4169ed42310926a5675fffd0986caa26" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:42 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:42 2008 -0800" }, "message": "RDMA/cxgb3: Endianness annotation for irs field\n\nt3_rdma_init_wr.irs is a big-endian field, so declare it as __be32.\nThis fixes one sparse warning.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "1a7d2dce4169ed42310926a5675fffd0986caa26", "tree": "ea3dcb6f1f3d114b89603fafb3f39f77292fab71", "parents": [ "5851bb893e5bb87150817c180ccddcf4e78db1b6" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Mon Oct 15 00:49:07 2007 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:41 2008 -0800" }, "message": "IB/ehca: Use round_jiffies() for EQ polling timer\n\nUse round_jiffies() to align ehca\u0027s 1-second timer with other timers\nand potentially save power by sleeping cores for longer.\n\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nAcked-by: Hoang-Nam Nguyen \u003chnguyen@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "1f813ca830f51ed404195750bdba86c41a8050ba", "tree": "6228b558696f5372ff89ec4b6969f128802c055b", "parents": [ "7da0498e7f0eb022107811b9d41697298329f6b4" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Sun Jan 06 21:12:38 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:40 2008 -0800" }, "message": "IB/ipath: Drop support for the original QHT7040 board\n\nThe original QHT7040 had significant performance issues so there was an\nadditional check in the driver for a newer serial number. Support for\nthe small quantities of that board shipped has been dropped, so this\npatch removes the special checks to simplify the code.\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7da0498e7f0eb022107811b9d41697298329f6b4", "tree": "935cd0b8069561de4bb12b0a10eb254b0b9cf7f8", "parents": [ "4ea61b548bc93fb87cec6f52059851076e2ff54d" ], "author": { "name": "Arthur Jones", "email": "arthur.jones@qlogic.com", "time": "Sun Jan 06 21:12:38 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:40 2008 -0800" }, "message": "IB/ipath: Add ipath_read_ireg() abstraction\n\nDifferent chips have different width interrupt status registers, so add\na flag and accessor function to decide which width register read to use.\n\nSigned-off-by: Arthur Jones \u003carthur.jones@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "4ea61b548bc93fb87cec6f52059851076e2ff54d", "tree": "b48ddf0865c393b2245dbb131098901f6cc3f318", "parents": [ "60948a415859cb859e24f0dfe739069d66577466" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Sun Jan 06 21:12:38 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:39 2008 -0800" }, "message": "IB/ipath: Add flag and handling for chips with swapped register bug\n\nThe 6110 had a bug that caused some registers to be swapped; it was\nfixed for the 7220 (and didn\u0027t affect the 6120 because it had fewer\nregisters). This adds a flag and related code to handle that, and\nincludes some minor cleanups in the same area.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\n" }, { "commit": "60948a415859cb859e24f0dfe739069d66577466", "tree": "392b6e21c7041998600a78821dc1ba1fba9c6572", "parents": [ "a18e26ae442001de62f6b84a923e8613347dc35f" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Sun Jan 06 21:02:34 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:39 2008 -0800" }, "message": "IB/ipath: Port config has on-chip effects for 7220\n\nThe number of configured ports for the 7220 changes the number of eager\nTIDs available per port, for all but port 0 (kernel port) which remains\nconstant, so add a field to give port0 count separate from the portdata\nstructure.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "a18e26ae442001de62f6b84a923e8613347dc35f", "tree": "36109aca4360deb0ca0ea12e429d917e54819d5a", "parents": [ "9e2ef36b5a83b3c8ec1153382559dff410cc4341" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Sun Jan 06 21:02:34 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:39 2008 -0800" }, "message": "IB/ipath: Allow more flexible user register alignments\n\nUser registers have different alignments on different chips (4KB on\nolder, 64KB on 7220). Allow mapping the user registers on kernels with\npage sizes up to 64K.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "9e2ef36b5a83b3c8ec1153382559dff410cc4341", "tree": "f075e20c043c46afbab0320b5a92bac24592bd58", "parents": [ "3029fcc3d44530601f19fd8f551ac195d3a918d7" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Sun Jan 06 21:02:34 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:38 2008 -0800" }, "message": "IB/ipath: Clean up some comments\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "3029fcc3d44530601f19fd8f551ac195d3a918d7", "tree": "df486443f140a8d47fab8bda9552744c3201b865", "parents": [ "6c719cae0b91f577738dfb4007baee28f03e48a5" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Sun Jan 06 21:02:34 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:38 2008 -0800" }, "message": "IB/ipath: Export hardware counters more consistently\n\nVarious hardware counters are exported via the ipath file system (since\nit is binary data). The old file format was very dependent on the HW\noffsets for these registers. Newer HCA chips can have different\ncounters at different offsets. This patch adds a level of indirection\nto make the file format consistent across HCAs.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6c719cae0b91f577738dfb4007baee28f03e48a5", "tree": "fef7fb60092c5ed84fe14f7aaafdf55a0551016a", "parents": [ "7aa54bd730df1468c90ae84b56ade7f322b44de7" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Sun Jan 06 21:02:33 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:38 2008 -0800" }, "message": "IB/ipath: MAD performance sampling registers support\n\nAdd support for QLogic HCAs which have hardware performance sampling\nregisters for PortSamplesControl and PortSamplesResult MADs.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "755807a296f77ca7c31dc000afdfe1e5172bbf72", "tree": "0df244c6d024ec0b7085b2d405b3836f2809b4d6", "parents": [ "d8274869d742c3d8082e1428de47e54d12104928" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Thu Dec 06 00:28:02 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:36 2008 -0800" }, "message": "IB/ipath: Changes for fields moving from devdata to portdata\n\nThis patch moves some arrays that were defined per-device to be\nvariables defined in the per context data structure, thus avoiding extra\nkzalloc() calls.\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d8274869d742c3d8082e1428de47e54d12104928", "tree": "128d36e05d5facbff15652eb24faf03cbec3da8e", "parents": [ "c59a80aca0bfc491d90534ed5606d5493eca24a3" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Fri Dec 21 01:50:59 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:36 2008 -0800" }, "message": "IB/ipath: Generalize some xxx_SHIFT macros\n\nIn preparation for upcoming chips that have different values for\nINFINIPATH_R_PORTENABLE_SHIFT, INFINIPATH_R_INTRAVAIL_SHIFT,\nINFINIPATH_R_TAILUPD_SHIFT, and portcfg_shift, remove the shared\n#defines and use device-specific variables instead.\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "c59a80aca0bfc491d90534ed5606d5493eca24a3", "tree": "181af3a515feb82e1c77b1d8bc5ec460485d44df", "parents": [ "d65708f3a766116662ff9bac81088d52a49901f4" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Thu Dec 20 02:43:23 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:35 2008 -0800" }, "message": "IB/ipath: kreceive uses portdata rather than devdata\n\nkreceive is now portdata * instead of devdata * and other kreceive\nrelated cleanups....\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d65708f3a766116662ff9bac81088d52a49901f4", "tree": "91b89bd66a0c032600e64b8de83e33ae38212f8e", "parents": [ "cc65edcf0c174eff4367cfbc594a2f33c0d477fa" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Fri Dec 21 16:47:04 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:35 2008 -0800" }, "message": "IB/ipath: Cleanup ipath_get_egrbuf()\n\nRemove an unused parameter and fix up the comment.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "cc65edcf0c174eff4367cfbc594a2f33c0d477fa", "tree": "0422b9197852617730b9b0d51964726dd5518ec3", "parents": [ "e57d62a14775c9d37195debe837431c75168ef69" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Fri Dec 14 19:22:34 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:34 2008 -0800" }, "message": "IB/ipath: Fix RNR NAK handling\n\nThis patch fixes a couple of minor problems with RNR NAK handling:\n - The insertion sort was causing extra delay when inserting ahead\n vs. behind an existing entry on the list.\n - A resend of a first packet of a message which is still not ready,\n needs another RNR NAK (i.e., it was suppressed when it shouldn\u0027t).\n - Also, the resend tasklet doesn\u0027t need to be woken up unless the\n ACK/NAK actually indicates progress has been made.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e57d62a14775c9d37195debe837431c75168ef69", "tree": "12ff8ce00a17101ba597f51ba50a2e0a05010721", "parents": [ "b3226184af6c13c9d5d38f13f0ef8e03f718bbf7" ], "author": { "name": "Hoang-Nam Nguyen", "email": "hnguyen@linux.vnet.ibm.com", "time": "Thu Dec 20 15:06:33 2007 +0100" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:34 2008 -0800" }, "message": "IB/ehca: Forward event client-reregister-required to registered clients\n\nThis patch allows ehca to forward event client-reregister-required to\nregistered clients. One such event is generated by a switch eg. after\nits reboot.\n\nSigned-off-by: Hoang-Nam Nguyen \u003chnguyen@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "b3226184af6c13c9d5d38f13f0ef8e03f718bbf7", "tree": "e79a895f7c320ada2cf8a1faffb735f9fc098c8a", "parents": [ "e57895d38991036f9ccf193b70fc5ebd5f6e6dc9" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:34 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:34 2008 -0800" }, "message": "IB/mlx4: Micro-optimize mlx4_ib_poll_one()\n\nRather than byte-swapping cqe-\u003eg_mlpath_rqpn each time we extract a\nfield from it, byte-swap it once into a temporary variable. This \nresults in smaller, better code -- eg, on 32-bit x86:\n\nadd/remove: 0/0 grow/shrink: 0/1 up/down: 0/-5 (-5)\nfunction old new delta\nmlx4_ib_poll_cq 1188 1183 -5\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e57895d38991036f9ccf193b70fc5ebd5f6e6dc9", "tree": "4c0e014a007a2e31c15bfa0232f5c5cbcc08136a", "parents": [ "38dc732f47948b9f91ae846806159a16aab1015f" ], "author": { "name": "Adrian Bunk", "email": "bunk@kernel.org", "time": "Tue Jan 01 15:47:10 2008 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:33 2008 -0800" }, "message": "IB/mthca: Remove MSI support as scheduled\n\nRemove MSI support from the mthca driver, as scheduled. There is no\nreason to use MSI instead of MSI-X, since MSI-X performs better. No\none has spoken up since MSI support was deprecated in commit f6be6fbe\n(\"IB/mthca: Schedule MSI support for removal\"), so apparently the MSI\nsupport is unused.\n\nSigned-off-by: Adrian Bunk \u003cbunk@kernel.org\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "94545e8c51fbf01d1c1cda7e6d017598d41e840a", "tree": "5e359d7786347ab0b3ee114934e1330c154090ec", "parents": [ "5920869f1ec263fee4255ec71d333c118406a419" ], "author": { "name": "Joe Perches", "email": "joe@perches.com", "time": "Mon Dec 17 11:30:36 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:29 2008 -0800" }, "message": "IB: Spelling fixes in comments\n\nSigned-off-by: Joe Perches \u003cjoe@perches.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "3c8450860ba9d6279dbc969633eacf99161860d9", "tree": "54f456c7987485009b4f4786e31de62a87939b2e", "parents": [ "a2f76cd69f4913079cad10670f8520ffe07f4067" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Thu Dec 13 15:58:57 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:29 2008 -0800" }, "message": "IB/ipath: Convert from .nopage to .fault\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "a2f76cd69f4913079cad10670f8520ffe07f4067", "tree": "f205a5409055cbbc5dc6a5a30e462f1c543b692d", "parents": [ "2f01a7001131bbf3ce1e39252bf72aea2da034df" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Fri Nov 02 17:40:36 2007 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:29 2008 -0800" }, "message": "IB/ipath: Add the work completion error code to the QP error debug output\n\nAdd the work completion error code to the QP error debug output.\nThis makes it easier to determine the cause of the error.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2f01a7001131bbf3ce1e39252bf72aea2da034df", "tree": "926b215a1da4cd9c6956306b187507ea0c5ae185", "parents": [ "6276980138292056aab162f7eb98afe5243b2976" ], "author": { "name": "Arthur Jones", "email": "arthur.jones@qlogic.com", "time": "Wed Oct 17 18:18:29 2007 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:28 2008 -0800" }, "message": "IB/ipath: Better comment for rmb() in ipath_intr()\n\nAn internal code review found the comment here lacking -- update it with \nmore specifics of how and why the rmb() is there.\n\nSigned-off-by: Arthur Jones \u003carthur.jones@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6276980138292056aab162f7eb98afe5243b2976", "tree": "55cb646a242238e5fc2150d23b037f45f8e400d1", "parents": [ "733d12813bd36ed7c727686ac1164f92f87a14a2" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Mon Nov 26 23:44:15 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:28 2008 -0800" }, "message": "IB/ipath: Fix comments for ipath_create_srq()\n\nDuring a code review, someone noticed the comments didn\u0027t match the code.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "733d12813bd36ed7c727686ac1164f92f87a14a2", "tree": "903cfeadcfd6e0ff129fc7736db526889ccf2f50", "parents": [ "e342c119172f87f2d812bccfd0283f62e1bc1c2a" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Thu Nov 08 19:53:01 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:28 2008 -0800" }, "message": "IB/ipath: Fix error returned from ib_resize_cq if new size smaller than # entries\n\nThe gen2_basic tests check for the errno value when a CQ is resized\nsmaller than the number of outstanding completions queue on the CQ.\nThis patch changes ib_ipath to return EINVAL which is what ib_mthca\nreturns and what gen2_basic expects.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e342c119172f87f2d812bccfd0283f62e1bc1c2a", "tree": "52eb0e75f5f894ab7f0f3c755f0876f18637e5a9", "parents": [ "9ab4295d1d9ab10a249aea002060685f935a528c" ], "author": { "name": "John Gregor", "email": "john.gregor@qlogic.com", "time": "Wed Sep 05 01:57:14 2007 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:27 2008 -0800" }, "message": "IB/ipath: Fix sendctrl locking\n\nCode review pointed out that the locking around uses of ipath_sendctrl \nand kr_sendctrl were, in several places, incorrect and/or inconsistent.\n\nSigned-off-by: John Gregor \u003cjohn.gregor@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "9ab4295d1d9ab10a249aea002060685f935a528c", "tree": "66950ae4a032120b0b22988c89fc7d699df420af", "parents": [ "457fe7b8a6822907cbe65897dc81b83d9df5bcbf" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Fri Oct 12 20:48:06 2007 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:27 2008 -0800" }, "message": "IB/ipath: Remove dead code for user process waiting for send buffer\n\nAt one point in time there was code to allow a user process to\nwait for a send buffer if none were available. This feature was\nnever used and most of the code was removed. This removes\nsome missed unused code.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "457fe7b8a6822907cbe65897dc81b83d9df5bcbf", "tree": "d30b8fa4987cd928bc4975e0a85b706c1124ef29", "parents": [ "7f049f2f4259e4a5c213720df1ce0c2ca095641a" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Nov 26 11:28:46 2007 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:26 2008 -0800" }, "message": "RDMA/cxgb3: Support version 5.0 firmware\n\nThe 5.0 firmware now supports translating sgls in recv work requests,\nso remove the host driver logic currently doing the translation.\n\nNote: this change requires 5.0 firmware.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7f049f2f4259e4a5c213720df1ce0c2ca095641a", "tree": "d59b130c0aa7f2600cb2c9dfd3d2b569c7bba601", "parents": [ "908cf9a565348b5a6d765d120cb189a568ea4883" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Mon Nov 26 11:28:44 2007 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:26 2008 -0800" }, "message": "RDMA/cxgb3: Hold rtnl_lock() around ethtool get_drvinfo call\n\nCurrently the call into cxgb3 to get the driver info is not serialized.\nThe iw_cxgb3 module needs to hold the rtnl_lock around the ethtool ops\ncall like dev_ioctl() does.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "908cf9a565348b5a6d765d120cb189a568ea4883", "tree": "ee37f9cbeb6631eb0d6ca82d24d6f0bc003ab726", "parents": [ "2c45688faed1b19583c388694025e39001b68c8d" ], "author": { "name": "Joe Perches", "email": "joe@perches.com", "time": "Mon Nov 19 17:48:11 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:26 2008 -0800" }, "message": "drivers/infiniband: Add missing \"space\"\n\nAdd missing spaces in the middle of format strings.\n\nSigned-off-by: Joe Perches \u003cjoe@perches.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2c45688faed1b19583c388694025e39001b68c8d", "tree": "38555f579fbdf6c9d74899482abc754d1793c8d4", "parents": [ "727792da2bc22e2ce125faef84aeca3b3e2f4a90" ], "author": { "name": "Matthias Kaehlcke", "email": "matthias.kaehlcke@gmail.com", "time": "Thu Nov 15 15:23:25 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:26 2008 -0800" }, "message": "IB/ipath: Convert ipath_eep_sem semaphore to a mutex\n\nSigned-off-by: Matthias Kaehlcke \u003cmatthias.kaehlcke@gmail.com\u003e\nAcked-by: Michael Albaugh \u003cMichael.Albaugh@qlogic.com\u003e\nTested-by: Arthur Jones \u003carthur.jones@qlogic.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f9b403532235520ec248c024f621efcaf6ba7b93", "tree": "43bf4fbd3ba599fa9a75054188930e8c96f86d5f", "parents": [ "3828ff457a694f97f88f6978bea428199df0a690" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Tue Oct 23 15:07:41 2007 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:25 2008 -0800" }, "message": "IB/ipath: Enable loopback of DR SMP responses from userspace\n\nThis patch is in response to reviewing a patch to the core MAD\nprocessing which fixes loopback of directed route packets to/from user\nlevel MAD agents. This change enables the core code to work for\nib_ipath by fixing the return code from the ipath process_mad method.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e193e3326c521eea6a0221e945627ae5e3274910", "tree": "7493676d8d2be425c6a5460c6db01e1268aca161", "parents": [ "68e995a295720439ad2bf8677114cdf9d262d905" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Wed Oct 10 05:10:35 2007 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:25 2008 -0800" }, "message": "IB/ipath: Improve interrupt handler cache footprint\n\nImprove interrupt handler cache footprint by noinline\u0027ing error\nfunctions that are rarely called.\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "657c2f2cbccbac88689ac5174fc13dd3f9aece34", "tree": "cdb292c2da582d49a3908244914dd192535e76cd", "parents": [ "b47711bfbcd4eb77ca61ef0162487b20e023ae55" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:21 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Jan 25 14:15:21 2008 -0800" }, "message": "IB/ipath: Fix crash on unload introduced by sysfs changes\n\nCommit 23b9c1ab (\"Infiniband: make ipath driver use default driver\ngroups.\") introduced a bug in the ipath driver where\nipath_device_create_group() fell through into the error path, even on\nsuccess, which meant that the sysfs groups it created would always get\nremoved right away. This made ipath_device_remove_group() hit the\nBUG_ON() in sysfs_remove_group() when it tried to remove those groups a\nsecond time.\n\nCorrect the return path so that the groups stick around until they are\nsupposed to be cleaned up.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "23b9c1ab5baf368a32b7242bf110ef1f48700d04", "tree": "e1da2529abd59a2b15213c837ab6bacd5e0f17dc", "parents": [ "0478b83adb0269033221dc063d1185a224681ee8" ], "author": { "name": "Greg Kroah-Hartman", "email": "gregkh@suse.de", "time": "Tue Dec 04 22:53:16 2007 -0800" }, "committer": { "name": "Greg Kroah-Hartman", "email": "gregkh@suse.de", "time": "Thu Jan 24 20:40:34 2008 -0800" }, "message": "Infiniband: make ipath driver use default driver groups.\n\nMake the ipath driver use the new driver functions so that it does not\ntouch the sysfs portion of the driver structure.\n\nWe also remove the redundant symlink from the device back to the driver,\nas it is already in the sysfs tree. Any userspace tools should be using\nthe standard symlink, not some driver specific one.\n\nCc: Roland Dreier \u003crdreier@cisco.com\u003e\nCc: Bryan O\u0027Sullivan \u003cbryan.osullivan@qlogic.com\u003e\nCc: Arthur Jones \u003carthur.jones@qlogic.com\u003e\nCc: Cornelia Huck \u003ccornelia.huck@de.ibm.com\u003e\nSigned-off-by: Greg Kroah-Hartman \u003cgregkh@suse.de\u003e\n\n" }, { "commit": "0a69631b2869093d7306e8f66cca8eb0a05aa919", "tree": "32788676e5f262d540d8da36ec3f76edda9cb262", "parents": [ "cdf71a10c7b6432d9b48e292cca2c62a0b9fa6cf" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Tue Jan 15 15:58:13 2008 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Jan 16 14:42:35 2008 -0800" }, "message": "IB/ipath: Fix receiving UD messages with immediate data\n\nThis fixes a small bug in ipath_ud_rcv()\u0027s handling of UD messages\nwith immediate data. We need to test whether immediate data is\npresent and update the header size accordingly *before* testing the\npacket size from the header against the actual received length.\nOtherwise the wrong header size will be used and all messages with\nimmediate data will be dropped.\n\nThis bug keeps MVAPICH-UD and HP MPI from working at all on ipath devices.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e1bb7843e4c25e6e331890a2ca512581e844bbaa", "tree": "7bbbf893b743468e8d1b4d4b914a612721f6acb8", "parents": [ "ed96f2470bf5d315770dc199f0250c1b8d3c2f3c" ], "author": { "name": "Dotan Barak", "email": "dotanb@dev.mellanox.co.il", "time": "Mon Jan 07 09:01:25 2008 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Jan 08 12:05:53 2008 -0800" }, "message": "IB/mlx4: Fix value of pkey_index in QP1 completions\n\nFix the value of pkey_index in completions to get a valid value for\nGSI QPs. Without this fix, incoming GSI packets on port 2 get an\ninvalid P_Key index in the completion, which prevents the MAD layer\nfrom sending back a response, which can make the second port of\nConnectX HCAs completely useless.\n\nSigned-off-by: Dotan Barak \u003cdotanb@dev.mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "3d758a4a48682639d3996968499913ecb1552e06", "tree": "7a9d7907f96d8a87e0e2c3acc6902c0e971a2989", "parents": [ "4faf7757955239c1b259e7dab224d4638a99b456" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Thu Dec 13 13:35:57 2007 +0100" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu Dec 13 09:37:23 2007 -0800" }, "message": "IB/ehca: Fix lock flag variable location, bump version number\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "4faf7757955239c1b259e7dab224d4638a99b456", "tree": "d6e56aef1706cf26c0daa67bad150cb88ad7f52f", "parents": [ "1457edc72d187f452be1374c7d9281f1dfa16f32" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Mon Dec 10 18:59:10 2007 +0100" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Dec 12 14:09:43 2007 -0800" }, "message": "IB/ehca: Serialize HCA-related hCalls if necessary\n\nSeveral pSeries firmware versions share a rare locking issue in the\nHCA-related hCalls. Check for a feature flag that indicates the issue\nbeing fixed and serialize all HCA hCalls if not.\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "1457edc72d187f452be1374c7d9281f1dfa16f32", "tree": "1f50a120763471dc4ba7a95249de41c2c27400eb", "parents": [ "4af75653031c6d454b4ace47c1536f0d2e727e3e" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Mon Dec 10 12:20:57 2007 +0100" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Dec 12 14:09:43 2007 -0800" }, "message": "IB/ehca: Return correct number of SGEs for SRQ\n\nFirmware would round up the number of SGEs to four, because the WQE\nstructure holds four SGEs. For SRQ, only three are supported, so return\na fixed value instead.\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "b1812582ba94b5f377d5d3cec7646cc17d84e733", "tree": "b176268f3b565171bc223fac2296f4982b12bbc1", "parents": [ "1401b53acc0328d96bacb2a3393d2852699df96b" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Fri Nov 30 16:19:41 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri Nov 30 16:19:41 2007 -0800" }, "message": "IB/ehca: Fix static rate if path faster than link\n\nThe formula would yield -1 if the path is faster than the link, which\nis wrong in a bad way (max throttling). Clamp to 0, which is the\ncorrect value.\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "3fe2ed344d4b36e7489b1d0c7cf677312b0bf870", "tree": "c9f9816ccb21a27b356c70620180d1edf6166373", "parents": [ "9ed87fd34c97a998e63505718ce7e107a23c84c3" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Thu Nov 22 12:26:26 2007 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Sat Nov 24 13:47:59 2007 -0800" }, "message": "IB/ehca: Fix static rate regression\n\nWrong choice of port number caused modify_qp() to fail -- fixed.\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "4187b915a0f7eaa69707715e80d9fc253ff6167a", "tree": "8ad1bada5abd9ef982a05a08b54a3dfdf0086187", "parents": [ "14de986a0ba560b54340fd277a3579e95a2d3838" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Wed Nov 14 13:34:14 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Nov 20 11:05:42 2007 -0800" }, "message": "IB/ipath: Normalize error return codes for posting work requests\n\nThe error codes for ib_post_send(), ib_post_recv(), and ib_post_srq_recv()\nwere inconsistent. Use EINVAL for too many SGEs and ENOMEM for too many\nWRs.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "14de986a0ba560b54340fd277a3579e95a2d3838", "tree": "853ca35f6c93dfc940cc359009cb315dbb28084e", "parents": [ "8a278e6d571ebe10b96f2b53c74f01fd0a3f005a" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Fri Nov 09 15:22:31 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Nov 20 11:04:41 2007 -0800" }, "message": "IB/ipath: Fix offset returned to ibv_modify_srq()\n\nThe wrong offset was being returned to libipathverbs so that when\nibv_modify_srq() calls mmap(), it always fails.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "8a278e6d571ebe10b96f2b53c74f01fd0a3f005a", "tree": "3d6ced2d41c7aa6d0db91e1141b943f202a93c64", "parents": [ "fb74dacb0f00dff851c78411773a5bd5d7128b81" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Wed Nov 14 12:09:05 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Nov 20 11:04:10 2007 -0800" }, "message": "IB/ipath: Fix error path in QP creation\n\nThis patch fixes the code which frees the partially allocated QP\nresources if there was an error while creating the QP. In particular,\nthe QPN wasn\u0027t deallocated and the QP wasn\u0027t removed from the hash\ntable.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "fb74dacb0f00dff851c78411773a5bd5d7128b81", "tree": "d16b6e0e9eb8bd95088db9841b7dfad003184883", "parents": [ "2ffbb8377c7a0713baf6644e285adc27a5654582" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Tue Nov 06 17:51:38 2007 -0800" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Nov 20 11:03:26 2007 -0800" }, "message": "IB/ipath: Fix offset returned to ibv_resize_cq()\n\nThe wrong offset was being returned to libipathverbs so that when\nibv_resize_cq() calls mmap(), it always fails.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "9a7666494bac60b99d2bd7d904bd22e8c9b1e3f7", "tree": "a224be9961ef75b43f67d78975df7301bd010a10", "parents": [ "51aaa54eb9e9f01878aa5d62277fd156e458dfe1" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Fri Nov 09 09:21:58 2007 -0600" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Nov 13 15:27:00 2007 -0800" }, "message": "RDMA/cxgb3: Set the max_qp_init_rd_atom attribute in query_device\n\nThe device attribute max_qp_init_rd_atom is not getting set in cxgb3\u0027s\nquery_device method. Version 1.0.4 of librdmacm now validates the\nuser\u0027s requested initiator and responder resources against the max\nsupported by the device. Since iw_cxgb3 wasn\u0027t setting this attribute\n(and it defaulted to 0), all rdma_connect()s fail if there are\ninitiator resources requested by the app. Fix this by setting the\ncorrect value in iwch_query_device().\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "51aaa54eb9e9f01878aa5d62277fd156e458dfe1", "tree": "135d4f2f8ae6543f034e9607ae58fa05b8944451", "parents": [ "40ebb5615e2e069d3b8936b894ceff436c914003" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Fri Nov 02 15:41:49 2007 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Nov 13 15:27:00 2007 -0800" }, "message": "IB/ehca: Fix static rate calculation\n\nThe IPD (inter-packet delay) formula was a little off and assumed a\nfixed physical link rate; fix the formula and query the actual\nphysical link rate, now that we can get it. Also, refactor the\ncalculation into a common function ehca_calc_ipd() and use that\ninstead of duplicating code.\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "40ebb5615e2e069d3b8936b894ceff436c914003", "tree": "23621b411d4921b94633b59408cca64f9ab52d8c", "parents": [ "f4ad1bcc4425a772ea584e1f24abadc64c2b839f" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Fri Nov 02 15:33:51 2007 +0200" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Nov 13 15:26:59 2007 -0800" }, "message": "IB/ehca: Return physical link information in query_port()\n\nNewer firmware versions return physical port information to the\npartition, so hand that information to the consumer if it\u0027s present.\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" } ], "next": "f4ad1bcc4425a772ea584e1f24abadc64c2b839f" }