)]}' { "log": [ { "commit": "c2448278e3be3a43fe0343e138444742af1e99ae", "tree": "f48201f00ebfb03e13c26e92514e9f2d118923e9", "parents": [ "e6b027a398bcfbb8897353a88a2edfcc97fd604d", "5a4f2b675210718aceb4abf41617a3af31bba718" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri May 23 11:11:44 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri May 23 11:11:44 2008 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:\n IB/mad: Fix kernel crash when .process_mad() returns SUCCESS|CONSUMED\n IPoIB: Test for NULL broadcast object in ipiob_mcast_join_finish()\n MAINTAINERS: Add cxgb3 and iw_cxgb3 NIC and iWARP driver entries\n IB/mlx4: Fix creation of kernel QP with max number of send s/g entries\n IB/mthca: Fix max_sge value returned by query_device\n RDMA/cxgb3: Fix uninitialized variable warning in iwch_post_send()\n IB/mlx4: Fix uninitialized-var warning in mlx4_ib_post_send()\n IB/ipath: Fix UC receive completion opcode for RDMA WRITE with immediate\n IB/ipath: Fix printk format for ipath_sdma_status\n" }, { "commit": "5a4f2b675210718aceb4abf41617a3af31bba718", "tree": "e8753ab50b255d53839e7fce70695965406a83c0", "parents": [ "e1d50dce5af77cb6d33555af70e2b8748dd84009" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Fri May 23 10:52:59 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri May 23 10:52:59 2008 -0700" }, "message": "IB/mad: Fix kernel crash when .process_mad() returns SUCCESS|CONSUMED\n\nIf a low-level driver returns IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED,\nhandle_outgoing_dr_smp() doesn\u0027t clean up properly. The fix is to\nkfree the local data and break, rather than falling through. This was\nobserved with the ipath driver, but could happen with any driver.\n\nThis fixes \u003chttps://bugs.openfabrics.org/show_bug.cgi?id\u003d1027\u003e.\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e1d50dce5af77cb6d33555af70e2b8748dd84009", "tree": "2ee7146889f82fa1b4f606fd7962a20433692158", "parents": [ "e5ec3789c16e12a1936a3be7bdda51897a4148b8" ], "author": { "name": "Jack Morgenstein", "email": "jackm@dev.mellanox.co.il", "time": "Tue May 20 15:41:09 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 20 15:41:09 2008 -0700" }, "message": "IPoIB: Test for NULL broadcast object in ipiob_mcast_join_finish()\n\nWe saw a kernel oops in our regression testing when a multicast \"join\nfinish\" occurred just after the interface was -- this is\n\u003chttps://bugs.openfabrics.org/show_bug.cgi?id\u003d1040\u003e. The test\nrandomly causes the HCA physical port to go down then up.\n\nThe cause of this is that ipoib_mcast_join_finish() processing happen\njust after ipoib_mcast_dev_flush() was invoked (in which case the\nbroadcast pointer is NULL). This patch tests for and handles the case\nwhere priv-\u003ebroadcast is NULL.\n\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Jack Morgenstein \u003cjackm@dev.mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "cd155c1c7c9e64df6afb5504d292fef7cb783a4f", "tree": "84981858bf7bbdd2e28b17557168124bc48650c3", "parents": [ "12103dca52e79e23afe2fbcaf3d9e7fc9ceb6b18" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 20 14:00:02 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 20 14:00:02 2008 -0700" }, "message": "IB/mlx4: Fix creation of kernel QP with max number of send s/g entries\n\nWhen creating a kernel QP where the consumer asked for a send queue\nwith lots of scatter/gater entries, set_kernel_sq_size() incorrectly\nreturned an error if the send queue stride is larger than the\nhardware\u0027s maximum send work request descriptor size. This is not a\nproblem; the only issue is to make sure that the actual descriptors\nused do not overflow the maximum descriptor size, so check this instead.\n\nClamp the returned max_send_sge value to be no bigger than what\nquery_device returns for the max_sge to avoid confusing hapless users,\neven if the hardware is capable of handling a few more s/g entries.\n\nThis bug caused NFS/RDMA mounts to fail when the server adapter used\nthe mlx4 driver.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6c06aec2487f7568cf57471a20f422568f25d551", "tree": "91ee5f4128333d7a10d634a209650381bc90ec06", "parents": [ "716ad8750a3ffe6b458d52da2d1c01cbf3e2f60d" ], "author": { "name": "Greg Kroah-Hartman", "email": "gregkh@suse.de", "time": "Fri May 16 17:55:12 2008 -0700" }, "committer": { "name": "Greg Kroah-Hartman", "email": "gregkh@suse.de", "time": "Tue May 20 13:31:55 2008 -0700" }, "message": "IB: fix race in device_create\n\nThere is a race from when a device is created with device_create() and\nthen the drvdata is set with a call to dev_set_drvdata() in which a\nsysfs file could be open, yet the drvdata will be NULL, causing all\nsorts of bad things to happen.\n\nThis patch fixes the problem by using the new function,\ndevice_create_drvdata().\n\nCc: Kay Sievers \u003ckay.sievers@vrfy.org\u003e\nReviewed-by: Roland Dreier \u003crolandd@cisco.com\u003e\nCc: Sean Hefty \u003csean.hefty@intel.com\u003e\nCc: Hal Rosenstock \u003chal.rosenstock@gmail.com\u003e\nSigned-off-by: Greg Kroah-Hartman \u003cgregkh@suse.de\u003e\n\n" }, { "commit": "12103dca52e79e23afe2fbcaf3d9e7fc9ceb6b18", "tree": "91c8f6f489e8e47a926c0bf6337660894b6a2e50", "parents": [ "21609ae3efa42f4118ce741f7e55d66d716cb17c" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri May 16 14:58:44 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri May 16 14:58:44 2008 -0700" }, "message": "IB/mthca: Fix max_sge value returned by query_device\n\nThe mthca driver returns the maximum number of scatter/gather entries\nreturned by the firmware as the max_sge value when device properties\nare queried. However, the firmware also reports a limit on the\nmaximum descriptor size allowed, and because mthca takes into account\nthe worst case send request overhead when checking whether to allow a\nQP to be created, the largest number of scatter/gather entries that\ncan be used with mthca may be limited by the maximum descriptor size\nrather than just by the actual s/g entry limit.\n\nThis means that applications cannot actually create QPs with\nmax_send_sge equal to the limit returned by ib_query_device(). Fix\nthis by checking if the maximum descriptor size imposes a lower limit\nand if so returning that lower limit.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "21609ae3efa42f4118ce741f7e55d66d716cb17c", "tree": "49627d1cfa7090f1f88049ac29ca1462d642d80a", "parents": [ "a3d8e1591dc90d359d444c759dfda2c6fc605251" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri May 16 14:58:40 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri May 16 14:58:40 2008 -0700" }, "message": "RDMA/cxgb3: Fix uninitialized variable warning in iwch_post_send()\n\n drivers/infiniband/hw/cxgb3/iwch_qp.c: In function \u0027iwch_post_send\u0027:\n drivers/infiniband/hw/cxgb3/iwch_qp.c:232: warning: \u0027t3_wr_flit_cnt\u0027 may be used uninitialized in this function\n\nThis is what akpm describes as \"the dopey\ngcc-doesn\u0027t-know-that-foo(\u0026var)-writes-to-var problem.\"\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\nAcked-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\n" }, { "commit": "a3d8e1591dc90d359d444c759dfda2c6fc605251", "tree": "04e77ad79237bffda26206235124df16bf00f962", "parents": [ "df3f0da8db6b5e7e8f0585221c8b1cd8ff806d35" ], "author": { "name": "Andrew Morton", "email": "akpm@linux-foundation.org", "time": "Fri May 16 14:28:30 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri May 16 14:28:30 2008 -0700" }, "message": "IB/mlx4: Fix uninitialized-var warning in mlx4_ib_post_send()\n\n drivers/infiniband/hw/mlx4/qp.c: In function \u0027mlx4_ib_post_send\u0027:\n drivers/infiniband/hw/mlx4/qp.c:1460: warning: \u0027seglen\u0027 may be used uninitialized in this function\n\nThis is the dopey gcc-doesn\u0027t-know-that-foo(\u0026var)-writes-to-var problem.\n\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "df3f0da8db6b5e7e8f0585221c8b1cd8ff806d35", "tree": "0b766d95942d8512daa33f6ce865008cfeff076a", "parents": [ "cd80ec6f81db89d109187a673470c04af4c09a63" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Thu May 15 16:37:25 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu May 15 16:37:25 2008 -0700" }, "message": "IB/ipath: Fix UC receive completion opcode for RDMA WRITE with immediate\n\nWhen I fixed the RC receive completion opcode in 2bfc8e9e (\"IB/ipath:\nReturn the correct opcode for RDMA WRITE with immediate\"), I forgot to\nfix UC, which had the same problem for RDMA write with immediate\nreturning the wrong opcode.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "cd80ec6f81db89d109187a673470c04af4c09a63", "tree": "ca46c8f6d51fd578e8eec366ed7f2638af0ec71a", "parents": [ "7371fd11a6e2aed99895db4f100940fa5022f7fe" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu May 15 15:28:55 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Thu May 15 15:28:55 2008 -0700" }, "message": "IB/ipath: Fix printk format for ipath_sdma_status\n\nCommit f018c7e1 (\"IB/ipath: Change ipath_devdata.ipath_sdma_status to be\nunsigned long\") changed ipath_sdma_status to be unsigned long, but left\na few debug messages that printed it out with a %016llx format, which\ngenerates the warnings\n\n drivers/infiniband/hw/ipath/ipath_sdma.c:348: warning: format \u0027%016llx\u0027 expects type \u0027long long unsigned int\u0027, but argument 3 has type \u0027long unsigned int\u0027\n drivers/infiniband/hw/ipath/ipath_sdma.c:618: warning: format \u0027%016llx\u0027 expects type \u0027long long unsigned int\u0027, but argument 3 has type \u0027long unsigned int\u0027\n\nFix this by changing the format used to print out the value to %08lx\n(8 hex digits are now sufficient, because the highest bit used is 31).\n\nWarnings reported by Randy Dunlap \u003crandy.dunlap@oracle.com\u003e.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "a58e58fafdff4c25949221e46132e86f709d0b79", "tree": "09ee58e05c6600d6ecb4c195357678afff5aea5e", "parents": [ "f018c7e177a50390f6fcb137f1a28a6027d8ba50" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Tue May 13 11:52:55 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 13 11:52:55 2008 -0700" }, "message": "RDMA/cxgb3: Wrap the software send queue pointer as needed on flush\n\ncxio_flush_sq() was failing to wrap around the software send queue\ncausing garbage completion entries on a flush operation.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f018c7e177a50390f6fcb137f1a28a6027d8ba50", "tree": "32edc8dfbb31acc027711f88a16c34d3fc69be15", "parents": [ "40d97692fbfe52ef68fa771d8121394b2210fd67" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 13 11:51:23 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 13 11:51:23 2008 -0700" }, "message": "IB/ipath: Change ipath_devdata.ipath_sdma_status to be unsigned long\n\nAndrew Morton \u003cakpm@linux-foundation.org\u003e pointed out that bitops\nshould take an unsigned long * arg. However, the ipath driver was\ndoing bitops on struct ipath_devdata.ipath_sdma_status, which is u64.\nChange this member to unsigned long to avoid tons of warnings when x86\nfixes the bitops to take unsigned long * instead of void *.\n\nAlso, change the IPATH_SDMA_RUNNING and IPATH_SDMA_SHUTDOWN bit\nnumbers to 30 and 31 (instead of 62 and 63) so that we\u0027re not setting\nanother booby trap for someone who tries to make ipath work on a\n32-bit architecture.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "40d97692fbfe52ef68fa771d8121394b2210fd67", "tree": "a9caaf61f737308b1a34e1a07914ba45d02bb434", "parents": [ "74116f580b7279543340dd716a2af642f5c1c2c7" ], "author": { "name": "Pavel Emelyanov", "email": "xemul@openvz.org", "time": "Tue May 13 11:45:32 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 13 11:45:32 2008 -0700" }, "message": "IB/ipath: Make ipath_portdata work with struct pid * not pid_t\n\nThe official reason is \"with the presence of pid namespaces in the\nkernel using pid_t-s inside one is no longer safe.\"\n\nBut the reason I fix this right now is the following:\n\nAbout a month ago (when 2.6.25 was not yet released) there still was a\none last caller of a to-be-deprecated-soon function find_pid() - the\nkill_proc() function, which in turn was only used by nfs callback\ncode.\n\nDuring the last merge window, this last caller was finally eliminated\nby some NFS patch(es) and I was about to finally kill this kill_proc()\nand find_pid(), but found, that I was late and the kill_proc is now\ncalled from the ipath driver since commit 58411d1c (\"IB/ipath: Head of\nLine blocking vs forward progress of user apps\").\n\nSo here\u0027s a patch that fixes this code to use struct pid * and (!)\nthe kill_pid routine.\n\nSigned-off-by: Pavel Emelyanov \u003cxemul@openvz.org\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "74116f580b7279543340dd716a2af642f5c1c2c7", "tree": "3c667c606001ee9d053305180ba8d465a5fe587c", "parents": [ "e509be898d8937634437caa474b57ac12795e5bc" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Tue May 13 11:42:20 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 13 11:42:20 2008 -0700" }, "message": "IB/ipath: Fix RDMA read response sequence checking\n\nIf an out of sequence RDMA read response middle or last packet is\nreceived, we should only resend the RDMA read request on the first\nout of sequence packet and drop subsequent out of sequence packets\notherwise, we get \"too many retries\".\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e509be898d8937634437caa474b57ac12795e5bc", "tree": "f99b0e3965ee0eaf89acccdba382689719881a29", "parents": [ "53dc1ca194c062aa9771e194047f27ec1ca592df" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Tue May 13 11:41:29 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 13 11:41:29 2008 -0700" }, "message": "IB/ipath: Fix many locking issues when switching to error state\n\nThe send DMA hardware queue voided a number of prior assumptions about\nwhen a send is complete which led to completions being generated out of\norder. There were also a number of locking issues when switching the QP\nto the error or reset states, and we implement the IB_QPS_SQD state.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "53dc1ca194c062aa9771e194047f27ec1ca592df", "tree": "4cf0fe73ea76f02f871d5e6def040a869b224f00", "parents": [ "dd37818dbdf8e51d0288c0197c351c005ffcdbdb" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Tue May 13 11:40:25 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 13 11:40:25 2008 -0700" }, "message": "IB/ipath: Fix RC and UC error handling\n\nWhen errors are detected in RC, the QP should transition to the\nIB_QPS_ERR state, not the IB_QPS_SQE state. Also, when the error is on\nthe responder side, the receive work completion error was incorrect\n(remote vs. local).\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "dd37818dbdf8e51d0288c0197c351c005ffcdbdb", "tree": "c7b220d8f17fd574d3b746082c4882148e2dff70", "parents": [ "c714a534d85576af21b06be605ca55cb2fb887ee" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 13 11:27:25 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 13 11:27:25 2008 -0700" }, "message": "RDMA/nes: Fix up nes_lro_max_aggr module parameter\n\nFix some bugs with the max_aggr module parameter added with LRO support:\n\n - The module parameter value ignored and not actually used to set\n lro_mgr.max_aggr.\n - MODULE_PARM_DESC had a typo \"_mro_\" instead of \"_lro_\" so it didn\u0027t\n end up describing the actual module parameter.\n - The nes_lro_max_aggr variable was declared as unsigned, but the\n module_param line said \"int\" instead of \"uint\" for the type.\n - The default value for the parameter was stuck in the permissions\n field of module_param, which led to nonsensical permissions for the\n file under /sys/module/iw_nes/param.\n - The parameter was used in only one file but defined in another, which\n led to the variable being global for no good reason. Move everything\n related to the parameter to the file nes_hw.c where it is actually\n used.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "12137c593d127c6c1a3eb050674da047682badaf", "tree": "f615c55e363b550c7489aa0aceeb8d62c201fcad", "parents": [ "ab69b3cf1219e0d07bb4ea373f36b1de38af531c" ], "author": { "name": "Stefan Roscher", "email": "ossrosch@linux.vnet.ibm.com", "time": "Wed May 07 11:35:06 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed May 07 11:35:06 2008 -0700" }, "message": "IB/ehca: Wait for async events to finish before destroying QP\n\nThis is necessary because, in a multicore environment, a race between\nuverbs async handler and destroy QP could occur.\n\nSigned-off-by: Stefan Roscher \u003cstefan.roscher at de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "ab69b3cf1219e0d07bb4ea373f36b1de38af531c", "tree": "cad988230450defcdc2d598fd70b6f4ed89df044", "parents": [ "e2ab41cae418108f376ad1634d7507f56379f7a2" ], "author": { "name": "John Gregor", "email": "john.gregor@qlogic.com", "time": "Wed May 07 11:01:10 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed May 07 11:01:10 2008 -0700" }, "message": "IB/ipath: Fix SDMA error recovery in absence of link status change\n\nWhat\u0027s fixed:\n\n in ipath_cancel_sends()\n\n We need to unconditionally set ABORTING. So, swap the tests\n so the set_bit() isn\u0027t shadowed by the \u0026\u0026.\n\n If we\u0027ve disarmed the piobufs, then we need to unconditionally\n set DISARMED. So, move it out from the overly protective if\n at the bottom.\n\n in sdma_abort_task()\n\n Abort_task was written knowing that the SDMA engine would always\n be reset (and restarted) on error. A recent change broke that\n fundamental assumption by taking the restart portion and making\n it conditional on a link status change. But, SDMA can go boom\n without a link status change in some conditions.\n\nSigned-off-by: John Gregor \u003cjohn.gregor@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e2ab41cae418108f376ad1634d7507f56379f7a2", "tree": "c14355ab189f36f02b56f1dd293d49f1fc056730", "parents": [ "2889d1ef1240591fa4c72a6753e0a8d1c6e18140" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Wed May 07 11:00:15 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed May 07 11:00:15 2008 -0700" }, "message": "IB/ipath: Need to always request and handle PIO avail interrupts\n\nNow that we always use PIO for vl15 on 7220, we could get stuck forever\nif we happened to run out of PIO buffers from the verbs code, because\nthe setup code wouldn\u0027t run; the interrupt was also ignored if SDMA was\nsupported. We also have to reduce the pio update threshold if we have\nfewer kernel buffers than the existing threshold.\n\nClean up the initialization a bit to get ordering safer and more\nsensible, and use the existing ipath_chg_kernavail call to do init,\nrather than doing it separately.\n\nDrop unnecessary clearing of pio buffer on pio parity error.\n\nDrop incorrect updating of pioavailshadow when exitting freeze mode\n(software state may not match chip state if buffer has been allocated\nand not yet written).\n\nIf we couldn\u0027t get a kernel buffer for a while, make sure we are\nin sync with hardware, mainly to handle the exitting freeze case.\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2889d1ef1240591fa4c72a6753e0a8d1c6e18140", "tree": "6540619947039fb63723fcbe69de0311bb77e9ce", "parents": [ "2bfc8e9edf200aeeca18ee44bcbf6bce65438a42" ], "author": { "name": "Michael Albaugh", "email": "Michael.Albaugh@Qlogic.com", "time": "Wed May 07 10:59:23 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed May 07 10:59:23 2008 -0700" }, "message": "IB/ipath: Fix count of packets received by kernel\n\nThe loop in ipath_kreceive() that processes packets increments the\nloop-index \u0027i\u0027 once too often, because the exit condition does not\ndepend on it, and is checked after the increment. By adding a check for\n!last to the iterator in the for loop, we correct that in a way that is\nnot so likely to be re-broken by changes in the loop body.\n\nSigned-off-by: Michael Albaugh \u003cmicheal.albaugh@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2bfc8e9edf200aeeca18ee44bcbf6bce65438a42", "tree": "2351a3c58ffeb2d3e8dcae988118deaa1bab1ee6", "parents": [ "b4d390d8d219452e5d4257c87134a6934d7fabeb" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Wed May 07 10:58:50 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed May 07 10:58:50 2008 -0700" }, "message": "IB/ipath: Return the correct opcode for RDMA WRITE with immediate\n\nThis patch fixes a bug in the RC responder which generates a completion\nentry with the wrong opcode when an RDMA WRITE with immediate is received.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "b4d390d8d219452e5d4257c87134a6934d7fabeb", "tree": "4d477e59d5e7540884b7740187f671b6fce2956a", "parents": [ "6e87d1500713767866db0668bbcec75719576f3c" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Wed May 07 10:57:48 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed May 07 10:57:48 2008 -0700" }, "message": "IB/ipath: Fix bug that can leave sends disabled after freeze recovery\n\nThe semantics of cancel_sends changed, but the code using it was missed.\nDon\u0027t leave sends and pioavail updates disabled, and add a comment as to\nwhy the force update is needed.\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6e87d1500713767866db0668bbcec75719576f3c", "tree": "f6924986ad4ff70ec9aaee7e26d82663bcb4276c", "parents": [ "5f51efc195dfb860c60fafb4e47fe4b7cad2626d" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Wed May 07 10:57:14 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed May 07 10:57:14 2008 -0700" }, "message": "IB/ipath: Only increment SSN if WQE is put on send queue\n\nIf a send work request has immediate errors and is not put on the\nsend queue, we shouldn\u0027t update any of the QP state.\n\nThe increment of the SSN wasn\u0027t obeying this.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "5f51efc195dfb860c60fafb4e47fe4b7cad2626d", "tree": "72efa481bbe7e3952920626c025df4444e053fe2", "parents": [ "273748cc908a901d082b4da5a16b2541c9d78a02" ], "author": { "name": "Michael Albaugh", "email": "Michael.Albaugh@Qlogic.com", "time": "Wed May 07 10:56:47 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed May 07 10:56:47 2008 -0700" }, "message": "IB/ipath: Only warn about prototype chip during init\n\nWe warn about prototype chips, but the function that checks for\nsupport is also called as a result of a get_portinfo request, which\ncan clutter the logs.\n\nRestrict warning to only appear during initialization.\n\nSigned-off-by: Michael Albaugh \u003cmichael.albaugh@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "273748cc908a901d082b4da5a16b2541c9d78a02", "tree": "b573f1f3f583acf2309a10e86f99a1842a8ccdc5", "parents": [ "0e9913362a967377eb886bbdf305ec58aa07a878" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 06 15:56:22 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 06 15:56:22 2008 -0700" }, "message": "RDMA/cxgb3: Fix severe limit on userspace memory registration size\n\nCurrently, iw_cxgb3 is severely limited on the amount of userspace\nmemory that can be registered in in a single memory region, which\ncauses big problems for applications that expect to be able to\nregister 100s of MB.\n\nThe problem is that the driver uses a single kmalloc()ed buffer to\nhold the physical buffer list (PBL) for the entire memory region\nduring registration, which means that 8 bytes of contiguous memory are\nrequired for each page of memory being registered. For example, a 64\nMB registration will require 128 KB of contiguous memory with 4 KB\npages, and it unlikely that such an allocation will succeed on a busy\nsystem.\n\nThis is purely a driver problem: the temporary page list buffer is not\nneeded by the hardware, so we can fix this by writing the PBL to the\nhardware in page-sized chunks rather than all at once. We do this by\nsplitting the memory registration operation up into several steps:\n\n - Allocate PBL space in adapter memory for the full registration\n - Copy PBL to adapter memory in chunks\n - Allocate STag and enable memory region\n\nThis also allows several other cleanups to the __cxio_tpt_op()\ninterface and related parts of the driver.\n\nThis change leaves the reregister memory region and memory window\noperations broken, but they already didn\u0027t work due to other\nlongstanding bugs, so fixing them will be left to a later patch.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "0e9913362a967377eb886bbdf305ec58aa07a878", "tree": "4677a588e942eb198c9cdb15338bcbcfb51f6902", "parents": [ "a15306365a16380f3bafee9e181ba01231d4acd7" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 06 15:03:38 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue May 06 15:03:38 2008 -0700" }, "message": "RDMA/cxgb3: Don\u0027t add PBL memory to gen_pool in chunks\n\nCurrent iw_cxgb3 code adds PBL memory to the driver\u0027s gen_pool in 2 MB\nchunks. This limits the largest single allocation that can be done to\nthe same size, which means that with 4 KB pages, each of which takes 8\nbytes of PBL memory, the largest memory region that can be allocated\nis 1 GB (256K PBL entries * 4 KB/entry).\n\nRemove this limit by adding all the PBL memory in a single gen_pool\nchunk, if possible. Add code that falls back to smaller chunks if\ngen_pool_add() fails, which can happen if there is not sufficient\ncontiguous lowmem for the internal gen_pool bitmap.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "cf04690885972eaba830ee761de545a6956197e6", "tree": "32b90005c3e7966672a4a473b1b7db12f4c4947e", "parents": [ "77a8d5741f3ee2c79554382179cca7b5893d6ae9" ], "author": { "name": "Stefan Roscher", "email": "ossrosch@linux.vnet.ibm.com", "time": "Mon May 05 15:51:49 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon May 05 15:51:49 2008 -0700" }, "message": "IB/ehca: Fix function return types\n\nAlso remove duplicate assignment of local_ca_ack_delay and change\nmin_t check for local_ca_ack_delay to u8 instead of int.\n\nSigned-off-by: Stefan Roscher \u003cstefan.roscher at de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "77a8d5741f3ee2c79554382179cca7b5893d6ae9", "tree": "a823edb4ea3319ebce33c288db970c1d02fbb9d5", "parents": [ "c4d49776e8f5bf2d900d2b6d4855c1670a535ac5" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Fri May 02 10:57:09 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri May 02 10:57:09 2008 -0700" }, "message": "RDMA/cxgb3: Bump up the MPA connection setup timeout.\n\nTesting on large clusters shows its way too short at 10 secs.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "c4d49776e8f5bf2d900d2b6d4855c1670a535ac5", "tree": "5e2f8d8dfc839436c3e5a07adbb3e1a861909e01", "parents": [ "c8286944b802c5ce4063ec3c334b38c6757a9434" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Fri May 02 10:57:09 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri May 02 10:57:09 2008 -0700" }, "message": "RDMA/cxgb3: Silently ignore close reply after abort.\n\nRemove bad BUG_ON() that can trigger in correct operation from\nclose_con_rpl(). It is possible to get a close_rpl message on a dead\nconnection. The sequence is:\n\n\t- host refs ep for close exchange\n\t- host posts close_req\n\t- hw posts PEER_ABORT from incoming RST\n\t- host marks ep DEAD\n\t- host posts ABORT_RPL and releases ep resources\n\t- hw posts CLOSE_RPL\n\t- host derefs ep and ep freed.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "c8286944b802c5ce4063ec3c334b38c6757a9434", "tree": "f1cbf7c3baa83cc2e4e92ad43cf5083cd956ad32", "parents": [ "57ce41d1d18279cc90223f3deadca70c7de1cfca" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Fri May 02 11:17:41 2008 -0500" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Fri May 02 10:56:57 2008 -0700" }, "message": "RDMA/cxgb3: QP flush fixes\n\n- Flush the QP only after the HW disables the connection. Currently\n we flush the QP when transitioning to CLOSING. This exposes a race\n condition where the HW can complete a RECV WR, for instance, -and-\n the SW can flush that same WR.\n\n- Only call CQ event handlers on flush IFF we actually flushed something.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "57ce41d1d18279cc90223f3deadca70c7de1cfca", "tree": "39111403527e4744b4a6a15d5ffe3fd038751489", "parents": [ "3ae15e1623b9d32eb410c2a23d90e47b16e6acd0" ], "author": { "name": "Eli Cohen", "email": "eli@dev.mellanox.co.il", "time": "Wed Apr 30 20:02:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 30 20:02:45 2008 -0700" }, "message": "IB/ipoib: Fix transmit queue stalling forever\n\nCommit f56bcd80 (\"IPoIB: Use separate CQ for UD send completions\")\nintroduced a bug where the transmit queue could get stopped and never\nwoken up. The problem is that send completions are only polled at the\nend of the xmit function, so if the send queue fills up and the xmit\npath stops the queue, then there is no way for send completions to\never get polled, and so the transmit queue stays stopped forever.\n\nFix this by arming the send CQ just before posting the last send\nrequest that fills the send queue. Then, when the completion event\nhandler is called, drain the send CQ. Since it is possible that not\nenough send completions are in the CQ, verify that the the net queue\nhas been woken up after draining the send CQ, and if not arm a timer\nand drain again at the timer function.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "3ae15e1623b9d32eb410c2a23d90e47b16e6acd0", "tree": "b1138d36523cc8f0f5b3fae12f81f573eae96997", "parents": [ "c65a3500b2947d344862da8cce626b7cc7ec5758" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 30 19:52:55 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 30 19:52:55 2008 -0700" }, "message": "IB/mlx4: Fix off-by-one errors in calls to mlx4_ib_free_cq_buf()\n\nWhen I merged bbf8eed1 (\"IB/mlx4: Add support for resizing CQs\") I\nchanged things around so that mlx4_ib_alloc_cq_buf() and\nmlx4_ib_free_cq_buf() were used everywhere they could be. However, I\nscrewed up the number of entries passed into mlx4_ib_alloc_cq_buf()\nin a couple places -- the function bumps the number of entries\ninternally, so the caller shouldn\u0027t add 1 as well.\n\nPassing a too-big value for the number of entries to mlx4_ib_free_cq_buf()\ncan cause the cleanup to go off the end of an array and corrupt\nallocator state in interesting ways.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7495ab6837ea4660f5e14ad49e5bfc558d6862e7", "tree": "2065081d5cd5285997eee480c5f092e831ca4e35", "parents": [ "0e1de5d62e751ca9c589d8dfabfc1e5074e62724" ], "author": { "name": "Glenn Streiff", "email": "gstreiff@neteffect.com", "time": "Tue Apr 29 13:46:54 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:54 2008 -0700" }, "message": "RDMA/nes: Formatting cleanup\n\nVarious cleanups:\n\t- Change // to /* .. */\n\t- Place whitespace around binary operators.\n\t- Trim down a few long lines.\n\t- Some minor alignment formatting for better readability.\n\t- Remove some silly tabs.\n\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "0e1de5d62e751ca9c589d8dfabfc1e5074e62724", "tree": "164536558179b7741fe2659f11c19b26a3f185a7", "parents": [ "37dab4112d7b53c3574426ef7bdd92a78d32ac3e" ], "author": { "name": "Eric Schneider", "email": "eric.schneider@neteffect.com", "time": "Tue Apr 29 13:46:54 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:54 2008 -0700" }, "message": "RDMA/nes: Add support for SFP+ PHY\n\nThis patch enables the iw_nes module for NetEffect RNICs to support\nadditional PHYs including SFP+ (referred to as ARGUS in the code).\n\nSigned-off-by: Eric Schneider \u003ceric.schneider@neteffect.com\u003e\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "37dab4112d7b53c3574426ef7bdd92a78d32ac3e", "tree": "c6d8e9e04a35baa6a0669281a923c4aa07542c7e", "parents": [ "b4132efa1a47858d741ecb05b8735e6fcb603bc8" ], "author": { "name": "Faisal Latif", "email": "flatif@neteffect.com", "time": "Tue Apr 29 13:46:54 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:54 2008 -0700" }, "message": "RDMA/nes: Use LRO\n\nSigned-off-by: Faisal Latif \u003cflatif@neteffect.com.\nSigned-off-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "b4132efa1a47858d741ecb05b8735e6fcb603bc8", "tree": "7345487035fb8725d5f6d3edeaf23839eef1da7e", "parents": [ "baaad380c0aa955f7d62e846467316c94067f1a5" ], "author": { "name": "Eli Cohen", "email": "eli@dev.mellanox.co.il", "time": "Tue Apr 29 13:46:53 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:53 2008 -0700" }, "message": "IPoIB: Copy child MTU from parent\n\nWhen creating a child interface, copy the MTU information from the\nparent. Otherwise when the child\u0027s multicast join completes, the MTU\nwill not be updated since the code does\n\n\tdev-\u003emtu \u003d min(priv-\u003emcast_mtu, priv-\u003eadmin_mtu);\n\nand priv-\u003eadmin_mtu will be set to 0.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "baaad380c0aa955f7d62e846467316c94067f1a5", "tree": "12c85eebd88793ddf7cb0643063ff93c8755dfae", "parents": [ "0bfe151cc4049f3f304adf28b37ea5437d02ad96" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:53 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:53 2008 -0700" }, "message": "IB/mthca: Avoid changing userspace ABI to handle DMA write barrier attribute\n\nCommit cb9fbc5c (\"IB: expand ib_umem_get() prototype\") changed the\nmthca userspace ABI to provide a way for userspace to indicate which\nmemory regions need the DMA write barrier attribute. However, it is\npossible to handle this without breaking existing userspace, by having\nthe mthca kernel driver recognize whether it is talking to old or new\nuserspace, depending on the size of the register MR structure passed in.\n\nThe only potential drawback of this is that is allows old userspace\n(which has a bug with DMA ordering on large SGI Altix systems) to\ncontinue to run on new kernels, but the advantage of allowing old\nuserspace to continue to work on unaffected systems seems to outweigh\nthis, and we can print a warning to push people to upgrade their\nuserspace.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "0bfe151cc4049f3f304adf28b37ea5437d02ad96", "tree": "4e67ca79ec441896bd9cfde98268eb287987989e", "parents": [ "bbdc2821db041fb07ffa52e4a0e1ebb5410790e9" ], "author": { "name": "Olaf Kirch", "email": "okir@lst.de", "time": "Tue Apr 29 13:46:53 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:53 2008 -0700" }, "message": "IB/mthca: Avoid recycling old FMR R_Keys too soon\n\nWhen a FMR is unmapped, mthca resets the map count to 0, and clears\nthe upper part of the R_Key which is used as the sequence counter.\n\nThis poses a problem for RDS, which uses ib_fmr_unmap as a fence\noperation. RDS assumes that after issuing an unmap, the old R_Keys\nwill be invalid for a \"reasonable\" period of time. For instance,\nOracle processes uses shared memory buffers allocated from a pool of\nbuffers. When a process dies, we want to reclaim these buffers -- but\nwe must make sure there are no pending RDMA operations to/from those\nbuffers. The only way to achieve that is by using unmap and sync the\nTPT.\n\nHowever, when the sequence count is reset on unmap, there is a high\nlikelihood that a new mapping will be given the same R_Key that was\nissued a few milliseconds ago.\n\nTo prevent this, don\u0027t reset the sequence count when unmapping a FMR.\n\nSigned-off-by: Olaf Kirch \u003colaf.kirch@oracle.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d227fa7288adebe5ba37fa8e4a589c977d4e4a34", "tree": "8e0f080fc78f0342b5fd2531615ea525333d8d25", "parents": [ "f56bcd8013566d4ad4759ae5fc85a6660e4655c7" ], "author": { "name": "Stefan Roscher", "email": "ossrosch@linux.vnet.ibm.com", "time": "Tue Apr 29 13:46:53 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:53 2008 -0700" }, "message": "IB/ehca: Allocate event queue size depending on max number of CQs and QPs\n\nIf a lot of QPs fall into Error state at once and the EQ of the\nrespective HCA is too small, it might overrun, causing the eHCA driver\nto stop processing completion events and calling the application\u0027s\ncompletion handlers, effectively causing traffic to stop.\n\nFix this by limiting available QPs and CQs to a customizable max\ncount, and determining EQ size based on these counts and a worst-case\nassumption.\n\nSigned-off-by: Stefan Roscher \u003cstefan.roscher@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f56bcd8013566d4ad4759ae5fc85a6660e4655c7", "tree": "58b7e23f81caf5e6d8ada5819170f0bfb783d7e3", "parents": [ "87528227dfa8776d12779d073c217f0835fd6d20" ], "author": { "name": "Eli Cohen", "email": "eli@dev.mellanox.co.il", "time": "Tue Apr 29 13:46:53 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:53 2008 -0700" }, "message": "IPoIB: Use separate CQ for UD send completions\n\nUse a dedicated CQ for UD send completions. Also, do not arm the UD\nsend CQ, which reduces the number of interrupts generated. This patch\nfarther reduces overhead by not calling poll CQ for every posted send\nWR -- it does polls only when there 16 or more outstanding work requests.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "87528227dfa8776d12779d073c217f0835fd6d20", "tree": "b81e95f35826bc266fef2f425bee225f4b347a02", "parents": [ "6f735e36bad6fa4949271b3c3d0f331aad812313" ], "author": { "name": "Eli Dorfman", "email": "dorfman.eli@gmail.com", "time": "Tue Apr 29 13:46:52 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:52 2008 -0700" }, "message": "IB/iser: Count FMR alignment violations per session\n\nCount FMR alignment violations per session as part of the iscsi\nstatistics.\n\nSigned-off-by: Eli Dorfman \u003celid@voltaire.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6f735e36bad6fa4949271b3c3d0f331aad812313", "tree": "eff436b7e4126b28a59dd7cc9c71e1fca783ce66", "parents": [ "7df109d917e85d3da2e25bd495c4997e87ed2a4e" ], "author": { "name": "Eli Dorfman", "email": "dorfman.eli@gmail.com", "time": "Tue Apr 29 13:46:52 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:52 2008 -0700" }, "message": "IB/iser: Move high-volume debug output to higher debug level\n\nAdd another level for debug.\n\nSigned-off-by: Eli Dorfman \u003celid@voltaire.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "7df109d917e85d3da2e25bd495c4997e87ed2a4e", "tree": "6eac844aee0badb05ac40dbfe1b3fe142e9d9f09", "parents": [ "f8b0dfd15277974b5c9f3ff17f9e3ab6fdbe45ee" ], "author": { "name": "Hoang-Nam Nguyen", "email": "hnguyen@linux.vnet.ibm.com", "time": "Tue Apr 29 13:46:52 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:52 2008 -0700" }, "message": "IB/ehca: handle negative return value from ibmebus_request_irq() properly\n\nehca_create_eq() was assigning a signed return value to an unsiged\nlocal variable and then checking if the variable was \u003c 0, which meant\nthat errors were always ignored. Fix this by using one variable for\nsigned integer return values and another for u64 hcall return values.\n\nBug originally found by Roel Kluin \u003c12o3l@tiscali.nl\u003e.\n\nSigned-off-by: Hoang-Nam Nguyen \u003chnguyen@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f8b0dfd15277974b5c9f3ff17f9e3ab6fdbe45ee", "tree": "34e393cd342578f9ff223be2b631af7ab9b418aa", "parents": [ "ccaf10d0ad17bf755750160ebe594de7261a893e" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Tue Apr 29 13:46:52 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:52 2008 -0700" }, "message": "RDMA/cxgb3: Support peer-2-peer connection setup\n\nOpen MPI, Intel MPI and other applications don\u0027t respect the iWARP\nrequirement that the client (active) side of the connection send the\nfirst RDMA message. This class of application connection setup is\ncalled peer-to-peer. Typically once the connection is setup, _both_\nsides want to send data.\n\nThis patch enables supporting peer-to-peer over the chelsio RNIC by\nenforcing this iWARP requirement in the driver itself as part of RDMA\nconnection setup.\n\nConnection setup is extended, when the peer2peer module option is 1,\nsuch that the MPA initiator will send a 0B Read (the RTR) just after\nconnection setup. The MPA responder will suspend SQ processing until\nthe RTR message is received and reply-to.\n\nIn the longer term, this will be handled in a standardized way by\nenhancing the MPA negotiation so peers can indicate whether they\nwant/need the RTR and what type of RTR (0B read, 0B write, or 0B send)\nshould be sent. This will be done by standardizing a few bits of the\nprivate data in order to negotiate all this. However this patch\nenables peer-to-peer applications now and allows most of the required\nfirmware and driver changes to be done and tested now.\n\nDesign:\n\n - Add a module option, peer2peer, to enable this mode.\n\n - New firmware support for peer-to-peer mode:\n\n\t- a new bit in the rdma_init WR to tell it to do peer-2-peer\n\t and what form of RTR message to send or expect.\n\n\t- process _all_ preposted recvs before moving the connection\n\t into rdma mode.\n\n\t- passive side: defer completing the rdma_init WR until all\n\t pre-posted recvs are processed. Suspend SQ processing until\n\t the RTR is received.\n\n\t- active side: expect and process the 0B read WR on offload TX\n\t queue. Defer completing the rdma_init WR until all\n\t pre-posted recvs are processed. Suspend SQ processing until\n\t the 0B read WR is processed from the offload TX queue.\n\n - If peer2peer is set, driver posts 0B read request on offload TX\n queue just after posting the rdma_init WR to the offload TX queue.\n\n - Add CQ poll logic to ignore unsolicitied read responses.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "ccaf10d0ad17bf755750160ebe594de7261a893e", "tree": "74c49b7d303cac5b7a25afd6cfb7859cc379ec68", "parents": [ "989a1780698c65dfe093a6aa89ceeff84c31f528" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Tue Apr 29 13:46:52 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:52 2008 -0700" }, "message": "RDMA/cxgb3: Set the max_mr_size device attribute correctly\n\ncxgb3 only supports 4GB memory regions. The lustre RDMA code uses\nthis attribute and currently has to code around our bad setting.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "989a1780698c65dfe093a6aa89ceeff84c31f528", "tree": "9fe0ca81bfbdbc9f7618fc6b09c1c0c9e3234057", "parents": [ "e463c7b197dbe64b8a99b0612c65f286937e5bf1" ], "author": { "name": "Steve Wise", "email": "swise@opengridcomputing.com", "time": "Tue Apr 29 13:46:51 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:51 2008 -0700" }, "message": "RDMA/cxgb3: Correctly serialize peer abort path\n\nOpen MPI and other stress testing exposed a few bad bugs in handling\naborts in the middle of a normal close. Fix these by:\n\n - serializing abort reply and peer abort processing with disconnect\n processing\n\n - warning (and ignoring) if ep timer is stopped when it wasn\u0027t running\n\n - cleaning up disconnect path to correctly deal with aborting and\n dead endpoints\n\n - in iwch_modify_qp(), taking a ref on the ep before releasing the qp\n lock if iwch_ep_disconnect() will be called. The ref is dropped\n after calling disconnect.\n\nSigned-off-by: Steve Wise \u003cswise@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e463c7b197dbe64b8a99b0612c65f286937e5bf1", "tree": "aadd360d04b9cdf7eaf7d4eed1f79bd29a3b12df", "parents": [ "7663c1e2792a9662b23dec6e19bfcd3d55360b8f" ], "author": { "name": "Yevgeny Petrilin", "email": "yevgenyp@mellanox.co.il", "time": "Tue Apr 29 13:46:50 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Tue Apr 29 13:46:50 2008 -0700" }, "message": "mlx4_core: Add a way to set the \"collapsed\" CQ flag\n\nExtend the mlx4_cq_resize() API with a way to set the \"collapsed\" flag\nfor the CQ being created.\n\nSigned-off-by: Yevgeny Petrilin \u003cyevgenyp@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "cb9fbc5c37b69ac584e61d449cfd590f5ae1f90d", "tree": "3079752ba33535a21db08bed1390aca9136fadfe", "parents": [ "309df0c503c35fbb5a09537fcbb1f4967b9ca489" ], "author": { "name": "Arthur Kepner", "email": "akepner@sgi.com", "time": "Tue Apr 29 01:00:34 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Apr 29 08:06:12 2008 -0700" }, "message": "IB: expand ib_umem_get() prototype\n\nAdd a new parameter, dmasync, to the ib_umem_get() prototype. Use dmasync \u003d 1\nwhen mapping user-allocated CQs with ib_umem_get().\n\nSigned-off-by: Arthur Kepner \u003cakepner@sgi.com\u003e\nCc: Tony Luck \u003ctony.luck@intel.com\u003e\nCc: Jesse Barnes \u003cjbarnes@virtuousgeek.org\u003e\nCc: Jes Sorensen \u003cjes@sgi.com\u003e\nCc: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nCc: Roland Dreier \u003crdreier@cisco.com\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nCc: David Miller \u003cdavem@davemloft.net\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Grant Grundler \u003cgrundler@parisc-linux.org\u003e\nCc: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "31d1e340f0e8d53804d737571b2f2bb28a74ecc5", "tree": "4a6c6c4dc67950e4218fded511b939e148f857d1", "parents": [ "f5b3a096b138940f283907debe9bde6c6f40ebf3" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "message": "RDMA/nes: Remove volatile qualifier from struct nes_hw_cq.cq_vbase\n\nRemove the volatile qualifier from the cq_vbase member of struct\nnes_hw_cq, and add an rmb() in the one place where it looks like\naccess order might make a difference. As usual, removing a volatile\nqualifier in a declaration is actually a bug fix, since a volatile\nqualifier is not sufficient to make sure that aggressively\nout-of-order CPUs don\u0027t reorder things and cause incorrect results.\n\nFor example, a CPU might speculatively execute reads of other cqe\nfields before the NIC hardware has written those fields and before it\nhas set the NES_CQE_VALID bit (even though those reads come after the\ntest of the NES_CQE_VALID bit in program order), but then when the CPU\nactually executes the conditional test of the NES_CQE_VALID, the bit\nhas been set, and the CPU will proceed with the results of the earlier\nspeculative execution and end up using bogus data.\n\nThis also gets rid of the warning:\n\n drivers/infiniband/hw/nes/nes_verbs.c: In function \u0027nes_destroy_cq\u0027:\n drivers/infiniband/hw/nes/nes_verbs.c:1978: warning: passing argument 3 of \u0027pci_free_consistent\u0027 discards qualifiers from pointer target type\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6296883ca4cd52dafb45f191d24102e28ded38f2", "tree": "341e90a9560d8cf6b498d249a6ac81aeea97dd7b", "parents": [ "14fb05b3497351fbeb514381bcd227d84e115bd9" ], "author": { "name": "Yevgeny Petrilin", "email": "yevgenyp@mellanox.co.il", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "message": "mlx4_core: Move kernel doorbell management into core\n\nIn addition to mlx4_ib, there will be ethernet and FC consumers of\nmlx4_core, so move the code for managing kernel doorbells into the\ncore module to avoid having to duplicate this multiple times.\n\nSigned-off-by: Yevgeny Petrilin \u003cyevgenyp@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "14fb05b3497351fbeb514381bcd227d84e115bd9", "tree": "06209333b10b7248fd0433316fb870517e5aafb4", "parents": [ "0455e36d81db76f5f4acb68a820da43adfa7ccec" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "message": "IB/ehca: Bump version number to 0026\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "0455e36d81db76f5f4acb68a820da43adfa7ccec", "tree": "90681c9064b6ababcd7ce3fdd59826d5363098fa", "parents": [ "a7607c9b1112b498c3044c9e5bc68fdb4985f93e" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "message": "IB/ehca: Make some module parameters bool, update descriptions\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "a7607c9b1112b498c3044c9e5bc68fdb4985f93e", "tree": "77cc87acd9ed1489d8f436356d0f8ffc3ec2facf", "parents": [ "4da27d6d5b92c8fe4b3a3e5bcf42606d9e4a6fc8" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "message": "IB/ehca: Remove mr_largepage parameter\n\nAlways enable large page support; didn\u0027t seem to cause problems for anyone.\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "4da27d6d5b92c8fe4b3a3e5bcf42606d9e4a6fc8", "tree": "971988a287044db1d26d1cab24ad5e4aeb578ea8", "parents": [ "863fb09fbf1eb74f56ea02184a62165056aa29cb" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "message": "IB/ehca: Move high-volume debug output to higher debug levels\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "863fb09fbf1eb74f56ea02184a62165056aa29cb", "tree": "7fb54dd86320f2fba3a6276f5b2fa0e09efed7a3", "parents": [ "bc7b3a36ba02e4053ca38653e6a753082d9add03" ], "author": { "name": "Joachim Fenkes", "email": "fenkes@de.ibm.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "message": "IB/ehca: Prevent posting of SQ WQEs if QP not in RTS\n\n...as required by IB Spec, C10-29.\n\nSigned-off-by: Joachim Fenkes \u003cfenkes@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "bc7b3a36ba02e4053ca38653e6a753082d9add03", "tree": "28fe1daa7cab6c7cab71bbc7af22ee6ca7746323", "parents": [ "bc5698f3ecc9587e1edb343a2878f8d228c49e0e" ], "author": { "name": "Shirley Ma", "email": "mashirle@us.ibm.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "message": "IPoIB: Handle 4K IB MTU for UD (datagram) mode\n\nThis patch enables IPoIB to use 4K UD messages (when the underlying\ndevice and fabrics support a 4K MTU) by using two scatter buffers when\nPAGE_SIZE is less than or equal to thhe HCA IB MTU size. The first\nbuffer is for IPoIB header + GRH header, and the second buffer is the\nIPoIB payload, which is 4K-4.\n\nSigned-off-by: Shirley Ma \u003cxma@us.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "bc5698f3ecc9587e1edb343a2878f8d228c49e0e", "tree": "3f16097356e04c4b023d31ee920e6804fe57ecce", "parents": [ "e447703123d817b3f802c6eb69171d5342c8832e" ], "author": { "name": "Chien Tung", "email": "ctung@neteffect.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:55:45 2008 -0700" }, "message": "RDMA/nes: Fix adapter reset after PXE boot\n\nAfter PXE boot, the iw_nes driver does a full reset to ensure the card\nis in a clean state. However, it doesn\u0027t wait for firmware to\ncomplete its work before issuing a port reset to enable the ports,\nwhich leads to problems bringing up the ports.\n\nThe solution is to wait for firmware to complete its work before\nproceeding with port reset.\n\nThis bug was flagged by Roland Dreier \u003crolandd@cisco.com\u003e.\n\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Chien Tung \u003cctung@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e447703123d817b3f802c6eb69171d5342c8832e", "tree": "2d84835bbd6f4427785772be252c8b34c7d0da4e", "parents": [ "2bd01c5d2ed04838d50548cb7b955505a20ac0bd" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:55:43 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:55:43 2008 -0700" }, "message": "RDMA/nes: Print IPv4 addresses in a readable format\n\nUse NIPQUAD_FMT instead of printing raw 32-bit hex quantities in\ndebugging output.\n\nAcked-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2bd01c5d2ed04838d50548cb7b955505a20ac0bd", "tree": "1e9821dd9178f0a48e54c7aa0781db3b34e7efc4", "parents": [ "807501475fce0ebe68baedf87f202c3e4ee0d12c" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:52:18 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 23 11:52:18 2008 -0700" }, "message": "RDMA/nes: Use print_mac() to format ethernet addresses for printing\n\nRemoving open-coded MAC formats shrinks the source and the generated\ncode too, eg on x86-64:\n\nadd/remove: 0/0 grow/shrink: 0/4 up/down: 0/-103 (-103)\nfunction old new delta\nmake_cm_node 932 912 -20\nnes_netdev_set_mac_address 427 406 -21\nnes_netdev_set_multicast_list 1148 1124 -24\nnes_probe 2349 2311 -38\n\nAcked-by: Glenn Streiff \u003cgstreiff@neteffect.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "bc751fe6fff3ff894784acfed1bed8639b632c09", "tree": "1df7d070d9d0f30e08e58f0446a0b0567e6797cc", "parents": [ "44957572cc198f6fcee9569813722b9ae1bd1679" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 21 18:19:15 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 21 18:19:15 2008 -0700" }, "message": "IB/ipath: Correct capitalization \"IntX\" -\u003e \"INTx\"\n\nMatch what the PCI specification uses.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "44957572cc198f6fcee9569813722b9ae1bd1679", "tree": "7b8b1a739912fe05f5a7d5281a84e07a680c06be", "parents": [ "480f58e6143135680fc1e61ea2dedc72cf3d1f95" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 21 18:19:15 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 21 18:19:15 2008 -0700" }, "message": "IB/ipath: Remove tests of PCI_MSI in ipath_iba7220.c\n\nThe PCI MSI interface is stubbed out properly so that all the\nfunctions just return failure if PCI_MSI\u003dn, so there\u0027s no reason to\nhave \"#ifdef CONFIG_PCI_MSI\" blocks in ipath_iba7220.c.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "480f58e6143135680fc1e61ea2dedc72cf3d1f95", "tree": "2ecc245be8c0085172694e0ccdb61ea5875cf07e", "parents": [ "37a6ab5227d856c175d8f3586050997bb10628d8" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 21 18:19:14 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 21 18:19:14 2008 -0700" }, "message": "IB/ipath: Remove dependency on PCI_MSI || HT_IRQ\n\nBefore IBA7220 support was added, the ipath driver didn\u0027t support any\nhardware unless PCI_MSI and/or HT_IRQ was enabled. However, the\nIBA7220 can generate INTx interrupts, so it makes sense to allow the\ndriver to be build even if PCI_MSI\u003dn and HT_IRQ\u003dn.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "37a6ab5227d856c175d8f3586050997bb10628d8", "tree": "d2eb89714aec9c317ddd2547b7c39c924ce5c344", "parents": [ "88a8317bcd2258e84a41c155590837036d6b80a8" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 21 18:19:14 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 21 18:19:14 2008 -0700" }, "message": "IB/ipath: Build IBA7220 code unconditionally\n\nThe new IBA7220 code added a call to ipath_init_iba7220_funcs() that\nis compiled unconditionally, but only built the IBA7220 code if\nPCI_MSI is enabled. Fix this by building the IBA7220 file\nunconditonally.\n\nThis fixes build breakage when PCI_MSI\u003dn, HT_IRQ\u003dy and\nINFINIBAND_IPATH\u003dy reported by Ingo Molnar \u003cmingo@elte.hu\u003e:\n\n drivers/built-in.o: In function `ipath_init_one\u0027:\n ipath_driver.c:(.devinit.text+0x1e5bc): undefined reference to `ipath_init_iba7220_funcs\u0027\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "88a8317bcd2258e84a41c155590837036d6b80a8", "tree": "87c0c406368a00388f74d5ba648026ec93c76ac4", "parents": [ "9862874d2138135dad9e78f61dbe415a4364945b" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 21 18:19:14 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 21 18:19:14 2008 -0700" }, "message": "IB/ipath: Remove reference to dev-\u003eclass_dev \n \nCommit 124b4dcb (\"IB/ipath: add calls to new 7220 code and enable in \nbuild\") inadvertently added core to set dev-\u003eclass_dev.dev back into \nib_ipath. This is completely redundant since commit 1912ffbb (\"IB: Set \nclass_dev-\u003edev in core for nice device symlink\"), which removed \nclass_dev setting from low-level drivers, and also will break the build\nwhen class_dev is removed completely from struct ib_device.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "9862874d2138135dad9e78f61dbe415a4364945b", "tree": "a8083fc2b8391d727f0ebe77d1cb66c6d0000f89", "parents": [ "6a5546e76c4b2367e03cb52884b97c94d6260a8c" ], "author": { "name": "Paul Bolle", "email": "pebolle@tiscali.nl", "time": "Mon Apr 21 18:19:13 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 21 18:19:13 2008 -0700" }, "message": "IB/ipath: Fix module parameter description for disable_sma\n\nDescribe disable_sma parameter with its name rather than the internal\nib_ipath_disable_sma variable name, so that the description shows up\nproperly in modinfo.\n\nSigned-off-by: Paul Bolle \u003cpebolle@tiscali.nl\u003e\nAcked-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "6a5546e76c4b2367e03cb52884b97c94d6260a8c", "tree": "f9282f783a76388b247864aeb0eaac825ee034e3", "parents": [ "135cedad7457be6a96d5e151dfd48f7888a75e94" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 21 18:19:12 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Mon Apr 21 18:19:12 2008 -0700" }, "message": "RDMA/nes: Remove unneeded function declarations\n\nRemove redundant static declarations of functions that are defined\nbefore they are used in the source.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e80ab411e589e00550e2e6e5a6a02d59cc730357", "tree": "870225ff7b5b8d03e82a996963213a4bb9cce248", "parents": [ "529a41e36673b518c9e091f3a8d932b6b9e3c461", "ee959b00c335d7780136c5abda37809191fe52c3" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 21 15:49:58 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 21 15:49:58 2008 -0700" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-2.6\n\n* git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-2.6: (36 commits)\n SCSI: convert struct class_device to struct device\n DRM: remove unused dev_class\n IB: rename \"dev\" to \"srp_dev\" in srp_host structure\n IB: convert struct class_device to struct device\n memstick: convert struct class_device to struct device\n driver core: replace remaining __FUNCTION__ occurrences\n sysfs: refill attribute buffer when reading from offset 0\n PM: Remove destroy_suspended_device()\n Firmware: add iSCSI iBFT Support\n PM: Remove legacy PM (fix)\n Kobject: Replace list_for_each() with list_for_each_entry().\n SYSFS: Explicitly include required header file slab.h.\n Driver core: make device_is_registered() work for class devices\n PM: Convert wakeup flag accessors to inline functions\n PM: Make wakeup flags available whenever CONFIG_PM is set\n PM: Fix misuse of wakeup flag accessors in serial core\n Driver core: Call device_pm_add() after bus_add_device() in device_add()\n PM: Handle device registrations during suspend/resume\n block: send disk \"change\" event for rescan_partitions()\n sysdev: detect multiple driver registrations\n ...\n\nFixed trivial conflict in include/linux/memory.h due to semaphore header\nfile change (made irrelevant by the change to mutex).\n" }, { "commit": "ee959b00c335d7780136c5abda37809191fe52c3", "tree": "7775f3b274fd8caf5e7e5154fea89e96f2babd94", "parents": [ "56d110e852b0b1c85ad6c9bfe1cb4473ceb16402" ], "author": { "name": "Tony Jones", "email": "tonyj@suse.de", "time": "Fri Feb 22 00:13:36 2008 +0100" }, "committer": { "name": "Greg Kroah-Hartman", "email": "gregkh@suse.de", "time": "Sat Apr 19 19:10:33 2008 -0700" }, "message": "SCSI: convert struct class_device to struct device\n\nIt\u0027s big, but there doesn\u0027t seem to be a way to split it up smaller...\n\nSigned-off-by: Tony Jones \u003ctonyj@suse.de\u003e\nSigned-off-by: Kay Sievers \u003ckay.sievers@vrfy.org\u003e\nCc: Roland Dreier \u003crolandd@cisco.com\u003e\nCc: Sean Hefty \u003csean.hefty@intel.com\u003e\nCc: Hal Rosenstock \u003chal.rosenstock@gmail.com\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nSigned-off-by: Greg Kroah-Hartman \u003cgregkh@suse.de\u003e\n\n" }, { "commit": "05321937469a8592d6a6d35f1d38ca882d243044", "tree": "ac164db005c0cbabf58a9bf99533dee9c6e03c3b", "parents": [ "f4e91eb4a81559da87a3843758a641b5cc590b65" ], "author": { "name": "Greg Kroah-Hartman", "email": "gregkh@suse.de", "time": "Thu Mar 06 00:13:36 2008 +0100" }, "committer": { "name": "Greg Kroah-Hartman", "email": "gregkh@suse.de", "time": "Sat Apr 19 19:10:30 2008 -0700" }, "message": "IB: rename \"dev\" to \"srp_dev\" in srp_host structure\n\nThis sets us up to be able to convert the srp_host to use a struct\ndevice instead of a class_device.\n\nBased on a original patch from Tony Jones, but split up into this piece\nby Greg.\n\nSigned-off-by: Tony Jones \u003ctonyj@suse.de\u003e\nSigned-off-by: Kay Sievers \u003ckay.sievers@vrfy.org\u003e\nReviewed-by: Roland Dreier \u003crolandd@cisco.com\u003e\nCc: Sean Hefty \u003csean.hefty@intel.com\u003e\nCc: Hal Rosenstock \u003chal.rosenstock@gmail.com\u003e\nSigned-off-by: Greg Kroah-Hartman \u003cgregkh@suse.de\u003e\n\n" }, { "commit": "f4e91eb4a81559da87a3843758a641b5cc590b65", "tree": "534335821d076764cbc072586b19c4b061710e3d", "parents": [ "c4c66cf1787d408066fbfc69209185701f5df15f" ], "author": { "name": "Tony Jones", "email": "tonyj@suse.de", "time": "Fri Feb 22 00:13:36 2008 +0100" }, "committer": { "name": "Greg Kroah-Hartman", "email": "gregkh@suse.de", "time": "Sat Apr 19 19:10:30 2008 -0700" }, "message": "IB: convert struct class_device to struct device\n\nThis converts the main ib_device to use struct device instead of struct\nclass_device as class_device is going away.\n\nSigned-off-by: Tony Jones \u003ctonyj@suse.de\u003e\nSigned-off-by: Kay Sievers \u003ckay.sievers@vrfy.org\u003e\nCc: Roland Dreier \u003crolandd@cisco.com\u003e\nCc: Sean Hefty \u003csean.hefty@intel.com\u003e\nCc: Hal Rosenstock \u003chal.rosenstock@gmail.com\u003e\nSigned-off-by: Greg Kroah-Hartman \u003cgregkh@suse.de\u003e\n\n\n" }, { "commit": "6188e10d38b8d7244ee7776d5f1f88c837b4b93f", "tree": "6675e02c47fb684a613e10513816b5dcc5de28a9", "parents": [ "d7b1acd3b524b39f418e463e836b48ac041954d6" ], "author": { "name": "Matthew Wilcox", "email": "matthew@wil.cx", "time": "Fri Apr 18 22:21:05 2008 -0400" }, "committer": { "name": "Matthew Wilcox", "email": "willy@linux.intel.com", "time": "Fri Apr 18 22:22:54 2008 -0400" }, "message": "Convert asm/semaphore.h users to linux/semaphore.h\n\nSigned-off-by: Matthew Wilcox \u003cwilly@linux.intel.com\u003e\n" }, { "commit": "d3135846f6c1858dbad6ccb780a42e6c98953e6d", "tree": "f1800b9b4b435f86c33385bb4a002239547e3879", "parents": [ "5f090dcb4d4fff373ce7165bce4ba5e87534d50a" ], "author": { "name": "Matthew Wilcox", "email": "matthew@wil.cx", "time": "Fri Apr 18 22:16:32 2008 -0400" }, "committer": { "name": "Matthew Wilcox", "email": "willy@linux.intel.com", "time": "Fri Apr 18 22:16:32 2008 -0400" }, "message": "drivers: Remove unnecessary inclusions of asm/semaphore.h\n\nNone of these files use any of the functionality promised by\nasm/semaphore.h. It\u0027s possible that they rely on it dragging in some\nunrelated header file, but I can\u0027t build all these files, so we\u0027ll have\nfix any build failures as they come up.\n\nSigned-off-by: Matthew Wilcox \u003cwilly@linux.intel.com\u003e\n" }, { "commit": "0a22ab92f51478796d5f3997f4f5922409c98b10", "tree": "97bf48294f96cb4cf00f565c08f7538e77f974c2", "parents": [ "068c4ea1bb9ef733961d3d7a104fa9250ba80087" ], "author": { "name": "Erez Zilber", "email": "erezz@voltaire.com", "time": "Wed Apr 16 21:09:35 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:35 2008 -0700" }, "message": "IB/iser: Don\u0027t change itt endianness\n\nThe itt field in struct iscsi_data is not defined with any particular\nendianness. open-iscsi should use it as-is without byte-swapping it.\nThis fixes sparse warnings coming from doing ntohl(hdr-\u003eitt).\n\nSigned-off-by: Erez Zilber \u003cerezz@voltaire.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "068c4ea1bb9ef733961d3d7a104fa9250ba80087", "tree": "0dd576c0390927b0f07a604dee5fcaa342924b90", "parents": [ "9fdd5e5bf682130d1e1dd83d06e99eeafa645c0c" ], "author": { "name": "Jack Morgenstein", "email": "jackm@dev.mellanox.co.il", "time": "Wed Apr 16 21:09:35 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:35 2008 -0700" }, "message": "IB/mlx4: Update module version and release date\n\nThe mlx4_ib driver is stable enough for production use, so bump the\nversion number to 1.0 to indicate this.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@dev.mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "9fdd5e5bf682130d1e1dd83d06e99eeafa645c0c", "tree": "623f92fc4f16377a9a0f2a3e791bfc435897f4ea", "parents": [ "d97c51707d7d0716881be84ffd2100449852e44b" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:35 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:35 2008 -0700" }, "message": "IPoIB: Handle case when P_Key is deleted and re-added at same index\n\nIf a P_Key is deleted and then re-added at the same index, then IPoIB\ngets confused because __ipoib_ib_dev_flush() only checks whether the\nindex is the same without checking whether the P_Key was present, so\nthe interface is stopped when the P_Key is deleted, but the event when\nthe P_Key is re-added gets ignored and the interface never gets\nrestarted.\n\nAlso, switch to using ib_find_pkey() instead of ib_find_cached_pkey()\neverywhere in IPoIB, since none of the places that look for P_Keys are\nin a fast path or in non-sleeping context, and in general we want to\nkill off the whole caching infrastructure eventually. This also fixes\nconsistency problems caused because some IPoIB queries were cached and\nsome were uncached during the window where the cache was not updated.\n\nThanks to Venkata Subramonyam \u003cvsubramo@cisco.com\u003e for debugging this\nproblem and testing this fix.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "d97c51707d7d0716881be84ffd2100449852e44b", "tree": "eed3555698bbe9ca771f0703aa45001362555f8c", "parents": [ "4ff08a76bce3ed5f7d109c646dcfc474d7946213" ], "author": { "name": "Erez Zilber", "email": "erezz@voltaire.com", "time": "Wed Apr 16 21:09:35 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:35 2008 -0700" }, "message": "IB/iser: Release connection resources on RDMA_CM_EVENT_DEVICE_REMOVAL event\n\nWhen a RDMA_CM_EVENT_DEVICE_REMOVAL event is raised, iSER should\nrelease the connection resources.\n\nThis is necessary when the IB HCA module is unloaded while open-iscsi\nis still running. Currently, iSER just BUG()s.\n\nSigned-off-by: Erez Zilber \u003cerezz@voltaire.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "c83b5b1cb2b050c7a9054f330598df99c31abb98", "tree": "4d6790054a25d4e98d4f772a2b93f4d13262ec6c", "parents": [ "4cd1e5eb3cbe6e0cc934959770b4c60eac6ecf66" ], "author": { "name": "Stefan Roscher", "email": "ossrosch@linux.vnet.ibm.com", "time": "Wed Apr 16 21:09:35 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:35 2008 -0700" }, "message": "IB/ehca: Support all ibv_devinfo values in query_device() and query_port()\n\nAlso, introduce a few inline helper functions to make the code more readable.\n\nSigned-off-by: Stefan Roscher \u003cstefan.roscher@de.ibm.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "4cd1e5eb3cbe6e0cc934959770b4c60eac6ecf66", "tree": "cf0a0219790a7fac9acf08727ad63de14c6c6bb4", "parents": [ "940801b27e021b3494a44bc93be3c73fadbe4c2f" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:34 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:34 2008 -0700" }, "message": "RDMA/nes: Free IRQ before killing tasklet\n\nMove the free_irq() call in nes_remove() to before the tasklet_kill();\notherwise there is a window after tasklet_kill() where a new interrupt\ncan be handled and reschedule the tasklet, leading to a use-after-free\ncrash.\n\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "940801b27e021b3494a44bc93be3c73fadbe4c2f", "tree": "fdb85ea93c822e40336cecec815dc275562e42fb", "parents": [ "0df67030958bad07c3f82f392e3ffb785c56e48d" ], "author": { "name": "Jack Morgenstein", "email": "jackm@dev.mellanox.co.il", "time": "Wed Apr 16 21:09:34 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:34 2008 -0700" }, "message": "IB/mthca: Update module version and release date\n\nThe ib_mthca driver has been stable for a while, so bump the version\nnumber to 1.0 to indicate this.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@dev.mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "0df67030958bad07c3f82f392e3ffb785c56e48d", "tree": "317bdffc336a40e344f50b05492de6350eb38f7a", "parents": [ "5121df3ae45731ce98374a1b0b4d48f072643f42" ], "author": { "name": "Dotan Barak", "email": "dotanb@dev.mellanox.co.il", "time": "Wed Apr 16 21:09:34 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:34 2008 -0700" }, "message": "IB/mlx4: Update QP state if query QP succeeds\n\nIf the QP was moved to another state (such as SQE) by the hardware,\nthen after this change the user won\u0027t have to set the IBV_QP_CUR_STATE\nmask in order to execute modify QP in order to recover from this state.\n\nSigned-off-by: Dotan Barak \u003cdotanb@dev.mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "5121df3ae45731ce98374a1b0b4d48f072643f42", "tree": "f0eba075bae9fde2dd37cadfe4ee96b62496732b", "parents": [ "9285faa1e7c8ffcc8901c40f6e1cc06d93e92431" ], "author": { "name": "Dotan Barak", "email": "dotanb@dev.mellanox.co.il", "time": "Wed Apr 16 21:09:34 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:34 2008 -0700" }, "message": "IB/mthca: Update QP state if query QP succeeds\n\nIf the QP was moved to another state (such as SQE) by the hardware,\nthen after this change the user won\u0027t have to set the IBV_QP_CUR_STATE\nmask in order to execute modify QP in order to recover from this state.\n\nSigned-off-by: Dotan Barak \u003cdotanb@dev.mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "9285faa1e7c8ffcc8901c40f6e1cc06d93e92431", "tree": "094647e312edba67f6f5b555020ecb6fd7f34f67", "parents": [ "bbf8eed1a0f8949f7385146624f736f829992a70" ], "author": { "name": "Tom Tucker", "email": "tom@opengridcomputing.com", "time": "Wed Apr 16 21:09:34 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:34 2008 -0700" }, "message": "RDMA/amso1100: Add check for NULL reply_msg in c2_intr()\n\nFix a place where we might dereference a NULL pointer; this fixes\nCoverity CID 1392. On inspection I also found a place where we could\nattempt to kmem_cache_free() a NULL pointer, so fix this too.\n\nSigned-off-by: Tom Tucker \u003ctom@opengridcomputing.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "bbf8eed1a0f8949f7385146624f736f829992a70", "tree": "5cf6a5c76ca4c038d3ca0f53abc5f2976872696b", "parents": [ "3fdcb97f0b8d8a29117dc36acd0b15965d2a2160" ], "author": { "name": "Vladimir Sokolovsky", "email": "vlad@dev.mellanox.co.il", "time": "Wed Apr 16 21:09:33 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:33 2008 -0700" }, "message": "IB/mlx4: Add support for resizing CQs\n\nSigned-off-by: Vladimir Sokolovsky \u003cvlad@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "3fdcb97f0b8d8a29117dc36acd0b15965d2a2160", "tree": "a8bad6e48e9654f10e1b8ebfde3b086d83d2756e", "parents": [ "28d52b3cd8d48ef0ff77d4a8a7a21fc2816bb0a5" ], "author": { "name": "Eli Cohen", "email": "eli@dev.mellanox.co.il", "time": "Wed Apr 16 21:09:33 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:33 2008 -0700" }, "message": "IB/mlx4: Add support for modifying CQ moderation parameters\n\nSigned-off-by: Eli Cohen \u003celi@mellnaox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "28d52b3cd8d48ef0ff77d4a8a7a21fc2816bb0a5", "tree": "b1b7615491047d7b00bcaf193ba3a5c730655549", "parents": [ "2dd5716227878d5950988514a2cbabf72f7fc888" ], "author": { "name": "Eli Cohen", "email": "eli@dev.mellanox.co.il", "time": "Wed Apr 16 21:09:33 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:33 2008 -0700" }, "message": "IPoIB: Support modifying IPoIB CQ event moderation\n\nThis can be used to tune at run time the parameters controlling the\nevent (interrupt) generation rate and thus reduce the overhead\nincurred by handling interrupts resulting in better throughput. Since\nIPoIB uses a single CQ for both RX and TX, RX is chosen to dictate\nconfiguration for both RX and TX.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2dd5716227878d5950988514a2cbabf72f7fc888", "tree": "cd999c4f9bcf1bb1f54fc6b91fac7d16552a930e", "parents": [ "82c24c18afc5e1c2a955bdc2762b19721283365c" ], "author": { "name": "Eli Cohen", "email": "eli@dev.mellanox.co.il", "time": "Wed Apr 16 21:09:33 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:33 2008 -0700" }, "message": "IB/core: Add support for modify CQ\n\nAdd support for modifying CQ parameters for controlling event\ngeneration moderation.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "82c24c18afc5e1c2a955bdc2762b19721283365c", "tree": "2dd054b0738962daee6bdfd268c8b9fbb9fc466d", "parents": [ "9b1f38515c41a5f13021e15b50b6558db236d6d5" ], "author": { "name": "Eli Cohen", "email": "eli@dev.mellanox.co.il", "time": "Wed Apr 16 21:09:32 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:32 2008 -0700" }, "message": "IPoIB: Add basic ethtool support\n\nJust add the infrastructure so we can add functionality later.\n\nSigned-off-by: Eli Cohen \u003celi@mellanox.co.il\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "139b2db7951ed0c808884cfebca02a884aebe0c3", "tree": "df4a799be1302f4776db9b612d38e0c1ca8eab79", "parents": [ "0f39cf3d54e67a705773fd0ec56ca3dcd3e9272f" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:32 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:32 2008 -0700" }, "message": "RDMA/amso1100: Add support for \"send with invalidate\" work requests\n\nHandle IB_WR_SEND_WITH_INV work requests.\n\nThis resurrects a patch sent long ago by Mikkel Hagen \u003cmhagen@iol.unh.edu\u003e.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "0f39cf3d54e67a705773fd0ec56ca3dcd3e9272f", "tree": "83f19f0014d0e880fb245906105e903dd6d733d5", "parents": [ "e7eacd36865ae0707f5efae8e4dda421ffcd1b66" ], "author": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:32 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:32 2008 -0700" }, "message": "IB/core: Add support for \"send with invalidate\" work requests\n\nAdd a new IB_WR_SEND_WITH_INV send opcode that can be used to mark a\n\"send with invalidate\" work request as defined in the iWARP verbs and\nthe InfiniBand base memory management extensions. Also put \"imm_data\"\nand a new \"invalidate_rkey\" member in a new \"ex\" union in struct\nib_send_wr. The invalidate_rkey member can be used to pass in an\nR_Key/STag to be invalidated. Add this new union to struct\nib_uverbs_send_wr. Add code to copy the invalidate_rkey field in\nib_uverbs_post_send().\n\nFix up low-level drivers to deal with the change to struct ib_send_wr,\nand just remove the imm_data initialization from net/sunrpc/xprtrdma/,\nsince that code never does any send with immediate operations.\n\nAlso, move the existing IB_DEVICE_SEND_W_INV flag to a new bit, since\nthe iWARP drivers currently in the tree set the bit. The amso1100\ndriver at least will silently fail to honor the IB_SEND_INVALIDATE bit\nif passed in as part of userspace send requests (since it does not\nimplement kernel bypass work request queueing). Remove the flag from\nall existing drivers that set it until we know which ones are OK.\n\nThe values chosen for the new flag is not consecutive to avoid clashing\nwith flags defined in the XRC patches, which are not merged yet but\nwhich are already in use and are likely to be merged soon.\n\nThis resurrects a patch sent long ago by Mikkel Hagen \u003cmhagen@iol.unh.edu\u003e.\n\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "e7eacd36865ae0707f5efae8e4dda421ffcd1b66", "tree": "0d0036656352901ddc08d43e9ce1edb1024d8338", "parents": [ "124b4dcb1dd3a6fb80051f1785117a732d785f70" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Wed Apr 16 21:09:32 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:32 2008 -0700" }, "message": "IB/ipath: Update copyright dates for files changed in 2008\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "124b4dcb1dd3a6fb80051f1785117a732d785f70", "tree": "d329e1f458646a33d675faa6a9c2a7efa8e4fd8b", "parents": [ "bb9171448deb1f7ece27674e2e431e4f267fd453" ], "author": { "name": "Dave Olson", "email": "dave.olson@qlogic.com", "time": "Wed Apr 16 21:09:32 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:32 2008 -0700" }, "message": "IB/ipath: add calls to new 7220 code and enable in build\n\nThis patch adds the initialization calls into the new 7220 HCA files,\nchanges the Makefile to compile and link the new files, and code to\nhandle send DMA.\n\nSigned-off-by: Dave Olson \u003cdave.olson@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "bb9171448deb1f7ece27674e2e431e4f267fd453", "tree": "b042155205bbbe3deb317d65a53a4180fb512435", "parents": [ "8babfa4fb9bfe93d57c700410a4f8be9fbd3edd7" ], "author": { "name": "Arthur Jones", "email": "arthur.jones@qlogic.com", "time": "Wed Apr 16 21:09:31 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:31 2008 -0700" }, "message": "IB/ipath: Misc changes to prepare for IB7220 introduction\n\nThe patch adds a number of minor changes to support newer HCAs:\n - New send buffer control bits\n - New error condition bits\n - Locking and initialization changes\n - More send buffers\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "8babfa4fb9bfe93d57c700410a4f8be9fbd3edd7", "tree": "6af24d071d0c41faf9297bdd054c08749080083b", "parents": [ "909c0faa8fd8a68fab34f099fe8469e608d8b362" ], "author": { "name": "Arthur Jones", "email": "arthur.jones@qlogic.com", "time": "Wed Apr 16 21:09:31 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:31 2008 -0700" }, "message": "IB/ipath: User mode send DMA\n\nA new file which allows the IBA7220 send DMA engine to be used from\nuserland. The routines here are not linked in yet, that will happen in\na follow-on patch...\n\nSigned-off-by: Arthur Jones \u003carthur.jones@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "909c0faa8fd8a68fab34f099fe8469e608d8b362", "tree": "c91f177dc23690a4af6100f181d5e12ebc4b4ddd", "parents": [ "f7a60d71af49d7d23d8b827833e4258eba00479d" ], "author": { "name": "Arthur Jones", "email": "arthur.jones@qlogic.com", "time": "Wed Apr 16 21:09:31 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:31 2008 -0700" }, "message": "IB/ipath: User mode send DMA header file\n\nA new header file which allows the IBA7220 send DMA engine to be used\nfrom userland. The definitions here are not used yet, that will happen\nin a follow-on patch...\n\nSigned-off-by: Arthur Jones \u003carthur.jones@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "f7a60d71af49d7d23d8b827833e4258eba00479d", "tree": "215553e30b15612cddafb213f7667544b0deafb3", "parents": [ "2c19643563aed5593c62525e9941a47e56273ccf" ], "author": { "name": "John Gregor", "email": "john.gregor@qlogic.com", "time": "Wed Apr 16 21:09:31 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:31 2008 -0700" }, "message": "IB/ipath: Add code for IBA7220 send DMA\n\nThe IBA7220 HCA has a new feature to DMA data to the on chip send\nbuffers instead of or in addition to the host CPU doing the data\ntransfer. This patch adds code to support the send DMA queue.\n\nSigned-off-by: John Gregor \u003cjohn.gregor@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "2c19643563aed5593c62525e9941a47e56273ccf", "tree": "b0a400bac9183d912251c331d69bb4de28d22bf9", "parents": [ "ab0fb2e0490e5e453a02ad72fd3529ce1561e1c6" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Wed Apr 16 21:09:31 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:31 2008 -0700" }, "message": "IB/ipath: Add IBA7220-specific SERDES initialization data\n\nThis patch adds binary data to initialize the IB SERDES.\n\nSigned-off-by: Michael Albaugh \u003cMichael.Albaugh@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "ab0fb2e0490e5e453a02ad72fd3529ce1561e1c6", "tree": "43055fea7a841d17723fba88da542048227e726f", "parents": [ "843e6ab489cb5a2fd5df45bed1254812bc8ed8fa" ], "author": { "name": "Michael Albaugh", "email": "Michael.Albaugh@Qlogic.com", "time": "Wed Apr 16 21:09:31 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:31 2008 -0700" }, "message": "IB/ipath: Support for SerDes portion of IBA7220\n\nThe control and initialization of the SerDes blocks of the IBA7220 is\nsufficiently complex to merit a separate file.\n\nSigned-off-by: Michael Albaugh \u003cMichael.Albaugh@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "843e6ab489cb5a2fd5df45bed1254812bc8ed8fa", "tree": "c7d1ab98ee0039ae2aa097874958a806c1352b25", "parents": [ "dd042d59c18b2f26375494af7f5b6d1499acd2bb" ], "author": { "name": "Ralph Campbell", "email": "ralph.campbell@qlogic.com", "time": "Wed Apr 16 21:09:30 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:30 2008 -0700" }, "message": "IB/ipath: HCA-specific code to support IBA7220\n\nThis patch adds the HCA-specific code for the IBA7220 HCA.\n\nSigned-off-by: Ralph Campbell \u003cralph.campbell@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" }, { "commit": "dd042d59c18b2f26375494af7f5b6d1499acd2bb", "tree": "8dda5010451586b9d883584ee13379e364c5c7ba", "parents": [ "afce688ba968723a9e281b141bf7b0ab43a36968" ], "author": { "name": "Michael Albaugh", "email": "Michael.Albaugh@Qlogic.com", "time": "Wed Apr 16 21:09:30 2008 -0700" }, "committer": { "name": "Roland Dreier", "email": "rolandd@cisco.com", "time": "Wed Apr 16 21:09:30 2008 -0700" }, "message": "IB/ipath: Isolate 7220-specific content\n\nThis patch adds a new ASIC-specific header file for the HCAs using the IBA7220.\n\nSigned-off-by: Michael Albaugh \u003cMichael.Albaugh@qlogic.com\u003e\nSigned-off-by: Roland Dreier \u003crolandd@cisco.com\u003e\n" } ], "next": "afce688ba968723a9e281b141bf7b0ab43a36968" }