)]}'
{
  "log": [
    {
      "commit": "f70dba83669bf718c2f1731f0f58b8149e883593",
      "tree": "cb0c2a5cff4678a860e230d33bea580b9e73aba0",
      "parents": [
        "058a0f9f31283d5eb9d8686d3b4f69e55d1589f1"
      ],
      "author": {
        "name": "Stephen M. Cameron",
        "email": "scameron@beardog.cce.hp.com",
        "time": "Mon Jul 19 13:46:38 2010 -0500"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jaxboe@fusionio.com",
        "time": "Sat Aug 07 18:52:30 2010 +0200"
      },
      "message": "cciss: use consistent variable names\n\ncciss: use consistent variable names\n\"h\", for the hba structure and \"c\" for the command structures.\nand get rid of trivial CCISS_LOCK macro.\n\nSigned-off-by: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n"
    },
    {
      "commit": "83123cb11b5a5205233c59357da2c8d9a8dc9d24",
      "tree": "6f74b67b9de4e59223efdeeb774ce17a1e7bf5d7",
      "parents": [
        "8e93bf6d6c9c6d864c17b7743f2cc5f2e052fe46"
      ],
      "author": {
        "name": "Stephen M. Cameron",
        "email": "scameron@beardog.cce.hp.com",
        "time": "Mon Jul 19 13:46:17 2010 -0500"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jaxboe@fusionio.com",
        "time": "Sat Aug 07 18:52:12 2010 +0200"
      },
      "message": "cciss: factor out cciss_reset_devices()\n\ncciss: factor out cciss_reset_devices()\n\nSigned-off-by: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n"
    },
    {
      "commit": "e99ba1362723df14bbe36da6eeaadf81d95782e6",
      "tree": "5bf701fa79a250f1fde71b1b22cf6e35b21e9c59",
      "parents": [
        "d474830da6218c0b7f81eab03aff7d8c539bdb57"
      ],
      "author": {
        "name": "Stephen M. Cameron",
        "email": "scameron@beardog.cce.hp.com",
        "time": "Mon Jul 19 13:45:15 2010 -0500"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jaxboe@fusionio.com",
        "time": "Sat Aug 07 18:52:11 2010 +0200"
      },
      "message": "cciss: factor out cciss_wait_for_board_ready()\n\ncciss: factor out cciss_wait_for_board_ready()\n\nSigned-off-by: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n"
    },
    {
      "commit": "5e216153c34ac21781110795284a784037f808e3",
      "tree": "b42ceb1e884bdb397283ddb01562fe03d1f95cad",
      "parents": [
        "1d1414419f034702bf587accdf2a9ac53245e000"
      ],
      "author": {
        "name": "Mike Miller",
        "email": "mike.miller@hp.com",
        "time": "Wed Jun 02 12:58:06 2010 -0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jaxboe@fusionio.com",
        "time": "Sat Aug 07 18:12:51 2010 +0200"
      },
      "message": "cciss: add performant mode support for Stars/Sirius\n\nAdd a mode of controller operation called Performant Mode.  Even though\ncciss has been deprecated in favor of hpsa there are new controllers due\nout next year that HP must support in older vendor distros.  Vendors\nrequire all fixes/features be upstream.  These new controllers support\nonly 16 commands in simple mode but support up to 1024 in performant mode.\nThis requires us to add this support at this late date.\n\nThe performant mode transport minimizes host PCI accesses by performinf\nmany completions per read.  PCI writes are posted so the host can write\nthen immediately get off the bus not waiting for the writwe to complete to\nthe target.  In the context of performant mode the host read out to a\ncontroller pulls all posted writes into host memory ensuring the reply\nqueue is coherent.\n\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n"
    },
    {
      "commit": "1d1414419f034702bf587accdf2a9ac53245e000",
      "tree": "c3a5b466c35118b3fff4ab1a981f15e471393605",
      "parents": [
        "2cf3af1c9ec26f8db3f386e48f9d979ad8bb3eff"
      ],
      "author": {
        "name": "Mike Miller",
        "email": "mike.miller@hp.com",
        "time": "Wed Jun 02 12:58:04 2010 -0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jaxboe@fusionio.com",
        "time": "Sat Aug 07 18:12:51 2010 +0200"
      },
      "message": "cciss: make interrupt access methods return type bool\n\nChange the return type of our interrupt access routines to bool from\nunsigned long.  It makes more sense that way.\n\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n"
    },
    {
      "commit": "aad9fb6f2c5beafe76a724c90a4bd0d695ab8b42",
      "tree": "811a687fc986084fbdf974a31fc2226ad759cd46",
      "parents": [
        "d45033ef56fa9b09b73a6eb2a0f280fa7c1bab09"
      ],
      "author": {
        "name": "Stephen M. Cameron",
        "email": "scameron@beardog.cce.hp.com",
        "time": "Fri Feb 26 16:01:42 2010 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Sun Feb 28 19:42:32 2010 +0100"
      },
      "message": "cciss: do not use void pointer for scsi hba data\n\ncciss: do not use void pointer for scsi hba data\nand get rid of related unnecessary type casting\nand delete some superfluous and misleading comments nearby.\n\nSigned-off-by: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "dccc9b563e455b91f7247b1ca6b0face40323538",
      "tree": "a800d412764ee22d9a54000cb844a04a1a006933",
      "parents": [
        "49fc5601ea3bf9625d699dc777f80f72e8126c0b"
      ],
      "author": {
        "name": "Stephen M. Cameron",
        "email": "scameron@beardog.cce.hp.com",
        "time": "Fri Feb 26 16:01:27 2010 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Sun Feb 28 19:42:31 2010 +0100"
      },
      "message": "cciss: simplify scatter gather code\n\ncciss: simplify scatter gather code.\nInstead of allocating an array of pointers to a structure\ncontaining an SGDescriptor structure, and two other elements\nthat aren\u0027t really used, just allocate SGDescriptor structs.\n\nSigned-off-by: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "b028461d66a4dc2754d4e5dab1b3974c44798c5d",
      "tree": "d12b0275b3fd1af7d6c841ae053248d6efb57169",
      "parents": [
        "488991e28e55b4fbca8067edf0259f69d1a6f92c"
      ],
      "author": {
        "name": "dann frazier",
        "email": "dannf@hp.com",
        "time": "Wed Feb 17 16:53:31 2010 -0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Mon Feb 22 13:44:45 2010 +0100"
      },
      "message": "cciss: remove C99-style comments\n\nSome cleanup before the header file split-out so we don\u0027t propagate this style\ninto new files.\n\nAcked-by: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nSigned-off-by: dann frazier \u003cdannf@hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "32a87c0114f37871aefb12a30de3e0c3300e3646",
      "tree": "d246240c07731a1f228a189ad373416997b496d3",
      "parents": [
        "d61c42690c6e2ff093a3d01338dad49f35b1e27b"
      ],
      "author": {
        "name": "Alex Chiang",
        "email": "achiang@hp.com",
        "time": "Mon Nov 23 09:35:06 2009 +0100"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Mon Nov 23 09:35:06 2009 +0100"
      },
      "message": "cciss: change Cmd_sg_list.sg_chain_dma type to dma_addr_t\n\nA recent commit broke the ia64 build:\n\n\tAuthor: Don Brace \u003cbrace@beardog.cce.hp.com\u003e\n\tDate:   Thu Nov 12 12:50:01 2009 -0600\n\n\tcciss: Add enhanced scatter-gather support.\n\nbecause of this hunk:\n\n\t--- a/drivers/block/cciss.h\n\t+++ b/drivers/block/cciss.h\n\t+struct Cmd_sg_list {\n\t+       SGDescriptor_struct     *sgchain;\n\t+       dma64_addr_t            sg_chain_dma;\n\t+       int                     chain_block_size;\n\t+};\n\nThe issue is that dma64_addr_t isn\u0027t #define\u0027d on ia64.\n\nThe way that we\u0027re using Cmd_sg_list.sg_chain_dma is to hold an\naddress returned from pci_map_single().\n\n\t+               temp64.val \u003d pci_map_single(h-\u003epdev,\n\t+                                 h-\u003ecmd_sg_list[c-\u003ecmdindex]-\u003esgchain,\n\t+                                 len, dir);\n\t+\n\t+               h-\u003ecmd_sg_list[c-\u003ecmdindex]-\u003esg_chain_dma \u003d temp64.val;\n\npci_map_single() returns a dma_addr_t too.\n\nThis code will still work even on a 32-bit x86 build, where\ndma_addr_t is defined to be a u32 because it will simply be\npromoted to the __u64 that temp64.val is defined as.\n\nThus, declaring Cmd_sg_list.sg_chain_dma as dma_addr_t is safe.\n\nCc: Don Brace \u003cbrace@beardog.cce.hp.com\u003e\nCc: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nSigned-off-by: Alex Chiang \u003cachiang@hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "5c07a311a80adb0138fc08e8279c60255d88d0b8",
      "tree": "1746b4ec4b7ea1f2f02b34d5c0adc86dc8e0d97f",
      "parents": [
        "da0021841c3ea6a82588efae3260015847ea5d33"
      ],
      "author": {
        "name": "Don Brace",
        "email": "brace@beardog.cce.hp.com",
        "time": "Thu Nov 12 12:50:01 2009 -0600"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Fri Nov 13 08:45:54 2009 +0100"
      },
      "message": "cciss: Add enhanced scatter-gather support.\n\ncciss: Add enhanced scatter-gather support.  For controllers which\nsupported, more than 512 scatter-gather elements per command may\nbe used, and the max transfer size can be increased to 8192 blocks.\n\nSigned-off-by: Don Brace \u003cbrace@beardog.cce.hp.com\u003e\nSigned-off-by: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "9cef0d2f4f68a5a2c6ea0495f958a074d21fbd07",
      "tree": "aee97fb9d8de37c0aee1fec563192e29a2425c70",
      "parents": [
        "e272afecaf18912e971374df4605496975942e5c"
      ],
      "author": {
        "name": "Stephen M. Cameron",
        "email": "scameron@beardog.cce.hp.com",
        "time": "Thu Sep 17 13:48:31 2009 -0500"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Thu Oct 01 21:15:45 2009 +0200"
      },
      "message": "cciss: Dynamically allocate the drive_info_struct for each logical drive.\n\ncciss: Dynamically allocate the drive_info_struct for each logical drive.\nThis reduces the size of the per-hba ctlr_info structure from 106936\nbytes to 8132 bytes.  That\u0027s on 32-bit systems.  On 64-bit systems, the\nimprovement is even bigger.  Without this, the ctlr_info struct is so big\nthat the driver won\u0027t even load on a 64 bit system if CISS_MAX_LUN was\nat it\u0027s current setting of 1024 logical drives.\n\nSigned-off-by: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "39ccf9a645dbca7f9866317380912327570787c0",
      "tree": "6b6a8217c4e2997694738b91b410fe37573688a9",
      "parents": [
        "983333cb0c445c56808502461bbb34876c63eb2b"
      ],
      "author": {
        "name": "Stephen M. Cameron",
        "email": "scameron@beardog.cce.hp.com",
        "time": "Thu Sep 17 13:48:00 2009 -0500"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Thu Oct 01 21:15:43 2009 +0200"
      },
      "message": "cciss: Preserve all 8 bytes of LUN ID for logical drives.\n\nPreserve all 8 bytes of the LunID field returned\nby CCISS_REPORT_LOGICAL instead of only saving 4 bytes.\nThis fixes a bug with logical volume addressing encountered on\nan MSA2012.\n\nSigned-off-by: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "617e1344229d22ea9ecb6538e50808541618ed2b",
      "tree": "8e6020a20ccb2c74b1547a6563e989be0c0eb133",
      "parents": [
        "21d9db0b6231ef908fcdbfacefa392352776857f"
      ],
      "author": {
        "name": "Stephen M. Cameron",
        "email": "scameron@beardog.cce.hp.com",
        "time": "Thu Sep 17 13:47:14 2009 -0500"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Thu Oct 01 21:15:41 2009 +0200"
      },
      "message": "cciss: Dynamically allocate struct device for each logical drive as needed.\n\nDynamically allocate struct device for each logical drive as needed\ninstead of allocating the maximum we would ever need at driver init time.\n\nSigned-off-by: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "b368c9dd65984d1860b97bff77644c0e3e46df96",
      "tree": "003e31b2bb29eff630c3c156e08f4eaea7d7b6e2",
      "parents": [
        "c64bebcd7f33a6260b6d4c9999f797a633a3fa1c"
      ],
      "author": {
        "name": "Andrew Patterson",
        "email": "andrew.patterson@hp.com",
        "time": "Thu Sep 17 13:46:58 2009 -0500"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Thu Oct 01 21:15:41 2009 +0200"
      },
      "message": "cciss: Use one scan thread per controller and fix hang during rmmod\n\nReplace the use of one scan kthread per controller with one per driver.\nUse a queue to hold a list of controllers that need to be rescanned with\nroutines to add and remove controllers from the queue.\n\nFix locking and completion handling to prevent a hang during rmmod.\n\nSigned-off-by: Andrew Patterson \u003candrew.patterson@hp.com\u003e\nSigned-off-by: Stephen M. Cameron \u003cscameron@beardog.cce.hp.com\u003e\nAcked-by: Mike Miller \u003cmike.miller@hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "72f9f1324fc4cd450c92e4600a710231b0445c75",
      "tree": "1b293d0fb9c28bde38c321fa213ce7e765a8fd69",
      "parents": [
        "85cc61ae41084cb6d8ecc6c9e01ac4563005c8ac"
      ],
      "author": {
        "name": "scameron@beardog.cca.cpqcorp.net",
        "email": "scameron@beardog.cca.cpqcorp.net",
        "time": "Mon Jun 08 16:09:32 2009 -0500"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Tue Jun 09 05:47:43 2009 +0200"
      },
      "message": "cciss: Remove no longer needed sendcmd reject processing code\n\nNow that the cciss SCSI error handling routines operate with interrupts\nenabled, we no longer need to maintain the list of command completions that\nsendcmd() might inadvertantly scoop up, since now it only runs at driver init\ntime, and there won\u0027t be any other commands for it to scoop up.  So we\ncan remove that list and the code that adds to it and processes it.\n\nSigned-off-by: Stephen M. Cameron \u003cscameron@beardog.cca.cpqcorp.net\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "789a424ad1352b335960e7c56494d0410577fa61",
      "tree": "7968d121b86b66c6271032441fd222e627f14ccd",
      "parents": [
        "3c2ab40296894d1f7ad9714550fdf9b96d4e9ee6"
      ],
      "author": {
        "name": "scameron@beardog.cca.cpqcorp.net",
        "email": "scameron@beardog.cca.cpqcorp.net",
        "time": "Mon Jun 08 16:05:56 2009 -0500"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Tue Jun 09 05:47:43 2009 +0200"
      },
      "message": "cciss: separate error processing and command retrying code in sendcmd_withirq_core()\n\nSeparate the error processing from sendcmd_withirq_core from the code\nwhich retries commands.  The rationale for this is that the SCSI error\nhandling code can then be made to use sendcmd_withirq_core, but avoid\nretrying commands.\n\nSigned-off-by: Stephen M. Cameron \u003cscameron@beardog.cca.cpqcorp.net\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "7fe063268e73681cdca1a6496a25f93d3332f517",
      "tree": "97c9b5f53012908343af83c481c0b8fad888690e",
      "parents": [
        "88f627ae394eadd75ada669904269f1a4a77b3bd"
      ],
      "author": {
        "name": "Andrew Patterson",
        "email": "andrew.patterson@hp.com",
        "time": "Tue Jun 02 14:48:39 2009 +0200"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Tue Jun 02 14:48:39 2009 +0200"
      },
      "message": "cciss: add cciss driver sysfs entries\n\nAdd sysfs entries to the cciss driver needed for the dm/multipath tools.\n\nA file for vendor, model, rev, and unique_id is added for each logical\ndrive under directory /sys/bus/pci/devices/\u003cdev\u003e/ccissX/cXdY.  Where X \u003d\nthe controller (or host) number and Y is the logical drive number.\n\nA link from /sys/bus/pci/devices/\u003cdev\u003e/ccissX/cXdY/block:cciss!cXdY to\n/sys/block/cciss!cXdY/device is also created.  A bus is created in\n/sys/bus/cciss.  A link is created from the pci ccissX entry to\n/sys/bus/cciss/devices/ccissX.  Please consider this for inclusion.\n\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: Stephen M. Cameron \u003cscameron@beardog.cca.cpqcorp.net\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "0a9279cc7cbe726e995c44a1acae81d446775816",
      "tree": "80b7eb06a7629f6e0ab0c865f791b6a421a0ef6e",
      "parents": [
        "ac44e5b2ed62bf4acf9df84575d3f18c7a6fdf22"
      ],
      "author": {
        "name": "Mike Miller",
        "email": "mike.miller@hp.com",
        "time": "Thu Apr 02 12:50:55 2009 -0700"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Tue Apr 07 08:12:38 2009 +0200"
      },
      "message": "cciss: kernel scan thread for MSA2012\n\nThe MSA2012 cannot inform the driver of configuration changes since all\nmanagement is out of band.  This is a departure from any storage we have\nsupported in the past.  We need some way to detect changes on the topology\nso we implement this kernel thread.  In some instances there\u0027s nothing we\ncan do from the driver (like LUN failure) so just print out a message.  In\nthe case where logical volumes are added or deleted we call\nrebuild_lun_table to refresh the driver\u0027s view of the world.\n\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "8a3173de4ab4cdacc43675dc5c077f9a5bf17f5f",
      "tree": "e1998a856a09c805c588740c8c83d50dd9663c40",
      "parents": [
        "7c0990c7ee988aa193abbb7da3faeb9279146dbf"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Thu Nov 20 09:46:09 2008 +0100"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Mon Dec 29 08:28:43 2008 +0100"
      },
      "message": "cciss: switch to using hlist for command list management\n\nThis both cleans up the code and also helps detect the spurious case\nof a command attempted being removed from a queue it doesn\u0027t belong\nto.\n\nAcked-by: Mike Miller \u003cmike.miller@hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "a72da29b6cbc5cf918567f2a0d76df6871e94b01",
      "tree": "1ec0caea10895d9265ee7769cffea09e808c378e",
      "parents": [
        "f7108f91cdcaca07c6a99777b2724093294f36ee"
      ],
      "author": {
        "name": "Mike Miller",
        "email": "mike.miller@hp.com",
        "time": "Mon Aug 04 11:54:51 2008 +0200"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Wed Aug 06 12:30:03 2008 +0200"
      },
      "message": "cciss: make rebuild_lun_table behave better\n\nThis patch makes the rebuild_lun_table smart enough to not rip a logical\nvolume out from under the OS. Without this fix if a customer is running\nhpacucli to monitor their storage the driver will blindly remove and re-add\nthe disks whenever the utility calls the CCISS_REGNEWD ioctl. Unfortunately,\nboth hpacucli and ACUXE call the ioctl repeatedly. Customers have reported\nIO coming to a standstill. Calling the ioctl is the problem, this patch is\nthe fix.\n\nSigned-off-by: Stephen M. Cameron \u003cscameron@beardog.cca.cpqcorp.net\u003e\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "799202cbd0ef6a201446d99fcbd78b9f0bda6ae5",
      "tree": "cfc6a988170f4e65b810ee6a523e6d858ee01ce2",
      "parents": [
        "3833a748aa75dd39494bb861ab018216b0a2c14e"
      ],
      "author": {
        "name": "Mike Miller",
        "email": "mike.miller@hp.com",
        "time": "Wed Dec 06 20:35:12 2006 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@woody.osdl.org",
        "time": "Thu Dec 07 08:39:30 2006 -0800"
      },
      "message": "[PATCH] cciss: add support for 1024 logical volumes\n\nAdd the support for a large number of logical volumes.  We will soon have\nhardware that support up to 1024 logical volumes.\n\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "92c4231aef720bd5e1d634d2f7335f31277318da",
      "tree": "3c08d3479b2db7db693c5439357648ea02135e2e",
      "parents": [
        "f92e2f5f889803306e50c06e17ee330403e91b8d"
      ],
      "author": {
        "name": "Mike Miller",
        "email": "mike.miller@hp.com",
        "time": "Wed Dec 06 20:35:06 2006 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@woody.osdl.org",
        "time": "Thu Dec 07 08:39:29 2006 -0800"
      },
      "message": "[PATCH] cciss: set sector_size to 2048 for performance\n\nChange the blk_queue_max_sectors from 512 to 2048.  This helps increase\nperformance.\n\n[akpm@osdl.org: s/sector_size/max_sectors/]\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "f880632f963c3611d096d9373d16663c076310c7",
      "tree": "f1e287ce43b1dd08cb7d5f8be661f48d99b902ed",
      "parents": [
        "4ff9a9a4baff2627d7bcf65d0ec07d647bc1ad29"
      ],
      "author": {
        "name": "Mike Miller",
        "email": "mike.miller@hp.com",
        "time": "Wed Dec 06 20:35:01 2006 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@woody.osdl.org",
        "time": "Thu Dec 07 08:39:29 2006 -0800"
      },
      "message": "[PATCH] cciss: increase number of commands on controller\n\nRemove #define NR_CMDS and replace it w/hba[i]-\u003enr_cmds.  Most Smart Array\ncontrollers can support up to 1024 commands but the E200 family can only\nsupport 128.  To prevent annoying \"fifo full\" messages we define nr_cmds on a\nper controller basis by adding it the product table.\n\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nAcked-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "00988a3514bbc0cce781c067cf52559741d88b80",
      "tree": "e0a844ecd9351c67dd9e73e8e6aafd064fa43137",
      "parents": [
        "82b0547cfae1fb2ee26cad588f6d49a347d24740"
      ],
      "author": {
        "name": "Mike Miller (OS Dev)",
        "email": "mikem@beardog.cca.cpqcorp.net",
        "time": "Sat Sep 30 23:27:23 2006 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Sun Oct 01 00:39:20 2006 -0700"
      },
      "message": "[PATCH] cciss: support for \u003e2TB logical volumes\n\nAdd support for logical volumes \u003e2TB.  All SAS/SATA controllers support\nlarge volumes.\n\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: Jens Axboe \u003caxboe@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "4e570309e80f7c7a532fe0074e74df26ff8ef5d2",
      "tree": "82e8e7e21b537605acd48375113188434c1c2b58",
      "parents": [
        "c33ac89bc7d697e23ce09ddae73e0ece5f65ad48"
      ],
      "author": {
        "name": "Bjorn Helgaas",
        "email": "bjorn.helgaas@hp.com",
        "time": "Sun Jun 25 05:49:02 2006 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Sun Jun 25 10:01:21 2006 -0700"
      },
      "message": "[PATCH] CCISS: request all PCI resources\n\nWe should call pci_request_regions() to claim all resources the device\ndecodes.  Previously, we claimed only the I/O port range.\n\nSigned-off-by: Bjorn Helgaas \u003cbjorn.helgaas@hp.com\u003e\nAcked-by: Jeff Garzik \u003cjeff@garzik.org\u003e\nAcked-by: Mike Miller \u003cmike.miller@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "564de74a7e2778e1d11b2d2e50ee8dab1cf1456a",
      "tree": "25b1ba320ac19aeb4bafecab2abc25c05d4a085d",
      "parents": [
        "7019e7e41e34388cb87a5f0e3d05e92992418f34"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Sun Jan 08 01:05:17 2006 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Sun Jan 08 20:14:09 2006 -0800"
      },
      "message": "[PATCH] cciss: avoid defining useless MAJOR_NR macro\n\nThis sneaked in with one of the updates.\n\nSigned-off-by: Adrian Bunk \u003cbunk@stusta.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "fb86a35b9ded8a7e53a432cbf28df603cdd4849c",
      "tree": "6cfc9de386c26f5b1c9a126aee2bdc8f80bc8e2b",
      "parents": [
        "d09cf7d77f62f6fb2f6d63fe5980583805f2d559"
      ],
      "author": {
        "name": "Mike Miller",
        "email": "mike.miller@hp.com",
        "time": "Sun Jan 08 01:03:50 2006 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Sun Jan 08 20:14:00 2006 -0800"
      },
      "message": "[PATCH] cciss: adds MSI and MSI-X support\n\nThis creates a new function, cciss_interrupt_mode called from\ncciss_pci_init.  This function determines what type of interrupt vector to\nuse, i.e., MSI, MSI-X, or IO-APIC.\n\nOne noticeable difference is changing the interrupt field of the controller\nstruct to an array of 4 unsigned ints.  The Smart Array HW is capable of\ngenerating 4 distinct interrupts depending on the transport method in use\nduring operation.  These are:\n\n#define DOORBELL_INT 0\nUsed to notify the contoller of configuration updates. We only use\nthis feature when in polling mode.\n\n#define PERF_MODE_INT 0\nUsed when the controller is in Performant Mode.\n\n#define SIMPLE_MODE_INT 2\nUsed when the controller is in Simple Mode (current Linux implementation).\n\n#define MEMQ_INT_MODE 3\nNot used.\n\nWhen using IO-APIC interrupts these 4 lines are OR\u0027ed together so when any\none fires an interrupt an is generated.  In MSI or MSI-X mode this hardware\nOR\u0027ing is ignored.  We must register for our interrupt depending on what\nmode the controller is running.  For Linux we use SIMPLE_MODE_INT\nexclusively at this time.  Please consider this for inclusion.\n\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: Jens Axboe \u003caxboe@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "3da8b713da723e78a03f0404beedf3cc6f4f860b",
      "tree": "a09cc4308fcf0087aa607029bd71825b568d97e5",
      "parents": [
        "13bf50d1f21b2f11452c4b8a82a91319791f8ba3"
      ],
      "author": {
        "name": "mike.miller@hp.com",
        "email": "mike.miller@hp.com",
        "time": "Fri Nov 04 12:30:37 2005 -0600"
      },
      "committer": {
        "name": "James Bottomley",
        "email": "jejb@mulgrave.(none)",
        "time": "Sun Nov 06 14:12:49 2005 -0600"
      },
      "message": "[SCSI] cciss: scsi error handling\n\nThis patch adds SCSI error handling code to the SCSI portion\nof the cciss driver.\n\nSigned-off-by: Stephen M. Cameron \u003csteve.cameron@hp.com\u003e\nAcked-by: Mike Miller \u003cmike.miller@hp.com\u003e\nSigned-off-by: James Bottomley \u003cJames.Bottomley@SteelEye.com\u003e\n"
    },
    {
      "commit": "33079b21978f478865068ee6a3c5807b6c6ecdbe",
      "tree": "086035c299e4dcc0ab6af6623c53ac72be81b303",
      "parents": [
        "ddd474420a0b0dfeda38b6b5f83c7af751235cc3"
      ],
      "author": {
        "name": "Mike Miller",
        "email": "mike.miller@hp.com",
        "time": "Tue Sep 13 01:25:22 2005 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Tue Sep 13 08:22:30 2005 -0700"
      },
      "message": "[PATCH] cciss: direct lookup for command completions\n\nThis patch changes the way we complete commands.  In the old method when we\ngot a completion we searched our command list from the top until we find it.\n\nThis method uses a tag associated with each command (not SCSI command tagging)\nto index us directly to the completed command.  This helps performance.\n\nSigned-off-by: Don Brace \u003cdab@hp.com\u003e\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "ddd474420a0b0dfeda38b6b5f83c7af751235cc3",
      "tree": "e081ba3d447eb4c1dd5a6ab38d7902c2db03ae59",
      "parents": [
        "1f8ef3806c40e74733f45f436d44b3d8e9a2fa48"
      ],
      "author": {
        "name": "Mike Miller",
        "email": "mike.miller@hp.com",
        "time": "Tue Sep 13 01:25:22 2005 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Tue Sep 13 08:22:30 2005 -0700"
      },
      "message": "[PATCH] cciss: new disk register/deregister routines\n\nThis patch removes a couple of functions dealing with configuration and\nreplaces them with new functions.  This implementation fixes some bugs\nassociated with the ACUXE.  It also allows a logical volume to be removed from\nthe middle without deleting all volumes behind it.\n\nIf a user has 5 logical volumes and decides he wants to reconfigure volume\nnumber 3, he can now do that without removing volumes 4 \u0026 5 first.  This code\nhas been tested in our labs against all application software.\n\nSigned-off-by: Chase Maupin \u003cchase.maupin@hp.com\u003e\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "1f8ef3806c40e74733f45f436d44b3d8e9a2fa48",
      "tree": "cf580823a617be7ef3654d7cd26f3fd048db823c",
      "parents": [
        "9dc7a86e85593c834bb930f5d5aba3a19ee7a350"
      ],
      "author": {
        "name": "Mike Miller",
        "email": "mike.miller@hp.com",
        "time": "Tue Sep 13 01:25:21 2005 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Tue Sep 13 08:22:29 2005 -0700"
      },
      "message": "[PATCH] cciss: busy_initializing flag\n\nThis patch adds a flag called busy_initializing.  If there are multiple\ncontrollers in a server AND the HP agents are running it\u0027s possible the agents\nmay try to poll a card that is still initializing if the driver is removed and\nthen added again.\n\nSigned-off-by: Don Brace \u003cdab@hp.com\u003e\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "ad2b93123d2b3cb4ba9a98dd5f62acb6d6b50391",
      "tree": "250d0f5157c98c1cc650a08bcad3f9f5a6f3ee17",
      "parents": [
        "eaaf9c68e75edf0fa51c5770eb68c2a6cb5ff66b"
      ],
      "author": {
        "name": "Mike Miller",
        "email": "mike.miller@hp.com",
        "time": "Thu Jul 28 01:07:31 2005 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Thu Jul 28 08:39:01 2005 -0700"
      },
      "message": "[PATCH] cciss per disk queue\n\nThis patch adds per disk queue functionality to cciss.  Sometime back I\nsubmitted a patch but it looks like only part of what I needed.  In the 2.6\nkernel if we have more than one logical volume the driver will Oops during\nrmmod.  It seems all of the queues actually point back to the same queue.\nSo after deleting the first volume you hit a null pointer on the second\none.\n\nThis has been tested in our labs.  There is no difference in performance,\nit just fixes the Oops.\n\nSigned-off-by: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: Jens Axboe \u003caxboe@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "1da177e4c3f41524e886b7f1b8a0c1fc7321cac2",
      "tree": "0bba044c4ce775e45a88a51686b5d9f90697ea9d",
      "parents": [],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@ppc970.osdl.org",
        "time": "Sat Apr 16 15:20:36 2005 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@ppc970.osdl.org",
        "time": "Sat Apr 16 15:20:36 2005 -0700"
      },
      "message": "Linux-2.6.12-rc2\n\nInitial git repository build. I\u0027m not bothering with the full history,\neven though we have it. We can create a separate \"historical\" git\narchive of that later if we want to, and in the meantime it\u0027s about\n3.2GB when imported into git - space that would just make the early\ngit days unnecessarily complicated, when we don\u0027t have a lot of good\ninfrastructure for it.\n\nLet it rip!\n"
    }
  ]
}