)]}'
{
  "log": [
    {
      "commit": "68154e90c9d1492d570671ae181d9a8f8530da55",
      "tree": "4b4e9cfbaa587a576e7e52284c53ef99cf69ac4d",
      "parents": [
        "657e93be356f51888f56a58d2b374caefbf2fe86"
      ],
      "author": {
        "name": "FUJITA Tomonori",
        "email": "fujita.tomonori@lab.ntt.co.jp",
        "time": "Fri Apr 25 12:47:50 2008 +0200"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Tue Apr 29 09:50:34 2008 +0200"
      },
      "message": "block: add dma alignment and padding support to blk_rq_map_kern\n\nThis patch adds bio_copy_kern similar to\nbio_copy_user. blk_rq_map_kern uses bio_copy_kern instead of\nbio_map_kern if necessary.\n\nbio_copy_kern uses temporary pages and the bi_end_io callback frees\nthese pages. bio_copy_kern saves the original kernel buffer at\nbio-\u003ebi_private it doesn\u0027t use something like struct bio_map_data to\nstore the information about the caller.\n\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nCc: Tejun Heo \u003chtejun@gmail.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "f18573abcc57844a7c3c12699d40eead8728cd8a",
      "tree": "99d5dcfdfe29578bb23900e63f226022f5e87281",
      "parents": [
        "afdc1a780ef84a54b613dae6f971407748aab61c"
      ],
      "author": {
        "name": "FUJITA Tomonori",
        "email": "fujita.tomonori@lab.ntt.co.jp",
        "time": "Fri Apr 11 12:56:52 2008 +0200"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Mon Apr 21 09:50:08 2008 +0200"
      },
      "message": "block: move the padding adjustment to blk_rq_map_sg\n\nblk_rq_map_user adjusts bi_size of the last bio. It breaks the rule\nthat req-\u003edata_len (the true data length) is equal to sum(bio). It\nbroke the scsi command completion code.\n\ncommit e97a294ef6938512b655b1abf17656cf2b26f709 was introduced to fix\nthe above issue. However, the partial completion code doesn\u0027t work\nwith it. The commit is also a layer violation (scsi mid-layer should\nnot know about the block layer\u0027s padding).\n\nThis patch moves the padding adjustment to blk_rq_map_sg (suggested by\nJames). The padding works like the drain buffer. This patch breaks the\nrule that req-\u003edata_len is equal to sum(sg), however, the drain buffer\nalready broke it. So this patch just restores the rule that\nreq-\u003edata_len is equal to sub(bio) without breaking anything new.\n\nNow when a low level driver needs padding, blk_rq_map_user and\nblk_rq_map_user_iov guarantee there\u0027s enough room for padding.\nblk_rq_map_sg can safely extend the last entry of a scatter list.\n\nblk_rq_map_sg must extend the last entry of a scatter list only for a\nrequest that got through bio_copy_user_iov. This patches introduces\nnew REQ_COPY_USER flag.\n\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nCc: Tejun Heo \u003chtejun@gmail.com\u003e\nCc: Mike Christie \u003cmichaelc@cs.wisc.edu\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "afdc1a780ef84a54b613dae6f971407748aab61c",
      "tree": "67f120001c9a0a3f95fbb3ee2dc545f0886440c0",
      "parents": [
        "c5dec1c3034f1ae3503efbf641ff3b0273b64797"
      ],
      "author": {
        "name": "FUJITA Tomonori",
        "email": "fujita.tomonori@lab.ntt.co.jp",
        "time": "Fri Apr 11 12:56:51 2008 +0200"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Mon Apr 21 09:50:08 2008 +0200"
      },
      "message": "block: add bio_copy_user_iov support to blk_rq_map_user_iov\n\nWith this patch, blk_rq_map_user_iov uses bio_copy_user_iov when a low\nlevel driver needs padding or a buffer in sg_iovec isn\u0027t aligned. That\nis, it uses temporary kernel buffers instead of mapping user pages\ndirectly.\n\nWhen a LLD needs padding, later blk_rq_map_sg needs to extend the last\nentry of a scatter list. bio_copy_user_iov guarantees that there is\nenough space for padding by using temporary kernel buffers instead of\nuser pages.\n\nblk_rq_map_user_iov needs buffers in sg_iovec to be aligned. The\ncomment in blk_rq_map_user_iov indicates that drivers/scsi/sg.c also\nneeds buffers in sg_iovec to be aligned. Actually, drivers/scsi/sg.c\nworks with unaligned buffers in sg_iovec (it always uses temporary\nkernel buffers).\n\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nCc: Tejun Heo \u003chtejun@gmail.com\u003e\nCc: Mike Christie \u003cmichaelc@cs.wisc.edu\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "56d94a37f63ad1c9da3bc8e903f79d0ee1e80170",
      "tree": "f5a89d4d6df7b959ca7e1ae3cd8f54a935496cc4",
      "parents": [
        "448da4d262b5db90817ce853726ff4d9b0c2bf48"
      ],
      "author": {
        "name": "Harvey Harrison",
        "email": "harvey.harrison@gmail.com",
        "time": "Tue Mar 04 11:31:22 2008 +0100"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Tue Mar 04 11:31:22 2008 +0100"
      },
      "message": "block: fix shadowed variable warning in blk-map.c\n\nIntroduced between 2.6.25-rc2 and -rc3\nblock/blk-map.c:154:14: warning: symbol \u0027bio\u0027 shadows an earlier one\nblock/blk-map.c:110:13: originally declared here\n\nSigned-off-by: Harvey Harrison \u003charvey.harrison@gmail.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "bec419404afe8b0d60000118ca90ada4c69a3a6d",
      "tree": "4febf3a554ef432a9de40a2653131f8a60137f45",
      "parents": [
        "9d7f1e6b9b2c2e4fe029ff35f4ca1e2879864208"
      ],
      "author": {
        "name": "Adrian Bunk",
        "email": "bunk@kernel.org",
        "time": "Tue Mar 04 11:23:48 2008 +0100"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Tue Mar 04 11:28:34 2008 +0100"
      },
      "message": "unexport blk_rq_map_user_iov\n\nThis patch removes the unused export of blk_rq_map_user_iov.\n\nSigned-off-by: Adrian Bunk \u003cbunk@kernel.org\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "e3790c7d42a545e8fe8b38b513613ca96687b670",
      "tree": "0b849ba46007c4d7f7a34271a76d58e7406cbad7",
      "parents": [
        "7a85f8896f4b4a4a0249563b92af9e3161a6b467"
      ],
      "author": {
        "name": "Tejun Heo",
        "email": "htejun@gmail.com",
        "time": "Tue Mar 04 11:18:17 2008 +0100"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Tue Mar 04 11:18:17 2008 +0100"
      },
      "message": "block: separate out padding from alignment\n\nBlock layer alignment was used for two different purposes - memory\nalignment and padding.  This causes problems in lower layers because\ndrivers which only require memory alignment ends up with adjusted\nrq-\u003edata_len.  Separate out padding such that padding occurs iff\ndriver explicitly requests it.\n\nTomo: restorethe code to update bio in blk_rq_map_user\n      introduced by the commit 40b01b9bbdf51ae543a04744283bf2d56c4a6afa\n      according to padding alignment.\n\nSigned-off-by: Tejun Heo \u003chtejun@gmail.com\u003e\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "7a85f8896f4b4a4a0249563b92af9e3161a6b467",
      "tree": "616c62e3c96237e874fc0f47133fbca2160913b5",
      "parents": [
        "89b6e743788516491846724d7ef89bcac7ac9c99"
      ],
      "author": {
        "name": "FUJITA Tomonori",
        "email": "fujita.tomonori@lab.ntt.co.jp",
        "time": "Tue Mar 04 11:17:11 2008 +0100"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@carl.home.kernel.dk",
        "time": "Tue Mar 04 11:17:11 2008 +0100"
      },
      "message": "block: restore the meaning of rq-\u003edata_len to the true data length\n\nThe meaning of rq-\u003edata_len was changed to the length of an allocated\nbuffer from the true data length. It breaks SG_IO friends and\nbsg. This patch restores the meaning of rq-\u003edata_len to the true data\nlength and adds rq-\u003eextra_len to store an extended length (due to\ndrain buffer and padding).\n\nThis patch also removes the code to update bio in blk_rq_map_user\nintroduced by the commit 40b01b9bbdf51ae543a04744283bf2d56c4a6afa.\nThe commit adjusts bio according to memory alignment\n(queue_dma_alignment). However, memory alignment is NOT padding\nalignment. This adjustment also breaks SG_IO friends and bsg. Padding\nalignment needs to be fixed in a proper way (by a separate patch).\n\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nSigned-off-by: Jens Axboe \u003caxboe@carl.home.kernel.dk\u003e\n"
    },
    {
      "commit": "6b00769fe1502b4ad97bb327ef7ac971b208bfb5",
      "tree": "2ffc51176437ebf4f8a4ab13de59a32431043f15",
      "parents": [
        "40b01b9bbdf51ae543a04744283bf2d56c4a6afa"
      ],
      "author": {
        "name": "Tejun Heo",
        "email": "htejun@gmail.com",
        "time": "Tue Feb 19 11:36:35 2008 +0100"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Tue Feb 19 11:36:35 2008 +0100"
      },
      "message": "block: add request-\u003eraw_data_len\n\nWith padding and draining moved into it, block layer now may extend\nrequests as directed by queue parameters, so now a request has two\nsizes - the original request size and the extended size which matches\nthe size of area pointed to by bios and later by sgs.  The latter size\nis what lower layers are primarily interested in when allocating,\nfilling up DMA tables and setting up the controller.\n\nBoth padding and draining extend the data area to accomodate\ncontroller characteristics.  As any controller which speaks SCSI can\nhandle underflows, feeding larger data area is safe.\n\nSo, this patch makes the primary data length field, request-\u003edata_len,\nindicate the size of full data area and add a separate length field,\nrequest-\u003eraw_data_len, for the unmodified request size.  The latter is\nused to report to higher layer (userland) and where the original\nrequest size should be fed to the controller or device.\n\nSigned-off-by: Tejun Heo \u003chtejun@gmail.com\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "40b01b9bbdf51ae543a04744283bf2d56c4a6afa",
      "tree": "0f81015c01834b97fdb5646a63c3fe1a24936d81",
      "parents": [
        "56c819df77f96c3fc0c2a979e12b478403728790"
      ],
      "author": {
        "name": "Tejun Heo",
        "email": "htejun@gmail.com",
        "time": "Tue Feb 19 11:35:38 2008 +0100"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Tue Feb 19 11:35:38 2008 +0100"
      },
      "message": "block: update bio according to DMA alignment padding\n\nDMA start address and transfer size alignment for PC requests are\nachieved using bio_copy_user() instead of bio_map_user().  This works\nbecause bio_copy_user() always uses full pages and block DMA alignment\nisn\u0027t allowed to go over PAGE_SIZE.\n\nHowever, the implementation didn\u0027t update the last bio of the request\nto make this padding visible to lower layers.  This patch makes\nblk_rq_map_user() extend the last bio such that it includes the\npadding area and the size of area pointed to by the request is\nproperly aligned.\n\nSigned-off-by: Tejun Heo \u003chtejun@gmail.com\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "84e9e03c55c2456799ab19f1d577e72f721fdd39",
      "tree": "e268a42aa43b6dae3c4f4c8d5c4b2e24d6e2d65a",
      "parents": [
        "86b6c7a7f78feca58d2d8615e53aee4d59ab9dc6"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Mon Feb 18 13:51:56 2008 +0100"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Tue Feb 19 10:04:00 2008 +0100"
      },
      "message": "block: make blk_rq_map_user() clear -\u003ebio if it unmaps it\n\nThat way the interface is symmetric, and calling blk_rq_unmap_user()\non the request wont oops.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "6728cb0e6343d4068ccec13f07212e6382d3ff33",
      "tree": "5a7826dc91cf2d9cf54e8c24b40aa3c4d892c797",
      "parents": [
        "22b132102f1540dd40f3e41df88796829b685f1a"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Thu Jan 31 13:03:55 2008 +0100"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Fri Feb 01 09:26:33 2008 +0100"
      },
      "message": "block: make core bits checkpatch compliant\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    },
    {
      "commit": "86db1e29772372155db08ff48a9ceb76e11a2ad1",
      "tree": "312f38eb3245873c476c50f816b85610fef9615a",
      "parents": [
        "8324aa91d1e11a1fc25f209687a0b2e6c2ed47d0"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Tue Jan 29 14:53:40 2008 +0100"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Tue Jan 29 21:55:08 2008 +0100"
      },
      "message": "block: continue ll_rw_blk.c splitup\n\nAdds files for barrier handling, rq execution, io context handling,\nmapping data to requests, and queue settings.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n"
    }
  ]
}