)]}' { "log": [ { "commit": "c295fc05789653ef24f296299df7c5f92fe74dce", "tree": "f1b14e69ba862d41baafbb30212e918e35ba626a", "parents": [ "adda766193ea1cf3137484a9521972d080d0b7af" ], "author": { "name": "Nikanth Karthikesan", "email": "knikanth@suse.de", "time": "Tue Sep 01 22:40:15 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Sep 01 22:40:15 2009 +0200" }, "message": "block: Allow changing max_sectors_kb above the default 512\n\nThe patch \"block: Use accessor functions for queue limits\"\n(ae03bf639a5027d27270123f5f6e3ee6a412781d) changed queue_max_sectors_store()\nto use blk_queue_max_sectors() instead of directly assigning the value.\n\nBut blk_queue_max_sectors() differs a bit\n1. It sets both max_sectors_kb, and max_hw_sectors_kb\n2. Never allows one to change max_sectors_kb above BLK_DEF_MAX_SECTORS. If one\nspecifies a value greater then max_hw_sectors is set to that value but\nmax_sectors is set to BLK_DEF_MAX_SECTORS\n\nI am not sure whether blk_queue_max_sectors() should be changed, as it seems\nto be that way for a long time. And there may be callers dependent on that\nbehaviour.\n\nThis patch simply reverts to the older way of directly assigning the value to\nmax_sectors as it was before.\n\nSigned-off-by: Nikanth Karthikesan \u003cknikanth@suse.de\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "14d9fa352592582e457cf75022202766baac1348", "tree": "a2944427d12a45f3d294f52ee350bd32f315d2bb", "parents": [ "7e5f5fb09e6fc657f21816b5a18ba645a913368e" ], "author": { "name": "John Stoffel", "email": "john@stoffel.org", "time": "Tue Aug 04 22:10:17 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Aug 04 22:10:17 2009 +0200" }, "message": "Make SCSI SG v4 driver enabled by default and remove EXPERIMENTAL dependency, since udev depends on BSG\n\nMake Block Layer SG support v4 the default, since recent udev versions\ndepend on this to access serial numbers and other low level info properly.\n\nThis should be backported to older kernels as well, since most distros have\nenabled this for a long time.\n\nSigned-off-by: John Stoffel \u003cjohn@stoffel.org\u003e\nCc: stable@kernel.org\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "7e5f5fb09e6fc657f21816b5a18ba645a913368e", "tree": "90a60c56f3bdc8f40969bda9d87eb3d31a066b8e", "parents": [ "70dd5bf3b99964d52862ad2810c24cc32a553535" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Fri Jul 31 11:49:13 2009 -0400" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Sat Aug 01 10:24:35 2009 +0200" }, "message": "block: Update topology documentation\n\nUpdate topology comments and sysfs documentation based upon discussions\nwith Neil Brown.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "70dd5bf3b99964d52862ad2810c24cc32a553535", "tree": "912cef9cf7545b9019ad4c54def7f651213f2725", "parents": [ "7c958e32649e0c35801762878fb0b6da8c55a515" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Fri Jul 31 11:49:12 2009 -0400" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Sat Aug 01 10:24:35 2009 +0200" }, "message": "block: Stack optimal I/O size\n\nWhen stacking block devices ensure that optimal I/O size is scaled\naccordingly.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nReviewed-by: Mike Snitzer \u003csnitzer@redhat.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "7c958e32649e0c35801762878fb0b6da8c55a515", "tree": "610b1e685b5f634ca591865cc9f5ce22f1e3e6c1", "parents": [ "fef246672b009cf3f7a74e2fc9a76932ef2eeed2" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Fri Jul 31 11:49:11 2009 -0400" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Sat Aug 01 10:24:35 2009 +0200" }, "message": "block: Add a wrapper for setting minimum request size without a queue\n\nIntroduce blk_limits_io_min() and make blk_queue_io_min() call it.\n\nSigned-off-by: Mike Snitzer \u003csnitzer@redhat.com\u003e\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "fef246672b009cf3f7a74e2fc9a76932ef2eeed2", "tree": "41d7dcf1ece710d6e4bf387dee140e47f66e9011", "parents": [ "ed680c4ad478d0fee9740f7d029087f181346564" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Fri Jul 31 11:49:10 2009 -0400" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Sat Aug 01 10:24:35 2009 +0200" }, "message": "block: Make blk_queue_stack_limits use the new stacking interface\n\nblk_queue_stack_limits() has been superceded by blk_stack_limits() and\ndisk_stack_limits(). Wrap the function call for now, we\u0027ll deprecate it\nlater.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "56ad1740d9a8dc271e71fee234be662638c64458", "tree": "bf060081bde4063a4d02d1da63f79e412cca329c", "parents": [ "3839e4b29b4385e4b31075e7805683e2aa2a8103" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jul 28 22:11:24 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jul 28 22:11:24 2009 +0200" }, "message": "block: make the end_io functions be non-GPL exports\n\nPrior to the change for more sane end_io functions, we exported\nthe helpers with the normal EXPORT_SYMBOL(). That got changed\nto _GPL() for the new interface. Revert that particular change,\non the basis that this is basic functionality and doesn\u0027t dip\ninto internal structures. If these exports can\u0027t be non-GPL,\nthen we may as well make EXPORT_SYMBOL() imply GPL for\neverything.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "3839e4b29b4385e4b31075e7805683e2aa2a8103", "tree": "48481cbd67b72e2a62f304daff2a7d3cf86bd1f4", "parents": [ "a4e7d46407d73f35d217013b363b79a8f8eafcaa" ], "author": { "name": "Xiaotian Feng", "email": "dfeng@redhat.com", "time": "Tue Jul 28 09:11:14 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jul 28 09:11:14 2009 +0200" }, "message": "block: fix improper kobject release in blk_integrity_unregister\n\nblk_integrity_unregister should use kobject_put to release the kobject,\notherwise after bi is freed, memory of bi-\u003ekobj-\u003ename is leaked.\n\nSigned-off-by: Xiaotian Feng \u003cdfeng@redhat.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "a4e7d46407d73f35d217013b363b79a8f8eafcaa", "tree": "109996edac0c6382e7a7cfb99736e75ea5398b49", "parents": [ "a85a00a699740f6f9863f88aef22060fe1534681" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jul 28 09:07:29 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jul 28 09:07:29 2009 +0200" }, "message": "block: always assign default lock to queues\n\nMove the assignment of a default lock below blk_init_queue() to\nblk_queue_make_request(), so we also get to set the default lock\nfor -\u003emake_request_fn() based drivers. This is important since the\nqueue flag locking requires a lock to be in place.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "9cb308ce8d32a1fb3600acab6034e19a90228743", "tree": "774c9b00be1b417cc805895b4da83dd59ea144c9", "parents": [ "8f47428704c2fd6f787a6f340071b9c338b65803" ], "author": { "name": "Xiaotian Feng", "email": "dfeng@redhat.com", "time": "Fri Jul 17 15:26:26 2009 +0800" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Jul 17 16:54:15 2009 +0900" }, "message": "block: sysfs fix mismatched queue_var_{store,show} in 64bit kernel\n\nIn blk-sysfs.c, queue_var_store uses unsigned long to store data,\nbut queue_var_show uses unsigned int to show data. This causes,\n\n\t# echo 70000000000 \u003e /sys/block/\u003cdev\u003e/queue/read_ahead_kb\n\t# cat /sys/block/\u003cdev\u003e/queue/read_ahead_kb \u003d\u003e get wrong value\n\nFix it by using unsigned long.\n\nWhile at it, convert queue_rq_affinity_show() such that it uses bool\nvariable instead of explicit !\u003d 0 testing.\n\nSigned-off-by: Xiaotian Feng \u003cdfeng@redhat.com\u003e\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "0a09f4319c6d88c732ed46735f8584bbb95cac65", "tree": "4bb79b77f020c340c6873d760b9de444fbbd5ffe", "parents": [ "c9d4bc289cd1cd43c3cff97b73efe2b0b5098a92" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Jul 16 15:26:55 2009 +0900" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Jul 17 14:50:43 2009 +0900" }, "message": "block: fix failfast merge testing in elv_rq_merge_ok()\n\nCommit ab0fd1debe730ec9998678a0c53caefbd121ed10 tries to prevent merge\nof requests with different failfast settings. In elv_rq_merge_ok(),\nit compares new bio\u0027s failfast flags against the merge target\nrequest\u0027s. However, the flag testing accessors for bio and blk don\u0027t\nreturn boolean but the tested bit value directly and FAILFAST on bio\nand blk don\u0027t match, so directly comparing them with \u003d\u003d results in\nfalse negative unnecessary preventing merge of readahead requests.\n\nThis patch convert the results to boolean by negating them before\ncomparison.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nCc: Boaz Harrosh \u003cbharrosh@panasas.com\u003e\nCc: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nCc: Jeff Garzik \u003cjeff@garzik.org\u003e\n" }, { "commit": "32f2e807a3938b24d0831211e6094f9e44b2fc83", "tree": "80baac86022bc36bc07a787008642149fa205642", "parents": [ "ecb554a846f8e9d2a58f6d6c118168a63ac065aa" ], "author": { "name": "Vivek Goyal", "email": "vgoyal@redhat.com", "time": "Thu Jul 09 22:13:16 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "axboe@carl.(none)", "time": "Fri Jul 10 20:31:54 2009 +0200" }, "message": "cfq-iosched: reset oom_cfqq in cfq_set_request()\n\nIn case memory is scarce, we now default to oom_cfqq. Once memory is\navailable again, we should allocate a new cfqq and stop using oom_cfqq for\na particular io context.\n\nOnce a new request comes in, check if we are using oom_cfqq, and if yes,\ntry to allocate a new cfqq.\n\nTested the patch by forcing the use of oom_cfqq and upon next request thread\nrealized that it was using oom_cfqq and it allocated a new cfqq.\n\nSigned-off-by: Vivek Goyal \u003cvgoyal@redhat.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "76da03467a1a78811777561bbb1fa56175ee4778", "tree": "fb4a6f2b7a42213ee76aba136f74f161fefd9618", "parents": [ "8aa7e847d834ed937a9ad37a0f2ad5b8584c1ab0" ], "author": { "name": "FUJITA Tomonori", "email": "fujita.tomonori@lab.ntt.co.jp", "time": "Thu Jul 09 09:48:28 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "axboe@carl.(none)", "time": "Fri Jul 10 20:31:53 2009 +0200" }, "message": "block: call blk_scsi_ioctl_init()\n\nCurrently, blk_scsi_ioctl_init() is not called since it lacks\nan initcall marking. This causes the command table to be\nunitialized, hence somce commands are block when they should\nnot have been.\n\nThis fixes a regression introduced by commit\n018e0446890661504783f92388ecce7138c1566d\n\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "ab0fd1debe730ec9998678a0c53caefbd121ed10", "tree": "c44de6ef7d876a32c4f733fdc26d40cdcbf7d374", "parents": [ "b59e64d0ddb756af57ea032383bfd393a286a8e8" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Jul 03 12:56:18 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "axboe@carl.(none)", "time": "Fri Jul 03 21:06:45 2009 +0200" }, "message": "block: don\u0027t merge requests of different failfast settings\n\nBlock layer used to merge requests and bios with different failfast\nsettings. This caused regular IOs to fail prematurely when they were\nmerged into failfast requests for readahead.\n\nNiel Lambrechts could trigger the problem semi-reliably on ext4 when\nresuming from STR. ext4 uses readahead when reading inodes and\ncombined with the deterministic extra SATA PHY exception cycle during\nresume on the specific configuration, non-readahead inode read would\nfail causing ext4 errors. Please read the following thread for\ndetails.\n\n http://lkml.org/lkml/2009/5/23/21\n\nThis patch makes block layer reject merging if the failfast settings\ndon\u0027t match. This is correct but likely to lower IO performance by\npreventing regular IOs from mingling into surrounding readahead\nrequests. Changes to allow such mixed merges and handle errors\ncorrectly will be added later.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nReported-by: Niel Lambrechts \u003cniel.lambrechts@gmail.com\u003e\nCc: Theodore Tso \u003ctytso@mit.edu\u003e\nSigned-off-by: Jens Axboe \u003caxboe@carl.(none)\u003e\n" }, { "commit": "b706f64281b24d8b1fdc8ae883700131d365c412", "tree": "3eed31b51cdcb2787ff2d90eaf39b19fba242a9f", "parents": [ "db64f680ba4b5c56c4be59f0698000df89ff0281" ], "author": { "name": "Shan Wei", "email": "shanwei@cn.fujitsu.com", "time": "Wed Jul 01 12:41:14 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Jul 01 12:41:14 2009 +0200" }, "message": "cfq-iosched: remove redundant check for NULL cfqq in cfq_set_request()\n\nWith the changes for falling back to an oom_cfqq, we never fail\nto find/allocate a queue in cfq_get_queue(). So remove the check.\n\nSigned-off-by: Shan Wei \u003cshanwei@cn.fujitsu.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "db64f680ba4b5c56c4be59f0698000df89ff0281", "tree": "f094e64952ba746525e4695256a70e0d32553065", "parents": [ "018e0446890661504783f92388ecce7138c1566d" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Jun 30 09:35:44 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Jul 01 10:56:26 2009 +0200" }, "message": "blocK: Restore barrier support for md and probably other virtual devices.\n\nThe next_ordered flag is only meaningful for devices that use __make_request.\nSo move the test against next_ordered out of generic code and in to\n__make_request\n\nSince this test was added, barriers have not worked on md or any\ndevices that don\u0027t use __make_request and so don\u0027t bother to set\nnext_ordered. (dm explicitly sets something other than\nQUEUE_ORDERED_NONE since\n commit 99360b4c18f7675b50d283301d46d755affe75fd\nbut notes in the comments that it is otherwise meaningless).\n\nCc: Ken Milmore \u003cken.milmore@googlemail.com\u003e\nCc: stable@kernel.org\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "018e0446890661504783f92388ecce7138c1566d", "tree": "d555758047dde4a26b2489d397a5a86be53723b9", "parents": [ "7878cba9f0037f5599004b03a1260b32d9050360" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Jun 26 16:27:10 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Jul 01 10:56:26 2009 +0200" }, "message": "block: get rid of queue-private command filter\n\nThe initial patches to support this through sysfs export were broken\nand have been if 0\u0027ed out in any release. So lets just kill the code\nand reclaim some space in struct request_queue, if anyone would later\nlike to fixup the sysfs bits, the git history can easily restore\nthe removed bits.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "7878cba9f0037f5599004b03a1260b32d9050360", "tree": "bff5e1a47b6e64e45df0428925cc6db8542cad62", "parents": [ "6118b70b3a0b4c583439bb77600194c82f220ce3" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Fri Jun 26 15:37:49 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Jul 01 10:56:25 2009 +0200" }, "message": "block: Create bip slabs with embedded integrity vectors\n\nThis patch restores stacking ability to the block layer integrity\ninfrastructure by creating a set of dedicated bip slabs. Each bip slab\nhas an embedded bio_vec array at the end. This cuts down on memory\nallocations and also simplifies the code compared to the original bvec\nversion. Only the largest bip slab is backed by a mempool. The pool is\ncontained in the bio_set so stacking drivers can ensure forward\nprogress.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003caxboe@carl.(none)\u003e\n" }, { "commit": "6118b70b3a0b4c583439bb77600194c82f220ce3", "tree": "6966f1b059f1bdadc0d679067796d9b4bf9a22c3", "parents": [ "d5036d770f871bd34c9cfd955e6dee692e1e8e81" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 30 09:34:12 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Jul 01 10:56:25 2009 +0200" }, "message": "cfq-iosched: get rid of the need for __GFP_NOFAIL in cfq_find_alloc_queue()\n\nSetup an emergency fallback cfqq that we allocate at IO scheduler init\ntime. If the slab allocation fails in cfq_find_alloc_queue(), we\u0027ll just\npunt IO to that cfqq instead. This ensures that cfq_find_alloc_queue()\nnever fails without having to ensure free memory.\n\nOn cfqq lookup, always try to allocate a new cfqq if the given cfq io\ncontext has the oom_cfqq assigned. This ensures that we only temporarily\npunt to this shared queue.\n\nReviewed-by: Jeff Moyer \u003cjmoyer@redhat.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "d5036d770f871bd34c9cfd955e6dee692e1e8e81", "tree": "d0718922511121e96bdd385d6c28a254cfc93519", "parents": [ "61fd21670d048017c81e62f60894ef1b04b481db" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Jun 26 10:44:34 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Jul 01 10:56:25 2009 +0200" }, "message": "cfq-iosched: move cfqq initialization out of cfq_find_alloc_queue()\n\nWe\u0027re going to be needing that init code outside of that function\nto get rid of the __GFP_NOFAIL in cfqq allocation.\n\nReviewed-by: Jeff Moyer \u003cjmoyer@redhat.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "111986593561fc4c94a1fba3f3cd84476fb40b22", "tree": "8af40a65c9d4a7abf0b6eaa461562b5a54f15dd2", "parents": [ "93bdcba5a7e55307e27671594c3cd8b4669b9e7a" ], "author": { "name": "FUJITA Tomonori", "email": "fujita.tomonori@lab.ntt.co.jp", "time": "Wed Jun 17 15:10:11 2009 +0900" }, "committer": { "name": "James Bottomley", "email": "James.Bottomley@HansenPartnership.com", "time": "Sun Jun 21 10:52:42 2009 -0500" }, "message": "block: revert \"bsg: setting rq-\u003ebio to NULL\"\n\nThe SMP handler (sas_smp_request) was fixed to use the block API\nproperly, so we don\u0027t need this workaround to avoid blk_put_request()\nwarning.\n\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nSigned-off-by: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\n" }, { "commit": "f740f5ca056f0a4eff3abdf272a8a4ba3965d57d", "tree": "6340ea4b20227733b380816d0552127de110905c", "parents": [ "90c699a9ee4be165966d40f1837909ccb8890a68" ], "author": { "name": "Randy Dunlap", "email": "randy.dunlap@oracle.com", "time": "Fri Jun 19 09:18:32 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Jun 19 09:18:32 2009 +0200" }, "message": "Fix kernel-doc parameter name typo in blk-settings.c:\n\nWarning(block/blk-settings.c:108): No description found for parameter \u0027lim\u0027\nWarning(block/blk-settings.c:108): Excess function parameter \u0027limits\u0027 description in \u0027blk_set_default_limits\u0027\n\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "90c699a9ee4be165966d40f1837909ccb8890a68", "tree": "ff136ce7b73c7d7bbf5eb4241d01cb3b930d3566", "parents": [ "3a02c8e8142f7f133d4c6e72bc3e1d830e6b8b9e" ], "author": { "name": "Bartlomiej Zolnierkiewicz", "email": "bzolnier@gmail.com", "time": "Fri Jun 19 08:08:50 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Jun 19 08:08:50 2009 +0200" }, "message": "block: rename CONFIG_LBD to CONFIG_LBDAF\n\nFollow-up to \"block: enable by default support for large devices\nand files on 32-bit archs\".\n\nRename CONFIG_LBD to CONFIG_LBDAF to:\n- allow update of existing [def]configs for \"default y\" change\n- reflect that it is used also for large files support nowadays\n\nSigned-off-by: Bartlomiej Zolnierkiewicz \u003cbzolnier@gmail.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "3a02c8e8142f7f133d4c6e72bc3e1d830e6b8b9e", "tree": "7485ad50ba3b773d186119d48cba2a124e667125", "parents": [ "ddeb9c3e949751992628628d000915a317df52c4" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Thu Jun 18 09:56:03 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Thu Jun 18 09:56:20 2009 +0200" }, "message": "block: Fix bounce_pfn setting\n\nCorrect stacking bounce_pfn limit setting and prevent warnings on\n32-bit.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "6fd03301d76bc439382710e449f58efbb233df1b", "tree": "3c8a3217aed67319683ffc1debccdb5b3245b16c", "parents": [ "cd5232bd6be2d215a800f3d88c287ca791debfbe", "e4792aa30f9d33584d7192685ed149cc5fee737f" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 12:57:37 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 12:57:37 2009 -0700" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core-2.6\n\n* git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core-2.6: (64 commits)\n debugfs: use specified mode to possibly mark files read/write only\n debugfs: Fix terminology inconsistency of dir name to mount debugfs filesystem.\n xen: remove driver_data direct access of struct device from more drivers\n usb: gadget: at91_udc: remove driver_data direct access of struct device\n uml: remove driver_data direct access of struct device\n block/ps3: remove driver_data direct access of struct device\n s390: remove driver_data direct access of struct device\n parport: remove driver_data direct access of struct device\n parisc: remove driver_data direct access of struct device\n of_serial: remove driver_data direct access of struct device\n mips: remove driver_data direct access of struct device\n ipmi: remove driver_data direct access of struct device\n infiniband: ehca: remove driver_data direct access of struct device\n ibmvscsi: gadget: at91_udc: remove driver_data direct access of struct device\n hvcs: remove driver_data direct access of struct device\n xen block: remove driver_data direct access of struct device\n thermal: remove driver_data direct access of struct device\n scsi: remove driver_data direct access of struct device\n pcmcia: remove driver_data direct access of struct device\n PCIE: remove driver_data direct access of struct device\n ...\n\nManually fix up trivial conflicts due to different direct driver_data\ndirect access fixups in drivers/block/{ps3disk.c,ps3vram.c}\n" }, { "commit": "e212d6f25084e8e9b02a04ba514d7bb1e4a4924a", "tree": "a94638953a7aa7f0bbd6f5d08fa3c649ce0ef8ce", "parents": [ "5ced504b1bd1979378de35c56aa5d3d79fb5033f" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Tue Jun 16 11:19:36 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 16 11:19:36 2009 +0200" }, "message": "block: remove some includings of blktrace_api.h\n\nWhen porting blktrace to tracepoints, we changed to trace/block.h\nfor trace prober declarations.\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "e475bba2fdee9c3dbfe25f026f8fb8de69508ad2", "tree": "cb2a050b58fbd8cd7a4d82349164622fedc2c6d0", "parents": [ "6923715ae39ed39ac2fc1993e5061668f4f71ad0" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Tue Jun 16 08:23:52 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 16 08:23:52 2009 +0200" }, "message": "block: Introduce helper to reset queue limits to default values\n\nDM reuses the request queue when swapping in a new device table\nIntroduce blk_set_default_limits() which can be used to reset the the\nqueue_limits prior to stacking devices.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nAcked-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\nAcked-by: Mike Snitzer \u003csnitzer@redhat.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "6923715ae39ed39ac2fc1993e5061668f4f71ad0", "tree": "98810062c76a07bf6914a192806ba2f927b3cb41", "parents": [ "a979eff1811a07f5fd331c5f6f727370747b42ad" ], "author": { "name": "Jeff Moyer", "email": "jmoyer@redhat.com", "time": "Fri Jun 12 15:29:30 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 16 08:21:04 2009 +0200" }, "message": "cfq: remove extraneous \u0027\\n\u0027 in blktrace output\n\nI noticed a blank line in blktrace output. This patch fixes that.\n\nSigned-off-by: Jeff Moyer \u003cjmoyer@redhat.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "0989a025d2f4f9f51ea641bd26c563c53dc63f55", "tree": "5b4f29d3b1a3d09d3052e0c18d63dba8a946da86", "parents": [ "81be834713a7d6b9463663145d493fe9daee2d61" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Jun 12 14:42:56 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 16 08:21:03 2009 +0200" }, "message": "block: don\u0027t overwrite bdi-\u003estate after bdi_init() has been run\n\nMove the defaults to where we do the init of the backing_dev_info.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "81be834713a7d6b9463663145d493fe9daee2d61", "tree": "1f70583e9148554abaf4b6128bdb7d9bd8bacb6c", "parents": [ "03347e2592078a90df818670fddf97a33eec70fb" ], "author": { "name": "Gui Jianfeng", "email": "guijianfeng@cn.fujitsu.com", "time": "Fri Jun 12 15:27:50 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 16 08:21:03 2009 +0200" }, "message": "cfq: cleanup for last_end_request in cfq_data\n\nActually, last_end_request in cfq_data isn\u0027t used now. So lets\njust remove it.\n\nSigned-off-by: Gui Jianfeng \u003cguijianfeng@cn.fujitsu.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "2bdf914915e98fe82495d05741a57e37f4b604e8", "tree": "6d598776789ff0ccd29b46fb6d08d183896e982f", "parents": [ "1ce8a0d396288f28070483a8190843c23b8282f4" ], "author": { "name": "Kay Sievers", "email": "kay.sievers@vrfy.org", "time": "Thu Apr 30 15:23:42 2009 +0200" }, "committer": { "name": "Greg Kroah-Hartman", "email": "gregkh@suse.de", "time": "Mon Jun 15 21:30:26 2009 -0700" }, "message": "Driver Core: bsg: add nodename for bsg driver\n\nThis adds support to the BSG driver to report the proper device name to\nuserspace for the bsg devices.\n\nSigned-off-by: Kay Sievers \u003ckay.sievers@vrfy.org\u003e\nSigned-off-by: Jan Blunck \u003cjblunck@suse.de\u003e\nSigned-off-by: Greg Kroah-Hartman \u003cgregkh@suse.de\u003e\n" }, { "commit": "b03f38b685e2e1db174fb8982930e789a516f414", "tree": "8ad84738e433409647a1450a991dba1ba90d7921", "parents": [ "f7a386c5b8ff34cd84ae922603d1c6f9d234edee" ], "author": { "name": "Kay Sievers", "email": "kay.sievers@vrfy.org", "time": "Thu Apr 30 15:23:42 2009 +0200" }, "committer": { "name": "Greg Kroah-Hartman", "email": "gregkh@suse.de", "time": "Mon Jun 15 21:30:25 2009 -0700" }, "message": "Driver Core: block: add nodename support for block drivers.\n\nThis adds support for block drivers to report their requested nodename\nto userspace. It also updates a number of block drivers to provide the\nneeded subdirectory and device name to be used for them.\n\nSigned-off-by: Kay Sievers \u003ckay.sievers@vrfy.org\u003e\nSigned-off-by: Jan Blunck \u003cjblunck@suse.de\u003e\nSigned-off-by: Greg Kroah-Hartman \u003cgregkh@suse.de\u003e\n" }, { "commit": "8ebf975608aaebd7feb33d77f07ba21a6380e086", "tree": "6de4ee1dd3ede890169644ea586ed7c8c9d8f7b2", "parents": [ "4b4f1d017815f96737ca4a62f90e5a1f0b9f02d6" ], "author": { "name": "Randy Dunlap", "email": "randy.dunlap@oracle.com", "time": "Thu Jun 11 20:00:41 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jun 11 20:14:23 2009 -0700" }, "message": "block: fix kernel-doc in recent block/ changes\n\nFix kernel-doc warnings in recently changed block/ source code.\n\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "c9059598ea8981d02356eead3188bf7fa4d717b8", "tree": "03e73b20a30e988da7c6a3e0ad93b2dc5843274d", "parents": [ "0a33f80a8373eca7f4bea3961d1346c3815fa5ed", "b0fd271d5fba0b2d00888363f3869e3f9b26caa9" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jun 11 10:52:27 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jun 11 11:10:35 2009 -0700" }, "message": "Merge branch \u0027for-2.6.31\u0027 of git://git.kernel.dk/linux-2.6-block\n\n* \u0027for-2.6.31\u0027 of git://git.kernel.dk/linux-2.6-block: (153 commits)\n block: add request clone interface (v2)\n floppy: fix hibernation\n ramdisk: remove long-deprecated \"ramdisk\u003d\" boot-time parameter\n fs/bio.c: add missing __user annotation\n block: prevent possible io_context-\u003erefcount overflow\n Add serial number support for virtio_blk, V4a\n block: Add missing bounce_pfn stacking and fix comments\n Revert \"block: Fix bounce limit setting in DM\"\n cciss: decode unit attention in SCSI error handling code\n cciss: Remove no longer needed sendcmd reject processing code\n cciss: change SCSI error handling routines to work with interrupts enabled.\n cciss: separate error processing and command retrying code in sendcmd_withirq_core()\n cciss: factor out fix target status processing code from sendcmd functions\n cciss: simplify interface of sendcmd() and sendcmd_withirq()\n cciss: factor out core of sendcmd_withirq() for use by SCSI error handling code\n cciss: Use schedule_timeout_uninterruptible in SCSI error handling code\n block: needs to set the residual length of a bidi request\n Revert \"block: implement blkdev_readpages\"\n block: Fix bounce limit setting in DM\n Removed reference to non-existing file Documentation/PCI/PCI-DMA-mapping.txt\n ...\n\nManually fix conflicts with tracing updates in:\n\tblock/blk-sysfs.c\n\tdrivers/ide/ide-atapi.c\n\tdrivers/ide/ide-cd.c\n\tdrivers/ide/ide-floppy.c\n\tdrivers/ide/ide-tape.c\n\tinclude/trace/events/block.h\n\tkernel/trace/blktrace.c\n" }, { "commit": "27951daa71f1c91300ae4de9441916d1ffe2b078", "tree": "72d9ecde8c784c0837b7caf64b97fac5ffd5a424", "parents": [ "59c288ffb6dfb55bdd6bfe6826ab6203ff791930", "e8e7526c3c0863be25ab03a0871ee0978de5ba50" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jun 11 10:00:03 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jun 11 10:00:03 2009 -0700" }, "message": "Merge branch \u0027for-2.6.31\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/bart/ide-2.6\n\n* \u0027for-2.6.31\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/bart/ide-2.6: (28 commits)\n ide-tape: fix debug call\n alim15x3: Remove historical hacks, re-enable init_hwif for PowerPC\n ide-dma: don\u0027t reset request fields on dma_timeout_retry()\n ide: drop rq-\u003edata handling from ide_map_sg()\n ide-atapi: kill unused fields and callbacks\n ide-tape: simplify read/write functions\n ide-tape: use byte size instead of sectors on rw issue functions\n ide-tape: unify r/w init paths\n ide-tape: kill idetape_bh\n ide-tape: use standard data transfer mechanism\n ide-tape: use single continuous buffer\n ide-atapi,tape,floppy: allow -\u003epc_callback() to change rq-\u003edata_len\n ide-tape,floppy: fix failed command completion after request sense\n ide-pm: don\u0027t abuse rq-\u003edata\n ide-cd,atapi: use bio for internal commands\n ide-atapi: convert ide-{floppy,tape} to using preallocated sense buffer\n ide-cd: convert to using generic sense request\n ide: add helpers for preparing sense requests\n ide-cd: don\u0027t abuse rq-\u003ebuffer\n ide-atapi: don\u0027t abuse rq-\u003ebuffer\n ...\n" }, { "commit": "b0fd271d5fba0b2d00888363f3869e3f9b26caa9", "tree": "0ffd49c013476e3dc96c8bcb2ddc4c1828797be5", "parents": [ "5e50b9ef975219304cc91d601530994861585bfe" ], "author": { "name": "Kiyoshi Ueda", "email": "k-ueda@ct.jp.nec.com", "time": "Thu Jun 11 13:10:16 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Thu Jun 11 13:11:05 2009 +0200" }, "message": "block: add request clone interface (v2)\n\nThis patch adds the following 2 interfaces for request-stacking drivers:\n\n - blk_rq_prep_clone(struct request *clone, struct request *orig,\n\t\t struct bio_set *bs, gfp_t gfp_mask,\n\t\t int (*bio_ctr)(struct bio *, struct bio*, void *),\n\t\t void *data)\n * Clones bios in the original request to the clone request\n (bio_ctr is called for each cloned bios.)\n * Copies attributes of the original request to the clone request.\n The actual data parts (e.g. -\u003ecmd, -\u003ebuffer, -\u003esense) are not\n copied.\n\n - blk_rq_unprep_clone(struct request *clone)\n * Frees cloned bios from the clone request.\n\nRequest stacking drivers (e.g. request-based dm) need to make a clone\nrequest for a submitted request and dispatch it to other devices.\n\nTo allocate request for the clone, request stacking drivers may not\nbe able to use blk_get_request() because the allocation may be done\nin an irq-disabled context.\nSo blk_rq_prep_clone() takes a request allocated by the caller\nas an argument.\n\nFor each clone bio in the clone request, request stacking drivers\nshould be able to set up their own completion handler.\nSo blk_rq_prep_clone() takes a callback function which is called\nfor each clone bio, and a pointer for private data which is passed\nto the callback.\n\nNOTE:\nblk_rq_prep_clone() doesn\u0027t copy any actual data of the original\nrequest. Pages are shared between original bios and cloned bios.\nSo caller must not complete the original request before the clone\nrequest.\n\nSigned-off-by: Kiyoshi Ueda \u003ck-ueda@ct.jp.nec.com\u003e\nSigned-off-by: Jun\u0027ichi Nomura \u003cj-nomura@ce.jp.nec.com\u003e\nCc: Boaz Harrosh \u003cbharrosh@panasas.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "862366118026a358882eefc70238dbcc3db37aac", "tree": "4eb62bc10327a5afac064a95a091ea05ecd2acc1", "parents": [ "57eee9ae7bbcfb692dc96c739a5184adb6349733", "511b01bdf64ad8a38414096eab283c7784aebfc4" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 19:53:40 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 19:53:40 2009 -0700" }, "message": "Merge branch \u0027tracing-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027tracing-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (244 commits)\n Revert \"x86, bts: reenable ptrace branch trace support\"\n tracing: do not translate event helper macros in print format\n ftrace/documentation: fix typo in function grapher name\n tracing/events: convert block trace points to TRACE_EVENT(), fix !CONFIG_BLOCK\n tracing: add protection around module events unload\n tracing: add trace_seq_vprint interface\n tracing: fix the block trace points print size\n tracing/events: convert block trace points to TRACE_EVENT()\n ring-buffer: fix ret in rb_add_time_stamp\n ring-buffer: pass in lockdep class key for reader_lock\n tracing: add annotation to what type of stack trace is recorded\n tracing: fix multiple use of __print_flags and __print_symbolic\n tracing/events: fix output format of user stack\n tracing/events: fix output format of kernel stack\n tracing/trace_stack: fix the number of entries in the header\n ring-buffer: discard timestamps that are at the start of the buffer\n ring-buffer: try to discard unneeded timestamps\n ring-buffer: fix bug in ring_buffer_discard_commit\n ftrace: do not profile functions when disabled\n tracing: make trace pipe recognize latency format flag\n ...\n" }, { "commit": "d9c7d394a8ebacb60097b192939ae9f15235225e", "tree": "4fbf9c7677acb03c23d05faba1a4b0bcfb6702b4", "parents": [ "1d589bb16b825b3a7b4edd34d997f1f1f953033d" ], "author": { "name": "Nikanth Karthikesan", "email": "knikanth@novell.com", "time": "Wed Jun 10 12:57:06 2009 -0700" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Jun 10 23:07:15 2009 +0200" }, "message": "block: prevent possible io_context-\u003erefcount overflow\n\nCurrently io_context has an atomic_t(32-bit) as refcount. In the case of\ncfq, for each device against whcih a task does I/O, a reference to the\nio_context would be taken. And when there are multiple process sharing\nio_contexts(CLONE_IO) would also have a reference to the same io_context.\n\nTheoretically the possible maximum number of processes sharing the same\nio_context + the number of disks/cfq_data referring to the same io_context\ncan overflow the 32-bit counter on a very high-end machine.\n\nEven though it is an improbable case, let us make it atomic_long_t.\n\nSigned-off-by: Nikanth Karthikesan \u003cknikanth@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "55782138e47d9baf2f7d3a7af9e7cf42adf72c56", "tree": "c7ccabae20e27bbeb08b69a358e8b86c98d1d9f3", "parents": [ "f57a8a1911342265e7acdc190333c4e9235a6632" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Tue Jun 09 13:43:05 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Jun 09 12:34:23 2009 -0400" }, "message": "tracing/events: convert block trace points to TRACE_EVENT()\n\nTRACE_EVENT is a more generic way to define tracepoints. Doing so adds\nthese new capabilities to this tracepoint:\n\n - zero-copy and per-cpu splice() tracing\n - binary tracing without printf overhead\n - structured logging records exposed under /debug/tracing/events\n - trace events embedded in function tracer output and other plugins\n - user-defined, per tracepoint filter expressions\n ...\n\nCons:\n\n - no dev_t info for the output of plug, unplug_timer and unplug_io events.\n no dev_t info for getrq and sleeprq events if bio \u003d\u003d NULL.\n no dev_t info for rq_abort,...,rq_requeue events if rq-\u003erq_disk \u003d\u003d NULL.\n\n This is mainly because we can\u0027t get the deivce from a request queue.\n But this may change in the future.\n\n - A packet command is converted to a string in TP_assign, not TP_print.\n While blktrace do the convertion just before output.\n\n Since pc requests should be rather rare, this is not a big issue.\n\n - In blktrace, an event can have 2 different print formats, but a TRACE_EVENT\n has a unique format, which means we have some unused data in a trace entry.\n\n The overhead is minimized by using __dynamic_array() instead of __array().\n\nI\u0027ve benchmarked the ioctl blktrace vs the splice based TRACE_EVENT tracing:\n\n dd dd + ioctl blktrace dd + TRACE_EVENT (splice)\n1 7.36s, 42.7 MB/s 7.50s, 42.0 MB/s 7.41s, 42.5 MB/s\n2 7.43s, 42.3 MB/s 7.48s, 42.1 MB/s 7.43s, 42.4 MB/s\n3 7.38s, 42.6 MB/s 7.45s, 42.2 MB/s 7.41s, 42.5 MB/s\n\nSo the overhead of tracing is very small, and no regression when using\nthose trace events vs blktrace.\n\nAnd the binary output of TRACE_EVENT is much smaller than blktrace:\n\n # ls -l -h\n -rw-r--r-- 1 root root 8.8M 06-09 13:24 sda.blktrace.0\n -rw-r--r-- 1 root root 195K 06-09 13:24 sda.blktrace.1\n -rw-r--r-- 1 root root 2.7M 06-09 13:25 trace_splice.out\n\nFollowing are some comparisons between TRACE_EVENT and blktrace:\n\nplug:\n kjournald-480 [000] 303.084981: block_plug: [kjournald]\n kjournald-480 [000] 303.084981: 8,0 P N [kjournald]\n\nunplug_io:\n kblockd/0-118 [000] 300.052973: block_unplug_io: [kblockd/0] 1\n kblockd/0-118 [000] 300.052974: 8,0 U N [kblockd/0] 1\n\nremap:\n kjournald-480 [000] 303.085042: block_remap: 8,0 W 102736992 + 8 \u003c- (8,8) 33384\n kjournald-480 [000] 303.085043: 8,0 A W 102736992 + 8 \u003c- (8,8) 33384\n\nbio_backmerge:\n kjournald-480 [000] 303.085086: block_bio_backmerge: 8,0 W 102737032 + 8 [kjournald]\n kjournald-480 [000] 303.085086: 8,0 M W 102737032 + 8 [kjournald]\n\ngetrq:\n kjournald-480 [000] 303.084974: block_getrq: 8,0 W 102736984 + 8 [kjournald]\n kjournald-480 [000] 303.084975: 8,0 G W 102736984 + 8 [kjournald]\n\n bash-2066 [001] 1072.953770: 8,0 G N [bash]\n bash-2066 [001] 1072.953773: block_getrq: 0,0 N 0 + 0 [bash]\n\nrq_complete:\n konsole-2065 [001] 300.053184: block_rq_complete: 8,0 W () 103669040 + 16 [0]\n konsole-2065 [001] 300.053191: 8,0 C W 103669040 + 16 [0]\n\n ksoftirqd/1-7 [001] 1072.953811: 8,0 C N (5a 00 08 00 00 00 00 00 24 00) [0]\n ksoftirqd/1-7 [001] 1072.953813: block_rq_complete: 0,0 N (5a 00 08 00 00 00 00 00 24 00) 0 + 0 [0]\n\nrq_insert:\n kjournald-480 [000] 303.084985: block_rq_insert: 8,0 W 0 () 102736984 + 8 [kjournald]\n kjournald-480 [000] 303.084986: 8,0 I W 102736984 + 8 [kjournald]\n\nChangelog from v2 -\u003e v3:\n\n- use the newly introduced __dynamic_array().\n\nChangelog from v1 -\u003e v2:\n\n- use __string() instead of __array() to minimize the memory required\n to store hex dump of rq-\u003ecmd().\n\n- support large pc requests.\n\n- add missing blk_fill_rwbs_rq() in block_rq_requeue TRACE_EVENT.\n\n- some cleanups.\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4A2DF669.5070905@cn.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "c1d4c41f2fdfe66dea957b76d005affba3e56b26", "tree": "9436a0f4417c1f938103a55c739c6c6e1fdbf94b", "parents": [ "3af968e066d593bc4dacc021715f3e95ddf0996f" ], "author": { "name": "FUJITA Tomonori", "email": "fujita.tomonori@lab.ntt.co.jp", "time": "Tue Jun 09 15:17:37 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 09 15:17:37 2009 +0200" }, "message": "bsg: setting rq-\u003ebio to NULL\n\nDue to commit 1cd96c242a829d52f7a5ae98f554ca9775429685 (\"block: WARN\nin __blk_put_request() for potential bio leak\"), BSG SMP requests get\nthe false warnings:\n\nWARNING: at block/blk-core.c:1068 __blk_put_request+0x52/0xc0()\n\nThis sets rq-\u003ebio to NULL to avoid that false warnings.\n\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "77634f33d4078542cf1087995cced0ffdae25aa2", "tree": "43d15cfb43bcfb6af567e1203419ad60ef2cb160", "parents": [ "9df1bb9b516daeece159ab7fb262d01a0359247c" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Tue Jun 09 06:23:22 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 09 06:23:22 2009 +0200" }, "message": "block: Add missing bounce_pfn stacking and fix comments\n\nDM no longer needs to set limits explicitly when calling blk_stack_limits.\nLet the latter automatically deal with bounce_pfn scaling.\n\nFix kerneldoc variable names.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "9df1bb9b516daeece159ab7fb262d01a0359247c", "tree": "602c7b02e85b031d0269a1f70ece81bac524c0ac", "parents": [ "3969251b80a7b143d01576780073fe0cc9ef6253" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 09 06:22:57 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 09 06:22:57 2009 +0200" }, "message": "Revert \"block: Fix bounce limit setting in DM\"\n\nThis reverts commit a05c0205ba031c01bba33a21bf0a35920eb64833.\n\nDM doesn\u0027t need to access the bounce_pfn directly.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "dbb66c4be020b01dc2f3d7c609ddb0e09d2c0af7", "tree": "b80ec96749fdc8f26a33496ee4593ddbcc58f6ed", "parents": [ "172124e220f1854acc99ee394671781b8b5e2120" ], "author": { "name": "FUJITA Tomonori", "email": "fujita.tomonori@lab.ntt.co.jp", "time": "Tue Jun 09 05:47:10 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 09 05:47:10 2009 +0200" }, "message": "block: needs to set the residual length of a bidi request\n\nTejun\u0027s \"block: set rq-\u003eresid_len to blk_rq_bytes() on issue\" patch\nseems to be incomplete; It doesn\u0027t set rq-\u003eresid_len to blk_rq_bytes()\nfor a bidi request (req-\u003enext_rq). As a result, all bidi users are\nbroken.\n\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nAcked-by: Tejun Heo \u003ctj@kernel.org\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "a05c0205ba031c01bba33a21bf0a35920eb64833", "tree": "517c7682fc415cdb122ee7fcfc75eff674cc7b78", "parents": [ "dbdc9dd342f0a7e32f40f0d4ade662bdfe057484" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Wed Jun 03 09:33:18 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Jun 03 09:33:18 2009 +0200" }, "message": "block: Fix bounce limit setting in DM\n\nblk_queue_bounce_limit() is more than a wrapper about the request queue\nlimits.bounce_pfn variable. Introduce blk_queue_bounce_pfn() which can\nbe called by stacking drivers that wish to set the bounce limit\nexplicitly.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "53c663ce0f39ba8e8ef652e400b317bc60ac7f19", "tree": "5d72723bbc35e4b35734fe770b5022192c4f92c9", "parents": [ "c143dc903d7c0b15f5052e00b2c7de33a8b4299c" ], "author": { "name": "Kiyoshi Ueda", "email": "k-ueda@ct.jp.nec.com", "time": "Tue Jun 02 08:44:01 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Jun 02 08:44:01 2009 +0200" }, "message": "block: fix a possible oops on elv_abort_queue()\n\nI found one more mis-conversion to the \u0027request is always dequeued\nwhen completing\u0027 model in elv_abort_queue() during code inspection.\nAlthough I haven\u0027t hit any problem caused by this mis-conversion yet\nand just done compile/boot test, please apply if you have no problem.\n\nRequest must be dequeued when it completes.\nHowever, elv_abort_queue() completes requests without dequeueing.\nThis will cause oops in the __blk_end_request_all().\nThis patch fixes the oops.\n\nSigned-off-by: Kiyoshi Ueda \u003ck-ueda@ct.jp.nec.com\u003e\nSigned-off-by: Jun\u0027ichi Nomura \u003cj-nomura@ce.jp.nec.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "c143dc903d7c0b15f5052e00b2c7de33a8b4299c", "tree": "6c7d82a398d92e48ee01563a0fc6f9a13ec442e4", "parents": [ "5d85d3247cc3555215d7d11c78576a396c98e4d9" ], "author": { "name": "James Bottomley", "email": "James.Bottomley@HansenPartnership.com", "time": "Sat May 30 06:43:49 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Sat May 30 06:43:49 2009 +0200" }, "message": "block: fix an oops on BLKPREP_KILL\n\nDoing a bit of torture testing, I ran across a BUG in the block\nsubsystem (at blk-core.c:2048): the test for if the request is queued.\n\nIt turns out the trigger was a BLKPREP_KILL coming out of the SCSI prep\nfunction. Currently for BLKPREP_KILL requests, we send them straight\ninto __blk_end_request_all() with an error, but they\u0027ve never been\ndequeued, so they trip the bug. Fix this by starting requests before\nkilling them.\n\nSigned-off-by: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "5d85d3247cc3555215d7d11c78576a396c98e4d9", "tree": "4db90509907b51425706add2239ad02d57cbef4a", "parents": [ "3c4198e874cde694f5ea1463706873e7907bdb18" ], "author": { "name": "Mike Snitzer", "email": "snitzer@redhat.com", "time": "Thu May 28 11:04:53 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Thu May 28 11:04:53 2009 +0200" }, "message": "block: export blk_stack_limits()\n\nDM needs to use blk_stack_limits(), so it needs to be exported.\n\nAcked-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "3c4198e874cde694f5ea1463706873e7907bdb18", "tree": "2315e8e86996c98ddfa74059dc61255317bef0eb", "parents": [ "ba396a6c104682dfe5c8b4fbbf5974d5ac9f3687" ], "author": { "name": "Kiyoshi Ueda", "email": "k-ueda@ct.jp.nec.com", "time": "Wed May 27 14:50:02 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed May 27 14:50:02 2009 +0200" }, "message": "block: fix no diskstat problem\n\nThe commit below in 2.6-block/for-2.6.31 causes no diskstat problem\nbecause the blk_discard_rq() check was added with \u0027\u0026\u0026\u0027.\nIt should be \u0027blk_fs_request() || blk_discard_rq()\u0027.\nThis patch does it and fixes the no diskstat problem.\nPlease review and apply.\n\n------ /proc/diskstat without this patch -------------------------------------\n 8 0 sda 0 0 0 0 0 0 0 0 0 0 0\n------------------------------------------------------------------------------\n\n----- /proc/diskstat with this patch applied ---------------------------------\n 8 0 sda 4186 303 373621 61600 9578 3859 107468 169479 2 89755 231059\n------------------------------------------------------------------------------\n\n--------------------------------------------------------------------------\ncommit c69d48540c201394d08cb4d48b905e001313d9b8\nAuthor: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nDate: Fri Apr 24 08:12:19 2009 +0200\n\n block: include discard requests in IO accounting\n\n We currently don\u0027t do merging on discard requests, but we potentially\n could. If we do, then we need to include discard requests in the IO\n accounting, or merging would end up decrementing in_flight IO counters\n for an IO which never incremented them.\n\n So enable accounting for discard requests.\n\n\u003csnip\u003e\n\n static inline int blk_do_io_stat(struct request *rq)\n {\n- return rq-\u003erq_disk \u0026\u0026 blk_rq_io_stat(rq) \u0026\u0026 blk_fs_request(rq);\n+ return rq-\u003erq_disk \u0026\u0026 blk_rq_io_stat(rq) \u0026\u0026 blk_fs_request(rq) \u0026\u0026\n+ blk_discard_rq(rq);\n }\n--------------------------------------------------------------------------\n\nSigned-off-by: Kiyoshi Ueda \u003ck-ueda@ct.jp.nec.com\u003e\nSigned-off-by: Jun\u0027ichi Nomura \u003cj-nomura@ce.jp.nec.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "ba396a6c104682dfe5c8b4fbbf5974d5ac9f3687", "tree": "ba8bf30382d1891c7f540264b6229db1bc1eb797", "parents": [ "3b77f777b8f1c001b63e317c4ce317292ff0ff94" ], "author": { "name": "James Bottomley", "email": "James.Bottomley@HansenPartnership.com", "time": "Wed May 27 14:17:08 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed May 27 14:17:08 2009 +0200" }, "message": "block: fix oops with block tag queueing\n\ncommit e8939a50466fd963eb1ba9118c34b9ffb7ff6aa6\nAuthor: Tejun Heo \u003ctj@kernel.org\u003e\nDate: Fri May 8 11:54:16 2009 +0900\n\n block: implement and enforce request peek/start/fetch\n\nAdded a BUG_ON(blk_queued_rq(req)) to the top of blk_finish_req().\nUnfortunately, this checks whether req-\u003equeuelist is empty. This list\nis doing double duty both as the queue list and the tag list, so tagged\nrequests come in here with this not empty and boom (the tag list is\nemptied by blk_queue_end_tag() lower down).\n\nFix this by moving the BUG_ON to below the end tag we also seem\nvulnerable to this in blk_requeue_request() as well. I think all uses\nof blk_queued_rq() need auditing because the check is clearly wrong in\nthe tagged case.\n\nSigned-off-by: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "c72758f33784e5e2a1a4bb9421ef3e6de8f9fcf3", "tree": "a83f7540cc894caafe74db911cba3998d6a9a164", "parents": [ "cd43e26f071524647e660706b784ebcbefbd2e44" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Fri May 22 17:17:53 2009 -0400" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri May 22 23:22:55 2009 +0200" }, "message": "block: Export I/O topology for block devices and partitions\n\nTo support devices with physical block sizes bigger than 512 bytes we\nneed to ensure proper alignment. This patch adds support for exposing\nI/O topology characteristics as devices are stacked.\n\n logical_block_size is the smallest unit the device can address.\n\n physical_block_size indicates the smallest I/O the device can write\n without incurring a read-modify-write penalty.\n\n The io_min parameter is the smallest preferred I/O size reported by\n the device. In many cases this is the same as the physical block\n size. However, the io_min parameter can be scaled up when stacking\n (RAID5 chunk size \u003e physical block size).\n\n The io_opt characteristic indicates the optimal I/O size reported by\n the device. This is usually the stripe width for arrays.\n\n The alignment_offset parameter indicates the number of bytes the start\n of the device/partition is offset from the device\u0027s natural alignment.\n Partition tools and MD/DM utilities can use this to pad their offsets\n so filesystems start on proper boundaries.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "cd43e26f071524647e660706b784ebcbefbd2e44", "tree": "11625a25ba8a7c5cd4fe41b54d53506a7982433b", "parents": [ "025146e13b63483add912706c101fb0fb6f015cc" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Fri May 22 17:17:52 2009 -0400" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri May 22 23:22:55 2009 +0200" }, "message": "block: Expose stacked device queues in sysfs\n\nCurrently stacking devices do not have a queue directory in sysfs.\nHowever, many of the I/O characteristics like sector size, maximum\nrequest size, etc. are queue properties.\n\nThis patch enables the queue directory for MD/DM devices. The elevator\ncode has been modified to deal with queues that do not have an I/O\nscheduler.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "025146e13b63483add912706c101fb0fb6f015cc", "tree": "42d2d42e2222f0a2d6373a0ddf0cbf733f75dcba", "parents": [ "ae03bf639a5027d27270123f5f6e3ee6a412781d" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Fri May 22 17:17:51 2009 -0400" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri May 22 23:22:55 2009 +0200" }, "message": "block: Move queue limits to an embedded struct\n\nTo accommodate stacking drivers that do not have an associated request\nqueue we\u0027re moving the limits to a separate, embedded structure.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "ae03bf639a5027d27270123f5f6e3ee6a412781d", "tree": "d705f41a188ad656b1f47f7952626a9f992e3b8f", "parents": [ "e1defc4ff0cf57aca6c5e3ff99fa503f5943c1f1" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Fri May 22 17:17:50 2009 -0400" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri May 22 23:22:54 2009 +0200" }, "message": "block: Use accessor functions for queue limits\n\nConvert all external users of queue limits to using wrapper functions\ninstead of poking the request queue variables directly.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "e1defc4ff0cf57aca6c5e3ff99fa503f5943c1f1", "tree": "d60d15a082171c58ac811d547d51a9c3119f23e3", "parents": [ "9bd7de51ee8537094656149eaf45338cadb7d7d4" ], "author": { "name": "Martin K. Petersen", "email": "martin.petersen@oracle.com", "time": "Fri May 22 17:17:49 2009 -0400" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri May 22 23:22:54 2009 +0200" }, "message": "block: Do away with the notion of hardsect_size\n\nUntil now we have had a 1:1 mapping between storage device physical\nblock size and the logical block sized used when addressing the device.\nWith SATA 4KB drives coming out that will no longer be the case. The\nsector size will be 4KB but the logical block size will remain\n512-bytes. Hence we need to distinguish between the physical block size\nand the logical ditto.\n\nThis patch renames hardsect_size to logical_block_size.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "e4b636366c00738b9609cda307014d71b1225b7f", "tree": "760b67b3624eda62e943e48ce93635c30a5b47bf", "parents": [ "b9ed7252d219c1c663944bf03846eabb515dbe75", "279e677faa775ad16e75c32e1bf4a37f8158bc61" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri May 22 20:25:34 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri May 22 20:25:34 2009 +0200" }, "message": "Merge branch \u0027master\u0027 into for-2.6.31\n\nConflicts:\n\tdrivers/block/hd.c\n\tdrivers/block/mg_disk.c\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "0a7ae2ff0d29bb3b327edff4c8ab67b3834fa811", "tree": "88309ac99a39e15b9b23525a00a15b1564957b32", "parents": [ "ac36552a52a6ec8563ac0a109e2a0935673f4abb" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed May 20 08:54:31 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed May 20 08:54:31 2009 +0200" }, "message": "block: change the tag sync vs async restriction logic\n\nMake them fully share the tag space, but disallow async requests using\nthe last any two slots.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "53674ac5a997a8eedbb2dfdc308b895170746c8b", "tree": "69fb2c7c2d9726e0ff3a8bc491b5bf1fc5e2d1d4", "parents": [ "a411f4bbb89f1f08687b344064d6775bce1e4658" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue May 19 19:52:35 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue May 19 19:52:35 2009 +0200" }, "message": "block: add warning to blk_make_request()\n\nAdd a note about how one needs to be careful when setting up these bio\nchains.\n\nExtracted from Boaz\u0027s updated patch.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "a411f4bbb89f1f08687b344064d6775bce1e4658", "tree": "8898f98285e712f8b5bb99db184bc1a21b1a643c", "parents": [ "c29b70f6ee4f2fa3ef07f55bc9082945861e5391" ], "author": { "name": "Boaz Harrosh", "email": "bharrosh@panasas.com", "time": "Sun May 17 19:00:01 2009 +0300" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue May 19 12:14:56 2009 +0200" }, "message": "block: Un-export blk_rq_append_bio\n\nOSD was the last in-tree user of blk_rq_append_bio(). Now\nthat it is fixed blk_rq_append_bio is un-exported and\nis only used internally by block layer.\n\nSigned-off-by: Boaz Harrosh \u003cbharrosh@panasas.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "79eb63e9e5875b84341a3a05f8e6ae9cdb4bb6f6", "tree": "bdadc2037c1d0f24c6c73b71ae82fdd7b907e610", "parents": [ "bc38bf106c967389a465d926be22c7371abba69d" ], "author": { "name": "Boaz Harrosh", "email": "bharrosh@panasas.com", "time": "Sun May 17 18:57:15 2009 +0300" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue May 19 12:14:56 2009 +0200" }, "message": "block: Add blk_make_request(), takes bio, returns a request\n\nNew block API:\ngiven a struct bio allocates a new request. This is the parallel of\ngeneric_make_request for BLOCK_PC commands users.\n\nThe passed bio may be a chained-bio. The bio is bounced if needed\ninside the call to this member.\n\nThis is in the effort of un-exporting blk_rq_append_bio().\n\nSigned-off-by: Boaz Harrosh \u003cbharrosh@panasas.com\u003e\nCC: Jeff Garzik \u003cjeff@garzik.org\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "3a5a39276d2a32b05b1ee25b384516805b17cf87", "tree": "8a52a4a158ed341b7c3049826c549c2a210386e3", "parents": [ "b2858d7d1639c04ca3c54988d76c5f7300b76f1c" ], "author": { "name": "James Bottomley", "email": "James.Bottomley@HansenPartnership.com", "time": "Sun May 17 18:55:18 2009 +0300" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue May 19 12:14:55 2009 +0200" }, "message": "block: allow blk_rq_map_kern to append to requests\n\nUse blk_rq_append_bio() internally instead of blk_rq_bio_prep()\nso blk_rq_map_kern can be called multiple times, to map multiple\nbuffers.\n\nThis is in the effort to un-export blk_rq_append_bio()\n\nSigned-off-by: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nSigned-off-by: Boaz Harrosh \u003cbharrosh@panasas.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "5f49f63178360b07a095bd33b0d850d60edf7590", "tree": "23764399405214c115543eb5dec59982cf0baa26", "parents": [ "3755100dd5f66761aaaa7ae44c70b319a7c78a56" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Tue May 19 18:33:05 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue May 19 11:36:08 2009 +0200" }, "message": "block: set rq-\u003eresid_len to blk_rq_bytes() on issue\n\nIn commit c3a4d78c580de4edc9ef0f7c59812fb02ceb037f, while introducing\nrq-\u003eresid_len, the default value of residue count was changed from\nfull count to zero. The conversion was done under the assumption that\nwhen a request fails residue count wasn\u0027t defined. However, Boaz and\nJames pointed out that this wasn\u0027t true and the residue count should\nbe preserved for failed requests too.\n\nThis patchset restores the original behavior by setting rq-\u003eresid_len\nto blk_rq_bytes(rq) on request start and restoring explicit clearing\nin affected drivers. While at it, take advantage of the fact that\nrq-\u003eresid_len is set to full count where applicable.\n\n* ide-cd: rq-\u003eresid_len cleared on pc success\n\n* mptsas: req-\u003eresid_len cleared on success\n\n* sas_expander: rsp/req-\u003eresid_len cleared on success\n\n* mpt2sas_transport: req-\u003eresid_len cleared on success\n\n* ide-cd, ide-tape, mptsas, sas_host_smp, mpt2sas_transport, ub: take\n advantage of initial full count to simplify code\n\nBoaz Harrosh spotted bug in resid_len initialization. Fixed as\nsuggested.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nAcked-by: Borislav Petkov \u003cpetkovbb@googlemail.com\u003e\nCc: Boaz Harrosh \u003cbharrosh@panasas.com\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nCc: Pete Zaitcev \u003czaitcev@redhat.com\u003e\nCc: Bartlomiej Zolnierkiewicz \u003cbzolnier@gmail.com\u003e\nCc: Sergei Shtylyov \u003csshtylyov@ru.mvista.com\u003e\nCc: Eric Moore \u003cEric.Moore@lsi.com\u003e\nCc: Darrick J. Wong \u003cdjwong@us.ibm.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "1079cac0f4eb7d968395378b1625979d4c818dd6", "tree": "d261058d95d27fe7250511d5fad69db30dc17731", "parents": [ "5872144f64b34a5942f6b4acedc90b02de72c58b", "1406de8e11eb043681297adf86d6892ff8efc27a" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 18 10:15:09 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 18 10:15:35 2009 +0200" }, "message": "Merge commit \u0027v2.6.30-rc6\u0027 into tracing/core\n\nMerge reason: we were on an -rc4 base, sync up to -rc6\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "af498d7fa3e786f52650819a56e117ed9a40920c", "tree": "4170275db90f306935e35be1c2cd2cbd6a1a27a8", "parents": [ "a4d7749be5de4a7261bcbe3c7d96c748792ec455" ], "author": { "name": "Kazuhisa Ichikawa", "email": "ki@epsilou.com", "time": "Tue May 12 13:27:45 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue May 12 13:27:45 2009 +0200" }, "message": "block: fix the bio_vec array index out-of-bounds test\n\nCurrent bio_vec array index out-of-bounds test within\n__end_that_request_first() does not seem correct.\nIt checks bio-\u003ebi_idx against bio-\u003ebi_vcnt, but the subsequent code\nuses idx (which is, bio-\u003ebi_idx + next_idx) as the array index into\nbio_vec array. This means that the test really make sense only at\nthe first iteration of !(nr_bytes \u003e\u003dbio-\u003ebi_size) case (when next_idx\n\u003d\u003d zero). Fix this by replacing bio-\u003ebi_idx with idx.\n(This patch applies to 2.6.30-rc4.)\n\nSigned-off-by: Kazuhisa Ichikawa \u003cki@epsilou.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "b1f744937f1be3e6d3009382a755679133cf782d", "tree": "0e90e43589ecfe28199030e8e396c0193199da7e", "parents": [ "e6bb7a96c2c36f20c05ef648f15bd3c2b1834c78" ], "author": { "name": "FUJITA Tomonori", "email": "fujita.tomonori@lab.ntt.co.jp", "time": "Mon May 11 17:56:09 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon May 11 11:06:48 2009 +0200" }, "message": "block: move completion related functions back to blk-core.c\n\nLet\u0027s put the completion related functions back to block/blk-core.c\nwhere they have lived. We can also unexport blk_end_bidi_request() and\n__blk_end_bidi_request(), which nobody uses.\n\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "9934c8c04561413609d2bc38c6b9f268cba774a4", "tree": "30dd8f7be54f9b2e03094de9cd03b6a9ee2909cd", "parents": [ "2343046826a8ca426b07601d9593ee046c298b68" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri May 08 11:54:16 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon May 11 09:52:18 2009 +0200" }, "message": "block: implement and enforce request peek/start/fetch\n\nTill now block layer allowed two separate modes of request execution.\nA request is always acquired from the request queue via\nelv_next_request(). After that, drivers are free to either dequeue it\nor process it without dequeueing. Dequeue allows elv_next_request()\nto return the next request so that multiple requests can be in flight.\n\nExecuting requests without dequeueing has its merits mostly in\nallowing drivers for simpler devices which can\u0027t do sg to deal with\nsegments only without considering request boundary. However, the\nbenefit this brings is dubious and declining while the cost of the API\nambiguity is increasing. Segment based drivers are usually for very\nold or limited devices and as converting to dequeueing model isn\u0027t\ndifficult, it doesn\u0027t justify the API overhead it puts on block layer\nand its more modern users.\n\nPrevious patches converted all block low level drivers to dequeueing\nmodel. This patch completes the API transition by...\n\n* renaming elv_next_request() to blk_peek_request()\n\n* renaming blkdev_dequeue_request() to blk_start_request()\n\n* adding blk_fetch_request() which is combination of peek and start\n\n* disallowing completion of queued (not started) requests\n\n* applying new API to all LLDs\n\nRenamings are for consistency and to break out of tree code so that\nit\u0027s apparent that out of tree drivers need updating.\n\n[ Impact: block request issue API cleanup, no functional change ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nCc: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: unsik Kim \u003cdonari75@gmail.com\u003e\nCc: Paul Clements \u003cpaul.clements@steeleye.com\u003e\nCc: Tim Waugh \u003ctim@cyberelk.net\u003e\nCc: Geert Uytterhoeven \u003cGeert.Uytterhoeven@sonycom.com\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nCc: Laurent Vivier \u003cLaurent@lvivier.info\u003e\nCc: Jeff Garzik \u003cjgarzik@pobox.com\u003e\nCc: Jeremy Fitzhardinge \u003cjeremy@xensource.com\u003e\nCc: Grant Likely \u003cgrant.likely@secretlab.ca\u003e\nCc: Adrian McMenamin \u003cadrian@mcmen.demon.co.uk\u003e\nCc: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nCc: Bartlomiej Zolnierkiewicz \u003cbzolnier@gmail.com\u003e\nCc: Borislav Petkov \u003cpetkovbb@googlemail.com\u003e\nCc: Sergei Shtylyov \u003csshtylyov@ru.mvista.com\u003e\nCc: Alex Dubov \u003coakad@yahoo.com\u003e\nCc: Pierre Ossman \u003cdrzeus@drzeus.cx\u003e\nCc: David Woodhouse \u003cdwmw2@infradead.org\u003e\nCc: Markus Lidel \u003cMarkus.Lidel@shadowconnect.com\u003e\nCc: Stefan Weinhuber \u003cwein@de.ibm.com\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: Pete Zaitcev \u003czaitcev@redhat.com\u003e\nCc: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "a2dec7b36364a5cc564c4d76cf16d2e7d33f5c05", "tree": "76dfb84ba5fa097a929ab81cf5718c6fcbc9d720", "parents": [ "34b7d2c957199834c474c9d46739265643f4d9c7" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu May 07 22:24:44 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon May 11 09:50:55 2009 +0200" }, "message": "block: hide request sector and data_len\n\nBlock low level drivers for some reason have been pretty good at\nabusing block layer API. Especially struct request\u0027s fields tend to\nget violated in all possible ways. Make it clear that low level\ndrivers MUST NOT access or manipulate rq-\u003esector and rq-\u003edata_len\ndirectly by prefixing them with double underscores.\n\nThis change is also necessary to break build of out-of-tree codes\nwhich assume the previous block API where internal fields can be\nmanipulated and rq-\u003edata_len carries residual count on completion.\n\n[ Impact: hide internal fields, block API change ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "2e46e8b27aa57c6bd34b3102b40ee4d0144b4fab", "tree": "134f560f66c2af277f0f25e5b85f6c1acaddfc06", "parents": [ "9780e2dd8254351f6cbe11304849126b51dbd561" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu May 07 22:24:41 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon May 11 09:50:54 2009 +0200" }, "message": "block: drop request-\u003ehard_* and *nr_sectors\n\nstruct request has had a few different ways to represent some\nproperties of a request. -\u003ehard_* represent block layer\u0027s view of the\nrequest progress (completion cursor) and the ones without the prefix\nare supposed to represent the issue cursor and allowed to be updated\nas necessary by the low level drivers. The thing is that as block\nlayer supports partial completion, the two cursors really aren\u0027t\nnecessary and only cause confusion. In addition, manual management of\nrequest detail from low level drivers is cumbersome and error-prone at\nthe very least.\n\nAnother interesting duplicate fields are rq-\u003e[hard_]nr_sectors and\nrq-\u003e{hard_cur|current}_nr_sectors against rq-\u003edata_len and\nrq-\u003ebio-\u003ebi_size. This is more convoluted than the hard_ case.\n\nrq-\u003e[hard_]nr_sectors are initialized for requests with bio but\nblk_rq_bytes() uses it only for !pc requests. rq-\u003edata_len is\ninitialized for all request but blk_rq_bytes() uses it only for pc\nrequests. This causes good amount of confusion throughout block layer\nand its drivers and determining the request length has been a bit of\nblack magic which may or may not work depending on circumstances and\nwhat the specific LLD is actually doing.\n\nrq-\u003e{hard_cur|current}_nr_sectors represent the number of sectors in\nthe contiguous data area at the front. This is mainly used by drivers\nwhich transfers data by walking request segment-by-segment. This\nvalue always equals rq-\u003ebio-\u003ebi_size \u003e\u003e 9. However, data length for\npc requests may not be multiple of 512 bytes and using this field\nbecomes a bit confusing.\n\nIn general, having multiple fields to represent the same property\nleads only to confusion and subtle bugs. With recent block low level\ndriver cleanups, no driver is accessing or manipulating these\nduplicate fields directly. Drop all the duplicates. Now rq-\u003esector\nmeans the current sector, rq-\u003edata_len the current total length and\nrq-\u003ebio-\u003ebi_size the current segment length. Everything else is\ndefined in terms of these three and available only through accessors.\n\n* blk_recalc_rq_sectors() is collapsed into blk_update_request() and\n now handles pc and fs requests equally other than rq-\u003esector update.\n This means that now pc requests can use partial completion too (no\n in-kernel user yet tho).\n\n* bio_cur_sectors() is replaced with bio_cur_bytes() as block layer\n now uses byte count as the primary data length.\n\n* blk_rq_pos() is now guranteed to be always correct. In-block users\n converted.\n\n* blk_rq_bytes() is now guaranteed to be always valid as is\n blk_rq_sectors(). In-block users converted.\n\n* blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() \u003e\u003e 9.\n More convenient one is used.\n\n* blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const\n pointer to request.\n\n[ Impact: API cleanup, single way to represent one property of a request ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Boaz Harrosh \u003cbharrosh@panasas.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "83096ebf1263b2c1ee5e653ba37d993d02e3eb7b", "tree": "2226b71a616ec1cb2d37511c6a09ba9507a1cd69", "parents": [ "5b93629b4509c03ffa87a9316412fedf6f58cb37" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu May 07 22:24:39 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon May 11 09:50:54 2009 +0200" }, "message": "block: convert to pos and nr_sectors accessors\n\nWith recent cleanups, there is no place where low level driver\ndirectly manipulates request fields. This means that the \u0027hard\u0027\nrequest fields always equal the !hard fields. Convert all\nrq-\u003esectors, nr_sectors and current_nr_sectors references to\naccessors.\n\nWhile at it, drop superflous blk_rq_pos() \u003c 0 test in swim.c.\n\n[ Impact: use pos and nr_sectors accessors ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nAcked-by: Geert Uytterhoeven \u003cGeert.Uytterhoeven@sonycom.com\u003e\nTested-by: Grant Likely \u003cgrant.likely@secretlab.ca\u003e\nAcked-by: Grant Likely \u003cgrant.likely@secretlab.ca\u003e\nTested-by: Adrian McMenamin \u003cadrian@mcmen.demon.co.uk\u003e\nAcked-by: Adrian McMenamin \u003cadrian@mcmen.demon.co.uk\u003e\nAcked-by: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nCc: Bartlomiej Zolnierkiewicz \u003cbzolnier@gmail.com\u003e\nCc: Borislav Petkov \u003cpetkovbb@googlemail.com\u003e\nCc: Sergei Shtylyov \u003csshtylyov@ru.mvista.com\u003e\nCc: Eric Moore \u003cEric.Moore@lsi.com\u003e\nCc: Alan Stern \u003cstern@rowland.harvard.edu\u003e\nCc: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nCc: Pete Zaitcev \u003czaitcev@redhat.com\u003e\nCc: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nCc: Paul Clements \u003cpaul.clements@steeleye.com\u003e\nCc: Tim Waugh \u003ctim@cyberelk.net\u003e\nCc: Jeff Garzik \u003cjgarzik@pobox.com\u003e\nCc: Jeremy Fitzhardinge \u003cjeremy@xensource.com\u003e\nCc: Alex Dubov \u003coakad@yahoo.com\u003e\nCc: David Woodhouse \u003cdwmw2@infradead.org\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: Dario Ballabio \u003cballabio_dario@emc.com\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nCc: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: unsik Kim \u003cdonari75@gmail.com\u003e\nCc: Laurent Vivier \u003cLaurent@lvivier.info\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "5b93629b4509c03ffa87a9316412fedf6f58cb37", "tree": "ad5ceda3f718361b8df3057b4f9edcc79aa4cd9d", "parents": [ "c3a4d78c580de4edc9ef0f7c59812fb02ceb037f" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu May 07 22:24:38 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon May 11 09:50:53 2009 +0200" }, "message": "block: implement blk_rq_pos/[cur_]sectors() and convert obvious ones\n\nImplement accessors - blk_rq_pos(), blk_rq_sectors() and\nblk_rq_cur_sectors() which return rq-\u003ehard_sector, rq-\u003ehard_nr_sectors\nand rq-\u003ehard_cur_sectors respectively and convert direct references of\nthe said fields to the accessors.\n\nThis is in preparation of request data length handling cleanup.\n\nGeert\t: suggested adding const to struct request * parameter to accessors\nSergei\t: spotted error in patch description\n\n[ Impact: cleanup ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nAcked-by: Geert Uytterhoeven \u003cGeert.Uytterhoeven@sonycom.com\u003e\nAcked-by: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nTested-by: Grant Likely \u003cgrant.likely@secretlab.ca\u003e\nAcked-by: Grant Likely \u003cgrant.likely@secretlab.ca\u003e\nAckec-by: Sergei Shtylyov \u003csshtylyov@ru.mvista.com\u003e\nCc: Bartlomiej Zolnierkiewicz \u003cbzolnier@gmail.com\u003e\nCc: Borislav Petkov \u003cpetkovbb@googlemail.com\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "c3a4d78c580de4edc9ef0f7c59812fb02ceb037f", "tree": "916ca44287100707508678e2cc0eff0c43b9ca39", "parents": [ "9720aef2539c10e3a872e9a92beec225030d99db" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu May 07 22:24:37 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon May 11 09:50:53 2009 +0200" }, "message": "block: add rq-\u003eresid_len\n\nrq-\u003edata_len served two purposes - the length of data buffer on issue\nand the residual count on completion. This duality creates some\nheadaches.\n\nFirst of all, block layer and low level drivers can\u0027t really determine\nwhat rq-\u003edata_len contains while a request is executing. It could be\nthe total request length or it coulde be anything else one of the\nlower layers is using to keep track of residual count. This\ncomplicates things because blk_rq_bytes() and thus\n[__]blk_end_request_all() relies on rq-\u003edata_len for PC commands.\nDrivers which want to report residual count should first cache the\ntotal request length, update rq-\u003edata_len and then complete the\nrequest with the cached data length.\n\nSecondly, it makes requests default to reporting full residual count,\nie. reporting that no data transfer occurred. The residual count is\nan exception not the norm; however, the driver should clear\nrq-\u003edata_len to zero to signify the normal cases while leaving it\nalone means no data transfer occurred at all. This reverse default\nbehavior complicates code unnecessarily and renders block PC on some\ndrivers (ide-tape/floppy) unuseable.\n\nThis patch adds rq-\u003eresid_len which is used only for residual count.\n\nWhile at it, remove now unnecessasry blk_rq_bytes() caching in\nide_pc_intr() as rq-\u003edata_len is not changed anymore.\n\nBoaz\t: spotted missing conversion in osd\nSergei\t: spotted too early conversion to blk_rq_bytes() in ide-tape\n\n[ Impact: cleanup residual count handling, report 0 resid by default ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\nCc: Bartlomiej Zolnierkiewicz \u003cbzolnier@gmail.com\u003e\nCc: Borislav Petkov \u003cpetkovbb@googlemail.com\u003e\nCc: Sergei Shtylyov \u003csshtylyov@ru.mvista.com\u003e\nCc: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: Eric Moore \u003cEric.Moore@lsi.com\u003e\nCc: Alan Stern \u003cstern@rowland.harvard.edu\u003e\nCc: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nCc: Doug Gilbert \u003cdgilbert@interlog.com\u003e\nCc: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: Eric Moore \u003cEric.Moore@lsi.com\u003e\nCc: Darrick J. Wong \u003cdjwong@us.ibm.com\u003e\nCc: Pete Zaitcev \u003czaitcev@redhat.com\u003e\nCc: Boaz Harrosh \u003cbharrosh@panasas.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "44347d947f628060b92449702071bfe1d31dfb75", "tree": "c6ed74610d5b3295df4296659f80f5feb94b28cc", "parents": [ "d94fc523f3c35bd8013f04827e94756cbc0212f4", "413f81eba35d6ede9289b0c8a920c013a84fac71" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu May 07 11:17:13 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu May 07 11:17:34 2009 +0200" }, "message": "Merge branch \u0027linus\u0027 into tracing/core\n\nMerge reason: tracing/core was on a .30-rc1 base and was missing out on\n on a handful of tracing fixes present in .30-rc5-almost.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "22a7c31a9659deaddafbbcec6562d44141e84474", "tree": "0fe1c64e82d673597c78c6ce5f3569d9101b5281", "parents": [ "a42aaa3bbce85ac487ad4fad5db99e8e91b7aac1" ], "author": { "name": "Alan D. Brunelle", "email": "Alan.Brunelle@hp.com", "time": "Mon May 04 16:35:08 2009 -0400" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed May 06 14:13:01 2009 +0200" }, "message": "blktrace: from-sector redundant in trace_block_remap\n\nRemove redundant from-sector parameter: it\u0027s /always/ the bio\u0027s sector\npassed in.\n\n[ Impact: cleanup ]\n\nSigned-off-by: Alan D. Brunelle \u003calan.brunelle@hp.com\u003e\nReviewed-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nLKML-Reference: \u003c49FF517C.7000503@hp.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "4c94dece1baf320d925cedb231489c4e0358ac5a", "tree": "fd0738e2f82c806e921e6c872b704cfbef3c0a1d", "parents": [ "9fd8d0e1bcb848257968d9a7d73ca4d890ea8bd1" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Tue Apr 28 13:06:05 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 08:14:50 2009 +0200" }, "message": "block: don\u0027t init rq fields unnecessarily\n\nblk_get_request() always returns properly zeroed requests. Don\u0027t set\nfields to zero/NULL unnecessarily.\n\n[ Impact: cleanup ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "9eb55b030c4b3227334ee4482402096cd1d1a6fe", "tree": "e6c5c6e31692c715b911b18474ef6e4c627723bd", "parents": [ "c69d48540c201394d08cb4d48b905e001313d9b8" ], "author": { "name": "Nikanth Karthikesan", "email": "knikanth@suse.de", "time": "Mon Apr 27 14:53:54 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:37 2009 +0200" }, "message": "block: catch trying to use more bits than request-\u003ecmd_flags has\n\nSigned-off-by: Nikanth Karthikesan \u003cknikanth@suse.de\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "c69d48540c201394d08cb4d48b905e001313d9b8", "tree": "6ad78b44cd7fc5d65a0c3bded49f8cb14f4790a9", "parents": [ "c2553b5844b06910435e40cfab9e6f384840cb97" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Apr 24 08:12:19 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:37 2009 +0200" }, "message": "block: include discard requests in IO accounting\n\nWe currently don\u0027t do merging on discard requests, but we potentially\ncould. If we do, then we need to include discard requests in the IO\naccounting, or merging would end up decrementing in_flight IO counters\nfor an IO which never incremented them.\n\nSo enable accounting for discard requests.\n\nProblem found by Nikanth Karthikesan \u003cknikanth@suse.de\u003e\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "c2553b5844b06910435e40cfab9e6f384840cb97", "tree": "00a6a1f0c056f19050a8b7c7a1db7b7e0e502062", "parents": [ "731ec497e5888c6792ad62613ae9be97eebcd7ca" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Apr 24 08:10:11 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:37 2009 +0200" }, "message": "block: make blk_do_io_stat() do the full \"is this rq accountable\" checks\n\nWe currently check for file system requests outside of blk_do_io_stat(rq),\nbut we may as well just include it.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "731ec497e5888c6792ad62613ae9be97eebcd7ca", "tree": "689a8442d8bdfd50ee6ab05b0c6acd0d229fe391", "parents": [ "ec24751a6b57e1373a12361e581b2458bc9bb791" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Apr 23 11:05:20 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:36 2009 +0200" }, "message": "block: kill rq-\u003edata\n\nNow that all block request data transfer is done via bio, rq-\u003edata\nisn\u0027t used. Kill it.\n\nWhile at it, make the roles of rq-\u003especial and buffer clear.\n\n[ Impact: drop now unncessary field from struct request ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Boaz Harrosh \u003cbharrosh@panasas.com\u003e\n" }, { "commit": "40cbbb781d3eba5d6ac0860db078af490e5c7c6b", "tree": "dec374543cf045fc630bccddbb7646c695094b0d", "parents": [ "b243ddcbe9be146172baa544dadecebf156eda0e" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Apr 23 11:05:19 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:35 2009 +0200" }, "message": "block: implement and use [__]blk_end_request_all()\n\nThere are many [__]blk_end_request() call sites which call it with\nfull request length and expect full completion. Many of them ensure\nthat the request actually completes by doing BUG_ON() the return\nvalue, which is awkward and error-prone.\n\nThis patch adds [__]blk_end_request_all() which takes @rq and @error\nand fully completes the request. BUG_ON() is added to to ensure that\nthis actually happens.\n\nMost conversions are simple but there are a few noteworthy ones.\n\n* cdrom/viocd: viocd_end_request() replaced with direct calls to\n __blk_end_request_all().\n\n* s390/block/dasd: dasd_end_request() replaced with direct calls to\n __blk_end_request_all().\n\n* s390/char/tape_block: tapeblock_end_request() replaced with direct\n calls to blk_end_request_all().\n\n[ Impact: cleanup ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Russell King \u003crmk@arm.linux.org.uk\u003e\nCc: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nCc: Mike Miller \u003cmike.miller@hp.com\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: Jeff Garzik \u003cjgarzik@pobox.com\u003e\nCc: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Jeremy Fitzhardinge \u003cjeremy@xensource.com\u003e\nCc: Alex Dubov \u003coakad@yahoo.com\u003e\nCc: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\n" }, { "commit": "b243ddcbe9be146172baa544dadecebf156eda0e", "tree": "20ae5d9460498ae6c53e9e82f1b9d9ed6daffbb3", "parents": [ "2e60e02297cf54e367567f2d85b2ca56b1c4a906" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Apr 23 11:05:18 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:35 2009 +0200" }, "message": "block: move rq-\u003estart_time initialization to blk_rq_init()\n\nrq-\u003estart_time was initialized in init_request_from_bio() so special\nrequests didn\u0027t have start_time set. This has been okay as start_time\nhas been used only for fs requests; however, there is no indication of\nthis actually is the case or not. Set rq-\u003estart_time in blk_rq_init()\nand guarantee that all initialized rq\u0027s have its start_time set. This\nimproves consistency at virtually no cost and future changes will make\nuse of the timestamp for !bio requests.\n\n[ Impact: rq-\u003estart_time is valid for all requests ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "2e60e02297cf54e367567f2d85b2ca56b1c4a906", "tree": "ea824afcaff58be894799a011f74d80c3560f372", "parents": [ "0b302d5aa7975006fa2ec3d66386610b9b36c669" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Apr 23 11:05:18 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:35 2009 +0200" }, "message": "block: clean up request completion API\n\nRequest completion has gone through several changes and became a bit\nmessy over the time. Clean it up.\n\n1. end_that_request_data() is a thin wrapper around\n end_that_request_data_first() which checks whether bio is NULL\n before doing anything and handles bidi completion.\n blk_update_request() is a thin wrapper around\n end_that_request_data() which clears nr_sectors on the last\n iteration but doesn\u0027t use the bidi completion.\n\n Clean it up by moving the initial bio NULL check and nr_sectors\n clearing on the last iteration into end_that_request_data() and\n renaming it to blk_update_request(), which makes blk_end_io() the\n only user of end_that_request_data(). Collapse\n end_that_request_data() into blk_end_io().\n\n2. There are four visible completion variants - blk_end_request(),\n __blk_end_request(), blk_end_bidi_request() and end_request().\n blk_end_request() and blk_end_bidi_request() uses blk_end_request()\n as the backend but __blk_end_request() and end_request() use\n separate implementation in __blk_end_request() due to different\n locking rules.\n\n blk_end_bidi_request() is identical to blk_end_io(). Collapse\n blk_end_io() into blk_end_bidi_request(), separate out request\n update into internal helper blk_update_bidi_request() and add\n __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin\n inline wrappers around [__]blk_end_bidi_request().\n\n3. As the whole request issue/completion usages are about to be\n modified and audited, it\u0027s a good chance to convert completion\n functions return bool which better indicates the intended meaning\n of return values.\n\n4. The function name end_that_request_last() is from the days when it\n was a public interface and slighly confusing. Give it a proper\n internal name - blk_finish_request().\n\n5. Add description explaning that blk_end_bidi_request() can be safely\n used for uni requests as suggested by Boaz Harrosh.\n\nThe only visible behavior change is from #1. nr_sectors counts are\ncleared after the final iteration no matter which function is used to\ncomplete the request. I couldn\u0027t find any place where the code\nassumes those nr_sectors counters contain the values for the last\nsegment and this change is good as it makes the API much more\nconsistent as the end result is now same whether a request is\ncompleted using [__]blk_end_request() alone or in combination with\nblk_update_request().\n\nAPI further cleaned up per Christoph\u0027s suggestion.\n\n[ Impact: cleanup, rq-\u003e*nr_sectors always updated after req completion ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nReviewed-by: Boaz Harrosh \u003cbharrosh@panasas.com\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\n" }, { "commit": "0b302d5aa7975006fa2ec3d66386610b9b36c669", "tree": "bba5de7b377ad167c4291cbdfd203ca7616d696d", "parents": [ "158dbda0068e63c7cce7bd47c123bd1dfa5a902c" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Apr 23 11:05:18 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:34 2009 +0200" }, "message": "block: kill blk_end_request_callback()\n\nWith recent IDE updates, blk_end_request_callback() doesn\u0027t have any\nuser now. Kill it.\n\n[ Impact: removal of unused convoluted interface ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "158dbda0068e63c7cce7bd47c123bd1dfa5a902c", "tree": "2665f31350ba4f0875c7611c980b0831c22d8c98", "parents": [ "5efccd17ceb0fc43837a331297c2c407969d7201" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Apr 23 11:05:18 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:34 2009 +0200" }, "message": "block: reorganize request fetching functions\n\nImpact: code reorganization\n\nelv_next_request() and elv_dequeue_request() are public block layer\ninterface than actual elevator implementation. They mostly deal with\nhow requests interact with block layer and low level drivers at the\nbeginning of rqeuest processing whereas __elv_next_request() is the\nactual eleveator request fetching interface.\n\nMove the two functions to blk-core.c. This prepares for further\ninterface cleanup.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "5efccd17ceb0fc43837a331297c2c407969d7201", "tree": "6678ebea73ffc9f2ad35029eaaf49e68073e4e88", "parents": [ "2eef33e439ba9ae387cdc3f1abcef2f3f6c4e7a8" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Apr 23 11:05:18 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:34 2009 +0200" }, "message": "block: reorder request completion functions\n\nReorder request completion functions such that\n\n* All request completion functions are located together.\n\n* Functions which are used by only one caller is put right above the\n caller.\n\n* end_request() is put after other completion functions but before\n blk_update_request().\n\nThis change is for completion function cleanup which will follow.\n\n[ Impact: cleanup, code reorganization ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "2eef33e439ba9ae387cdc3f1abcef2f3f6c4e7a8", "tree": "a25b4d1f59aaf23295a853beeb3922f58ee04b2b", "parents": [ "10732f5661fb7adf62e20733b0030fc0fc93b0c4" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Apr 23 11:05:18 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:34 2009 +0200" }, "message": "block: clean up misc stuff after block layer timeout conversion\n\n* In blk_rq_timed_out_timer(), else { if } to else if\n\n* In blk_add_timer(), simplify if/else block\n\n[ Impact: cleanup ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "10732f5661fb7adf62e20733b0030fc0fc93b0c4", "tree": "4d3792fd76624671503513e727bd5de6bcaa2450", "parents": [ "e4025f6c21f1389696c069be2dc647f364925c45" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Apr 23 11:05:18 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:34 2009 +0200" }, "message": "block: cleanup REQ_SOFTBARRIER usages\n\nblk_insert_request() doesn\u0027t need to worry about REQ_SOFTBARRIER.\nDon\u0027t set it. Combined with recent ide updates, REQ_SOFTBARRIER is\nnow only used in elevator proper and for discard requests.\n\n[ Impact: cleanup ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "e4025f6c21f1389696c069be2dc647f364925c45", "tree": "4d7ee21062293c9a9d398063c22339b47f581283", "parents": [ "a7f557923441186a3cdbabc54f1bcacf42b63bf5" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Apr 23 11:05:17 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:33 2009 +0200" }, "message": "block: don\u0027t set REQ_NOMERGE unnecessarily\n\nRQ_NOMERGE_FLAGS already clears defines which REQ flags aren\u0027t\nmergeable. There is no reason to specify it superflously. It only\nadds to confusion. Don\u0027t set REQ_NOMERGE for barriers and requests\nwith specific queueing directive. REQ_NOMERGE is now exclusively used\nby the merging code.\n\n[ Impact: cleanup ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "a7f557923441186a3cdbabc54f1bcacf42b63bf5", "tree": "48e37802174cb98be43d89eb8bc4e466f4d79a02", "parents": [ "a538cd03be6f363d039daa94199c28cfbd508455" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Apr 23 11:05:17 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:33 2009 +0200" }, "message": "block: kill blk_start_queueing()\n\nblk_start_queueing() is identical to __blk_run_queue() except that it\ndoesn\u0027t check for recursion. None of the current users depends on\nblk_start_queueing() running request_fn directly. Replace usages of\nblk_start_queueing() with [__]blk_run_queue() and kill it.\n\n[ Impact: removal of mostly duplicate interface function ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "a538cd03be6f363d039daa94199c28cfbd508455", "tree": "47d327e3339f5f07c4f4386537fab526310344a7", "parents": [ "db2dbb12dc47a50c7a4c5678f526014063e486f6" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Apr 23 11:05:17 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:33 2009 +0200" }, "message": "block: merge blk_invoke_request_fn() into __blk_run_queue()\n\n__blk_run_queue wraps blk_invoke_request_fn() such that it\nadditionally removes plug and bails out early if the queue is empty.\nBoth extra operations have their own pending mechanisms and don\u0027t\ncause any harm correctness-wise when they are done superflously.\n\nThe only user of blk_invoke_request_fn() being blk_start_queue(),\nthere isn\u0027t much reason to keep both functions around. Merge\nblk_invoke_request_fn() into __blk_run_queue() and make\nblk_start_queue() use __blk_run_queue() instead.\n\n[ Impact: merge two subtly different internal functions ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "db29a6b49674085f136331014ba0eee249c16a2c", "tree": "423676abaf2067b2d359a2439e00616812ee55f7", "parents": [ "586cf2681f527ce8b85b9bd57c8b9f7945fbe051" ], "author": { "name": "Bartlomiej Zolnierkiewicz", "email": "bzolnier@gmail.com", "time": "Tue Apr 21 09:27:03 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:33 2009 +0200" }, "message": "block: enable by default support for large devices and files on 32-bit archs\n\nEnable by default support for large devices and files (CONFIG_LBD):\n\n- With 1TB disks being a commodity hardware it is quite easy to hit 2TB\n limitation while building RAIDs etc. and many distros have been using\n CONFIG_LBD\u003dy by default already (at least Fedora 10 and openSUSE 11.1).\n\n- This should also prevent a subtle ext4 filesystem compatibility issue:\n mke2fs.ext4 defaults to creating filesystems with huge_files feature\n enabled and such filesystems cannot be later mounted read-write on\n machines with CONFIG_LBD\u003dn (it should be quite easy to hit this issue\n when trying to use filesystem created using distro kernel on system\n running the self-build kernel, think about USB disk enclosures \u0026 co.).\n\nWhile at it:\n\n- Clarify config option help text w.r.t. mounting ext4 filesystems\n (they can be mounted with CONFIG_LBD\u003dn but in the read-only mode).\n\nCc: \"Theodore Ts\u0027o\" \u003ctytso@mit.edu\u003e\nSigned-off-by: Bartlomiej Zolnierkiewicz \u003cbzolnier@gmail.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "924cec7789f65ab7f022256f6533ecba0747b5f3", "tree": "aeb53f094712161d61990d22fecb0874e4ff3f2a", "parents": [ "e686307fdc84f249490e6c9da92fcb2424491f14" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Sun Apr 19 07:00:41 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Tue Apr 28 07:37:28 2009 +0200" }, "message": "block: clear req-\u003eerrors on bio completion only for fs requests\n\nImpact: subtle behavior change\n\nFor fs requests, rq is only carrier of bios and rq error status as a\nwhole doesn\u0027t mean much. This is the reason why rq-\u003eerrors is being\ncleared on each partial completion of a request as on each partial\ncompletion the error status is transferred to the respective bios.\n\nFor pc requests, rq-\u003eerrors is used to carry error status to the\nissuer and thus __end_that_request_first() doesn\u0027t clear it on such\ncases.\n\nThe condition was fine till now as only fs and pc requests have used\nbio and thus the bio completion path. However, future changes will\nunify data accesses to bio and all non fs users care about rq error\nstatus. Clear rq-\u003eerrors on bio completion only for fs requests.\n\nIn general, the implicit clearing is a bit too subtle especially as\nthe meaning of rq-\u003eerrors is completely dependent on low level\ndrivers. Unifying / cleaning up rq-\u003eerrors usage and letting llds\nmanage it would be better. TODO comment added.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nAcked-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n" }, { "commit": "f2d1f0ae7851be5ebd9613a80dac139270938809", "tree": "91efc4740f854b94ea84583a2cd6c34d14eafc8e", "parents": [ "3ac6c9f8a66726745136e46f63600550c3eb6cec" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Thu Apr 23 12:19:38 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Apr 24 08:54:22 2009 +0200" }, "message": "cfq-iosched: cache prio_tree root in cfqq-\u003ep_root\n\nCurrently we look it up from -\u003eioprio, but -\u003eioprio can change if\neither the process gets its IO priority changed explicitly, or if\ncfq decides to temporarily boost it. So if we are unlucky, we can\nend up attempting to remove a node from a different rbtree root than\nwhere it was added.\n\nFix this by using -\u003eorg_ioprio as the prio_tree index, since that\nwill only change for explicit IO priority settings (not for a boost).\nAdditionally cache the rbtree root inside the cfqq, then we don\u0027t have\nto add code to reinsert the cfqq in the prio_tree if IO priority changes.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "3ac6c9f8a66726745136e46f63600550c3eb6cec", "tree": "93d3217dc15a8183c8e6b29b36862caef01546d7", "parents": [ "26a2ac009c2b07e1959c8864ca23486c1c485587" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Thu Apr 23 12:14:56 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Apr 24 08:54:22 2009 +0200" }, "message": "cfq-iosched: fix bug with aliased request and cooperation detection\n\ncfq_prio_tree_lookup() should return the direct match, yet it always\nreturns zero. Fix that.\n\ncfq_prio_tree_add() assumes that we don\u0027t get a direct match, while\nit is very possible that we do. Using O_DIRECT, you can have different\ncfqq with matching requests, since you don\u0027t have the page cache\nto serialize things for you. Fix this bug by only adding the cfqq if\nthere isn\u0027t an existing match.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "26a2ac009c2b07e1959c8864ca23486c1c485587", "tree": "f3c0ae95578cd454f04dc48226b3b6f1ebd1d345", "parents": [ "17d5c8ca7572124c9623045f24b0c21d4aa2b47f" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Thu Apr 23 12:13:27 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Apr 24 08:54:22 2009 +0200" }, "message": "cfq-iosched: clear -\u003eprio_trees[] on cfqd alloc\n\nNot strictly needed, but we should make it clear that we init the\nrbtree roots here.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "17d5c8ca7572124c9623045f24b0c21d4aa2b47f", "tree": "dfecc3aa2acae305c01238002a3e53d6ae8d3238", "parents": [ "f3c737de8f57b5ce756010c2175f7d574194b30d" ], "author": { "name": "Hannes Reinecke", "email": "hare@suse.de", "time": "Thu Apr 23 10:32:59 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Apr 24 08:54:21 2009 +0200" }, "message": "block: fix intermittent dm timeout based oops\n\nVery rarely under stress testing of dm, oopses are occuring as\nsomething tampers with an old stack frame. This has been traced back\nto blk_abort_queue() leaving a timeout_list pointing to the stack.\nThe reason is that sometimes blk_abort_request() won\u0027t delete the\ntimer (if the request is marked as complete but before the timer has\nbeen removed, a small race window). Fix this by splicing back from\nthe ususally empty list to the q-\u003etimeout_list.\n\nSigned-off-by: Hannes Reinecke \u003chare@suse.de\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "42dad7647aec49b3ad20dd0cb832b232a6ae514f", "tree": "b70d4cb7706f2647e65426e24f078ddf14d6e139", "parents": [ "097102c2d04974bdfcfa16a5f3062d499842139c" ], "author": { "name": "Jerome Marchand", "email": "jmarchan@redhat.com", "time": "Wed Apr 22 14:01:49 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Apr 24 08:54:21 2009 +0200" }, "message": "block: simplify I/O stat accounting\n\nThis simplifies I/O stat accounting switching code and separates it\ncompletely from I/O scheduler switch code.\n\nRequests are accounted according to the state of their request queue\nat the time of the request allocation. There is no need anymore to\nflush the request queue when switching I/O accounting state.\n\nSigned-off-by: Jerome Marchand \u003cjmarchan@redhat.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "04dc6e71a28d4815bf9431efcafc107bb0ad2792", "tree": "dd51f2491b984d9f8f571f2bdc6b51cadb8c686d", "parents": [ "4d00aa47e2337dcfe2d8a7215dbde3765b507167" ], "author": { "name": "Jeff Moyer", "email": "jmoyer@redhat.com", "time": "Tue Apr 21 07:31:56 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Apr 22 08:35:11 2009 +0200" }, "message": "cfq-iosched: use the default seek distance when there aren\u0027t enough seek samples\n\nIf the cfq io context doesn\u0027t have enough samples yet to provide a mean\nseek distance, then use the default threshold we have for seeky IO instead\nof defaulting to 0.\n\nSigned-off-by: Jeff Moyer \u003cjmoyer@redhat.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "4d00aa47e2337dcfe2d8a7215dbde3765b507167", "tree": "069f0c202e6a3f3017b0a8b4320b31172bcc1071", "parents": [ "b759113499d6c7cb75fab04f56772579308bc0f8" ], "author": { "name": "Jeff Moyer", "email": "jmoyer@redhat.com", "time": "Tue Apr 21 07:25:04 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Apr 22 08:35:11 2009 +0200" }, "message": "cfq-iosched: make seek_mean converge more quickly\n\nRight now, depending on the first sector to which a process issues I/O,\nthe seek time may start out way out of whack. So make sure we start\nwith 0 sectors in seek, instead of the offset of the first request\nissued.\n\nSigned-off-by: Jeff Moyer \u003cjmoyer@redhat.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "b759113499d6c7cb75fab04f56772579308bc0f8", "tree": "d36a0ea295f675bd678ee30e8191c0358cfc5b74", "parents": [ "71982a409f12c50d011325a4471aa20666bb908d" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Apr 17 08:36:50 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Apr 22 08:35:10 2009 +0200" }, "message": "block: make blk_abort_queue() ignore non-request based devices\n\nThere\u0027s nothing to do for those devices, since the timeout handling is\nbased on requests.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "71982a409f12c50d011325a4471aa20666bb908d", "tree": "d457415cc6c50b386a6876acf0abc4472f0e5630", "parents": [ "a9e9dc24bbc3e084450a22cf4fb82f5f5d4cbeea" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Apr 17 08:34:48 2009 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Apr 22 08:35:10 2009 +0200" }, "message": "block: include empty disks in /proc/diskstats\n\n/proc/diskstats used to show stats for all disks whether they\u0027re\nzero-sized or not and their non-zero partitions. Commit\n074a7aca7afa6f230104e8e65eba3420263714a5 accidentally changed the\nbehavior such that it doesn\u0027t print out zero sized disks. This patch\nimplements DISK_PITER_INCL_EMPTY_PART0 flag to partition iterator and\nuses it in diskstats_show() such that empty part0 is shown in\n/proc/diskstats.\n\nReported and bisectd by Dianel Collins.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nReported-by: Daniel Collins \u003csolemnwarning@solemnwarning.no-ip.org\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "cd0aca2d550f238d80ba58e7dcade4ea3d0a3aa7", "tree": "9581a77ce54247a18963c9d827063923a667add7", "parents": [ "25636e282fe95508cae96bb27f86407aef935817" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Wed Apr 15 22:10:25 2009 +0900" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Apr 22 08:35:09 2009 +0200" }, "message": "block: fix queue bounce limit setting\n\nImpact: don\u0027t set GFP_DMA in q-\u003ebounce_gfp unnecessarily\n\nAll DMA address limits are expressed in terms of the last addressable\nunit (byte or page) instead of one plus that. However, when\ndetermining bounce_gfp for 64bit machines in blk_queue_bounce_limit(),\nit compares the specified limit against 0x100000000UL to determine\nwhether it\u0027s below 4G ending up falsely setting GFP_DMA in\nq-\u003ebounce_gfp.\n\nAs DMA zone is very small on x86_64, this makes larger SG_IO transfers\nvery eager to trigger OOM killer. Fix it. While at it, rename the\nparameter to @dma_mask for clarity and convert comment to proper\nwinged style.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" } ], "next": "25636e282fe95508cae96bb27f86407aef935817" }