)]}' { "log": [ { "commit": "46bed2b5c16bb7c82e1088d7ae75fb958c8a8c4e", "tree": "bab932a8eec324ca470407ff54097d86a3c0e27f", "parents": [ "c1084561bb85da3630540ebe951749a8cd8fc714" ], "author": { "name": "Jonathan Brassow", "email": "jbrassow@redhat.com", "time": "Tue Aug 02 12:32:07 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:07 2011 +0100" }, "message": "dm raid: add write_mostly parameter\n\nAdd the write_mostly parameter to RAID1 dm-raid tables.\n\nThis allows the user to set the WriteMostly flag on a RAID1 device that\nshould normally be avoided for read I/O.\n\nSigned-off-by: Jonathan Brassow \u003cjbrassow@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "c1084561bb85da3630540ebe951749a8cd8fc714", "tree": "ecdefcf24dd88f4c19a873fa5d26039a0edf03a7", "parents": [ "c0a2fa1ef1057a1e9450d6f055f1cde2ad4f85a2" ], "author": { "name": "Jonathan Brassow", "email": "jbrassow@redhat.com", "time": "Tue Aug 02 12:32:07 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:07 2011 +0100" }, "message": "dm raid: add region_size parameter\n\nAllow the user to specify the region_size.\n\nEnsures that the supplied value meets md\u0027s constraints, viz. the number of\nregions does not exceed 2^21.\n\nSigned-off-by: Jonathan Brassow \u003cjbrassow@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "c0a2fa1ef1057a1e9450d6f055f1cde2ad4f85a2", "tree": "e854f60aea4d5ed24644ee32d6bf97e8cf7e2101", "parents": [ "759dea204cce9f1fc2a5d00ea25211299fc7a4a0" ], "author": { "name": "Jonathan Brassow", "email": "jbrassow@redhat.com", "time": "Tue Aug 02 12:32:06 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:06 2011 +0100" }, "message": "dm raid: improve table parameters documentation\n\nAdd more information about some dm-raid table parameters and clarify how\nparameters are printed when \u0027dmsetup table\u0027 is issued.\n\nSigned-off-by: Jonathan Brassow \u003cjbrassow@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "759dea204cce9f1fc2a5d00ea25211299fc7a4a0", "tree": "3ddbfdc0c4cb97317ea0d0d7bb6879fcac72b840", "parents": [ "ba2e19b0f4ccd6920fe175a86521ff18ede260cb" ], "author": { "name": "Mikulas Patocka", "email": "mpatocka@redhat.com", "time": "Tue Aug 02 12:32:06 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:06 2011 +0100" }, "message": "dm ioctl: forbid multiple device specifiers\n\nExactly one of name, uuid or device must be specified when referencing\nan existing device. This removes the ambiguity (risking the wrong\ndevice being updated) if two conflicting parameters were specified.\nPreviously one parameter got used and any others were ignored silently.\n\nSigned-off-by: Mikulas Patocka \u003cmpatocka@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "ba2e19b0f4ccd6920fe175a86521ff18ede260cb", "tree": "25a9533cfbd1946da36483c3172914b9ea1f51cb", "parents": [ "0ddf9644cc26e74ed671525e61a17bdbebf18da6" ], "author": { "name": "Mikulas Patocka", "email": "mpatocka@redhat.com", "time": "Tue Aug 02 12:32:06 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:06 2011 +0100" }, "message": "dm ioctl: introduce __get_dev_cell\n\nMove logic to find device based on major/minor number to a separate\nfunction __get_dev_cell (similar to __get_uuid_cell and __get_name_cell).\nThis makes the function __find_device_hash_cell more straightforward.\n\nSigned-off-by: Mikulas Patocka \u003cmpatocka@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "0ddf9644cc26e74ed671525e61a17bdbebf18da6", "tree": "fa10cf2fda8f52c0da7f2f1fcec54f2ce2d5bd1f", "parents": [ "a3998799fb4df0b0af8271a7d50c4269032397aa" ], "author": { "name": "Mikulas Patocka", "email": "mpatocka@redhat.com", "time": "Tue Aug 02 12:32:06 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:06 2011 +0100" }, "message": "dm ioctl: fill in device parameters in more ioctls\n\nMove parameter filling from find_device to __find_device_hash_cell.\n\nThis patch causes ioctls using __find_device_hash_cell\n(DM_DEV_REMOVE_CMD, DM_DEV_SUSPEND_CMD - resume, DM_TABLE_CLEAR_CMD)\nto return device parameters, bringing them into line with the other\nioctls.\n\nSigned-off-by: Mikulas Patocka \u003cmpatocka@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "a3998799fb4df0b0af8271a7d50c4269032397aa", "tree": "2a0dc0a082519afd70cc991da36f620bc21272fe", "parents": [ "b26f5e3d7127487e934758c1fbe05d683b082cb0" ], "author": { "name": "Mike Snitzer", "email": "snitzer@redhat.com", "time": "Tue Aug 02 12:32:06 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:06 2011 +0100" }, "message": "dm flakey: add corrupt_bio_byte feature\n\nAdd corrupt_bio_byte feature to simulate corruption by overwriting a byte at a\nspecified position with a specified value during intervals when the device is\n\"down\".\n\nSigned-off-by: Mike Snitzer \u003csnitzer@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "b26f5e3d7127487e934758c1fbe05d683b082cb0", "tree": "8b120e0e45e3a50c1c5adada0eede0870d62457d", "parents": [ "dfd068b01f02653c6650f1c0eda443b2655d1471" ], "author": { "name": "Mike Snitzer", "email": "snitzer@redhat.com", "time": "Tue Aug 02 12:32:05 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:05 2011 +0100" }, "message": "dm flakey: add drop_writes\n\nAdd \u0027drop_writes\u0027 option to drop writes silently while the\ndevice is \u0027down\u0027. Reads are not touched.\n\nSigned-off-by: Mike Snitzer \u003csnitzer@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "dfd068b01f02653c6650f1c0eda443b2655d1471", "tree": "e61e92a4a1e6b4c0170a87453219cabaf66e312a", "parents": [ "30e4171bfe3d1c49689803338005cc0071dddaff" ], "author": { "name": "Mike Snitzer", "email": "snitzer@redhat.com", "time": "Tue Aug 02 12:32:05 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:05 2011 +0100" }, "message": "dm flakey: support feature args\n\nAdd the ability to specify arbitrary feature flags when creating a\nflakey target. This code uses the same target argument helpers that\nthe multipath target does.\n\nAlso remove the superfluous \u0027dm-flakey\u0027 prefixes from the error messages,\nas they already contain the prefix \u0027flakey\u0027.\n\nSigned-off-by: Mike Snitzer \u003csnitzer@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "30e4171bfe3d1c49689803338005cc0071dddaff", "tree": "8ba89dcca8774a94cbd5bb7685a9ea27570d772c", "parents": [ "498f0103ea13123e007660def9072a0b7dd1c599" ], "author": { "name": "Mike Snitzer", "email": "snitzer@redhat.com", "time": "Tue Aug 02 12:32:05 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:05 2011 +0100" }, "message": "dm flakey: use dm_target_offset and support discards\n\nUse dm_target_offset() and support discards.\n\nSigned-off-by: Mike Snitzer \u003csnitzer@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "498f0103ea13123e007660def9072a0b7dd1c599", "tree": "3940ca8e50f13c3ed3a79c1939bacbc841ecb179", "parents": [ "a6e50b409d3f9e0833e69c3c9cca822e8fa4adbb" ], "author": { "name": "Mike Snitzer", "email": "snitzer@redhat.com", "time": "Tue Aug 02 12:32:04 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:04 2011 +0100" }, "message": "dm table: share target argument parsing functions\n\nMove multipath target argument parsing code into dm-table so other\ntargets can share it.\n\nSigned-off-by: Mike Snitzer \u003csnitzer@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "a6e50b409d3f9e0833e69c3c9cca822e8fa4adbb", "tree": "82ca807c21156437270e6a1ed255b18ccf8b3672", "parents": [ "d5b9dd04bd74b774b8e8d93ced7a0d15ad403fa9" ], "author": { "name": "Mikulas Patocka", "email": "mpatocka@redhat.com", "time": "Tue Aug 02 12:32:04 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:04 2011 +0100" }, "message": "dm snapshot: skip reading origin when overwriting complete chunk\n\nIf we write a full chunk in the snapshot, skip reading the origin device\nbecause the whole chunk will be overwritten anyway.\n\nThis patch changes the snapshot write logic when a full chunk is written.\nIn this case:\n 1. allocate the exception\n 2. dispatch the bio (but don\u0027t report the bio completion to device mapper)\n 3. write the exception record\n 4. report bio completed\n\nCallbacks must be done through the kcopyd thread, because callbacks must not\nrace with each other. So we create two new functions:\n\n dm_kcopyd_prepare_callback: allocate a job structure and prepare the callback.\n (This function must not be called from interrupt context.)\n\n dm_kcopyd_do_callback: submit callback.\n (This function may be called from interrupt context.)\n\nPerformance test (on snapshots with 4k chunk size):\n without the patch:\n non-direct-io sequential write (dd): 17.7MB/s\n direct-io sequential write (dd): 20.9MB/s\n non-direct-io random write (mkfs.ext2): 0.44s\n\n with the patch:\n non-direct-io sequential write (dd): 26.5MB/s\n direct-io sequential write (dd): 33.2MB/s\n non-direct-io random write (mkfs.ext2): 0.27s\n\nSigned-off-by: Mikulas Patocka \u003cmpatocka@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "d5b9dd04bd74b774b8e8d93ced7a0d15ad403fa9", "tree": "060512c4c411e4adda203fd721b79b50b0ff54df", "parents": [ "08649012545cfb116798260352547cf4d47064ec" ], "author": { "name": "Mikulas Patocka", "email": "mpatocka@redhat.com", "time": "Tue Aug 02 12:32:04 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:04 2011 +0100" }, "message": "dm: ignore merge_bvec for snapshots when safe\n\nAdd a new flag DMF_MERGE_IS_OPTIONAL to struct mapped_device to indicate\nwhether the device can accept bios larger than the size its merge\nfunction returns. When set, use this to send large bios to snapshots\nwhich can split them if necessary. Snapshot I/O may be significantly\nfragmented and this approach seems to improve peformance.\n\nBefore the patch, dm_set_device_limits restricted bio size to page size\nif the underlying device had a merge function and the target didn\u0027t\nprovide a merge function. After the patch, dm_set_device_limits\nrestricts bio size to page size if the underlying device has a merge\nfunction, doesn\u0027t have DMF_MERGE_IS_OPTIONAL flag and the target doesn\u0027t\nprovide a merge function.\n\nThe snapshot target can\u0027t provide a merge function because when the merge\nfunction is called, it is impossible to determine where the bio will be\nremapped. Previously this led us to impose a 4k limit, which we can\nnow remove if the snapshot store is located on a device without a merge\nfunction. Together with another patch for optimizing full chunk writes,\nit improves performance from 29MB/s to 40MB/s when writing to the\nfilesystem on snapshot store.\n\nIf the snapshot store is placed on a non-dm device with a merge function\n(such as md-raid), device mapper still limits all bios to page size.\n\nSigned-off-by: Mikulas Patocka \u003cmpatocka@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "08649012545cfb116798260352547cf4d47064ec", "tree": "8aa7eac4b53a07a9bdcb01ed2da11e250c823187", "parents": [ "3e8dbb7f3966c80d77272f8b4f430babc99f6595" ], "author": { "name": "Mike Snitzer", "email": "snitzer@redhat.com", "time": "Tue Aug 02 12:32:04 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:04 2011 +0100" }, "message": "dm table: clean dm_get_device and move exports\n\nThere is no need for __table_get_device to be factored out.\nAlso move the exports to the end of their respective functions.\n\nSigned-off-by: Mike Snitzer \u003csnitzer@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "3e8dbb7f3966c80d77272f8b4f430babc99f6595", "tree": "00192da87f8e5db890bd5c6dab9c941a905b294e", "parents": [ "2ca4c92f58f9386e080b26f9ccd78c9ca5825a42" ], "author": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:03 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:03 2011 +0100" }, "message": "dm raid: tidy includes\n\nA dm target only needs to use include/linux dm headers.\n\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "2ca4c92f58f9386e080b26f9ccd78c9ca5825a42", "tree": "638f6e97f829cdf8cfc090dabff9213dc50db149", "parents": [ "13c87583ea4e867211fc3e7edab750c353c47c95" ], "author": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:03 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:03 2011 +0100" }, "message": "dm ioctl: prevent empty message\n\nDetect invalid empty messages in core dm instead of requiring every target to\ncheck this.\n\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "13c87583ea4e867211fc3e7edab750c353c47c95", "tree": "93d1a2b20f1033e031eedf86a19ab822b1fbb576", "parents": [ "a2d2b0345a0f30c169b7d08b8cebdd4853fcb0f8" ], "author": { "name": "Jonathan Brassow", "email": "jbrassow@redhat.com", "time": "Tue Aug 02 12:32:03 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:03 2011 +0100" }, "message": "dm raid: cleanup parameter handling\n\nRe-order the parameters so they are handled consistently in the same order\nwhere defined, parsed and output.\n\nOnly include rebuild parameters in the STATUSTYPE_TABLE output if they were\nsupplied in the original table line.\n\nCorrect the parameter count when outputting rebuild: there are two words,\nnot one.\n\nUse case-independent checks for keywords (as in other device-mapper targets).\n\nSigned-off-by: Jonathan Brassow \u003cjbrassow@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "a2d2b0345a0f30c169b7d08b8cebdd4853fcb0f8", "tree": "baa54cd731f8c191eb8574ae34bc4f8638a6ed79", "parents": [ "aa3f0794d279cd154ac100f92ff3904ea1f56de2" ], "author": { "name": "Jonathan Brassow", "email": "jbrassow@redhat.com", "time": "Tue Aug 02 12:32:03 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:03 2011 +0100" }, "message": "dm snapshot: style cleanups\n\nCoding style cleanups.\n\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\nSigned-off-by: Jonathan Brassow \u003cjbrassow@redhat.com\u003e\n" }, { "commit": "aa3f0794d279cd154ac100f92ff3904ea1f56de2", "tree": "a18baeb6727d8be3089dc9aea74239462d2ce82c", "parents": [ "5bf45a3dcdba9ff43959f7b5b44523fab254c19c" ], "author": { "name": "Mikulas Patocka", "email": "mpatocka@redhat.com", "time": "Tue Aug 02 12:32:03 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:03 2011 +0100" }, "message": "dm snapshot: remove unused definitions\n\nRemove a couple of unused #defines.\n\nSigned-off-by: Mikulas Patocka \u003cmpatocka@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "5bf45a3dcdba9ff43959f7b5b44523fab254c19c", "tree": "5306d66f4afd6336ee07dc59bd3ddf964b57e318", "parents": [ "4622afb3f50e03ce6da42002e7ed3675dfafc187" ], "author": { "name": "Mikulas Patocka", "email": "mpatocka@redhat.com", "time": "Tue Aug 02 12:32:02 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:02 2011 +0100" }, "message": "dm kcopyd: remove nr_pages field from job structure\n\nThe nr_pages field in struct kcopyd_job is only used temporarily in\nrun_pages_job() to count the number of required pages.\nWe can use a local variable instead.\n\nSigned-off-by: Mikulas Patocka \u003cmpatocka@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "4622afb3f50e03ce6da42002e7ed3675dfafc187", "tree": "6143b3a7a3963c693cd018886ff51e10113c8805", "parents": [ "e29e65aacbd9e628378084905cbcf62a9fa4a8cc" ], "author": { "name": "Mikulas Patocka", "email": "mpatocka@redhat.com", "time": "Tue Aug 02 12:32:02 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:02 2011 +0100" }, "message": "dm kcopyd: remove offset field from job structure\n\nThe offset field in struct kcopyd_job is always zero so remove it.\n\nSigned-off-by: Mikulas Patocka \u003cmpatocka@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "e29e65aacbd9e628378084905cbcf62a9fa4a8cc", "tree": "279e6e87d60da82c082833205c996d7046b1a46d", "parents": [ "6c9b27ab08aaf46426515b8b858ad9c60731c7a1" ], "author": { "name": "Joe Perches", "email": "joe@perches.com", "time": "Tue Aug 02 12:32:02 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:02 2011 +0100" }, "message": "dm: use vzalloc\n\nUse vzalloc() instead of vmalloc()+memset().\n\nSigned-off-by: Joe Perches \u003cjoe@perches.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "6c9b27ab08aaf46426515b8b858ad9c60731c7a1", "tree": "4a6acc8a539df7371f1df85376a71029a5c1f4f9", "parents": [ "c8f543e0786785d8c7118fc2878e42bc0193a88d" ], "author": { "name": "Kirill A. Shutemov", "email": "kirill@shutemov.name", "time": "Tue Aug 02 12:32:02 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:02 2011 +0100" }, "message": "dm log: userspace use list_move\n\nReplace list_del() followed by list_add() with list_move().\n\nSigned-off-by: Kirill A. Shutemov \u003ckirill@shutemov.name\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "c8f543e0786785d8c7118fc2878e42bc0193a88d", "tree": "b8984adc44c3a15f1bee56f3b6b9ff49f8ed4d2c", "parents": [ "936688d7eb0f39be96c5791be1a04994cc8d6aa0" ], "author": { "name": "Akinobu Mita", "email": "akinobu.mita@gmail.com", "time": "Tue Aug 02 12:32:01 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:01 2011 +0100" }, "message": "dm log: clean up bit little endian bitops\n\nUsing __test_and_{set,clear}_bit_le() with ignoring its return value\ncan be replaced with __{set,clear}_bit_le().\n\nThis also removes unnecessary casts.\n\nSigned-off-by: Akinobu Mita \u003cakinobu.mita@gmail.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "936688d7eb0f39be96c5791be1a04994cc8d6aa0", "tree": "4001f52284d39f5353174096e76b357f52ee2fb7", "parents": [ "283a8328ca5b987e547848de8ff0e28edcfb9e08" ], "author": { "name": "Mike Snitzer", "email": "snitzer@redhat.com", "time": "Tue Aug 02 12:32:01 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:01 2011 +0100" }, "message": "dm table: fix discard support\n\nRemove \u0027discards_supported\u0027 from the dm_table structure. The same\ninformation can be easily discovered from the table\u0027s target(s) in\ndm_table_supports_discards().\n\nBefore this fix dm_table_supports_discards() would skip checking the\nindividual targets\u0027 \u0027discards_supported\u0027 flag if any one target in the\ntable didn\u0027t set num_discard_requests \u003e 0. Now the per-target\n\u0027discards_supported\u0027 flag is effective at insuring the final DM device\nadvertises discard support. But, to be clear, targets that don\u0027t\nsupport discards (!num_discard_requests) will not receive discard\nrequests.\n\nAlso DMWARN if a target sets \u0027discards_supported\u0027 override but forgets\nto set \u0027num_discard_requests\u0027.\n\nSigned-off-by: Mike Snitzer \u003csnitzer@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "283a8328ca5b987e547848de8ff0e28edcfb9e08", "tree": "b500dbe90c0ebad2ff96ba1b7f0db16089bb3560", "parents": [ "d15b774c2920d55e3d58275c97fbe3adc3afde38" ], "author": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:01 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:01 2011 +0100" }, "message": "dm: suppress endian warnings\n\nSuppress sparse warnings about cpu_to_le32() by using __le32 types for\non-disk data etc.\n\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "d15b774c2920d55e3d58275c97fbe3adc3afde38", "tree": "4801d4e5a70f1e8e57475e6ea2f8e1238b6bbc75", "parents": [ "bb91bc7bacb906c9f3a9b22744c53fa7564b51ba" ], "author": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:01 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:01 2011 +0100" }, "message": "dm: fix idr leak on module removal\n\nDestroy _minor_idr when unloading the core dm module. (Found by kmemleak.)\n\nCc: stable@kernel.org\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "bb91bc7bacb906c9f3a9b22744c53fa7564b51ba", "tree": "8acd6ee46ab5a557afcd1c491b55a68830252301", "parents": [ "286f367dad40beb3234a18c17391d03ba939a7f3" ], "author": { "name": "Mikulas Patocka", "email": "mpatocka@redhat.com", "time": "Tue Aug 02 12:32:01 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:01 2011 +0100" }, "message": "dm io: flush cpu cache with vmapped io\n\nFor normal kernel pages, CPU cache is synchronized by the dma layer.\nHowever, this is not done for pages allocated with vmalloc. If we do I/O\nto/from vmallocated pages, we must synchronize CPU cache explicitly.\n\nPrior to doing I/O on vmallocated page we must call\nflush_kernel_vmap_range to flush dirty cache on the virtual address.\nAfter finished read we must call invalidate_kernel_vmap_range to\ninvalidate cache on the virtual address, so that accesses to the virtual\naddress return newly read data and not stale data from CPU cache.\n\nThis patch fixes metadata corruption on dm-snapshots on PA-RISC and\npossibly other architectures with caches indexed by virtual address.\n\nCc: stable \u003cstable@kernel.org\u003e\nSigned-off-by: Mikulas Patocka \u003cmpatocka@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "286f367dad40beb3234a18c17391d03ba939a7f3", "tree": "50e7b04332ce6e8ab920284528d555e67aae2081", "parents": [ "762a80d9fc9f690a3a35983f3b4619a220650808" ], "author": { "name": "Mike Snitzer", "email": "snitzer@redhat.com", "time": "Tue Aug 02 12:32:00 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:00 2011 +0100" }, "message": "dm mpath: fix potential NULL pointer in feature arg processing\n\nAvoid dereferencing a NULL pointer if the number of feature arguments\nsupplied is fewer than indicated.\n\nSigned-off-by: Mike Snitzer \u003csnitzer@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\nCc: stable@kernel.org\n" }, { "commit": "762a80d9fc9f690a3a35983f3b4619a220650808", "tree": "807d9cfcd1c2395cd1cf62a95ebd6676ee2a6a4d", "parents": [ "6140333d3656f62ac7e6a5af87e7fe92cfb8d655" ], "author": { "name": "Mikulas Patocka", "email": "mpatocka@redhat.com", "time": "Tue Aug 02 12:32:00 2011 +0100" }, "committer": { "name": "Alasdair G Kergon", "email": "agk@redhat.com", "time": "Tue Aug 02 12:32:00 2011 +0100" }, "message": "dm snapshot: flush disk cache when merging\n\nThis patch makes dm-snapshot flush disk cache when writing metadata for\nmerging snapshot.\n\nWithout cache flushing the disk may reorder metadata write and other\ndata writes and there is a possibility of data corruption in case of\npower fault.\n\nCc: stable@kernel.org\nSigned-off-by: Mikulas Patocka \u003cmpatocka@redhat.com\u003e\nSigned-off-by: Alasdair G Kergon \u003cagk@redhat.com\u003e\n" }, { "commit": "6140333d3656f62ac7e6a5af87e7fe92cfb8d655", "tree": "d96f7ad2196b4383f5ca4396c956e24c82b2952c", "parents": [ "6f56c218666b5c7eff354364357307d18c10058b", "58c54fcca3bac5bf9290cfed31c76e4c4bfbabaf" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 28 05:50:27 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 28 05:50:27 2011 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://neil.brown.name/md\n\n* \u0027for-linus\u0027 of git://neil.brown.name/md: (75 commits)\n md/raid10: handle further errors during fix_read_error better.\n md/raid10: Handle read errors during recovery better.\n md/raid10: simplify read error handling during recovery.\n md/raid10: record bad blocks due to write errors during resync/recovery.\n md/raid10: attempt to fix read errors during resync/check\n md/raid10: Handle write errors by updating badblock log.\n md/raid10: clear bad-block record when write succeeds.\n md/raid10: avoid writing to known bad blocks on known bad drives.\n md/raid10 record bad blocks as needed during recovery.\n md/raid10: avoid reading known bad blocks during resync/recovery.\n md/raid10 - avoid reading from known bad blocks - part 3\n md/raid10: avoid reading from known bad blocks - part 2\n md/raid10: avoid reading from known bad blocks - part 1\n md/raid10: Split handle_read_error out from raid10d.\n md/raid10: simplify/reindent some loops.\n md/raid5: Clear bad blocks on successful write.\n md/raid5. Don\u0027t write to known bad block on doubtful devices.\n md/raid5: write errors should be recorded as bad blocks if possible.\n md/raid5: use bad-block log to improve handling of uncorrectable read errors.\n md/raid5: avoid reading from known bad blocks.\n ...\n" }, { "commit": "6f56c218666b5c7eff354364357307d18c10058b", "tree": "5c18d12d2410d25b0f8b5a2150e2f2f4df20e95b", "parents": [ "95b6886526bb510b8370b625a49bc0ab3b8ff10f", "8d34e6d3ec0393a286569587fbd9675abd258d93" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 28 05:49:31 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 28 05:49:31 2011 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6:\n sound: oss: rename local change_bits to avoid powerpc bitsops.h definition\n ALSA: hda - Fix duplicated DAC assignments for Realtek\n ALSA: asihpi - off by one in asihpi_hpi_ioctl()\n ALSA: hda - Fix Oops with Realtek quirks with NULL adc_nids\n ALSA: asihpi - bug fix pa use before init.\n ALSA: hda - Add support for vref-out based mute LED control on IDT codecs\n" }, { "commit": "95b6886526bb510b8370b625a49bc0ab3b8ff10f", "tree": "2862606224820d200be12d2092dcd26df1654b80", "parents": [ "22712200e175e0df5c7f9edfe6c6bf5c94c23b83", "29412f0f6a19e34336368f13eab848091c343952" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 19:26:38 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 19:26:38 2011 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6: (54 commits)\n tpm_nsc: Fix bug when loading multiple TPM drivers\n tpm: Move tpm_tis_reenable_interrupts out of CONFIG_PNP block\n tpm: Fix compilation warning when CONFIG_PNP is not defined\n TOMOYO: Update kernel-doc.\n tpm: Fix a typo\n tpm_tis: Probing function for Intel iTPM bug\n tpm_tis: Fix the probing for interrupts\n tpm_tis: Delay ACPI S3 suspend while the TPM is busy\n tpm_tis: Re-enable interrupts upon (S3) resume\n tpm: Fix display of data in pubek sysfs entry\n tpm_tis: Add timeouts sysfs entry\n tpm: Adjust interface timeouts if they are too small\n tpm: Use interface timeouts returned from the TPM\n tpm_tis: Introduce durations sysfs entry\n tpm: Adjust the durations if they are too small\n tpm: Use durations returned from TPM\n TOMOYO: Enable conditional ACL.\n TOMOYO: Allow using argv[]/envp[] of execve() as conditions.\n TOMOYO: Allow using executable\u0027s realpath and symlink\u0027s target as conditions.\n TOMOYO: Allow using owner/group etc. of file objects as conditions.\n ...\n\nFix up trivial conflict in security/tomoyo/realpath.c\n" }, { "commit": "58c54fcca3bac5bf9290cfed31c76e4c4bfbabaf", "tree": "25f663873429468c3b582bc7544f983759b7592e", "parents": [ "5e5702898e93eee7d69b6efde109609a89a61001" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:25 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:25 2011 +1000" }, "message": "md/raid10: handle further errors during fix_read_error better.\n\nIf we find more read/write errors we should record a bad block before\nfailing the device.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "5e5702898e93eee7d69b6efde109609a89a61001", "tree": "87f47cc7e66da78befd16af6d479761b70f7adea", "parents": [ "e684e41db3bad44f1262341300b827c0d94ae220" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:25 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:25 2011 +1000" }, "message": "md/raid10: Handle read errors during recovery better.\n\nCurrently when we get a read error during recovery, we simply abort\nthe recovery.\n\nInstead, repeat the read in page-sized blocks.\nOn successful reads, write to the target.\nOn read errors, record a bad block on the destination,\nand only if that fails do we abort the recovery.\n\nAs we now retry reads we need to know where we read from. This was in\nbi_sector but that can be changed during a read attempt.\nSo store the correct from_addr and to_addr in the r10_bio for later\naccess.\n\n\nSigned-off-by: NeilBrown\u003cneilb@suse.de\u003e\n" }, { "commit": "e684e41db3bad44f1262341300b827c0d94ae220", "tree": "a3ff2ec212d4f69a06a64b3a6841895b8cf85673", "parents": [ "1a0b7cd82657a590f163b090bd9123a3a6b9aae4" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:25 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:25 2011 +1000" }, "message": "md/raid10: simplify read error handling during recovery.\n\nIf a read error is detected during recovery the code currently\nfails the read device.\nThis isn\u0027t really necessary. recovery_request_write will signal\na write error to end_sync_write and it will record a write\nerror on the destination device which will record a bad block\nthere or kick it from the array.\n\nSo just remove this call to do md_error.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "1a0b7cd82657a590f163b090bd9123a3a6b9aae4", "tree": "0dc3ccf6ad6ad88283e6d7924c38524865866cba", "parents": [ "f84ee364dd15af11cada1e673f94128f62db189e" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:25 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:25 2011 +1000" }, "message": "md/raid10: record bad blocks due to write errors during resync/recovery.\n\nIf we get a write error during resync/recovery don\u0027t fail the device\nbut instead record a bad block. If that fails we can then fail the\ndevice.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "f84ee364dd15af11cada1e673f94128f62db189e", "tree": "e57fc87130b8bb6958413f39ae51718977540152", "parents": [ "bd870a16c5946d86126f7203db3c73b71de0a1d8" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:25 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:25 2011 +1000" }, "message": "md/raid10: attempt to fix read errors during resync/check\n\nWe already attempt to fix read errors found during normal IO\nand a \u0027repair\u0027 process.\nIt is best to try to repair them at any time they are found,\nso move a test so that during sync and check a read error will\nbe corrected by over-writing with good data.\n\nIf both (all) devices have known bad blocks in the sync section we\nwon\u0027t try to fix even though the bad blocks might not overlap. That\nshould be considered later.\n\nAlso if we hit a read error during recovery we don\u0027t try to fix it.\nIt would only be possible to fix if there were at least three copies\nof data, which is not very common with RAID10. But it should still\nbe considered later.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "bd870a16c5946d86126f7203db3c73b71de0a1d8", "tree": "3492f61a441266c796b8a08ec30c06f7f6f27fbc", "parents": [ "749c55e942d91cb27045fe2eb313aa5afe68ae0b" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:24 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:24 2011 +1000" }, "message": "md/raid10: Handle write errors by updating badblock log.\n\nWhen we get a write error (in the data area, not in metadata),\nupdate the badblock log rather than failing the whole device.\n\nAs the write may well be many blocks, we trying writing each\nblock individually and only log the ones which fail.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "749c55e942d91cb27045fe2eb313aa5afe68ae0b", "tree": "ddf80a1eb3ef9005bc209c1c4946916b89c22a33", "parents": [ "d4432c23be957ff061f7b23fd60e8506cb472a55" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:24 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:24 2011 +1000" }, "message": "md/raid10: clear bad-block record when write succeeds.\n\nIf we succeed in writing to a block that was recorded as\nbeing bad, we clear the bad-block record.\n\nThis requires some delayed handling as the bad-block-list update has\nto happen in process-context.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "d4432c23be957ff061f7b23fd60e8506cb472a55", "tree": "1e9e8cbc75721e62300bb2251658de870bf79d8a", "parents": [ "e875ecea266a543e643b19e44cf472f1412708f9" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:24 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:24 2011 +1000" }, "message": "md/raid10: avoid writing to known bad blocks on known bad drives.\n\nWriting to known bad blocks on drives that have seen a write error\nis asking for trouble. So try to avoid these blocks.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "e875ecea266a543e643b19e44cf472f1412708f9", "tree": "b602d08f7aa4a743d3c27ad55e347d36991f0814", "parents": [ "40c356ce5ad1a6be817825e1da1bc7494349cc6d" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:24 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:24 2011 +1000" }, "message": "md/raid10 record bad blocks as needed during recovery.\n\nWhen recovering one or more devices, if all the good devices have\nbad blocks we should record a bad block on the device being rebuilt.\n\nIf this fails, we need to abort the recovery.\n\nTo ensure we don\u0027t think that we aborted later than we actually did,\nwe need to move the check for MD_RECOVERY_INTR earlier in md_do_sync,\nin particular before mddev-\u003ecurr_resync is updated.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "40c356ce5ad1a6be817825e1da1bc7494349cc6d", "tree": "6843d537ecdfda6c03860455c187b775bc6dec97", "parents": [ "8dbed5cebdf6796bf2618457b3653cf820934366" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:24 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:24 2011 +1000" }, "message": "md/raid10: avoid reading known bad blocks during resync/recovery.\n\nDuring resync/recovery limit the size of the request to avoid\nreading into a bad block that does not start at-or-before the current\nread address.\n\nSimilarly if there is a bad block at this address, don\u0027t allow the\ncurrent request to extend beyond the end of that bad block.\n\nNow that we don\u0027t ever read from known bad blocks, it is safe to allow\ndevices with those blocks into the array.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "8dbed5cebdf6796bf2618457b3653cf820934366", "tree": "b8e8421a3aae1ee8f21df97f76b116fd0a0a9b1c", "parents": [ "7399c31bc92a26bb8388a73f8e14acadcc512fe5" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:24 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:24 2011 +1000" }, "message": "md/raid10 - avoid reading from known bad blocks - part 3\n\nWhen attempting to repair a read error, don\u0027t read from\ndevices with a known bad block.\n\nAs we are only reading PAGE_SIZE blocks, we don\u0027t try to\nnarrow down to smaller regions in the hope that only part of this\npage is bad - it isn\u0027t worth the effort.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "7399c31bc92a26bb8388a73f8e14acadcc512fe5", "tree": "0f1d9904fde1d5258c84643a26947288251b9776", "parents": [ "856e08e23762dfb92ffc68fd0a8d228f9e152160" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:23 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:23 2011 +1000" }, "message": "md/raid10: avoid reading from known bad blocks - part 2\n\nWhen redirecting a read error to a different device, we must\nagain avoid bad blocks and possibly split the request.\n\nSpin_lock typo fixed thanks to Dan Carpenter \u003cerror27@gmail.com\u003e\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "856e08e23762dfb92ffc68fd0a8d228f9e152160", "tree": "fa9977a39da542eebb2129712703c11009a56ff2", "parents": [ "560f8e5532d63a314271bfb99d3d1d53c938ed14" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:23 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:23 2011 +1000" }, "message": "md/raid10: avoid reading from known bad blocks - part 1\n\nThis patch just covers the basic read path:\n 1/ read_balance needs to check for badblocks, and return not only\n the chosen slot, but also how many good blocks are available\n there.\n 2/ read submission must be ready to issue multiple reads to\n different devices as different bad blocks on different devices\n could mean that a single large read cannot be served by any one\n device, but can still be served by the array.\n This requires keeping count of the number of outstanding requests\n per bio. This count is stored in \u0027bi_phys_segments\u0027\n\nOn read error we currently just fail the request if another target\ncannot handle the whole request. Next patch refines that a bit.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "560f8e5532d63a314271bfb99d3d1d53c938ed14", "tree": "c47cbeb54b1e98f626a3e4af1bf0a184a831d3b9", "parents": [ "1294b9c973251a5e68b62c9b40dd914517bda675" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:23 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:23 2011 +1000" }, "message": "md/raid10: Split handle_read_error out from raid10d.\n\nraid10d() is too big and is about to get bigger, so split\nhandle_read_error() out as a separate function.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "1294b9c973251a5e68b62c9b40dd914517bda675", "tree": "45547cfff8997a3a633490341f8166dc6d00e962", "parents": [ "b84db560ead5417b5594349512baf8837959df4f" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:23 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:23 2011 +1000" }, "message": "md/raid10: simplify/reindent some loops.\n\nWhen a loop ends with a large if, it can be neater to change the\nif to invert the condition and just \u0027continue\u0027.\nThen the body of the if can be indented to a lower level.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "b84db560ead5417b5594349512baf8837959df4f", "tree": "77f8cfe305a32ace5f4ead4eb820e3f9fa14ce67", "parents": [ "73e92e51b7969ef5477dd28fe2ae4d77675896f4" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:23 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:23 2011 +1000" }, "message": "md/raid5: Clear bad blocks on successful write.\n\nOn a successful write to a known bad block, flag the sh\nso that raid5d can remove the known bad block from the list.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "73e92e51b7969ef5477dd28fe2ae4d77675896f4", "tree": "05f3d45d6c686abed79c0e5fac1d0b61ae9f93bd", "parents": [ "bc2607f393bd4fb844c1886a02af929ca0372056" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:22 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:22 2011 +1000" }, "message": "md/raid5. Don\u0027t write to known bad block on doubtful devices.\n\nIf a device has seen write errors, don\u0027t write to any known\nbad blocks on that device.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "bc2607f393bd4fb844c1886a02af929ca0372056", "tree": "45c7f9c538b5e196e389454286771f3beb8628ba", "parents": [ "7f0da59bdc2f65795a57009d78f7753d3aea1de3" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:22 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:22 2011 +1000" }, "message": "md/raid5: write errors should be recorded as bad blocks if possible.\n\nWhen a write error is detected, don\u0027t mark the device as failed\nimmediately but rather record the fact for handle_stripe to deal with.\n\nHandle_stripe then attempts to record a bad block. Only if that fails\ndoes the device get marked as faulty.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "7f0da59bdc2f65795a57009d78f7753d3aea1de3", "tree": "4ab3ae7188122657c12dfab61626d96360fb6240", "parents": [ "31c176ecdf3563140e6395249eda51a18130d9f6" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:22 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:22 2011 +1000" }, "message": "md/raid5: use bad-block log to improve handling of uncorrectable read errors.\n\nIf we get an uncorrectable read error - record a bad block rather than\nfailing the device.\nAnd if these errors (which may be due to known bad blocks) cause\nrecovery to be impossible, record a bad block on the recovering\ndevices, or abort the recovery.\n\nAs we might abort a recovery without failing a device we need to teach\nRAID5 about recovery_disabled handling.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "31c176ecdf3563140e6395249eda51a18130d9f6", "tree": "5ad7dba363214e9d36fa921c221316d2597078ef", "parents": [ "62096bce231b3760882ed91205fc84682d6b0529" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:22 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:39:22 2011 +1000" }, "message": "md/raid5: avoid reading from known bad blocks.\n\nThere are two times that we might read in raid5:\n1/ when a read request fits within a chunk on a single\n working device.\n In this case, if there is any bad block in the range of\n the read, we simply fail the cache-bypass read and\n perform the read though the stripe cache.\n\n2/ when reading into the stripe cache. In this case we\n mark as failed any device which has a bad block in that\n strip (1 page wide).\n Note that we will both avoid reading and avoid writing.\n This is correct (as we will never read from the block, there\n is no point writing), but not optimal (as writing could \u0027fix\u0027\n the error) - that will be addressed later.\n\nIf we have not seen any write errors on the device yet, we treat a bad\nblock like a recent read error. This will encourage an attempt to fix\nthe read error which will either generate a write error, or will\nensure good data is stored there. We don\u0027t yet forget the bad block\nin that case. That comes later.\n\nNow that we honour bad blocks when reading we can allow devices with\nbad blocks into the array.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "62096bce231b3760882ed91205fc84682d6b0529", "tree": "90b8a89be6f3c1983e88a4b0fe9d5a0e15ccda7e", "parents": [ "3a9f28a5117e00a868dd8b4395f9a707ae56764b" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:38:13 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:38:13 2011 +1000" }, "message": "md/raid1: factor several functions out or raid1d()\n\nraid1d is too big with several deep branches.\nSo separate them out into their own functions.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\n" }, { "commit": "3a9f28a5117e00a868dd8b4395f9a707ae56764b", "tree": "36fe0fc7a7ccfc0da03dea546286b7bdef581246", "parents": [ "d8f05d2995d467a91db1af01637e6ffd94660ca8" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:33:42 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:33:42 2011 +1000" }, "message": "md/raid1: improve handling of read failure during recovery.\n\nIf we cannot read a block from anywhere during recovery, there is\nnow a better approach than just giving up.\nWe can record a bad block on each device and keep going - being\ncareful not to clear the bad block when a write succeeds as it might -\nit will be a write of incorrect data.\n\nWe have now reached the state where - for raid1 - we only call\nmd_error if md_set_badblocks has failed.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\n" }, { "commit": "d8f05d2995d467a91db1af01637e6ffd94660ca8", "tree": "e35959bc4f6c370c982df8222eb818c720b94ffd", "parents": [ "cd5ff9a16f0831f68c1024d5d776075b5123b034" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:33:00 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:33:00 2011 +1000" }, "message": "md/raid1: record badblocks found during resync etc.\n\nIf we find a bad block while writing as part of resync/recovery we\nneed to report that back to raid1d which must record the bad block,\nor fail the device.\n\nSimilarly when fixing a read error, a further error should just\nrecord a bad block if possible rather than failing the device.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\n" }, { "commit": "cd5ff9a16f0831f68c1024d5d776075b5123b034", "tree": "490e297bde3d0c52b55d38b38ed1cdb5b5b6f43e", "parents": [ "2ca68f5ed7383733102ee53cd8fa4021ecc3b275" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:32:41 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:32:41 2011 +1000" }, "message": "md/raid1: Handle write errors by updating badblock log.\n\nWhen we get a write error (in the data area, not in metadata),\nupdate the badblock log rather than failing the whole device.\n\nAs the write may well be many blocks, we trying writing each\nblock individually and only log the ones which fail.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\n" }, { "commit": "2ca68f5ed7383733102ee53cd8fa4021ecc3b275", "tree": "29543cff802770d90380b889cf8b0cc01e7d1814", "parents": [ "4367af556133723d0f443e14ca8170d9447317cb" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:32:10 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:32:10 2011 +1000" }, "message": "md/raid1: store behind-write pages in bi_vecs.\n\nWhen performing write-behind we allocate pages to store the data\nduring write.\nPreviously we just keep a list of pages. Now we keep a list of\nbi_vec which includes offset and size.\nThis means that the r1bio has complete information to create a new\nbio which will be needed for retrying after write errors.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\n" }, { "commit": "4367af556133723d0f443e14ca8170d9447317cb", "tree": "d87bb40920f0f43cea586b7dd99b45f713ffd614", "parents": [ "1f68f0c4b677ccd6935ff61e4e6888787505f8dc" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:49 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:49 2011 +1000" }, "message": "md/raid1: clear bad-block record when write succeeds.\n\nIf we succeed in writing to a block that was recorded as\nbeing bad, we clear the bad-block record.\n\nThis requires some delayed handling as the bad-block-list update has\nto happen in process-context.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\n" }, { "commit": "1f68f0c4b677ccd6935ff61e4e6888787505f8dc", "tree": "aaff73efbc3fb7b6092eb2106e142e1684c4b554", "parents": [ "0b7d83865cb7a60b1768212c1e60b8fd7c280506" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "message": "md/raid1: avoid writing to known-bad blocks on known-bad drives.\n\nIf we have seen any write error on a drive, then don\u0027t write to\nany known-bad blocks on that drive.\nIf necessary, we divide the write request up into pieces just\nlike we do for reads, so each piece is either all written or\nall not written to any given drive.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\n" }, { "commit": "0b7d83865cb7a60b1768212c1e60b8fd7c280506", "tree": "6a2bd09b219504e4ae8649d77eff487191667d24", "parents": [ "de393cdea66cbd63c90725663f400c76faf1b255" ], "author": { "name": "Namhyung Kim", "email": "namhyung@gmail.com", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "message": "md: update documentation for md/rdev/state sysfs interface\n\nPrevious patches in the bad block series extended behavior of\nrdev\u0027s \u0027state\u0027 interface but lacked documentation update.\nFix it.\n\nSigned-off-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "de393cdea66cbd63c90725663f400c76faf1b255", "tree": "6a2bf37bee98bf7de42856f904bd23c81e082f8e", "parents": [ "d7a9d443bc8a75a24873c0506f50051edfedc714" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "message": "md: make it easier to wait for bad blocks to be acknowledged.\n\nIt is only safe to choose not to write to a bad block if that bad\nblock is safely recorded in metadata - i.e. if it has been\n\u0027acknowledged\u0027.\n\nIf it hasn\u0027t we need to wait for the acknowledgement.\n\nWe support that using rdev-\u003eblocked wait and\nmd_wait_for_blocked_rdev by introducing a new device flag\n\u0027BlockedBadBlock\u0027.\n\nThis flag is only advisory.\nIt is cleared whenever we acknowledge a bad block, so that a waiter\ncan re-check the particular bad blocks that it is interested it.\n\nIt should be set by a caller when they find they need to wait.\nThis (set after test) is inherently racy, but as\nmd_wait_for_blocked_rdev already has a timeout, losing the race will\nhave minimal impact.\n\nWhen we clear \"Blocked\" was also clear \"BlockedBadBlocks\" incase it\nwas set incorrectly (see above race).\n\nWe also modify the way we manage \u0027Blocked\u0027 to fit better with the new\nhandling of \u0027BlockedBadBlocks\u0027 and to make it consistent between\nexternally managed and internally managed metadata. This requires\nthat each raidXd loop checks if the metadata needs to be written and\ntriggers a write (md_check_recovery) if needed. Otherwise a queued\nwrite request might cause raidXd to wait for the metadata to write,\nand only that thread can write it.\n\nBefore writing metadata, we set FaultRecorded for all devices that\nare Faulty, then after writing the metadata we clear Blocked for any\ndevice for which the Fault was certainly Recorded.\n\nThe \u0027faulty\u0027 device flag now appears in sysfs if the device is faulty\n*or* it has unacknowledged bad blocks. So user-space which does not\nunderstand bad blocks can continue to function correctly.\nUser space which does, should not assume a device is faulty until it\nsees the \u0027faulty\u0027 flag, and then sees the list of unacknowledged bad\nblocks is empty.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "d7a9d443bc8a75a24873c0506f50051edfedc714", "tree": "6255771f6cca87698dcc8eb11d62e7fc217b8d0b", "parents": [ "06f603851fa90bcd236328438278d4dc8b655495" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "message": "md: add \u0027write_error\u0027 flag to component devices.\n\nIf a device has ever seen a write error, we will want to handle\nknown-bad-blocks differently.\nSo create an appropriate state flag and export it via sysfs.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\n" }, { "commit": "06f603851fa90bcd236328438278d4dc8b655495", "tree": "49a7f239a9c2de4bf97d998f161b229a565e33cd", "parents": [ "d2eb35acfdccbe2a3622ed6cc441a5482148423b" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "message": "md/raid1: avoid reading known bad blocks during resync\n\nWhen performing resync/etc, keep the size of the request\nsmall enough that it doesn\u0027t overlap any known bad blocks.\nDevices with badblocks at the start of the request are completely\nexcluded.\nIf there is nowhere to read from due to bad blocks, record\na bad block on each target device.\n\nNow that we never read from known-bad-blocks we can allow devices with\nknown-bad-blocks into a RAID1.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "d2eb35acfdccbe2a3622ed6cc441a5482148423b", "tree": "77600cab29fc9e1fd39d612773086a456fc32d88", "parents": [ "9f2f3830789a4c9c1af2d1437d407c43e05136e6" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "message": "md/raid1: avoid reading from known bad blocks.\n\nNow that we have a bad block list, we should not read from those\nblocks.\nThere are several main parts to this:\n 1/ read_balance needs to check for bad blocks, and return not only\n the chosen device, but also how many good blocks are available\n there.\n 2/ fix_read_error needs to avoid trying to read from bad blocks.\n 3/ read submission must be ready to issue multiple reads to\n different devices as different bad blocks on different devices\n could mean that a single large read cannot be served by any one\n device, but can still be served by the array.\n This requires keeping count of the number of outstanding requests\n per bio. This count is stored in \u0027bi_phys_segments\u0027\n 4/ retrying a read needs to also be ready to submit a smaller read\n and queue another request for the rest.\n\nThis does not yet handle bad blocks when reading to perform resync,\nrecovery, or check.\n\n\u0027md_trim_bio\u0027 will also be used for RAID10, so put it in md.c and\nexport it.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "9f2f3830789a4c9c1af2d1437d407c43e05136e6", "tree": "8e20afbfca82acd7346fb93d35170f44ee01a807", "parents": [ "2699b67223aca6b1450fc2f72e40fada952afc85" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:47 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:47 2011 +1000" }, "message": "md: Disable bad blocks and v0.90 metadata.\n\nv0.90 metadata cannot record bad blocks, so when loading metadata\nfor such a device, set shift to -1.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "2699b67223aca6b1450fc2f72e40fada952afc85", "tree": "c84d0cbb763ad03cd770a218a37f0f1ec31118af", "parents": [ "34b343cff4354ab9864be83be88405fd53d928a0" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:47 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:47 2011 +1000" }, "message": "md: load/store badblock list from v1.x metadata\n\nSpace must have been allocated when array was created.\nA feature flag is set when the badblock list is non-empty, to\nensure old kernels don\u0027t load and trust the whole device.\n\nWe only update the on-disk badblocklist when it has changed.\nIf the badblocklist (or other metadata) is stored on a bad block, we\ndon\u0027t cope very well.\n\nIf metadata has no room for bad block, flag bad-blocks as disabled,\nand do the same for 0.90 metadata.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "34b343cff4354ab9864be83be88405fd53d928a0", "tree": "10d75ecac6091f955cbb8a60b79f443355ca4ea8", "parents": [ "6e0d2d0312fb20c1edac1b2c849068c1c7944abf" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:47 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:47 2011 +1000" }, "message": "md: don\u0027t allow arrays to contain devices with bad blocks.\n\nAs no personality understand bad block lists yet, we must\nreject any device that is known to contain bad blocks.\nAs the personalities get taught, these tests can be removed.\n\nThis only applies to raid1/raid5/raid10.\nFor linear/raid0/multipath/faulty the whole concept of bad blocks\ndoesn\u0027t mean anything so there is no point adding the checks.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\n" }, { "commit": "6e0d2d0312fb20c1edac1b2c849068c1c7944abf", "tree": "5272bdcaf69ccc6d3f2b4e6df90a530d8ee69fbb", "parents": [ "16c791a5af3e50d0c11760485fd68e5829f3be4d" ], "author": { "name": "Namhyung Kim", "email": "namhyung@gmail.com", "time": "Thu Jul 28 11:31:47 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:47 2011 +1000" }, "message": "md: add documentation for bad block log\n\nPrevious patch in the bad block series added new sysfs interfaces\n([unacknowledged_]bad_blocks) for each rdev without documentation.\nAdd it.\n\nSigned-off-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "16c791a5af3e50d0c11760485fd68e5829f3be4d", "tree": "24182e37b278a55a9b05b19154ff52597d220714", "parents": [ "2230dfe4ccc3add340dc6d437965b2de1d269fde" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:47 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:47 2011 +1000" }, "message": "md/bad-block-log: add sysfs interface for accessing bad-block-log.\n\nThis can show the log (providing it fits in one page) and\nallows bad blocks to be \u0027acknowledged\u0027 meaning that they\nhave safely been recorded in metadata.\n\nClearing bad blocks is not allowed via sysfs (except for\ncode testing). A bad block can only be cleared when\na write to the block succeeds.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\n" }, { "commit": "2230dfe4ccc3add340dc6d437965b2de1d269fde", "tree": "fc45b727ad2e1a148e7d20f327b45a3afc474e9d", "parents": [ "a519b26dbe6533416d21b552053b0bf687f878d7" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:46 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:46 2011 +1000" }, "message": "md: beginnings of bad block management.\n\nThis the first step in allowing md to track bad-blocks per-device so\nthat we can fail individual blocks rather than the whole device.\n\nThis patch just adds a data structure for recording bad blocks, with\nroutines to add, remove, search the list.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\n" }, { "commit": "22712200e175e0df5c7f9edfe6c6bf5c94c23b83", "tree": "a3e332aab7f5a953ff4f12e67af2a0e5f32f5be5", "parents": [ "597a67e0ba758e3d2239c81fbb648c6e69ec30a2", "ff95acb6733d41a8d45feb0e18b96df25e610e78" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 16:43:52 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 16:43:52 2011 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:\n Btrfs: make sure reserve_metadata_bytes doesn\u0027t leak out strange errors\n Btrfs: use the commit_root for reading free_space_inode crcs\n Btrfs: reduce extent_state lock contention for metadata\n Btrfs: remove lockdep magic from btrfs_next_leaf\n Btrfs: make a lockdep class for each root\n Btrfs: switch the btrfs tree locks to reader/writer\n Btrfs: fix deadlock when throttling transactions\n Btrfs: stop using highmem for extent_buffers\n Btrfs: fix BUG_ON() caused by ENOSPC when relocating space\n Btrfs: tag pages for writeback in sync\n Btrfs: fix enospc problems with delalloc\n Btrfs: don\u0027t flush delalloc arbitrarily\n Btrfs: use find_or_create_page instead of grab_cache_page\n Btrfs: use a worker thread to do caching\n Btrfs: fix how we merge extent states and deal with cached states\n Btrfs: use the normal checksumming infrastructure for free space cache\n Btrfs: serialize flushers in reserve_metadata_bytes\n Btrfs: do transaction space reservation before joining the transaction\n Btrfs: try to only do one btrfs_search_slot in do_setxattr\n" }, { "commit": "a519b26dbe6533416d21b552053b0bf687f878d7", "tree": "bef24eab8604ef2275eb8f1b591ea52bd4b89194", "parents": [ "768e587e18c1c4ce0403b9532115752189422408" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 07:56:24 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 07:56:24 2011 +1000" }, "message": "md: remove suspicious size_of()\n\nWhen calling bioset_create we pass the size of the front_pad as\n sizeof(mddev)\nwhich looks suspicious as mddev is a pointer and so it looks like a\ncommon mistake where\n sizeof(*mddev)\nwas intended.\nThe size is actually correct as we want to store a pointer in the\nfront padding of the bios created by the bioset, so make the intent\nmore explicit by using\n sizeof(mddev_t *)\n\nReported-by: Zdenek Kabelac \u003czdenek.kabelac@gmail.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "597a67e0ba758e3d2239c81fbb648c6e69ec30a2", "tree": "e2b6146df41943e7f87168fe3f5825722b434223", "parents": [ "28890d3598c352ae065b560e0fded3e79c800ba1", "510792ee29770a38dd409bf2b469ade2fea9eb52" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 13:41:51 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 13:41:51 2011 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://oss.sgi.com/xfs/xfs\n\n* \u0027for-linus\u0027 of git://oss.sgi.com/xfs/xfs:\n xfs: optimize the negative xattr caching\n xfs: prevent against ioend livelocks in xfs_file_fsync\n xfs: flag all buffers as metadata\n xfs: encapsulate a block of debug code\n" }, { "commit": "28890d3598c352ae065b560e0fded3e79c800ba1", "tree": "93267c5b29b9e81185e66a6c2e70e67dc626b63f", "parents": [ "91d41fdf31f74e6e2e5f3cb018eca4200e36e202", "ed1e6211a0a134ff23592c6f057af982ad5dab52" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 13:23:02 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 13:23:02 2011 -0700" }, "message": "Merge branch \u0027nfs-for-3.1\u0027 of git://git.linux-nfs.org/projects/trondmy/linux-nfs\n\n* \u0027nfs-for-3.1\u0027 of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (44 commits)\n NFSv4: Don\u0027t use the delegation-\u003einode in nfs_mark_return_delegation()\n nfs: don\u0027t use d_move in nfs_async_rename_done\n RDMA: Increasing RPCRDMA_MAX_DATA_SEGS\n SUNRPC: Replace xprt-\u003eresend and xprt-\u003esending with a priority queue\n SUNRPC: Allow caller of rpc_sleep_on() to select priority levels\n SUNRPC: Support dynamic slot allocation for TCP connections\n SUNRPC: Clean up the slot table allocation\n SUNRPC: Initalise the struct xprt upon allocation\n SUNRPC: Ensure that we grab the XPRT_LOCK before calling xprt_alloc_slot\n pnfs: simplify pnfs files module autoloading\n nfs: document nfsv4 sillyrename issues\n NFS: Convert nfs4_set_ds_client to EXPORT_SYMBOL_GPL\n SUNRPC: Convert the backchannel exports to EXPORT_SYMBOL_GPL\n SUNRPC: sunrpc should not explicitly depend on NFS config options\n NFS: Clean up - simplify the switch to read/write-through-MDS\n NFS: Move the pnfs write code into pnfs.c\n NFS: Move the pnfs read code into pnfs.c\n NFS: Allow the nfs_pageio_descriptor to signal that a re-coalesce is needed\n NFS: Use the nfs_pageio_descriptor-\u003epg_bsize in the read/write request\n NFS: Cache rpc_ops in struct nfs_pageio_descriptor\n ...\n" }, { "commit": "91d41fdf31f74e6e2e5f3cb018eca4200e36e202", "tree": "81ef11f06bd8047031a2d93706dc263fa1bacd56", "parents": [ "c1095c6da518b0b64e724f629051fa67655cd8d9", "277c5f27a2c86a9a733c0ec0f6a9b1032dfa3e15" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 13:21:40 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 13:21:40 2011 -0700" }, "message": "Merge branch \u0027for-next\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending\n\n* \u0027for-next\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending:\n target: Convert to DIV_ROUND_UP_SECTOR_T usage for sectors / dev_max_sectors\n kernel.h: Add DIV_ROUND_UP_ULL and DIV_ROUND_UP_SECTOR_T macro usage\n iscsi-target: Add iSCSI fabric support for target v4.1\n iscsi: Add Serial Number Arithmetic LT and GT into iscsi_proto.h\n iscsi: Use struct scsi_lun in iscsi structs instead of u8[8]\n iscsi: Resolve iscsi_proto.h naming conflicts with drivers/target/iscsi\n" }, { "commit": "ff95acb6733d41a8d45feb0e18b96df25e610e78", "tree": "e20983c579c9095970aefa9cb176a9df0654d1e4", "parents": [ "02f8c6aee8df3cdc935e9bdd4f2d020306035dbe", "75c195a2cac2c3c8366c0b87de2d6814c4f4d638" ], "author": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 16:13:10 2011 -0400" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 16:18:13 2011 -0400" }, "message": "Merge branch \u0027integration\u0027 into for-linus\n" }, { "commit": "75c195a2cac2c3c8366c0b87de2d6814c4f4d638", "tree": "82ac06d2c8f3746a3d438853d03239311c2a71a1", "parents": [ "2cf8572dac62cc2ff7e995173e95b6c694401b3f" ], "author": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 15:57:44 2011 -0400" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 16:11:41 2011 -0400" }, "message": "Btrfs: make sure reserve_metadata_bytes doesn\u0027t leak out strange errors\n\nThe btrfs transaction code will return any errors that come from\nreserve_metadata_bytes. We need to make sure we don\u0027t return funny\nthings like 1 or EAGAIN.\n\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\n" }, { "commit": "c1095c6da518b0b64e724f629051fa67655cd8d9", "tree": "8c2e33ca6c8e3caa71437c3b69b36a8cf03b4f08", "parents": [ "678624e401b0b7747762b5223fb23f86dcdacc93" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Wed Jul 27 12:49:44 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 12:53:36 2011 -0700" }, "message": "signals: sys_ssetmask/sys_rt_sigsuspend should use set_current_blocked()\n\nsys_ssetmask(), sys_rt_sigsuspend() and compat_sys_rt_sigsuspend()\nchange -\u003eblocked directly. This is not correct, see the changelog in\ne6fa16ab \"signal: sigprocmask() should do retarget_shared_pending()\"\n\nChange them to use set_current_blocked().\n\nAnother change is that now we are doing -\u003esaved_sigmask \u003d -\u003eblocked\nlockless, it doesn\u0027t make any sense to do this under -\u003esiglock.\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nReviewed-by: Matt Fleming \u003cmatt.fleming@linux.intel.com\u003e\nAcked-by: Tejun Heo \u003ctj@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "678624e401b0b7747762b5223fb23f86dcdacc93", "tree": "f3a413887b7ac98c66aa6e77fd6b187ec2c249cb", "parents": [ "09570f914914d2beb0db29c5a9c7344934f2fa8c" ], "author": { "name": "Stephen Rothwell", "email": "sfr@canb.auug.org.au", "time": "Wed Jul 27 12:49:44 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 12:53:36 2011 -0700" }, "message": "sparc: rename atomic_add_unless\n\nShould have been done in commit 1af08a1407f4 (\"This is in preparation\nfor more generic atomic\").\n\nSigned-off-by: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nCc: Arun Sharma \u003casharma@fb.com\u003e\nCc: David Miller \u003cdavem@davemloft.net\u003e\nCc: \"Hans-Christian Egtvedt\" \u003chans-christian.egtvedt@atmel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "09570f914914d2beb0db29c5a9c7344934f2fa8c", "tree": "a93900db5e607887aca3ef2cecc2426abe007d87", "parents": [ "5fd00b031530cc476240f654c078c930f1dcd6ea" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Wed Jul 27 21:47:03 2011 +0300" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 12:50:45 2011 -0700" }, "message": "proc: make struct proc_dir_entry::name a terminal array rather than a pointer\n\nSince __proc_create() appends the name it is given to the end of the PDE\nstructure that it allocates, there isn\u0027t a need to store a name pointer.\nInstead we can just replace the name pointer with a terminal char array of\n_unspecified_ length. The compiler will simply append the string to statically\ndefined variables of PDE type overlapping any hole at the end of the structure\nand, unlike specifying an explicitly _zero_ length array, won\u0027t give a warning\nif you try to statically initialise it with a string of more than zero length.\n\nAlso, whilst we\u0027re at it:\n\n (1) Move namelen to end just prior to name and reduce it to a single byte\n (name shouldn\u0027t be longer than NAME_MAX).\n\n (2) Move pde_unload_lock two places further on so that if it\u0027s four bytes in\n size on a 64-bit machine, it won\u0027t cause an unused hole in the PDE struct.\n\nSigned-off-by: David Howells \u003cdhowells@redhat.com\u003e\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "8d34e6d3ec0393a286569587fbd9675abd258d93", "tree": "a9cc1ef4024ff96a93b0c0f2013d0d604a7b9177", "parents": [ "c48a8fb0d31d6147d8d76b8e2ad7f51a2fbb5c4d" ], "author": { "name": "Andy Whitcroft", "email": "apw@canonical.com", "time": "Wed Jul 27 17:48:41 2011 +0100" }, "committer": { "name": "Takashi Iwai", "email": "tiwai@suse.de", "time": "Wed Jul 27 19:16:05 2011 +0200" }, "message": "sound: oss: rename local change_bits to avoid powerpc bitsops.h definition\n\nThis collides with powerpc exported functions from bitops.h. Rename the\nlocal copy in the oss soundblaster mixer and ad1848 driver.\n\nSigned-off-by: Andy Whitcroft \u003capw@canonical.com\u003e\nSigned-off-by: Takashi Iwai \u003ctiwai@suse.de\u003e\n" }, { "commit": "2cf8572dac62cc2ff7e995173e95b6c694401b3f", "tree": "ae37f2f4a2f4a797ee971a94ee2c29c55a8048dc", "parents": [ "19b6caf4acbf065dc96b47741d99f1b87243c468" ], "author": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Tue Jul 26 15:35:09 2011 -0400" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 12:46:48 2011 -0400" }, "message": "Btrfs: use the commit_root for reading free_space_inode crcs\n\nNow that we are using regular file crcs for the free space cache,\nwe can deadlock if we try to read the free_space_inode while we are\nupdating the crc tree.\n\nThis commit fixes things by using the commit_root to read the crcs. This is\nsafe because we the free space cache file would already be loaded if\nthat block group had been changed in the current transaction.\n\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\n" }, { "commit": "19b6caf4acbf065dc96b47741d99f1b87243c468", "tree": "4bce889648c2459e1dbd9fd835a196db26c06f9b", "parents": [ "31533fb263928c93a34cda41b66a6e83ade5c766" ], "author": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Mon Jul 25 06:50:50 2011 -0400" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 12:46:47 2011 -0400" }, "message": "Btrfs: reduce extent_state lock contention for metadata\n\nFor metadata buffers that don\u0027t straddle pages (all of them), btrfs\ncan safely use the page uptodate bits and extent_buffer uptodate bit\ninstead of needing to use the extent_state tree.\n\nThis greatly reduces contention on the state tree lock.\n\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\n" }, { "commit": "31533fb263928c93a34cda41b66a6e83ade5c766", "tree": "b4f3a770e805403adc1931f3bb15213ee2a0d624", "parents": [ "85d4e461117b40eb10722f774566b19bd5e77879" ], "author": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Tue Jul 26 16:01:59 2011 -0400" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 12:46:47 2011 -0400" }, "message": "Btrfs: remove lockdep magic from btrfs_next_leaf\n\nBefore the reader/writer locks, btrfs_next_leaf needed to keep\nthe path blocking to avoid making lockdep upset.\n\nNow that btrfs_next_leaf only takes read locks, this isn\u0027t required.\n\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\n" }, { "commit": "85d4e461117b40eb10722f774566b19bd5e77879", "tree": "56b7c66d03a72008e0db0bf4f58edbee5170fee1", "parents": [ "bd681513fa6f2ff29aa391f01e413a2d1c59fd77" ], "author": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Tue Jul 26 16:11:19 2011 -0400" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 12:46:46 2011 -0400" }, "message": "Btrfs: make a lockdep class for each root\n\nThis patch was originally from Tejun Heo. lockdep complains about the btrfs\nlocking because we sometimes take btree locks from two different trees at the\nsame time. The current classes are based only on level in the btree, which\nisn\u0027t enough information for lockdep to figure out if the lock is safe.\n\nThis patch makes a class for each type of tree, and lumps all the FS trees that\nactually have files and directories into the same class.\n\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\n" }, { "commit": "bd681513fa6f2ff29aa391f01e413a2d1c59fd77", "tree": "bb10ec6ef876b4d7a553cbe54976ec49a0d10b21", "parents": [ "81317fdeddcef259b6ecf7b5c0d04caa167c6b54" ], "author": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Sat Jul 16 15:23:14 2011 -0400" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 12:46:46 2011 -0400" }, "message": "Btrfs: switch the btrfs tree locks to reader/writer\n\nThe btrfs metadata btree is the source of significant\nlock contention, especially in the root node. This\ncommit changes our locking to use a reader/writer\nlock.\n\nThe lock is built on top of rw spinlocks, and it\nextends the lock tracking to remember if we have a\nread lock or a write lock when we go to blocking. Atomics\ncount the number of blocking readers or writers at any\ngiven time.\n\nIt removes all of the adaptive spinning from the old code\nand uses only the spinning/blocking hints inside of btrfs\nto decide when it should continue spinning.\n\nIn read heavy workloads this is dramatically faster. In write\nheavy workloads we\u0027re still faster because of less contention\non the root node lock.\n\nWe suffer slightly in dbench because we schedule more often\nduring write locks, but all other benchmarks so far are improved.\n\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\n" }, { "commit": "81317fdeddcef259b6ecf7b5c0d04caa167c6b54", "tree": "aeca005b8b595539b554a6b8a92dc052ccad5601", "parents": [ "a65917156e345946dbde3d7effd28124c6d6a8c2" ], "author": { "name": "Josef Bacik", "email": "josef@redhat.com", "time": "Sun Jul 24 15:45:34 2011 -0400" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 12:46:46 2011 -0400" }, "message": "Btrfs: fix deadlock when throttling transactions\n\nHit this nice little deadlock. What happens is this\n\n__btrfs_end_transaction with throttle set, --use_count so it equals 0\n btrfs_commit_transaction\n \u003csomebody else actually manages to start the commit\u003e\n btrfs_end_transaction --use_count so now its -1 \u003c\u003d\u003d BAD\n we just return and wait on the transaction\n\nThis is bad because we just return after our use_count is -1 and don\u0027t let go\nof our num_writer count on the transaction, so the guy committing the\ntransaction just sits there forever. Fix this by inc\u0027ing our use_count if we\u0027re\ngoing to call commit_transaction so that if we call btrfs_end_transaction it\u0027s\nvalid. Thanks,\n\nSigned-off-by: Josef Bacik \u003cjosef@redhat.com\u003e\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\n" }, { "commit": "a65917156e345946dbde3d7effd28124c6d6a8c2", "tree": "dc5478189be0f6a321bfc23ee0545f71de67763b", "parents": [ "199c36eaa95077a47ae1bc55532fc0fbeb80cc95" ], "author": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Tue Jul 19 12:04:14 2011 -0400" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 12:46:45 2011 -0400" }, "message": "Btrfs: stop using highmem for extent_buffers\n\nThe extent_buffers have a very complex interface where\nwe use HIGHMEM for metadata and try to cache a kmap mapping\nto access the memory.\n\nThe next commit adds reader/writer locks, and concurrent use\nof this kmap cache would make it even more complex.\n\nThis commit drops the ability to use HIGHMEM with extent buffers,\nand rips out all of the related code.\n\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\n" }, { "commit": "199c36eaa95077a47ae1bc55532fc0fbeb80cc95", "tree": "ef4e9a5ff244c842b9b335cb391223d9a4d5f854", "parents": [ "f7aaa06bff6f5fe049ce9723267e1639c2c3d8b5" ], "author": { "name": "Miao Xie", "email": "miaox@cn.fujitsu.com", "time": "Fri Jul 15 10:34:36 2011 +0000" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 12:46:45 2011 -0400" }, "message": "Btrfs: fix BUG_ON() caused by ENOSPC when relocating space\n\nWhen we balanced the chunks across the devices, BUG_ON() in\n__finish_chunk_alloc() was triggered.\n\n------------[ cut here ]------------\nkernel BUG at fs/btrfs/volumes.c:2568!\n[SNIP]\nCall Trace:\n [\u003cffffffffa049525e\u003e] btrfs_alloc_chunk+0x8e/0xa0 [btrfs]\n [\u003cffffffffa04546b0\u003e] do_chunk_alloc+0x330/0x3a0 [btrfs]\n [\u003cffffffffa045c654\u003e] btrfs_reserve_extent+0xb4/0x1f0 [btrfs]\n [\u003cffffffffa045c86b\u003e] btrfs_alloc_free_block+0xdb/0x350 [btrfs]\n [\u003cffffffffa048a8d8\u003e] ? read_extent_buffer+0xd8/0x1d0 [btrfs]\n [\u003cffffffffa04476fd\u003e] __btrfs_cow_block+0x14d/0x5e0 [btrfs]\n [\u003cffffffffa044660d\u003e] ? read_block_for_search+0x14d/0x4d0 [btrfs]\n [\u003cffffffffa0447c9b\u003e] btrfs_cow_block+0x10b/0x240 [btrfs]\n [\u003cffffffffa044dd5e\u003e] btrfs_search_slot+0x49e/0x7a0 [btrfs]\n [\u003cffffffffa044f07d\u003e] btrfs_insert_empty_items+0x8d/0xf0 [btrfs]\n [\u003cffffffffa045e973\u003e] insert_with_overflow+0x43/0x110 [btrfs]\n [\u003cffffffffa045eb0d\u003e] btrfs_insert_dir_item+0xcd/0x1f0 [btrfs]\n [\u003cffffffffa0489bd0\u003e] ? map_extent_buffer+0xb0/0xc0 [btrfs]\n [\u003cffffffff812276ad\u003e] ? rb_insert_color+0x9d/0x160\n [\u003cffffffffa046cc40\u003e] ? inode_tree_add+0xf0/0x150 [btrfs]\n [\u003cffffffffa0474801\u003e] btrfs_add_link+0xc1/0x1c0 [btrfs]\n [\u003cffffffff811dacac\u003e] ? security_inode_init_security+0x1c/0x30\n [\u003cffffffffa04a28aa\u003e] ? btrfs_init_acl+0x4a/0x180 [btrfs]\n [\u003cffffffffa047492f\u003e] btrfs_add_nondir+0x2f/0x70 [btrfs]\n [\u003cffffffffa046af16\u003e] ? btrfs_init_inode_security+0x46/0x60 [btrfs]\n [\u003cffffffffa0474ac0\u003e] btrfs_create+0x150/0x1d0 [btrfs]\n [\u003cffffffff81159c63\u003e] ? generic_permission+0x23/0xb0\n [\u003cffffffff8115b415\u003e] vfs_create+0xa5/0xc0\n [\u003cffffffff8115ce6e\u003e] do_last+0x5fe/0x880\n [\u003cffffffff8115dc0d\u003e] path_openat+0xcd/0x3d0\n [\u003cffffffff8115e029\u003e] do_filp_open+0x49/0xa0\n [\u003cffffffff8116a965\u003e] ? alloc_fd+0x95/0x160\n [\u003cffffffff8114f0c7\u003e] do_sys_open+0x107/0x1e0\n [\u003cffffffff810bcc3f\u003e] ? audit_syscall_entry+0x1bf/0x1f0\n [\u003cffffffff8114f1e0\u003e] sys_open+0x20/0x30\n [\u003cffffffff81484ec2\u003e] system_call_fastpath+0x16/0x1b\n[SNIP]\nRIP [\u003cffffffffa049444a\u003e] __finish_chunk_alloc+0x20a/0x220 [btrfs]\n\nThe reason is:\nTask1\t\t\t\t\tSpace balance task\ndo_chunk_alloc()\n __finish_chunk_alloc()\n update device info\n in the chunk tree\n alloc system metadata block\n\t\t\t\t\trelocate system metadata block group\n\t\t\t\t\t set system metadata block group\n\t\t\t\t\t readonly, This block group is the\n\t\t\t\t\t only one that can allocate space. So\n\t\t\t\t\t there is no free space that can be\n\t\t\t\t\t allocated now.\n find no space and don\u0027t try\n to alloc new chunk, and then\n return ENOSPC\n BUG_ON() in __finish_chunk_alloc()\n was triggered.\n\nFix this bug by allocating a new system metadata chunk before relocating the\nold one if we find there is no free space which can be allocated after setting\nthe old block group to be read-only.\n\nReported-by: Tsutomu Itoh \u003ct-itoh@jp.fujitsu.com\u003e\nSigned-off-by: Miao Xie \u003cmiaox@cn.fujitsu.com\u003e\nTested-by: Tsutomu Itoh \u003ct-itoh@jp.fujitsu.com\u003e\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\n" }, { "commit": "f7aaa06bff6f5fe049ce9723267e1639c2c3d8b5", "tree": "d3b5e20709a91f4bc473a898e37531f322a1bc6c", "parents": [ "9e0baf60dea69f31ac3b1adeb35b03b02a53e8e1" ], "author": { "name": "Josef Bacik", "email": "josef@redhat.com", "time": "Fri Jul 15 21:26:38 2011 +0000" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 12:46:44 2011 -0400" }, "message": "Btrfs: tag pages for writeback in sync\n\nEverybody else does this, we need to do it too. If we\u0027re syncing, we need to\ntag the pages we\u0027re going to write for writeback so we don\u0027t end up writing the\nsame stuff over and over again if somebody is constantly redirtying our file.\nThis will keep us from having latencies with heavy sync workloads. Thanks,\n\nSigned-off-by: Josef Bacik \u003cjosef@redhat.com\u003e\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\n" }, { "commit": "9e0baf60dea69f31ac3b1adeb35b03b02a53e8e1", "tree": "0fb899e1fa78b599d22389ca3befc8ab51ff5049", "parents": [ "a5991428064e98c7367fe1c1686ea6a23fb6a4b3" ], "author": { "name": "Josef Bacik", "email": "josef@redhat.com", "time": "Fri Jul 15 15:16:44 2011 +0000" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 12:46:44 2011 -0400" }, "message": "Btrfs: fix enospc problems with delalloc\n\nSo I had this brilliant idea to use atomic counters for outstanding and reserved\nextents, but this turned out to be a bad idea. Consider this where we have 1\noutstanding extent and 1 reserved extent\n\nReserver\t\t\t\tReleaser\n\t\t\t\t\tatomic_dec(outstanding) now 0\natomic_read(outstanding)+1 get 1\natomic_read(reserved) get 1\ndon\u0027t actually reserve anything because\nthey are the same\n\t\t\t\t\tatomic_cmpxchg(reserved, 1, 0)\natomic_inc(outstanding)\natomic_add(0, reserved)\n\t\t\t\t\tfree reserved space for 1 extent\n\nThen the reserver now has no actual space reserved for it, and when it goes to\nfinish the ordered IO it won\u0027t have enough space to do it\u0027s allocation and you\nget those lovely warnings.\n\nSigned-off-by: Josef Bacik \u003cjosef@redhat.com\u003e\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\n" }, { "commit": "a5991428064e98c7367fe1c1686ea6a23fb6a4b3", "tree": "4e063831c205d707bd1e85fb5814a95f61843dc8", "parents": [ "a94733d0bc630edaedc6ca156752dd5a7cb82521" ], "author": { "name": "Josef Bacik", "email": "josef@redhat.com", "time": "Fri Jul 15 16:01:03 2011 +0000" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 12:46:43 2011 -0400" }, "message": "Btrfs: don\u0027t flush delalloc arbitrarily\n\nKill the check to see if we have 512mb of reserved space in delalloc and\nshrink_delalloc if we do. This causes unexpected latencies and we have other\nlogic to see if we need to throttle. Thanks,\n\nSigned-off-by: Josef Bacik \u003cjosef@redhat.com\u003e\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\n" }, { "commit": "a94733d0bc630edaedc6ca156752dd5a7cb82521", "tree": "3f0bd508aa1ce5894e43df45bb73031a380ed8f5", "parents": [ "bab39bf998133510f2dad08158006197ec0dabea" ], "author": { "name": "Josef Bacik", "email": "josef@redhat.com", "time": "Mon Jul 11 10:47:06 2011 -0400" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 12:46:43 2011 -0400" }, "message": "Btrfs: use find_or_create_page instead of grab_cache_page\n\ngrab_cache_page will use mapping_gfp_mask(), which for all inodes is set to\nGFP_HIGHUSER_MOVABLE. So instead use find_or_create_page in all cases where we\nneed GFP_NOFS so we don\u0027t deadlock. Thanks,\n\nSigned-off-by: Josef Bacik \u003cjosef@redhat.com\u003e\n" }, { "commit": "bab39bf998133510f2dad08158006197ec0dabea", "tree": "0ea50b2b07a9f75988829de6c42b6936e2355545", "parents": [ "df98b6e2c52f65665eaf0fc23e647fb64335b289" ], "author": { "name": "Josef Bacik", "email": "josef@redhat.com", "time": "Thu Jun 30 14:42:28 2011 -0400" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Jul 27 12:46:25 2011 -0400" }, "message": "Btrfs: use a worker thread to do caching\n\nA user reported a deadlock when copying a bunch of files. This is because they\nwere low on memory and kthreadd got hung up trying to migrate pages for an\nallocation when starting the caching kthread. The page was locked by the person\nstarting the caching kthread. To fix this we just need to use the async thread\nstuff so that the threads are already created and we don\u0027t have to worry about\ndeadlocks. Thanks,\n\nReported-by: Roman Mamedov \u003crm@romanrm.ru\u003e\nSigned-off-by: Josef Bacik \u003cjosef@redhat.com\u003e\n" }, { "commit": "5fd00b031530cc476240f654c078c930f1dcd6ea", "tree": "1673effc8eb32932cdcbbd211d4632a80e5693a0", "parents": [ "333c066bb76f1f270ca77f16afe198e54e352c83", "3c2c22628599006047781946b317a16d9ff3883d" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 09:26:39 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 09:26:39 2011 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/shaggy/jfs-2.6\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/shaggy/jfs-2.6:\n jfs: clean up some compiler warnings\n" }, { "commit": "333c066bb76f1f270ca77f16afe198e54e352c83", "tree": "07343bcb01b28ca48c4e364a5da7dcacc0c37439", "parents": [ "75623437167d9d1ef14acaf6b3fb4ccd38fcbc84", "19237039919088781b4191a00bdc1284d8fea1dd" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 09:26:22 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 09:26:22 2011 -0700" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-fixes\n\n* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-fixes:\n GFS2: Fix mount hang caused by certain access pattern to sysfs files\n" }, { "commit": "75623437167d9d1ef14acaf6b3fb4ccd38fcbc84", "tree": "b7136121995cc6c2b5211a5393b1ad7c179a2f3b", "parents": [ "70a3eff5768350c0313a9ae70a15da113171d0ab", "636f78581dbd5529a52057973fe2bdfc1c2f528e" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 09:25:15 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 09:25:15 2011 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6: (22 commits)\n ALSA: hda - Cirrus Logic CS421x support\n ALSA: Make pcm.h self-contained\n ALSA: hda - Allow codec-specific set_power_state ops\n ALSA: hda - Add post_suspend patch ops\n ALSA: hda - Make CONFIG_SND_HDA_POWER_SAVE depending on CONFIG_PM\n ALSA: hda - Make sure mute led reflects master mute state\n ALSA: hda - Fix invalid mute led state on resume of IDT codecs\n ASoC: Revert \"ASoC: SAMSUNG: Add I2S0 internal dma driver\"\n ALSA: hda - Add support of the 4 internal speakers on certain HP laptops\n ALSA: Make snd_pcm_debug_name usable outside pcm_lib\n ALSA: hda - Fix DAC filling for multi-connection pins in Realtek parser\n ASoC: dapm - Add methods to retrieve snd_card and soc_card from dapm context.\n ASoC: SAMSUNG: Add I2S0 internal dma driver\n ASoC: SAMSUNG: Modify I2S driver to support idma\n ASoC: davinci: add missing break statement\n ASoC: davinci: fix codec start and stop functions\n ASoC: dapm - add DAPM macro for external enum widgets\n ASoC: Acknowledge WM8962 interrupts before acting on them\n ASoC: sgtl5000: guide user when regulator support is needed\n ASoC: sgtl5000: refactor registering internal ldo\n ...\n" }, { "commit": "70a3eff5768350c0313a9ae70a15da113171d0ab", "tree": "9c2558f92e567bcb35c79f59bc7ebc9cf6fdc9d3", "parents": [ "9ed3689bdceb0064ee6faf0e76f6467122794970", "aa7eb8e78d8ecd6cd0475d86ea8385ff9cb47ece" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 09:24:56 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 09:24:56 2011 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input: (53 commits)\n Input: synaptics - fix reporting of min coordinates\n Input: tegra-kbc - enable key autorepeat\n Input: kxtj9 - fix locking typo in kxtj9_set_poll()\n Input: kxtj9 - fix bug in probe()\n Input: intel-mid-touch - remove pointless checking for variable \u0027found\u0027\n Input: hp_sdc - staticize hp_sdc_kicker()\n Input: pmic8xxx-keypad - fix a leak of the IRQ during init failure\n Input: cy8ctmg110_ts - set reset_pin and irq_pin from platform data\n Input: cy8ctmg110_ts - constify i2c_device_id table\n Input: cy8ctmg110_ts - fix checking return value of i2c_master_send\n Input: lifebook - make dmi callback functions return 1\n Input: atkbd - make dmi callback functions return 1\n Input: gpio_keys - switch to using SIMPLE_DEV_PM_OPS\n Input: gpio_keys - add support for device-tree platform data\n Input: aiptek - remove double define\n Input: synaptics - set minimum coordinates as reported by firmware\n Input: synaptics - process button bits in AGM packets\n Input: synaptics - rename set_slot to be more descriptive\n Input: synaptics - fuzz position for touchpad with reduced filtering\n Input: synaptics - set resolution for MT_POSITION_X/Y axes\n ...\n" }, { "commit": "9ed3689bdceb0064ee6faf0e76f6467122794970", "tree": "059fbf494ac721faaefef1dd6e0131e9e576f6fb", "parents": [ "8aae36cdf12313cd9cc0e4799fe1ea64d3c623f3", "363922946f96ad1d6420107ebcfa9a95b659fe75" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 09:24:20 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 27 09:24:20 2011 -0700" }, "message": "Merge branch \u0027next\u0027 of git://git.monstr.eu/linux-2.6-microblaze\n\n* \u0027next\u0027 of git://git.monstr.eu/linux-2.6-microblaze:\n microblaze: Do not show error message for 32 interrupt lines\n Revert \"microblaze: PCI fix typo fault in of_node pointer moving into pci_bus\"\n microblaze: PCI fix typo fault in of_node pointer moving into pci_bus\n microblaze: Add support for early console on mdm\n microblaze: Simplify early console binding from DT\n microblaze: Get early printk console earlier\n microblaze: Standardise cpuinfo output for cache policy\n microblaze: Unprivileged stream instruction awareness\n microblaze: trivial: Fix typo fault\n microblaze: exec: Remove redundant set_fs(USER_DS)\n microblaze: Remove duplicated prototype of start_thread()\n microblaze: Fix unaligned value saving to the stack for system with MMU\n microblaze/irqs: Do not trace arch_local_{*,irq_*} functions\n" } ], "next": "8aae36cdf12313cd9cc0e4799fe1ea64d3c623f3" }