)]}' { "log": [ { "commit": "26dd8e0291fd699142722632c6588a438d6ef0e4", "tree": "42c9d4e7d88f71850e025d94ebdcd820041110a8", "parents": [ "dcd6c92267155e70a94b3927bce681ce74b80d1f" ], "author": { "name": "Akinobu Mita", "email": "akinobu.mita@gmail.com", "time": "Sat Jan 21 00:15:23 2012 +0900" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Jan 20 09:23:16 2012 -0800" }, "message": "percpu: use bitmap_clear\n\nUse bitmap_clear rather than clearing individual bits in a memory region.\n\nSigned-off-by: Akinobu Mita \u003cakinobu.mita@gmail.com\u003e\nAcked-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "a855b84c3d8c73220d4d3cd392a7bee7c83de70e", "tree": "3134cd884a2c625cf72172c9cb4e4a5e68d749f2", "parents": [ "90459ce06f410b983540be56209c0abcbce23944" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Nov 18 10:55:35 2011 -0800" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Tue Nov 22 08:09:46 2011 -0800" }, "message": "percpu: fix chunk range calculation\n\nPercpu allocator recorded the cpus which map to the first and last\nunits in pcpu_first/last_unit_cpu respectively and used them to\ndetermine the address range of a chunk - e.g. it assumed that the\nfirst unit has the lowest address in a chunk while the last unit has\nthe highest address.\n\nThis simply isn\u0027t true. Groups in a chunk can have arbitrary positive\nor negative offsets from the previous one and there is no guarantee\nthat the first unit occupies the lowest offset while the last one the\nhighest.\n\nFix it by actually comparing unit offsets to determine cpus occupying\nthe lowest and highest offsets. Also, rename pcu_first/last_unit_cpu\nto pcpu_low/high_unit_cpu to avoid confusion.\n\nThe chunk address range is used to flush cache on vmalloc area\nmap/unmap and decide whether a given address is in the first chunk by\nper_cpu_ptr_to_phys() and the bug was discovered by invalid\nper_cpu_ptr_to_phys() translation for crash_note.\n\nKudos to Dave Young for tracking down the problem.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nReported-by: WANG Cong \u003cxiyou.wangcong@gmail.com\u003e\nReported-by: Dave Young \u003cdyoung@redhat.com\u003e\nTested-by: Dave Young \u003cdyoung@redhat.com\u003e\nLKML-Reference: \u003c4EC21F67.10905@redhat.com\u003e\nCc: stable @kernel.org\n" }, { "commit": "90459ce06f410b983540be56209c0abcbce23944", "tree": "de385624ae9bf2dc3c5bf0f54d97ac7db5241108", "parents": [ "f8f5ed7c996ad9426847ce09b828d415cb19bc06" ], "author": { "name": "Bob Liu", "email": "lliubbo@gmail.com", "time": "Thu Aug 04 11:02:33 2011 +0200" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Tue Nov 22 08:09:41 2011 -0800" }, "message": "percpu: rename pcpu_mem_alloc to pcpu_mem_zalloc\n\nCurrently pcpu_mem_alloc() is implemented always return zeroed memory.\nSo rename it to make user like pcpu_get_pages_and_bitmap() know don\u0027t\nreinit it.\n\nSigned-off-by: Bob Liu \u003clliubbo@gmail.com\u003e\nReviewed-by: Pekka Enberg \u003cpenberg@kernel.org\u003e\nReviewed-by: Michal Hocko \u003cmhocko@suse.cz\u003e\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "ec3f64fc9c196a304c4b7db3e1ff56d640628509", "tree": "43de86d9fbb6543b99e1f450b1a3c15a3f151fa0", "parents": [ "e5a5623b28198aa91ea71ee5d3846757fc76bc87" ], "author": { "name": "David Rientjes", "email": "rientjes@google.com", "time": "Thu Jan 13 15:46:01 2011 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jan 13 17:32:34 2011 -0800" }, "message": "mm: remove gfp mask from pcpu_get_vm_areas\n\npcpu_get_vm_areas() only uses GFP_KERNEL allocations, so remove the gfp_t\nformal and use the mask internally.\n\nSigned-off-by: David Rientjes \u003crientjes@google.com\u003e\nCc: Christoph Lameter \u003ccl@linux.com\u003e\nCc: 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": "9f6455325618821dcf6775d7972881fde32e77c5", "tree": "6031e6f28aaaa3bf8d8e08dd59031d94c19fa89e", "parents": [ "88999a898b565960690f18e4a13a1e8a9fa4dfef" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Apr 09 18:57:01 2010 +0900" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Sat May 01 08:30:50 2010 +0200" }, "message": "percpu: move vmalloc based chunk management into percpu-vm.c\n\nSeparate out and move chunk management (creation/desctruction and\n[de]population) code into percpu-vm.c which is included by percpu.c\nand compiled together. The interface for chunk management is defined\nas follows.\n\n * pcpu_populate_chunk\t\t- populate the specified range of a chunk\n * pcpu_depopulate_chunk\t- depopulate the specified range of a chunk\n * pcpu_create_chunk\t\t- create a new chunk\n * pcpu_destroy_chunk\t\t- destroy a chunk, always preceded by full depop\n * pcpu_addr_to_page\t\t- translate address to physical address\n * pcpu_verify_alloc_info\t- check alloc_info is acceptable during init\n\nOther than wrapping vmalloc_to_page() inside pcpu_addr_to_page() and\ndummy pcpu_verify_alloc_info() implementation, this patch only moves\ncode around. This separation is to allow alternate chunk management\nimplementation.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nReviewed-by: David Howells \u003cdhowells@redhat.com\u003e\nCc: Graff Yang \u003cgraff.yang@gmail.com\u003e\nCc: Sonic Zhang \u003csonic.adi@gmail.com\u003e\n" } ] }