)]}' { "log": [ { "commit": "6ba2ef7baac23a5d9bb85e28b882d16b439a2293", "tree": "609150ce473b6466d53d42bd7bf9353b7a65ab66", "parents": [ "4b805b17382c11a8b1c9bb8053ce9d1dcde0701a" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Sep 24 09:34:53 2009 -0600" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Sep 24 09:34:53 2009 +0930" }, "message": "cpumask: Move deprecated functions to end of header.\n\nThe new ones have pretty kerneldoc. Move the old ones to the end to\navoid confusing people.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: benh@kernel.crashing.org\n" }, { "commit": "4b805b17382c11a8b1c9bb8053ce9d1dcde0701a", "tree": "7d602732c50015b0ff2a7b88ef80555bc9074b3c", "parents": [ "db7907865817137bfa3d5b4b30de9cc859b41bf1" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Sep 24 09:34:52 2009 -0600" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Sep 24 09:34:53 2009 +0930" }, "message": "cpumask: remove unused deprecated functions, avoid accusations of insanity\n\nWe\u0027re not forcing removal of the old cpu_ functions, but we might as\nwell delete the now-unused ones.\n\nEspecially CPUMASK_ALLOC and friends. I actually got a phone call (!)\nfrom a hacker who thought I had introduced them as the new cpumask\nAPI. He seemed bewildered that I had lost all taste.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: benh@kernel.crashing.org\n" }, { "commit": "72d78d05cbaa69f2a32f5f9d65a4551ba0da571f", "tree": "9116e29924269c671f19dba69abe38f5730bc00e", "parents": [ "51c870a2d8708bda83c4ba47f26012a8420bdaff" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Sep 24 09:34:36 2009 -0600" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Sep 24 09:34:36 2009 +0930" }, "message": "cpumask: remove unused cpu_mask_all\n\nIt\u0027s only defined for NR_CPUS \u003e BITS_PER_LONG; cpu_all_mask is always\ndefined (and const).\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "a0219d948dd712561817b0d7c95fd2f10b698203", "tree": "64157005de183c3468cd39b81a1d1d397ebf2b29", "parents": [ "29c337a034b5526e80a785409d15d3b7c7edecf4" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Sep 24 09:34:35 2009 -0600" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Sep 24 09:34:35 2009 +0930" }, "message": "cpumask: remove dangerous CPU_MASK_ALL_PTR\n\n(Thanks to Al Viro for reminding me of this, via Ingo)\n\nCPU_MASK_ALL is the (deprecated) \"all bits set\" cpumask, defined as so:\n\n\t#define CPU_MASK_ALL (cpumask_t) { { ... } }\n\nTaking the address of such a temporary is questionable at best,\nunfortunately 321a8e9d (cpumask: add CPU_MASK_ALL_PTR macro) added\nCPU_MASK_ALL_PTR:\n\n\t#define CPU_MASK_ALL_PTR (\u0026CPU_MASK_ALL)\n\nWhich formalizes this practice. One day gcc could bite us over this\nusage (though we seem to have gotten away with it so far).\n\nNow all callers are removed, we kill it.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nAcked-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nReported-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nCc: Mike Travis \u003ctravis@sgi.com\u003e\n" }, { "commit": "54fdade1c3332391948ec43530c02c4794a38172", "tree": "a44cfa6888bbe702321e4d4737786e5292d72eaa", "parents": [ "5c725138437837291db5c25f4a076ee852e806e3" ], "author": { "name": "Xiao Guangrong", "email": "xiaoguangrong@cn.fujitsu.com", "time": "Tue Sep 22 16:43:39 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Sep 23 07:39:28 2009 -0700" }, "message": "generic-ipi: make struct call_function_data lockless\n\nThis patch can remove spinlock from struct call_function_data, the\nreasons are below:\n\n1: add a new interface for cpumask named cpumask_test_and_clear_cpu(),\n it can atomically test and clear specific cpu, we can use it instead\n of cpumask_test_cpu() and cpumask_clear_cpu() and no need data-\u003elock\n to protect those in generic_smp_call_function_interrupt().\n\n2: in smp_call_function_many(), after csd_lock() return, the current\u0027s\n cfd_data is deleted from call_function list, so it not have race\n between other cpus, then cfs_data is only used in\n smp_call_function_many() that must disable preemption and not from\n a hardware interrupthandler or from a bottom half handler to call,\n only the correspond cpu can use it, so it not have race in current\n cpu, no need cfs_data-\u003elock to protect it.\n\n3: after 1 and 2, cfs_data-\u003elock is only use to protect cfs_data-\u003erefs in\n generic_smp_call_function_interrupt(), so we can define cfs_data-\u003erefs\n to atomic_t, and no need cfs_data-\u003elock any more.\n\nSigned-off-by: Xiao Guangrong \u003cxiaoguangrong@cn.fujitsu.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nAcked-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n[akpm@linux-foundation.org: use atomic_dec_return()]\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f4b0373b26567cafd421d91101852ed7a34e9e94", "tree": "35607b1c1d28429bb275ca3472cd0065fbde2f14", "parents": [ "83d349f35e1ae72268c5104dbf9ab2ae635425d4" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Aug 21 09:26:15 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Aug 21 09:26:15 2009 -0700" }, "message": "Make bitmask \u0027and\u0027 operators return a result code\n\nWhen \u0027and\u0027ing two bitmasks (where \u0027andnot\u0027 is a variation on it), some\ncases want to know whether the result is the empty set or not. In\nparticular, the TLB IPI sending code wants to do cpumask operations and\ndetermine if there are any CPU\u0027s left in the final set.\n\nSo this just makes the bitmask (and cpumask) functions return a boolean\nfor whether the result has any bits set.\n\nCc: stable@kernel.org (2.6.30, needed by TLB shootdown fix)\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "0281b5dc0350cbf6dd21ed558a33cccce77abc02", "tree": "4523b6f48722eee44a854207e268c71ae4d84771", "parents": [ "3af968e066d593bc4dacc021715f3e95ddf0996f" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Sat Jun 06 14:50:36 2009 -0700" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Jun 09 22:30:26 2009 +0930" }, "message": "cpumask: introduce zalloc_cpumask_var\n\nSo can get cpumask_var with cpumask_clear\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "8c384cdee3e04d6194a2c2b192b624754f990835", "tree": "3a9bd2e7ce02cd5e739c521e073467a3b201198d", "parents": [ "2a53008033189ed09bfe241c6b33811ba4ce980d" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Jan 01 10:12:30 2009 +1030" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Jan 01 10:12:30 2009 +1030" }, "message": "cpumask: CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS\n\nImpact: new debug CONFIG options\n\nThis helps find unconverted code. It currently breaks compile horribly,\nbut we never wanted a flag day so that\u0027s expected.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "3fa41520696fec2815e2d88fbcccdda77ba4d693", "tree": "418c698535189083b9cbed28bc30e895bda147e3", "parents": [ "ae7a47e72e1a0b5e2b46d1596bc2c22942a73023" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Dec 30 09:05:16 2008 +1030" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Dec 30 09:05:16 2008 +1030" }, "message": "cpumask: make set_cpu_*/init_cpu_* out-of-line\n\nThey\u0027re only for use in boot/cpu hotplug code anyway, and this avoids\nthe use of deprecated cpu_*_map.\n\nStephen Rothwell points out that gcc 4.2.4 (on powerpc at least)\ndidn\u0027t like the cast away of const anyway:\n\n include/linux/cpumask.h: In function \u0027set_cpu_possible\u0027:\n include/linux/cpumask.h:1052: warning: passing argument 2 of \u0027cpumask_set_cpu\u0027 discards qualifiers from pointer target type\n\nSo this kills two birds with one stone.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "ae7a47e72e1a0b5e2b46d1596bc2c22942a73023", "tree": "7cfbed58940f2feb9e2405d81a6688c6bce237b4", "parents": [ "b3199c025d1646e25e7d1d640dd605db251dccf8" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Dec 30 09:05:15 2008 +1030" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Dec 30 09:05:15 2008 +1030" }, "message": "cpumask: make cpumask.h eat its own dogfood.\n\nChanges:\n1) cpumask_t to struct cpumask,\n2) cpus_weight_nr to cpumask_weight,\n3) cpu_isset to cpumask_test_cpu,\n4) -\u003ebits to cpumask_bits()\n5) cpu_*_map to cpu_*_mask.\n6) for_each_cpu_mask_nr to for_each_cpu\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "b3199c025d1646e25e7d1d640dd605db251dccf8", "tree": "752bd257f2db6b4d39bf9cdce18ca25ade5e63a9", "parents": [ "cb78a0ce69fad2026825f957e24e2d9cda1ec9f1" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Dec 30 09:05:14 2008 +1030" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Dec 30 09:05:14 2008 +1030" }, "message": "cpumask: switch over to cpu_online/possible/active/present_mask: core\n\nImpact: cleanup\n\nThis implements the obsolescent cpu_online_map in terms of\ncpu_online_mask, rather than the other way around. Same for the other\nmaps.\n\nThe documentation comments are also updated to refer to _mask rather\nthan _map.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nSigned-off-by: Mike Travis \u003ctravis@sgi.com\u003e\n" }, { "commit": "7b4967c532045a1983d6d4af5c69cc7c5109f62b", "tree": "50f385985ed028b5316c1aad4b70ad08bd932e81", "parents": [ "7be7585393d311866653564fbcd10a3232773c0b" ], "author": { "name": "Mike Travis", "email": "travis@sgi.com", "time": "Fri Dec 19 16:56:37 2008 +1030" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Fri Dec 19 16:56:37 2008 +1030" }, "message": "cpumask: Add alloc_cpumask_var_node()\n\nImpact: New API\n\nThis will be needed in x86 code to allocate the domain and old_domain\ncpumasks on the same node as where the containing irq_cfg struct is\nallocated.\n\n(Also fixes double-dump_stack on rare CONFIG_DEBUG_PER_CPU_MAPS case)\n\nSigned-off-by: Mike Travis \u003ctravis@sgi.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e (re-impl alloc_cpumask_var)\n" }, { "commit": "7be7585393d311866653564fbcd10a3232773c0b", "tree": "50399f8f3bd97d521f91bf2de30dd41c081e3321", "parents": [ "f0b848ce6fe9062d504d997e9e97fe0f87d57217" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Sat Dec 13 21:20:28 2008 +1030" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Sat Dec 13 21:20:28 2008 +1030" }, "message": "cpumask: Use all NR_CPUS bits unless CONFIG_CPUMASK_OFFSTACK\n\nImpact: futureproof as we convert more code to new APIs\n\nThe old cpumask operators treat all NR_CPUS bits as relevent, the new\nones use nr_cpumask_bits. For large NR_CPUS and small nr_cpu_ids, this\nmakes a difference.\n\nHowever, mixing the two can cause problems with undefined bits. An\narch which sets CONFIG_CPUMASK_OFFSTACK should have converted across\nto the new operators, so it\u0027s safe in that case.\n\n(Thanks to Stephen Rothwell for bisecting the initial unused-bits bug,\nand Mike Travis for this solution).\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Mike Travis \u003ctravis@sgi.com\u003e\n" }, { "commit": "29c0177e6a4ac094302bed54a1d4bbb6b740a9ef", "tree": "d8ee57c5b40baa3f53d607b719344dd20f8c85a0", "parents": [ "98a79d6a50181ca1ecf7400eda01d5dc1bc0dbf0" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Sat Dec 13 21:20:25 2008 +1030" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Sat Dec 13 21:20:25 2008 +1030" }, "message": "cpumask: change cpumask_scnprintf, cpumask_parse_user, cpulist_parse, and cpulist_scnprintf to take pointers.\n\nImpact: change calling convention of existing cpumask APIs\n\nMost cpumask functions started with cpus_: these have been replaced by\ncpumask_ ones which take struct cpumask pointers as expected.\n\nThese four functions don\u0027t have good replacement names; fortunately\nthey\u0027re rarely used, so we just change them over.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nSigned-off-by: Mike Travis \u003ctravis@sgi.com\u003e\nAcked-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: paulus@samba.org\nCc: mingo@redhat.com\nCc: tony.luck@intel.com\nCc: ralf@linux-mips.org\nCc: Greg Kroah-Hartman \u003cgregkh@suse.de\u003e\nCc: cl@linux-foundation.org\nCc: srostedt@redhat.com\n" }, { "commit": "984f2f377fdfd098f5ae58d09ee04d5e29e6112b", "tree": "6f6ea07057f5680586a8ac6f77700c118f253bcb", "parents": [ "cd83e42c6b0413dcbb548c2ead799111ff7e6a13" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Sat Nov 08 20:24:19 2008 +1100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Nov 09 21:09:54 2008 +0100" }, "message": "cpumask: introduce new API, without changing anything, v3\n\nImpact: cleanup\n\nClean up based on feedback from Andrew Morton and others:\n\n - change to inline functions instead of macros\n - add __init to bootmem method\n - add a missing debug check\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "cd83e42c6b0413dcbb548c2ead799111ff7e6a13", "tree": "0110f8f39a8f88aacfbe4f0692b099373523edc0", "parents": [ "2d3854a37e8b767a51aba38ed6d22817b0631e33" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Fri Nov 07 11:12:29 2008 +1100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Nov 07 12:52:30 2008 +0100" }, "message": "cpumask: new API, v2\n\n- add cpumask_of()\n- add free_bootmem_cpumask_var()\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "2d3854a37e8b767a51aba38ed6d22817b0631e33", "tree": "3b55cc93720b2e525460216b196ed20298ae985b", "parents": [ "75fa67706cce5272bcfc51ed646f2da21f3bdb6e" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Wed Nov 05 13:39:10 2008 +1100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Nov 06 09:05:33 2008 +0100" }, "message": "cpumask: introduce new API, without changing anything\n\nImpact: introduce new APIs\n\nWe want to deprecate cpumasks on the stack, as we are headed for\ngynormous numbers of CPUs. Eventually, we want to head towards an\nundefined \u0027struct cpumask\u0027 so they can never be declared on stack.\n\n1) New cpumask functions which take pointers instead of copies.\n (cpus_* -\u003e cpumask_*)\n\n2) Several new helpers to reduce requirements for temporary cpumasks\n (cpumask_first_and, cpumask_next_and, cpumask_any_and)\n\n3) Helpers for declaring cpumasks on or offstack for large NR_CPUS\n (cpumask_var_t, alloc_cpumask_var and free_cpumask_var)\n\n4) \u0027struct cpumask\u0027 for explicitness and to mark new-style code.\n\n5) Make iterator functions stop at nr_cpu_ids (a runtime constant),\n not NR_CPUS for time efficiency and for smaller dynamic allocations\n in future.\n\n6) cpumask_copy() so we can allocate less than a full cpumask eventually\n (for alloc_cpumask_var), and so we can eliminate the \u0027struct cpumask\u0027\n definition eventually.\n\n7) work_on_cpu() helper for doing task on a CPU, rather than saving old\n cpumask for current thread and manipulating it.\n\n8) smp_call_function_many() which is smp_call_function_mask() except\n taking a cpumask pointer.\n\nNote that this patch simply introduces the new functions and leaves\nthe obsolescent ones in place. This is to simplify the transition\npatches.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "3dd730f2b49f101b90d283c3efc4e6cd826dd8f6", "tree": "040c55f93a1d3fbbd85e2e81319d8f259f71c55f", "parents": [ "a4319d9fa02fb3f032596d18c6fcc8b05d01a3a5" ], "author": { "name": "Stephen Rothwell", "email": "sfr@canb.auug.org.au", "time": "Tue Jul 29 16:07:37 2008 +1000" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 30 10:35:49 2008 -0700" }, "message": "cpumask: statement expressions confuse some versions of gcc\n\nwhen you take the address of the result. Noticed on a sparc64 compile\nusing a version 3.4.5 cross compiler.\n\n kernel/time/tick-common.c: In function `tick_check_new_device\u0027:\n kernel/time/tick-common.c:210: error: invalid lvalue in unary `\u0026\u0027\n ...\n\nJust make it a regular expression.\n\nSigned-off-by: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nAcked-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e56b3bc7942982ac2589c942fb345e38bc7a341a", "tree": "8130492904f5bb9cff061f62ebb1c5d6eed3308b", "parents": [ "414f746d232d41ed6ae8632c4495ae795373c44b" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jul 28 11:32:33 2008 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Jul 28 22:20:41 2008 +0200" }, "message": "cpu masks: optimize and clean up cpumask_of_cpu()\n\nClean up and optimize cpumask_of_cpu(), by sharing all the zero words.\n\nInstead of stupidly generating all possible i\u003d0...NR_CPUS 2^i patterns\ncreating a huge array of constant bitmasks, realize that the zero words\ncan be shared.\n\nIn other words, on a 64-bit architecture, we only ever need 64 of these\narrays - with a different bit set in one single world (with enough zero\nwords around it so that we can create any bitmask by just offsetting in\nthat big array). And then we just put enough zeroes around it that we\ncan point every single cpumask to be one of those things.\n\nSo when we have 4k CPU\u0027s, instead of having 4k arrays (of 4k bits each,\nwith one bit set in each array - 2MB memory total), we have exactly 64\narrays instead, each 8k bits in size (64kB total).\n\nAnd then we just point cpumask(n) to the right position (which we can\ncalculate dynamically). Once we have the right arrays, getting\n\"cpumask(n)\" ends up being:\n\n static inline const cpumask_t *get_cpu_mask(unsigned int cpu)\n {\n const unsigned long *p \u003d cpu_bit_bitmap[1 + cpu % BITS_PER_LONG];\n p -\u003d cpu / BITS_PER_LONG;\n return (const cpumask_t *)p;\n }\n\nThis brings other advantages and simplifications as well:\n\n - we are not wasting memory that is just filled with a single bit in\n various different places\n\n - we don\u0027t need all those games to re-create the arrays in some dense\n format, because they\u0027re already going to be dense enough.\n\nif we compile a kernel for up to 4k CPU\u0027s, \"wasting\" that 64kB of memory\nis a non-issue (especially since by doing this \"overlapping\" trick we\nprobably get better cache behaviour anyway).\n\n[ mingo@elte.hu:\n\n Converted Linus\u0027s mails into a commit. See:\n\n http://lkml.org/lkml/2008/7/27/156\n http://lkml.org/lkml/2008/7/28/320\n\n Also applied a family filter - which also has the side-effect of leaving\n out the bits where Linus calls me an idio... Oh, never mind ;-)\n]\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Al Viro \u003cviro@ZenIV.linux.org.uk\u003e\nCc: Mike Travis \u003ctravis@sgi.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "b8d317d10cca76cabe6b03ebfeb23cc99118b731", "tree": "a997d21960099095822ffbfe8be4d3f6176f33a9", "parents": [ "024e8ac04453b3525448c31ef39848cf675ba6db" ], "author": { "name": "Mike Travis", "email": "travis@sgi.com", "time": "Thu Jul 24 18:21:29 2008 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Jul 26 16:40:32 2008 +0200" }, "message": "cpumask: make cpumask_of_cpu_map generic\n\nIf an arch doesn\u0027t define cpumask_of_cpu_map, create a generic\nstatically-initialized one for them. This allows removal of the buggy\ncpumask_of_cpu() macro (\u0026cpumask_of_cpu() gives address of\nout-of-scope var).\n\nAn arch with NR_CPUS of 4096 probably wants to allocate this itself\nbased on the actual number of CPUs, since otherwise they\u0027re using 2MB\nof rodata (1024 cpus means 128k). That\u0027s what\nCONFIG_HAVE_CPUMASK_OF_CPU_MAP is for (only x86/64 does so at the\nmoment).\n\nIn future as we support more CPUs, we\u0027ll need to resort to a\nget_cpu_map()/put_cpu_map() allocation scheme.\n\nSigned-off-by: Mike Travis \u003ctravis@sgi.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Jack Steiner \u003csteiner@sgi.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "7f9dce38378f0a4a298e885553d6bb7121376376", "tree": "5bfd688c9f356f7216bbc3cef3b4c10153de334b", "parents": [ "26dcce0fabbef75ae426461edf21b5030bad60f3", "ba42059fbd0aa1ac91b582412b5fedb1258f241f" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 23 19:36:53 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 23 19:36:53 2008 -0700" }, "message": "Merge branch \u0027sched/for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027sched/for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n sched: hrtick_enabled() should use cpu_active()\n sched, x86: clean up hrtick implementation\n sched: fix build error, provide partition_sched_domains() unconditionally\n sched: fix warning in inc_rt_tasks() to not declare variable \u0027rq\u0027 if it\u0027s not needed\n cpu hotplug: Make cpu_active_map synchronization dependency clear\n cpu hotplug, sched: Introduce cpu_active_map and redo sched domain managment (take 2)\n sched: rework of \"prioritize non-migratable tasks over migratable ones\"\n sched: reduce stack size in isolated_cpu_setup()\n Revert parts of \"ftrace: do not trace scheduler functions\"\n\nFixed up conflicts in include/asm-x86/thread_info.h (due to the\nTIF_SINGLESTEP unification vs TIF_HRTICK_RESCHED removal) and\nkernel/sched_fair.c (due to cpu_active_map vs for_each_cpu_mask_nr()\nintroduction).\n" }, { "commit": "80422d3431cc990b967da129f9eb8e3e9989f841", "tree": "4c8424e7c22433caa39192e6273b7859545f7be1", "parents": [ "b38868aabeeb9c0c76a41ac5fa98c24bf0096f2a" ], "author": { "name": "Mike Travis", "email": "travis@sgi.com", "time": "Fri Jul 18 18:11:33 2008 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Jul 20 10:21:12 2008 +0200" }, "message": "cpumask: Provide a generic set of CPUMASK_ALLOC macros, FIXUP\n\n * Rename CPUMASK_VAR --\u003e CPUMASK_PTR (and simplify)\n\n * Fix a semantic error in CPUMASK_ALLOC\n\n * Add a bit of commentry to cpumask.h\n\nSigned-off-by: Mike Travis \u003ctravis@sgi.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "77586c2bdad0798cb24e35de5a878e7c6b200574", "tree": "ba400aecb986671fb70d2fb0c80140ac2fdedfb5", "parents": [ "4755b9291204982ac908e069674d6e5eb45815b3" ], "author": { "name": "Mike Travis", "email": "travis@sgi.com", "time": "Tue Jul 15 14:14:36 2008 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 18 22:03:00 2008 +0200" }, "message": "cpumask: Provide a generic set of CPUMASK_ALLOC macros\n\n * Provide a generic set of CPUMASK_ALLOC macros patterned after the\n SCHED_CPUMASK_ALLOC macros. This is used where multiple cpumask_t\n variables are declared on the stack to reduce the amount of stack\n space required.\n\nSigned-off-by: Mike Travis \u003ctravis@sgi.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "65c011845316d3c1381f478ca0d8265c43b3b039", "tree": "a7e29e92a1ad0440ef5fe16dc16d73e8bf7983d2", "parents": [ "bb2c018b09b681d43f5e08124b83e362647ea82b" ], "author": { "name": "Mike Travis", "email": "travis@sgi.com", "time": "Tue Jul 15 14:14:30 2008 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 18 22:02:57 2008 +0200" }, "message": "cpumask: Replace cpumask_of_cpu with cpumask_of_cpu_ptr\n\n * This patch replaces the dangerous lvalue version of cpumask_of_cpu\n with new cpumask_of_cpu_ptr macros. These are patterned after the\n node_to_cpumask_ptr macros.\n\n In general terms, if there is a cpumask_of_cpu_map[] then a pointer to\n the cpumask_of_cpu_map[cpu] entry is used. The cpumask_of_cpu_map\n is provided when there is a large NR_CPUS count, reducing\n greatly the amount of code generated and stack space used for\n cpumask_of_cpu(). The pointer to the cpumask_t value is needed for\n calling set_cpus_allowed_ptr() to reduce the amount of stack space\n needed to pass the cpumask_t value.\n\n If there isn\u0027t a cpumask_of_cpu_map[], then a temporary variable is\n declared and filled in with value from cpumask_of_cpu(cpu) as well as\n a pointer variable pointing to this temporary variable. Afterwards,\n the pointer is used to reference the cpumask value. The compiler\n will optimize out the extra dereference through the pointer as well\n as the stack space used for the pointer, resulting in identical code.\n\n A good example of the orthogonal usages is in net/sunrpc/svc.c:\n\n\tcase SVC_POOL_PERCPU:\n\t{\n\t\tunsigned int cpu \u003d m-\u003epool_to[pidx];\n\t\tcpumask_of_cpu_ptr(cpumask, cpu);\n\n\t\t*oldmask \u003d current-\u003ecpus_allowed;\n\t\tset_cpus_allowed_ptr(current, cpumask);\n\t\treturn 1;\n\t}\n\tcase SVC_POOL_PERNODE:\n\t{\n\t\tunsigned int node \u003d m-\u003epool_to[pidx];\n\t\tnode_to_cpumask_ptr(nodecpumask, node);\n\n\t\t*oldmask \u003d current-\u003ecpus_allowed;\n\t\tset_cpus_allowed_ptr(current, nodecpumask);\n\t\treturn 1;\n\t}\n\nSigned-off-by: Mike Travis \u003ctravis@sgi.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "e761b7725234276a802322549cee5255305a0930", "tree": "27b351a7d5fc9a93590e0effce1c5adb1bfcebc0", "parents": [ "7ebefa8ceefed44cc321be70afc54a585a68ac0b" ], "author": { "name": "Max Krasnyansky", "email": "maxk@qualcomm.com", "time": "Tue Jul 15 04:43:49 2008 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 18 13:22:25 2008 +0200" }, "message": "cpu hotplug, sched: Introduce cpu_active_map and redo sched domain managment (take 2)\n\nThis is based on Linus\u0027 idea of creating cpu_active_map that prevents\nscheduler load balancer from migrating tasks to the cpu that is going\ndown.\n\nIt allows us to simplify domain management code and avoid unecessary\ndomain rebuilds during cpu hotplug event handling.\n\nPlease ignore the cpusets part for now. It needs some more work in order\nto avoid crazy lock nesting. Although I did simplfy and unify domain\nreinitialization logic. We now simply call partition_sched_domains() in\nall the cases. This means that we\u0027re using exact same code paths as in\ncpusets case and hence the test below cover cpusets too.\nCpuset changes to make rebuild_sched_domains() callable from various\ncontexts are in the separate patch (right next after this one).\n\nThis not only boots but also easily handles\n\twhile true; do make clean; make -j 8; done\nand\n\twhile true; do on-off-cpu 1; done\nat the same time.\n(on-off-cpu 1 simple does echo 0/1 \u003e /sys/.../cpu1/online thing).\n\nSuprisingly the box (dual-core Core2) is quite usable. In fact I\u0027m typing\nthis on right now in gnome-terminal and things are moving just fine.\n\nAlso this is running with most of the debug features enabled (lockdep,\nmutex, etc) no BUG_ONs or lockdep complaints so far.\n\nI believe I addressed all of the Dmitry\u0027s comments for original Linus\u0027\nversion. I changed both fair and rt balancer to mask out non-active cpus.\nAnd replaced cpu_is_offline() with !cpu_active() in the main scheduler\ncode where it made sense (to me).\n\nSigned-off-by: Max Krasnyanskiy \u003cmaxk@qualcomm.com\u003e\nAcked-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\nAcked-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nAcked-by: Gregory Haskins \u003cghaskins@novell.com\u003e\nCc: dmitry.adamushko@gmail.com\nCc: pj@sgi.com\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "9982fbface82893e77d211fbabfbd229da6bdde6", "tree": "a6ea65ecff0335be6cc426e12bb3f571a762139b", "parents": [ "68083e05d72d94f347293d8cc0067050ba904bfa" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Jul 06 14:24:08 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Jul 06 14:24:08 2008 +0200" }, "message": "Revert \"cpumask: introduce new APIs\"\n\nThis reverts commit acb7669c125676e63cf96582455509216c39745e.\n\nthe wrappers are not needed anymore.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "68083e05d72d94f347293d8cc0067050ba904bfa", "tree": "842e71365bd90866be7add181661a4039d891564", "parents": [ "7baac8b91f9871ba8cb09af84de4ae1d86d07812", "b7279469d66b55119784b8b9529c99c1955fe747" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Jul 06 14:23:39 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Jul 06 14:23:39 2008 +0200" }, "message": "Merge commit \u0027v2.6.26-rc9\u0027 into cpus4096\n" }, { "commit": "acb7669c125676e63cf96582455509216c39745e", "tree": "fedc51a1c66c14ef9985c0114b57f1ec11cd3854", "parents": [ "603ded16a308d0a7a17738c973e3c8cbcd5db7dd" ], "author": { "name": "Stephen Rothwell", "email": "sfr@canb.auug.org.au", "time": "Fri Jul 04 10:00:05 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 04 10:40:09 2008 -0700" }, "message": "cpumask: introduce new APIs\n\nIn linux-next there is a commit (\"x86: Add performance variants of cpumask\noperators\") which, as part of the 4096 cpu support work adds some new APIs\nfor dealing with cpu masks. Add trivial versions of these now so that\nsubsystems can update in a timely manner and avoid conflicts in linux-next\nand the next merge window.\n\nCc: Mike Travis \u003ctravis@sgi.com\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7baac8b91f9871ba8cb09af84de4ae1d86d07812", "tree": "4624f10539c3bb4581f99c1a187f1008502b8438", "parents": [ "3f9b48a7584851997702cdc3f58e7811b5546397" ], "author": { "name": "Alexander van Heukelum", "email": "heukelum@mailshack.com", "time": "Tue May 13 11:28:21 2008 +0200" }, "committer": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Fri May 23 18:46:12 2008 +0200" }, "message": "cpumask: make for_each_cpu_mask a bit smaller\n\nThe for_each_cpu_mask loop is used quite often in the kernel. It\nmakes use of two functions: first_cpu and next_cpu. This patch\nchanges for_each_cpu_mask to use only the latter. Because next_cpu\nfinds the next eligible cpu _after_ the given one, the iteration\nvariable has to be initialized to -1 and next_cpu has to be\ncalled with this value before the first iteration. An x86_64\ndefconfig kernel (from sched/latest) is about 2500 bytes smaller\nwith this patch applied:\n\n text\t data\t bss\t dec\t hex\tfilename\n6222517\t 917952\t 749932\t7890401\t 7865e1\tvmlinux.orig\n6219922\t 917952\t 749932\t7887806\t 785bbe\tvmlinux\n\nThe same size reduction is seen for defconfig+MAXSMP\n\n text\t data\t bss\t dec\t hex\tfilename\n6241772\t2563968\t1492716\t10298456\t 9d2458\tvmlinux.orig\n6239211\t2563968\t1492716\t10295895\t 9d1a57\tvmlinux\n\nSigned-off-by: Alexander van Heukelum \u003cheukelum@fastmail.fm\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "41df0d61c266998b8049df7fec119cd518a43aa1", "tree": "6791fa6e3fdaee51ae348f9fe63972d648beaf5a", "parents": [ "143aa5c53bd3895d42d7c08753fe58293988a69d" ], "author": { "name": "Mike Travis", "email": "travis@sgi.com", "time": "Mon May 12 21:21:13 2008 +0200" }, "committer": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Fri May 23 18:23:38 2008 +0200" }, "message": "x86: Add performance variants of cpumask operators\n\n * Increase performance for systems with large count NR_CPUS by limiting\n the range of the cpumask operators that loop over the bits in a cpumask_t\n variable. This removes a large amount of wasted cpu cycles.\n\n * Add performance variants of the cpumask operators:\n\n int cpus_weight_nr(mask)\t Same using nr_cpu_ids instead of NR_CPUS\n int first_cpu_nr(mask)\t Number lowest set bit, or nr_cpu_ids\n int next_cpu_nr(cpu, mask)\t Next cpu past \u0027cpu\u0027, or nr_cpu_ids\n for_each_cpu_mask_nr(cpu, mask) for-loop cpu over mask using nr_cpu_ids\n\n * Modify following to use performance variants:\n\n #define num_online_cpus()\tcpus_weight_nr(cpu_online_map)\n #define num_possible_cpus()\tcpus_weight_nr(cpu_possible_map)\n #define num_present_cpus()\tcpus_weight_nr(cpu_present_map)\n\n #define for_each_possible_cpu(cpu) for_each_cpu_mask_nr((cpu), ...)\n #define for_each_online_cpu(cpu) for_each_cpu_mask_nr((cpu), ...)\n #define for_each_present_cpu(cpu) for_each_cpu_mask_nr((cpu), ...)\n\n * Comment added to include/linux/cpumask.h:\n\n Note: The alternate operations with the suffix \"_nr\" are used\n\t to limit the range of the loop to nr_cpu_ids instead of\n\t NR_CPUS when NR_CPUS \u003e 64 for performance reasons.\n\t If NR_CPUS is \u003c\u003d 64 then most assembler bitmask\n\t operators execute faster with a constant range, so\n\t the operator will continue to use NR_CPUS.\n\n\t Another consideration is that nr_cpu_ids is initialized\n\t to NR_CPUS and isn\u0027t lowered until the possible cpus are\n\t discovered (including any disabled cpus). So early uses\n\t will span the entire range of NR_CPUS.\n\n (The net effect is that for systems with 64 or less CPU\u0027s there are no\n functional changes.)\n\nFor inclusion into sched-devel/latest tree.\n\nBased on:\n\tgit://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git\n + sched-devel/latest .../mingo/linux-2.6-sched-devel.git\n\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nReviewed-by: Paul Jackson \u003cpj@sgi.com\u003e\nReviewed-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Mike Travis \u003ctravis@sgi.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "f4ed0deae8983591264d0e194e168ef65f4775f5", "tree": "6d25ff09060a69530b1ba0711d20e978edfda92e", "parents": [ "53c78dd1718b99dc365ff8a2244d7d4504b070a5" ], "author": { "name": "Paul Jackson", "email": "pj@sgi.com", "time": "Mon May 12 14:02:29 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 13 08:02:25 2008 -0700" }, "message": "cpumask: remove bitmap_scnprintf_len and cpumask_scnprintf_len\n\nThey aren\u0027t used. They were briefly used as part of some other patches to\nprovide an alternative format for displaying some /proc and /sys cpumasks.\nThey probably should have been removed when those other patches were dropped,\nin favor of a different solution.\n\nSigned-off-by: Paul Jackson \u003cpj@sgi.com\u003e\nCc: \"Mike Travis\" \u003ctravis@sgi.com\u003e\nCc: \"Bert Wesarg\" \u003cbert.wesarg@googlemail.com\u003e\nCc: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nCc: WANG Cong \u003cxiyou.wangcong@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7ea931c9fc80c4d0a4306c30ec92eb0f1d922a0b", "tree": "4f2c85d658c75e8679e01943e3e95866b3729b54", "parents": [ "f5b087b52f1710eb0bf15a2d2b030c51a6a1ca9e" ], "author": { "name": "Paul Jackson", "email": "pj@sgi.com", "time": "Mon Apr 28 02:12:29 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:19 2008 -0700" }, "message": "mempolicy: add bitmap_onto() and bitmap_fold() operations\n\nThe following adds two more bitmap operators, bitmap_onto() and bitmap_fold(),\nwith the usual cpumask and nodemask wrappers.\n\nThe bitmap_onto() operator computes one bitmap relative to another. If the\nn-th bit in the origin mask is set, then the m-th bit of the destination mask\nwill be set, where m is the position of the n-th set bit in the relative mask.\n\nThe bitmap_fold() operator folds a bitmap into a second that has bit m set iff\nthe input bitmap has some bit n set, where m \u003d\u003d n mod sz, for the specified sz\nvalue.\n\nThere are two substantive changes between this patch and its\npredecessor bitmap_relative:\n 1) Renamed bitmap_relative() to be bitmap_onto().\n 2) Added bitmap_fold().\n\nThe essential motivation for bitmap_onto() is to provide a mechanism for\nconverting a cpuset-relative CPU or Node mask to an absolute mask. Cpuset\nrelative masks are written as if the current task were in a cpuset whose CPUs\nor Nodes were just the consecutive ones numbered 0..N-1, for some N. The\nbitmap_onto() operator is provided in anticipation of adding support for the\nfirst such cpuset relative mask, by the mbind() and set_mempolicy() system\ncalls, using a planned flag of MPOL_F_RELATIVE_NODES. These bitmap operators\n(and their nodemask wrappers, in particular) will be used in code that\nconverts the user specified cpuset relative memory policy to a specific system\nnode numbered policy, given the current mems_allowed of the tasks cpuset.\n\nSuch cpuset relative mempolicies will address two deficiencies\nof the existing interface between cpusets and mempolicies:\n 1) A task cannot at present reliably establish a cpuset\n relative mempolicy because there is an essential race\n condition, in that the tasks cpuset may be changed in\n between the time the task can query its cpuset placement,\n and the time the task can issue the applicable mbind or\n set_memplicy system call.\n 2) A task cannot at present establish what cpuset relative\n mempolicy it would like to have, if it is in a smaller\n cpuset than it might have mempolicy preferences for,\n because the existing interface only allows specifying\n mempolicies for nodes currently allowed by the cpuset.\n\nCpuset relative mempolicies are useful for tasks that don\u0027t distinguish\nparticularly between one CPU or Node and another, but only between how many of\neach are allowed, and the proper placement of threads and memory pages on the\nvarious CPUs and Nodes available.\n\nThe motivation for the added bitmap_fold() can be seen in the following\nexample.\n\nLet\u0027s say an application has specified some mempolicies that presume 16 memory\nnodes, including say a mempolicy that specified MPOL_F_RELATIVE_NODES (cpuset\nrelative) nodes 12-15. Then lets say that application is crammed into a\ncpuset that only has 8 memory nodes, 0-7. If one just uses bitmap_onto(),\nthis mempolicy, mapped to that cpuset, would ignore the requested relative\nnodes above 7, leaving it empty of nodes. That\u0027s not good; better to fold the\nhigher nodes down, so that some nodes are included in the resulting mapped\nmempolicy. In this case, the mempolicy nodes 12-15 are taken modulo 8 (the\nweight of the mems_allowed of the confining cpuset), resulting in a mempolicy\nspecifying nodes 4-7.\n\nSigned-off-by: Paul Jackson \u003cpj@sgi.com\u003e\nSigned-off-by: David Rientjes \u003crientjes@google.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: \u003cray-lk@madrabbit.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "9f0e8d0400d925c3acd5f4e01dbeb736e4011882", "tree": "970dab54eeba019e4649aa32730489206be5f8a2", "parents": [ "321a8e9dcb714f3c350ba55e41ed447bf3f05fac" ], "author": { "name": "Mike Travis", "email": "travis@sgi.com", "time": "Fri Apr 04 18:11:01 2008 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Apr 19 19:44:59 2008 +0200" }, "message": "x86: convert cpumask_of_cpu macro to allocated array\n\n * Here is a simple patch to use an allocated array of cpumasks to\n represent cpumask_of_cpu() instead of constructing one on the stack.\n It\u0027s based on the Kconfig option \"HAVE_CPUMASK_OF_CPU_MAP\" which is\n currently only set for x86_64 SMP. Otherwise the the existing\n cpumask_of_cpu() is used but has been changed to produce an lvalue\n so a pointer to it can be used.\n\nCc: H. Peter Anvin \u003chpa@zytor.com\u003e\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Mike Travis \u003ctravis@sgi.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "321a8e9dcb714f3c350ba55e41ed447bf3f05fac", "tree": "e75ca8ebcee0954dc6e313864ebba9f72e984fc8", "parents": [ "7c16ec585c558960a508ccf9a08fcb9ed49b3754" ], "author": { "name": "Mike Travis", "email": "travis@sgi.com", "time": "Fri Apr 04 18:11:02 2008 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Apr 19 19:44:59 2008 +0200" }, "message": "cpumask: add CPU_MASK_ALL_PTR macro\n\n * Add a static cpumask_t variable \"CPU_MASK_ALL_PTR\" to use as\n a pointer reference to CPU_MASK_ALL. This reduces where possible\n the instances where CPU_MASK_ALL allocates and fills a large\n array on the stack. Used only if NR_CPUS \u003e BITS_PER_LONG.\n\n * Change init/main.c to use new set_cpus_allowed_ptr().\n\nDepends on:\n\t[sched-devel]: sched: add new set_cpus_allowed_ptr function\n\nCc: H. Peter Anvin \u003chpa@zytor.com\u003e\nSigned-off-by: Mike Travis \u003ctravis@sgi.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "30ca60c15a725f655e5d3f14e0238a066bc5aeb7", "tree": "96d36a2cf12e7a964ce4cd0c49d30b2d40f94b52", "parents": [ "9f0e738f492522a2f70ad9a2a0287e4e966c633a" ], "author": { "name": "Mike Travis", "email": "travis@sgi.com", "time": "Tue Mar 25 15:06:55 2008 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Apr 19 19:44:58 2008 +0200" }, "message": "cpumask: add cpumask_scnprintf_len function\n\nAdd a new function cpumask_scnprintf_len() to return the number of\ncharacters needed to display \"len\" cpumask bits. The current method\nof allocating NR_CPUS bytes is incorrect as what\u0027s really needed is\n9 characters per 32-bit word of cpumask bits (8 hex digits plus the\nseperator [\u0027,\u0027] or the terminating NULL.) This function provides the\ncaller the means to allocate the correct string length.\n\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nSigned-off-by: Mike Travis \u003ctravis@sgi.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "2355188570790930718fb72444cddc2959039d9d", "tree": "eacc078c7acbc1fbd2087d2542fa6f7fb0334ad2", "parents": [ "675a0813609f9097e323261b1cc4b9dc3f50d40b" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Jan 30 13:31:10 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Jan 30 13:31:10 2008 +0100" }, "message": "x86: avoid build warning\n\nfix this build warning:\n\n include/asm/topology_32.h: In function \u0027node_to_first_cpu\u0027:\n include/asm/topology_32.h:66: warning: unused variable \u0027mask\u0027\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "a263898f628dd21e59210b547986c154788f628e", "tree": "b6c0a05c607c9b748336e629b3b6f4ddfea191ee", "parents": [ "57a04513cb35086d54bcb2cb92e6627fc8fa0fae" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Dec 30 11:58:17 2007 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Sun Jan 06 12:39:42 2008 -0800" }, "message": "CPU hotplug: fix cpu_is_offline() on !CONFIG_HOTPLUG_CPU\n\nmake randconfig bootup testing found that the cpufreq code\ncrashes on bootup, if the powernow-k8 driver is enabled and\nif maxcpus\u003d1 passed on the boot line to a !CONFIG_HOTPLUG_CPU\nkernel.\n\nFirst lockdep found out that there\u0027s an inconsistent unlock\nsequence:\n\n \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n [ BUG: bad unlock balance detected! ]\n -------------------------------------\n swapper/1 is trying to release lock (\u0026per_cpu(cpu_policy_rwsem, cpu)) at:\n [\u003cffffffff806ffd8e\u003e] unlock_policy_rwsem_write+0x3c/0x42\n but there are no more locks to release!\n\nCall Trace:\n [\u003cffffffff806ffd8e\u003e] unlock_policy_rwsem_write+0x3c/0x42\n [\u003cffffffff80251c29\u003e] print_unlock_inbalance_bug+0x104/0x12c\n [\u003cffffffff80252f3a\u003e] mark_held_locks+0x56/0x94\n [\u003cffffffff806ffd8e\u003e] unlock_policy_rwsem_write+0x3c/0x42\n [\u003cffffffff807008b6\u003e] cpufreq_add_dev+0x2a8/0x5c4\n ...\n\nthen shortly afterwards the cpufreq code crashed on an assert:\n\n ------------[ cut here ]------------\n kernel BUG at drivers/cpufreq/cpufreq.c:1068!\n invalid opcode: 0000 [1] SMP\n [...]\n Call Trace:\n [\u003cffffffff805145d6\u003e] sysdev_driver_unregister+0x5b/0x91\n [\u003cffffffff806ff520\u003e] cpufreq_register_driver+0x15d/0x1a2\n [\u003cffffffff80cc0596\u003e] powernowk8_init+0x86/0x94\n [...]\n ---[ end trace 1e9219be2b4431de ]---\n\nthe bug was caused by maxcpus\u003d1 bootup, which brought up the\nsecondary core as !cpu_online() but !cpu_is_offline() either,\nwhich on on !CONFIG_HOTPLUG_CPU is always 0 (include/linux/cpu.h):\n\n /* CPUs don\u0027t go offline once they\u0027re online w/o CONFIG_HOTPLUG_CPU */\n static inline int cpu_is_offline(int cpu) { return 0; }\n\nbut the cpufreq code uses cpu_online() and cpu_is_offline() in\na mixed way - the low-level drivers use cpu_online(), while\nthe cpufreq core uses cpu_is_offline(). This opened up the\npossibility to add the non-initialized sysdev device of the\nsecondary core:\n\n cpufreq-core: trying to register driver powernow-k8\n cpufreq-core: adding CPU 0\n powernow-k8: BIOS error - no PSB or ACPI _PSS objects\n cpufreq-core: initialization failed\n cpufreq-core: adding CPU 1\n cpufreq-core: initialization failed\n\nwhich then blew up. The fix is to make cpu_is_offline() always\nthe negation of cpu_online(). With that fix applied the kernel\nboots up fine without crashing:\n\n Calling initcall 0xffffffff80cc0510: powernowk8_init+0x0/0x94()\n powernow-k8: Found 1 AMD Athlon(tm) 64 X2 Dual Core Processor 3800+ processors (1 cpu cores) (version 2.20.00)\n powernow-k8: BIOS error - no PSB or ACPI _PSS objects\n initcall 0xffffffff80cc0510: powernowk8_init+0x0/0x94() returned -19.\n initcall 0xffffffff80cc0510 ran for 19 msecs: powernowk8_init+0x0/0x94()\n Calling initcall 0xffffffff80cc328f: init_lapic_nmi_sysfs+0x0/0x39()\n\nWe could fix this by making CPU enumeration aware of max_cpus, but that\nwould be more fragile IMO, and the cpu_online(cpu) !\u003d cpu_is_offline(cpu)\npossibility was quite confusing and a continuous source of bugs too.\n\nMost distributions have kernels with CPU hotplug enabled, so this bug\nremained hidden for a long time.\n\nBug forensics:\n\nThe broken cpu_is_offline() API variant was introduced via:\n\n commit a59d2e4e6977e7b94e003c96a41f07e96cddc340\n Author: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n Date: Mon Mar 8 06:06:03 2004 -0800\n\n [PATCH] minor cleanups for hotplug CPUs\n\n( this predates linux-2.6.git, this commit is available from Thomas\u0027s\n historic git tree. )\n\nThen 1.5 years later the cpufreq code made use of it:\n\n commit c32b6b8e524d2c337767d312814484d9289550cf\n Author: Ashok Raj \u003cashok.raj@intel.com\u003e\n Date: Sun Oct 30 14:59:54 2005 -0800\n\n [PATCH] create and destroy cpufreq sysfs entries based on cpu notifiers\n\n + if (cpu_is_offline(cpu))\n + return 0;\n\nwhich is a correct use of the subtly broken new API. v2.6.15 then\nshipped with this bug included.\n\nthen it took two more years for random-kernel qa to hit it.\n\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "53b8a315b76a3f3c70a5644976c0095460eb13d8", "tree": "f407a607adb1f552942aef9150ec709ed3f01798", "parents": [ "74c7aa8b8581e0ba8d6d17c623b9279aaabbb0cf" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Feb 20 13:57:51 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Feb 20 17:10:13 2007 -0800" }, "message": "[PATCH] Convert highest_possible_processor_id to nr_cpu_ids\n\nWe frequently need the maximum number of possible processors in order to\nallocate arrays for all processors. So far this was done using\nhighest_possible_processor_id(). However, we do need the number of\nprocessors not the highest id. Moreover the number was so far dynamically\ncalculated on each invokation. The number of possible processors does not\nchange when the system is running. We can therefore calculate that number\nonce.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Frederik Deweerdt \u003cfrederik.deweerdt@gmail.com\u003e\nCc: Neil Brown \u003cneilb@suse.de\u003e\nCc: Trond Myklebust \u003ctrond.myklebust@fys.uio.no\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "01a3ee2b203e511e20f98b85a9172fd32c53e87c", "tree": "0dd90d81dc86f231828af23bdb97522405b06cab", "parents": [ "39484e53bb00f55b6303a908070db133608ef2a5" ], "author": { "name": "Reinette Chatre", "email": "reinette.chatre@linux.intel.com", "time": "Wed Oct 11 01:21:55 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Oct 11 11:14:22 2006 -0700" }, "message": "[PATCH] bitmap: parse input from kernel and user buffers\n\nlib/bitmap.c:bitmap_parse() is a library function that received as input a\nuser buffer. This seemed to have originated from the way the write_proc\nfunction of the /proc filesystem operates.\n\nThis has been reworked to not use kmalloc and eliminates a lot of\nget_user() overhead by performing one access_ok before using __get_user().\n\nWe need to test if we are in kernel or user space (is_user) and access the\nbuffer differently. We cannot use __get_user() to access kernel addresses\nin all cases, for example in architectures with separate address space for\nkernel and user.\n\nThis function will be useful for other uses as well; for example, taking\ninput for /sysfs instead of /proc, so it was changed to accept kernel\nbuffers. We have this use for the Linux UWB project, as part as the\nupcoming bandwidth allocator code.\n\nOnly a few routines used this function and they were changed too.\n\nSigned-off-by: Reinette Chatre \u003creinette.chatre@linux.intel.com\u003e\nSigned-off-by: Inaky Perez-Gonzalez \u003cinaky@linux.intel.com\u003e\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nCc: Joe Korty \u003cjoe.korty@ccur.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "9de9adb615bddbdb786273c41ec3c03837e32fa5", "tree": "d9c37e52c032f9bbb2da5f55868a79b299e58d25", "parents": [ "eab98702afa567927c9b052499b43acad2f25a1c" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Sun Jun 25 05:48:10 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Jun 25 10:01:12 2006 -0700" }, "message": "[PATCH] for_each_cpu_mask() warning fix\n\nOn UP, this:\n\n cpumask_t mask \u003d node_to_cpumask(numa_node_id());\n\n for_each_cpu_mask(cpu, mask)\n\ndoes this:\n\nmm/readahead.c: In function `node_readahead_aging\u0027:\nmm/readahead.c:850: warning: unused variable `mask\u0027\n\nwhich is unpleasantly fixed by this:\n\nAcked-by: Paul Jackson \u003cpj@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "fb1bb34d45400f12e0a33f8c487b3795674908a7", "tree": "11c593c83eff5a83999f4feee0d8937d1f575712", "parents": [ "1e48275adc8c94c3281e646c8beb829f8e6f5bfc" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Sun Jun 25 05:46:43 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Jun 25 10:00:54 2006 -0700" }, "message": "[PATCH] remove for_each_cpu()\n\nConvert a few stragglers over to for_each_possible_cpu(), remove\nfor_each_cpu().\n\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "631d6747e1d877a4baa924cb373b8b9511a53e5e", "tree": "5bb88d5c9716b9d9f398a6a1e8c8be4501671643", "parents": [ "68c3431ae22912be580c68d3955ef46515582943" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Mar 28 01:56:36 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Mar 28 09:16:04 2006 -0800" }, "message": "[PATCH] for_each_possible_cpu: defines for_each_possible_cpu\n\nfor_each_cpu() is a for-loop over cpu_possible_map. for_each_online_cpu is\nfor-loop cpu over cpu_online_map. .....for_each_cpu() is not sufficiently\nexplicit and can lead to mistakes.\n\nThis patch adds for_each_possible_cpu() in preparation for the removal of\nfor_each_cpu().\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "96a9b4d31eba4722ba7aad2cc15118a7799f499f", "tree": "f96739e328e3e50b43122e551a36415f6e26a1e8", "parents": [ "8630282070b4a52b12cfa514ba8558e2f3d56360" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Sat Mar 25 03:08:10 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sat Mar 25 08:23:00 2006 -0800" }, "message": "[PATCH] cpumask: uninline any_online_cpu()\n\n text data bss dec hex filename\nbefore: 3605597 1363528 363328 5332453 515de5 vmlinux\nafter: 3605295 1363612 363200 5332107 515c8b vmlinux\n\n218 bytes saved.\n\nAlso, optimise any_online_cpu() out of existence on CONFIG_SMP\u003dn.\n\nThis function seems inefficient. Can\u0027t we simply AND the two masks, then use\nfind_first_bit()?\n\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "8630282070b4a52b12cfa514ba8558e2f3d56360", "tree": "cf648185ccc0a0ba4e7cf752c1c09a0272a6d192", "parents": [ "3d18bd74a22d0bed3bc81fc64c4ba6344a10f155" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Sat Mar 25 03:08:09 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sat Mar 25 08:23:00 2006 -0800" }, "message": "[PATCH] cpumask: uninline highest_possible_processor_id()\n\nShrinks the only caller (net/bridge/netfilter/ebtables.c) by 174 bytes.\n\nAlso, optimise highest_possible_processor_id() out of existence on\nCONFIG_SMP\u003dn.\n\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "3d18bd74a22d0bed3bc81fc64c4ba6344a10f155", "tree": "414b44796651db833481e17030f0b18a1be3527b", "parents": [ "ccb46000f4bb459777686611157ac0eac928704e" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Sat Mar 25 03:08:09 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sat Mar 25 08:22:59 2006 -0800" }, "message": "[PATCH] cpumask: uninline next_cpu()\n\n text data bss dec hex filename\nbefore: 3488027 1322496 360128 5170651 4ee5db vmlinux\nafter: 3485112 1322480 359968 5167560 4ed9c8 vmlinux\n\n2931 bytes saved\n\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "ccb46000f4bb459777686611157ac0eac928704e", "tree": "461e956d9e27a7afa7de64950f3186070ffa61f5", "parents": [ "64b91379439ff0fb007bde90eb496299c14a9b2a" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Sat Mar 25 03:08:08 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sat Mar 25 08:22:59 2006 -0800" }, "message": "[PATCH] cpumask: uninline first_cpu()\n\n text data bss dec hex filename\nbefore: 3490577 1322408 360000 5172985 4eeef9 vmlinux\nafter: 3488027 1322496 360128 5170651 4ee5db vmlinux\n\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "7a8ef1cb774e5438d292365626f9b96616283706", "tree": "82d085204e8728d28a5267fb39aa2e26ea8824c9", "parents": [ "705672935f8a9e661264e34cd8c409e8cddcc7db" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Fri Feb 10 01:51:08 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Feb 10 08:13:12 2006 -0800" }, "message": "[PATCH] x86: don\u0027t initialise cpu_possible_map to all ones\n\nInitialising cpu_possible_map to all-ones with CONFIG_HOTPLUG_CPU means that\n\na) All for_each_cpu() loops will iterate across all NR_CPUS CPUs, rather\n than over possible ones. That can be quite expensive.\n\nb) Soon we\u0027ll be allocating per-cpu areas only for possible CPUs. So with\n CPU_MASK_ALL, we\u0027ll be wasting memory.\n\nI also switched voyager over to not use CPU_MASK_ALL in the non-CPU-hotplug\ncase. Should be OK..\n\nI note that parisc is also using CPU_MASK_ALL. Suggest that it stop doing\nthat.\n\nCc: James Bottomley \u003cJames.Bottomley@steeleye.com\u003e\nCc: Kyle McMartin \u003ckyle@mcmartin.ca\u003e\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nCc: Ashok Raj \u003cashok.raj@intel.com\u003e\nCc: Zwane Mwaikambo \u003czwane@linuxpower.ca\u003e\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1b8623545b42c03eb92e51b28c84acf4b8ba00a3", "tree": "071045ad9c60d2697292c523c77322a70a248fb9", "parents": [ "92118c739df879497b8cc5a2eb3a9dc255f01b20" ], "author": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Thu Dec 15 01:07:03 2005 -0500" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Tue Feb 07 20:56:35 2006 -0500" }, "message": "[PATCH] remove bogus asm/bug.h includes.\n\nA bunch of asm/bug.h includes are both not needed (since it will get\npulled anyway) and bogus (since they are done too early). Removed.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "fb5eeeee44edb248b4837416966f19731f497f79", "tree": "f947a4dcf103f55d526bb5c71f69b657d8f22e61", "parents": [ "28a42b9ea7e42e1efb02cc2dcacba0b6af234e1b" ], "author": { "name": "Paul Jackson", "email": "pj@sgi.com", "time": "Sun Oct 30 15:02:33 2005 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Oct 30 17:37:21 2005 -0800" }, "message": "[PATCH] cpusets: bitmap and mask remap operators\n\nIn the forthcoming task migration support, a key calculation will be\nmapping cpu and node numbers from the old set to the new set while\npreserving cpuset-relative offset.\n\nFor example, if a task and its pages on nodes 8-11 are being migrated to\nnodes 24-27, then pages on node 9 (the 2nd node in the old set) should be\nmoved to node 25 (the 2nd node in the new set.)\n\nAs with other bitmap operations, the proper way to code this is to provide\nthe underlying calculation in lib/bitmap.c, and then to provide the usual\ncpumask and nodemask wrappers.\n\nThis patch provides that. These operations are termed \u0027remap\u0027 operations.\nBoth remapping a single bit and a set of bits is supported.\n\nSigned-off-by: Paul Jackson \u003cpj@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "688ce17b8599abc548b406c00e4d18ae0dec954f", "tree": "c64c78c72bf9582c2dcc5a3455d6fe561c6e7085", "parents": [ "e6850cce8f0fcb0e16b981f13cb9c69618bbdaf1" ], "author": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Sun Oct 16 00:17:33 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Oct 16 00:17:33 2005 -0700" }, "message": "[PATCH]: highest_possible_processor_id() has to be a macro\n\n\t... otherwise, things like alpha and sparc64 break and break\nbadly. They define cpu_possible_map to something else in smp.h\n*AFTER* having included cpumask.h.\n\n\tIf that puppy is a macro, expansion will happen at the actual\ncaller, when we\u0027d already seen #define cpu_possible_map ... and we will\nget the right thing used.\n\n\tAs an inline helper it will be tokenized before we get to that\ndefine and that\u0027s it; no matter what we define later, it won\u0027t affect\nanything. We get modules with dependency on cpu_possible_map instead\nof the right symbol (phys_cpu_present_map in case of sparc64), or outright\nlink errors if they are built-in.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n\n" }, { "commit": "c8923c6b852d3a97c1faad0566e38fca330375a7", "tree": "eb79e97c5468bba641c7a34b83514876f4902cf2", "parents": [ "c931488cc4619eecfe68a2f046b5898fddc2f904" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Oct 13 14:41:23 2005 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Oct 13 14:41:23 2005 -0700" }, "message": "[NETFILTER]: Fix OOPSes on machines with discontiguous cpu numbering.\n\nOriginal patch by Harald Welte, with feedback from Herbert Xu\nand testing by Sébastien Bernard.\n\nEBTABLES, ARP tables, and IP/IP6 tables all assume that cpus\nare numbered linearly. That is not necessarily true.\n\nThis patch fixes that up by calculating the largest possible\ncpu number, and allocating enough per-cpu structure space given\nthat.\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1da177e4c3f41524e886b7f1b8a0c1fc7321cac2", "tree": "0bba044c4ce775e45a88a51686b5d9f90697ea9d", "parents": [], "author": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "message": "Linux-2.6.12-rc2\n\nInitial git repository build. I\u0027m not bothering with the full history,\neven though we have it. We can create a separate \"historical\" git\narchive of that later if we want to, and in the meantime it\u0027s about\n3.2GB when imported into git - space that would just make the early\ngit days unnecessarily complicated, when we don\u0027t have a lot of good\ninfrastructure for it.\n\nLet it rip!\n" } ] }