)]}' { "log": [ { "commit": "839052d27e8db0c1545256fe5827abcd00fb51c5", "tree": "003839d444943ba8f125846e776b068721da2c8f", "parents": [ "3fb2c74ee20b77affd494c6b8ce7928d0ebbb62e" ], "author": { "name": "Huang, Xiaolan", "email": "xiaolan.huang@intel.com", "time": "Thu May 15 10:18:41 2008 +0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu May 15 09:54:19 2008 -0700" }, "message": "[IA64] fix personality(PER_LINUX32) performance issue\n\nThe patch aims to fix a performance issue for the syscall\npersonality(PER_LINUX32).\n\nOn IA-64 box, the syscall personality (PER_LINUX32) has poor performance\nbecause it failed to find the Linux/x86 execution domain. Then it tried\nto load the kernel module however it failed always and it used the default\nexecution domain PER_LINUX instead. Requesting kernel modules is very\nexpensive. It caused the performance issue. (see the function\nlookup_exec_domain in kernel/exec_domain.c).\n\nTo resolve the issue, execution domain Linux/x86 is always registered in\ninitialization time for IA-64 architecture.\n\nSigned-off-by: Xiaolan Huang \u003cxiaolan.huang@intel.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "e617fce64e5faea149fcf3bffc1b42e4ba29e7e5", "tree": "23a3f38995e55bbcbb79c93aa7504acd12f9dd4e", "parents": [ "7663c1e2792a9662b23dec6e19bfcd3d55360b8f" ], "author": { "name": "Hidetoshi Seto", "email": "seto.hidetoshi@jp.fujitsu.com", "time": "Fri Apr 25 23:13:09 2008 +0900" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Apr 29 13:47:45 2008 -0700" }, "message": "[IA64] bugfix: nptcg breaks cpu-hotadd\n\nIf \"max_purges\" from PAL is 0, it actually means 1.\n\nHowever it was not handled later when a hot-added cpu pass the\nmax_purges from PAL. This makes systems easy to go BUG_ON().\n\nSigned-off-by: Hidetoshi Seto \u003cseto.hidetoshi@jp.fujitsu.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "180c06efce691f2b721dd0d965079827bdd7ee03", "tree": "6d5dbde8f341544bbd212e9d376af1e7880a4229", "parents": [ "ea01ea937dcae2caa146dea1918cccf2f16ed3c4" ], "author": { "name": "Jeremy Fitzhardinge", "email": "jeremy@goop.org", "time": "Mon Apr 28 02:12:03 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:17 2008 -0700" }, "message": "hotplug-memory: make online_page() common\n\nAll architectures use an effectively identical definition of online_page(), so\njust make it common code. x86-64, ia64, powerpc and sh are actually\nidentical; x86-32 is slightly different.\n\nx86-32\u0027s differences arise because it puts its hotplug pages in the highmem\nzone. We can handle this in the generic code by inspecting the page to see if\nits in highmem, and update the totalhigh_pages count appropriately. This\nleaves init_32.c:free_new_highpage with a single caller, so I folded it into\nadd_one_highpage_init.\n\nI also removed an incorrect comment referring to the NUMA case; any NUMA\ndetails have already been dealt with by the time online_page() is called.\n\n[akpm@linux-foundation.org: fix indenting]\nSigned-off-by: Jeremy Fitzhardinge \u003cjeremy.fitzhardinge@citrix.com\u003e\nAcked-by: Dave Hansen \u003cdave@linux.vnet.ibm.com\u003e\nReviewed-by: KAMEZAWA Hiroyuki \u003ckamez.hiroyu@jp.fujitsu.com\u003e\nTested-by: KAMEZAWA Hiroyuki \u003ckamez.hiroyu@jp.fujitsu.com\u003e\nCc: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nAcked-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nAcked-by: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "71b264f85ff50c14fe945ffff06ae0d5e9a9124e", "tree": "9fd79c63fd630c4d030a97d254d42a3a73f1328b", "parents": [ "f4df39cbdd9e9ab615e80148cc271db22a8508ad", "072f042df335d7e0da2027637bcf720d7ff1589b" ], "author": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Apr 17 10:14:51 2008 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Apr 17 10:14:51 2008 -0700" }, "message": "Pull miscellaneous into release branch\n\nConflicts:\n\n\tarch/ia64/kernel/mca.c\n" }, { "commit": "f4df39cbdd9e9ab615e80148cc271db22a8508ad", "tree": "312fcf9de1154c85782c121a46fa2952f9812292", "parents": [ "a49072bb367a94a9af6c6a6dcbaa1dc5617d7fa0", "a6c75b86ce9f01db4ea9912877b526c2dc4d2f0a" ], "author": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Apr 17 10:13:57 2008 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Apr 17 10:13:57 2008 -0700" }, "message": "Pull nptcg into release branch\n\nConflicts:\n\n\tarch/ia64/mm/tlb.c\n" }, { "commit": "a49072bb367a94a9af6c6a6dcbaa1dc5617d7fa0", "tree": "155159e2ace7175298465b6fbf1024c77de8edce", "parents": [ "fc494d6c1825de37f04abe147741d50be08403ab", "31a6b11fed6ceec07ec4bdfefae56b8252d450cf" ], "author": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Apr 17 10:13:09 2008 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Apr 17 10:13:09 2008 -0700" }, "message": "Pull kvm-patches into release branch\n" }, { "commit": "98075d245a5bc4aeebc2e9f16fa8b089a5c200ac", "tree": "5d248fa7ec872548e43ed2acb864d701adc65f42", "parents": [ "c19b2930df0621500913c005c06978bd8933110b" ], "author": { "name": "Zoltan Menyhart", "email": "Zoltan.Menyhart@bull.net", "time": "Fri Apr 11 15:21:35 2008 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Fri Apr 11 15:21:35 2008 -0700" }, "message": "[IA64] Fix NUMA configuration issue\n\nThere is a NUMA memory configuration issue in 2.6.24:\n\nA 2-node machine of ours has got the following memory layout:\n\nNode 0:\t0 - 2 Gbytes\nNode 0:\t4 - 8 Gbytes\nNode 1:\t8 - 16 Gbytes\nNode 0:\t16 - 18 Gbytes\n\n\"efi_memmap_init()\" merges the three last ranges into one.\n\n\"register_active_ranges()\" is called as follows:\n\nefi_memmap_walk(register_active_ranges, NULL);\n\ni.e. once for the 4 - 18 Gbytes range. It picks up the node\nnumber from the start address, and registers all the memory for\nthe node #0.\n\n\"register_active_ranges()\" should be called as follows to\nmake sure there is no merged address range at its entry:\n\nefi_memmap_walk(filter_memory, register_active_ranges);\n\n\"filter_memory()\" is similar to \"filter_rsvd_memory()\",\nbut the reserved memory ranges are not filtered out.\n\nSigned-off-by: Zoltan Menyhart \u003cZoltan.Menyhart@bull.net\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "273988fa4dffd1b1e6deb3de18b979a44e9d8732", "tree": "f28645f5d5a5432bf0cd3f91318ce4709830f196", "parents": [ "5cf1f7cef1c67b5c81736f00e81a2890e07041b9" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Wed Apr 09 13:05:41 2008 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Wed Apr 09 13:05:41 2008 -0700" }, "message": "[IA64] Untangle sync_icache_dcache() page size determination\n\nUntangle the chaos of page size determination in this function by\nsimply using PAGE_SIZE \u003c\u003c compound_order().\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "734bc367b4830a4c80502a3f9ded7428b1c652e3", "tree": "3bac326add6e8009b1c393fe3efe378ff5b348be", "parents": [ "b34eb53cdcb4f49fd31d78d0e385240820ed9063" ], "author": { "name": "Johannes Weiner", "email": "hannes@saeurebad.de", "time": "Fri Mar 28 14:27:04 2008 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Wed Apr 09 10:37:51 2008 -0700" }, "message": "[IA64] remove redundant display of free swap space in show_mem()\n\nshow_mem() has no need to print the amount of free swap space manually because\nshow_free_areas() does this already and is called by the former.\n\nThe two outputs only differ in text formatting:\n\n printk(\"Free swap \u003d %lukB\\n\", ...);\n printk(\"Free swap: %6ldkB\\n\", ...);\n\nSigned-off-by: Johannes Weiner \u003channes@saeurebad.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "2c6e6db41f01b6b4eb98809350827c9678996698", "tree": "00438344c0ad599c1301db2abe32a4c2ee89b607", "parents": [ "41bd26d67c41e325c6b9e56aadfe9dad8af9a565" ], "author": { "name": "holt@sgi.com", "email": "holt@sgi.com", "time": "Thu Apr 03 15:17:13 2008 -0500" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Apr 08 13:51:35 2008 -0700" }, "message": "[IA64] Minimize per_cpu reservations.\n\nThis attached patch significantly shrinks boot memory allocation on ia64.\nIt does this by not allocating per_cpu areas for cpus that can never\nexist.\n\nIn the case where acpi does not have any numa node description of the\ncpus, I defaulted to assigning the first 32 round-robin on the known\nnodes.. For the !CONFIG_ACPI I used for_each_possible_cpu().\n\nSigned-off-by: Robin Holt \u003cholt@sgi.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "41bd26d67c41e325c6b9e56aadfe9dad8af9a565", "tree": "d2a2c7dc8b570dd049e33412935ca26ea54a0d7f", "parents": [ "7180c4c9e09888db0a188f729c96c6d7bd61fa83" ], "author": { "name": "holt@sgi.com", "email": "holt@sgi.com", "time": "Thu Apr 03 15:17:12 2008 -0500" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Apr 08 13:50:58 2008 -0700" }, "message": "[IA64] Correct pernodesize calculation.\n\nA simple fix. The existing pernodesize reservation is not taking into\naccount a second array of pg_data_t structures. This is normally not\nimportant because the PAGE_ALIGN macro reserves adequate space.\n\nI made the compute_pernodesize steps in the same order as the fill_pernode\nsteps to make the correlation more clear.\n\nSigned-off-by: Robin Holt \u003cholt@sgi.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "a6c75b86ce9f01db4ea9912877b526c2dc4d2f0a", "tree": "a8763d9be28ffff5d28f1ff3235f044aaa64a0fa", "parents": [ "2046b94e7c4fce92eb8165c2c36c6478f4927178" ], "author": { "name": "Fenghua Yu", "email": "fenghua.yu@intel.com", "time": "Fri Mar 14 13:57:08 2008 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Fri Apr 04 11:06:38 2008 -0700" }, "message": "[IA64] Kernel parameter for max number of concurrent global TLB purges\n\nThe patch defines kernel parameter \"nptcg\u003d\". The parameter overrides max number\nof concurrent global TLB purges which is reported from either PAL_VM_SUMMARY or\nSAL PALO.\n\nSigned-off-by: Fenghua Yu \u003cfenghua.yu@intel.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "2046b94e7c4fce92eb8165c2c36c6478f4927178", "tree": "0dbbdf17d64b521f2debcc8677368ceec8805d8c", "parents": [ "e315c121a858499d84dc88c499046b9f10bb61ec" ], "author": { "name": "Fenghua Yu", "email": "fenghua.yu@intel.com", "time": "Fri Apr 04 11:05:59 2008 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Fri Apr 04 11:05:59 2008 -0700" }, "message": "[IA64] Multiple outstanding ptc.g instruction support\n\nAccording to SDM2.2, Itanium supports multiple outstanding ptc.g instructions.\nBut current kernel function ia64_global_tlb_purge() uses a spinlock to serialize\nptc.g instructions issued by multiple processors. This serialization might have\nscalability issue on a big SMP machine where many processors could purge TLB\nin parallel.\n\nThe patch fixes this problem by issuing multiple ptc.g instructions in\nia64_global_tlb_purge(). It also adds support for the \"PALO\" table to get\na platform view of the max number of outstanding ptc.g instructions (which\nmay be different from the processor view found from PAL_VM_SUMMARY).\n\nPALO specification can be found at: http://www.dig64.org/home/DIG64_PALO_R1_0.pdf\n\nspinaphore implementation by Matthew Wilcox.\n\nSigned-off-by: Fenghua Yu \u003cfenghua.yu@intel.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "96651896b8d9ad4244a1c3ed9691faa3e382f503", "tree": "d1982cf832e019deb8619fd0eae9133e5b98bc99", "parents": [ "9597362d354f8655ece324b01d0c640a0e99c077" ], "author": { "name": "Xiantao Zhang", "email": "xiantao.zhang@intel.com", "time": "Thu Apr 03 11:02:58 2008 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Apr 03 11:02:58 2008 -0700" }, "message": "[IA64] Add API for allocating Dynamic TR resource.\n\nDynamic TR resource should be managed in the uniform way.\nAdd two interfaces for kernel:\nia64_itr_entry: Allocate a (pair of) TR for caller.\nia64_ptr_entry: Purge a (pair of ) TR by caller.\n\nSigned-off-by: Xiantao Zhang \u003cxiantao.zhang@intel.com\u003e\nSigned-off-by: Anthony Xu \u003canthony.xu@intel.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "45e18c228e131592a922859e1525770a1803191d", "tree": "a971746de55c007d222ef2f7834045261240fffb", "parents": [ "818c7e866f920b145424c2c46deda4b27c3fb316" ], "author": { "name": "Harvey Harrison", "email": "harvey.harrison@gmail.com", "time": "Thu Mar 06 09:49:01 2008 -0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Mar 06 09:49:01 2008 -0800" }, "message": "[IA64] kprobes arch consolidation build fix\n\nia64 named their handler kprobes_fault_handler while all other\narches used kprobe_fault_handler. Change the function definition\nand header declaration.\n\nSigned-off-by: Harvey Harrison \u003charvey.harrison@gmail.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "d4ed80841ad4a1d59decccfbe2d010558568c5fb", "tree": "81ebf4a87688f4b0cc46f74266b5b0cac76932b0", "parents": [ "2d9b06c72a9f2e6042d72df7d9000a48bcba34f0" ], "author": { "name": "Harvey Harrison", "email": "harvey.harrison@gmail.com", "time": "Tue Mar 04 15:15:00 2008 -0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Mar 06 09:19:27 2008 -0800" }, "message": "[IA64] remove remaining __FUNCTION__ occurrences\n\n__FUNCTION__ is gcc-specific, use __func__\n\nLong lines have been kept where they exist, some small spacing changes\nhave been done.\n\nSigned-off-by: Harvey Harrison \u003charvey.harrison@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "72a7fe3967dbf86cb34e24fbf1d957fe24d2f246", "tree": "c19f7d0b530577359840e959cce204939caf0649", "parents": [ "25fad945a7f7ff2cf06e437381c6a1121784dbd9" ], "author": { "name": "Bernhard Walle", "email": "bwalle@suse.de", "time": "Thu Feb 07 00:15:17 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Feb 07 08:42:25 2008 -0800" }, "message": "Introduce flags for reserve_bootmem()\n\nThis patchset adds a flags variable to reserve_bootmem() and uses the\nBOOTMEM_EXCLUSIVE flag in crashkernel reservation code to detect collisions\nbetween crashkernel area and already used memory.\n\nThis patch:\n\nChange the reserve_bootmem() function to accept a new flag BOOTMEM_EXCLUSIVE.\nIf that flag is set, the function returns with -EBUSY if the memory already\nhas been reserved in the past. This is to avoid conflicts.\n\nBecause that code runs before SMP initialisation, there\u0027s no race condition\ninside reserve_bootmem_core().\n\n[akpm@linux-foundation.org: coding-style fixes]\n[akpm@linux-foundation.org: fix powerpc build]\nSigned-off-by: Bernhard Walle \u003cbwalle@suse.de\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nCc: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nCc: Vivek Goyal \u003cvgoyal@in.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "620de2f5dc697f906408743b1139fe5fb7b0b7f8", "tree": "01c731dfc3f8aca8f100482ef79d6795e03b4dba", "parents": [ "ef3c4cb936d854d1564172f2dcce9c20d1b08761" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Mon Feb 04 23:43:03 2008 -0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Feb 05 08:26:44 2008 -0800" }, "message": "[IA64] honor notify_die() returning NOTIFY_STOP\n\nThis requires making die() and die_if_kernel() return a value, and their\ncallers to honor this (and be prepared that it returns).\n\nSigned-off-by: Jan Beulich \u003cjbeulich@novell.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "aec103bfa60e9f72bd66a144236592f54b986a03", "tree": "90c1cf2de8853dd6e3972f295d1aecfe3aee507a", "parents": [ "3cdc7fc7fd5bd1ead75758dfadef609a6e9fd3de" ], "author": { "name": "de Dinechin, Christophe (Integrity VM)", "email": "christophe.de-dinechin@hp.com", "time": "Thu Dec 13 15:03:07 2007 +0000" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Dec 18 16:56:50 2007 -0800" }, "message": "[IA64] Avoid unnecessary TLB flushes when allocating memory\n\nImprove performance of memory allocations on ia64 by avoiding a global TLB\npurge to purge a single page from the file cache. This happens whenever we\nevict a page from the buffer cache to make room for some other allocation.\n\nTest case: Run \u0027find /usr -type f | xargs cat \u003e /dev/null\u0027 in the\nbackground to fill the buffer cache, then run something that uses memory,\ne.g. \u0027gmake -j50 install\u0027. Instrumentation showed that the number of\nglobal TLB purges went from a few millions down to about 170 over a 12\nhours run of the above.\n\nThe performance impact is particularly noticeable under virtualization,\nbecause a virtual TLB is generally both larger and slower to purge than\na physical one.\n\nSigned-off-by: Christophe de Dinechin \u003cddd@hp.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "c2eeb321a8f059112bdf0f8d4ac7ab35800f3f66", "tree": "7fc333e3cb8aa08ffca1265fdd80f715db4b0794", "parents": [ "685c7f5d3629d558b17ee193b6d7f194e82aadf0" ], "author": { "name": "Joe Perches", "email": "joe@perches.com", "time": "Mon Nov 19 17:47:53 2007 -0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Fri Dec 07 16:12:17 2007 -0800" }, "message": "[IA64] Add missing \"space\" to concatenated strings\n\nSigned-off-by: Joe Perches \u003cjoe@perches.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "4b9ddc7cf272a0af321c22ef9c00d76384402d48", "tree": "14b91c54bd8d77e8218ec5df84f5cc5cd469077e", "parents": [ "4b07ae9b9d7b05a63e3ece32a666041949b7f421" ], "author": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Nov 06 15:14:45 2007 -0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Nov 06 15:14:45 2007 -0800" }, "message": "[IA64] Fix section mismatch in contig.c version of per_cpu_init()\n\nThere is a section mismatch when building CONFIG_FLATMEM\u003dy kernels\nthat also have CONFIG_HOTPLUG_CPU\u003dy\n\nWARNING: vmlinux.o(.text+0x5a902): Section mismatch: reference to \\\n.init.text:__alloc_bootmem (between \u0027per_cpu_init\u0027 and \u0027count_pages\u0027)\n\nThe issue occurs because per_cpu_init() in mm/contig.c is\nmarked __cpuinit (which is #define\u0027d to nothing on a hot\nplug cpu configuration) call __alloc_bootmem() (which is\nan __init function). The usage is actually safe because\nthe __alloc_bootmem() is inside an \"if (first_time)\" test\nso that the call is only made while it is still legal to\ndo so.\n\nBut the warning is irritating. Move the allocation to\nfind_memory().\n\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "18b8befd3755b2b9afa86e270b701473676644b7", "tree": "fd98090ef001af571b84f8d7578bf6f2eaa635a8", "parents": [ "2a397e82c7db18019e408f953dd58dc1963a328c" ], "author": { "name": "Adrian Bunk", "email": "bunk@kernel.org", "time": "Mon Oct 29 13:49:47 2007 +0100" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon Oct 29 10:42:35 2007 -0700" }, "message": "[IA64] ia64/mm/init.c: fix section mismatches\n\nThis patch fixes the following section mismatches:\n\n\u003c-- snip --\u003e\n\n...\nWARNING: vmlinux.o(.text+0x5b5c2): Section mismatch: reference to .init.text:memmap_init_zone (between \u0027memmap_init\u0027 and \u0027virtual_memmap_init\u0027)\nWARNING: vmlinux.o(.text+0x5b842): Section mismatch: reference to .init.text:memmap_init_zone (between \u0027virtual_memmap_init\u0027 and \u0027ia64_mmu_init\u0027)\n...\n\n\u003c-- snip --\u003e\n\nSigned-off-by: Adrian Bunk \u003cbunk@kernel.org\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "b460cbc581a53cc088ceba80608021dd49c63c43", "tree": "83c28d0adbc15f4157c77b40fa60c40a71cb8673", "parents": [ "3743ca05ff464b8a9e345c08a6c9ce30485f9805" ], "author": { "name": "Serge E. Hallyn", "email": "serue@us.ibm.com", "time": "Thu Oct 18 23:39:52 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Oct 19 11:53:37 2007 -0700" }, "message": "pid namespaces: define is_global_init() and is_container_init()\n\nis_init() is an ambiguous name for the pid\u003d\u003d1 check. Split it into\nis_global_init() and is_container_init().\n\nA cgroup init has it\u0027s tsk-\u003epid \u003d\u003d 1.\n\nA global init also has it\u0027s tsk-\u003epid \u003d\u003d 1 and it\u0027s active pid namespace\nis the init_pid_ns. But rather than check the active pid namespace,\ncompare the task structure with \u0027init_pid_ns.child_reaper\u0027, which is\ninitialized during boot to the /sbin/init process and never changes.\n\nChangelog:\n\n\t2.6.22-rc4-mm2-pidns1:\n\t- Use \u0027init_pid_ns.child_reaper\u0027 to determine if a given task is the\n\t global init (/sbin/init) process. This would improve performance\n\t and remove dependence on the task_pid().\n\n\t2.6.21-mm2-pidns2:\n\n\t- [Sukadev Bhattiprolu] Changed is_container_init() calls in {powerpc,\n\t ppc,avr32}/traps.c for the _exception() call to is_global_init().\n\t This way, we kill only the cgroup if the cgroup\u0027s init has a\n\t bug rather than force a kernel panic.\n\n[akpm@linux-foundation.org: fix comment]\n[sukadev@us.ibm.com: Use is_global_init() in arch/m32r/mm/fault.c]\n[bunk@stusta.de: kernel/pid.c: remove unused exports]\n[sukadev@us.ibm.com: Fix capability.c to work with threaded init]\nSigned-off-by: Serge E. Hallyn \u003cserue@us.ibm.com\u003e\nSigned-off-by: Sukadev Bhattiprolu \u003csukadev@us.ibm.com\u003e\nAcked-by: Pavel Emelianov \u003cxemul@openvz.org\u003e\nCc: Eric W. Biederman \u003cebiederm@xmission.com\u003e\nCc: Cedric Le Goater \u003cclg@fr.ibm.com\u003e\nCc: Dave Hansen \u003chaveblue@us.ibm.com\u003e\nCc: Herbert Poetzel \u003cherbert@13thfloor.at\u003e\nCc: Kirill Korotaev \u003cdev@sw.ru\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "3ed75eb8f1cd89565966599c4f77d2edb086d5b0", "tree": "54e77a47b40da80d76baf5eacc2259e0bc5bdf7c", "parents": [ "1c7037db50ebecf3d5cfbf7082daa5d97d900fef" ], "author": { "name": "Coly Li", "email": "coyli@suse.de", "time": "Thu Oct 18 23:39:15 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Oct 19 11:53:34 2007 -0700" }, "message": "setup vma-\u003evm_page_prot by vm_get_page_prot()\n\nThis patch uses vm_get_page_prot() to setup vma-\u003evm_page_prot.\n\nThough inside vm_get_page_prot() the protection flags is AND with\n(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED), it does not hurt correct code.\n\nSigned-off-by: Coly Li \u003ccoyli@suse.de\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Tony Luck \u003ctony.luck@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "fd59d231f81cb02870b9cf15f456a897f3669b4e", "tree": "5713c13bd678774f1ba3c42bfff5008c1812deae", "parents": [ "0e647c04f665e9b3451a1ebe8252b38ffe0207c8" ], "author": { "name": "Ken\u0027ichi Ohmichi", "email": "oomichi@mxs.nes.nec.co.jp", "time": "Tue Oct 16 23:27:27 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:42:54 2007 -0700" }, "message": "Add vmcoreinfo\n\nThis patch set frees the restriction that makedumpfile users should install a\nvmlinux file (including the debugging information) into each system.\n\nmakedumpfile command is the dump filtering feature for kdump. It creates a\nsmall dumpfile by filtering unnecessary pages for the analysis. To\ndistinguish unnecessary pages, it needs a vmlinux file including the debugging\ninformation. These days, the debugging package becomes a huge file, and it is\nhard to install it into each system.\n\nTo solve the problem, kdump developers discussed it at lkml and kexec-ml. As\nthe result, we reached the conclusion that necessary information for dump\nfiltering (called \"vmcoreinfo\") should be embedded into the first kernel file\nand it should be accessed through /proc/vmcore during the second kernel.\n(http://www.uwsg.iu.edu/hypermail/linux/kernel/0707.0/1806.html)\n\nDan Aloni created the patch set for the above implementation.\n(http://www.uwsg.iu.edu/hypermail/linux/kernel/0707.1/1053.html)\n\nAnd I updated it for multi architectures and memory models.\n(http://lists.infradead.org/pipermail/kexec/2007-August/000479.html)\n\nSigned-off-by: Dan Aloni \u003cda-x@monatomic.org\u003e\nSigned-off-by: Ken\u0027ichi Ohmichi \u003coomichi@mxs.nes.nec.co.jp\u003e\nSigned-off-by: Bernhard Walle \u003cbwalle@suse.de\u003e\nSigned-off-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "48e94196a533dbee17c252bf80d0310fb8c8c2eb", "tree": "9b29060b0e2600dc7da645fd436dc94c25d1fb36", "parents": [ "de33b821f34dc9e2fabf81a8ba464f3ef039bd00" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Oct 16 01:26:14 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:02 2007 -0700" }, "message": "fix memory hot remove not configured case.\n\nNow, arch dependent code around CONFIG_MEMORY_HOTREMOVE is a mess.\nThis patch cleans up them. This is against 2.6.23-rc6-mm1.\n\n - fix compile failure on ia64/ CONFIG_MEMORY_HOTPLUG \u0026\u0026 !CONFIG_MEMORY_HOTREMOVE case.\n - For !CONFIG_MEMORY_HOTREMOVE, add generic no-op remove_memory(),\n which returns -EINVAL.\n - removed remove_pages() only used in powerpc.\n - removed no-op remove_memory() in i386, sh, sparc64, x86_64.\n\n - only powerpc returns -ENOSYS at memory hot remove(no-op). changes it\n to return -EINVAL.\n\nNote:\nCurrently, only ia64 supports CONFIG_MEMORY_HOTREMOVE. I welcome other\narchs if there are requirements and testers.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "de33b821f34dc9e2fabf81a8ba464f3ef039bd00", "tree": "fa7486b6a5ab054b7c220559e4af262629579a26", "parents": [ "0c0e6195896535481173df98935ad8db174f4d45" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Oct 16 01:26:13 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:02 2007 -0700" }, "message": "memory unplug: ia64 interface\n\nIA64 memory unplug interface.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d9c2340052278d8eb2ffb16b0484f8f794def4de", "tree": "aec7e4e11473a4fcdfd389c718544780a042c6df", "parents": [ "d100313fd615cc30374ff92e0b3facb053838330" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:26:01 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "Do not depend on MAX_ORDER when grouping pages by mobility\n\nCurrently mobility grouping works at the MAX_ORDER_NR_PAGES level. This makes\nsense for the majority of users where this is also the huge page size.\nHowever, on platforms like ia64 where the huge page size is runtime\nconfigurable it is desirable to group at a lower order. On x86_64 and\noccasionally on x86, the hugepage size may not always be MAX_ORDER_NR_PAGES.\n\nThis patch groups pages together based on the value of HUGETLB_PAGE_ORDER. It\nuses a compile-time constant if possible and a variable where the huge page\nsize is runtime configurable.\n\nIt is assumed that grouping should be done at the lowest sensible order and\nthat the user would not want to override this. If this is not true,\npage_block order could be forced to a variable initialised via a boot-time\nkernel parameter.\n\nOne potential issue with this patch is that IA64 now parses hugepagesz with\nearly_param() instead of __setup(). __setup() is called after the memory\nallocator has been initialised and the pageblock bitmaps already setup. In\ntests on one IA64 there did not seem to be any problem with using\nearly_param() and in fact may be more correct as it guarantees the parameter\nis handled before the parsing of hugepages\u003d.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nAcked-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "954ffcb35f5aca428661d29b96c4eee82b3c19cd", "tree": "2dd8aaf26a8ae81b461b6d5d824ae8744690e483", "parents": [ "97ee052461446526e1de7236497e6f1b1ffedf8c" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Oct 16 01:25:44 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "flush icache before set_pte() on ia64: flush icache at set_pte\n\nCurrent ia64 kernel flushes icache by lazy_mmu_prot_update() *after*\nset_pte(). This is too late. This patch removes lazy_mmu_prot_update and\nadd modfied set_pte() for flushing if necessary.\n\nThis patch flush icache of a page when\n\tnew pte has exec bit.\n\t\u0026\u0026 new pte has present bit\n\t\u0026\u0026 new pte is user\u0027s page.\n\t\u0026\u0026 (old *ptep is not present\n || new pte\u0027s pfn is not same to old *ptep\u0027s ptn)\n\t\u0026\u0026 new pte\u0027s page has no Pg_arch_1 bit.\n\t Pg_arch_1 is set when a page is cache consistent.\n\nI think this condition checks are much easier to understand than considering\n\"Where sync_icache_dcache() should be inserted ?\".\n\npte_user() for ia64 was removed by http://lkml.org/lkml/2007/6/12/67 as\nclean-up. So, I added it again.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nAcked-by: David S. Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "dcca2bde4f86a14d3291660bede8f1844fe2b3df", "tree": "6beef48bb4eb715e091c7db87953328314471886", "parents": [ "1cd7daa51baf0934882bf24a7ae378ec75df665e" ], "author": { "name": "Will Schmidt", "email": "will_schmidt@vnet.ibm.com", "time": "Tue Oct 16 01:24:18 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:52 2007 -0700" }, "message": "During VM oom condition, kill all threads in process group\n\nWe have had complaints where a threaded application is left in a bad state\nafter one of it\u0027s threads is killed when we hit a VM: out_of_memory\ncondition.\n\nKilling just one of the process threads can leave the application in a bad\nstate, whereas killing the entire process group would allow for the\napplication to restart, or be otherwise handled, and makes it very obvious\nthat something has gone wrong.\n\nThis change allows the entire process group to be taken down, rather\nthan just the one thread.\n\nSigned-off-by: Will Schmidt \u003cwill_schmidt@vnet.ibm.com\u003e\nCc: Richard Henderson \u003crth@twiddle.net\u003e\nCc: Ivan Kokshaysky \u003cink@jurassic.park.msu.ru\u003e\nCc: Russell King \u003crmk@arm.linux.org.uk\u003e\nCc: Ian Molton \u003cspyro@f2s.com\u003e\nCc: Haavard Skinnemoen \u003chskinnemoen@atmel.com\u003e\nCc: Mikael Starvik \u003cstarvik@axis.com\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Hirokazu Takata \u003ctakata@linux-m32r.org\u003e\nCc: Geert Uytterhoeven \u003cgeert@linux-m68k.org\u003e\nCc: Roman Zippel \u003czippel@linux-m68k.org\u003e\nCc: Ralf Baechle \u003cralf@linux-mips.org\u003e\nCc: Kyle McMartin \u003ckyle@mcmartin.ca\u003e\nCc: Matthew Wilcox \u003cwilly@debian.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Heiko Carstens \u003cheiko.carstens@de.ibm.com\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: Kazumoto Kojima \u003ckkojima@rr.iij4u.or.jp\u003e\nCc: Richard Curnow \u003crc@rc0.org.uk\u003e\nCc: William Lee Irwin III \u003cwli@holomorphy.com\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nCc: Chris Zankel \u003cchris@zankel.net\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ef229c5a5e7701ab08a6a06258f415b150348bcc", "tree": "606a128b3408ca39b95e1bdd93ad17dd2a9d9f33", "parents": [ "0889eba5b38f66d7d892a167d88284daddd3d43b" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:24:15 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:51 2007 -0700" }, "message": "IA64: SPARSEMEM_VMEMMAP 16K page size support\n\nEquip IA64 sparsemem with a virtual memmap. This is similar to the existing\nCONFIG_VIRTUAL_MEM_MAP functionality for DISCONTIGMEM. It uses a PAGE_SIZE\nmapping.\n\nThis is provided as a minimally intrusive solution. We split the 128TB\nVMALLOC area into two 64TB areas and use one for the virtual memmap.\n\nThis should replace CONFIG_VIRTUAL_MEM_MAP long term.\n\n[apw@shadowen.org: convert to new helper based initialisation]\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nAcked-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ea3c4b126ad63bd782c7bb5266bb4fd88e203169", "tree": "1b1dedd3ee501c165910389aea9082fb96a9e8f4", "parents": [ "a5229e6b3fb77ef92ff585e17ba4aa8a3e945727", "7b3166dbc3df5b72f2ba4ea130f4461e318a3838" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 04 00:43:57 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 04 00:43:57 2007 -0700" }, "message": "Merge branch \u0027release\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6\n" }, { "commit": "99a19cf1c0eb22bad83fff060f08330ee9e029e2", "tree": "a4e6726edfbcf9fcb89e9ebd8ebdcae53f26d48b", "parents": [ "6e9de18120988388cdae5097c09e774416d58745" ], "author": { "name": "Prarit Bhargava", "email": "prarit@redhat.com", "time": "Wed Aug 22 14:34:38 2007 -0400" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Sat Sep 01 02:50:21 2007 -0700" }, "message": "[IA64] Stop bogus NMI \u0026 softlockup warnings in ia64 show_mem\n\nWhen dumping memory via sysrq-m it is possible to take a bogus NMI watchdog\nor softlockup watchdog because the dump can take a long time on big memory\nsystems.\n\nOccasionally tickle the watchdog when doing the dump.\n\nSigned-off-by: Prarit Bhargava \u003cprarit@redhat.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "dec4ad86c2fbea062e9ef9caa6d6e79f7c5e0b12", "tree": "9882d3b1f59fb293cf0f70afc80bdc7bb1e0021e", "parents": [ "4a58448b0a375f7198de34dd0d3e2881afeaf025" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Thu Aug 30 23:56:40 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Aug 31 01:42:23 2007 -0700" }, "message": "hugepage: fix broken check for offset alignment in hugepage mappings\n\nFor hugepage mappings, the file offset, like the address and size, needs to\nbe aligned to the size of a hugepage.\n\nIn commit 68589bc353037f233fe510ad9ff432338c95db66, the check for this was\nmoved into prepare_hugepage_range() along with the address and size checks.\n But since BenH\u0027s rework of the get_unmapped_area() paths leading up to\ncommit 4b1d89290b62bb2db476c94c82cf7442aab440c8, prepare_hugepage_range()\nis only called for MAP_FIXED mappings, not for other mappings. This means\nwe\u0027re no longer ever checking for an aligned offset - I\u0027ve confirmed that\nmmap() will (apparently) succeed with a misaligned offset on both powerpc\nand i386 at least.\n\nThis patch restores the check, removing it from prepare_hugepage_range()\nand putting it back into hugetlbfs_file_mmap(). I\u0027m putting it there,\nrather than in the get_unmapped_area() path so it only needs to go in one\nplace, than separately in the half-dozen or so arch-specific\nimplementations of hugetlb_get_unmapped_area().\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nCc: Adam Litke \u003cagl@us.ibm.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e8c59c0cf9c91dccfb6367c306d753500d5a0150", "tree": "db4a13d5f5f88e2cc2da56fb4e8a3d6d6ea3ba4e", "parents": [ "182fdd225de8fc3b1b721ae944fc41146a0bd812" ], "author": { "name": "Andrew Burgess", "email": "andrew@transitive.com", "time": "Thu Aug 16 10:30:46 2007 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Aug 16 10:30:46 2007 -0700" }, "message": "[IA64] Failure to grow RBS\n\nThere is a bug in the ia64_do_page_fault code that can cause a failure\nto grow the register backing store, or any mapping that is marked as\nVM_GROWSUP if the mapping is the highest mapped area of memory.\n\nWhen the address accessed is below the first mapping the previous mapping\nis returned as NULL, and this case is handled. However, when the address\naccessed is above the highest mapping the vma returned is NULL, this\ncase is not handled correctly, and it fails to spot that this access\nmight require an existing mapping to grow upwards.\n\nSigned-off-by: Andrew Burgess \u003candrew@transitive.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "83c54070ee1a2d05c89793884bea1a03f2851ed4", "tree": "dc732f5a9b93fb7004ed23f551bd98b77cc580e0", "parents": [ "d0217ac04ca6591841e5665f518e38064f4e65bd" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Thu Jul 19 01:47:05 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Jul 19 10:04:41 2007 -0700" }, "message": "mm: fault feedback #2\n\nThis patch completes Linus\u0027s wish that the fault return codes be made into\nbit flags, which I agree makes everything nicer. This requires requires\nall handle_mm_fault callers to be modified (possibly the modifications\nshould go further and do things like fault accounting in handle_mm_fault --\nhowever that would be for another patch).\n\n[akpm@linux-foundation.org: fix alpha build]\n[akpm@linux-foundation.org: fix s390 build]\n[akpm@linux-foundation.org: fix sparc build]\n[akpm@linux-foundation.org: fix sparc64 build]\n[akpm@linux-foundation.org: fix ia64 build]\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Richard Henderson \u003crth@twiddle.net\u003e\nCc: Ivan Kokshaysky \u003cink@jurassic.park.msu.ru\u003e\nCc: Russell King \u003crmk@arm.linux.org.uk\u003e\nCc: Ian Molton \u003cspyro@f2s.com\u003e\nCc: Bryan Wu \u003cbryan.wu@analog.com\u003e\nCc: Mikael Starvik \u003cstarvik@axis.com\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc: Yoshinori Sato \u003cysato@users.sourceforge.jp\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Hirokazu Takata \u003ctakata@linux-m32r.org\u003e\nCc: Geert Uytterhoeven \u003cgeert@linux-m68k.org\u003e\nCc: Roman Zippel \u003czippel@linux-m68k.org\u003e\nCc: Greg Ungerer \u003cgerg@uclinux.org\u003e\nCc: Matthew Wilcox \u003cwilly@debian.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Heiko Carstens \u003cheiko.carstens@de.ibm.com\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: Kazumoto Kojima \u003ckkojima@rr.iij4u.or.jp\u003e\nCc: Richard Curnow \u003crc@rc0.org.uk\u003e\nCc: William Lee Irwin III \u003cwli@holomorphy.com\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nCc: Jeff Dike \u003cjdike@addtoit.com\u003e\nCc: Paolo \u0027Blaisorblade\u0027 Giarrusso \u003cblaisorblade@yahoo.it\u003e\nCc: Miles Bader \u003cuclinux-v850@lsi.nec.co.jp\u003e\nCc: Chris Zankel \u003cchris@zankel.net\u003e\nAcked-by: Kyle McMartin \u003ckyle@mcmartin.ca\u003e\nAcked-by: Haavard Skinnemoen \u003chskinnemoen@atmel.com\u003e\nAcked-by: Ralf Baechle \u003cralf@linux-mips.org\u003e\nAcked-by: Andi Kleen \u003cak@muc.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\n[ Still apparently needs some ARM and PPC loving - Linus ]\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "256a7e097ba3d1179867b4c9aba1b75fb32d44f2", "tree": "4d2a3095ddf1d95c816927554e859aab0c92aa13", "parents": [ "012b7105cc816fb797eb1c161cdfc0052b5c3f53" ], "author": { "name": "Jes Sorensen", "email": "jes@sgi.com", "time": "Wed Jul 11 17:26:30 2007 +0200" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Wed Jul 11 11:40:42 2007 -0700" }, "message": "[IA64] silence GCC ia64 unused variable warnings\n\nTell GCC to stop spewing out unnecessary warnings for unused variables\npassed to functions as pointers for ia64 files.\n\nSigned-off-by: Jes Sorensen \u003cjes@sgi.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "9be26f4c4b138c425598bd3cc50411bd87fce287", "tree": "9517030267a1bd3be5f5e0d7d08178f283f031e4", "parents": [ "189548642c5962e60c3667bdb3a703fe0bed12a6" ], "author": { "name": "vignesh babu", "email": "vignesh.babu@wipro.com", "time": "Thu Jun 07 15:27:46 2007 +0530" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Jun 26 13:32:59 2007 -0700" }, "message": "[IA64] is_power_of_2-ia64/mm/hugetlbpage.c\n\nReplacing (n \u0026 (n-1)) in the context of power of 2 checks\nwith is_power_of_2\n\nSigned-off-by: vignesh babu \u003cvignesh.babu@wipro.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "576fe0bd7e52dce7afb6b9b2450744555b2eb53a", "tree": "acf2a5f8d7f7906cfa2da9bf53a74d8e3fcd42bb", "parents": [ "17028c5c91580036eb41da2fad292965fa3b9a7d" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Wed May 16 14:52:19 2007 +0200" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Wed May 16 09:00:51 2007 -0700" }, "message": "[IA64] optimize pagefaults a little\n\nGet rid of the notifier list and call the kprobes code directly\nif compiled in. This mirrors the changes that recently went\ninto powerpc, s390 and sparc64.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "72fdbdce3d52282f8ea95f512e871791256754e6", "tree": "b7d544875c5d89e10859f3e5dc97e2e064a00e54", "parents": [ "0a3fd051c7036ef71b58863f8e5da7c3dabd9d3f" ], "author": { "name": "Simon Arlott", "email": "simon@fire.lp0.eu", "time": "Fri May 11 14:55:43 2007 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Fri May 11 14:55:43 2007 -0700" }, "message": "[IA64] spelling fixes: arch/ia64/\n\nSpelling and apostrophe fixes in arch/ia64/.\n\nSigned-off-by: Simon Arlott \u003csimon@fire.lp0.eu\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "2bd62a40f63bd628c43a2f3637b252d0967659b0", "tree": "73b5dbda741421812f487ff0a9b753109fb105b4", "parents": [ "cdc7dbdfe6edac177acb32e4ca56b525d0743fe7" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Thu May 10 22:42:53 2007 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Fri May 11 09:40:00 2007 -0700" }, "message": "[IA64] Quicklist support for IA64\n\nIA64 is the origin of the quicklist implementation. So cut out the pieces\nthat are now in core code and modify the functions called.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "38cb162b7585d837083b8365da1eb32687c5164c", "tree": "e4ae15715b23b320b1a92699fac767bc766c8f0b", "parents": [ "ba7cc09c9c9e29a57045dc5bbf843ac1cfad3283", "e180583b85f4a48bd55924712c88e5d8eb182e08" ], "author": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed May 09 13:38:45 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed May 09 13:38:45 2007 -0700" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6\n\n* git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6:\n [IA64] wire up pselect, ppoll\n [IA64] Add TIF_RESTORE_SIGMASK\n [IA64] unwind did not work for processes born with CLONE_STOPPED\n [IA64] Optional method to purge the TLB on SN systems\n [IA64] SPIN_LOCK_UNLOCKED macro cleanup in arch/ia64\n [IA64-SN2][KJ] mmtimer.c-kzalloc\n [IA64] fix stack alignment for ia32 signal handlers\n [IA64] - Altix: hotplug after intr redirect can crash system\n [IA64] save and restore cpus_allowed in cpu_idle_wait\n [IA64] Removal of percpu TR cleanup in kexec code\n [IA64] Fix some section mismatch errors\n" }, { "commit": "8737d59579c5e61ea3d5da4bd63303159fd1cf7e", "tree": "afa05a729bc597e97688de3c70389fb9ade29389", "parents": [ "1cfb9c94b6525763ee0eb9551842ded093c5827f" ], "author": { "name": "Milind Arun Choudhary", "email": "milindchoudhary@gmail.com", "time": "Sun Apr 15 22:51:23 2007 +0530" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue May 08 12:00:39 2007 -0700" }, "message": "[IA64] SPIN_LOCK_UNLOCKED macro cleanup in arch/ia64\n\nSPIN_LOCK_UNLOCKED macro cleanup, use __SPIN_LOCK_UNLOCKED instead.\n\nSigned-off-by: Milind Arun Choudhary \u003cmilindchoudhary@gmail.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "e63340ae6b6205fef26b40a75673d1c9c0c8bb90", "tree": "8d3212705515edec73c3936bb9e23c71d34a7b41", "parents": [ "04c9167f91e309c9c4ea982992aa08e83b2eb42e" ], "author": { "name": "Randy Dunlap", "email": "randy.dunlap@oracle.com", "time": "Tue May 08 00:28:08 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue May 08 11:15:07 2007 -0700" }, "message": "header cleaning: don\u0027t include smp_lock.h when not used\n\nRemove includes of \u003clinux/smp_lock.h\u003e where it is not used/needed.\nSuggested by Al Viro.\n\nBuilds cleanly on x86_64, i386, alpha, ia64, powerpc, sparc,\nsparc64, and arm (all 59 defconfigs).\n\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "1eeb66a1bb973534dc3d064920a5ca683823372e", "tree": "19c22d611e6adefb352dbc107b859e4d13ba38c1", "parents": [ "e3869792990f708c97be5877499cada70d469bd3" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Tue May 08 00:27:03 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue May 08 11:15:04 2007 -0700" }, "message": "move die notifier handling to common code\n\nThis patch moves the die notifier handling to common code. Previous\nvarious architectures had exactly the same code for it. Note that the new\ncode is compiled unconditionally, this should be understood as an appel to\nthe other architecture maintainer to implement support for it aswell (aka\nsprinkling a notify_die or two in the proper place)\n\narm had a notifiy_die that did something totally different, I renamed it to\narm_notify_die as part of the patch and made it static to the file it\u0027s\ndeclared and used at. avr32 used to pass slightly less information through\nthis interface and I brought it into line with the other architectures.\n\n[akpm@linux-foundation.org: build fix]\n[akpm@linux-foundation.org: fix vmalloc_sync_all bustage]\n[bryan.wu@analog.com: fix vmalloc_sync_all in nommu]\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nCc: Russell King \u003crmk@arm.linux.org.uk\u003e\nSigned-off-by: Bryan Wu \u003cbryan.wu@analog.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a3142c8e1dd57ff48040bdb3478cff9312543dc3", "tree": "14beeb03421338b917a956e9269a2ce95e0f62cf", "parents": [ "0ceb331433e8aad9c5f441a965d7c681f8b9046f" ], "author": { "name": "Yasunori Goto", "email": "y-goto@jp.fujitsu.com", "time": "Tue May 08 00:23:07 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue May 08 11:14:57 2007 -0700" }, "message": "Fix section mismatch of memory hotplug related code.\n\nThis is to fix many section mismatches of code related to memory hotplug.\nI checked compile with memory hotplug on/off on ia64 and x86-64 box.\n\nSigned-off-by: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a989705c4cf6e6c1a339c95f9daf658b4ba88ca8", "tree": "d1925b831ec9fbae65db1b193dbad1869c43a9bc", "parents": [ "2d56d3c43cc97ae48586745556f5a5b564d61582", "d29182534c5f39ff899763d1e0982d8f33791d6f" ], "author": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon May 07 12:34:57 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon May 07 12:34:57 2007 -0700" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6\n\n* git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6:\n [IA64] update memory attribute aliasing documentation \u0026 test cases\n [IA64] fail mmaps that span areas with incompatible attributes\n [IA64] allow WB /sys/.../legacy_mem mmaps\n [IA64] make ioremap avoid unsupported attributes\n [IA64] rename ioremap variables to match i386\n [IA64] relax per-cpu TLB requirement to DTC\n [IA64] remove per-cpu ia64_phys_stacked_size_p8\n [IA64] Fix example error injection program\n [IA64] Itanium MC Error Injection Tool: pal_mc_error_inject() interface\n [IA64] Itanium MC Error Injection Tool: Makefile changes\n [IA64] Itanium MC Error Injection Tool: Driver sysfs interface\n [IA64] Itanium MC Error Injection Tool: Doc and sample application\n [IA64] Itanium MC Error Injection Tool: Kernel configuration\n" }, { "commit": "afa37394d6bfc91907b0e08c902d36d848232b99", "tree": "6b43da63c023f441a5f22bd1d767989aabb193cd", "parents": [ "5a8130f2b186ac91190d1dcea875d66d08e6a1de" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Sun May 06 14:50:09 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon May 07 12:12:56 2007 -0700" }, "message": "get_unmapped_area handles MAP_FIXED on ia64\n\nHandle MAP_FIXED in ia64 arch_get_unmapped_area and\nhugetlb_get_unmapped_area(), just call prepare_hugepage_range in the later and\nis_hugepage_only_range() in the former.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nAcked-by: William Irwin \u003cbill.irwin@oracle.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d85f33855c303acfa87fa457157cef755b6087df", "tree": "f1184a1a24b432727b0399594ede37c7539db888", "parents": [ "30520864839dc796fd314812e7036e754880b47d" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Sun May 06 14:49:39 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon May 07 12:12:53 2007 -0700" }, "message": "Make page-\u003eprivate usable in compound pages\n\nIf we add a new flag so that we can distinguish between the first page and the\ntail pages then we can avoid to use page-\u003eprivate in the first page.\npage-\u003eprivate \u003d\u003d page for the first page, so there is no real information in\nthere.\n\nFreeing up page-\u003eprivate makes the use of compound pages more transparent.\nThey become more usable like real pages. Right now we have to be careful f.e.\n if we are going beyond PAGE_SIZE allocations in the slab on i386 because we\ncan then no longer use the private field. This is one of the issues that\ncause us not to support debugging for page size slabs in SLAB.\n\nHaving page-\u003eprivate available for SLUB would allow more meta information in\nthe page struct. I can probably avoid the 16 bit ints that I have in there\nright now.\n\nAlso if page-\u003eprivate is available then a compound page may be equipped with\nbuffer heads. This may free up the way for filesystems to support larger\nblocks than page size.\n\nWe add PageTail as an alias of PageReclaim. Compound pages cannot currently\nbe reclaimed. Because of the alias one needs to check PageCompound first.\n\nThe RFC for the this approach was discussed at\nhttp://marc.info/?t\u003d117574302800001\u0026r\u003d1\u0026w\u003d2\n\n[nacc@us.ibm.com: fix hugetlbfs]\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d29182534c5f39ff899763d1e0982d8f33791d6f", "tree": "69fd6a52145b22650799493b54e8795e988a89af", "parents": [ "b643b0fdbc59cf6bbb086974b29d2571e9e9f646", "ddd83eff58888928115b3e225a46d3c686e64594" ], "author": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon Apr 30 13:56:17 2007 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon Apr 30 13:56:17 2007 -0700" }, "message": "Pull mem-attribute into release branch\n" }, { "commit": "b643b0fdbc59cf6bbb086974b29d2571e9e9f646", "tree": "59d1a1298ffc98877183a8def5c180c0f74e568b", "parents": [ "e0cc09e295f346b7921e921f385fe5213472316a", "00b65985fb2fc542b855b03fcda0d0f2bab4f442" ], "author": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon Apr 30 13:56:00 2007 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon Apr 30 13:56:00 2007 -0700" }, "message": "Pull percpu-dtc into release branch\n" }, { "commit": "9b50ffb0c0281bc5a08ccd56ae9bb84296c28f38", "tree": "85462c93df91c2fdd0c8fc31643158e9e5cf6734", "parents": [ "c4add2e537e6f60048dce8dc518254e7e605301d" ], "author": { "name": "Bjorn Helgaas", "email": "bjorn.helgaas@hp.com", "time": "Fri Mar 30 10:34:05 2007 -0600" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Fri Mar 30 09:37:41 2007 -0700" }, "message": "[IA64] make ioremap avoid unsupported attributes\n\nExample memory map (from HP sx1000 with VGA enabled):\n 0x00000 - 0x9FFFF supports only WB (cacheable) access\n 0xA0000 - 0xBFFFF supports only UC (uncacheable) access\n 0xC0000 - 0xFFFFF supports only WB (cacheable) access\n\npci_read_rom() indirectly uses ioremap(0xC0000) to read the shadow VGA option\nROM. ioremap() used to default to a 16MB or 64MB UC kernel identity mapping,\nwhich would cause an MCA when reading 0xC0000 since only WB is supported there.\n\nX uses reads the option ROM to initialize devices. A smaller test case is:\n # echo 1 \u003e /sys/bus/pci/devices/0000:aa:03.0/rom\n # cp /sys/bus/pci/devices/0000:aa:03.0/rom x\n\nTo avoid this, we can use the same ioremap_page_range() strategy that most\narchitectures use for all ioremaps. These page table mappings come out of the\nvmalloc area. On ia64, these are in region 5 (0xA... addresses) and typically\nuse 16KB or 64KB mappings instead of 16MB or 64MB mappings. The smaller\nmappings give more flexibility to use the correct attributes.\n\nSigned-off-by: Bjorn Helgaas \u003cbjorn.helgaas@hp.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "c4add2e537e6f60048dce8dc518254e7e605301d", "tree": "80558c6c5b79b82c9851b00a739d2effa870ce9a", "parents": [ "ce20269d1e97030afa476e12b99d2437e748d225" ], "author": { "name": "Bjorn Helgaas", "email": "bjorn.helgaas@hp.com", "time": "Fri Mar 30 10:33:11 2007 -0600" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Fri Mar 30 09:37:17 2007 -0700" }, "message": "[IA64] rename ioremap variables to match i386\n\nNo functional change, just use the same names as i386.\n\nSigned-off-by: Bjorn Helgaas \u003cbjorn.helgaas@hp.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "83d2cd3de48a7fb73838c45145780cfa9b1f61fd", "tree": "85d056d9a718f69c7242a8bb6cde17fc928fa4cc", "parents": [ "8a3a0ee736b9a0150c9d894f2c6cc836a62125a1" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Fri Mar 23 12:17:46 2007 +0900" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Mar 29 15:15:24 2007 -0700" }, "message": "[IA64] bugfix stack layout upside-down\n\nia64 expects following vm layout:\n\n\u003d\u003d low memory\n[register-stack grows up]\n[memory-stack grows down]\n\u003d\u003d high memory\n\nBut the code assigns the base of the register stack at the\nmaximum stack size offset from the fixed address where the\nstack *might* start. Stack randomization will result in the\nmemory stack starting at a lower address than this, and if the\nuser has set a low stack limit with \"ulimit -s\", then you can\nend up with the register stack above the memory stack (or if\nyou were very unlucky right on top of it!).\n\nFix: Calculate the base address for the register stack starting\nfrom the actual address of the memory stack.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "a3f5c338b9f30f328276739d9589beae19254936", "tree": "5c197e9c6565382a548180bdfb57ee5315d9fc60", "parents": [ "be521466feb3bb1cd89de82a2b1d080e9ebd3cb6" ], "author": { "name": "Zou Nan hai", "email": "nanhai.zou@intel.com", "time": "Tue Mar 20 13:41:57 2007 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Mar 20 13:41:57 2007 -0700" }, "message": "[IA64] min_low_pfn and max_low_pfn calculation fix\n\nWe have seen bad_pte_print when testing crashdump on an SN machine in\nrecent 2.6.20 kernel. There are tons of bad pte print (pfn \u003c max_low_pfn)\nreports when the crash kernel boots up, all those reported bad pages\nare inside initmem range; That is because if the crash kernel code and\ndata happens to be at the beginning of the 1st node. build_node_maps in\ndiscontig.c will bypass reserved regions with filter_rsvd_memory. Since\nmin_low_pfn is calculated in build_node_map, so in this case, min_low_pfn\nwill be greater than kernel code and data.\n\nBecause pages inside initmem are freed and reused later, we saw\npfn_valid check fail on those pages.\n\nI think this theoretically happen on a normal kernel. When I check\nmin_low_pfn and max_low_pfn calculation in contig.c and discontig.c.\nI found more issues than this.\n\n1. min_low_pfn and max_low_pfn calculation is inconsistent between\ncontig.c and discontig.c,\nmin_low_pfn is calculated as the first page number of boot memmap in\ncontig.c (Why? Though this may work at the most of the time, I don\u0027t\nthink it is the right logic). It is calculated as the lowest physical\nmemory page number bypass reserved regions in discontig.c.\nmax_low_pfn is calculated include reserved regions in contig.c. It is\ncalculated exclude reserved regions in discontig.c.\n\n2. If kernel code and data region is happen to be at the begin or the\nend of physical memory, when min_low_pfn and max_low_pfn calculation is\nbypassed kernel code and data, pages in initmem will report bad.\n\n3. initrd is also in reserved regions, if it is at the begin or at the\nend of physical memory, kernel will refuse to reuse the memory. Because\nthe virt_addr_valid check in free_initrd_mem.\n\nSo it is better to fix and clean up those issues.\nCalculate min_low_pfn and max_low_pfn in a consistent way.\n\nSigned-off-by:\tZou Nan hai \u003cnanhai.zou@intel.com\u003e\nAcked-by: Jay Lan \u003cjlan@sgi.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "f4a570997e71b892805a1e71303d09c327af135f", "tree": "9fe577e7b97ee7365481489f1c263aa1f868e199", "parents": [ "25667d675454f2cd258c5fa798a2281af1ef2ae9" ], "author": { "name": "Horms", "email": "horms@verge.net.au", "time": "Tue Mar 06 02:34:21 2007 -0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Mar 06 14:47:54 2007 -0800" }, "message": "[IA64] point saved_max_pfn to the max_pfn of the entire system\n\nMake saved_max_pfn point to max_pfn of entire system.\n\nWithout this patch is so that vmcore is zero length on ia64. This is\nbecause saved_max_pfn was wrongly being set to the max_pfn of the crash\nkernel\u0027s address space, rather than the max_pfg on the physical memory of\nthe machine - the whole purpose of vmcore is to access physical memory that\nis not part of the crash kernel\u0027s addresss space.\n\nSigned-off-by: Simon Horman \u003chorms@verge.net.au\u003e\nSigned-off-by: Zou Nan hai \u003cnanhai.zou@intel.com\u003e\nSort-Of-Acked-By: Jay Lan \u003cjlan@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "c376222960ae91d5ffb9197ee36771aaed1d9f90", "tree": "7f431c42529fec77433d33490bd9f2a8c47ba091", "parents": [ "1b135431abf5ea92e61bf4e91d93726c7b96da5f" ], "author": { "name": "Robert P. J. Day", "email": "rpjday@mindspring.com", "time": "Sat Feb 10 01:45:03 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Sun Feb 11 10:51:27 2007 -0800" }, "message": "[PATCH] Transform kmem_cache_alloc()+memset(0) -\u003e kmem_cache_zalloc().\n\nReplace appropriate pairs of \"kmem_cache_alloc()\" + \"memset(0)\" with the\ncorresponding \"kmem_cache_zalloc()\" call.\n\nSigned-off-by: Robert P. J. Day \u003crpjday@mindspring.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Andi Kleen \u003cak@muc.de\u003e\nCc: Roland McGrath \u003croland@redhat.com\u003e\nCc: James Bottomley \u003cJames.Bottomley@steeleye.com\u003e\nCc: Greg KH \u003cgreg@kroah.com\u003e\nAcked-by: Joel Becker \u003cJoel.Becker@oracle.com\u003e\nCc: Steven Whitehouse \u003cswhiteho@redhat.com\u003e\nCc: Jan Kara \u003cjack@ucw.cz\u003e\nCc: Michael Halcrow \u003cmhalcrow@us.ibm.com\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nCc: Stephen Smalley \u003csds@tycho.nsa.gov\u003e\nCc: James Morris \u003cjmorris@namei.org\u003e\nCc: Chris Wright \u003cchrisw@sous-sol.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "09ae1f585e9def652cdb1d0484611d4f4dc2d5fd", "tree": "d759e739ae0a8ba72f20938d5ac8c19dac76acba", "parents": [ "4b51d66989218aad731a721b5b28c79bf5388c09" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Sat Feb 10 01:43:11 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Sun Feb 11 10:51:18 2007 -0800" }, "message": "[PATCH] optional ZONE_DMA: optional ZONE_DMA for ia64\n\nZONE_DMA less operation for IA64 SGI platform\n\nDisable ZONE_DMA for SGI SN2. All memory is addressable by all devices and we\ndo not need any special memory pool.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "9195481d2f869a2707a272057f3f8664fd277534", "tree": "995f43619af48009b616bf5a7ce4a6bffd75de79", "parents": [ "96177299416dbccb73b54e6b344260154a445375" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Sat Feb 10 01:43:04 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Sun Feb 11 10:51:18 2007 -0800" }, "message": "[PATCH] Drop nr_free_pages_pgdat()\n\nFunction is unnecessary now. We can use the summing features of the ZVCs to\nget the values we need.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "00b65985fb2fc542b855b03fcda0d0f2bab4f442", "tree": "dc9372aced10184945862b9adf0848da3e0e946f", "parents": [ "a0776ec8e97bf109e7d973d09fc3e1814eb32bfb" ], "author": { "name": "Chen, Kenneth W", "email": "kenneth.w.chen@intel.com", "time": "Fri Oct 13 10:08:13 2006 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Feb 06 15:04:48 2007 -0800" }, "message": "[IA64] relax per-cpu TLB requirement to DTC\n\nInstead of pinning per-cpu TLB into a DTR, use DTC. This will free up\none TLB entry for application, or even kernel if access pattern to\nper-cpu data area has high temporal locality.\n\nSince per-cpu is mapped at the top of region 7 address, we just need to\nadd special case in alt_dtlb_miss. The physical address of per-cpu data\nis already conveniently stored in IA64_KR(PER_CPU_DATA). Latency for\nalt_dtlb_miss is not affected as we can hide all the latency. It was\nmeasured that alt_dtlb_miss handler has 23 cycles latency before and\nafter the patch.\n\nThe performance effect is massive for applications that put lots of tlb\npressure on CPU. Workload environment like database online transaction\nprocessing or application uses tera-byte of memory would benefit the most.\nMeasurement with industry standard database benchmark shown an upward\nof 1.6% gain. While smaller workloads like cpu, java also showing small\nimprovement.\n\nSigned-off-by: Ken Chen \u003ckenneth.w.chen@intel.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "cde14bbfb3aa79b479db35bd29e6c083513d8614", "tree": "68b2d66d1eee3067051f4a6e4df8ace461bf440f", "parents": [ "86afa9eb88af2248bcc91d5b3568c63fdea65d6c" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Mon Feb 05 18:46:40 2007 -0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon Feb 05 18:46:40 2007 -0800" }, "message": "[IA64] swiotlb bug fixes\n\nThis patch fixes\n- marking I-cache clean of pages DMAed to now only done for IA64\n- broken multiple inclusion in include/asm-x86_64/swiotlb.h\n- missing call to mark_clean in swiotlb_sync_sg()\n- a (perhaps only theoretical) issue in swiotlb_dma_supported() when\nio_tlb_end is exactly at the end of memory\n\nSigned-off-by: Jan Beulich \u003cjbeulich@novell.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "524fd988bb83153ddc9cfea867129eb6efb7ac23", "tree": "ccb7944903d7f62b750c8e8729b28281ef7af094", "parents": [ "f1c0afa2e8802c01cf82c915e2bb3cb2a81570d4" ], "author": { "name": "Bob Picco", "email": "bob.picco@hp.com", "time": "Mon Feb 05 16:20:08 2007 -0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon Feb 05 16:54:11 2007 -0800" }, "message": "[IA64] clean up sparsemem memory_present call\n\nEliminate arch specific memory_present call ia64 NUMA by utilizing\nsparse_memory_present_with_active_regions.\n\nAcked-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Bob Picco \u003cbob.picco@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "f1c0afa2e8802c01cf82c915e2bb3cb2a81570d4", "tree": "af867a8c57b025b4e149157c885a968b9126339d", "parents": [ "671496affdb5228786896864c3f900f66563e8c1" ], "author": { "name": "George Beshers", "email": "gbeshers@sgi.com", "time": "Mon Feb 05 16:20:04 2007 -0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon Feb 05 16:51:59 2007 -0800" }, "message": "[IA64] show_mem() for IA64 sparsemem NUMA\n\nOn the ia64 architecture only this patch upgrades show_mem() for sparse\nmemory to be the same as it was for discontig memory. It has been shown to\nwork on NUMA and flatmem architectures.\n\nSigned-off-by: George Beshers \u003cgbeshers@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "139b830477ccdca21b68c40f9a83ec327e65eb56", "tree": "0aab2140315579525dfef89189b9bea5033af2ba", "parents": [ "d1598e05faa11d9f04e0a226122dd57674fb1dab" ], "author": { "name": "Bob Picco", "email": "bob.picco@hp.com", "time": "Tue Jan 30 02:11:09 2007 -0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon Feb 05 15:07:47 2007 -0800" }, "message": "[IA64] register memory ranges in a consistent manner\n\nWhile pursuing and unrelated issue with 64Mb granules I noticed a problem\nrelated to inconsistent use of add_active_range. There doesn\u0027t appear any\nreason to me why FLATMEM versus DISCONTIG_MEM should register memory to\nadd_active_range with different code. So I\u0027ve changed the code into a\ncommon implementation.\n\nThe other subtle issue fixed by this patch was calling add_active_range in\ncount_node_pages before granule aligning is performed. We were lucky with\n16MB granules but not so with 64MB granules. count_node_pages has reserved\nregions filtered out and as a consequence linked kernel text and data\naren\u0027t covered by calls to count_node_pages. So linked kernel regions\nwasn\u0027t reported to add_active_regions. This resulted in free_initmem\ncausing numerous bad_page reports. This won\u0027t occur with this patch\nbecause now all known memory regions are reported by\nregister_active_ranges.\n\nAcked-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Bob Picco \u003cbob.picco@hp.com\u003e\nAcked-by: Simon Horman \u003chorms@verge.net.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "233c2f99d6605343fa4a4c68560a4f74882b2693", "tree": "9a7b02a48936e2048b36017af384e3191f0e550e", "parents": [ "475c63bded322545d1e9ccc5930c8903d2c97c4c" ], "author": { "name": "Horms", "email": "horms@verge.net.au", "time": "Mon Feb 05 11:05:29 2007 +0900" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon Feb 05 11:30:25 2007 -0800" }, "message": "[IA64] kexec: typo in the saved_max_pfn description in contig.c\n\nFix a typo in the saved_max_pfn description in contig.c\n\nSigned-off-by: Simon Horman \u003chorms@verge.net.au\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "475c63bded322545d1e9ccc5930c8903d2c97c4c", "tree": "b7f254c1b94a61283a50cefe52f571d97493a37e", "parents": [ "bcb9b99d1fb6a1cbe592f131dc95450d2f18c91f" ], "author": { "name": "Horms", "email": "horms@verge.net.au", "time": "Mon Feb 05 10:59:03 2007 +0900" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon Feb 05 11:29:33 2007 -0800" }, "message": "[IA64] Zero size /proc/vmcore on ia64\n\nSet saved_max_pfn when discontig memory is in use.\n\nThis sets up saved_max_pfn when disctontig memory is in use.\nThis mirrors the code for contig memory.\n\nThis patch does not entirely solve the problem of making vmcore work,\nhowever it does appear to be neccessary. Please consider applying.\n\nSigned-off-by: Simon Horman \u003chorms@verge.net.au\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "a2f3aa02576632cdb60bd3de1f4bf55e9ac65604", "tree": "2b9b73675de73866fbd219fab5bf2d804e6817b1", "parents": [ "47a4d5be7c50b2e9b905abbe2b97dc87051c5a44" ], "author": { "name": "Dave Hansen", "email": "haveblue@us.ibm.com", "time": "Wed Jan 10 23:15:30 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Thu Jan 11 18:18:20 2007 -0800" }, "message": "[PATCH] Fix sparsemem on Cell\n\nFix an oops experienced on the Cell architecture when init-time functions,\nearly_*(), are called at runtime. It alters the call paths to make sure\nthat the callers explicitly say whether the call is being made on behalf of\na hotplug even, or happening at boot-time.\n\nIt has been compile tested on ppc64, ia64, s390, i386 and x86_64.\n\nAcked-by: Arnd Bergmann \u003carndb@de.ibm.com\u003e\nSigned-off-by: Dave Hansen \u003chaveblue@us.ibm.com\u003e\nCc: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nAcked-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nCc: Christoph Lameter \u003cclameter@engr.sgi.com\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nAcked-by: Heiko Carstens \u003cheiko.carstens@de.ibm.com\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "8b9c106856d92c8266697328b148d115538b59ce", "tree": "a8c68bb48290d97ae942ca63efeb94856fb892ae", "parents": [ "f889a26a703b03c774849685583cec7746738f3c" ], "author": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Dec 12 11:18:55 2006 -0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Dec 12 11:18:55 2006 -0800" }, "message": "[IA64] fix arch/ia64/mm/contig.c:235: warning: unused variable `nid\u0027\n\nThis warning only shows up with CONFIG_VIRTUAL_MEM_MAP\u003dy and\nCONFIG_FLATMEM\u003dy.\n\nThere is only one caller left for register_active_ranges() from the\ncontig.c code ... so it doesn\u0027t need to pick up the node number, the\nnode number is always zero.\n\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "45a98fc622ae700eed34eb2be00743910d50dbe1", "tree": "e5e5279c25582a7d26c37af189330318fe0f42dd", "parents": [ "adf142e379bd20ad906a7e36f722eaabb3b44b0c" ], "author": { "name": "Horms", "email": "horms@verge.net.au", "time": "Tue Dec 12 17:49:03 2006 +0900" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Dec 12 10:11:00 2006 -0800" }, "message": "[IA64] CONFIG_KEXEC/CONFIG_CRASH_DUMP permutations\n\nActually, on reflection I think that there is a good case for\nkeeping the options separate. I am thinking particularly of people\nwho want a very small crashdump kernel and thus don\u0027t want to compile\nin kexec.\n\nThe patch below should fix things up so that all valid combinations of\nKEXEC, CRASH_DUMP and VMCORE compile cleanly - VMCORE depends on\nCRASH_DUMP which is why I said valid combinations. In a nutshell\nit just untangles unrelated code and switches around a few defines.\n\nPlease note that it creats a new file, arch/ia64/kernel/crash_dump.c\nThis is in keeping with the i386 implementation.\n\nSigned-off-by: Simon Horman \u003chorms@verge.net.au\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "e94b1766097d53e6f3ccfb36c8baa562ffeda3fc", "tree": "93fa0a8ab84976d4e89c50768ca8b8878d642a0d", "parents": [ "54e6ecb23951b195d02433a741c7f7cb0b796c78" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Wed Dec 06 20:33:17 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Thu Dec 07 08:39:24 2006 -0800" }, "message": "[PATCH] slab: remove SLAB_KERNEL\n\nSLAB_KERNEL is an alias of GFP_KERNEL.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "39dde65c9940c97fcd178a3d2b1c57ed8b7b68aa", "tree": "750818d68ac7381f80fec31491e1d1c78df4b9f6", "parents": [ "e1dbeda60a7ea9e82a908d93c07308d104d50d79" ], "author": { "name": "Chen, Kenneth W", "email": "kenneth.w.chen@intel.com", "time": "Wed Dec 06 20:32:03 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Thu Dec 07 08:39:21 2006 -0800" }, "message": "[PATCH] shared page table for hugetlb page\n\nFollowing up with the work on shared page table done by Dave McCracken. This\nset of patch target shared page table for hugetlb memory only.\n\nThe shared page table is particular useful in the situation of large number of\nindependent processes sharing large shared memory segments. In the normal\npage case, the amount of memory saved from process\u0027 page table is quite\nsignificant. For hugetlb, the saving on page table memory is not the primary\nobjective (as hugetlb itself already cuts down page table overhead\nsignificantly), instead, the purpose of using shared page table on hugetlb is\nto allow faster TLB refill and smaller cache pollution upon TLB miss.\n\nWith PT sharing, pte entries are shared among hundreds of processes, the cache\nconsumption used by all the page table is smaller and in return, application\ngets much higher cache hit ratio. One other effect is that cache hit ratio\nwith hardware page walker hitting on pte in cache will be higher and this\nhelps to reduce tlb miss latency. These two effects contribute to higher\napplication performance.\n\nSigned-off-by: Ken Chen \u003ckenneth.w.chen@intel.com\u003e\nAcked-by: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Dave McCracken \u003cdmccr@us.ibm.com\u003e\nCc: William Lee Irwin III \u003cwli@holomorphy.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nCc: Adam Litke \u003cagl@us.ibm.com\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "68589bc353037f233fe510ad9ff432338c95db66", "tree": "dedc58ff66134f54796642917e2a2a26ac6802b0", "parents": [ "69ae9e3ee4ce99140a7db424bebf55d8d180da2f" ], "author": { "name": "Hugh Dickins", "email": "hugh@veritas.com", "time": "Tue Nov 14 02:03:32 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Tue Nov 14 09:09:27 2006 -0800" }, "message": "[PATCH] hugetlb: prepare_hugepage_range check offset too\n\n(David:)\n\nIf hugetlbfs_file_mmap() returns a failure to do_mmap_pgoff() - for example,\nbecause the given file offset is not hugepage aligned - then do_mmap_pgoff\nwill go to the unmap_and_free_vma backout path.\n\nBut at this stage the vma hasn\u0027t been marked as hugepage, and the backout path\nwill call unmap_region() on it. That will eventually call down to the\nnon-hugepage version of unmap_page_range(). On ppc64, at least, that will\ncause serious problems if there are any existing hugepage pagetable entries in\nthe vicinity - for example if there are any other hugepage mappings under the\nsame PUD. unmap_page_range() will trigger a bad_pud() on the hugepage pud\nentries. I suspect this will also cause bad problems on ia64, though I don\u0027t\nhave a machine to test it on.\n\n(Hugh:)\n\nprepare_hugepage_range() should check file offset alignment when it checks\nvirtual address and length, to stop MAP_FIXED with a bad huge offset from\nunmapping before it fails further down. PowerPC should apply the same\nprepare_hugepage_range alignment checks as ia64 and all the others do.\n\nThen none of the alignment checks in hugetlbfs_file_mmap are required (nor\nis the check for too small a mapping); but even so, move up setting of\nVM_HUGETLB and add a comment to warn of what David Gibson discovered - if\nhugetlbfs_file_mmap fails before setting it, do_mmap_pgoff\u0027s unmap_region\nwhen unwinding from error will go the non-huge way, which may cause bad\nbehaviour on architectures (powerpc and ia64) which segregate their huge\nmappings into a separate region of the address space.\n\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nAcked-by: Adam Litke \u003cagl@us.ibm.com\u003e\nAcked-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "6391af174ad75f72e92043c1dd8302660a2fec58", "tree": "43dfb9a1acfbdabb820180834d4e8efdcfcbe46e", "parents": [ "4e0fadfcf62e252d2b14de0e0927eb2830c0c28c" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Wed Oct 11 01:20:39 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Oct 11 11:14:14 2006 -0700" }, "message": "[PATCH] mm: use symbolic names instead of indices for zone initialisation\n\nArch-independent zone-sizing is using indices instead of symbolic names to\noffset within an array related to zones (max_zone_pfns). The unintended\nimpact is that ZONE_DMA and ZONE_NORMAL is initialised on powerpc instead\nof ZONE_DMA and ZONE_HIGHMEM when CONFIG_HIGHMEM is set. As a result, the\nthe machine fails to boot but will boot with CONFIG_HIGHMEM turned off.\n\nThe following patch properly initialises the max_zone_pfns[] array and uses\nsymbolic names instead of indices in each architecture using\narch-independent zone-sizing. Two users have successfully booted their\npowerpcs with it (one an ibook G4). It has also been boot tested on x86,\nx86_64, ppc64 and ia64. Please merge for 2.6.19-rc2.\n\nCredit to Benjamin Herrenschmidt for identifying the bug and rolling the\nfirst fix. Additional credit to Johannes Berg and Andreas Schwab for\nreporting the problem and testing on powerpc.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "8c2676a5870ab15cbeea9f826266bc946fe3cc26", "tree": "0df06fce24312d7f2d1120d984dd7ae258cb40ef", "parents": [ "4942e998b40b8f6080930ec16442444e9930aee5" ], "author": { "name": "Keith Mannthey", "email": "kmannth@us.ibm.com", "time": "Sat Sep 30 23:27:07 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Oct 01 00:39:18 2006 -0700" }, "message": "[PATCH] hot-add-mem x86_64: memory_add_physaddr_to_nid node fixup\n\nIn cases where the acpi memory-add event does not containe the pxm (node)\ninfomation allow the driver to look up node info based on the address. The\nacpi_get_node call returns -1 if it can\u0027t decode the pxm info, this causes\nadd_memory to panic. acpi_get_node would have to decode the resource from the\nhandle (a lenghty proposition). This seems to be the cleanist point to\ninterject the hook.\n\n[kamezawa.hiroyu@jp.fujitsu.com: build fixes]\n[y-goto@jp.fujitsu.com: build fixes]\nSigned-off-by: Keith Mannthey \u003ckmannth@us.ibm.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Andi Kleen \u003cak@muc.de\u003e\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "f400e198b2ed26ce55b22a1412ded0896e7516ac", "tree": "a3d78bfc1c20635e199fe0fe85aaa1d8792acc58", "parents": [ "959ed340f4867fda7684340625f60e211c2296d6" ], "author": { "name": "Sukadev Bhattiprolu", "email": "sukadev@us.ibm.com", "time": "Fri Sep 29 02:00:07 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Sep 29 09:18:12 2006 -0700" }, "message": "[PATCH] pidspace: is_init()\n\nThis is an updated version of Eric Biederman\u0027s is_init() patch.\n(http://lkml.org/lkml/2006/2/6/280). It applies cleanly to 2.6.18-rc3 and\nreplaces a few more instances of -\u003epid \u003d\u003d 1 with is_init().\n\nFurther, is_init() checks pid and thus removes dependency on Eric\u0027s other\npatches for now.\n\nEric\u0027s original description:\n\n\tThere are a lot of places in the kernel where we test for init\n\tbecause we give it special properties. Most significantly init\n\tmust not die. This results in code all over the kernel test\n\t-\u003epid \u003d\u003d 1.\n\n\tIntroduce is_init to capture this case.\n\n\tWith multiple pid spaces for all of the cases affected we are\n\tlooking for only the first process on the system, not some other\n\tprocess that has pid \u003d\u003d 1.\n\nSigned-off-by: Eric W. Biederman \u003cebiederm@xmission.com\u003e\nSigned-off-by: Sukadev Bhattiprolu \u003csukadev@us.ibm.com\u003e\nCc: Dave Hansen \u003chaveblue@us.ibm.com\u003e\nCc: Serge Hallyn \u003cserue@us.ibm.com\u003e\nCc: Cedric Le Goater \u003cclg@fr.ibm.com\u003e\nCc: \u003clxc-devel@lists.sourceforge.net\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "df67b3daea602728b51325a4debaeeb912ee51d1", "tree": "22181d324d541a27b037673cf1315827900e998c", "parents": [ "15a67dd8ccf696392176c95a08234a8b8ee59005" ], "author": { "name": "Jason Baron", "email": "jbaron@redhat.com", "time": "Fri Sep 29 01:58:58 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Sep 29 09:18:05 2006 -0700" }, "message": "[PATCH] make PROT_WRITE imply PROT_READ\n\nMake PROT_WRITE imply PROT_READ for a number of architectures which don\u0027t\nsupport write only in hardware.\n\nWhile looking at this, I noticed that some architectures which do not\nsupport write only mappings already take the exact same approach. For\nexample, in arch/alpha/mm/fault.c:\n\n\"\n if (cause \u003c 0) {\n if (!(vma-\u003evm_flags \u0026 VM_EXEC))\n goto bad_area;\n } else if (!cause) {\n /* Allow reads even for write-only mappings */\n if (!(vma-\u003evm_flags \u0026 (VM_READ | VM_WRITE)))\n goto bad_area;\n } else {\n if (!(vma-\u003evm_flags \u0026 VM_WRITE))\n goto bad_area;\n }\n\"\n\nThus, this patch brings other architectures which do not support write only\nmappings in-line and consistent with the rest. I\u0027ve verified the patch on\nia64, x86_64 and x86.\n\nAdditional discussion:\n\nSeveral architectures, including x86, can not support write-only mappings.\nThe pte for x86 reserves a single bit for protection and its two states are\nread only or read/write. Thus, write only is not supported in h/w.\n\nCurrently, if i \u0027mmap\u0027 a page write-only, the first read attempt on that page\ncreates a page fault and will SEGV. That check is enforced in\narch/blah/mm/fault.c. However, if i first write that page it will fault in\nand the pte will be set to read/write. Thus, any subsequent reads to the page\nwill succeed. It is this inconsistency in behavior that this patch is\nattempting to address. Furthermore, if the page is swapped out, and then\nbrought back the first read will also cause a SEGV. Thus, any arbitrary read\non a page can potentially result in a SEGV.\n\nAccording to the SuSv3 spec, \"if the application requests only PROT_WRITE, the\nimplementation may also allow read access.\" Also as mentioned, some\narchtectures, such as alpha, shown above already take the approach that i am\nsuggesting.\n\nThe counter-argument to this raised by Arjan, is that the kernel is enforcing\nthe write only mapping the best it can given the h/w limitations. This is\ntrue, however Alan Cox, and myself would argue that the inconsitency in\nbehavior, that is applications can sometimes work/sometimes fails is highly\nundesireable. If you read through the thread, i think people, came to an\nagreement on the last patch i posted, as nobody has objected to it...\n\nSigned-off-by: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Russell King \u003crmk@arm.linux.org.uk\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Roman Zippel \u003czippel@linux-m68k.org\u003e\nCc: Geert Uytterhoeven \u003cgeert@linux-m68k.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nAcked-by: Andi Kleen \u003cak@muc.de\u003e\nAcked-by: Alan Cox \u003calan@lxorguk.ukuu.org.uk\u003e\nCc: Arjan van de Ven \u003carjan@linux.intel.com\u003e\nAcked-by: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: Kazumoto Kojima \u003ckkojima@rr.iij4u.or.jp\u003e\nCc: Ian Molton \u003cspyro@f2s.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "cdb8355add9b1d87ecfcb58b12879897dc1e3e36", "tree": "9af61da194aaa6c255cf17de9e324c21a35581b3", "parents": [ "b98adfccdf5f8dd34ae56a2d5adbe2c030bd4674", "df8f0ec1a413ae610899f009e25dc9777881e149" ], "author": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Sep 27 10:53:30 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Sep 27 10:53:30 2006 -0700" }, "message": "Merge branch \u0027release\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6\n\n* \u0027release\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6:\n [IA64] minor reformatting to vmlinux.lds.S\n [IA64] CMC/CPE: Reverse the order of fetching log and checking poll threshold\n [IA64] PAL calls need physical mode, stacked\n [IA64] ar.fpsr not set on MCA/INIT kernel entry\n [IA64] printing support for MCA/INIT\n [IA64] trim output of show_mem()\n [IA64] show_mem() printk levels\n [IA64] Make gp value point to Region 5 in mca handler\n Revert \"[IA64] Unwire set/get_robust_list\"\n [IA64] Implement futex primitives\n [IA64-SGI] Do not request DMA memory for BTE\n [IA64] Move perfmon tables from thread_struct to pfm_context\n [IA64] Add interface so modules can discover whether multithreading is on.\n [IA64] kprobes: fixup the pagefault exception caused by probehandlers\n [IA64] kprobe opcode 16 bytes alignment on IA64\n [IA64] esi-support\n [IA64] Add \"model name\" to /proc/cpuinfo\n" }, { "commit": "05e0caad3b7bd0d0fbeff980bca22f186241a501", "tree": "d213789aca5bf91b74bbf5946d428590e3e368b1", "parents": [ "5cb248abf5ab65ab543b2d5fc16c738b28031fc0" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Wed Sep 27 01:49:54 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Sep 27 08:26:11 2006 -0700" }, "message": "[PATCH] Have ia64 use add_active_range() and free_area_init_nodes\n\nSize zones and holes in an architecture independent manner for ia64.\n\n[bob.picco@hp.com: fix ia64 FLATMEM+VIRTUAL_MEM_MAP]\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: Dave Hansen \u003chaveblue@us.ibm.com\u003e\nCc: Andy Whitcroft \u003capw@shadowen.org\u003e\nCc: Andi Kleen \u003cak@muc.de\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: \"Keith Mannthey\" \u003ckmannth@gmail.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nSigned-off-by: Bob Picco \u003cbob.picco@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "816add4e986499145135c4014a7c8a8857f9f3c3", "tree": "659155937ec49b48fa488a8b19a7cf347e1baa13", "parents": [ "709a6c1c07673a9f7879b5f7306dc8d723db93a2" ], "author": { "name": "Jes Sorensen", "email": "jes@sgi.com", "time": "Thu Sep 14 07:10:30 2006 -0400" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Sep 26 14:16:56 2006 -0700" }, "message": "[IA64] trim output of show_mem()\n\nCut the number of lines of memory info output per node from five\nto one line.\n\nSigned-off-by: Jes Sorensen \u003cjes@sgi.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "709a6c1c07673a9f7879b5f7306dc8d723db93a2", "tree": "9703e9652852bad1aa55bba3ba91b22fcd710c25", "parents": [ "f5a3f3dc189485d607fbd42678cc23958acc0a6e" ], "author": { "name": "Jes Sorensen", "email": "jes@sgi.com", "time": "Wed Sep 13 08:43:42 2006 -0400" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Tue Sep 26 14:15:54 2006 -0700" }, "message": "[IA64] show_mem() printk levels\n\nUse the default sysrq printk level for printing show_mem() output both\nfor disconfig and contig versions. This is consistent with the printk\nlevel used on other architectures (well ia32 at least).\n\nSigned-off-by: Jes Sorensen \u003cjes@sgi.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "e44e41d0c832ebbda7311a1fe43584d844026357", "tree": "05a8ac85029b041db8defef35bf808d431bb3528", "parents": [ "921eea1cdf6ce7f0db88e4579474a04b1fb0fe6d" ], "author": { "name": "Bob Picco", "email": "bob.picco@hp.com", "time": "Wed Jun 28 12:55:43 2006 -0400" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Aug 03 10:13:23 2006 -0700" }, "message": "[IA64] fix show_mem for VIRTUAL_MEM_MAP+FLATMEM\n\ncontig.c (FLATMEM) requires the same optimization as in discontig.c for show_mem\nwhen VIRTUAL_MEM_MAP is in use. Otherwise FLATMEM has softlockup timeouts.\nThis was boot tested for memory configuration: SPARSEMEM,\nDISCONTIG+VIRTUAL_MEM_MAP, FLATMEM, FLATMEM+VIRTUAL_MEM_MAP and\nFLATMEM+VIRTUAL_MEM_MAP with largest memory gap less than LARGE_GAP by\nusing boot parameter \"mem\u003d\".\n\nThis was boot tested and \"echo m \u003e/proc/sysrq-trigger\" output evaluated for\n: FLATMEM, FLATMEM+VIRTUAL_MEM_MAP, DISCONTIGMEM+VIRTUAL_MEM_MAP and\nSPARSEMEM.\n\nSigned-off-by: Bob Picco \u003cbob.picco@hp.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "921eea1cdf6ce7f0db88e4579474a04b1fb0fe6d", "tree": "51a9099562dffa2276100f1bff429cc5dc2e4118", "parents": [ "0a69ca91be2b36f99a48daacd1f12d9d49ecaf87" ], "author": { "name": "Bob Picco", "email": "bob.picco@hp.com", "time": "Wed Jun 28 12:54:55 2006 -0400" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Aug 03 10:12:30 2006 -0700" }, "message": "[IA64] align high endpoint of VIRTUAL_MEM_MAP\n\nAssure that vmem_map\u0027s high endpoint is MAX_ORDER aligned. Not doing so violates\nthe buddy allocator algorithm. Also anyone using mem\u003dXXX on boot line and\nnot aligned to MAX_ORDER requires this patch in order to satisfy buddy\nallocator. vmem_map always starts at pfn 0. The potentially large MAX_ORDER\non ia64 (due to hugetlbfs) requires that the end of vmem_map be aligned\nto MAX_ORDER_NR_PAGES.\n\nThis was boot tested for: FLATMEM, FLATMEM+VIRTUAL_MEM_MAP,\nDISCONTIGMEM+VIRTUAL_MEM_MAP and SPARSEMEM.\n\nSigned-off-by: Bob Picco \u003cbob.picco@hp.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "e037cda559547e6353c5a792802963572d0b750e", "tree": "5e76f7706d30d725f4bc80dd9b460f8a5c2da005", "parents": [ "4f2ef124b274baac80f64e290aa44e87a7753933" ], "author": { "name": "Keith Owens", "email": "kaos@sgi.com", "time": "Mon Jul 17 15:41:59 2006 +1000" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Wed Aug 02 16:03:44 2006 -0700" }, "message": "[IA64] sparse cleanups\n\nFix some sparse warnings on ia64. Large constants that should be long\ninstead of int. Use NULL instead of 0. Add some missing __iomem\ncasts. Replace a non-C99 structure assignment.\n\nSigned-off-by: Keith Owens \u003ckaos@sgi.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "dd8041f16b117f63f40fb844d6cdebe8b03514d2", "tree": "40521ea93b2034484ceb1f16af7d47bfa1b35b6c", "parents": [ "31304c909e6945b005af62cd55a582e9c010a0b4" ], "author": { "name": "Yasunori Goto", "email": "y-goto@jp.fujitsu.com", "time": "Tue Jul 04 02:57:51 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Jul 04 10:24:57 2006 -0700" }, "message": "[PATCH] Fix copying of pgdat array on each node for ia64 memory hotplug\n\nI found a bug in memory hot-add code for ia64.\n\nIA64\u0027s code has copies of pgdat\u0027s array on each node to reduce memory\naccess over crossing node. This array is used by NODE_DATA() macro. When\nnew node is hot-added, this pgdat\u0027s array should be updated and copied on\nnew node too.\n\nHowever, I used for_each_online_node() in scatter_node_data() to copy\nit. This meant its array is not copied on new node.\nBecause initialization of structures for new node was halfway,\nso online_node_map couldn\u0027t be set at this time.\n\nTo copy arrays on new node, I changed it to check value of pgdat_list[]\nwhich is source array of copies. I tested this patch with my Memory Hotadd\nemulation on Tiger4. This patch is for 2.6.17-git20.\n\nSigned-off-by: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "6ab3d5624e172c553004ecc862bfeac16d9d68b7", "tree": "6d98881fe91fd9583c109208d5c27131b93fa248", "parents": [ "e02169b682bc448ccdc819dc8639ed34a23cedd8" ], "author": { "name": "Jörn Engel", "email": "joern@wohnheim.fh-wedel.de", "time": "Fri Jun 30 19:25:36 2006 +0200" }, "committer": { "name": "Adrian Bunk", "email": "bunk@stusta.de", "time": "Fri Jun 30 19:25:36 2006 +0200" }, "message": "Remove obsolete #include \u003clinux/config.h\u003e\n\nSigned-off-by: Jörn Engel \u003cjoern@wohnheim.fh-wedel.de\u003e\nSigned-off-by: Adrian Bunk \u003cbunk@stusta.de\u003e\n" }, { "commit": "dd0932d9d4301bd58a4d5a634a3a8298c4fc5e24", "tree": "864da70354875dadfcaebd51571122462959530a", "parents": [ "7049027c6f0098eb6b23b8f6ca65a905541faf81" ], "author": { "name": "Yasunori Goto", "email": "y-goto@jp.fujitsu.com", "time": "Tue Jun 27 02:53:40 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Jun 27 17:32:37 2006 -0700" }, "message": "[PATCH] pgdat allocation and update for ia64 of memory hotplug: allocate pgdat and per node data\n\nThis is a patch to allocate pgdat and per node data area for ia64. The size\nfor them can be calculated by compute_pernodesize().\n\nSigned-off-by: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "7049027c6f0098eb6b23b8f6ca65a905541faf81", "tree": "ab5528625be6e79c02767c6d9444599c1980cf0e", "parents": [ "ae5a2c1c9b2bc3633032f97d02e60ae547a6047c" ], "author": { "name": "Yasunori Goto", "email": "y-goto@jp.fujitsu.com", "time": "Tue Jun 27 02:53:39 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Jun 27 17:32:37 2006 -0700" }, "message": "[PATCH] pgdat allocation and update for ia64 of memory hotplug: update pgdat address array\n\nThis is to refresh node_data[] array for ia64. As I mentioned previous\npatches, ia64 has copies of information of pgdat address array on each node as\nper node data.\n\nAt v2 of node_add, this function used stop_machine_run() to update them. (I\nwished that they were copied safety as much as possible.) But, in this patch,\nthis arrays are just copied simply, and set node_online_map bit after\ncompletion of pgdat initialization.\n\nSo, kernel must touch NODE_DATA() macro after checking node_online_map().\n(Current code has already done it.) This is more simple way for just\nhot-add.....\n\nNote : It will be problem when hot-remove will occur,\n because, even if online_map bit is set, kernel may\n touch NODE_DATA() due to race condition. :-(\n\nSigned-off-by: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "ae5a2c1c9b2bc3633032f97d02e60ae547a6047c", "tree": "51244762aca6ff087d4934f184c3877888b198c3", "parents": [ "0fc44159bfcb5b0afa178f9c3f50db23aebc76ff" ], "author": { "name": "Yasunori Goto", "email": "y-goto@jp.fujitsu.com", "time": "Tue Jun 27 02:53:38 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Jun 27 17:32:36 2006 -0700" }, "message": "[PATCH] pgdat allocation and update for ia64 of memory hotplug: hold pgdat address at system running\n\nThis is a preparatory patch to make common code for updating of NODE_DATA() of\nia64 between boottime and hotplug.\n\nCurrent code remembers pgdat address in mem_data which is used at just boot\ntime. But its information can be used at hotplug time by moving to global\nvalue. The next patch uses this array.\n\nSigned-off-by: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "bc02af93dd2bbddce1b55e0a493f833a1b7cf140", "tree": "bda7998531b9c612c5597be9158f082d1cb5ab26", "parents": [ "dd56a8e36f91f63c0a31e8a118d87b7cf01526b8" ], "author": { "name": "Yasunori Goto", "email": "y-goto@jp.fujitsu.com", "time": "Tue Jun 27 02:53:30 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Jun 27 17:32:35 2006 -0700" }, "message": "[PATCH] pgdat allocation for new node add (specify node id)\n\nChange the name of old add_memory() to arch_add_memory. And use node id to\nget pgdat for the node at NODE_DATA().\n\nNote: Powerpc\u0027s old add_memory() is defined as __devinit. However,\n add_memory() is usually called only after bootup.\n I suppose it may be redundant. But, I\u0027m not well known about powerpc.\n So, I keep it. (But, __meminit is better at least.)\n\nSigned-off-by: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nCc: Dave Hansen \u003chaveblue@us.ibm.com\u003e\nCc: \"Brown, Len\" \u003clen.brown@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "ae9a5b85655d7133ab8e7c99b742ef20c8dbb7d2", "tree": "011bf055ef888a4cfb949fec467bd6385a090d12", "parents": [ "b71b5b652852db1b499d22aaabed8f5043acafad" ], "author": { "name": "Anil S Keshavamurthy", "email": "anil.s.keshavamurthy@intel.com", "time": "Mon Jun 26 00:25:26 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Jun 26 09:58:22 2006 -0700" }, "message": "[PATCH] Notify page fault call chain for ia64\n\nOverloading of page fault notification with the notify_die() has performance\nissues(since the only interested components for page fault is kprobes and/or\nkdb) and hence this patch introduces the new notifier call chain exclusively\nfor page fault notifications their by avoiding notifying unnecessary\ncomponents in the do_page_fault() code path.\n\nSigned-off-by: Anil S Keshavamurthy \u003canil.s.keshavamurthy@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "8cf60e04a131310199d5776e2f9e915f0c468899", "tree": "373a68e88e6737713a0a5723d552cdeefffff929", "parents": [ "1323523f505606cfd24af6122369afddefc3b09d", "95eaa5fa8eb2c345244acd5f65b200b115ae8c65" ], "author": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Fri Jun 23 13:46:23 2006 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Fri Jun 23 13:46:23 2006 -0700" }, "message": "Auto-update from upstream\n" }, { "commit": "9c576ff1bc9ab42d06457e68e39c121481138562", "tree": "8082e3ccad2ea162eee9889a681b87267e42f6f6", "parents": [ "ebd5f2ca811b75f7145fa487748f26430c584a72" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Thu Apr 27 05:25:00 2006 -0400" }, "committer": { "name": "Len Brown", "email": "len.brown@intel.com", "time": "Mon May 15 02:23:35 2006 -0400" }, "message": "ACPI add ia64 exports to build acpi_memhotplug as a module\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Len Brown \u003clen.brown@intel.com\u003e\n" }, { "commit": "32e62c636a728cb39c0b3bd191286f2ca65d4028", "tree": "656454a01e720819103c172daae15b5f2fd85d68", "parents": [ "6810b548b25114607e0814612d84125abccc0a4f" ], "author": { "name": "Bjorn Helgaas", "email": "bjorn.helgaas@hp.com", "time": "Fri May 05 17:19:50 2006 -0600" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon May 08 16:32:05 2006 -0700" }, "message": "[IA64] rework memory attribute aliasing\n\nThis closes a couple holes in our attribute aliasing avoidance scheme:\n\n - The current kernel fails mmaps of some /dev/mem MMIO regions because\n they don\u0027t appear in the EFI memory map. This keeps X from working\n on the Intel Tiger box.\n\n - The current kernel allows UC mmap of the 0-1MB region of\n /sys/.../legacy_mem even when the chipset doesn\u0027t support UC\n access. This causes an MCA when starting X on HP rx7620 and rx8620\n boxes in the default configuration.\n\nThere\u0027s more detail in the Documentation/ia64/aliasing.txt file this\nadds, but the general idea is that if a region might be covered by\na granule-sized kernel identity mapping, any access via /dev/mem or\nmmap must use the same attribute as the identity mapping.\n\nOtherwise, we fall back to using an attribute that is supported\naccording to the EFI memory map, or to using UC if the EFI memory\nmap doesn\u0027t mention the region.\n\nSigned-off-by: Bjorn Helgaas \u003cbjorn.helgaas@hp.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "ace1d816a13ff42d4f41989862552032f9c19853", "tree": "084277670a76f9a50449e82b308ecc7b881fd5ac", "parents": [ "356a5c1c6fdfb8eed6dbb3979d90c7cc7060017a" ], "author": { "name": "Robin Holt", "email": "holt@sgi.com", "time": "Thu Apr 13 15:34:45 2006 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Apr 13 15:34:45 2006 -0700" }, "message": "[IA64] Make show_mem() skip holes in a pgdat\n\nThis patch modifies ia64\u0027s show_mem() to walk the vmem_map page tables and\nrapidly skip forward across regions where the page tables are missing.\nThis prevents the pfn_valid() check from causing numerous unnecessary\npage faults.\n\nWithout this patch on a 512 node 512 cpu system where every node has four\nmemory holes, the show_mem() call takes 1 hour 18 minutes. With this\npatch, it takes less than 3 seconds.\n\nSigned-off-by: Robin Holt \u003cholt@sgi.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "0ffe984917b9cd6ecc19ffbc06f35869d8c18df8", "tree": "49b54ea585dcd657083c8b755726820b002ae75a", "parents": [ "8cab7ccccbdd9fe3cf6b3400d5a88ecb683a5b1b" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Mar 28 22:54:38 2006 -0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Fri Apr 07 23:08:16 2006 -0700" }, "message": "[IA64] Prefetch mmap_sem in ia64_do_page_fault()\n\nTake a hint from an x86_64 optimization by Arjan van de Ven and use it\nfor ia64. See a9ba9a3b3897561d01e04cd21433746df46548c0\n\nPrefetch the mmap_sem, which is critical for the performance of the page fault\nhandler.\n\nNote: mm may be NULL but I guess that is safe.\nSee 458f935527372499b714bf4f8e646a68bb0f52e3\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "d1127e40e8d75cd3855e35424937c73d0bcec558", "tree": "093f020e971827c63d3eed1d646022c581ded2ea", "parents": [ "5abc97aa25b2c41413b3a520faee83f2282d9f18", "c1c57d767100417f63c18da52d7e96f82b2b9e1a" ], "author": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Mar 30 12:38:18 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Thu Mar 30 12:38:18 2006 -0800" }, "message": "Merge branch \u0027release\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6\n\n* \u0027release\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6:\n [IA64] ioremap() should prefer WB over UC\n [IA64] Add __mca_table to the DISCARD list in gate.lds\n [IA64] Move __mca_table out of the __init section\n [IA64] simplify some condition checks in iosapic_check_gsi_range\n [IA64] correct some messages and fixes some minor things\n [IA64-SGI] fix for-loop in sn_hwperf_geoid_to_cnode()\n [IA64-SGI] sn_hwperf use of num_online_cpus()\n [IA64] optimize flush_tlb_range on large numa box\n [IA64] lazy_mmu_prot_update needs to be aware of huge pages\n" }, { "commit": "c1c57d767100417f63c18da52d7e96f82b2b9e1a", "tree": "c8427f85c043e50845b3226699fcf6c16d380b05", "parents": [ "3283a67d8618c9a292eced23e8753ab64adc6dba" ], "author": { "name": "Bjorn Helgaas", "email": "bjorn.helgaas@hp.com", "time": "Thu Mar 30 09:53:39 2006 -0700" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Thu Mar 30 09:05:41 2006 -0800" }, "message": "[IA64] ioremap() should prefer WB over UC\n\nefi_memmap_init() collects full granules of WB memory, without\nregard for whether they also support UC. So in order for ioremap()\nto work for main memory, it must prefer WB mappings when possible.\n\nSigned-off-by: Bjorn Helgaas \u003cbjorn.helgaas@hp.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "ce9eed5a98efacb896551d3470d9d46826caaee5", "tree": "13752f8ae5e941b83f57ba815b1af4e7bbcff34d", "parents": [ "5e48521e869de7d904bb5ffe9739258ffa026927" ], "author": { "name": "Chen, Kenneth W", "email": "kenneth.w.chen@intel.com", "time": "Mon Mar 06 14:12:54 2006 -0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon Mar 27 10:20:03 2006 -0800" }, "message": "[IA64] optimize flush_tlb_range on large numa box\n\nIt was reported from a field customer that global spin lock ptcg_lock\nis giving a lot of grief on munmap performance running on a large numa\nmachine. What appears to be a problem coming from flush_tlb_range(),\nwhich currently unconditionally calls platform_global_tlb_purge().\nFor some of the numa machines in existence today, this function is\nmapped into ia64_global_tlb_purge(), which holds ptcg_lock spin lock\nwhile executing ptc.ga instruction.\n\nHere is a patch that attempt to avoid global tlb purge whenever\npossible. It will use local tlb purge as much as possible. Though the\nconditions to use local tlb purge is pretty restrictive. One of the\nside effect of having flush tlb range instruction on ia64 is that\nkernel don\u0027t get a chance to clear out cpu_vm_mask. On ia64, this mask\nis sticky and it will accumulate if process bounces around. Thus\ndiminishing the possible use of ptc.l. Thoughts?\n\nSigned-off-by: Ken Chen \u003ckenneth.w.chen@intel.com\u003e\nAcked-by: Jack Steiner \u003csteiner@sgi.com\u003e\nAcked-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "5e48521e869de7d904bb5ffe9739258ffa026927", "tree": "3827383a0a769cac6386bba65915bd6b54c33766", "parents": [ "64bc0430ee78c03c5c4ce549e217bb74bff7ea5d" ], "author": { "name": "Zhang, Yanmin", "email": "yanmin.zhang@intel.com", "time": "Thu Feb 23 11:07:20 2006 +0800" }, "committer": { "name": "Tony Luck", "email": "tony.luck@intel.com", "time": "Mon Mar 27 10:15:41 2006 -0800" }, "message": "[IA64] lazy_mmu_prot_update needs to be aware of huge pages\n\nFunction lazy_mmu_prot_update is also used on huge pages when it is called\nby set_huge_ptep_writable, but it isn\u0027t aware of huge pages.\n\nSigned-off-by: Zhang Yanmin \u003cyanmin.zhang@intel.com\u003e\nAcked-by: Ken Chen \u003ckenneth.w.chen@intel.com\u003e\nSigned-off-by: Tony Luck \u003ctony.luck@intel.com\u003e\n" }, { "commit": "3571761fe49d960bb720c2308ffb9401f0a5e161", "tree": "2b100cedf9f18ec59f0aa38e8c0f6b25bec9dfab", "parents": [ "ec936fc563715a9e2b2e363eb060655b49529325" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Mon Mar 27 01:16:00 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Mar 27 08:44:48 2006 -0800" }, "message": "[PATCH] for_each_online_pgdat: remove sorting pgdat\n\nBecause pgdat_list was linked to pgdat_list in *reverse* order, (By default)\nsome of arch has to sort it by themselves.\n\nfor_each_pgdat has gone..for_each_online_pgdat() uses node_online_map, which\ndoesn\u0027t need to be sorted.\n\nThis patch removes codes for sorting pgdat.\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" } ], "next": "ec936fc563715a9e2b2e363eb060655b49529325" }