)]}' { "log": [ { "commit": "8054a3428fbec2d91dfeb5bd78d7e75064cf163b", "tree": "f48bc5305c24ea79e530a264f4901caf249abc9d", "parents": [ "53b5cd349556394f91553b3bab3b483b4024e6d8" ], "author": { "name": "Christoph Egger", "email": "siccegge@cs.fau.de", "time": "Tue Jun 08 23:59:55 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jun 15 15:02:32 2010 +1000" }, "message": "powerpc: Remove dead CONFIG_HIGHPTE\n\nCONFIG_HIGHPTE doesn\u0027t exist in Kconfig, therefore removing all\nreferences for it from the source code.\n\nSigned-off-by: Christoph Egger \u003csiccegge@cs.fau.de\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "98edb6ca4174f17a64890a02f44c211c8b44fb3c", "tree": "033bc5f7da410046d28dd1cefcd2d63cda33d25b", "parents": [ "a8251096b427283c47e7d8f9568be6b388dd68ec", "8fbf065d625617bbbf6b72d5f78f84ad13c8b547" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri May 21 17:16:21 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri May 21 17:16:21 2010 -0700" }, "message": "Merge branch \u0027kvm-updates/2.6.35\u0027 of git://git.kernel.org/pub/scm/virt/kvm/kvm\n\n* \u0027kvm-updates/2.6.35\u0027 of git://git.kernel.org/pub/scm/virt/kvm/kvm: (269 commits)\n KVM: x86: Add missing locking to arch specific vcpu ioctls\n KVM: PPC: Add missing vcpu_load()/vcpu_put() in vcpu ioctls\n KVM: MMU: Segregate shadow pages with different cr0.wp\n KVM: x86: Check LMA bit before set_efer\n KVM: Don\u0027t allow lmsw to clear cr0.pe\n KVM: Add cpuid.txt file\n KVM: x86: Tell the guest we\u0027ll warn it about tsc stability\n x86, paravirt: don\u0027t compute pvclock adjustments if we trust the tsc\n x86: KVM guest: Try using new kvm clock msrs\n KVM: x86: export paravirtual cpuid flags in KVM_GET_SUPPORTED_CPUID\n KVM: x86: add new KVMCLOCK cpuid feature\n KVM: x86: change msr numbers for kvmclock\n x86, paravirt: Add a global synchronization point for pvclock\n x86, paravirt: Enable pvclock flags in vcpu_time_info structure\n KVM: x86: Inject #GP with the right rip on efer writes\n KVM: SVM: Don\u0027t allow nested guest to VMMCALL into host\n KVM: x86: Fix exception reinjection forced to true\n KVM: Fix wallclock version writing race\n KVM: MMU: Don\u0027t read pdptrs with mmu spinlock held in mmu_alloc_roots\n KVM: VMX: enable VMXON check with SMX enabled (Intel TXT)\n ...\n" }, { "commit": "bc8449cc57898bc9cf1ffc4619d026f77bf327c1", "tree": "bb4d846c5c3ad66d4e98278f43ff520320f8d917", "parents": [ "56608209d34b8add40af54031d4e420afbcde9f6" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Sun May 16 20:28:35 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri May 21 17:31:12 2010 +1000" }, "message": "powerpc/numa: Use ibm,architecture-vec-5 to detect form 1 affinity\n\nI\u0027ve been told that the architected way to determine we are in form 1\naffinity mode is by reading the ibm,architecture-vec-5 property which\nmirrors the layout of the fifth vector of the ibm,client-architecture\nstructure.\n\nEventually we may want to parse the ibm,architecture-vec-5 and create\nFW_FEATURE_* bits.\n\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "78f622377f7d31d988db350a43c5689dd5f31876", "tree": "f399c9c492b9a3397a0974981049b2adaddf279d", "parents": [ "78e2e68a2b79f394b7cd61e07987a8a89af907f7" ], "author": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Thu May 13 14:38:21 2010 -0500" }, "committer": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Mon May 17 10:56:20 2010 -0500" }, "message": "powerpc/fsl-booke: Move loadcam_entry back to asm code to fix SMP ftrace\n\nWhen we build with ftrace enabled its possible that loadcam_entry would\nhave used the stack pointer (even though the code doesn\u0027t need it). We\ncall loadcam_entry in __secondary_start before the stack is setup. To\nensure that loadcam_entry doesn\u0027t use the stack pointer the easiest\nsolution is to just have it in asm code.\n\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\n" }, { "commit": "c83ec269e6931edf61abe1ed777ebb867b06a85c", "tree": "a346c886a435cb07c35c20c5f6ad685ab37535de", "parents": [ "0737279427bef48f552b3ab63a6c0ba7491fe29f" ], "author": { "name": "Alexander Graf", "email": "agraf@suse.de", "time": "Fri Apr 16 00:11:36 2010 +0200" }, "committer": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Mon May 17 12:18:20 2010 +0300" }, "message": "PPC: Split context init/destroy functions\n\nWe need to reserve a context from KVM to make sure we have our own\nsegment space. While we did that split for Book3S_64 already, 32 bit\nis still outstanding.\n\nSo let\u0027s split it now.\n\nSigned-off-by: Alexander Graf \u003cagraf@suse.de\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCC: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Avi Kivity \u003cavi@redhat.com\u003e\n" }, { "commit": "1ed31d6db90d51010545921e59d369d2f92b7ac2", "tree": "358a0b346bc8135cd5e53700eb44308b1a7c8c5b", "parents": [ "ceba1abcb00b0ef0b1efcd715285f6e05523edef", "722154e4cacf015161efe60009ae9be23d492296" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri May 07 11:29:25 2010 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri May 07 11:29:25 2010 +1000" }, "message": "Merge commit \u0027origin/master\u0027 into next\n" }, { "commit": "25863de07af9cb90e6365cc8216bdd17f2394515", "tree": "ac765e8b06006efea240ce287d587103341bf380", "parents": [ "8729faaa5e87557876c02f1665d517e2b41299f1" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Mon Apr 26 15:32:43 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu May 06 17:41:58 2010 +1000" }, "message": "powerpc/cpumask: Convert NUMA code to new cpumask API\n\nConvert NUMA code to new cpumask API. We shift the node to cpumask\nsetup code until after we complete bootmem allocation so we can\ndynamically allocate the cpumasks.\n\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "e460c2c91af44374cbfa3f1c70f5ca9bbf099aa9", "tree": "7b59d216c38c9a20c6fed47c93f3fed944d72219", "parents": [ "91eea67c6d8704396a98226508c56a8501e141e3" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu May 06 17:15:58 2010 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu May 06 17:15:58 2010 +1000" }, "message": "powerpc: Invoke oom-killer from page fault\n\nAs explained in commit 1c0fe6e3bd, we want to call the architecture independent\noom killer when getting an unexplained OOM from handle_mm_fault, rather than\nsimply killing current.\n\nCc: linuxppc-dev@ozlabs.org\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: linux-arch@vger.kernel.org\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "91eea67c6d8704396a98226508c56a8501e141e3", "tree": "94d65c6bae001fa3835398056fea936720e86ed7", "parents": [ "13bb5339966d49942878a46b0a7fda0639d7db5f" ], "author": { "name": "Mark Nelson", "email": "markn@au1.ibm.com", "time": "Wed Apr 21 16:21:03 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu May 06 16:49:27 2010 +1000" }, "message": "powerpc/mm: Track backing pages allocated by vmemmap_populate()\n\nWe need to keep track of the backing pages that get allocated by\nvmemmap_populate() so that when we use kdump, the dump-capture kernel knows\nwhere these pages are.\n\nWe use a simple linked list of structures that contain the physical address\nof the backing page and corresponding virtual address to track the backing\npages.\nTo save space, we just use a pointer to the next struct vmemmap_backing. We\ncan also do this because we never remove nodes. We call the pointer \"list\"\nto be compatible with changes made to the crash utility.\n\nvmemmap_populate() is called either at boot-time or on a memory hotplug\noperation. We don\u0027t have to worry about the boot-time calls because they\nwill be inherently single-threaded, and for a memory hotplug operation\nvmemmap_populate() is called through:\nsparse_add_one_section()\n |\n V\nkmalloc_section_memmap()\n |\n V\nsparse_mem_map_populate()\n |\n V\nvmemmap_populate()\nand in sparse_add_one_section() we\u0027re protected by pgdat_resize_lock().\nSo, we don\u0027t need a spinlock to protect the vmemmap_list.\n\nWe allocate space for the vmemmap_backing structs by allocating whole pages\nin vmemmap_list_alloc() and then handing out chunks of this to\nvmemmap_list_populate().\n\nThis means that we waste at most just under one page, but this keeps the code\nis simple.\n\nSigned-off-by: Mark Nelson \u003cmarkn@au1.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "75c1d539ea13117cbe95e2c343e52af67d735145", "tree": "f45295016163b1e1914dc1f48c307e64215f5f2c", "parents": [ "aef40e87d866355ffd279ab21021de733242d0d5" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Apr 27 21:22:55 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu May 06 16:49:26 2010 +1000" }, "message": "powerpc: Fix CONFIG_DEBUG_PAGEALLOC on 603/e300\n\nSo we tried to speed things up a bit using flush_hash_pages() directly\nbut that falls over on 603 of course meaning we fail to flush the TLB\nproperly and we may even end up having it corrupt memory randomly by\naccessing a hash table that doesn\u0027t exist.\n\nThis removes the \"optimization\" by always going through flush_tlb_page()\nfor now at least.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "e7f75ad01d590243904c2d95ab47e6b2e9ef6dad", "tree": "454cf065417973e9c2fcd75542351c2534b9a4b9", "parents": [ "795033c344d88dc6aa5106d0cc358656f29bd722" ], "author": { "name": "Dave Kleikamp", "email": "shaggy@linux.vnet.ibm.com", "time": "Fri Mar 05 10:43:12 2010 +0000" }, "committer": { "name": "Josh Boyer", "email": "jwboyer@linux.vnet.ibm.com", "time": "Wed May 05 09:11:10 2010 -0400" }, "message": "powerpc/47x: Base ppc476 support\n\nThis patch adds the base support for the 476 processor. The code was\nprimarily written by Ben Herrenschmidt and Torez Smith, but I\u0027ve been\nmaintaining it for a while.\n\nThe goal is to have a single binary that will run on 44x and 47x, but\nwe still have some details to work out. The biggest is that the L1 cache\nline size differs on the two platforms, but it\u0027s currently a compile-time\noption.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Torez Smith \u003clnxtorez@linux.vnet.ibm.com\u003e\nSigned-off-by: Dave Kleikamp \u003cshaggy@linux.vnet.ibm.com\u003e\nSigned-off-by: Josh Boyer \u003cjwboyer@linux.vnet.ibm.com\u003e\n" }, { "commit": "b18262eda36e1f340e3c29a8da9a36b3452621f9", "tree": "9ec97b524d41ba1a84ff013296b63f2db057be0d", "parents": [ "e97e7120eb24800cf8eb62c7da07b161cc2a8c73", "56151e753468e34aeb322af4b0309ab727c97d2e" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Apr 29 20:01:42 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Apr 29 20:01:42 2010 -0700" }, "message": "Merge branch \u0027for_linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/jwessel/linux-2.6-kgdb\n\n* \u0027for_linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/jwessel/linux-2.6-kgdb:\n kgdb: don\u0027t needlessly skip PAGE_USER test for Fsl booke\n" }, { "commit": "56151e753468e34aeb322af4b0309ab727c97d2e", "tree": "dd2b28d468e3c5fda711df1c0a3a6a3356772be9", "parents": [ "79dba2eaa771c3173957eccfd288e0e0d12e4d3f" ], "author": { "name": "Wufei", "email": "fei.wu@windriver.com", "time": "Wed Apr 28 17:42:32 2010 -0400" }, "committer": { "name": "Jason Wessel", "email": "jason.wessel@windriver.com", "time": "Thu Apr 29 21:41:44 2010 -0500" }, "message": "kgdb: don\u0027t needlessly skip PAGE_USER test for Fsl booke\n\nThe bypassing of this test is a leftover from 2.4 vintage\nkernels, and is no longer appropriate, or even used by KGDB.\nCurrently KGDB uses probe_kernel_write() for all access to\nmemory via the KGDB core, so it can simply be deleted.\n\nThis fixes CVE-2010-1446.\n\nCC: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCC: Paul Mackerras \u003cpaulus@samba.org\u003e\nCC: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nSigned-off-by: Wufei \u003cfei.wu@windriver.com\u003e\nSigned-off-by: Jason Wessel \u003cjason.wessel@windriver.com\u003e\n" }, { "commit": "4b83c330b4d38e869111bda6e9077d4f61ed974a", "tree": "c85d12aaea6be5dd26caa1b99ffa6adcaa50bc05", "parents": [ "dbc9632a8c25c6efcc1ca3f3a2177c855b6e053e" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Wed Apr 07 15:33:44 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Apr 28 16:22:33 2010 +1000" }, "message": "powerpc/numa: Add form 1 NUMA affinity\n\nFirmware changed the way it represents memory and cpu affinity on POWER7.\nUnfortunately the old method now caps the topology to work around issues\nwith legacy operating systems. For Linux to get the correct topology we\nneed to use the new form 1 affinity information.\n\nWe set the form 1 field in the client architecture, and if we see \"1\" in the\nibm,associativity-form property firmware supports form 1 affinity and\nwe should look at the first field in the ibm,associativity-reference-points\narray. If not we use the second field as we always have.\n\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "e8137341b1bb9bbdc29d9fd8980485ec7dcb4109", "tree": "f4ed1bc7db8a75fa7ff03d0e6d2b070562bb3d7f", "parents": [ "e0f278adc29e8986531a51e5ed33db42e34bf952" ], "author": { "name": "Becky Bruce", "email": "beckyb@kernel.crashing.org", "time": "Mon Apr 12 11:21:50 2010 -0500" }, "committer": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Mon Apr 19 23:12:44 2010 -0500" }, "message": "powerpc/fsl_booke: Correct test for MMU_FTR_BIG_PHYS\n\nThe code was looking for this in cpu_features, not mmu_features. Fix this.\n\nSigned-off-by: Becky Bruce \u003cbeckyb@kernel.crashing.org\u003e\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\n" }, { "commit": "9c7cc234dc5edf5379fbbab4973f6704f59bc57b", "tree": "6129dffa0ffc36da27718059c9b2ff40b74aa16b", "parents": [ "578b7cd1518f8d1b17a7fb1671d3d756c9cb49f1" ], "author": { "name": "K.Prasad", "email": "prasad@linux.vnet.ibm.com", "time": "Mon Mar 29 23:59:25 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Apr 07 14:44:38 2010 +1000" }, "message": "powerpc: Disable interrupts for data breakpoint exceptions\n\nData address breakpoint exceptions are currently handled along with page-faults\nwhich require interrupts to remain in enabled state. Since exception handling\nfor data breakpoints aren\u0027t pre-empt safe, we handle them separately.\n\nSigned-off-by: K.Prasad \u003cprasad@linux.vnet.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "55052eeca6d71d76f7c3f156c0501814d8e5e6d3", "tree": "7a13664cc8c99ffbad425dbc0eefd4ccceb70b8a", "parents": [ "f467bc148d05a1465211102804858df9c667f8b9" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Apr 07 14:39:36 2010 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Apr 07 14:39:47 2010 +1000" }, "message": "powerpc: Fix ioremap_flags() with book3e pte definition\n\nWe can\u0027t just clear the user read permission in book3e pte, because\nthat will also clear supervisor read permission. This surely isn\u0027t\ndesired. Fix the problem by adding the supervisor read back.\n\nBenH: Slightly simplified the ifdef and applied to ppc64 too\n\nSigned-off-by: Li Yang \u003cleoli@freescale.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "5a0e3ad6af8660be21ca98a971cd00f331318c05", "tree": "5bfb7be11a03176a87296a43ac6647975c00a1d1", "parents": [ "ed391f4ebf8f701d3566423ce8f17e614cde9806" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Wed Mar 24 17:04:11 2010 +0900" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Tue Mar 30 22:02:32 2010 +0900" }, "message": "include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h\n\npercpu.h is included by sched.h and module.h and thus ends up being\nincluded when building most .c files. percpu.h includes slab.h which\nin turn includes gfp.h making everything defined by the two files\nuniversally available and complicating inclusion dependencies.\n\npercpu.h -\u003e slab.h dependency is about to be removed. Prepare for\nthis change by updating users of gfp and slab facilities include those\nheaders directly instead of assuming availability. As this conversion\nneeds to touch large number of source files, the following script is\nused as the basis of conversion.\n\n http://userweb.kernel.org/~tj/misc/slabh-sweep.py\n\nThe script does the followings.\n\n* Scan files for gfp and slab usages and update includes such that\n only the necessary includes are there. ie. if only gfp is used,\n gfp.h, if slab is used, slab.h.\n\n* When the script inserts a new include, it looks at the include\n blocks and try to put the new include such that its order conforms\n to its surrounding. It\u0027s put in the include block which contains\n core kernel includes, in the same order that the rest are ordered -\n alphabetical, Christmas tree, rev-Xmas-tree or at the end if there\n doesn\u0027t seem to be any matching order.\n\n* If the script can\u0027t find a place to put a new include (mostly\n because the file doesn\u0027t have fitting include block), it prints out\n an error message indicating which .h file needs to be added to the\n file.\n\nThe conversion was done in the following steps.\n\n1. The initial automatic conversion of all .c files updated slightly\n over 4000 files, deleting around 700 includes and adding ~480 gfp.h\n and ~3000 slab.h inclusions. The script emitted errors for ~400\n files.\n\n2. Each error was manually checked. Some didn\u0027t need the inclusion,\n some needed manual addition while adding it to implementation .h or\n embedding .c file was more appropriate for others. This step added\n inclusions to around 150 files.\n\n3. The script was run again and the output was compared to the edits\n from #2 to make sure no file was left behind.\n\n4. Several build tests were done and a couple of problems were fixed.\n e.g. lib/decompress_*.c used malloc/free() wrappers around slab\n APIs requiring slab.h to be added manually.\n\n5. The script was run on all .h files but without automatically\n editing them as sprinkling gfp.h and slab.h inclusions around .h\n files could easily lead to inclusion dependency hell. Most gfp.h\n inclusion directives were ignored as stuff from gfp.h was usually\n wildly available and often used in preprocessor macros. Each\n slab.h inclusion directive was examined and added manually as\n necessary.\n\n6. percpu.h was updated not to include slab.h.\n\n7. Build test were done on the following configurations and failures\n were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my\n distributed build env didn\u0027t work with gcov compiles) and a few\n more options had to be turned off depending on archs to make things\n build (like ipr on powerpc/64 which failed due to missing writeq).\n\n * x86 and x86_64 UP and SMP allmodconfig and a custom test config.\n * powerpc and powerpc64 SMP allmodconfig\n * sparc and sparc64 SMP allmodconfig\n * ia64 SMP allmodconfig\n * s390 SMP allmodconfig\n * alpha SMP allmodconfig\n * um on x86_64 SMP allmodconfig\n\n8. percpu.h modifications were reverted so that it could be applied as\n a separate patch and serve as bisection point.\n\nGiven the fact that I had only a couple of failures from tests on step\n6, I\u0027m fairly confident about the coverage of this conversion patch.\nIf there is a breakage, it\u0027s likely to be something in one of the arch\nheaders which should be easily discoverable easily on most builds of\nthe specific arch.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nGuess-its-ok-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Ingo Molnar \u003cmingo@redhat.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\n" }, { "commit": "a93272969c6b1d59883fcbb04845420bd72c9a20", "tree": "16b980ded87e94ac4eee7375eaf38605fb69a211", "parents": [ "09156a7a409cf93d1ca2706bf05d714879a5b7ea" ], "author": { "name": "FUJITA Tomonori", "email": "fujita.tomonori@lab.ntt.co.jp", "time": "Tue Mar 16 13:16:25 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Mar 19 16:38:16 2010 +1100" }, "message": "powerpc: Fix swiotlb to respect the boot option\n\npowerpc initializes swiotlb before parsing the kernel boot options so\nswiotlb options (e.g. specifying the swiotlb buffer size) are ignored.\n\nAny time before freeing bootmem works for swiotlb so this patch moves\npowerpc\u0027s swiotlb initialization after parsing the kernel boot\noptions, mem_init (as x86 does).\n\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nTested-by: Becky Bruce \u003cbeckyb@kernel.crashing.org\u003e\nTested-by: Albert Herranz \u003calbert_herranz@yahoo.es\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "318ae2edc3b29216abd8a2510f3f80b764f06858", "tree": "ce595adde342f57f379d277b25e4dd206988a052", "parents": [ "25cf84cf377c0aae5dbcf937ea89bc7893db5176", "3e58974027b04e84f68b964ef368a6cd758e2f84" ], "author": { "name": "Jiri Kosina", "email": "jkosina@suse.cz", "time": "Mon Mar 08 16:55:37 2010 +0100" }, "committer": { "name": "Jiri Kosina", "email": "jkosina@suse.cz", "time": "Mon Mar 08 16:55:37 2010 +0100" }, "message": "Merge branch \u0027for-next\u0027 into for-linus\n\nConflicts:\n\tDocumentation/filesystems/proc.txt\n\tarch/arm/mach-u300/include/mach/debug-macro.S\n\tdrivers/net/qlge/qlge_ethtool.c\n\tdrivers/net/qlge/qlge_main.c\n\tdrivers/net/typhoon.c\n" }, { "commit": "72c3368856c543ace033f6a5b9a3edf1f4043236", "tree": "53fe8b4b19f42915a5f7d97bd1f779327dd534d4", "parents": [ "d554ed895dc8f293cc712c71f14b101ace82579a" ], "author": { "name": "H Hartley Sweeten", "email": "hartleys@visionengravers.com", "time": "Fri Mar 05 13:42:43 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 06 11:26:31 2010 -0800" }, "message": "nodemask.h: remove macro any_online_node\n\nThe macro any_online_node() is prone to producing sparse warnings due to\nthe local symbol \u0027node\u0027. Since all the in-tree users are really\nrequesting the first online node (the mask argument is either\nNODE_MASK_ALL or node_online_map) just use the first_online_node macro and\nremove the any_online_node macro since there are no users.\n\nSigned-off-by: H Hartley Sweeten \u003chsweeten@visionengravers.com\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nReviewed-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Dave Hansen \u003cdave@linux.vnet.ibm.com\u003e\nCc: Milton Miller \u003cmiltonm@bga.com\u003e\nCc: Nathan Fontenot \u003cnfont@austin.ibm.com\u003e\nCc: Geoff Levand \u003cgeoffrey.levand@am.sony.com\u003e\nCc: Grant Likely \u003cgrant.likely@secretlab.ca\u003e\nCc: J. Bruce Fields \u003cbfields@fieldses.org\u003e\nCc: Neil Brown \u003cneilb@suse.de\u003e\nCc: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nCc: Benny Halevy \u003cbhalevy@panasas.com\u003e\nCc: Chuck Lever \u003cchuck.lever@oracle.com\u003e\nCc: Ricardo Labiaga \u003cRicardo.Labiaga@netapp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ac0f6f927db539e03e1f3f61bcd4ed57d5cde7a9", "tree": "816e5ac643b15c2050c64a7075f0f7e13d86ea09", "parents": [ "b1bf9368407ae7e89d8a005bb40beb70a41df539", "9f33be2c3a80bdc2cc08342dd77fac87652e0548" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Mar 01 09:15:15 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Mar 01 09:15:15 2010 -0800" }, "message": "Merge branch \u0027for-linus\u0027 of master.kernel.org:/home/rmk/linux-2.6-arm\n\n* \u0027for-linus\u0027 of master.kernel.org:/home/rmk/linux-2.6-arm: (100 commits)\n ARM: Eliminate decompressor -Dstatic\u003d PIC hack\n ARM: 5958/1: ARM: U300: fix inverted clk round rate\n ARM: 5956/1: misplaced parentheses\n ARM: 5955/1: ep93xx: move timer defines into core.c and document\n ARM: 5954/1: ep93xx: move gpio interrupt support to gpio.c\n ARM: 5953/1: ep93xx: fix broken build of clock.c\n ARM: 5952/1: ARM: MM: Add ARM_L1_CACHE_SHIFT_6 for handle inside each ARCH Kconfig\n ARM: 5949/1: NUC900 add gpio virtual memory map\n ARM: 5948/1: Enable timer0 to time4 clock support for nuc910\n ARM: 5940/2: ARM: MMCI: remove custom DBG macro and printk\n ARM: make_coherent(): fix problems with highpte, part 2\n MM: Pass a PTE pointer to update_mmu_cache() rather than the PTE itself\n ARM: 5945/1: ep93xx: include correct irq.h in core.c\n ARM: 5933/1: amba-pl011: support hardware flow control\n ARM: 5930/1: Add PKMAP area description to memory.txt.\n ARM: 5929/1: Add checks to detect overlap of memory regions.\n ARM: 5928/1: Change type of VMALLOC_END to unsigned long.\n ARM: 5927/1: Make delimiters of DMA area globally visibly.\n ARM: 5926/1: Add \"Virtual kernel memory...\" printout.\n ARM: 5920/1: OMAP4: Enable L2 Cache\n ...\n\nFix up trivial conflict in arch/arm/mach-mx25/clock.c\n" }, { "commit": "4b3073e1c53a256275f1079c0fbfbe85883d9275", "tree": "a0fa98cb75edbbc58c43bbe38ac4c6da0913ae6d", "parents": [ "ed42acaef1a9d51631a31b55e9ed52d400430492" ], "author": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Fri Dec 18 16:40:18 2009 +0000" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Sat Feb 20 16:41:46 2010 +0000" }, "message": "MM: Pass a PTE pointer to update_mmu_cache() rather than the PTE itself\n\nOn VIVT ARM, when we have multiple shared mappings of the same file\nin the same MM, we need to ensure that we have coherency across all\ncopies. We do this via make_coherent() by making the pages\nuncacheable.\n\nThis used to work fine, until we allowed highmem with highpte - we\nnow have a page table which is mapped as required, and is not available\nfor modification via update_mmu_cache().\n\nRalf Beache suggested getting rid of the PTE value passed to\nupdate_mmu_cache():\n\n On MIPS update_mmu_cache() calls __update_tlb() which walks pagetables\n to construct a pointer to the pte again. Passing a pte_t * is much\n more elegant. Maybe we might even replace the pte argument with the\n pte_t?\n\nBen Herrenschmidt would also like the pte pointer for PowerPC:\n\n Passing the ptep in there is exactly what I want. I want that\n -instead- of the PTE value, because I have issue on some ppc cases,\n for I$/D$ coherency, where set_pte_at() may decide to mask out the\n _PAGE_EXEC.\n\nSo, pass in the mapped page table pointer into update_mmu_cache(), and\nremove the PTE value, updating all implementations and call sites to\nsuit.\n\nIncludes a fix from Stephen Rothwell:\n\n sparc: fix fallout from update_mmu_cache API change\n\n Signed-off-by: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\n\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n" }, { "commit": "3eb93c558a9e3651f86a88565e59488e936ff346", "tree": "b62d097caf3e31ba64d6d79f4fd7736247bad4e5", "parents": [ "203041ad1f66d2afb893c2adb9c11bfd13209d06" ], "author": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Thu Feb 18 02:22:44 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Feb 19 14:52:33 2010 +1100" }, "message": "powerpc: Convert tlbivax_lock to raw_spinlock\n\ntlbivax_lock needs to be a real spinlock in RT. Convert it to\nraw_spinlock.\n\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nAcked-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "6b9c9b8a66f7696ce392d34f90d4d6aa7045f51d", "tree": "33baf0862f45c3fbea4b683e671a1f8041a6ba10", "parents": [ "5181e7909b28abe5ce6674412a74167fd074824a" ], "author": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Thu Feb 18 02:22:35 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Feb 19 14:52:30 2010 +1100" }, "message": "powerpc: Convert native_tlbie_lock to raw_spinlock\n\nnative_tlbie_lock needs to be a real spinlock in RT. Convert it to\nraw_spinlock.\n\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "be833f3371bd9580d9f5a507390d72452577f394", "tree": "329b435c37f9957f9c65a8a7cba11868b1537e57", "parents": [ "87d31345c0a90ccdf185feed9923ed14764f45dc" ], "author": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Thu Feb 18 02:22:39 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Feb 19 14:52:30 2010 +1100" }, "message": "powerpc: Convert context_lock to raw_spinlock\n\ncontext_lock needs to be a real spinlock in RT. Convert it to\nraw_spinlock.\n\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "efd0f0f385da6ee6d1a22cfe1ac94607ebe2a292", "tree": "6ba1a89db2eb68046c238a7fca9bae4f72d92874", "parents": [ "3bffb6529cf10d48a97ac0d6d789986894c25c37", "c7b66698122796623f1838c0ee6a8e12ec832468" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Feb 18 09:34:38 2010 +1100" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Feb 18 09:34:38 2010 +1100" }, "message": "Merge commit \u0027jwb/next\u0027 into next\n" }, { "commit": "66d99b883419b8df6d0a24ca957da7ab4831cf6e", "tree": "78950f0267b698314487fa6c514481d811e6da0c", "parents": [ "864b9e6fd76489aab422bac62162f57c52e06ed8" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Wed Feb 10 01:03:06 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Feb 17 14:03:15 2010 +1100" }, "message": "powerpc: Convert open coded native hashtable bit lock\n\nNow we have real bit locks use them instead of open coding it.\n\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "ec144a81ade915b5b38adedf10e84690813ed768", "tree": "c94b53c971ab2c39e27433267318b3c7bc86ff1b", "parents": [ "b919ee827e048826786fd7e889a2b04f63382fe6", "88626272549b94310975932a9970d11a9b362a16" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Feb 17 10:00:42 2010 +1100" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Feb 17 10:00:42 2010 +1100" }, "message": "Merge commit \u0027origin/master\u0027 into next\n" }, { "commit": "c7b66698122796623f1838c0ee6a8e12ec832468", "tree": "f4f18204ba82d2d9ec74ba7896b91d823ab3a92c", "parents": [ "573bff5ab9437b4e59ba9be34a7b08bca5ff054a" ], "author": { "name": "Stefan Roese", "email": "sr@denx.de", "time": "Wed Feb 10 03:54:59 2010 +0000" }, "committer": { "name": "Josh Boyer", "email": "jwboyer@linux.vnet.ibm.com", "time": "Fri Feb 12 07:54:45 2010 -0500" }, "message": "powerpc/40x: Add support for PPC40x boards with \u003e 512MB SDRAM\n\nThis patch adds support for boards with more that 512MByte RAM. Currently\nonly 512MB of memory are enabled in the DCCR/ICCR real-mode cache\ncontrol registers. This patch now enables caching in real-mode for\n2GByte.\n\nSigned-off-by: Stefan Roese \u003csr@denx.de\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Josh Boyer \u003cjwboyer@linux.vnet.ibm.com\u003e\nSigned-off-by: Josh Boyer \u003cjwboyer@linux.vnet.ibm.com\u003e\n" }, { "commit": "77058e1adcc439151db41f2b84e4867a88113cd8", "tree": "8467dab77d8b66423f65612d878aef3efb1056ca", "parents": [ "ac73fddfc523bf3c3525d16356b44527c44fae6d" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Mon Feb 08 20:09:03 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Feb 10 13:58:06 2010 +1100" }, "message": "powerpc: Fix address masking bug in hpte_need_flush()\n\nCommit f71dc176aa06359681c30ba6877ffccab6fba3a6 \u0027Make\nhpte_need_flush() correctly mask for multiple page sizes\u0027 introduced\nbug, which is triggered when a kernel with a 64k base page size is run\non a system whose hardware does not 64k hash PTEs. In this case, we\nemulate 64k pages with multiple 4k hash PTEs, however in\nhpte_need_flush() we incorrectly only mask the hardware page size from\nthe address, instead of the logical page size. This causes things to\ngo wrong when we later attempt to iterate through the hardware\nsubpages of the logical page.\n\nThis patch corrects the error. It has been tested on pSeries bare\nmetal by Michael Neuling.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "7317ac87119dfb6fac36af4bcc64a25b62b5898d", "tree": "b426ba6d983f0eb0eb6273d392349d8f979f95a2", "parents": [ "66fcb1059deeae072c1bf1536a8e2613028bce3e" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Sun Feb 07 12:30:12 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Feb 09 13:56:07 2010 +1100" }, "message": "powerpc: Convert mmu context allocator from idr to ida\n\nWe can use the much more lightweight ida allocator since we don\u0027t\nneed the pointer storage idr provides.\n\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "9ddc5b6f18fbac07d2746566b73b89e89fdd4e6a", "tree": "aaf691482ac8e36ccccb413b9b698063e6d0b489", "parents": [ "659431fcafd820cc426afedadcc4548933224985" ], "author": { "name": "Uwe Kleine-König", "email": "u.kleine-koenig@pengutronix.de", "time": "Wed Jan 20 17:02:24 2010 +0100" }, "committer": { "name": "Jiri Kosina", "email": "jkosina@suse.cz", "time": "Fri Feb 05 12:22:40 2010 +0100" }, "message": "tree-wide: fix typos \"ammount\" -\u003e \"amount\"\n\nSigned-off-by: Uwe Kleine-König \u003cu.kleine-koenig@pengutronix.de\u003e\nSigned-off-by: Jiri Kosina \u003cjkosina@suse.cz\u003e\n" }, { "commit": "2273130de8b24adeb59231a9a8c6274bf5d35447", "tree": "743140aeb25bc07665e11b95e65cb1ebc84cad4d", "parents": [ "de8164fb2242d77c8a83fb3c63830eb7914d696d" ], "author": { "name": "Thadeu Lima de Souza Cascardo", "email": "cascardo@holoscopio.com", "time": "Sun Jan 17 19:23:14 2010 -0200" }, "committer": { "name": "Jiri Kosina", "email": "jkosina@suse.cz", "time": "Fri Feb 05 12:22:38 2010 +0100" }, "message": "fix comment typo leve -\u003e level in powerpc\n\nSigned-off-by: Thadeu Lima de Souza Cascardo \u003ccascardo@holoscopio.com\u003e\nSigned-off-by: Jiri Kosina \u003cjkosina@suse.cz\u003e\n" }, { "commit": "6c504d423147770d7bd73aab3228726379700786", "tree": "81df38aa7f978cb8edbb2f0bb4c3247633faeded", "parents": [ "24551f64d47af9539a7f324343bffeea09d9dcfa" ], "author": { "name": "Thadeu Lima de Souza Cascardo", "email": "cascardo@holoscopio.com", "time": "Sun Jan 17 11:23:14 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Feb 03 17:39:50 2010 +1100" }, "message": "powerpc: Fix typo s/leve/level/ in TLB code\n\nSigned-off-by: Thadeu Lima de Souza Cascardo \u003ccascardo@holoscopio.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "4bf936b9e484bb8ee5f32bfd1351893810864f58", "tree": "c1ae85550c155bdcd8eb482898d3c0ea52409975", "parents": [ "c81b812a333818c5cc1be2e086c8509d853ebeeb" ], "author": { "name": "Jiri Slaby", "email": "jslaby@suse.cz", "time": "Wed Jan 06 05:24:31 2010 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jan 15 13:20:08 2010 +1100" }, "message": "powerpc: Use helpers for rlimits\n\nMake sure compiler won\u0027t do weird things with limits. E.g. fetching\nthem twice may return 2 different values after writable limits are\nimplemented.\n\nI.e. either use rlimit helpers added in\n3e10e716abf3c71bdb5d86b8f507f9e72236c9cd\nor ACCESS_ONCE if not applicable.\n\nSigned-off-by: Jiri Slaby \u003cjslaby@suse.cz\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: linuxppc-dev@ozlabs.org\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "a1128f8f0ff06ccbea5d6b4a69446b506c57bfbc", "tree": "b537d9cbe2678b4c6a986d95918c1ca2e4fd1a9c", "parents": [ "c3a66359398028cd8e5f32611950dc7dc32ea2f2" ], "author": { "name": "David Gibson", "email": "dwg@au1.ibm.com", "time": "Wed Dec 16 14:29:56 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Dec 18 14:55:44 2009 +1100" }, "message": "powerpc/mm: Fix stupid bug in subpge protection handling\n\nCommit d28513bc7f675d28b479db666d572e078ecf182d (\"Fix bug in pagetable\ncache cleanup with CONFIG_PPC_SUBPAGE_PROT\"), itself a fix for\nbreakage caused by an earlier clean up patch of mine, contains a\nstupid bug. I changed the parameters of the subpage_protection()\nfunction, but failed to update one of the callers.\n\nThis patch fixes it, and replaces a void * with a typed pointer so\nthat the compiler will warn on such an error in future.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "f04b10cddb0fbceadbad7af38c31543298948d8f", "tree": "c2c00dd85d8bd867e787f72cfaa6003283ed1c56", "parents": [ "5c3399198791f7f828eb9fd504dbb46eef3cb472" ], "author": { "name": "Yang Li", "email": "leoli@freescale.com", "time": "Mon Dec 14 03:01:49 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Dec 18 14:54:27 2009 +1100" }, "message": "powerpc/mm: Fix typo of cpumask_clear_cpu()\n\nThe function name of cpumask_clear_cpu was not correct. Fortunately\nnobody uses that code with hotplug yet :-)\n\nReported-by: Jin Qing \u003cb24347@freescale.com\u003e\nSigned-off-by: Li Yang \u003cleoli@freescale.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "5c3399198791f7f828eb9fd504dbb46eef3cb472", "tree": "c090c3565204d7d81aec31c3317818cc6d608480", "parents": [ "01ae45bcd48527e90923d4a247259770eb836d2b" ], "author": { "name": "Sachin P. Sant", "email": "sachinp@in.ibm.com", "time": "Sun Dec 13 21:15:12 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Dec 18 14:54:27 2009 +1100" }, "message": "powerpc/mm: Fix hash_utils_64.c compile errors with DEBUG enabled.\n\nThis time without the funny characters.\n\nFix following build errors generated with DEBUG\u003d1\n\ncc1: warnings being treated as errors\narch/powerpc/mm/hash_utils_64.c: In function \u0027htab_dt_scan_page_sizes\u0027:\narch/powerpc/mm/hash_utils_64.c:343: error: format \u0027%04x\u0027 expects type \u0027unsigned int\u0027, but argument 4 has type \u0027long unsigned int\u0027\narch/powerpc/mm/hash_utils_64.c:343: error: format \u0027%08x\u0027 expects type \u0027unsigned int\u0027, but argument 5 has type \u0027long unsigned int\u0027\narch/powerpc/mm/hash_utils_64.c: In function \u0027htab_initialize\u0027:\narch/powerpc/mm/hash_utils_64.c:666: error: format \u0027%x\u0027 expects type \u0027unsigned int\u0027, but argument 4 has type \u0027long unsigned int\u0027\n... SNIP ...\n\nSigned-off-by: Sachin Sant \u003csachinp@in.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "50891457f1001450be61be0861b2b49abdcb5fb9", "tree": "655ba01774854f86665aca52478527e8798fa520", "parents": [ "030bdc3fd0807b6097a937468859f4b4baf1b950" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Dec 08 21:08:44 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Dec 18 14:54:26 2009 +1100" }, "message": "powerpc/mm: Fix a WARN_ON() with CONFIG_DEBUG_PAGEALLOC and CONFIG_DEBUG_VM\n\nSet need to call __set_pte_at() and not set_pte_at() from __change_page_attr()\nsince the later will perform checks with CONFIG_DEBUG_VM that aren\u0027t suitable\nto the way we override an existing PTE. (More specifically, it doesn\u0027t let\nyou write over a present PTE).\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "a73611b6aafa3b902524dad2d68e378c4ec9f4db", "tree": "5dc4877055a2297d9f7f5db4cf6a5a7aad392dd0", "parents": [ "5fa3577b1a1202972e6e419040438c29f39f59cc", "ae4cec4736969ec2196a6bbce4ab263ff7cb7eef" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 13:26:53 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 13:26:53 2009 -0800" }, "message": "Merge branch \u0027next\u0027 of git://git.secretlab.ca/git/linux-2.6\n\n* \u0027next\u0027 of git://git.secretlab.ca/git/linux-2.6: (23 commits)\n powerpc: fix up for mmu_mapin_ram api change\n powerpc: wii: allow ioremap within the memory hole\n powerpc: allow ioremap within reserved memory regions\n wii: use both mem1 and mem2 as ram\n wii: bootwrapper: add fixup to calc useable mem2\n powerpc: gamecube/wii: early debugging using usbgecko\n powerpc: reserve fixmap entries for early debug\n powerpc: wii: default config\n powerpc: wii: platform support\n powerpc: wii: hollywood interrupt controller support\n powerpc: broadway processor support\n powerpc: wii: bootwrapper bits\n powerpc: wii: device tree\n powerpc: gamecube: default config\n powerpc: gamecube: platform support\n powerpc: gamecube/wii: flipper interrupt controller support\n powerpc: gamecube/wii: udbg support for usbgecko\n powerpc: gamecube/wii: do not include PCI support\n powerpc: gamecube/wii: declare as non-coherent platforms\n powerpc: gamecube/wii: introduce GAMECUBE_COMMON\n ...\n\nFix up conflicts in arch/powerpc/mm/fsl_booke_mmu.c.\n\nHopefully even close to correctly.\n" }, { "commit": "ae4cec4736969ec2196a6bbce4ab263ff7cb7eef", "tree": "23ba5a6155ff43e51b32f9feb1378dc9d3fe2352", "parents": [ "c0577eeee0101433a0d929699f4543a1ff3c3014" ], "author": { "name": "Stephen Rothwell", "email": "sfr@canb.auug.org.au", "time": "Mon Dec 14 09:04:24 2009 -0700" }, "committer": { "name": "Grant Likely", "email": "grant.likely@secretlab.ca", "time": "Mon Dec 14 09:04:24 2009 -0700" }, "message": "powerpc: fix up for mmu_mapin_ram api change\n\nToday\u0027s linux-next build (powerpc ppc44x_defconfig) failed like this:\n\narch/powerpc/mm/pgtable_32.c: In function \u0027mapin_ram\u0027:\narch/powerpc/mm/pgtable_32.c:318: error: too many arguments to function \u0027mmu_mapin_ram\u0027\n\nCasued by commit de32400dd26e743c5d500aa42d8d6818b79edb73 (\"wii: use both\nmem1 and mem2 as ram\").\n\nSigned-off-by: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nSigned-off-by: Grant Likely \u003cgrant.likely@secretlab.ca\u003e\n" }, { "commit": "c5df7f775148723de39274537a886e9502eef336", "tree": "548acbcef58b1d60308f7e7cd894d514583895a2", "parents": [ "de32400dd26e743c5d500aa42d8d6818b79edb73" ], "author": { "name": "Albert Herranz", "email": "albert_herranz@yahoo.es", "time": "Sat Dec 12 06:31:54 2009 +0000" }, "committer": { "name": "Grant Likely", "email": "grant.likely@secretlab.ca", "time": "Sat Dec 12 22:24:32 2009 -0700" }, "message": "powerpc: allow ioremap within reserved memory regions\n\nAdd a flag to let a platform ioremap memory regions marked as reserved.\n\nThis flag will be used later by the Nintendo Wii support code to allow\nioremapping the I/O region sitting between MEM1 and MEM2 and marked\nas reserved RAM in the patch \"wii: use both mem1 and mem2 as ram\".\n\nThis will no longer be needed when proper discontig memory support\nfor 32-bit PowerPC is added to the kernel.\n\nSigned-off-by: Albert Herranz \u003calbert_herranz@yahoo.es\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Grant Likely \u003cgrant.likely@secretlab.ca\u003e\n" }, { "commit": "de32400dd26e743c5d500aa42d8d6818b79edb73", "tree": "5fee868e4fac044dca4fb3a18532b67b62c90c96", "parents": [ "02d748a9ee56735641bade9b734dc2fa9be4df4c" ], "author": { "name": "Albert Herranz", "email": "albert_herranz@yahoo.es", "time": "Sat Dec 12 06:31:53 2009 +0000" }, "committer": { "name": "Grant Likely", "email": "grant.likely@secretlab.ca", "time": "Sat Dec 12 22:24:31 2009 -0700" }, "message": "wii: use both mem1 and mem2 as ram\n\nThe Nintendo Wii video game console has two discontiguous RAM regions:\n- MEM1: 24MB @ 0x00000000\n- MEM2: 64MB @ 0x10000000\n\nUnfortunately, the kernel currently does not support discontiguous RAM\nmemory regions on 32-bit PowerPC platforms.\n\nThis patch adds a series of workarounds to allow the use of the second\nmemory region (MEM2) as RAM by the kernel.\nBasically, a single range of memory from the beginning of MEM1 to the\nend of MEM2 is reported to the kernel, and a memory reservation is\ncreated for the hole between MEM1 and MEM2.\n\nWith this patch the system is able to use all the available RAM and not\njust ~27% of it.\n\nThis will no longer be needed when proper discontig memory support\nfor 32-bit PowerPC is added to the kernel.\n\nSigned-off-by: Albert Herranz \u003calbert_herranz@yahoo.es\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Grant Likely \u003cgrant.likely@secretlab.ca\u003e\n" }, { "commit": "5efab4a02c89c252fb4cce097aafde5f8208dbfe", "tree": "52816daf92f813f8b53149ff2f177337d313e22d", "parents": [ "0285ae37d4366b2d614df0c83cb413cf59ad8944" ], "author": { "name": "Joakim Tjernlund", "email": "joakim.tjernlund@transmode.se", "time": "Fri Nov 20 00:21:02 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Dec 09 17:10:35 2009 +1100" }, "message": "powerpc/8xx: Invalidate non present TLBs\n\n8xx sometimes need to load a invalid/non-present TLBs in\nit DTLB asm handler.\n\nThese must be invalidated separaly as linux mm don\u0027t.\n\nSigned-off-by: Joakim Tjernlund \u003cJoakim.Tjernlund@transmode.se\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "d28513bc7f675d28b479db666d572e078ecf182d", "tree": "0d9ba33a8e0ae40f7d2e34f8fd0607ab1a63a7e9", "parents": [ "5a7b4193e564d1611ecf1cd859aed60d5612d78f" ], "author": { "name": "David Gibson", "email": "dwg@au1.ibm.com", "time": "Thu Nov 26 18:56:04 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Dec 08 15:59:33 2009 +1100" }, "message": "powerpc/mm: Fix pgtable cache cleanup with CONFIG_PPC_SUBPAGE_PROT\n\nCommit a0668cdc154e54bf0c85182e0535eea237d53146 cleans up the handling\nof kmem_caches for allocating various levels of pagetables.\nUnfortunately, it conflicts badly with CONFIG_PPC_SUBPAGE_PROT, due to\nthe latter\u0027s cleverly hidden technique of adding some extra allocation\nspace to the top level page directory to store the extra information\nit needs.\n\nSince that extra allocation really doesn\u0027t fit into the cleaned up\npage directory allocating scheme, this patch alters\nCONFIG_PPC_SUBPAGE_PROT to instead allocate its struct\nsubpage_prot_table as part of the mm_context_t.\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "5a7b4193e564d1611ecf1cd859aed60d5612d78f", "tree": "8831669121df3d50845718b848d7c6e4bc51be26", "parents": [ "86f9e097f340fd0fbd37afe92bd5453f5a84cbca" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Dec 02 09:28:35 2009 +1100" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Dec 02 09:28:35 2009 +1100" }, "message": "Revert \"powerpc/mm: Fix bug in pagetable cache cleanup with CONFIG_PPC_SUBPAGE_PROT\"\n\nThis reverts commit c045256d146800ea1d741a8e9e377dada6b7e195.\n\nIt breaks build when CONFIG_PPC_SUBPAGE_PROT is not set. I will\ncommit a fixed version separately\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "39adfa540fa0b32e41b2a5a9e225384009ae6128", "tree": "7cbb8f5e4b2be480b9a0bd37fa57a0ebf6981ab7", "parents": [ "c045256d146800ea1d741a8e9e377dada6b7e195" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Mon Nov 23 20:03:40 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Nov 27 14:24:30 2009 +1100" }, "message": "powerpc/mm: Fix bug in gup_hugepd()\n\nCommit a4fe3ce7699bfe1bd88f816b55d42d8fe1dac655 introduced a new\nget_user_pages() path for hugepages on powerpc. Unfortunately, there\nis a bug in it\u0027s loop logic, which can cause it to overrun the end of\nthe intended region. This came about by copying the logic from the\nnormal page path, which assumes the address and end parameters have\nbeen pagesize aligned at the top-level. Since they\u0027re not *hugepage*\nsize aligned, the simplistic logic could step over the end of the gup\nregion without triggering the loop end condition.\n\nThis patch fixes the bug by using the technique that the normal page\npath uses in levels above the lowest to truncate the ending address to\nsomething we know we\u0027ll match with.\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "c045256d146800ea1d741a8e9e377dada6b7e195", "tree": "4369d1f7c0859a373321c9b3b2d2a101a63282fc", "parents": [ "1e43bee9c70654b4d52472c19e5f0a0cc18b6b36" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Mon Nov 23 19:31:14 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Nov 27 14:24:29 2009 +1100" }, "message": "powerpc/mm: Fix bug in pagetable cache cleanup with CONFIG_PPC_SUBPAGE_PROT\n\nCommit a0668cdc154e54bf0c85182e0535eea237d53146 cleans up the handling\nof kmem_caches for allocating various levels of pagetables.\nUnfortunately, it conflicts badly with CONFIG_PPC_SUBPAGE_PROT, due to\nthe latter\u0027s cleverly hidden technique of adding some extra allocation\nspace to the top level page directory to store the extra information\nit needs.\n\nSince that extra allocation really doesn\u0027t fit into the cleaned up\npage directory allocating scheme, this patch alters\nCONFIG_PPC_SUBPAGE_PROT to instead allocate its struct\nsubpage_prot_table as part of the mm_context_t.\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "8b27f0b61db57f5555fc2d3fc95c3ea9fd1a9d6c", "tree": "a1b1181a62555b2d76b1d63b31a873c42f26d4d6", "parents": [ "5753c082f66eca5be81f6bda85c1718c5eea6ada" ], "author": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Thu Oct 15 12:49:01 2009 -0500" }, "committer": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Fri Nov 20 16:45:33 2009 -0600" }, "message": "powerpc/fsl-booke: Rework TLB CAM code\n\nRe-write the code so its more standalone and fixed some issues:\n* Bump\u0027d # of CAM entries to 64 to support e500mc\n* Make the code handle MAS7 properly\n* Use pr_cont instead of creating a string as we go\n\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\n" }, { "commit": "0526484aa345adbf790d1201a6f5d09be0a648a3", "tree": "8da37ac2858a960e80dc59ebc4afc460935724f4", "parents": [ "e0ea8b2c0677e6cc44a0e5b867be48867f91de5b", "aa021baa3295fa6e3f367d80f8955dd5176656eb" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Nov 12 10:59:04 2009 +1100" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Nov 12 10:59:04 2009 +1100" }, "message": "Merge commit \u0027origin/master\u0027 into next\n" }, { "commit": "e85a47106abb928e048d89d7fa48f982fcb018aa", "tree": "22b19d0e8f06dfdb9186d8395ff75aa3bd430090", "parents": [ "4ab79aa801b6b4f2e2fb508d6107cdd9320d682d" ], "author": { "name": "Alexander Graf", "email": "agraf@suse.de", "time": "Mon Nov 02 12:02:30 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Nov 05 16:50:25 2009 +1100" }, "message": "Split init_new_context and destroy_context\n\nFor KVM we need to allocate a new context id, but don\u0027t really care about\nall the mm context around it.\n\nSo let\u0027s split the alloc and destroy functions for the context id, so we can\ngrab one without allocating an mm context.\n\nSigned-off-by: Alexander Graf \u003cagraf@suse.de\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "4ab79aa801b6b4f2e2fb508d6107cdd9320d682d", "tree": "9b3d92f8c6db41404fafbc2d2fa1e04bbc3a4411", "parents": [ "62908905b2fd98c11bd472c1e617d35eff33fc84" ], "author": { "name": "Alexander Graf", "email": "agraf@suse.de", "time": "Fri Oct 30 05:47:19 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Nov 05 16:50:24 2009 +1100" }, "message": "Export symbols for KVM module\n\nWe want to be able to build KVM as a module. To enable us doing so, we\nneed some more exports from core Linux parts.\n\nThis patch exports all functions and variables that are required for KVM.\n\nSigned-off-by: Alexander Graf \u003cagraf@suse.de\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "f1167fb318f0ff0bcb9cbb57bb6d16ad450f0cfb", "tree": "a3ebf98234b27fde62800fff6898381698897fea", "parents": [ "5a1eb5c4453207ad9e7f6e8ca4f8db289743c993" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@au1.ibm.com", "time": "Wed Nov 04 13:39:52 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Nov 05 16:41:59 2009 +1100" }, "message": "powerpc/mm: Remove debug context clamping from nohash code\n\nI inadvertently left that debug code enabled, causing the number of\ncontexts to be clamped to 31 which is going to slow things down on\n4xx and just plain breaks 8xx\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "0895ecda79428df48501e48dd0a868e0c8e1aae2", "tree": "8ecfc6e0bf9c47c793df4c1a1bf1f503c9351281", "parents": [ "883a3e523672ebba2ec3969837ba02af4f70fae2" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Mon Oct 26 19:24:31 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Oct 30 17:21:23 2009 +1100" }, "message": "powerpc/mm: Bring hugepage PTE accessor functions back into sync with normal accessors\n\nThe hugepage arch code provides a number of hook functions/macros\nwhich mirror the functionality of various normal page pte access\nfunctions. Various changes in the normal page accessors (in\nparticular BenH\u0027s recent changes to the handling of lazy icache\nflushing and PAGE_EXEC) have caused the hugepage versions to get out\nof sync with the originals. In some cases, this is a bug, at least on\nsome MMU types.\n\nOne of the reasons that some hooks were not identical to the normal\npage versions, is that the fact we\u0027re dealing with a hugepage needed\nto be passed down do use the correct dcache-icache flush function.\nThis patch makes the main flush_dcache_icache_page() function hugepage\naware (by checking for the PageCompound flag). That in turn means we\ncan make set_huge_pte_at() just a call to set_pte_at() bringing it\nback into sync. As a bonus, this lets us remove the\nhash_huge_page_do_lazy_icache() function, replacing it with a call to\nthe hash_page_do_lazy_icache() function it was based on.\n\nSome other hugepage pte access hooks - huge_ptep_get_and_clear() and\nhuge_ptep_clear_flush() - are not so easily unified, but this patch at\nleast brings them back into sync with the current versions of the\ncorresponding normal page functions.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "883a3e523672ebba2ec3969837ba02af4f70fae2", "tree": "ff8000aab5bc56348bd1b16ac904fe3a9b660b4a", "parents": [ "d1837cba5d5d5458c09f0a2849db2d3c203cb8e9" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Mon Oct 26 19:24:31 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Oct 30 17:20:59 2009 +1100" }, "message": "powerpc/mm: Split hash MMU specific hugepage code into a new file\n\nThis patch separates the parts of hugetlbpage.c which are inherently\nspecific to the hash MMU into a new hugelbpage-hash64.c file.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "d1837cba5d5d5458c09f0a2849db2d3c203cb8e9", "tree": "144a4eb43ed6b9909133dc1ac0619d813e4cb131", "parents": [ "a4fe3ce7699bfe1bd88f816b55d42d8fe1dac655" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Mon Oct 26 19:24:31 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Oct 30 17:20:58 2009 +1100" }, "message": "powerpc/mm: Cleanup initialization of hugepages on powerpc\n\nThis patch simplifies the logic used to initialize hugepages on\npowerpc. The somewhat oddly named set_huge_psize() is renamed to\nadd_huge_page_size() and now does all necessary verification of\nwhether it\u0027s given a valid hugepage sizes (instead of just some) and\ninstantiates the generic hstate structure (but no more).\n\nhugetlbpage_init() now steps through the available pagesizes, checks\nif they\u0027re valid for hugepages by calling add_huge_page_size() and\ninitializes the kmem_caches for the hugepage pagetables. This means\nwe can now eliminate the mmu_huge_psizes array, since we no longer\nneed to pass the sizing information for the pagetable caches from\nset_huge_psize() into hugetlbpage_init()\n\nDetermination of the default huge page size is also moved from the\nhash code into the general hugepage code.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "a4fe3ce7699bfe1bd88f816b55d42d8fe1dac655", "tree": "b72c982ffbb9f05d78a952288d60c4dc2d31a4d9", "parents": [ "a0668cdc154e54bf0c85182e0535eea237d53146" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Mon Oct 26 19:24:31 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Oct 30 17:20:58 2009 +1100" }, "message": "powerpc/mm: Allow more flexible layouts for hugepage pagetables\n\nCurrently each available hugepage size uses a slightly different\npagetable layout: that is, the bottem level table of pointers to\nhugepages is a different size, and may branch off from the normal page\ntables at a different level. Every hugepage aware path that needs to\nwalk the pagetables must therefore look up the hugepage size from the\nslice info first, and work out the correct way to walk the pagetables\naccordingly. Future hardware is likely to add more possible hugepage\nsizes, more layout options and more mess.\n\nThis patch, therefore reworks the handling of hugepage pagetables to\nreduce this complexity. In the new scheme, instead of having to\nconsult the slice mask, pagetable walking code can check a flag in the\nPGD/PUD/PMD entries to see where to branch off to hugepage pagetables,\nand the entry also contains the information (eseentially hugepage\nshift) necessary to then interpret that table without recourse to the\nslice mask. This scheme can be extended neatly to handle multiple\nlevels of self-describing \"special\" hugepage pagetables, although for\nnow we assume only one level exists.\n\nThis approach means that only the pagetable allocation path needs to\nknow how the pagetables should be set out. All other (hugepage)\npagetable walking paths can just interpret the structure as they go.\n\nThere already was a flag bit in PGD/PUD/PMD entries for hugepage\ndirectory pointers, but it was only used for debug. We alter that\nflag bit to instead be a 0 in the MSB to indicate a hugepage pagetable\npointer (normally it would be 1 since the pointer lies in the linear\nmapping). This means that asm pagetable walking can test for (and\npunt on) hugepage pointers with the same test that checks for\nunpopulated page directory entries (beq becomes bge), since hugepage\npointers will always be positive, and normal pointers always negative.\n\nWhile we\u0027re at it, we get rid of the confusing (and grep defeating)\n#defining of hugepte_shift to be the same thing as mmu_huge_psizes.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "a0668cdc154e54bf0c85182e0535eea237d53146", "tree": "84efcadf011e16c240ac9b1c948141fc1cc7d324", "parents": [ "f71dc176aa06359681c30ba6877ffccab6fba3a6" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Wed Oct 28 16:27:18 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Oct 30 17:20:57 2009 +1100" }, "message": "powerpc/mm: Cleanup management of kmem_caches for pagetables\n\nCurrently we have a fair bit of rather fiddly code to manage the\nvarious kmem_caches used to store page tables of various levels. We\ngenerally have two caches holding some combination of PGD, PUD and PMD\ntables, plus several more for the special hugepage pagetables.\n\nThis patch cleans this all up by taking a different approach. Rather\nthan the caches being designated as for PUDs or for hugeptes for 16M\npages, the caches are simply allocated to be a specific size. Thus\nsharing of caches between different types/levels of pagetables happens\nnaturally. The pagetable size, where needed, is passed around encoded\nin the same way as {PGD,PUD,PMD}_INDEX_SIZE; that is n where the\npagetable contains 2^n pointers.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "f71dc176aa06359681c30ba6877ffccab6fba3a6", "tree": "b72d97c2db323ab94399cd2633108c0a00a5da31", "parents": [ "8be8cf5b47f72096e42bf88cc3afff7a942a346c" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Mon Oct 26 19:24:31 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Oct 30 17:20:57 2009 +1100" }, "message": "powerpc/mm: Make hpte_need_flush() correctly mask for multiple page sizes\n\nCurrently, hpte_need_flush() only correctly flushes the given address\nfor normal pages. Callers for hugepages are required to mask the\naddress themselves.\n\nBut hpte_need_flush() already looks up the page sizes for its own\nreasons, so this is a rather silly imposition on the callers. This\npatch alters it to mask based on the pagesize it has looked up itself,\nand removes the awkward masking code in the hugepage caller.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "8d8997f34e66124577db52f6e7ee10ab5f869e07", "tree": "cfca0e3e7251d1a36b311283772725589822b93d", "parents": [ "aee7a283bb1e7d722f3431e0689c2c281ad0c1f6" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Mon Oct 12 20:43:47 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Oct 14 16:58:36 2009 +1100" }, "message": "powerpc/mm: Fix hang accessing top of vmalloc space\n\nOn pSeries, we always force the IO space to be mapped using 4K\npages even with a 64K base page size to cope with some limitations\nin the HV interface to some devices.\n\nHowever, the SLB miss handler code to discriminate between vmalloc\nand ioremap space uses a CPU feature section such that the code\nis nop\u0027ed out when the processor support large pages non-cachable\nmappings.\n\nThus, we end up always using the ioremap page size for vmalloc\nsegments on such processors, causing a discrepency between the\nsegment and the hash table, and thus a hang continously hashing\nthe page.\n\nIt works for the first segment of the vmalloc space since that\nsegment is \"bolted\" in by C code correctly, and thankfully we\nalmost never use the vmalloc space beyond the first segment,\nbut the new percpu code made the bug happen.\n\nThis fixes it by removing the feature section from the assembly,\nwe now always do the comparison between vmalloc and ioremap.\n\nSigned-off-by; Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "e0908085fc2391c85b85fb814ae1df377c8e0dcb", "tree": "46560ab77e41c84ff15c05b5753d7512f8850ba8", "parents": [ "daf8f40391b2a1978ea2071c20959d91fade6b1a" ], "author": { "name": "Rex Feany", "email": "RFeany@mrv.com", "time": "Wed Sep 23 14:45:52 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Sep 24 15:56:30 2009 +1000" }, "message": "powerpc/8xx: Fix regression introduced by cache coherency rewrite\n\nAfter upgrading to the latest kernel on my mpc875 userspace started\nrunning incredibly slow (hours to get to a shell, even!).\nI tracked it down to commit 8d30c14cab30d405a05f2aaceda1e9ad57800f36,\nthat patch removed a work-around for the 8xx. Adding it\nback makes my problem go away.\n\nSigned-off-by: Rex Feany \u003crfeany@mrv.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "b9eceb2307f8dda124669a9dc213aad8c1569b5a", "tree": "c7fbabaf506464a6be54f2eaa42dd798252283ec", "parents": [ "5c8f382c0b96aedcd709c05eae13bd684e16417e" ], "author": { "name": "Huang Weiyi", "email": "weiyi.huang@gmail.com", "time": "Wed Sep 16 03:09:22 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Sep 24 15:31:42 2009 +1000" }, "message": "powerpc/mm: Remove duplicated #include\n\nRemove duplicated #include(\u0027s) in\n arch/powerpc/mm/tlb_low_64e.S\n\nSigned-off-by: Huang Weiyi \u003cweiyi.huang@gmail.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "3089aa1b0c07fb7c48f9829c619f50198307789d", "tree": "63677c773c559458ba301bd448ecce6e007b6742", "parents": [ "908eedc6168bd92e89f90d89fa389065a36358fa" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Sep 22 16:45:48 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Sep 23 07:39:41 2009 -0700" }, "message": "kcore: use registerd physmem information\n\nFor /proc/kcore, each arch registers its memory range by kclist_add().\nIn usual,\n\n\t- range of physical memory\n\t- range of vmalloc area\n\t- text, etc...\n\nare registered but \"range of physical memory\" has some troubles. It\ndoesn\u0027t updated at memory hotplug and it tend to include unnecessary\nmemory holes. Now, /proc/iomem (kernel/resource.c) includes required\nphysical memory range information and it\u0027s properly updated at memory\nhotplug. Then, it\u0027s good to avoid using its own code(duplicating\ninformation) and to rebuild kclist for physical memory based on\n/proc/iomem.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Jiri Slaby \u003cjirislaby@gmail.com\u003e\nCc: Ralf Baechle \u003cralf@linux-mips.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: WANG Cong \u003cxiyou.wangcong@gmail.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@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": "908eedc6168bd92e89f90d89fa389065a36358fa", "tree": "612881abb2aae920ab1e62e88990ee7b6a988f51", "parents": [ "9492587cf35d370db33ef4b38375dfb35a105b61" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Sep 22 16:45:46 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Sep 23 07:39:41 2009 -0700" }, "message": "walk system ram range\n\nOriginally, walk_memory_resource() was introduced to traverse all memory\nof \"System RAM\" for detecting memory hotplug/unplug range. For doing so,\nflags of IORESOUCE_MEM|IORESOURCE_BUSY was used and this was enough for\nmemory hotplug.\n\nBut for using other purpose, /proc/kcore, this may includes some firmware\narea marked as IORESOURCE_BUSY | IORESOUCE_MEM. This patch makes the\ncheck strict to find out busy \"System RAM\".\n\nNote: PPC64 keeps their own walk_memory_resouce(), which walk through\nppc64\u0027s lmb informaton. Because old kclist_add() is called per lmb, this\npatch makes no difference in behavior, finally.\n\nAnd this patch removes CONFIG_MEMORY_HOTPLUG check from this function.\nBecause pfn_valid() just show \"there is memmap or not* and cannot be used\nfor \"there is physical memory or not\", this function is useful in generic\nto scan physical memory range.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Ralf Baechle \u003cralf@linux-mips.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: WANG Cong \u003cxiyou.wangcong@gmail.com\u003e\nCc: Américo Wang \u003cxiyou.wangcong@gmail.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Roland Dreier \u003crolandd@cisco.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a0614da88b67ffa3dbcc0d40b817e682c7c4a0ee", "tree": "ae4ca3a8553592af41f7c2cc1a64912d934f6baf", "parents": [ "c30bb2a25fcfde6157e6154a32c14686fb0bedbe" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Sep 22 16:45:44 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Sep 23 07:39:41 2009 -0700" }, "message": "kcore: register vmalloc area in generic way\n\nFor /proc/kcore, vmalloc areas are registered per arch. But, all of them\nregisters same range of [VMALLOC_START...VMALLOC_END) This patch unifies\nthem. By this. archs which have no kclist_add() hooks can see vmalloc\narea correctly.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Ralf Baechle \u003cralf@linux-mips.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: WANG Cong \u003cxiyou.wangcong@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "c30bb2a25fcfde6157e6154a32c14686fb0bedbe", "tree": "afa4811d46e5f9035a035b2c8c864bbb6c5af049", "parents": [ "2ef43ec772551e975a6ea7cf22b59c84955aadf9" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Sep 22 16:45:43 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Sep 23 07:39:41 2009 -0700" }, "message": "kcore: add kclist types\n\nPresently, kclist_add() only eats start address and size as its arguments.\nConsidering to make kclist dynamically reconfigulable, it\u0027s necessary to\nknow which kclists are for System RAM and which are not.\n\nThis patch add kclist types as\n KCORE_RAM\n KCORE_VMALLOC\n KCORE_TEXT\n KCORE_OTHER\n\nThis \"type\" is used in a patch following this for detecting KCORE_RAM.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Ralf Baechle \u003cralf@linux-mips.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: WANG Cong \u003cxiyou.wangcong@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "cc013a88906bad9d2832d6316de1c7dbc1c2a794", "tree": "c47d1bc76cf9bbf94c328ca6e15ac99ddbab7603", "parents": [ "73d7c33e81aed92ac185950a20407c1a2ea65a83" ], "author": { "name": "Geert Uytterhoeven", "email": "Geert.Uytterhoeven@sonycom.com", "time": "Mon Sep 21 17:02:36 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:34 2009 -0700" }, "message": "arches: drop superfluous casts in nr_free_pages() callers\n\nCommit 96177299416dbccb73b54e6b344260154a445375 (\"Drop free_pages()\")\nmodified nr_free_pages() to return \u0027unsigned long\u0027 instead of \u0027unsigned\nint\u0027. This made the casts to \u0027unsigned long\u0027 in most callers superfluous,\nso remove them.\n\n[akpm@linux-foundation.org: coding-style fixes]\nSigned-off-by: Geert Uytterhoeven \u003cGeert.Uytterhoeven@sonycom.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nAcked-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nAcked-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\nAcked-by: David S. Miller \u003cdavem@davemloft.net\u003e\nAcked-by: Kyle McMartin \u003ckyle@mcmartin.ca\u003e\nAcked-by: WANG Cong \u003cxiyou.wangcong@gmail.com\u003e\nCc: Richard Henderson \u003crth@twiddle.net\u003e\nCc: Ivan Kokshaysky \u003cink@jurassic.park.msu.ru\u003e\nCc: Haavard Skinnemoen \u003chskinnemoen@atmel.com\u003e\nCc: Mikael Starvik \u003cstarvik@axis.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Hirokazu Takata \u003ctakata@linux-m32r.org\u003e\nCc: Ralf Baechle \u003cralf@linux-mips.org\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: Chris Zankel \u003czankel@tensilica.com\u003e\nCc: Michal Simek \u003cmonstr@monstr.eu\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "cdd6c482c9ff9c55475ee7392ec8f672eddb7be6", "tree": "81f98a3ab46c589792057fe2392c1e10f8ad7893", "parents": [ "dfc65094d0313cc48969fa60bcf33d693aeb05a7" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Sep 21 12:02:48 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Sep 21 14:28:04 2009 +0200" }, "message": "perf: Do the big rename: Performance Counters -\u003e Performance Events\n\nBye-bye Performance Counters, welcome Performance Events!\n\nIn the past few months the perfcounters subsystem has grown out its\ninitial role of counting hardware events, and has become (and is\nbecoming) a much broader generic event enumeration, reporting, logging,\nmonitoring, analysis facility.\n\nNaming its core object \u0027perf_counter\u0027 and naming the subsystem\n\u0027perfcounters\u0027 has become more and more of a misnomer. With pending\ncode like hw-breakpoints support the \u0027counter\u0027 name is less and\nless appropriate.\n\nAll in one, we\u0027ve decided to rename the subsystem to \u0027performance\nevents\u0027 and to propagate this rename through all fields, variables\nand API names. (in an ABI compatible fashion)\n\nThe word \u0027event\u0027 is also a bit shorter than \u0027counter\u0027 - which makes\nit slightly more convenient to write/handle as well.\n\nThanks goes to Stephane Eranian who first observed this misnomer and\nsuggested a rename.\n\nUser-space tooling and ABI compatibility is not affected - this patch\nshould be function-invariant. (Also, defconfigs were not touched to\nkeep the size down.)\n\nThis patch has been generated via the following script:\n\n FILES\u003d$(find * -type f | grep -vE \u0027oprofile|[^K]config\u0027)\n\n sed -i \\\n -e \u0027s/PERF_EVENT_/PERF_RECORD_/g\u0027 \\\n -e \u0027s/PERF_COUNTER/PERF_EVENT/g\u0027 \\\n -e \u0027s/perf_counter/perf_event/g\u0027 \\\n -e \u0027s/nb_counters/nb_events/g\u0027 \\\n -e \u0027s/swcounter/swevent/g\u0027 \\\n -e \u0027s/tpcounter_event/tp_event/g\u0027 \\\n $FILES\n\n for N in $(find . -name perf_counter.[ch]); do\n M\u003d$(echo $N | sed \u0027s/perf_counter/perf_event/g\u0027)\n mv $N $M\n done\n\n FILES\u003d$(find . -name perf_event.*)\n\n sed -i \\\n -e \u0027s/COUNTER_MASK/REG_MASK/g\u0027 \\\n -e \u0027s/COUNTER/EVENT/g\u0027 \\\n -e \u0027s/\\\u003cevent\\\u003e/event_id/g\u0027 \\\n -e \u0027s/counter/event/g\u0027 \\\n -e \u0027s/Counter/Event/g\u0027 \\\n $FILES\n\n... to keep it as correct as possible. This script can also be\nused by anyone who has pending perfcounters patches - it converts\na Linux kernel tree over to the new naming. We tried to time this\nchange to the point in time where the amount of pending patches\nis the smallest: the end of the merge window.\n\nNamespace clashes were fixed up in a preparatory patch - and some\nstylistic fallout will be fixed up in a subsequent patch.\n\n( NOTE: \u0027counters\u0027 are still the proper terminology when we deal\n with hardware registers - and these sed scripts are a bit\n over-eager in renaming them. I\u0027ve undone some of that, but\n in case there\u0027s something left where \u0027counter\u0027 would be\n better than \u0027event\u0027 we can undo that on an individual basis\n instead of touching an otherwise nicely automated patch. )\n\nSuggested-by: Stephane Eranian \u003ceranian@google.com\u003e\nAcked-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nReviewed-by: Arjan van de Ven \u003carjan@linux.intel.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc: Kyle McMartin \u003ckyle@mcmartin.ca\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: \"H. Peter Anvin\" \u003chpa@zytor.com\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "723e9db7a46e328527cc3da2b478b831184fe828", "tree": "cdeda255633057dcb4c84097bed27b2bbf76970f", "parents": [ "ada3fa15057205b7d3f727bba5cd26b5912e350f", "d331d8305cba713605854aab63a000fb892353a7" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 15 09:51:09 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 15 09:51:09 2009 -0700" }, "message": "Merge branch \u0027next\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc\n\n* \u0027next\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (134 commits)\n powerpc/nvram: Enable use Generic NVRAM driver for different size chips\n powerpc/iseries: Fix oops reading from /proc/iSeries/mf/*/cmdline\n powerpc/ps3: Workaround for flash memory I/O error\n powerpc/booke: Don\u0027t set DABR on 64-bit BookE, use DAC1 instead\n powerpc/perf_counters: Reduce stack usage of power_check_constraints\n powerpc: Fix bug where perf_counters breaks oprofile\n powerpc/85xx: Fix SMP compile error and allow NULL for smp_ops\n powerpc/irq: Improve nanodoc\n powerpc: Fix some late PowerMac G5 with PCIe ATI graphics\n powerpc/fsl-booke: Use HW PTE format if CONFIG_PTE_64BIT\n powerpc/book3e: Add missing page sizes\n powerpc/pseries: Fix to handle slb resize across migration\n powerpc/powermac: Thermal control turns system off too eagerly\n powerpc/pci: Merge ppc32 and ppc64 versions of phb_scan()\n powerpc/405ex: support cuImage via included dtb\n powerpc/405ex: provide necessary fixup function to support cuImage\n powerpc/40x: Add support for the ESTeem 195E (PPC405EP) SBC\n powerpc/44x: Add Eiger AMCC (AppliedMicro) PPC460SX evaluation board support.\n powerpc/44x: Update Arches defconfig\n powerpc/44x: Update Arches dts\n ...\n\nFix up conflicts in drivers/char/agp/uninorth-agp.c\n" }, { "commit": "ada3fa15057205b7d3f727bba5cd26b5912e350f", "tree": "60962fc9e4021b92f484d1a58e72cd3906d4f3db", "parents": [ "2f82af08fcc7dc01a7e98a49a5995a77e32a2925", "5579fd7e6aed8860ea0c8e3f11897493153b10ad" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 15 09:39:44 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 15 09:39:44 2009 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (46 commits)\n powerpc64: convert to dynamic percpu allocator\n sparc64: use embedding percpu first chunk allocator\n percpu: kill lpage first chunk allocator\n x86,percpu: use embedding for 64bit NUMA and page for 32bit NUMA\n percpu: update embedding first chunk allocator to handle sparse units\n percpu: use group information to allocate vmap areas sparsely\n vmalloc: implement pcpu_get_vm_areas()\n vmalloc: separate out insert_vmalloc_vm()\n percpu: add chunk-\u003ebase_addr\n percpu: add pcpu_unit_offsets[]\n percpu: introduce pcpu_alloc_info and pcpu_group_info\n percpu: move pcpu_lpage_build_unit_map() and pcpul_lpage_dump_cfg() upward\n percpu: add @align to pcpu_fc_alloc_fn_t\n percpu: make @dyn_size mandatory for pcpu_setup_first_chunk()\n percpu: drop @static_size from first chunk allocators\n percpu: generalize first chunk allocator selection\n percpu: build first chunk allocators selectively\n percpu: rename 4k first chunk allocator to page\n percpu: improve boot messages\n percpu: fix pcpu_reclaim() locking\n ...\n\nFix trivial conflict as by Tejun Heo in kernel/sched.c\n" }, { "commit": "46db2f86a3b2a94e0b33e0b4548fb7b7b6bdff66", "tree": "6aef8ab146a54d04dd207b0f85f362a4aee3ef5d", "parents": [ "b8e4a7dae53760b9791aca96e74366078692d90f" ], "author": { "name": "Brian King", "email": "brking@linux.vnet.ibm.com", "time": "Fri Aug 28 12:06:29 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Sep 02 16:19:01 2009 +1000" }, "message": "powerpc/pseries: Fix to handle slb resize across migration\n\nThe SLB can change sizes across a live migration, which was not\nbeing handled, resulting in possible machine crashes during\nmigration if migrating to a machine which has a smaller max SLB\nsize than the source machine. Fix this by first reducing the\nSLB size to the minimum possible value, which is 32, prior to\nmigration. Then during the device tree update which occurs after\nmigration, we make the call to ensure the SLB gets updated. Also\nadd the slb_size to the lparcfg output so that the migration\ntools can check to make sure the kernel has this capability\nbefore allowing migration in scenarios where the SLB size will change.\n\nBenH: Fixed #include \u003casm/mmu-hash64.h\u003e -\u003e \u003casm/mmu.h\u003e to avoid\n breaking ppc32 build\n\nSigned-off-by: Brian King \u003cbrking@linux.vnet.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "df5d6ecf8157245ef733db87597adb2c6e2510da", "tree": "9b1df8a76713d55ca08d11bd212281b11f6af652", "parents": [ "23e55f92d4fd733365dd572ea6e9e211387123c2" ], "author": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Mon Aug 24 15:52:48 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Aug 28 14:24:12 2009 +1000" }, "message": "powerpc/mm: Add MMU features for TLB reservation \u0026 Paired MAS registers\n\nSupport for TLB reservation (or TLB Write Conditional) and Paired MAS\nregisters are optional for a processor implementation so we handle\nthem via MMU feature sections.\n\nWe currently only used paired MAS registers to access the full RPN + perm\nbits that are kept in MAS7||MAS3. We assume that if an implementation has\nhardware page table at this time it also implements in TLB reservations.\n\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "3c2ee2d9f41ef43a581b26b677d2b4054ccbd200", "tree": "f427586e5a1fecd1a21d9f4a5e088f31363f5282", "parents": [ "6776426320e151051a16bc7bf86f12d310c9e8ca", "1dcd8ffc81e80a170625883f63f6a5db3cd0428d" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 27 13:13:41 2009 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 27 13:13:41 2009 +1000" }, "message": "Merge commit \u0027kumar/next\u0027 into next\n" }, { "commit": "ea3cc330ac0cd521ff07c7cd432a1848c19a7e92", "tree": "82f3e84e28ebf5ae33d05ec0142c22b30a21c60a", "parents": [ "f480fe3916de2e2cbb6e384cb685f0f1d8272188" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Aug 18 19:00:34 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 27 13:12:51 2009 +1000" }, "message": "powerpc/mm: Cleanup handling of execute permission\n\nThis is an attempt at cleaning up a bit the way we handle execute\npermission on powerpc. _PAGE_HWEXEC is gone, _PAGE_EXEC is now only\ndefined by CPUs that can do something with it, and the myriad of\n#ifdef\u0027s in the I$/D$ coherency code is reduced to 2 cases that\nhopefully should cover everything.\n\nThe logic on BookE is a little bit different than what it was though\nnot by much. Since now, _PAGE_EXEC will be set by the generic code\nfor executable pages, we need to filter out if they are unclean and\nrecover it. However, I don\u0027t expect the code to be more bloated than\nit already was in that area due to that change.\n\nI could boast that this brings proper enforcing of per-page execute\npermissions to all BookE and 40x but in fact, we\u0027ve had that now for\nsome time as a side effect of my previous rework in that area (and\nI didn\u0027t even know it :-) We would only enable execute permission if\nthe page was cache clean and we would only cache clean it if we took\nand exec fault. Since we now enforce that the later only work if\nVM_EXEC is part of the VMA flags, we de-fact already enforce per-page\nexecute permissions... Unless I missed something\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "fc4bdb35fba1c8f464fd85b94a5059e752fc85d4", "tree": "249a02a1515fb814d703215352e86de89f09dfbf", "parents": [ "8934210cfe925f0d3e3089c69e9e88021324801b" ], "author": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Fri Aug 14 09:38:34 2009 -0500" }, "committer": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Mon Aug 24 20:48:05 2009 -0500" }, "message": "powerpc/booke: Move MMUCSR definition into mmu-book3e.h\n\nThe MMUCSR is now defined as part of the Book-3E architecture so we\ncan move it into mmu-book3e.h and add some of the additional bits\ndefined by the architecture specs.\n\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\n" }, { "commit": "4f0dbc2781b9dc457159b676289f874ab2dc3560", "tree": "2b8af0f301eaf0bc47d643b99d48a84611b4bed3", "parents": [ "3c15a68880023722fc794018768df556f438ae98", "20002ded4d937ca87aca6253b874920a96a763c4" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 11:07:56 2009 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 11:07:56 2009 +1000" }, "message": "Merge commit \u0027paulus-perf/master\u0027 into next\n" }, { "commit": "797a747a82e23530ee45d2927bf84f3571c1acb2", "tree": "1d198cf33c42d91b87116ea48dff71327f7bddae", "parents": [ "433abcdf321322495d83c8b571bdf7134622c734" ], "author": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Tue Aug 18 15:21:40 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:28:32 2009 +1000" }, "message": "powerpc/mm: Fix assert_pte_locked to work properly on uniprocessor\n\nSince the pte_lockptr is a spinlock it gets optimized away on\nuniprocessor builds so using spin_is_locked is not correct. We can use\nassert_spin_locked instead and get the proper behavior between UP and\nSMP builds.\n\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "8dcd038a13b8e322c49fe0d3e31a0deaba4fd5fd", "tree": "657cb5c3ef0da7de481ebd2c3297f68653e5d410", "parents": [ "b6c316a1f6447d6dd0fd8d443b66643e328e04fa" ], "author": { "name": "Roel Kluin", "email": "roel.kluin@gmail.com", "time": "Thu Aug 06 16:00:37 2009 -0700" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:27:12 2009 +1000" }, "message": "powerpc/fsl-booke: read buffer overflow\n\ncam[tlbcam_index] is checked before tlbcam_index \u003c ARRAY_SIZE(cam)\n\nSigned-off-by: Roel Kluin \u003croel.kluin@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "67050b5c3e9992d98554bd224d5a7898cc4881ff", "tree": "296c4d21e193c22e3e31f01799c0048f45df41c7", "parents": [ "af984b816530b4725b92e01ecfba7c5e3eab910d" ], "author": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Tue Aug 04 22:33:32 2009 -0500" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:25:12 2009 +1000" }, "message": "powerpc/mm: Fix switch_mmu_context to iterate of the proper list of cpus\n\nIntroduced a temporary variable into our iterating over the list cpus\nthat are threads on the same core. For some reason Ben forgot how for\nloops work.\n\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "2d27cfd3286966c04d4192a9db5a6c7ea60eebf1", "tree": "a9e3feb764da5a2be1a6ef9b3a0bf694e874a424", "parents": [ "32a74949b7337726e76d69f51c48715431126c6c" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Jul 23 23:15:59 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:25:11 2009 +1000" }, "message": "powerpc: Remaining 64-bit Book3E support\n\nThis contains all the bits that didn\u0027t fit in previous patches :-) This\nincludes the actual exception handlers assembly, the changes to the\nkernel entry, other misc bits and wiring it all up in Kconfig.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "32a74949b7337726e76d69f51c48715431126c6c", "tree": "22383b2b4d568c7fc651e1def000049dde7156c3", "parents": [ "25d21ad6e799cccd097b9df2a2fefe19a7e1dfcf" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Jul 23 23:15:58 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:25:10 2009 +1000" }, "message": "powerpc/mm: Add support for SPARSEMEM_VMEMMAP on 64-bit Book3E\n\nThe base TLB support didn\u0027t include support for SPARSEMEM_VMEMMAP, though\nwe did carve out some virtual space for it, the necessary support code\nwasn\u0027t there. This implements it by using 16M pages for now, though the\npage size could easily be changed at runtime if necessary.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "25d21ad6e799cccd097b9df2a2fefe19a7e1dfcf", "tree": "cd381527a069fed6cffa8755cac177639cc48b0b", "parents": [ "a8f7758c1c52a13e031266483efd5525157e43e9" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Jul 23 23:15:47 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:25:09 2009 +1000" }, "message": "powerpc: Add TLB management code for 64-bit Book3E\n\nThis adds the TLB miss handler assembly, the low level TLB flush routines\nalong with the necessary hook for dealing with our virtual page tables\nor indirect TLB entries that need to be flushes when PTE pages are freed.\n\nThere is currently no support for hugetlbfs\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "a8f7758c1c52a13e031266483efd5525157e43e9", "tree": "d2b58130580e5c904b5fdf22f9b27388f93ed913", "parents": [ "dce6670aaa7efece0558010b48d5ef9d421154be" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Jul 23 23:15:45 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:25:09 2009 +1000" }, "message": "powerpc/mm: Move around mmu_gathers definition on 64-bit\n\nThe definition for the global structure mmu_gathers, used by generic code,\nis currently defined in multiple places not including anything used by\n64-bit Book3E. This changes it by moving to one place common to all\nprocessors.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "57e2a99f74b0d3720c97a6aadb57ae6aad3c61ea", "tree": "4268a98ad222dbcf790749aed52417eb0a3a2a35", "parents": [ "0257c99cdfaca53a881339e1cbca638c61569b05" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 28 11:59:34 2009 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:25:06 2009 +1000" }, "message": "powerpc: Add memory management headers for new 64-bit BookE\n\nThis adds the PTE and pgtable format definitions, along with changes\nto the kernel memory map and other definitions related to implementing\nsupport for 64-bit Book3E. This also shields some asm-offset bits that\nare currently only relevant on 32-bit\n\nWe also move the definition of the \"linux\" page size constants to\nthe common mmu.h file and add a few sizes that are relevant to\nembedded processors.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "c7cc58a1ad8dfe3c199d3b6ce50412b86dd3edaf", "tree": "1d1ded72de81743ddd1306677d64757136972402", "parents": [ "cf54dc7cd4f9aab55cd3e1794b0b74c3c88cd1a0" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Jul 23 23:15:28 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:24:56 2009 +1000" }, "message": "powerpc/mm: Rework \u0026 cleanup page table freeing code path\n\nThat patch used to just add a hook to page table flushing but\npulling that string brought out a whole bunch of issues, so it\nnow does that and more:\n\n - We now make the RCU batching of page freeing SMP only, as I\nbelieve it was intended initially. We make a few more things compile\nto nothing on !CONFIG_SMP\n\n - Some macros are turned into functions, though that forced me to\nout of line a few stuffs due to unsolvable include depenencies,\nhowever it\u0027s probably better that way anyway, it\u0027s not -that-\ncritical code path.\n\n - 32-bit didn\u0027t call pte_free_finish() on tlb_flush() which means\nthat it wouldn\u0027t push out the batch to RCU for delayed freeing when\na bunch of page tables have been freed, they would just stay in there\nuntil the batch gets full.\n\n64-bit BookE will use that hook to maintain the virtually linear\npage tables or the indirect entries in the TLB when using the\nHW loader.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "d4e167da4cb60910f6ac305aee03714937f70b71", "tree": "44a0faf402dd91024544b3450033b80524b25799", "parents": [ "44c58ccc8dc25f78a4f641901f17092c93dd0458" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Jul 23 23:15:24 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:12:41 2009 +1000" }, "message": "powerpc/mm: Make low level TLB flush ops on BookE take additional args\n\nWe need to pass down whether the page is direct or indirect and we\u0027ll\nneed to pass the page size to _tlbil_va and _tlbivax_bcast\n\nWe also add a new low level _tlbil_pid_noind() which does a TLB flush\nby PID but avoids flushing indirect entries if possible\n\nThis implements those new prototypes but defines them with inlines\nor macros so that no additional arguments are actually passed on current\nprocessors.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "a245067e204f69c69abf92d94fc45ec65bf1f07e", "tree": "8a9ee8920c8b42d5d13cd2f7a05f578d99dd438e", "parents": [ "1fe1a21005c14ad772caeb9005580f473c4b6c57" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Jul 23 23:15:16 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:12:40 2009 +1000" }, "message": "powerpc/mm: Add support for early ioremap on non-hash 64-bit processors\n\nThis adds some code to do early ioremap\u0027s using page tables instead of\nbolting entries in the hash table. This will be used by the upcoming\n64-bits BookE port.\n\nThe patch also changes the test for early vs. late ioremap to use\nslab_is_available() instead of our old hackish mem_init_done.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "fcce810986b3f32a8322faf240f8cc5560a4c463", "tree": "4ee99143e18a008c52a274d74c1cc11055983bc6", "parents": [ "6c1719942e19936044c4673b18afa26e45a02320" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Jul 23 23:15:10 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:12:37 2009 +1000" }, "message": "powerpc/mm: Add HW threads support to no_hash TLB management\n\nThe current \"no hash\" MMU context management code is written with\nthe assumption that one CPU \u003d\u003d one TLB. This is not the case on\nimplementations that support HW multithreading, where several\nlinux CPUs can share the same TLB.\n\nThis adds some basic support for this to our context management\nand our TLB flushing code.\n\nIt also cleans up the optional debugging output a bit\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "ee43eb788b3a06425fffb912677e2e1c8b00dd3b", "tree": "7233cb47647837ab00af81270b3a16555d88a1f1", "parents": [ "8aa34ab8b2dc96ca6c4feecfb87ed13f0d40ef98" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 14 20:52:54 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:12:27 2009 +1000" }, "message": "powerpc: Use names rather than numbers for SPRGs (v2)\n\nThe kernel uses SPRG registers for various purposes, typically in\nlow level assembly code as scratch registers or to hold per-cpu\nglobal infos such as the PACA or the current thread_info pointer.\n\nWe want to be able to easily shuffle the usage of those registers\nas some implementations have specific constraints realted to some\nof them, for example, some have userspace readable aliases, etc..\nand the current choice isn\u0027t always the best.\n\nThis patch should not change any code generation, and replaces the\nusage of SPRN_SPRGn everywhere in the kernel with a named replacement\nand adds documentation next to the definition of the names as to\nwhat those are used for on each processor family.\n\nThe only parts that still use the original numbers are bits of KVM\nor suspend/resume code that just blindly needs to save/restore all\nthe SPRGs.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "de4376c2846bb5a8fc6fe8dbd0e4ff30905493e6", "tree": "58c430e20a457b36059c983afeb08ddd712c6661", "parents": [ "5eb9bac0406f2beb84b21aac6feb89d33d9f3f5c" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Mon Jul 13 20:53:53 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:12:26 2009 +1000" }, "message": "powerpc: Preload application text segment instead of TASK_UNMAPPED_BASE\n\nTASK_UNMAPPED_BASE is not used with the new top down mmap layout. We can\nreuse this preload slot by loading in the segment at 0x10000000, where almost\nall PowerPC binaries are linked at.\n\nOn a microbenchmark that bounces a token between two 64bit processes over pipes\nand calls gettimeofday each iteration (to access the VDSO), both the 32bit and\n64bit context switch rate improves (tested on a 4GHz POWER6):\n\n32bit: 273k/sec -\u003e 283k/sec\n64bit: 277k/sec -\u003e 284k/sec\n\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "5eb9bac0406f2beb84b21aac6feb89d33d9f3f5c", "tree": "04b7dfa2acd16f308a161f6baab2a83e024951b1", "parents": [ "30d0b3682887a81f0335b42f20116fd40d743371" ], "author": { "name": "Anton Blanchard", "email": "anton@samba.org", "time": "Mon Jul 13 20:53:52 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Thu Aug 20 10:12:25 2009 +1000" }, "message": "powerpc: Rearrange SLB preload code\n\nWith the new top down layout it is likely that the pc and stack will be in the\nsame segment, because the pc is most likely in a library allocated via a top\ndown mmap. Right now we bail out early if these segments match.\n\nRearrange the SLB preload code to sanity check all SLB preload addresses\nare not in the kernel, then check all addresses for conflicts.\n\nSigned-off-by: Anton Blanchard \u003canton@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "9c1e105238c474d19905af504f2e7f42d4f71f9e", "tree": "39406fa1c36e5894f2eb48a7f5fbb787736118a4", "parents": [ "1660e9d3d04b6c636b7171bf6c08ac7b82a7de79" ], "author": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Aug 17 15:17:54 2009 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Aug 18 14:48:43 2009 +1000" }, "message": "powerpc: Allow perf_counters to access user memory at interrupt time\n\nThis provides a mechanism to allow the perf_counters code to access\nuser memory in a PMU interrupt routine. Such an access can cause\nvarious kinds of interrupt: SLB miss, MMU hash table miss, segment\ntable miss, or TLB miss, depending on the processor. This commit\nonly deals with 64-bit classic/server processors, which use an MMU\nhash table. 32-bit processors are already able to access user memory\nat interrupt time. Since we don\u0027t soft-disable on 32-bit, we avoid\nthe possibility of reentering hash_page or the TLB miss handlers,\nsince they run with interrupts disabled.\n\nOn 64-bit processors, an SLB miss interrupt on a user address will\nupdate the slb_cache and slb_cache_ptr fields in the paca. This is\nOK except in the case where a PMU interrupt occurs in switch_slb,\nwhich also accesses those fields. To prevent this, we hard-disable\ninterrupts in switch_slb. Interrupts are already soft-disabled at\nthis point, and will get hard-enabled when they get soft-enabled\nlater.\n\nThis also reworks slb_flush_and_rebolt: to avoid hard-disabling twice,\nand to make sure that it clears the slb_cache_ptr when called from\nother callers than switch_slb, the existing routine is renamed to\n__slb_flush_and_rebolt, which is called by switch_slb and the new\nversion of slb_flush_and_rebolt.\n\nSimilarly, switch_stab (used on POWER3 and RS64 processors) gets a\nhard_irq_disable() to protect the per-cpu variables used there and\nin ste_allocate.\n\nIf a MMU hashtable miss interrupt occurs, normally we would call\nhash_page to look up the Linux PTE for the address and create a HPTE.\nHowever, hash_page is fairly complex and takes some locks, so to\navoid the possibility of deadlock, we check the preemption count\nto see if we are in a (pseudo-)NMI handler, and if so, we don\u0027t call\nhash_page but instead treat it like a bad access that will get\nreported up through the exception table mechanism. An interrupt\nwhose handler runs even though the interrupt occurred when\nsoft-disabled (such as the PMU interrupt) is considered a pseudo-NMI\nhandler, which should use nmi_enter()/nmi_exit() rather than\nirq_enter()/irq_exit().\n\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "384be2b18a5f9475eab9ca2bdfa95cc1a04ef59c", "tree": "04c93f391a1b65c8bf8d7ba8643c07d26c26590a", "parents": [ "a76761b621bcd8336065c4fe3a74f046858bc34c", "142d44b0dd6741a64a7bdbe029110e7c1dcf1d23" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Aug 14 14:41:02 2009 +0900" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Aug 14 14:45:31 2009 +0900" }, "message": "Merge branch \u0027percpu-for-linus\u0027 into percpu-for-next\n\nConflicts:\n\tarch/sparc/kernel/smp_64.c\n\tarch/x86/kernel/cpu/perf_counter.c\n\tarch/x86/kernel/setup_percpu.c\n\tdrivers/cpufreq/cpufreq_ondemand.c\n\tmm/percpu.c\n\nConflicts in core and arch percpu codes are mostly from commit\ned78e1e078dd44249f88b1dd8c76dafb39567161 which substituted many\nnum_possible_cpus() with nr_cpu_ids. As for-next branch has moved all\nthe first chunk allocators into mm/percpu.c, the changes are moved\nfrom arch code to mm/percpu.c.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "5156ddce6c0a152ee7ccab2c976c6a8abc8a49b5", "tree": "0782ea70dc80dd28d5081d5f53c28979ad6b022b", "parents": [ "4733fd328f14280900435d9dbae1487d110a4d56" ], "author": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Wed Jul 29 23:04:25 2009 -0500" }, "committer": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Wed Jul 29 23:05:43 2009 -0500" }, "message": "powerpc/mm: Fix SMP issue with MMU context handling code\n\nIn switch_mmu_context() if we call steal_context_smp() to get a context\nto use we shouldn\u0027t fall through and than call steal_context_up(). Doing\nso can be problematic in that the \u0027mm\u0027 that steal_context_up() ends up\nusing will not get marked dirty in the stale_map[] for other CPUs that\nmight have used that mm. Thus we could end up with stale TLB entries in\nthe other CPUs that can cause all kinda of havoc.\n\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\n" }, { "commit": "9e1b32caa525cb236e80e9c671e179bcecccc657", "tree": "8a1f0abf5291b23047cfdf099d5cfc96cc9d9253", "parents": [ "4be3bd7849165e7efa6b0b35a23d6a3598d97465" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 22 15:44:28 2009 +1000" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jul 27 12:10:38 2009 -0700" }, "message": "mm: Pass virtual address to [__]p{te,ud,md}_free_tlb()\n\nmm: Pass virtual address to [__]p{te,ud,md}_free_tlb()\n\nUpcoming paches to support the new 64-bit \"BookE\" powerpc architecture\nwill need to have the virtual address corresponding to PTE page when\nfreeing it, due to the way the HW table walker works.\n\nBasically, the TLB can be loaded with \"large\" pages that cover the whole\nvirtual space (well, sort-of, half of it actually) represented by a PTE\npage, and which contain an \"indirect\" bit indicating that this TLB entry\nRPN points to an array of PTEs from which the TLB can then create direct\nentries. Thus, in order to invalidate those when PTE pages are deleted,\nwe need the virtual address to pass to tlbilx or tlbivax instructions.\n\nThe old trick of sticking it somewhere in the PTE page struct page sucks\ntoo much, the address is almost readily available in all call sites and\nalmost everybody implemets these as macros, so we may as well add the\nargument everywhere. I added it to the pmd and pud variants for consistency.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nAcked-by: David Howells \u003cdhowells@redhat.com\u003e [MN10300 \u0026 FRV]\nAcked-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nAcked-by: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e [s390]\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "30c5af435b2e3e5700b0e4a53ac37a39b3b3516e", "tree": "52c870ee4cdd02f05588ec942732a3827f34ecdf", "parents": [ "33875f03307452650309a7d071678b2ca5f2fc26" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Wed Jun 17 18:13:52 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 08 13:50:24 2009 +1000" }, "message": "powerpc: Use pr_devel() in do_dcache_icache_coherency()\n\npr_debug() can now result in code being generated even when DEBUG\nis not defined. That\u0027s not really desirable in some places.\n\nWith CONFIG_DYNAMIC_DEBUG\u003dy:\n\nsize before:\n text data bss dec hex filename\n 2036 368 8 2412 96c arch/powerpc/mm/pgtable.o\n\nsize after:\n text data bss dec hex filename\n 1677 248 8 1933 78d arch/powerpc/mm/pgtable.o\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "29e5fa59e5ebe06d6bd7e04e7752a47ead23f89e", "tree": "c31773cb4d84f5df3a6bca5080cc86a4d69937dc", "parents": [ "651e2dd2a1c47bb078d446f123a9ae950ba7a1f0" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Wed Jun 17 18:13:51 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 08 13:50:23 2009 +1000" }, "message": "powerpc: Use pr_devel() in arch/powerpc/mm/gup.c\n\npr_debug() can now result in code being generated even when DEBUG\nis not defined. That\u0027s not really desirable in some places.\n\nWith CONFIG_DYNAMIC_DEBUG\u003dy:\n\nsize before:\n text data bss dec hex filename\n 3252 384 0 3636 e34 arch/powerpc/mm/gup.o\n\nsize after:\n text data bss dec hex filename\n 2576 96 0 2672 a70 arch/powerpc/mm/gup.o\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "651e2dd2a1c47bb078d446f123a9ae950ba7a1f0", "tree": "d18de17d4940b59f9c219a7a64dd3fe8857e7a4b", "parents": [ "3665ee36fac936b2ad0ab170d101a3e2c8eb3fd2" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Wed Jun 17 18:13:51 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 08 13:50:22 2009 +1000" }, "message": "powerpc: Cleanup \u0026 use pr_devel() in arch/powerpc/mm/slb.c\n\npr_debug() can now result in code being generated even when DEBUG\nis not defined. That\u0027s not really desirable in some places.\n\nWith CONFIG_DYNAMIC_DEBUG\u003dy:\n\nsize before:\n text data bss dec hex filename\n 3261 416 4 3681 e61 arch/powerpc/mm/slb.o\n\nsize after:\n text data bss dec hex filename\n 2861 248 4 3113 c29 arch/powerpc/mm/slb.o\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "a1ac38ab98e8a79ce225347b725f3b9751c70f1e", "tree": "0213205a85e173d5228f2e6de5e629de69f92afd", "parents": [ "b69e9e931d2c6116921fdb260684e0546285c3c8" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Wed Jun 17 18:13:54 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 08 13:50:22 2009 +1000" }, "message": "powerpc: Use pr_devel() in arch/powerpc/mm/mmu_context_nohash.c\n\npr_debug() can now result in code being generated even when DEBUG\nis not defined. That\u0027s not really desirable in some places.\n\nWith CONFIG_DYNAMIC_DEBUG\u003dy:\n\nsize before:\n text\t data\t bss\t dec\t hex\tfilename\n 1508\t 48\t 28\t 1584\t 630\tpowerpc/mm/mmu_context_nohash.o\n\nsize after:\n text\t data\t bss\t dec\t hex\tfilename\n 1088\t 0\t 28\t 1116\t 45c\tpowerpc/mm/mmu_context_nohash.o\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" } ], "next": "d258e64ef595792d6f749518354b69583e9a97f4" }