)]}' { "log": [ { "commit": "83ac6a1ed40bfbe185cf2bac5505d8d97aad8b1d", "tree": "f29cf4d1b3b6f859ead2598c9d741ffc5a56ec8b", "parents": [ "124c27d375f72dd857eac27f2932f9f01df76bf4" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Sun Jul 27 20:28:03 2008 -0700" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Mon Jul 28 16:30:52 2008 +1000" }, "message": "powerpc/mm: Implement _PAGE_SPECIAL \u0026 pte_special() for 64-bit\n\nImplement _PAGE_SPECIAL and pte_special() for 64-bit powerpc. This bit will\nbe used by the fast get_user_pages() to differenciate PTEs that correspond\nto a valid struct page from special mappings that don\u0027t such as IO mappings\nobtained via io_remap_pfn_ranges().\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: \"Paul E. McKenney\" \u003cpaulmck@us.ibm.com\u003e\nReviewed-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "e9efed3b80a83e44b98fc626f3268ae072550b84", "tree": "cbe7cc897dc112e2eb93f9bbded5aa3a8e6e0bf3", "parents": [ "440a0857e32a05979fb01fc59ea454a723e80e4b" ], "author": { "name": "Nathan Lynch", "email": "ntl@pobox.com", "time": "Sun Jul 27 15:24:54 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Mon Jul 28 16:30:52 2008 +1000" }, "message": "powerpc: Make core id information available to userspace\n\nExisting Open Firmware practice is to report each processor core as a\nseparate node in the device tree. Report the value of the \"reg\" OF\nproperty corresponding to a logical CPU\u0027s device node as the core_id\nattribute in /sys/devices/system/cpu/cpu*/topology/core_id.\n\nSigned-off-by: Nathan Lynch \u003cntl@pobox.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "440a0857e32a05979fb01fc59ea454a723e80e4b", "tree": "9776655cd83b18cdd9cc8f08b836a6811f77ced0", "parents": [ "0764bf63da5466474eebf7d21994cf6b106265a3" ], "author": { "name": "Nathan Lynch", "email": "ntl@pobox.com", "time": "Sun Jul 27 15:24:53 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Mon Jul 28 16:30:51 2008 +1000" }, "message": "powerpc: Make core sibling information available to userspace\n\nImplement the notion of \"core siblings\" for powerpc. This makes\n/sys/devices/system/cpu/cpu*/topology/core_siblings present sensible\nvalues, indicating online CPUs which share an L2 cache.\n\nBenH: Made cpu_to_l2cache() use of_find_node_by_phandle() instead\nof IBM-specific open coded search\n\nSigned-off-by: Nathan Lynch \u003cntl@pobox.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "7d6d637dac2050f30a1b57b0a3dc5de4a10616ba", "tree": "5108cacaf5e204d58bc07afb1d67c73144f1bf55", "parents": [ "f1ba12856b7a7d43e495e216bc91e6bbf7aac383" ], "author": { "name": "Roland McGrath", "email": "roland@redhat.com", "time": "Sun Jul 27 16:52:52 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Mon Jul 28 16:30:50 2008 +1000" }, "message": "powerpc: Add TIF_NOTIFY_RESUME support for tracehook\n\nThis adds TIF_NOTIFY_RESUME support for powerpc. When set,\nwe call tracehook_notify_resume() on the way to user mode.\nThis overloads do_signal() to do the work, but changes its\narguments to it has the TIF_* bits handy in a register and\ndrops the useless first argument that was always zero.\n\nSigned-off-by: Roland McGrath \u003croland@redhat.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "f1ba12856b7a7d43e495e216bc91e6bbf7aac383", "tree": "dd222ece64f06306ef85272654b6251a29632739", "parents": [ "4f72c4279eab1e5f3ed1ac4e55d4527617582392" ], "author": { "name": "Roland McGrath", "email": "roland@redhat.com", "time": "Sun Jul 27 16:51:35 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Mon Jul 28 16:30:49 2008 +1000" }, "message": "powerpc: Add asm/syscall.h with the tracehook entry points\n\nAdd asm/syscall.h for powerpc with all the required entry points.\nThis will allow arch-independent tracing code for system calls.\n\nBenH: Fixed up use of regs-\u003etrap to properly mask low bit\n\nSigned-off-by: Roland McGrath \u003croland@redhat.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "ff8dc7698c904f2a911e89b3d54e7c4a74f5575d", "tree": "d305d3030df749c6860da03c8d996496dde69066", "parents": [ "b9fa49a9a908407d9366b0e1e7222aee81a2df5b" ], "author": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Sun Jul 27 03:57:30 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Mon Jul 28 16:30:48 2008 +1000" }, "message": "powerpc: Fix 8xx build failure\n\nThe \u0027powerpc ioremap_prot\u0027 broke 8xx builds:\n\ninclude2/asm/pgtable-ppc32.h:555: error: \u0027_PAGE_WRITETHRU\u0027 undeclared (first use in this function)\ninclude2/asm/pgtable-ppc32.h:555: error: (Each undeclared identifier is reported only once\ninclude2/asm/pgtable-ppc32.h:555: error: for each function it appears in.)\n\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "cc04454fa81e93b5f1b5133950331639d2f59f85", "tree": "adc2c214ccfc66dd097ec9c71f2995e65acc565a", "parents": [ "5a00a5e7a3e013b2323f87c1b69ff9557eae5ec9" ], "author": { "name": "Hollis Blanchard", "email": "hollisb@us.ibm.com", "time": "Fri Jul 25 13:54:50 2008 -0500" }, "committer": { "name": "Avi Kivity", "email": "avi@qumranet.com", "time": "Sun Jul 27 12:02:05 2008 +0300" }, "message": "KVM: ppc: fix invalidation of large guest pages\n\nWhen guest invalidates a large tlb map, there may be more than one\ncorresponding shadow tlb maps that need to be invalidated. Use eaddr and eend\nto find these shadow tlb maps.\n\nSigned-off-by: Liu Yu \u003cyu.liu@freescale.com\u003e\nSigned-off-by: Hollis Blanchard \u003chollisb@us.ibm.com\u003e\nSigned-off-by: Avi Kivity \u003cavi@qumranet.com\u003e\n" }, { "commit": "7f2da1e7d0330395e5e9e350b879b98a1ea495df", "tree": "adc01ced45bb1de10fe58511e7143bbbd138a192", "parents": [ "8bb79224b87aab92071e94d46e70bd160d89bf34" ], "author": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Sat May 10 20:44:54 2008 -0400" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Sat Jul 26 20:53:20 2008 -0400" }, "message": "[PATCH] kill altroot\n\nlong overdue...\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "8d8bb39b9eba32dd70e87fd5ad5c5dd4ba118e06", "tree": "64090a84f4c4466f9f30ff46c993e0cede379052", "parents": [ "c485b465a031b6f9b9a51300e0ee1f86efc6db87" ], "author": { "name": "FUJITA Tomonori", "email": "fujita.tomonori@lab.ntt.co.jp", "time": "Fri Jul 25 19:44:49 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jul 26 12:00:03 2008 -0700" }, "message": "dma-mapping: add the device argument to dma_mapping_error()\n\nAdd per-device dma_mapping_ops support for CONFIG_X86_64 as POWER\narchitecture does:\n\nThis enables us to cleanly fix the Calgary IOMMU issue that some devices\nare not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423).\n\nI think that per-device dma_mapping_ops support would be also helpful for\nKVM people to support PCI passthrough but Andi thinks that this makes it\ndifficult to support the PCI passthrough (see the above thread). So I\nCC\u0027ed this to KVM camp. Comments are appreciated.\n\nA pointer to dma_mapping_ops to struct dev_archdata is added. If the\npointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it\u0027s\nNULL, the system-wide dma_ops pointer is used as before.\n\nIf it\u0027s useful for KVM people, I plan to implement a mechanism to register\na hook called when a new pci (or dma capable) device is created (it works\nwith hot plugging). It enables IOMMUs to set up an appropriate\ndma_mapping_ops per device.\n\nThe major obstacle is that dma_mapping_error doesn\u0027t take a pointer to the\ndevice unlike other DMA operations. So x86 can\u0027t have dma_mapping_ops per\ndevice. Note all the POWER IOMMUs use the same dma_mapping_error function\nso this is not a problem for POWER but x86 IOMMUs use different\ndma_mapping_error functions.\n\nThe first patch adds the device argument to dma_mapping_error. The patch\nis trivial but large since it touches lots of drivers and dma-mapping.h in\nall the architecture.\n\nThis patch:\n\ndma_mapping_error() doesn\u0027t take a pointer to the device unlike other DMA\noperations. So we can\u0027t have dma_mapping_ops per device.\n\nNote that POWER already has dma_mapping_ops per device but all the POWER\nIOMMUs use the same dma_mapping_error function. x86 IOMMUs use device\nargument.\n\n[akpm@linux-foundation.org: fix sge]\n[akpm@linux-foundation.org: fix svc_rdma]\n[akpm@linux-foundation.org: build fix]\n[akpm@linux-foundation.org: fix bnx2x]\n[akpm@linux-foundation.org: fix s2io]\n[akpm@linux-foundation.org: fix pasemi_mac]\n[akpm@linux-foundation.org: fix sdhci]\n[akpm@linux-foundation.org: build fix]\n[akpm@linux-foundation.org: fix sparc]\n[akpm@linux-foundation.org: fix ibmvscsi]\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nCc: Muli Ben-Yehuda \u003cmuli@il.ibm.com\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Avi Kivity \u003cavi@qumranet.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "5047887caf1806f31652210df27fb62a7c43f27d", "tree": "4098ead40c1aa7b904167f67cff87a247cfa0b6c", "parents": [ "996abf053eec4d67136be8b911bbaaf989cfb99c", "973b7d83ebeb1e34b8bee69208916e5f0e2353c3" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 25 11:08:17 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 25 11:08:17 2008 -0700" }, "message": "Merge branch \u0027merge\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc\n\n* \u0027merge\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (34 commits)\n powerpc: Wireup new syscalls\n Move update_mmu_cache() declaration from tlbflush.h to pgtable.h\n powerpc/pseries: Remove kmalloc call in handling writes to lparcfg\n powerpc/pseries: Update arch vector to indicate support for CMO\n ibmvfc: Add support for collaborative memory overcommit\n ibmvscsi: driver enablement for CMO\n ibmveth: enable driver for CMO\n ibmveth: Automatically enable larger rx buffer pools for larger mtu\n powerpc/pseries: Verify CMO memory entitlement updates with virtual I/O\n powerpc/pseries: vio bus support for CMO\n powerpc/pseries: iommu enablement for CMO\n powerpc/pseries: Add CMO paging statistics\n powerpc/pseries: Add collaborative memory manager\n powerpc/pseries: Utilities to set firmware page state\n powerpc/pseries: Enable CMO feature during platform setup\n powerpc/pseries: Split retrieval of processor entitlement data into a helper routine\n powerpc/pseries: Add memory entitlement capabilities to /proc/ppc64/lparcfg\n powerpc/pseries: Split processor entitlement retrieval and gathering to helper routines\n powerpc/pseries: Remove extraneous error reporting for hcall failures in lparcfg\n powerpc: Fix compile error with binutils 2.15\n ...\n\nFixed up conflict in arch/powerpc/platforms/52xx/Kconfig manually.\n" }, { "commit": "f22ab814a24e654b1de24db0c5f8b57b5ab2026a", "tree": "827f3fe1c94ba9cfd180f199ea6d2dc2dfa885df", "parents": [ "bc64efd220dcd4449aef8dd2564d73127b583b09" ], "author": { "name": "Adrian Bunk", "email": "bunk@kernel.org", "time": "Fri Jul 25 01:47:34 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 25 10:53:39 2008 -0700" }, "message": "include/asm/ptrace.h userspace headers cleanup\n\nThis patch contains the following cleanups for the asm/ptrace.h\nuserspace headers:\n\n- include/asm-generic/Kbuild.asm already lists ptrace.h, remove\n the superfluous listings in the Kbuild files of the following\n architectures:\n - cris\n - frv\n - powerpc\n - x86\n- don\u0027t expose function prototypes and macros to userspace:\n - arm\n - blackfin\n - cris\n - mn10300\n - parisc\n- remove #ifdef CONFIG_\u0027s around #define\u0027s:\n - blackfin\n - m68knommu\n- sh: AFAIK __SH5__ should work in both kernel and userspace,\n no need to leak CONFIG_SUPERH64 to userspace\n- xtensa: cosmetical change to remove empty\n #ifndef __ASSEMBLY__ #else #endif\n from the userspace headers\n\nNot changed by this patch is the fact that the following architectures\nhave a different struct pt_regs depending on CONFIG_ variables:\n- h8300\n- m68knommu\n- mips\n\nThis does not work in userspace.\n\nSigned-off-by: Adrian Bunk \u003cbunk@kernel.org\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nCc: Roland McGrath \u003croland@redhat.com\u003e\nCc: Oleg Nesterov \u003coleg@tv-sign.ru\u003e\nAcked-by: Greg Ungerer \u003cgerg@uclinux.org\u003e\nAcked-by: Paul Mundt \u003clethal@linux-sh.org\u003e\nAcked-by: Grant Grundler \u003cgrundler@parisc-linux.org\u003e\nAcked-by: Jesper Nilsson \u003cjesper.nilsson@axis.com\u003e\nAcked-by: Chris Zankel \u003cchris@zankel.net\u003e\nAcked-by: David Howells \u003cdhowells@redhat.com\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nAcked-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7444a72effa632fcd8edc566f880d96fe213c73b", "tree": "89d3e70c22751a6b00091df2b4dce7202eb3b1f5", "parents": [ "ff1d5c2f0268f4e32103536e2e65480b5b7b6530" ], "author": { "name": "Michael Buesch", "email": "mb@bu3sch.de", "time": "Fri Jul 25 01:46:11 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 25 10:53:30 2008 -0700" }, "message": "gpiolib: allow user-selection\n\nThis patch adds functionality to the gpio-lib subsystem to make it\npossible to enable the gpio-lib code even if the architecture code didn\u0027t\nrequest to get it built in.\n\nThe archtitecture code does still need to implement the gpiolib accessor\nfunctions in its asm/gpio.h file. This patch adds the implementations for\nx86 and PPC.\n\nWith these changes it is possible to run generic GPIO expansion cards on\nevery architecture that implements the trivial wrapper functions. Support\nfor more architectures can easily be added.\n\nSigned-off-by: Michael Buesch \u003cmb@bu3sch.de\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nCc: David Brownell \u003cdavid-b@pacbell.net\u003e\nCc: Russell King \u003crmk@arm.linux.org.uk\u003e\nCc: Haavard Skinnemoen \u003chskinnemoen@atmel.com\u003e\nCc: Jesper Nilsson \u003cjesper.nilsson@axis.com\u003e\nCc: Ralf Baechle \u003cralf@linux-mips.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: Jean Delvare \u003ckhali@linux-fr.org\u003e\nCc: Samuel Ortiz \u003csameo@openedhand.com\u003e\nCc: Kumar Gala \u003cgalak@gate.crashing.org\u003e\nCc: Sam Ravnborg \u003csam@ravnborg.org\u003e\nCc: Adrian Bunk \u003cbunk@stusta.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b69c49b78457f681ecfb3147bd968434ee6559c1", "tree": "9557c950c21cf4336ccc403136ea11384150af31", "parents": [ "62ec30d45ecbb85b5991474c8f04192697687495" ], "author": { "name": "FUJITA Tomonori", "email": "fujita.tomonori@lab.ntt.co.jp", "time": "Fri Jul 25 01:45:40 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 25 10:53:28 2008 -0700" }, "message": "clean up duplicated alloc/free_thread_info\n\nWe duplicate alloc/free_thread_info defines on many platforms (the\nmajority uses __get_free_pages/free_pages). This patch defines common\ndefines and removes these duplicated defines.\n__HAVE_ARCH_THREAD_INFO_ALLOCATOR is introduced for platforms that do\nsomething different.\n\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nAcked-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "973b7d83ebeb1e34b8bee69208916e5f0e2353c3", "tree": "df862362c27668798e85dd6c15868a79b3dfa489", "parents": [ "1e3519f8e1baec0b733cd42684fcd3d9681662f1" ], "author": { "name": "Tony Breeds", "email": "tony@bakeyournoodle.com", "time": "Fri Jul 25 16:21:51 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jul 25 16:40:55 2008 +1000" }, "message": "powerpc: Wireup new syscalls\n\nsignalfd4, eventfd2, epoll_create1, dup3, pipe2 and inotify_init1\n\nSigned-off-by: Tony Breeds \u003ctony@bakeyournoodle.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "1e3519f8e1baec0b733cd42684fcd3d9681662f1", "tree": "87300d5f6492e3e2407e9efd8d40a93fb3b23be2", "parents": [ "16c14b4621c7b6fc4611abf1f86cd78cdb1b2b03" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jul 25 16:21:11 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jul 25 16:21:11 2008 +1000" }, "message": "Move update_mmu_cache() declaration from tlbflush.h to pgtable.h\nwhere it belongs. This fixes some build problems on some configs\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e" }, { "commit": "a90ab95a9576d35de0d05f9f4fc435edcccafaa9", "tree": "53824dbf844fafda141e625be3a9d8f3957511e6", "parents": [ "6490c4903d12f242bec4454301f76f6a7520e399" ], "author": { "name": "Robert Jennings", "email": "rcj@linux.vnet.ibm.com", "time": "Thu Jul 24 04:31:33 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jul 25 15:44:43 2008 +1000" }, "message": "powerpc/pseries: vio bus support for CMO\n\nThis is a large patch but the normal code path is not affected. For\nnon-pSeries platforms the code is ifdef\u0027ed out and for non-CMO enabled\npSeries systems this does not affect the normal code path. Devices that\ndo not perform DMA operations do not need modification with this patch.\nThe function get_desired_dma was renamed from get_io_entitlement for\nclarity.\n\nOverview\n\nCooperative Memory Overcommitment (CMO) allows for a set of OS partitions\nto be run with less RAM than the aggregate needs of the group of\npartitions. The firmware will balance memory between the partitions\nand page in/out memory as needed. Based on the number and type of IO\nadpaters preset each partition is allocated an amount of memory for\nDMA operations and this allocation will be guaranteed to the partition;\nthis is referred to as the partition\u0027s \u0027entitlement\u0027.\n\nPartitions running in a CMO environment can only have virtual IO devices\npresent. The VIO bus layer will manage the IO entitlement for the system.\nAccounting, at a system and per-device level, is tracked in the VIO bus\ncode and exposed via sysfs. A set of dma_ops functions are added to\nthe bus to allow for this accounting.\n\nBus initialization\n\nAt initialization, the bus will calculate the minimum needs of the system\nbased on providing each device present with a standard minimum entitlement\nalong with a spare allocation for the bus to handle hotplug events.\nIf the minimum needs can not be met the system boot will be halted.\n\nDevice changes\n\nThe significant changes for devices while running under CMO are that the\ndevices must specify how much dedicated IO entitlement they desire and\nmust also handle DMA mapping errors that can occur due to constrained\nIO memory. The virtual IO drivers are modified to silence errors when\nDMA mappings fail for CMO and handle these failures gracefully.\n\nEach devices will be guaranteed a minimum entitlement that can always\nbe mapped. Devices will specify how much entitlement they desire and\nthe VIO bus will attempt to provide for this. Devices can change their\ndesired entitlement level at any point in time to address particular needs\n(via vio_cmo_set_dev_desired()), not just at device probe time.\n\nVIO bus changes\n\nThe system will have a particular entitlement level available from which\nit can provide memory to the devices. The bus defines two pools of memory\nwithin this entitlement, the reserved and excess pools. Each device is\nprovided with it\u0027s own entitlement no less than a system defined minimum\nentitlement and no greater than what the device has specified as it\u0027s\ndesired entitlement. The entitlement provided to devices comes from the\nreserve pool. The reserve pool can also contain a spare allocation as\nlarge as the system defined minimum entitlement which is used for device\nhotplug events. Any entitlement not needed to fulfill the needs of a\nreserve pool is placed in the excess pool. Each device is guaranteed\nthat it can map up to it\u0027s entitled level; additional mapping are possible\nas long as there is unmapped memory in the excess pool.\n\nBus probe\n\nAs the system starts, each device is given an entitlement equal only\nto the system defined minimum entitlement. The reserve pool is equal\nto the sum of these entitlements, plus a spare allocation. The VIO bus\nalso tracks the aggregate desired entitlement of all the devices. If the\nsystem desired entitlement is greater than the size of the reserve pool,\nwhen devices unmap IO memory it will be reserved and a balance operation\nwill be scheduled for some time in the future.\n\nEntitlement balancing\n\nThe balance function tries to fairly distribute entitlement between the\ndevices in the system with the goal of providing each device with it\u0027s\ndesired amount of entitlement. Devices using more than what would be\nideal will have their entitled set-point adjusted; this will effectively\nset a goal for lower IO memory usage as future mappings can fail and\ndeallocations will trigger a balance operation to distribute the newly\nunmapped memory. A fair distribution of entitlement can take several\nbalance operations to achieve. Entitlement changes and device DLPAR\nevents will alter the state of CMO and will trigger balance operations.\n\nHotplug events\n\nThe VIO bus allows for changes in system entitlement at run-time via\n\u0027vio_cmo_entitlement_update()\u0027. When devices are added the hotplug\ndevice event will be preceded by a system entitlement increase and this\nis reversed when devices are removed.\n\nThe following changes are made that the VIO bus layer for CMO:\n * add IO memory accounting per device structure.\n * add IO memory entitlement query function to driver structure.\n * during vio bus probe, if CMO is enabled, check that driver has\n memory entitlement query function defined. Fail if function not defined.\n * fail to register driver if io entitlement function not defined.\n * create set of dma_ops at vio level for CMO that will track allocations\n and return DMA failures once entitlement is reached. Entitlement will\n limited by overall system entitlement. Devices will have a reserved\n quantity of memory that is guaranteed, the rest can be used as available.\n * expose entitlement, current allocation, desired allocation, and the\n allocation error counter for devices to the user through sysfs\n * provide mechanism for changing a device\u0027s desired entitlement at run time\n for devices as an exported function and sysfs tunable\n * track any DMA failures for entitled IO memory for each vio device.\n * check entitlement against available system entitlement on device add\n * track entitlement metrics (high water mark, current usage)\n * provide function to reset high water mark\n * provide minimum and desired entitlement numbers at a bus level\n * provide drivers with a minimum guaranteed entitlement\n * balance available entitlement between devices to satisfy their needs\n * handle system entitlement changes and device hotplug\n\nSigned-off-by: Robert Jennings \u003crcj@linux.vnet.ibm.com\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "6490c4903d12f242bec4454301f76f6a7520e399", "tree": "8b4bc5fb45618ed4af993da51985be2e42a39475", "parents": [ "ffa5abbd0c399b32fc13a1b4718d87ee7a716999" ], "author": { "name": "Robert Jennings", "email": "rcj@linux.vnet.ibm.com", "time": "Thu Jul 24 04:31:16 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jul 25 15:44:43 2008 +1000" }, "message": "powerpc/pseries: iommu enablement for CMO\n\nTo support Cooperative Memory Overcommitment (CMO), we need to check\nfor failure from some of the tce hcalls.\n\nThese changes for the pseries platform affect the powerpc architecture;\npatches for the other affected platforms are included in this patch.\n\npSeries platform IOMMU code changes:\n * platform TCE functions must handle H_NOT_ENOUGH_RESOURCES errors and\n return an error.\n\nArchitecture IOMMU code changes:\n * Calls to ppc_md.tce_build need to check return values and return\n DMA_MAPPING_ERROR for transient errors.\n\nArchitecture changes:\n * struct machdep_calls for tce_build*_pSeriesLP functions need to change\n to indicate failure.\n * all other platforms will need updates to iommu functions to match the new\n calling semantics; they will return 0 on success. The other platforms\n default configs have been built, but no further testing was performed.\n\nSigned-off-by: Robert Jennings \u003crcj@linux.vnet.ibm.com\u003e\nAcked-by: Olof Johansson \u003colof@lixom.net\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "ffa5abbd0c399b32fc13a1b4718d87ee7a716999", "tree": "79e2136b4de01bee9c5f8f8cee23823a801b8972", "parents": [ "84af458bb23bf5f0ba1af4320dd2a57f7c4363e5" ], "author": { "name": "Brian King", "email": "brking@linux.vnet.ibm.com", "time": "Thu Jul 24 04:30:58 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jul 25 15:44:42 2008 +1000" }, "message": "powerpc/pseries: Add CMO paging statistics\n\nWith the addition of Cooperative Memory Overcommitment (CMO) support\nfor IBM Power Systems, two fields have been added to the VPA to report\npaging statistics. Add support in lparcfg to report them to userspace.\n\nSigned-off-by: Brian King \u003cbrking@linux.vnet.ibm.com\u003e\nSigned-off-by: Robert Jennings \u003crcj@linux.vnet.ibm.com\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "86630a32320f83736c4c24e2c8bae218e4c56c7c", "tree": "3fee9905e0edde44bb0137b66c46215110061ad6", "parents": [ "e46de429cb954d30a5642fba81d516ede518c65e" ], "author": { "name": "Brian King", "email": "brking@linux.vnet.ibm.com", "time": "Thu Jul 24 04:29:16 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jul 25 15:44:42 2008 +1000" }, "message": "powerpc/pseries: Utilities to set firmware page state\n\nNewer versions of firmware support page states, which are used by the\ncollaborative memory manager (future patch) to \"loan\" pages to the\nhypervisor for use by other partitions.\n\nSigned-off-by: Brian King \u003cbrking@linux.vnet.ibm.com\u003e\nSigned-off-by: Robert Jennings \u003crcj@linux.vnet.ibm.com\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "e46de429cb954d30a5642fba81d516ede518c65e", "tree": "b04b9fb575c5d4c0cddbb891d6621729820a3027", "parents": [ "398778f78b76fb72cb18411487af01dea202709e" ], "author": { "name": "Robert Jennings", "email": "rcj@linux.vnet.ibm.com", "time": "Thu Jul 24 04:29:03 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jul 25 15:44:42 2008 +1000" }, "message": "powerpc/pseries: Enable CMO feature during platform setup\n\nFor Cooperative Memory Overcommitment (CMO), set the FW_FEATURE_CMO\nflag in powerpc_firmware_features from the rtas ibm,get-system-parameters\ntable prior to calling iommu_init_early_pSeries.\n\nWith this, any CMO specific functionality can be controlled by checking:\n firmware_has_feature(FW_FEATURE_CMO)\n\nSigned-off-by: Robert Jennings \u003crcj@linux.vnet.ibm.com\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "dfc3403f0e5ffb94ee29942f313b87d4061d951b", "tree": "8e16a830d4869907f5f3b423dd400c927fcf8e4b", "parents": [ "11529396ea3190113173f7a15e59a58dbcaa36c8" ], "author": { "name": "Nathan Fontenot", "email": "nfont@austin.ibm.com", "time": "Thu Jul 24 04:27:30 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jul 25 15:44:41 2008 +1000" }, "message": "powerpc/pseries: Add memory entitlement capabilities to /proc/ppc64/lparcfg\n\nUpdate /proc/ppc64/lparcfg to display Cooperative Memory\nOvercommitment statistics as reported by the H_GET_MPP hcall. This\nalso updates the lparcfg interface to allow setting memory entitlement\nand weight.\n\nSigned-off-by: Nathan Fontenot \u003cnfont@austin.ibm.com\u003e\nSigned-off-by: Robert Jennings \u003crcj@linux.vnet.ibm.com\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "d6a61bfc06d6f2248f3e75f208d64e794082013c", "tree": "d46aec6b68e30f9d7d9198bd9102fcf1c054ab7e", "parents": [ "00bf6e906156b07cd641fe154ad0efe78f989692" ], "author": { "name": "Luis Machado", "email": "luisgpm@linux.vnet.ibm.com", "time": "Thu Jul 24 02:10:41 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jul 25 15:44:39 2008 +1000" }, "message": "powerpc: BookE hardware watchpoint support\n\nThis patch implements support for HW based watchpoint via the\nDBSR_DAC (Data Address Compare) facility of the BookE processors.\n\nIt does so by interfacing with the existing DABR breakpoint code\nand adding the necessary bits and pieces for the new bits to\nbe properly set or cleared\n\nSigned-off-by: Luis Machado \u003cluisgpm@br.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "9115d13453dee22473a1e8cacc90a8d64a9c4bc9", "tree": "dc6c7b1aad8861ae5f88aaf496fd634338686330", "parents": [ "483fad1c3fa1060d7e6710e84a065ad514571739" ], "author": { "name": "Nathan Lynch", "email": "ntl@pobox.com", "time": "Wed Jul 16 09:58:51 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jul 25 15:44:39 2008 +1000" }, "message": "powerpc: Enable AT_BASE_PLATFORM aux vector\n\nStash the first platform string matched by identify_cpu() in\npowerpc_base_platform, and supply that to the ELF loader for the value\nof AT_BASE_PLATFORM.\n\nSigned-off-by: Nathan Lynch \u003cntl@pobox.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "c174aff95642bcc830102becb9802adeb8f87a5a", "tree": "360ad80985487939be071bf0205cdaa5ca88155f", "parents": [ "fb2e405fc1fc8b20d9c78eaa1c7fd5a297efde43", "79c28acb2b7d66ca48d23e1c8b5e9e043aa634f8" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jul 25 15:35:03 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Jul 25 15:35:03 2008 +1000" }, "message": "Merge commit \u0027gcl/gcl-next\u0027\n" }, { "commit": "b5684b83b1e1579bbbc80e703e990c0cccf5892c", "tree": "3f1b62b2320bce4d658d2ad0d4b77856499ac533", "parents": [ "1481b9109fe771ec8b035d7760f42e36d2bed5d4", "1b8ebad87b459e2e1333fbf28005977245ff5402" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 14:55:09 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 14:55:09 2008 -0700" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/bart/ide-2.6\n\n* git://git.kernel.org/pub/scm/linux/kernel/git/bart/ide-2.6: (76 commits)\n ide: use proper printk() KERN_* levels in ide-probe.c\n ide: fix for EATA SCSI HBA in ATA emulating mode\n ide: remove stale comments from drivers/ide/Makefile\n ide: enable local IRQs in all handlers for TASKFILE_NO_DATA data phase\n ide-scsi: remove kmalloced struct request\n ht6560b: remove old history\n ht6560b: update email address\n ide-cd: fix oops when using growisofs\n gayle: release resources on ide_host_add() failure\n palm_bk3710: add UltraDMA/100 support\n ide: trivial sparse annotations\n ide: ide-tape.c sparse annotations and unaligned access removal\n ide: drop \u0027name\u0027 parameter from -\u003einit_chipset method\n ide: prefix messages from IDE PCI host drivers by driver name\n it821x: remove DECLARE_ITE_DEV() macro\n it8213: remove DECLARE_ITE_DEV() macro\n ide: include PCI device name in messages from IDE PCI host drivers\n ide: remove \u003casm/ide.h\u003e for some archs\n ide-generic: remove ide_default_{io_base,irq}() inlines (take 3)\n ide-generic: is no longer needed on ppc32\n ...\n" }, { "commit": "ffed0b6e1a6f5132681d4b521531d992f893190b", "tree": "35894dcc2e2458cedf382ad59d272f4c3a33817d", "parents": [ "d83b8b85cd56a083d30df73f3fd5e4714591b910" ], "author": { "name": "Bartlomiej Zolnierkiewicz", "email": "bzolnier@gmail.com", "time": "Thu Jul 24 22:53:30 2008 +0200" }, "committer": { "name": "Bartlomiej Zolnierkiewicz", "email": "bzolnier@gmail.com", "time": "Thu Jul 24 22:53:30 2008 +0200" }, "message": "ide-generic: remove broken PPC_PREP support\n\nPPC_PREP has been depending on BROKEN for some time now.\n\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Bartlomiej Zolnierkiewicz \u003cbzolnier@gmail.com\u003e\n" }, { "commit": "d83b8b85cd56a083d30df73f3fd5e4714591b910", "tree": "1fac379e8d909361ecbf934645463a00e706dafc", "parents": [ "2c9d86438a0104800da2a8ecdc1e27baf38ba6a4" ], "author": { "name": "Bartlomiej Zolnierkiewicz", "email": "bzolnier@gmail.com", "time": "Thu Jul 24 22:53:30 2008 +0200" }, "committer": { "name": "Bartlomiej Zolnierkiewicz", "email": "bzolnier@gmail.com", "time": "Thu Jul 24 22:53:30 2008 +0200" }, "message": "ide: define MAX_HWIFS in \u003clinux/ide.h\u003e\n\n* Now that ide_hwif_t instances are allocated dynamically\n the difference between MAX_HWIFS \u003d\u003d 2 and MAX_HWIFS \u003d\u003d 10\n is ~100 bytes (x86-32) so use MAX_HWIFS \u003d\u003d 10 on all archs\n except these ones that use MAX_HWIFS \u003d\u003d 1.\n\n* Define MAX_HWIFS in \u003clinux/ide.h\u003e instead of \u003casm/ide.h\u003e.\n\n[ Please note that avr32/cris/v850 have no \u003casm/ide.h\u003e\n and alpha/ia64/sh always define CONFIG_IDE_MAX_HWIFS. ]\n\nSigned-off-by: Bartlomiej Zolnierkiewicz \u003cbzolnier@gmail.com\u003e\n" }, { "commit": "7540081c6b16dc941895bca840749cabfd0d3b48", "tree": "9e6b2270d700bf99489b570aa2b4c2c0b6cd0ead", "parents": [ "3fde80e94c2bbffbb13f5faa3340cf438440ebea", "b552068999b0b05087c454e525b30b785c79dc9b" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 12:24:40 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 12:24:40 2008 -0700" }, "message": "Merge branch \u0027semaphore\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/willy/misc\n\n* \u0027semaphore\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/willy/misc:\n Remove __DECLARE_SEMAPHORE_GENERIC\n Remove asm/semaphore.h\n Remove use of asm/semaphore.h\n Add missing semaphore.h includes\n Remove mention of semaphores from kernel-locking\n" }, { "commit": "27ac792ca0b0a1e7e65f20342260650516c95864", "tree": "8e0bc93612da0803fe12303ccb75c837cd633c83", "parents": [ "d92bc318547507a944a22e7ef936793dc0fe167f" ], "author": { "name": "Andrea Righi", "email": "righi.andrea@gmail.com", "time": "Wed Jul 23 21:28:13 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 10:47:21 2008 -0700" }, "message": "PAGE_ALIGN(): correctly handle 64-bit values on 32-bit architectures\n\nOn 32-bit architectures PAGE_ALIGN() truncates 64-bit values to the 32-bit\nboundary. For example:\n\n\tu64 val \u003d PAGE_ALIGN(size);\n\nalways returns a value \u003c 4GB even if size is greater than 4GB.\n\nThe problem resides in PAGE_MASK definition (from include/asm-x86/page.h for\nexample):\n\n#define PAGE_SHIFT 12\n#define PAGE_SIZE (_AC(1,UL) \u003c\u003c PAGE_SHIFT)\n#define PAGE_MASK (~(PAGE_SIZE-1))\n...\n#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)\u0026PAGE_MASK)\n\nThe \"~\" is performed on a 32-bit value, so everything in \"and\" with\nPAGE_MASK greater than 4GB will be truncated to the 32-bit boundary.\nUsing the ALIGN() macro seems to be the right way, because it uses\ntypeof(addr) for the mask.\n\nAlso move the PAGE_ALIGN() definitions out of include/asm-*/page.h in\ninclude/linux/mm.h.\n\nSee also lkml discussion: http://lkml.org/lkml/2008/6/11/237\n\n[akpm@linux-foundation.org: fix drivers/media/video/uvc/uvc_queue.c]\n[akpm@linux-foundation.org: fix v850]\n[akpm@linux-foundation.org: fix powerpc]\n[akpm@linux-foundation.org: fix arm]\n[akpm@linux-foundation.org: fix mips]\n[akpm@linux-foundation.org: fix drivers/media/video/pvrusb2/pvrusb2-dvb.c]\n[akpm@linux-foundation.org: fix drivers/mtd/maps/uclinux.c]\n[akpm@linux-foundation.org: fix powerpc]\nSigned-off-by: Andrea Righi \u003crighi.andrea@gmail.com\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "0d9ea75443dc7e37843e656b8ebc947a6d16d618", "tree": "4eb47a4468a92c90a90873d1646196955b487996", "parents": [ "f4a67cceee4a6f5ed38011a698c9e34747270ae5" ], "author": { "name": "Jon Tollefson", "email": "kniht@linux.vnet.ibm.com", "time": "Wed Jul 23 21:27:56 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 10:47:19 2008 -0700" }, "message": "powerpc: support multiple hugepage sizes\n\nInstead of using the variable mmu_huge_psize to keep track of the huge\npage size we use an array of MMU_PAGE_* values. For each supported huge\npage size we need to know the hugepte_shift value and have a\npgtable_cache. The hstate or an mmu_huge_psizes index is passed to\nfunctions so that they know which huge page size they should use.\n\nThe hugepage sizes 16M and 64K are setup(if available on the hardware) so\nthat they don\u0027t have to be set on the boot cmd line in order to use them.\nThe number of 16G pages have to be specified at boot-time though (e.g.\nhugepagesz\u003d16G hugepages\u003d5).\n\nSigned-off-by: Jon Tollefson \u003ckniht@linux.vnet.ibm.com\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "91224346aa8c1cdaa660300a98e0b074a3a95030", "tree": "7b4d9604001afd55e9a3fdb6d1a414f5f2d15214", "parents": [ "658013e93eb70494f7300bc90457b09a807232a4" ], "author": { "name": "Jon Tollefson", "email": "kniht@linux.vnet.ibm.com", "time": "Wed Jul 23 21:27:55 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 10:47:19 2008 -0700" }, "message": "powerpc: define support for 16G hugepages\n\nThe huge page size is defined for 16G pages. If a hugepagesz of 16G is\nspecified at boot-time then it becomes the huge page size instead of the\ndefault 16M.\n\nThe change in pgtable-64K.h is to the macro pte_iterate_hashed_subpages to\nmake the increment to va (the 1 being shifted) be a long so that it is not\nshifted to 0. Otherwise it would create an infinite loop when the shift\nvalue is for a 16G page (when base page size is 64K).\n\nSigned-off-by: Jon Tollefson \u003ckniht@linux.vnet.ibm.com\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "658013e93eb70494f7300bc90457b09a807232a4", "tree": "d03a23ac4fff0b35138b5d8abb761e9fad85b09c", "parents": [ "ec4b2c0c8312d1118c2acd00c89988ecf955d5cc" ], "author": { "name": "Jon Tollefson", "email": "kniht@linux.vnet.ibm.com", "time": "Wed Jul 23 21:27:54 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 10:47:19 2008 -0700" }, "message": "powerpc: scan device tree for gigantic pages\n\nThe 16G huge pages have to be reserved in the HMC prior to boot. The\nlocation of the pages are placed in the device tree. This patch adds code\nto scan the device tree during very early boot and save these page\nlocations until hugetlbfs is ready for them.\n\nAcked-by: Adam Litke \u003cagl@us.ibm.com\u003e\nSigned-off-by: Jon Tollefson \u003ckniht@linux.vnet.ibm.com\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a5516438959d90b071ff0a484ce4f3f523dc3152", "tree": "e356ba9364c76b93c176b4d4a262b7aca3ee8f91", "parents": [ "b7ba30c679ed1eb7ed3ed8f281f6493282042bd4" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jul 23 21:27:41 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 10:47:17 2008 -0700" }, "message": "hugetlb: modular state for hugetlb page size\n\nThe goal of this patchset is to support multiple hugetlb page sizes. This\nis achieved by introducing a new struct hstate structure, which\nencapsulates the important hugetlb state and constants (eg. huge page\nsize, number of huge pages currently allocated, etc).\n\nThe hstate structure is then passed around the code which requires these\nfields, they will do the right thing regardless of the exact hstate they\nare operating on.\n\nThis patch adds the hstate structure, with a single global instance of it\n(default_hstate), and does the basic work of converting hugetlb to use the\nhstate.\n\nFuture patches will add more hstate structures to allow for different\nhugetlbfs mounts to have different page sizes.\n\n[akpm@linux-foundation.org: coding-style fixes]\nAcked-by: Adam Litke \u003cagl@us.ibm.com\u003e\nAcked-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "42b7772812d15b86543a23b82bd6070eef9a08b1", "tree": "10665ee01fe82ce17c68a6278d044531b1ed64c0", "parents": [ "a352894d07059649398c4769dc8b645e1a1dad88" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jul 23 21:27:10 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 10:47:15 2008 -0700" }, "message": "mm: remove double indirection on tlb parameter to free_pgd_range() \u0026 Co\n\nThe double indirection here is not needed anywhere and hence (at least)\nconfusing.\n\nSigned-off-by: Jan Beulich \u003cjbeulich@novell.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nAcked-by: Jeremy Fitzhardinge \u003cjeremy@goop.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a1f242ff460e4b50a045fa237c3c56cce9eabf83", "tree": "657766b55251042b38967422dc9c3ea893b98747", "parents": [ "7ae8ed5053a39082d224a3f48409e016baca9c16" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 23 21:27:08 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 10:47:15 2008 -0700" }, "message": "powerpc ioremap_prot\n\nThis adds ioremap_prot and pte_pgprot() so that one can extract protection\nbits from a PTE and use them to ioremap_prot() (in order to support ptrace\nof VM_IO | VM_PFNMAP as per Rik\u0027s patch).\n\nThis moves a couple of flag checks around in the ioremap implementations\nof arch/powerpc. There\u0027s a side effect of allowing non-cacheable and\nnon-guarded mappings on ppc32 which before would always have _PAGE_GUARDED\nset whenever _PAGE_NO_CACHE is.\n\n(standard ioremap will still set _PAGE_GUARDED, but ioremap_prot will be\ncapable of setting such a non guarded mapping).\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Rik van Riel \u003criel@redhat.com\u003e\nCc: Dave Airlie \u003cairlied@linux.ie\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Arnd Bergmann \u003carnd@arndb.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "2351ec533ed0dd56052ab96988d2161d5ecc8ed9", "tree": "f60585af065bc7728f55ff0681c3f3f1015ba0a1", "parents": [ "6310e472717ed736c9bff9840febb71f7bb400ed" ], "author": { "name": "Matthew Wilcox", "email": "matthew@wil.cx", "time": "Thu Jul 24 08:09:32 2008 -0400" }, "committer": { "name": "Matthew Wilcox", "email": "willy@linux.intel.com", "time": "Thu Jul 24 08:31:12 2008 -0400" }, "message": "Remove asm/semaphore.h\n\nAll users have now been converted to linux/semaphore.h and we don\u0027t need\nto keep these files around any longer.\n\nSigned-off-by: Matthew Wilcox \u003cwilly@linux.intel.com\u003e\n" }, { "commit": "17ce452f7ea3df760b7f9f42453b6f6acd765217", "tree": "a53c70b553363ce404ff49cb49ccc532cf4c7e78", "parents": [ "5cbad0ebf45c5417104b383dc0e34f64fa7f2473" ], "author": { "name": "Jason Wessel", "email": "jason.wessel@windriver.com", "time": "Wed Jul 23 11:30:15 2008 -0500" }, "committer": { "name": "Jason Wessel", "email": "jason.wessel@windriver.com", "time": "Wed Jul 23 11:30:15 2008 -0500" }, "message": "kgdb, powerpc: arch specific powerpc kgdb support\n\nThis patch removes the old kgdb reminants from ARCH\u003dpowerpc and\nimplements the new style arch specific stub for the common kgdb core\ninterface.\n\nIt is possible to have xmon and kgdb in the same kernel, but you\ncannot use both at the same time because there is only one set of\ndebug hooks.\n\nThe arch specific kgdb implementation saves the previous state of the\ndebug hooks and restores them if you unconfigure the kgdb I/O driver.\nKgdb should have no impact on a kernel that has no kgdb I/O driver\nconfigured.\n\nSigned-off-by: Jason Wessel \u003cjason.wessel@windriver.com\u003e\n" }, { "commit": "a19dd1bd7df839c52a668abcf288c2239442c3c9", "tree": "9e0be9f20f09d2755f51b169af521f05d2a87cae", "parents": [ "6d5509babce654fd9ce0ff6689dbdf6ce56c43ae" ], "author": { "name": "Grant Likely", "email": "grant.likely@secretlab.ca", "time": "Tue Jul 22 01:13:54 2008 -0600" }, "committer": { "name": "Grant Likely", "email": "grant.likely@secretlab.ca", "time": "Tue Jul 22 01:13:54 2008 -0600" }, "message": "powerpc/mpc5200: add PSC SICR bit definitions\n\nRequired by the PSC I2S audio driver.\n\nSigned-off-by: Grant Likely \u003cgrant.likely@secretlab.ca\u003e\n" }, { "commit": "6a4a636fad018500c5db7a2b56a00caeb21cbb2c", "tree": "c95f8727d432bb7fd728c4640d549b7bb3764ada", "parents": [ "11d579ee0a19052a5a90ebfe0c39e7ed8ce8a9dc" ], "author": { "name": "Jon Smirl", "email": "jonsmirl@gmail.com", "time": "Sun Jul 20 11:27:22 2008 -0400" }, "committer": { "name": "Grant Likely", "email": "grant.likely@secretlab.ca", "time": "Tue Jul 22 01:13:11 2008 -0600" }, "message": "powerpc/mpc5200: Add AC97 register definitions for the MPC52xx PSC\n\nNeeded by the PSC AC97 sound driver\n\nSigned-off-by: Jon Smirl \u003cjonsmirl@gmail.com\u003e\nSigned-off-by: Grant Likely \u003cgrant.likely@secretlab.ca\u003e\n" }, { "commit": "8725f25acc656c1522d48a6746055099efdaca4c", "tree": "e241424fa58178ed6c2a95a4eb931ea83dbea33c", "parents": [ "c69cccc95fe4b90dde5fe33e6a3b77880b534fa4", "93ded9b8fd42abe2c3607097963d8de6ad9117eb" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 22 17:12:37 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 22 17:12:37 2008 +1000" }, "message": "Merge commit \u0027origin/master\u0027\n\nManually fixed up:\n\n\tdrivers/net/fs_enet/fs_enet-main.c" }, { "commit": "551c3c04b478b987ccd335f1a42362d571b1592d", "tree": "9f1cab317e0f0b680fe00cba54b3b4cdeea608bf", "parents": [ "6a2a24bb755405d5311efaaed865042477b26f30" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Thu Jul 17 17:17:52 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 22 10:39:35 2008 +1000" }, "message": "powerpc: Use PPC_LONG_ALIGN in uaccess.h\n\nUse the new PPC_LONG_ALIGN macro instead of passing an argument\nto the asm for consistency.\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "6a2a24bb755405d5311efaaed865042477b26f30", "tree": "ec40f3888c588438a0fbad72fb4cffb75b068efd", "parents": [ "67260ac9a397eb7c9e2980be2865912d3840b042" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Thu Jul 17 17:17:51 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 22 10:39:34 2008 +1000" }, "message": "powerpc: Add a #define for aligning to a long-sized boundary\n\nAdd a #define for aligning to a long-sized boundary. It would be nice\nto use sizeof(long) for this, but that requires generating the value\nwith asm-offsets.c, and asm-offsets.c includes asm-compat.h and we\ndescend into some sort of recursive include hell.\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "059e4938f8b060b10c4352e6c45739473bc73267", "tree": "27bd214190ba1a42b45fade9bbae310c2369d6cb", "parents": [ "6e5f1537833a9fc8251157dff403231f5c89a894" ], "author": { "name": "Masakazu Mokuno", "email": "mokuno@sm.sony.co.jp", "time": "Thu Jul 17 07:22:19 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 22 10:39:33 2008 +1000" }, "message": "powerpc/ps3: Add a sub-match id to ps3_system_bus\n\nAdd sub match id for ps3 system bus so that two different system bus\ndevices can be connected to a shared device.\n\nSigned-off-by: Masakazu Mokuno \u003cmokuno@sm.sony.co.jp\u003e\nSigned-off-by: Geoff Levand \u003cgeoffrey.levand@am.sony.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "4f3dd8a06239c0a19d772a27c2f618dc2faadf4a", "tree": "f7185cd89a1ec2c4bdb356a52a39407e432e7f7d", "parents": [ "4795b7801b07e1b7286edb0d9321433fc0eac6cc" ], "author": { "name": "Mark Nelson", "email": "markn@au1.ibm.com", "time": "Wed Jul 16 05:51:47 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 22 10:39:32 2008 +1000" }, "message": "powerpc/dma: Use the struct dma_attrs in iommu code\n\nUpdate iommu_alloc() to take the struct dma_attrs and pass them on to\ntce_build(). This change propagates down to the tce_build functions of\nall the platforms.\n\nSigned-off-by: Mark Nelson \u003cmarkn@au1.ibm.com\u003e\nSigned-off-by: Arnd Bergmann \u003carnd@arndb.de\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "4795b7801b07e1b7286edb0d9321433fc0eac6cc", "tree": "74ee09ea441a4ebb57cb2e35d2d8def1e63f98f6", "parents": [ "70694a8bab22bd0cc98ff4ee5cc75fe9be30fcd0" ], "author": { "name": "Christian Krafft", "email": "krafft@de.ibm.com", "time": "Wed Jul 16 05:51:45 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 22 10:39:32 2008 +1000" }, "message": "powerpc/cell: Add support for power button of future IBM cell blades\n\nThis patch adds support for the power button on future IBM cell blades.\nIt actually doesn\u0027t shut down the machine. Instead it exposes an\ninput device /dev/input/event0 to userspace which sends KEY_POWER\nif power button has been pressed.\nhaldaemon actually recognizes the button, so a plattform independent acpid\nreplacement should handle it correctly.\n\nSigned-off-by: Christian Krafft \u003ckrafft@de.ibm.com\u003e\nSigned-off-by: Arnd Bergmann \u003carnd@arndb.de\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "588968b6b7d34e6a88f538d1db9aca47b203623e", "tree": "0ffb6f15b2b6cab5b758f62d71f9e264ddc0a4fb", "parents": [ "542472b53ea9e0add0ba23976018210191d84754" ], "author": { "name": "Laurent Vivier", "email": "Laurent.Vivier@bull.net", "time": "Fri May 30 16:05:56 2008 +0200" }, "committer": { "name": "Avi Kivity", "email": "avi@qumranet.com", "time": "Sun Jul 20 12:42:31 2008 +0300" }, "message": "KVM: Add coalesced MMIO support (powerpc part)\n\nThis patch enables coalesced MMIO for powerpc architecture.\nIt defines KVM_MMIO_PAGE_OFFSET and KVM_CAP_COALESCED_MMIO.\nIt enables the compilation of coalesced_mmio.c.\n\nSigned-off-by: Laurent Vivier \u003cLaurent.Vivier@bull.net\u003e\nSigned-off-by: Avi Kivity \u003cavi@qumranet.com\u003e\n" }, { "commit": "6cfd8990e27d3a491c1c605d6cbc18a46ae51fef", "tree": "89ff46a4d744fa20e236186deef82971a36e9498", "parents": [ "2d07db33d1875dcaada8eb7e69c68aeede722bb5" ], "author": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Wed Jul 09 10:03:28 2008 -0500" }, "committer": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Wed Jul 16 17:57:51 2008 -0500" }, "message": "powerpc: rework FSL Book-E PTE access and TLB miss\n\nThis converts the FSL Book-E PTE access and TLB miss handling to match\nwith the recent changes to 44x that introduce support for non-atomic PTE\noperations in pgtable-ppc32.h and removes write back to the PTE from\nthe TLB miss handlers. In addition, the DSI interrupt code no longer\ntries to fixup write permission, this is left to generic code, and\n_PAGE_HWWRITE is gone.\n\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\n" }, { "commit": "7e1cc9c55a2a4af62f30fade62fb612a243def39", "tree": "68e0d0812543a83d3b611dd9aaade13cca952353", "parents": [ "4cd7e1cbd43bb67927af2b8b4e0ffd43fd5ed6b4" ], "author": { "name": "Andy Fleming", "email": "afleming@freescale.com", "time": "Wed May 07 13:19:44 2008 -0500" }, "committer": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Wed Jul 16 17:57:45 2008 -0500" }, "message": "powerpc: Fix a bunch of sparse warnings in the qe_lib\n\nMostly having to do with not marking things __iomem. And some failure\nto use appropriate accessors to read MMIO regs.\n\nSigned-off-by: Andy Fleming \u003cafleming@freescale.com\u003e\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\n" }, { "commit": "d49747bdfb2ddebea24d1580da55b79d093d48a9", "tree": "cb2ae6ea03bab0ff7901c9997ef50131bba6b511", "parents": [ "7e72063c9aaeb618815589cd4d57f26186e6fcad" ], "author": { "name": "Scott Wood", "email": "scottwood@freescale.com", "time": "Tue Oct 09 12:37:13 2007 -0500" }, "committer": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Wed Jul 16 17:57:30 2008 -0500" }, "message": "powerpc/mpc83xx: Power Management support\n\nBasic PM support for 83xx. Standby is implemented as sleep.\nSuspend-to-RAM is implemented as \"deep sleep\" (with the processor\nturned off) on 831x.\n\nSigned-off-by: Scott Wood \u003cscottwood@freescale.com\u003e\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\n" }, { "commit": "84c3d4aaec3338201b449034beac41635866bddf", "tree": "3412951682fb2dd4feb8a5532f8efbaf8b345933", "parents": [ "43d2548bb2ef7e6d753f91468a746784041e522d", "fafa3a3f16723997f039a0193997464d66dafd8f" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 16 11:07:59 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 16 11:07:59 2008 +1000" }, "message": "Merge commit \u0027origin/master\u0027\n\nManual merge of:\n\n\tarch/powerpc/Kconfig\n\tarch/powerpc/kernel/stacktrace.c\n\tarch/powerpc/mm/slice.c\n\tarch/ppc/kernel/smp.c" }, { "commit": "1a781a777b2f6ac46523fe92396215762ced624d", "tree": "4f34bb4aade85c0eb364b53d664ec7f6ab959006", "parents": [ "b9d2252c1e44fa83a4e65fdc9eb93db6297c55af", "42a2f217a5e324ed5f2373ab1b7a0a15187c4d6c" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jul 15 21:55:59 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jul 15 21:55:59 2008 +0200" }, "message": "Merge branch \u0027generic-ipi\u0027 into generic-ipi-for-linus\n\nConflicts:\n\n\tarch/powerpc/Kconfig\n\tarch/s390/kernel/time.c\n\tarch/x86/kernel/apic_32.c\n\tarch/x86/kernel/cpu/perfctr-watchdog.c\n\tarch/x86/kernel/i8259_64.c\n\tarch/x86/kernel/ldt.c\n\tarch/x86/kernel/nmi_64.c\n\tarch/x86/kernel/smpboot.c\n\tarch/x86/xen/smp.c\n\tinclude/asm-x86/hw_irq_32.h\n\tinclude/asm-x86/hw_irq_64.h\n\tinclude/asm-x86/mach-default/irq_vectors.h\n\tinclude/asm-x86/mach-voyager/irq_vectors.h\n\tinclude/asm-x86/smp.h\n\tkernel/Makefile\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "43d2548bb2ef7e6d753f91468a746784041e522d", "tree": "77d13fcd48fd998393abb825ec36e2b732684a73", "parents": [ "585583d95c5660973bc0cf64add517b040acd8a4", "85082fd7cbe3173198aac0eb5e85ab1edcc6352c" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 15 15:44:51 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 15 15:44:51 2008 +1000" }, "message": "Merge commit \u002785082fd7cbe3173198aac0eb5e85ab1edcc6352c\u0027 into test-build\n\nManual fixup of:\n\n\tarch/powerpc/Kconfig" }, { "commit": "585583d95c5660973bc0cf64add517b040acd8a4", "tree": "4885b69235f5d34bd76260747dcf93f51a362b50", "parents": [ "7ff86b0317bc40c665aab62f3b7669713ade07c5" ], "author": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Mon Jul 14 08:08:45 2008 -0500" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 15 15:44:02 2008 +1000" }, "message": "powerpc: Fix pte_update for CONFIG_PTE_64BIT and !PTE_ATOMIC_UPDATES\n\nBecause the pte is now 64-bits the compiler was optimizing the update\nto always clear the upper 32-bits of the pte. We need to ensure the\nclr mask is treated as an unsigned long long to get the proper behavior.\n\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nAcked-by: Josh Boyer \u003cjwboyer@linux.vnet.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "7c29217096d83f657e6ee70479af09b46f4275f6", "tree": "96fd96226d2998b1f56d7fb8110e27c489dbba89", "parents": [ "01f4b8b8b8db09b88be7df7e51192e4e678b69d3" ], "author": { "name": "Michael Neuling", "email": "mikey@neuling.org", "time": "Fri Jul 11 16:29:12 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 15 12:29:23 2008 +1000" }, "message": "powerpc: fix giveup_vsx to save registers correctly\n\ngiveup_vsx didn\u0027t save the FPU and VMX regsiters. Change it to be\nlike giveup_fpr/altivec which save these registers.\n\nAlso update call sites where FPU and VMX are already saved to use the\noriginal giveup_vsx (renamed to __giveup_vsx).\n\nSigned-off-by: Michael Neuling \u003cmikey@neuling.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "0f47331475201c7785454030a9976c8ac902a35d", "tree": "62c366e29e7a3e2731cdb872dfe8368dfaae65d1", "parents": [ "fe9e8d53772b5ea9ccf8ea4e8f0f009a6885eb70" ], "author": { "name": "Nathan Lynch", "email": "ntl@pobox.com", "time": "Thu Jul 10 01:06:57 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 15 12:24:57 2008 +1000" }, "message": "powerpc: Add PPC_FEATURE_PSERIES_PERFMON_COMPAT\n\nBackground from Maynard Johnson:\nAs of POWER6, a set of 32 common events is defined that must be\nsupported on all future POWER processors. The main impetus for this\ncompat set is the need to support partition migration, especially from\nprocessor P(n) to processor P(n+1), where performance software that\u0027s\nrunning in the new partition may not be knowledgeable about processor\nP(n+1). If a performance tool determines it does not support the\nphysical processor, but is told (via the\nPPC_FEATURE_PSERIES_PERFMON_COMPAT bit) that the processor supports\nthe notion of the PMU compat set, then the performance tool can\nsurface just those events to the user of the tool.\n\nPPC_FEATURE_PSERIES_PERFMON_COMPAT indicates that the PMU supports at\nleast this basic subset of events which is compatible across POWER\nprocessor lines.\n\nSigned-off-by: Nathan Lynch \u003cntl@pobox.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "b3fcaaa8a6359e9ed623ed4c1d2d48c79eed4648", "tree": "d19456b1c7a928e643db783547459e53839a96d9", "parents": [ "5b0504c0d795d6b0a904ff861c043d7a231f67a4" ], "author": { "name": "Stephen Rothwell", "email": "sfr@canb.auug.org.au", "time": "Mon Jul 14 19:25:57 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 15 12:24:53 2008 +1000" }, "message": "powerpc: mman.h export fixups\n\nCommit ef3d3246a0d06be622867d21af25f997aeeb105f (\"powerpc/mm: Add Strong\nAccess Ordering support\") in the powerpc/{next,master} tree caused the\nfollowing in a powerpc allmodconfig build:\n\nusr/include/asm/mman.h requires linux/mm.h, which does not exist in exported headers\n\nWe should not use CONFIG_PPC64 in an unprotected (by __KERNEL__)\nsection of an exported include file and linux/mm.h is not exported. So\nprotect the whole section that is CONFIG_PPC64 with __KERNEL__ and put\nthe two introduced includes in there as well.\n\nSigned-off-by: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nAcked-by: Dave Kleikamp \u003cshaggy@linux.vnet.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "930074b6b9c4895d20cdadba5aff97907e28728d", "tree": "3725eca121188f2e9c3b8bb4d4b8ba35e92640c7", "parents": [ "3fd44736db9a5bf33e4a216b9cd43c9cfd57c459", "2bf3016f89344d4cd8b2c96bbec2b642a2bde413" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 15 11:54:57 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 15 11:54:57 2008 +1000" }, "message": "Merge commit \u0027jwb/jwb-next\u0027\n" }, { "commit": "11c2d8174ed3dc4f1971564732689b4a39129702", "tree": "ac00daa548ea8ac24ae7a5c8062312e335ab9858", "parents": [ "cde274c0c789404df8ece3f9e7d6506caf0127e2", "bce7f793daec3e65ec5c5705d2457b81fe7b5725" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Mon Jul 14 14:29:49 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Mon Jul 14 14:29:49 2008 +1000" }, "message": "Merge commit \u0027origin/HEAD\u0027 into test-merge\n\nManual fixup of include/asm-powerpc/pgtable-ppc64.h" }, { "commit": "bac0c9103b31c3dd83ad9d731dd9834e2ba75e4f", "tree": "702dd6a7ce06d224d594c2293af546b11ac9f51b", "parents": [ "6329d3021bcfa9038621e6e917d98929421d8ec8", "98a05ed4bd7774f533ab185fe0bf2fdc58292d7c" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jul 10 11:43:00 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jul 10 11:43:00 2008 +0200" }, "message": "Merge branch \u0027tracing/ftrace\u0027 into auto-ftrace-next\n" }, { "commit": "1bc54c03117b90716e0dedd7abb2a20405de65df", "tree": "8e82fd610abaff36f1e20b5aaaf7bdeaee883aac", "parents": [ "beae4c03c0fe69cf7d57518aa0572ad21730b8be" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jul 08 15:54:40 2008 +1000" }, "committer": { "name": "Josh Boyer", "email": "jwboyer@linux.vnet.ibm.com", "time": "Wed Jul 09 13:36:17 2008 -0400" }, "message": "powerpc: rework 4xx PTE access and TLB miss\n\nThis is some preliminary work to improve TLB management on SW loaded\nTLB powerpc platforms. This introduce support for non-atomic PTE\noperations in pgtable-ppc32.h and removes write back to the PTE from\nthe TLB miss handlers. In addition, the DSI interrupt code no longer\ntries to fixup write permission, this is left to generic code, and\n_PAGE_HWWRITE is gone.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Josh Boyer \u003cjwboyer@linux.vnet.ibm.com\u003e\n" }, { "commit": "ef3d3246a0d06be622867d21af25f997aeeb105f", "tree": "9f0ae1913e0e637ec3aa104cc5e81557e5661b3c", "parents": [ "379070491e1e744a59e69e5bcf3765012d15ecb4" ], "author": { "name": "Dave Kleikamp", "email": "shaggy@linux.vnet.ibm.com", "time": "Tue Jul 08 00:28:54 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 09 16:30:45 2008 +1000" }, "message": "powerpc/mm: Add Strong Access Ordering support\n\nAllow an application to enable Strong Access Ordering on specific pages of\nmemory on Power 7 hardware. Currently, power has a weaker memory model than\nx86. Implementing a stronger memory model allows an emulator to more\nefficiently translate x86 code into power code, resulting in faster code\nexecution.\n\nOn Power 7 hardware, storing 0b1110 in the WIMG bits of the hpte enables\nstrong access ordering mode for the memory page. This patchset allows a\nuser to specify which pages are thus enabled by passing a new protection\nbit through mmap() and mprotect(). I have defined PROT_SAO to be 0x10.\n\nSigned-off-by: Dave Kleikamp \u003cshaggy@linux.vnet.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "379070491e1e744a59e69e5bcf3765012d15ecb4", "tree": "32524cdac93dce578438d14529f2a5c7caca5092", "parents": [ "aba46c5027cb59d98052231b36efcbbde9c77a1d" ], "author": { "name": "Dave Kleikamp", "email": "shaggy@linux.vnet.ibm.com", "time": "Tue Jul 08 00:28:53 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 09 16:30:45 2008 +1000" }, "message": "powerpc/mm: Add SAO Feature bit to the cputable\n\nAdd the CPU feature bit for the new Strong Access Ordering\nfacility of Power7\n\nSigned-off-by: Dave Kleikamp \u003cshaggy@linux.vnet.ibm.com\u003e\nSigned-off-by: Joel Schopp \u003cjschopp@austin.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "aba46c5027cb59d98052231b36efcbbde9c77a1d", "tree": "b69dd362c74db562789d14136294c5fcbb7632e7", "parents": [ "b845f313d78e4e259ec449909e3bbadf77b53a6d" ], "author": { "name": "Dave Kleikamp", "email": "shaggy@linux.vnet.ibm.com", "time": "Tue Jul 08 00:28:52 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 09 16:30:45 2008 +1000" }, "message": "powerpc/mm: Define flags for Strong Access Ordering\n\nThis patch defines:\n\n- PROT_SAO, which is passed into mmap() and mprotect() in the prot field\n- VM_SAO in vma-\u003evm_flags, and\n- _PAGE_SAO, the combination of WIMG bits in the pte that enables strong\naccess ordering for the page.\n\nSigned-off-by: Dave Kleikamp \u003cshaggy@linux.vnet.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "e5093ff05d36c64e8f36a9ddb26358256dc133ea", "tree": "06e27ffb2a70ddb293c56aaf6499e618fce761d1", "parents": [ "058c78f4ba89df7b2de82ac271452f09e2b8fa05" ], "author": { "name": "Srinivasa Ds", "email": "srinivasa@in.ibm.com", "time": "Tue Jul 08 00:22:27 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 09 16:30:44 2008 +1000" }, "message": "powerpc: Implement task_pt_regs() accessor\n\nThe task_pt_regs() macro allows access to the pt_regs of a given task.\n\nThis macro is not currently defined for the powerpc architecture, but\nwe need it for some upcoming utrace additions.\n\nSigned-off-by: Srinivasa DS \u003csrinivasa@in.ibm.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "3a4c6f0b1540811110a59112b4c83f55c229728c", "tree": "6d2cc36af1100103ceb649a6fbdf8b2a9b526947", "parents": [ "7e5f8105030038de94b44a74cd7b64dd000830fc" ], "author": { "name": "Mark Nelson", "email": "markn@au1.ibm.com", "time": "Sat Jul 05 05:05:45 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 09 16:30:44 2008 +1000" }, "message": "powerpc: move device_to_mask() to dma-mapping.h\n\nMove device_to_mask() to dma-mapping.h because we need to use it from\noutside dma_64.c in a later patch.\n\nSigned-off-by: Mark Nelson \u003cmarkn@au1.ibm.com\u003e\nSigned-off-by: Arnd Bergmann \u003carnd@arndb.de\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "3affedc4e1ce837033b6c5e9289d2ce2f5a62d31", "tree": "83296af2c727e5b5f64b88b629dcf37f8e60e3f0", "parents": [ "c8692362db3db3a6f644e05a477161d967430aac" ], "author": { "name": "Mark Nelson", "email": "markn@au1.ibm.com", "time": "Sat Jul 05 05:05:42 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 09 16:30:43 2008 +1000" }, "message": "powerpc/dma: implement new dma_*map*_attrs() interfaces\n\nUpdate powerpc to use the new dma_*map*_attrs() interfaces. In doing so\nupdate struct dma_mapping_ops to accept a struct dma_attrs and propagate\nthese changes through to all users of the code (generic IOMMU and the\n64bit DMA code, and the iseries and ps3 platform code).\n\nThe old dma_*map_*() interfaces are reimplemented as calls to the\ncorresponding new interfaces.\n\nSigned-off-by: Mark Nelson \u003cmarkn@au1.ibm.com\u003e\nSigned-off-by: Arnd Bergmann \u003carnd@arndb.de\u003e\nAcked-by: Geoff Levand \u003cgeoffrey.levand@am.sony.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "c8692362db3db3a6f644e05a477161d967430aac", "tree": "b240cfe972dda9768fc330458da5667a7c15864f", "parents": [ "fabb657005edbbcb0d13ee49a40f1f4b042a1d19" ], "author": { "name": "Mark Nelson", "email": "markn@au1.ibm.com", "time": "Sat Jul 05 05:05:41 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 09 16:30:43 2008 +1000" }, "message": "powerpc/dma: Add struct iommu_table argument to iommu_map_sg()\n\nMake iommu_map_sg take a struct iommu_table. It did so before commit\n740c3ce66700640a6e6136ff679b067e92125794 (iommu sg merging: ppc: make\niommu respect the segment size limits).\n\nThis stops the function looking in the archdata.dma_data for the iommu\ntable because in the future it will be called with a device that has\nno table there.\n\nThis also has the nice side effect of making iommu_map_sg() match the\nother map functions.\n\nSigned-off-by: Mark Nelson \u003cmarkn@au1.ibm.com\u003e\nSigned-off-by: Arnd Bergmann \u003carnd@arndb.de\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "fabb657005edbbcb0d13ee49a40f1f4b042a1d19", "tree": "5f402e272ff2933c9e3fe9d6e0eeb10c166d7c2c", "parents": [ "88b90c96b787ecb5c72384b6873468f814cce650" ], "author": { "name": "Maxim Shchetynin", "email": "maxim@de.ibm.com", "time": "Sat Jul 05 05:05:39 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 09 16:30:42 2008 +1000" }, "message": "powerpc/spufs: add atomic busy_spus counter to struct cbe_spu_info\n\nAs nr_active counter includes also spus waiting for syscalls to return\nwe need a seperate counter that only counts spus that are currently running\non spu side. This counter shall be used by a cpufreq governor that targets\na frequency dependent from the number of running spus.\n\nSigned-off-by: Christian Krafft \u003ckrafft@de.ibm.com\u003e\nAcked-by: Jeremy Kerr \u003cjk@ozlabs.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "86df86424939d316b1f6cfac1b6204f0c7dee317", "tree": "447924f4ecf0ae4bd2ba1af513ff84af66e681b1", "parents": [ "7b51ba38d9baca207152d1c97ec793cfb673a6cd" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Tue Jul 08 15:58:16 2008 +1000" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jul 08 09:27:58 2008 -0700" }, "message": "Correct hash flushing from huge_ptep_set_wrprotect()\n\nAs Andy Whitcroft recently pointed out, the current powerpc version of\nhuge_ptep_set_wrprotect() has a bug. It just calls ptep_set_wrprotect()\nwhich in turn calls pte_update() then hpte_need_flush() with the \u0027huge\u0027\nargument set to 0. This will cause hpte_need_flush() to flush the wrong\nhash entries (of any). Andy\u0027s fix for this is already in the powerpc\ntree as commit 016b33c4958681c24056abed8ec95844a0da80a3.\n\nI have confirmed this is a real bug, not masked by some other\nsynchronization, with a new testcase for libhugetlbfs. A process write\na (MAP_PRIVATE) hugepage mapping, fork(), then alter the mapping and\nhave the child incorrectly see the second write.\n\nTherefore, this should be fixed for 2.6.26, and for the stable tree.\nHere is a suitable patch for 2.6.26, which I think will also be suitable\nfor the stable tree (neither of the headers in question has been changed\nmuch recently).\n\nIt is cut down slighlty from Andy\u0027s original version, in that it does\nnot include a 32-bit version of huge_ptep_set_wrprotect(). Currently,\nhugepages are not supported on any 32-bit powerpc platform. When they\nare, a suitable 32-bit version can be added - the only 32-bit hardware\nwhich supports hugepages does not use the conventional hashtable MMU and\nso will have different needs anyway.\n\nSigned-off-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "3c3f67eafad12d4ccabe491c6c8a50bf6e75b89a", "tree": "be4081be92d8a7c165281242384cb79cb8c2d06d", "parents": [ "92ecd1790b10e12015070e33a0f70493d51aca50" ], "author": { "name": "Nathan Fontenot", "email": "nfont@austin.ibm.com", "time": "Thu Jul 03 13:22:39 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Jul 03 16:58:16 2008 +1000" }, "message": "powerpc/pseries: Update the device tree correctly for drconf memory add/remove\n\nThis updates the device tree manipulation routines so that memory\nadd/remove of lmbs represented under the\nibm,dynamic-reconfiguration-memory node of the device tree invokes the\nhotplug notifier chain.\n\nThis change is needed because of the change in the way memory is\nrepresented under the ibm,dynamic-reconfiguration-memory node. All lmbs\nare described in the ibm,dynamic-memory property instead of having a\nseparate node for each lmb as in previous device tree layouts. This\nrequires the update_node() routine to check for updates to the\nibm,dynamic-memory property and invoke the hotplug notifier chain.\n\nThis also updates the pseries hotplug notifier to be able to gather information\nfor lmbs represented under the ibm,dynamic-reconfiguration-memory node and\nhave the lmbs added/removed.\n\nSigned-off-by: Nathan Fontenot \u003cnfont@austin.ibm.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "138fc1ee06e58f12fc2b755e435ce15bb36a0471", "tree": "c553c9186d0d3d70b444680c0f500fc58ced61a4", "parents": [ "6a274c08f2f4dfac7167bbd849621f3a2b55d424" ], "author": { "name": "Michael Neuling", "email": "mikey@neuling.org", "time": "Wed Jul 02 22:51:37 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Jul 03 16:58:13 2008 +1000" }, "message": "powerpc: Remove old dump_task_* functions\n\nSince Roland\u0027s ptrace cleanup starting with commit\nf65255e8d51ecbc6c9eef20d39e0377d19b658ca (\"[POWERPC] Use user_regset\naccessors for FP regs\"), the dump_task_* functions are no longer being\nused.\n\nSigned-off-by: Michael Neuling \u003cmikey@neuling.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "2d1b2027626d5151fff8ef7c06ca8e7876a1a510", "tree": "6ecc861f4f45a5d26309bf12683aa0372358ef7c", "parents": [ "5888da18765ca9af7f10015263d8bc8e3057f128" ], "author": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Wed Jul 02 01:16:40 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Jul 03 16:58:10 2008 +1000" }, "message": "powerpc: Fixup lwsync at runtime\n\nTo allow for a single kernel image on e500 v1/v2/mc we need to fixup lwsync\nat runtime. On e500v1/v2 lwsync causes an illop so we need to patch up\nthe code. We default to \u0027sync\u0027 since that is always safe and if the cpu\nis capable we will replace \u0027sync\u0027 with \u0027lwsync\u0027.\n\nWe introduce CPU_FTR_LWSYNC as a way to determine at runtime if this is\nneeded. This flag could be moved elsewhere since we dont really use it\nfor the normal CPU_FTR purpose.\n\nFinally we only store the relative offset in the fixup section to keep it\nas small as possible rather than using a full fixup_entry.\n\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "e17a2565bf61204cb925c3f77c3c7f6a09eb2fbe", "tree": "f82df5037a68fa9ded94d81115dde005057ad923", "parents": [ "db7f37de2c8346c33cf9279fa9d8e8316e8d821c" ], "author": { "name": "Michael Neuling", "email": "mikey@neuling.org", "time": "Tue Jul 01 17:00:39 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Jul 03 16:58:08 2008 +1000" }, "message": "powerpc: Fix compile warning in init_thread\n\nCurrently we get this warning:\narch/powerpc/kernel/init_task.c:33: warning: missing braces around initializer\narch/powerpc/kernel/init_task.c:33: warning: (near initialization for \u0027init_task.thread.fpr[0]\u0027)\n\nThis fixes it.\n\nNoticed by Stephen Rothwell.\n\nSigned-off-by: Michael Neuling \u003cmikey@neuling.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "db7f37de2c8346c33cf9279fa9d8e8316e8d821c", "tree": "0a49c9aeb1c5c071d5766fca1fbfc6c5f2c3d0ff", "parents": [ "f3e909c2750eb20536bacacc867dc9047b70546a" ], "author": { "name": "Tony Breeds", "email": "tony@bakeyournoodle.com", "time": "Tue Jul 01 11:30:06 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Jul 03 16:58:07 2008 +1000" }, "message": "powerpc: Fix building of arch/powerpc/mm/mem.o when MEMORY_HOTPLUG\u003dy and SPARSEMEM\u003dn\n\nCurrently the kernel fails to build with the above config options with:\n CC arch/powerpc/mm/mem.o\narch/powerpc/mm/mem.c: In function \u0027arch_add_memory\u0027:\narch/powerpc/mm/mem.c:130: error: implicit declaration of function \u0027create_section_mapping\u0027\n\nThis explicitly includes asm/sparsemem.h in arch/powerpc/mm/mem.c and\nmoves the guards in include/asm-powerpc/sparsemem.h to protect the\nSPARSEMEM specific portions only.\n\nSigned-off-by: Tony Breeds \u003ctony@bakeyournoodle.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "f3e909c2750eb20536bacacc867dc9047b70546a", "tree": "97bf54aafb93313d54aaeaa05eb99d1a9ab48c3c", "parents": [ "436db693c4f4d02d375780a1f0b2ebdca2451cd6" ], "author": { "name": "Michael Neuling", "email": "mikey@neuling.org", "time": "Tue Jul 01 14:01:39 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 14:47:09 2008 +1000" }, "message": "powerpc: Update for VSX core file and ptrace\n\nThis correctly hooks the VSX dump into Roland McGrath core file\ninfrastructure. It adds the VSX dump information as an additional elf\nnote in the core file (after talking more to the tool chain/gdb guys).\nThis also ensures the formats are consistent between signals, ptrace\nand core files.\n\nSigned-off-by: Michael Neuling \u003cmikey@neuling.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "a91a03ee31a5c29a934708b7cf37bb8da516d016", "tree": "bb2c25456759a865a64ae5326846301e7962802b", "parents": [ "89b5810f6ed4b2d42415e5ec656ab6b148cd2bde" ], "author": { "name": "Eric B Munson", "email": "ebmunson@us.ibm.com", "time": "Tue Jul 01 02:12:13 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 14:47:02 2008 +1000" }, "message": "powerpc: Keep 3 high personality bytes across exec\n\nCurrently when a 32 bit process is exec\u0027d on a powerpc 64 bit host the\nvalue in the top three bytes of the personality is clobbered. patch\nadds a check in the SET_PERSONALITY macro that will carry all the\nvalues in the top three bytes across the exec.\n\nThese three bytes currently carry flags to disable address randomisation,\nlimit the address space, force zeroing of an mmapped page, etc. Should an\napplication set any of these bits they will be maintained and honoured on\nhomogeneous environment but discarded and ignored on a heterogeneous\nenvironment. So if an application requires all mmapped pages to be initialised\nto zero and a wrapper is used to setup the personality and exec the target,\nthese flags will remain set on an all 32 or all 64 bit envrionment, but they\nwill be lost in the exec on a mixed 32/64 bit environment. Losing these bits\nmeans that the same application would behave differently in different\nenvironments. Tested on a POWER5+ machine with 64bit kernel and a mixed\n64/32 bit user space.\n\nSigned-off-by: Eric B Munson \u003cebmunson@us.ibm.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "89b5810f6ed4b2d42415e5ec656ab6b148cd2bde", "tree": "e3116100d5be38f2ebfaa078cd53033d1f612059", "parents": [ "fcbc5a976b1cafe2e866871c86d239d57503bfd5" ], "author": { "name": "Bart Van Assche", "email": "bart.vanassche@gmail.com", "time": "Sat Jun 28 16:51:35 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:29:00 2008 +1000" }, "message": "powerpc: Make sure that include/asm-powerpc/spinlock.h does not trigger compilation warnings\n\nWhen compiling kernel modules for ppc that include \u003clinux/spinlock.h\u003e,\ngcc prints a warning message every time it encounters a function\ndeclaration where the inline keyword appears after the return type.\nThis makes sure that the order of the inline keyword and the return\ntype is as gcc expects it. Additionally, the __inline__ keyword is\nreplaced by inline, as checkpatch expects.\n\nSigned-off-by: Bart Van Assche \u003cbart.vanassche@gmail.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "016b33c4958681c24056abed8ec95844a0da80a3", "tree": "67ba81cb6bc980119fab4eee15f09488e5777012", "parents": [ "03d70617b8a789c3721afaafde06fcbba7c7ebf1" ], "author": { "name": "Andy Whitcroft", "email": "apw@shadowen.org", "time": "Thu Jun 26 19:55:58 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:56 2008 +1000" }, "message": "powerpc: Add 64 bit version of huge_ptep_set_wrprotect\n\nThe implementation of huge_ptep_set_wrprotect() directly calls\nptep_set_wrprotect() to mark a hugepte write protected. However this\ncall is not appropriate on ppc64 kernels as this is a small page only\nimplementation. This can lead to the hash not being flushed correctly\nwhen a mapping is being converted to COW, allowing processes to continue\nusing the original copy.\n\nCurrently huge_ptep_set_wrprotect() unconditionally calls\nptep_set_wrprotect(). This is fine on ppc32 kernels as this call is\ngeneric. On 64 bit this is implemented as:\n\n\tpte_update(mm, addr, ptep, _PAGE_RW, 0);\n\nOn ppc64 this last parameter is the page size and is passed directly on\nto hpte_need_flush():\n\n\thpte_need_flush(mm, addr, ptep, old, huge);\n\nAnd this directly affects the page size we pass to flush_hash_page():\n\n\tflush_hash_page(vaddr, rpte, psize, ssize, 0);\n\nAs this changes the way the hash is calculated we will flush the wrong\npages, potentially leaving live hashes to the original page.\n\nMove the definition of huge_ptep_set_wrprotect() to the 32/64 bit specific\nheaders.\n\nSigned-off-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "ce48b2100785e5ca629fb3aa8e3b50aca808f692", "tree": "63532ff7cc68b18ca4902bd10e03fcbaaf01cade", "parents": [ "72ffff5b1792b0fa4d40a8e2f3276fff999820ec" ], "author": { "name": "Michael Neuling", "email": "mikey@neuling.org", "time": "Wed Jun 25 14:07:18 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:50 2008 +1000" }, "message": "powerpc: Add VSX context save/restore, ptrace and signal support\n\nThis patch extends the floating point save and restore code to use the\nVSX load/stores when VSX is available. This will make FP context\nsave/restore marginally slower on FP only code, when VSX is available,\nas it has to load/store 128bits rather than just 64bits.\n\nMixing FP, VMX and VSX code will get constant architected state.\n\nThe signals interface is extended to enable access to VSR 0-31\ndoubleword 1 after discussions with tool chain maintainers. Backward\ncompatibility is maintained.\n\nThe ptrace interface is also extended to allow access to VSR 0-31 full\nregisters.\n\nSigned-off-by: Michael Neuling \u003cmikey@neuling.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "72ffff5b1792b0fa4d40a8e2f3276fff999820ec", "tree": "50dbf11b043350b98fcccd9f838b0f31f49997a5", "parents": [ "b962ce9d26fd6677e6720949642420ceb029a102" ], "author": { "name": "Michael Neuling", "email": "mikey@neuling.org", "time": "Wed Jun 25 14:07:18 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:48 2008 +1000" }, "message": "powerpc: Add VSX assembler code macros\n\nThis adds the macros for the VSX load/store instruction as most\nbinutils are not going to support this for a while.\n\nAlso add VSX register save/restore macros and vsr[0-63] register definitions.\n\nSigned-off-by: Michael Neuling \u003cmikey@neuling.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "b962ce9d26fd6677e6720949642420ceb029a102", "tree": "dd05752d5f48204b3b87f8330be043b9c39745a8", "parents": [ "c6e6771b87d4e339d27f1383c8a808ae9b4ee5b8" ], "author": { "name": "Michael Neuling", "email": "mikey@neuling.org", "time": "Wed Jun 25 14:07:18 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:47 2008 +1000" }, "message": "powerpc: Add VSX CPU feature\n\nAdd a VSX CPU feature. Also add code to detect if VSX is available\nfrom the device tree.\n\nSigned-off-by: Michael Neuling \u003cmikey@neuling.org\u003e\nSigned-off-by: Joel Schopp \u003cjschopp@austin.ibm.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "c6e6771b87d4e339d27f1383c8a808ae9b4ee5b8", "tree": "1900b7350ec685c3a31f2233fd88a57e34725b5c", "parents": [ "6f3d8e6947ec98e358514fc0f7b2e37fe88a21bb" ], "author": { "name": "Michael Neuling", "email": "mikey@neuling.org", "time": "Wed Jun 25 14:07:18 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:46 2008 +1000" }, "message": "powerpc: Introduce VSX thread_struct and CONFIG_VSX\n\nThe layout of the new VSR registers and how they overlap on top of the\nlegacy FPR and VR registers is:\n\n VSR doubleword 0 VSR doubleword 1\n ----------------------------------------------------------------\n VSR[0] | FPR[0] | |\n ----------------------------------------------------------------\n VSR[1] | FPR[1] | |\n ----------------------------------------------------------------\n | ... | |\n | ... | |\n ----------------------------------------------------------------\n VSR[30] | FPR[30] | |\n ----------------------------------------------------------------\n VSR[31] | FPR[31] | |\n ----------------------------------------------------------------\n VSR[32] | VR[0] |\n ----------------------------------------------------------------\n VSR[33] | VR[1] |\n ----------------------------------------------------------------\n | ... |\n | ... |\n ----------------------------------------------------------------\n VSR[62] | VR[30] |\n ----------------------------------------------------------------\n VSR[63] | VR[31] |\n ----------------------------------------------------------------\n\nVSX has 64 128bit registers. The first 32 regs overlap with the FP\nregisters and hence extend them with and additional 64 bits. The\nsecond 32 regs overlap with the VMX registers.\n\nThis commit introduces the thread_struct changes required to reflect\nthis register layout. Ptrace and signals code is updated so that the\nfloating point registers are correctly accessed from the thread_struct\nwhen CONFIG_VSX is enabled.\n\nSigned-off-by: Michael Neuling \u003cmikey@neuling.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "9c75a31c3525a127f70b919856e32be3d8b03755", "tree": "3beee76d3dd4a55af868b5edfbef80c911819fed", "parents": [ "9e7511861c4f8d35852a3721c5bcd92661cb4c9f" ], "author": { "name": "Michael Neuling", "email": "mikey@neuling.org", "time": "Thu Jun 26 17:07:48 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:43 2008 +1000" }, "message": "powerpc: Add macros to access floating point registers in thread_struct.\n\nWe are going to change where the floating point registers are stored\nin the thread_struct, so in preparation add some macros to access the\nfloating point registers. Update all code to use these new macros.\n\nSigned-off-by: Michael Neuling \u003cmikey@neuling.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "fac23fe4be23259a8eaa9bad822f5b14dd07d15c", "tree": "23979268a5b893d676bba2bdb514307d5417ea56", "parents": [ "c1137c37a9370f510dc022e6e95fff036ccb90be" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Tue Jun 24 11:32:54 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:28 2008 +1000" }, "message": "powerpc: Introduce infrastructure for feature sections with alternatives\n\nThe current feature section logic only supports nop\u0027ing out code, this means\nif you want to choose at runtime between instruction sequences, one or both\ncases will have to execute the nop\u0027ed out contents of the other section, eg:\n\nBEGIN_FTR_SECTION\n\tor\t1,1,1\nEND_FTR_SECTION_IFSET(FOO)\nBEGIN_FTR_SECTION\n\tor\t2,2,2\nEND_FTR_SECTION_IFCLR(FOO)\n\nand the resulting code will be either,\n\n\tor\t1,1,1\n\tnop\n\nor,\n\tnop\n\tor\t2,2,2\n\nFor small code segments this is fine, but for larger code blocks and in\nperformance criticial code segments, it would be nice to avoid the nops.\nThis commit starts to implement logic to allow the following:\n\nBEGIN_FTR_SECTION\n\tor\t1,1,1\nFTR_SECTION_ELSE\n\tor\t2,2,2\nALT_FTR_SECTION_END_IFSET(FOO)\n\nand the resulting code will be:\n\n\tor\t1,1,1\nor,\n\tor\t2,2,2\n\nWe achieve this by extending the existing FTR macros. The current feature\nsection semantic just becomes a special case, ie. if the else case is empty\nwe nop out the default case.\n\nThe key limitation is that the size of the else case must be less than or\nequal to the size of the default case. If the else case is smaller the\nremainder of the section is nop\u0027ed.\n\nWe let the linker put the else case code in with the rest of the text,\nso that relative branches from the else case are more likley to link,\nthis has the disadvantage that we can\u0027t free the unused else cases.\n\nThis commit introduces the required macro and linker script changes, but\ndoes not enable the patching of the alternative sections.\n\nWe also need to update two hand-made section entries in reg.h and timex.h\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "c1137c37a9370f510dc022e6e95fff036ccb90be", "tree": "96fd89dd4daa06178ade06558f6ab489791be667", "parents": [ "c5157e587b33b1185cf73207fc53760cf1351430" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Tue Jun 24 11:32:48 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:26 2008 +1000" }, "message": "powerpc: Consolidate feature fixup macros for 64/32 bit\n\nCurrently we have three versions of MAKE_FTR_SECTION_ENTRY(), the macro that\ngenerates a feature section entry. There is 64bit version, a 32bit version\nand version for 32bit code built with a 64bit kernel.\n\nRather than triplicating (?) the MAKE_FTR_SECTION_ENTRY() logic, we can\nmove the 64bit/32bit differences into separate macros, and then only have\none version of MAKE_FTR_SECTION_ENTRY().\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nAcked-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "c5157e587b33b1185cf73207fc53760cf1351430", "tree": "996a4e76bae11001a8e97141c617c159dde37ec8", "parents": [ "51c52e86694f19e84600a40f6156889feafd8ae9" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Tue Jun 24 11:32:39 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:25 2008 +1000" }, "message": "powerpc: Consolidate CPU and firmware feature fixup macros\n\nThe CPU and firmware feature fixup macros are currently spread across\nthree files, firmware.h, cputable.h and asm-compat.h. Consolidate them\ninto their own file, feature-fixups.h\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nAcked-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "b7bcda631e87eb3466d0baa9885650ba7d7ed89d", "tree": "3a04957c5f1b22e2d4405ccdaa980e6e513ef388", "parents": [ "ae0dc73625f9b0e636ccd130e394c9b654a062fb" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Tue Jun 24 11:32:35 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:23 2008 +1000" }, "message": "powerpc: Add PPC_NOP_INSTR, a hash define for the preferred nop instruction\n\nA bunch of code has hard-coded the value for a \"nop\" instruction, it\nwould be nice to have a #define for it.\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nAcked-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "411781a290b0d0a31fd73826b3ee110f1e3cc3b6", "tree": "4a5eb482d99916c17f19a013b52cf808161f32ea", "parents": [ "07630a37beefe8e4401c602f04e3e5bcbba50b31" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Tue Jun 24 11:32:29 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:21 2008 +1000" }, "message": "powerpc: Add new code patching routines\n\nThis commit adds some new routines for patching code, which will be used\nin a following commit.\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "07630a37beefe8e4401c602f04e3e5bcbba50b31", "tree": "7e7c7b76abe634eeebb1b161ebfbd18638af2149", "parents": [ "053a858efa46c9ab86363b271374ec02ad2af753" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Tue Jun 24 11:32:28 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:20 2008 +1000" }, "message": "powerpc: Add ppc_function_entry() which gets the entry point for a function\n\nBecause function pointers point to different things on 32-bit vs 64-bit,\nadd a macro that deals with dereferencing the OPD on 64-bit. The soon to\nbe merged ftrace wants this, as well as other code I am working on.\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nAcked-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "e7a57273c6407bb6903fbaddec8c2119bf318617", "tree": "4d5b787c286e1d0ae64f757ef1f68fedd9743a3c", "parents": [ "aaddd3eacaeaef3503035750b3f21ac2bfe97cbf" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Tue Jun 24 11:32:22 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:19 2008 +1000" }, "message": "powerpc: Allow create_branch() to return errors\n\nCurrently create_branch() creates a branch instruction for you, and\npatches it into the call site. In some circumstances it would be nice\nto be able to create the instruction and patch it later, and also some\ncode might want to check for errors in the branch creation before\ndoing the patching. A future commit will change create_branch() to\ncheck for errors.\n\nFor callers that don\u0027t care, replace create_branch() with\npatch_branch(), which just creates the branch and patches it directly.\n\nWhile we\u0027re touching all the callers, change to using unsigned int *,\nas this seems to match usage better. That allows (and requires) us to\nremove the volatile in the definition of vector in powermac/smp.c and\nmpc86xx_smp.c, that\u0027s correct because now that we\u0027re passing vector as\nan unsigned int * the compiler knows that it\u0027s value might change\nacross the patch_branch() call.\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nAcked-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nAcked-by: Jon Loeliger \u003cjdl@freescale.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "aaddd3eacaeaef3503035750b3f21ac2bfe97cbf", "tree": "2bac0bedc2185edec916679d218e1c8b89276453", "parents": [ "73f38fe1b563a9d23ffacbda7b51decf41b0c49c" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Tue Jun 24 11:32:21 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:18 2008 +1000" }, "message": "powerpc: Move code patching code into arch/powerpc/lib/code-patching.c\n\nWe currently have a few routines for patching code in asm/system.h, because\nthey didn\u0027t fit anywhere else. I\u0027d like to clean them up a little and add\nsome more, so first move them into a dedicated C file - they don\u0027t need to\nbe inlined.\n\nWhile we\u0027re moving the code, drop create_function_call(), it\u0027s intended\ncaller never got merged and will be replaced in future with something\ndifferent.\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nAcked-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "178f8d78fdeaace8b22a759a059b74f39caf23a4", "tree": "b2c7561f04f86944aa76206495fe02a3f5aa8e6d", "parents": [ "d1cdcf2241723d6596d56abb8777b5ef79b4a878" ], "author": { "name": "Adrian Bunk", "email": "bunk@kernel.org", "time": "Tue Jun 24 03:48:28 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:15 2008 +1000" }, "message": "powerpc: asm/elf.h: Reduce userspace header\n\nThis makes asm/elf.h export less non-userspace stuff to userspace.\n\nSigned-off-by: Adrian Bunk \u003cbunk@kernel.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "d1cdcf2241723d6596d56abb8777b5ef79b4a878", "tree": "05c9fe12af0027c517b08f4c6c205615d1979554", "parents": [ "9b4a8dd2e9f8af206eb39e3d99c442b0d6158953" ], "author": { "name": "Adrian Bunk", "email": "bunk@kernel.org", "time": "Tue Jun 24 03:48:21 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:28:09 2008 +1000" }, "message": "powerpc: Don\u0027t export asm/asm-compat.h to userspace\n\nasm/asm-compat.h doesn\u0027t seem to be intended for userspace usage.\n\nSigned-off-by: Adrian Bunk \u003cbunk@kernel.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "3a8247cc2c856930f34eafce33f6a039227ee175", "tree": "aa8599cdf09893f1150a2bc137878d8b8a661780", "parents": [ "e952e6c4d6635b36c212c056a9427bd93460178c" ], "author": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Wed Jun 18 15:29:12 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Jul 01 11:27:57 2008 +1000" }, "message": "powerpc: Only demote individual slices rather than whole process\n\nAt present, if we have a kernel with a 64kB page size, and some\nprocess maps something that has to be mapped with 4kB pages (such as a\ncache-inhibited mapping on POWER5+, or the eHCA infiniband queue-pair\npages), we change the process to use 4kB pages everywhere. This hurts\nthe performance of HPC programs that access eHCA from userspace.\n\nWith this patch, the kernel will only demote the slice(s) containing\nthe eHCA or cache-inhibited mappings, leaving the remaining slices\nable to use 64kB hardware pages.\n\nThis also changes the slice_get_unmapped_area code so that it is\nwilling to place a 64k-page mapping into (or across) a 4k-page slice\nif there is no better alternative, i.e. if the program specified\nMAP_FIXED or if there is not sufficient space available in slices that\nare either empty or already have 64k-page mappings in them.\n\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "e952e6c4d6635b36c212c056a9427bd93460178c", "tree": "1791007d187ffea2e66a0150977dc5f3cc3b8c53", "parents": [ "e2d755051129c61a9f67bf752d0b7cc82b115338" ], "author": { "name": "Michael Neuling", "email": "mikey@neuling.org", "time": "Wed Jun 18 10:47:26 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Jun 30 22:31:11 2008 +1000" }, "message": "powerpc: Add cputable entry for POWER7\n\nAdd a cputable entry for the POWER7 processor.\n\nAlso tell firmware that we know about POWER7.\n\nSigned-off-by: Michael Neuling \u003cmikey@neuling.org\u003e\nSigned-off-by: Joel Schopp \u003cjschopp@austin.ibm.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "e2d755051129c61a9f67bf752d0b7cc82b115338", "tree": "d3b150352393244018e26469383a9f859517b757", "parents": [ "316a405841cc03723d401b098d188aa4e3daa69b" ], "author": { "name": "Scott Wood", "email": "scottwood@freescale.com", "time": "Wed Jun 18 02:59:59 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Jun 30 22:31:07 2008 +1000" }, "message": "powerpc: Fix copy-and-paste error in clrsetbits_le16\n\nThis was pointed out by Detlev Zundel when this code was being\nadded to U-boot.\n\nSigned-off-by: Scott Wood \u003cscottwood@freescale.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "316a405841cc03723d401b098d188aa4e3daa69b", "tree": "476be4fad16c690d1650890757aacc3095e85129", "parents": [ "7c5c4325d2d911fe54db3bc14149bfa558ae0acb" ], "author": { "name": "Becky Bruce", "email": "becky.bruce@freescale.com", "time": "Sat Jun 14 09:41:43 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Jun 30 22:31:05 2008 +1000" }, "message": "powerpc: Get rid of bitfields in ppc_bat struct\n\nWhile working on the 36-bit physical support, I noticed that there\nwas exactly one line of code that actually referenced the bitfields.\nSo I got rid of them and redefined ppc_bat as a struct of 2 u32\u0027s:\nbatu and batl. I also got rid of the previous union that held the\nbitfield structs and a word representation of the batu/l values.\n\nThis seems like a nicer solution than adding in a bunch of\nnew bitfields to support extended bat addressing that would never\nget used, and just leaving the struct as-is would have been\nincomplete in the face of large physical addressing.\n\nSigned-off-by: Becky Bruce \u003cbecky.bruce@freescale.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "7c5c4325d2d911fe54db3bc14149bfa558ae0acb", "tree": "97c02e9d03bbbb1fff89e9e44eef1e53762e823e", "parents": [ "bf2737f74ffd36f43c6ed11cd2c0826e1d59ad48" ], "author": { "name": "Becky Bruce", "email": "becky.bruce@freescale.com", "time": "Sat Jun 14 09:41:42 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Jun 30 22:31:03 2008 +1000" }, "message": "powerpc: Change BAT code to use phys_addr_t\n\nCurrently, the physical address is an unsigned long, but it should\nbe phys_addr_t in set_bat, [v/p]_mapped_by_bat. Also, create a\nmacro that can convert a large physical address into the correct\nformat for programming the BAT registers.\n\nSigned-off-by: Becky Bruce \u003cbecky.bruce@freescale.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "bf2737f74ffd36f43c6ed11cd2c0826e1d59ad48", "tree": "e42e618207c22141cb17c77dfba99473d865d5de", "parents": [ "36c35be332faa8ba1aaa8a237e72b9460117129d" ], "author": { "name": "Becky Bruce", "email": "becky.bruce@freescale.com", "time": "Sat Jun 14 09:12:44 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Jun 30 22:31:01 2008 +1000" }, "message": "powerpc: Silly spelling fix in pgtable-ppc32\n\nSigned-off-by: Becky Bruce \u003cbecky.bruce@freescale.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "aee10c6145199f872bc51f811b115a4b686b2426", "tree": "138ff9e8eb0929992d0c97cc4da67e7a939b5071", "parents": [ "41743a4e34f0777f51c1cf0675b91508ba143050" ], "author": { "name": "Arnd Bergmann", "email": "arnd@arndb.de", "time": "Thu Jun 12 19:14:34 2008 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Jun 30 22:30:55 2008 +1000" }, "message": "powerpc: Provide dummy crash_shutdown_register\n\nWhen kexec is disabled, the crash_shutdown_{un,}register\nfunctions are not available in the kernel.\nThis provides dummy inline functions for those so that\nthe callers don\u0027t have to worry about it.\n\nSigned-off-by: Arnd Bergmann \u003carnd@arndb.de\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" } ], "next": "41743a4e34f0777f51c1cf0675b91508ba143050" }