)]}' { "log": [ { "commit": "4d922c8dc332f4c7bc156fa832187661d4899cee", "tree": "d123df4223b040d0c361c5e8a02d349523bc8c6c", "parents": [ "e90f3b74d884d0f2826e06dbab4f615ca346eaa4" ], "author": { "name": "Josh Boyer", "email": "jwboyer@linux.vnet.ibm.com", "time": "Mon Aug 20 07:28:48 2007 -0500" }, "committer": { "name": "Josh Boyer", "email": "jwboyer@linux.vnet.ibm.com", "time": "Mon Aug 20 07:28:48 2007 -0500" }, "message": "[POWERPC] 40x MMU\n\nAdd MMU definitions for 40x platforms. Also fixes two warnings in 40x_mmu.c.\n\nSigned-off-by: Josh Boyer \u003cjwboyer@linux.vnet.ibm.com\u003e\nAcked-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\n" }, { "commit": "3120234551ebf5f6e24a23082334eb3897b5db41", "tree": "be5ab37d2a0be2b6ef0f883acb448c313e6999f5", "parents": [ "67f74c9d223815e30eac456b4956a846143b65c6" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Fri Jun 22 14:58:55 2007 +1000" }, "committer": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Tue Jul 03 03:00:28 2007 -0500" }, "message": "[POWERPC] Split out asm-ppc/mmu.h portions for PowerPC 8xx\n\narch/powerpc still relies on asm-ppc/mmu.h for some 32-bit MMU types.\nThis patch is another step towards fixing this. It takes the portions\nof asm-ppc/mmu.h related to 8xx embedded CPUs which are still relevant\nin arch/powerpc and puts them in a new asm-powerpc/mmu-8xx.h,\nincluded when appropriate from asm-powerpc/mmu.h.\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\n" }, { "commit": "67f74c9d223815e30eac456b4956a846143b65c6", "tree": "45b7f3658f95405c937034448d4708886746b051", "parents": [ "b3710f5a1802876717600afad10156e54d5fdb18" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Fri Jun 15 15:33:09 2007 +1000" }, "committer": { "name": "Kumar Gala", "email": "galak@kernel.crashing.org", "time": "Tue Jul 03 03:00:16 2007 -0500" }, "message": "[POWERPC] Split out asm-ppc/mmu.h portions for Freescale Book-E\n\narch/powerpc still relies on asm-ppc/mmu.h for some 32-bit MMU types.\nThis patch is another step towards fixing this. It takes the portions\nof asm-ppc/mmu.h related to Freescale Book-E which are still relevant\nin arch/powerpc and puts them in a new asm-powerpc/mmu-fsl-booke.h,\nincluded when appropriate from asm-powerpc/mmu.h.\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Kumar Gala \u003cgalak@kernel.crashing.org\u003e\n" }, { "commit": "4db68bfe71940c0851bc81041ade6dc293fe2b96", "tree": "9959af9fe8cf9e02e40ba6e86c619b48e2d42623", "parents": [ "2e6016133755eb3cc44e8efab92573d23ed75888" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Wed Jun 13 14:52:54 2007 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Jun 14 22:30:15 2007 +1000" }, "message": "[POWERPC] Split out asm-ppc/mmu.h portions for the \"classic\" hash-based MMU\n\narch/powerpc still relies on asm-ppc/mmu.h for most 32-bit MMU types.\nThis is another step towards fixing this. It takes the portions\nof asm-ppc/mmu.h related to the \"classic\" 32-bit hash page table MMU\nwhich are still relevant in arch/powerpc and puts them in a new\nasm-powerpc/mmu-hash32.h, included when appropriate from\nasm-powerpc/mmu.h.\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "57d7909e0d2dd54567ae775e22b14076b777042a", "tree": "6f2e14e0bbb92ff138ae89468136668e58e60d1f", "parents": [ "c3e8011ad1bf4791a9c6d70ac1b377df93a9f5af" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Mon Apr 30 14:06:25 2007 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Wed May 02 20:04:29 2007 +1000" }, "message": "[POWERPC] Revise PPC44x MMU code for arch/powerpc\n\nThis patch takes the definitions for the PPC44x MMU (a software loaded\nTLB) from asm-ppc/mmu.h, cleans them up of things no longer necessary\nin arch/powerpc and puts them in a new asm-powerpc/mmu_44x.h file. It\nalso substantially simplifies arch/powerpc/mm/44x_mmu.c and makes a\ncouple of small fixes necessary for the 44x MMU code to build and work\nproperly in arch/powerpc.\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "8d2169e8d6b8a91413df33bc402e0f602ceaabcc", "tree": "4de3e19d8cd9a09049e531e4cc1f02b2328b943c", "parents": [ "173ba87b9584e4cba41ce9a06916eba80baa1bf4" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Fri Apr 27 11:53:52 2007 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Fri Apr 27 21:14:26 2007 +1000" }, "message": "[POWERPC] Prepare for splitting up mmu.h by MMU type\n\nCurrently asm-powerpc/mmu.h has definitions for the 64-bit hash based\nMMU. If CONFIG_PPC64 is not set, it instead includes asm-ppc/mmu.h\nwhich contains a particularly horrible mess of #ifdefs giving the\ndefinitions for all the various 32-bit MMUs.\n\nIt would be nice to have the low level definitions for each MMU type\nneatly in their own separate files. It would also be good to wean\narch/powerpc off dependence on the old asm-ppc/mmu.h.\n\nThis patch makes a start on such a cleanup by moving the definitions\nfor the 64-bit hash MMU to their own file, asm-powerpc/mmu_hash64.h.\nDefinitions for the other MMUs still all come from asm-ppc/mmu.h,\nhowever each MMU type can now be one-by-one moved over to their own\nfile, in the process cleaning them up stripping them of cruft no\nlonger necessary in arch/powerpc.\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "57dace2391ba10135e38457904121e7ef34d0c83", "tree": "1be720be47bd6f1d929e9242b8a89a8f2e5fe61d", "parents": [ "62c05d583ec016c40011462d5f03b072bfbd3dc7" ], "author": { "name": "Arnd Bergmann", "email": "arnd.bergmann@de.ibm.com", "time": "Mon Apr 23 21:08:15 2007 +0200" }, "committer": { "name": "Arnd Bergmann", "email": "arnd@klappe.arndb.de", "time": "Mon Apr 23 21:18:55 2007 +0200" }, "message": "[POWERPC] spufs: make spu page faults not block scheduling\n\nUntil now, we have always entered the spu page fault handler\nwith a mutex for the spu context held. This has multiple\nbad side-effects:\n- it becomes impossible to suspend the context during\n page faults\n- if an spu program attempts to access its own mmio\n areas through DMA, we get an immediate livelock when\n the nopage function tries to acquire the same mutex\n\nThis patch makes the page fault logic operate on a\nstruct spu_context instead of a struct spu, and moves it\nfrom spu_base.c to a new file fault.c inside of spufs.\n\nWe now also need to copy the dar and dsisr contents\nof the last fault into the saved context to have it\naccessible in case we schedule out the context before\nactivating the page fault handler.\n\nSigned-off-by: Arnd Bergmann \u003carnd.bergmann@de.ibm.com\u003e\n" }, { "commit": "fe4a0cf1c2e79c3c256992c4f731734ecacb45c3", "tree": "dc648763c6bf4e8e64d7fc778cc64637999960d3", "parents": [ "97a9b58409403baf7a8b0ccbd3d27993790dcdab" ], "author": { "name": "Ishizaki Kou", "email": "kou.ishizaki@toshiba.co.jp", "time": "Fri Feb 02 16:42:28 2007 +0900" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Wed Feb 07 14:03:21 2007 +1100" }, "message": "[POWERPC] Celleb: htab routines\n\nAdds htab routines for Celleb platform.\n\nSigned-off-by: Kou Ishizaki \u003ckou.ishizaki@toshiba.co.jp\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "035223fb28791f0eb0d5719727355d3f6817d228", "tree": "a59490ee5cea453a0637d2aa7edb4f2f1163b0f0", "parents": [ "0f03a43b8f0fc221986a46654282ec6a1e8c6d45" ], "author": { "name": "Geoff Levand", "email": "geoffrey.levand@am.sony.com", "time": "Thu Oct 05 11:35:10 2006 -0700" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Oct 16 16:33:04 2006 +1000" }, "message": "[POWERPC] Make pSeries_lpar_hpte_insert static\n\nChange the powerpc hpte_insert routines now called through ppc_md to\nstatic scope.\n\nSigned-off-by: Geoff Levand \u003cgeoffrey.levand@am.sony.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "7d0daae4ae1a3e80d78b83cddf414a3b98a962f4", "tree": "f8dcd24a598212b58652c771a5e81c8a167bb3d1", "parents": [ "7a4571ae553e2972b7958306fd796a2fd24fd7d1" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Fri Jun 23 18:16:38 2006 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Wed Jun 28 11:59:47 2006 +1000" }, "message": "[POWERPC] powerpc: Initialise ppc_md htab pointers earlier\n\nInitialise the ppc_md htab callbacks earlier, in the probe routines. This\nallows us to call htab_finish_init() from htab_initialize(), and makes it\nprivate to hash_utils_64.c. Move htab_finish_init() and make_bl() above\nhtab_initialize() to avoid forward declarations.\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "bf72aeba2ffef599d1d386425c9e46b82be657cd", "tree": "ead8e5111dbcfa22e156999d1bb8a96e50f06fef", "parents": [ "31925323b1b51bb65db729e029472a8b1f635b7d" ], "author": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Jun 15 10:45:18 2006 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Jun 15 10:45:18 2006 +1000" }, "message": "powerpc: Use 64k pages without needing cache-inhibited large pages\n\nSome POWER5+ machines can do 64k hardware pages for normal memory but\nnot for cache-inhibited pages. This patch lets us use 64k hardware\npages for most user processes on such machines (assuming the kernel\nhas been configured with CONFIG_PPC_64K_PAGES\u003dy). User processes\nstart out using 64k pages and get switched to 4k pages if they use any\nnon-cacheable mappings.\n\nWith this, we use 64k pages for the vmalloc region and 4k pages for\nthe imalloc region. If anything creates a non-cacheable mapping in\nthe vmalloc region, the vmalloc region will get switched to 4k pages.\nI don\u0027t know of any driver other than the DRM that would do this,\nthough, and these machines don\u0027t have AGP.\n\nWhen a region gets switched from 64k pages to 4k pages, we do not have\nto clear out all the 64k HPTEs from the hash table immediately. We\nuse the _PAGE_COMBO bit in the Linux PTE to indicate whether the page\nwas hashed in as a 64k page or a set of 4k pages. If hash_page is\ntrying to insert a 4k page for a Linux PTE and it sees that it has\nalready been inserted as a 64k page, it first invalidates the 64k HPTE\nbefore inserting the 4k HPTE. The hash invalidation routines also use\nthe _PAGE_COMBO bit, to determine whether to look for a 64k HPTE or a\nset of 4k HPTEs to remove. With those two changes, we can tolerate a\nmix of 4k and 64k HPTEs in the hash table, and they will all get\nremoved when the address space is torn down.\n\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "c5cf0e30bf3d8cb56758abb612827647c0a821cf", "tree": "54a471818e91204db11f14544df0bb38bd03058f", "parents": [ "a5bba930d802009c259e56c8d53086d96f63813b" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@au1.ibm.com", "time": "Tue May 30 14:14:19 2006 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Fri Jun 09 21:20:59 2006 +1000" }, "message": "[PATCH] powerpc: Fix buglet with MMU hash management\n\nOur MMU hash management code would not set the \"C\" bit (changed bit) in\nthe hardware PTE when updating a RO PTE into a RW PTE. That would cause\nthe hardware to possibly to a write back to the hash table to set it on\nthe first store access, which in addition to being a performance issue,\nmight also hit a bug when running with native hash management (non-HV)\nas our code is specifically optimized for the case where no write back\nhappens.\n\nThus there is a very small therocial window were a hash PTE can become\ncorrupted if that HPTE has just been upgraded to read write, a store\naccess happens on it, and that races with another processor evicting\nthat same slot. Since eviction (caused by an almost full hash) is\nextremely rare, the bug is very unlikely to happen fortunately.\n\nThis fixes by allowing the updating of the protection bits in the native\nhash handling to also set (but not clear) the \"C\" bit, and, in order to\nalso improve performances in the general case, by always setting that\nbit on newly inserted hash PTE so that writeback really never happens.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "a5bba930d802009c259e56c8d53086d96f63813b", "tree": "8dd60002042bc0795b3d0544fcae7f5082405b16", "parents": [ "98a90c02792f22afd8161f96fc9b9f0f0eb0880e" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue May 30 13:51:37 2006 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Fri Jun 09 21:20:57 2006 +1000" }, "message": "[PATCH] powerpc vdso updates\n\nThis patch cleans up some locking \u0026 error handling in the ppc vdso and\nmoves the vdso base pointer from the thread struct to the mm context\nwhere it more logically belongs. It brings the powerpc implementation\ncloser to Ingo\u0027s new x86 one and also adds an arch_vma_name() function\nallowing to print [vsdo] in /proc/\u003cpid\u003e/maps if Ingo\u0027s x86 vdso patch is\nalso applied.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "f8642ebee8e46d054d83828a4048fba4ebcd8f68", "tree": "98dba337c34de68e2b319d03f8c41c7c47807ae8", "parents": [ "6c600ad8da189aebe65b765fd0349ef6c9dd8c1f" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Tue Mar 21 20:46:11 2006 +1100" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Wed Mar 22 15:04:30 2006 +1100" }, "message": "[PATCH] powerpc: Remove calculation of io hole\n\nIn mm_init_ppc64() we calculate the location of the \"IO hole\", but then\nno one ever looks at the value. So don\u0027t bother.\n\nThat\u0027s actually all mm_init_ppc64() does, so get rid of it too.\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "337a7128dbe68ebe7627b6f954cb32d30d7b11c6", "tree": "6189f61386f3be72cffab14ed1b42a508ef1793c", "parents": [ "bd6ef57e08d6cce32e93f9fc7b93d361b6a7884f" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Tue Feb 21 17:22:55 2006 +1100" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Fri Feb 24 11:36:18 2006 +1100" }, "message": "[PATCH] powerpc: Only calculate htab_size in one place for kexec\n\nFor kexec we need to know the size of the MMU hash table.\n\nCurrently we calculate the size once in the htab code, and then twice more in\nthe kexec code, once using htab_hash_mask and once using ppc64_pft_size.\nOn some machines the ppc64_pft_size calculation is broken because\nppc64_pft_size is not set.\n\nSo we need to fix the second calculation, but better still we should just\ncalculate the size once and use it everywhere else.\n\nTested on Power5 LPAR, Power4 non-LPAR and Power3.\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "88ced0314938814e1772b4d0d7ab20c52e4472b6", "tree": "3e06de882c0bf5706ee7a8994e06eb8c9ed3feca", "parents": [ "e1333803c3a8fb167ba67ffc5540dbb53fa7deb3" ], "author": { "name": "Arnd Bergmann", "email": "arnd@arndb.de", "time": "Fri Dec 16 22:43:46 2005 +0100" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Jan 09 15:13:08 2006 +1100" }, "message": "[PATCH] powerpc: sanitize header files for user space includes\n\ninclude/asm-ppc/ had #ifdef __KERNEL__ in all header files that\nare not meant for use by user space, include/asm-powerpc does\nnot have this yet.\n\nThis patch gets us a lot closer there. There are a few cases\nwhere I was not sure, so I left them out. I have verified\nthat no CONFIG_* symbols are used outside of __KERNEL__\nany more and that there are no obvious compile errors when\nincluding any of the headers in user space libraries.\n\nSigned-off-by: Arnd Bergmann \u003carnd@arndb.de\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "758438a7b8da593c9116e95cc7fdff6e9e0b0c40", "tree": "5343d8ec40016294902278c27a9f5647bd061890", "parents": [ "0cc4746cadda16826a1b3214c042a2f75445b71c" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Mon Dec 05 15:49:00 2005 -0600" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Jan 09 14:52:25 2006 +1100" }, "message": "[PATCH] powerpc: Fixups for kernel linked at 32 MB\n\nThere\u0027s a few places where we need to fix things up for the kernel to work\nif it\u0027s linked at 32MB:\n\n - platforms/powermac/smp.c\n To start secondary cpus on pmac we patch the reset vector, which is fine.\n Except if we\u0027re above 32MB we don\u0027t have enough bits for an absolute branch,\n it needs to relative.\n - kernel/head_64.s\n - A few branches in the cpu hold code need to load the full target address\n and do a bctr.\n - after_prom_start needs to load PHYSICAL_START as the dest address, not 0.\n - The exception prolog needs to load the low word of the target adddress,\n not just the low halfword.\n - Fixup handling of the initial stab address.\n - kernel/setup_64.c\n smp_release_cpus() needs to write 1 to the spinloop flag near 0, not 32 MB.\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "d1405b869850982f05c7ec0d3f137ca27588192f", "tree": "b95b4e6e36f654205ad720609734a5b2ca549de0", "parents": [ "bcb05504edf0e27a648aa1059cbb71e8746758a1" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Nov 23 17:53:42 2005 +1100" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Jan 09 14:49:46 2006 +1100" }, "message": "[PATCH] powerpc: Add OF address parsing code (#2)\n\nParsing addresses extracted from Open Firmware isn\u0027t a simple matter. We\nhave various bits of code that try to do it in various place, including\nsome heuristics in prom.c that pre-parse addresses at boot and fill\ndevice-nodes \"addrs\", but those are dodgy at best and I want to\ndeprecate them. So this patch introduces a new set of routines that\nshould be capable of parsing most types of addresses and translating\nthem into CPU physical addresses. It currently works for things on PCI\nbusses and ISA busses and should work on \"standard\" busses like the root\nbus or the MacIO bus that don\u0027t put funky flags in addresses. If you\nhave other bus types that do use funky flags, you\u0027ll have to add new bus\ntype translators, which is fairly easy.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "cbf52afdc0eb88492cf7808cc4b4f58a46f1b1ad", "tree": "89910c9d9a054f0bf64670757a3715e19fcc62b2", "parents": [ "dabcafd3f363bacd6b89f537af27dc79128e4806" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Fri Dec 09 14:20:52 2005 +1100" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Fri Dec 09 16:30:48 2005 +1100" }, "message": "[PATCH] powerpc: Add missing icache flushes for hugepages\n\nOn most powerpc CPUs, the dcache and icache are not coherent so\nbetween writing and executing a page, the caches must be flushed.\nUserspace programs assume pages given to them by the kernel are icache\nclean, so we must do this flush between the kernel clearing a page and\nit being mapped into userspace for execute. We were not doing this\nfor hugepages, this patch corrects the situation.\n\nWe use the same lazy mechanism as we use for normal pages, delaying\nthe flush until userspace actually attempts to execute from the page\nin question.\n\nTested on G5.\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "047ea7846565917c4a666635fa1fa4b5c587cd55", "tree": "409c8f6ddd1f145fb364a8d6f813febd0c94d06b", "parents": [ "800fc3eeb0eed3bf98d621c0da24d68cabcf6526" ], "author": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Sat Nov 19 20:17:32 2005 +1100" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Sat Nov 19 20:17:32 2005 +1100" }, "message": "powerpc: Trivially merge several headers from asm-ppc64 to asm-powerpc\n\nFor these, I have just done the lame-o merge where the file ends up\nlooking like:\n\n\t#ifndef CONFIG_PPC64\n\t#include \u003casm-ppc/foo.h\u003e\n\t#else\n\t... contents from asm-ppc64/foo.h\n\t#endif\n\nso nothing has changed, really, except that we reduce include/asm-ppc64\na bit more.\n\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "49b09853df1a303876b82a6480efb2f7b45ef041", "tree": "bf3d76ff0ddfe2e854f48ed890258ad89fa9c1dc", "parents": [ "d3d2176a0bc696b5365ce0e8f82a29a521d85fd0" ], "author": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Nov 10 15:53:40 2005 +1100" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Nov 10 15:53:40 2005 +1100" }, "message": "powerpc: Move some extern declarations from C code into headers\n\nThis also make klimit have the same type on 32-bit as on 64-bit,\nnamely unsigned long, and defines and initializes it in one place.\n\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "799d6046d3fb557006e6d7c9767fdb96479b0e0a", "tree": "fff321e3c0c0e6d1192f453aab23ad204f350851", "parents": [ "3ddfbcf19b15ccd25a0b4b2dc2e38000e08de739" ], "author": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Nov 10 13:37:51 2005 +1100" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Nov 10 13:37:51 2005 +1100" }, "message": "[PATCH] powerpc: merge code values for identifying platforms\n\nThis patch merges platform codes. systemcfg-\u003eplatform is no longer used,\nsystemcfg use in general is deprecated as much as possible (and renamed\n_systemcfg before it gets completely moved elsewhere in a future patch),\n_machine is now used on ppc64 along as ppc32. Platform codes aren\u0027t gone\nyet but we are getting a step closer. A bunch of asm code in head[_64].S\nis also turned into C code.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "3ddfbcf19b15ccd25a0b4b2dc2e38000e08de739", "tree": "ca77158ab291453ed39e87f2d81beef9e8d1a560", "parents": [ "f6d3577da14e877b79517c883d1139ee6ad7da45" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Thu Nov 10 12:56:55 2005 +1100" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Nov 10 13:10:38 2005 +1100" }, "message": "[PATCH] powerpc: Consolidate asm compatibility macros\n\nThis patch consolidates macros used to generate assembly for\ncompatibility across different CPUs or configs. A new header,\nasm-powerpc/asm-compat.h contains the main compatibility macros. It\nuses some preprocessor magic to make the macros suitable both for use\nin .S files, and in inline asm in .c files. Headers (bitops.h,\nuaccess.h, atomic.h, bug.h) which had their own such compatibility\nmacros are changed to use asm-compat.h.\n\nppc_asm.h is now for use in .S files *only*, and a #error enforces\nthat. As such, we\u0027re a lot more careless about namespace pollution\nhere than in asm-compat.h.\n\nWhile we\u0027re at it, this patch adds a call to the PPC405_ERR77 macro in\nfutex.h which should have had it already, but didn\u0027t.\n\nBuilt and booted on pSeries, Maple and iSeries (ARCH\u003dpowerpc). Built\nfor 32-bit powermac (ARCH\u003dpowerpc) and Walnut (ARCH\u003dppc).\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "3c726f8dee6f55e96475574e9f645327e461884c", "tree": "f67c381e8f57959aa4a94bda4c68e24253cd8171", "parents": [ "f912696ab330bf539231d1f8032320f2a08b850f" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Mon Nov 07 11:06:55 2005 +1100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Nov 06 16:56:47 2005 -0800" }, "message": "[PATCH] ppc64: support 64k pages\n\nAdds a new CONFIG_PPC_64K_PAGES which, when enabled, changes the kernel\nbase page size to 64K. The resulting kernel still boots on any\nhardware. On current machines with 4K pages support only, the kernel\nwill maintain 16 \"subpages\" for each 64K page transparently.\n\nNote that while real 64K capable HW has been tested, the current patch\nwill not enable it yet as such hardware is not released yet, and I\u0027m\nstill verifying with the firmware architects the proper to get the\ninformation from the newer hypervisors.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "4c55130b2aa93370f1bf52d2304394e91cf8ee39", "tree": "522c7f510775f221c4e8046bc238a618db4768df", "parents": [ "ba293fff085fde5b9f1b5a57c8abb1a8098d0c59" ], "author": { "name": "Michael Ellerman", "email": "michael@ellerman.id.au", "time": "Fri Sep 23 14:47:58 2005 +1000" }, "committer": { "name": "Stephen Rothwell", "email": "sfr@canb.auug.org.au", "time": "Fri Sep 23 14:47:58 2005 +1000" }, "message": "ppc64 iSeries: Update create_pte_mapping to replace iSeries_bolt_kernel()\n\nearly_setup() calls htab_initialize() which is similar, but not identical\nto iSeries_bolt_kernel().\n\nOn iSeries the Hypervisor has already inserted some ptes for us, and we\nsimply have to detect that and bolt them. iSeries_hpte_bolt_or_insert()\nimplements that logic.\n\nFor the case of a non-existing pte we just call iSeries_hpte_insert(). This\nappears to work, although it\u0027s not entirely equivalent to the old code in\niSeries_make_pte() which panicked if we got a secondary slot. Not sure if\nthat\u0027s important.\n\nFinally we call iSeries_hpte_bolt_or_insert() from create_pte_mapping(),\nwhich is called from htab_initialize() for each lmb region.\n\nSigned-off-by: Michael Ellerman \u003cmichael@ellerman.id.au\u003e\nSigned-off-by: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\n" }, { "commit": "637a6ff6ce525d8495df944550efea0f023dd521", "tree": "f4d31da12a348ecf9136cef8f5986172d6af6003", "parents": [ "d0035c62d9145a2ce3057c8182a7ff0b4921a41c" ], "author": { "name": "Olof Johansson", "email": "olof@lixom.net", "time": "Tue Sep 20 13:47:41 2005 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Wed Sep 21 19:21:07 2005 +1000" }, "message": "[PATCH] ppc64: Updated Olof misc updates 3/3\n\nReplace some of the hard-coded constants with PAGE_SIZE/SHIFT/ORDER where\nappropriate.\n\nLikewise, in a couple of places it doesn\u0027t make sense to base some\nallocations on page size when all that\u0027s required is a constant 4K,\netc.\n\nSigned-off-by: Olof Johansson \u003colof@lixom.net\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "5f7c690728ace1404f72d74972dcc261674c0dd4", "tree": "d2fea77e39c2103be9ae41b9b849dce949cd9efd", "parents": [ "0a1e1222b77b9b02457d8126f598e3713559d5c7" ], "author": { "name": "Kumar Gala", "email": "galak@freescale.com", "time": "Fri Sep 09 15:02:25 2005 -0500" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Sep 19 09:38:49 2005 +1000" }, "message": "[PATCH] powerpc: Merged ppc_asm.h\n\nMerged ppc_asm.h between ppc32 \u0026 ppc64. The majority of the file is\ncommon between the two architectures excluding how a single GPR is\nsaved/restored and which GPRs are non-volatile.\n\nAdditionally, moved the ASM_CONST macro used on ppc64 into ppc_asm.h.\n\nSigned-off-by: Kumar Gala \u003ckumar.gala@freescale.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "14b34661615ec036ab4c91637913706e4caccc93", "tree": "98915b1889422383a85186d8455ecca69fa2327b", "parents": [ "0fdf0b8634055b016f7b93cfcdea2eb9091f0271" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Tue Sep 06 14:59:47 2005 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Tue Sep 06 16:57:46 2005 +1000" }, "message": "[PATCH] Invert sense of SLB class bit\n\nCurrently, we set the class bit in kernel SLB entries, and clear it on\nuser SLB entries. On POWER5, ERAT entries created in real mode have\nthe class bit clear. So to avoid flushing kernel ERAT entries on each\ncontext switch, this patch inverts our usage of the class bit, setting\nit on user SLB entries and clearing it on kernel SLB entries.\n\nBooted on POWER5 and G5.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "c594adad5653491813959277fb87a2fef54c4e05", "tree": "baefdce10a0b490017b0a5acbe9dbeb8cb14c003", "parents": [ "9a5573e378c5c8976c6000a7643b52e2a0481688" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Thu Aug 11 16:55:21 2005 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Aug 29 10:53:38 2005 +1000" }, "message": "[PATCH] Dynamic hugepage addresses for ppc64\n\nPaulus, I think this is now a reasonable candidate for the post-2.6.13\nqueue.\n\nRelax address restrictions for hugepages on ppc64\n\nPresently, 64-bit applications on ppc64 may only use hugepages in the\naddress region from 1-1.5T. Furthermore, if hugepages are enabled in\nthe kernel config, they may only use hugepages and never normal pages\nin this area. This patch relaxes this restriction, allowing any\naddress to be used with hugepages, but with a 1TB granularity. That\nis if you map a hugepage anywhere in the region 1TB-2TB, that entire\narea will be reserved exclusively for hugepages for the remainder of\nthe process\u0027s lifetime. This works analagously to hugepages in 32-bit\napplications, where hugepages can be mapped anywhere, but with 256MB\n(mmu segment) granularity.\n\nThis patch applies on top of the four level pagetable patch\n(http://patchwork.ozlabs.org/linuxppc64/patch?id\u003d1936).\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "c59c464a3e29830bcfae5eea1777cad9e00087f3", "tree": "ebf8eb2885e8431c82c011f46138d41630a8ba49", "parents": [ "ec465515eeb662f66725c8c483a46b6bdd9bdd48" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Fri Aug 19 14:52:31 2005 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Aug 29 10:53:33 2005 +1000" }, "message": "[PATCH] Change address of ppc64 initial segment table\n\nOn ppc64 machines with segment tables, CPU0\u0027s segment table is at a\nfixed address, currently 0x9000. This patch moves it to the free\nspace at 0x6000, just below the fwnmi data area. This saves 8k of\nspace in vmlinux and the runtime kernel image.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "e28f7faf05159f1cfd564596f5e6178edba6bd49", "tree": "45534d2c33bff8b64e3fd155fba55146cb7518e6", "parents": [ "decd300b30e499fe6be1bbfc5650fc971de8c1fa" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Fri Aug 05 19:39:06 2005 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Mon Aug 29 10:53:31 2005 +1000" }, "message": "[PATCH] Four level pagetables for ppc64\n\nImplement 4-level pagetables for ppc64\n\nThis patch implements full four-level page tables for ppc64, thereby\nextending the usable user address range to 44 bits (16T).\n\nThe patch uses a full page for the tables at the bottom and top level,\nand a quarter page for the intermediate levels. It uses full 64-bit\npointers at every level, thus also increasing the addressable range of\nphysical memory. This patch also tweaks the VSID allocation to allow\nmatching range for user addresses (this halves the number of available\ncontexts) and adds some #if and BUILD_BUG sanity checks.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "488f84994c55927eef587a0827dc957c908a0bad", "tree": "34bdc42927e2eb559bd64039ed87508a440dffc6", "parents": [ "533f08172e21521a74e15cdef8a13c929596d506" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Wed Jul 27 11:44:21 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jul 27 16:25:58 2005 -0700" }, "message": "[PATCH] ppc64: remove another fixed address constraint\n\nPresently the LparMap, one of the structures the kernel shares with the\nlegacy iSeries hypervisor has a fixed offset address in head.S. This patch\nchanges this so the LparMap is a normally initialized structure, without\nfixed address. This allows us to use macros to compute some of the values\nin the structure, which wasn\u0027t previously possible because the assembler\nalways uses signed-% which gets the wrong answers for the computations in\nquestion.\n\nUnfortunately, a gcc bug means that doing this requires another structure\n(hvReleaseData) to be initialized in asm instead of C, but on the whole the\nresult is cleaner than before.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "533f08172e21521a74e15cdef8a13c929596d506", "tree": "60f2117ffb85f61fcdc0e17d864d0114096a4192", "parents": [ "6fdfb382813d66757aef4d83e369f8153a40b371" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Wed Jul 27 11:44:19 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jul 27 16:25:58 2005 -0700" }, "message": "[PATCH] ppc64: dynamically allocate segment tables\n\nPPC64 machines before Power4 need a segment table page allocated for each\nCPU. Currently these are allocated statically in a big array in head.S for\nall CPUs. The segment tables need to be in the first segment (so\ndo_stab_bolted doesn\u0027t take a recursive fault on the stab itself), but\nother than that there are no constraints which require the stabs for the\nsecondary CPUs to be statically allocated.\n\nThis patch allocates segment tables dynamically during boot, using\nlmb_alloc() to ensure they are within the first 256M segment. This reduces\nthe kernel image size by 192k...\n\nTested on RS64 iSeries, POWER3 pSeries, and POWER5.\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "96e2844999f99878fc5b03b81ccaa60580005b81", "tree": "353c1bc9a5602d556e6741f4a261010cde45e93b", "parents": [ "f13487c66c75f5db004a0631047309d9e7c5aab7" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Wed Jul 13 01:11:42 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jul 13 11:25:25 2005 -0700" }, "message": "[PATCH] ppc64: kill bitfields in ppc64 hash code\n\nThis patch removes the use of bitfield types from the ppc64 hash table\nmanipulation code.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nAcked-by: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "f4c82d5132b0592f5d6befc5b652cbd4b08f12ff", "tree": "3889ea8eeb4dfa6c995b6dc93574d24c238a6deb", "parents": [ "70765aa4bdb8862a49fcf5b28f3deaf561cf5ae7" ], "author": { "name": "R Sharada", "email": "sharada@in.ibm.com", "time": "Sat Jun 25 14:58:08 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Jun 25 16:24:51 2005 -0700" }, "message": "[PATCH] ppc64 kexec: native hash clear\n\nAdd code to clear the hash table and invalidate the tlb for native (SMP,\nnon-LPAR) mode. Supports 16M and 4k pages.\n\nSigned-off-by: Milton Miller \u003cmiltonm@bga.com\u003e\nSigned-off-by: R Sharada \u003csharada@in.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "fef1c772fa154c16e0a54577e9ecb5480f7b937e", "tree": "7c1483966f984c822b58f761b9be873dce94999c", "parents": [ "031f7edecf46d731673a5dd19ecb0de38f1a2219" ], "author": { "name": "Arnd Bergmann", "email": "arnd@arndb.de", "time": "Thu Jun 23 09:43:37 2005 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Jun 23 09:43:37 2005 +1000" }, "message": "[PATCH] ppc64: add BPA platform type\n\nThis adds the basic support for running on BPA machines.\nSo far, this is only the IBM workstation, and it will\nnot run on others without a little more generalization.\n\nIt should be possible to configure a kernel for any\ncombination of CONFIG_PPC_BPA with any of the other\nmultiplatform targets.\n\nSigned-off-by: Arnd Bergmann \u003carndb@de.ibm.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "1f8d419e291f7f7f7f3ffd4f0ba00834621690c8", "tree": "833df93032a38bc749458ce8be3a316eae1d5215", "parents": [ "e685752de107201432a055f7c45c396a5b04dc17" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Thu May 05 16:15:13 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Thu May 05 16:36:32 2005 -0700" }, "message": "[PATCH] ppc64: pgtable.h and other header cleanups\n\nThis patch started as simply removing a few never-used macros from\nasm-ppc64/pgtable.h, then kind of grew. It now makes a bunch of\ncleanups to the ppc64 low-level header files (with corresponding\nchanges to .c files where necessary) such as:\n\t- Abolishing never-used macros\n\t- Eliminating multiple #defines with the same purpose\n\t- Removing pointless macros (cases where just expanding the\nmacro everywhere turns out clearer and more sensible)\n\t- Removing some cases where macros which could be defined in\nterms of each other weren\u0027t\n\t- Moving imalloc() related definitions from pgtable.h to their\nown header file (imalloc.h)\n\t- Re-arranging headers to group things more logically\n\t- Moving all VSID allocation related things to mmu.h, instead\nof being split between mmu.h and mmu_context.h\n\t- Removing some reserved space for flags from the PMD - we\u0027re\nnot using it.\n\t- Fix some bugs which broke compile with STRICT_MM_TYPECHECKS.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1da177e4c3f41524e886b7f1b8a0c1fc7321cac2", "tree": "0bba044c4ce775e45a88a51686b5d9f90697ea9d", "parents": [], "author": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "message": "Linux-2.6.12-rc2\n\nInitial git repository build. I\u0027m not bothering with the full history,\neven though we have it. We can create a separate \"historical\" git\narchive of that later if we want to, and in the meantime it\u0027s about\n3.2GB when imported into git - space that would just make the early\ngit days unnecessarily complicated, when we don\u0027t have a lot of good\ninfrastructure for it.\n\nLet it rip!\n" } ] }