)]}' { "log": [ { "commit": "48f13bf3e742fca8aab87f6c39451d03bf5952d4", "tree": "668160019ab157500a90655cf44f798ed3c77893", "parents": [ "ea3061d227816d00717446ac12b853d7ae04b4fe" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:26:10 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:01 2007 -0700" }, "message": "Breakout page_order() to internal.h to avoid special knowledge of the buddy allocator\n\nThe statistics patch later needs to know what order a free page is on the free\nlists. Rather than having special knowledge of page_private() when\nPageBuddy() is set, this patch places out page_order() in internal.h and adds\na VM_BUG_ON to catch using it on non-PageBuddy pages.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nAcked-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ea3061d227816d00717446ac12b853d7ae04b4fe", "tree": "fa63e359433ba09481d0c758cdf54c877b29e5f0", "parents": [ "42a9fdbb12ac6c027b4b91ab9b5a60aa3a834489" ], "author": { "name": "Andrew Morton", "email": "akpm@linux-foundation.org", "time": "Tue Oct 16 01:26:09 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:01 2007 -0700" }, "message": "slub: list_locations() can use GFP_TEMPORARY\n\nIt\u0027s a short-lived allocation.\n\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "42a9fdbb12ac6c027b4b91ab9b5a60aa3a834489", "tree": "d319573849af86fa405b93e5b93add0d34305db7", "parents": [ "4c93c355d5d563f300df7e61ef753d7a064411e9" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:26:09 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:01 2007 -0700" }, "message": "SLUB: Optimize cacheline use for zeroing\n\nWe touch a cacheline in the kmem_cache structure for zeroing to get the\nsize. However, the hot paths in slab_alloc and slab_free do not reference\nany other fields in kmem_cache, so we may have to just bring in the\ncacheline for this one access.\n\nAdd a new field to kmem_cache_cpu that contains the object size. That\ncacheline must already be used in the hotpaths. So we save one cacheline\non every slab_alloc if we zero.\n\nWe need to update the kmem_cache_cpu object size if an aliasing operation\nchanges the objsize of an non debug slab.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4c93c355d5d563f300df7e61ef753d7a064411e9", "tree": "24bcdbed58a51c69640da9c8e220dd5ce0c054a7", "parents": [ "ee3c72a14bfecdf783738032ff3c73ef6412f5b3" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:26:08 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:01 2007 -0700" }, "message": "SLUB: Place kmem_cache_cpu structures in a NUMA aware way\n\nThe kmem_cache_cpu structures introduced are currently an array placed in the\nkmem_cache struct. Meaning the kmem_cache_cpu structures are overwhelmingly\non the wrong node for systems with a higher amount of nodes. These are\nperformance critical structures since the per node information has\nto be touched for every alloc and free in a slab.\n\nIn order to place the kmem_cache_cpu structure optimally we put an array\nof pointers to kmem_cache_cpu structs in kmem_cache (similar to SLAB).\n\nHowever, the kmem_cache_cpu structures can now be allocated in a more\nintelligent way.\n\nWe would like to put per cpu structures for the same cpu but different\nslab caches in cachelines together to save space and decrease the cache\nfootprint. However, the slab allocators itself control only allocations\nper node. We set up a simple per cpu array for every processor with\n100 per cpu structures which is usually enough to get them all set up right.\nIf we run out then we fall back to kmalloc_node. This also solves the\nbootstrap problem since we do not have to use slab allocator functions\nearly in boot to get memory for the small per cpu structures.\n\nPro:\n\t- NUMA aware placement improves memory performance\n\t- All global structures in struct kmem_cache become readonly\n\t- Dense packing of per cpu structures reduces cacheline\n\t footprint in SMP and NUMA.\n\t- Potential avoidance of exclusive cacheline fetches\n\t on the free and alloc hotpath since multiple kmem_cache_cpu\n\t structures are in one cacheline. This is particularly important\n\t for the kmalloc array.\n\nCons:\n\t- Additional reference to one read only cacheline (per cpu\n\t array of pointers to kmem_cache_cpu) in both slab_alloc()\n\t and slab_free().\n\n[akinobu.mita@gmail.com: fix cpu hotplug offline/online path]\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: \"Pekka Enberg\" \u003cpenberg@cs.helsinki.fi\u003e\nCc: Akinobu Mita \u003cakinobu.mita@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ee3c72a14bfecdf783738032ff3c73ef6412f5b3", "tree": "876c2c5d33058be8502504330726bb16b876ba52", "parents": [ "b3fba8da653999c67d7517050f196e92da6f8d3b" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:26:07 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:01 2007 -0700" }, "message": "SLUB: Avoid touching page struct when freeing to per cpu slab\n\nSet c-\u003enode to -1 if we allocate from a debug slab instead for SlabDebug\nwhich requires access the page struct cacheline.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nTested-by: Alexey Dobriyan \u003cadobriyan@sw.ru\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b3fba8da653999c67d7517050f196e92da6f8d3b", "tree": "12ee00ca91ceafe4fa9bb75d62debaf1feebb7b9", "parents": [ "8e65d24c7caf2a4c69b3ae0ce170bf3082ba359f" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:26:06 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:01 2007 -0700" }, "message": "SLUB: Move page-\u003eoffset to kmem_cache_cpu-\u003eoffset\n\nWe need the offset from the page struct during slab_alloc and slab_free. In\nboth cases we also reference the cacheline of the kmem_cache_cpu structure.\nWe can therefore move the offset field into the kmem_cache_cpu structure\nfreeing up 16 bits in the page struct.\n\nMoving the offset allows an allocation from slab_alloc() without touching the\npage struct in the hot path.\n\nThe only thing left in slab_free() that touches the page struct cacheline for\nper cpu freeing is the checking of SlabDebug(page). The next patch deals with\nthat.\n\nUse the available 16 bits to broaden page-\u003einuse. More than 64k objects per\nslab become possible and we can get rid of the checks for that limitation.\n\nNo need anymore to shrink the order of slabs if we boot with 2M sized slabs\n(slub_min_order\u003d9).\n\nNo need anymore to switch off the offset calculation for very large slabs\nsince the field in the kmem_cache_cpu structure is 32 bits and so the offset\nfield can now handle slab sizes of up to 8GB.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "8e65d24c7caf2a4c69b3ae0ce170bf3082ba359f", "tree": "4f690448c1363bf02f74abd9293126c3e3a9e4c9", "parents": [ "dfb4f09609827301740ef0a11b37530d190f1681" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:26:06 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:01 2007 -0700" }, "message": "SLUB: Do not use page-\u003emapping\n\nAfter moving the lockless_freelist to kmem_cache_cpu we no longer need\npage-\u003elockless_freelist. Restructure the use of the struct page fields in\nsuch a way that we never touch the mapping field.\n\nThis is turn allows us to remove the special casing of SLUB when determining\nthe mapping of a page (needed for corner cases of virtual caches machines that\nneed to flush caches of processors mapping a page).\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "dfb4f09609827301740ef0a11b37530d190f1681", "tree": "eb4d13d8699cf01abada9f45e1670cc601fb4b00", "parents": [ "484f51f820199ab3e0ef15d08f1b6be20f53bf39" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:26:05 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:01 2007 -0700" }, "message": "SLUB: Avoid page struct cacheline bouncing due to remote frees to cpu slab\n\nA remote free may access the same page struct that also contains the lockless\nfreelist for the cpu slab. If objects have a short lifetime and are freed by\na different processor then remote frees back to the slab from which we are\ncurrently allocating are frequent. The cacheline with the page struct needs\nto be repeately acquired in exclusive mode by both the allocating thread and\nthe freeing thread. If this is frequent enough then performance will suffer\nbecause of cacheline bouncing.\n\nThis patchset puts the lockless_freelist pointer in its own cacheline. In\norder to make that happen we introduce a per cpu structure called\nkmem_cache_cpu.\n\nInstead of keeping an array of pointers to page structs we now keep an array\nto a per cpu structure that--among other things--contains the pointer to the\nlockless freelist. The freeing thread can then keep possession of exclusive\naccess to the page struct cacheline while the allocating thread keeps its\nexclusive access to the cacheline containing the per cpu structure.\n\nThis works as long as the allocating cpu is able to service its request\nfrom the lockless freelist. If the lockless freelist runs empty then the\nallocating thread needs to acquire exclusive access to the cacheline with\nthe page struct lock the slab.\n\nThe allocating thread will then check if new objects were freed to the per\ncpu slab. If so it will keep the slab as the cpu slab and continue with the\nrecently remote freed objects. So the allocating thread can take a series\nof just freed remote pages and dish them out again. Ideally allocations\ncould be just recycling objects in the same slab this way which will lead\nto an ideal allocation / remote free pattern.\n\nThe number of objects that can be handled in this way is limited by the\ncapacity of one slab. Increasing slab size via slub_min_objects/\nslub_max_order may increase the number of objects and therefore performance.\n\nIf the allocating thread runs out of objects and finds that no objects were\nput back by the remote processor then it will retrieve a new slab (from the\npartial lists or from the page allocator) and start with a whole\nnew set of objects while the remote thread may still be freeing objects to\nthe old cpu slab. This may then repeat until the new slab is also exhausted.\nIf remote freeing has freed objects in the earlier slab then that earlier\nslab will now be on the partial freelist and the allocating thread will\npick that slab next for allocation. So the loop is extended. However,\nboth threads need to take the list_lock to make the swizzling via\nthe partial list happen.\n\nIt is likely that this kind of scheme will keep the objects being passed\naround to a small set that can be kept in the cpu caches leading to increased\nperformance.\n\nMore code cleanups become possible:\n\n- Instead of passing a cpu we can now pass a kmem_cache_cpu structure around.\n Allows reducing the number of parameters to various functions.\n- Can define a new node_match() function for NUMA to encapsulate locality\n checks.\n\nEffect on allocations:\n\nCachelines touched before this patch:\n\n\tWrite:\tpage cache struct and first cacheline of object\n\nCachelines touched after this patch:\n\n\tWrite:\tkmem_cache_cpu cacheline and first cacheline of object\n\tRead: page cache struct (but see later patch that avoids touching\n\t\tthat cacheline)\n\nThe handling when the lockless alloc list runs empty gets to be a bit more\ncomplicated since another cacheline has now to be written to. But that is\nhalfway out of the hot path.\n\nEffect on freeing:\n\nCachelines touched before this patch:\n\n\tWrite: page_struct and first cacheline of object\n\nCachelines touched after this patch depending on how we free:\n\n Write(to cpu_slab):\tkmem_cache_cpu struct and first cacheline of object\n Write(to other):\tpage struct and first cacheline of object\n\n Read(to cpu_slab):\tpage struct to id slab etc. (but see later patch that\n \t\t\tavoids touching the page struct on free)\n Read(to other):\tcpu local kmem_cache_cpu struct to verify its not\n \t\t\tthe cpu slab.\n\nSummary:\n\nPro:\n\t- Distinct cachelines so that concurrent remote frees and local\n\t allocs on a cpuslab can occur without cacheline bouncing.\n\t- Avoids potential bouncing cachelines because of neighboring\n\t per cpu pointer updates in kmem_cache\u0027s cpu_slab structure since\n\t it now grows to a cacheline (Therefore remove the comment\n\t that talks about that concern).\n\nCons:\n\t- Freeing objects now requires the reading of one additional\n\t cacheline. That can be mitigated for some cases by the following\n\t patches but its not possible to completely eliminate these\n\t references.\n\n\t- Memory usage grows slightly.\n\n\tThe size of each per cpu object is blown up from one word\n\t(pointing to the page_struct) to one cacheline with various data.\n\tSo this is NR_CPUS*NR_SLABS*L1_BYTES more memory use. Lets say\n\tNR_SLABS is 100 and a cache line size of 128 then we have just\n\tincreased SLAB metadata requirements by 12.8k per cpu.\n\t(Another later patch reduces these requirements)\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "484f51f820199ab3e0ef15d08f1b6be20f53bf39", "tree": "eea15a3cb546463488595e7a5fae8628a5dd7877", "parents": [ "467c996c1e1910633fa8e7adc9b052aa3ed5f97c" ], "author": { "name": "Adrian Bunk", "email": "bunk@stusta.de", "time": "Tue Oct 16 01:26:03 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:01 2007 -0700" }, "message": "mm/page_alloc.c: make code static\n\nThis patch makes needlessly global code static.\n\nSigned-off-by: 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": "467c996c1e1910633fa8e7adc9b052aa3ed5f97c", "tree": "09e0e70160386be1bdaa12801afddf287e12c8a1", "parents": [ "d9c2340052278d8eb2ffb16b0484f8f794def4de" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:26:02 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "Print out statistics in relation to fragmentation avoidance to /proc/pagetypeinfo\n\nThis patch provides fragmentation avoidance statistics via /proc/pagetypeinfo.\n The information is collected only on request so there is no runtime overhead.\n The statistics are in three parts:\n\nThe first part prints information on the size of blocks that pages are\nbeing grouped on and looks like\n\nPage block order: 10\nPages per block: 1024\n\nThe second part is a more detailed version of /proc/buddyinfo and looks like\n\nFree pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10\nNode 0, zone DMA, type Unmovable 0 0 0 0 0 0 0 0 0 0 0\nNode 0, zone DMA, type Reclaimable 1 0 0 0 0 0 0 0 0 0 0\nNode 0, zone DMA, type Movable 0 0 0 0 0 0 0 0 0 0 0\nNode 0, zone DMA, type Reserve 0 4 4 0 0 0 0 1 0 1 0\nNode 0, zone Normal, type Unmovable 111 8 4 4 2 3 1 0 0 0 0\nNode 0, zone Normal, type Reclaimable 293 89 8 0 0 0 0 0 0 0 0\nNode 0, zone Normal, type Movable 1 6 13 9 7 6 3 0 0 0 0\nNode 0, zone Normal, type Reserve 0 0 0 0 0 0 0 0 0 0 4\n\nThe third part looks like\n\nNumber of blocks type Unmovable Reclaimable Movable Reserve\nNode 0, zone DMA 0 1 2 1\nNode 0, zone Normal 3 17 94 4\n\nTo walk the zones within a node with interrupts disabled, walk_zones_in_node()\nis introduced and shared between /proc/buddyinfo, /proc/zoneinfo and\n/proc/pagetypeinfo to reduce code duplication. It seems specific to what\nvmstat.c requires but could be broken out as a general utility function in\nmmzone.c if there were other other potential users.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nAcked-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d9c2340052278d8eb2ffb16b0484f8f794def4de", "tree": "aec7e4e11473a4fcdfd389c718544780a042c6df", "parents": [ "d100313fd615cc30374ff92e0b3facb053838330" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:26:01 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "Do not depend on MAX_ORDER when grouping pages by mobility\n\nCurrently mobility grouping works at the MAX_ORDER_NR_PAGES level. This makes\nsense for the majority of users where this is also the huge page size.\nHowever, on platforms like ia64 where the huge page size is runtime\nconfigurable it is desirable to group at a lower order. On x86_64 and\noccasionally on x86, the hugepage size may not always be MAX_ORDER_NR_PAGES.\n\nThis patch groups pages together based on the value of HUGETLB_PAGE_ORDER. It\nuses a compile-time constant if possible and a variable where the huge page\nsize is runtime configurable.\n\nIt is assumed that grouping should be done at the lowest sensible order and\nthat the user would not want to override this. If this is not true,\npage_block order could be forced to a variable initialised via a boot-time\nkernel parameter.\n\nOne potential issue with this patch is that IA64 now parses hugepagesz with\nearly_param() instead of __setup(). __setup() is called after the memory\nallocator has been initialised and the pageblock bitmaps already setup. In\ntests on one IA64 there did not seem to be any problem with using\nearly_param() and in fact may be more correct as it guarantees the parameter\nis handled before the parsing of hugepages\u003d.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nAcked-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d100313fd615cc30374ff92e0b3facb053838330", "tree": "f0bcd5e3b07bee40a65182c63b54baceca366849", "parents": [ "64c5e135bf5a2a7f0ededb3435a31adbe0202f0c" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:26:00 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "Fix calculation in move_freepages_block for counting pages\n\nmove_freepages_block() returns the number of blocks moved. This value is used\nto determine if a block of pages should be stolen for the exclusive use of a\nmigrate type or not. However, the value returned is being used correctly.\nThis patch fixes the calculation to return the number of base pages that have\nbeen moved.\n\nThis should be considered a fix to the patch\nmove-free-pages-between-lists-on-steal.patch\n\nCredit to Andy Whitcroft for spotting the problem.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nAcked-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "64c5e135bf5a2a7f0ededb3435a31adbe0202f0c", "tree": "cb4ff93cbcc3c27176723419a313d7c53545d36b", "parents": [ "ac0e5b7a6b93fb291b01fe1e951e3c16bcdd3503" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:59 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "don\u0027t group high order atomic allocations\n\nGrouping high-order atomic allocations together was intended to allow\nbursty users of atomic allocations to work such as e1000 in situations\nwhere their preallocated buffers were depleted. This did not work in at\nleast one case with a wireless network adapter needing order-1 allocations\nfrequently. To resolve that, the free pages used for min_free_kbytes were\nmoved to separate contiguous blocks with the patch\nbias-the-location-of-pages-freed-for-min_free_kbytes-in-the-same-max_order_nr_pages-blocks.\n\nIt is felt that keeping the free pages in the same contiguous blocks should\nbe sufficient for bursty short-lived high-order atomic allocations to\nsucceed, maybe even with the e1000. Even if there is a failure, increasing\nthe value of min_free_kbytes will free pages as contiguous bloks in\ncontrast to the standard buddy allocator which makes no attempt to keep the\nminimum number of free pages contiguous.\n\nThis patch backs out grouping high order atomic allocations together to\ndetermine if it is really needed or not. If a new report comes in about\nhigh-order atomic allocations failing, the feature can be reintroduced to\ndetermine if it fixes the problem or not. As a side-effect, this patch\nreduces by 1 the number of bits required to track the mobility type of\npages within a MAX_ORDER_NR_PAGES block.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ac0e5b7a6b93fb291b01fe1e951e3c16bcdd3503", "tree": "732f67c8de6e0d2e001b60c17af9599468b80163", "parents": [ "56fd56b868f19385c50af8941a4c78df433b2d32" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:58 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "remove PAGE_GROUP_BY_MOBILITY\n\nGrouping pages by mobility can be disabled at compile-time. This was\nconsidered undesirable by a number of people. However, in the current stack of\npatches, it is not a simple case of just dropping the configurable patch as it\nwould cause merge conflicts. This patch backs out the configuration option.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "56fd56b868f19385c50af8941a4c78df433b2d32", "tree": "5ea8362e6e141e2d1124d4640811c76489567bc5", "parents": [ "5c0e3066474b57c56ff0d88ca31d95bd14232fee" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:58 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "Bias the location of pages freed for min_free_kbytes in the same MAX_ORDER_NR_PAGES blocks\n\nThe standard buddy allocator always favours the smallest block of pages.\nThe effect of this is that the pages free to satisfy min_free_kbytes tends\nto be preserved since boot time at the same location of memory ffor a very\nlong time and as a contiguous block. When an administrator sets the\nreserve at 16384 at boot time, it tends to be the same MAX_ORDER blocks\nthat remain free. This allows the occasional high atomic allocation to\nsucceed up until the point the blocks are split. In practice, it is\ndifficult to split these blocks but when they do split, the benefit of\nhaving min_free_kbytes for contiguous blocks disappears. Additionally,\nincreasing min_free_kbytes once the system has been running for some time\nhas no guarantee of creating contiguous blocks.\n\nOn the other hand, CONFIG_PAGE_GROUP_BY_MOBILITY favours splitting large\nblocks when there are no free pages of the appropriate type available. A\nside-effect of this is that all blocks in memory tends to be used up and\nthe contiguous free blocks from boot time are not preserved like in the\nvanilla allocator. This can cause a problem if a new caller is unwilling\nto reclaim or does not reclaim for long enough.\n\nA failure scenario was found for a wireless network device allocating\norder-1 atomic allocations but the allocations were not intense or frequent\nenough for a whole block of pages to be preserved for MIGRATE_HIGHALLOC.\nThis was reproduced on a desktop by booting with mem\u003d256mb, forcing the\ndriver to allocate at order-1, running a bittorrent client (downloading a\ndebian ISO) and building a kernel with -j2.\n\nThis patch addresses the problem on the desktop machine booted with\nmem\u003d256mb. It works by setting aside a reserve of MAX_ORDER_NR_PAGES\nblocks, the number of which depends on the value of min_free_kbytes. These\nblocks are only fallen back to when there is no other free pages. Then the\nsmallest possible page is used just like the normal buddy allocator instead\nof the largest possible page to preserve contiguous pages The pages in free\nlists in the reserve blocks are never taken for another migrate type. The\nresults is that even if min_free_kbytes is set to a low value, contiguous\nblocks will be preserved in the MIGRATE_RESERVE blocks.\n\nThis works better than the vanilla allocator because if min_free_kbytes is\nincreased, a new reserve block will be chosen based on the location of\nreclaimable pages and the block will free up as contiguous pages. In the\nvanilla allocator, no effort is made to target a block of pages to free as\ncontiguous pages and min_free_kbytes pages are scattered randomly.\n\nThis effect has been observed on the test machine. min_free_kbytes was set\ninitially low but it was kept as a contiguous free block within\nMIGRATE_RESERVE. min_free_kbytes was then set to a higher value and over a\nperiod of time, the free blocks were within the reserve and coalescing.\nHow long it takes to free up depends on how quickly LRU is rotating.\nAmusingly, this means that more activity will free the blocks faster.\n\nThis mechanism potentially replaces MIGRATE_HIGHALLOC as it may be more\neffective than grouping contiguous free pages together. It all depends on\nwhether the number of active atomic high allocations exceeds\nmin_free_kbytes or not. If the number of active allocations exceeds\nmin_free_kbytes, it\u0027s worth it but maybe in that situation, min_free_kbytes\nshould be set higher. Once there are no more reports of allocation\nfailures, a patch will be submitted that backs out MIGRATE_HIGHALLOC and\nsee if the reports stay missing.\n\nCredit to Mariusz Kozlowski for discovering the problem, describing the\nfailure scenario and testing patches and scenarios.\n\n[akpm@linux-foundation.org: cleanups]\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "5c0e3066474b57c56ff0d88ca31d95bd14232fee", "tree": "90c963c62891db4a9039e84e615c01408b09c845", "parents": [ "46dafbca2bba811665b01d8cedf911204820623c" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:56 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "Fix corruption of memmap on IA64 SPARSEMEM when mem_section is not a power of 2\n\nThere are problems in the use of SPARSEMEM and pageblock flags that causes\nproblems on ia64.\n\nThe first part of the problem is that units are incorrect in\nSECTION_BLOCKFLAGS_BITS computation. This results in a map_section\u0027s\nsection_mem_map being treated as part of a bitmap which isn\u0027t good. This\nwas evident with an invalid virtual address when mem_init attempted to free\nbootmem pages while relinquishing control from the bootmem allocator.\n\nThe second part of the problem occurs because the pageblock flags bitmap is\nbe located with the mem_section. The SECTIONS_PER_ROOT computation using\nsizeof (mem_section) may not be a power of 2 depending on the size of the\nbitmap. This renders masks and other such things not power of 2 base.\nThis issue was seen with SPARSEMEM_EXTREME on ia64. This patch moves the\nbitmap outside of mem_section and uses a pointer instead in the\nmem_section. The bitmaps are allocated when the section is being\ninitialised.\n\nNote that sparse_early_usemap_alloc() does not use alloc_remap() like\nsparse_early_mem_map_alloc(). The allocation required for the bitmap on\nx86, the only architecture that uses alloc_remap is typically smaller than\na cache line. alloc_remap() pads out allocations to the cache size which\nwould be a needless waste.\n\nCredit to Bob Picco for identifying the original problem and effecting a\nfix for the SECTION_BLOCKFLAGS_BITS calculation. Credit to Andy Whitcroft\nfor devising the best way of allocating the bitmaps only when required for\nthe section.\n\n[wli@holomorphy.com: warning fix]\nSigned-off-by: Bob Picco \u003cbob.picco@hp.com\u003e\nSigned-off-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nSigned-off-by: William Irwin \u003cbill.irwin@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "46dafbca2bba811665b01d8cedf911204820623c", "tree": "c0dbc78b3da9749f257fa8756cd3133f39cd4f88", "parents": [ "5adc5be7cd1bcef6bb64f5255d2a33f20a3cf5be" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:55 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "Be more agressive about stealing when MIGRATE_RECLAIMABLE allocations fallback\n\nMIGRATE_RECLAIMABLE allocations tend to be very bursty in nature like when\nupdatedb starts. It is likely this will occur in situations where MAX_ORDER\nblocks of pages are not free. This means that updatedb can scatter\nMIGRATE_RECLAIMABLE pages throughout the address space. This patch is more\nagressive about stealing blocks of pages for MIGRATE_RECLAIMABLE.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "5adc5be7cd1bcef6bb64f5255d2a33f20a3cf5be", "tree": "39ed023e8c36cde0c0f9cba50f945e77d3ca26fa", "parents": [ "9ef9acb05a741ec10a5e9122717736de12adced9" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:54 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "Bias the placement of kernel pages at lower PFNs\n\nThis patch chooses blocks with lower PFNs when placing kernel allocations.\nThis is particularly important during fallback in low memory situations to\nstop unmovable pages being placed throughout the entire address space.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "9ef9acb05a741ec10a5e9122717736de12adced9", "tree": "6008083999b3c6e115714fcdea637195f2b53df6", "parents": [ "e010487dbe09d63cf916fd1b119d17abd0f48207" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:54 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "Do not group pages by mobility type on low memory systems\n\nGrouping pages by mobility can only successfully operate when there are more\nMAX_ORDER_NR_PAGES areas than mobility types. When there are insufficient\nareas, fallbacks cannot be avoided. This has noticeable performance impacts\non machines with small amounts of memory in comparison to MAX_ORDER_NR_PAGES.\nFor example, on IA64 with a configuration including huge pages spans 1GiB with\nMAX_ORDER_NR_PAGES so would need at least 4GiB of RAM before grouping pages by\nmobility would be useful. In comparison, an x86 would need 16MB.\n\nThis patch checks the size of vm_total_pages in build_all_zonelists(). If\nthere are not enough areas, mobility is effectivly disabled by considering\nall allocations as the same type (UNMOVABLE). This is achived via a\n__read_mostly flag.\n\nWith this patch, performance is comparable to disabling grouping pages\nby mobility at compile-time on a test machine with insufficient memory.\nWith this patch, it is reasonable to get rid of grouping pages by mobility\na compile-time option.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e010487dbe09d63cf916fd1b119d17abd0f48207", "tree": "37c7f36913daf4bc0a68a1d0ba1cc30ee0d4e307", "parents": [ "e12ba74d8ff3e2f73a583500d7095e406df4d093" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:53 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "Group high-order atomic allocations\n\nIn rare cases, the kernel needs to allocate a high-order block of pages\nwithout sleeping. For example, this is the case with e1000 cards configured\nto use jumbo frames. Migrating or reclaiming pages in this situation is not\nan option.\n\nThis patch groups these allocations together as much as possible by adding a\nnew MIGRATE_TYPE. The MIGRATE_HIGHATOMIC type are exactly what they sound\nlike. Care is taken that pages of other migrate types do not use the same\nblocks as high-order atomic allocations.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e12ba74d8ff3e2f73a583500d7095e406df4d093", "tree": "a0d3385b65f0b3e1e00b0bbf11b75e7538a93edb", "parents": [ "c361be55b3128474aa66d31092db330b07539103" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:52 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "Group short-lived and reclaimable kernel allocations\n\nThis patch marks a number of allocations that are either short-lived such as\nnetwork buffers or are reclaimable such as inode allocations. When something\nlike updatedb is called, long-lived and unmovable kernel allocations tend to\nbe spread throughout the address space which increases fragmentation.\n\nThis patch groups these allocations together as much as possible by adding a\nnew MIGRATE_TYPE. The MIGRATE_RECLAIMABLE type is for allocations that can be\nreclaimed on demand, but not moved. i.e. they can be migrated by deleting\nthem and re-reading the information from elsewhere.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andy Whitcroft \u003capw@shadowen.org\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "c361be55b3128474aa66d31092db330b07539103", "tree": "9ce134f4e679144d28f5c32924bdba999a1aae6b", "parents": [ "e2c55dc87f4a398b9c4dcc702dbc23a07fe14e23" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:51 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:00 2007 -0700" }, "message": "Move free pages between lists on steal\n\nWhen a fallback occurs, there will be free pages for one allocation type\nstored on the list for another. When a large steal occurs, this patch will\nmove all the free pages within one list to the other.\n\n[y-goto@jp.fujitsu.com: fix BUG_ON check at move_freepages()]\n[apw@shadowen.org: Move to using pfn_valid_within()]\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Christoph Lameter \u003cclameter@engr.sgi.com\u003e\nSigned-off-by: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nCc: Bjorn Helgaas \u003cbjorn.helgaas@hp.com\u003e\nSigned-off-by: Andy Whitcroft \u003candyw@uk.ibm.com\u003e\nCc: Bob Picco \u003cbob.picco@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e2c55dc87f4a398b9c4dcc702dbc23a07fe14e23", "tree": "b3811de298d4c98c4765db4af3838428553b5382", "parents": [ "b92a6edd4b77a8794adb497280beea5df5e59a14" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:50 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "Drain per-cpu lists when high-order allocations fail\n\nPer-cpu pages can accidentally cause fragmentation because they are free, but\npinned pages in an otherwise contiguous block. When this patch is applied,\nthe per-cpu caches are drained after the direct-reclaim is entered if the\nrequested order is greater than 0. It simply reuses the code used by suspend\nand hotplug.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b92a6edd4b77a8794adb497280beea5df5e59a14", "tree": "396ea5cf2b53fc066e949c443f03747ec868de1e", "parents": [ "535131e6925b4a95f321148ad7293f496e0e58d7" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:50 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "Add a configure option to group pages by mobility\n\nThe grouping mechanism has some memory overhead and a more complex allocation\npath. This patch allows the strategy to be disabled for small memory systems\nor if it is known the workload is suffering because of the strategy. It also\nacts to show where the page groupings strategy interacts with the standard\nbuddy allocator.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Joel Schopp \u003cjschopp@austin.ibm.com\u003e\nCc: Andy Whitcroft \u003capw@shadowen.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "535131e6925b4a95f321148ad7293f496e0e58d7", "tree": "fdd49e29f89eb6db3ba2b5ba7df7b059de95a91f", "parents": [ "b2a0ac8875a0a3b9f0739b60526f8c5977d2200f" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:49 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "Choose pages from the per-cpu list based on migration type\n\nThe freelists for each migrate type can slowly become polluted due to the\nper-cpu list. Consider what happens when the following happens\n\n1. A 2^(MAX_ORDER-1) list is reserved for __GFP_MOVABLE pages\n2. An order-0 page is allocated from the newly reserved block\n3. The page is freed and placed on the per-cpu list\n4. alloc_page() is called with GFP_KERNEL as the gfp_mask\n5. The per-cpu list is used to satisfy the allocation\n\nThis results in a kernel page is in the middle of a migratable region. This\npatch prevents this leak occuring by storing the MIGRATE_ type of the page in\npage-\u003eprivate. On allocate, a page will only be returned of the desired type,\nelse more pages will be allocated. This may temporarily allow a per-cpu list\nto go over the pcp-\u003ehigh limit but it\u0027ll be corrected on the next free. Care\nis taken to preserve the hotness of pages recently freed.\n\nThe additional code is not measurably slower for the workloads we\u0027ve tested.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b2a0ac8875a0a3b9f0739b60526f8c5977d2200f", "tree": "31826716b3209751a5468b840ff14190b4a5a8a2", "parents": [ "835c134ec4dd755e5c4470af566db226d1e96742" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:48 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "Split the free lists for movable and unmovable allocations\n\nThis patch adds the core of the fragmentation reduction strategy. It works by\ngrouping pages together based on their ability to migrate or be reclaimed.\nBasically, it works by breaking the list in zone-\u003efree_area list into\nMIGRATE_TYPES number of lists.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "835c134ec4dd755e5c4470af566db226d1e96742", "tree": "7bc659978b4fba5089fc820185a8b6f0cc010b08", "parents": [ "954ffcb35f5aca428661d29b96c4eee82b3c19cd" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Oct 16 01:25:47 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "Add a bitmap that is used to track flags affecting a block of pages\n\nHere is the latest revision of the anti-fragmentation patches. Of particular\nnote in this version is special treatment of high-order atomic allocations.\nCare is taken to group them together and avoid grouping pages of other types\nnear them. Artifical tests imply that it works. I\u0027m trying to get the\nhardware together that would allow setting up of a \"real\" test. If anyone\nalready has a setup and test that can trigger the atomic-allocation problem,\nI\u0027d appreciate a test of these patches and a report. The second major change\nis that these patches will apply cleanly with patches that implement\nanti-fragmentation through zones.\n\nkernbench shows effectively no performance difference varying between -0.2%\nand +2% on a variety of test machines. Success rates for huge page allocation\nare dramatically increased. For example, on a ppc64 machine, the vanilla\nkernel was only able to allocate 1% of memory as a hugepage and this was due\nto a single hugepage reserved as min_free_kbytes. With these patches applied,\n17% was allocatable as superpages. With reclaim-related fixes from Andy\nWhitcroft, it was 40% and further reclaim-related improvements should increase\nthis further.\n\nChangelog Since V28\no Group high-order atomic allocations together\no It is no longer required to set min_free_kbytes to 10% of memory. A value\n of 16384 in most cases will be sufficient\no Now applied with zone-based anti-fragmentation\no Fix incorrect VM_BUG_ON within buffered_rmqueue()\no Reorder the stack so later patches do not back out work from earlier patches\no Fix bug were journal pages were being treated as movable\no Bias placement of non-movable pages to lower PFNs\no More agressive clustering of reclaimable pages in reactions to workloads\n like updatedb that flood the size of inode caches\n\nChangelog Since V27\n\no Renamed anti-fragmentation to Page Clustering. Anti-fragmentation was giving\n the mistaken impression that it was the 100% solution for high order\n allocations. Instead, it greatly increases the chances high-order\n allocations will succeed and lays the foundation for defragmentation and\n memory hot-remove to work properly\no Redefine page groupings based on ability to migrate or reclaim instead of\n basing on reclaimability alone\no Get rid of spurious inits\no Per-cpu lists are no longer split up per-type. Instead the per-cpu list is\n searched for a page of the appropriate type\no Added more explanation commentary\no Fix up bug in pageblock code where bitmap was used before being initalised\n\nChangelog Since V26\no Fix double init of lists in setup_pageset\n\nChangelog Since V25\no Fix loop order of for_each_rclmtype_order so that order of loop matches args\no gfpflags_to_rclmtype uses gfp_t instead of unsigned long\no Rename get_pageblock_type() to get_page_rclmtype()\no Fix alignment problem in move_freepages()\no Add mechanism for assigning flags to blocks of pages instead of page-\u003eflags\no On fallback, do not examine the preferred list of free pages a second time\n\nThe purpose of these patches is to reduce external fragmentation by grouping\npages of related types together. When pages are migrated (or reclaimed under\nmemory pressure), large contiguous pages will be freed.\n\nThis patch works by categorising allocations by their ability to migrate;\n\nMovable - The pages may be moved with the page migration mechanism. These are\n\tgenerally userspace pages.\n\nReclaimable - These are allocations for some kernel caches that are\n\treclaimable or allocations that are known to be very short-lived.\n\nUnmovable - These are pages that are allocated by the kernel that\n\tare not trivially reclaimed. For example, the memory allocated for a\n\tloaded module would be in this category. By default, allocations are\n\tconsidered to be of this type\n\nHighAtomic - These are high-order allocations belonging to callers that\n\tcannot sleep or perform any IO. In practice, this is restricted to\n\tjumbo frame allocation for network receive. It is assumed that the\n\tallocations are short-lived\n\nInstead of having one MAX_ORDER-sized array of free lists in struct free_area,\nthere is one for each type of reclaimability. Once a 2^MAX_ORDER block of\npages is split for a type of allocation, it is added to the free-lists for\nthat type, in effect reserving it. Hence, over time, pages of the different\ntypes can be clustered together.\n\nWhen the preferred freelists are expired, the largest possible block is taken\nfrom an alternative list. Buddies that are split from that large block are\nplaced on the preferred allocation-type freelists to mitigate fragmentation.\n\nThis implementation gives best-effort for low fragmentation in all zones.\nIdeally, min_free_kbytes needs to be set to a value equal to 4 * (1 \u003c\u003c\n(MAX_ORDER-1)) pages in most cases. This would be 16384 on x86 and x86_64 for\nexample.\n\nOur tests show that about 60-70% of physical memory can be allocated on a\ndesktop after a few days uptime. In benchmarks and stress tests, we are\nfinding that 80% of memory is available as contiguous blocks at the end of the\ntest. To compare, a standard kernel was getting \u003c 1% of memory as large pages\non a desktop and about 8-12% of memory as large pages at the end of stress\ntests.\n\nFollowing this email are 12 patches that implement thie page grouping feature.\n The first patch introduces a mechanism for storing flags related to a whole\nblock of pages. Then allocations are split between movable and all other\nallocations. Following that are patches to deal with per-cpu pages and make\nthe mechanism configurable. The next patch moves free pages between lists\nwhen partially allocated blocks are used for pages of another migrate type.\nThe second last patch groups reclaimable kernel allocations such as inode\ncaches together. The final patch related to groupings keeps high-order atomic\nallocations.\n\nThe last two patches are more concerned with control of fragmentation. The\nsecond last patch biases placement of non-movable allocations towards the\nstart of memory. This is with a view of supporting memory hot-remove of DIMMs\nwith higher PFNs in the future. The biasing could be enforced a lot heavier\nbut it would cost. The last patch agressively clusters reclaimable pages like\ninode caches together.\n\nThe fragmentation reduction strategy needs to track if pages within a block\ncan be moved or reclaimed so that pages are freed to the appropriate list.\nThis patch adds a bitmap for flags affecting a whole a MAX_ORDER block of\npages.\n\nIn non-SPARSEMEM configurations, the bitmap is stored in the struct zone and\nallocated during initialisation. SPARSEMEM statically allocates the bitmap in\na struct mem_section so that bitmaps do not have to be resized during memory\nhotadd. This wastes a small amount of memory per unused section (usually\nsizeof(unsigned long)) but the complexity of dynamically allocating the memory\nis quite high.\n\nAdditional credit to Andy Whitcroft who reviewed up an earlier implementation\nof the mechanism an suggested how to make it a *lot* cleaner.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andy Whitcroft \u003capw@shadowen.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "954ffcb35f5aca428661d29b96c4eee82b3c19cd", "tree": "2dd8aaf26a8ae81b461b6d5d824ae8744690e483", "parents": [ "97ee052461446526e1de7236497e6f1b1ffedf8c" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Oct 16 01:25:44 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "flush icache before set_pte() on ia64: flush icache at set_pte\n\nCurrent ia64 kernel flushes icache by lazy_mmu_prot_update() *after*\nset_pte(). This is too late. This patch removes lazy_mmu_prot_update and\nadd modfied set_pte() for flushing if necessary.\n\nThis patch flush icache of a page when\n\tnew pte has exec bit.\n\t\u0026\u0026 new pte has present bit\n\t\u0026\u0026 new pte is user\u0027s page.\n\t\u0026\u0026 (old *ptep is not present\n || new pte\u0027s pfn is not same to old *ptep\u0027s ptn)\n\t\u0026\u0026 new pte\u0027s page has no Pg_arch_1 bit.\n\t Pg_arch_1 is set when a page is cache consistent.\n\nI think this condition checks are much easier to understand than considering\n\"Where sync_icache_dcache() should be inserted ?\".\n\npte_user() for ia64 was removed by http://lkml.org/lkml/2007/6/12/67 as\nclean-up. So, I added it again.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nAcked-by: David S. Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "97ee052461446526e1de7236497e6f1b1ffedf8c", "tree": "7c91270577191ed32de22d8183695c1354d555c8", "parents": [ "4106f83a9f86afc423557d0d92ebf4b3f36728c1" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Oct 16 01:25:43 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "flush cache before installing new page at migraton\n\nIn migration, a new page should be cache flushed before set_pte() in some\narchs which have virtually-tagged cache.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nAcked-by: David S. Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4106f83a9f86afc423557d0d92ebf4b3f36728c1", "tree": "b2da62d411e720b6053a80074c9fb8343ec17ccc", "parents": [ "6cb062296f73e74768cca2f3eaf90deac54de02d" ], "author": { "name": "Andrea Arcangeli", "email": "andrea@suse.de", "time": "Tue Oct 16 01:25:42 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "make swappiness safer to use\n\nSwappiness isn\u0027t a safe sysctl. Setting it to 0 for example can hang a\nsystem. That\u0027s a corner case but even setting it to 10 or lower can waste\nenormous amounts of cpu without making much progress. We\u0027ve customers who\nwants to use swappiness but they can\u0027t because of the current\nimplementation (if you change it so the system stops swapping it really\nstops swapping and nothing works sane anymore if you really had to swap\nsomething to make progress).\n\nThis patch from Kurt Garloff makes swappiness safer to use (no more huge\ncpu usage or hangs with low swappiness values).\n\nI think the prev_priority can also be nuked since it wastes 4 bytes per\nzone (that would be an incremental patch but I wait the nr_scan_[in]active\nto be nuked first for similar reasons). Clearly somebody at some point\nnoticed how broken that thing was and they had to add min(priority,\nprev_priority) to give it some reliability, but they didn\u0027t go the last\nmile to nuke prev_priority too. Calculating distress only in function of\nnot-racy priority is correct and sure more than enough without having to\nadd randomness into the equation.\n\nPatch is tested on older kernels but it compiles and it\u0027s quite simple\nso...\n\nOverall I\u0027m not very satisified by the swappiness tweak, since it doesn\u0027t\nrally do anything with the dirty pagecache that may be inactive. We need\nanother kind of tweak that controls the inactive scan and tunes the\ncan_writepage feature (not yet in mainline despite having submitted it a\nfew times), not only the active one. That new tweak will tell the kernel\nhow hard to scan the inactive list for pure clean pagecache (something the\nmainline kernel isn\u0027t capable of yet). We already have that feature\nworking in all our enterprise kernels with the default reasonable tune, or\nthey can\u0027t even run a readonly backup with tar without triggering huge\nwrite I/O. I think it should be available also in mainline later.\n\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Kurt Garloff \u003cgarloff@suse.de\u003e\nSigned-off-by: Andrea Arcangeli \u003candrea@suse.de\u003e\nSigned-off-by: Fengguang Wu \u003cwfg@mail.ustc.edu.cn\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6cb062296f73e74768cca2f3eaf90deac54de02d", "tree": "1572139653a6fc97cdffd06f2c1bfa650da2ce03", "parents": [ "58c0a4a7864b2dad6da4090813322fcd29a11c92" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:41 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "Categorize GFP flags\n\nThe function of GFP_LEVEL_MASK seems to be unclear. In order to clear up\nthe mystery we get rid of it and replace GFP_LEVEL_MASK with 3 sets of GFP\nflags:\n\nGFP_RECLAIM_MASK\tFlags used to control page allocator reclaim behavior.\n\nGFP_CONSTRAINT_MASK\tFlags used to limit where allocations can occur.\n\nGFP_SLAB_BUG_MASK\tFlags that the slab allocator BUG()s on.\n\nThese replace the uses of GFP_LEVEL mask in the slab allocators and in\nvmalloc.c.\n\nThe use of the flags not included in these sets may occur as a result of a\nslab allocation standing in for a page allocation when constructing scatter\ngather lists. Extraneous flags are cleared and not passed through to the\npage allocator. __GFP_MOVABLE/RECLAIMABLE, __GFP_COLD and __GFP_COMP will\nnow be ignored if passed to a slab allocator.\n\nChange the allocation of allocator meta data in SLAB and vmalloc to not\npass through flags listed in GFP_CONSTRAINT_MASK. SLAB already removes the\n__GFP_THISNODE flag for such allocations. Generalize that to also cover\nvmalloc. The use of GFP_CONSTRAINT_MASK also includes __GFP_HARDWALL.\n\nThe impact of allocator metadata placement on access latency to the\ncachelines of the object itself is minimal since metadata is only\nreferenced on alloc and free. The attempt is still made to place the meta\ndata optimally but we consistently allow fallback both in SLAB and vmalloc\n(SLUB does not need to allocate metadata like that).\n\nAllocator metadata may serve multiple in kernel users and thus should not\nbe subject to the limitations arising from a single allocation context.\n\n[akpm@linux-foundation.org: fix fallback_alloc()]\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "58c0a4a7864b2dad6da4090813322fcd29a11c92", "tree": "239da4074ced93ee6918fdb03e3839ef721191bb", "parents": [ "37b07e4163f7306aa735a6e250e8d22293e5b8de" ], "author": { "name": "Yasunori Goto", "email": "y-goto@jp.fujitsu.com", "time": "Tue Oct 16 01:25:40 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "Fix panic of cpu online with memory less node\n\nWhen a cpu is onlined on memory-less-node box, kernel panics due to touch\nNULL pointer of pgdat-\u003ekswapd. Current kswapd runs only nodes which have\nmemory. So, calling of set_cpus_allowed() is not necessary for memory-less\nnode.\n\nThis is fix for it.\n\nSigned-off-by: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "37b07e4163f7306aa735a6e250e8d22293e5b8de", "tree": "5c9c1935253a39aa840a9923bf1c86620cb6f733", "parents": [ "0e1e7c7a739562a321fda07c7cd2a97a7114f8f8" ], "author": { "name": "Lee Schermerhorn", "email": "Lee.Schermerhorn@hp.com", "time": "Tue Oct 16 01:25:39 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "memoryless nodes: fixup uses of node_online_map in generic code\n\nHere\u0027s a cut at fixing up uses of the online node map in generic code.\n\nmm/shmem.c:shmem_parse_mpol()\n\n\tEnsure nodelist is subset of nodes with memory.\n\tUse node_states[N_HIGH_MEMORY] as default for missing\n\tnodelist for interleave policy.\n\nmm/shmem.c:shmem_fill_super()\n\n\tinitialize policy_nodes to node_states[N_HIGH_MEMORY]\n\nmm/page-writeback.c:highmem_dirtyable_memory()\n\n\tsum over nodes with memory\n\nmm/page_alloc.c:zlc_setup()\n\n\tallowednodes - use nodes with memory.\n\nmm/page_alloc.c:default_zonelist_order()\n\n\taverage over nodes with memory.\n\nmm/page_alloc.c:find_next_best_node()\n\n\tskip nodes w/o memory.\n\tN_HIGH_MEMORY state mask may not be initialized at this time,\n\tunless we want to depend on early_calculate_totalpages() [see\n\tbelow]. Will ZONE_MOVABLE ever be configurable?\n\nmm/page_alloc.c:find_zone_movable_pfns_for_nodes()\n\n\tspread kernelcore over nodes with memory.\n\n\tThis required calling early_calculate_totalpages()\n\tunconditionally, and populating N_HIGH_MEMORY node\n\tstate therein from nodes in the early_node_map[].\n\tIf we can depend on this, we can eliminate the\n\tpopulation of N_HIGH_MEMORY mask from __build_all_zonelists()\n\tand use the N_HIGH_MEMORY mask in find_next_best_node().\n\nmm/mempolicy.c:mpol_check_policy()\n\n\tEnsure nodes specified for policy are subset of\n\tnodes with memory.\n\n[akpm@linux-foundation.org: fix warnings]\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Shaohua Li \u003cshaohua.li@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "0e1e7c7a739562a321fda07c7cd2a97a7114f8f8", "tree": "f2148e5b667152681625c19cf8b2a556500994ea", "parents": [ "523b945855a1427000ffc707c610abe5947ae607" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:38 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "Memoryless nodes: Use N_HIGH_MEMORY for cpusets\n\ncpusets try to ensure that any node added to a cpuset\u0027s mems_allowed is\non-line and contains memory. The assumption was that online nodes contained\nmemory. Thus, it is possible to add memoryless nodes to a cpuset and then add\ntasks to this cpuset. This results in continuous series of oom-kill and\napparent system hang.\n\nChange cpusets to use node_states[N_HIGH_MEMORY] [a.k.a. node_memory_map] in\nplace of node_online_map when vetting memories. Return error if admin\nattempts to write a non-empty mems_allowed node mask containing only\nmemoryless-nodes.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Bob Picco \u003cbob.picco@hp.com\u003e\nSigned-off-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "523b945855a1427000ffc707c610abe5947ae607", "tree": "2d84b5b6822a2a20bfd79146c08ce06ac8c80b9b", "parents": [ "633c0666b5a5c41c376a5a7e4304d638dc48c1b9" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:37 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "Memoryless nodes: Fix GFP_THISNODE behavior\n\nGFP_THISNODE checks that the zone selected is within the pgdat (node) of the\nfirst zone of a nodelist. That only works if the node has memory. A\nmemoryless node will have its first node on another pgdat (node).\n\nGFP_THISNODE currently will return simply memory on the first pgdat. Thus it\nis returning memory on other nodes. GFP_THISNODE should fail if there is no\nlocal memory on a node.\n\nAdd a new set of zonelists for each node that only contain the nodes that\nbelong to the zones itself so that no fallback is possible.\n\nThen modify gfp_type to pickup the right zone based on the presence of\n__GFP_THISNODE.\n\nDrop the existing GFP_THISNODE checks from the page_allocators hot path.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nAcked-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nTested-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "633c0666b5a5c41c376a5a7e4304d638dc48c1b9", "tree": "a8f42f5d4aaa4d25786d5a60e9c92b6d727254fd", "parents": [ "37c0708dbee5825df3bd9ce6ef2199c6c1713970" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:37 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "Memoryless nodes: drop one memoryless node boot warning\n\nget_pfn_range_for_nid() is called multiple times for each node at boot time.\nEach time, it will warn about nodes with no memory, resulting in boot messages\nlike:\n\n Node 0 active with no memory\n Node 0 active with no memory\n Node 0 active with no memory\n Node 0 active with no memory\n Node 0 active with no memory\n Node 0 active with no memory\n On node 0 totalpages: 0\n Node 0 active with no memory\n Node 0 active with no memory\n DMA zone: 0 pages used for memmap\n Node 0 active with no memory\n Node 0 active with no memory\n Normal zone: 0 pages used for memmap\n Node 0 active with no memory\n Node 0 active with no memory\n Movable zone: 0 pages used for memmap\n\nand so on for each memoryless node.\n\nWe already have the \"On node N totalpages: ...\" and other related messages, so\ndrop the \"Node N active with no memory\" warnings.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "37c0708dbee5825df3bd9ce6ef2199c6c1713970", "tree": "747551aa58484e7f872da118b864c8f3ca6e892d", "parents": [ "56bbd65df0e92a4a8eb70c5f2b416ae2b6c5fb31" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:36 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "Memoryless nodes: Add N_CPU node state\n\nWe need the check for a node with cpu in zone reclaim. Zone reclaim will not\nallow remote zone reclaim if a node has a cpu.\n\n[Lee.Schermerhorn@hp.com: Move setup of N_CPU node state mask]\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nTested-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "56bbd65df0e92a4a8eb70c5f2b416ae2b6c5fb31", "tree": "714154b7b16d2e08c60d49b925aa0e789f0f0be0", "parents": [ "4199cfa02b982f4c739e8a6a304d6a40e1935d25" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:35 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "Memoryless nodes: Update memory policy and page migration\n\nOnline nodes now may have no memory. The checks and initialization must\ntherefore be changed to no longer use the online functions.\n\nThis will correctly initialize the interleave on bootup to only target nodes\nwith memory and will make sys_move_pages return an error when a page is to be\nmoved to a memoryless node. Similarly we will get an error if MPOL_BIND and\nMPOL_INTERLEAVE is used on a memoryless node.\n\nThese are somewhat new semantics. So far one could specify memoryless nodes\nand we would maybe do the right thing and just ignore the node (or we\u0027d do\nsomething strange like with MPOL_INTERLEAVE). If we want to allow the\nspecification of memoryless nodes via memory policies then we need to keep\nchecking for online nodes.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nAcked-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nTested-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4199cfa02b982f4c739e8a6a304d6a40e1935d25", "tree": "c917040b3ed5be157bee34a03408f31cf330dad0", "parents": [ "2dca53a9dabe76f49209c9128313347510416c68" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:34 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "Memoryless nodes: Allow profiling data to fall back to other nodes\n\nProcessors on memoryless nodes must be able to fall back to remote nodes in\norder to get a profiling buffer. This may lead to excessive NUMA traffic but\nI think we should allow this rather than failing.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nAcked-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nAcked-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "2dca53a9dabe76f49209c9128313347510416c68", "tree": "73b58d1f6277305b592f2c53d7b43b151a3f9e3b", "parents": [ "f64dc58c5412233d4d44b0275eaebdc11bde23b3" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:33 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "Memoryless nodes: Uncached allocator updates\n\nThe checks for node_online in the uncached allocator are made to make sure\nthat memory is available on these nodes. Thus switch all the checks to use\nN_HIGH_MEMORY and to N_ONLINE.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Jes Sorensen \u003cjes@sgi.com\u003e\nAcked-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f64dc58c5412233d4d44b0275eaebdc11bde23b3", "tree": "c35755b1a2a04eefd97d3561640992e5d817ccba", "parents": [ "04231b3002ac53f8a64a7bd142fde3fa4b6808c6" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:33 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "Memoryless nodes: SLUB support\n\nSimply switch all for_each_online_node to for_each_node_state(NORMAL_MEMORY).\nThat way SLUB only operates on nodes with regular memory. Any allocation\nattempt on a memoryless node or a node with just highmem will fall whereupon\nSLUB will fetch memory from a nearby node (depending on how memory policies\nand cpuset describe fallback).\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nTested-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "04231b3002ac53f8a64a7bd142fde3fa4b6808c6", "tree": "7c55f86dbe697621943176cfa2a341dc0e6760ef", "parents": [ "9422ffba4adc82b4b67a3ca6ef51516aa61f8248" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:32 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "Memoryless nodes: Slab support\n\nSlab should not allocate control structures for nodes without memory. This\nmay seem to work right now but its unreliable since not all allocations can\nfall back due to the use of GFP_THISNODE.\n\nSwitching a few for_each_online_node\u0027s to N_NORMAL_MEMORY will allow us to\nonly allocate for nodes that have regular memory.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nAcked-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nAcked-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "9422ffba4adc82b4b67a3ca6ef51516aa61f8248", "tree": "e30f87beca455b3e3b1f4c8c8921e9ef049c000f", "parents": [ "ee31af5d649d8aa6ac7948a6d97ae48367ff2d7e" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:31 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "Memoryless nodes: No need for kswapd\n\nA node without memory does not need a kswapd. So use the memory map instead\nof the online map when starting kswapd.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nAcked-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nTested-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ee31af5d649d8aa6ac7948a6d97ae48367ff2d7e", "tree": "8a16d8c15b8b56058b905c2b83a3a5f8112746c4", "parents": [ "6eaf806a223e61dc5f2de4ab591f11beb97a8f3b" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:30 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "Memoryless nodes: OOM: use N_HIGH_MEMORY map instead of constructing one on the fly\n\nconstrained_alloc() builds its own memory map for nodes with memory. We have\nthat available in N_HIGH_MEMORY now. So simplify the code.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nAcked-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nAcked-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6eaf806a223e61dc5f2de4ab591f11beb97a8f3b", "tree": "fd63b422c3cb357792d12f9170c354e25b94daa0", "parents": [ "7ea1530ab3fdfa85441061909cc8040e84776fd4" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:30 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "Memoryless nodes: Fix interleave behavior for memoryless nodes\n\nMPOL_INTERLEAVE currently simply loops over all nodes. Allocations on\nmemoryless nodes will be redirected to nodes with memory. This results in an\nimbalance because the neighboring nodes to memoryless nodes will get\nsignificantly more interleave hits that the rest of the nodes on the system.\n\nWe can avoid this imbalance by clearing the nodes in the interleave node set\nthat have no memory. If we use the node map of the memory nodes instead of\nthe online nodes then we have only the nodes we want.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nTested-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7ea1530ab3fdfa85441061909cc8040e84776fd4", "tree": "f3af0f8ed40a6df90bdbb9396d6163d59798a821", "parents": [ "13808910713a98cc1159291e62cdfec92cc94d05" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:29 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "Memoryless nodes: introduce mask of nodes with memory\n\nIt is necessary to know if nodes have memory since we have recently begun to\nadd support for memoryless nodes. For that purpose we introduce a two new\nnode states: N_HIGH_MEMORY and N_NORMAL_MEMORY.\n\nA node has its bit in N_HIGH_MEMORY set if it has any memory regardless of the\ntype of mmemory. If a node has memory then it has at least one zone defined\nin its pgdat structure that is located in the pgdat itself.\n\nA node has its bit in N_NORMAL_MEMORY set if it has a lower zone than\nZONE_HIGHMEM. This means it is possible to allocate memory that is not\nsubject to kmap.\n\nN_HIGH_MEMORY and N_NORMAL_MEMORY can then be used in various places to insure\nthat we do the right thing when we encounter a memoryless node.\n\n[akpm@linux-foundation.org: build fix]\n[Lee.Schermerhorn@hp.com: update N_HIGH_MEMORY node state for memory hotadd]\n[y-goto@jp.fujitsu.com: Fix memory hotplug + sparsemem build]\nSigned-off-by: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nSigned-off-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nSigned-off-by: Paul Mundt \u003clethal@linux-sh.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "13808910713a98cc1159291e62cdfec92cc94d05", "tree": "0fd7189dc2a76e1ae165ca5d6e8c6b4e6f1761af", "parents": [ "55144768e100b68447f44c5e5c9deb155ad661bd" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:27 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "Memoryless nodes: Generic management of nodemasks for various purposes\n\nWhy do we need to support memoryless nodes?\n\nKAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e wrote:\n\n\u003e For fujitsu, problem is called \"empty\" node.\n\u003e\n\u003e When ACPI\u0027s SRAT table includes \"possible nodes\", ia64 bootstrap(acpi_numa_init)\n\u003e creates nodes, which includes no memory, no cpu.\n\u003e\n\u003e I tried to remove empty-node in past, but that was denied.\n\u003e It was because we can hot-add cpu to the empty node.\n\u003e (node-hotplug triggered by cpu is not implemented now. and it will be ugly.)\n\u003e\n\u003e\n\u003e For HP, (Lee can comment on this later), they have memory-less-node.\n\u003e As far as I hear, HP\u0027s machine can have following configration.\n\u003e\n\u003e (example)\n\u003e Node0: CPU0 memory AAA MB\n\u003e Node1: CPU1 memory AAA MB\n\u003e Node2: CPU2 memory AAA MB\n\u003e Node3: CPU3 memory AAA MB\n\u003e Node4: Memory XXX GB\n\u003e\n\u003e AAA is very small value (below 16MB) and will be omitted by ia64 bootstrap.\n\u003e After boot, only Node 4 has valid memory (but have no cpu.)\n\u003e\n\u003e Maybe this is memory-interleave by firmware config.\n\nChristoph Lameter \u003cclameter@sgi.com\u003e wrote:\n\n\u003e Future SGI platforms (actually also current one can have but nothing like\n\u003e that is deployed to my knowledge) have nodes with only cpus. Current SGI\n\u003e platforms have nodes with just I/O that we so far cannot manage in the\n\u003e core. So the arch code maps them to the nearest memory node.\n\nLee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e wrote:\n\n\u003e For the HP platforms, we can configure each cell with from 0% to 100%\n\u003e \"cell local memory\". When we configure with \u003c100% CLM, the \"missing\n\u003e percentages\" are interleaved by hardware on a cache-line granularity to\n\u003e improve bandwidth at the expense of latency for numa-challenged\n\u003e applications [and OSes, but not our problem ;-)]. When we boot Linux on\n\u003e such a config, all of the real nodes have no memory--it all resides in a\n\u003e single interleaved pseudo-node.\n\u003e\n\u003e When we boot Linux on a 100% CLM configuration [\u003d\u003d NUMA], we still have\n\u003e the interleaved pseudo-node. It contains a few hundred MB stolen from\n\u003e the real nodes to contain the DMA zone. [Interleaved memory resides at\n\u003e phys addr 0]. The memoryless-nodes patches, along with the zoneorder\n\u003e patches, support this config as well.\n\u003e\n\u003e Also, when we boot a NUMA config with the \"mem\u003d\" command line,\n\u003e specifying less memory than actually exists, Linux takes the excluded\n\u003e memory \"off the top\" rather than distributing it across the nodes. This\n\u003e can result in memoryless nodes, as well.\n\u003e\n\nThis patch:\n\nPreparation for memoryless node patches.\n\nProvide a generic way to keep nodemasks describing various characteristics of\nNUMA nodes.\n\nRemove the node_online_map and the node_possible map and realize the same\nfunctionality using two nodes stats: N_POSSIBLE and N_ONLINE.\n\n[Lee.Schermerhorn@hp.com: Initialize N_*_MEMORY and N_CPU masks for non-NUMA config]\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nTested-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: \"Serge E. Hallyn\" \u003cserge@hallyn.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "55144768e100b68447f44c5e5c9deb155ad661bd", "tree": "9889682ee3b64627ad9eb504f30672fad844752f", "parents": [ "03158cd7eb3374843de68421142ca5900df845d9" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:26 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "fs: remove some AOP_TRUNCATED_PAGE\n\nprepare/commit_write no longer returns AOP_TRUNCATED_PAGE since OCFS2 and\nGFS2 were converted to the new aops, so we can make some simplifications\nfor that.\n\n[michal.k.k.piotrowski@gmail.com: fix warning]\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Michael Halcrow \u003cmhalcrow@us.ibm.com\u003e\nCc: Mark Fasheh \u003cmark.fasheh@oracle.com\u003e\nCc: Steven Whitehouse \u003cswhiteho@redhat.com\u003e\nSigned-off-by: Michal Piotrowski \u003cmichal.k.k.piotrowski@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "03158cd7eb3374843de68421142ca5900df845d9", "tree": "5e1bfc1f981651e7f7d7cf30afd15d7bd96b2a57", "parents": [ "b6af1bcd8720cb3062c8c4d4c8ba02bee10ff03f" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:25 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "fs: restore nobh\n\nImplement nobh in new aops. This is a bit tricky. FWIW, nobh_truncate is\nnow implemented in a way that does not create blocks in sparse regions,\nwhich is a silly thing for it to have been doing (isn\u0027t it?)\n\next2 survives fsx and fsstress. jfs is converted as well... ext3\nshould be easy to do (but not done yet).\n\n[akpm@linux-foundation.org: coding-style fixes]\nCc: Badari Pulavarty \u003cpbadari@us.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b6af1bcd8720cb3062c8c4d4c8ba02bee10ff03f", "tree": "e6cb27498f649dd3addc48fb4d92ac20ae8de7cb", "parents": [ "f2b6a16eb8f5b4851b01625a21e0c71207c2ce77" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:24 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "ocfs2: convert to new aops\n\nPlug ocfs2 into the -\u003ewrite_begin and -\u003ewrite_end aops.\n\nA bunch of custom code is now gone - the iovec iteration stuff during write\nand the ocfs2 splice write actor.\n\nSigned-off-by: Mark Fasheh \u003cmark.fasheh@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f2b6a16eb8f5b4851b01625a21e0c71207c2ce77", "tree": "6903e844147078f8f8d817b17eada5a65b4a7623", "parents": [ "b4585729f0b616c95aacafb8c8cb5e1af0d4242f" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:24 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "fs: affs convert to new aops\n\nCc: Roman Zippel \u003czippel@linux-m68k.org\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": "b4585729f0b616c95aacafb8c8cb5e1af0d4242f", "tree": "d87045fed9cf165dca1e3e41802f5c2f7e2bbf09", "parents": [ "d5c5f84ba9b9138b03ba90f1b7f83a379cfaea6a" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:23 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:57 2007 -0700" }, "message": "fs: adfs convert to new aops\n\nAcked-by: Russell King \u003crmk+kernel@arm.linux.org.uk\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": "d5c5f84ba9b9138b03ba90f1b7f83a379cfaea6a", "tree": "6b4ec3492101c30de0b1062e20543063cbb16cad", "parents": [ "4a66af9eaa9531372cfcb9e20103ed147c729ff9" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:22 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:57 2007 -0700" }, "message": "jfs: convert to new aops\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nAcked-by: Dave Kleikamp \u003cshaggy@linux.vnet.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4a66af9eaa9531372cfcb9e20103ed147c729ff9", "tree": "8c766cdab76be6369e450b783c61d168e8374762", "parents": [ "26a6441aadde864132672750b3cf0892e5acaaf4" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:21 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:57 2007 -0700" }, "message": "minixfs: convert to new aops\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Andries Brouwer \u003cAndries.Brouwer@cwi.nl\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "26a6441aadde864132672750b3cf0892e5acaaf4", "tree": "2e85db7e46c956f5e0d7150e09accb67235983b6", "parents": [ "be021ee41a8b65d181fe22799de6be62adf72efb" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:21 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:57 2007 -0700" }, "message": "sysv: convert to new aops\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "be021ee41a8b65d181fe22799de6be62adf72efb", "tree": "d02e79ac30c6b03ea361bc425a566a402a8db0c0", "parents": [ "82b9d1d0da8046088b0f505f92a97d12d9804613" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:20 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:57 2007 -0700" }, "message": "udf: convert to new aops\n\nConvert udf to new aops. Also seem to have fixed pagecache corruption in\nudf_adinicb_commit_write -- page was marked uptodate when it is not. Also,\nfixed the silly setup where prepare_write was doing a kmap to be used in\ncommit_write: just do kmap_atomic in write_end. Use libfs helpers to make\nthis easier.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: \u003cbfennema@falcon.csc.calpoly.edu\u003e\nCc: Jan Kara \u003cjack@ucw.cz\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "82b9d1d0da8046088b0f505f92a97d12d9804613", "tree": "de9d6f5a0fa7482a097bcf97152c25dedf68e19e", "parents": [ "205c109a7a96d9a3d8ffe64c4068b70811fef5e8" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:19 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:57 2007 -0700" }, "message": "ufs: convert to new aops\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Evgeniy Dushistov \u003cdushistov@mail.ru\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "205c109a7a96d9a3d8ffe64c4068b70811fef5e8", "tree": "2822c27a8d51045bb55821517dc763e73fe19871", "parents": [ "ae361ff46ba93b2644675d9de19e885185f0d0c1" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:18 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:57 2007 -0700" }, "message": "jffs2: convert to new aops\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: David Woodhouse \u003cdwmw2@infradead.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ae361ff46ba93b2644675d9de19e885185f0d0c1", "tree": "b5af5dd9b66382e5681ae9195147c38cc8f1f3b4", "parents": [ "5e6f58a1d7ce2fd5ef099f9aec5b3e3f7ba176b4" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:17 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:57 2007 -0700" }, "message": "hostfs: convert to new aops\n\nThis also gets rid of a lot of useless read_file stuff. And also\noptimises the full page write case by marking a !uptodate page uptodate.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Jeff Dike \u003cjdike@addtoit.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "5e6f58a1d7ce2fd5ef099f9aec5b3e3f7ba176b4", "tree": "2a63f0587a60d30d00cbadb6d33756725173576f", "parents": [ "fb53b3094888be0cf8ddf052277654268904bdf5" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:17 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:57 2007 -0700" }, "message": "fuse: convert to new aops\n\n[mszeredi]\n - don\u0027t send zero length write requests\n - it is not legal for the filesystem to return with zero written bytes\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "fb53b3094888be0cf8ddf052277654268904bdf5", "tree": "49c63bf1c06c207443fe14b4a5f8e3c479e2ea2d", "parents": [ "4899f9c852564ce7b6d0ca932ac6674bf471fd28" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:16 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:57 2007 -0700" }, "message": "smbfs: convert to new aops\n\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": "4899f9c852564ce7b6d0ca932ac6674bf471fd28", "tree": "4248794207b9b82077f48ce08655a018d89d2683", "parents": [ "a20fa20c549ed569885d871f689a59cfd2f6ff77" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:16 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:57 2007 -0700" }, "message": "nfs: convert to new aops\n\n[akpm@linux-foundation.org: fix against git-nfs]\n[peterz@infradead.org: fix against git-nfs]\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nAcked-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\nCc: \"J. Bruce Fields\" \u003cbfields@fieldses.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a20fa20c549ed569885d871f689a59cfd2f6ff77", "tree": "bc6f7119cec83032eb43c27d6ec7bbbebd2fdddb", "parents": [ "f7557e8f7ff785d6c2b5bc914cd1675314ff0fcf" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:15 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:56 2007 -0700" }, "message": "With reiserfs no longer using the weird generic_cont_expand, remove it completely.\n\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": "f7557e8f7ff785d6c2b5bc914cd1675314ff0fcf", "tree": "ad00de4fd519ff462df289f23dfb21d395e1e011", "parents": [ "ba9d8cec6c7165e440f9b2413a0464cf3c12fb25" ], "author": { "name": "Vladimir Saveliev", "email": "vs@namesys.com", "time": "Tue Oct 16 01:25:14 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:56 2007 -0700" }, "message": "reiserfs: use generic_cont_expand_simple\n\nThis patch makes reiserfs to use AOP_FLAG_CONT_EXPAND\nin order to get rid of the special generic_cont_expand routine\n\nSigned-off-by: Vladimir Saveliev \u003cvs@namesys.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": "ba9d8cec6c7165e440f9b2413a0464cf3c12fb25", "tree": "7fc05b10cdd18da51fce987b3323754ecdc53973", "parents": [ "797b4cffdf79b9ed66759b8d2d5252eba965fb18" ], "author": { "name": "Vladimir Saveliev", "email": "vs@namesys.com", "time": "Tue Oct 16 01:25:14 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:56 2007 -0700" }, "message": "reiserfs: convert to new aops\n\nConvert reiserfs to new aops\n\nSigned-off-by: Vladimir Saveliev \u003cvs@namesys.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": "797b4cffdf79b9ed66759b8d2d5252eba965fb18", "tree": "5704fe75e0e9ff45ccd078d0b34420ad71f242a8", "parents": [ "f87061842877cf822251c65b39cc624cc94046da" ], "author": { "name": "Vladimir Saveliev", "email": "vs@namesys.com", "time": "Tue Oct 16 01:25:12 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:56 2007 -0700" }, "message": "reiserfs: use generic write\n\nMake reiserfs to write via generic routines.\nOriginal reiserfs write optimized for big writes is deadlock rone\n\nSigned-off-by: Vladimir Saveliev \u003cvs@namesys.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": "f87061842877cf822251c65b39cc624cc94046da", "tree": "d1d5b57b32ced0e4ac657ca1aee2ecdbec57bb77", "parents": [ "eedcbba5e012978ec1bf972723aa02ab4df972e6" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:12 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:56 2007 -0700" }, "message": "qnx4: convert to new aops\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nAcked-by: Anders Larsen \u003cal@alarsen.net\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "eedcbba5e012978ec1bf972723aa02ab4df972e6", "tree": "6b31163962fb96fa58c5198777efd515db821788", "parents": [ "d6091b720184c72909ef4dc4059b73bf68abea56" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:11 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:56 2007 -0700" }, "message": "bfs: convert to new aops\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Tigran Aivazian \u003ctigran@aivazian.fsnet.co.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d6091b720184c72909ef4dc4059b73bf68abea56", "tree": "75b6bee2f5d4c928687de680f0be5eb7ebac11e2", "parents": [ "7c0efc627738c840a685ea0f2c23d09aad7d5d3b" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:10 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:56 2007 -0700" }, "message": "hpfs: convert to new aops\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: \u003cmikulas@artax.karlin.mff.cuni.cz\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7c0efc627738c840a685ea0f2c23d09aad7d5d3b", "tree": "e51573472f37260d57541bb4456ae1a948307cc7", "parents": [ "7903d9eed82db81c15ee8b4114187dfdcad7650f" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:09 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:56 2007 -0700" }, "message": "hfsplus: convert to new aops\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Roman Zippel \u003czippel@linux-m68k.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7903d9eed82db81c15ee8b4114187dfdcad7650f", "tree": "44037552fb748df45ff2ad60e5467b81bfaeee7a", "parents": [ "d7777a25a07e88fcfceb30f1a6f799e2ed87abb5" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:09 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:56 2007 -0700" }, "message": "hfs: convert to new aops\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Roman Zippel \u003czippel@linux-m68k.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d7777a25a07e88fcfceb30f1a6f799e2ed87abb5", "tree": "6aaee0ed9b821d5c189d411248f0c77e4d6e502d", "parents": [ "89e107877b65bf6eff1d63a1302dee9a091586f5" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:08 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "fat: convert to new aops\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: OGAWA Hirofumi \u003chirofumi@mail.parknet.co.jp\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "89e107877b65bf6eff1d63a1302dee9a091586f5", "tree": "8a120a04c46f19229d1cf9b9c546f1818cf84c44", "parents": [ "7765ec26ae1c01bb29bedf910e4efcced8cc81d2" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:07 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "fs: new cont helpers\n\nRework the generic block \"cont\" routines to handle the new aops. Supporting\ncont_prepare_write would take quite a lot of code to support, so remove it\ninstead (and we later convert all filesystems to use it).\n\nwrite_begin gets passed AOP_FLAG_CONT_EXPAND when called from\ngeneric_cont_expand, so filesystems can avoid the old hacks they used.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: OGAWA Hirofumi \u003chirofumi@mail.parknet.co.jp\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7765ec26ae1c01bb29bedf910e4efcced8cc81d2", "tree": "8ce0e877daf805e5e546f10b389cd1c686ec0365", "parents": [ "d79689c7038ea07182e8d7340786f7fcf8c77780" ], "author": { "name": "Steven Whitehouse", "email": "swhiteho@redhat.com", "time": "Tue Oct 16 01:25:07 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "gfs2: convert to new aops\n\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Steven Whitehouse \u003cswhiteho@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d79689c7038ea07182e8d7340786f7fcf8c77780", "tree": "8275c8ab209a8ecd03838f41e42228b053de00af", "parents": [ "bfc1af650a8f36feba6b90a6c398325f885c00bc" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:06 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "xfs: convert to new aops\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: David Chinner \u003cdgc@sgi.com\u003e\nCc: Timothy Shimmin \u003ctes@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "bfc1af650a8f36feba6b90a6c398325f885c00bc", "tree": "c7db5bbfad01d2c18533e7a128027e26d1992a42", "parents": [ "f4fc66a894546bdc88a775d0e83ad20a65210bcb" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:05 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "ext4: convert to new aops\n\nConvert ext4 to use write_begin()/write_end() methods.\n\nSigned-off-by: Badari Pulavarty \u003cpbadari@us.ibm.com\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Dmitriy Monakhov \u003cdmonakhov@sw.ru\u003e\nCc: Mark Fasheh \u003cmark.fasheh@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f4fc66a894546bdc88a775d0e83ad20a65210bcb", "tree": "87d725ad4e579eb353f615eab26dbf705e2e4bc2", "parents": [ "f34fb6eccc962e4137b77c4bbe1e9a31d27a30e6" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:05 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "ext3: convert to new aops\n\nVarious fixes and improvements\n\nSigned-off-by: Badari Pulavarty \u003cpbadari@us.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": "f34fb6eccc962e4137b77c4bbe1e9a31d27a30e6", "tree": "58fd363d892ee2d341a17e52a297632a10219af9", "parents": [ "6272b5a5868f3d5fbf9815f9984891ced343dabc" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:04 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "ext2: convert to new aops\n\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": "6272b5a5868f3d5fbf9815f9984891ced343dabc", "tree": "350eb309221242119901f1f4fcdb04a52abaea36", "parents": [ "800d15a53e7d14fa26495b7b95d3bfe7877dd69d" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:04 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "block_dev: convert to new aops\n\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": "800d15a53e7d14fa26495b7b95d3bfe7877dd69d", "tree": "09a59e32043f1b601b73ad6105e7634679337884", "parents": [ "674b892ede247ef4fb8d00918f02e29c32b9bbaf" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:03 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "implement simple fs aops\n\nImplement new aops for some of the simpler filesystems.\n\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": "674b892ede247ef4fb8d00918f02e29c32b9bbaf", "tree": "8e170040e64073932ba559cc31f3ec9802337406", "parents": [ "8268f5a7415d914fc855a86aa2284ac819dc6b2e" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:03 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "mm: restore KERNEL_DS optimisations\n\nRestore the KERNEL_DS optimisation, especially helpful to the 2copy write\npath.\n\nThis may be a pretty questionable gain in most cases, especially after the\nlegacy 2copy write path is removed, but it doesn\u0027t cost much.\n\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": "8268f5a7415d914fc855a86aa2284ac819dc6b2e", "tree": "13628a6d3cb31f04472c4cccdc741979ecdf0ad0", "parents": [ "afddba49d18f346e5cc2938b6ed7c512db18ca68" ], "author": { "name": "Dmitry Monakhov", "email": "dmonakhov@sw.ru", "time": "Tue Oct 16 01:25:02 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "deny partial write for loop dev fd\n\nPartial write can be easily supported by LO_CRYPT_NONE mode, but it is not\neasy in LO_CRYPT_CRYPTOAPI case, because of its block nature. I don\u0027t know\nwho still used cryptoapi, but theoretically it is possible. So let\u0027s leave\nthings as they are. Loop device doesn\u0027t support partial write before\nNick\u0027s \"write_begin/write_end\" patch set, and let\u0027s it behave the same way\nafter.\n\nSigned-off-by: Dmitriy Monakhov \u003cdmonakhov@openvz.org\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "afddba49d18f346e5cc2938b6ed7c512db18ca68", "tree": "4726e3d3b0e9e8e5b5d3b2b0cccb36446bbdf3ca", "parents": [ "637aff46f94a754207c80c8c64bf1b74f24b967d" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:01 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "fs: introduce write_begin, write_end, and perform_write aops\n\nThese are intended to replace prepare_write and commit_write with more\nflexible alternatives that are also able to avoid the buffered write\ndeadlock problems efficiently (which prepare_write is unable to do).\n\n[mark.fasheh@oracle.com: API design contributions, code review and fixes]\n[akpm@linux-foundation.org: various fixes]\n[dmonakhov@sw.ru: new aop block_write_begin fix]\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Mark Fasheh \u003cmark.fasheh@oracle.com\u003e\nSigned-off-by: Dmitriy Monakhov \u003cdmonakhov@openvz.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "637aff46f94a754207c80c8c64bf1b74f24b967d", "tree": "837fb3196236998c3c3ae44762ed3167ef0256f4", "parents": [ "2f718ffc16c43a435d12919c75dbfad518abd056" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:25:00 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "fs: fix data-loss on error\n\nNew buffers against uptodate pages are simply be marked uptodate, while the\nbuffer_new bit remains set. This causes error-case code to zero out parts of\nthose buffers because it thinks they contain stale data: wrong, they are\nactually uptodate so this is a data loss situation.\n\nFix this by actually clearning buffer_new and marking the buffer dirty. It\nmakes sense to always clear buffer_new before setting a buffer uptodate.\n\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": "2f718ffc16c43a435d12919c75dbfad518abd056", "tree": "55588cb2815d844e9d0b2404cf8ceafe98b5c55d", "parents": [ "08291429cfa6258c4cd95d8833beb40f828b194e" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:24:59 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:55 2007 -0700" }, "message": "mm: buffered write iterator\n\nAdd an iterator data structure to operate over an iovec. Add usercopy\noperators needed by generic_file_buffered_write, and convert that function\nover.\n\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": "08291429cfa6258c4cd95d8833beb40f828b194e", "tree": "50a206f0f0e7a5400b44073107ff00517e6f50ac", "parents": [ "4a9e5ef1f4f15205e477817a5cefc34bd3f65f55" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:24:59 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "mm: fix pagecache write deadlocks\n\nModify the core write() code so that it won\u0027t take a pagefault while holding a\nlock on the pagecache page. There are a number of different deadlocks possible\nif we try to do such a thing:\n\n1. generic_buffered_write\n2. lock_page\n3. prepare_write\n4. unlock_page+vmtruncate\n5. copy_from_user\n6. mmap_sem(r)\n7. handle_mm_fault\n8. lock_page (filemap_nopage)\n9. commit_write\n10. unlock_page\n\na. sys_munmap / sys_mlock / others\nb. mmap_sem(w)\nc. make_pages_present\nd. get_user_pages\ne. handle_mm_fault\nf. lock_page (filemap_nopage)\n\n2,8\t- recursive deadlock if page is same\n2,8;2,8\t- ABBA deadlock is page is different\n2,6;b,f\t- ABBA deadlock if page is same\n\nThe solution is as follows:\n1. If we find the destination page is uptodate, continue as normal, but use\n atomic usercopies which do not take pagefaults and do not zero the uncopied\n tail of the destination. The destination is already uptodate, so we can\n commit_write the full length even if there was a partial copy: it does not\n matter that the tail was not modified, because if it is dirtied and written\n back to disk it will not cause any problems (uptodate *means* that the\n destination page is as new or newer than the copy on disk).\n\n1a. The above requires that fault_in_pages_readable correctly returns access\n information, because atomic usercopies cannot distinguish between\n non-present pages in a readable mapping, from lack of a readable mapping.\n\n2. If we find the destination page is non uptodate, unlock it (this could be\n made slightly more optimal), then allocate a temporary page to copy the\n source data into. Relock the destination page and continue with the copy.\n However, instead of a usercopy (which might take a fault), copy the data\n from the pinned temporary page via the kernel address space.\n\n(also, rename maxlen to seglen, because it was confusing)\n\nThis increases the CPU/memory copy cost by almost 50% on the affected\nworkloads. That will be solved by introducing a new set of pagecache write\naops in a subsequent patch.\n\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": "4a9e5ef1f4f15205e477817a5cefc34bd3f65f55", "tree": "51f52086ecbccc3f41955d8d12293ef7a566a05b", "parents": [ "eb2be189317d031895b5ca534fbf735eb546158b" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:24:58 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "mm: write iovec cleanup\n\nHide some of the open-coded nr_segs tests into the iovec helpers. This is all\nto simplify generic_file_buffered_write, because that gets more complex in the\nnext patch.\n\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": "eb2be189317d031895b5ca534fbf735eb546158b", "tree": "8f1eda7af3be7285244a6f1ad77682e90d403c7b", "parents": [ "64649a58919e66ec21792dbb6c48cb3da22cbd7f" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:24:57 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "mm: buffered write cleanup\n\nQuite a bit of code is used in maintaining these \"cached pages\" that are\nprobably pretty unlikely to get used. It would require a narrow race where\nthe page is inserted concurrently while this process is allocating a page\nin order to create the spare page. Then a multi-page write into an uncached\npart of the file, to make use of it.\n\nNext, the buffered write path (and others) uses its own LRU pagevec when it\nshould be just using the per-CPU LRU pagevec (which will cut down on both data\nand code size cacheline footprint). Also, these private LRU pagevecs are\nemptied after just a very short time, in contrast with the per-CPU pagevecs\nthat are persistent. Net result: 7.3 times fewer lru_lock acquisitions required\nto add the pages to pagecache for a bulk write (in 4K chunks).\n\n[this gets rid of some cond_resched() calls in readahead.c and mpage.c due\n to clashes in -mm. What put them there, and why? ]\n\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": "64649a58919e66ec21792dbb6c48cb3da22cbd7f", "tree": "054605b7da7bad43c299ef66de9d33fda87cd38d", "parents": [ "5fe172370687e03cc6ba8dca990b75db18ff9bb3" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:24:56 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "mm: trim more holes\n\nIf prepare_write fails with AOP_TRUNCATED_PAGE, or if commit_write fails, then\nwe may have failed the write operation despite prepare_write having\ninstantiated blocks past i_size. Fix this, and consolidate the trimming into\none place.\n\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": "5fe172370687e03cc6ba8dca990b75db18ff9bb3", "tree": "8ce000fee15fa9ccd4313018f7f9ab1ffbc8cdaa", "parents": [ "ae37461c70bc8c8416cad1bab13a9898ed030aa1" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:24:56 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "mm: debug write deadlocks\n\nAllow CONFIG_DEBUG_VM to switch off the prefaulting logic, to simulate the\nMakes the race much easier to hit.\n\nThis is useful for demonstration and testing purposes, but is removed in a\nsubsequent patch.\n\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": "ae37461c70bc8c8416cad1bab13a9898ed030aa1", "tree": "7ba24faab6f89651fd2b3d33563847764744d544", "parents": [ "6814d7a91289ceb143285975e244a8f00fd3a830" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Tue Oct 16 01:24:55 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "mm: clean up buffered write code\n\nRename some variables and fix some types.\n\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\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": "6814d7a91289ceb143285975e244a8f00fd3a830", "tree": "e439e5d802d6ebaa73bac8b08c311ca60d4c8ee4", "parents": [ "4b49643fbb3fa8bf4910f82be02d45e94e8972a4" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Tue Oct 16 01:24:54 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "Revert \"[PATCH] generic_file_buffered_write(): deadlock on vectored write\"\n\nThis reverts commit 6527c2bdf1f833cc18e8f42bd97973d583e4aa83, which\nfixed the following bug:\n\n When prefaulting in the pages in generic_file_buffered_write(), we only\n faulted in the pages for the firts segment of the iovec. If the second of\n successive segment described a mmapping of the page into which we\u0027re\n write()ing, and that page is not up-to-date, the fault handler tries to lock\n the already-locked page (to bring it up to date) and deadlocks.\n\n An exploit for this bug is in writev-deadlock-demo.c, in\n http://www.zip.com.au/~akpm/linux/patches/stuff/ext3-tools.tar.gz.\n\n (These demos assume blocksize \u003c PAGE_CACHE_SIZE).\n\nThe problem with this fix is that it takes the kernel back to doing a single\nprepare_write()/commit_write() per iovec segment. So in the worst case we\u0027ll\nrun prepare_write+commit_write 1024 times where we previously would have run\nit once. The other problem with the fix is that it fix all the locking problems.\n\n\u003cinsert numbers obtained via ext3-tools\u0027s writev-speed.c here\u003e\n\nAnd apparently this change killed NFS overwrite performance, because, I\nsuppose, it talks to the server for each prepare_write+commit_write.\n\nSo just back that patch out - we\u0027ll be fixing the deadlock by other means.\n\nNick says: also it only ever actually papered over the bug, because after\nfaulting in the pages, they might be unmapped or reclaimed.\n\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": "4b49643fbb3fa8bf4910f82be02d45e94e8972a4", "tree": "ee3bc7881a1e0b71fa093254bb725ad467d8ef72", "parents": [ "41cb8ac025dbbf6782eae10d231e7e2336ad3724" ], "author": { "name": "Andrew Morton", "email": "akpm@osdl.org", "time": "Tue Oct 16 01:24:54 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "Revert \"[PATCH] generic_file_buffered_write(): handle zero-length iovec segments\"\n\nThis reverts commit 81b0c8713385ce1b1b9058e916edcf9561ad76d6, which was\na bugfix against 6527c2bdf1f833cc18e8f42bd97973d583e4aa83 (\"[PATCH]\ngeneric_file_buffered_write(): deadlock on vectored write\"), which we\nalso revert.\n\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\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": "41cb8ac025dbbf6782eae10d231e7e2336ad3724", "tree": "0070e26ee574338a4a3f56f574e1c126a4357c8e", "parents": [ "902aaed0d983dfd459fcb2b678608d4584782200" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:24:53 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "mm: revert KERNEL_DS buffered write optimisation\n\nRevert the patch from Neil Brown to optimise NFSD writev handling.\n\nCc: Neil Brown \u003cneilb@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": "902aaed0d983dfd459fcb2b678608d4584782200", "tree": "00b18597d87101ba1b37e5dcfde1d91312870160", "parents": [ "754af6f5a85fcd1ecb456851d20c65e4c6ce10ab" ], "author": { "name": "Hisashi Hifumi", "email": "hifumi.hisashi@oss.ntt.co.jp", "time": "Tue Oct 16 01:24:52 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "mm: use pagevec to rotate reclaimable page\n\nWhile running some memory intensive load, system response deteriorated just\nafter swap-out started.\n\nThe cause of this problem is that when a PG_reclaim page is moved to the tail\nof the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is\nacquired every page writeback . This deteriorates system performance and\nmakes interrupt hold off time longer when swap-out started.\n\nFollowing patch solves this problem. I use pagevec in rotating reclaimable\npages to mitigate LRU spin lock contention and reduce interrupt hold off time.\n\nI did a test that allocating and touching pages in multiple processes, and\npinging to the test machine in flooding mode to measure response under memory\nintensive load.\n\nThe test result is:\n\n\t-2.6.23-rc5\n\t--- testmachine ping statistics ---\n\t3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms\n\trtt min/avg/max/mdev \u003d 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma\n17.746/0.092 ms\n\n\t-2.6.23-rc5-patched\n\t--- testmachine ping statistics ---\n\t3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms\n\trtt min/avg/max/mdev \u003d 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma\n17.314/0.091 ms\n\nMax round-trip-time was improved.\n\nThe test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled)\n8GB memory , 8GB swap.\n\nI did ping test again to observe performance deterioration caused by taking\na ref.\n\n\t-2.6.23-rc6-with-modifiedpatch\n\t--- testmachine ping statistics ---\n\t3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms\n\trtt min/avg/max/mdev \u003d 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms\n\nThe result for my original patch is as follows.\n\n\t-2.6.23-rc5-with-originalpatch\n\t--- testmachine ping statistics ---\n\t3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms\n\trtt min/avg/max/mdev \u003d 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms\n\nThe influence to response was small.\n\n[akpm@linux-foundation.org: fix uninitalised var warning]\n[hugh@veritas.com: fix locking]\n[randy.dunlap@oracle.com: fix function declaration]\n[hugh@veritas.com: fix BUG at include/linux/mm.h:220!]\n[hugh@veritas.com: kill redundancy in rotate_reclaimable_page]\n[hugh@veritas.com: move_tail_pages into lru_add_drain]\nSigned-off-by: Hisashi Hifumi \u003chifumi.hisashi@oss.ntt.co.jp\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "754af6f5a85fcd1ecb456851d20c65e4c6ce10ab", "tree": "8c985bfd704a8c993d6ca992725969c6fc5c9e5a", "parents": [ "32a4330d4156e55a4888a201f484dbafed9504ed" ], "author": { "name": "Lee Schermerhorn", "email": "Lee.Schermerhorn@hp.com", "time": "Tue Oct 16 01:24:51 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "Mem Policy: add MPOL_F_MEMS_ALLOWED get_mempolicy() flag\n\nAllow an application to query the memories allowed by its context.\n\nUpdated numa_memory_policy.txt to mention that applications can use this to\nobtain allowed memories for constructing valid policies.\n\nTODO: update out-of-tree libnuma wrapper[s], or maybe add a new\nwrapper--e.g., numa_get_mems_allowed() ?\n\nAlso, update numa syscall man pages.\n\nTested with memtoy V\u003e\u003d0.13.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Andi Kleen \u003cak@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": "32a4330d4156e55a4888a201f484dbafed9504ed", "tree": "1339473dab0fe493dc9feb59833cdf23cf2b1780", "parents": [ "8691f3a72f32f8b3ed535faa27140b3ae293c90b" ], "author": { "name": "Rik van Riel", "email": "riel@redhat.com", "time": "Tue Oct 16 01:24:50 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "mm: prevent kswapd from freeing excessive amounts of lowmem\n\nThe current VM can get itself into trouble fairly easily on systems with a\nsmall ZONE_HIGHMEM, which is common on i686 computers with 1GB of memory.\n\nOn one side, page_alloc() will allocate down to zone-\u003epages_low, while on\nthe other side, kswapd() and balance_pgdat() will try to free memory from\nevery zone, until every zone has more free pages than zone-\u003epages_high.\n\nHighmem can be filled up to zone-\u003epages_low with page tables, ramfs,\nvmalloc allocations and other unswappable things quite easily and without\nmany bad side effects, since we still have a huge ZONE_NORMAL to do future\nallocations from.\n\nHowever, as long as the number of free pages in the highmem zone is below\nzone-\u003epages_high, kswapd will continue swapping things out from\nZONE_NORMAL, too!\n\nSami Farin managed to get his system into a stage where kswapd had freed\nabout 700MB of low memory and was still \"going strong\".\n\nThe attached patch will make kswapd stop paging out data from zones when\nthere is more than enough memory free. We do go above zone-\u003epages_high in\norder to keep pressure between zones equal in normal circumstances, but the\npatch should prevent the kind of excesses that made Sami\u0027s computer totally\nunusable.\n\nSigned-off-by: Rik van Riel \u003criel@redhat.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "8691f3a72f32f8b3ed535faa27140b3ae293c90b", "tree": "78ed23998e99de2fb4fb5b135c1fa4ad70612ef0", "parents": [ "26fb1589cb0aaec3a0b4418c54f30c1a2b1781f6" ], "author": { "name": "Jesper Juhl", "email": "jesper.juhl@gmail.com", "time": "Tue Oct 16 01:24:49 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "mm: no need to cast vmalloc() return value in zone_wait_table_init()\n\nvmalloc() returns a void pointer, so there\u0027s no need to cast its\nreturn value in mm/page_alloc.c::zone_wait_table_init().\n\nSigned-off-by: Jesper Juhl \u003cjesper.juhl@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "26fb1589cb0aaec3a0b4418c54f30c1a2b1781f6", "tree": "1486600f31a6f1387f4f5db276684f0b727eec89", "parents": [ "a4b0672db3a698d0684ee6e54f44e2e162a3da1b" ], "author": { "name": "Jeff Moyer", "email": "jmoyer@redhat.com", "time": "Tue Oct 16 01:24:49 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "fix the max path calculation in radix-tree.c\n\nA while back, Nick Piggin introduced a patch to reduce the node memory\nusage for small files (commit cfd9b7df4abd3257c9e381b0e445817b26a51c0c):\n\n-#define RADIX_TREE_MAP_SHIFT\t6\n+#define RADIX_TREE_MAP_SHIFT\t(CONFIG_BASE_SMALL ? 4 : 6)\n\nUnfortunately, he didn\u0027t take into account the fact that the\ncalculation of the maximum path was based on an assumption of having\nto round up:\n\n#define RADIX_TREE_MAX_PATH (RADIX_TREE_INDEX_BITS/RADIX_TREE_MAP_SHIFT + 2)\n\nSo, if CONFIG_BASE_SMALL is set, you will end up with a\nRADIX_TREE_MAX_PATH that is one greater than necessary. The practical\nupshot of this is just a bit of wasted memory (one long in the\nheight_to_maxindex array, an extra pre-allocated radix tree node per\ncpu, and extra stack usage in a couple of functions), but it seems\nworth getting right.\n\nIt\u0027s also worth noting that I never build with CONFIG_BASE_SMALL.\nWhat I did to test this was duplicate the code in a small user-space\nprogram and check the results of the calculations for max path and the\ncontents of the height_to_maxindex array.\n\nSigned-off-by: Jeff Moyer \u003cjmoyer@redhat.com\u003e\nAcked-by: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a4b0672db3a698d0684ee6e54f44e2e162a3da1b", "tree": "d53c52b251856520b0fd02969bfcdd4b5d332da6", "parents": [ "68671f35fe8d785277118a333c88768a4f894917" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Oct 16 01:24:48 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "fs: fix nobh error handling\n\nnobh mode error handling is not just pretty slack, it\u0027s wrong.\n\nOne cannot zero out the whole page to ensure new blocks are zeroed, because\nit just brings the whole page \"uptodate\" with zeroes even if that may not\nbe the correct uptodate data. Also, other parts of the page may already\ncontain dirty data which would get lost by zeroing it out. Thirdly, the\nwriteback of zeroes to the new blocks will also erase existing blocks. All\nthese conditions are pagecache and/or filesystem corruption.\n\nThe problem comes about because we didn\u0027t keep track of which buffers\nactually are new or old. However it is not enough just to keep only this\nstate, because at the point we start dirtying parts of the page (new\nblocks, with zeroes), the handling of IO errors becomes impossible without\nbuffers because the page may only be partially uptodate, in which case the\npage flags allone cannot capture the state of the parts of the page.\n\nSo allocate all buffers for the page upfront, but leave them unattached so\nthat they don\u0027t pick up any other references and can be freed when we\u0027re\ndone. If the error path is hit, then zero the new buffers as the regular\nbuffer path does, then attach the buffers to the page so that it can\nactually be written out correctly and be subject to the normal IO error\nhandling paths.\n\nAs an upshot, we save 1K of kernel stack on ia64 or powerpc 64K page\nsystems.\n\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" } ], "next": "68671f35fe8d785277118a333c88768a4f894917" }