)]}' { "log": [ { "commit": "66f0dc481e5b802ab363b979fc1753410c7d82b5", "tree": "9f8609685f07d410bc6536a0d3e47e366edf93d4", "parents": [ "75c85a0bc13367aabb36e8208d4e373b022b43b3" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Wed Dec 30 20:17:34 2009 +0000" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 30 12:23:27 2009 -0800" }, "message": "mm: move sys_mmap_pgoff from util.c\n\nMove sys_mmap_pgoff() from mm/util.c to mm/mmap.c and mm/nommu.c,\nwhere we\u0027d expect to find such code: especially now that it contains\nthe MAP_HUGETLB handling. Revert mm/util.c to how it was in 2.6.32.\n\nThis patch just ignores MAP_HUGETLB in the nommu case, as in 2.6.32,\nwhereas 2.6.33-rc2 reported -ENOSYS. Perhaps validate_mmap_request()\nshould reject it with -EINVAL? Add that later if necessary.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "c9d0bf241451a3ab7d02e1652c22b80cd7d93e8f", "tree": "f72d7eedf3fee82193407c7190321399833f422c", "parents": [ "62c0c2f198c1f2ead05c961e83ef486c45888325" ], "author": { "name": "Magnus Damm", "email": "damm@opensource.se", "time": "Mon Dec 14 17:59:49 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:21 2009 -0800" }, "message": "mm: uncached vma support with writenotify\n\nModify the generic mmap() code to keep the cache attribute in\nvma-\u003evm_page_prot regardless if writenotify is enabled or not. Without\nthis patch the cache configuration selected by f_op-\u003emmap() is overwritten\nif writenotify is enabled, making it impossible to keep the vma uncached.\n\nNeeded by drivers such as drivers/video/sh_mobile_lcdcfb.c which uses\ndeferred io together with uncached memory.\n\nSigned-off-by: Magnus Damm \u003cdamm@opensource.se\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: Jaya Kumar \u003cjayakumar.lkml@gmail.com\u003e\nCc: Arnd Bergmann \u003carnd@arndb.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "659ace584e7a9fdda872eab4d6d7be1e0afb6cae", "tree": "e9d8ca3d7429bfa48e823a6f105d76254e34daf0", "parents": [ "bb86a7338b7a864c03e1736a8d370b10254b0300" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Dec 14 17:57:56 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:11 2009 -0800" }, "message": "mmap: don\u0027t return ENOMEM when mapcount is temporarily exceeded in munmap()\n\nOn ia64, the following test program exit abnormally, because glibc thread\nlibrary called abort().\n\n \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n (gdb) bt\n #0 0xa000000000010620 in __kernel_syscall_via_break ()\n #1 0x20000000003208e0 in raise () from /lib/libc.so.6.1\n #2 0x2000000000324090 in abort () from /lib/libc.so.6.1\n #3 0x200000000027c3e0 in __deallocate_stack () from /lib/libpthread.so.0\n #4 0x200000000027f7c0 in start_thread () from /lib/libpthread.so.0\n #5 0x200000000047ef60 in __clone2 () from /lib/libc.so.6.1\n \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n\nThe fact is, glibc call munmap() when thread exitng time for freeing\nstack, and it assume munlock() never fail. However, munmap() often make\nvma splitting and it with many mapcount make -ENOMEM.\n\nOh well, that\u0027s crazy, because stack unmapping never increase mapcount.\nThe maxcount exceeding is only temporary. internal temporary exceeding\nshouldn\u0027t make ENOMEM.\n\nThis patch does it.\n\n test_max_mapcount.c\n \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n #include\u003cstdio.h\u003e\n #include\u003cstdlib.h\u003e\n #include\u003cstring.h\u003e\n #include\u003cpthread.h\u003e\n #include\u003cerrno.h\u003e\n #include\u003cunistd.h\u003e\n\n #define THREAD_NUM 30000\n #define MAL_SIZE (8*1024*1024)\n\n void *wait_thread(void *args)\n {\n \tvoid *addr;\n\n \taddr \u003d malloc(MAL_SIZE);\n \tsleep(10);\n\n \treturn NULL;\n }\n\n void *wait_thread2(void *args)\n {\n \tsleep(60);\n\n \treturn NULL;\n }\n\n int main(int argc, char *argv[])\n {\n \tint i;\n \tpthread_t thread[THREAD_NUM], th;\n \tint ret, count \u003d 0;\n \tpthread_attr_t attr;\n\n \tret \u003d pthread_attr_init(\u0026attr);\n \tif(ret) {\n \t\tperror(\"pthread_attr_init\");\n \t}\n\n \tret \u003d pthread_attr_setdetachstate(\u0026attr, PTHREAD_CREATE_DETACHED);\n \tif(ret) {\n \t\tperror(\"pthread_attr_setdetachstate\");\n \t}\n\n \tfor (i \u003d 0; i \u003c THREAD_NUM; i++) {\n \t\tret \u003d pthread_create(\u0026th, \u0026attr, wait_thread, NULL);\n \t\tif(ret) {\n \t\t\tfprintf(stderr, \"[%d] \", count);\n \t\t\tperror(\"pthread_create\");\n \t\t} else {\n \t\t\tprintf(\"[%d] create OK.\\n\", count);\n \t\t}\n \t\tcount++;\n\n \t\tret \u003d pthread_create(\u0026thread[i], \u0026attr, wait_thread2, NULL);\n \t\tif(ret) {\n \t\t\tfprintf(stderr, \"[%d] \", count);\n \t\t\tperror(\"pthread_create\");\n \t\t} else {\n \t\t\tprintf(\"[%d] create OK.\\n\", count);\n \t\t}\n \t\tcount++;\n \t}\n\n \tsleep(3600);\n \treturn 0;\n }\n \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n\n[akpm@linux-foundation.org: coding-style fixes]\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "2c6a10161d0b5fc047b5bd81b03693b9af99fab5", "tree": "298916728f640d1ae156a6dfc855b1c8f6c46e37", "parents": [ "9206de95b1ea68357996ec02be5db0638a0de2c1" ], "author": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Thu Dec 03 19:40:46 2009 -0500" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Fri Dec 11 06:44:58 2009 -0500" }, "message": "switch do_brk() to get_unmapped_area()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "9206de95b1ea68357996ec02be5db0638a0de2c1", "tree": "e32b41a06a8465af0e8cfa0660b517930cc2fea5", "parents": [ "8c7b49b3ecd48923eb64ff57e07a1cdb74782970" ], "author": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Thu Dec 03 15:23:11 2009 -0500" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Fri Dec 11 06:44:58 2009 -0500" }, "message": "Take arch_mmap_check() into get_unmapped_area()\n\nAcked-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "8c7b49b3ecd48923eb64ff57e07a1cdb74782970", "tree": "3bb2335ccaa34ef227459800c2221e71cf6b1987", "parents": [ "f8b7256096a20436f6d0926747e3ac3d64c81d24" ], "author": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Mon Nov 30 20:12:03 2009 -0500" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Fri Dec 11 06:44:57 2009 -0500" }, "message": "fix a struct file leak in do_mmap_pgoff()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "6c21a7fb492bf7e2c4985937082ce58ddeca84bd", "tree": "6cfe11ba4b8eee26ee8b02d2b4a5fcc6ea07e4bd", "parents": [ "6e8e16c7bc298d7887584c3d027e05db3e86eed9" ], "author": { "name": "Mimi Zohar", "email": "zohar@linux.vnet.ibm.com", "time": "Thu Oct 22 17:30:13 2009 -0400" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Sun Oct 25 12:22:48 2009 +0800" }, "message": "LSM: imbed ima calls in the security hooks\n\nBased on discussions on LKML and LSM, where there are consecutive\nsecurity_ and ima_ calls in the vfs layer, move the ima_ calls to\nthe existing security_ hooks.\n\nSigned-off-by: Mimi Zohar \u003czohar@us.ibm.com\u003e\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "f0f37e2f77731b3473fa6bd5ee53255d9a9cdb40", "tree": "3c26d3ed1a453156e9c208ccb5567a8954dba064", "parents": [ "6f5071020d5ec89b5d095aa488db604adb921aec" ], "author": { "name": "Alexey Dobriyan", "email": "adobriyan@gmail.com", "time": "Sun Sep 27 22:29:37 2009 +0400" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Sep 27 11:39:25 2009 -0700" }, "message": "const: mark struct vm_struct_operations\n\n* mark struct vm_area_struct::vm_ops as const\n* mark vm_ops in AGP code\n\nBut leave TTM code alone, something is fishy there with global vm_ops\nbeing used.\n\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4e52780d41a741fb4861ae1df2413dd816ec11b1", "tree": "b3722349661ed0ce87841b110f568616892cf719", "parents": [ "90f72aa58bbf076b68e289fbd71eb829bc505923" ], "author": { "name": "Eric B Munson", "email": "ebmunson@us.ibm.com", "time": "Mon Sep 21 17:03:47 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:42 2009 -0700" }, "message": "hugetlb: add MAP_HUGETLB for mmaping pseudo-anonymous huge page regions\n\nAdd a flag for mmap that will be used to request a huge page region that\nwill look like anonymous memory to userspace. This is accomplished by\nusing a file on the internal vfsmount. MAP_HUGETLB is a modifier of\nMAP_ANONYMOUS and so must be specified with it. The region will behave\nthe same as a MAP_ANONYMOUS region using small pages.\n\n[akpm@linux-foundation.org: fix arch definitions of MAP_HUGETLB]\nSigned-off-by: Eric B Munson \u003cebmunson@us.ibm.com\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Adam Litke \u003cagl@us.ibm.com\u003e\nCc: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Arnd Bergmann \u003carnd@arndb.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f8dbf0a7a4c5d98e8b70da9f7f4f6a89f3b7a7bb", "tree": "1f40d51f39965017999c36e3a5ae78b67e43f5d5", "parents": [ "252c5f94d944487e9f50ece7942b0fbf659c5c31" ], "author": { "name": "Huang Shijie", "email": "shijie8@gmail.com", "time": "Mon Sep 21 17:03:41 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:41 2009 -0700" }, "message": "mmap: save some cycles for the shared anonymous mapping\n\nshmem_zero_setup() does not change vm_start, pgoff or vm_flags, only some\ndrivers change them (such as /driver/video/bfin-t350mcqb-fb.c).\n\nMove these codes to a more proper place to save cycles for shared\nanonymous mapping.\n\nSigned-off-by: Huang Shijie \u003cshijie8@gmail.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nAcked-by: Hugh Dickins \u003chugh.dickins@tiscali.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": "252c5f94d944487e9f50ece7942b0fbf659c5c31", "tree": "0dd21bdb968ce5bd3f30fadce261984d3b1abf98", "parents": [ "3f96b79ad96263cc0ece7bb340cddf9b2ddfb1b3" ], "author": { "name": "Lee Schermerhorn", "email": "Lee.Schermerhorn@hp.com", "time": "Mon Sep 21 17:03:40 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:41 2009 -0700" }, "message": "mmap: avoid unnecessary anon_vma lock acquisition in vma_adjust()\n\nWe noticed very erratic behavior [throughput] with the AIM7 shared\nworkload running on recent distro [SLES11] and mainline kernels on an\n8-socket, 32-core, 256GB x86_64 platform. On the SLES11 kernel\n[2.6.27.19+] with Barcelona processors, as we increased the load [10s of\nthousands of tasks], the throughput would vary between two \"plateaus\"--one\nat ~65K jobs per minute and one at ~130K jpm. The simple patch below\ncauses the results to smooth out at the ~130k plateau.\n\nBut wait, there\u0027s more:\n\nWe do not see this behavior on smaller platforms--e.g., 4 socket/8 core.\nThis could be the result of the larger number of cpus on the larger\nplatform--a scalability issue--or it could be the result of the larger\nnumber of interconnect \"hops\" between some nodes in this platform and how\nthe tasks for a given load end up distributed over the nodes\u0027 cpus and\nmemories--a stochastic NUMA effect.\n\nThe variability in the results are less pronounced [on the same platform]\nwith Shanghai processors and with mainline kernels. With 31-rc6 on\nShanghai processors and 288 file systems on 288 fibre attached storage\nvolumes, the curves [jpm vs load] are both quite flat with the patched\nkernel consistently producing ~3.9% better throughput [~80K jpm vs ~77K\njpm] than the unpatched kernel.\n\nProfiling indicated that the \"slow\" runs were incurring high[er]\ncontention on an anon_vma lock in vma_adjust(), apparently called from the\nsbrk() system call.\n\nThe patch:\n\nA comment in mm/mmap.c:vma_adjust() suggests that we don\u0027t really need the\nanon_vma lock when we\u0027re only adjusting the end of a vma, as is the case\nfor brk(). The comment questions whether it\u0027s worth while to optimize for\nthis case. Apparently, on the newer, larger x86_64 platforms, with\ninteresting NUMA topologies, it is worth while--especially considering\nthat the patch [if correct!] is quite simple.\n\nWe can detect this condition--no overlap with next vma--by noting a NULL\n\"importer\". The anon_vma pointer will also be NULL in this case, so\nsimply avoid loading vma-\u003eanon_vma to avoid the lock.\n\nHowever, we DO need to take the anon_vma lock when we\u0027re inserting a vma\n[\u0027insert\u0027 non-NULL] even when we have no overlap [NULL \"importer\"], so we\nneed to check for \u0027insert\u0027, as well. And Hugh points out that we should\nalso take it when adjusting vm_start (so that rmap.c can rely upon\nvma_address() while it holds the anon_vma lock).\n\nakpm: Zhang Yanmin reprts a 150% throughput improvement with aim7, so it\nmight be -stable material even though thiss isn\u0027t a regression: \"this\nissue is not clear on dual socket Nehalem machine (2*4*2 cpu), but is\nsevere on large machine (4*8*2 cpu)\"\n\n[hugh.dickins@tiscali.co.uk: test vma start too]\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Eric Whitney \u003ceric.whitney@hp.com\u003e\nTested-by: \"Zhang, Yanmin\" \u003cyanmin_zhang@linux.intel.com\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "cdf7b3418ad5a8783efe8f9124023d9b869fec0f", "tree": "0504a26ba5d7cbbaa71bdd2911d55c6934de8be5", "parents": [ "03f6462a3ae78f36eb1f0ee8b4d5ae2f7859c1d5" ], "author": { "name": "Huang Shijie", "email": "shijie8@gmail.com", "time": "Mon Sep 21 17:03:36 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:41 2009 -0700" }, "message": "mmap: remove unnecessary code\n\nIf (flags \u0026 MAP_LOCKED) is true, it means vm_flags has already contained\nthe bit VM_LOCKED which is set by calc_vm_flag_bits().\n\nSo there is no need to reset it again, just remove it.\n\nSigned-off-by: Huang Shijie \u003cshijie8@gmail.com\u003e\nAcked-by: Hugh Dickins \u003chugh.dickins@tiscali.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": "a913e182ab9484308e870af37a14d372742d53b0", "tree": "0fca5598aeba4c53999ec46b6b82b46f9a981965", "parents": [ "8314c4f24a0a5c9b1f7544e9fa83a1d5367ddaa7" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Sep 21 17:02:26 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:33 2009 -0700" }, "message": "ksm: clean up obsolete references\n\nA few cleanups, given the munlock fix: the comment on ksm_test_exit() no\nlonger applies, and it can be made private to ksm.c; there\u0027s no more\nreference to mmu_gather or tlb.h, and mmap.c doesn\u0027t need ksm.h.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nAcked-by: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@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": "8314c4f24a0a5c9b1f7544e9fa83a1d5367ddaa7", "tree": "f3265e2ff817e447c11b9f9070ce1eed9a19731a", "parents": [ "7701c9c0f54feb682d0cefa2ae1f4a1e00e0ba09" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Sep 21 17:02:25 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:33 2009 -0700" }, "message": "ksm: remove VM_MERGEABLE_FLAGS\n\nKSM originally stood for Kernel Shared Memory: but the kernel has long\nsupported shared memory, and VM_SHARED and VM_MAYSHARE vmas, and KSM is\nsomething else. So we switched to saying \"merge\" instead of \"share\".\n\nBut Chris Wright points out that this is confusing where mmap.c merges\nadjacent vmas: most especially in the name VM_MERGEABLE_FLAGS, used by\nis_mergeable_vma() to let vmas be merged despite flags being different.\n\nCall it VMA_MERGE_DESPITE_FLAGS? Perhaps, but at present it consists\nonly of VM_CAN_NONLINEAR: so for now it\u0027s clearer on all sides to use\nthat directly, with a comment on it in is_mergeable_vma().\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nAcked-by: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@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": "1c2fb7a4c2ca7a958b02bc1e615d0254990bba8d", "tree": "489a97bd453b8002f2234f7e736548103315fa38", "parents": [ "9ba6929480088a85c1ff60a4b1f1c9fc80dbd2b7" ], "author": { "name": "Andrea Arcangeli", "email": "aarcange@redhat.com", "time": "Mon Sep 21 17:02:22 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:32 2009 -0700" }, "message": "ksm: fix deadlock with munlock in exit_mmap\n\nRawhide users have reported hang at startup when cryptsetup is run: the\nsame problem can be simply reproduced by running a program int main() {\nmlockall(MCL_CURRENT | MCL_FUTURE); return 0; }\n\nThe problem is that exit_mmap() applies munlock_vma_pages_all() to\nclean up VM_LOCKED areas, and its current implementation (stupidly)\ntries to fault in absent pages, for example where PROT_NONE prevented\nthem being faulted in when mlocking. Whereas the \"ksm: fix oom\ndeadlock\" patch, knowing there\u0027s a race by which KSM might try to fault\nin pages after exit_mmap() had finally zapped the range, backs out of\nsuch faults doing nothing when its ksm_test_exit() notices mm_users 0.\n\nSo revert that part of \"ksm: fix oom deadlock\" which moved the\nksm_exit() call from before exit_mmap() to the middle of exit_mmap();\nand remove those ksm_test_exit() checks from the page fault paths, so\nallowing the munlocking to proceed without interference.\n\nksm_exit, if there are rmap_items still chained on this mm slot, takes\nmmap_sem write side: so preventing KSM from working on an mm while\nexit_mmap runs. And KSM will bail out as soon as it notices that\nmm_users is already zero, thanks to its internal ksm_test_exit checks.\nSo that when a task is killed by OOM killer or the user, KSM will not\nindefinitely prevent it from running exit_mmap to release its memory.\n\nThis does break a part of what \"ksm: fix oom deadlock\" was trying to\nachieve. When unmerging KSM (echo 2 \u003e/sys/kernel/mm/ksm), and even\nwhen ksmd itself has to cancel a KSM page, it is possible that the\nfirst OOM-kill victim would be the KSM process being faulted: then its\nmemory won\u0027t be freed until a second victim has been selected (freeing\nmemory for the unmerging fault to complete).\n\nBut the OOM killer is already liable to kill a second victim once the\nintended victim\u0027s p-\u003emm goes to NULL: so there\u0027s not much point in\nrejecting this KSM patch before fixing that OOM behaviour. It is very\nmuch more important to allow KSM users to boot up, than to haggle over\nan unlikely and poorly supported OOM case.\n\nWe also intend to fix munlocking to not fault pages: at which point\nthis patch _could_ be reverted; though that would be controversial, so\nwe hope to find a better solution.\n\nSigned-off-by: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nAcked-by: Justin M. Forbes \u003cjforbes@redhat.com\u003e\nAcked-for-now-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@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": "9ba6929480088a85c1ff60a4b1f1c9fc80dbd2b7", "tree": "39aab8cdffae598b55e35c578f70820712286ab4", "parents": [ "cd551f97519d35855be5a8720a47cc802ee4fd06" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Sep 21 17:02:20 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:32 2009 -0700" }, "message": "ksm: fix oom deadlock\n\nThere\u0027s a now-obvious deadlock in KSM\u0027s out-of-memory handling:\nimagine ksmd or KSM_RUN_UNMERGE handling, holding ksm_thread_mutex,\ntrying to allocate a page to break KSM in an mm which becomes the\nOOM victim (quite likely in the unmerge case): it\u0027s killed and goes\nto exit, and hangs there waiting to acquire ksm_thread_mutex.\n\nClearly we must not require ksm_thread_mutex in __ksm_exit, simple\nthough that made everything else: perhaps use mmap_sem somehow?\nAnd part of the answer lies in the comments on unmerge_ksm_pages:\n__ksm_exit should also leave all the rmap_item removal to ksmd.\n\nBut there\u0027s a fundamental problem, that KSM relies upon mmap_sem to\nguarantee the consistency of the mm it\u0027s dealing with, yet exit_mmap\ntears down an mm without taking mmap_sem. And bumping mm_users won\u0027t\nhelp at all, that just ensures that the pages the OOM killer assumes\nare on their way to being freed will not be freed.\n\nThe best answer seems to be, to move the ksm_exit callout from just\nbefore exit_mmap, to the middle of exit_mmap: after the mm\u0027s pages\nhave been freed (if the mmu_gather is flushed), but before its page\ntables and vma structures have been freed; and down_write,up_write\nmmap_sem there to serialize with KSM\u0027s own reliance on mmap_sem.\n\nBut KSM then needs to be careful, whenever it downs mmap_sem, to\ncheck that the mm is not already exiting: there\u0027s a danger of using\nfind_vma on a layout that\u0027s being torn apart, or writing into page\ntables which have been freed for reuse; and even do_anonymous_page\nand __do_fault need to check they\u0027re not being called by break_ksm\nto reinstate a pte after zap_pte_range has zapped that page table.\n\nThough it might be clearer to add an exiting flag, set while holding\nmmap_sem in __ksm_exit, that wouldn\u0027t cover the issue of reinstating\na zapped pte. All we need is to check whether mm_users is 0 - but\nmust remember that ksmd may detect that before __ksm_exit is reached.\nSo, ksm_test_exit(mm) added to comment such checks on mm-\u003emm_users.\n\n__ksm_exit now has to leave clearing up the rmap_items to ksmd,\nthat needs ksm_thread_mutex; but shift the exiting mm just after the\nksm_scan cursor so that it will soon be dealt with. __ksm_enter raise\nmm_count to hold the mm_struct, ksmd\u0027s exit processing (exactly like\nits processing when it finds all VM_MERGEABLEs unmapped) mmdrop it,\nsimilar procedure for KSM_RUN_UNMERGE (which has stopped ksmd).\n\nBut also give __ksm_exit a fast path: when there\u0027s no complication\n(no rmap_items attached to mm and it\u0027s not at the ksm_scan cursor),\nit can safely do all the exiting work itself. This is not just an\noptimization: when ksmd is not running, the raised mm_count would\notherwise leak mm_structs.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nAcked-by: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@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": "cdd6c482c9ff9c55475ee7392ec8f672eddb7be6", "tree": "81f98a3ab46c589792057fe2392c1e10f8ad7893", "parents": [ "dfc65094d0313cc48969fa60bcf33d693aeb05a7" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Sep 21 12:02:48 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Sep 21 14:28:04 2009 +0200" }, "message": "perf: Do the big rename: Performance Counters -\u003e Performance Events\n\nBye-bye Performance Counters, welcome Performance Events!\n\nIn the past few months the perfcounters subsystem has grown out its\ninitial role of counting hardware events, and has become (and is\nbecoming) a much broader generic event enumeration, reporting, logging,\nmonitoring, analysis facility.\n\nNaming its core object \u0027perf_counter\u0027 and naming the subsystem\n\u0027perfcounters\u0027 has become more and more of a misnomer. With pending\ncode like hw-breakpoints support the \u0027counter\u0027 name is less and\nless appropriate.\n\nAll in one, we\u0027ve decided to rename the subsystem to \u0027performance\nevents\u0027 and to propagate this rename through all fields, variables\nand API names. (in an ABI compatible fashion)\n\nThe word \u0027event\u0027 is also a bit shorter than \u0027counter\u0027 - which makes\nit slightly more convenient to write/handle as well.\n\nThanks goes to Stephane Eranian who first observed this misnomer and\nsuggested a rename.\n\nUser-space tooling and ABI compatibility is not affected - this patch\nshould be function-invariant. (Also, defconfigs were not touched to\nkeep the size down.)\n\nThis patch has been generated via the following script:\n\n FILES\u003d$(find * -type f | grep -vE \u0027oprofile|[^K]config\u0027)\n\n sed -i \\\n -e \u0027s/PERF_EVENT_/PERF_RECORD_/g\u0027 \\\n -e \u0027s/PERF_COUNTER/PERF_EVENT/g\u0027 \\\n -e \u0027s/perf_counter/perf_event/g\u0027 \\\n -e \u0027s/nb_counters/nb_events/g\u0027 \\\n -e \u0027s/swcounter/swevent/g\u0027 \\\n -e \u0027s/tpcounter_event/tp_event/g\u0027 \\\n $FILES\n\n for N in $(find . -name perf_counter.[ch]); do\n M\u003d$(echo $N | sed \u0027s/perf_counter/perf_event/g\u0027)\n mv $N $M\n done\n\n FILES\u003d$(find . -name perf_event.*)\n\n sed -i \\\n -e \u0027s/COUNTER_MASK/REG_MASK/g\u0027 \\\n -e \u0027s/COUNTER/EVENT/g\u0027 \\\n -e \u0027s/\\\u003cevent\\\u003e/event_id/g\u0027 \\\n -e \u0027s/counter/event/g\u0027 \\\n -e \u0027s/Counter/Event/g\u0027 \\\n $FILES\n\n... to keep it as correct as possible. This script can also be\nused by anyone who has pending perfcounters patches - it converts\na Linux kernel tree over to the new naming. We tried to time this\nchange to the point in time where the amount of pending patches\nis the smallest: the end of the merge window.\n\nNamespace clashes were fixed up in a preparatory patch - and some\nstylistic fallout will be fixed up in a subsequent patch.\n\n( NOTE: \u0027counters\u0027 are still the proper terminology when we deal\n with hardware registers - and these sed scripts are a bit\n over-eager in renaming them. I\u0027ve undone some of that, but\n in case there\u0027s something left where \u0027counter\u0027 would be\n better than \u0027event\u0027 we can undo that on an individual basis\n instead of touching an otherwise nicely automated patch. )\n\nSuggested-by: Stephane Eranian \u003ceranian@google.com\u003e\nAcked-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nReviewed-by: Arjan van de Ven \u003carjan@linux.intel.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc: Kyle McMartin \u003ckyle@mcmartin.ca\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: \"H. Peter Anvin\" \u003chpa@zytor.com\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "27f5de7963f46388932472b660f2f9a86ab58454", "tree": "83bd98f83819ae9012ada5f077e59fcb18319769", "parents": [ "8f1ecc9fbc5b223e4f5d5bb8bcd6f5672c4bc4b6" ], "author": { "name": "Jianjun Kong", "email": "jianjun@zeuux.org", "time": "Thu Sep 17 19:26:26 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Sep 18 09:48:52 2009 -0700" }, "message": "mm: Fix problem of parameter in note\n\n\u0027current\u0027 is a pointer, so the right form is \u0027down_write(\u0026current-\u003emm-\u003emmap_sem)\u0027.\n\nSigned-off-by: Jianjun Kong \u003cjianjun@zeuux.org\u003e\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "788084aba2ab7348257597496befcbccabdc98a3", "tree": "2da42d746d67b16ef705229a1b5a3528ec19c725", "parents": [ "8cf948e744e0218af604c32edecde10006dc8e9e" ], "author": { "name": "Eric Paris", "email": "eparis@redhat.com", "time": "Fri Jul 31 12:54:11 2009 -0400" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Mon Aug 17 15:09:11 2009 +1000" }, "message": "Security/SELinux: seperate lsm specific mmap_min_addr\n\nCurrently SELinux enforcement of controls on the ability to map low memory\nis determined by the mmap_min_addr tunable. This patch causes SELinux to\nignore the tunable and instead use a seperate Kconfig option specific to how\nmuch space the LSM should protect.\n\nThe tunable will now only control the need for CAP_SYS_RAWIO and SELinux\npermissions will always protect the amount of low memory designated by\nCONFIG_LSM_MMAP_MIN_ADDR.\n\nThis allows users who need to disable the mmap_min_addr controls (usual reason\nbeing they run WINE as a non-root user) to do so and still have SELinux\ncontrols preventing confined domains (like a web server) from being able to\nmap some area of low memory.\n\nSigned-off-by: Eric Paris \u003ceparis@redhat.com\u003e\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "8a1ca8cedd108c8e76a6ab34079d0bbb4f244799", "tree": "636c715524f1718599209cc289908ea44b6cb859", "parents": [ "b640f042faa2a2fad6464f259a8afec06e2f6386", "940010c5a314a7bd9b498593bc6ba1718ac5aec5" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jun 11 14:01:07 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jun 11 14:01:07 2009 -0700" }, "message": "Merge branch \u0027perfcounters-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027perfcounters-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (574 commits)\n perf_counter: Turn off by default\n perf_counter: Add counter-\u003eid to the throttle event\n perf_counter: Better align code\n perf_counter: Rename L2 to LL cache\n perf_counter: Standardize event names\n perf_counter: Rename enums\n perf_counter tools: Clean up u64 usage\n perf_counter: Rename perf_counter_limit sysctl\n perf_counter: More paranoia settings\n perf_counter: powerpc: Implement generalized cache events for POWER processors\n perf_counters: powerpc: Add support for POWER7 processors\n perf_counter: Accurate period data\n perf_counter: Introduce struct for sample data\n perf_counter tools: Normalize data using per sample period data\n perf_counter: Annotate exit ctx recursion\n perf_counter tools: Propagate signals properly\n perf_counter tools: Small frequency related fixes\n perf_counter: More aggressive frequency adjustment\n perf_counter/x86: Fix the model number of Intel Core2 processors\n perf_counter, x86: Correct some event and umask values for Intel processors\n ...\n" }, { "commit": "089dd79db9264dc0da602bad45d42f1b3e7d1e07", "tree": "017b1efd0bc4f3d15b92ed6fae5dfc3d1b164872", "parents": [ "f7b6eb3fa07269da20dbbde8ba37a0273fdbd9c9" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Fri Jun 05 14:04:55 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jun 05 14:46:41 2009 +0200" }, "message": "perf_counter: Generate mmap events for install_special_mapping()\n\nIn order to track the vdso also generate mmap events for\ninstall_special_mapping().\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "d99e9446200c1ffab28cb0e39b76c34a2bfafd06", "tree": "10cd2f67f3bffaf8dcec79c197689f440faf9265", "parents": [ "60313ebed739b331e8e61079da27a11ee3b73a30" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Thu Jun 04 17:08:58 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jun 04 17:51:38 2009 +0200" }, "message": "perf_counter: Remove munmap stuff\n\nIn name of keeping it simple, only track mmap events. Userspace\nwill have to remove old overlapping maps when it encounters them.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "e0a94c2a63f2644826069044649669b5e7ca75d3", "tree": "debf8a9af6ac23dadd116dc1cd1f9dcefe9629c6", "parents": [ "7d2948b1248109dbc7f4aaf9867c54b1912d494c" ], "author": { "name": "Christoph Lameter", "email": "cl@linux-foundation.org", "time": "Wed Jun 03 16:04:31 2009 -0400" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Thu Jun 04 12:07:48 2009 +1000" }, "message": "security: use mmap_min_addr indepedently of security models\n\nThis patch removes the dependency of mmap_min_addr on CONFIG_SECURITY.\nIt also sets a default mmap_min_addr of 4096.\n\nmmapping of addresses below 4096 will only be possible for processes\nwith CAP_SYS_RAWIO.\n\nSigned-off-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nAcked-by: Eric Paris \u003ceparis@redhat.com\u003e\nLooks-ok-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "dc3f81b129b5439ba7bac265bbc6a51a39275dae", "tree": "216030731d911249496d2e97206cd61431e31c89", "parents": [ "d2517a49d55536b38c7a87e5289550cfedaa4dcc", "1406de8e11eb043681297adf86d6892ff8efc27a" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 18 07:37:44 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 18 07:37:49 2009 +0200" }, "message": "Merge commit \u0027v2.6.30-rc6\u0027 into perfcounters/core\n\nMerge reason: this branch was on an -rc4 base, merge it up to -rc6\n to get the latest upstream fixes.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "00a62ce91e554198ef28234c91c36f850f5a3bc9", "tree": "367ef134219deef91903c3fa0eb108c13658f2c7", "parents": [ "0763ed2355198cdef2f6a2098e9d52eb1fe4365d" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Thu Apr 30 15:08:51 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat May 02 15:36:10 2009 -0700" }, "message": "mm: fix Committed_AS underflow on large NR_CPUS environment\n\nThe Committed_AS field can underflow in certain situations:\n\n\u003e # while true; do cat /proc/meminfo | grep _AS; sleep 1; done | uniq -c\n\u003e 1 Committed_AS: 18446744073709323392 kB\n\u003e 11 Committed_AS: 18446744073709455488 kB\n\u003e 6 Committed_AS: 35136 kB\n\u003e 5 Committed_AS: 18446744073709454400 kB\n\u003e 7 Committed_AS: 35904 kB\n\u003e 3 Committed_AS: 18446744073709453248 kB\n\u003e 2 Committed_AS: 34752 kB\n\u003e 9 Committed_AS: 18446744073709453248 kB\n\u003e 8 Committed_AS: 34752 kB\n\u003e 3 Committed_AS: 18446744073709320960 kB\n\u003e 7 Committed_AS: 18446744073709454080 kB\n\u003e 3 Committed_AS: 18446744073709320960 kB\n\u003e 5 Committed_AS: 18446744073709454080 kB\n\u003e 6 Committed_AS: 18446744073709320960 kB\n\nBecause NR_CPUS can be greater than 1000 and meminfo_proc_show() does\nnot check for underflow.\n\nBut NR_CPUS proportional isn\u0027t good calculation. In general,\npossibility of lock contention is proportional to the number of online\ncpus, not theorical maximum cpus (NR_CPUS).\n\nThe current kernel has generic percpu-counter stuff. using it is right\nway. it makes code simplify and percpu_counter_read_positive() don\u0027t\nmake underflow issue.\n\nReported-by: Dave Hansen \u003cdave@linux.vnet.ibm.com\u003e\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Eric B Munson \u003cebmunson@us.ibm.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: \u003cstable@kernel.org\u003e\t\t[All kernel versions]\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e7fd5d4b3d240f42c30a9e3d20a4689c4d3a795a", "tree": "4ba588631dd8189a818a91c9e3976526071178b6", "parents": [ "1130b0296184bc21806225fd06d533515a99d2db", "56a50adda49b2020156616c4eb15353e0f9ad7de" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Apr 29 14:46:59 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Apr 29 14:47:05 2009 +0200" }, "message": "Merge branch \u0027linus\u0027 into perfcounters/core\n\nMerge reason: This brach was on -rc1, refresh it to almost-rc4 to pick up\n the latest upstream fixes.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "05fa199d45c54a9bda7aa3ae6537253d6f097aa9", "tree": "cfdcdd04bfcef7d0dcb47fad93ba8fa676349dd3", "parents": [ "05f54c13cd0c33694eec39a265475c5d6cf223cf" ], "author": { "name": "Hugh Dickins", "email": "hugh@veritas.com", "time": "Thu Apr 16 21:58:12 2009 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Apr 16 14:41:25 2009 -0700" }, "message": "mm: pass correct mm when growing stack\n\nTetsuo Handa reports seeing the WARN_ON(current-\u003emm \u003d\u003d NULL) in\nsecurity_vm_enough_memory(), when do_execve() is touching the\ntarget mm\u0027s stack, to set up its args and environment.\n\nYes, a UMH_NO_WAIT or UMH_WAIT_PROC call_usermodehelper() spawns\nan mm-less kernel thread to do the exec. And in any case, that\nvm_enough_memory check when growing stack ought to be done on the\ntarget mm, not on the execer\u0027s mm (though apart from the warning,\nit only makes a slight tweak to OVERCOMMIT_NEVER behaviour).\n\nReported-by: Tetsuo Handa \u003cpenguin-kernel@i-love.sakura.ne.jp\u003e\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: stable@kernel.org\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "0a4a93919bdc5cee48fe4367591e8e0449c1086c", "tree": "0f0d7ac3ee4f61c1e7e53f0ba4e3b01e0e4ac728", "parents": [ "195564390210977954fe4ef45b39cdee34f41b59" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Mar 30 19:07:05 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Apr 06 09:30:38 2009 +0200" }, "message": "perf_counter: executable mmap() information\n\nCurrently the profiling information returns userspace IPs but no way\nto correlate them to userspace code. Userspace could look into\n/proc/$pid/maps but that might not be current or even present anymore\nat the time of analyzing the IPs.\n\nTherefore provide means to track the mmap information and provide it\nin the output stream.\n\nXXX: only covers mmap()/munmap(), mremap() and mprotect() are missing.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nOrig-LKML-Reference: \u003c20090330171023.417259499@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "33e5d76979cf01e3834814fe0aea569d1d602c1a", "tree": "58a03e5da59db203245da10db144a4f6f61a83ba", "parents": [ "5482415a5ecc0cd791a5d885cc3db8281401078f" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Thu Apr 02 16:56:32 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Apr 02 19:04:48 2009 -0700" }, "message": "nommu: fix a number of issues with the per-MM VMA patch\n\nFix a number of issues with the per-MM VMA patch:\n\n (1) Make mmap_pages_allocated an atomic_long_t, just in case this is used on\n a NOMMU system with more than 2G pages. Makes no difference on a 32-bit\n system.\n\n (2) Report vma-\u003evm_pgoff * PAGE_SIZE as a 64-bit value, not a 32-bit value,\n lest it overflow.\n\n (3) Move the allocation of the vm_area_struct slab back for fork.c.\n\n (4) Use KMEM_CACHE() for both vm_area_struct and vm_region slabs.\n\n (5) Use BUG_ON() rather than if () BUG().\n\n (6) Make the default validate_nommu_regions() a static inline rather than a\n #define.\n\n (7) Make free_page_series()\u0027s objection to pages with a refcount !\u003d 1 more\n informative.\n\n (8) Adjust the __put_nommu_region() banner comment to indicate that the\n semaphore must be held for writing.\n\n (9) Limit the number of warnings about munmaps of non-mmapped regions.\n\nReported-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: David Howells \u003cdhowells@redhat.com\u003e\nCc: Greg Ungerer \u003cgerg@snapgear.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "703a3cd72817e99201cef84a8a7aecc60b2b3581", "tree": "3e943755178ff410694722bb031f523136fbc432", "parents": [ "df7f54c012b92ec93d56b68547351dcdf8a163d3", "8e0ee43bc2c3e19db56a4adaa9a9b04ce885cd84" ], "author": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Tue Mar 24 10:52:46 2009 +1100" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Tue Mar 24 10:52:46 2009 +1100" }, "message": "Merge branch \u0027master\u0027 into next\n" }, { "commit": "9480c53e9b2aa13a06283ffb96bb8f1873ac4e9a", "tree": "4d7949c56e6877f0aac372bebed379eda7b0e646", "parents": [ "3abdbf90a3ffb006108c831c56b092e35483b6ec" ], "author": { "name": "Jeremy Fitzhardinge", "email": "jeremy@goop.org", "time": "Wed Feb 11 13:04:41 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Feb 11 14:25:37 2009 -0800" }, "message": "mm: rearrange exit_mmap() to unlock before arch_exit_mmap\n\nChristophe Saout reported [in precursor to:\nhttp://marc.info/?l\u003dlinux-kernel\u0026m\u003d123209902707347\u0026w\u003d4]:\n\n\u003e Note that I also some a different issue with CONFIG_UNEVICTABLE_LRU.\n\u003e Seems like Xen tears down current-\u003emm early on process termination, so\n\u003e that __get_user_pages in exit_mmap causes nasty messages when the\n\u003e process had any mlocked pages. (in fact, it somehow manages to get into\n\u003e the swapping code and produces a null pointer dereference trying to get\n\u003e a swap token)\n\nJeremy explained:\n\nYes. In the normal case under Xen, an in-use pagetable is \"pinned\",\nmeaning that it is RO to the kernel, and all updates must go via hypercall\n(or writes are trapped and emulated, which is much the same thing). An\nunpinned pagetable is not currently in use by any process, and can be\ndirectly accessed as normal RW pages.\n\nAs an optimisation at process exit time, we unpin the pagetable as early\nas possible (switching the process to init_mm), so that all the normal\npagetable teardown can happen with direct memory accesses.\n\nThis happens in exit_mmap() -\u003e arch_exit_mmap(). The munlocking happens\na few lines below. The obvious thing to do would be to move\narch_exit_mmap() to below the munlock code, but I think we\u0027d want to\ncall it even if mm-\u003emmap is NULL, just to be on the safe side.\n\nThus, this patch:\n\nexit_mmap() needs to unlock any locked vmas before calling arch_exit_mmap,\nas the latter may switch the current mm to init_mm, which would cause the\nformer to fail.\n\nSigned-off-by: Jeremy Fitzhardinge \u003cjeremy.fitzhardinge@citrix.com\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christophe Saout \u003cchristophe@saout.de\u003e\nCc: Keir Fraser \u003ckeir.fraser@eu.citrix.com\u003e\nCc: Christophe Saout \u003cchristophe@saout.de\u003e\nCc: Alex Williamson \u003calex.williamson@hp.com\u003e\nCc: \u003cstable@kernel.org\u003e\t\t[2.6.28.x]\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "5a6fe125950676015f5108fb71b2a67441755003", "tree": "c985fac46de39392466c4917c497b50bdc9c0757", "parents": [ "4c098bcd55fad34dcf224bf8343db6a9ac58fc68" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Feb 10 14:02:27 2009 +0000" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Feb 10 10:48:42 2009 -0800" }, "message": "Do not account for the address space used by hugetlbfs using VM_ACCOUNT\n\nWhen overcommit is disabled, the core VM accounts for pages used by anonymous\nshared, private mappings and special mappings. It keeps track of VMAs that\nshould be accounted for with VM_ACCOUNT and VMAs that never had a reserve\nwith VM_NORESERVE.\n\nOvercommit for hugetlbfs is much riskier than overcommit for base pages\ndue to contiguity requirements. It avoids overcommiting on both shared and\nprivate mappings using reservation counters that are checked and updated\nduring mmap(). This ensures (within limits) that hugepages exist in the\nfuture when faults occurs or it is too easy to applications to be SIGKILLed.\n\nAs hugetlbfs makes its own reservations of a different unit to the base page\nsize, VM_ACCOUNT should never be set. Even if the units were correct, we would\ndouble account for the usage in the core VM and hugetlbfs. VM_NORESERVE may\nbe set because an application can request no reserves be made for hugetlbfs\nat the risk of getting killed later.\n\nWith commit fc8744adc870a8d4366908221508bb113d8b72ee, VM_NORESERVE and\nVM_ACCOUNT are getting unconditionally set for hugetlbfs-backed mappings. This\nbreaks the accounting for both the core VM and hugetlbfs, can trigger an\nOOM storm when hugepage pools are too small lockups and corrupted counters\notherwise are used. This patch brings hugetlbfs more in line with how the\ncore VM treats VM_NORESERVE but prevents VM_ACCOUNT being set.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "cb5629b10d64a8006622ce3a52bc887d91057d69", "tree": "7c06d8f30783115e3384721046258ce615b129c5", "parents": [ "8920d5ad6ba74ae8ab020e90cc4d976980e68701", "f01d1d546abb2f4028b5299092f529eefb01253a" ], "author": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Fri Feb 06 11:01:45 2009 +1100" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Fri Feb 06 11:01:45 2009 +1100" }, "message": "Merge branch \u0027master\u0027 into next\n\nConflicts:\n\tfs/namei.c\n\nManually merged per:\n\ndiff --cc fs/namei.c\nindex 734f2b5,bbc15c2..0000000\n--- a/fs/namei.c\n+++ b/fs/namei.c\n@@@ -860,9 -848,8 +849,10 @@@ static int __link_path_walk(const char\n \t\tnd-\u003eflags |\u003d LOOKUP_CONTINUE;\n \t\terr \u003d exec_permission_lite(inode);\n \t\tif (err \u003d\u003d -EAGAIN)\n- \t\t\terr \u003d vfs_permission(nd, MAY_EXEC);\n+ \t\t\terr \u003d inode_permission(nd-\u003epath.dentry-\u003ed_inode,\n+ \t\t\t\t\t MAY_EXEC);\n +\t\tif (!err)\n +\t\t\terr \u003d ima_path_check(\u0026nd-\u003epath, MAY_EXEC);\n \t\tif (err)\n \t\t\tbreak;\n\n@@@ -1525,14 -1506,9 +1509,14 @@@ int may_open(struct path *path, int acc\n \t\tflag \u0026\u003d ~O_TRUNC;\n \t}\n\n- \terror \u003d vfs_permission(nd, acc_mode);\n+ \terror \u003d inode_permission(inode, acc_mode);\n \tif (error)\n \t\treturn error;\n +\n- \terror \u003d ima_path_check(\u0026nd-\u003epath,\n++\terror \u003d ima_path_check(path,\n +\t\t\t acc_mode \u0026 (MAY_READ | MAY_WRITE | MAY_EXEC));\n +\tif (error)\n +\t\treturn error;\n \t/*\n \t * An append-only file must be opened in append mode for writing.\n \t */\n\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "6146f0d5e47ca4047ffded0fb79b6c25359b386c", "tree": "edd792e52ad56d4a5d3ac6caa8437d3283fc157e", "parents": [ "659aaf2bb5496a425ba14036b5b5900f593e4484" ], "author": { "name": "Mimi Zohar", "email": "zohar@linux.vnet.ibm.com", "time": "Wed Feb 04 09:06:57 2009 -0500" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Fri Feb 06 09:05:30 2009 +1100" }, "message": "integrity: IMA hooks\n\nThis patch replaces the generic integrity hooks, for which IMA registered\nitself, with IMA integrity hooks in the appropriate places directly\nin the fs directory.\n\nSigned-off-by: Mimi Zohar \u003czohar@us.ibm.com\u003e\nAcked-by: Serge Hallyn \u003cserue@us.ibm.com\u003e\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "fc8744adc870a8d4366908221508bb113d8b72ee", "tree": "755f4c4a1cc30567fde4e60c9cc5e6a889c360b0", "parents": [ "33bfad54b58cf05cfe6678c3ec9235d4bc8db4c2" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jan 31 15:08:56 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jan 31 15:08:56 2009 -0800" }, "message": "Stop playing silly games with the VM_ACCOUNT flag\n\nThe mmap_region() code would temporarily set the VM_ACCOUNT flag for\nanonymous shared mappings just to inform shmem_zero_setup() that it\nshould enable accounting for the resulting shm object. It would then\nclear the flag after calling -\u003emmap (for the /dev/zero case) or doing\nshmem_zero_setup() (for the MAP_ANON case).\n\nThis just resulted in vma merge issues, but also made for just\nunnecessary confusion. Use the already-existing VM_NORESERVE flag for\nthis instead, and let shmem_{zero|file}_setup() just figure it out from\nthat.\n\nThis also happens to make it obvious that the new DRI2 GEM layer uses a\nnon-reserving backing store for its object allocation - which is quite\npossibly not intentional. But since I didn\u0027t want to change semantics\nin this patch, I left it alone, and just updated the caller to use the\nnew flag semantics.\n\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "33bfad54b58cf05cfe6678c3ec9235d4bc8db4c2", "tree": "d6be0ff97effa23289b2566acf8e56a49aa5657e", "parents": [ "c01a25e7cf6dcb0fa69c155706d5dd1e76e53796" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jan 30 11:37:22 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jan 30 11:37:22 2009 -0800" }, "message": "Allow opportunistic merging of VM_CAN_NONLINEAR areas\n\nCommit de33c8db5910cda599899dd431cc30d7c1018cbf (\"Fix OOPS in\nmmap_region() when merging adjacent VM_LOCKED file segments\") unified\nthe vma merging of anonymous and file maps to just one place, which\nsimplified the code and fixed a use-after-free bug that could cause an\noops.\n\nBut by doing the merge opportunistically before even having called\n-\u003emmap() on the file method, it now compares two different \u0027vm_flags\u0027\nvalues: the pre-mmap() value of the new not-yet-formed vma, and previous\nmappings of the same file around it.\n\nAnd in doing so, it refused to merge the common file case, which adds a\nmarker to say \"I can be made non-linear\".\n\nThis fixes it by just adding a set of flags that don\u0027t have to match,\nbecause we know they are ok to merge. Currently it\u0027s only that single\nVM_CAN_NONLINEAR flag, but at least conceptually there could be others\nin the future.\n\nReported-and-acked-by: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Greg KH \u003cgregkh@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "de33c8db5910cda599899dd431cc30d7c1018cbf", "tree": "4ee9ba8685bae5d1719a3158284d0c197c83afde", "parents": [ "18e352e4a73465349711a9324767e1b2453383e2" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jan 29 17:46:42 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jan 29 17:46:42 2009 -0800" }, "message": "Fix OOPS in mmap_region() when merging adjacent VM_LOCKED file segments\n\nAs of commit ba470de43188cdbff795b5da43a1474523c6c2fb (\"map: handle\nmlocked pages during map, remap, unmap\") we now use the \u0027vma\u0027 variable\nat the end of mmap_region() to handle the page-in of newly mapped\nmlocked pages.\n\nHowever, if we merged adjacent vma\u0027s together, the vma we\u0027re using may\nbe stale. We historically consciously avoided using it after the merge\noperation, but that got overlooked when redoing the locked page\nhandling.\n\nThis commit simplifies mmap_region() by doing any vma merges early,\navoiding the issue entirely, and \u0027vma\u0027 will always be valid. As pointed\nout by Hugh Dickins, this depends on any drivers that change the page\noffset of flags to have set one of the VM_SPECIAL bits (so that they\ncannot trigger the early merge logic), but that\u0027s true in general.\n\nReported-and-tested-by: Maksim Yevmenkin \u003cmaksim.yevmenkin@gmail.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6a6160a7b5c27b3c38651baef92a14fa7072b3c1", "tree": "a4a7640bd12611c445dfc013f69ce307674d1b13", "parents": [ "64fd1de3d821659ac0a3004fd5ee1de59e64af30" ], "author": { "name": "Heiko Carstens", "email": "heiko.carstens@de.ibm.com", "time": "Wed Jan 14 14:14:15 2009 +0100" }, "committer": { "name": "Heiko Carstens", "email": "heiko.carstens@de.ibm.com", "time": "Wed Jan 14 14:15:23 2009 +0100" }, "message": "[CVE-2009-0029] System call wrappers part 13\n\nSigned-off-by: Heiko Carstens \u003cheiko.carstens@de.ibm.com\u003e\n" }, { "commit": "2ed7c03ec17779afb4fcfa3b8c61df61bd4879ba", "tree": "4e0fefd574bab5470a02edf439727f472a9663c6", "parents": [ "4c696ba7982501d43dea11dbbaabd2aa8a19cc42" ], "author": { "name": "Heiko Carstens", "email": "heiko.carstens@de.ibm.com", "time": "Wed Jan 14 14:13:54 2009 +0100" }, "committer": { "name": "Heiko Carstens", "email": "heiko.carstens@de.ibm.com", "time": "Wed Jan 14 14:15:14 2009 +0100" }, "message": "[CVE-2009-0029] Convert all system calls to return a long\n\nConvert all system calls to return a long. This should be a NOP since all\nconverted types should have the same size anyway.\nWith the exception of sys_exit_group which returned void. But that doesn\u0027t\nmatter since the system call doesn\u0027t return.\n\nSigned-off-by: Heiko Carstens \u003cheiko.carstens@de.ibm.com\u003e\n" }, { "commit": "8feae13110d60cc6287afabc2887366b0eb226c2", "tree": "b3188986faab70e753e00ea8670a11ba8ec844c0", "parents": [ "41836382ebb415d68d3ebc4525e78e871fe58baf" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Thu Jan 08 12:04:47 2009 +0000" }, "committer": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Thu Jan 08 12:04:47 2009 +0000" }, "message": "NOMMU: Make VMAs per MM as for MMU-mode linux\n\nMake VMAs per mm_struct as for MMU-mode linux. This solves two problems:\n\n (1) In SYSV SHM where nattch for a segment does not reflect the number of\n shmat\u0027s (and forks) done.\n\n (2) In mmap() where the VMA\u0027s vm_mm is set to point to the parent mm by an\n exec\u0027ing process when VM_EXECUTABLE is specified, regardless of the fact\n that a VMA might be shared and already have its vm_mm assigned to another\n process or a dead process.\n\nA new struct (vm_region) is introduced to track a mapped region and to remember\nthe circumstances under which it may be shared and the vm_list_struct structure\nis discarded as it\u0027s no longer required.\n\nThis patch makes the following additional changes:\n\n (1) Regions are now allocated with alloc_pages() rather than kmalloc() and\n with no recourse to __GFP_COMP, so the pages are not composite. Instead,\n each page has a reference on it held by the region. Anything else that is\n interested in such a page will have to get a reference on it to retain it.\n When the pages are released due to unmapping, each page is passed to\n put_page() and will be freed when the page usage count reaches zero.\n\n (2) Excess pages are trimmed after an allocation as the allocation must be\n made as a power-of-2 quantity of pages.\n\n (3) VMAs are added to the parent MM\u0027s R/B tree and mmap lists. As an MM may\n end up with overlapping VMAs within the tree, the VMA struct address is\n appended to the sort key.\n\n (4) Non-anonymous VMAs are now added to the backing inode\u0027s prio list.\n\n (5) Holes may be punched in anonymous VMAs with munmap(), releasing parts of\n the backing region. The VMA and region structs will be split if\n necessary.\n\n (6) sys_shmdt() only releases one attachment to a SYSV IPC shared memory\n segment instead of all the attachments at that addresss. Multiple\n shmat()\u0027s return the same address under NOMMU-mode instead of different\n virtual addresses as under MMU-mode.\n\n (7) Core dumping for ELF-FDPIC requires fewer exceptions for NOMMU-mode.\n\n (8) /proc/maps is now the global list of mapped regions, and may list bits\n that aren\u0027t actually mapped anywhere.\n\n (9) /proc/meminfo gains a line (tagged \"MmapCopy\") that indicates the amount\n of RAM currently allocated by mmap to hold mappable regions that can\u0027t be\n mapped directly. These are copies of the backing device or file if not\n anonymous.\n\nThese changes make NOMMU mode more similar to MMU mode. The downside is that\nNOMMU mode requires some extra memory to track things over NOMMU without this\npatch (VMAs are no longer shared, and there are now region structs).\n\nSigned-off-by: David Howells \u003cdhowells@redhat.com\u003e\nTested-by: Mike Frysinger \u003cvapier.adi@gmail.com\u003e\nAcked-by: Paul Mundt \u003clethal@linux-sh.org\u003e\n" }, { "commit": "dcd4a049b9751828c516c59709f3fdf50436df85", "tree": "126fe11368da94f0c2e11ed586a870fa1b02f0a6", "parents": [ "084f71ae5ceeb16734d8ac47559d3c718456a865" ], "author": { "name": "Johannes Weiner", "email": "hannes@cmpxchg.org", "time": "Tue Jan 06 14:40:31 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jan 06 15:59:10 2009 -0800" }, "message": "mm: check for no mmaps in exit_mmap()\n\nWhen dup_mmap() ooms we can end up with mm-\u003emmap \u003d\u003d NULL. The error\npath does mmput() and unmap_vmas() gets a NULL vma which it\ndereferences.\n\nIn exit_mmap() there is nothing to do at all for this case, we can\ncancel the callpath right there.\n\n[akpm@linux-foundation.org: add sorely-needed comment]\nSigned-off-by: Johannes Weiner \u003channes@cmpxchg.org\u003e\nReported-by: Akinobu Mita \u003cakinobu.mita@gmail.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "901608d9045146aec6f14a7777ea4b1501c379f0", "tree": "0155189f48479b920855dedccba6829363376d4d", "parents": [ "67d58ac47d25f7e2a105248a4aea6113131ab874" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Tue Jan 06 14:40:29 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jan 06 15:59:09 2009 -0800" }, "message": "mm: introduce get_mm_hiwater_xxx(), fix taskstats-\u003ehiwater_xxx accounting\n\nxacct_add_tsk() relies on do_exit()-\u003eupdate_hiwater_xxx() and uses\nmm-\u003ehiwater_xxx directly, this leads to 2 problems:\n\n- taskstats_user_cmd() can call fill_pid()-\u003exacct_add_tsk() at any\n moment before the task exits, so we should check the current values of\n rss/vm anyway.\n\n- do_exit()-\u003eupdate_hiwater_xxx() calls are racy. An exiting thread can\n be preempted right before mm-\u003ehiwater_xxx \u003d new_val, and another thread\n can use A_LOT of memory and exit in between. When the first thread\n resumes it can be the last thread in the thread group, in that case we\n report the wrong hiwater_xxx values which do not take A_LOT into\n account.\n\nIntroduce get_mm_hiwater_rss() and get_mm_hiwater_vm() helpers and change\nxacct_add_tsk() to use them. The first helper will also be used by\nrusage-\u003eru_maxrss accounting.\n\nKill do_exit()-\u003eupdate_hiwater_xxx() calls. Unless we are going to\ndecrease rss/vm there is no point to update mm-\u003ehiwater_xxx, and nobody\ncan look at this mm_struct when exit_mmap() actually unmaps the memory.\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nAcked-by: Hugh Dickins \u003chugh@veritas.com\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nAcked-by: Balbir Singh \u003cbalbir@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": "48aae42556e5ea1ba0d8ddab25352706577af2ed", "tree": "6a016f91627ce717f5f68f27f47a5771dc7058f8", "parents": [ "853ac43ab194f5051b27a55060215d696dc9480d" ], "author": { "name": "ZhenwenXu", "email": "helight.xu@gmail.com", "time": "Tue Jan 06 14:40:21 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jan 06 15:59:08 2009 -0800" }, "message": "mm/mmap.c: fix coding style\n\nFix a little of the coding style in mm/mmap.c\n\n[akpm@linux-foundation.org: cleanup]\nSigned-off-by: ZhenwenXu \u003chelight.xu@gmail.com\u003e\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "046c68842bce6b77509cf56e94a561029124b0ce", "tree": "1a355899ba92ce4059027264cf759986234a930c", "parents": [ "5641f1fde074651ce2488e93944cf05dedd9bf74" ], "author": { "name": "Alan Cox", "email": "alan@lxorguk.ukuu.org.uk", "time": "Mon Jan 05 14:06:29 2009 +0000" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 05 17:44:42 2009 -0800" }, "message": "mm: update my address\n\nSigned-off-by: Alan Cox \u003calan@redhat.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "1c1271850494f06b63ae6b485e2e1b9c27ffb2d1", "tree": "d077bacff7d7ce6a103e3627ca7c662d233a34f7", "parents": [ "08c1184fa2b785f23453b8cbb43f86b409cde3a6" ], "author": { "name": "Denys Vlasenko", "email": "vda.linux@googlemail.com", "time": "Wed Nov 12 01:24:41 2008 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Nov 12 10:37:48 2008 -0800" }, "message": "parisc: fix find_extend_vma() breakage\n\nThe STACK_GROWSUP case of stack expansion was missing a test for \u0027prev\u0027,\nwhich got removed by commit cb8f488c33539f096580e202f5438a809195008f\n(\"mmap.c: deinline a few functions\") by mistake.\n\nI found my original email in \"sent\" folder. The patch in that mail\ndoes NOT remove !prev. That change had beed added by someone else.\n\nOk, I think we are not much interested in who did it, let\u0027s\nfix it for good.\n\n[ \"It looks like this was caused by me fixing rejects. That was the\n fancy include-lots-of-context-so-it-wont-apply patch.\" - akpm ]\n\nReported-and-bisected-by: Helge Deller \u003cdeller@gmx.de\u003e\nSigned-off-by: Denys Vlasenko \u003cvda.linux@googlemail.com\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Jiri Kosina \u003cjkosina@suse.cz\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "731572d39fcd3498702eda4600db4c43d51e0b26", "tree": "f892907ae20539845f353d72d2a2bf202b67e007", "parents": [ "6c89161b10f5771ee0b51ada0fce0e8835e72ade" ], "author": { "name": "Alan Cox", "email": "alan@redhat.com", "time": "Wed Oct 29 14:01:20 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Oct 30 11:38:47 2008 -0700" }, "message": "nfsd: fix vm overcommit crash\n\nJunjiro R. Okajima reported a problem where knfsd crashes if you are\nusing it to export shmemfs objects and run strict overcommit. In this\nsituation the current-\u003emm based modifier to the overcommit goes through a\nNULL pointer.\n\nWe could simply check for NULL and skip the modifier but we\u0027ve caught\nother real bugs in the past from mm being NULL here - cases where we did\nneed a valid mm set up (eg the exec bug about a year ago).\n\nTo preserve the checks and get the logic we want shuffle the checking\naround and add a new helper to the vm_ security wrappers\n\nAlso fix a current-\u003emm reference in nommu that should use the passed mm\n\n[akpm@linux-foundation.org: coding-style fixes]\n[akpm@linux-foundation.org: fix build]\nReported-by: Junjiro R. Okajima \u003chooanon05@yahoo.co.jp\u003e\nAcked-by: James Morris \u003cjmorris@namei.org\u003e\nSigned-off-by: Alan Cox \u003calan@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": "cb8f488c33539f096580e202f5438a809195008f", "tree": "888b60a8638774d50ba897526e24b25ccc28c30f", "parents": [ "51b07fc3c5c830bb49c80fc5eac041e1f66a72e7" ], "author": { "name": "Denys Vlasenko", "email": "vda.linux@googlemail.com", "time": "Sat Oct 18 20:27:01 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Oct 20 08:52:32 2008 -0700" }, "message": "mmap.c: deinline a few functions\n\n__vma_link_file and expand_downwards functions are not small, yeat they\nare marked inline. They probably had one callsite sometime in the past,\nbut now they have more. In order to prevent similar thing, I also\ndeinlined expand_upwards, despite it having only pne callsite. Nowadays\ngcc auto-inlines such static functions anyway. In find_extend_vma, I\nremoved one extra level of indirection.\n\nPatch is deliberately generated with -U $BIGNUM to make\nit easier to see that functions are big.\n\nResult:\n\n# size */*/mmap.o */vmlinux\n text data bss dec hex filename\n 9514 188 16 9718 25f6 0.org/mm/mmap.o\n 9237 188 16 9441 24e1 deinline/mm/mmap.o\n6124402 858996 389480 7372878 70804e 0.org/vmlinux\n6124113 858996 389480 7372589 707f2d deinline/vmlinux\n\nSigned-off-by: Denys Vlasenko \u003cvda.linux@googlemail.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ba470de43188cdbff795b5da43a1474523c6c2fb", "tree": "0477460fa8c3e61edd9f1534cd2193656e586f8b", "parents": [ "8edb08caf68184fb170f4f69c7445929e199eaea" ], "author": { "name": "Rik van Riel", "email": "riel@redhat.com", "time": "Sat Oct 18 20:26:50 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Oct 20 08:52:31 2008 -0700" }, "message": "mmap: handle mlocked pages during map, remap, unmap\n\nOriginally by Nick Piggin \u003cnpiggin@suse.de\u003e\n\nRemove mlocked pages from the LRU using \"unevictable infrastructure\"\nduring mmap(), munmap(), mremap() and truncate(). Try to move back to\nnormal LRU lists on munmap() when last mlocked mapping removed. Remove\nPageMlocked() status when page truncated from file.\n\n[akpm@linux-foundation.org: cleanup]\n[kamezawa.hiroyu@jp.fujitsu.com: fix double unlock_page()]\n[kosaki.motohiro@jp.fujitsu.com: split LRU: munlock rework]\n[lee.schermerhorn@hp.com: mlock: fix __mlock_vma_pages_range comment block]\n[akpm@linux-foundation.org: remove bogus kerneldoc token]\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Rik van Riel \u003criel@redhat.com\u003e\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamewzawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b291f000393f5a0b679012b39d79fbc85c018233", "tree": "28eb785d4d157d3396e4377294e6054635a4bd90", "parents": [ "89e004ea55abe201b29e2d6e35124101f1288ef7" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Sat Oct 18 20:26:44 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Oct 20 08:52:30 2008 -0700" }, "message": "mlock: mlocked pages are unevictable\n\nMake sure that mlocked pages also live on the unevictable LRU, so kswapd\nwill not scan them over and over again.\n\nThis is achieved through various strategies:\n\n1) add yet another page flag--PG_mlocked--to indicate that\n the page is locked for efficient testing in vmscan and,\n optionally, fault path. This allows early culling of\n unevictable pages, preventing them from getting to\n page_referenced()/try_to_unmap(). Also allows separate\n accounting of mlock\u0027d pages, as Nick\u0027s original patch\n did.\n\n Note: Nick\u0027s original mlock patch used a PG_mlocked\n flag. I had removed this in favor of the PG_unevictable\n flag + an mlock_count [new page struct member]. I\n restored the PG_mlocked flag to eliminate the new\n count field.\n\n2) add the mlock/unevictable infrastructure to mm/mlock.c,\n with internal APIs in mm/internal.h. This is a rework\n of Nick\u0027s original patch to these files, taking into\n account that mlocked pages are now kept on unevictable\n LRU list.\n\n3) update vmscan.c:page_evictable() to check PageMlocked()\n and, if vma passed in, the vm_flags. Note that the vma\n will only be passed in for new pages in the fault path;\n and then only if the \"cull unevictable pages in fault\n path\" patch is included.\n\n4) add try_to_unlock() to rmap.c to walk a page\u0027s rmap and\n ClearPageMlocked() if no other vmas have it mlocked.\n Reuses as much of try_to_unmap() as possible. This\n effectively replaces the use of one of the lru list links\n as an mlock count. If this mechanism let\u0027s pages in mlocked\n vmas leak through w/o PG_mlocked set [I don\u0027t know that it\n does], we should catch them later in try_to_unmap(). One\n hopes this will be rare, as it will be relatively expensive.\n\nOriginal mm/internal.h, mm/rmap.c and mm/mlock.c changes:\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\n\nsplitlru: introduce __get_user_pages():\n\n New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.\n because current get_user_pages() can\u0027t grab PROT_NONE pages theresore it\n cause PROT_NONE pages can\u0027t munlock.\n\n[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]\n[akpm@linux-foundation.org: untangle patch interdependencies]\n[akpm@linux-foundation.org: fix things after out-of-order merging]\n[hugh@veritas.com: fix page-flags mess]\n[lee.schermerhorn@hp.com: fix munlock page table walk - now requires \u0027mm\u0027]\n[kosaki.motohiro@jp.fujitsu.com: build fix]\n[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]\n[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nSigned-off-by: Rik van Riel \u003criel@redhat.com\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Dave Hansen \u003cdave@linux.vnet.ibm.com\u003e\nCc: Matt Mackall \u003cmpm@selenic.com\u003e\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ce36394269ccd9d1d286d6192ba09fa6894365e9", "tree": "fb235ff6ea1363ae4fd933e29268e76cdade5682", "parents": [ "d210baf53b699fc61aa891c177b71d7082d3b957" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Wed Sep 03 16:09:47 2008 +0200" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Sep 03 19:58:53 2008 -0700" }, "message": "mmap: fix petty bug in anonymous shared mmap offset handling\n\nAnonymous mappings should ignore offset but shared anonymous mapping\nforgot to clear it and makes the following legit test program trigger\nSIGBUS.\n\n #include \u003csys/mman.h\u003e\n #include \u003cstdio.h\u003e\n #include \u003cerrno.h\u003e\n\n #define PAGE_SIZE\t4096\n\n int main(void)\n {\n\t char *p;\n\t int i;\n\n\t p \u003d mmap(NULL, 2 * PAGE_SIZE, PROT_READ|PROT_WRITE,\n\t\t MAP_SHARED|MAP_ANONYMOUS, -1, PAGE_SIZE);\n\t if (p \u003d\u003d MAP_FAILED) {\n\t\t perror(\"mmap\");\n\t\t return 1;\n\t }\n\n\t for (i \u003d 0; i \u003c 2; i++) {\n\t\t printf(\"page %d\\n\", i);\n\t\t p[i * 4096] \u003d i;\n\t }\n\t return 0;\n }\n\nFix it.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nAcked-by: Hugh Dickins \u003chugh@veritas.com\u003e\nAcked-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "23a0ee908cbfba3264d19729c67c22b20fa73886", "tree": "541103f6283cbac6b82cff88a7b91128acfce046", "parents": [ "cc7a486cac78f6fc1a24e8cd63036bae8d2ab431", "0f2bc27be27ca1dcc66b96131e44bf7648b959c6" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 12 00:11:49 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 12 00:11:49 2008 +0200" }, "message": "Merge branch \u0027core/locking\u0027 into core/urgent\n" }, { "commit": "7cd5a02f54f4c9d16cf7fdffa2122bc73bb09b43", "tree": "05b0be34c4dd02899c4f771e89795780465810a6", "parents": [ "454ed842d55740160334efc9ad56cfef54ed37bc" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Aug 11 09:30:25 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Aug 11 09:30:25 2008 +0200" }, "message": "mm: fix mm_take_all_locks() locking order\n\nLockdep spotted:\n\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n[ INFO: possible circular locking dependency detected ]\n2.6.27-rc1 #270\n-------------------------------------------------------\nqemu-kvm/2033 is trying to acquire lock:\n (\u0026inode-\u003ei_data.i_mmap_lock){----}, at: [\u003cffffffff802996cc\u003e] mm_take_all_locks+0xc2/0xea\n\nbut task is already holding lock:\n (\u0026anon_vma-\u003elock){----}, at: [\u003cffffffff8029967a\u003e] mm_take_all_locks+0x70/0xea\n\nwhich lock already depends on the new lock.\n\nthe existing dependency chain (in reverse order) is:\n\n-\u003e #1 (\u0026anon_vma-\u003elock){----}:\n [\u003cffffffff8025cd37\u003e] __lock_acquire+0x11be/0x14d2\n [\u003cffffffff8025d0a9\u003e] lock_acquire+0x5e/0x7a\n [\u003cffffffff804c655b\u003e] _spin_lock+0x3b/0x47\n [\u003cffffffff8029a2ef\u003e] vma_adjust+0x200/0x444\n [\u003cffffffff8029a662\u003e] split_vma+0x12f/0x146\n [\u003cffffffff8029bc60\u003e] mprotect_fixup+0x13c/0x536\n [\u003cffffffff8029c203\u003e] sys_mprotect+0x1a9/0x21e\n [\u003cffffffff8020c0db\u003e] system_call_fastpath+0x16/0x1b\n [\u003cffffffffffffffff\u003e] 0xffffffffffffffff\n\n-\u003e #0 (\u0026inode-\u003ei_data.i_mmap_lock){----}:\n [\u003cffffffff8025ca54\u003e] __lock_acquire+0xedb/0x14d2\n [\u003cffffffff8025d397\u003e] lock_release_non_nested+0x1c2/0x219\n [\u003cffffffff8025d515\u003e] lock_release+0x127/0x14a\n [\u003cffffffff804c6403\u003e] _spin_unlock+0x1e/0x50\n [\u003cffffffff802995d9\u003e] mm_drop_all_locks+0x7f/0xb0\n [\u003cffffffff802a965d\u003e] do_mmu_notifier_register+0xe2/0x112\n [\u003cffffffff802a96a8\u003e] mmu_notifier_register+0xe/0x10\n [\u003cffffffffa0043b6b\u003e] kvm_dev_ioctl+0x11e/0x287 [kvm]\n [\u003cffffffff802bd0ca\u003e] vfs_ioctl+0x2a/0x78\n [\u003cffffffff802bd36f\u003e] do_vfs_ioctl+0x257/0x274\n [\u003cffffffff802bd3e1\u003e] sys_ioctl+0x55/0x78\n [\u003cffffffff8020c0db\u003e] system_call_fastpath+0x16/0x1b\n [\u003cffffffffffffffff\u003e] 0xffffffffffffffff\n\nother info that might help us debug this:\n\n5 locks held by qemu-kvm/2033:\n #0: (\u0026mm-\u003emmap_sem){----}, at: [\u003cffffffff802a95d0\u003e] do_mmu_notifier_register+0x55/0x112\n #1: (mm_all_locks_mutex){--..}, at: [\u003cffffffff8029963e\u003e] mm_take_all_locks+0x34/0xea\n #2: (\u0026anon_vma-\u003elock){----}, at: [\u003cffffffff8029967a\u003e] mm_take_all_locks+0x70/0xea\n #3: (\u0026anon_vma-\u003elock){----}, at: [\u003cffffffff8029967a\u003e] mm_take_all_locks+0x70/0xea\n #4: (\u0026anon_vma-\u003elock){----}, at: [\u003cffffffff8029967a\u003e] mm_take_all_locks+0x70/0xea\n\nstack backtrace:\nPid: 2033, comm: qemu-kvm Not tainted 2.6.27-rc1 #270\n\nCall Trace:\n [\u003cffffffff8025b7c7\u003e] print_circular_bug_tail+0xb8/0xc3\n [\u003cffffffff8025ca54\u003e] __lock_acquire+0xedb/0x14d2\n [\u003cffffffff80259bb1\u003e] ? add_lock_to_list+0x7e/0xad\n [\u003cffffffff8029967a\u003e] ? mm_take_all_locks+0x70/0xea\n [\u003cffffffff8029967a\u003e] ? mm_take_all_locks+0x70/0xea\n [\u003cffffffff8025d397\u003e] lock_release_non_nested+0x1c2/0x219\n [\u003cffffffff802996cc\u003e] ? mm_take_all_locks+0xc2/0xea\n [\u003cffffffff802996cc\u003e] ? mm_take_all_locks+0xc2/0xea\n [\u003cffffffff8025b202\u003e] ? trace_hardirqs_on_caller+0x4d/0x115\n [\u003cffffffff802995d9\u003e] ? mm_drop_all_locks+0x7f/0xb0\n [\u003cffffffff8025d515\u003e] lock_release+0x127/0x14a\n [\u003cffffffff804c6403\u003e] _spin_unlock+0x1e/0x50\n [\u003cffffffff802995d9\u003e] mm_drop_all_locks+0x7f/0xb0\n [\u003cffffffff802a965d\u003e] do_mmu_notifier_register+0xe2/0x112\n [\u003cffffffff802a96a8\u003e] mmu_notifier_register+0xe/0x10\n [\u003cffffffffa0043b6b\u003e] kvm_dev_ioctl+0x11e/0x287 [kvm]\n [\u003cffffffff8033f9f2\u003e] ? file_has_perm+0x83/0x8e\n [\u003cffffffff802bd0ca\u003e] vfs_ioctl+0x2a/0x78\n [\u003cffffffff802bd36f\u003e] do_vfs_ioctl+0x257/0x274\n [\u003cffffffff802bd3e1\u003e] sys_ioctl+0x55/0x78\n [\u003cffffffff8020c0db\u003e] system_call_fastpath+0x16/0x1b\n\nWhich the locking hierarchy in mm/rmap.c confirms as valid.\n\nFix this by first taking all the mapping-\u003ei_mmap_lock instances and then\ntake all anon_vma-\u003elock instances.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nAcked-by: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "454ed842d55740160334efc9ad56cfef54ed37bc", "tree": "1b60057a0dc7d65c530b6b1ad4514200f828ac9a", "parents": [ "b7d39aff91454f2534db2275f55908656ec0470c" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Aug 11 09:30:25 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Aug 11 09:30:25 2008 +0200" }, "message": "lockdep: annotate mm_take_all_locks()\n\nThe nesting is correct due to holding mmap_sem, use the new annotation\nto annotate this.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "dfe195fb79e88c334481f1362fef52f6d2e30b2d", "tree": "4e7c30eabca8e5d8f30f8bf3d45e046281677ac4", "parents": [ "bf1db69fbf4ff511e88736ce2e6318846f34492b" ], "author": { "name": "Benny Halevy", "email": "bhalevy@panasas.com", "time": "Tue Aug 05 13:01:41 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Aug 05 14:33:50 2008 -0700" }, "message": "mm: fix uninitialized variables for find_vma_prepare callers\n\ngcc 4.3.0 correctly emits the following warnings.\nWhen a vma covering addr is found, find_vma_prepare indeed returns without\nsetting pprev, rb_link, and rb_parent.\n\n mm/mmap.c: In function `insert_vm_struct\u0027:\n mm/mmap.c:2085: warning: `rb_parent\u0027 may be used uninitialized in this function\n mm/mmap.c:2085: warning: `rb_link\u0027 may be used uninitialized in this function\n mm/mmap.c:2084: warning: `prev\u0027 may be used uninitialized in this function\n mm/mmap.c: In function `copy_vma\u0027:\n mm/mmap.c:2124: warning: `rb_parent\u0027 may be used uninitialized in this function\n mm/mmap.c:2124: warning: `rb_link\u0027 may be used uninitialized in this function\n mm/mmap.c:2123: warning: `prev\u0027 may be used uninitialized in this function\n mm/mmap.c: In function `do_brk\u0027:\n mm/mmap.c:1951: warning: `rb_parent\u0027 may be used uninitialized in this function\n mm/mmap.c:1951: warning: `rb_link\u0027 may be used uninitialized in this function\n mm/mmap.c:1949: warning: `prev\u0027 may be used uninitialized in this function\n mm/mmap.c: In function `mmap_region\u0027:\n mm/mmap.c:1092: warning: `rb_parent\u0027 may be used uninitialized in this function\n mm/mmap.c:1092: warning: `rb_link\u0027 may be used uninitialized in this function\n mm/mmap.c:1089: warning: `prev\u0027 may be used uninitialized in this function\n\nHugh adds: in fact, none of find_vma_prepare\u0027s callers use those values\nwhen a vma is found to be already covering addr, it\u0027s either an error or\nan occasion to munmap and repeat. Okay, let\u0027s quieten the compiler (but I\nwould prefer it if pprev, rb_link and rb_parent were meaningful in that\ncase, rather than whatever\u0027s in them from descending the tree).\n\nSigned-off-by: Benny Halevy \u003cbhalevy@panasas.com\u003e\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: \"Ryan Hope\" \u003crmh3093@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": "cddb8a5c14aa89810b40495d94d3d2a0faee6619", "tree": "d0b47b071f7d2dd1d6f9c36084aa8cfcef90d1da", "parents": [ "7906d00cd1f687268f0a3599442d113767795ae6" ], "author": { "name": "Andrea Arcangeli", "email": "andrea@qumranet.com", "time": "Mon Jul 28 15:46:29 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jul 28 16:30:21 2008 -0700" }, "message": "mmu-notifiers: core\n\nWith KVM/GFP/XPMEM there isn\u0027t just the primary CPU MMU pointing to pages.\n There are secondary MMUs (with secondary sptes and secondary tlbs) too.\nsptes in the kvm case are shadow pagetables, but when I say spte in\nmmu-notifier context, I mean \"secondary pte\". In GRU case there\u0027s no\nactual secondary pte and there\u0027s only a secondary tlb because the GRU\nsecondary MMU has no knowledge about sptes and every secondary tlb miss\nevent in the MMU always generates a page fault that has to be resolved by\nthe CPU (this is not the case of KVM where the a secondary tlb miss will\nwalk sptes in hardware and it will refill the secondary tlb transparently\nto software if the corresponding spte is present). The same way\nzap_page_range has to invalidate the pte before freeing the page, the spte\n(and secondary tlb) must also be invalidated before any page is freed and\nreused.\n\nCurrently we take a page_count pin on every page mapped by sptes, but that\nmeans the pages can\u0027t be swapped whenever they\u0027re mapped by any spte\nbecause they\u0027re part of the guest working set. Furthermore a spte unmap\nevent can immediately lead to a page to be freed when the pin is released\n(so requiring the same complex and relatively slow tlb_gather smp safe\nlogic we have in zap_page_range and that can be avoided completely if the\nspte unmap event doesn\u0027t require an unpin of the page previously mapped in\nthe secondary MMU).\n\nThe mmu notifiers allow kvm/GRU/XPMEM to attach to the tsk-\u003emm and know\nwhen the VM is swapping or freeing or doing anything on the primary MMU so\nthat the secondary MMU code can drop sptes before the pages are freed,\navoiding all page pinning and allowing 100% reliable swapping of guest\nphysical address space. Furthermore it avoids the code that teardown the\nmappings of the secondary MMU, to implement a logic like tlb_gather in\nzap_page_range that would require many IPI to flush other cpu tlbs, for\neach fixed number of spte unmapped.\n\nTo make an example: if what happens on the primary MMU is a protection\ndowngrade (from writeable to wrprotect) the secondary MMU mappings will be\ninvalidated, and the next secondary-mmu-page-fault will call\nget_user_pages and trigger a do_wp_page through get_user_pages if it\ncalled get_user_pages with write\u003d1, and it\u0027ll re-establishing an updated\nspte or secondary-tlb-mapping on the copied page. Or it will setup a\nreadonly spte or readonly tlb mapping if it\u0027s a guest-read, if it calls\nget_user_pages with write\u003d0. This is just an example.\n\nThis allows to map any page pointed by any pte (and in turn visible in the\nprimary CPU MMU), into a secondary MMU (be it a pure tlb like GRU, or an\nfull MMU with both sptes and secondary-tlb like the shadow-pagetable layer\nwith kvm), or a remote DMA in software like XPMEM (hence needing of\nschedule in XPMEM code to send the invalidate to the remote node, while no\nneed to schedule in kvm/gru as it\u0027s an immediate event like invalidating\nprimary-mmu pte).\n\nAt least for KVM without this patch it\u0027s impossible to swap guests\nreliably. And having this feature and removing the page pin allows\nseveral other optimizations that simplify life considerably.\n\nDependencies:\n\n1) mm_take_all_locks() to register the mmu notifier when the whole VM\n isn\u0027t doing anything with \"mm\". This allows mmu notifier users to keep\n track if the VM is in the middle of the invalidate_range_begin/end\n critical section with an atomic counter incraese in range_begin and\n decreased in range_end. No secondary MMU page fault is allowed to map\n any spte or secondary tlb reference, while the VM is in the middle of\n range_begin/end as any page returned by get_user_pages in that critical\n section could later immediately be freed without any further\n -\u003einvalidate_page notification (invalidate_range_begin/end works on\n ranges and -\u003einvalidate_page isn\u0027t called immediately before freeing\n the page). To stop all page freeing and pagetable overwrites the\n mmap_sem must be taken in write mode and all other anon_vma/i_mmap\n locks must be taken too.\n\n2) It\u0027d be a waste to add branches in the VM if nobody could possibly\n run KVM/GRU/XPMEM on the kernel, so mmu notifiers will only enabled if\n CONFIG_KVM\u003dm/y. In the current kernel kvm won\u0027t yet take advantage of\n mmu notifiers, but this already allows to compile a KVM external module\n against a kernel with mmu notifiers enabled and from the next pull from\n kvm.git we\u0027ll start using them. And GRU/XPMEM will also be able to\n continue the development by enabling KVM\u003dm in their config, until they\n submit all GRU/XPMEM GPLv2 code to the mainline kernel. Then they can\n also enable MMU_NOTIFIERS in the same way KVM does it (even if KVM\u003dn).\n This guarantees nobody selects MMU_NOTIFIER\u003dy if KVM and GRU and XPMEM\n are all \u003dn.\n\nThe mmu_notifier_register call can fail because mm_take_all_locks may be\ninterrupted by a signal and return -EINTR. Because mmu_notifier_reigster\nis used when a driver startup, a failure can be gracefully handled. Here\nan example of the change applied to kvm to register the mmu notifiers.\nUsually when a driver startups other allocations are required anyway and\n-ENOMEM failure paths exists already.\n\n struct kvm *kvm_arch_create_vm(void)\n {\n struct kvm *kvm \u003d kzalloc(sizeof(struct kvm), GFP_KERNEL);\n+ int err;\n\n if (!kvm)\n return ERR_PTR(-ENOMEM);\n\n INIT_LIST_HEAD(\u0026kvm-\u003earch.active_mmu_pages);\n\n+ kvm-\u003earch.mmu_notifier.ops \u003d \u0026kvm_mmu_notifier_ops;\n+ err \u003d mmu_notifier_register(\u0026kvm-\u003earch.mmu_notifier, current-\u003emm);\n+ if (err) {\n+ kfree(kvm);\n+ return ERR_PTR(err);\n+ }\n+\n return kvm;\n }\n\nmmu_notifier_unregister returns void and it\u0027s reliable.\n\nThe patch also adds a few needed but missing includes that would prevent\nkernel to compile after these changes on non-x86 archs (x86 didn\u0027t need\nthem by luck).\n\n[akpm@linux-foundation.org: coding-style fixes]\n[akpm@linux-foundation.org: fix mm/filemap_xip.c build]\n[akpm@linux-foundation.org: fix mm/mmu_notifier.c build]\nSigned-off-by: Andrea Arcangeli \u003candrea@qumranet.com\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Jack Steiner \u003csteiner@sgi.com\u003e\nCc: Robin Holt \u003cholt@sgi.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Kanoj Sarcar \u003ckanojsarcar@yahoo.com\u003e\nCc: Roland Dreier \u003crdreier@cisco.com\u003e\nCc: Steve Wise \u003cswise@opengridcomputing.com\u003e\nCc: Avi Kivity \u003cavi@qumranet.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Anthony Liguori \u003caliguori@us.ibm.com\u003e\nCc: Chris Wright \u003cchrisw@redhat.com\u003e\nCc: Marcelo Tosatti \u003cmarcelo@kvack.org\u003e\nCc: Eric Dumazet \u003cdada1@cosmosbay.com\u003e\nCc: \"Paul E. McKenney\" \u003cpaulmck@us.ibm.com\u003e\nCc: Izik Eidus \u003cizike@qumranet.com\u003e\nCc: Anthony Liguori \u003caliguori@us.ibm.com\u003e\nCc: Rik van Riel \u003criel@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": "7906d00cd1f687268f0a3599442d113767795ae6", "tree": "63609454d164a088d7f535f826764579c0f297f6", "parents": [ "6beeac76f5f96590fb751af5e138fbc3f62e8460" ], "author": { "name": "Andrea Arcangeli", "email": "andrea@qumranet.com", "time": "Mon Jul 28 15:46:26 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jul 28 16:30:21 2008 -0700" }, "message": "mmu-notifiers: add mm_take_all_locks() operation\n\nmm_take_all_locks holds off reclaim from an entire mm_struct. This allows\nmmu notifiers to register into the mm at any time with the guarantee that\nno mmu operation is in progress on the mm.\n\nThis operation locks against the VM for all pte/vma/mm related operations\nthat could ever happen on a certain mm. This includes vmtruncate,\ntry_to_unmap, and all page faults.\n\nThe caller must take the mmap_sem in write mode before calling\nmm_take_all_locks(). The caller isn\u0027t allowed to release the mmap_sem\nuntil mm_drop_all_locks() returns.\n\nmmap_sem in write mode is required in order to block all operations that\ncould modify pagetables and free pages without need of altering the vma\nlayout (for example populate_range() with nonlinear vmas). It\u0027s also\nneeded in write mode to avoid new anon_vmas to be associated with existing\nvmas.\n\nA single task can\u0027t take more than one mm_take_all_locks() in a row or it\nwould deadlock.\n\nmm_take_all_locks() and mm_drop_all_locks are expensive operations that\nmay have to take thousand of locks.\n\nmm_take_all_locks() can fail if it\u0027s interrupted by signals.\n\nWhen mmu_notifier_register returns, we must be sure that the driver is\nnotified if some task is in the middle of a vmtruncate for the \u0027mm\u0027 where\nthe mmu notifier was registered (mmu_notifier_invalidate_range_start/end\nis run around the vmtruncation but mmu_notifier_register can run after\nmmu_notifier_invalidate_range_start and before\nmmu_notifier_invalidate_range_end). Same problem for rmap paths. And\nwe\u0027ve to remove page pinning to avoid replicating the tlb_gather logic\ninside KVM (and GRU doesn\u0027t work well with page pinning regardless of\nneeding tlb_gather), so without mm_take_all_locks when vmtruncate frees\nthe page, kvm would have no way to notice that it mapped into sptes a page\nthat is going into the freelist without a chance of any further\nmmu_notifier notification.\n\n[akpm@linux-foundation.org: coding-style fixes]\nSigned-off-by: Andrea Arcangeli \u003candrea@qumranet.com\u003e\nAcked-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Jack Steiner \u003csteiner@sgi.com\u003e\nCc: Robin Holt \u003cholt@sgi.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Kanoj Sarcar \u003ckanojsarcar@yahoo.com\u003e\nCc: Roland Dreier \u003crdreier@cisco.com\u003e\nCc: Steve Wise \u003cswise@opengridcomputing.com\u003e\nCc: Avi Kivity \u003cavi@qumranet.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Anthony Liguori \u003caliguori@us.ibm.com\u003e\nCc: Chris Wright \u003cchrisw@redhat.com\u003e\nCc: Marcelo Tosatti \u003cmarcelo@kvack.org\u003e\nCc: Eric Dumazet \u003cdada1@cosmosbay.com\u003e\nCc: \"Paul E. McKenney\" \u003cpaulmck@us.ibm.com\u003e\nCc: Izik Eidus \u003cizike@qumranet.com\u003e\nCc: Anthony Liguori \u003caliguori@us.ibm.com\u003e\nCc: Rik van Riel \u003criel@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": "a5516438959d90b071ff0a484ce4f3f523dc3152", "tree": "e356ba9364c76b93c176b4d4a262b7aca3ee8f91", "parents": [ "b7ba30c679ed1eb7ed3ed8f281f6493282042bd4" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jul 23 21:27:41 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 10:47:17 2008 -0700" }, "message": "hugetlb: modular state for hugetlb page size\n\nThe goal of this patchset is to support multiple hugetlb page sizes. This\nis achieved by introducing a new struct hstate structure, which\nencapsulates the important hugetlb state and constants (eg. huge page\nsize, number of huge pages currently allocated, etc).\n\nThe hstate structure is then passed around the code which requires these\nfields, they will do the right thing regardless of the exact hstate they\nare operating on.\n\nThis patch adds the hstate structure, with a single global instance of it\n(default_hstate), and does the basic work of converting hugetlb to use the\nhstate.\n\nFuture patches will add more hstate structures to allow for different\nhugetlbfs mounts to have different page sizes.\n\n[akpm@linux-foundation.org: coding-style fixes]\nAcked-by: Adam Litke \u003cagl@us.ibm.com\u003e\nAcked-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "cdfd4325c0d878679bd6a3ba8285b71d9980e3c0", "tree": "1b1d52ce2ac528851630c706fbcf9db1072460a5", "parents": [ "e7c4b0bfd025f71cf7624b7c1be174f63caade33" ], "author": { "name": "Andy Whitcroft", "email": "apw@shadowen.org", "time": "Wed Jul 23 21:27:28 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 10:47:16 2008 -0700" }, "message": "mm: record MAP_NORESERVE status on vmas and fix small page mprotect reservations\n\nWith Mel\u0027s hugetlb private reservation support patches applied, strict\novercommit semantics are applied to both shared and private huge page\nmappings. This can be a problem if an application relied on unlimited\novercommit semantics for private mappings. An example of this would be an\napplication which maps a huge area with the intention of using it very\nsparsely. These application would benefit from being able to opt-out of\nthe strict overcommit. It should be noted that prior to hugetlb\nsupporting demand faulting all mappings were fully populated and so\napplications of this type should be rare.\n\nThis patch stack implements the MAP_NORESERVE mmap() flag for huge page\nmappings. This flag has the same meaning as for small page mappings,\nsuppressing reservations for that mapping.\n\nThanks to Mel Gorman for reviewing a number of early versions of these\npatches.\n\nThis patch:\n\nWhen a small page mapping is created with mmap() reservations are created\nby default for any memory pages required. When the region is read/write\nthe reservation is increased for every page, no reservation is needed for\nread-only regions (as they implicitly share the zero page). Reservations\nare tracked via the VM_ACCOUNT vma flag which is present when the region\nhas reservation backing it. When we convert a region from read-only to\nread-write new reservations are aquired and VM_ACCOUNT is set. However,\nwhen a read-only map is created with MAP_NORESERVE it is indistinguishable\nfrom a normal mapping. When we then convert that to read/write we are\nforced to incorrectly create reservations for it as we have no record of\nthe original MAP_NORESERVE.\n\nThis patch introduces a new vma flag VM_NORESERVE which records the\npresence of the original MAP_NORESERVE flag. This allows us to\ndistinguish these two circumstances and correctly account the reserve.\n\nAs well as fixing this FIXME in the code, this makes it much easier to\nintroduce MAP_NORESERVE support for huge pages as this flag is available\nconsistantly for the life of the mapping. VM_ACCOUNT on the other hand is\nheavily used at the generic level in association with small pages.\n\nSigned-off-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Adam Litke \u003cagl@us.ibm.com\u003e\nCc: Johannes Weiner \u003channes@saeurebad.de\u003e\nCc: Andy Whitcroft \u003capw@shadowen.org\u003e\nCc: William Lee Irwin III \u003cwli@holomorphy.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Michael Kerrisk \u003cmtk.manpages@googlemail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "42b7772812d15b86543a23b82bd6070eef9a08b1", "tree": "10665ee01fe82ce17c68a6278d044531b1ed64c0", "parents": [ "a352894d07059649398c4769dc8b645e1a1dad88" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jul 23 21:27:10 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 10:47:15 2008 -0700" }, "message": "mm: remove double indirection on tlb parameter to free_pgd_range() \u0026 Co\n\nThe double indirection here is not needed anywhere and hence (at least)\nconfusing.\n\nSigned-off-by: Jan Beulich \u003cjbeulich@novell.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nAcked-by: Jeremy Fitzhardinge \u003cjeremy@goop.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b845f313d78e4e259ec449909e3bbadf77b53a6d", "tree": "03239e77dbc43f627ce112963736c8b4c53117e6", "parents": [ "e5093ff05d36c64e8f36a9ddb26358256dc133ea" ], "author": { "name": "Dave Kleikamp", "email": "shaggy@linux.vnet.ibm.com", "time": "Tue Jul 08 00:28:51 2008 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 09 16:30:45 2008 +1000" }, "message": "mm: Allow architectures to define additional protection bits\n\nThis patch allows architectures to define functions to deal with\nadditional protections bits for mmap() and mprotect().\n\narch_calc_vm_prot_bits() maps additonal protection bits to vm_flags\narch_vm_get_page_prot() maps additional vm_flags to the vma\u0027s vm_page_prot\narch_validate_prot() checks for valid values of the protection bits\n\nNote: vm_get_page_prot() is now pretty ugly, but the generated code\nshould be identical for architectures that don\u0027t define additional\nprotection bits.\n\nSigned-off-by: Dave Kleikamp \u003cshaggy@linux.vnet.ibm.com\u003e\nAcked-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nAcked-by: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "a5b4592cf77b973c29e7c9695873a26052b58951", "tree": "9f2af3014d5d41ddc22d7aa2793b871ee15297d8", "parents": [ "33dda515a1995dfb3b6b57d7ace9b3ee9d449c11" ], "author": { "name": "Jiri Kosina", "email": "jkosina@suse.cz", "time": "Thu Jun 05 22:46:05 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jun 06 11:29:09 2008 -0700" }, "message": "brk: make sys_brk() honor COMPAT_BRK when computing lower bound\n\nFix a regression introduced by\n\ncommit 4cc6028d4040f95cdb590a87db478b42b8be0508\nAuthor: Jiri Kosina \u003cjkosina@suse.cz\u003e\nDate: Wed Feb 6 22:39:44 2008 +0100\n\n brk: check the lower bound properly\n\nThe check in sys_brk() on minimum value the brk might have must take\nCONFIG_COMPAT_BRK setting into account. When this option is turned on\n(i.e. we support ancient legacy binaries, e.g. libc5-linked stuff), the\nlower bound on brk value is mm-\u003eend_code, otherwise the brk start is\nallowed to be arbitrarily shifted.\n\nSigned-off-by: Jiri Kosina \u003cjkosina@suse.cz\u003e\nTested-by: Geert Uytterhoeven \u003cgeert@linux-m68k.org\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "80119ef5c8153e0a6cc5edf00c083dc98a9bd348", "tree": "a2af11a3991b1bebe9d764ab6d4d28891e86eda2", "parents": [ "6c7c6afbb8c0e60d32a563cae7c6889211e9d9d8" ], "author": { "name": "Alan Cox", "email": "alan@redhat.com", "time": "Fri May 23 13:04:31 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat May 24 09:56:09 2008 -0700" }, "message": "mm: fix atomic_t overflow in vm\n\nThe atomic_t type is 32bit but a 64bit system can have more than 2^32\npages of virtual address space available. Without this we overflow on\nludicrously large mappings\n\nSigned-off-by: Alan Cox \u003calan@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": "925d1c401fa6cfd0df5d2e37da8981494ccdec07", "tree": "4f3b7a09311cd99783b822350628125e44f9902d", "parents": [ "e93b4ea20adb20f1f1f07f10ba5d7dd739d2843e" ], "author": { "name": "Matt Helsley", "email": "matthltc@us.ibm.com", "time": "Tue Apr 29 01:01:36 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Apr 29 08:06:17 2008 -0700" }, "message": "procfs task exe symlink\n\nThe kernel implements readlink of /proc/pid/exe by getting the file from\nthe first executable VMA. Then the path to the file is reconstructed and\nreported as the result.\n\nBecause of the VMA walk the code is slightly different on nommu systems.\nThis patch avoids separate /proc/pid/exe code on nommu systems. Instead of\nwalking the VMAs to find the first executable file-backed VMA we store a\nreference to the exec\u0027d file in the mm_struct.\n\nThat reference would prevent the filesystem holding the executable file\nfrom being unmounted even after unmapping the VMAs. So we track the number\nof VM_EXECUTABLE VMAs and drop the new reference when the last one is\nunmapped. This avoids pinning the mounted filesystem.\n\n[akpm@linux-foundation.org: improve comments]\n[yamamoto@valinux.co.jp: fix dup_mmap]\nSigned-off-by: Matt Helsley \u003cmatthltc@us.ibm.com\u003e\nCc: Oleg Nesterov \u003coleg@tv-sign.ru\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc:\"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nCc: Christoph Hellwig \u003chch@lst.de\u003e\nCc: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: YAMAMOTO Takashi \u003cyamamoto@valinux.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": "846a16bf0fc80dc95a414ffce465e3cbf9680247", "tree": "45e03061c5e3d8242bf470509771926f37177415", "parents": [ "f0be3d32b05d3fea2fcdbbb81a39dac2a7163169" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:09 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:23 2008 -0700" }, "message": "mempolicy: rename mpol_copy to mpol_dup\n\nThis patch renames mpol_copy() to mpol_dup() because, well, that\u0027s what it\ndoes. Like, e.g., strdup() for strings, mpol_dup() takes a pointer to an\nexisting mempolicy, allocates a new one and copies the contents.\n\nIn a later patch, I want to use the name mpol_copy() to copy the contents from\none mempolicy to another like, e.g., strcpy() does for strings.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\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": "f0be3d32b05d3fea2fcdbbb81a39dac2a7163169", "tree": "5794ce6a8befbce82cd3e44ff15fbf3bb5f2f3bf", "parents": [ "3b1163006332302117b1b2acf226d4014ff46525" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:08 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:23 2008 -0700" }, "message": "mempolicy: rename mpol_free to mpol_put\n\nThis is a change that was requested some time ago by Mel Gorman. Makes sense\nto me, so here it is.\n\nNote: I retain the name \"mpol_free_shared_policy()\" because it actually does\nfree the shared_policy, which is NOT a reference counted object. However, ...\n\nThe mempolicy object[s] referenced by the shared_policy are reference counted,\nso mpol_put() is used to release the reference held by the shared_policy. The\nmempolicy might not be freed at this time, because some task attached to the\nshared object associated with the shared policy may be in the process of\nallocating a page based on the mempolicy. In that case, the task performing\nthe allocation will hold a reference on the mempolicy, obtained via\nmpol_shared_policy_lookup(). The mempolicy will be freed when all tasks\nholding such a reference have called mpol_put() for the mempolicy.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\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": "4d3d5b41a72b52555d43efbfc4ccde6ba6e5444f", "tree": "5935f5d9e741f63c190c4edf4d5f6f6005e33d0f", "parents": [ "0dd1334faf7e075bfdb6f5284eed65210b296fc1" ], "author": { "name": "Oleg Nesterov", "email": "oleg@tv-sign.ru", "time": "Mon Apr 28 02:12:10 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:18 2008 -0700" }, "message": "mmap_region: cleanup the final vma_merge() related code\n\nIt is not easy to actually understand the \"if (!file || !vma_merge())\"\ncode, turn it into \"if (file \u0026\u0026 vma_merge())\". This makes immediately\nobvious that the subsequent \"if (file)\" is superfluous.\n\nAs Hugh Dickins pointed out, we can also factor out the -\u003ei_writecount\ncorrections, and add a small comment about that.\n\nSigned-off-by: Oleg Nesterov \u003coleg@tv-sign.ru\u003e\nCc: Miklos Szeredi \u003cmiklos@szeredi.hu\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b1d0e4f535e10775cffde922208b49629169aeaa", "tree": "c5fa68fb25ffd2485da5de236fcf2b67d9df3dfd", "parents": [ "6a306e8b4c81a1c1f538e390d92bfe80d04b254c" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Sat Feb 09 01:15:19 2008 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Feb 08 18:57:39 2008 -0800" }, "message": "mm: special mapping nopage\n\nConvert special mapping install from nopage to fault.\n\nBecause the \"vm_file\" is NULL for the special mapping, the generic VM\ncode has messed up \"vm_pgoff\" thinking that it\u0027s an anonymous mapping\nand the offset does\u0027t matter. For that reason, we need to undo the\nvm_pgoff offset that got added into vmf-\u003epgoff.\n\n[ We _really_ should clean that up - either by making this whole special\n mapping code just use a real file entry rather than that ugly array of\n \"struct page\" pointers, or by just making the VM code realize that\n even if vm_file is NULL it may not be a regular anonymous mmap.\n\t\t\t\t\t\t\t - Linus ]\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: linux-mm@kvack.org\nCc: linux-kernel@vger.kernel.org\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4cc6028d4040f95cdb590a87db478b42b8be0508", "tree": "9b9879d8b8cc055e4bb8eabd69b979a17e6e52cd", "parents": [ "2d684cd6d9cf0c6a0e28978362671b6e2d8fb56c" ], "author": { "name": "Jiri Kosina", "email": "jkosina@suse.cz", "time": "Wed Feb 06 22:39:44 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Feb 06 22:39:44 2008 +0100" }, "message": "brk: check the lower bound properly\n\nThere is a check in sys_brk(), that tries to make sure that we do not\nunderflow the area that is dedicated to brk heap.\n\nThe check is however wrong, as it assumes that brk area starts immediately\nafter the end of the code (+bss), which is wrong for example in\nenvironments with randomized brk start. The proper way is to check whether\nthe address is not below the start_brk address.\n\nSigned-off-by: Jiri Kosina \u003cjkosina@suse.cz\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "08e7d9b557299ba6ce57165ce8df310780bd681c", "tree": "8733b402eaa1de1a6bcdea5ee72ea8655c896dd4", "parents": [ "5e5419734c8719cbc01af959ad9c0844002c0df5" ], "author": { "name": "Martin Schwidefsky", "email": "schwidefsky@de.ibm.com", "time": "Mon Feb 04 22:29:16 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Feb 05 09:44:18 2008 -0800" }, "message": "arch_rebalance_pgtables call\n\nIn order to change the layout of the page tables after an mmap has crossed the\nadress space limit of the current page table layout a architecture hook in\nget_unmapped_area is needed. The arguments are the address of the new mapping\nand the length of it.\n\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "2f98735c9c24ea1f0d40a364d4e63611b689b795", "tree": "a42b3802449af474d36cda3b6f9fb190a717defb", "parents": [ "fe2528b96b02173395f5a75e37714c07f3e25e73" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Sat Feb 02 03:08:53 2008 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Feb 04 07:55:38 2008 -0800" }, "message": "vm audit: add VM_DONTEXPAND to mmap for drivers that need it\n\nDrivers that register a -\u003efault handler, but do not range-check the\noffset argument, must set VM_DONTEXPAND in the vm_flags in order to\nprevent an expanding mremap from overflowing the resource.\n\nI\u0027ve audited the tree and attempted to fix these problems (usually by\nadding VM_DONTEXPAND where it is not obvious).\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "c1d171a002942ea2d93b4fbd0c9583c56fce0772", "tree": "49249c927dc1644e7c92150808269cb474bdd411", "parents": [ "7b83dae7aa31db4f6d6e78c3c6d490a7ac58699c" ], "author": { "name": "Jiri Kosina", "email": "jkosina@suse.cz", "time": "Wed Jan 30 13:30:40 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Jan 30 13:30:40 2008 +0100" }, "message": "x86: randomize brk\n\nRandomize the location of the heap (brk) for i386 and x86_64. The range is\nrandomized in the range starting at current brk location up to 0x02000000\noffset for both architectures. This, together with\npie-executable-randomization.patch and\npie-executable-randomization-fix.patch, should make the address space\nrandomization on i386 and x86_64 complete.\n\nArjan says:\n\nThis is known to break older versions of some emacs variants, whose dumper\ncode assumed that the last variable declared in the program is equal to the\nstart of the dynamically allocated memory region.\n\n(The dumper is the code where emacs effectively dumps core at the end of it\u0027s\ncompilation stage; this coredump is then loaded as the main program during\nnormal use)\n\niirc this was 5 years or so; we found this way back when I was at RH and we\nfirst did the security stuff there (including this brk randomization). It\nwasn\u0027t all variants of emacs, and it got fixed as a result (I vaguely remember\nthat emacs already had code to deal with it for other archs/oses, just\nifdeffed wrongly).\n\nIt\u0027s a rare and wrong assumption as a general thing, just on x86 it mostly\nhappened to be true (but to be honest, it\u0027ll break too if gcc does\nsomething fancy or if the linker does a non-standard order). Still its\nsomething we should at least document.\n\nNote 2: afaik it only broke the emacs *build*. I\u0027m not 100% sure about that\n(it IS 5 years ago) though.\n\n[ akpm@linux-foundation.org: deuglification ]\n\nSigned-off-by: Jiri Kosina \u003cjkosina@suse.cz\u003e\nCc: Arjan van de Ven \u003carjan@infradead.org\u003e\nCc: Roland McGrath \u003croland@redhat.com\u003e\nCc: Jakub Jelinek \u003cjakub@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "88c3f7a8f2c86be264d326cf6f49a3e8c30d13a6", "tree": "9ab4e6996d3630652e55468b0a8ce77242630ac3", "parents": [ "c9180a57a9ab2d5525faf8815a332364ee9e89b7" ], "author": { "name": "Richard Knutsson", "email": "ricknu-0@student.ltu.se", "time": "Sat Dec 08 12:02:48 2007 +0100" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Fri Jan 25 11:29:48 2008 +1100" }, "message": "Security: remove security_file_mmap hook sparse-warnings (NULL as 0).\n\nFixing:\n CHECK mm/mmap.c\nmm/mmap.c:1623:29: warning: Using plain integer as NULL pointer\nmm/mmap.c:1623:29: warning: Using plain integer as NULL pointer\nmm/mmap.c:1944:29: warning: Using plain integer as NULL pointer\n\nSigned-off-by: Richard Knutsson \u003cricknu-0@student.ltu.se\u003e\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "5a211a5deabcafdc764817d5b4510c767d317ddc", "tree": "d330ce692f43c1b02c84ff81284e6191d567e02f", "parents": [ "7cd94146cd504016315608e297219f9fb7b1413b" ], "author": { "name": "Eric Paris", "email": "eparis@redhat.com", "time": "Tue Dec 04 11:06:55 2007 -0500" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Thu Dec 06 00:25:30 2007 +1100" }, "message": "VM/Security: add security hook to do_brk\n\nGiven a specifically crafted binary do_brk() can be used to get low\npages available in userspace virtually memory and can thus be used to\ncircumvent the mmap_min_addr low memory protection. Add security checks\nin do_brk().\n\nSigned-off-by: Eric Paris \u003ceparis@redhat.com\u003e\nAcked-by: Alan Cox \u003calan@redhat.com\u003e\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "7cd94146cd504016315608e297219f9fb7b1413b", "tree": "1d118d6af0a6d3efb9be66f7305827aee2ceffea", "parents": [ "8869477a49c3e99def1fcdadd6bbc407fea14b45" ], "author": { "name": "Eric Paris", "email": "eparis@redhat.com", "time": "Mon Nov 26 18:47:40 2007 -0500" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Thu Dec 06 00:25:10 2007 +1100" }, "message": "Security: round mmap hint address above mmap_min_addr\n\nIf mmap_min_addr is set and a process attempts to mmap (not fixed) with a\nnon-null hint address less than mmap_min_addr the mapping will fail the\nsecurity checks. Since this is just a hint address this patch will round\nsuch a hint address above mmap_min_addr.\n\ngcj was found to try to be very frugal with vm usage and give hint addresses\nin the 8k-32k range. Without this patch all such programs failed and with\nthe patch they happily get a higher address.\n\nThis patch is wrappad in CONFIG_SECURITY since mmap_min_addr doesn\u0027t exist\nwithout it and there would be no security check possible no matter what. So\nwe should not bother compiling in this rounding if it is just a waste of\ntime.\n\nSigned-off-by: Eric Paris \u003ceparis@redhat.com\u003e\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "8869477a49c3e99def1fcdadd6bbc407fea14b45", "tree": "a3f77dcac695a12986715b119750f85f124179bb", "parents": [ "ab5a91a8364c3d6fc617abc47cc81d162c01d90a" ], "author": { "name": "Eric Paris", "email": "eparis@redhat.com", "time": "Mon Nov 26 18:47:26 2007 -0500" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Thu Dec 06 00:24:48 2007 +1100" }, "message": "security: protect from stack expantion into low vm addresses\n\nAdd security checks to make sure we are not attempting to expand the\nstack into memory protected by mmap_min_addr\n\nSigned-off-by: Eric Paris \u003ceparis@redhat.com\u003e\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "1ddd439ef987c9f0209e6ce824b67518f2afe67b", "tree": "1f6e0ef40c2b9cf5819d9193d7d06c6a0a33ff6c", "parents": [ "4ae3f847e49e3787eca91bced31f8fd328d50496" ], "author": { "name": "Hugh Dickins", "email": "hugh@veritas.com", "time": "Mon Oct 22 20:45:12 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 23 08:32:06 2007 -0700" }, "message": "fix mprotect vma_wants_writenotify prot\n\nFix mprotect bug in recent commit 3ed75eb8f1cd89565966599c4f77d2edb086d5b0\n(setup vma-\u003evm_page_prot by vm_get_page_prot()): the vma_wants_writenotify\ncase was setting the same prot as when not.\n\nNothing wrong with the use of protection_map[] in mmap_region(),\nbut use vm_get_page_prot() there too in the same ~VM_SHARED way.\n\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Coly Li \u003ccoyli@suse.de\u003e\nCc: Tony Luck \u003ctony.luck@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "3ed75eb8f1cd89565966599c4f77d2edb086d5b0", "tree": "54e77a47b40da80d76baf5eacc2259e0bc5bdf7c", "parents": [ "1c7037db50ebecf3d5cfbf7082daa5d97d900fef" ], "author": { "name": "Coly Li", "email": "coyli@suse.de", "time": "Thu Oct 18 23:39:15 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Oct 19 11:53:34 2007 -0700" }, "message": "setup vma-\u003evm_page_prot by vm_get_page_prot()\n\nThis patch uses vm_get_page_prot() to setup vma-\u003evm_page_prot.\n\nThough inside vm_get_page_prot() the protection flags is AND with\n(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED), it does not hurt correct code.\n\nSigned-off-by: Coly Li \u003ccoyli@suse.de\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Tony Luck \u003ctony.luck@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "cbfee34520666862f8ff539e580c48958fbb7706", "tree": "ded5cafce333e908a0fbeda1f7c55eaf7c1fbaaa", "parents": [ "b53767719b6cd8789392ea3e7e2eb7b8906898f0" ], "author": { "name": "Adrian Bunk", "email": "bunk@kernel.org", "time": "Tue Oct 16 23:31:38 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:43:07 2007 -0700" }, "message": "security/ cleanups\n\nThis patch contains the following cleanups that are now possible:\n- remove the unused security_operations-\u003einode_xattr_getsuffix\n- remove the no longer used security_operations-\u003eunregister_security\n- remove some no longer required exit code\n- remove a bunch of no longer used exports\n\nSigned-off-by: Adrian Bunk \u003cbunk@kernel.org\u003e\nAcked-by: James Morris \u003cjmorris@namei.org\u003e\nCc: Chris Wright \u003cchrisw@sous-sol.org\u003e\nCc: Stephen Smalley \u003csds@tycho.nsa.gov\u003e\nCc: Serge Hallyn \u003cserue@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": "4af3c9cc4fad54c3627e9afebf905aafde5690ed", "tree": "655364e458b8734a86c632316f4b5a1518529c60", "parents": [ "1a614f505193fcfc1b298643268a5db5b48e297f" ], "author": { "name": "Alexey Dobriyan", "email": "adobriyan@gmail.com", "time": "Tue Oct 16 23:29:23 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 17 08:42:55 2007 -0700" }, "message": "Drop some headers from mm.h\n\nmm.h doesn\u0027t use directly anything from mutex.h and backing-dev.h, so\nremove them and add them back to files which need them.\n\nCross-compile tested on many configs and archs.\n\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@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": "34b4e4aa3c470ce8fa2bd78abb1741b4b58baad7", "tree": "91d620288f1aaf63c12dc84ca1015465818601f2", "parents": [ "afe1ab4d577892822de2c8e803fbfaed6ec44ba3" ], "author": { "name": "Alan Cox", "email": "alan@lxorguk.ukuu.org.uk", "time": "Wed Aug 22 14:01:28 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Aug 22 19:52:45 2007 -0700" }, "message": "fix NULL pointer dereference in __vm_enough_memory()\n\nThe new exec code inserts an accounted vma into an mm struct which is not\ncurrent-\u003emm. The existing memory check code has a hard coded assumption\nthat this does not happen as does the security code.\n\nAs the correct mm is known we pass the mm to the security method and the\nhelper function. A new security test is added for the case where we need\nto pass the mm and the existing one is modified to pass current-\u003emm to\navoid the need to change large amounts of code.\n\n(Thanks to Tobias for fixing rejects and testing)\n\nSigned-off-by: Alan Cox \u003calan@redhat.com\u003e\nCc: WU Fengguang \u003cwfg@mail.ustc.edu.cn\u003e\nCc: James Morris \u003cjmorris@redhat.com\u003e\nCc: Tobias Diedrich \u003cranma+kernel@tdiedrich.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4e950f6f0189f65f8bf069cf2272649ef418f5e4", "tree": "95710bedf2a5aa3b61002f3399e0950192fdd504", "parents": [ "673d5b43daa00b42759cecc6b0760b8bf6be80d2" ], "author": { "name": "Alexey Dobriyan", "email": "adobriyan@gmail.com", "time": "Mon Jul 30 02:36:13 2007 +0400" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Sun Jul 29 17:09:29 2007 -0700" }, "message": "Remove fs.h from mm.h\n\nRemove fs.h from mm.h. For this,\n 1) Uninline vma_wants_writenotify(). It\u0027s pretty huge anyway.\n 2) Add back fs.h or less bloated headers (err.h) to files that need it.\n\nAs result, on x86_64 allyesconfig, fs.h dependencies cut down from 3929 files\nrebuilt down to 3444 (-12.3%).\n\nCross-compile tested without regressions on my two usual configs and (sigh):\n\nalpha arm-mx1ads mips-bigsur powerpc-ebony\nalpha-allnoconfig arm-neponset mips-capcella powerpc-g5\nalpha-defconfig arm-netwinder mips-cobalt powerpc-holly\nalpha-up arm-netx mips-db1000 powerpc-iseries\narm arm-ns9xxx mips-db1100 powerpc-linkstation\narm-assabet arm-omap_h2_1610 mips-db1200 powerpc-lite5200\narm-at91rm9200dk arm-onearm mips-db1500 powerpc-maple\narm-at91rm9200ek arm-picotux200 mips-db1550 powerpc-mpc7448_hpc2\narm-at91sam9260ek arm-pleb mips-ddb5477 powerpc-mpc8272_ads\narm-at91sam9261ek arm-pnx4008 mips-decstation powerpc-mpc8313_rdb\narm-at91sam9263ek arm-pxa255-idp mips-e55 powerpc-mpc832x_mds\narm-at91sam9rlek arm-realview mips-emma2rh powerpc-mpc832x_rdb\narm-ateb9200 arm-realview-smp mips-excite powerpc-mpc834x_itx\narm-badge4 arm-rpc mips-fulong powerpc-mpc834x_itxgp\narm-carmeva arm-s3c2410 mips-ip22 powerpc-mpc834x_mds\narm-cerfcube arm-shannon mips-ip27 powerpc-mpc836x_mds\narm-clps7500 arm-shark mips-ip32 powerpc-mpc8540_ads\narm-collie arm-simpad mips-jazz powerpc-mpc8544_ds\narm-corgi arm-spitz mips-jmr3927 powerpc-mpc8560_ads\narm-csb337 arm-trizeps4 mips-malta powerpc-mpc8568mds\narm-csb637 arm-versatile mips-mipssim powerpc-mpc85xx_cds\narm-ebsa110 i386 mips-mpc30x powerpc-mpc8641_hpcn\narm-edb7211 i386-allnoconfig mips-msp71xx powerpc-mpc866_ads\narm-em_x270 i386-defconfig mips-ocelot powerpc-mpc885_ads\narm-ep93xx i386-up mips-pb1100 powerpc-pasemi\narm-footbridge ia64 mips-pb1500 powerpc-pmac32\narm-fortunet ia64-allnoconfig mips-pb1550 powerpc-ppc64\narm-h3600 ia64-bigsur mips-pnx8550-jbs powerpc-prpmc2800\narm-h7201 ia64-defconfig mips-pnx8550-stb810 powerpc-ps3\narm-h7202 ia64-gensparse mips-qemu powerpc-pseries\narm-hackkit ia64-sim mips-rbhma4200 powerpc-up\narm-integrator ia64-sn2 mips-rbhma4500 s390\narm-iop13xx ia64-tiger mips-rm200 s390-allnoconfig\narm-iop32x ia64-up mips-sb1250-swarm s390-defconfig\narm-iop33x ia64-zx1 mips-sead s390-up\narm-ixp2000 m68k mips-tb0219 sparc\narm-ixp23xx m68k-amiga mips-tb0226 sparc-allnoconfig\narm-ixp4xx m68k-apollo mips-tb0287 sparc-defconfig\narm-jornada720 m68k-atari mips-workpad sparc-up\narm-kafa m68k-bvme6000 mips-wrppmc sparc64\narm-kb9202 m68k-hp300 mips-yosemite sparc64-allnoconfig\narm-ks8695 m68k-mac parisc sparc64-defconfig\narm-lart m68k-mvme147 parisc-allnoconfig sparc64-up\narm-lpd270 m68k-mvme16x parisc-defconfig um-x86_64\narm-lpd7a400 m68k-q40 parisc-up x86_64\narm-lpd7a404 m68k-sun3 powerpc x86_64-allnoconfig\narm-lubbock m68k-sun3x powerpc-cell x86_64-defconfig\narm-lusl7200 mips powerpc-celleb x86_64-up\narm-mainstone mips-atlas powerpc-chrp32\n\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b6a2fea39318e43fee84fa7b0b90d68bed92d2ba", "tree": "c9c3619cb2730b5c10c7427b837146bce3d69156", "parents": [ "bdf4c48af20a3b0f01671799ace345e3d49576da" ], "author": { "name": "Ollie Wild", "email": "aaw@google.com", "time": "Thu Jul 19 01:48:16 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Jul 19 10:04:45 2007 -0700" }, "message": "mm: variable length argument support\n\nRemove the arg+env limit of MAX_ARG_PAGES by copying the strings directly from\nthe old mm into the new mm.\n\nWe create the new mm before the binfmt code runs, and place the new stack at\nthe very top of the address space. Once the binfmt code runs and figures out\nwhere the stack should be, we move it downwards.\n\nIt is a bit peculiar in that we have one task with two mm\u0027s, one of which is\ninactive.\n\n[a.p.zijlstra@chello.nl: limit stack size]\nSigned-off-by: Ollie Wild \u003caaw@google.com\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\n[bunk@stusta.de: unexport bprm_mm_init]\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": "54cb8821de07f2ffcd28c380ce9b93d5784b40d7", "tree": "1de676534963d96af42863b20191bc9f80060dea", "parents": [ "d00806b183152af6d24f46f0c33f14162ca1262a" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Thu Jul 19 01:46:59 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Jul 19 10:04:41 2007 -0700" }, "message": "mm: merge populate and nopage into fault (fixes nonlinear)\n\nNonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes\nthe virtual address -\u003e file offset differently from linear mappings.\n\n-\u003epopulate is a layering violation because the filesystem/pagecache code\nshould need to know anything about the virtual memory mapping. The hitch here\nis that the -\u003enopage handler didn\u0027t pass down enough information (ie. pgoff).\n But it is more logical to pass pgoff rather than have the -\u003enopage function\ncalculate it itself anyway (because that\u0027s a similar layering violation).\n\nHaving the populate handler install the pte itself is likewise a nasty thing\nto be doing.\n\nThis patch introduces a new fault handler that replaces -\u003enopage and\n-\u003epopulate and (later) -\u003enopfn. Most of the old mechanism is still in place\nso there is a lot of duplication and nice cleanups that can be removed if\neveryone switches over.\n\nThe rationale for doing this in the first place is that nonlinear mappings are\nsubject to the pagefault vs invalidate/truncate race too, and it seemed stupid\nto duplicate the synchronisation logic rather than just consolidate the two.\n\nAfter this patch, MAP_NONBLOCK no longer sets up ptes for pages present in\npagecache. Seems like a fringe functionality anyway.\n\nNOPAGE_REFAULT is removed. This should be implemented with -\u003efault, and no\nusers have hit mainline yet.\n\n[akpm@linux-foundation.org: cleanup]\n[randy.dunlap@oracle.com: doc. fixes for readahead]\n[akpm@linux-foundation.org: build fix]\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\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": "0165ab443556bdfad388da6c33d74a71b77d72b2", "tree": "c2449128f60ebed846b7d63633ccee3f88949a1c", "parents": [ "c44939ecb6e05aeaaf12d4e1bb046719c97e457e" ], "author": { "name": "Miklos Szeredi", "email": "mszeredi@suse.cz", "time": "Sun Jul 15 23:38:26 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Jul 16 09:05:37 2007 -0700" }, "message": "split mmap\n\nThis is a straightforward split of do_mmap_pgoff() into two functions:\n\n - do_mmap_pgoff() checks the parameters, and calculates the vma\n flags. Then it calls\n\n - mmap_region(), which does the actual mapping\n\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\nAcked-by: 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": "ed0321895182ffb6ecf210e066d87911b270d587", "tree": "832bb54666f73b06e55322df40f915c5e9ef64d7", "parents": [ "13bddc2e9d591e31bf20020dc19ea6ca85de420e" ], "author": { "name": "Eric Paris", "email": "eparis@redhat.com", "time": "Thu Jun 28 15:55:21 2007 -0400" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Wed Jul 11 22:52:29 2007 -0400" }, "message": "security: Protection for exploiting null dereference using mmap\n\nAdd a new security check on mmap operations to see if the user is attempting\nto mmap to low area of the address space. The amount of space protected is\nindicated by the new proc tunable /proc/sys/vm/mmap_min_addr and defaults to\n0, preserving existing behavior.\n\nThis patch uses a new SELinux security class \"memprotect.\" Policy already\ncontains a number of allow rules like a_t self:process * (unconfined_t being\none of them) which mean that putting this check in the process class (its\nbest current fit) would make it useless as all user processes, which we also\nwant to protect against, would be allowed. By taking the memprotect name of\nthe new class it will also make it possible for us to move some of the other\nmemory protect permissions out of \u0027process\u0027 and into the new class next time\nwe bump the policy version number (which I also think is a good future idea)\n\nAcked-by: Stephen Smalley \u003csds@tycho.nsa.gov\u003e\nAcked-by: Chris Wright \u003cchrisw@sous-sol.org\u003e\nSigned-off-by: Eric Paris \u003ceparis@redhat.com\u003e\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "06b32f3ab6df4c7489729f94bdc7093c72681d4b", "tree": "07fabea840fa598e510b4da899ef7f5b06282683", "parents": [ "d2f1c0fa2b346769ac35559ae3bafccf151dd446" ], "author": { "name": "Helge Deller", "email": "deller@gmx.de", "time": "Tue Dec 19 19:28:33 2006 +0100" }, "committer": { "name": "Kyle McMartin", "email": "kyle@minerva.i.cabal.ca", "time": "Thu Jun 21 17:46:20 2007 -0400" }, "message": "[PARISC] Handle wrapping in expand_upwards()\n\nFunction expand_upwards() did not guarded against wrapping\naround to address 0. This fixes the adjtimex02 testcase from\nthe Linux Test Project on a 32bit PARISC kernel.\n\n[expand_upwards is only used on parisc and ia64; it looks like it does\n the right thing on both. --kyle]\n\nSigned-off-by: Helge Deller \u003cdeller@gmx.de\u003e\nCc: Tony Luck \u003ctony.luck@intel.com\u003e\nSigned-off-by: Kyle McMartin \u003ckyle@parisc-linux.org\u003e\n" }, { "commit": "59c51591a0ac7568824f541f57de967e88adaa07", "tree": "243d20eb0a26b76d5d312f39ec5a1ff60e036711", "parents": [ "02a3e59a088749c08b0293ee1535f5bf48f5926c" ], "author": { "name": "Michael Opdenacker", "email": "michael@free-electrons.com", "time": "Wed May 09 08:57:56 2007 +0200" }, "committer": { "name": "Adrian Bunk", "email": "bunk@stusta.de", "time": "Wed May 09 08:57:56 2007 +0200" }, "message": "Fix occurrences of \"the the \"\n\nSigned-off-by: Michael Opdenacker \u003cmichael@free-electrons.com\u003e\nSigned-off-by: Adrian Bunk \u003cbunk@stusta.de\u003e\n" }, { "commit": "74add80cbd7fe246c893b93ee75ac59acdd01dd4", "tree": "57ab3f1754bb90fb81721a76b8e342871203a75c", "parents": [ "02a93208edec0d655c9f18613d830dc6afeda7d4" ], "author": { "name": "Roland McGrath", "email": "roland@redhat.com", "time": "Tue May 08 11:19:38 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue May 08 11:35:28 2007 -0700" }, "message": "Remove unused variable in get_unmapped_area\n\nSigned-off-by: Roland McGrath \u003croland@redhat.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4b1d89290b62bb2db476c94c82cf7442aab440c8", "tree": "9db89e2dbf5a0cb222f3d042a5ad167d75df265c", "parents": [ "06abdfb47ee745a4d79721de24260815ec6bca2b" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Sun May 06 14:50:14 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon May 07 12:12:57 2007 -0700" }, "message": "get_unmapped_area doesn\u0027t need hugetlbfs hacks anymore\n\nRemove the hugetlbfs specific hacks in toplevel get_unmapped_area() now that\nall archs and hugetlbfs itself do the right thing for both cases.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nAcked-by: William Irwin \u003cbill.irwin@oracle.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Richard Henderson \u003crth@twiddle.net\u003e\nCc: Ivan Kokshaysky \u003cink@jurassic.park.msu.ru\u003e\nCc: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Kyle McMartin \u003ckyle@mcmartin.ca\u003e\nCc: Grant Grundler \u003cgrundler@parisc-linux.org\u003e\nCc: Matthew Wilcox \u003cwilly@debian.org\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nCc: Adam Litke \u003cagl@us.ibm.com\u003e\nCc: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "06abdfb47ee745a4d79721de24260815ec6bca2b", "tree": "afbf3f7a0f020529317ec115d2b5f62f67c84404", "parents": [ "036e08568cbee4b16e14551e9f004c3d490d6271" ], "author": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Sun May 06 14:50:13 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon May 07 12:12:57 2007 -0700" }, "message": "get_unmapped_area handles MAP_FIXED in generic code\n\ngeneric arch_get_unmapped_area() now handles MAP_FIXED. Now that all\nimplementations have been fixed, change the toplevel get_unmapped_area() to\ncall into arch or drivers for the MAP_FIXED case.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Richard Henderson \u003crth@twiddle.net\u003e\nCc: Ivan Kokshaysky \u003cink@jurassic.park.msu.ru\u003e\nCc: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Kyle McMartin \u003ckyle@mcmartin.ca\u003e\nCc: Grant Grundler \u003cgrundler@parisc-linux.org\u003e\nCc: Matthew Wilcox \u003cwilly@debian.org\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nCc: William Irwin \u003cbill.irwin@oracle.com\u003e\nCc: Adam Litke \u003cagl@us.ibm.com\u003e\nCc: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d6dd61c831226f9cd7750885da04d360d6455101", "tree": "30f84a429821d207f7de5dd6225d3d9515042c0a", "parents": [ "5311ab62cdc7788784971ed816ce85e926f3e994" ], "author": { "name": "Jeremy Fitzhardinge", "email": "jeremy@goop.org", "time": "Wed May 02 19:27:14 2007 +0200" }, "committer": { "name": "Andi Kleen", "email": "andi@basil.nowhere.org", "time": "Wed May 02 19:27:14 2007 +0200" }, "message": "[PATCH] x86: PARAVIRT: add hooks to intercept mm creation and destruction\n\nAdd hooks to allow a paravirt implementation to track the lifetime of\nan mm. Paravirtualization requires three hooks, but only two are\nneeded in common code. They are:\n\narch_dup_mmap, which is called when a new mmap is created at fork\n\narch_exit_mmap, which is called when the last process reference to an\n mm is dropped, which typically happens on exit and exec.\n\nThe third hook is activate_mm, which is called from the arch-specific\nactivate_mm() macro/function, and so doesn\u0027t need stub versions for\nother architectures. It\u0027s called when an mm is first used.\n\nSigned-off-by: Jeremy Fitzhardinge \u003cjeremy@xensource.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nCc: linux-arch@vger.kernel.org\nCc: James Bottomley \u003cJames.Bottomley@SteelEye.com\u003e\nAcked-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "d1af65d13f3625543916a85c86d02826df910fcf", "tree": "6f04906a3837bd92d89751925e2b4937439e74c0", "parents": [ "04a51e66adcdc0de6ffaa488934ce3ffb3818ecf" ], "author": { "name": "David Miller", "email": "davem@davemloft.net", "time": "Wed Feb 28 20:13:13 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Mar 01 14:53:38 2007 -0800" }, "message": "[PATCH] Bug in MM_RB debugging\n\nThe code is seemingly trying to make sure that rb_next() brings us to\nsuccessive increasing vma entries.\n\nBut the two variables, prev and pend, used to perform these checks, are\nnever advanced.\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\nCc: Andrea Arcangeli \u003candrea@novell.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "fa5dc22f8586cc3742413dd05f5cd9e039dfab9e", "tree": "39a97d91e25794f64e3cc03f1d4a8fa2c8ad78d2", "parents": [ "a25700a53f715fde30443e737e52310c6d4a311a" ], "author": { "name": "Roland McGrath", "email": "roland@redhat.com", "time": "Thu Feb 08 14:20:41 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Feb 09 09:25:47 2007 -0800" }, "message": "[PATCH] Add install_special_mapping\n\nThis patch adds a utility function install_special_mapping, for creating a\nspecial vma using a fixed set of preallocated pages as backing, such as for a\nvDSO. This consolidates some nearly identical code used for vDSO mapping\nreimplemented for different architectures.\n\nSigned-off-by: Roland McGrath \u003croland@redhat.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\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": "0d59a01bc461bbab4017ff449b8401151ef44cf6", "tree": "ec388c127883f8dddde3a933eac44a45aca6520c", "parents": [ "bcdddfb66cc998252d34758ce4109cedc0d24a5c" ], "author": { "name": "Adam Litke", "email": "agl@us.ibm.com", "time": "Tue Jan 30 14:35:39 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Jan 30 16:01:35 2007 -0800" }, "message": "[PATCH] Don\u0027t allow the stack to grow into hugetlb reserved regions\n\nWhen expanding the stack, we don\u0027t currently check if the VMA will cross\ninto an area of the address space that is reserved for hugetlb pages.\nSubsequent faults on the expanded portion of such a VMA will confuse the\nlow-level MMU code, resulting in an OOPS. Check for this.\n\nSigned-off-by: Adam Litke \u003cagl@us.ibm.com\u003e\nCc: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nCc: William Lee Irwin III \u003cwli@holomorphy.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d3ac7f892b7d07d61d0895caa4f6e190e43112f8", "tree": "0ff35e7e5ab822b600075d79910d3cc136ba07ef", "parents": [ "f3a43f3f64bff8e205c3702f6b4804d66e306848" ], "author": { "name": "Josef \"Jeff\" Sipek", "email": "jsipek@cs.sunysb.edu", "time": "Fri Dec 08 02:36:44 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Fri Dec 08 08:28:43 2006 -0800" }, "message": "[PATCH] mm: change uses of f_{dentry,vfsmnt} to use f_path\n\nChange all the uses of f_{dentry,vfsmnt} to f_path.{dentry,mnt} in linux/mm/.\n\nSigned-off-by: Josef \"Jeff\" Sipek \u003cjsipek@cs.sunysb.edu\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "e94b1766097d53e6f3ccfb36c8baa562ffeda3fc", "tree": "93fa0a8ab84976d4e89c50768ca8b8878d642a0d", "parents": [ "54e6ecb23951b195d02433a741c7f7cb0b796c78" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Wed Dec 06 20:33:17 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Thu Dec 07 08:39:24 2006 -0800" }, "message": "[PATCH] slab: remove SLAB_KERNEL\n\nSLAB_KERNEL is an alias of GFP_KERNEL.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "cd2579d7aa7bfc966cc271a88e77f8cfc3b0b7ba", "tree": "47687e0e88bf5f5ea266112490a63f55085b8c18", "parents": [ "1f794b6082a5ff88f7c48d1634056026acf806f4" ], "author": { "name": "Hugh Dickins", "email": "hugh@veritas.com", "time": "Tue Nov 14 13:43:38 2006 +0000" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Tue Nov 14 15:15:01 2006 -0800" }, "message": "[PATCH] hugetlb: fix error return for brk() entering a hugepage region\n\nCommit cb07c9a1864a8eac9f3123e428100d5b2a16e65a causes the wrong return\nvalue. is_hugepage_only_range() is a boolean, so we should return\n-EINVAL rather than 1.\n\nAlso - we can use \"mm\" instead of looking up \"current-\u003emm\" again.\n\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "cb07c9a1864a8eac9f3123e428100d5b2a16e65a", "tree": "fadc568154bbe3c1466081b718e9638438c82c46", "parents": [ "68589bc353037f233fe510ad9ff432338c95db66" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Tue Nov 14 02:03:38 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Tue Nov 14 09:09:27 2006 -0800" }, "message": "[PATCH] hugetlb: check for brk() entering a hugepage region\n\nUnlike mmap(), the codepath for brk() creates a vma without first checking\nthat it doesn\u0027t touch a region exclusively reserved for hugepages. On\npowerpc, this can allow it to create a normal page vma in a hugepage\nregion, causing oopses and other badness.\n\nAdd a test to prevent this. With this patch, brk() will simply fail if it\nattempts to move the break into a hugepage reserved region.\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nCc: Adam Litke \u003cagl@us.ibm.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "68589bc353037f233fe510ad9ff432338c95db66", "tree": "dedc58ff66134f54796642917e2a2a26ac6802b0", "parents": [ "69ae9e3ee4ce99140a7db424bebf55d8d180da2f" ], "author": { "name": "Hugh Dickins", "email": "hugh@veritas.com", "time": "Tue Nov 14 02:03:32 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Tue Nov 14 09:09:27 2006 -0800" }, "message": "[PATCH] hugetlb: prepare_hugepage_range check offset too\n\n(David:)\n\nIf hugetlbfs_file_mmap() returns a failure to do_mmap_pgoff() - for example,\nbecause the given file offset is not hugepage aligned - then do_mmap_pgoff\nwill go to the unmap_and_free_vma backout path.\n\nBut at this stage the vma hasn\u0027t been marked as hugepage, and the backout path\nwill call unmap_region() on it. That will eventually call down to the\nnon-hugepage version of unmap_page_range(). On ppc64, at least, that will\ncause serious problems if there are any existing hugepage pagetable entries in\nthe vicinity - for example if there are any other hugepage mappings under the\nsame PUD. unmap_page_range() will trigger a bad_pud() on the hugepage pud\nentries. I suspect this will also cause bad problems on ia64, though I don\u0027t\nhave a machine to test it on.\n\n(Hugh:)\n\nprepare_hugepage_range() should check file offset alignment when it checks\nvirtual address and length, to stop MAP_FIXED with a bad huge offset from\nunmapping before it fails further down. PowerPC should apply the same\nprepare_hugepage_range alignment checks as ia64 and all the others do.\n\nThen none of the alignment checks in hugetlbfs_file_mmap are required (nor\nis the check for too small a mapping); but even so, move up setting of\nVM_HUGETLB and add a comment to warn of what David Gibson discovered - if\nhugetlbfs_file_mmap fails before setting it, do_mmap_pgoff\u0027s unmap_region\nwhen unwinding from error will go the non-huge way, which may cause bad\nbehaviour on architectures (powerpc and ia64) which segregate their huge\nmappings into a separate region of the address space.\n\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nAcked-by: Adam Litke \u003cagl@us.ibm.com\u003e\nAcked-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "80c5606c3b45e0176c32d3108ade1e1cb0b954f3", "tree": "441944cc1c2e47e2d34cabb5313c25e03f3284d3", "parents": [ "a7a0d86f5aa40a2215e36fe21d7911cf718ba428" ], "author": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Oct 15 14:09:55 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Oct 15 14:09:55 2006 -0700" }, "message": "Fix VM_MAYEXEC calculation\n\n.. and clean up the file mapping code while at it. No point in having a\n\"if (file)\" repeated twice, and generally doing similar checks in two\ndifferent sections of the same code\n\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" } ], "next": "972d1a7b140569084439a81265a0f15b74e924e0" }