linux-stable/include/linux/hugetlb.h

370 lines
10 KiB
C
Raw Normal View History

#ifndef _LINUX_HUGETLB_H
#define _LINUX_HUGETLB_H
#include <linux/mm_types.h>
Remove fs.h from mm.h Remove fs.h from mm.h. For this, 1) Uninline vma_wants_writenotify(). It's pretty huge anyway. 2) Add back fs.h or less bloated headers (err.h) to files that need it. As result, on x86_64 allyesconfig, fs.h dependencies cut down from 3929 files rebuilt down to 3444 (-12.3%). Cross-compile tested without regressions on my two usual configs and (sigh): alpha arm-mx1ads mips-bigsur powerpc-ebony alpha-allnoconfig arm-neponset mips-capcella powerpc-g5 alpha-defconfig arm-netwinder mips-cobalt powerpc-holly alpha-up arm-netx mips-db1000 powerpc-iseries arm arm-ns9xxx mips-db1100 powerpc-linkstation arm-assabet arm-omap_h2_1610 mips-db1200 powerpc-lite5200 arm-at91rm9200dk arm-onearm mips-db1500 powerpc-maple arm-at91rm9200ek arm-picotux200 mips-db1550 powerpc-mpc7448_hpc2 arm-at91sam9260ek arm-pleb mips-ddb5477 powerpc-mpc8272_ads arm-at91sam9261ek arm-pnx4008 mips-decstation powerpc-mpc8313_rdb arm-at91sam9263ek arm-pxa255-idp mips-e55 powerpc-mpc832x_mds arm-at91sam9rlek arm-realview mips-emma2rh powerpc-mpc832x_rdb arm-ateb9200 arm-realview-smp mips-excite powerpc-mpc834x_itx arm-badge4 arm-rpc mips-fulong powerpc-mpc834x_itxgp arm-carmeva arm-s3c2410 mips-ip22 powerpc-mpc834x_mds arm-cerfcube arm-shannon mips-ip27 powerpc-mpc836x_mds arm-clps7500 arm-shark mips-ip32 powerpc-mpc8540_ads arm-collie arm-simpad mips-jazz powerpc-mpc8544_ds arm-corgi arm-spitz mips-jmr3927 powerpc-mpc8560_ads arm-csb337 arm-trizeps4 mips-malta powerpc-mpc8568mds arm-csb637 arm-versatile mips-mipssim powerpc-mpc85xx_cds arm-ebsa110 i386 mips-mpc30x powerpc-mpc8641_hpcn arm-edb7211 i386-allnoconfig mips-msp71xx powerpc-mpc866_ads arm-em_x270 i386-defconfig mips-ocelot powerpc-mpc885_ads arm-ep93xx i386-up mips-pb1100 powerpc-pasemi arm-footbridge ia64 mips-pb1500 powerpc-pmac32 arm-fortunet ia64-allnoconfig mips-pb1550 powerpc-ppc64 arm-h3600 ia64-bigsur mips-pnx8550-jbs powerpc-prpmc2800 arm-h7201 ia64-defconfig mips-pnx8550-stb810 powerpc-ps3 arm-h7202 ia64-gensparse mips-qemu powerpc-pseries arm-hackkit ia64-sim mips-rbhma4200 powerpc-up arm-integrator ia64-sn2 mips-rbhma4500 s390 arm-iop13xx ia64-tiger mips-rm200 s390-allnoconfig arm-iop32x ia64-up mips-sb1250-swarm s390-defconfig arm-iop33x ia64-zx1 mips-sead s390-up arm-ixp2000 m68k mips-tb0219 sparc arm-ixp23xx m68k-amiga mips-tb0226 sparc-allnoconfig arm-ixp4xx m68k-apollo mips-tb0287 sparc-defconfig arm-jornada720 m68k-atari mips-workpad sparc-up arm-kafa m68k-bvme6000 mips-wrppmc sparc64 arm-kb9202 m68k-hp300 mips-yosemite sparc64-allnoconfig arm-ks8695 m68k-mac parisc sparc64-defconfig arm-lart m68k-mvme147 parisc-allnoconfig sparc64-up arm-lpd270 m68k-mvme16x parisc-defconfig um-x86_64 arm-lpd7a400 m68k-q40 parisc-up x86_64 arm-lpd7a404 m68k-sun3 powerpc x86_64-allnoconfig arm-lubbock m68k-sun3x powerpc-cell x86_64-defconfig arm-lusl7200 mips powerpc-celleb x86_64-up arm-mainstone mips-atlas powerpc-chrp32 Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-29 22:36:13 +00:00
#include <linux/fs.h>
#include <linux/hugetlb_inline.h>
#include <linux/cgroup.h>
Remove fs.h from mm.h Remove fs.h from mm.h. For this, 1) Uninline vma_wants_writenotify(). It's pretty huge anyway. 2) Add back fs.h or less bloated headers (err.h) to files that need it. As result, on x86_64 allyesconfig, fs.h dependencies cut down from 3929 files rebuilt down to 3444 (-12.3%). Cross-compile tested without regressions on my two usual configs and (sigh): alpha arm-mx1ads mips-bigsur powerpc-ebony alpha-allnoconfig arm-neponset mips-capcella powerpc-g5 alpha-defconfig arm-netwinder mips-cobalt powerpc-holly alpha-up arm-netx mips-db1000 powerpc-iseries arm arm-ns9xxx mips-db1100 powerpc-linkstation arm-assabet arm-omap_h2_1610 mips-db1200 powerpc-lite5200 arm-at91rm9200dk arm-onearm mips-db1500 powerpc-maple arm-at91rm9200ek arm-picotux200 mips-db1550 powerpc-mpc7448_hpc2 arm-at91sam9260ek arm-pleb mips-ddb5477 powerpc-mpc8272_ads arm-at91sam9261ek arm-pnx4008 mips-decstation powerpc-mpc8313_rdb arm-at91sam9263ek arm-pxa255-idp mips-e55 powerpc-mpc832x_mds arm-at91sam9rlek arm-realview mips-emma2rh powerpc-mpc832x_rdb arm-ateb9200 arm-realview-smp mips-excite powerpc-mpc834x_itx arm-badge4 arm-rpc mips-fulong powerpc-mpc834x_itxgp arm-carmeva arm-s3c2410 mips-ip22 powerpc-mpc834x_mds arm-cerfcube arm-shannon mips-ip27 powerpc-mpc836x_mds arm-clps7500 arm-shark mips-ip32 powerpc-mpc8540_ads arm-collie arm-simpad mips-jazz powerpc-mpc8544_ds arm-corgi arm-spitz mips-jmr3927 powerpc-mpc8560_ads arm-csb337 arm-trizeps4 mips-malta powerpc-mpc8568mds arm-csb637 arm-versatile mips-mipssim powerpc-mpc85xx_cds arm-ebsa110 i386 mips-mpc30x powerpc-mpc8641_hpcn arm-edb7211 i386-allnoconfig mips-msp71xx powerpc-mpc866_ads arm-em_x270 i386-defconfig mips-ocelot powerpc-mpc885_ads arm-ep93xx i386-up mips-pb1100 powerpc-pasemi arm-footbridge ia64 mips-pb1500 powerpc-pmac32 arm-fortunet ia64-allnoconfig mips-pb1550 powerpc-ppc64 arm-h3600 ia64-bigsur mips-pnx8550-jbs powerpc-prpmc2800 arm-h7201 ia64-defconfig mips-pnx8550-stb810 powerpc-ps3 arm-h7202 ia64-gensparse mips-qemu powerpc-pseries arm-hackkit ia64-sim mips-rbhma4200 powerpc-up arm-integrator ia64-sn2 mips-rbhma4500 s390 arm-iop13xx ia64-tiger mips-rm200 s390-allnoconfig arm-iop32x ia64-up mips-sb1250-swarm s390-defconfig arm-iop33x ia64-zx1 mips-sead s390-up arm-ixp2000 m68k mips-tb0219 sparc arm-ixp23xx m68k-amiga mips-tb0226 sparc-allnoconfig arm-ixp4xx m68k-apollo mips-tb0287 sparc-defconfig arm-jornada720 m68k-atari mips-workpad sparc-up arm-kafa m68k-bvme6000 mips-wrppmc sparc64 arm-kb9202 m68k-hp300 mips-yosemite sparc64-allnoconfig arm-ks8695 m68k-mac parisc sparc64-defconfig arm-lart m68k-mvme147 parisc-allnoconfig sparc64-up arm-lpd270 m68k-mvme16x parisc-defconfig um-x86_64 arm-lpd7a400 m68k-q40 parisc-up x86_64 arm-lpd7a404 m68k-sun3 powerpc x86_64-allnoconfig arm-lubbock m68k-sun3x powerpc-cell x86_64-defconfig arm-lusl7200 mips powerpc-celleb x86_64-up arm-mainstone mips-atlas powerpc-chrp32 Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-29 22:36:13 +00:00
struct ctl_table;
struct user_struct;
struct mmu_gather;
#ifdef CONFIG_HUGETLB_PAGE
#include <linux/mempolicy.h>
#include <linux/shm.h>
#include <asm/tlbflush.h>
hugepages: fix use after free bug in "quota" handling hugetlbfs_{get,put}_quota() are badly named. They don't interact with the general quota handling code, and they don't much resemble its behaviour. Rather than being about maintaining limits on on-disk block usage by particular users, they are instead about maintaining limits on in-memory page usage (including anonymous MAP_PRIVATE copied-on-write pages) associated with a particular hugetlbfs filesystem instance. Worse, they work by having callbacks to the hugetlbfs filesystem code from the low-level page handling code, in particular from free_huge_page(). This is a layering violation of itself, but more importantly, if the kernel does a get_user_pages() on hugepages (which can happen from KVM amongst others), then the free_huge_page() can be delayed until after the associated inode has already been freed. If an unmount occurs at the wrong time, even the hugetlbfs superblock where the "quota" limits are stored may have been freed. Andrew Barry proposed a patch to fix this by having hugepages, instead of storing a pointer to their address_space and reaching the superblock from there, had the hugepages store pointers directly to the superblock, bumping the reference count as appropriate to avoid it being freed. Andrew Morton rejected that version, however, on the grounds that it made the existing layering violation worse. This is a reworked version of Andrew's patch, which removes the extra, and some of the existing, layering violation. It works by introducing the concept of a hugepage "subpool" at the lower hugepage mm layer - that is a finite logical pool of hugepages to allocate from. hugetlbfs now creates a subpool for each filesystem instance with a page limit set, and a pointer to the subpool gets added to each allocated hugepage, instead of the address_space pointer used now. The subpool has its own lifetime and is only freed once all pages in it _and_ all other references to it (i.e. superblocks) are gone. subpools are optional - a NULL subpool pointer is taken by the code to mean that no subpool limits are in effect. Previous discussion of this bug found in: "Fix refcounting in hugetlbfs quota handling.". See: https://lkml.org/lkml/2011/8/11/28 or http://marc.info/?l=linux-mm&m=126928970510627&w=1 v2: Fixed a bug spotted by Hillf Danton, and removed the extra parameter to alloc_huge_page() - since it already takes the vma, it is not necessary. Signed-off-by: Andrew Barry <abarry@cray.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 23:34:12 +00:00
struct hugepage_subpool {
spinlock_t lock;
long count;
long max_hpages, used_hpages;
};
extern spinlock_t hugetlb_lock;
extern int hugetlb_max_hstate __read_mostly;
#define for_each_hstate(h) \
for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++)
hugepages: fix use after free bug in "quota" handling hugetlbfs_{get,put}_quota() are badly named. They don't interact with the general quota handling code, and they don't much resemble its behaviour. Rather than being about maintaining limits on on-disk block usage by particular users, they are instead about maintaining limits on in-memory page usage (including anonymous MAP_PRIVATE copied-on-write pages) associated with a particular hugetlbfs filesystem instance. Worse, they work by having callbacks to the hugetlbfs filesystem code from the low-level page handling code, in particular from free_huge_page(). This is a layering violation of itself, but more importantly, if the kernel does a get_user_pages() on hugepages (which can happen from KVM amongst others), then the free_huge_page() can be delayed until after the associated inode has already been freed. If an unmount occurs at the wrong time, even the hugetlbfs superblock where the "quota" limits are stored may have been freed. Andrew Barry proposed a patch to fix this by having hugepages, instead of storing a pointer to their address_space and reaching the superblock from there, had the hugepages store pointers directly to the superblock, bumping the reference count as appropriate to avoid it being freed. Andrew Morton rejected that version, however, on the grounds that it made the existing layering violation worse. This is a reworked version of Andrew's patch, which removes the extra, and some of the existing, layering violation. It works by introducing the concept of a hugepage "subpool" at the lower hugepage mm layer - that is a finite logical pool of hugepages to allocate from. hugetlbfs now creates a subpool for each filesystem instance with a page limit set, and a pointer to the subpool gets added to each allocated hugepage, instead of the address_space pointer used now. The subpool has its own lifetime and is only freed once all pages in it _and_ all other references to it (i.e. superblocks) are gone. subpools are optional - a NULL subpool pointer is taken by the code to mean that no subpool limits are in effect. Previous discussion of this bug found in: "Fix refcounting in hugetlbfs quota handling.". See: https://lkml.org/lkml/2011/8/11/28 or http://marc.info/?l=linux-mm&m=126928970510627&w=1 v2: Fixed a bug spotted by Hillf Danton, and removed the extra parameter to alloc_huge_page() - since it already takes the vma, it is not necessary. Signed-off-by: Andrew Barry <abarry@cray.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 23:34:12 +00:00
struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
void hugepage_put_subpool(struct hugepage_subpool *spool);
mm: introduce PageHuge() for testing huge/gigantic pages A series of patches to enhance the /proc/pagemap interface and to add a userspace executable which can be used to present the pagemap data. Export 10 more flags to end users (and more for kernel developers): 11. KPF_MMAP (pseudo flag) memory mapped page 12. KPF_ANON (pseudo flag) memory mapped page (anonymous) 13. KPF_SWAPCACHE page is in swap cache 14. KPF_SWAPBACKED page is swap/RAM backed 15. KPF_COMPOUND_HEAD (*) 16. KPF_COMPOUND_TAIL (*) 17. KPF_HUGE hugeTLB pages 18. KPF_UNEVICTABLE page is in the unevictable LRU list 19. KPF_HWPOISON hardware detected corruption 20. KPF_NOPAGE (pseudo flag) no page frame at the address (*) For compound pages, exporting _both_ head/tail info enables users to tell where a compound page starts/ends, and its order. a simple demo of the page-types tool # ./page-types -h page-types [options] -r|--raw Raw mode, for kernel developers -a|--addr addr-spec Walk a range of pages -b|--bits bits-spec Walk pages with specified bits -l|--list Show page details in ranges -L|--list-each Show page details one by one -N|--no-summary Don't show summay info -h|--help Show this usage message addr-spec: N one page at offset N (unit: pages) N+M pages range from N to N+M-1 N,M pages range from N to M-1 N, pages range from N to end ,M pages range from 0 to M bits-spec: bit1,bit2 (flags & (bit1|bit2)) != 0 bit1,bit2=bit1 (flags & (bit1|bit2)) == bit1 bit1,~bit2 (flags & (bit1|bit2)) == bit1 =bit1,bit2 flags == (bit1|bit2) bit-names: locked error referenced uptodate dirty lru active slab writeback reclaim buddy mmap anonymous swapcache swapbacked compound_head compound_tail huge unevictable hwpoison nopage reserved(r) mlocked(r) mappedtodisk(r) private(r) private_2(r) owner_private(r) arch(r) uncached(r) readahead(o) slob_free(o) slub_frozen(o) slub_debug(o) (r) raw mode bits (o) overloaded bits # ./page-types flags page-count MB symbolic-flags long-symbolic-flags 0x0000000000000000 487369 1903 _________________________________ 0x0000000000000014 5 0 __R_D____________________________ referenced,dirty 0x0000000000000020 1 0 _____l___________________________ lru 0x0000000000000024 34 0 __R__l___________________________ referenced,lru 0x0000000000000028 3838 14 ___U_l___________________________ uptodate,lru 0x0001000000000028 48 0 ___U_l_______________________I___ uptodate,lru,readahead 0x000000000000002c 6478 25 __RU_l___________________________ referenced,uptodate,lru 0x000100000000002c 47 0 __RU_l_______________________I___ referenced,uptodate,lru,readahead 0x0000000000000040 8344 32 ______A__________________________ active 0x0000000000000060 1 0 _____lA__________________________ lru,active 0x0000000000000068 348 1 ___U_lA__________________________ uptodate,lru,active 0x0001000000000068 12 0 ___U_lA______________________I___ uptodate,lru,active,readahead 0x000000000000006c 988 3 __RU_lA__________________________ referenced,uptodate,lru,active 0x000100000000006c 48 0 __RU_lA______________________I___ referenced,uptodate,lru,active,readahead 0x0000000000004078 1 0 ___UDlA_______b__________________ uptodate,dirty,lru,active,swapbacked 0x000000000000407c 34 0 __RUDlA_______b__________________ referenced,uptodate,dirty,lru,active,swapbacked 0x0000000000000400 503 1 __________B______________________ buddy 0x0000000000000804 1 0 __R________M_____________________ referenced,mmap 0x0000000000000828 1029 4 ___U_l_____M_____________________ uptodate,lru,mmap 0x0001000000000828 43 0 ___U_l_____M_________________I___ uptodate,lru,mmap,readahead 0x000000000000082c 382 1 __RU_l_____M_____________________ referenced,uptodate,lru,mmap 0x000100000000082c 12 0 __RU_l_____M_________________I___ referenced,uptodate,lru,mmap,readahead 0x0000000000000868 192 0 ___U_lA____M_____________________ uptodate,lru,active,mmap 0x0001000000000868 12 0 ___U_lA____M_________________I___ uptodate,lru,active,mmap,readahead 0x000000000000086c 800 3 __RU_lA____M_____________________ referenced,uptodate,lru,active,mmap 0x000100000000086c 31 0 __RU_lA____M_________________I___ referenced,uptodate,lru,active,mmap,readahead 0x0000000000004878 2 0 ___UDlA____M__b__________________ uptodate,dirty,lru,active,mmap,swapbacked 0x0000000000001000 492 1 ____________a____________________ anonymous 0x0000000000005808 4 0 ___U_______Ma_b__________________ uptodate,mmap,anonymous,swapbacked 0x0000000000005868 2839 11 ___U_lA____Ma_b__________________ uptodate,lru,active,mmap,anonymous,swapbacked 0x000000000000586c 30 0 __RU_lA____Ma_b__________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked total 513968 2007 # ./page-types -r flags page-count MB symbolic-flags long-symbolic-flags 0x0000000000000000 468002 1828 _________________________________ 0x0000000100000000 19102 74 _____________________r___________ reserved 0x0000000000008000 41 0 _______________H_________________ compound_head 0x0000000000010000 188 0 ________________T________________ compound_tail 0x0000000000008014 1 0 __R_D__________H_________________ referenced,dirty,compound_head 0x0000000000010014 4 0 __R_D___________T________________ referenced,dirty,compound_tail 0x0000000000000020 1 0 _____l___________________________ lru 0x0000000800000024 34 0 __R__l__________________P________ referenced,lru,private 0x0000000000000028 3794 14 ___U_l___________________________ uptodate,lru 0x0001000000000028 46 0 ___U_l_______________________I___ uptodate,lru,readahead 0x0000000400000028 44 0 ___U_l_________________d_________ uptodate,lru,mappedtodisk 0x0001000400000028 2 0 ___U_l_________________d_____I___ uptodate,lru,mappedtodisk,readahead 0x000000000000002c 6434 25 __RU_l___________________________ referenced,uptodate,lru 0x000100000000002c 47 0 __RU_l_______________________I___ referenced,uptodate,lru,readahead 0x000000040000002c 14 0 __RU_l_________________d_________ referenced,uptodate,lru,mappedtodisk 0x000000080000002c 30 0 __RU_l__________________P________ referenced,uptodate,lru,private 0x0000000800000040 8124 31 ______A_________________P________ active,private 0x0000000000000040 219 0 ______A__________________________ active 0x0000000800000060 1 0 _____lA_________________P________ lru,active,private 0x0000000000000068 322 1 ___U_lA__________________________ uptodate,lru,active 0x0001000000000068 12 0 ___U_lA______________________I___ uptodate,lru,active,readahead 0x0000000400000068 13 0 ___U_lA________________d_________ uptodate,lru,active,mappedtodisk 0x0000000800000068 12 0 ___U_lA_________________P________ uptodate,lru,active,private 0x000000000000006c 977 3 __RU_lA__________________________ referenced,uptodate,lru,active 0x000100000000006c 48 0 __RU_lA______________________I___ referenced,uptodate,lru,active,readahead 0x000000040000006c 5 0 __RU_lA________________d_________ referenced,uptodate,lru,active,mappedtodisk 0x000000080000006c 3 0 __RU_lA_________________P________ referenced,uptodate,lru,active,private 0x0000000c0000006c 3 0 __RU_lA________________dP________ referenced,uptodate,lru,active,mappedtodisk,private 0x0000000c00000068 1 0 ___U_lA________________dP________ uptodate,lru,active,mappedtodisk,private 0x0000000000004078 1 0 ___UDlA_______b__________________ uptodate,dirty,lru,active,swapbacked 0x000000000000407c 34 0 __RUDlA_______b__________________ referenced,uptodate,dirty,lru,active,swapbacked 0x0000000000000400 538 2 __________B______________________ buddy 0x0000000000000804 1 0 __R________M_____________________ referenced,mmap 0x0000000000000828 1029 4 ___U_l_____M_____________________ uptodate,lru,mmap 0x0001000000000828 43 0 ___U_l_____M_________________I___ uptodate,lru,mmap,readahead 0x000000000000082c 382 1 __RU_l_____M_____________________ referenced,uptodate,lru,mmap 0x000100000000082c 12 0 __RU_l_____M_________________I___ referenced,uptodate,lru,mmap,readahead 0x0000000000000868 192 0 ___U_lA____M_____________________ uptodate,lru,active,mmap 0x0001000000000868 12 0 ___U_lA____M_________________I___ uptodate,lru,active,mmap,readahead 0x000000000000086c 800 3 __RU_lA____M_____________________ referenced,uptodate,lru,active,mmap 0x000100000000086c 31 0 __RU_lA____M_________________I___ referenced,uptodate,lru,active,mmap,readahead 0x0000000000004878 2 0 ___UDlA____M__b__________________ uptodate,dirty,lru,active,mmap,swapbacked 0x0000000000001000 492 1 ____________a____________________ anonymous 0x0000000000005008 2 0 ___U________a_b__________________ uptodate,anonymous,swapbacked 0x0000000000005808 4 0 ___U_______Ma_b__________________ uptodate,mmap,anonymous,swapbacked 0x000000000000580c 1 0 __RU_______Ma_b__________________ referenced,uptodate,mmap,anonymous,swapbacked 0x0000000000005868 2839 11 ___U_lA____Ma_b__________________ uptodate,lru,active,mmap,anonymous,swapbacked 0x000000000000586c 29 0 __RU_lA____Ma_b__________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked total 513968 2007 # ./page-types --raw --list --no-summary --bits reserved offset count flags 0 15 _____________________r___________ 31 4 _____________________r___________ 159 97 _____________________r___________ 4096 2067 _____________________r___________ 6752 2390 _____________________r___________ 9355 3 _____________________r___________ 9728 14526 _____________________r___________ This patch: Introduce PageHuge(), which identifies huge/gigantic pages by their dedicated compound destructor functions. Also move prep_compound_gigantic_page() to hugetlb.c and make __free_pages_ok() non-static. Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Matt Mackall <mpm@selenic.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-16 22:32:22 +00:00
int PageHuge(struct page *page);
hugetlb: reserve huge pages for reliable MAP_PRIVATE hugetlbfs mappings until fork() This patch reserves huge pages at mmap() time for MAP_PRIVATE mappings in a similar manner to the reservations taken for MAP_SHARED mappings. The reserve count is accounted both globally and on a per-VMA basis for private mappings. This guarantees that a process that successfully calls mmap() will successfully fault all pages in the future unless fork() is called. The characteristics of private mappings of hugetlbfs files behaviour after this patch are; 1. The process calling mmap() is guaranteed to succeed all future faults until it forks(). 2. On fork(), the parent may die due to SIGKILL on writes to the private mapping if enough pages are not available for the COW. For reasonably reliable behaviour in the face of a small huge page pool, children of hugepage-aware processes should not reference the mappings; such as might occur when fork()ing to exec(). 3. On fork(), the child VMAs inherit no reserves. Reads on pages already faulted by the parent will succeed. Successful writes will depend on enough huge pages being free in the pool. 4. Quotas of the hugetlbfs mount are checked at reserve time for the mapper and at fault time otherwise. Before this patch, all reads or writes in the child potentially needs page allocations that can later lead to the death of the parent. This applies to reads and writes of uninstantiated pages as well as COW. After the patch it is only a write to an instantiated page that causes problems. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Adam Litke <agl@us.ibm.com> Cc: Andy Whitcroft <apw@shadowen.org> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:27:23 +00:00
void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
int hugetlb_treat_movable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
hugetlb: derive huge pages nodes allowed from task mempolicy This patch derives a "nodes_allowed" node mask from the numa mempolicy of the task modifying the number of persistent huge pages to control the allocation, freeing and adjusting of surplus huge pages when the pool page count is modified via the new sysctl or sysfs attribute "nr_hugepages_mempolicy". The nodes_allowed mask is derived as follows: * For "default" [NULL] task mempolicy, a NULL nodemask_t pointer is produced. This will cause the hugetlb subsystem to use node_online_map as the "nodes_allowed". This preserves the behavior before this patch. * For "preferred" mempolicy, including explicit local allocation, a nodemask with the single preferred node will be produced. "local" policy will NOT track any internode migrations of the task adjusting nr_hugepages. * For "bind" and "interleave" policy, the mempolicy's nodemask will be used. * Other than to inform the construction of the nodes_allowed node mask, the actual mempolicy mode is ignored. That is, all modes behave like interleave over the resulting nodes_allowed mask with no "fallback". See the updated documentation [next patch] for more information about the implications of this patch. Examples: Starting with: Node 0 HugePages_Total: 0 Node 1 HugePages_Total: 0 Node 2 HugePages_Total: 0 Node 3 HugePages_Total: 0 Default behavior [with or without this patch] balances persistent hugepage allocation across nodes [with sufficient contiguous memory]: sysctl vm.nr_hugepages[_mempolicy]=32 yields: Node 0 HugePages_Total: 8 Node 1 HugePages_Total: 8 Node 2 HugePages_Total: 8 Node 3 HugePages_Total: 8 Of course, we only have nr_hugepages_mempolicy with the patch, but with default mempolicy, nr_hugepages_mempolicy behaves the same as nr_hugepages. Applying mempolicy--e.g., with numactl [using '-m' a.k.a. '--membind' because it allows multiple nodes to be specified and it's easy to type]--we can allocate huge pages on individual nodes or sets of nodes. So, starting from the condition above, with 8 huge pages per node, add 8 more to node 2 using: numactl -m 2 sysctl vm.nr_hugepages_mempolicy=40 This yields: Node 0 HugePages_Total: 8 Node 1 HugePages_Total: 8 Node 2 HugePages_Total: 16 Node 3 HugePages_Total: 8 The incremental 8 huge pages were restricted to node 2 by the specified mempolicy. Similarly, we can use mempolicy to free persistent huge pages from specified nodes: numactl -m 0,1 sysctl vm.nr_hugepages_mempolicy=32 yields: Node 0 HugePages_Total: 4 Node 1 HugePages_Total: 4 Node 2 HugePages_Total: 16 Node 3 HugePages_Total: 8 The 8 huge pages freed were balanced over nodes 0 and 1. [rientjes@google.com: accomodate reworked NODEMASK_ALLOC] Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Andi Kleen <andi@firstfloor.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Randy Dunlap <randy.dunlap@oracle.com> Cc: Nishanth Aravamudan <nacc@us.ibm.com> Cc: Adam Litke <agl@us.ibm.com> Cc: Andy Whitcroft <apw@canonical.com> Cc: Eric Whitney <eric.whitney@hp.com> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 01:58:21 +00:00
#ifdef CONFIG_NUMA
int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
#endif
int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
struct page **, struct vm_area_struct **,
unsigned long *, int *, int, unsigned int flags);
hugetlb: guarantee that COW faults for a process that called mmap(MAP_PRIVATE) on hugetlbfs will succeed After patch 2 in this series, a process that successfully calls mmap() for a MAP_PRIVATE mapping will be guaranteed to successfully fault until a process calls fork(). At that point, the next write fault from the parent could fail due to COW if the child still has a reference. We only reserve pages for the parent but a copy must be made to avoid leaking data from the parent to the child after fork(). Reserves could be taken for both parent and child at fork time to guarantee faults but if the mapping is large it is highly likely we will not have sufficient pages for the reservation, and it is common to fork only to exec() immediatly after. A failure here would be very undesirable. Note that the current behaviour of mainline with MAP_PRIVATE pages is pretty bad. The following situation is allowed to occur today. 1. Process calls mmap(MAP_PRIVATE) 2. Process calls mlock() to fault all pages and makes sure it succeeds 3. Process forks() 4. Process writes to MAP_PRIVATE mapping while child still exists 5. If the COW fails at this point, the process gets SIGKILLed even though it had taken care to ensure the pages existed This patch improves the situation by guaranteeing the reliability of the process that successfully calls mmap(). When the parent performs COW, it will try to satisfy the allocation without using reserves. If that fails the parent will steal the page leaving any children without a page. Faults from the child after that point will result in failure. If the child COW happens first, an attempt will be made to allocate the page without reserves and the child will get SIGKILLed on failure. To summarise the new behaviour: 1. If the original mapper performs COW on a private mapping with multiple references, it will attempt to allocate a hugepage from the pool or the buddy allocator without using the existing reserves. On fail, VMAs mapping the same area are traversed and the page being COW'd is unmapped where found. It will then steal the original page as the last mapper in the normal way. 2. The VMAs the pages were unmapped from are flagged to note that pages with data no longer exist. Future no-page faults on those VMAs will terminate the process as otherwise it would appear that data was corrupted. A warning is printed to the console that this situation occured. 2. If the child performs COW first, it will attempt to satisfy the COW from the pool if there are enough pages or via the buddy allocator if overcommit is allowed and the buddy allocator can satisfy the request. If it fails, the child will be killed. If the pool is large enough, existing applications will not notice that the reserves were a factor. Existing applications depending on the no-reserves been set are unlikely to exist as for much of the history of hugetlbfs, pages were prefaulted at mmap(), allocating the pages at that point or failing the mmap(). [npiggin@suse.de: fix CONFIG_HUGETLB=n build] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Adam Litke <agl@us.ibm.com> Cc: Andy Whitcroft <apw@shadowen.org> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:27:25 +00:00
void unmap_hugepage_range(struct vm_area_struct *,
unsigned long, unsigned long, struct page *);
mm: hugetlbfs: close race during teardown of hugetlbfs shared page tables If a process creates a large hugetlbfs mapping that is eligible for page table sharing and forks heavily with children some of whom fault and others which destroy the mapping then it is possible for page tables to get corrupted. Some teardowns of the mapping encounter a "bad pmd" and output a message to the kernel log. The final teardown will trigger a BUG_ON in mm/filemap.c. This was reproduced in 3.4 but is known to have existed for a long time and goes back at least as far as 2.6.37. It was probably was introduced in 2.6.20 by [39dde65c: shared page table for hugetlb page]. The messages look like this; [ ..........] Lots of bad pmd messages followed by this [ 127.164256] mm/memory.c:391: bad pmd ffff880412e04fe8(80000003de4000e7). [ 127.164257] mm/memory.c:391: bad pmd ffff880412e04ff0(80000003de6000e7). [ 127.164258] mm/memory.c:391: bad pmd ffff880412e04ff8(80000003de0000e7). [ 127.186778] ------------[ cut here ]------------ [ 127.186781] kernel BUG at mm/filemap.c:134! [ 127.186782] invalid opcode: 0000 [#1] SMP [ 127.186783] CPU 7 [ 127.186784] Modules linked in: af_packet cpufreq_conservative cpufreq_userspace cpufreq_powersave acpi_cpufreq mperf ext3 jbd dm_mod coretemp crc32c_intel usb_storage ghash_clmulni_intel aesni_intel i2c_i801 r8169 mii uas sr_mod cdrom sg iTCO_wdt iTCO_vendor_support shpchp serio_raw cryptd aes_x86_64 e1000e pci_hotplug dcdbas aes_generic container microcode ext4 mbcache jbd2 crc16 sd_mod crc_t10dif i915 drm_kms_helper drm i2c_algo_bit ehci_hcd ahci libahci usbcore rtc_cmos usb_common button i2c_core intel_agp video intel_gtt fan processor thermal thermal_sys hwmon ata_generic pata_atiixp libata scsi_mod [ 127.186801] [ 127.186802] Pid: 9017, comm: hugetlbfs-test Not tainted 3.4.0-autobuild #53 Dell Inc. OptiPlex 990/06D7TR [ 127.186804] RIP: 0010:[<ffffffff810ed6ce>] [<ffffffff810ed6ce>] __delete_from_page_cache+0x15e/0x160 [ 127.186809] RSP: 0000:ffff8804144b5c08 EFLAGS: 00010002 [ 127.186810] RAX: 0000000000000001 RBX: ffffea000a5c9000 RCX: 00000000ffffffc0 [ 127.186811] RDX: 0000000000000000 RSI: 0000000000000009 RDI: ffff88042dfdad00 [ 127.186812] RBP: ffff8804144b5c18 R08: 0000000000000009 R09: 0000000000000003 [ 127.186813] R10: 0000000000000000 R11: 000000000000002d R12: ffff880412ff83d8 [ 127.186814] R13: ffff880412ff83d8 R14: 0000000000000000 R15: ffff880412ff83d8 [ 127.186815] FS: 00007fe18ed2c700(0000) GS:ffff88042dce0000(0000) knlGS:0000000000000000 [ 127.186816] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 127.186817] CR2: 00007fe340000503 CR3: 0000000417a14000 CR4: 00000000000407e0 [ 127.186818] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 127.186819] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 127.186820] Process hugetlbfs-test (pid: 9017, threadinfo ffff8804144b4000, task ffff880417f803c0) [ 127.186821] Stack: [ 127.186822] ffffea000a5c9000 0000000000000000 ffff8804144b5c48 ffffffff810ed83b [ 127.186824] ffff8804144b5c48 000000000000138a 0000000000001387 ffff8804144b5c98 [ 127.186825] ffff8804144b5d48 ffffffff811bc925 ffff8804144b5cb8 0000000000000000 [ 127.186827] Call Trace: [ 127.186829] [<ffffffff810ed83b>] delete_from_page_cache+0x3b/0x80 [ 127.186832] [<ffffffff811bc925>] truncate_hugepages+0x115/0x220 [ 127.186834] [<ffffffff811bca43>] hugetlbfs_evict_inode+0x13/0x30 [ 127.186837] [<ffffffff811655c7>] evict+0xa7/0x1b0 [ 127.186839] [<ffffffff811657a3>] iput_final+0xd3/0x1f0 [ 127.186840] [<ffffffff811658f9>] iput+0x39/0x50 [ 127.186842] [<ffffffff81162708>] d_kill+0xf8/0x130 [ 127.186843] [<ffffffff81162812>] dput+0xd2/0x1a0 [ 127.186845] [<ffffffff8114e2d0>] __fput+0x170/0x230 [ 127.186848] [<ffffffff81236e0e>] ? rb_erase+0xce/0x150 [ 127.186849] [<ffffffff8114e3ad>] fput+0x1d/0x30 [ 127.186851] [<ffffffff81117db7>] remove_vma+0x37/0x80 [ 127.186853] [<ffffffff81119182>] do_munmap+0x2d2/0x360 [ 127.186855] [<ffffffff811cc639>] sys_shmdt+0xc9/0x170 [ 127.186857] [<ffffffff81410a39>] system_call_fastpath+0x16/0x1b [ 127.186858] Code: 0f 1f 44 00 00 48 8b 43 08 48 8b 00 48 8b 40 28 8b b0 40 03 00 00 85 f6 0f 88 df fe ff ff 48 89 df e8 e7 cb 05 00 e9 d2 fe ff ff <0f> 0b 55 83 e2 fd 48 89 e5 48 83 ec 30 48 89 5d d8 4c 89 65 e0 [ 127.186868] RIP [<ffffffff810ed6ce>] __delete_from_page_cache+0x15e/0x160 [ 127.186870] RSP <ffff8804144b5c08> [ 127.186871] ---[ end trace 7cbac5d1db69f426 ]--- The bug is a race and not always easy to reproduce. To reproduce it I was doing the following on a single socket I7-based machine with 16G of RAM. $ hugeadm --pool-pages-max DEFAULT:13G $ echo $((18*1048576*1024)) > /proc/sys/kernel/shmmax $ echo $((18*1048576*1024)) > /proc/sys/kernel/shmall $ for i in `seq 1 9000`; do ./hugetlbfs-test; done On my particular machine, it usually triggers within 10 minutes but enabling debug options can change the timing such that it never hits. Once the bug is triggered, the machine is in trouble and needs to be rebooted. The machine will respond but processes accessing proc like "ps aux" will hang due to the BUG_ON. shutdown will also hang and needs a hard reset or a sysrq-b. The basic problem is a race between page table sharing and teardown. For the most part page table sharing depends on i_mmap_mutex. In some cases, it is also taking the mm->page_table_lock for the PTE updates but with shared page tables, it is the i_mmap_mutex that is more important. Unfortunately it appears to be also insufficient. Consider the following situation Process A Process B --------- --------- hugetlb_fault shmdt LockWrite(mmap_sem) do_munmap unmap_region unmap_vmas unmap_single_vma unmap_hugepage_range Lock(i_mmap_mutex) Lock(mm->page_table_lock) huge_pmd_unshare/unmap tables <--- (1) Unlock(mm->page_table_lock) Unlock(i_mmap_mutex) huge_pte_alloc ... Lock(i_mmap_mutex) ... vma_prio_walk, find svma, spte ... Lock(mm->page_table_lock) ... share spte ... Unlock(mm->page_table_lock) ... Unlock(i_mmap_mutex) ... hugetlb_no_page <--- (2) free_pgtables unlink_file_vma hugetlb_free_pgd_range remove_vma_list In this scenario, it is possible for Process A to share page tables with Process B that is trying to tear them down. The i_mmap_mutex on its own does not prevent Process A walking Process B's page tables. At (1) above, the page tables are not shared yet so it unmaps the PMDs. Process A sets up page table sharing and at (2) faults a new entry. Process B then trips up on it in free_pgtables. This patch fixes the problem by adding a new function __unmap_hugepage_range_final that is only called when the VMA is about to be destroyed. This function clears VM_MAYSHARE during unmap_hugepage_range() under the i_mmap_mutex. This makes the VMA ineligible for sharing and avoids the race. Superficially this looks like it would then be vunerable to truncate and madvise issues but hugetlbfs has its own truncate handlers so does not use unmap_mapping_range() and does not support madvise(DONTNEED). This should be treated as a -stable candidate if it is merged. Test program is as follows. The test case was mostly written by Michal Hocko with a few minor changes to reproduce this bug. ==== CUT HERE ==== static size_t huge_page_size = (2UL << 20); static size_t nr_huge_page_A = 512; static size_t nr_huge_page_B = 5632; unsigned int get_random(unsigned int max) { struct timeval tv; gettimeofday(&tv, NULL); srandom(tv.tv_usec); return random() % max; } static void play(void *addr, size_t size) { unsigned char *start = addr, *end = start + size, *a; start += get_random(size/2); /* we could itterate on huge pages but let's give it more time. */ for (a = start; a < end; a += 4096) *a = 0; } int main(int argc, char **argv) { key_t key = IPC_PRIVATE; size_t sizeA = nr_huge_page_A * huge_page_size; size_t sizeB = nr_huge_page_B * huge_page_size; int shmidA, shmidB; void *addrA = NULL, *addrB = NULL; int nr_children = 300, n = 0; if ((shmidA = shmget(key, sizeA, IPC_CREAT|SHM_HUGETLB|0660)) == -1) { perror("shmget:"); return 1; } if ((addrA = shmat(shmidA, addrA, SHM_R|SHM_W)) == (void *)-1UL) { perror("shmat"); return 1; } if ((shmidB = shmget(key, sizeB, IPC_CREAT|SHM_HUGETLB|0660)) == -1) { perror("shmget:"); return 1; } if ((addrB = shmat(shmidB, addrB, SHM_R|SHM_W)) == (void *)-1UL) { perror("shmat"); return 1; } fork_child: switch(fork()) { case 0: switch (n%3) { case 0: play(addrA, sizeA); break; case 1: play(addrB, sizeB); break; case 2: break; } break; case -1: perror("fork:"); break; default: if (++n < nr_children) goto fork_child; play(addrA, sizeA); break; } shmdt(addrA); shmdt(addrB); do { wait(NULL); } while (--n > 0); shmctl(shmidA, IPC_RMID, NULL); shmctl(shmidB, IPC_RMID, NULL); return 0; } [akpm@linux-foundation.org: name the declaration's args, fix CONFIG_HUGETLBFS=n build] Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 23:46:20 +00:00
void __unmap_hugepage_range_final(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct page *ref_page);
void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct page *ref_page);
int hugetlb_prefault(struct address_space *, struct vm_area_struct *);
void hugetlb_report_meminfo(struct seq_file *);
int hugetlb_report_node_meminfo(int, char *);
unsigned long hugetlb_total_pages(void);
int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, unsigned int flags);
hugetlb: reserve huge pages for reliable MAP_PRIVATE hugetlbfs mappings until fork() This patch reserves huge pages at mmap() time for MAP_PRIVATE mappings in a similar manner to the reservations taken for MAP_SHARED mappings. The reserve count is accounted both globally and on a per-VMA basis for private mappings. This guarantees that a process that successfully calls mmap() will successfully fault all pages in the future unless fork() is called. The characteristics of private mappings of hugetlbfs files behaviour after this patch are; 1. The process calling mmap() is guaranteed to succeed all future faults until it forks(). 2. On fork(), the parent may die due to SIGKILL on writes to the private mapping if enough pages are not available for the COW. For reasonably reliable behaviour in the face of a small huge page pool, children of hugepage-aware processes should not reference the mappings; such as might occur when fork()ing to exec(). 3. On fork(), the child VMAs inherit no reserves. Reads on pages already faulted by the parent will succeed. Successful writes will depend on enough huge pages being free in the pool. 4. Quotas of the hugetlbfs mount are checked at reserve time for the mapper and at fault time otherwise. Before this patch, all reads or writes in the child potentially needs page allocations that can later lead to the death of the parent. This applies to reads and writes of uninstantiated pages as well as COW. After the patch it is only a write to an instantiated page that causes problems. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Adam Litke <agl@us.ibm.com> Cc: Andy Whitcroft <apw@shadowen.org> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:27:23 +00:00
int hugetlb_reserve_pages(struct inode *inode, long from, long to,
Do not account for the address space used by hugetlbfs using VM_ACCOUNT When overcommit is disabled, the core VM accounts for pages used by anonymous shared, private mappings and special mappings. It keeps track of VMAs that should be accounted for with VM_ACCOUNT and VMAs that never had a reserve with VM_NORESERVE. Overcommit for hugetlbfs is much riskier than overcommit for base pages due to contiguity requirements. It avoids overcommiting on both shared and private mappings using reservation counters that are checked and updated during mmap(). This ensures (within limits) that hugepages exist in the future when faults occurs or it is too easy to applications to be SIGKILLed. As hugetlbfs makes its own reservations of a different unit to the base page size, VM_ACCOUNT should never be set. Even if the units were correct, we would double account for the usage in the core VM and hugetlbfs. VM_NORESERVE may be set because an application can request no reserves be made for hugetlbfs at the risk of getting killed later. With commit fc8744adc870a8d4366908221508bb113d8b72ee, VM_NORESERVE and VM_ACCOUNT are getting unconditionally set for hugetlbfs-backed mappings. This breaks the accounting for both the core VM and hugetlbfs, can trigger an OOM storm when hugepage pools are too small lockups and corrupted counters otherwise are used. This patch brings hugetlbfs more in line with how the core VM treats VM_NORESERVE but prevents VM_ACCOUNT being set. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-10 14:02:27 +00:00
struct vm_area_struct *vma,
vm_flags_t vm_flags);
void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
int dequeue_hwpoisoned_huge_page(struct page *page);
void copy_huge_page(struct page *dst, struct page *src);
extern unsigned long hugepages_treat_as_movable;
extern const unsigned long hugetlb_zero, hugetlb_infinity;
extern int sysctl_hugetlb_shm_group;
extern struct list_head huge_boot_pages;
/* arch callbacks */
pte_t *huge_pte_alloc(struct mm_struct *mm,
unsigned long addr, unsigned long sz);
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr);
[PATCH] shared page table for hugetlb page Following up with the work on shared page table done by Dave McCracken. This set of patch target shared page table for hugetlb memory only. The shared page table is particular useful in the situation of large number of independent processes sharing large shared memory segments. In the normal page case, the amount of memory saved from process' page table is quite significant. For hugetlb, the saving on page table memory is not the primary objective (as hugetlb itself already cuts down page table overhead significantly), instead, the purpose of using shared page table on hugetlb is to allow faster TLB refill and smaller cache pollution upon TLB miss. With PT sharing, pte entries are shared among hundreds of processes, the cache consumption used by all the page table is smaller and in return, application gets much higher cache hit ratio. One other effect is that cache hit ratio with hardware page walker hitting on pte in cache will be higher and this helps to reduce tlb miss latency. These two effects contribute to higher application performance. Signed-off-by: Ken Chen <kenneth.w.chen@intel.com> Acked-by: Hugh Dickins <hugh@veritas.com> Cc: Dave McCracken <dmccr@us.ibm.com> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: Adam Litke <agl@us.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07 04:32:03 +00:00
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
int write);
struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmd, int write);
struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
pud_t *pud, int write);
int pmd_huge(pmd_t pmd);
int pud_huge(pud_t pmd);
unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
[PATCH] Enable mprotect on huge pages 2.6.16-rc3 uses hugetlb on-demand paging, but it doesn_t support hugetlb mprotect. From: David Gibson <david@gibson.dropbear.id.au> Remove a test from the mprotect() path which checks that the mprotect()ed range on a hugepage VMA is hugepage aligned (yes, really, the sense of is_aligned_hugepage_range() is the opposite of what you'd guess :-/). In fact, we don't need this test. If the given addresses match the beginning/end of a hugepage VMA they must already be suitably aligned. If they don't, then mprotect_fixup() will attempt to split the VMA. The very first test in split_vma() will check for a badly aligned address on a hugepage VMA and return -EINVAL if necessary. From: "Chen, Kenneth W" <kenneth.w.chen@intel.com> On i386 and x86-64, pte flag _PAGE_PSE collides with _PAGE_PROTNONE. The identify of hugetlb pte is lost when changing page protection via mprotect. A page fault occurs later will trigger a bug check in huge_pte_alloc(). The fix is to always make new pte a hugetlb pte and also to clean up legacy code where _PAGE_PRESENT is forced on in the pre-faulting day. Signed-off-by: Zhang Yanmin <yanmin.zhang@intel.com> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: "David S. Miller" <davem@davemloft.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: William Lee Irwin III <wli@holomorphy.com> Signed-off-by: Ken Chen <kenneth.w.chen@intel.com> Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-22 08:08:50 +00:00
unsigned long address, unsigned long end, pgprot_t newprot);
#else /* !CONFIG_HUGETLB_PAGE */
mm: introduce PageHuge() for testing huge/gigantic pages A series of patches to enhance the /proc/pagemap interface and to add a userspace executable which can be used to present the pagemap data. Export 10 more flags to end users (and more for kernel developers): 11. KPF_MMAP (pseudo flag) memory mapped page 12. KPF_ANON (pseudo flag) memory mapped page (anonymous) 13. KPF_SWAPCACHE page is in swap cache 14. KPF_SWAPBACKED page is swap/RAM backed 15. KPF_COMPOUND_HEAD (*) 16. KPF_COMPOUND_TAIL (*) 17. KPF_HUGE hugeTLB pages 18. KPF_UNEVICTABLE page is in the unevictable LRU list 19. KPF_HWPOISON hardware detected corruption 20. KPF_NOPAGE (pseudo flag) no page frame at the address (*) For compound pages, exporting _both_ head/tail info enables users to tell where a compound page starts/ends, and its order. a simple demo of the page-types tool # ./page-types -h page-types [options] -r|--raw Raw mode, for kernel developers -a|--addr addr-spec Walk a range of pages -b|--bits bits-spec Walk pages with specified bits -l|--list Show page details in ranges -L|--list-each Show page details one by one -N|--no-summary Don't show summay info -h|--help Show this usage message addr-spec: N one page at offset N (unit: pages) N+M pages range from N to N+M-1 N,M pages range from N to M-1 N, pages range from N to end ,M pages range from 0 to M bits-spec: bit1,bit2 (flags & (bit1|bit2)) != 0 bit1,bit2=bit1 (flags & (bit1|bit2)) == bit1 bit1,~bit2 (flags & (bit1|bit2)) == bit1 =bit1,bit2 flags == (bit1|bit2) bit-names: locked error referenced uptodate dirty lru active slab writeback reclaim buddy mmap anonymous swapcache swapbacked compound_head compound_tail huge unevictable hwpoison nopage reserved(r) mlocked(r) mappedtodisk(r) private(r) private_2(r) owner_private(r) arch(r) uncached(r) readahead(o) slob_free(o) slub_frozen(o) slub_debug(o) (r) raw mode bits (o) overloaded bits # ./page-types flags page-count MB symbolic-flags long-symbolic-flags 0x0000000000000000 487369 1903 _________________________________ 0x0000000000000014 5 0 __R_D____________________________ referenced,dirty 0x0000000000000020 1 0 _____l___________________________ lru 0x0000000000000024 34 0 __R__l___________________________ referenced,lru 0x0000000000000028 3838 14 ___U_l___________________________ uptodate,lru 0x0001000000000028 48 0 ___U_l_______________________I___ uptodate,lru,readahead 0x000000000000002c 6478 25 __RU_l___________________________ referenced,uptodate,lru 0x000100000000002c 47 0 __RU_l_______________________I___ referenced,uptodate,lru,readahead 0x0000000000000040 8344 32 ______A__________________________ active 0x0000000000000060 1 0 _____lA__________________________ lru,active 0x0000000000000068 348 1 ___U_lA__________________________ uptodate,lru,active 0x0001000000000068 12 0 ___U_lA______________________I___ uptodate,lru,active,readahead 0x000000000000006c 988 3 __RU_lA__________________________ referenced,uptodate,lru,active 0x000100000000006c 48 0 __RU_lA______________________I___ referenced,uptodate,lru,active,readahead 0x0000000000004078 1 0 ___UDlA_______b__________________ uptodate,dirty,lru,active,swapbacked 0x000000000000407c 34 0 __RUDlA_______b__________________ referenced,uptodate,dirty,lru,active,swapbacked 0x0000000000000400 503 1 __________B______________________ buddy 0x0000000000000804 1 0 __R________M_____________________ referenced,mmap 0x0000000000000828 1029 4 ___U_l_____M_____________________ uptodate,lru,mmap 0x0001000000000828 43 0 ___U_l_____M_________________I___ uptodate,lru,mmap,readahead 0x000000000000082c 382 1 __RU_l_____M_____________________ referenced,uptodate,lru,mmap 0x000100000000082c 12 0 __RU_l_____M_________________I___ referenced,uptodate,lru,mmap,readahead 0x0000000000000868 192 0 ___U_lA____M_____________________ uptodate,lru,active,mmap 0x0001000000000868 12 0 ___U_lA____M_________________I___ uptodate,lru,active,mmap,readahead 0x000000000000086c 800 3 __RU_lA____M_____________________ referenced,uptodate,lru,active,mmap 0x000100000000086c 31 0 __RU_lA____M_________________I___ referenced,uptodate,lru,active,mmap,readahead 0x0000000000004878 2 0 ___UDlA____M__b__________________ uptodate,dirty,lru,active,mmap,swapbacked 0x0000000000001000 492 1 ____________a____________________ anonymous 0x0000000000005808 4 0 ___U_______Ma_b__________________ uptodate,mmap,anonymous,swapbacked 0x0000000000005868 2839 11 ___U_lA____Ma_b__________________ uptodate,lru,active,mmap,anonymous,swapbacked 0x000000000000586c 30 0 __RU_lA____Ma_b__________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked total 513968 2007 # ./page-types -r flags page-count MB symbolic-flags long-symbolic-flags 0x0000000000000000 468002 1828 _________________________________ 0x0000000100000000 19102 74 _____________________r___________ reserved 0x0000000000008000 41 0 _______________H_________________ compound_head 0x0000000000010000 188 0 ________________T________________ compound_tail 0x0000000000008014 1 0 __R_D__________H_________________ referenced,dirty,compound_head 0x0000000000010014 4 0 __R_D___________T________________ referenced,dirty,compound_tail 0x0000000000000020 1 0 _____l___________________________ lru 0x0000000800000024 34 0 __R__l__________________P________ referenced,lru,private 0x0000000000000028 3794 14 ___U_l___________________________ uptodate,lru 0x0001000000000028 46 0 ___U_l_______________________I___ uptodate,lru,readahead 0x0000000400000028 44 0 ___U_l_________________d_________ uptodate,lru,mappedtodisk 0x0001000400000028 2 0 ___U_l_________________d_____I___ uptodate,lru,mappedtodisk,readahead 0x000000000000002c 6434 25 __RU_l___________________________ referenced,uptodate,lru 0x000100000000002c 47 0 __RU_l_______________________I___ referenced,uptodate,lru,readahead 0x000000040000002c 14 0 __RU_l_________________d_________ referenced,uptodate,lru,mappedtodisk 0x000000080000002c 30 0 __RU_l__________________P________ referenced,uptodate,lru,private 0x0000000800000040 8124 31 ______A_________________P________ active,private 0x0000000000000040 219 0 ______A__________________________ active 0x0000000800000060 1 0 _____lA_________________P________ lru,active,private 0x0000000000000068 322 1 ___U_lA__________________________ uptodate,lru,active 0x0001000000000068 12 0 ___U_lA______________________I___ uptodate,lru,active,readahead 0x0000000400000068 13 0 ___U_lA________________d_________ uptodate,lru,active,mappedtodisk 0x0000000800000068 12 0 ___U_lA_________________P________ uptodate,lru,active,private 0x000000000000006c 977 3 __RU_lA__________________________ referenced,uptodate,lru,active 0x000100000000006c 48 0 __RU_lA______________________I___ referenced,uptodate,lru,active,readahead 0x000000040000006c 5 0 __RU_lA________________d_________ referenced,uptodate,lru,active,mappedtodisk 0x000000080000006c 3 0 __RU_lA_________________P________ referenced,uptodate,lru,active,private 0x0000000c0000006c 3 0 __RU_lA________________dP________ referenced,uptodate,lru,active,mappedtodisk,private 0x0000000c00000068 1 0 ___U_lA________________dP________ uptodate,lru,active,mappedtodisk,private 0x0000000000004078 1 0 ___UDlA_______b__________________ uptodate,dirty,lru,active,swapbacked 0x000000000000407c 34 0 __RUDlA_______b__________________ referenced,uptodate,dirty,lru,active,swapbacked 0x0000000000000400 538 2 __________B______________________ buddy 0x0000000000000804 1 0 __R________M_____________________ referenced,mmap 0x0000000000000828 1029 4 ___U_l_____M_____________________ uptodate,lru,mmap 0x0001000000000828 43 0 ___U_l_____M_________________I___ uptodate,lru,mmap,readahead 0x000000000000082c 382 1 __RU_l_____M_____________________ referenced,uptodate,lru,mmap 0x000100000000082c 12 0 __RU_l_____M_________________I___ referenced,uptodate,lru,mmap,readahead 0x0000000000000868 192 0 ___U_lA____M_____________________ uptodate,lru,active,mmap 0x0001000000000868 12 0 ___U_lA____M_________________I___ uptodate,lru,active,mmap,readahead 0x000000000000086c 800 3 __RU_lA____M_____________________ referenced,uptodate,lru,active,mmap 0x000100000000086c 31 0 __RU_lA____M_________________I___ referenced,uptodate,lru,active,mmap,readahead 0x0000000000004878 2 0 ___UDlA____M__b__________________ uptodate,dirty,lru,active,mmap,swapbacked 0x0000000000001000 492 1 ____________a____________________ anonymous 0x0000000000005008 2 0 ___U________a_b__________________ uptodate,anonymous,swapbacked 0x0000000000005808 4 0 ___U_______Ma_b__________________ uptodate,mmap,anonymous,swapbacked 0x000000000000580c 1 0 __RU_______Ma_b__________________ referenced,uptodate,mmap,anonymous,swapbacked 0x0000000000005868 2839 11 ___U_lA____Ma_b__________________ uptodate,lru,active,mmap,anonymous,swapbacked 0x000000000000586c 29 0 __RU_lA____Ma_b__________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked total 513968 2007 # ./page-types --raw --list --no-summary --bits reserved offset count flags 0 15 _____________________r___________ 31 4 _____________________r___________ 159 97 _____________________r___________ 4096 2067 _____________________r___________ 6752 2390 _____________________r___________ 9355 3 _____________________r___________ 9728 14526 _____________________r___________ This patch: Introduce PageHuge(), which identifies huge/gigantic pages by their dedicated compound destructor functions. Also move prep_compound_gigantic_page() to hugetlb.c and make __free_pages_ok() non-static. Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Matt Mackall <mpm@selenic.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-16 22:32:22 +00:00
static inline int PageHuge(struct page *page)
{
return 0;
}
hugetlb: reserve huge pages for reliable MAP_PRIVATE hugetlbfs mappings until fork() This patch reserves huge pages at mmap() time for MAP_PRIVATE mappings in a similar manner to the reservations taken for MAP_SHARED mappings. The reserve count is accounted both globally and on a per-VMA basis for private mappings. This guarantees that a process that successfully calls mmap() will successfully fault all pages in the future unless fork() is called. The characteristics of private mappings of hugetlbfs files behaviour after this patch are; 1. The process calling mmap() is guaranteed to succeed all future faults until it forks(). 2. On fork(), the parent may die due to SIGKILL on writes to the private mapping if enough pages are not available for the COW. For reasonably reliable behaviour in the face of a small huge page pool, children of hugepage-aware processes should not reference the mappings; such as might occur when fork()ing to exec(). 3. On fork(), the child VMAs inherit no reserves. Reads on pages already faulted by the parent will succeed. Successful writes will depend on enough huge pages being free in the pool. 4. Quotas of the hugetlbfs mount are checked at reserve time for the mapper and at fault time otherwise. Before this patch, all reads or writes in the child potentially needs page allocations that can later lead to the death of the parent. This applies to reads and writes of uninstantiated pages as well as COW. After the patch it is only a write to an instantiated page that causes problems. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Adam Litke <agl@us.ibm.com> Cc: Andy Whitcroft <apw@shadowen.org> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:27:23 +00:00
static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
}
static inline unsigned long hugetlb_total_pages(void)
{
return 0;
}
#define follow_hugetlb_page(m,v,p,vs,a,b,i,w) ({ BUG(); 0; })
#define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL)
#define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; })
#define hugetlb_prefault(mapping, vma) ({ BUG(); 0; })
static inline void hugetlb_report_meminfo(struct seq_file *m)
{
}
#define hugetlb_report_node_meminfo(n, buf) 0
#define follow_huge_pmd(mm, addr, pmd, write) NULL
#define follow_huge_pud(mm, addr, pud, write) NULL
#define prepare_hugepage_range(file, addr, len) (-EINVAL)
#define pmd_huge(x) 0
#define pud_huge(x) 0
#define is_hugepage_only_range(mm, addr, len) 0
[PATCH] hugepage: Fix hugepage logic in free_pgtables() free_pgtables() has special logic to call hugetlb_free_pgd_range() instead of the normal free_pgd_range() on hugepage VMAs. However, the test it uses to do so is incorrect: it calls is_hugepage_only_range on a hugepage sized range at the start of the vma. is_hugepage_only_range() will return true if the given range has any intersection with a hugepage address region, and in this case the given region need not be hugepage aligned. So, for example, this test can return true if called on, say, a 4k VMA immediately preceding a (nicely aligned) hugepage VMA. At present we get away with this because the powerpc version of hugetlb_free_pgd_range() is just a call to free_pgd_range(). On ia64 (the only other arch with a non-trivial is_hugepage_only_range()) we get away with it for a different reason; the hugepage area is not contiguous with the rest of the user address space, and VMAs are not permitted in between, so the test can't return a false positive there. Nonetheless this should be fixed. We do that in the patch below by replacing the is_hugepage_only_range() test with an explicit test of the VMA using is_vm_hugetlb_page(). This in turn changes behaviour for platforms where is_hugepage_only_range() returns false always (everything except powerpc and ia64). We address this by ensuring that hugetlb_free_pgd_range() is defined to be identical to free_pgd_range() (instead of a no-op) on everything except ia64. Even so, it will prevent some otherwise possible coalescing of calls down to free_pgd_range(). Since this only happens for hugepage VMAs, removing this small optimization seems unlikely to cause any trouble. This patch causes no regressions on the libhugetlbfs testsuite - ppc64 POWER5 (8-way), ppc64 G5 (2-way) and i386 Pentium M (UP). Signed-off-by: David Gibson <dwg@au1.ibm.com> Cc: William Lee Irwin III <wli@holomorphy.com> Acked-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-22 08:08:57 +00:00
#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
#define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; })
hugetlb, rmap: add reverse mapping for hugepage This patch adds reverse mapping feature for hugepage by introducing mapcount for shared/private-mapped hugepage and anon_vma for private-mapped hugepage. While hugepage is not currently swappable, reverse mapping can be useful for memory error handler. Without this patch, memory error handler cannot identify processes using the bad hugepage nor unmap it from them. That is: - for shared hugepage: we can collect processes using a hugepage through pagecache, but can not unmap the hugepage because of the lack of mapcount. - for privately mapped hugepage: we can neither collect processes nor unmap the hugepage. This patch solves these problems. This patch include the bug fix given by commit 23be7468e8, so reverts it. Dependency: "hugetlb: move definition of is_vm_hugetlb_page() to hugepage_inline.h" ChangeLog since May 24. - create hugetlb_inline.h and move is_vm_hugetlb_index() in it. - move functions setting up anon_vma for hugepage into mm/rmap.c. ChangeLog since May 13. - rebased to 2.6.34 - fix logic error (in case that private mapping and shared mapping coexist) - move is_vm_hugetlb_page() into include/linux/mm.h to use this function from linear_page_index() - define and use linear_hugepage_index() instead of compound_order() - use page_move_anon_rmap() in hugetlb_cow() - copy exclusive switch of __set_page_anon_rmap() into hugepage counterpart. - revert commit 24be7468 completely Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Acked-by: Fengguang Wu <fengguang.wu@intel.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andi Kleen <ak@linux.intel.com>
2010-05-28 00:29:16 +00:00
#define huge_pte_offset(mm, address) 0
static inline int dequeue_hwpoisoned_huge_page(struct page *page)
{
return 0;
}
static inline void copy_huge_page(struct page *dst, struct page *src)
{
}
static inline unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
unsigned long address, unsigned long end, pgprot_t newprot)
{
return 0;
}
[PATCH] Enable mprotect on huge pages 2.6.16-rc3 uses hugetlb on-demand paging, but it doesn_t support hugetlb mprotect. From: David Gibson <david@gibson.dropbear.id.au> Remove a test from the mprotect() path which checks that the mprotect()ed range on a hugepage VMA is hugepage aligned (yes, really, the sense of is_aligned_hugepage_range() is the opposite of what you'd guess :-/). In fact, we don't need this test. If the given addresses match the beginning/end of a hugepage VMA they must already be suitably aligned. If they don't, then mprotect_fixup() will attempt to split the VMA. The very first test in split_vma() will check for a badly aligned address on a hugepage VMA and return -EINVAL if necessary. From: "Chen, Kenneth W" <kenneth.w.chen@intel.com> On i386 and x86-64, pte flag _PAGE_PSE collides with _PAGE_PROTNONE. The identify of hugetlb pte is lost when changing page protection via mprotect. A page fault occurs later will trigger a bug check in huge_pte_alloc(). The fix is to always make new pte a hugetlb pte and also to clean up legacy code where _PAGE_PRESENT is forced on in the pre-faulting day. Signed-off-by: Zhang Yanmin <yanmin.zhang@intel.com> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: "David S. Miller" <davem@davemloft.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: William Lee Irwin III <wli@holomorphy.com> Signed-off-by: Ken Chen <kenneth.w.chen@intel.com> Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-22 08:08:50 +00:00
mm: hugetlbfs: close race during teardown of hugetlbfs shared page tables If a process creates a large hugetlbfs mapping that is eligible for page table sharing and forks heavily with children some of whom fault and others which destroy the mapping then it is possible for page tables to get corrupted. Some teardowns of the mapping encounter a "bad pmd" and output a message to the kernel log. The final teardown will trigger a BUG_ON in mm/filemap.c. This was reproduced in 3.4 but is known to have existed for a long time and goes back at least as far as 2.6.37. It was probably was introduced in 2.6.20 by [39dde65c: shared page table for hugetlb page]. The messages look like this; [ ..........] Lots of bad pmd messages followed by this [ 127.164256] mm/memory.c:391: bad pmd ffff880412e04fe8(80000003de4000e7). [ 127.164257] mm/memory.c:391: bad pmd ffff880412e04ff0(80000003de6000e7). [ 127.164258] mm/memory.c:391: bad pmd ffff880412e04ff8(80000003de0000e7). [ 127.186778] ------------[ cut here ]------------ [ 127.186781] kernel BUG at mm/filemap.c:134! [ 127.186782] invalid opcode: 0000 [#1] SMP [ 127.186783] CPU 7 [ 127.186784] Modules linked in: af_packet cpufreq_conservative cpufreq_userspace cpufreq_powersave acpi_cpufreq mperf ext3 jbd dm_mod coretemp crc32c_intel usb_storage ghash_clmulni_intel aesni_intel i2c_i801 r8169 mii uas sr_mod cdrom sg iTCO_wdt iTCO_vendor_support shpchp serio_raw cryptd aes_x86_64 e1000e pci_hotplug dcdbas aes_generic container microcode ext4 mbcache jbd2 crc16 sd_mod crc_t10dif i915 drm_kms_helper drm i2c_algo_bit ehci_hcd ahci libahci usbcore rtc_cmos usb_common button i2c_core intel_agp video intel_gtt fan processor thermal thermal_sys hwmon ata_generic pata_atiixp libata scsi_mod [ 127.186801] [ 127.186802] Pid: 9017, comm: hugetlbfs-test Not tainted 3.4.0-autobuild #53 Dell Inc. OptiPlex 990/06D7TR [ 127.186804] RIP: 0010:[<ffffffff810ed6ce>] [<ffffffff810ed6ce>] __delete_from_page_cache+0x15e/0x160 [ 127.186809] RSP: 0000:ffff8804144b5c08 EFLAGS: 00010002 [ 127.186810] RAX: 0000000000000001 RBX: ffffea000a5c9000 RCX: 00000000ffffffc0 [ 127.186811] RDX: 0000000000000000 RSI: 0000000000000009 RDI: ffff88042dfdad00 [ 127.186812] RBP: ffff8804144b5c18 R08: 0000000000000009 R09: 0000000000000003 [ 127.186813] R10: 0000000000000000 R11: 000000000000002d R12: ffff880412ff83d8 [ 127.186814] R13: ffff880412ff83d8 R14: 0000000000000000 R15: ffff880412ff83d8 [ 127.186815] FS: 00007fe18ed2c700(0000) GS:ffff88042dce0000(0000) knlGS:0000000000000000 [ 127.186816] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 127.186817] CR2: 00007fe340000503 CR3: 0000000417a14000 CR4: 00000000000407e0 [ 127.186818] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 127.186819] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 127.186820] Process hugetlbfs-test (pid: 9017, threadinfo ffff8804144b4000, task ffff880417f803c0) [ 127.186821] Stack: [ 127.186822] ffffea000a5c9000 0000000000000000 ffff8804144b5c48 ffffffff810ed83b [ 127.186824] ffff8804144b5c48 000000000000138a 0000000000001387 ffff8804144b5c98 [ 127.186825] ffff8804144b5d48 ffffffff811bc925 ffff8804144b5cb8 0000000000000000 [ 127.186827] Call Trace: [ 127.186829] [<ffffffff810ed83b>] delete_from_page_cache+0x3b/0x80 [ 127.186832] [<ffffffff811bc925>] truncate_hugepages+0x115/0x220 [ 127.186834] [<ffffffff811bca43>] hugetlbfs_evict_inode+0x13/0x30 [ 127.186837] [<ffffffff811655c7>] evict+0xa7/0x1b0 [ 127.186839] [<ffffffff811657a3>] iput_final+0xd3/0x1f0 [ 127.186840] [<ffffffff811658f9>] iput+0x39/0x50 [ 127.186842] [<ffffffff81162708>] d_kill+0xf8/0x130 [ 127.186843] [<ffffffff81162812>] dput+0xd2/0x1a0 [ 127.186845] [<ffffffff8114e2d0>] __fput+0x170/0x230 [ 127.186848] [<ffffffff81236e0e>] ? rb_erase+0xce/0x150 [ 127.186849] [<ffffffff8114e3ad>] fput+0x1d/0x30 [ 127.186851] [<ffffffff81117db7>] remove_vma+0x37/0x80 [ 127.186853] [<ffffffff81119182>] do_munmap+0x2d2/0x360 [ 127.186855] [<ffffffff811cc639>] sys_shmdt+0xc9/0x170 [ 127.186857] [<ffffffff81410a39>] system_call_fastpath+0x16/0x1b [ 127.186858] Code: 0f 1f 44 00 00 48 8b 43 08 48 8b 00 48 8b 40 28 8b b0 40 03 00 00 85 f6 0f 88 df fe ff ff 48 89 df e8 e7 cb 05 00 e9 d2 fe ff ff <0f> 0b 55 83 e2 fd 48 89 e5 48 83 ec 30 48 89 5d d8 4c 89 65 e0 [ 127.186868] RIP [<ffffffff810ed6ce>] __delete_from_page_cache+0x15e/0x160 [ 127.186870] RSP <ffff8804144b5c08> [ 127.186871] ---[ end trace 7cbac5d1db69f426 ]--- The bug is a race and not always easy to reproduce. To reproduce it I was doing the following on a single socket I7-based machine with 16G of RAM. $ hugeadm --pool-pages-max DEFAULT:13G $ echo $((18*1048576*1024)) > /proc/sys/kernel/shmmax $ echo $((18*1048576*1024)) > /proc/sys/kernel/shmall $ for i in `seq 1 9000`; do ./hugetlbfs-test; done On my particular machine, it usually triggers within 10 minutes but enabling debug options can change the timing such that it never hits. Once the bug is triggered, the machine is in trouble and needs to be rebooted. The machine will respond but processes accessing proc like "ps aux" will hang due to the BUG_ON. shutdown will also hang and needs a hard reset or a sysrq-b. The basic problem is a race between page table sharing and teardown. For the most part page table sharing depends on i_mmap_mutex. In some cases, it is also taking the mm->page_table_lock for the PTE updates but with shared page tables, it is the i_mmap_mutex that is more important. Unfortunately it appears to be also insufficient. Consider the following situation Process A Process B --------- --------- hugetlb_fault shmdt LockWrite(mmap_sem) do_munmap unmap_region unmap_vmas unmap_single_vma unmap_hugepage_range Lock(i_mmap_mutex) Lock(mm->page_table_lock) huge_pmd_unshare/unmap tables <--- (1) Unlock(mm->page_table_lock) Unlock(i_mmap_mutex) huge_pte_alloc ... Lock(i_mmap_mutex) ... vma_prio_walk, find svma, spte ... Lock(mm->page_table_lock) ... share spte ... Unlock(mm->page_table_lock) ... Unlock(i_mmap_mutex) ... hugetlb_no_page <--- (2) free_pgtables unlink_file_vma hugetlb_free_pgd_range remove_vma_list In this scenario, it is possible for Process A to share page tables with Process B that is trying to tear them down. The i_mmap_mutex on its own does not prevent Process A walking Process B's page tables. At (1) above, the page tables are not shared yet so it unmaps the PMDs. Process A sets up page table sharing and at (2) faults a new entry. Process B then trips up on it in free_pgtables. This patch fixes the problem by adding a new function __unmap_hugepage_range_final that is only called when the VMA is about to be destroyed. This function clears VM_MAYSHARE during unmap_hugepage_range() under the i_mmap_mutex. This makes the VMA ineligible for sharing and avoids the race. Superficially this looks like it would then be vunerable to truncate and madvise issues but hugetlbfs has its own truncate handlers so does not use unmap_mapping_range() and does not support madvise(DONTNEED). This should be treated as a -stable candidate if it is merged. Test program is as follows. The test case was mostly written by Michal Hocko with a few minor changes to reproduce this bug. ==== CUT HERE ==== static size_t huge_page_size = (2UL << 20); static size_t nr_huge_page_A = 512; static size_t nr_huge_page_B = 5632; unsigned int get_random(unsigned int max) { struct timeval tv; gettimeofday(&tv, NULL); srandom(tv.tv_usec); return random() % max; } static void play(void *addr, size_t size) { unsigned char *start = addr, *end = start + size, *a; start += get_random(size/2); /* we could itterate on huge pages but let's give it more time. */ for (a = start; a < end; a += 4096) *a = 0; } int main(int argc, char **argv) { key_t key = IPC_PRIVATE; size_t sizeA = nr_huge_page_A * huge_page_size; size_t sizeB = nr_huge_page_B * huge_page_size; int shmidA, shmidB; void *addrA = NULL, *addrB = NULL; int nr_children = 300, n = 0; if ((shmidA = shmget(key, sizeA, IPC_CREAT|SHM_HUGETLB|0660)) == -1) { perror("shmget:"); return 1; } if ((addrA = shmat(shmidA, addrA, SHM_R|SHM_W)) == (void *)-1UL) { perror("shmat"); return 1; } if ((shmidB = shmget(key, sizeB, IPC_CREAT|SHM_HUGETLB|0660)) == -1) { perror("shmget:"); return 1; } if ((addrB = shmat(shmidB, addrB, SHM_R|SHM_W)) == (void *)-1UL) { perror("shmat"); return 1; } fork_child: switch(fork()) { case 0: switch (n%3) { case 0: play(addrA, sizeA); break; case 1: play(addrB, sizeB); break; case 2: break; } break; case -1: perror("fork:"); break; default: if (++n < nr_children) goto fork_child; play(addrA, sizeA); break; } shmdt(addrA); shmdt(addrB); do { wait(NULL); } while (--n > 0); shmctl(shmidA, IPC_RMID, NULL); shmctl(shmidB, IPC_RMID, NULL); return 0; } [akpm@linux-foundation.org: name the declaration's args, fix CONFIG_HUGETLBFS=n build] Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 23:46:20 +00:00
static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page)
{
BUG();
}
static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page)
{
BUG();
}
#endif /* !CONFIG_HUGETLB_PAGE */
#define HUGETLB_ANON_FILE "anon_hugepage"
hugetlbfs: allow the creation of files suitable for MAP_PRIVATE on the vfs internal mount This patchset adds a flag to mmap that allows the user to request that an anonymous mapping be backed with huge pages. This mapping will borrow functionality from the huge page shm code to create a file on the kernel internal mount and use it to approximate an anonymous mapping. The MAP_HUGETLB flag is a modifier to MAP_ANONYMOUS and will not work without both flags being preset. A new flag is necessary because there is no other way to hook into huge pages without creating a file on a hugetlbfs mount which wouldn't be MAP_ANONYMOUS. To userspace, this mapping will behave just like an anonymous mapping because the file is not accessible outside of the kernel. This patchset is meant to simplify the programming model. Presently there is a large chunk of boiler platecode, contained in libhugetlbfs, required to create private, hugepage backed mappings. This patch set would allow use of hugepages without linking to libhugetlbfs or having hugetblfs mounted. Unification of the VM code would provide these same benefits, but it has been resisted each time that it has been suggested for several reasons: it would break PAGE_SIZE assumptions across the kernel, it makes page-table abstractions really expensive, and it does not provide any benefit on architectures that do not support huge pages, incurring fast path penalties without providing any benefit on these architectures. This patch: There are two means of creating mappings backed by huge pages: 1. mmap() a file created on hugetlbfs 2. Use shm which creates a file on an internal mount which essentially maps it MAP_SHARED The internal mount is only used for shared mappings but there is very little that stops it being used for private mappings. This patch extends hugetlbfs_file_setup() to deal with the creation of files that will be mapped MAP_PRIVATE on the internal hugetlbfs mount. This extended API is used in a subsequent patch to implement the MAP_HUGETLB mmap() flag. Signed-off-by: Eric Munson <ebmunson@us.ibm.com> Acked-by: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Adam Litke <agl@us.ibm.com> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 00:03:43 +00:00
enum {
/*
* The file will be used as an shm file so shmfs accounting rules
* apply
*/
HUGETLB_SHMFS_INODE = 1,
/*
* The file is being created on the internal vfs mount and shmfs
* accounting rules do not apply
*/
HUGETLB_ANONHUGE_INODE = 2,
hugetlbfs: allow the creation of files suitable for MAP_PRIVATE on the vfs internal mount This patchset adds a flag to mmap that allows the user to request that an anonymous mapping be backed with huge pages. This mapping will borrow functionality from the huge page shm code to create a file on the kernel internal mount and use it to approximate an anonymous mapping. The MAP_HUGETLB flag is a modifier to MAP_ANONYMOUS and will not work without both flags being preset. A new flag is necessary because there is no other way to hook into huge pages without creating a file on a hugetlbfs mount which wouldn't be MAP_ANONYMOUS. To userspace, this mapping will behave just like an anonymous mapping because the file is not accessible outside of the kernel. This patchset is meant to simplify the programming model. Presently there is a large chunk of boiler platecode, contained in libhugetlbfs, required to create private, hugepage backed mappings. This patch set would allow use of hugepages without linking to libhugetlbfs or having hugetblfs mounted. Unification of the VM code would provide these same benefits, but it has been resisted each time that it has been suggested for several reasons: it would break PAGE_SIZE assumptions across the kernel, it makes page-table abstractions really expensive, and it does not provide any benefit on architectures that do not support huge pages, incurring fast path penalties without providing any benefit on these architectures. This patch: There are two means of creating mappings backed by huge pages: 1. mmap() a file created on hugetlbfs 2. Use shm which creates a file on an internal mount which essentially maps it MAP_SHARED The internal mount is only used for shared mappings but there is very little that stops it being used for private mappings. This patch extends hugetlbfs_file_setup() to deal with the creation of files that will be mapped MAP_PRIVATE on the internal hugetlbfs mount. This extended API is used in a subsequent patch to implement the MAP_HUGETLB mmap() flag. Signed-off-by: Eric Munson <ebmunson@us.ibm.com> Acked-by: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Adam Litke <agl@us.ibm.com> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 00:03:43 +00:00
};
#ifdef CONFIG_HUGETLBFS
struct hugetlbfs_sb_info {
long max_inodes; /* inodes allowed */
long free_inodes; /* inodes free */
spinlock_t stat_lock;
struct hstate *hstate;
hugepages: fix use after free bug in "quota" handling hugetlbfs_{get,put}_quota() are badly named. They don't interact with the general quota handling code, and they don't much resemble its behaviour. Rather than being about maintaining limits on on-disk block usage by particular users, they are instead about maintaining limits on in-memory page usage (including anonymous MAP_PRIVATE copied-on-write pages) associated with a particular hugetlbfs filesystem instance. Worse, they work by having callbacks to the hugetlbfs filesystem code from the low-level page handling code, in particular from free_huge_page(). This is a layering violation of itself, but more importantly, if the kernel does a get_user_pages() on hugepages (which can happen from KVM amongst others), then the free_huge_page() can be delayed until after the associated inode has already been freed. If an unmount occurs at the wrong time, even the hugetlbfs superblock where the "quota" limits are stored may have been freed. Andrew Barry proposed a patch to fix this by having hugepages, instead of storing a pointer to their address_space and reaching the superblock from there, had the hugepages store pointers directly to the superblock, bumping the reference count as appropriate to avoid it being freed. Andrew Morton rejected that version, however, on the grounds that it made the existing layering violation worse. This is a reworked version of Andrew's patch, which removes the extra, and some of the existing, layering violation. It works by introducing the concept of a hugepage "subpool" at the lower hugepage mm layer - that is a finite logical pool of hugepages to allocate from. hugetlbfs now creates a subpool for each filesystem instance with a page limit set, and a pointer to the subpool gets added to each allocated hugepage, instead of the address_space pointer used now. The subpool has its own lifetime and is only freed once all pages in it _and_ all other references to it (i.e. superblocks) are gone. subpools are optional - a NULL subpool pointer is taken by the code to mean that no subpool limits are in effect. Previous discussion of this bug found in: "Fix refcounting in hugetlbfs quota handling.". See: https://lkml.org/lkml/2011/8/11/28 or http://marc.info/?l=linux-mm&m=126928970510627&w=1 v2: Fixed a bug spotted by Hillf Danton, and removed the extra parameter to alloc_huge_page() - since it already takes the vma, it is not necessary. Signed-off-by: Andrew Barry <abarry@cray.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 23:34:12 +00:00
struct hugepage_subpool *spool;
};
static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
{
return sb->s_fs_info;
}
extern const struct file_operations hugetlbfs_file_operations;
extern const struct vm_operations_struct hugetlb_vm_ops;
struct file *hugetlb_file_setup(const char *name, unsigned long addr,
size_t size, vm_flags_t acct,
hugetlbfs: allow the creation of files suitable for MAP_PRIVATE on the vfs internal mount This patchset adds a flag to mmap that allows the user to request that an anonymous mapping be backed with huge pages. This mapping will borrow functionality from the huge page shm code to create a file on the kernel internal mount and use it to approximate an anonymous mapping. The MAP_HUGETLB flag is a modifier to MAP_ANONYMOUS and will not work without both flags being preset. A new flag is necessary because there is no other way to hook into huge pages without creating a file on a hugetlbfs mount which wouldn't be MAP_ANONYMOUS. To userspace, this mapping will behave just like an anonymous mapping because the file is not accessible outside of the kernel. This patchset is meant to simplify the programming model. Presently there is a large chunk of boiler platecode, contained in libhugetlbfs, required to create private, hugepage backed mappings. This patch set would allow use of hugepages without linking to libhugetlbfs or having hugetblfs mounted. Unification of the VM code would provide these same benefits, but it has been resisted each time that it has been suggested for several reasons: it would break PAGE_SIZE assumptions across the kernel, it makes page-table abstractions really expensive, and it does not provide any benefit on architectures that do not support huge pages, incurring fast path penalties without providing any benefit on these architectures. This patch: There are two means of creating mappings backed by huge pages: 1. mmap() a file created on hugetlbfs 2. Use shm which creates a file on an internal mount which essentially maps it MAP_SHARED The internal mount is only used for shared mappings but there is very little that stops it being used for private mappings. This patch extends hugetlbfs_file_setup() to deal with the creation of files that will be mapped MAP_PRIVATE on the internal hugetlbfs mount. This extended API is used in a subsequent patch to implement the MAP_HUGETLB mmap() flag. Signed-off-by: Eric Munson <ebmunson@us.ibm.com> Acked-by: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Adam Litke <agl@us.ibm.com> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 00:03:43 +00:00
struct user_struct **user, int creat_flags);
static inline int is_file_hugepages(struct file *file)
{
if (file->f_op == &hugetlbfs_file_operations)
return 1;
if (is_file_shm_hugepages(file))
return 1;
return 0;
}
#else /* !CONFIG_HUGETLBFS */
#define is_file_hugepages(file) 0
static inline struct file *
hugetlb_file_setup(const char *name, unsigned long addr, size_t size,
vm_flags_t acctflag, struct user_struct **user, int creat_flags)
{
return ERR_PTR(-ENOSYS);
}
#endif /* !CONFIG_HUGETLBFS */
#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags);
#endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */
#ifdef CONFIG_HUGETLB_PAGE
hugetlb: new sysfs interface Provide new hugepages user APIs that are more suited to multiple hstates in sysfs. There is a new directory, /sys/kernel/hugepages. Underneath that directory there will be a directory per-supported hugepage size, e.g.: /sys/kernel/hugepages/hugepages-64kB /sys/kernel/hugepages/hugepages-16384kB /sys/kernel/hugepages/hugepages-16777216kB corresponding to 64k, 16m and 16g respectively. Within each hugepages-size directory there are a number of files, corresponding to the tracked counters in the hstate, e.g.: /sys/kernel/hugepages/hugepages-64/nr_hugepages /sys/kernel/hugepages/hugepages-64/nr_overcommit_hugepages /sys/kernel/hugepages/hugepages-64/free_hugepages /sys/kernel/hugepages/hugepages-64/resv_hugepages /sys/kernel/hugepages/hugepages-64/surplus_hugepages Of these files, the first two are read-write and the latter three are read-only. The size of the hugepage being manipulated is trivially deducible from the enclosing directory and is always expressed in kB (to match meminfo). [dave@linux.vnet.ibm.com: fix build] [nacc@us.ibm.com: hugetlb: hang off of /sys/kernel/mm rather than /sys/kernel] [nacc@us.ibm.com: hugetlb: remove CONFIG_SYSFS dependency] Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:27:44 +00:00
#define HSTATE_NAME_LEN 32
/* Defines one hugetlb page size */
struct hstate {
int next_nid_to_alloc;
int next_nid_to_free;
unsigned int order;
unsigned long mask;
unsigned long max_huge_pages;
unsigned long nr_huge_pages;
unsigned long free_huge_pages;
unsigned long resv_huge_pages;
unsigned long surplus_huge_pages;
unsigned long nr_overcommit_huge_pages;
struct list_head hugepage_activelist;
struct list_head hugepage_freelists[MAX_NUMNODES];
unsigned int nr_huge_pages_node[MAX_NUMNODES];
unsigned int free_huge_pages_node[MAX_NUMNODES];
unsigned int surplus_huge_pages_node[MAX_NUMNODES];
#ifdef CONFIG_CGROUP_HUGETLB
/* cgroup control files */
struct cftype cgroup_files[5];
#endif
hugetlb: new sysfs interface Provide new hugepages user APIs that are more suited to multiple hstates in sysfs. There is a new directory, /sys/kernel/hugepages. Underneath that directory there will be a directory per-supported hugepage size, e.g.: /sys/kernel/hugepages/hugepages-64kB /sys/kernel/hugepages/hugepages-16384kB /sys/kernel/hugepages/hugepages-16777216kB corresponding to 64k, 16m and 16g respectively. Within each hugepages-size directory there are a number of files, corresponding to the tracked counters in the hstate, e.g.: /sys/kernel/hugepages/hugepages-64/nr_hugepages /sys/kernel/hugepages/hugepages-64/nr_overcommit_hugepages /sys/kernel/hugepages/hugepages-64/free_hugepages /sys/kernel/hugepages/hugepages-64/resv_hugepages /sys/kernel/hugepages/hugepages-64/surplus_hugepages Of these files, the first two are read-write and the latter three are read-only. The size of the hugepage being manipulated is trivially deducible from the enclosing directory and is always expressed in kB (to match meminfo). [dave@linux.vnet.ibm.com: fix build] [nacc@us.ibm.com: hugetlb: hang off of /sys/kernel/mm rather than /sys/kernel] [nacc@us.ibm.com: hugetlb: remove CONFIG_SYSFS dependency] Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com> Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:27:44 +00:00
char name[HSTATE_NAME_LEN];
};
struct huge_bootmem_page {
struct list_head list;
struct hstate *hstate;
#ifdef CONFIG_HIGHMEM
phys_addr_t phys;
#endif
};
struct page *alloc_huge_page_node(struct hstate *h, int nid);
/* arch callback */
int __init alloc_bootmem_huge_page(struct hstate *h);
void __init hugetlb_add_hstate(unsigned order);
struct hstate *size_to_hstate(unsigned long size);
#ifndef HUGE_MAX_HSTATE
#define HUGE_MAX_HSTATE 1
#endif
extern struct hstate hstates[HUGE_MAX_HSTATE];
extern unsigned int default_hstate_idx;
#define default_hstate (hstates[default_hstate_idx])
static inline struct hstate *hstate_inode(struct inode *i)
{
struct hugetlbfs_sb_info *hsb;
hsb = HUGETLBFS_SB(i->i_sb);
return hsb->hstate;
}
static inline struct hstate *hstate_file(struct file *f)
{
return hstate_inode(f->f_dentry->d_inode);
}
static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
{
return hstate_file(vma->vm_file);
}
static inline unsigned long huge_page_size(struct hstate *h)
{
return (unsigned long)PAGE_SIZE << h->order;
}
extern unsigned long vma_kernel_pagesize(struct vm_area_struct *vma);
extern unsigned long vma_mmu_pagesize(struct vm_area_struct *vma);
static inline unsigned long huge_page_mask(struct hstate *h)
{
return h->mask;
}
static inline unsigned int huge_page_order(struct hstate *h)
{
return h->order;
}
static inline unsigned huge_page_shift(struct hstate *h)
{
return h->order + PAGE_SHIFT;
}
static inline unsigned int pages_per_huge_page(struct hstate *h)
{
return 1 << h->order;
}
static inline unsigned int blocks_per_huge_page(struct hstate *h)
{
return huge_page_size(h) / 512;
}
#include <asm/hugetlb.h>
#ifndef arch_make_huge_pte
static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
struct page *page, int writable)
{
return entry;
}
#endif
static inline struct hstate *page_hstate(struct page *page)
{
return size_to_hstate(PAGE_SIZE << compound_order(page));
}
static inline unsigned hstate_index_to_shift(unsigned index)
{
return hstates[index].order + PAGE_SHIFT;
}
static inline int hstate_index(struct hstate *h)
{
return h - hstates;
}
#else
struct hstate {};
#define alloc_huge_page_node(h, nid) NULL
#define alloc_bootmem_huge_page(h) NULL
#define hstate_file(f) NULL
#define hstate_vma(v) NULL
#define hstate_inode(i) NULL
#define huge_page_size(h) PAGE_SIZE
#define huge_page_mask(h) PAGE_MASK
#define vma_kernel_pagesize(v) PAGE_SIZE
#define vma_mmu_pagesize(v) PAGE_SIZE
#define huge_page_order(h) 0
#define huge_page_shift(h) PAGE_SHIFT
static inline unsigned int pages_per_huge_page(struct hstate *h)
{
return 1;
}
#define hstate_index_to_shift(index) 0
#define hstate_index(h) 0
#endif
#endif /* _LINUX_HUGETLB_H */