42d7395feb
There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
70 lines
2.7 KiB
C
70 lines
2.7 KiB
C
#ifndef __ASM_GENERIC_MMAN_COMMON_H
|
|
#define __ASM_GENERIC_MMAN_COMMON_H
|
|
|
|
/*
|
|
Author: Michael S. Tsirkin <mst@mellanox.co.il>, Mellanox Technologies Ltd.
|
|
Based on: asm-xxx/mman.h
|
|
*/
|
|
|
|
#define PROT_READ 0x1 /* page can be read */
|
|
#define PROT_WRITE 0x2 /* page can be written */
|
|
#define PROT_EXEC 0x4 /* page can be executed */
|
|
#define PROT_SEM 0x8 /* page may be used for atomic ops */
|
|
#define PROT_NONE 0x0 /* page can not be accessed */
|
|
#define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */
|
|
#define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */
|
|
|
|
#define MAP_SHARED 0x01 /* Share changes */
|
|
#define MAP_PRIVATE 0x02 /* Changes are private */
|
|
#define MAP_TYPE 0x0f /* Mask for type of mapping */
|
|
#define MAP_FIXED 0x10 /* Interpret addr exactly */
|
|
#define MAP_ANONYMOUS 0x20 /* don't use a file */
|
|
#ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED
|
|
# define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be uninitialized */
|
|
#else
|
|
# define MAP_UNINITIALIZED 0x0 /* Don't support this flag */
|
|
#endif
|
|
|
|
#define MS_ASYNC 1 /* sync memory asynchronously */
|
|
#define MS_INVALIDATE 2 /* invalidate the caches */
|
|
#define MS_SYNC 4 /* synchronous memory sync */
|
|
|
|
#define MADV_NORMAL 0 /* no further special treatment */
|
|
#define MADV_RANDOM 1 /* expect random page references */
|
|
#define MADV_SEQUENTIAL 2 /* expect sequential page references */
|
|
#define MADV_WILLNEED 3 /* will need these pages */
|
|
#define MADV_DONTNEED 4 /* don't need these pages */
|
|
|
|
/* common parameters: try to keep these consistent across architectures */
|
|
#define MADV_REMOVE 9 /* remove these pages & resources */
|
|
#define MADV_DONTFORK 10 /* don't inherit across fork */
|
|
#define MADV_DOFORK 11 /* do inherit across fork */
|
|
#define MADV_HWPOISON 100 /* poison a page for testing */
|
|
#define MADV_SOFT_OFFLINE 101 /* soft offline page for testing */
|
|
|
|
#define MADV_MERGEABLE 12 /* KSM may merge identical pages */
|
|
#define MADV_UNMERGEABLE 13 /* KSM may not merge identical pages */
|
|
|
|
#define MADV_HUGEPAGE 14 /* Worth backing with hugepages */
|
|
#define MADV_NOHUGEPAGE 15 /* Not worth backing with hugepages */
|
|
|
|
#define MADV_DONTDUMP 16 /* Explicity exclude from the core dump,
|
|
overrides the coredump filter bits */
|
|
#define MADV_DODUMP 17 /* Clear the MADV_NODUMP flag */
|
|
|
|
/* compatibility flags */
|
|
#define MAP_FILE 0
|
|
|
|
/*
|
|
* When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
|
|
* This gives us 6 bits, which is enough until someone invents 128 bit address
|
|
* spaces.
|
|
*
|
|
* Assume these are all power of twos.
|
|
* When 0 use the default page size.
|
|
*/
|
|
#define MAP_HUGE_SHIFT 26
|
|
#define MAP_HUGE_MASK 0x3f
|
|
|
|
#endif /* __ASM_GENERIC_MMAN_COMMON_H */
|