mirror of
https://github.com/torvalds/linux
synced 2024-11-05 18:23:50 +00:00
f6b3ec238d
Here is the patch to implement madvise(MADV_REMOVE) - which frees up a given range of pages & its associated backing store. Current implementation supports only shmfs/tmpfs and other filesystems return -ENOSYS. "Some app allocates large tmpfs files, then when some task quits and some client disconnect, some memory can be released. However the only way to release tmpfs-swap is to MADV_REMOVE". - Andrea Arcangeli Databases want to use this feature to drop a section of their bufferpool (shared memory segments) - without writing back to disk/swap space. This feature is also useful for supporting hot-plug memory on UML. Concerns raised by Andrew Morton: - "We have no plan for holepunching! If we _do_ have such a plan (or might in the future) then what would the API look like? I think sys_holepunch(fd, start, len), so we should start out with that." - Using madvise is very weird, because people will ask "why do I need to mmap my file before I can stick a hole in it?" - None of the other madvise operations call into the filesystem in this manner. A broad question is: is this capability an MM operation or a filesytem operation? truncate, for example, is a filesystem operation which sometimes has MM side-effects. madvise is an mm operation and with this patch, it gains FS side-effects, only they're really, really significant ones." Comments: - Andrea suggested the fs operation too but then it's more efficient to have it as a mm operation with fs side effects, because they don't immediatly know fd and physical offset of the range. It's possible to fixup in userland and to use the fs operation but it's more expensive, the vmas are already in the kernel and we can use them. Short term plan & Future Direction: - We seem to need this interface only for shmfs/tmpfs files in the short term. We have to add hooks into the filesystem for correctness and completeness. This is what this patch does. - In the future, plan is to support both fs and mmap apis also. This also involves (other) filesystem specific functions to be implemented. - Current patch doesn't support VM_NONLINEAR - which can be addressed in the future. Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Andrea Arcangeli <andrea@suse.de> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Ulrich Drepper <drepper@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
58 lines
2.7 KiB
C
58 lines
2.7 KiB
C
#ifndef __PARISC_MMAN_H__
|
|
#define __PARISC_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 0x03 /* Mask for type of mapping */
|
|
#define MAP_FIXED 0x04 /* Interpret addr exactly */
|
|
#define MAP_ANONYMOUS 0x10 /* don't use a file */
|
|
|
|
#define MAP_DENYWRITE 0x0800 /* ETXTBSY */
|
|
#define MAP_EXECUTABLE 0x1000 /* mark it as an executable */
|
|
#define MAP_LOCKED 0x2000 /* pages are locked */
|
|
#define MAP_NORESERVE 0x4000 /* don't check for reservations */
|
|
#define MAP_GROWSDOWN 0x8000 /* stack-like segment */
|
|
#define MAP_POPULATE 0x10000 /* populate (prefault) pagetables */
|
|
#define MAP_NONBLOCK 0x20000 /* do not block on IO */
|
|
|
|
#define MS_SYNC 1 /* synchronous memory sync */
|
|
#define MS_ASYNC 2 /* sync memory asynchronously */
|
|
#define MS_INVALIDATE 4 /* invalidate the caches */
|
|
|
|
#define MCL_CURRENT 1 /* lock all current mappings */
|
|
#define MCL_FUTURE 2 /* lock all future mappings */
|
|
|
|
#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 */
|
|
#define MADV_SPACEAVAIL 5 /* insure that resources are reserved */
|
|
#define MADV_VPS_PURGE 6 /* Purge pages from VM page cache */
|
|
#define MADV_VPS_INHERIT 7 /* Inherit parents page size */
|
|
#define MADV_REMOVE 8 /* remove these pages & resources */
|
|
|
|
/* The range 12-64 is reserved for page size specification. */
|
|
#define MADV_4K_PAGES 12 /* Use 4K pages */
|
|
#define MADV_16K_PAGES 14 /* Use 16K pages */
|
|
#define MADV_64K_PAGES 16 /* Use 64K pages */
|
|
#define MADV_256K_PAGES 18 /* Use 256K pages */
|
|
#define MADV_1M_PAGES 20 /* Use 1 Megabyte pages */
|
|
#define MADV_4M_PAGES 22 /* Use 4 Megabyte pages */
|
|
#define MADV_16M_PAGES 24 /* Use 16 Megabyte pages */
|
|
#define MADV_64M_PAGES 26 /* Use 64 Megabyte pages */
|
|
|
|
/* compatibility flags */
|
|
#define MAP_ANON MAP_ANONYMOUS
|
|
#define MAP_FILE 0
|
|
#define MAP_VARIABLE 0
|
|
|
|
#endif /* __PARISC_MMAN_H__ */
|