mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 05:48:40 +00:00
![Badari Pulavarty](/assets/img/avatar_default.png)
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>
63 lines
2.8 KiB
C
63 lines
2.8 KiB
C
/* $Id: mman.h,v 1.2 2000/03/15 02:44:26 davem Exp $ */
|
|
#ifndef __SPARC64_MMAN_H__
|
|
#define __SPARC64_MMAN_H__
|
|
|
|
/* SunOS'ified... */
|
|
|
|
#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 */
|
|
#define MAP_RENAME MAP_ANONYMOUS /* In SunOS terminology */
|
|
#define MAP_NORESERVE 0x40 /* don't reserve swap pages */
|
|
#define MAP_INHERIT 0x80 /* SunOS doesn't do this, but... */
|
|
#define MAP_LOCKED 0x100 /* lock the mapping */
|
|
#define _MAP_NEW 0x80000000 /* Binary compatibility is fun... */
|
|
|
|
#define MAP_GROWSDOWN 0x0200 /* stack-like segment */
|
|
#define MAP_DENYWRITE 0x0800 /* ETXTBSY */
|
|
#define MAP_EXECUTABLE 0x1000 /* mark it as an executable */
|
|
|
|
#define MS_ASYNC 1 /* sync memory asynchronously */
|
|
#define MS_INVALIDATE 2 /* invalidate the caches */
|
|
#define MS_SYNC 4 /* synchronous memory sync */
|
|
|
|
#define MCL_CURRENT 0x2000 /* lock all currently mapped pages */
|
|
#define MCL_FUTURE 0x4000 /* lock all additions to address space */
|
|
|
|
#define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */
|
|
#define MAP_NONBLOCK 0x10000 /* do not block on IO */
|
|
|
|
/* XXX Need to add flags to SunOS's mctl, mlockall, and madvise system
|
|
* XXX calls.
|
|
*/
|
|
|
|
/* SunOS sys_mctl() stuff... */
|
|
#define MC_SYNC 1 /* Sync pages in memory with storage (usu. a file) */
|
|
#define MC_LOCK 2 /* Lock pages into core ram, do not allow swapping of them */
|
|
#define MC_UNLOCK 3 /* Unlock pages locked via previous mctl() with MC_LOCK arg */
|
|
#define MC_LOCKAS 5 /* Lock an entire address space of the calling process */
|
|
#define MC_UNLOCKAS 6 /* Unlock entire address space of calling process */
|
|
|
|
#define MADV_NORMAL 0x0 /* default page-in behavior */
|
|
#define MADV_RANDOM 0x1 /* page-in minimum required */
|
|
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
|
|
#define MADV_WILLNEED 0x3 /* pre-fault pages */
|
|
#define MADV_DONTNEED 0x4 /* discard these pages */
|
|
#define MADV_FREE 0x5 /* (Solaris) contents can be freed */
|
|
#define MADV_REMOVE 0x6 /* remove these pages & resources */
|
|
|
|
/* compatibility flags */
|
|
#define MAP_ANON MAP_ANONYMOUS
|
|
#define MAP_FILE 0
|
|
|
|
#endif /* __SPARC64_MMAN_H__ */
|