2005-04-17 02:20:36 +04:00
/*
* linux / mm / madvise . c
*
* Copyright ( C ) 1999 Linus Torvalds
* Copyright ( C ) 2002 Christoph Hellwig
*/
# include <linux/mman.h>
# include <linux/pagemap.h>
# include <linux/syscalls.h>
2005-06-22 04:14:37 +04:00
# include <linux/mempolicy.h>
2005-04-17 02:20:36 +04:00
# include <linux/hugetlb.h>
Detach sched.h from mm.h
First thing mm.h does is including sched.h solely for can_do_mlock() inline
function which has "current" dereference inside. By dealing with can_do_mlock()
mm.h can be detached from sched.h which is good. See below, why.
This patch
a) removes unconditional inclusion of sched.h from mm.h
b) makes can_do_mlock() normal function in mm/mlock.c
c) exports can_do_mlock() to not break compilation
d) adds sched.h inclusions back to files that were getting it indirectly.
e) adds less bloated headers to some files (asm/signal.h, jiffies.h) that were
getting them indirectly
Net result is:
a) mm.h users would get less code to open, read, preprocess, parse, ... if
they don't need sched.h
b) sched.h stops being dependency for significant number of files:
on x86_64 allmodconfig touching sched.h results in recompile of 4083 files,
after patch it's only 3744 (-8.3%).
Cross-compile tested on
all arm defconfigs, all mips defconfigs, all powerpc defconfigs,
alpha alpha-up
arm
i386 i386-up i386-defconfig i386-allnoconfig
ia64 ia64-up
m68k
mips
parisc parisc-up
powerpc powerpc-up
s390 s390-up
sparc sparc-up
sparc64 sparc64-up
um-x86_64
x86_64 x86_64-up x86_64-defconfig x86_64-allnoconfig
as well as my two usual configs.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-21 01:22:52 +04:00
# include <linux/sched.h>
2005-04-17 02:20:36 +04:00
2007-05-07 01:49:53 +04:00
/*
* Any behaviour which results in changes to the vma - > vm_flags needs to
* take mmap_sem for writing . Others , which simply traverse vmas , need
* to only take it for reading .
*/
static int madvise_need_mmap_write ( int behavior )
{
switch ( behavior ) {
case MADV_REMOVE :
case MADV_WILLNEED :
case MADV_DONTNEED :
return 0 ;
default :
/* be safe, default to 1. list exceptions explicitly */
return 1 ;
}
}
2005-04-17 02:20:36 +04:00
/*
* We can potentially split a vm area into separate
* areas , each area with its own behavior .
*/
2005-06-22 04:14:37 +04:00
static long madvise_behavior ( struct vm_area_struct * vma ,
struct vm_area_struct * * prev ,
unsigned long start , unsigned long end , int behavior )
2005-04-17 02:20:36 +04:00
{
struct mm_struct * mm = vma - > vm_mm ;
int error = 0 ;
2005-06-22 04:14:37 +04:00
pgoff_t pgoff ;
2006-02-15 00:53:08 +03:00
int new_flags = vma - > vm_flags ;
2005-06-22 04:14:36 +04:00
switch ( behavior ) {
2006-02-15 00:53:08 +03:00
case MADV_NORMAL :
new_flags = new_flags & ~ VM_RAND_READ & ~ VM_SEQ_READ ;
break ;
2005-06-22 04:14:36 +04:00
case MADV_SEQUENTIAL :
2006-02-15 00:53:08 +03:00
new_flags = ( new_flags & ~ VM_RAND_READ ) | VM_SEQ_READ ;
2005-06-22 04:14:36 +04:00
break ;
case MADV_RANDOM :
2006-02-15 00:53:08 +03:00
new_flags = ( new_flags & ~ VM_SEQ_READ ) | VM_RAND_READ ;
2005-06-22 04:14:36 +04:00
break ;
2006-02-15 00:53:08 +03:00
case MADV_DONTFORK :
new_flags | = VM_DONTCOPY ;
break ;
case MADV_DOFORK :
new_flags & = ~ VM_DONTCOPY ;
2005-06-22 04:14:36 +04:00
break ;
}
2005-06-22 04:14:37 +04:00
if ( new_flags = = vma - > vm_flags ) {
* prev = vma ;
2005-09-04 02:54:53 +04:00
goto out ;
2005-06-22 04:14:37 +04:00
}
pgoff = vma - > vm_pgoff + ( ( start - vma - > vm_start ) > > PAGE_SHIFT ) ;
* prev = vma_merge ( mm , * prev , start , end , new_flags , vma - > anon_vma ,
vma - > vm_file , pgoff , vma_policy ( vma ) ) ;
if ( * prev ) {
vma = * prev ;
goto success ;
}
* prev = vma ;
2005-04-17 02:20:36 +04:00
if ( start ! = vma - > vm_start ) {
error = split_vma ( mm , vma , start , 1 ) ;
if ( error )
goto out ;
}
if ( end ! = vma - > vm_end ) {
error = split_vma ( mm , vma , end , 0 ) ;
if ( error )
goto out ;
}
2005-09-04 02:54:53 +04:00
success :
2005-04-17 02:20:36 +04:00
/*
* vm_flags is protected by the mmap_sem held in write mode .
*/
2005-06-22 04:14:36 +04:00
vma - > vm_flags = new_flags ;
2005-04-17 02:20:36 +04:00
out :
if ( error = = - ENOMEM )
error = - EAGAIN ;
return error ;
}
/*
* Schedule all required I / O operations . Do not wait for completion .
*/
static long madvise_willneed ( struct vm_area_struct * vma ,
2005-06-22 04:14:37 +04:00
struct vm_area_struct * * prev ,
2005-04-17 02:20:36 +04:00
unsigned long start , unsigned long end )
{
struct file * file = vma - > vm_file ;
2005-10-11 19:29:06 +04:00
if ( ! file )
return - EBADF ;
2008-04-28 13:13:02 +04:00
if ( file - > f_mapping - > a_ops - > get_xip_mem ) {
2005-06-24 09:05:29 +04:00
/* no bad return value, but ignore advice */
return 0 ;
}
2005-06-22 04:14:37 +04:00
* prev = vma ;
2005-04-17 02:20:36 +04:00
start = ( ( start - vma - > vm_start ) > > PAGE_SHIFT ) + vma - > vm_pgoff ;
if ( end > vma - > vm_end )
end = vma - > vm_end ;
end = ( ( end - vma - > vm_start ) > > PAGE_SHIFT ) + vma - > vm_pgoff ;
2009-06-17 02:31:20 +04:00
force_page_cache_readahead ( file - > f_mapping , file , start , end - start ) ;
2005-04-17 02:20:36 +04:00
return 0 ;
}
/*
* Application no longer needs these pages . If the pages are dirty ,
* it ' s OK to just throw them away . The app will be more careful about
* data it wants to keep . Be sure to free swap resources too . The
2008-07-30 09:33:39 +04:00
* zap_page_range call sets things up for shrink_active_list to actually free
2005-04-17 02:20:36 +04:00
* these pages later if no one else has touched them in the meantime ,
* although we could add these pages to a global reuse list for
2008-07-30 09:33:39 +04:00
* shrink_active_list to pick up before reclaiming other pages .
2005-04-17 02:20:36 +04:00
*
* NB : This interface discards data rather than pushes it out to swap ,
* as some implementations do . This has performance implications for
* applications like large transactional databases which want to discard
* pages in anonymous maps after committing to backing store the data
* that was kept in them . There is no reason to write this data out to
* the swap area if the application is discarding it .
*
* An interface that causes the system to free clean pages and flush
* dirty pages is already available as msync ( MS_INVALIDATE ) .
*/
static long madvise_dontneed ( struct vm_area_struct * vma ,
2005-06-22 04:14:37 +04:00
struct vm_area_struct * * prev ,
2005-04-17 02:20:36 +04:00
unsigned long start , unsigned long end )
{
2005-06-22 04:14:37 +04:00
* prev = vma ;
2005-11-29 01:34:23 +03:00
if ( vma - > vm_flags & ( VM_LOCKED | VM_HUGETLB | VM_PFNMAP ) )
2005-04-17 02:20:36 +04:00
return - EINVAL ;
if ( unlikely ( vma - > vm_flags & VM_NONLINEAR ) ) {
struct zap_details details = {
. nonlinear_vma = vma ,
. last_index = ULONG_MAX ,
} ;
zap_page_range ( vma , start , end - start , & details ) ;
} else
zap_page_range ( vma , start , end - start , NULL ) ;
return 0 ;
}
[PATCH] madvise(MADV_REMOVE): remove pages from tmpfs shm backing store
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>
2006-01-06 11:10:38 +03:00
/*
* Application wants to free up the pages and associated backing store .
* This is effectively punching a hole into the middle of a file .
*
* NOTE : Currently , only shmfs / tmpfs is supported for this operation .
* Other filesystems return - ENOSYS .
*/
static long madvise_remove ( struct vm_area_struct * vma ,
2007-03-17 00:38:10 +03:00
struct vm_area_struct * * prev ,
[PATCH] madvise(MADV_REMOVE): remove pages from tmpfs shm backing store
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>
2006-01-06 11:10:38 +03:00
unsigned long start , unsigned long end )
{
struct address_space * mapping ;
2007-03-29 12:20:38 +04:00
loff_t offset , endoff ;
int error ;
[PATCH] madvise(MADV_REMOVE): remove pages from tmpfs shm backing store
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>
2006-01-06 11:10:38 +03:00
2007-03-29 12:20:38 +04:00
* prev = NULL ; /* tell sys_madvise we drop mmap_sem */
2007-03-17 00:38:10 +03:00
[PATCH] madvise(MADV_REMOVE): remove pages from tmpfs shm backing store
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>
2006-01-06 11:10:38 +03:00
if ( vma - > vm_flags & ( VM_LOCKED | VM_NONLINEAR | VM_HUGETLB ) )
return - EINVAL ;
if ( ! vma - > vm_file | | ! vma - > vm_file - > f_mapping
| | ! vma - > vm_file - > f_mapping - > host ) {
return - EINVAL ;
}
2006-04-18 01:46:32 +04:00
if ( ( vma - > vm_flags & ( VM_SHARED | VM_WRITE ) ) ! = ( VM_SHARED | VM_WRITE ) )
return - EACCES ;
[PATCH] madvise(MADV_REMOVE): remove pages from tmpfs shm backing store
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>
2006-01-06 11:10:38 +03:00
mapping = vma - > vm_file - > f_mapping ;
offset = ( loff_t ) ( start - vma - > vm_start )
+ ( ( loff_t ) vma - > vm_pgoff < < PAGE_SHIFT ) ;
endoff = ( loff_t ) ( end - vma - > vm_start - 1 )
+ ( ( loff_t ) vma - > vm_pgoff < < PAGE_SHIFT ) ;
2007-03-29 12:20:38 +04:00
/* vmtruncate_range needs to take i_mutex and i_alloc_sem */
2007-05-07 01:49:53 +04:00
up_read ( & current - > mm - > mmap_sem ) ;
2007-03-29 12:20:38 +04:00
error = vmtruncate_range ( mapping - > host , offset , endoff ) ;
2007-05-07 01:49:53 +04:00
down_read ( & current - > mm - > mmap_sem ) ;
2007-03-29 12:20:38 +04:00
return error ;
[PATCH] madvise(MADV_REMOVE): remove pages from tmpfs shm backing store
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>
2006-01-06 11:10:38 +03:00
}
2005-07-27 22:43:59 +04:00
static long
madvise_vma ( struct vm_area_struct * vma , struct vm_area_struct * * prev ,
unsigned long start , unsigned long end , int behavior )
2005-04-17 02:20:36 +04:00
{
2005-10-11 19:29:06 +04:00
long error ;
2005-07-27 22:43:59 +04:00
2005-04-17 02:20:36 +04:00
switch ( behavior ) {
2006-02-15 00:53:08 +03:00
case MADV_DOFORK :
if ( vma - > vm_flags & VM_IO ) {
error = - EINVAL ;
break ;
}
case MADV_DONTFORK :
2005-04-17 02:20:36 +04:00
case MADV_NORMAL :
case MADV_SEQUENTIAL :
case MADV_RANDOM :
2005-06-22 04:14:37 +04:00
error = madvise_behavior ( vma , prev , start , end , behavior ) ;
2005-04-17 02:20:36 +04:00
break ;
[PATCH] madvise(MADV_REMOVE): remove pages from tmpfs shm backing store
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>
2006-01-06 11:10:38 +03:00
case MADV_REMOVE :
2007-03-17 00:38:10 +03:00
error = madvise_remove ( vma , prev , start , end ) ;
[PATCH] madvise(MADV_REMOVE): remove pages from tmpfs shm backing store
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>
2006-01-06 11:10:38 +03:00
break ;
2005-04-17 02:20:36 +04:00
case MADV_WILLNEED :
2005-06-22 04:14:37 +04:00
error = madvise_willneed ( vma , prev , start , end ) ;
2005-04-17 02:20:36 +04:00
break ;
case MADV_DONTNEED :
2005-06-22 04:14:37 +04:00
error = madvise_dontneed ( vma , prev , start , end ) ;
2005-04-17 02:20:36 +04:00
break ;
default :
2009-06-17 02:32:38 +04:00
BUG ( ) ;
2005-04-17 02:20:36 +04:00
break ;
}
return error ;
}
2009-06-17 02:32:38 +04:00
static int
madvise_behavior_valid ( int behavior )
{
switch ( behavior ) {
case MADV_DOFORK :
case MADV_DONTFORK :
case MADV_NORMAL :
case MADV_SEQUENTIAL :
case MADV_RANDOM :
case MADV_REMOVE :
case MADV_WILLNEED :
case MADV_DONTNEED :
return 1 ;
default :
return 0 ;
}
}
2005-04-17 02:20:36 +04:00
/*
* The madvise ( 2 ) system call .
*
* Applications can use madvise ( ) to advise the kernel how it should
* handle paging I / O in this VM area . The idea is to help the kernel
* use appropriate read - ahead and caching techniques . The information
* provided is advisory only , and can be safely disregarded by the
* kernel without affecting the correct operation of the application .
*
* behavior values :
* MADV_NORMAL - the default behavior is to read clusters . This
* results in some read - ahead and read - behind .
* MADV_RANDOM - the system should read the minimum amount of data
* on any access , since it is unlikely that the appli -
* cation will need more than what it asks for .
* MADV_SEQUENTIAL - pages in the given range will probably be accessed
* once , so they can be aggressively read ahead , and
* can be freed soon after they are accessed .
* MADV_WILLNEED - the application is notifying the system to read
* some pages ahead .
* MADV_DONTNEED - the application is finished with the given range ,
* so the kernel can free resources associated with it .
[PATCH] madvise(MADV_REMOVE): remove pages from tmpfs shm backing store
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>
2006-01-06 11:10:38 +03:00
* MADV_REMOVE - the application wants to free up the given range of
* pages and associated backing store .
2005-04-17 02:20:36 +04:00
*
* return values :
* zero - success
* - EINVAL - start + len < 0 , start is not page - aligned ,
* " behavior " is not a valid value , or application
* is attempting to release locked or shared pages .
* - ENOMEM - addresses in the specified range are not currently
* mapped , or are outside the AS of the process .
* - EIO - an I / O error occurred while paging in data .
* - EBADF - map exists , but area maps something that isn ' t a file .
* - EAGAIN - a kernel resource was temporarily unavailable .
*/
2009-01-14 16:14:16 +03:00
SYSCALL_DEFINE3 ( madvise , unsigned long , start , size_t , len_in , int , behavior )
2005-04-17 02:20:36 +04:00
{
2005-06-22 04:14:37 +04:00
unsigned long end , tmp ;
struct vm_area_struct * vma , * prev ;
2005-04-17 02:20:36 +04:00
int unmapped_error = 0 ;
int error = - EINVAL ;
2007-07-16 10:38:21 +04:00
int write ;
2005-04-17 02:20:36 +04:00
size_t len ;
2009-06-17 02:32:38 +04:00
if ( ! madvise_behavior_valid ( behavior ) )
return error ;
2007-07-16 10:38:21 +04:00
write = madvise_need_mmap_write ( behavior ) ;
if ( write )
2007-05-07 01:49:53 +04:00
down_write ( & current - > mm - > mmap_sem ) ;
else
down_read ( & current - > mm - > mmap_sem ) ;
2005-04-17 02:20:36 +04:00
if ( start & ~ PAGE_MASK )
goto out ;
len = ( len_in + ~ PAGE_MASK ) & PAGE_MASK ;
/* Check to see whether len was rounded up from small -ve to zero */
if ( len_in & & ! len )
goto out ;
end = start + len ;
if ( end < start )
goto out ;
error = 0 ;
if ( end = = start )
goto out ;
/*
* If the interval [ start , end ) covers some unmapped address
* ranges , just ignore them , but return - ENOMEM at the end .
2005-06-22 04:14:37 +04:00
* - different from the way of handling in mlock etc .
2005-04-17 02:20:36 +04:00
*/
2005-06-22 04:14:37 +04:00
vma = find_vma_prev ( current - > mm , start , & prev ) ;
2005-09-04 02:54:53 +04:00
if ( vma & & start > vma - > vm_start )
prev = vma ;
2005-04-17 02:20:36 +04:00
for ( ; ; ) {
/* Still start < end. */
error = - ENOMEM ;
if ( ! vma )
goto out ;
2005-06-22 04:14:37 +04:00
/* Here start < (end|vma->vm_end). */
2005-04-17 02:20:36 +04:00
if ( start < vma - > vm_start ) {
unmapped_error = - ENOMEM ;
start = vma - > vm_start ;
2005-06-22 04:14:37 +04:00
if ( start > = end )
goto out ;
2005-04-17 02:20:36 +04:00
}
2005-06-22 04:14:37 +04:00
/* Here vma->vm_start <= start < (end|vma->vm_end) */
tmp = vma - > vm_end ;
if ( end < tmp )
tmp = end ;
2005-04-17 02:20:36 +04:00
2005-06-22 04:14:37 +04:00
/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
error = madvise_vma ( vma , & prev , start , tmp , behavior ) ;
2005-04-17 02:20:36 +04:00
if ( error )
goto out ;
2005-06-22 04:14:37 +04:00
start = tmp ;
2007-03-29 12:20:38 +04:00
if ( prev & & start < prev - > vm_end )
2005-06-22 04:14:37 +04:00
start = prev - > vm_end ;
error = unmapped_error ;
if ( start > = end )
goto out ;
2007-03-29 12:20:38 +04:00
if ( prev )
vma = prev - > vm_next ;
else /* madvise_remove dropped mmap_sem */
vma = find_vma ( current - > mm , start ) ;
2005-04-17 02:20:36 +04:00
}
out :
2007-07-16 10:38:21 +04:00
if ( write )
2007-05-07 01:49:53 +04:00
up_write ( & current - > mm - > mmap_sem ) ;
else
up_read ( & current - > mm - > mmap_sem ) ;
2005-04-17 02:20:36 +04:00
return error ;
}