mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-05 18:14:07 +08:00
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>
310 lines
8.2 KiB
C
310 lines
8.2 KiB
C
/*
|
|
* 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>
|
|
#include <linux/mempolicy.h>
|
|
#include <linux/hugetlb.h>
|
|
|
|
/*
|
|
* We can potentially split a vm area into separate
|
|
* areas, each area with its own behavior.
|
|
*/
|
|
static long madvise_behavior(struct vm_area_struct * vma,
|
|
struct vm_area_struct **prev,
|
|
unsigned long start, unsigned long end, int behavior)
|
|
{
|
|
struct mm_struct * mm = vma->vm_mm;
|
|
int error = 0;
|
|
pgoff_t pgoff;
|
|
int new_flags = vma->vm_flags & ~VM_READHINTMASK;
|
|
|
|
switch (behavior) {
|
|
case MADV_SEQUENTIAL:
|
|
new_flags |= VM_SEQ_READ;
|
|
break;
|
|
case MADV_RANDOM:
|
|
new_flags |= VM_RAND_READ;
|
|
break;
|
|
default:
|
|
break;
|
|
}
|
|
|
|
if (new_flags == vma->vm_flags) {
|
|
*prev = vma;
|
|
goto out;
|
|
}
|
|
|
|
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;
|
|
|
|
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;
|
|
}
|
|
|
|
success:
|
|
/*
|
|
* vm_flags is protected by the mmap_sem held in write mode.
|
|
*/
|
|
vma->vm_flags = new_flags;
|
|
|
|
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,
|
|
struct vm_area_struct ** prev,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
struct file *file = vma->vm_file;
|
|
|
|
if (!file)
|
|
return -EBADF;
|
|
|
|
if (file->f_mapping->a_ops->get_xip_page) {
|
|
/* no bad return value, but ignore advice */
|
|
return 0;
|
|
}
|
|
|
|
*prev = vma;
|
|
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;
|
|
|
|
force_page_cache_readahead(file->f_mapping,
|
|
file, start, max_sane_readahead(end - start));
|
|
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
|
|
* zap_page_range call sets things up for refill_inactive to actually free
|
|
* 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
|
|
* refill_inactive to pick up before reclaiming other pages.
|
|
*
|
|
* 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,
|
|
struct vm_area_struct ** prev,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
*prev = vma;
|
|
if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
|
|
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;
|
|
}
|
|
|
|
/*
|
|
* 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,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
struct address_space *mapping;
|
|
loff_t offset, endoff;
|
|
|
|
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;
|
|
}
|
|
|
|
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);
|
|
return vmtruncate_range(mapping->host, offset, endoff);
|
|
}
|
|
|
|
static long
|
|
madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
|
|
unsigned long start, unsigned long end, int behavior)
|
|
{
|
|
long error;
|
|
|
|
switch (behavior) {
|
|
case MADV_NORMAL:
|
|
case MADV_SEQUENTIAL:
|
|
case MADV_RANDOM:
|
|
error = madvise_behavior(vma, prev, start, end, behavior);
|
|
break;
|
|
case MADV_REMOVE:
|
|
error = madvise_remove(vma, start, end);
|
|
break;
|
|
|
|
case MADV_WILLNEED:
|
|
error = madvise_willneed(vma, prev, start, end);
|
|
break;
|
|
|
|
case MADV_DONTNEED:
|
|
error = madvise_dontneed(vma, prev, start, end);
|
|
break;
|
|
|
|
default:
|
|
error = -EINVAL;
|
|
break;
|
|
}
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* 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.
|
|
* MADV_REMOVE - the application wants to free up the given range of
|
|
* pages and associated backing store.
|
|
*
|
|
* 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.
|
|
*/
|
|
asmlinkage long sys_madvise(unsigned long start, size_t len_in, int behavior)
|
|
{
|
|
unsigned long end, tmp;
|
|
struct vm_area_struct * vma, *prev;
|
|
int unmapped_error = 0;
|
|
int error = -EINVAL;
|
|
size_t len;
|
|
|
|
down_write(¤t->mm->mmap_sem);
|
|
|
|
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.
|
|
* - different from the way of handling in mlock etc.
|
|
*/
|
|
vma = find_vma_prev(current->mm, start, &prev);
|
|
if (vma && start > vma->vm_start)
|
|
prev = vma;
|
|
|
|
for (;;) {
|
|
/* Still start < end. */
|
|
error = -ENOMEM;
|
|
if (!vma)
|
|
goto out;
|
|
|
|
/* Here start < (end|vma->vm_end). */
|
|
if (start < vma->vm_start) {
|
|
unmapped_error = -ENOMEM;
|
|
start = vma->vm_start;
|
|
if (start >= end)
|
|
goto out;
|
|
}
|
|
|
|
/* Here vma->vm_start <= start < (end|vma->vm_end) */
|
|
tmp = vma->vm_end;
|
|
if (end < tmp)
|
|
tmp = end;
|
|
|
|
/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
|
|
error = madvise_vma(vma, &prev, start, tmp, behavior);
|
|
if (error)
|
|
goto out;
|
|
start = tmp;
|
|
if (start < prev->vm_end)
|
|
start = prev->vm_end;
|
|
error = unmapped_error;
|
|
if (start >= end)
|
|
goto out;
|
|
vma = prev->vm_next;
|
|
}
|
|
out:
|
|
up_write(¤t->mm->mmap_sem);
|
|
return error;
|
|
}
|