summaryrefslogtreecommitdiffstats
path: root/mm/madvise.c
diff options
context:
space:
mode:
authorBadari Pulavarty <pbadari@us.ibm.com>2006-01-06 00:10:38 -0800
committerLinus Torvalds <torvalds@g5.osdl.org>2006-01-06 08:33:22 -0800
commitf6b3ec238d12c8cc6cc71490c6e3127988460349 (patch)
treeb395c1054802760b0e938199231a9de9ac2f358a /mm/madvise.c
parentd7339071f6a8b50101d7ba327926b770f22d5d8b (diff)
[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>
Diffstat (limited to 'mm/madvise.c')
-rw-r--r--mm/madvise.c35
1 files changed, 35 insertions, 0 deletions
diff --git a/mm/madvise.c b/mm/madvise.c
index 2b7cf0400a2..ae0ae3ea299 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -140,6 +140,36 @@ static long madvise_dontneed(struct vm_area_struct * vma,
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)
@@ -152,6 +182,9 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
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);
@@ -190,6 +223,8 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
* 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