aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux
diff options
context:
space:
mode:
authorBadari Pulavarty <pbadari@us.ibm.com>2006-01-06 03:10:38 -0500
committerLinus Torvalds <torvalds@g5.osdl.org>2006-01-06 11:33:22 -0500
commitf6b3ec238d12c8cc6cc71490c6e3127988460349 (patch)
treeb395c1054802760b0e938199231a9de9ac2f358a /include/linux
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 'include/linux')
-rw-r--r--include/linux/fs.h1
-rw-r--r--include/linux/mm.h1
2 files changed, 2 insertions, 0 deletions
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ed9a41a71e8b..115e72be25d0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1050,6 +1050,7 @@ struct inode_operations {
1050 ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t); 1050 ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
1051 ssize_t (*listxattr) (struct dentry *, char *, size_t); 1051 ssize_t (*listxattr) (struct dentry *, char *, size_t);
1052 int (*removexattr) (struct dentry *, const char *); 1052 int (*removexattr) (struct dentry *, const char *);
1053 void (*truncate_range)(struct inode *, loff_t, loff_t);
1053}; 1054};
1054 1055
1055struct seq_file; 1056struct seq_file;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 92acae9f1f4c..6c9be99429f3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -690,6 +690,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
690} 690}
691 691
692extern int vmtruncate(struct inode * inode, loff_t offset); 692extern int vmtruncate(struct inode * inode, loff_t offset);
693extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end);
693extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot); 694extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot);
694extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot); 695extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot);
695extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, unsigned long address, int write_access); 696extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, unsigned long address, int write_access);