#define MADV_WILLNEED 3 /* will need these pages */
#define MADV_SPACEAVAIL 5 /* ensure resources are available */
#define MADV_DONTNEED 6 /* don't need these pages */
+#define MADV_REMOVE 7 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SPACEAVAIL 5 /* insure that resources are reserved */
#define MADV_VPS_PURGE 6 /* Purge pages from VM page cache */
#define MADV_VPS_INHERIT 7 /* Inherit parents page size */
+#define MADV_REMOVE 8 /* remove these pages & resources */
/* The range 12-64 is reserved for page size specification. */
#define MADV_4K_PAGES 12 /* Use 4K pages */
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#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 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 MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
#define MADV_SEQUENTIAL 0x2 /* read-ahead aggressively */
#define MADV_WILLNEED 0x3 /* pre-fault pages */
#define MADV_DONTNEED 0x4 /* discard these pages */
+#define MADV_REMOVE 0x5 /* remove these pages & resources */
/* compatibility flags */
#define MAP_ANON MAP_ANONYMOUS
ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
int (*removexattr) (struct dentry *, const char *);
+ void (*truncate_range)(struct inode *, loff_t, loff_t);
};
struct seq_file;
}
extern int vmtruncate(struct inode * inode, loff_t offset);
+extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end);
extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot);
extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot);
extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, unsigned long address, int write_access);
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)
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);
* 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
out_busy:
return -ETXTBSY;
}
-
EXPORT_SYMBOL(vmtruncate);
+int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
+{
+ struct address_space *mapping = inode->i_mapping;
+
+ /*
+ * If the underlying filesystem is not going to provide
+ * a way to truncate a range of blocks (punch a hole) -
+ * we should return failure right now.
+ */
+ if (!inode->i_op || !inode->i_op->truncate_range)
+ return -ENOSYS;
+
+ down(&inode->i_sem);
+ down_write(&inode->i_alloc_sem);
+ unmap_mapping_range(mapping, offset, (end - offset), 1);
+ truncate_inode_pages_range(mapping, offset, end);
+ inode->i_op->truncate_range(inode, offset, end);
+ up_write(&inode->i_alloc_sem);
+ up(&inode->i_sem);
+
+ return 0;
+}
+EXPORT_SYMBOL(vmtruncate_range);
+
/*
* Primitive swap readahead code. We simply read an aligned block of
* (1 << page_cluster) entries in the swap area. This method is chosen
} while (next);
}
-static void shmem_truncate(struct inode *inode)
+static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
{
struct shmem_inode_info *info = SHMEM_I(inode);
unsigned long idx;
long nr_swaps_freed = 0;
int offset;
int freed;
+ int punch_hole = 0;
inode->i_ctime = inode->i_mtime = CURRENT_TIME;
- idx = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (idx >= info->next_index)
return;
spin_lock(&info->lock);
info->flags |= SHMEM_TRUNCATE;
- limit = info->next_index;
- info->next_index = idx;
+ if (likely(end == (loff_t) -1)) {
+ limit = info->next_index;
+ info->next_index = idx;
+ } else {
+ limit = (end + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ if (limit > info->next_index)
+ limit = info->next_index;
+ punch_hole = 1;
+ }
+
topdir = info->i_indirect;
- if (topdir && idx <= SHMEM_NR_DIRECT) {
+ if (topdir && idx <= SHMEM_NR_DIRECT && !punch_hole) {
info->i_indirect = NULL;
nr_pages_to_free++;
list_add(&topdir->lru, &pages_to_free);
set_page_private(subdir, page_private(subdir) - freed);
if (offset)
spin_unlock(&info->lock);
- BUG_ON(page_private(subdir) > offset);
+ if (!punch_hole)
+ BUG_ON(page_private(subdir) > offset);
}
if (offset)
offset = 0;
- else if (subdir) {
+ else if (subdir && !page_private(subdir)) {
dir[diroff] = NULL;
nr_pages_to_free++;
list_add(&subdir->lru, &pages_to_free);
* Also, though shmem_getpage checks i_size before adding to
* cache, no recheck after: so fix the narrow window there too.
*/
- truncate_inode_pages(inode->i_mapping, inode->i_size);
+ truncate_inode_pages_range(inode->i_mapping, start, end);
}
spin_lock(&info->lock);
}
}
+static void shmem_truncate(struct inode *inode)
+{
+ shmem_truncate_range(inode, inode->i_size, (loff_t)-1);
+}
+
static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = dentry->d_inode;
static struct inode_operations shmem_inode_operations = {
.truncate = shmem_truncate,
.setattr = shmem_notify_change,
+ .truncate_range = shmem_truncate_range,
};
static struct inode_operations shmem_dir_inode_operations = {