#include <linux/hugetlb.h>
/*
+ * 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;
+ }
+}
+
+/*
* We can potentially split a vm area into separate
* areas, each area with its own behavior.
*/
struct mm_struct * mm = vma->vm_mm;
int error = 0;
pgoff_t pgoff;
- int new_flags = vma->vm_flags & ~VM_READHINTMASK;
+ int new_flags = vma->vm_flags;
switch (behavior) {
+ case MADV_NORMAL:
+ new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ;
+ break;
case MADV_SEQUENTIAL:
- new_flags |= VM_SEQ_READ;
+ new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ;
break;
case MADV_RANDOM:
- new_flags |= VM_RAND_READ;
+ new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ;
break;
- default:
+ case MADV_DONTFORK:
+ new_flags |= VM_DONTCOPY;
+ break;
+ case MADV_DOFORK:
+ new_flags &= ~VM_DONTCOPY;
break;
}
if (new_flags == vma->vm_flags) {
*prev = vma;
- goto success;
+ goto out;
}
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
goto out;
}
+success:
/*
* vm_flags is protected by the mmap_sem held in write mode.
*/
- VM_ClearReadHint(vma);
vma->vm_flags = new_flags;
out:
if (error == -ENOMEM)
error = -EAGAIN;
-success:
return error;
}
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)
unsigned long start, unsigned long end)
{
*prev = vma;
- if ((vma->vm_flags & VM_LOCKED) || is_vm_hugetlb_page(vma))
+ if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
return -EINVAL;
if (unlikely(vma->vm_flags & VM_NONLINEAR)) {
return 0;
}
-static long madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
- unsigned long start, unsigned long end, int behavior)
+/*
+ * 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,
+ struct vm_area_struct **prev,
+ unsigned long start, unsigned long end)
+{
+ struct address_space *mapping;
+ loff_t offset, endoff;
+ int error;
+
+ *prev = NULL; /* tell sys_madvise we drop mmap_sem */
+
+ 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;
+ }
+
+ if ((vma->vm_flags & (VM_SHARED|VM_WRITE)) != (VM_SHARED|VM_WRITE))
+ return -EACCES;
+
+ 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);
+
+ /* vmtruncate_range needs to take i_mutex and i_alloc_sem */
+ up_read(¤t->mm->mmap_sem);
+ error = vmtruncate_range(mapping->host, offset, endoff);
+ down_read(¤t->mm->mmap_sem);
+ return error;
+}
+
+static long
+madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
+ unsigned long start, unsigned long end, int behavior)
{
- long error = -EBADF;
+ long error;
switch (behavior) {
+ case MADV_DOFORK:
+ if (vma->vm_flags & VM_IO) {
+ error = -EINVAL;
+ break;
+ }
+ case MADV_DONTFORK:
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, prev, start, end);
+ break;
case MADV_WILLNEED:
error = madvise_willneed(vma, prev, start, end);
error = -EINVAL;
break;
}
-
return error;
}
* 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
int error = -EINVAL;
size_t len;
- down_write(¤t->mm->mmap_sem);
+ if (madvise_need_mmap_write(behavior))
+ down_write(¤t->mm->mmap_sem);
+ else
+ down_read(¤t->mm->mmap_sem);
if (start & ~PAGE_MASK)
goto out;
* - different from the way of handling in mlock etc.
*/
vma = find_vma_prev(current->mm, start, &prev);
- if (!vma && prev)
- vma = prev->vm_next;
+ if (vma && start > vma->vm_start)
+ prev = vma;
+
for (;;) {
/* Still start < end. */
error = -ENOMEM;
if (error)
goto out;
start = tmp;
- if (start < prev->vm_end)
+ if (prev && start < prev->vm_end)
start = prev->vm_end;
error = unmapped_error;
if (start >= end)
goto out;
- vma = prev->vm_next;
+ if (prev)
+ vma = prev->vm_next;
+ else /* madvise_remove dropped mmap_sem */
+ vma = find_vma(current->mm, start);
}
out:
- up_write(¤t->mm->mmap_sem);
+ if (madvise_need_mmap_write(behavior))
+ up_write(¤t->mm->mmap_sem);
+ else
+ up_read(¤t->mm->mmap_sem);
+
return error;
}