summaryrefslogtreecommitdiff
path: root/mm/madvise.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@ppc970.osdl.org>2005-04-17 02:20:36 +0400
committerLinus Torvalds <torvalds@ppc970.osdl.org>2005-04-17 02:20:36 +0400
commit1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 (patch)
tree0bba044c4ce775e45a88a51686b5d9f90697ea9d /mm/madvise.c
downloadlinux-1da177e4c3f41524e886b7f1b8a0c1fc7321cac2.tar.xz
Linux-2.6.12-rc2
Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
Diffstat (limited to 'mm/madvise.c')
-rw-r--r--mm/madvise.c242
1 files changed, 242 insertions, 0 deletions
diff --git a/mm/madvise.c b/mm/madvise.c
new file mode 100644
index 000000000000..944b5e52d812
--- /dev/null
+++ b/mm/madvise.c
@@ -0,0 +1,242 @@
+/*
+ * 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/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, unsigned long start,
+ unsigned long end, int behavior)
+{
+ struct mm_struct * mm = vma->vm_mm;
+ int error = 0;
+
+ 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;
+ }
+
+ /*
+ * vm_flags is protected by the mmap_sem held in write mode.
+ */
+ VM_ClearReadHint(vma);
+
+ switch (behavior) {
+ case MADV_SEQUENTIAL:
+ vma->vm_flags |= VM_SEQ_READ;
+ break;
+ case MADV_RANDOM:
+ vma->vm_flags |= VM_RAND_READ;
+ break;
+ default:
+ break;
+ }
+
+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,
+ unsigned long start, unsigned long end)
+{
+ struct file *file = vma->vm_file;
+
+ if (!file)
+ return -EBADF;
+
+ 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,
+ unsigned long start, unsigned long end)
+{
+ if ((vma->vm_flags & VM_LOCKED) || is_vm_hugetlb_page(vma))
+ 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;
+}
+
+static long madvise_vma(struct vm_area_struct * vma, unsigned long start,
+ unsigned long end, int behavior)
+{
+ long error = -EBADF;
+
+ switch (behavior) {
+ case MADV_NORMAL:
+ case MADV_SEQUENTIAL:
+ case MADV_RANDOM:
+ error = madvise_behavior(vma, start, end, behavior);
+ break;
+
+ case MADV_WILLNEED:
+ error = madvise_willneed(vma, start, end);
+ break;
+
+ case MADV_DONTNEED:
+ error = madvise_dontneed(vma, 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.
+ *
+ * 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;
+ struct vm_area_struct * vma;
+ int unmapped_error = 0;
+ int error = -EINVAL;
+ size_t len;
+
+ down_write(&current->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.
+ */
+ vma = find_vma(current->mm, start);
+ for (;;) {
+ /* Still start < end. */
+ error = -ENOMEM;
+ if (!vma)
+ goto out;
+
+ /* Here start < vma->vm_end. */
+ if (start < vma->vm_start) {
+ unmapped_error = -ENOMEM;
+ start = vma->vm_start;
+ }
+
+ /* Here vma->vm_start <= start < vma->vm_end. */
+ if (end <= vma->vm_end) {
+ if (start < end) {
+ error = madvise_vma(vma, start, end,
+ behavior);
+ if (error)
+ goto out;
+ }
+ error = unmapped_error;
+ goto out;
+ }
+
+ /* Here vma->vm_start <= start < vma->vm_end < end. */
+ error = madvise_vma(vma, start, vma->vm_end, behavior);
+ if (error)
+ goto out;
+ start = vma->vm_end;
+ vma = vma->vm_next;
+ }
+
+out:
+ up_write(&current->mm->mmap_sem);
+ return error;
+}