aboutsummaryrefslogtreecommitdiff
path: root/mm/madvise.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/madvise.c')
-rw-r--r--mm/madvise.c162
1 files changed, 134 insertions, 28 deletions
diff --git a/mm/madvise.c b/mm/madvise.c
index 14d260fa0d1..a402f8fdc68 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -16,6 +16,9 @@
#include <linux/ksm.h>
#include <linux/fs.h>
#include <linux/file.h>
+#include <linux/blkdev.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
/*
* Any behaviour which results in changes to the vma->vm_flags needs to
@@ -39,11 +42,11 @@ static int madvise_need_mmap_write(int behavior)
* 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,
+static long madvise_behavior(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end, int behavior)
{
- struct mm_struct * mm = vma->vm_mm;
+ struct mm_struct *mm = vma->vm_mm;
int error = 0;
pgoff_t pgoff;
unsigned long new_flags = vma->vm_flags;
@@ -69,10 +72,14 @@ static long madvise_behavior(struct vm_area_struct * vma,
new_flags &= ~VM_DONTCOPY;
break;
case MADV_DONTDUMP:
- new_flags |= VM_NODUMP;
+ new_flags |= VM_DONTDUMP;
break;
case MADV_DODUMP:
- new_flags &= ~VM_NODUMP;
+ if (new_flags & VM_SPECIAL) {
+ error = -EINVAL;
+ goto out;
+ }
+ new_flags &= ~VM_DONTDUMP;
break;
case MADV_MERGEABLE:
case MADV_UNMERGEABLE:
@@ -127,15 +134,105 @@ out:
return error;
}
+#ifdef CONFIG_SWAP
+static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
+ unsigned long end, struct mm_walk *walk)
+{
+ pte_t *orig_pte;
+ struct vm_area_struct *vma = walk->private;
+ unsigned long index;
+
+ if (pmd_none_or_trans_huge_or_clear_bad(pmd))
+ return 0;
+
+ for (index = start; index != end; index += PAGE_SIZE) {
+ pte_t pte;
+ swp_entry_t entry;
+ struct page *page;
+ spinlock_t *ptl;
+
+ orig_pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl);
+ pte = *(orig_pte + ((index - start) / PAGE_SIZE));
+ pte_unmap_unlock(orig_pte, ptl);
+
+ if (pte_present(pte) || pte_none(pte) || pte_file(pte))
+ continue;
+ entry = pte_to_swp_entry(pte);
+ if (unlikely(non_swap_entry(entry)))
+ continue;
+
+ page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
+ vma, index);
+ if (page)
+ page_cache_release(page);
+ }
+
+ return 0;
+}
+
+static void force_swapin_readahead(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ struct mm_walk walk = {
+ .mm = vma->vm_mm,
+ .pmd_entry = swapin_walk_pmd_entry,
+ .private = vma,
+ };
+
+ walk_page_range(start, end, &walk);
+
+ lru_add_drain(); /* Push any new pages onto the LRU now */
+}
+
+static void force_shm_swapin_readahead(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end,
+ struct address_space *mapping)
+{
+ pgoff_t index;
+ struct page *page;
+ swp_entry_t swap;
+
+ for (; start < end; start += PAGE_SIZE) {
+ index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+
+ page = find_get_entry(mapping, index);
+ if (!radix_tree_exceptional_entry(page)) {
+ if (page)
+ page_cache_release(page);
+ continue;
+ }
+ swap = radix_to_swp_entry(page);
+ page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
+ NULL, 0);
+ if (page)
+ page_cache_release(page);
+ }
+
+ lru_add_drain(); /* Push any new pages onto the LRU now */
+}
+#endif /* CONFIG_SWAP */
+
/*
* Schedule all required I/O operations. Do not wait for completion.
*/
-static long madvise_willneed(struct vm_area_struct * vma,
- struct vm_area_struct ** prev,
+static long madvise_willneed(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
unsigned long start, unsigned long end)
{
struct file *file = vma->vm_file;
+#ifdef CONFIG_SWAP
+ if (!file || mapping_cap_swap_backed(file->f_mapping)) {
+ *prev = vma;
+ if (!file)
+ force_swapin_readahead(vma, start, end);
+ else
+ force_shm_swapin_readahead(vma, start, end,
+ file->f_mapping);
+ return 0;
+ }
+#endif
+
if (!file)
return -EBADF;
@@ -173,8 +270,8 @@ static long madvise_willneed(struct vm_area_struct * vma,
* 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,
- struct vm_area_struct ** prev,
+static long madvise_dontneed(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
unsigned long start, unsigned long end)
{
*prev = vma;
@@ -246,29 +343,35 @@ static long madvise_remove(struct vm_area_struct *vma,
*/
static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end)
{
- int ret = 0;
-
+ struct page *p;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- for (; start < end; start += PAGE_SIZE) {
- struct page *p;
- int ret = get_user_pages_fast(start, 1, 0, &p);
+ for (; start < end; start += PAGE_SIZE <<
+ compound_order(compound_head(p))) {
+ int ret;
+
+ ret = get_user_pages_fast(start, 1, 0, &p);
if (ret != 1)
return ret;
+
+ if (PageHWPoison(p)) {
+ put_page(p);
+ continue;
+ }
if (bhv == MADV_SOFT_OFFLINE) {
- printk(KERN_INFO "Soft offlining page %lx at %lx\n",
+ pr_info("Soft offlining page %#lx at %#lx\n",
page_to_pfn(p), start);
ret = soft_offline_page(p, MF_COUNT_INCREASED);
if (ret)
- break;
+ return ret;
continue;
}
- printk(KERN_INFO "Injecting memory failure for page %lx at %lx\n",
+ pr_info("Injecting memory failure for page %#lx at %#lx\n",
page_to_pfn(p), start);
/* Ignore return value for now */
memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED);
}
- return ret;
+ return 0;
}
#endif
@@ -362,11 +465,12 @@ madvise_behavior_valid(int behavior)
SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
{
unsigned long end, tmp;
- struct vm_area_struct * vma, *prev;
+ struct vm_area_struct *vma, *prev;
int unmapped_error = 0;
int error = -EINVAL;
int write;
size_t len;
+ struct blk_plug plug;
#ifdef CONFIG_MEMORY_FAILURE
if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE)
@@ -375,27 +479,27 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
if (!madvise_behavior_valid(behavior))
return error;
- write = madvise_need_mmap_write(behavior);
- if (write)
- down_write(&current->mm->mmap_sem);
- else
- down_read(&current->mm->mmap_sem);
-
if (start & ~PAGE_MASK)
- goto out;
+ return error;
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;
+ return error;
end = start + len;
if (end < start)
- goto out;
+ return error;
error = 0;
if (end == start)
- goto out;
+ return error;
+
+ write = madvise_need_mmap_write(behavior);
+ if (write)
+ down_write(&current->mm->mmap_sem);
+ else
+ down_read(&current->mm->mmap_sem);
/*
* If the interval [start,end) covers some unmapped address
@@ -406,6 +510,7 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
if (vma && start > vma->vm_start)
prev = vma;
+ blk_start_plug(&plug);
for (;;) {
/* Still start < end. */
error = -ENOMEM;
@@ -441,6 +546,7 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
vma = find_vma(current->mm, start);
}
out:
+ blk_finish_plug(&plug);
if (write)
up_write(&current->mm->mmap_sem);
else