#include <linux/rcupdate.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
+#include <linux/memcontrol.h>
#include <asm/tlbflush.h>
anon_vma_free(anon_vma);
}
-static void anon_vma_ctor(void *data, struct kmem_cache *cachep,
- unsigned long flags)
+static void anon_vma_ctor(struct kmem_cache *cachep, void *data)
{
struct anon_vma *anon_vma = data;
void __init anon_vma_init(void)
{
anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma),
- 0, SLAB_DESTROY_BY_RCU|SLAB_PANIC, anon_vma_ctor, NULL);
+ 0, SLAB_DESTROY_BY_RCU|SLAB_PANIC, anon_vma_ctor);
}
/*
}
/*
- * At what user virtual address is page expected in vma?
+ * At what user virtual address is page expected in @vma?
+ * Returns virtual address or -EFAULT if page's index/offset is not
+ * within the range mapped the @vma.
*/
static inline unsigned long
vma_address(struct page *page, struct vm_area_struct *vma)
address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
if (unlikely(address < vma->vm_start || address >= vma->vm_end)) {
- /* page should be within any vma from prio_tree_next */
- BUG_ON(!PageAnon(page));
+ /* page should be within @vma mapping range */
return -EFAULT;
}
return address;
if (!pte)
goto out;
- if (ptep_clear_flush_young(vma, address, pte))
+ if (vma->vm_flags & VM_LOCKED) {
+ referenced++;
+ *mapcount = 1; /* break early from loop */
+ } else if (ptep_clear_flush_young(vma, address, pte))
referenced++;
/* Pretend the page is referenced if the task has the
return referenced;
}
-static int page_referenced_anon(struct page *page)
+static int page_referenced_anon(struct page *page,
+ struct mem_cgroup *mem_cont)
{
unsigned int mapcount;
struct anon_vma *anon_vma;
mapcount = page_mapcount(page);
list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
+ /*
+ * If we are reclaiming on behalf of a cgroup, skip
+ * counting on behalf of references from different
+ * cgroups
+ */
+ if (mem_cont && !vm_match_cgroup(vma->vm_mm, mem_cont))
+ continue;
referenced += page_referenced_one(page, vma, &mapcount);
if (!mapcount)
break;
*
* This function is only called from page_referenced for object-based pages.
*/
-static int page_referenced_file(struct page *page)
+static int page_referenced_file(struct page *page,
+ struct mem_cgroup *mem_cont)
{
unsigned int mapcount;
struct address_space *mapping = page->mapping;
mapcount = page_mapcount(page);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
+ /*
+ * If we are reclaiming on behalf of a cgroup, skip
+ * counting on behalf of references from different
+ * cgroups
+ */
+ if (mem_cont && !vm_match_cgroup(vma->vm_mm, mem_cont))
+ continue;
if ((vma->vm_flags & (VM_LOCKED|VM_MAYSHARE))
== (VM_LOCKED|VM_MAYSHARE)) {
referenced++;
* Quick test_and_clear_referenced for all mappings to a page,
* returns the number of ptes which referenced the page.
*/
-int page_referenced(struct page *page, int is_locked)
+int page_referenced(struct page *page, int is_locked,
+ struct mem_cgroup *mem_cont)
{
int referenced = 0;
if (page_mapped(page) && page->mapping) {
if (PageAnon(page))
- referenced += page_referenced_anon(page);
+ referenced += page_referenced_anon(page, mem_cont);
else if (is_locked)
- referenced += page_referenced_file(page);
+ referenced += page_referenced_file(page, mem_cont);
else if (TestSetPageLocked(page))
referenced++;
else {
if (page->mapping)
- referenced += page_referenced_file(page);
+ referenced +=
+ page_referenced_file(page, mem_cont);
unlock_page(page);
}
}
entry = pte_wrprotect(entry);
entry = pte_mkclean(entry);
set_pte_at(mm, address, pte, entry);
- lazy_mmu_prot_update(entry);
ret = 1;
}
if (page_mapped(page)) {
struct address_space *mapping = page_mapping(page);
- if (mapping)
+ if (mapping) {
ret = page_mkclean_file(mapping, page);
- if (page_test_dirty(page)) {
- page_clear_dirty(page);
- ret = 1;
+ if (page_test_dirty(page)) {
+ page_clear_dirty(page);
+ ret = 1;
+ }
}
}
VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
if (atomic_inc_and_test(&page->_mapcount))
__page_set_anon_rmap(page, vma, address);
- else
+ else {
__page_check_anon_rmap(page, vma, address);
+ /*
+ * We unconditionally charged during prepare, we uncharge here
+ * This takes care of balancing the reference counts
+ */
+ mem_cgroup_uncharge_page(page);
+ }
}
/*
{
if (atomic_inc_and_test(&page->_mapcount))
__inc_zone_page_state(page, NR_FILE_MAPPED);
+ else
+ /*
+ * We unconditionally charged during prepare, we uncharge here
+ * This takes care of balancing the reference counts
+ */
+ mem_cgroup_uncharge_page(page);
}
#ifdef CONFIG_DEBUG_VM
printk (KERN_EMERG " page->count = %x\n", page_count(page));
printk (KERN_EMERG " page->mapping = %p\n", page->mapping);
print_symbol (KERN_EMERG " vma->vm_ops = %s\n", (unsigned long)vma->vm_ops);
- if (vma->vm_ops)
+ if (vma->vm_ops) {
print_symbol (KERN_EMERG " vma->vm_ops->nopage = %s\n", (unsigned long)vma->vm_ops->nopage);
+ print_symbol (KERN_EMERG " vma->vm_ops->fault = %s\n", (unsigned long)vma->vm_ops->fault);
+ }
if (vma->vm_file && vma->vm_file->f_op)
print_symbol (KERN_EMERG " vma->vm_file->f_op->mmap = %s\n", (unsigned long)vma->vm_file->f_op->mmap);
BUG();
page_clear_dirty(page);
set_page_dirty(page);
}
+ mem_cgroup_uncharge_page(page);
+
__dec_zone_page_state(page,
PageAnon(page) ? NR_ANON_PAGES : NR_FILE_MAPPED);
}