#include <linux/rcupdate.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
+#include <linux/memcontrol.h>
+#include <linux/mmu_notifier.h>
#include <asm/tlbflush.h>
anon_vma_free(anon_vma);
}
-static void anon_vma_ctor(struct kmem_cache *cachep, void *data)
+static void anon_vma_ctor(void *data)
{
struct anon_vma *anon_vma = data;
}
/*
- * 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;
/*
* Check that @page is mapped at @address into @mm.
*
+ * If @sync is false, page_check_address may perform a racy check to avoid
+ * the page table lock when the pte is not present (helpful when reclaiming
+ * highly shared pages).
+ *
* On success returns with pte mapped and locked.
*/
pte_t *page_check_address(struct page *page, struct mm_struct *mm,
- unsigned long address, spinlock_t **ptlp)
+ unsigned long address, spinlock_t **ptlp, int sync)
{
pgd_t *pgd;
pud_t *pud;
pte = pte_offset_map(pmd, address);
/* Make a quick check before getting the lock */
- if (!pte_present(*pte)) {
+ if (!sync && !pte_present(*pte)) {
pte_unmap(pte);
return NULL;
}
if (address == -EFAULT)
goto out;
- pte = page_check_address(page, mm, address, &ptl);
+ pte = page_check_address(page, mm, address, &ptl, 0);
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_notify(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 && !mm_match_cgroup(vma->vm_mm, mem_cont))
+ continue;
referenced += page_referenced_one(page, vma, &mapcount);
if (!mapcount)
break;
/**
* page_referenced_file - referenced check for object-based rmap
* @page: the page we're checking references on.
+ * @mem_cont: target memory controller
*
* For an object-based mapped page, find all the places it is mapped and
* check/clear the referenced flag. This is done by following the page->mapping
*
* 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 && !mm_match_cgroup(vma->vm_mm, mem_cont))
+ continue;
if ((vma->vm_flags & (VM_LOCKED|VM_MAYSHARE))
== (VM_LOCKED|VM_MAYSHARE)) {
referenced++;
* page_referenced - test if the page was referenced
* @page: the page to test
* @is_locked: caller holds lock on the page
+ * @mem_cont: target memory controller
*
* 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_test_and_clear_young(page))
- referenced++;
-
if (TestClearPageReferenced(page))
referenced++;
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);
- else if (TestSetPageLocked(page))
+ referenced += page_referenced_file(page, mem_cont);
+ else if (!trylock_page(page))
referenced++;
else {
if (page->mapping)
- referenced += page_referenced_file(page);
+ referenced +=
+ page_referenced_file(page, mem_cont);
unlock_page(page);
}
}
+
+ if (page_test_and_clear_young(page))
+ referenced++;
+
return referenced;
}
if (address == -EFAULT)
goto out;
- pte = page_check_address(page, mm, address, &ptl);
+ pte = page_check_address(page, mm, address, &ptl, 1);
if (!pte)
goto out;
pte_t entry;
flush_cache_page(vma, address, pte_pfn(*pte));
- entry = ptep_clear_flush(vma, address, pte);
+ entry = ptep_clear_flush_notify(vma, address, pte);
entry = pte_wrprotect(entry);
entry = pte_mkclean(entry);
set_pte_at(mm, address, pte, entry);
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;
+ }
}
}
EXPORT_SYMBOL_GPL(page_mkclean);
/**
- * page_set_anon_rmap - setup new anonymous rmap
+ * __page_set_anon_rmap - setup new anonymous rmap
* @page: the page to add the mapping to
* @vma: the vm area in which the mapping is added
* @address: the user virtual address mapped
}
/**
- * page_set_anon_rmap - sanity check anonymous rmap addition
+ * __page_check_anon_rmap - sanity check anonymous rmap addition
* @page: the page to add the mapping to
* @vma: the vm area in which the mapping is added
* @address: the user virtual address mapped
__page_check_anon_rmap(page, vma, address);
}
-/*
+/**
* page_add_new_anon_rmap - add pte mapping to a new anonymous page
* @page: the page to add the mapping to
* @vma: the vm area in which the mapping is added
/**
* page_dup_rmap - duplicate pte mapping to a page
* @page: the page to add the mapping to
+ * @vma: the vm area being duplicated
+ * @address: the user virtual address mapped
*
* For copy_page_range only: minimal extract from page_add_file_rmap /
* page_add_anon_rmap, avoiding unnecessary tests (already checked) so it's
/**
* page_remove_rmap - take down pte mapping from a page
* @page: page to remove mapping from
+ * @vma: the vm area in which the mapping is removed
*
* The caller needs to hold the pte lock.
*/
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) {
- 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)
}
/*
+ * Now that the last pte has gone, s390 must transfer dirty
+ * flag from storage key to struct page. We can usually skip
+ * this if the page is anon, so about to be freed; but perhaps
+ * not if it's in swapcache - there might be another pte slot
+ * containing the swap entry, but page not yet written to swap.
+ */
+ if ((!PageAnon(page) || PageSwapCache(page)) &&
+ page_test_dirty(page)) {
+ 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);
+ /*
* It would be tidy to reset the PageAnon mapping here,
* but that might overwrite a racing page_add_anon_rmap
* which increments mapcount after us but sets mapping
* Leaving it set also helps swapoff to reinstate ptes
* faster for those pages still in swapcache.
*/
- if (page_test_dirty(page)) {
- page_clear_dirty(page);
- set_page_dirty(page);
- }
- __dec_zone_page_state(page,
- PageAnon(page) ? NR_ANON_PAGES : NR_FILE_MAPPED);
}
}
if (address == -EFAULT)
goto out;
- pte = page_check_address(page, mm, address, &ptl);
+ pte = page_check_address(page, mm, address, &ptl, 0);
if (!pte)
goto out;
* skipped over this mm) then we should reactivate it.
*/
if (!migration && ((vma->vm_flags & VM_LOCKED) ||
- (ptep_clear_flush_young(vma, address, pte)))) {
+ (ptep_clear_flush_young_notify(vma, address, pte)))) {
ret = SWAP_FAIL;
goto out_unmap;
}
/* Nuke the page table entry. */
flush_cache_page(vma, address, page_to_pfn(page));
- pteval = ptep_clear_flush(vma, address, pte);
+ pteval = ptep_clear_flush_notify(vma, address, pte);
/* Move the dirty bit to the physical page now the pte is gone. */
if (pte_dirty(pteval))
page = vm_normal_page(vma, address, *pte);
BUG_ON(!page || PageAnon(page));
- if (ptep_clear_flush_young(vma, address, pte))
+ if (ptep_clear_flush_young_notify(vma, address, pte))
continue;
/* Nuke the page table entry. */
flush_cache_page(vma, address, pte_pfn(*pte));
- pteval = ptep_clear_flush(vma, address, pte);
+ pteval = ptep_clear_flush_notify(vma, address, pte);
/* If nonlinear, store the file page offset in the pte. */
if (page->index != linear_page_index(vma, address))
/**
* try_to_unmap_file - unmap file page using the object-based rmap method
* @page: the page to unmap
+ * @migration: migration flag
*
* Find all the mappings of a page using the mapping pointer and the vma chains
* contained in the address_space struct it points to.
/**
* try_to_unmap - try to remove all page table mappings to a page
* @page: the page to get unmapped
+ * @migration: migration flag
*
* Tries to remove all the page table entries which are mapping this
* page, used in the pageout path. Caller must hold the page lock.
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff