* Original design by Rik van Riel <riel@conectiva.com.br> 2001
* File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004
* Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004
- * Contributions by Hugh Dickins <hugh@veritas.com> 2003, 2004
+ * Contributions by Hugh Dickins 2003, 2004
*/
/*
* mapping->tree_lock (widely used, in set_page_dirty,
* in arch-dependent flush_dcache_mmap_lock,
* within inode_lock in __sync_single_inode)
+ *
+ * (code doesn't rely on that order so it could be switched around)
+ * ->tasklist_lock
+ * anon_vma->lock (memory_failure, collect_procs_anon)
+ * pte map lock
*/
#include <linux/mm.h>
#include <linux/rmap.h>
#include <linux/rcupdate.h>
#include <linux/module.h>
-#include <linux/kallsyms.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
+#include <linux/migrate.h>
#include <asm/tlbflush.h>
#include "internal.h"
-struct kmem_cache *anon_vma_cachep;
+static struct kmem_cache *anon_vma_cachep;
+
+static inline struct anon_vma *anon_vma_alloc(void)
+{
+ return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
+}
+
+static inline void anon_vma_free(struct anon_vma *anon_vma)
+{
+ kmem_cache_free(anon_vma_cachep, anon_vma);
+}
/**
* anon_vma_prepare - attach an anon_vma to a memory region
* if the page is not mapped into the page tables of this VMA. Only
* valid for normal file or anonymous VMAs.
*/
-static int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
+int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
{
unsigned long address;
pte_t *pte;
* repeatedly from either page_referenced_anon or page_referenced_file.
*/
static int page_referenced_one(struct page *page,
- struct vm_area_struct *vma, unsigned int *mapcount)
+ struct vm_area_struct *vma,
+ unsigned int *mapcount,
+ unsigned long *vm_flags)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
*/
if (vma->vm_flags & VM_LOCKED) {
*mapcount = 1; /* break early from loop */
+ *vm_flags |= VM_LOCKED;
goto out_unmap;
}
- if (ptep_clear_flush_young_notify(vma, address, pte))
- referenced++;
+ if (ptep_clear_flush_young_notify(vma, address, pte)) {
+ /*
+ * Don't treat a reference through a sequentially read
+ * mapping as such. If the page has been used in
+ * another mapping, we will catch it; if this other
+ * mapping is already gone, the unmap path will have
+ * set PG_referenced or activated the page.
+ */
+ if (likely(!VM_SequentialReadHint(vma)))
+ referenced++;
+ }
/* Pretend the page is referenced if the task has the
swap token and is in the middle of a page fault. */
(*mapcount)--;
pte_unmap_unlock(pte, ptl);
out:
+ if (referenced)
+ *vm_flags |= vma->vm_flags;
return referenced;
}
static int page_referenced_anon(struct page *page,
- struct mem_cgroup *mem_cont)
+ struct mem_cgroup *mem_cont,
+ unsigned long *vm_flags)
{
unsigned int mapcount;
struct anon_vma *anon_vma;
*/
if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
continue;
- referenced += page_referenced_one(page, vma, &mapcount);
+ referenced += page_referenced_one(page, vma,
+ &mapcount, vm_flags);
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
+ * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
*
* 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,
- struct mem_cgroup *mem_cont)
+ struct mem_cgroup *mem_cont,
+ unsigned long *vm_flags)
{
unsigned int mapcount;
struct address_space *mapping = page->mapping;
*/
if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
continue;
- referenced += page_referenced_one(page, vma, &mapcount);
+ referenced += page_referenced_one(page, vma,
+ &mapcount, vm_flags);
if (!mapcount)
break;
}
* @page: the page to test
* @is_locked: caller holds lock on the page
* @mem_cont: target memory controller
+ * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
*
* 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,
- struct mem_cgroup *mem_cont)
+int page_referenced(struct page *page,
+ int is_locked,
+ struct mem_cgroup *mem_cont,
+ unsigned long *vm_flags)
{
int referenced = 0;
if (TestClearPageReferenced(page))
referenced++;
+ *vm_flags = 0;
if (page_mapped(page) && page->mapping) {
if (PageAnon(page))
- referenced += page_referenced_anon(page, mem_cont);
+ referenced += page_referenced_anon(page, mem_cont,
+ vm_flags);
else if (is_locked)
- referenced += page_referenced_file(page, mem_cont);
+ referenced += page_referenced_file(page, mem_cont,
+ vm_flags);
else if (!trylock_page(page))
referenced++;
else {
if (page->mapping)
- referenced +=
- page_referenced_file(page, mem_cont);
+ referenced += page_referenced_file(page,
+ mem_cont, vm_flags);
unlock_page(page);
}
}
void page_add_new_anon_rmap(struct page *page,
struct vm_area_struct *vma, unsigned long address)
{
- BUG_ON(address < vma->vm_start || address >= vma->vm_end);
- atomic_set(&page->_mapcount, 0); /* elevate count by 1 (starts at -1) */
+ VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+ SetPageSwapBacked(page);
+ atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
__page_set_anon_rmap(page, vma, address);
+ if (page_evictable(page, vma))
+ lru_cache_add_lru(page, LRU_ACTIVE_ANON);
+ else
+ add_page_to_unevictable_list(page);
}
/**
*/
void page_add_file_rmap(struct page *page)
{
- if (atomic_inc_and_test(&page->_mapcount))
+ if (atomic_inc_and_test(&page->_mapcount)) {
__inc_zone_page_state(page, NR_FILE_MAPPED);
+ mem_cgroup_update_mapped_file_stat(page, 1);
+ }
}
#ifdef CONFIG_DEBUG_VM
*/
void page_dup_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address)
{
- BUG_ON(page_mapcount(page) == 0);
if (PageAnon(page))
__page_check_anon_rmap(page, vma, address);
atomic_inc(&page->_mapcount);
/**
* 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.
*/
-void page_remove_rmap(struct page *page, struct vm_area_struct *vma)
+void page_remove_rmap(struct page *page)
{
if (atomic_add_negative(-1, &page->_mapcount)) {
- if (unlikely(page_mapcount(page) < 0)) {
- printk (KERN_EMERG "Eeek! page_mapcount(page) went negative! (%d)\n", page_mapcount(page));
- printk (KERN_EMERG " page pfn = %lx\n", page_to_pfn(page));
- printk (KERN_EMERG " page->flags = %lx\n", page->flags);
- 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) {
- 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();
- }
-
/*
* Now that the last pte has gone, s390 must transfer dirty
* flag from storage key to struct page. We can usually skip
page_clear_dirty(page);
set_page_dirty(page);
}
-
- mem_cgroup_uncharge_page(page);
+ if (PageAnon(page))
+ mem_cgroup_uncharge_page(page);
__dec_zone_page_state(page,
PageAnon(page) ? NR_ANON_PAGES : NR_FILE_MAPPED);
+ mem_cgroup_update_mapped_file_stat(page, -1);
/*
* It would be tidy to reset the PageAnon mapping here,
* but that might overwrite a racing page_add_anon_rmap
* repeatedly from either try_to_unmap_anon or try_to_unmap_file.
*/
static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
- int migration)
+ enum ttu_flags flags)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
* If it's recently referenced (perhaps page_referenced
* skipped over this mm) then we should reactivate it.
*/
- if (!migration) {
+ if (!(flags & TTU_IGNORE_MLOCK)) {
if (vma->vm_flags & VM_LOCKED) {
ret = SWAP_MLOCK;
goto out_unmap;
}
+ }
+ if (!(flags & TTU_IGNORE_ACCESS)) {
if (ptep_clear_flush_young_notify(vma, address, pte)) {
ret = SWAP_FAIL;
goto out_unmap;
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
- if (PageAnon(page)) {
+ if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
+ if (PageAnon(page))
+ dec_mm_counter(mm, anon_rss);
+ else
+ dec_mm_counter(mm, file_rss);
+ set_pte_at(mm, address, pte,
+ swp_entry_to_pte(make_hwpoison_entry(page)));
+ } else if (PageAnon(page)) {
swp_entry_t entry = { .val = page_private(page) };
if (PageSwapCache(page)) {
spin_unlock(&mmlist_lock);
}
dec_mm_counter(mm, anon_rss);
-#ifdef CONFIG_MIGRATION
- } else {
+ } else if (PAGE_MIGRATION) {
/*
* Store the pfn of the page in a special migration
* pte. do_swap_page() will wait until the migration
* pte is removed and then restart fault handling.
*/
- BUG_ON(!migration);
+ BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION);
entry = make_migration_entry(page, pte_write(pteval));
-#endif
}
set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
BUG_ON(pte_file(*pte));
- } else
-#ifdef CONFIG_MIGRATION
- if (migration) {
+ } else if (PAGE_MIGRATION && (TTU_ACTION(flags) == TTU_MIGRATION)) {
/* Establish migration entry for a file page */
swp_entry_t entry;
entry = make_migration_entry(page, pte_write(pteval));
set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
} else
-#endif
dec_mm_counter(mm, file_rss);
- page_remove_rmap(page, vma);
+ page_remove_rmap(page);
page_cache_release(page);
out_unmap:
if (pte_dirty(pteval))
set_page_dirty(page);
- page_remove_rmap(page, vma);
+ page_remove_rmap(page);
page_cache_release(page);
dec_mm_counter(mm, file_rss);
(*mapcount)--;
* vm_flags for that VMA. That should be OK, because that vma shouldn't be
* 'LOCKED.
*/
-static int try_to_unmap_anon(struct page *page, int unlock, int migration)
+static int try_to_unmap_anon(struct page *page, enum ttu_flags flags)
{
struct anon_vma *anon_vma;
struct vm_area_struct *vma;
unsigned int mlocked = 0;
int ret = SWAP_AGAIN;
+ int unlock = TTU_ACTION(flags) == TTU_MUNLOCK;
if (MLOCK_PAGES && unlikely(unlock))
ret = SWAP_SUCCESS; /* default for try_to_munlock() */
continue; /* must visit all unlocked vmas */
ret = SWAP_MLOCK; /* saw at least one mlocked vma */
} else {
- ret = try_to_unmap_one(page, vma, migration);
+ ret = try_to_unmap_one(page, vma, flags);
if (ret == SWAP_FAIL || !page_mapped(page))
break;
}
/**
* try_to_unmap_file - unmap/unlock file page using the object-based rmap method
* @page: the page to unmap/unlock
- * @unlock: request for unlock rather than unmap [unlikely]
- * @migration: unmapping for migration - ignored if @unlock
+ * @flags: action and flags
*
* Find all the mappings of a page using the mapping pointer and the vma chains
* contained in the address_space struct it points to.
* vm_flags for that VMA. That should be OK, because that vma shouldn't be
* 'LOCKED.
*/
-static int try_to_unmap_file(struct page *page, int unlock, int migration)
+static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
{
struct address_space *mapping = page->mapping;
pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
unsigned long max_nl_size = 0;
unsigned int mapcount;
unsigned int mlocked = 0;
+ int unlock = TTU_ACTION(flags) == TTU_MUNLOCK;
if (MLOCK_PAGES && unlikely(unlock))
ret = SWAP_SUCCESS; /* default for try_to_munlock() */
spin_lock(&mapping->i_mmap_lock);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
if (MLOCK_PAGES && unlikely(unlock)) {
- if (!(vma->vm_flags & VM_LOCKED))
+ if (!((vma->vm_flags & VM_LOCKED) &&
+ page_mapped_in_vma(page, vma)))
continue; /* must visit all vmas */
ret = SWAP_MLOCK;
} else {
- ret = try_to_unmap_one(page, vma, migration);
+ ret = try_to_unmap_one(page, vma, flags);
if (ret == SWAP_FAIL || !page_mapped(page))
goto out;
}
ret = SWAP_MLOCK; /* leave mlocked == 0 */
goto out; /* no need to look further */
}
- if (!MLOCK_PAGES && !migration && (vma->vm_flags & VM_LOCKED))
+ if (!MLOCK_PAGES && !(flags & TTU_IGNORE_MLOCK) &&
+ (vma->vm_flags & VM_LOCKED))
continue;
cursor = (unsigned long) vma->vm_private_data;
if (cursor > max_nl_cursor)
do {
list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
shared.vm_set.list) {
- if (!MLOCK_PAGES && !migration &&
+ if (!MLOCK_PAGES && !(flags & TTU_IGNORE_MLOCK) &&
(vma->vm_flags & VM_LOCKED))
continue;
cursor = (unsigned long) vma->vm_private_data;
/**
* try_to_unmap - try to remove all page table mappings to a page
* @page: the page to get unmapped
- * @migration: migration flag
+ * @flags: action and flags
*
* Tries to remove all the page table entries which are mapping this
* page, used in the pageout path. Caller must hold the page lock.
* SWAP_FAIL - the page is unswappable
* SWAP_MLOCK - page is mlocked.
*/
-int try_to_unmap(struct page *page, int migration)
+int try_to_unmap(struct page *page, enum ttu_flags flags)
{
int ret;
BUG_ON(!PageLocked(page));
if (PageAnon(page))
- ret = try_to_unmap_anon(page, 0, migration);
+ ret = try_to_unmap_anon(page, flags);
else
- ret = try_to_unmap_file(page, 0, migration);
+ ret = try_to_unmap_file(page, flags);
if (ret != SWAP_MLOCK && !page_mapped(page))
ret = SWAP_SUCCESS;
return ret;
}
-#ifdef CONFIG_UNEVICTABLE_LRU
/**
* try_to_munlock - try to munlock a page
* @page: the page to be munlocked
VM_BUG_ON(!PageLocked(page) || PageLRU(page));
if (PageAnon(page))
- return try_to_unmap_anon(page, 1, 0);
+ return try_to_unmap_anon(page, TTU_MUNLOCK);
else
- return try_to_unmap_file(page, 1, 0);
+ return try_to_unmap_file(page, TTU_MUNLOCK);
}
-#endif
+
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff