#include <linux/swapops.h>
#include <linux/slab.h>
#include <linux/init.h>
+#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/rcupdate.h>
#include <linux/module.h>
return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
}
-static inline void anon_vma_free(struct anon_vma *anon_vma)
+void anon_vma_free(struct anon_vma *anon_vma)
{
kmem_cache_free(anon_vma_cachep, anon_vma);
}
list_del(&vma->anon_vma_node);
/* We must garbage collect the anon_vma if it's empty */
- empty = list_empty(&anon_vma->head);
+ empty = list_empty(&anon_vma->head) && !ksm_refcount(anon_vma);
spin_unlock(&anon_vma->lock);
if (empty)
struct anon_vma *anon_vma = data;
spin_lock_init(&anon_vma->lock);
+ ksm_refcount_init(anon_vma);
INIT_LIST_HEAD(&anon_vma->head);
}
unsigned long anon_mapping;
rcu_read_lock();
- anon_mapping = (unsigned long) page->mapping;
- if (!(anon_mapping & PAGE_MAPPING_ANON))
+ anon_mapping = (unsigned long) ACCESS_ONCE(page->mapping);
+ if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
goto out;
if (!page_mapped(page))
goto out;
unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
{
if (PageAnon(page)) {
- if ((void *)vma->anon_vma !=
- (void *)page->mapping - PAGE_MAPPING_ANON)
+ if (vma->anon_vma != page_anon_vma(page))
return -EFAULT;
} else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
if (!vma->vm_file ||
* Subfunctions of page_referenced: page_referenced_one called
* 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,
- unsigned long *vm_flags)
+int page_referenced_one(struct page *page, struct vm_area_struct *vma,
+ unsigned long address, unsigned int *mapcount,
+ unsigned long *vm_flags)
{
struct mm_struct *mm = vma->vm_mm;
- unsigned long address;
pte_t *pte;
spinlock_t *ptl;
int referenced = 0;
- address = vma_address(page, vma);
- if (address == -EFAULT)
- goto out;
-
pte = page_check_address(page, mm, address, &ptl, 0);
if (!pte)
goto out;
out_unmap:
(*mapcount)--;
pte_unmap_unlock(pte, ptl);
-out:
+
if (referenced)
*vm_flags |= vma->vm_flags;
+out:
return referenced;
}
mapcount = page_mapcount(page);
list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
+ unsigned long address = vma_address(page, vma);
+ if (address == -EFAULT)
+ continue;
/*
* If we are reclaiming on behalf of a cgroup, skip
* counting on behalf of references from different
*/
if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
continue;
- referenced += page_referenced_one(page, vma,
+ referenced += page_referenced_one(page, vma, address,
&mapcount, vm_flags);
if (!mapcount)
break;
mapcount = page_mapcount(page);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
+ unsigned long address = vma_address(page, vma);
+ if (address == -EFAULT)
+ continue;
/*
* If we are reclaiming on behalf of a cgroup, skip
* counting on behalf of references from different
*/
if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
continue;
- referenced += page_referenced_one(page, vma,
+ referenced += page_referenced_one(page, vma, address,
&mapcount, vm_flags);
if (!mapcount)
break;
unsigned long *vm_flags)
{
int referenced = 0;
+ int we_locked = 0;
if (TestClearPageReferenced(page))
referenced++;
*vm_flags = 0;
- if (page_mapped(page) && page->mapping) {
- if (PageAnon(page))
+ if (page_mapped(page) && page_rmapping(page)) {
+ if (!is_locked && (!PageAnon(page) || PageKsm(page))) {
+ we_locked = trylock_page(page);
+ if (!we_locked) {
+ referenced++;
+ goto out;
+ }
+ }
+ if (unlikely(PageKsm(page)))
+ referenced += page_referenced_ksm(page, mem_cont,
+ vm_flags);
+ else if (PageAnon(page))
referenced += page_referenced_anon(page, mem_cont,
vm_flags);
- else if (is_locked)
+ else if (page->mapping)
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, vm_flags);
+ if (we_locked)
unlock_page(page);
- }
}
-
+out:
if (page_test_and_clear_young(page))
referenced++;
return referenced;
}
-static int page_mkclean_one(struct page *page, struct vm_area_struct *vma)
+static int page_mkclean_one(struct page *page, struct vm_area_struct *vma,
+ unsigned long address)
{
struct mm_struct *mm = vma->vm_mm;
- unsigned long address;
pte_t *pte;
spinlock_t *ptl;
int ret = 0;
- address = vma_address(page, vma);
- if (address == -EFAULT)
- goto out;
-
pte = page_check_address(page, mm, address, &ptl, 1);
if (!pte)
goto out;
spin_lock(&mapping->i_mmap_lock);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
- if (vma->vm_flags & VM_SHARED)
- ret += page_mkclean_one(page, vma);
+ if (vma->vm_flags & VM_SHARED) {
+ unsigned long address = vma_address(page, vma);
+ if (address == -EFAULT)
+ continue;
+ ret += page_mkclean_one(page, vma, address);
+ }
}
spin_unlock(&mapping->i_mmap_lock);
return ret;
BUG_ON(!anon_vma);
anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
page->mapping = (struct address_space *) anon_vma;
-
page->index = linear_page_index(vma, address);
-
- /*
- * nr_mapped state can be updated without turning off
- * interrupts because it is not modified via interrupt.
- */
- __inc_zone_page_state(page, NR_ANON_PAGES);
}
/**
* @vma: the vm area in which the mapping is added
* @address: the user virtual address mapped
*
- * The caller needs to hold the pte lock and the page must be locked.
+ * The caller needs to hold the pte lock, and the page must be locked in
+ * the anon_vma case: to serialize mapping,index checking after setting,
+ * and to ensure that PageAnon is not being upgraded racily to PageKsm
+ * (but PageKsm is never downgraded to PageAnon).
*/
void page_add_anon_rmap(struct page *page,
struct vm_area_struct *vma, unsigned long address)
{
+ int first = atomic_inc_and_test(&page->_mapcount);
+ if (first)
+ __inc_zone_page_state(page, NR_ANON_PAGES);
+ if (unlikely(PageKsm(page)))
+ return;
+
VM_BUG_ON(!PageLocked(page));
VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
- if (atomic_inc_and_test(&page->_mapcount))
+ if (first)
__page_set_anon_rmap(page, vma, address);
else
__page_check_anon_rmap(page, vma, address);
VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
SetPageSwapBacked(page);
atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
+ __inc_zone_page_state(page, NR_ANON_PAGES);
__page_set_anon_rmap(page, vma, address);
if (page_evictable(page, vma))
lru_cache_add_lru(page, LRU_ACTIVE_ANON);
{
if (atomic_inc_and_test(&page->_mapcount)) {
__inc_zone_page_state(page, NR_FILE_MAPPED);
- mem_cgroup_update_mapped_file_stat(page, 1);
+ mem_cgroup_update_file_mapped(page, 1);
}
}
__dec_zone_page_state(page, NR_ANON_PAGES);
} else {
__dec_zone_page_state(page, NR_FILE_MAPPED);
+ mem_cgroup_update_file_mapped(page, -1);
}
- 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
* Subfunctions of try_to_unmap: try_to_unmap_one called
* 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,
- enum ttu_flags flags)
+int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
+ unsigned long address, enum ttu_flags flags)
{
struct mm_struct *mm = vma->vm_mm;
- unsigned long address;
pte_t *pte;
pte_t pteval;
spinlock_t *ptl;
int ret = SWAP_AGAIN;
- address = vma_address(page, vma);
- if (address == -EFAULT)
- goto out;
-
pte = page_check_address(page, mm, address, &ptl, 0);
if (!pte)
goto out;
* skipped over this mm) then we should reactivate it.
*/
if (!(flags & TTU_IGNORE_MLOCK)) {
- if (vma->vm_flags & VM_LOCKED) {
- ret = SWAP_MLOCK;
+ if (vma->vm_flags & VM_LOCKED)
+ goto out_mlock;
+
+ if (TTU_ACTION(flags) == TTU_MUNLOCK)
goto out_unmap;
- }
}
if (!(flags & TTU_IGNORE_ACCESS)) {
if (ptep_clear_flush_young_notify(vma, address, pte)) {
} else
dec_mm_counter(mm, file_rss);
-
page_remove_rmap(page);
page_cache_release(page);
pte_unmap_unlock(pte, ptl);
out:
return ret;
+
+out_mlock:
+ pte_unmap_unlock(pte, ptl);
+
+
+ /*
+ * We need mmap_sem locking, Otherwise VM_LOCKED check makes
+ * unstable result and race. Plus, We can't wait here because
+ * we now hold anon_vma->lock or mapping->i_mmap_lock.
+ * if trylock failed, the page remain in evictable lru and later
+ * vmscan could retry to move the page to unevictable lru if the
+ * page is actually mlocked.
+ */
+ if (down_read_trylock(&vma->vm_mm->mmap_sem)) {
+ if (vma->vm_flags & VM_LOCKED) {
+ mlock_vma_page(page);
+ ret = SWAP_MLOCK;
+ }
+ up_read(&vma->vm_mm->mmap_sem);
+ }
+ return ret;
}
/*
return ret;
/*
- * MLOCK_PAGES => feature is configured.
- * if we can acquire the mmap_sem for read, and vma is VM_LOCKED,
+ * If we can acquire the mmap_sem for read, and vma is VM_LOCKED,
* keep the sem while scanning the cluster for mlocking pages.
*/
- if (MLOCK_PAGES && down_read_trylock(&vma->vm_mm->mmap_sem)) {
+ if (down_read_trylock(&vma->vm_mm->mmap_sem)) {
locked_vma = (vma->vm_flags & VM_LOCKED);
if (!locked_vma)
up_read(&vma->vm_mm->mmap_sem); /* don't need it */
return ret;
}
-/*
- * common handling for pages mapped in VM_LOCKED vmas
- */
-static int try_to_mlock_page(struct page *page, struct vm_area_struct *vma)
-{
- int mlocked = 0;
-
- if (down_read_trylock(&vma->vm_mm->mmap_sem)) {
- if (vma->vm_flags & VM_LOCKED) {
- mlock_vma_page(page);
- mlocked++; /* really mlocked the page */
- }
- up_read(&vma->vm_mm->mmap_sem);
- }
- return mlocked;
-}
-
/**
* try_to_unmap_anon - unmap or unlock anonymous page using the object-based
* rmap method
{
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() */
anon_vma = page_lock_anon_vma(page);
if (!anon_vma)
return ret;
list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
- if (MLOCK_PAGES && unlikely(unlock)) {
- if (!((vma->vm_flags & VM_LOCKED) &&
- page_mapped_in_vma(page, vma)))
- continue; /* must visit all unlocked vmas */
- ret = SWAP_MLOCK; /* saw at least one mlocked vma */
- } else {
- ret = try_to_unmap_one(page, vma, flags);
- if (ret == SWAP_FAIL || !page_mapped(page))
- break;
- }
- if (ret == SWAP_MLOCK) {
- mlocked = try_to_mlock_page(page, vma);
- if (mlocked)
- break; /* stop if actually mlocked page */
- }
+ unsigned long address = vma_address(page, vma);
+ if (address == -EFAULT)
+ continue;
+ ret = try_to_unmap_one(page, vma, address, flags);
+ if (ret != SWAP_AGAIN || !page_mapped(page))
+ break;
}
page_unlock_anon_vma(anon_vma);
-
- if (mlocked)
- ret = SWAP_MLOCK; /* actually mlocked the page */
- else if (ret == SWAP_MLOCK)
- ret = SWAP_AGAIN; /* saw VM_LOCKED vma */
-
return ret;
}
unsigned long max_nl_cursor = 0;
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) &&
- page_mapped_in_vma(page, vma)))
- continue; /* must visit all vmas */
- ret = SWAP_MLOCK;
- } else {
- ret = try_to_unmap_one(page, vma, flags);
- if (ret == SWAP_FAIL || !page_mapped(page))
- goto out;
- }
- if (ret == SWAP_MLOCK) {
- mlocked = try_to_mlock_page(page, vma);
- if (mlocked)
- goto out; /* stop if actually mlocked page */
- }
+ unsigned long address = vma_address(page, vma);
+ if (address == -EFAULT)
+ continue;
+ ret = try_to_unmap_one(page, vma, address, flags);
+ if (ret != SWAP_AGAIN || !page_mapped(page))
+ goto out;
}
if (list_empty(&mapping->i_mmap_nonlinear))
goto out;
+ /*
+ * We don't bother to try to find the munlocked page in nonlinears.
+ * It's costly. Instead, later, page reclaim logic may call
+ * try_to_unmap(TTU_MUNLOCK) and recover PG_mlocked lazily.
+ */
+ if (TTU_ACTION(flags) == TTU_MUNLOCK)
+ goto out;
+
list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
shared.vm_set.list) {
- if (MLOCK_PAGES && unlikely(unlock)) {
- if (!(vma->vm_flags & VM_LOCKED))
- continue; /* must visit all vmas */
- ret = SWAP_MLOCK; /* leave mlocked == 0 */
- goto out; /* no need to look further */
- }
- 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)
max_nl_cursor = cursor;
do {
list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
shared.vm_set.list) {
- if (!MLOCK_PAGES && !(flags & TTU_IGNORE_MLOCK) &&
- (vma->vm_flags & VM_LOCKED))
- continue;
cursor = (unsigned long) vma->vm_private_data;
while ( cursor < max_nl_cursor &&
cursor < vma->vm_end - vma->vm_start) {
- ret = try_to_unmap_cluster(cursor, &mapcount,
- vma, page);
- if (ret == SWAP_MLOCK)
- mlocked = 2; /* to return below */
+ if (try_to_unmap_cluster(cursor, &mapcount,
+ vma, page) == SWAP_MLOCK)
+ ret = SWAP_MLOCK;
cursor += CLUSTER_SIZE;
vma->vm_private_data = (void *) cursor;
if ((int)mapcount <= 0)
vma->vm_private_data = NULL;
out:
spin_unlock(&mapping->i_mmap_lock);
- if (mlocked)
- ret = SWAP_MLOCK; /* actually mlocked the page */
- else if (ret == SWAP_MLOCK)
- ret = SWAP_AGAIN; /* saw VM_LOCKED vma */
return ret;
}
BUG_ON(!PageLocked(page));
- if (PageAnon(page))
+ if (unlikely(PageKsm(page)))
+ ret = try_to_unmap_ksm(page, flags);
+ else if (PageAnon(page))
ret = try_to_unmap_anon(page, flags);
else
ret = try_to_unmap_file(page, flags);
*
* Return values are:
*
- * SWAP_SUCCESS - no vma's holding page mlocked.
+ * SWAP_AGAIN - no vma is holding page mlocked, or,
* SWAP_AGAIN - page mapped in mlocked vma -- couldn't acquire mmap sem
+ * SWAP_FAIL - page cannot be located at present
* SWAP_MLOCK - page is now mlocked.
*/
int try_to_munlock(struct page *page)
{
VM_BUG_ON(!PageLocked(page) || PageLRU(page));
- if (PageAnon(page))
+ if (unlikely(PageKsm(page)))
+ return try_to_unmap_ksm(page, TTU_MUNLOCK);
+ else if (PageAnon(page))
return try_to_unmap_anon(page, TTU_MUNLOCK);
else
return try_to_unmap_file(page, TTU_MUNLOCK);
}
+#ifdef CONFIG_MIGRATION
+/*
+ * rmap_walk() and its helpers rmap_walk_anon() and rmap_walk_file():
+ * Called by migrate.c to remove migration ptes, but might be used more later.
+ */
+static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *,
+ struct vm_area_struct *, unsigned long, void *), void *arg)
+{
+ struct anon_vma *anon_vma;
+ struct vm_area_struct *vma;
+ int ret = SWAP_AGAIN;
+
+ /*
+ * Note: remove_migration_ptes() cannot use page_lock_anon_vma()
+ * because that depends on page_mapped(); but not all its usages
+ * are holding mmap_sem, which also gave the necessary guarantee
+ * (that this anon_vma's slab has not already been destroyed).
+ * This needs to be reviewed later: avoiding page_lock_anon_vma()
+ * is risky, and currently limits the usefulness of rmap_walk().
+ */
+ anon_vma = page_anon_vma(page);
+ if (!anon_vma)
+ return ret;
+ spin_lock(&anon_vma->lock);
+ list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
+ unsigned long address = vma_address(page, vma);
+ if (address == -EFAULT)
+ continue;
+ ret = rmap_one(page, vma, address, arg);
+ if (ret != SWAP_AGAIN)
+ break;
+ }
+ spin_unlock(&anon_vma->lock);
+ return ret;
+}
+
+static int rmap_walk_file(struct page *page, int (*rmap_one)(struct page *,
+ struct vm_area_struct *, unsigned long, void *), void *arg)
+{
+ struct address_space *mapping = page->mapping;
+ pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+ struct vm_area_struct *vma;
+ struct prio_tree_iter iter;
+ int ret = SWAP_AGAIN;
+
+ if (!mapping)
+ return ret;
+ spin_lock(&mapping->i_mmap_lock);
+ vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
+ unsigned long address = vma_address(page, vma);
+ if (address == -EFAULT)
+ continue;
+ ret = rmap_one(page, vma, address, arg);
+ if (ret != SWAP_AGAIN)
+ break;
+ }
+ /*
+ * No nonlinear handling: being always shared, nonlinear vmas
+ * never contain migration ptes. Decide what to do about this
+ * limitation to linear when we need rmap_walk() on nonlinear.
+ */
+ spin_unlock(&mapping->i_mmap_lock);
+ return ret;
+}
+
+int rmap_walk(struct page *page, int (*rmap_one)(struct page *,
+ struct vm_area_struct *, unsigned long, void *), void *arg)
+{
+ VM_BUG_ON(!PageLocked(page));
+
+ if (unlikely(PageKsm(page)))
+ return rmap_walk_ksm(page, rmap_one, arg);
+ else if (PageAnon(page))
+ return rmap_walk_anon(page, rmap_one, arg);
+ else
+ return rmap_walk_file(page, rmap_one, arg);
+}
+#endif /* CONFIG_MIGRATION */
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff