#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>
-struct kmem_cache *anon_vma_cachep;
+#include "internal.h"
-static inline void validate_anon_vma(struct vm_area_struct *find_vma)
+static struct kmem_cache *anon_vma_cachep;
+
+static inline struct anon_vma *anon_vma_alloc(void)
{
-#ifdef CONFIG_DEBUG_VM
- struct anon_vma *anon_vma = find_vma->anon_vma;
- struct vm_area_struct *vma;
- unsigned int mapcount = 0;
- int found = 0;
+ return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
+}
- list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
- mapcount++;
- BUG_ON(mapcount > 100000);
- if (vma == find_vma)
- found = 1;
- }
- BUG_ON(!found);
-#endif
+static inline void anon_vma_free(struct anon_vma *anon_vma)
+{
+ kmem_cache_free(anon_vma_cachep, anon_vma);
}
-/* This must be called under the mmap_sem. */
+/**
+ * anon_vma_prepare - attach an anon_vma to a memory region
+ * @vma: the memory region in question
+ *
+ * This makes sure the memory mapping described by 'vma' has
+ * an 'anon_vma' attached to it, so that we can associate the
+ * anonymous pages mapped into it with that anon_vma.
+ *
+ * The common case will be that we already have one, but if
+ * if not we either need to find an adjacent mapping that we
+ * can re-use the anon_vma from (very common when the only
+ * reason for splitting a vma has been mprotect()), or we
+ * allocate a new one.
+ *
+ * Anon-vma allocations are very subtle, because we may have
+ * optimistically looked up an anon_vma in page_lock_anon_vma()
+ * and that may actually touch the spinlock even in the newly
+ * allocated vma (it depends on RCU to make sure that the
+ * anon_vma isn't actually destroyed).
+ *
+ * As a result, we need to do proper anon_vma locking even
+ * for the new allocation. At the same time, we do not want
+ * to do any locking for the common case of already having
+ * an anon_vma.
+ *
+ * This must be called with the mmap_sem held for reading.
+ */
int anon_vma_prepare(struct vm_area_struct *vma)
{
struct anon_vma *anon_vma = vma->anon_vma;
might_sleep();
if (unlikely(!anon_vma)) {
struct mm_struct *mm = vma->vm_mm;
- struct anon_vma *allocated, *locked;
+ struct anon_vma *allocated;
anon_vma = find_mergeable_anon_vma(vma);
- if (anon_vma) {
- allocated = NULL;
- locked = anon_vma;
- spin_lock(&locked->lock);
- } else {
+ allocated = NULL;
+ if (!anon_vma) {
anon_vma = anon_vma_alloc();
if (unlikely(!anon_vma))
return -ENOMEM;
allocated = anon_vma;
- locked = NULL;
}
+ spin_lock(&anon_vma->lock);
/* page_table_lock to protect against threads */
spin_lock(&mm->page_table_lock);
}
spin_unlock(&mm->page_table_lock);
- if (locked)
- spin_unlock(&locked->lock);
+ spin_unlock(&anon_vma->lock);
if (unlikely(allocated))
anon_vma_free(allocated);
}
{
struct anon_vma *anon_vma = vma->anon_vma;
- if (anon_vma) {
+ if (anon_vma)
list_add_tail(&vma->anon_vma_node, &anon_vma->head);
- validate_anon_vma(vma);
- }
}
void anon_vma_link(struct vm_area_struct *vma)
if (anon_vma) {
spin_lock(&anon_vma->lock);
list_add_tail(&vma->anon_vma_node, &anon_vma->head);
- validate_anon_vma(vma);
spin_unlock(&anon_vma->lock);
}
}
return;
spin_lock(&anon_vma->lock);
- validate_anon_vma(vma);
list_del(&vma->anon_vma_node);
/* We must garbage collect the anon_vma if it's empty */
anon_vma_free(anon_vma);
}
-static void anon_vma_ctor(void *data, struct kmem_cache *cachep,
- unsigned long flags)
+static void anon_vma_ctor(void *data)
{
- if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
- SLAB_CTOR_CONSTRUCTOR) {
- struct anon_vma *anon_vma = data;
+ struct anon_vma *anon_vma = data;
- spin_lock_init(&anon_vma->lock);
- INIT_LIST_HEAD(&anon_vma->head);
- }
+ spin_lock_init(&anon_vma->lock);
+ INIT_LIST_HEAD(&anon_vma->head);
}
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);
}
/*
*/
static struct anon_vma *page_lock_anon_vma(struct page *page)
{
- struct anon_vma *anon_vma = NULL;
+ struct anon_vma *anon_vma;
unsigned long anon_mapping;
rcu_read_lock();
anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
spin_lock(&anon_vma->lock);
+ return anon_vma;
out:
rcu_read_unlock();
- return anon_vma;
+ return NULL;
+}
+
+static void page_unlock_anon_vma(struct anon_vma *anon_vma)
+{
+ spin_unlock(&anon_vma->lock);
+ rcu_read_unlock();
}
/*
- * 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;
}
return NULL;
}
+/**
+ * page_mapped_in_vma - check whether a page is really mapped in a VMA
+ * @page: the page to test
+ * @vma: the VMA to test
+ *
+ * Returns 1 if the page is mapped into the page tables of the VMA, 0
+ * 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)
+{
+ unsigned long address;
+ pte_t *pte;
+ spinlock_t *ptl;
+
+ address = vma_address(page, vma);
+ if (address == -EFAULT) /* out of vma range */
+ return 0;
+ pte = page_check_address(page, vma->vm_mm, address, &ptl, 1);
+ if (!pte) /* the page is not in this mm */
+ return 0;
+ pte_unmap_unlock(pte, ptl);
+
+ return 1;
+}
+
/*
* Subfunctions of page_referenced: page_referenced_one called
* repeatedly from either page_referenced_anon or page_referenced_file.
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))
- referenced++;
+ /*
+ * Don't want to elevate referenced for mlocked page that gets this far,
+ * in order that it progresses to try_to_unmap and is moved to the
+ * unevictable list.
+ */
+ if (vma->vm_flags & VM_LOCKED) {
+ *mapcount = 1; /* break early from loop */
+ goto out_unmap;
+ }
+
+ 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. */
rwsem_is_locked(&mm->mmap_sem))
referenced++;
+out_unmap:
(*mapcount)--;
pte_unmap_unlock(pte, ptl);
out:
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;
}
- spin_unlock(&anon_vma->lock);
+
+ page_unlock_anon_vma(anon_vma);
return referenced;
}
/**
* 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 ((vma->vm_flags & (VM_LOCKED|VM_MAYSHARE))
- == (VM_LOCKED|VM_MAYSHARE)) {
- referenced++;
- break;
- }
+ /*
+ * 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 - 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;
}
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
- pte_t *pte, entry;
+ pte_t *pte;
spinlock_t *ptl;
int ret = 0;
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;
- if (!pte_dirty(*pte) && !pte_write(*pte))
- goto unlock;
+ if (pte_dirty(*pte) || pte_write(*pte)) {
+ pte_t entry;
- entry = ptep_get_and_clear(mm, address, pte);
- entry = pte_mkclean(entry);
- entry = pte_wrprotect(entry);
- ptep_establish(vma, address, pte, entry);
- lazy_mmu_prot_update(entry);
- ret = 1;
+ flush_cache_page(vma, address, pte_pfn(*pte));
+ entry = ptep_clear_flush_notify(vma, address, pte);
+ entry = pte_wrprotect(entry);
+ entry = pte_mkclean(entry);
+ set_pte_at(mm, address, pte, entry);
+ ret = 1;
+ }
-unlock:
pte_unmap_unlock(pte, ptl);
out:
return ret;
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;
+ }
+ }
}
return ret;
}
+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_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
+ */
+static void __page_check_anon_rmap(struct page *page,
+ struct vm_area_struct *vma, unsigned long address)
+{
+#ifdef CONFIG_DEBUG_VM
+ /*
+ * The page's anon-rmap details (mapping and index) are guaranteed to
+ * be set up correctly at this point.
+ *
+ * We have exclusion against page_add_anon_rmap because the caller
+ * always holds the page locked, except if called from page_dup_rmap,
+ * in which case the page is already known to be setup.
+ *
+ * We have exclusion against page_add_new_anon_rmap because those pages
+ * are initially only visible via the pagetables, and the pte is locked
+ * over the call to page_add_new_anon_rmap.
+ */
+ struct anon_vma *anon_vma = vma->anon_vma;
+ anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
+ BUG_ON(page->mapping != (struct address_space *)anon_vma);
+ BUG_ON(page->index != linear_page_index(vma, address));
+#endif
+}
+
+/**
* page_add_anon_rmap - add pte mapping to an anonymous page
* @page: the page to add the mapping to
* @vma: the vm area in which the mapping is added
* @address: the user virtual address mapped
*
- * The caller needs to hold the pte lock.
+ * The caller needs to hold the pte lock and the page must be locked.
*/
void page_add_anon_rmap(struct page *page,
struct vm_area_struct *vma, unsigned long address)
{
+ VM_BUG_ON(!PageLocked(page));
+ 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 checking page index and mapping is racy */
+ else
+ __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
*
* Same as page_add_anon_rmap but must only be called on *new* pages.
* This means the inc-and-test can be bypassed.
+ * Page does not have to be locked.
*/
void page_add_new_anon_rmap(struct page *page,
struct vm_area_struct *vma, unsigned long address)
{
- 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);
}
/**
__inc_zone_page_state(page, NR_FILE_MAPPED);
}
+#ifdef CONFIG_DEBUG_VM
+/**
+ * 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
+ * quicker.
+ *
+ * The caller needs to hold the pte lock.
+ */
+void page_dup_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address)
+{
+ if (PageAnon(page))
+ __page_check_anon_rmap(page, vma, address);
+ atomic_inc(&page->_mapcount);
+}
+#endif
+
/**
* page_remove_rmap - take down pte mapping from a page
* @page: page to remove mapping from
*
* 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->nopage = %s\n", (unsigned long)vma->vm_ops->nopage);
- 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
+ * 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);
}
-
+ if (PageAnon(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
* Leaving it set also helps swapoff to reinstate ptes
* faster for those pages still in swapcache.
*/
- if (page_test_and_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;
* If it's recently referenced (perhaps page_referenced
* skipped over this mm) then we should reactivate it.
*/
- if (!migration && ((vma->vm_flags & VM_LOCKED) ||
- (ptep_clear_flush_young(vma, address, pte)))) {
- ret = SWAP_FAIL;
- goto out_unmap;
- }
+ if (!migration) {
+ if (vma->vm_flags & VM_LOCKED) {
+ ret = SWAP_MLOCK;
+ goto out_unmap;
+ }
+ if (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))
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
*/
BUG_ON(!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 && 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:
* For very sparsely populated VMAs this is a little inefficient - chances are
* there there won't be many ptes located within the scan cluster. In this case
* maybe we could scan further - to the end of the pte page, perhaps.
+ *
+ * Mlocked pages: check VM_LOCKED under mmap_sem held for read, if we can
+ * acquire it without blocking. If vma locked, mlock the pages in the cluster,
+ * rather than unmapping them. If we encounter the "check_page" that vmscan is
+ * trying to unmap, return SWAP_MLOCK, else default SWAP_AGAIN.
*/
#define CLUSTER_SIZE min(32*PAGE_SIZE, PMD_SIZE)
#define CLUSTER_MASK (~(CLUSTER_SIZE - 1))
-static void try_to_unmap_cluster(unsigned long cursor,
- unsigned int *mapcount, struct vm_area_struct *vma)
+static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
+ struct vm_area_struct *vma, struct page *check_page)
{
struct mm_struct *mm = vma->vm_mm;
pgd_t *pgd;
struct page *page;
unsigned long address;
unsigned long end;
+ int ret = SWAP_AGAIN;
+ int locked_vma = 0;
address = (vma->vm_start + cursor) & CLUSTER_MASK;
end = address + CLUSTER_SIZE;
pgd = pgd_offset(mm, address);
if (!pgd_present(*pgd))
- return;
+ return ret;
pud = pud_offset(pgd, address);
if (!pud_present(*pud))
- return;
+ return ret;
pmd = pmd_offset(pud, address);
if (!pmd_present(*pmd))
- return;
+ return ret;
+
+ /*
+ * MLOCK_PAGES => feature is configured.
+ * 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)) {
+ locked_vma = (vma->vm_flags & VM_LOCKED);
+ if (!locked_vma)
+ up_read(&vma->vm_mm->mmap_sem); /* don't need it */
+ }
pte = pte_offset_map_lock(mm, pmd, address, &ptl);
page = vm_normal_page(vma, address, *pte);
BUG_ON(!page || PageAnon(page));
- if (ptep_clear_flush_young(vma, address, pte))
+ if (locked_vma) {
+ mlock_vma_page(page); /* no-op if already mlocked */
+ if (page == check_page)
+ ret = SWAP_MLOCK;
+ continue; /* don't unmap */
+ }
+
+ 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))
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)--;
}
pte_unmap_unlock(pte - 1, ptl);
+ if (locked_vma)
+ up_read(&vma->vm_mm->mmap_sem);
+ 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;
}
-static int try_to_unmap_anon(struct page *page, int migration)
+/**
+ * try_to_unmap_anon - unmap or unlock anonymous 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
+ *
+ * Find all the mappings of a page using the mapping pointer and the vma chains
+ * contained in the anon_vma struct it points to.
+ *
+ * This function is only called from try_to_unmap/try_to_munlock for
+ * anonymous pages.
+ * When called from try_to_munlock(), the mmap_sem of the mm containing the vma
+ * where the page was found will be held for write. So, we won't recheck
+ * 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)
{
struct anon_vma *anon_vma;
struct vm_area_struct *vma;
+ unsigned int mlocked = 0;
int ret = SWAP_AGAIN;
+ 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) {
- ret = try_to_unmap_one(page, vma, migration);
- if (ret == SWAP_FAIL || !page_mapped(page))
- break;
+ 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, migration);
+ 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 */
+ }
}
- spin_unlock(&anon_vma->lock);
+
+ 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;
}
/**
- * try_to_unmap_file - unmap file page using the object-based rmap method
- * @page: the page to unmap
+ * 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
*
* Find all the mappings of a page using the mapping pointer and the vma chains
* contained in the address_space struct it points to.
*
- * This function is only called from try_to_unmap for object-based pages.
+ * This function is only called from try_to_unmap/try_to_munlock for
+ * object-based pages.
+ * When called from try_to_munlock(), the mmap_sem of the mm containing the vma
+ * where the page was found will be held for write. So, we won't recheck
+ * 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 migration)
+static int try_to_unmap_file(struct page *page, int unlock, int migration)
{
struct address_space *mapping = page->mapping;
pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
unsigned long max_nl_cursor = 0;
unsigned long max_nl_size = 0;
unsigned int mapcount;
+ unsigned int mlocked = 0;
+
+ 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) {
- ret = try_to_unmap_one(page, vma, migration);
- if (ret == SWAP_FAIL || !page_mapped(page))
- goto out;
+ 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, migration);
+ if (ret == SWAP_FAIL || !page_mapped(page))
+ goto out;
+ }
+ if (ret == SWAP_MLOCK) {
+ mlocked = try_to_mlock_page(page, vma);
+ if (mlocked)
+ break; /* stop if actually mlocked page */
+ }
}
+ if (mlocked)
+ goto out;
+
if (list_empty(&mapping->i_mmap_nonlinear))
goto out;
list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
shared.vm_set.list) {
- if ((vma->vm_flags & VM_LOCKED) && !migration)
+ 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 && !migration && (vma->vm_flags & VM_LOCKED))
continue;
cursor = (unsigned long) vma->vm_private_data;
if (cursor > max_nl_cursor)
max_nl_size = cursor;
}
- if (max_nl_size == 0) { /* any nonlinears locked or reserved */
+ if (max_nl_size == 0) { /* all nonlinears locked or reserved ? */
ret = SWAP_FAIL;
goto out;
}
do {
list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
shared.vm_set.list) {
- if ((vma->vm_flags & VM_LOCKED) && !migration)
+ if (!MLOCK_PAGES && !migration &&
+ (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) {
- try_to_unmap_cluster(cursor, &mapcount, vma);
+ ret = try_to_unmap_cluster(cursor, &mapcount,
+ vma, page);
+ if (ret == SWAP_MLOCK)
+ mlocked = 2; /* to return below */
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;
}
/**
* 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.
* SWAP_SUCCESS - we succeeded in removing all mappings
* SWAP_AGAIN - we missed a mapping, try again later
* SWAP_FAIL - the page is unswappable
+ * SWAP_MLOCK - page is mlocked.
*/
int try_to_unmap(struct page *page, int migration)
{
BUG_ON(!PageLocked(page));
if (PageAnon(page))
- ret = try_to_unmap_anon(page, migration);
+ ret = try_to_unmap_anon(page, 0, migration);
else
- ret = try_to_unmap_file(page, migration);
-
- if (!page_mapped(page))
+ ret = try_to_unmap_file(page, 0, migration);
+ 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
+ *
+ * Called from munlock code. Checks all of the VMAs mapping the page
+ * to make sure nobody else has this page mlocked. The page will be
+ * returned with PG_mlocked cleared if no other vmas have it mlocked.
+ *
+ * Return values are:
+ *
+ * SWAP_SUCCESS - no vma's holding page mlocked.
+ * SWAP_AGAIN - page mapped in mlocked vma -- couldn't acquire mmap sem
+ * SWAP_MLOCK - page is now mlocked.
+ */
+int try_to_munlock(struct page *page)
+{
+ VM_BUG_ON(!PageLocked(page) || PageLRU(page));
+
+ if (PageAnon(page))
+ return try_to_unmap_anon(page, 1, 0);
+ else
+ return try_to_unmap_file(page, 1, 0);
+}
+#endif
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff