* 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/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>
-#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 struct kmem_cache *anon_vma_cachep;
+static struct kmem_cache *anon_vma_chain_cachep;
+
+static inline struct anon_vma *anon_vma_alloc(void)
+{
+ return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
+}
+
+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. */
+static inline struct anon_vma_chain *anon_vma_chain_alloc(void)
+{
+ return kmem_cache_alloc(anon_vma_chain_cachep, GFP_KERNEL);
+}
+
+void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain)
+{
+ kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain);
+}
+
+/**
+ * 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;
+ struct anon_vma_chain *avc;
might_sleep();
if (unlikely(!anon_vma)) {
struct mm_struct *mm = vma->vm_mm;
- struct anon_vma *allocated, *locked;
+ struct anon_vma *allocated;
+
+ avc = anon_vma_chain_alloc();
+ if (!avc)
+ goto out_enomem;
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;
+ goto out_enomem_free_avc;
allocated = anon_vma;
- locked = NULL;
}
+ spin_lock(&anon_vma->lock);
/* page_table_lock to protect against threads */
spin_lock(&mm->page_table_lock);
if (likely(!vma->anon_vma)) {
vma->anon_vma = anon_vma;
- list_add_tail(&vma->anon_vma_node, &anon_vma->head);
+ avc->anon_vma = anon_vma;
+ avc->vma = vma;
+ list_add(&avc->same_vma, &vma->anon_vma_chain);
+ list_add(&avc->same_anon_vma, &anon_vma->head);
allocated = NULL;
}
spin_unlock(&mm->page_table_lock);
- if (locked)
- spin_unlock(&locked->lock);
- if (unlikely(allocated))
+ spin_unlock(&anon_vma->lock);
+ if (unlikely(allocated)) {
anon_vma_free(allocated);
+ anon_vma_chain_free(avc);
+ }
}
return 0;
+
+ out_enomem_free_avc:
+ anon_vma_chain_free(avc);
+ out_enomem:
+ return -ENOMEM;
}
-void __anon_vma_merge(struct vm_area_struct *vma, struct vm_area_struct *next)
+static void anon_vma_chain_link(struct vm_area_struct *vma,
+ struct anon_vma_chain *avc,
+ struct anon_vma *anon_vma)
{
- BUG_ON(vma->anon_vma != next->anon_vma);
- list_del(&next->anon_vma_node);
+ avc->vma = vma;
+ avc->anon_vma = anon_vma;
+ list_add(&avc->same_vma, &vma->anon_vma_chain);
+
+ spin_lock(&anon_vma->lock);
+ list_add_tail(&avc->same_anon_vma, &anon_vma->head);
+ spin_unlock(&anon_vma->lock);
}
-void __anon_vma_link(struct vm_area_struct *vma)
+/*
+ * Attach the anon_vmas from src to dst.
+ * Returns 0 on success, -ENOMEM on failure.
+ */
+int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
{
- struct anon_vma *anon_vma = vma->anon_vma;
+ struct anon_vma_chain *avc, *pavc;
- if (anon_vma)
- list_add_tail(&vma->anon_vma_node, &anon_vma->head);
+ list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) {
+ avc = anon_vma_chain_alloc();
+ if (!avc)
+ goto enomem_failure;
+ anon_vma_chain_link(dst, avc, pavc->anon_vma);
+ }
+ return 0;
+
+ enomem_failure:
+ unlink_anon_vmas(dst);
+ return -ENOMEM;
}
-void anon_vma_link(struct vm_area_struct *vma)
+/*
+ * Attach vma to its own anon_vma, as well as to the anon_vmas that
+ * the corresponding VMA in the parent process is attached to.
+ * Returns 0 on success, non-zero on failure.
+ */
+int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
{
- struct anon_vma *anon_vma = vma->anon_vma;
+ struct anon_vma_chain *avc;
+ struct anon_vma *anon_vma;
- if (anon_vma) {
- spin_lock(&anon_vma->lock);
- list_add_tail(&vma->anon_vma_node, &anon_vma->head);
- spin_unlock(&anon_vma->lock);
- }
+ /* Don't bother if the parent process has no anon_vma here. */
+ if (!pvma->anon_vma)
+ return 0;
+
+ /*
+ * First, attach the new VMA to the parent VMA's anon_vmas,
+ * so rmap can find non-COWed pages in child processes.
+ */
+ if (anon_vma_clone(vma, pvma))
+ return -ENOMEM;
+
+ /* Then add our own anon_vma. */
+ anon_vma = anon_vma_alloc();
+ if (!anon_vma)
+ goto out_error;
+ avc = anon_vma_chain_alloc();
+ if (!avc)
+ goto out_error_free_anon_vma;
+ anon_vma_chain_link(vma, avc, anon_vma);
+ /* Mark this anon_vma as the one where our new (COWed) pages go. */
+ vma->anon_vma = anon_vma;
+
+ return 0;
+
+ out_error_free_anon_vma:
+ anon_vma_free(anon_vma);
+ out_error:
+ return -ENOMEM;
}
-void anon_vma_unlink(struct vm_area_struct *vma)
+static void anon_vma_unlink(struct anon_vma_chain *anon_vma_chain)
{
- struct anon_vma *anon_vma = vma->anon_vma;
+ struct anon_vma *anon_vma = anon_vma_chain->anon_vma;
int empty;
+ /* If anon_vma_fork fails, we can get an empty anon_vma_chain. */
if (!anon_vma)
return;
spin_lock(&anon_vma->lock);
- list_del(&vma->anon_vma_node);
+ list_del(&anon_vma_chain->same_anon_vma);
/* 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)
anon_vma_free(anon_vma);
}
-static void anon_vma_ctor(struct kmem_cache *cachep, void *data)
+void unlink_anon_vmas(struct vm_area_struct *vma)
+{
+ struct anon_vma_chain *avc, *next;
+
+ /* Unlink each anon_vma chained to the VMA. */
+ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
+ anon_vma_unlink(avc);
+ list_del(&avc->same_vma);
+ anon_vma_chain_free(avc);
+ }
+}
+
+static void anon_vma_ctor(void *data)
{
struct anon_vma *anon_vma = data;
spin_lock_init(&anon_vma->lock);
+ ksm_refcount_init(anon_vma);
INIT_LIST_HEAD(&anon_vma->head);
}
{
anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma),
0, SLAB_DESTROY_BY_RCU|SLAB_PANIC, anon_vma_ctor);
+ anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC);
}
/*
* Getting a lock on a stable anon_vma from a page off the LRU is
* tricky: page_lock_anon_vma rely on RCU to guard against the races.
*/
-static struct anon_vma *page_lock_anon_vma(struct page *page)
+struct anon_vma *page_lock_anon_vma(struct page *page)
{
struct anon_vma *anon_vma;
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;
return NULL;
}
-static void page_unlock_anon_vma(struct anon_vma *anon_vma)
+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;
}
/*
- * At what user virtual address is page expected in vma? checking that the
- * page matches the vma: currently only used on anon pages, by unuse_vma;
+ * At what user virtual address is page expected in vma?
+ * checking that the page matches the vma.
*/
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 ||
/*
* 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.
+ */
+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.
*/
-static int page_referenced_one(struct page *page,
- struct vm_area_struct *vma, unsigned int *mapcount)
+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);
+ 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 */
+ *vm_flags |= VM_LOCKED;
+ 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);
+
+ if (referenced)
+ *vm_flags |= vma->vm_flags;
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 long *vm_flags)
{
unsigned int mapcount;
struct anon_vma *anon_vma;
- struct vm_area_struct *vma;
+ struct anon_vma_chain *avc;
int referenced = 0;
anon_vma = page_lock_anon_vma(page);
return referenced;
mapcount = page_mapcount(page);
- list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
- referenced += page_referenced_one(page, vma, &mapcount);
+ list_for_each_entry(avc, &anon_vma->head, same_anon_vma) {
+ struct vm_area_struct *vma = avc->vma;
+ 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
+ * cgroups
+ */
+ if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
+ continue;
+ referenced += page_referenced_one(page, vma, address,
+ &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)
+static int page_referenced_file(struct page *page,
+ struct mem_cgroup *mem_cont,
+ unsigned long *vm_flags)
{
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;
- }
- referenced += page_referenced_one(page, vma, &mapcount);
+ 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
+ * cgroups
+ */
+ if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
+ continue;
+ referenced += page_referenced_one(page, vma, address,
+ &mapcount, vm_flags);
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
+ * @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)
+int page_referenced(struct page *page,
+ int is_locked,
+ struct mem_cgroup *mem_cont,
+ unsigned long *vm_flags)
{
int referenced = 0;
-
+ int we_locked = 0;
+
+ *vm_flags = 0;
+ 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 (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++;
- if (TestClearPageReferenced(page))
- referenced++;
-
- if (page_mapped(page) && page->mapping) {
- if (PageAnon(page))
- referenced += page_referenced_anon(page);
- else if (is_locked)
- referenced += page_referenced_file(page);
- else if (TestSetPageLocked(page))
- referenced++;
- else {
- if (page->mapping)
- referenced += page_referenced_file(page);
- unlock_page(page);
- }
- }
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);
+ 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);
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;
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_move_anon_rmap - move a page to our anon_vma
+ * @page: the page to move to our anon_vma
+ * @vma: the vma the page belongs to
+ * @address: the user virtual address mapped
+ *
+ * When a page belongs exclusively to one process after a COW event,
+ * that page can be moved into the anon_vma that belongs to just that
+ * process, so the rmap code will not search the parent or sibling
+ * processes.
+ */
+void page_move_anon_rmap(struct page *page,
+ struct vm_area_struct *vma, unsigned long address)
+{
+ struct anon_vma *anon_vma = vma->anon_vma;
+
+ VM_BUG_ON(!PageLocked(page));
+ VM_BUG_ON(!anon_vma);
+ VM_BUG_ON(page->index != linear_page_index(vma, address));
+
+ anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
+ page->mapping = (struct address_space *) anon_vma;
+}
+
+/**
+ * __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
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);
}
/**
- * 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
* 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
}
* @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);
}
-/*
+/**
* 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
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) */
+ __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);
+ 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_file_mapped(page, 1);
+ }
}
-#ifdef CONFIG_DEBUG_VM
-/**
- * page_dup_rmap - duplicate pte mapping to a page
- * @page: the page to add the mapping to
- *
- * 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)
-{
- BUG_ON(page_mapcount(page) == 0);
- 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)
-{
- 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);
- 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();
- }
+void page_remove_rmap(struct page *page)
+{
+ /* page still mapped by someone else? */
+ if (!atomic_add_negative(-1, &page->_mapcount))
+ return;
- /*
- * 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
- * before us: so leave the reset to free_hot_cold_page,
- * and remember that it's only reliable while mapped.
- * 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);
+ /*
+ * 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, NR_ANON_PAGES);
+ } else {
+ __dec_zone_page_state(page, NR_FILE_MAPPED);
+ mem_cgroup_update_file_mapped(page, -1);
+ }
+ /*
+ * 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
+ * before us: so leave the reset to free_hot_cold_page,
+ * and remember that it's only reliable while mapped.
+ * Leaving it set also helps swapoff to reinstate ptes
+ * faster for those pages still in swapcache.
+ */
}
/*
* 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,
- int migration)
+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);
+ 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 (!(flags & TTU_IGNORE_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)) {
+ 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))
/* 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, MM_ANONPAGES);
+ else
+ dec_mm_counter(mm, MM_FILEPAGES);
+ 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)) {
* Store the swap location in the pte.
* See handle_pte_fault() ...
*/
- swap_duplicate(entry);
+ if (swap_duplicate(entry) < 0) {
+ set_pte_at(mm, address, pte, pteval);
+ ret = SWAP_FAIL;
+ goto out_unmap;
+ }
if (list_empty(&mm->mmlist)) {
spin_lock(&mmlist_lock);
if (list_empty(&mm->mmlist))
list_add(&mm->mmlist, &init_mm.mmlist);
spin_unlock(&mmlist_lock);
}
- dec_mm_counter(mm, anon_rss);
-#ifdef CONFIG_MIGRATION
- } else {
+ dec_mm_counter(mm, MM_ANONPAGES);
+ inc_mm_counter(mm, MM_SWAPENTS);
+ } 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);
-
+ dec_mm_counter(mm, MM_FILEPAGES);
- page_remove_rmap(page, vma);
+ page_remove_rmap(page);
page_cache_release(page);
out_unmap:
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;
}
/*
* 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;
+
+ /*
+ * 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 (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);
+ dec_mm_counter(mm, MM_FILEPAGES);
(*mapcount)--;
}
pte_unmap_unlock(pte - 1, ptl);
+ if (locked_vma)
+ up_read(&vma->vm_mm->mmap_sem);
+ return ret;
}
-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
+ * @flags: action and flags
+ *
+ * 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, enum ttu_flags flags)
{
struct anon_vma *anon_vma;
- struct vm_area_struct *vma;
+ struct anon_vma_chain *avc;
int ret = SWAP_AGAIN;
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))
+ list_for_each_entry(avc, &anon_vma->head, same_anon_vma) {
+ struct vm_area_struct *vma = avc->vma;
+ 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;
}
}
/**
- * 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
+ * @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.
*
- * 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, enum ttu_flags flags)
{
struct address_space *mapping = page->mapping;
pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
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))
+ 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 ((vma->vm_flags & VM_LOCKED) && !migration)
- continue;
cursor = (unsigned long) vma->vm_private_data;
if (cursor > max_nl_cursor)
max_nl_cursor = 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)
- 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);
+ 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)
/**
* try_to_unmap - try to remove all page table mappings to a page
* @page: the page to get unmapped
+ * @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_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)
+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, migration);
+ 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, migration);
-
- if (!page_mapped(page))
+ ret = try_to_unmap_file(page, flags);
+ if (ret != SWAP_MLOCK && !page_mapped(page))
ret = SWAP_SUCCESS;
return ret;
}
+/**
+ * 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_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 (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 anon_vma_chain *avc;
+ 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(avc, &anon_vma->head, same_anon_vma) {
+ struct vm_area_struct *vma = avc->vma;
+ 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 */