* Lock ordering in mm:
*
* inode->i_mutex (while writing or truncating, not reading or faulting)
- * inode->i_alloc_sem (vmtruncate_range)
* mm->mmap_sem
* page->flags PG_locked (lock_page)
- * mapping->i_mmap_lock
- * anon_vma->lock
+ * mapping->i_mmap_mutex
+ * anon_vma->mutex
* mm->page_table_lock or pte_lock
* zone->lru_lock (in mark_page_accessed, isolate_lru_page)
* swap_lock (in swap_duplicate, swap_info_get)
* mmlist_lock (in mmput, drain_mmlist and others)
* mapping->private_lock (in __set_page_dirty_buffers)
- * inode_lock (in set_page_dirty's __mark_inode_dirty)
+ * inode->i_lock (in set_page_dirty's __mark_inode_dirty)
+ * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
* sb_lock (within inode_lock in fs/fs-writeback.c)
* mapping->tree_lock (widely used, in set_page_dirty,
* in arch-dependent flush_dcache_mmap_lock,
- * within inode_lock in __sync_single_inode)
+ * within bdi.wb->list_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)
+ * anon_vma->mutex,mapping->i_mutex (memory_failure, collect_procs_anon)
+ * ->tasklist_lock
* pte map lock
*/
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/rcupdate.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
static inline struct anon_vma *anon_vma_alloc(void)
{
- return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
+ struct anon_vma *anon_vma;
+
+ anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
+ if (anon_vma) {
+ atomic_set(&anon_vma->refcount, 1);
+ /*
+ * Initialise the anon_vma root to point to itself. If called
+ * from fork, the root will be reset to the parents anon_vma.
+ */
+ anon_vma->root = anon_vma;
+ }
+
+ return anon_vma;
}
-void anon_vma_free(struct anon_vma *anon_vma)
+static inline void anon_vma_free(struct anon_vma *anon_vma)
{
+ VM_BUG_ON(atomic_read(&anon_vma->refcount));
+
+ /*
+ * Synchronize against page_lock_anon_vma() such that
+ * we can safely hold the lock without the anon_vma getting
+ * freed.
+ *
+ * Relies on the full mb implied by the atomic_dec_and_test() from
+ * put_anon_vma() against the acquire barrier implied by
+ * mutex_trylock() from page_lock_anon_vma(). This orders:
+ *
+ * page_lock_anon_vma() VS put_anon_vma()
+ * mutex_trylock() atomic_dec_and_test()
+ * LOCK MB
+ * atomic_read() mutex_is_locked()
+ *
+ * LOCK should suffice since the actual taking of the lock must
+ * happen _before_ what follows.
+ */
+ if (mutex_is_locked(&anon_vma->root->mutex)) {
+ anon_vma_lock(anon_vma);
+ anon_vma_unlock(anon_vma);
+ }
+
kmem_cache_free(anon_vma_cachep, anon_vma);
}
-static inline struct anon_vma_chain *anon_vma_chain_alloc(void)
+static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp)
{
- return kmem_cache_alloc(anon_vma_chain_cachep, GFP_KERNEL);
+ return kmem_cache_alloc(anon_vma_chain_cachep, gfp);
}
static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain)
kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain);
}
+static void anon_vma_chain_link(struct vm_area_struct *vma,
+ struct anon_vma_chain *avc,
+ struct anon_vma *anon_vma)
+{
+ avc->vma = vma;
+ avc->anon_vma = anon_vma;
+ list_add(&avc->same_vma, &vma->anon_vma_chain);
+
+ /*
+ * It's critical to add new vmas to the tail of the anon_vma,
+ * see comment in huge_memory.c:__split_huge_page().
+ */
+ list_add_tail(&avc->same_anon_vma, &anon_vma->head);
+}
+
/**
* anon_vma_prepare - attach an anon_vma to a memory region
* @vma: the memory region in question
struct mm_struct *mm = vma->vm_mm;
struct anon_vma *allocated;
- avc = anon_vma_chain_alloc();
+ avc = anon_vma_chain_alloc(GFP_KERNEL);
if (!avc)
goto out_enomem;
if (unlikely(!anon_vma))
goto out_enomem_free_avc;
allocated = anon_vma;
- /*
- * This VMA had no anon_vma yet. This anon_vma is
- * the root of any anon_vma tree that might form.
- */
- anon_vma->root = anon_vma;
}
anon_vma_lock(anon_vma);
spin_lock(&mm->page_table_lock);
if (likely(!vma->anon_vma)) {
vma->anon_vma = anon_vma;
- avc->anon_vma = anon_vma;
- avc->vma = vma;
- list_add(&avc->same_vma, &vma->anon_vma_chain);
- list_add_tail(&avc->same_anon_vma, &anon_vma->head);
+ anon_vma_chain_link(vma, avc, anon_vma);
allocated = NULL;
avc = NULL;
}
anon_vma_unlock(anon_vma);
if (unlikely(allocated))
- anon_vma_free(allocated);
+ put_anon_vma(allocated);
if (unlikely(avc))
anon_vma_chain_free(avc);
}
return -ENOMEM;
}
-static void anon_vma_chain_link(struct vm_area_struct *vma,
- struct anon_vma_chain *avc,
- struct anon_vma *anon_vma)
+/*
+ * This is a useful helper function for locking the anon_vma root as
+ * we traverse the vma->anon_vma_chain, looping over anon_vma's that
+ * have the same vma.
+ *
+ * Such anon_vma's should have the same root, so you'd expect to see
+ * just a single mutex_lock for the whole traversal.
+ */
+static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma)
{
- avc->vma = vma;
- avc->anon_vma = anon_vma;
- list_add(&avc->same_vma, &vma->anon_vma_chain);
+ struct anon_vma *new_root = anon_vma->root;
+ if (new_root != root) {
+ if (WARN_ON_ONCE(root))
+ mutex_unlock(&root->mutex);
+ root = new_root;
+ mutex_lock(&root->mutex);
+ }
+ return root;
+}
- anon_vma_lock(anon_vma);
- /*
- * It's critical to add new vmas to the tail of the anon_vma,
- * see comment in huge_memory.c:__split_huge_page().
- */
- list_add_tail(&avc->same_anon_vma, &anon_vma->head);
- anon_vma_unlock(anon_vma);
+static inline void unlock_anon_vma_root(struct anon_vma *root)
+{
+ if (root)
+ mutex_unlock(&root->mutex);
}
/*
int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
{
struct anon_vma_chain *avc, *pavc;
+ struct anon_vma *root = NULL;
list_for_each_entry_reverse(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);
+ struct anon_vma *anon_vma;
+
+ avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN);
+ if (unlikely(!avc)) {
+ unlock_anon_vma_root(root);
+ root = NULL;
+ avc = anon_vma_chain_alloc(GFP_KERNEL);
+ if (!avc)
+ goto enomem_failure;
+ }
+ anon_vma = pavc->anon_vma;
+ root = lock_anon_vma_root(root, anon_vma);
+ anon_vma_chain_link(dst, avc, anon_vma);
}
+ unlock_anon_vma_root(root);
return 0;
enomem_failure:
}
/*
+ * Some rmap walk that needs to find all ptes/hugepmds without false
+ * negatives (like migrate and split_huge_page) running concurrent
+ * with operations that copy or move pagetables (like mremap() and
+ * fork()) to be safe. They depend on the anon_vma "same_anon_vma"
+ * list to be in a certain order: the dst_vma must be placed after the
+ * src_vma in the list. This is always guaranteed by fork() but
+ * mremap() needs to call this function to enforce it in case the
+ * dst_vma isn't newly allocated and chained with the anon_vma_clone()
+ * function but just an extension of a pre-existing vma through
+ * vma_merge.
+ *
+ * NOTE: the same_anon_vma list can still be changed by other
+ * processes while mremap runs because mremap doesn't hold the
+ * anon_vma mutex to prevent modifications to the list while it
+ * runs. All we need to enforce is that the relative order of this
+ * process vmas isn't changing (we don't care about other vmas
+ * order). Each vma corresponds to an anon_vma_chain structure so
+ * there's no risk that other processes calling anon_vma_moveto_tail()
+ * and changing the same_anon_vma list under mremap() will screw with
+ * the relative order of this process vmas in the list, because we
+ * they can't alter the order of any vma that belongs to this
+ * process. And there can't be another anon_vma_moveto_tail() running
+ * concurrently with mremap() coming from this process because we hold
+ * the mmap_sem for the whole mremap(). fork() ordering dependency
+ * also shouldn't be affected because fork() only cares that the
+ * parent vmas are placed in the list before the child vmas and
+ * anon_vma_moveto_tail() won't reorder vmas from either the fork()
+ * parent or child.
+ */
+void anon_vma_moveto_tail(struct vm_area_struct *dst)
+{
+ struct anon_vma_chain *pavc;
+ struct anon_vma *root = NULL;
+
+ list_for_each_entry_reverse(pavc, &dst->anon_vma_chain, same_vma) {
+ struct anon_vma *anon_vma = pavc->anon_vma;
+ VM_BUG_ON(pavc->vma != dst);
+ root = lock_anon_vma_root(root, anon_vma);
+ list_del(&pavc->same_anon_vma);
+ list_add_tail(&pavc->same_anon_vma, &anon_vma->head);
+ }
+ unlock_anon_vma_root(root);
+}
+
+/*
* 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.
anon_vma = anon_vma_alloc();
if (!anon_vma)
goto out_error;
- avc = anon_vma_chain_alloc();
+ avc = anon_vma_chain_alloc(GFP_KERNEL);
if (!avc)
goto out_error_free_anon_vma;
*/
anon_vma->root = pvma->anon_vma->root;
/*
- * With KSM refcounts, an anon_vma can stay around longer than the
- * process it belongs to. The root anon_vma needs to be pinned
- * until this anon_vma is freed, because the lock lives in the root.
+ * With refcounts, an anon_vma can stay around longer than the
+ * process it belongs to. The root anon_vma needs to be pinned until
+ * this anon_vma is freed, because the lock lives in the root.
*/
get_anon_vma(anon_vma->root);
/* Mark this anon_vma as the one where our new (COWed) pages go. */
vma->anon_vma = anon_vma;
+ anon_vma_lock(anon_vma);
anon_vma_chain_link(vma, avc, anon_vma);
+ anon_vma_unlock(anon_vma);
return 0;
out_error_free_anon_vma:
- anon_vma_free(anon_vma);
+ put_anon_vma(anon_vma);
out_error:
unlink_anon_vmas(vma);
return -ENOMEM;
}
-static void anon_vma_unlink(struct anon_vma_chain *anon_vma_chain)
+void unlink_anon_vmas(struct vm_area_struct *vma)
{
- struct anon_vma *anon_vma = anon_vma_chain->anon_vma;
- int empty;
+ struct anon_vma_chain *avc, *next;
+ struct anon_vma *root = NULL;
- /* If anon_vma_fork fails, we can get an empty anon_vma_chain. */
- if (!anon_vma)
- return;
+ /*
+ * Unlink each anon_vma chained to the VMA. This list is ordered
+ * from newest to oldest, ensuring the root anon_vma gets freed last.
+ */
+ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
+ struct anon_vma *anon_vma = avc->anon_vma;
- anon_vma_lock(anon_vma);
- list_del(&anon_vma_chain->same_anon_vma);
+ root = lock_anon_vma_root(root, anon_vma);
+ list_del(&avc->same_anon_vma);
- /* We must garbage collect the anon_vma if it's empty */
- empty = list_empty(&anon_vma->head) && !anonvma_external_refcount(anon_vma);
- anon_vma_unlock(anon_vma);
+ /*
+ * Leave empty anon_vmas on the list - we'll need
+ * to free them outside the lock.
+ */
+ if (list_empty(&anon_vma->head))
+ continue;
- if (empty) {
- /* We no longer need the root anon_vma */
- if (anon_vma->root != anon_vma)
- drop_anon_vma(anon_vma->root);
- anon_vma_free(anon_vma);
+ list_del(&avc->same_vma);
+ anon_vma_chain_free(avc);
}
-}
-
-void unlink_anon_vmas(struct vm_area_struct *vma)
-{
- struct anon_vma_chain *avc, *next;
+ unlock_anon_vma_root(root);
/*
- * Unlink each anon_vma chained to the VMA. This list is ordered
- * from newest to oldest, ensuring the root anon_vma gets freed last.
+ * Iterate the list once more, it now only contains empty and unlinked
+ * anon_vmas, destroy them. Could not do before due to __put_anon_vma()
+ * needing to acquire the anon_vma->root->mutex.
*/
list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
- anon_vma_unlink(avc);
+ struct anon_vma *anon_vma = avc->anon_vma;
+
+ put_anon_vma(anon_vma);
+
list_del(&avc->same_vma);
anon_vma_chain_free(avc);
}
{
struct anon_vma *anon_vma = data;
- spin_lock_init(&anon_vma->lock);
- anonvma_external_refcount_init(anon_vma);
+ mutex_init(&anon_vma->mutex);
+ atomic_set(&anon_vma->refcount, 0);
INIT_LIST_HEAD(&anon_vma->head);
}
}
/*
- * 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.
+ * Getting a lock on a stable anon_vma from a page off the LRU is tricky!
+ *
+ * Since there is no serialization what so ever against page_remove_rmap()
+ * the best this function can do is return a locked anon_vma that might
+ * have been relevant to this page.
+ *
+ * The page might have been remapped to a different anon_vma or the anon_vma
+ * returned may already be freed (and even reused).
+ *
+ * In case it was remapped to a different anon_vma, the new anon_vma will be a
+ * child of the old anon_vma, and the anon_vma lifetime rules will therefore
+ * ensure that any anon_vma obtained from the page will still be valid for as
+ * long as we observe page_mapped() [ hence all those page_mapped() tests ].
+ *
+ * All users of this function must be very careful when walking the anon_vma
+ * chain and verify that the page in question is indeed mapped in it
+ * [ something equivalent to page_mapped_in_vma() ].
+ *
+ * Since anon_vma's slab is DESTROY_BY_RCU and we know from page_remove_rmap()
+ * that the anon_vma pointer from page->mapping is valid if there is a
+ * mapcount, we can dereference the anon_vma after observing those.
*/
-struct anon_vma *__page_lock_anon_vma(struct page *page)
+struct anon_vma *page_get_anon_vma(struct page *page)
{
- struct anon_vma *anon_vma, *root_anon_vma;
+ struct anon_vma *anon_vma = NULL;
unsigned long anon_mapping;
rcu_read_lock();
goto out;
anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
- root_anon_vma = ACCESS_ONCE(anon_vma->root);
- spin_lock(&root_anon_vma->lock);
+ if (!atomic_inc_not_zero(&anon_vma->refcount)) {
+ anon_vma = NULL;
+ goto out;
+ }
/*
* If this page is still mapped, then its anon_vma cannot have been
- * freed. But if it has been unmapped, we have no security against
- * the anon_vma structure being freed and reused (for another anon_vma:
- * SLAB_DESTROY_BY_RCU guarantees that - so the spin_lock above cannot
- * corrupt): with anon_vma_prepare() or anon_vma_fork() redirecting
- * anon_vma->root before page_unlock_anon_vma() is called to unlock.
+ * freed. But if it has been unmapped, we have no security against the
+ * anon_vma structure being freed and reused (for another anon_vma:
+ * SLAB_DESTROY_BY_RCU guarantees that - so the atomic_inc_not_zero()
+ * above cannot corrupt).
*/
- if (page_mapped(page))
- return anon_vma;
+ if (!page_mapped(page)) {
+ put_anon_vma(anon_vma);
+ anon_vma = NULL;
+ }
+out:
+ rcu_read_unlock();
+
+ return anon_vma;
+}
+
+/*
+ * Similar to page_get_anon_vma() except it locks the anon_vma.
+ *
+ * Its a little more complex as it tries to keep the fast path to a single
+ * atomic op -- the trylock. If we fail the trylock, we fall back to getting a
+ * reference like with page_get_anon_vma() and then block on the mutex.
+ */
+struct anon_vma *page_lock_anon_vma(struct page *page)
+{
+ struct anon_vma *anon_vma = NULL;
+ struct anon_vma *root_anon_vma;
+ unsigned long anon_mapping;
+
+ rcu_read_lock();
+ 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;
+
+ anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
+ root_anon_vma = ACCESS_ONCE(anon_vma->root);
+ if (mutex_trylock(&root_anon_vma->mutex)) {
+ /*
+ * If the page is still mapped, then this anon_vma is still
+ * its anon_vma, and holding the mutex ensures that it will
+ * not go away, see anon_vma_free().
+ */
+ if (!page_mapped(page)) {
+ mutex_unlock(&root_anon_vma->mutex);
+ anon_vma = NULL;
+ }
+ goto out;
+ }
+
+ /* trylock failed, we got to sleep */
+ if (!atomic_inc_not_zero(&anon_vma->refcount)) {
+ anon_vma = NULL;
+ goto out;
+ }
+
+ if (!page_mapped(page)) {
+ put_anon_vma(anon_vma);
+ anon_vma = NULL;
+ goto out;
+ }
+
+ /* we pinned the anon_vma, its safe to sleep */
+ rcu_read_unlock();
+ anon_vma_lock(anon_vma);
+
+ if (atomic_dec_and_test(&anon_vma->refcount)) {
+ /*
+ * Oops, we held the last refcount, release the lock
+ * and bail -- can't simply use put_anon_vma() because
+ * we'll deadlock on the anon_vma_lock() recursion.
+ */
+ anon_vma_unlock(anon_vma);
+ __put_anon_vma(anon_vma);
+ anon_vma = NULL;
+ }
+
+ return anon_vma;
- spin_unlock(&root_anon_vma->lock);
out:
rcu_read_unlock();
- return NULL;
+ return anon_vma;
}
void page_unlock_anon_vma(struct anon_vma *anon_vma)
- __releases(&anon_vma->root->lock)
- __releases(RCU)
{
anon_vma_unlock(anon_vma);
- rcu_read_unlock();
}
/*
struct mm_struct *mm = vma->vm_mm;
int referenced = 0;
- /*
- * 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 = 0; /* break early from loop */
- *vm_flags |= VM_LOCKED;
- goto out;
- }
-
- /* Pretend the page is referenced if the task has the
- swap token and is in the middle of a page fault. */
- if (mm != current->mm && has_swap_token(mm) &&
- rwsem_is_locked(&mm->mmap_sem))
- referenced++;
-
if (unlikely(PageTransHuge(page))) {
pmd_t *pmd;
spin_lock(&mm->page_table_lock);
+ /*
+ * rmap might return false positives; we must filter
+ * these out using page_check_address_pmd().
+ */
pmd = page_check_address_pmd(page, mm, address,
PAGE_CHECK_ADDRESS_PMD_FLAG);
- if (pmd && !pmd_trans_splitting(*pmd) &&
- pmdp_clear_flush_young_notify(vma, address, pmd))
+ if (!pmd) {
+ spin_unlock(&mm->page_table_lock);
+ goto out;
+ }
+
+ if (vma->vm_flags & VM_LOCKED) {
+ spin_unlock(&mm->page_table_lock);
+ *mapcount = 0; /* break early from loop */
+ *vm_flags |= VM_LOCKED;
+ goto out;
+ }
+
+ /* go ahead even if the pmd is pmd_trans_splitting() */
+ if (pmdp_clear_flush_young_notify(vma, address, pmd))
referenced++;
spin_unlock(&mm->page_table_lock);
} else {
pte_t *pte;
spinlock_t *ptl;
+ /*
+ * rmap might return false positives; we must filter
+ * these out using page_check_address().
+ */
pte = page_check_address(page, mm, address, &ptl, 0);
if (!pte)
goto out;
+ if (vma->vm_flags & VM_LOCKED) {
+ pte_unmap_unlock(pte, ptl);
+ *mapcount = 0; /* break early from loop */
+ *vm_flags |= VM_LOCKED;
+ goto out;
+ }
+
if (ptep_clear_flush_young_notify(vma, address, pte)) {
/*
* Don't treat a reference through a sequentially read
pte_unmap_unlock(pte, ptl);
}
+ /* Pretend the page is referenced if the task has the
+ swap token and is in the middle of a page fault. */
+ if (mm != current->mm && has_swap_token(mm) &&
+ rwsem_is_locked(&mm->mmap_sem))
+ referenced++;
+
(*mapcount)--;
if (referenced)
}
static int page_referenced_anon(struct page *page,
- struct mem_cgroup *mem_cont,
+ struct mem_cgroup *memcg,
unsigned long *vm_flags)
{
unsigned int mapcount;
* counting on behalf of references from different
* cgroups
*/
- if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
+ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg))
continue;
referenced += page_referenced_one(page, vma, address,
&mapcount, vm_flags);
/**
* page_referenced_file - referenced check for object-based rmap
* @page: the page we're checking references on.
- * @mem_cont: target memory controller
+ * @memcg: target memory control group
* @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
* 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 *memcg,
unsigned long *vm_flags)
{
unsigned int mapcount;
* The page lock not only makes sure that page->mapping cannot
* suddenly be NULLified by truncation, it makes sure that the
* structure at mapping cannot be freed and reused yet,
- * so we can safely take mapping->i_mmap_lock.
+ * so we can safely take mapping->i_mmap_mutex.
*/
BUG_ON(!PageLocked(page));
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
/*
- * i_mmap_lock does not stabilize mapcount at all, but mapcount
+ * i_mmap_mutex does not stabilize mapcount at all, but mapcount
* is more likely to be accurate if we note it after spinning.
*/
mapcount = page_mapcount(page);
* counting on behalf of references from different
* cgroups
*/
- if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
+ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg))
continue;
referenced += page_referenced_one(page, vma, address,
&mapcount, vm_flags);
break;
}
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
return referenced;
}
* page_referenced - test if the page was referenced
* @page: the page to test
* @is_locked: caller holds lock on the page
- * @mem_cont: target memory controller
+ * @memcg: target memory cgroup
* @vm_flags: collect encountered vma->vm_flags who actually referenced the page
*
* Quick test_and_clear_referenced for all mappings to a page,
*/
int page_referenced(struct page *page,
int is_locked,
- struct mem_cgroup *mem_cont,
+ struct mem_cgroup *memcg,
unsigned long *vm_flags)
{
int referenced = 0;
}
}
if (unlikely(PageKsm(page)))
- referenced += page_referenced_ksm(page, mem_cont,
+ referenced += page_referenced_ksm(page, memcg,
vm_flags);
else if (PageAnon(page))
- referenced += page_referenced_anon(page, mem_cont,
+ referenced += page_referenced_anon(page, memcg,
vm_flags);
else if (page->mapping)
- referenced += page_referenced_file(page, mem_cont,
+ referenced += page_referenced_file(page, memcg,
vm_flags);
if (we_locked)
unlock_page(page);
+
+ if (page_test_and_clear_young(page_to_pfn(page)))
+ referenced++;
}
out:
- if (page_test_and_clear_young(page))
- referenced++;
-
return referenced;
}
BUG_ON(PageAnon(page));
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
if (vma->vm_flags & VM_SHARED) {
unsigned long address = vma_address(page, vma);
ret += page_mkclean_one(page, vma, address);
}
}
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
return ret;
}
struct address_space *mapping = page_mapping(page);
if (mapping) {
ret = page_mkclean_file(mapping, page);
- if (page_test_dirty(page)) {
- page_clear_dirty(page, 1);
+ if (page_test_and_clear_dirty(page_to_pfn(page), 1))
ret = 1;
- }
}
}
return;
VM_BUG_ON(!PageLocked(page));
- VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+ /* address might be in next vma when migration races vma_adjust */
if (first)
__page_set_anon_rmap(page, vma, address, exclusive);
else
*/
void page_add_file_rmap(struct page *page)
{
+ bool locked;
+ unsigned long flags;
+
+ mem_cgroup_begin_update_page_stat(page, &locked, &flags);
if (atomic_inc_and_test(&page->_mapcount)) {
__inc_zone_page_state(page, NR_FILE_MAPPED);
- mem_cgroup_update_file_mapped(page, 1);
+ mem_cgroup_inc_page_stat(page, MEMCG_NR_FILE_MAPPED);
}
+ mem_cgroup_end_update_page_stat(page, &locked, &flags);
}
/**
*/
void page_remove_rmap(struct page *page)
{
+ bool anon = PageAnon(page);
+ bool locked;
+ unsigned long flags;
+
+ /*
+ * The anon case has no mem_cgroup page_stat to update; but may
+ * uncharge_page() below, where the lock ordering can deadlock if
+ * we hold the lock against page_stat move: so avoid it on anon.
+ */
+ if (!anon)
+ mem_cgroup_begin_update_page_stat(page, &locked, &flags);
+
/* page still mapped by someone else? */
if (!atomic_add_negative(-1, &page->_mapcount))
- return;
+ goto out;
/*
* Now that the last pte has gone, s390 must transfer dirty
* 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, 1);
+ if ((!anon || PageSwapCache(page)) &&
+ page_test_and_clear_dirty(page_to_pfn(page), 1))
set_page_dirty(page);
- }
/*
* Hugepages are not counted in NR_ANON_PAGES nor NR_FILE_MAPPED
* and not charged by memcg for now.
*/
if (unlikely(PageHuge(page)))
- return;
- if (PageAnon(page)) {
+ goto out;
+ if (anon) {
mem_cgroup_uncharge_page(page);
if (!PageTransHuge(page))
__dec_zone_page_state(page, NR_ANON_PAGES);
NR_ANON_TRANSPARENT_HUGEPAGES);
} else {
__dec_zone_page_state(page, NR_FILE_MAPPED);
- mem_cgroup_update_file_mapped(page, -1);
+ mem_cgroup_dec_page_stat(page, MEMCG_NR_FILE_MAPPED);
}
/*
* It would be tidy to reset the PageAnon mapping here,
* Leaving it set also helps swapoff to reinstate ptes
* faster for those pages still in swapcache.
*/
+out:
+ if (!anon)
+ mem_cgroup_end_update_page_stat(page, &locked, &flags);
}
/*
* Subfunctions of try_to_unmap: try_to_unmap_one called
- * repeatedly from either try_to_unmap_anon or try_to_unmap_file.
+ * repeatedly from try_to_unmap_ksm, try_to_unmap_anon or try_to_unmap_file.
*/
int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
unsigned long address, enum ttu_flags flags)
}
dec_mm_counter(mm, MM_ANONPAGES);
inc_mm_counter(mm, MM_SWAPENTS);
- } else if (PAGE_MIGRATION) {
+ } else if (IS_ENABLED(CONFIG_MIGRATION)) {
/*
* Store the pfn of the page in a special migration
* pte. do_swap_page() will wait until the migration
}
set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
BUG_ON(pte_file(*pte));
- } else if (PAGE_MIGRATION && (TTU_ACTION(flags) == TTU_MIGRATION)) {
+ } else if (IS_ENABLED(CONFIG_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));
/*
* 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.
+ * we now hold anon_vma->mutex or mapping->i_mmap_mutex.
* 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.
* locking requirements of exec(), migration skips
* temporary VMAs until after exec() completes.
*/
- if (PAGE_MIGRATION && (flags & TTU_MIGRATION) &&
+ if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) &&
is_vma_temporary_stack(vma))
continue;
unsigned long max_nl_size = 0;
unsigned int mapcount;
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
unsigned long address = vma_address(page, vma);
if (address == -EFAULT)
mapcount = page_mapcount(page);
if (!mapcount)
goto out;
- cond_resched_lock(&mapping->i_mmap_lock);
+ cond_resched();
max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK;
if (max_nl_cursor == 0)
}
vma->vm_private_data = (void *) max_nl_cursor;
}
- cond_resched_lock(&mapping->i_mmap_lock);
+ cond_resched();
max_nl_cursor += CLUSTER_SIZE;
} while (max_nl_cursor <= max_nl_size);
list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
vma->vm_private_data = NULL;
out:
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
return ret;
}
return try_to_unmap_file(page, TTU_MUNLOCK);
}
-#if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION)
-/*
- * Drop an anon_vma refcount, freeing the anon_vma and anon_vma->root
- * if necessary. Be careful to do all the tests under the lock. Once
- * we know we are the last user, nobody else can get a reference and we
- * can do the freeing without the lock.
- */
-void drop_anon_vma(struct anon_vma *anon_vma)
+void __put_anon_vma(struct anon_vma *anon_vma)
{
- BUG_ON(atomic_read(&anon_vma->external_refcount) <= 0);
- if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->root->lock)) {
- struct anon_vma *root = anon_vma->root;
- int empty = list_empty(&anon_vma->head);
- int last_root_user = 0;
- int root_empty = 0;
+ struct anon_vma *root = anon_vma->root;
- /*
- * The refcount on a non-root anon_vma got dropped. Drop
- * the refcount on the root and check if we need to free it.
- */
- if (empty && anon_vma != root) {
- BUG_ON(atomic_read(&root->external_refcount) <= 0);
- last_root_user = atomic_dec_and_test(&root->external_refcount);
- root_empty = list_empty(&root->head);
- }
- anon_vma_unlock(anon_vma);
+ if (root != anon_vma && atomic_dec_and_test(&root->refcount))
+ anon_vma_free(root);
- if (empty) {
- anon_vma_free(anon_vma);
- if (root_empty && last_root_user)
- anon_vma_free(root);
- }
- }
+ anon_vma_free(anon_vma);
}
-#endif
#ifdef CONFIG_MIGRATION
/*
if (!mapping)
return ret;
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
unsigned long address = vma_address(page, vma);
if (address == -EFAULT)
* 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);
+ mutex_unlock(&mapping->i_mmap_mutex);
return ret;
}
BUG_ON(!PageLocked(page));
BUG_ON(!anon_vma);
- BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+ /* address might be in next vma when migration races vma_adjust */
first = atomic_inc_and_test(&page->_mapcount);
if (first)
__hugepage_set_anon_rmap(page, vma, address, 0);