mm: preemptibility -v3

Index: linux-2.6/arch/powerpc/mm/pgtable.c
===================================================================
@@ -93,7 +93,7 @@ static void pte_free_rcu_callback(struct
 static void pte_free_submit(struct pte_freelist_batch *batch)
 {
 	INIT_RCU_HEAD(&batch->rcu);
-	call_rcu(&batch->rcu, pte_free_rcu_callback);
+	call_rcu_sched(&batch->rcu, pte_free_rcu_callback);
 }
 
 void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)

Index: linux-2.6/mm/rmap.c
===================================================================
@@ -286,8 +286,22 @@ void __init anon_vma_init(void)
 }
 
 /*
- * 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).
+ *
+ * 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)
 {

Index: linux-2.6/include/linux/rmap.h
===================================================================
@@ -99,14 +99,14 @@ static inline struct anon_vma *page_anon
 	return page_rmapping(page);
 }
 
-static inline void anon_vma_lock(struct vm_area_struct *vma)
+static inline void vma_lock_anon_vma(struct vm_area_struct *vma)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 	if (anon_vma)
 		spin_lock(&anon_vma->lock);
 }
 
-static inline void anon_vma_unlock(struct vm_area_struct *vma)
+static inline void vma_unlock_anon_vma(struct vm_area_struct *vma)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 	if (anon_vma)

Index: linux-2.6/mm/mmap.c
===================================================================
@@ -452,12 +452,12 @@ static void vma_link(struct mm_struct *m
 		spin_lock(&mapping->i_mmap_lock);
 		vma->vm_truncate_count = mapping->truncate_count;
 	}
-	anon_vma_lock(vma);
+	vma_lock_anon_vma(vma);
 
 	__vma_link(mm, vma, prev, rb_link, rb_parent);
 	__vma_link_file(vma);
 
-	anon_vma_unlock(vma);
+	vma_unlock_anon_vma(vma);
 	if (mapping)
 		spin_unlock(&mapping->i_mmap_lock);
 

@@ -1710,7 +1710,7 @@ int expand_upwards(struct vm_area_struct
 	 */
 	if (unlikely(anon_vma_prepare(vma)))
 		return -ENOMEM;
-	anon_vma_lock(vma);
+	vma_lock_anon_vma(vma);
 
 	/*
 	 * vma->vm_start/vm_end cannot change under us because the caller

@@ -1721,7 +1721,7 @@ int expand_upwards(struct vm_area_struct
 	if (address < PAGE_ALIGN(address+4))
 		address = PAGE_ALIGN(address+4);
 	else {
-		anon_vma_unlock(vma);
+		vma_unlock_anon_vma(vma);
 		return -ENOMEM;
 	}
 	error = 0;

@@ -1737,7 +1737,7 @@ int expand_upwards(struct vm_area_struct
 		if (!error)
 			vma->vm_end = address;
 	}
-	anon_vma_unlock(vma);
+	vma_unlock_anon_vma(vma);
 	return error;
 }
 #endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */

@@ -1762,7 +1762,7 @@ static int expand_downwards(struct vm_ar
 	if (error)
 		return error;
 
-	anon_vma_lock(vma);
+	vma_lock_anon_vma(vma);
 
 	/*
 	 * vma->vm_start/vm_end cannot change under us because the caller

Index: linux-2.6/mm/mmap.c
===================================================================
@@ -1783,7 +1783,7 @@ static int expand_downwards(struct vm_ar
 			vma->vm_pgoff -= grow;
 		}
 	}
-	anon_vma_unlock(vma);
+	vma_unlock_anon_vma(vma);
 	return error;
 }
 

Index: linux-2.6/include/linux/rmap.h
===================================================================
@@ -113,6 +113,16 @@ static inline void vma_unlock_anon_vma(s
 		spin_unlock(&anon_vma->lock);
 }
 
+static inline void anon_vma_lock(struct anon_vma *anon_vma)
+{
+	spin_lock(&anon_vma->lock);
+}
+
+static inline void anon_vma_unlock(struct anon_vma *anon_vma)
+{
+	spin_unlock(&anon_vma->lock);
+}
+
 /*
  * anon_vma helper functions.
  */

Index: linux-2.6/mm/ksm.c
===================================================================
@@ -327,7 +327,7 @@ static void drop_anon_vma(struct rmap_it
 
 	if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->lock)) {
 		int empty = list_empty(&anon_vma->head);
-		spin_unlock(&anon_vma->lock);
+		anon_vma_unlock(anon_vma);
 		if (empty)
 			anon_vma_free(anon_vma);
 	}

@@ -1566,7 +1566,7 @@ again:
 		struct anon_vma_chain *vmac;
 		struct vm_area_struct *vma;
 
-		spin_lock(&anon_vma->lock);
+		anon_vma_lock(anon_vma);
 		list_for_each_entry(vmac, &anon_vma->head, same_anon_vma) {
 			vma = vmac->vma;
 			if (rmap_item->address < vma->vm_start ||

@@ -1589,7 +1589,7 @@ again:
 			if (!search_new_forks || !mapcount)
 				break;
 		}
-		spin_unlock(&anon_vma->lock);
+		anon_vma_unlock(anon_vma);
 		if (!mapcount)
 			goto out;
 	}

@@ -1619,7 +1619,7 @@ again:
 		struct anon_vma_chain *vmac;
 		struct vm_area_struct *vma;
 
-		spin_lock(&anon_vma->lock);
+		anon_vma_lock(anon_vma);
 		list_for_each_entry(vmac, &anon_vma->head, same_anon_vma) {
 			vma = vmac->vma;
 			if (rmap_item->address < vma->vm_start ||

@@ -1637,11 +1637,11 @@ again:
 			ret = try_to_unmap_one(page, vma,
 					rmap_item->address, flags);
 			if (ret != SWAP_AGAIN || !page_mapped(page)) {
-				spin_unlock(&anon_vma->lock);
+				anon_vma_unlock(anon_vma);
 				goto out;
 			}
 		}
-		spin_unlock(&anon_vma->lock);
+		anon_vma_unlock(anon_vma);
 	}
 	if (!search_new_forks++)
 		goto again;

@@ -1671,7 +1671,7 @@ again:
 		struct anon_vma_chain *vmac;
 		struct vm_area_struct *vma;
 
-		spin_lock(&anon_vma->lock);
+		anon_vma_lock(anon_vma);
 		list_for_each_entry(vmac, &anon_vma->head, same_anon_vma) {
 			vma = vmac->vma;
 			if (rmap_item->address < vma->vm_start ||

@@ -1688,11 +1688,11 @@ again:
 
 			ret = rmap_one(page, vma, rmap_item->address, arg);
 			if (ret != SWAP_AGAIN) {
-				spin_unlock(&anon_vma->lock);
+				anon_vma_unlock(anon_vma);
 				goto out;
 			}
 		}
-		spin_unlock(&anon_vma->lock);
+		anon_vma_unlock(anon_vma);
 	}
 	if (!search_new_forks++)
 		goto again;

Index: linux-2.6/mm/mmap.c
===================================================================
@@ -2589,7 +2589,7 @@ static void vm_unlock_anon_vma(struct an
 		if (!__test_and_clear_bit(0, (unsigned long *)
 					  &anon_vma->head.next))
 			BUG();
-		spin_unlock(&anon_vma->lock);
+		anon_vma_unlock(anon_vma);
 	}
 }
 

Index: linux-2.6/mm/rmap.c
===================================================================
@@ -134,7 +134,7 @@ int anon_vma_prepare(struct vm_area_stru
 			allocated = anon_vma;
 		}
 
-		spin_lock(&anon_vma->lock);
+		anon_vma_lock(anon_vma);
 		/* page_table_lock to protect against threads */
 		spin_lock(&mm->page_table_lock);
 		if (likely(!vma->anon_vma)) {

@@ -147,7 +147,7 @@ int anon_vma_prepare(struct vm_area_stru
 			avc = NULL;
 		}
 		spin_unlock(&mm->page_table_lock);
-		spin_unlock(&anon_vma->lock);
+		anon_vma_unlock(anon_vma);
 
 		if (unlikely(allocated))
 			anon_vma_free(allocated);

@@ -170,9 +170,9 @@ static void anon_vma_chain_link(struct v
 	avc->anon_vma = anon_vma;
 	list_add(&avc->same_vma, &vma->anon_vma_chain);
 
-	spin_lock(&anon_vma->lock);
+	anon_vma_lock(anon_vma);
 	list_add_tail(&avc->same_anon_vma, &anon_vma->head);
-	spin_unlock(&anon_vma->lock);
+	anon_vma_unlock(anon_vma);
 }
 
 /*

@@ -246,12 +246,12 @@ static void anon_vma_unlink(struct anon_
 	if (!anon_vma)
 		return;
 
-	spin_lock(&anon_vma->lock);
+	anon_vma_lock(anon_vma);
 	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) && !anonvma_external_refcount(anon_vma);
-	spin_unlock(&anon_vma->lock);
+	anon_vma_unlock(anon_vma);
 
 	if (empty)
 		anon_vma_free(anon_vma);

@@ -302,7 +302,7 @@ struct anon_vma *page_lock_anon_vma(stru
 		goto out;
 
 	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
-	spin_lock(&anon_vma->lock);
+	anon_vma_lock(anon_vma);
 	return anon_vma;
 out:
 	rcu_read_unlock();

@@ -311,7 +311,7 @@ out:
 
 void page_unlock_anon_vma(struct anon_vma *anon_vma)
 {
-	spin_unlock(&anon_vma->lock);
+	anon_vma_unlock(anon_vma);
 	rcu_read_unlock();
 }
 

@@ -1389,7 +1389,7 @@ static int rmap_walk_anon(struct page *p
 	anon_vma = page_anon_vma(page);
 	if (!anon_vma)
 		return ret;
-	spin_lock(&anon_vma->lock);
+	anon_vma_lock(anon_vma);
 	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);

@@ -1399,7 +1399,7 @@ static int rmap_walk_anon(struct page *p
 		if (ret != SWAP_AGAIN)
 			break;
 	}
-	spin_unlock(&anon_vma->lock);
+	anon_vma_unlock(anon_vma);
 	return ret;
 }
 

Index: linux-2.6/mm/migrate.c
===================================================================
@@ -684,7 +684,7 @@ rcu_unlock:
 	/* Drop an anon_vma reference if we took one */
 	if (anon_vma && atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->lock)) {
 		int empty = list_empty(&anon_vma->head);
-		spin_unlock(&anon_vma->lock);
+		anon_vma_unlock(anon_vma);
 		if (empty)
 			anon_vma_free(anon_vma);
 	}

Index: linux-2.6/include/linux/rmap.h
===================================================================
@@ -26,6 +26,7 @@
  */
 struct anon_vma {
 	spinlock_t lock;	/* Serialize access to vma list */
+	struct anon_vma *root;	/* Root of this anon_vma tree */
 #if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION)
 
 	/*

Index: linux-2.6/mm/rmap.c
===================================================================
@@ -132,6 +132,11 @@ int anon_vma_prepare(struct vm_area_stru
 			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);

@@ -224,9 +229,15 @@ int anon_vma_fork(struct vm_area_struct 
 	avc = anon_vma_chain_alloc();
 	if (!avc)
 		goto out_error_free_anon_vma;
-	anon_vma_chain_link(vma, avc, anon_vma);
+
+	/*
+	 * The root anon_vm's spinlock is the lock actually used when we
+	 * lock any of the anon_vmas in this anon_vma tree.
+	 */
+	anon_vma->root = pvma->anon_vma->root;
 	/* Mark this anon_vma as the one where our new (COWed) pages go. */
 	vma->anon_vma = anon_vma;
+	anon_vma_chain_link(vma, avc, anon_vma);
 
 	return 0;
 

@@ -261,7 +272,10 @@ void unlink_anon_vmas(struct vm_area_str
 {
 	struct anon_vma_chain *avc, *next;
 
-	/* Unlink each anon_vma chained to the VMA. */
+	/*
+	 * 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) {
 		anon_vma_unlink(avc);
 		list_del(&avc->same_vma);

Index: linux-2.6/include/linux/rmap.h
===================================================================
@@ -104,24 +104,24 @@ static inline void vma_lock_anon_vma(str
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 	if (anon_vma)
-		spin_lock(&anon_vma->lock);
+		spin_lock(&anon_vma->root->lock);
 }
 
 static inline void vma_unlock_anon_vma(struct vm_area_struct *vma)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 	if (anon_vma)
-		spin_unlock(&anon_vma->lock);
+		spin_unlock(&anon_vma->root->lock);
 }
 
 static inline void anon_vma_lock(struct anon_vma *anon_vma)
 {
-	spin_lock(&anon_vma->lock);
+	spin_lock(&anon_vma->root->lock);
 }
 
 static inline void anon_vma_unlock(struct anon_vma *anon_vma)
 {
-	spin_unlock(&anon_vma->lock);
+	spin_unlock(&anon_vma->root->lock);
 }
 
 /*

Index: linux-2.6/mm/ksm.c
===================================================================
@@ -325,7 +325,7 @@ static void drop_anon_vma(struct rmap_it
 {
 	struct anon_vma *anon_vma = rmap_item->anon_vma;
 
-	if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->lock)) {
+	if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->root->lock)) {
 		int empty = list_empty(&anon_vma->head);
 		anon_vma_unlock(anon_vma);
 		if (empty)

Index: linux-2.6/mm/mmap.c
===================================================================
@@ -506,6 +506,7 @@ int vma_adjust(struct vm_area_struct *vm
 	struct vm_area_struct *importer = NULL;
 	struct address_space *mapping = NULL;
 	struct prio_tree_root *root = NULL;
+	struct anon_vma *anon_vma = NULL;
 	struct file *file = vma->vm_file;
 	long adjust_next = 0;
 	int remove_next = 0;

@@ -578,6 +579,17 @@ again:			remove_next = 1 + (end > next->
 		}
 	}
 
+	/*
+	 * When changing only vma->vm_end, we don't really need anon_vma
+	 * lock. This is a fairly rare case by itself, but the anon_vma
+	 * lock may be shared between many sibling processes.  Skipping
+	 * the lock for brk adjustments makes a difference sometimes.
+	 */
+	if (vma->anon_vma && (insert || importer || start != vma->vm_start)) {
+		anon_vma = vma->anon_vma;
+		anon_vma_lock(anon_vma);
+	}
+
 	if (root) {
 		flush_dcache_mmap_lock(mapping);
 		vma_prio_tree_remove(vma, root);

@@ -617,6 +629,8 @@ again:			remove_next = 1 + (end > next->
 		__insert_vm_struct(mm, insert);
 	}
 
+	if (anon_vma)
+		anon_vma_unlock(anon_vma);
 	if (mapping)
 		spin_unlock(&mapping->i_mmap_lock);
 

@@ -2466,23 +2480,23 @@ static DEFINE_MUTEX(mm_all_locks_mutex);
 
 static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
 {
-	if (!test_bit(0, (unsigned long *) &anon_vma->head.next)) {
+	if (!test_bit(0, (unsigned long *) &anon_vma->root->head.next)) {
 		/*
 		 * The LSB of head.next can't change from under us
 		 * because we hold the mm_all_locks_mutex.
 		 */
-		spin_lock_nest_lock(&anon_vma->lock, &mm->mmap_sem);
+		spin_lock_nest_lock(&anon_vma->root->lock, &mm->mmap_sem);
 		/*
 		 * We can safely modify head.next after taking the
-		 * anon_vma->lock. If some other vma in this mm shares
+		 * anon_vma->root->lock. If some other vma in this mm shares
 		 * the same anon_vma we won't take it again.
 		 *
 		 * No need of atomic instructions here, head.next
 		 * can't change from under us thanks to the
-		 * anon_vma->lock.
+		 * anon_vma->root->lock.
 		 */
 		if (__test_and_set_bit(0, (unsigned long *)
-				       &anon_vma->head.next))
+				       &anon_vma->root->head.next))
 			BUG();
 	}
 }

@@ -2573,7 +2587,7 @@ out_unlock:
 
 static void vm_unlock_anon_vma(struct anon_vma *anon_vma)
 {
-	if (test_bit(0, (unsigned long *) &anon_vma->head.next)) {
+	if (test_bit(0, (unsigned long *) &anon_vma->root->head.next)) {
 		/*
 		 * The LSB of head.next can't change to 0 from under
 		 * us because we hold the mm_all_locks_mutex.

@@ -2584,10 +2598,10 @@ static void vm_unlock_anon_vma(struct an
 		 *
 		 * No need of atomic instructions here, head.next
 		 * can't change from under us until we release the
-		 * anon_vma->lock.
+		 * anon_vma->root->lock.
 		 */
 		if (!__test_and_clear_bit(0, (unsigned long *)
-					  &anon_vma->head.next))
+					  &anon_vma->root->head.next))
 			BUG();
 		anon_vma_unlock(anon_vma);
 	}

Index: linux-2.6/mm/migrate.c
===================================================================
@@ -682,7 +682,7 @@ skip_unmap:
 rcu_unlock:
 
 	/* Drop an anon_vma reference if we took one */
-	if (anon_vma && atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->lock)) {
+	if (anon_vma && atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->root->lock)) {
 		int empty = list_empty(&anon_vma->head);
 		anon_vma_unlock(anon_vma);
 		if (empty)

Index: linux-2.6/include/linux/rmap.h
===================================================================
@@ -81,6 +81,13 @@ static inline int anonvma_external_refco
 {
 	return atomic_read(&anon_vma->external_refcount);
 }
+
+static inline void get_anon_vma(struct anon_vma *anon_vma)
+{
+	atomic_inc(&anon_vma->external_refcount);
+}
+
+void drop_anon_vma(struct anon_vma *);
 #else
 static inline void anonvma_external_refcount_init(struct anon_vma *anon_vma)
 {

@@ -90,6 +97,14 @@ static inline int anonvma_external_refco
 {
 	return 0;
 }
+
+static inline void get_anon_vma(struct anon_vma *anon_vma)
+{
+}
+
+static inline void drop_anon_vma(struct anon_vma *anon_vma)
+{
+}
 #endif /* CONFIG_KSM */
 
 static inline struct anon_vma *page_anon_vma(struct page *page)

Index: linux-2.6/mm/ksm.c
===================================================================
@@ -318,19 +318,14 @@ static void hold_anon_vma(struct rmap_it
 			  struct anon_vma *anon_vma)
 {
 	rmap_item->anon_vma = anon_vma;
-	atomic_inc(&anon_vma->external_refcount);
+	get_anon_vma(anon_vma);
 }
 
-static void drop_anon_vma(struct rmap_item *rmap_item)
+static void ksm_drop_anon_vma(struct rmap_item *rmap_item)
 {
 	struct anon_vma *anon_vma = rmap_item->anon_vma;
 
-	if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->root->lock)) {
-		int empty = list_empty(&anon_vma->head);
-		anon_vma_unlock(anon_vma);
-		if (empty)
-			anon_vma_free(anon_vma);
-	}
+	drop_anon_vma(anon_vma);
 }
 
 /*

@@ -415,7 +410,7 @@ static void break_cow(struct rmap_item *
 	 * It is not an accident that whenever we want to break COW
 	 * to undo, we also need to drop a reference to the anon_vma.
 	 */
-	drop_anon_vma(rmap_item);
+	ksm_drop_anon_vma(rmap_item);
 
 	down_read(&mm->mmap_sem);
 	if (ksm_test_exit(mm))

@@ -470,7 +465,7 @@ static void remove_node_from_stable_tree
 			ksm_pages_sharing--;
 		else
 			ksm_pages_shared--;
-		drop_anon_vma(rmap_item);
+		ksm_drop_anon_vma(rmap_item);
 		rmap_item->address &= PAGE_MASK;
 		cond_resched();
 	}

@@ -558,7 +553,7 @@ static void remove_rmap_item_from_tree(s
 		else
 			ksm_pages_shared--;
 
-		drop_anon_vma(rmap_item);
+		ksm_drop_anon_vma(rmap_item);
 		rmap_item->address &= PAGE_MASK;
 
 	} else if (rmap_item->address & UNSTABLE_FLAG) {

64 lines not on this page · raw message

Index: linux-2.6/mm/migrate.c
===================================================================
@@ -639,7 +639,7 @@ static int unmap_and_move(new_page_t get
 			 * exist when the page is remapped later
 			 */
 			anon_vma = page_anon_vma(page);
-			atomic_inc(&anon_vma->external_refcount);
+			get_anon_vma(anon_vma);
 		}
 	}
 

@@ -682,12 +682,8 @@ skip_unmap:
 rcu_unlock:
 
 	/* Drop an anon_vma reference if we took one */
-	if (anon_vma && atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->root->lock)) {
-		int empty = list_empty(&anon_vma->head);
-		anon_vma_unlock(anon_vma);
-		if (empty)
-			anon_vma_free(anon_vma);
-	}
+	if (anon_vma)
+		drop_anon_vma(anon_vma);
 
 	if (rcu_locked)
 		rcu_read_unlock();

Index: linux-2.6/include/linux/rmap.h
===================================================================
@@ -87,7 +87,7 @@ static inline void get_anon_vma(struct a
 	atomic_inc(&anon_vma->external_refcount);
 }
 
-void drop_anon_vma(struct anon_vma *);
+void put_anon_vma(struct anon_vma *);
 #else
 static inline void anonvma_external_refcount_init(struct anon_vma *anon_vma)
 {

@@ -102,7 +102,7 @@ static inline void get_anon_vma(struct a
 {
 }
 
-static inline void drop_anon_vma(struct anon_vma *anon_vma)
+static inline void put_anon_vma(struct anon_vma *anon_vma)
 {
 }
 #endif /* CONFIG_KSM */

Index: linux-2.6/mm/ksm.c
===================================================================
@@ -321,11 +321,11 @@ static void hold_anon_vma(struct rmap_it
 	get_anon_vma(anon_vma);
 }
 
-static void ksm_drop_anon_vma(struct rmap_item *rmap_item)
+static void ksm_put_anon_vma(struct rmap_item *rmap_item)
 {
 	struct anon_vma *anon_vma = rmap_item->anon_vma;
 
-	drop_anon_vma(anon_vma);
+	put_anon_vma(anon_vma);
 }
 
 /*

@@ -410,7 +410,7 @@ static void break_cow(struct rmap_item *
 	 * It is not an accident that whenever we want to break COW
 	 * to undo, we also need to drop a reference to the anon_vma.
 	 */
-	ksm_drop_anon_vma(rmap_item);
+	ksm_put_anon_vma(rmap_item);
 
 	down_read(&mm->mmap_sem);
 	if (ksm_test_exit(mm))

@@ -465,7 +465,7 @@ static void remove_node_from_stable_tree
 			ksm_pages_sharing--;
 		else
 			ksm_pages_shared--;
-		ksm_drop_anon_vma(rmap_item);
+		ksm_put_anon_vma(rmap_item);
 		rmap_item->address &= PAGE_MASK;
 		cond_resched();
 	}

@@ -553,7 +553,7 @@ static void remove_rmap_item_from_tree(s
 		else
 			ksm_pages_shared--;
 
-		ksm_drop_anon_vma(rmap_item);
+		ksm_put_anon_vma(rmap_item);
 		rmap_item->address &= PAGE_MASK;
 
 	} else if (rmap_item->address & UNSTABLE_FLAG) {

Index: linux-2.6/mm/migrate.c
===================================================================
@@ -683,7 +683,7 @@ rcu_unlock:
 
 	/* Drop an anon_vma reference if we took one */
 	if (anon_vma)
-		drop_anon_vma(anon_vma);
+		put_anon_vma(anon_vma);
 
 	if (rcu_locked)
 		rcu_read_unlock();

Index: linux-2.6/mm/rmap.c
===================================================================
@@ -272,7 +272,7 @@ static void anon_vma_unlink(struct anon_
 
 	if (empty) {
 		/* We no longer need the root anon_vma */
-		drop_anon_vma(anon_vma->root);
+		put_anon_vma(anon_vma->root);
 		anon_vma_free(anon_vma);
 	}
 }

@@ -1398,7 +1398,7 @@ int try_to_munlock(struct page *page)
  * 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)
 {
 	if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->root->lock)) {
 		struct anon_vma *root = anon_vma->root;

Index: linux-2.6/include/linux/rmap.h
===================================================================
@@ -27,18 +27,15 @@
 struct anon_vma {
 	spinlock_t lock;	/* Serialize access to vma list */
 	struct anon_vma *root;	/* Root of this anon_vma tree */
-#if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION)
-
 	/*
-	 * The external_refcount is taken by either KSM or page migration
-	 * to take a reference to an anon_vma when there is no
+	 * The refcount is taken on an anon_vma when there is no
 	 * guarantee that the vma of page tables will exist for
 	 * the duration of the operation. A caller that takes
 	 * the reference is responsible for clearing up the
 	 * anon_vma if they are the last user on release
 	 */
-	atomic_t external_refcount;
-#endif
+	atomic_t refcount;
+
 	/*
 	 * NOTE: the LSB of the head.next is set by
 	 * mm_take_all_locks() _after_ taking the above lock. So the

@@ -71,41 +68,12 @@ struct anon_vma_chain {
 };
 
 #ifdef CONFIG_MMU
-#if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION)
-static inline void anonvma_external_refcount_init(struct anon_vma *anon_vma)
-{
-	atomic_set(&anon_vma->external_refcount, 0);
-}
-
-static inline int anonvma_external_refcount(struct anon_vma *anon_vma)
-{
-	return atomic_read(&anon_vma->external_refcount);
-}
-
 static inline void get_anon_vma(struct anon_vma *anon_vma)
 {
-	atomic_inc(&anon_vma->external_refcount);
+	atomic_inc(&anon_vma->refcount);
 }
 
 void put_anon_vma(struct anon_vma *);
-#else
-static inline void anonvma_external_refcount_init(struct anon_vma *anon_vma)
-{
-}
-
-static inline int anonvma_external_refcount(struct anon_vma *anon_vma)
-{
-	return 0;
-}
-
-static inline void get_anon_vma(struct anon_vma *anon_vma)
-{
-}
-
-static inline void put_anon_vma(struct anon_vma *anon_vma)
-{
-}
-#endif /* CONFIG_KSM */
 
 static inline struct anon_vma *page_anon_vma(struct page *page)
 {

Index: linux-2.6/mm/rmap.c
===================================================================
@@ -267,7 +267,7 @@ static void anon_vma_unlink(struct anon_
 	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) && !anonvma_external_refcount(anon_vma);
+	empty = list_empty(&anon_vma->head) && !atomic_read(&anon_vma->refcount);
 	anon_vma_unlock(anon_vma);
 
 	if (empty) {

@@ -297,7 +297,7 @@ static void anon_vma_ctor(void *data)
 	struct anon_vma *anon_vma = data;
 
 	spin_lock_init(&anon_vma->lock);
-	anonvma_external_refcount_init(anon_vma);
+	atomic_set(&anon_vma->refcount, 0);
 	INIT_LIST_HEAD(&anon_vma->head);
 }
 

@@ -1391,7 +1391,6 @@ int try_to_munlock(struct page *page)
 		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

@@ -1400,7 +1399,7 @@ int try_to_munlock(struct page *page)
  */
 void put_anon_vma(struct anon_vma *anon_vma)
 {
-	if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->root->lock)) {
+	if (atomic_dec_and_lock(&anon_vma->refcount, &anon_vma->root->lock)) {
 		struct anon_vma *root = anon_vma->root;
 		int empty = list_empty(&anon_vma->head);
 		int last_root_user = 0;

@@ -1411,7 +1410,7 @@ void put_anon_vma(struct anon_vma *anon_
 		 * the refcount on the root and check if we need to free it.
 		 */
 		if (empty && anon_vma != root) {
-			last_root_user = atomic_dec_and_test(&root->external_refcount);
+			last_root_user = atomic_dec_and_test(&root->refcount);
 			root_empty = list_empty(&root->head);
 		}
 		anon_vma_unlock(anon_vma);

@@ -1423,7 +1422,6 @@ void put_anon_vma(struct anon_vma *anon_
 		}
 	}
 }
-#endif
 
 #ifdef CONFIG_MIGRATION
 /*

Index: linux-2.6/include/linux/rmap.h
===================================================================
@@ -73,7 +73,13 @@ static inline void get_anon_vma(struct a
 	atomic_inc(&anon_vma->refcount);
 }
 
-void put_anon_vma(struct anon_vma *);
+void __put_anon_vma(struct anon_vma *anon_vma);
+
+static inline void put_anon_vma(struct anon_vma *anon_vma)
+{
+	if (atomic_dec_and_test(&anon_vma->refcount))
+		__put_anon_vma(anon_vma);
+}
 
 static inline struct anon_vma *page_anon_vma(struct page *page)
 {

@@ -116,7 +122,6 @@ void unlink_anon_vmas(struct vm_area_str
 int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *);
 int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);
 void __anon_vma_link(struct vm_area_struct *);
-void anon_vma_free(struct anon_vma *);
 
 static inline void anon_vma_merge(struct vm_area_struct *vma,
 				  struct vm_area_struct *next)

@@ -125,6 +130,8 @@ static inline void anon_vma_merge(struct
 	unlink_anon_vmas(next);
 }
 
+struct anon_vma *page_get_anon_vma(struct page *page);
+
 /*
  * rmap interfaces called when adding or removing pte of page
  */

Index: linux-2.6/mm/ksm.c
===================================================================
@@ -323,9 +323,7 @@ static void hold_anon_vma(struct rmap_it
 
 static void ksm_put_anon_vma(struct rmap_item *rmap_item)
 {
-	struct anon_vma *anon_vma = rmap_item->anon_vma;
-
-	put_anon_vma(anon_vma);
+	put_anon_vma(rmap_item->anon_vma);
 }
 
 /*

156 lines not on this page · raw message

Index: linux-2.6/fs/exec.c
===================================================================
@@ -503,7 +503,7 @@ static int shift_arg_pages(struct vm_are
 	unsigned long length = old_end - old_start;
 	unsigned long new_start = old_start - shift;
 	unsigned long new_end = old_end - shift;
-	struct mmu_gather *tlb;
+	struct mmu_gather tlb;
 
 	BUG_ON(new_start > new_end);
 

@@ -529,12 +529,12 @@ static int shift_arg_pages(struct vm_are
 		return -ENOMEM;
 
 	lru_add_drain();
-	tlb = tlb_gather_mmu(mm, 0);
+	tlb_gather_mmu(&tlb, mm, 0);
 	if (new_end > old_start) {
 		/*
 		 * when the old and new regions overlap clear from new_end.
 		 */
-		free_pgd_range(tlb, new_end, old_end, new_end,
+		free_pgd_range(&tlb, new_end, old_end, new_end,
 			vma->vm_next ? vma->vm_next->vm_start : 0);
 	} else {
 		/*

@@ -543,10 +543,10 @@ static int shift_arg_pages(struct vm_are
 		 * have constraints on va-space that make this illegal (IA64) -
 		 * for the others its just a little faster.
 		 */
-		free_pgd_range(tlb, old_start, old_end, new_end,
+		free_pgd_range(&tlb, old_start, old_end, new_end,
 			vma->vm_next ? vma->vm_next->vm_start : 0);
 	}
-	tlb_finish_mmu(tlb, new_end, old_end);
+	tlb_finish_mmu(&tlb, new_end, old_end);
 
 	/*
 	 * Shrink the vma to just the new range.  Always succeeds.

97 lines not on this page · raw message

Index: linux-2.6/include/linux/mm.h
===================================================================
@@ -760,7 +760,7 @@ int zap_vma_ptes(struct vm_area_struct *
 		unsigned long size);
 unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size, struct zap_details *);
-unsigned long unmap_vmas(struct mmu_gather **tlb,
+unsigned long unmap_vmas(struct mmu_gather *tlb,
 		struct vm_area_struct *start_vma, unsigned long start_addr,
 		unsigned long end_addr, unsigned long *nr_accounted,
 		struct zap_details *);

Index: linux-2.6/mm/memory.c
===================================================================
@@ -1095,17 +1095,14 @@ static unsigned long unmap_page_range(st
  * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
  * drops the lock and schedules.
  */
-unsigned long unmap_vmas(struct mmu_gather **tlbp,
+unsigned long unmap_vmas(struct mmu_gather *tlb,
 		struct vm_area_struct *vma, unsigned long start_addr,
 		unsigned long end_addr, unsigned long *nr_accounted,
 		struct zap_details *details)
 {
 	long zap_work = ZAP_BLOCK_SIZE;
-	unsigned long tlb_start = 0;	/* For tlb_finish_mmu */
-	int tlb_start_valid = 0;
 	unsigned long start = start_addr;
 	spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
-	int fullmm = (*tlbp)->fullmm;
 	struct mm_struct *mm = vma->vm_mm;
 
 	mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);

@@ -1126,11 +1123,6 @@ unsigned long unmap_vmas(struct mmu_gath
 			untrack_pfn_vma(vma, 0, 0);
 
 		while (start != end) {
-			if (!tlb_start_valid) {
-				tlb_start = start;
-				tlb_start_valid = 1;
-			}
-
 			if (unlikely(is_vm_hugetlb_page(vma))) {
 				/*
 				 * It is undesirable to test vma->vm_file as it

@@ -1151,7 +1143,7 @@ unsigned long unmap_vmas(struct mmu_gath
 
 				start = end;
 			} else
-				start = unmap_page_range(*tlbp, vma,
+				start = unmap_page_range(tlb, vma,
 						start, end, &zap_work, details);
 
 			if (zap_work > 0) {

@@ -1159,19 +1151,13 @@ unsigned long unmap_vmas(struct mmu_gath
 				break;
 			}
 
-			tlb_finish_mmu(*tlbp, tlb_start, start);
-
 			if (need_resched() ||
 				(i_mmap_lock && spin_needbreak(i_mmap_lock))) {
-				if (i_mmap_lock) {
-					*tlbp = NULL;
+				if (i_mmap_lock)
 					goto out;
-				}
 				cond_resched();
 			}
 
-			*tlbp = tlb_gather_mmu(vma->vm_mm, fullmm);
-			tlb_start_valid = 0;
 			zap_work = ZAP_BLOCK_SIZE;
 		}
 	}

@@ -1191,16 +1177,15 @@ unsigned long zap_page_range(struct vm_a
 		unsigned long size, struct zap_details *details)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	struct mmu_gather *tlb;
+	struct mmu_gather tlb;
 	unsigned long end = address + size;
 	unsigned long nr_accounted = 0;
 
 	lru_add_drain();
-	tlb = tlb_gather_mmu(mm, 0);
+	tlb_gather_mmu(&tlb, mm, 0);
 	update_hiwater_rss(mm);
 	end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details);
-	if (tlb)
-		tlb_finish_mmu(tlb, address, end);
+	tlb_finish_mmu(&tlb, address, end);
 	return end;
 }
 

Index: linux-2.6/mm/mmap.c
===================================================================
@@ -1844,17 +1844,17 @@ static void unmap_region(struct mm_struc
 		unsigned long start, unsigned long end)
 {
 	struct vm_area_struct *next = prev? prev->vm_next: mm->mmap;
-	struct mmu_gather *tlb;
+	struct mmu_gather tlb;
 	unsigned long nr_accounted = 0;
 
 	lru_add_drain();
-	tlb = tlb_gather_mmu(mm, 0);
+	tlb_gather_mmu(&tlb, mm, 0);
 	update_hiwater_rss(mm);
 	unmap_vmas(&tlb, vma, start, end, &nr_accounted, NULL);
 	vm_unacct_memory(nr_accounted);
-	free_pgtables(tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS,
+	free_pgtables(&tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS,
 				 next? next->vm_start: 0);
-	tlb_finish_mmu(tlb, start, end);
+	tlb_finish_mmu(&tlb, start, end);
 }
 
 /*

@@ -2190,7 +2190,7 @@ EXPORT_SYMBOL(do_brk);
 /* Release all mmaps. */
 void exit_mmap(struct mm_struct *mm)
 {
-	struct mmu_gather *tlb;
+	struct mmu_gather tlb;
 	struct vm_area_struct *vma;
 	unsigned long nr_accounted = 0;
 	unsigned long end;

@@ -2215,14 +2215,14 @@ void exit_mmap(struct mm_struct *mm)
 
 	lru_add_drain();
 	flush_cache_mm(mm);
-	tlb = tlb_gather_mmu(mm, 1);
+	tlb_gather_mmu(&tlb, mm, 1);
 	/* update_hiwater_rss(mm) here? but nobody should be looking */
 	/* Use -1 here to ensure all VMAs in the mm are unmapped */
 	end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL);
 	vm_unacct_memory(nr_accounted);
 
-	free_pgtables(tlb, vma, FIRST_USER_ADDRESS, 0);
-	tlb_finish_mmu(tlb, 0, end);
+	free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0);
+	tlb_finish_mmu(&tlb, 0, end);
 
 	/*
 	 * Walk the list again, actually closing and freeing it,

Index: linux-2.6/arch/powerpc/include/asm/tlb.h
===================================================================
@@ -28,6 +28,16 @@
 #define tlb_start_vma(tlb, vma)	do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
 
+#define HAVE_ARCH_MMU_GATHER 1
+
+struct pte_freelist_batch;
+
+struct arch_mmu_gather {
+	struct pte_freelist_batch *batch;
+};
+
+#define ARCH_MMU_GATHER_INIT (struct arch_mmu_gather){ .batch = NULL, }
+
 extern void tlb_flush(struct mmu_gather *tlb);
 
 /* Get the generic bits... */

Index: linux-2.6/arch/powerpc/kernel/process.c
===================================================================
@@ -392,6 +392,9 @@ struct task_struct *__switch_to(struct t
 	struct thread_struct *new_thread, *old_thread;
 	unsigned long flags;
 	struct task_struct *last;
+#ifdef CONFIG_PPC64
+	struct ppc64_tlb_batch *batch;
+#endif
 
 #ifdef CONFIG_SMP
 	/* avoid complexity of lazy save/restore of fpu

@@ -482,6 +485,14 @@ struct task_struct *__switch_to(struct t
 		old_thread->accum_tb += (current_tb - start_tb);
 		new_thread->start_tb = current_tb;
 	}
+
+	batch = &__get_cpu_var(ppc64_tlb_batch);
+	if (batch->active) {
+		task_thread_info(prev)->local_flags |= _TLF_LAZY_MMU;
+		if (batch->index)
+			__flush_tlb_pending(batch);
+		batch->active = 0;
+	}
 #endif
 
 	local_irq_save(flags);

@@ -498,6 +509,14 @@ struct task_struct *__switch_to(struct t
 	hard_irq_disable();
 	last = _switch(old_thread, new_thread);
 
+#ifdef CONFIG_PPC64
+	if (task_thread_info(new)->local_flags & _TLF_LAZY_MMU) {
+		task_thread_info(new)->local_flags &= ~_TLF_LAZY_MMU;
+		batch = &__get_cpu_var(ppc64_tlb_batch);
+		batch->active = 1;
+	}
+#endif
+
 	local_irq_restore(flags);
 
 	return last;

Index: linux-2.6/arch/powerpc/mm/pgtable.c
===================================================================
@@ -33,8 +33,6 @@
 
 #include "mmu_decl.h"
 
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 #ifdef CONFIG_SMP
 
 /*

@@ -43,7 +41,6 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_ga
  * freeing a page table page that is being walked without locks
  */
 
-static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
 static unsigned long pte_freelist_forced_free;
 
 struct pte_freelist_batch

@@ -98,12 +95,10 @@ static void pte_free_submit(struct pte_f
 
 void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
 {
-	/* This is safe since tlb_gather_mmu has disabled preemption */
-	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
+	struct pte_freelist_batch **batchp = &tlb->arch.batch;
 	unsigned long pgf;
 
-	if (atomic_read(&tlb->mm->mm_users) < 2 ||
-	    cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))){
+	if (atomic_read(&tlb->mm->mm_users) < 2) {
 		pgtable_free(table, shift);
 		return;
 	}

@@ -125,10 +120,9 @@ void pgtable_free_tlb(struct mmu_gather 
 	}
 }
 
-void pte_free_finish(void)
+void pte_free_finish(struct mmu_gather *tlb)
 {
-	/* This is safe since tlb_gather_mmu has disabled preemption */
-	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
+	struct pte_freelist_batch **batchp = &tlb->arch.batch;
 
 	if (*batchp == NULL)
 		return;

Index: linux-2.6/arch/powerpc/mm/tlb_hash64.c
===================================================================
@@ -38,13 +38,11 @@ DEFINE_PER_CPU(struct ppc64_tlb_batch, p
  * neesd to be flushed. This function will either perform the flush
  * immediately or will batch it up if the current CPU has an active
  * batch on it.
- *
- * Must be called from within some kind of spinlock/non-preempt region...
  */
 void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, unsigned long pte, int huge)
 {
-	struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+	struct ppc64_tlb_batch *batch = &get_cpu_var(ppc64_tlb_batch);
 	unsigned long vsid, vaddr;
 	unsigned int psize;
 	int ssize;

@@ -99,6 +97,7 @@ void hpte_need_flush(struct mm_struct *m
 	 */
 	if (!batch->active) {
 		flush_hash_page(vaddr, rpte, psize, ssize, 0);
+		put_cpu_var(ppc64_tlb_batch);
 		return;
 	}
 

@@ -127,6 +126,7 @@ void hpte_need_flush(struct mm_struct *m
 	batch->index = ++i;
 	if (i >= PPC64_TLB_BATCH_NR)
 		__flush_tlb_pending(batch);
+	put_cpu_var(ppc64_tlb_batch);
 }
 
 /*

@@ -155,7 +155,7 @@ void __flush_tlb_pending(struct ppc64_tl
 
 void tlb_flush(struct mmu_gather *tlb)
 {
-	struct ppc64_tlb_batch *tlbbatch = &__get_cpu_var(ppc64_tlb_batch);
+	struct ppc64_tlb_batch *tlbbatch = &get_cpu_var(ppc64_tlb_batch);
 
 	/* If there's a TLB batch pending, then we must flush it because the
 	 * pages are going to be freed and we really don't want to have a CPU

@@ -164,8 +164,10 @@ void tlb_flush(struct mmu_gather *tlb)
 	if (tlbbatch->index)
 		__flush_tlb_pending(tlbbatch);
 
+	put_cpu_var(ppc64_tlb_batch);
+
 	/* Push out batch of freed page tables */
-	pte_free_finish();
+	pte_free_finish(tlb);
 }
 
 /**

Index: linux-2.6/arch/powerpc/include/asm/thread_info.h
===================================================================
@@ -139,10 +139,12 @@ static inline struct thread_info *curren
 #define TLF_NAPPING		0	/* idle thread enabled NAP mode */
 #define TLF_SLEEPING		1	/* suspend code enabled SLEEP mode */
 #define TLF_RESTORE_SIGMASK	2	/* Restore signal mask in do_signal */
+#define TLF_LAZY_MMU		3	/* tlb_batch is active */
 
 #define _TLF_NAPPING		(1 << TLF_NAPPING)
 #define _TLF_SLEEPING		(1 << TLF_SLEEPING)
 #define _TLF_RESTORE_SIGMASK	(1 << TLF_RESTORE_SIGMASK)
+#define _TLF_LAZY_MMU		(1 << TLF_LAZY_MMU)
 
 #ifndef __ASSEMBLY__
 #define HAVE_SET_RESTORE_SIGMASK	1

Index: linux-2.6/arch/powerpc/include/asm/pgalloc.h
===================================================================
@@ -32,13 +32,13 @@ static inline void pte_free(struct mm_st
 
 #ifdef CONFIG_SMP
 extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift);
-extern void pte_free_finish(void);
+extern void pte_free_finish(struct mmu_gather *tlb);
 #else /* CONFIG_SMP */
 static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
 {
 	pgtable_free(table, shift);
 }
-static inline void pte_free_finish(void) { }
+static inline void pte_free_finish(struct mmu_gather *tlb) { }
 #endif /* !CONFIG_SMP */
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,

Index: linux-2.6/arch/powerpc/mm/tlb_hash32.c
===================================================================
@@ -73,7 +73,7 @@ void tlb_flush(struct mmu_gather *tlb)
 	}
 
 	/* Push out batch of freed page tables */
-	pte_free_finish();
+	pte_free_finish(tlb);
 }
 
 /*

Index: linux-2.6/arch/powerpc/mm/tlb_nohash.c
===================================================================
@@ -298,7 +298,7 @@ void tlb_flush(struct mmu_gather *tlb)
 	flush_tlb_mm(tlb->mm);
 
 	/* Push out batch of freed page tables */
-	pte_free_finish();
+	pte_free_finish(tlb);
 }
 
 /*

Index: linux-2.6/arch/sparc/include/asm/pgalloc_64.h
===================================================================
@@ -78,4 +78,7 @@ static inline void check_pgt_cache(void)
 	quicklist_trim(0, NULL, 25, 16);
 }
 
+#define __pte_free_tlb(tlb, pte, addr)	pte_free((tlb)->mm, pte)
+#define __pmd_free_tlb(tlb, pmd, addr)	pmd_free((tlb)->mm, pmd)
+
 #endif /* _SPARC64_PGALLOC_H */

110 lines not on this page · raw message

Index: linux-2.6/arch/sparc/include/asm/tlbflush_64.h
===================================================================
@@ -5,9 +5,17 @@
 #include <asm/mmu_context.h>
 
 /* TSB flush operations. */
-struct mmu_gather;
+
+#define TLB_BATCH_NR	192
+
+struct tlb_batch {
+	struct mm_struct *mm;
+	unsigned long tlb_nr;
+	unsigned long vaddrs[TLB_BATCH_NR];
+};
+
 extern void flush_tsb_kernel_range(unsigned long start, unsigned long end);
-extern void flush_tsb_user(struct mmu_gather *mp);
+extern void flush_tsb_user(struct tlb_batch *tb);
 
 /* TLB flush operations. */
 

78 lines not on this page · raw message

Index: linux-2.6/arch/sparc/mm/tsb.c
===================================================================
@@ -47,12 +47,13 @@ void flush_tsb_kernel_range(unsigned lon
 	}
 }
 
-static void __flush_tsb_one(struct mmu_gather *mp, unsigned long hash_shift, unsigned long tsb, unsigned long nentries)
+static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
+			    unsigned long tsb, unsigned long nentries)
 {
 	unsigned long i;
 
-	for (i = 0; i < mp->tlb_nr; i++) {
-		unsigned long v = mp->vaddrs[i];
+	for (i = 0; i < tb->tlb_nr; i++) {
+		unsigned long v = tb->vaddrs[i];
 		unsigned long tag, ent, hash;
 
 		v &= ~0x1UL;

@@ -65,9 +66,9 @@ static void __flush_tsb_one(struct mmu_g
 	}
 }
 
-void flush_tsb_user(struct mmu_gather *mp)
+void flush_tsb_user(struct tlb_batch *tb)
 {
-	struct mm_struct *mm = mp->mm;
+	struct mm_struct *mm = tb->mm;
 	unsigned long nentries, base, flags;
 
 	spin_lock_irqsave(&mm->context.lock, flags);

@@ -76,7 +77,7 @@ void flush_tsb_user(struct mmu_gather *m
 	nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
 	if (tlb_type == cheetah_plus || tlb_type == hypervisor)
 		base = __pa(base);
-	__flush_tsb_one(mp, PAGE_SHIFT, base, nentries);
+	__flush_tsb_one(tb, PAGE_SHIFT, base, nentries);
 
 #ifdef CONFIG_HUGETLB_PAGE
 	if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {

@@ -84,7 +85,7 @@ void flush_tsb_user(struct mmu_gather *m
 		nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
 		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
 			base = __pa(base);
-		__flush_tsb_one(mp, HPAGE_SHIFT, base, nentries);
+		__flush_tsb_one(tb, HPAGE_SHIFT, base, nentries);
 	}
 #endif
 	spin_unlock_irqrestore(&mm->context.lock, flags);

Index: linux-2.6/arch/s390/include/asm/tlb.h
===================================================================
@@ -28,45 +28,51 @@
 #include <asm/smp.h>
 #include <asm/tlbflush.h>
 
-#ifndef CONFIG_SMP
-#define TLB_NR_PTRS	1
-#else
-#define TLB_NR_PTRS	508
-#endif
-
 struct mmu_gather {
 	struct mm_struct *mm;
 	unsigned int fullmm;
 	unsigned int nr_ptes;
 	unsigned int nr_pxds;
-	void *array[TLB_NR_PTRS];
+	unsigned int max;
+	void **array;
+	void *local[8];
 };
 
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-static inline struct mmu_gather *tlb_gather_mmu(struct mm_struct *mm,
-						unsigned int full_mm_flush)
+static inline void __tlb_alloc_pages(struct mmu_gather *tlb)
 {
-	struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
+	unsigned long addr = __get_free_pages(GFP_ATOMIC, 0);
+
+	if (addr) {
+		tlb->array = (void *) addr;
+		tlb->max = PAGE_SIZE / sizeof(void *);
+	}
+}
 
+static inline void tlb_gather_mmu(struct mmu_gather *tlb,
+				  struct mm_struct *mm,
+				  unsigned int full_mm_flush)
+{
 	tlb->mm = mm;
+	tlb->max = ARRAY_SIZE(tlb->local);
+	tlb->array = tlb->local;
 	tlb->fullmm = full_mm_flush || (num_online_cpus() == 1) ||
 		(atomic_read(&mm->mm_users) <= 1 && mm == current->active_mm);
-	tlb->nr_ptes = 0;
-	tlb->nr_pxds = TLB_NR_PTRS;
 	if (tlb->fullmm)
 		__tlb_flush_mm(mm);
-	return tlb;
+	else
+		__tlb_alloc_pages(tlb);
+	tlb->nr_ptes = 0;
+	tlb->nr_pxds = tlb->max;
 }
 
 static inline void tlb_flush_mmu(struct mmu_gather *tlb,
 				 unsigned long start, unsigned long end)
 {
-	if (!tlb->fullmm && (tlb->nr_ptes > 0 || tlb->nr_pxds < TLB_NR_PTRS))
+	if (!tlb->fullmm && (tlb->nr_ptes > 0 || tlb->nr_pxds < tlb->max))
 		__tlb_flush_mm(tlb->mm);
 	while (tlb->nr_ptes > 0)
 		pte_free(tlb->mm, tlb->array[--tlb->nr_ptes]);
-	while (tlb->nr_pxds < TLB_NR_PTRS)
+	while (tlb->nr_pxds < tlb->max)
 		/* pgd_free frees the pointer as region or segment table */
 		pgd_free(tlb->mm, tlb->array[tlb->nr_pxds++]);
 }

@@ -79,7 +85,8 @@ static inline void tlb_finish_mmu(struct
 	/* keep the page table cache within bounds */
 	check_pgt_cache();
 
-	put_cpu_var(mmu_gathers);
+	if (tlb->array != tlb->local)
+		free_pages((unsigned long) tlb->array, 0);
 }
 
 /*

Index: linux-2.6/arch/arm/include/asm/tlb.h
===================================================================
@@ -40,17 +40,11 @@ struct mmu_gather {
 	unsigned long		range_end;
 };
 
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-static inline struct mmu_gather *
-tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
+static inline void
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
 {
-	struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
-
 	tlb->mm = mm;
 	tlb->fullmm = full_mm_flush;
-
-	return tlb;
 }
 
 static inline void

@@ -61,8 +55,6 @@ tlb_finish_mmu(struct mmu_gather *tlb, u
 
 	/* keep the page table cache within bounds */
 	check_pgt_cache();
-
-	put_cpu_var(mmu_gathers);
 }
 
 /*

Index: linux-2.6/arch/sh/include/asm/tlb.h
===================================================================
@@ -23,8 +23,6 @@ struct mmu_gather {
 	unsigned long		start, end;
 };
 
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 static inline void init_tlb_gather(struct mmu_gather *tlb)
 {
 	tlb->start = TASK_SIZE;

@@ -36,17 +34,13 @@ static inline void init_tlb_gather(struc
 	}
 }
 
-static inline struct mmu_gather *
-tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
+static inline void
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
 {
-	struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
-
 	tlb->mm = mm;
 	tlb->fullmm = full_mm_flush;
 
 	init_tlb_gather(tlb);
-
-	return tlb;
 }
 
 static inline void

@@ -57,8 +51,6 @@ tlb_finish_mmu(struct mmu_gather *tlb, u
 
 	/* keep the page table cache within bounds */
 	check_pgt_cache();
-
-	put_cpu_var(mmu_gathers);
 }
 
 static inline void

Index: linux-2.6/arch/um/include/asm/tlb.h
===================================================================
@@ -22,9 +22,6 @@ struct mmu_gather {
 	unsigned int		fullmm; /* non-zero means full mm flush */
 };
 
-/* Users of the generic TLB shootdown code must declare this storage space. */
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
 					  unsigned long address)
 {

@@ -47,20 +44,13 @@ static inline void init_tlb_gather(struc
 	}
 }
 
-/* tlb_gather_mmu
- *	Return a pointer to an initialized struct mmu_gather.
- */
-static inline struct mmu_gather *
-tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
+static inline void
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
 {
-	struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
-
 	tlb->mm = mm;
 	tlb->fullmm = full_mm_flush;
 
 	init_tlb_gather(tlb);
-
-	return tlb;
 }
 
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,

@@ -87,8 +77,6 @@ tlb_finish_mmu(struct mmu_gather *tlb, u
 
 	/* keep the page table cache within bounds */
 	check_pgt_cache();
-
-	put_cpu_var(mmu_gathers);
 }
 
 /* tlb_remove_page

Index: linux-2.6/arch/ia64/include/asm/tlb.h
===================================================================
@@ -47,21 +47,21 @@
 #include <asm/machvec.h>
 
 #ifdef CONFIG_SMP
-# define FREE_PTE_NR		2048
 # define tlb_fast_mode(tlb)	((tlb)->nr == ~0U)
 #else
-# define FREE_PTE_NR		0
 # define tlb_fast_mode(tlb)	(1)
 #endif
 
 struct mmu_gather {
 	struct mm_struct	*mm;
 	unsigned int		nr;		/* == ~0U => fast mode */
+	unsigned int		max;
 	unsigned char		fullmm;		/* non-zero means full mm flush */
 	unsigned char		need_flush;	/* really unmapped some PTEs? */
 	unsigned long		start_addr;
 	unsigned long		end_addr;
-	struct page 		*pages[FREE_PTE_NR];
+	struct page		**pages;
+	struct page		*local[8];
 };
 
 struct ia64_tr_entry {

@@ -90,9 +90,6 @@ extern struct ia64_tr_entry *ia64_idtrs[
 #define RR_RID_MASK	0x00000000ffffff00L
 #define RR_TO_RID(val) 	((val >> 8) & 0xffffff)
 
-/* Users of the generic TLB shootdown code must declare this storage space. */
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
 /*
  * Flush the TLB for address range START to END and, if not in fast mode, release the
  * freed pages that where gathered up to this point.

@@ -147,15 +144,25 @@ ia64_tlb_flush_mmu (struct mmu_gather *t
 	}
 }
 
-/*
- * Return a pointer to an initialized struct mmu_gather.
- */
-static inline struct mmu_gather *
-tlb_gather_mmu (struct mm_struct *mm, unsigned int full_mm_flush)
+static inline void __tlb_alloc_pages(struct mmu_gather *tlb)
+{
+	unsigned long addr = __get_free_pages(GFP_ATOMIC, 0);
+
+	if (addr) {
+		tlb->pages = (void *)addr;
+		tlb->max = PAGE_SIZE / sizeof(void *);
+	}
+}
+
+
+static inline void
+tlb_gather_mmu (struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
 {
 	struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
 
 	tlb->mm = mm;
+	tlb->max = ARRAY_SIZE(tlb->local);
+	tlb->pages = tlb->local;
 	/*
 	 * Use fast mode if only 1 CPU is online.
 	 *

@@ -191,7 +198,8 @@ tlb_finish_mmu (struct mmu_gather *tlb, 
 	/* keep the page table cache within bounds */
 	check_pgt_cache();
 
-	put_cpu_var(mmu_gathers);
+	if (tlb->pages != tlb->local)
+		free_pages((unsigned long)tlb->pages, 0);
 }
 
 /*

@@ -208,8 +216,12 @@ tlb_remove_page (struct mmu_gather *tlb,
 		free_page_and_swap_cache(page);
 		return;
 	}
+
+	if (!tlb->nr && tlb->pages == tlb->local)
+		__tlb_alloc_pages(tlb);
+
 	tlb->pages[tlb->nr++] = page;
-	if (tlb->nr >= FREE_PTE_NR)
+	if (tlb->nr >= tlb->max)
 		ia64_tlb_flush_mmu(tlb, tlb->start_addr, tlb->end_addr);
 }
 

Index: linux-2.6/arch/powerpc/include/asm/pgalloc.h
===================================================================
@@ -31,14 +31,31 @@ static inline void pte_free(struct mm_st
 #endif
 
 #ifdef CONFIG_SMP
-extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift);
-extern void pte_free_finish(struct mmu_gather *tlb);
+#define HAVE_ARCH_RCU_TABLE_FREE
+
+struct mmu_gather;
+extern void tlb_remove_table(struct mmu_gather *, void *);
+
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
+{
+	unsigned long pgf = (unsigned long)table;
+	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+	pgf |= shift;
+	tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+	unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+	pgtable_free(table, shift);
+}
 #else /* CONFIG_SMP */
 static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
 {
 	pgtable_free(table, shift);
 }
-static inline void pte_free_finish(struct mmu_gather *tlb) { }
 #endif /* !CONFIG_SMP */
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,

Index: linux-2.6/arch/powerpc/include/asm/tlb.h
===================================================================
@@ -28,16 +28,6 @@
 #define tlb_start_vma(tlb, vma)	do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
 
-#define HAVE_ARCH_MMU_GATHER 1
-
-struct pte_freelist_batch;
-
-struct arch_mmu_gather {
-	struct pte_freelist_batch *batch;
-};
-
-#define ARCH_MMU_GATHER_INIT (struct arch_mmu_gather){ .batch = NULL, }
-
 extern void tlb_flush(struct mmu_gather *tlb);
 
 /* Get the generic bits... */

105 lines not on this page · raw message

Index: linux-2.6/arch/powerpc/mm/tlb_hash32.c
===================================================================
@@ -71,9 +71,6 @@ void tlb_flush(struct mmu_gather *tlb)
 		 */
 		_tlbia();
 	}
-
-	/* Push out batch of freed page tables */
-	pte_free_finish(tlb);
 }
 
 /*

Index: linux-2.6/arch/powerpc/mm/tlb_hash64.c
===================================================================
@@ -165,9 +165,6 @@ void tlb_flush(struct mmu_gather *tlb)
 		__flush_tlb_pending(tlbbatch);
 
 	put_cpu_var(ppc64_tlb_batch);
-
-	/* Push out batch of freed page tables */
-	pte_free_finish(tlb);
 }
 
 /**

Index: linux-2.6/arch/powerpc/mm/tlb_nohash.c
===================================================================
@@ -296,9 +296,6 @@ EXPORT_SYMBOL(flush_tlb_range);
 void tlb_flush(struct mmu_gather *tlb)
 {
 	flush_tlb_mm(tlb->mm);
-
-	/* Push out batch of freed page tables */
-	pte_free_finish(tlb);
 }
 
 /*

83 lines not on this page · raw message

84 lines not on this page · raw message

Index: linux-2.6/arch/sparc/include/asm/pgalloc_64.h
===================================================================
@@ -5,7 +5,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
-#include <linux/quicklist.h>
 
 #include <asm/spitfire.h>
 #include <asm/cpudata.h>

@@ -14,69 +13,68 @@
 
 /* Page table allocation/freeing. */
 
+extern struct kmem_cache *pgtable_cache;
+
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return quicklist_alloc(0, GFP_KERNEL, NULL);
+	return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-	quicklist_free(0, NULL, pgd);
+	kmem_cache_free(pgtable_cache, pgd);
 }
 
 #define pud_populate(MM, PUD, PMD)	pud_set(PUD, PMD)
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return quicklist_alloc(0, GFP_KERNEL, NULL);
+	return kmem_cache_alloc(pgtable_cache,
+				GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-	quicklist_free(0, NULL, pmd);
+	kmem_cache_free(pgtable_cache, pmd);
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	return quicklist_alloc(0, GFP_KERNEL, NULL);
+	return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
 }
 
 static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 					unsigned long address)
 {
 	struct page *page;
-	void *pg;
+	pte_t *pte;
 
-	pg = quicklist_alloc(0, GFP_KERNEL, NULL);
-	if (!pg)
+	pte = pte_alloc_one_kernel(mm, address);
+	if (!pte)
 		return NULL;
-	page = virt_to_page(pg);
+	page = virt_to_page(pte);
 	pgtable_page_ctor(page);
 	return page;
 }
 
 static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
 {
-	quicklist_free(0, NULL, pte);
+	free_page((unsigned long)pte);
 }
 
 static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 {
 	pgtable_page_dtor(ptepage);
-	quicklist_free_page(0, NULL, ptepage);
+	__free_page(ptepage);
 }
 
-
 #define pmd_populate_kernel(MM, PMD, PTE)	pmd_set(PMD, PTE)
 #define pmd_populate(MM,PMD,PTE_PAGE)		\
 	pmd_populate_kernel(MM,PMD,page_address(PTE_PAGE))
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
-static inline void check_pgt_cache(void)
-{
-	quicklist_trim(0, NULL, 25, 16);
-}
+#define check_pgt_cache()	do { } while (0)
 
 #define __pte_free_tlb(tlb, pte, addr)	pte_free((tlb)->mm, pte)
 #define __pmd_free_tlb(tlb, pmd, addr)	pmd_free((tlb)->mm, pmd)

Index: linux-2.6/arch/sparc/mm/tsb.c
===================================================================
@@ -236,6 +236,8 @@ static void setup_tsb_params(struct mm_s
 	}
 }
 
+struct kmem_cache *pgtable_cache __read_mostly;
+
 static struct kmem_cache *tsb_caches[8] __read_mostly;
 
 static const char *tsb_cache_names[8] = {

@@ -253,6 +255,15 @@ void __init pgtable_cache_init(void)
 {
 	unsigned long i;
 
+	pgtable_cache = kmem_cache_create("pgtable_cache",
+					  PAGE_SIZE, PAGE_SIZE,
+					  0,
+					  _clear_page);
+	if (!pgtable_cache) {
+		prom_printf("pgtable_cache_init(): Could not create!\n");
+		prom_halt();
+	}
+
 	for (i = 0; i < 8; i++) {
 		unsigned long size = 8192 << i;
 		const char *name = tsb_cache_names[i];

Index: linux-2.6/arch/sparc/include/asm/pgalloc_64.h
===================================================================
@@ -76,7 +76,52 @@ static inline void pte_free(struct mm_st
 
 #define check_pgt_cache()	do { } while (0)
 
-#define __pte_free_tlb(tlb, pte, addr)	pte_free((tlb)->mm, pte)
-#define __pmd_free_tlb(tlb, pmd, addr)	pmd_free((tlb)->mm, pmd)
+static inline void pgtable_free(void *table, bool is_page)
+{
+	if (is_page)
+		free_page((unsigned long)table);
+	else
+		kmem_cache_free(pgtable_cache, table);
+}
+
+#ifdef CONFIG_SMP
+#define HAVE_ARCH_RCU_TABLE_FREE
+
+struct mmu_gather;
+extern void tlb_remove_table(struct mmu_gather *, void *);
+
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, bool is_page)
+{
+	unsigned long pgf = (unsigned long)table;
+	if (is_page)
+		pgf |= 0x1UL;
+	tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+	void *table = (void *)((unsigned long)_table & ~0x1UL);
+	bool is_page = false;
+
+	if ((unsigned long)_table & 0x1UL)
+		is_page = true;
+	pgtable_free(table, is_page);
+}
+#else /* CONFIG_SMP */
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, bool is_page)
+{
+	pgtable_free(table, is_page);
+}
+#endif /* !CONFIG_SMP */
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,
+				  unsigned long address)
+{
+	pgtable_page_dtor(ptepage);
+	pgtable_free_tlb(tlb, page_address(ptepage), true);
+}
+
+#define __pmd_free_tlb(tlb, pmd, addr)		      \
+	pgtable_free_tlb(tlb, pmd, false)
 
 #endif /* _SPARC64_PGALLOC_H */

Index: linux-2.6/arch/sparc/include/asm/pgtable_64.h
===================================================================
@@ -95,6 +95,10 @@
 /* PTE bits which are the same in SUN4U and SUN4V format.  */
 #define _PAGE_VALID	  _AC(0x8000000000000000,UL) /* Valid TTE            */
 #define _PAGE_R	  	  _AC(0x8000000000000000,UL) /* Keep ref bit uptodate*/
+#define _PAGE_SPECIAL     _AC(0x0200000000000000,UL) /* Special page         */
+
+/* Advertise support for _PAGE_SPECIAL */
+#define __HAVE_ARCH_PTE_SPECIAL
 
 /* SUN4U pte bits... */
 #define _PAGE_SZ4MB_4U	  _AC(0x6000000000000000,UL) /* 4MB Page             */

@@ -104,6 +108,7 @@
 #define _PAGE_NFO_4U	  _AC(0x1000000000000000,UL) /* No Fault Only        */
 #define _PAGE_IE_4U	  _AC(0x0800000000000000,UL) /* Invert Endianness    */
 #define _PAGE_SOFT2_4U	  _AC(0x07FC000000000000,UL) /* Software bits, set 2 */
+#define _PAGE_SPECIAL_4U  _AC(0x0200000000000000,UL) /* Special page         */
 #define _PAGE_RES1_4U	  _AC(0x0002000000000000,UL) /* Reserved             */
 #define _PAGE_SZ32MB_4U	  _AC(0x0001000000000000,UL) /* (Panther) 32MB page  */
 #define _PAGE_SZ256MB_4U  _AC(0x2001000000000000,UL) /* (Panther) 256MB page */

@@ -133,6 +138,7 @@
 #define _PAGE_ACCESSED_4V _AC(0x1000000000000000,UL) /* Accessed (ref'd)     */
 #define _PAGE_READ_4V	  _AC(0x0800000000000000,UL) /* Readable SW Bit      */
 #define _PAGE_WRITE_4V	  _AC(0x0400000000000000,UL) /* Writable SW Bit      */
+#define _PAGE_SPECIAL_4V  _AC(0x0200000000000000,UL) /* Special page         */
 #define _PAGE_PADDR_4V	  _AC(0x00FFFFFFFFFFE000,UL) /* paddr[55:13]         */
 #define _PAGE_IE_4V	  _AC(0x0000000000001000,UL) /* Invert Endianness    */
 #define _PAGE_E_4V	  _AC(0x0000000000000800,UL) /* side-Effect          */

@@ -302,10 +308,10 @@ static inline pte_t pte_modify(pte_t pte
 	: "=r" (mask), "=r" (tmp)
 	: "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U |
 	       _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U | _PAGE_PRESENT_4U |
-	       _PAGE_SZBITS_4U),
+	       _PAGE_SZBITS_4U | _PAGE_SPECIAL),
 	  "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
 	       _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V | _PAGE_PRESENT_4V |
-	       _PAGE_SZBITS_4V));
+	       _PAGE_SZBITS_4V | _PAGE_SPECIAL));
 
 	return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask));
 }

@@ -502,6 +508,7 @@ static inline pte_t pte_mkyoung(pte_t pt
 
 static inline pte_t pte_mkspecial(pte_t pte)
 {
+	pte_val(pte) |= _PAGE_SPECIAL;
 	return pte;
 }
 

@@ -607,9 +614,9 @@ static inline unsigned long pte_present(
 	return val;
 }
 
-static inline int pte_special(pte_t pte)
+static inline unsigned long pte_special(pte_t pte)
 {
-	return 0;
+	return pte_val(pte) & _PAGE_SPECIAL;
 }
 
 #define pmd_set(pmdp, ptep)	\

181 lines not on this page · raw message

Index: linux-2.6/include/linux/lockdep.h
===================================================================
@@ -484,12 +484,15 @@ static inline void print_irqtrace_events
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # ifdef CONFIG_PROVE_LOCKING
 #  define mutex_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 2, NULL, i)
+#  define mutex_acquire_nest(l, s, t, n, i)	lock_acquire(l, s, t, 0, 2, n, i)
 # else
 #  define mutex_acquire(l, s, t, i)		lock_acquire(l, s, t, 0, 1, NULL, i)
+#  define mutex_acquire_nest(l, s, t, n, i)	lock_acquire(l, s, t, 0, 1, n, i)
 # endif
 # define mutex_release(l, n, i)			lock_release(l, n, i)
 #else
 # define mutex_acquire(l, s, t, i)		do { } while (0)
+# define mutex_acquire_nest(l, s, t, n, i)	do { } while (0)
 # define mutex_release(l, n, i)			do { } while (0)
 #endif
 

Index: linux-2.6/include/linux/mutex.h
===================================================================
@@ -124,6 +124,7 @@ static inline int mutex_is_locked(struct
  */
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
+extern void _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock);
 extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock,
 					unsigned int subclass);
 extern int __must_check mutex_lock_killable_nested(struct mutex *lock,

@@ -132,6 +133,13 @@ extern int __must_check mutex_lock_killa
 #define mutex_lock(lock) mutex_lock_nested(lock, 0)
 #define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0)
 #define mutex_lock_killable(lock) mutex_lock_killable_nested(lock, 0)
+
+#define mutex_lock_nest_lock(lock, nest_lock)				\
+do {									\
+	typecheck(struct lockdep_map *, &(nest_lock)->dep_map);		\
+	_mutex_lock_nest_lock(lock, &(nest_lock)->dep_map);		\
+} while (0)
+
 #else
 extern void mutex_lock(struct mutex *lock);
 extern int __must_check mutex_lock_interruptible(struct mutex *lock);

@@ -140,6 +148,7 @@ extern int __must_check mutex_lock_killa
 # define mutex_lock_nested(lock, subclass) mutex_lock(lock)
 # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock)
 # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock)
+# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
 #endif
 
 /*

Index: linux-2.6/kernel/mutex.c
===================================================================
@@ -140,14 +140,14 @@ EXPORT_SYMBOL(mutex_unlock);
  */
 static inline int __sched
 __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
-	       	unsigned long ip)
+		    struct lockdep_map *nest_lock, unsigned long ip)
 {
 	struct task_struct *task = current;
 	struct mutex_waiter waiter;
 	unsigned long flags;
 
 	preempt_disable();
-	mutex_acquire(&lock->dep_map, subclass, 0, ip);
+	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 	/*

@@ -278,16 +278,25 @@ void __sched
 mutex_lock_nested(struct mutex *lock, unsigned int subclass)
 {
 	might_sleep();
-	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, _RET_IP_);
+	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_);
 }
 
 EXPORT_SYMBOL_GPL(mutex_lock_nested);
 
+void __sched
+_mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
+{
+	might_sleep();
+	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, nest, _RET_IP_);
+}
+
+EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);
+
 int __sched
 mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass)
 {
 	might_sleep();
-	return __mutex_lock_common(lock, TASK_KILLABLE, subclass, _RET_IP_);
+	return __mutex_lock_common(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_);
 }
 EXPORT_SYMBOL_GPL(mutex_lock_killable_nested);
 

@@ -296,7 +305,7 @@ mutex_lock_interruptible_nested(struct m
 {
 	might_sleep();
 	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE,
-				   subclass, _RET_IP_);
+				   subclass, NULL, _RET_IP_);
 }
 
 EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);

@@ -402,7 +411,7 @@ __mutex_lock_slowpath(atomic_t *lock_cou
 {
 	struct mutex *lock = container_of(lock_count, struct mutex, count);
 
-	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, _RET_IP_);
+	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_);
 }
 
 static noinline int __sched

@@ -410,7 +419,7 @@ __mutex_lock_killable_slowpath(atomic_t 
 {
 	struct mutex *lock = container_of(lock_count, struct mutex, count);
 
-	return __mutex_lock_common(lock, TASK_KILLABLE, 0, _RET_IP_);
+	return __mutex_lock_common(lock, TASK_KILLABLE, 0, NULL, _RET_IP_);
 }
 
 static noinline int __sched

@@ -418,7 +427,7 @@ __mutex_lock_interruptible_slowpath(atom
 {
 	struct mutex *lock = container_of(lock_count, struct mutex, count);
 
-	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, _RET_IP_);
+	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_);
 }
 #endif
 

Index: linux-2.6/include/linux/mutex.h
===================================================================
@@ -118,6 +118,11 @@ static inline int mutex_is_locked(struct
 	return atomic_read(&lock->count) != 1;
 }
 
+static inline int mutex_is_contended(struct mutex *lock)
+{
+	return atomic_read(&lock->count) < 0;
+}
+
 /*
  * See kernel/mutex.c for detailed documentation of these APIs.
  * Also see Documentation/mutex-design.txt.

Index: linux-2.6/arch/x86/mm/hugetlbpage.c
===================================================================
@@ -72,7 +72,7 @@ static void huge_pmd_share(struct mm_str
 	if (!vma_shareable(vma, addr))
 		return;
 
-	spin_lock(&mapping->i_mmap_lock);
+	mutex_lock(&mapping->i_mmap_lock);
 	vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) {
 		if (svma == vma)
 			continue;

@@ -97,7 +97,7 @@ static void huge_pmd_share(struct mm_str
 		put_page(virt_to_page(spte));
 	spin_unlock(&mm->page_table_lock);
 out:
-	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->i_mmap_lock);
 }
 
 /*

Index: linux-2.6/fs/hugetlbfs/inode.c
===================================================================
@@ -429,10 +429,10 @@ static int hugetlb_vmtruncate(struct ino
 	pgoff = offset >> PAGE_SHIFT;
 
 	i_size_write(inode, offset);
-	spin_lock(&mapping->i_mmap_lock);
+	mutex_lock(&mapping->i_mmap_lock);
 	if (!prio_tree_empty(&mapping->i_mmap))
 		hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
-	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->i_mmap_lock);
 	truncate_hugepages(inode, offset);
 	return 0;
 }

Index: linux-2.6/fs/inode.c
===================================================================
@@ -258,7 +258,7 @@ void inode_init_once(struct inode *inode
 	INIT_LIST_HEAD(&inode->i_devices);
 	INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC);
 	spin_lock_init(&inode->i_data.tree_lock);
-	spin_lock_init(&inode->i_data.i_mmap_lock);
+	mutex_init(&inode->i_data.i_mmap_lock);
 	INIT_LIST_HEAD(&inode->i_data.private_list);
 	spin_lock_init(&inode->i_data.private_lock);
 	INIT_RAW_PRIO_TREE_ROOT(&inode->i_data.i_mmap);

Index: linux-2.6/include/linux/fs.h
===================================================================
@@ -627,7 +627,7 @@ struct address_space {
 	unsigned int		i_mmap_writable;/* count VM_SHARED mappings */
 	struct prio_tree_root	i_mmap;		/* tree of private and shared mappings */
 	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
-	spinlock_t		i_mmap_lock;	/* protect tree, count, list */
+	struct mutex		i_mmap_lock;	/* protect tree, count, list */
 	unsigned int		truncate_count;	/* Cover race condition with truncate */
 	unsigned long		nrpages;	/* number of total pages */
 	pgoff_t			writeback_index;/* writeback starts here */

Index: linux-2.6/include/linux/mm.h
===================================================================
@@ -754,7 +754,7 @@ struct zap_details {
 	struct address_space *check_mapping;	/* Check page->mapping if set */
 	pgoff_t	first_index;			/* Lowest page->index to unmap */
 	pgoff_t last_index;			/* Highest page->index to unmap */
-	spinlock_t *i_mmap_lock;		/* For unmap_mapping_range: */
+	struct mutex *i_mmap_lock;		/* For unmap_mapping_range: */
 	unsigned long truncate_count;		/* Compare vm_truncate_count */
 };
 

Index: linux-2.6/include/linux/rmap.h
===================================================================
@@ -7,7 +7,7 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include <linux/memcontrol.h>
 
 /*

@@ -25,7 +25,7 @@
  * pointing to this anon_vma once its vma list is empty.
  */
 struct anon_vma {
-	spinlock_t lock;	/* Serialize access to vma list */
+	struct mutex lock;	/* Serialize access to vma list */
 	struct anon_vma *root;	/* Root of this anon_vma tree */
 	/*
 	 * The refcount is taken on an anon_vma when there is no

@@ -93,24 +93,24 @@ static inline void vma_lock_anon_vma(str
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 	if (anon_vma)
-		spin_lock(&anon_vma->root->lock);
+		mutex_lock(&anon_vma->root->lock);
 }
 
 static inline void vma_unlock_anon_vma(struct vm_area_struct *vma)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 	if (anon_vma)
-		spin_unlock(&anon_vma->root->lock);
+		mutex_unlock(&anon_vma->root->lock);
 }
 
 static inline void anon_vma_lock(struct anon_vma *anon_vma)
 {
-	spin_lock(&anon_vma->root->lock);
+	mutex_lock(&anon_vma->root->lock);
 }
 
 static inline void anon_vma_unlock(struct anon_vma *anon_vma)
 {
-	spin_unlock(&anon_vma->root->lock);
+	mutex_unlock(&anon_vma->root->lock);
 }
 
 /*

Index: linux-2.6/kernel/fork.c
===================================================================
@@ -368,7 +368,7 @@ static int dup_mmap(struct mm_struct *mm
 			get_file(file);
 			if (tmp->vm_flags & VM_DENYWRITE)
 				atomic_dec(&inode->i_writecount);
-			spin_lock(&mapping->i_mmap_lock);
+			mutex_lock(&mapping->i_mmap_lock);
 			if (tmp->vm_flags & VM_SHARED)
 				mapping->i_mmap_writable++;
 			tmp->vm_truncate_count = mpnt->vm_truncate_count;

@@ -376,7 +376,7 @@ static int dup_mmap(struct mm_struct *mm
 			/* insert tmp into the share list, just after mpnt */
 			vma_prio_tree_add(tmp, mpnt);
 			flush_dcache_mmap_unlock(mapping);
-			spin_unlock(&mapping->i_mmap_lock);
+			mutex_unlock(&mapping->i_mmap_lock);
 		}
 
 		/*

Index: linux-2.6/mm/filemap_xip.c
===================================================================
@@ -183,7 +183,7 @@ __xip_unmap (struct address_space * mapp
 		return;
 
 retry:
-	spin_lock(&mapping->i_mmap_lock);
+	mutex_lock(&mapping->i_mmap_lock);
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
 		mm = vma->vm_mm;
 		address = vma->vm_start +

@@ -201,7 +201,7 @@ retry:
 			page_cache_release(page);
 		}
 	}
-	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->i_mmap_lock);
 
 	if (locked) {
 		mutex_unlock(&xip_sparse_mutex);

Index: linux-2.6/mm/fremap.c
===================================================================
@@ -208,13 +208,13 @@ SYSCALL_DEFINE5(remap_file_pages, unsign
 			}
 			goto out;
 		}
-		spin_lock(&mapping->i_mmap_lock);
+		mutex_lock(&mapping->i_mmap_lock);
 		flush_dcache_mmap_lock(mapping);
 		vma->vm_flags |= VM_NONLINEAR;
 		vma_prio_tree_remove(vma, &mapping->i_mmap);
 		vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
 		flush_dcache_mmap_unlock(mapping);
-		spin_unlock(&mapping->i_mmap_lock);
+		mutex_unlock(&mapping->i_mmap_lock);
 	}
 
 	if (vma->vm_flags & VM_LOCKED) {

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -2215,9 +2215,9 @@ void __unmap_hugepage_range(struct vm_ar
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 			  unsigned long end, struct page *ref_page)
 {
-	spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+	mutex_lock(&vma->vm_file->f_mapping->i_mmap_lock);
 	__unmap_hugepage_range(vma, start, end, ref_page);
-	spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
 }
 
 /*

@@ -2249,7 +2249,7 @@ static int unmap_ref_private(struct mm_s
 	 * this mapping should be shared between all the VMAs,
 	 * __unmap_hugepage_range() is called as the lock is already held
 	 */
-	spin_lock(&mapping->i_mmap_lock);
+	mutex_lock(&mapping->i_mmap_lock);
 	vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
 		/* Do not unmap the current VMA */
 		if (iter_vma == vma)

@@ -2267,7 +2267,7 @@ static int unmap_ref_private(struct mm_s
 				address, address + huge_page_size(h),
 				page);
 	}
-	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->i_mmap_lock);
 
 	return 1;
 }

@@ -2685,7 +2685,7 @@ void hugetlb_change_protection(struct vm
 	BUG_ON(address >= end);
 	flush_cache_range(vma, address, end);
 
-	spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+	mutex_lock(&vma->vm_file->f_mapping->i_mmap_lock);
 	spin_lock(&mm->page_table_lock);
 	for (; address < end; address += huge_page_size(h)) {
 		ptep = huge_pte_offset(mm, address);

@@ -2700,7 +2700,7 @@ void hugetlb_change_protection(struct vm
 		}
 	}
 	spin_unlock(&mm->page_table_lock);
-	spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
 
 	flush_tlb_range(vma, start, end);
 }

Index: linux-2.6/mm/memory-failure.c
===================================================================
@@ -422,7 +422,7 @@ static void collect_procs_file(struct pa
 	 */
 
 	read_lock(&tasklist_lock);
-	spin_lock(&mapping->i_mmap_lock);
+	mutex_lock(&mapping->i_mmap_lock);
 	for_each_process(tsk) {
 		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
 

@@ -442,7 +442,7 @@ static void collect_procs_file(struct pa
 				add_to_kill(tsk, page, vma, to_kill, tkc);
 		}
 	}
-	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->i_mmap_lock);
 	read_unlock(&tasklist_lock);
 }
 

Index: linux-2.6/mm/memory.c
===================================================================
@@ -1183,7 +1183,7 @@ unsigned long unmap_vmas(struct mmu_gath
 {
 	long zap_work = ZAP_BLOCK_SIZE;
 	unsigned long start = start_addr;
-	spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
+	struct mutex *i_mmap_lock = details ? details->i_mmap_lock : NULL;
 	struct mm_struct *mm = vma->vm_mm;
 
 	mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);

@@ -1233,7 +1233,7 @@ unsigned long unmap_vmas(struct mmu_gath
 			}
 
 			if (need_resched() ||
-				(i_mmap_lock && spin_needbreak(i_mmap_lock))) {
+				(i_mmap_lock && mutex_is_contended(i_mmap_lock))) {
 				if (i_mmap_lock)
 					goto out;
 				cond_resched();

@@ -2517,7 +2517,7 @@ again:
 
 	restart_addr = zap_page_range(vma, start_addr,
 					end_addr - start_addr, details);
-	need_break = need_resched() || spin_needbreak(details->i_mmap_lock);
+	need_break = need_resched() || mutex_is_contended(details->i_mmap_lock);
 
 	if (restart_addr >= end_addr) {
 		/* We have now completed this vma: mark it so */

@@ -2531,9 +2531,9 @@ again:
 			goto again;
 	}
 
-	spin_unlock(details->i_mmap_lock);
+	mutex_unlock(details->i_mmap_lock);
 	cond_resched();
-	spin_lock(details->i_mmap_lock);
+	mutex_lock(details->i_mmap_lock);
 	return -EINTR;
 }
 

@@ -2629,7 +2629,7 @@ void unmap_mapping_range(struct address_
 		details.last_index = ULONG_MAX;
 	details.i_mmap_lock = &mapping->i_mmap_lock;
 
-	spin_lock(&mapping->i_mmap_lock);
+	mutex_lock(&mapping->i_mmap_lock);
 
 	/* Protect against endless unmapping loops */
 	mapping->truncate_count++;

@@ -2644,7 +2644,7 @@ void unmap_mapping_range(struct address_
 		unmap_mapping_range_tree(&mapping->i_mmap, &details);
 	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
 		unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
-	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->i_mmap_lock);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 

Index: linux-2.6/mm/mmap.c
===================================================================
@@ -216,9 +216,9 @@ void unlink_file_vma(struct vm_area_stru
 
 	if (file) {
 		struct address_space *mapping = file->f_mapping;
-		spin_lock(&mapping->i_mmap_lock);
+		mutex_lock(&mapping->i_mmap_lock);
 		__remove_shared_vm_struct(vma, file, mapping);
-		spin_unlock(&mapping->i_mmap_lock);
+		mutex_unlock(&mapping->i_mmap_lock);
 	}
 }
 

@@ -449,7 +449,7 @@ static void vma_link(struct mm_struct *m
 		mapping = vma->vm_file->f_mapping;
 
 	if (mapping) {
-		spin_lock(&mapping->i_mmap_lock);
+		mutex_lock(&mapping->i_mmap_lock);
 		vma->vm_truncate_count = mapping->truncate_count;
 	}
 	vma_lock_anon_vma(vma);

@@ -459,7 +459,7 @@ static void vma_link(struct mm_struct *m
 
 	vma_unlock_anon_vma(vma);
 	if (mapping)
-		spin_unlock(&mapping->i_mmap_lock);
+		mutex_unlock(&mapping->i_mmap_lock);
 
 	mm->map_count++;
 	validate_mm(mm);

@@ -558,7 +558,7 @@ again:			remove_next = 1 + (end > next->
 		mapping = file->f_mapping;
 		if (!(vma->vm_flags & VM_NONLINEAR))
 			root = &mapping->i_mmap;
-		spin_lock(&mapping->i_mmap_lock);
+		mutex_lock(&mapping->i_mmap_lock);
 		if (importer &&
 		    vma->vm_truncate_count != next->vm_truncate_count) {
 			/*

@@ -632,7 +632,7 @@ again:			remove_next = 1 + (end > next->
 	if (anon_vma)
 		anon_vma_unlock(anon_vma);
 	if (mapping)
-		spin_unlock(&mapping->i_mmap_lock);
+		mutex_unlock(&mapping->i_mmap_lock);
 
 	if (remove_next) {
 		if (file) {

@@ -2489,7 +2489,7 @@ static void vm_lock_anon_vma(struct mm_s
 		 * The LSB of head.next can't change from under us
 		 * because we hold the mm_all_locks_mutex.
 		 */
-		spin_lock_nest_lock(&anon_vma->root->lock, &mm->mmap_sem);
+		mutex_lock_nest_lock(&anon_vma->root->lock, &mm->mmap_sem);
 		/*
 		 * We can safely modify head.next after taking the
 		 * anon_vma->root->lock. If some other vma in this mm shares

@@ -2519,7 +2519,7 @@ static void vm_lock_mapping(struct mm_st
 		 */
 		if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags))
 			BUG();
-		spin_lock_nest_lock(&mapping->i_mmap_lock, &mm->mmap_sem);
+		mutex_lock_nest_lock(&mapping->i_mmap_lock, &mm->mmap_sem);
 	}
 }
 

@@ -2618,7 +2618,7 @@ static void vm_unlock_mapping(struct add
 		 * AS_MM_ALL_LOCKS can't change to 0 from under us
 		 * because we hold the mm_all_locks_mutex.
 		 */
-		spin_unlock(&mapping->i_mmap_lock);
+		mutex_unlock(&mapping->i_mmap_lock);
 		if (!test_and_clear_bit(AS_MM_ALL_LOCKS,
 					&mapping->flags))
 			BUG();

Index: linux-2.6/mm/mremap.c
===================================================================
@@ -90,7 +90,7 @@ static void move_ptes(struct vm_area_str
 		 * and we propagate stale pages into the dst afterward.
 		 */
 		mapping = vma->vm_file->f_mapping;
-		spin_lock(&mapping->i_mmap_lock);
+		mutex_lock(&mapping->i_mmap_lock);
 		if (new_vma->vm_truncate_count &&
 		    new_vma->vm_truncate_count != vma->vm_truncate_count)
 			new_vma->vm_truncate_count = 0;

@@ -122,7 +122,7 @@ static void move_ptes(struct vm_area_str
 	pte_unmap_nested(new_pte - 1);
 	pte_unmap_unlock(old_pte - 1, old_ptl);
 	if (mapping)
-		spin_unlock(&mapping->i_mmap_lock);
+		mutex_unlock(&mapping->i_mmap_lock);
 	mmu_notifier_invalidate_range_end(vma->vm_mm, old_start, old_end);
 }
 

Index: linux-2.6/mm/rmap.c
===================================================================
@@ -300,7 +300,7 @@ static void anon_vma_ctor(void *data)
 {
 	struct anon_vma *anon_vma = data;
 
-	spin_lock_init(&anon_vma->lock);
+	mutex_init(&anon_vma->lock);
 	atomic_set(&anon_vma->refcount, 0);
 	INIT_LIST_HEAD(&anon_vma->head);
 }

@@ -612,7 +612,7 @@ static int page_referenced_file(struct p
 	 */
 	BUG_ON(!PageLocked(page));
 
-	spin_lock(&mapping->i_mmap_lock);
+	mutex_lock(&mapping->i_mmap_lock);
 
 	/*
 	 * i_mmap_lock does not stabilize mapcount at all, but mapcount

@@ -637,7 +637,7 @@ static int page_referenced_file(struct p
 			break;
 	}
 
-	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->i_mmap_lock);
 	return referenced;
 }
 

@@ -724,7 +724,7 @@ static int page_mkclean_file(struct addr
 
 	BUG_ON(PageAnon(page));
 
-	spin_lock(&mapping->i_mmap_lock);
+	mutex_lock(&mapping->i_mmap_lock);
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
 		if (vma->vm_flags & VM_SHARED) {
 			unsigned long address = vma_address(page, vma);

@@ -733,7 +733,7 @@ static int page_mkclean_file(struct addr
 			ret += page_mkclean_one(page, vma, address);
 		}
 	}
-	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->i_mmap_lock);
 	return ret;
 }
 

@@ -1283,7 +1283,7 @@ static int try_to_unmap_file(struct page
 	unsigned long max_nl_size = 0;
 	unsigned int mapcount;
 
-	spin_lock(&mapping->i_mmap_lock);
+	mutex_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)