[PATCH 0/8] mm: Preemptibility -v8

[PATCH 0/8] mm: Preemptibility -v8

[Peter Zijlstra]

This series depends on the previous two series:
  - mm: Simplify anon_vma lifetime rules
  - mm: mmu_gather rework

These patches make part of the mm a lot more preemptible. It converts
i_mmap_lock and anon_vma->lock to mutexes which together with the mmu_gather
rework makes mmu_gather preemptible as well.

Making i_mmap_lock a mutex also enables a clean-up of the truncate code.

This also allows for preemptible mmu_notifiers, something that XPMEM I think
wants.



--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 1/8] lockdep, mutex: Provide mutex_lock_nest_lock

[Peter Zijlstra]

[-- Attachment #1: peter_zijlstra-lockdep_mutex-provide_mutex_lock_nest_lock.patch --]
[-- Type: text/plain, Size: 5745 bytes --]

Provide the mutex_lock_nest_lock() annotation.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 include/linux/lockdep.h |    3 +++
 include/linux/mutex.h   |    9 +++++++++
 kernel/mutex.c          |   25 +++++++++++++++++--------
 3 files changed, 29 insertions(+), 8 deletions(-)

Index: linux-2.6/include/linux/lockdep.h
===================================================================
--- linux-2.6.orig/include/linux/lockdep.h
+++ linux-2.6/include/linux/lockdep.h
@@ -495,12 +495,15 @@ 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
===================================================================
--- linux-2.6.orig/include/linux/mutex.h
+++ linux-2.6/include/linux/mutex.h
@@ -132,6 +132,7 @@ 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,
@@ -140,6 +141,13 @@ 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);
@@ -148,6 +156,7 @@ 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
===================================================================
--- linux-2.6.orig/kernel/mutex.c
+++ linux-2.6/kernel/mutex.c
@@ -131,14 +131,14 @@ 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
 	/*
@@ -276,16 +276,25 @@ 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);
 
@@ -294,7 +303,7 @@ 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);
@@ -400,7 +409,7 @@ __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
@@ -408,7 +417,7 @@ __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
@@ -416,7 +425,7 @@ __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
 


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 2/8] mm: Remove i_mmap_mutex lockbreak

[Peter Zijlstra]

[-- Attachment #1: mm-fix-zap_block_size.patch --]
[-- Type: text/plain, Size: 16470 bytes --]

Hugh says:
 "The only significant loser, I think, would be page reclaim (when
  concurrent with truncation): could spin for a long time waiting for
  the i_mmap_mutex it expects would soon be dropped? "

Counter points:
 - cpu contention makes the spin stop (need_resched())
 - zap pages should be freeing pages at a higher rate than reclaim
   ever can
 - shouldn't hold up reclaim more than lock_page() would

I think the simplification of the truncate code is definately worth
it.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 include/linux/fs.h       |    1 
 include/linux/mm.h       |    2 
 include/linux/mm_types.h |    1 
 kernel/fork.c            |    1 
 mm/memory.c              |  193 ++++++-----------------------------------------
 mm/mmap.c                |   13 ---
 mm/mremap.c              |    3 
 7 files changed, 27 insertions(+), 187 deletions(-)

Index: linux-2.6/include/linux/mm.h
===================================================================
--- linux-2.6.orig/include/linux/mm.h
+++ linux-2.6/include/linux/mm.h
@@ -878,8 +878,6 @@ 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: */
-	unsigned long truncate_count;		/* Compare vm_truncate_count */
 };
 
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
Index: linux-2.6/mm/memory.c
===================================================================
--- linux-2.6.orig/mm/memory.c
+++ linux-2.6/mm/memory.c
@@ -986,13 +986,13 @@ int copy_page_range(struct mm_struct *ds
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				struct vm_area_struct *vma, pmd_t *pmd,
 				unsigned long addr, unsigned long end,
-				long *zap_work, struct zap_details *details)
+				struct zap_details *details)
 {
 	struct mm_struct *mm = tlb->mm;
 	int need_flush = 0;
-	pte_t *pte;
-	spinlock_t *ptl;
 	int rss[NR_MM_COUNTERS];
+	spinlock_t *ptl;
+	pte_t *pte;
 
 	init_rss_vec(rss);
 again:
@@ -1001,12 +1001,9 @@ static unsigned long zap_pte_range(struc
 	do {
 		pte_t ptent = *pte;
 		if (pte_none(ptent)) {
-			(*zap_work)--;
 			continue;
 		}
 
-		(*zap_work) -= PAGE_SIZE;
-
 		if (pte_present(ptent)) {
 			struct page *page;
 
@@ -1073,8 +1070,7 @@ static unsigned long zap_pte_range(struc
 				print_bad_pte(vma, addr, ptent, NULL);
 		}
 		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
-	} while (pte++, addr += PAGE_SIZE,
-			(addr != end && *zap_work > 0 && !need_flush));
+	} while (pte++, addr += PAGE_SIZE, (addr != end && !need_flush));
 
 	add_mm_rss_vec(mm, rss);
 	arch_leave_lazy_mmu_mode();
@@ -1093,7 +1089,7 @@ static unsigned long zap_pte_range(struc
 static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 				struct vm_area_struct *vma, pud_t *pud,
 				unsigned long addr, unsigned long end,
-				long *zap_work, struct zap_details *details)
+				struct zap_details *details)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -1105,19 +1101,15 @@ static inline unsigned long zap_pmd_rang
 			if (next-addr != HPAGE_PMD_SIZE) {
 				VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem));
 				split_huge_page_pmd(vma->vm_mm, pmd);
-			} else if (zap_huge_pmd(tlb, vma, pmd)) {
-				(*zap_work)--;
+			} else if (zap_huge_pmd(tlb, vma, pmd))
 				continue;
-			}
 			/* fall through */
 		}
-		if (pmd_none_or_clear_bad(pmd)) {
-			(*zap_work)--;
+		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		}
-		next = zap_pte_range(tlb, vma, pmd, addr, next,
-						zap_work, details);
-	} while (pmd++, addr = next, (addr != end && *zap_work > 0));
+		next = zap_pte_range(tlb, vma, pmd, addr, next, details);
+		cond_resched();
+	} while (pmd++, addr = next, addr != end);
 
 	return addr;
 }
@@ -1125,7 +1117,7 @@ static inline unsigned long zap_pmd_rang
 static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
 				struct vm_area_struct *vma, pgd_t *pgd,
 				unsigned long addr, unsigned long end,
-				long *zap_work, struct zap_details *details)
+				struct zap_details *details)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -1133,13 +1125,10 @@ static inline unsigned long zap_pud_rang
 	pud = pud_offset(pgd, addr);
 	do {
 		next = pud_addr_end(addr, end);
-		if (pud_none_or_clear_bad(pud)) {
-			(*zap_work)--;
+		if (pud_none_or_clear_bad(pud))
 			continue;
-		}
-		next = zap_pmd_range(tlb, vma, pud, addr, next,
-						zap_work, details);
-	} while (pud++, addr = next, (addr != end && *zap_work > 0));
+		next = zap_pmd_range(tlb, vma, pud, addr, next, details);
+	} while (pud++, addr = next, addr != end);
 
 	return addr;
 }
@@ -1147,7 +1136,7 @@ static inline unsigned long zap_pud_rang
 static unsigned long unmap_page_range(struct mmu_gather *tlb,
 				struct vm_area_struct *vma,
 				unsigned long addr, unsigned long end,
-				long *zap_work, struct zap_details *details)
+				struct zap_details *details)
 {
 	pgd_t *pgd;
 	unsigned long next;
@@ -1161,13 +1150,10 @@ static unsigned long unmap_page_range(st
 	pgd = pgd_offset(vma->vm_mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		if (pgd_none_or_clear_bad(pgd)) {
-			(*zap_work)--;
+		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		}
-		next = zap_pud_range(tlb, vma, pgd, addr, next,
-						zap_work, details);
-	} while (pgd++, addr = next, (addr != end && *zap_work > 0));
+		next = zap_pud_range(tlb, vma, pgd, addr, next, details);
+	} while (pgd++, addr = next, addr != end);
 	tlb_end_vma(tlb, vma);
 	mem_cgroup_uncharge_end();
 
@@ -1212,9 +1198,7 @@ unsigned long unmap_vmas(struct mmu_gath
 		unsigned long end_addr, unsigned long *nr_accounted,
 		struct zap_details *details)
 {
-	long zap_work = ZAP_BLOCK_SIZE;
 	unsigned long start = start_addr;
-	spinlock_t *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);
@@ -1247,33 +1231,15 @@ unsigned long unmap_vmas(struct mmu_gath
 				 * Since no pte has actually been setup, it is
 				 * safe to do nothing in this case.
 				 */
-				if (vma->vm_file) {
+				if (vma->vm_file)
 					unmap_hugepage_range(vma, start, end, NULL);
-					zap_work -= (end - start) /
-					pages_per_huge_page(hstate_vma(vma));
-				}
 
 				start = end;
 			} else
-				start = unmap_page_range(tlb, vma,
-						start, end, &zap_work, details);
-
-			if (zap_work > 0) {
-				BUG_ON(start != end);
-				break;
-			}
-
-			if (need_resched() ||
-				(i_mmap_lock && spin_needbreak(i_mmap_lock))) {
-				if (i_mmap_lock)
-					goto out;
-				cond_resched();
-			}
-
-			zap_work = ZAP_BLOCK_SIZE;
+				start = unmap_page_range(tlb, vma, start, end, details);
 		}
 	}
-out:
+
 	mmu_notifier_invalidate_range_end(mm, start_addr, end_addr);
 	return start;	/* which is now the end (or restart) address */
 }
@@ -2535,96 +2501,11 @@ static int do_wp_page(struct mm_struct *
 	return ret;
 }
 
-/*
- * Helper functions for unmap_mapping_range().
- *
- * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __
- *
- * We have to restart searching the prio_tree whenever we drop the lock,
- * since the iterator is only valid while the lock is held, and anyway
- * a later vma might be split and reinserted earlier while lock dropped.
- *
- * The list of nonlinear vmas could be handled more efficiently, using
- * a placeholder, but handle it in the same way until a need is shown.
- * It is important to search the prio_tree before nonlinear list: a vma
- * may become nonlinear and be shifted from prio_tree to nonlinear list
- * while the lock is dropped; but never shifted from list to prio_tree.
- *
- * In order to make forward progress despite restarting the search,
- * vm_truncate_count is used to mark a vma as now dealt with, so we can
- * quickly skip it next time around.  Since the prio_tree search only
- * shows us those vmas affected by unmapping the range in question, we
- * can't efficiently keep all vmas in step with mapping->truncate_count:
- * so instead reset them all whenever it wraps back to 0 (then go to 1).
- * mapping->truncate_count and vma->vm_truncate_count are protected by
- * i_mmap_lock.
- *
- * In order to make forward progress despite repeatedly restarting some
- * large vma, note the restart_addr from unmap_vmas when it breaks out:
- * and restart from that address when we reach that vma again.  It might
- * have been split or merged, shrunk or extended, but never shifted: so
- * restart_addr remains valid so long as it remains in the vma's range.
- * unmap_mapping_range forces truncate_count to leap over page-aligned
- * values so we can save vma's restart_addr in its truncate_count field.
- */
-#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK))
-
-static void reset_vma_truncate_counts(struct address_space *mapping)
-{
-	struct vm_area_struct *vma;
-	struct prio_tree_iter iter;
-
-	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
-		vma->vm_truncate_count = 0;
-	list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
-		vma->vm_truncate_count = 0;
-}
-
-static int unmap_mapping_range_vma(struct vm_area_struct *vma,
+static void unmap_mapping_range_vma(struct vm_area_struct *vma,
 		unsigned long start_addr, unsigned long end_addr,
 		struct zap_details *details)
 {
-	unsigned long restart_addr;
-	int need_break;
-
-	/*
-	 * files that support invalidating or truncating portions of the
-	 * file from under mmaped areas must have their ->fault function
-	 * return a locked page (and set VM_FAULT_LOCKED in the return).
-	 * This provides synchronisation against concurrent unmapping here.
-	 */
-
-again:
-	restart_addr = vma->vm_truncate_count;
-	if (is_restart_addr(restart_addr) && start_addr < restart_addr) {
-		start_addr = restart_addr;
-		if (start_addr >= end_addr) {
-			/* Top of vma has been split off since last time */
-			vma->vm_truncate_count = details->truncate_count;
-			return 0;
-		}
-	}
-
-	restart_addr = zap_page_range(vma, start_addr,
-					end_addr - start_addr, details);
-	need_break = need_resched() || spin_needbreak(details->i_mmap_lock);
-
-	if (restart_addr >= end_addr) {
-		/* We have now completed this vma: mark it so */
-		vma->vm_truncate_count = details->truncate_count;
-		if (!need_break)
-			return 0;
-	} else {
-		/* Note restart_addr in vma's truncate_count field */
-		vma->vm_truncate_count = restart_addr;
-		if (!need_break)
-			goto again;
-	}
-
-	spin_unlock(details->i_mmap_lock);
-	cond_resched();
-	spin_lock(details->i_mmap_lock);
-	return -EINTR;
+	zap_page_range(vma, start_addr, end_addr - start_addr, details);
 }
 
 static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
@@ -2634,12 +2515,8 @@ static inline void unmap_mapping_range_t
 	struct prio_tree_iter iter;
 	pgoff_t vba, vea, zba, zea;
 
-restart:
 	vma_prio_tree_foreach(vma, &iter, root,
 			details->first_index, details->last_index) {
-		/* Skip quickly over those we have already dealt with */
-		if (vma->vm_truncate_count == details->truncate_count)
-			continue;
 
 		vba = vma->vm_pgoff;
 		vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
@@ -2651,11 +2528,10 @@ static inline void unmap_mapping_range_t
 		if (zea > vea)
 			zea = vea;
 
-		if (unmap_mapping_range_vma(vma,
+		unmap_mapping_range_vma(vma,
 			((zba - vba) << PAGE_SHIFT) + vma->vm_start,
 			((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
-				details) < 0)
-			goto restart;
+				details);
 	}
 }
 
@@ -2670,15 +2546,9 @@ static inline void unmap_mapping_range_l
 	 * across *all* the pages in each nonlinear VMA, not just the pages
 	 * whose virtual address lies outside the file truncation point.
 	 */
-restart:
 	list_for_each_entry(vma, head, shared.vm_set.list) {
-		/* Skip quickly over those we have already dealt with */
-		if (vma->vm_truncate_count == details->truncate_count)
-			continue;
 		details->nonlinear_vma = vma;
-		if (unmap_mapping_range_vma(vma, vma->vm_start,
-					vma->vm_end, details) < 0)
-			goto restart;
+		unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details);
 	}
 }
 
@@ -2717,19 +2587,8 @@ void unmap_mapping_range(struct address_
 	details.last_index = hba + hlen - 1;
 	if (details.last_index < details.first_index)
 		details.last_index = ULONG_MAX;
-	details.i_mmap_lock = &mapping->i_mmap_lock;
 
 	spin_lock(&mapping->i_mmap_lock);
-
-	/* Protect against endless unmapping loops */
-	mapping->truncate_count++;
-	if (unlikely(is_restart_addr(mapping->truncate_count))) {
-		if (mapping->truncate_count == 0)
-			reset_vma_truncate_counts(mapping);
-		mapping->truncate_count++;
-	}
-	details.truncate_count = mapping->truncate_count;
-
 	if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
 		unmap_mapping_range_tree(&mapping->i_mmap, &details);
 	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
Index: linux-2.6/include/linux/fs.h
===================================================================
--- linux-2.6.orig/include/linux/fs.h
+++ linux-2.6/include/linux/fs.h
@@ -640,7 +640,6 @@ struct address_space {
 	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 */
-	unsigned int		truncate_count;	/* Cover race condition with truncate */
 	unsigned long		nrpages;	/* number of total pages */
 	pgoff_t			writeback_index;/* writeback starts here */
 	const struct address_space_operations *a_ops;	/* methods */
Index: linux-2.6/include/linux/mm_types.h
===================================================================
--- linux-2.6.orig/include/linux/mm_types.h
+++ linux-2.6/include/linux/mm_types.h
@@ -175,7 +175,6 @@ struct vm_area_struct {
 					   units, *not* PAGE_CACHE_SIZE */
 	struct file * vm_file;		/* File we map to (can be NULL). */
 	void * vm_private_data;		/* was vm_pte (shared mem) */
-	unsigned long vm_truncate_count;/* truncate_count or restart_addr */
 
 #ifndef CONFIG_MMU
 	struct vm_region *vm_region;	/* NOMMU mapping region */
Index: linux-2.6/kernel/fork.c
===================================================================
--- linux-2.6.orig/kernel/fork.c
+++ linux-2.6/kernel/fork.c
@@ -379,7 +379,6 @@ static int dup_mmap(struct mm_struct *mm
 			spin_lock(&mapping->i_mmap_lock);
 			if (tmp->vm_flags & VM_SHARED)
 				mapping->i_mmap_writable++;
-			tmp->vm_truncate_count = mpnt->vm_truncate_count;
 			flush_dcache_mmap_lock(mapping);
 			/* insert tmp into the share list, just after mpnt */
 			vma_prio_tree_add(tmp, mpnt);
Index: linux-2.6/mm/mmap.c
===================================================================
--- linux-2.6.orig/mm/mmap.c
+++ linux-2.6/mm/mmap.c
@@ -464,10 +464,8 @@ static void vma_link(struct mm_struct *m
 	if (vma->vm_file)
 		mapping = vma->vm_file->f_mapping;
 
-	if (mapping) {
+	if (mapping)
 		spin_lock(&mapping->i_mmap_lock);
-		vma->vm_truncate_count = mapping->truncate_count;
-	}
 
 	__vma_link(mm, vma, prev, rb_link, rb_parent);
 	__vma_link_file(vma);
@@ -577,16 +575,7 @@ again:			remove_next = 1 + (end > next->
 		if (!(vma->vm_flags & VM_NONLINEAR))
 			root = &mapping->i_mmap;
 		spin_lock(&mapping->i_mmap_lock);
-		if (importer &&
-		    vma->vm_truncate_count != next->vm_truncate_count) {
-			/*
-			 * unmap_mapping_range might be in progress:
-			 * ensure that the expanding vma is rescanned.
-			 */
-			importer->vm_truncate_count = 0;
-		}
 		if (insert) {
-			insert->vm_truncate_count = vma->vm_truncate_count;
 			/*
 			 * Put into prio_tree now, so instantiated pages
 			 * are visible to arm/parisc __flush_dcache_page
Index: linux-2.6/mm/mremap.c
===================================================================
--- linux-2.6.orig/mm/mremap.c
+++ linux-2.6/mm/mremap.c
@@ -94,9 +94,6 @@ static void move_ptes(struct vm_area_str
 		 */
 		mapping = vma->vm_file->f_mapping;
 		spin_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;
 	}
 
 	/*


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 3/8] mm: Convert i_mmap_lock to a mutex

[Peter Zijlstra]

[-- Attachment #1: peter_zijlstra-mm-convert_i_mmap_lock_to_mutexes.patch --]
[-- Type: text/plain, Size: 23113 bytes --]

Straight fwd conversion of i_mmap_lock to a mutex

Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 Documentation/lockstat.txt   |    2 +-
 Documentation/vm/locking     |    2 +-
 arch/x86/mm/hugetlbpage.c    |    4 ++--
 fs/gfs2/main.c               |    2 +-
 fs/hugetlbfs/inode.c         |    4 ++--
 fs/inode.c                   |    2 +-
 fs/nilfs2/page.c             |    2 +-
 include/linux/fs.h           |    2 +-
 include/linux/mm.h           |    1 +
 include/linux/mmu_notifier.h |    2 +-
 kernel/fork.c                |    4 ++--
 mm/filemap.c                 |   10 +++++-----
 mm/filemap_xip.c             |    4 ++--
 mm/fremap.c                  |    4 ++--
 mm/hugetlb.c                 |   14 +++++++-------
 mm/memory-failure.c          |    4 ++--
 mm/memory.c                  |    4 ++--
 mm/mmap.c                    |   22 +++++++++++-----------
 mm/mremap.c                  |    4 ++--
 mm/rmap.c                    |   28 ++++++++++++++--------------
 20 files changed, 61 insertions(+), 60 deletions(-)

Index: linux-2.6/arch/x86/mm/hugetlbpage.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/hugetlbpage.c
+++ 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_mutex);
 	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_mutex);
 }
 
 /*
Index: linux-2.6/fs/hugetlbfs/inode.c
===================================================================
--- linux-2.6.orig/fs/hugetlbfs/inode.c
+++ linux-2.6/fs/hugetlbfs/inode.c
@@ -413,10 +413,10 @@ 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_mutex);
 	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_mutex);
 	truncate_hugepages(inode, offset);
 	return 0;
 }
Index: linux-2.6/fs/inode.c
===================================================================
--- linux-2.6.orig/fs/inode.c
+++ linux-2.6/fs/inode.c
@@ -310,7 +310,7 @@ void inode_init_once(struct inode *inode
 	INIT_LIST_HEAD(&inode->i_lru);
 	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_mutex);
 	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
===================================================================
--- linux-2.6.orig/include/linux/fs.h
+++ linux-2.6/include/linux/fs.h
@@ -639,7 +639,7 @@ 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_mutex;	/* protect tree, count, list */
 	unsigned long		nrpages;	/* number of total pages */
 	pgoff_t			writeback_index;/* writeback starts here */
 	const struct address_space_operations *a_ops;	/* methods */
Index: linux-2.6/kernel/fork.c
===================================================================
--- linux-2.6.orig/kernel/fork.c
+++ linux-2.6/kernel/fork.c
@@ -376,14 +376,14 @@ 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_mutex);
 			if (tmp->vm_flags & VM_SHARED)
 				mapping->i_mmap_writable++;
 			flush_dcache_mmap_lock(mapping);
 			/* 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_mutex);
 		}
 
 		/*
Index: linux-2.6/mm/filemap_xip.c
===================================================================
--- linux-2.6.orig/mm/filemap_xip.c
+++ 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_mutex);
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
 		mm = vma->vm_mm;
 		address = vma->vm_start +
@@ -201,7 +201,7 @@ __xip_unmap (struct address_space * mapp
 			page_cache_release(page);
 		}
 	}
-	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->i_mmap_mutex);
 
 	if (locked) {
 		mutex_unlock(&xip_sparse_mutex);
Index: linux-2.6/mm/fremap.c
===================================================================
--- linux-2.6.orig/mm/fremap.c
+++ linux-2.6/mm/fremap.c
@@ -211,13 +211,13 @@ SYSCALL_DEFINE5(remap_file_pages, unsign
 			}
 			goto out;
 		}
-		spin_lock(&mapping->i_mmap_lock);
+		mutex_lock(&mapping->i_mmap_mutex);
 		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_mutex);
 	}
 
 	if (vma->vm_flags & VM_LOCKED) {
Index: linux-2.6/mm/hugetlb.c
===================================================================
--- linux-2.6.orig/mm/hugetlb.c
+++ linux-2.6/mm/hugetlb.c
@@ -2207,7 +2207,7 @@ void __unmap_hugepage_range(struct vm_ar
 	unsigned long sz = huge_page_size(h);
 
 	/*
-	 * A page gathering list, protected by per file i_mmap_lock. The
+	 * A page gathering list, protected by per file i_mmap_mutex. The
 	 * lock is used to avoid list corruption from multiple unmapping
 	 * of the same page since we are using page->lru.
 	 */
@@ -2276,9 +2276,9 @@ 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_mutex);
 	__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_mutex);
 }
 
 /*
@@ -2310,7 +2310,7 @@ 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_mutex);
 	vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
 		/* Do not unmap the current VMA */
 		if (iter_vma == vma)
@@ -2328,7 +2328,7 @@ 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_mutex);
 
 	return 1;
 }
@@ -2812,7 +2812,7 @@ 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_mutex);
 	spin_lock(&mm->page_table_lock);
 	for (; address < end; address += huge_page_size(h)) {
 		ptep = huge_pte_offset(mm, address);
@@ -2827,7 +2827,7 @@ 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_mutex);
 
 	flush_tlb_range(vma, start, end);
 }
Index: linux-2.6/mm/memory-failure.c
===================================================================
--- linux-2.6.orig/mm/memory-failure.c
+++ linux-2.6/mm/memory-failure.c
@@ -429,7 +429,7 @@ static void collect_procs_file(struct pa
 	 */
 
 	read_lock(&tasklist_lock);
-	spin_lock(&mapping->i_mmap_lock);
+	mutex_lock(&mapping->i_mmap_mutex);
 	for_each_process(tsk) {
 		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
 
@@ -449,7 +449,7 @@ 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_mutex);
 	read_unlock(&tasklist_lock);
 }
 
Index: linux-2.6/mm/memory.c
===================================================================
--- linux-2.6.orig/mm/memory.c
+++ linux-2.6/mm/memory.c
@@ -2588,12 +2588,12 @@ void unmap_mapping_range(struct address_
 	if (details.last_index < details.first_index)
 		details.last_index = ULONG_MAX;
 
-	spin_lock(&mapping->i_mmap_lock);
+	mutex_lock(&mapping->i_mmap_mutex);
 	if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
 		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_mutex);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
Index: linux-2.6/mm/mmap.c
===================================================================
--- linux-2.6.orig/mm/mmap.c
+++ linux-2.6/mm/mmap.c
@@ -190,7 +190,7 @@ int __vm_enough_memory(struct mm_struct 
 }
 
 /*
- * Requires inode->i_mapping->i_mmap_lock
+ * Requires inode->i_mapping->i_mmap_mutex
  */
 static void __remove_shared_vm_struct(struct vm_area_struct *vma,
 		struct file *file, struct address_space *mapping)
@@ -218,9 +218,9 @@ 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_mutex);
 		__remove_shared_vm_struct(vma, file, mapping);
-		spin_unlock(&mapping->i_mmap_lock);
+		mutex_unlock(&mapping->i_mmap_mutex);
 	}
 }
 
@@ -465,13 +465,13 @@ 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_mutex);
 
 	__vma_link(mm, vma, prev, rb_link, rb_parent);
 	__vma_link_file(vma);
 
 	if (mapping)
-		spin_unlock(&mapping->i_mmap_lock);
+		mutex_unlock(&mapping->i_mmap_mutex);
 
 	mm->map_count++;
 	validate_mm(mm);
@@ -574,7 +574,7 @@ 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_mutex);
 		if (insert) {
 			/*
 			 * Put into prio_tree now, so instantiated pages
@@ -641,7 +641,7 @@ 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_mutex);
 
 	if (remove_next) {
 		if (file) {
@@ -2300,7 +2300,7 @@ void exit_mmap(struct mm_struct *mm)
 
 /* Insert vm structure into process list sorted by address
  * and into the inode's i_mmap tree.  If vm_file is non-NULL
- * then i_mmap_lock is taken here.
+ * then i_mmap_mutex is taken here.
  */
 int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
 {
@@ -2542,7 +2542,7 @@ 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_mutex, &mm->mmap_sem);
 	}
 }
 
@@ -2569,7 +2569,7 @@ static void vm_lock_mapping(struct mm_st
  * vma in this mm is backed by the same anon_vma or address_space.
  *
  * We can take all the locks in random order because the VM code
- * taking i_mmap_lock or anon_vma->lock outside the mmap_sem never
+ * taking i_mmap_mutex or anon_vma->lock outside the mmap_sem never
  * takes more than one of them in a row. Secondly we're protected
  * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex.
  *
@@ -2641,7 +2641,7 @@ 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_mutex);
 		if (!test_and_clear_bit(AS_MM_ALL_LOCKS,
 					&mapping->flags))
 			BUG();
Index: linux-2.6/mm/mremap.c
===================================================================
--- linux-2.6.orig/mm/mremap.c
+++ linux-2.6/mm/mremap.c
@@ -93,7 +93,7 @@ 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_mutex);
 	}
 
 	/*
@@ -122,7 +122,7 @@ static void move_ptes(struct vm_area_str
 	pte_unmap(new_pte - 1);
 	pte_unmap_unlock(old_pte - 1, old_ptl);
 	if (mapping)
-		spin_unlock(&mapping->i_mmap_lock);
+		mutex_unlock(&mapping->i_mmap_mutex);
 	mmu_notifier_invalidate_range_end(vma->vm_mm, old_start, old_end);
 }
 
Index: linux-2.6/mm/rmap.c
===================================================================
--- linux-2.6.orig/mm/rmap.c
+++ linux-2.6/mm/rmap.c
@@ -24,7 +24,7 @@
  *   inode->i_alloc_sem (vmtruncate_range)
  *   mm->mmap_sem
  *     page->flags PG_locked (lock_page)
- *       mapping->i_mmap_lock
+ *       mapping->i_mmap_mutex
  *         anon_vma->lock
  *           mm->page_table_lock or pte_lock
  *             zone->lru_lock (in mark_page_accessed, isolate_lru_page)
@@ -629,14 +629,14 @@ static int page_referenced_file(struct p
 	 * 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);
@@ -658,7 +658,7 @@ static int page_referenced_file(struct p
 			break;
 	}
 
-	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->i_mmap_mutex);
 	return referenced;
 }
 
@@ -745,7 +745,7 @@ static int page_mkclean_file(struct addr
 
 	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);
@@ -754,7 +754,7 @@ 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_mutex);
 	return ret;
 }
 
@@ -1105,7 +1105,7 @@ int try_to_unmap_one(struct page *page, 
 	/*
 	 * 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->lock 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.
@@ -1331,7 +1331,7 @@ 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_mutex);
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
 		unsigned long address = vma_address(page, vma);
 		if (address == -EFAULT)
@@ -1377,7 +1377,7 @@ static int try_to_unmap_file(struct page
 	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)
@@ -1399,7 +1399,7 @@ static int try_to_unmap_file(struct page
 			}
 			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);
 
@@ -1411,7 +1411,7 @@ static int try_to_unmap_file(struct page
 	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;
 }
 
@@ -1527,7 +1527,7 @@ static int rmap_walk_file(struct page *p
 
 	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)
@@ -1541,7 +1541,7 @@ static int rmap_walk_file(struct page *p
 	 * 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;
 }
 
Index: linux-2.6/fs/gfs2/main.c
===================================================================
--- linux-2.6.orig/fs/gfs2/main.c
+++ linux-2.6/fs/gfs2/main.c
@@ -62,7 +62,7 @@ static void gfs2_init_gl_aspace_once(voi
 	memset(mapping, 0, sizeof(*mapping));
 	INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
 	spin_lock_init(&mapping->tree_lock);
-	spin_lock_init(&mapping->i_mmap_lock);
+	mutex_init(&mapping->i_mmap_mutex);
 	INIT_LIST_HEAD(&mapping->private_list);
 	spin_lock_init(&mapping->private_lock);
 	INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
Index: linux-2.6/fs/nilfs2/page.c
===================================================================
--- linux-2.6.orig/fs/nilfs2/page.c
+++ linux-2.6/fs/nilfs2/page.c
@@ -500,7 +500,7 @@ void nilfs_mapping_init_once(struct addr
 	INIT_LIST_HEAD(&mapping->private_list);
 	spin_lock_init(&mapping->private_lock);
 
-	spin_lock_init(&mapping->i_mmap_lock);
+	mutex_init(&mapping->i_mmap_mutex);
 	INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
 	INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
 }
Index: linux-2.6/Documentation/lockstat.txt
===================================================================
--- linux-2.6.orig/Documentation/lockstat.txt
+++ linux-2.6/Documentation/lockstat.txt
@@ -136,7 +136,7 @@ The integer part of the time values is i
                              dcache_lock:          1037           1161           0.38          45.32         774.51           6611         243371           0.15         306.48       77387.24
                          &inode->i_mutex:           161            286 18446744073709       62882.54     1244614.55           3653          20598 18446744073709       62318.60     1693822.74
                          &zone->lru_lock:            94             94           0.53           7.33          92.10           4366          32690           0.29          59.81       16350.06
-              &inode->i_data.i_mmap_lock:            79             79           0.40           3.77          53.03          11779          87755           0.28         116.93       29898.44
+              &inode->i_data.i_mmap_mutex:            79             79           0.40           3.77          53.03          11779          87755           0.28         116.93       29898.44
                         &q->__queue_lock:            48             50           0.52          31.62          86.31            774          13131           0.17         113.08       12277.52
                         &rq->rq_lock_key:            43             47           0.74          68.50         170.63           3706          33929           0.22         107.99       17460.62
                       &rq->rq_lock_key#2:            39             46           0.75           6.68          49.03           2979          32292           0.17         125.17       17137.63
Index: linux-2.6/Documentation/vm/locking
===================================================================
--- linux-2.6.orig/Documentation/vm/locking
+++ linux-2.6/Documentation/vm/locking
@@ -66,7 +66,7 @@ in some cases it is not really needed. E
 expand_stack(), it is hard to come up with a destructive scenario without 
 having the vmlist protection in this case.
 
-The page_table_lock nests with the inode i_mmap_lock and the kmem cache
+The page_table_lock nests with the inode i_mmap_mutex and the kmem cache
 c_spinlock spinlocks.  This is okay, since the kmem code asks for pages after
 dropping c_spinlock.  The page_table_lock also nests with pagecache_lock and
 pagemap_lru_lock spinlocks, and no code asks for memory with these locks
Index: linux-2.6/include/linux/mmu_notifier.h
===================================================================
--- linux-2.6.orig/include/linux/mmu_notifier.h
+++ linux-2.6/include/linux/mmu_notifier.h
@@ -150,7 +150,7 @@ struct mmu_notifier_ops {
  * Therefore notifier chains can only be traversed when either
  *
  * 1. mmap_sem is held.
- * 2. One of the reverse map locks is held (i_mmap_lock or anon_vma->lock).
+ * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->lock).
  * 3. No other concurrent thread can access the list (release)
  */
 struct mmu_notifier {
Index: linux-2.6/mm/filemap.c
===================================================================
--- linux-2.6.orig/mm/filemap.c
+++ linux-2.6/mm/filemap.c
@@ -58,16 +58,16 @@
 /*
  * Lock ordering:
  *
- *  ->i_mmap_lock		(truncate_pagecache)
+ *  ->i_mmap_mutex		(truncate_pagecache)
  *    ->private_lock		(__free_pte->__set_page_dirty_buffers)
  *      ->swap_lock		(exclusive_swap_page, others)
  *        ->mapping->tree_lock
  *
  *  ->i_mutex
- *    ->i_mmap_lock		(truncate->unmap_mapping_range)
+ *    ->i_mmap_mutex		(truncate->unmap_mapping_range)
  *
  *  ->mmap_sem
- *    ->i_mmap_lock
+ *    ->i_mmap_mutex
  *      ->page_table_lock or pte_lock	(various, mainly in memory.c)
  *        ->mapping->tree_lock	(arch-dependent flush_dcache_mmap_lock)
  *
@@ -84,7 +84,7 @@
  *    ->sb_lock			(fs/fs-writeback.c)
  *    ->mapping->tree_lock	(__sync_single_inode)
  *
- *  ->i_mmap_lock
+ *  ->i_mmap_mutex
  *    ->anon_vma.lock		(vma_adjust)
  *
  *  ->anon_vma.lock
@@ -104,7 +104,7 @@
  *
  *  (code doesn't rely on that order, so you could switch it around)
  *  ->tasklist_lock             (memory_failure, collect_procs_ao)
- *    ->i_mmap_lock
+ *    ->i_mmap_mutex
  */
 
 /*


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 4/8] mm: Revert page_lock_anon_vma() lock annotation

[Peter Zijlstra]

[-- Attachment #1: peter_zijlstra-mm-revert_page_lock_anon_vma_lock_annotation.patch --]
[-- Type: text/plain, Size: 2207 bytes --]

Its beyond ugly and gets in the way.

Cc: Namhyung Kim <namhyung@gmail.com>
Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 include/linux/rmap.h |   15 +--------------
 mm/rmap.c            |    4 +---
 2 files changed, 2 insertions(+), 17 deletions(-)

Index: linux-2.6/include/linux/rmap.h
===================================================================
--- linux-2.6.orig/include/linux/rmap.h
+++ linux-2.6/include/linux/rmap.h
@@ -243,20 +243,7 @@ int try_to_munlock(struct page *);
 /*
  * Called by memory-failure.c to kill processes.
  */
-struct anon_vma *__page_lock_anon_vma(struct page *page);
-
-static inline struct anon_vma *page_lock_anon_vma(struct page *page)
-{
-	struct anon_vma *anon_vma;
-
-	__cond_lock(RCU, anon_vma = __page_lock_anon_vma(page));
-
-	/* (void) is needed to make gcc happy */
-	(void) __cond_lock(&anon_vma->root->lock, anon_vma);
-
-	return anon_vma;
-}
-
+struct anon_vma *page_lock_anon_vma(struct page *page);
 void page_unlock_anon_vma(struct anon_vma *anon_vma);
 int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
 
Index: linux-2.6/mm/rmap.c
===================================================================
--- linux-2.6.orig/mm/rmap.c
+++ linux-2.6/mm/rmap.c
@@ -318,7 +318,7 @@ 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.
  */
-struct anon_vma *__page_lock_anon_vma(struct page *page)
+struct anon_vma *page_lock_anon_vma(struct page *page)
 {
 	struct anon_vma *anon_vma, *root_anon_vma;
 	unsigned long anon_mapping;
@@ -352,8 +352,6 @@ struct anon_vma *__page_lock_anon_vma(st
 }
 
 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();


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 5/8] mm: Improve page_lock_anon_vma() comment

[Peter Zijlstra]

[-- Attachment #1: peter_zijlstra-mm-improve_page_lock_anon_vma_comment.patch --]
[-- Type: text/plain, Size: 1988 bytes --]

A slightly more verbose comment to go along with the trickery in
page_lock_anon_vma().

Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 mm/rmap.c |   18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

Index: linux-2.6/mm/rmap.c
===================================================================
--- linux-2.6.orig/mm/rmap.c
+++ linux-2.6/mm/rmap.c
@@ -315,8 +315,22 @@ 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)
 {


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 6/8] mm: Use refcounts for page_lock_anon_vma()

[Peter Zijlstra]

[-- Attachment #1: peter_zijlstra-mm-use_refcounts_for_page_lock_anon_vma.patch --]
[-- Type: text/plain, Size: 4302 bytes --]

Convert page_lock_anon_vma() over to use refcounts. This is done to
prepare for the conversion of anon_vma from spinlock to mutex.

Sadly this inceases the cost of page_lock_anon_vma() from one to two
atomics, a follow up patch addresses this, lets keep that simple for
now.

Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 mm/migrate.c |   17 ++++-------------
 mm/rmap.c    |   42 +++++++++++++++++++++++++++---------------
 2 files changed, 31 insertions(+), 28 deletions(-)

Index: linux-2.6/mm/rmap.c
===================================================================
--- linux-2.6.orig/mm/rmap.c
+++ linux-2.6/mm/rmap.c
@@ -336,9 +336,9 @@ void __init anon_vma_init(void)
  * 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();
@@ -349,30 +349,42 @@ struct anon_vma *page_lock_anon_vma(stru
 		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;
-
-	spin_unlock(&root_anon_vma->lock);
+	if (!page_mapped(page)) {
+		put_anon_vma(anon_vma);
+		anon_vma = NULL;
+	}
 out:
 	rcu_read_unlock();
-	return NULL;
+
+	return anon_vma;
+}
+
+struct anon_vma *page_lock_anon_vma(struct page *page)
+{
+	struct anon_vma *anon_vma = page_get_anon_vma(page);
+
+	if (anon_vma)
+		anon_vma_lock(anon_vma);
+
+	return anon_vma;
 }
 
 void page_unlock_anon_vma(struct anon_vma *anon_vma)
 {
 	anon_vma_unlock(anon_vma);
-	rcu_read_unlock();
+	put_anon_vma(anon_vma);
 }
 
 /*
Index: linux-2.6/mm/migrate.c
===================================================================
--- linux-2.6.orig/mm/migrate.c
+++ linux-2.6/mm/migrate.c
@@ -703,15 +703,11 @@ static int unmap_and_move(new_page_t get
 		 * Only page_lock_anon_vma() understands the subtleties of
 		 * getting a hold on an anon_vma from outside one of its mms.
 		 */
-		anon_vma = page_lock_anon_vma(page);
+		anon_vma = page_get_anon_vma(page);
 		if (anon_vma) {
 			/*
-			 * Take a reference count on the anon_vma if the
-			 * page is mapped so that it is guaranteed to
-			 * exist when the page is remapped later
+			 * Anon page
 			 */
-			get_anon_vma(anon_vma);
-			page_unlock_anon_vma(anon_vma);
 		} else if (PageSwapCache(page)) {
 			/*
 			 * We cannot be sure that the anon_vma of an unmapped
@@ -840,13 +836,8 @@ static int unmap_and_move_huge_page(new_
 		lock_page(hpage);
 	}
 
-	if (PageAnon(hpage)) {
-		anon_vma = page_lock_anon_vma(hpage);
-		if (anon_vma) {
-			get_anon_vma(anon_vma);
-			page_unlock_anon_vma(anon_vma);
-		}
-	}
+	if (PageAnon(hpage))
+		anon_vma = page_get_anon_vma(hpage);
 
 	try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
 


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 7/8] mm: Convert anon_vma->lock to a mutex

[Peter Zijlstra]

[-- Attachment #1: peter_zijlstra-mm-anon_vma-lock_to_mutexes.patch --]
[-- Type: text/plain, Size: 8044 bytes --]

Straight fwd conversion of anon_vma->lock to a mutex.

Acked-by: Hugh Dickins <hughd@google.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 include/linux/huge_mm.h      |    8 ++------
 include/linux/mmu_notifier.h |    2 +-
 include/linux/rmap.h         |   14 +++++++-------
 mm/huge_memory.c             |    4 ++--
 mm/mmap.c                    |   10 +++++-----
 mm/rmap.c                    |    8 ++++----
 6 files changed, 21 insertions(+), 25 deletions(-)

Index: linux-2.6/include/linux/rmap.h
===================================================================
--- linux-2.6.orig/include/linux/rmap.h
+++ 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>
 
 /*
@@ -26,7 +26,7 @@
  */
 struct anon_vma {
 	struct anon_vma *root;	/* Root of this anon_vma tree */
-	spinlock_t lock;	/* Serialize access to vma list */
+	struct mutex mutex;	/* Serialize access to vma list */
 	/*
 	 * The refcount is taken on an anon_vma when there is no
 	 * guarantee that the vma of page tables will exist for
@@ -64,7 +64,7 @@ struct anon_vma_chain {
 	struct vm_area_struct *vma;
 	struct anon_vma *anon_vma;
 	struct list_head same_vma;   /* locked by mmap_sem & page_table_lock */
-	struct list_head same_anon_vma;	/* locked by anon_vma->lock */
+	struct list_head same_anon_vma;	/* locked by anon_vma->mutex */
 };
 
 #ifdef CONFIG_MMU
@@ -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->mutex);
 }
 
 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->mutex);
 }
 
 static inline void anon_vma_lock(struct anon_vma *anon_vma)
 {
-	spin_lock(&anon_vma->root->lock);
+	mutex_lock(&anon_vma->root->mutex);
 }
 
 static inline void anon_vma_unlock(struct anon_vma *anon_vma)
 {
-	spin_unlock(&anon_vma->root->lock);
+	mutex_unlock(&anon_vma->root->mutex);
 }
 
 /*
Index: linux-2.6/mm/rmap.c
===================================================================
--- linux-2.6.orig/mm/rmap.c
+++ linux-2.6/mm/rmap.c
@@ -25,7 +25,7 @@
  *   mm->mmap_sem
  *     page->flags PG_locked (lock_page)
  *       mapping->i_mmap_mutex
- *         anon_vma->lock
+ *         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)
@@ -39,7 +39,7 @@
  *
  * (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      (memory_failure, collect_procs_anon)
  *     pte map lock
  */
 
@@ -306,7 +306,7 @@ static void anon_vma_ctor(void *data)
 {
 	struct anon_vma *anon_vma = data;
 
-	spin_lock_init(&anon_vma->lock);
+	mutex_init(&anon_vma->mutex);
 	atomic_set(&anon_vma->refcount, 0);
 	INIT_LIST_HEAD(&anon_vma->head);
 }
@@ -1129,7 +1129,7 @@ int try_to_unmap_one(struct page *page, 
 	/*
 	 * 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_mutex.
+	 * 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.
Index: linux-2.6/mm/mmap.c
===================================================================
--- linux-2.6.orig/mm/mmap.c
+++ linux-2.6/mm/mmap.c
@@ -2523,15 +2523,15 @@ 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->mutex, &mm->mmap_sem);
 		/*
 		 * We can safely modify head.next after taking the
-		 * anon_vma->root->lock. If some other vma in this mm shares
+		 * anon_vma->root->mutex. 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->root->lock.
+		 * anon_vma->root->mutex.
 		 */
 		if (__test_and_set_bit(0, (unsigned long *)
 				       &anon_vma->root->head.next))
@@ -2580,7 +2580,7 @@ static void vm_lock_mapping(struct mm_st
  * vma in this mm is backed by the same anon_vma or address_space.
  *
  * We can take all the locks in random order because the VM code
- * taking i_mmap_mutex or anon_vma->lock outside the mmap_sem never
+ * taking i_mmap_mutex or anon_vma->mutex outside the mmap_sem never
  * takes more than one of them in a row. Secondly we're protected
  * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex.
  *
@@ -2636,7 +2636,7 @@ 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->root->lock.
+		 * anon_vma->root->mutex.
 		 */
 		if (!__test_and_clear_bit(0, (unsigned long *)
 					  &anon_vma->root->head.next))
Index: linux-2.6/include/linux/mmu_notifier.h
===================================================================
--- linux-2.6.orig/include/linux/mmu_notifier.h
+++ linux-2.6/include/linux/mmu_notifier.h
@@ -150,7 +150,7 @@ struct mmu_notifier_ops {
  * Therefore notifier chains can only be traversed when either
  *
  * 1. mmap_sem is held.
- * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->lock).
+ * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->mutex).
  * 3. No other concurrent thread can access the list (release)
  */
 struct mmu_notifier {
Index: linux-2.6/mm/huge_memory.c
===================================================================
--- linux-2.6.orig/mm/huge_memory.c
+++ linux-2.6/mm/huge_memory.c
@@ -1128,7 +1128,7 @@ static int __split_huge_page_splitting(s
 		 * We can't temporarily set the pmd to null in order
 		 * to split it, the pmd must remain marked huge at all
 		 * times or the VM won't take the pmd_trans_huge paths
-		 * and it won't wait on the anon_vma->root->lock to
+		 * and it won't wait on the anon_vma->root->mutex to
 		 * serialize against split_huge_page*.
 		 */
 		pmdp_splitting_flush_notify(vma, address, pmd);
@@ -1315,7 +1315,7 @@ static int __split_huge_page_map(struct 
 	return ret;
 }
 
-/* must be called with anon_vma->root->lock hold */
+/* must be called with anon_vma->root->mutex hold */
 static void __split_huge_page(struct page *page,
 			      struct anon_vma *anon_vma)
 {
Index: linux-2.6/include/linux/huge_mm.h
===================================================================
--- linux-2.6.orig/include/linux/huge_mm.h
+++ linux-2.6/include/linux/huge_mm.h
@@ -91,12 +91,8 @@ extern void __split_huge_page_pmd(struct
 #define wait_split_huge_page(__anon_vma, __pmd)				\
 	do {								\
 		pmd_t *____pmd = (__pmd);				\
-		spin_unlock_wait(&(__anon_vma)->root->lock);		\
-		/*							\
-		 * spin_unlock_wait() is just a loop in C and so the	\
-		 * CPU can reorder anything around it.			\
-		 */							\
-		smp_mb();						\
+		anon_vma_lock(__anon_vma);				\
+		anon_vma_unlock(__anon_vma);				\
 		BUG_ON(pmd_trans_splitting(*____pmd) ||			\
 		       pmd_trans_huge(*____pmd));			\
 	} while (0)


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 8/8] mm: Optimize page_lock_anon_vma() fast-path

[Peter Zijlstra]

[-- Attachment #1: peter_zijlstra-mm-optimize_page_lock_anon_vma_fast-path.patch --]
[-- Type: text/plain, Size: 3739 bytes --]

Optimize the page_lock_anon_vma() fast path to be one LOCKed op,
instead of two.

Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 mm/rmap.c |   85 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 81 insertions(+), 4 deletions(-)

Index: linux-2.6/mm/rmap.c
===================================================================
--- linux-2.6.orig/mm/rmap.c
+++ linux-2.6/mm/rmap.c
@@ -371,20 +371,75 @@ struct anon_vma *page_get_anon_vma(struc
 	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 = page_get_anon_vma(page);
+	struct anon_vma *anon_vma = NULL;
+	unsigned long anon_mapping;
 
-	if (anon_vma)
-		anon_vma_lock(anon_vma);
+	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);
+	if (mutex_trylock(&anon_vma->root->mutex)) {
+		/*
+		 * If we observe a !0 refcount, then holding the lock ensures
+		 * the anon_vma will not go away, see __put_anon_vma().
+		 */
+		if (!atomic_read(&anon_vma->refcount)) {
+			anon_vma_unlock(anon_vma);
+			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;
+
+out:
+	rcu_read_unlock();
 	return anon_vma;
 }
 
 void page_unlock_anon_vma(struct anon_vma *anon_vma)
 {
 	anon_vma_unlock(anon_vma);
-	put_anon_vma(anon_vma);
 }
 
 /*
@@ -1500,6 +1555,28 @@ int try_to_munlock(struct page *page)
 
 void __put_anon_vma(struct anon_vma *anon_vma)
 {
+	/*
+	 * 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);
+	}
+
 	if (anon_vma->root != anon_vma)
 		put_anon_vma(anon_vma->root);
 	anon_vma_free(anon_vma);


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 0/8] mm: Preemptibility -v8

[Peter Zijlstra]

On Thu, 2011-02-17 at 18:05 +0100, Peter Zijlstra wrote:
> This series depends on the previous two series:
>   - mm: Simplify anon_vma lifetime rules
>   - mm: mmu_gather rework
> 
> These patches make part of the mm a lot more preemptible. It converts
> i_mmap_lock and anon_vma->lock to mutexes which together with the mmu_gather
> rework makes mmu_gather preemptible as well.
> 
> Making i_mmap_lock a mutex also enables a clean-up of the truncate code.
> 
> This also allows for preemptible mmu_notifiers, something that XPMEM I think
> wants.

---
 Documentation/lockstat.txt   |    2 
 Documentation/vm/locking     |    2 
 arch/x86/mm/hugetlbpage.c    |    4 
 fs/gfs2/main.c               |    2 
 fs/hugetlbfs/inode.c         |    4 
 fs/inode.c                   |    2 
 fs/nilfs2/page.c             |    2 
 include/linux/fs.h           |    3 
 include/linux/huge_mm.h      |    8 -
 include/linux/lockdep.h      |    3 
 include/linux/mm.h           |    2 
 include/linux/mm_types.h     |    1 
 include/linux/mmu_notifier.h |    2 
 include/linux/mutex.h        |    9 +
 include/linux/rmap.h         |   29 +-----
 kernel/fork.c                |    5 -
 kernel/mutex.c               |   25 +++--
 mm/filemap.c                 |   10 +-
 mm/filemap_xip.c             |    4 
 mm/fremap.c                  |    4 
 mm/huge_memory.c             |    4 
 mm/hugetlb.c                 |   14 +--
 mm/memory-failure.c          |    4 
 mm/memory.c                  |  197 ++++++-------------------------------------
 mm/migrate.c                 |   17 ---
 mm/mmap.c                    |   43 +++------
 mm/mremap.c                  |    7 -
 mm/rmap.c                    |  171 +++++++++++++++++++++++++++++--------
 28 files changed, 258 insertions(+), 322 deletions(-)

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 2/8] mm: Remove i_mmap_mutex lockbreak

[KAMEZAWA Hiroyuki]

On Thu, 17 Feb 2011 18:05:22 +0100
Peter Zijlstra <a.p.zijlstra@chello.nl> wrote:

> Hugh says:
>  "The only significant loser, I think, would be page reclaim (when
>   concurrent with truncation): could spin for a long time waiting for
>   the i_mmap_mutex it expects would soon be dropped? "
> 
> Counter points:
>  - cpu contention makes the spin stop (need_resched())
>  - zap pages should be freeing pages at a higher rate than reclaim
>    ever can
>  - shouldn't hold up reclaim more than lock_page() would
> 
> I think the simplification of the truncate code is definately worth
> it.
> 
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>

Maybe I have to improve batched-uncharge in memcg, whose work depends
on ZAP_BLOCK_SIZE....but the zap routine seems cleaner.

Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>