Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

9 files changed, 109 insertions, 78 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index cf7d027a8844..ddffc74cdebe 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -35,6 +35,7 @@
 #include <linux/limits.h>
 #include <linux/mutex.h>
 #include <linux/rbtree.h>
+#include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index eac0ba561491..740c4f52059c 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -391,10 +391,11 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	struct task_struct *tsk;
 	struct anon_vma *av;
 
-	read_lock(&tasklist_lock);
 	av = page_lock_anon_vma(page);
 	if (av == NULL)	/* Not actually mapped anymore */
-		goto out;
+		return;
+
+	read_lock(&tasklist_lock);
 	for_each_process (tsk) {
 		struct anon_vma_chain *vmac;
 
@@ -408,9 +409,8 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 				add_to_kill(tsk, page, vma, to_kill, tkc);
 		}
 	}
-	page_unlock_anon_vma(av);
-out:
 	read_unlock(&tasklist_lock);
+	page_unlock_anon_vma(av);
 }
 
 /*
@@ -424,17 +424,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	struct prio_tree_iter iter;
 	struct address_space *mapping = page->mapping;
 
-	/*
-	 * A note on the locking order between the two locks.
-	 * We don't rely on this particular order.
-	 * If you have some other code that needs a different order
-	 * feel free to switch them around. Or add a reverse link
-	 * from mm_struct to task_struct, then this could be all
-	 * done without taking tasklist_lock and looping over all tasks.
-	 */
-
-	read_lock(&tasklist_lock);
 	mutex_lock(&mapping->i_mmap_mutex);
+	read_lock(&tasklist_lock);
 	for_each_process(tsk) {
 		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
 
@@ -454,8 +445,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 				add_to_kill(tsk, page, vma, to_kill, tkc);
 		}
 	}
-	mutex_unlock(&mapping->i_mmap_mutex);
 	read_unlock(&tasklist_lock);
+	mutex_unlock(&mapping->i_mmap_mutex);
 }
 
 /*
diff --git a/mm/memory.c b/mm/memory.c
index 87d935333f0d..40b7531ee8ba 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2798,30 +2798,6 @@ void unmap_mapping_range(struct address_space *mapping,
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
-int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
-{
-	struct address_space *mapping = inode->i_mapping;
-
-	/*
-	 * If the underlying filesystem is not going to provide
-	 * a way to truncate a range of blocks (punch a hole) -
-	 * we should return failure right now.
-	 */
-	if (!inode->i_op->truncate_range)
-		return -ENOSYS;
-
-	mutex_lock(&inode->i_mutex);
-	down_write(&inode->i_alloc_sem);
-	unmap_mapping_range(mapping, offset, (end - offset), 1);
-	truncate_inode_pages_range(mapping, offset, end);
-	unmap_mapping_range(mapping, offset, (end - offset), 1);
-	inode->i_op->truncate_range(inode, offset, end);
-	up_write(&inode->i_alloc_sem);
-	mutex_unlock(&inode->i_mutex);
-
-	return 0;
-}
-
 /*
  * We enter with non-exclusive mmap_sem (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 02159c755136..c46887b5a11e 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -498,7 +498,9 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 	 * The node we allocated has no zone fallback lists. For avoiding
 	 * to access not-initialized zonelist, build here.
 	 */
+	mutex_lock(&zonelists_mutex);
 	build_all_zonelists(NULL);
+	mutex_unlock(&zonelists_mutex);
 
 	return pgdat;
 }
@@ -521,7 +523,7 @@ int mem_online_node(int nid)
 
 	lock_memory_hotplug();
 	pgdat = hotadd_new_pgdat(nid, 0);
-	if (pgdat) {
+	if (!pgdat) {
 		ret = -ENOMEM;
 		goto out;
 	}
diff --git a/mm/rmap.c b/mm/rmap.c
index 27dfd3b82b0f..23295f65ae43 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -38,9 +38,8 @@
  *                           in arch-dependent flush_dcache_mmap_lock,
  *                           within inode_wb_list_lock in __sync_single_inode)
  *
- * (code doesn't rely on that order so it could be switched around)
- * ->tasklist_lock
- *   anon_vma->mutex      (memory_failure, collect_procs_anon)
+ * anon_vma->mutex,mapping->i_mutex      (memory_failure, collect_procs_anon)
+ *   ->tasklist_lock
  *     pte map lock
  */
 
diff --git a/mm/shmem.c b/mm/shmem.c
index d221a1cfd7b1..fcedf5464eb7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -539,7 +539,7 @@ static void shmem_free_pages(struct list_head *next)
 	} while (next);
 }
 
-static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
+void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	unsigned long idx;
@@ -562,6 +562,8 @@ static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
 	spinlock_t *punch_lock;
 	unsigned long upper_limit;
 
+	truncate_inode_pages_range(inode->i_mapping, start, end);
+
 	inode->i_ctime = inode->i_mtime = CURRENT_TIME;
 	idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	if (idx >= info->next_index)
@@ -738,16 +740,8 @@ done2:
 		 * lowered next_index.  Also, though shmem_getpage checks
 		 * i_size before adding to cache, no recheck after: so fix the
 		 * narrow window there too.
-		 *
-		 * Recalling truncate_inode_pages_range and unmap_mapping_range
-		 * every time for punch_hole (which never got a chance to clear
-		 * SHMEM_PAGEIN at the start of vmtruncate_range) is expensive,
-		 * yet hardly ever necessary: try to optimize them out later.
 		 */
 		truncate_inode_pages_range(inode->i_mapping, start, end);
-		if (punch_hole)
-			unmap_mapping_range(inode->i_mapping, start,
-							end - start, 1);
 	}
 
 	spin_lock(&info->lock);
@@ -766,22 +760,23 @@ done2:
 		shmem_free_pages(pages_to_free.next);
 	}
 }
+EXPORT_SYMBOL_GPL(shmem_truncate_range);
 
-static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
+static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = dentry->d_inode;
-	loff_t newsize = attr->ia_size;
 	int error;
 
 	error = inode_change_ok(inode, attr);
 	if (error)
 		return error;
 
-	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)
-					&& newsize != inode->i_size) {
+	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
+		loff_t oldsize = inode->i_size;
+		loff_t newsize = attr->ia_size;
 		struct page *page = NULL;
 
-		if (newsize < inode->i_size) {
+		if (newsize < oldsize) {
 			/*
 			 * If truncating down to a partial page, then
 			 * if that page is already allocated, hold it
@@ -810,12 +805,19 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
 				spin_unlock(&info->lock);
 			}
 		}
-
-		/* XXX(truncate): truncate_setsize should be called last */
-		truncate_setsize(inode, newsize);
+		if (newsize != oldsize) {
+			i_size_write(inode, newsize);
+			inode->i_ctime = inode->i_mtime = CURRENT_TIME;
+		}
+		if (newsize < oldsize) {
+			loff_t holebegin = round_up(newsize, PAGE_SIZE);
+			unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
+			shmem_truncate_range(inode, newsize, (loff_t)-1);
+			/* unmap again to remove racily COWed private pages */
+			unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
+		}
 		if (page)
 			page_cache_release(page);
-		shmem_truncate_range(inode, newsize, (loff_t)-1);
 	}
 
 	setattr_copy(inode, attr);
@@ -832,7 +834,6 @@ static void shmem_evict_inode(struct inode *inode)
 	struct shmem_xattr *xattr, *nxattr;
 
 	if (inode->i_mapping->a_ops == &shmem_aops) {
-		truncate_inode_pages(inode->i_mapping, 0);
 		shmem_unacct_size(info->flags, inode->i_size);
 		inode->i_size = 0;
 		shmem_truncate_range(inode, 0, (loff_t)-1);
@@ -2706,7 +2707,7 @@ static const struct file_operations shmem_file_operations = {
 };
 
 static const struct inode_operations shmem_inode_operations = {
-	.setattr	= shmem_notify_change,
+	.setattr	= shmem_setattr,
 	.truncate_range	= shmem_truncate_range,
 #ifdef CONFIG_TMPFS_XATTR
 	.setxattr	= shmem_setxattr,
@@ -2739,7 +2740,7 @@ static const struct inode_operations shmem_dir_inode_operations = {
 	.removexattr	= shmem_removexattr,
 #endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
-	.setattr	= shmem_notify_change,
+	.setattr	= shmem_setattr,
 	.check_acl	= generic_check_acl,
 #endif
 };
@@ -2752,7 +2753,7 @@ static const struct inode_operations shmem_special_inode_operations = {
 	.removexattr	= shmem_removexattr,
 #endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
-	.setattr	= shmem_notify_change,
+	.setattr	= shmem_setattr,
 	.check_acl	= generic_check_acl,
 #endif
 };
@@ -2908,6 +2909,12 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
 	return 0;
 }
 
+void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
+{
+	truncate_inode_pages_range(inode->i_mapping, start, end);
+}
+EXPORT_SYMBOL_GPL(shmem_truncate_range);
+
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 /**
  * mem_cgroup_get_shmem_target - find a page or entry assigned to the shmem file
@@ -3028,3 +3035,26 @@ int shmem_zero_setup(struct vm_area_struct *vma)
 	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }
+
+/**
+ * shmem_read_mapping_page_gfp - read into page cache, using specified page allocation flags.
+ * @mapping:	the page's address_space
+ * @index:	the page index
+ * @gfp:	the page allocator flags to use if allocating
+ *
+ * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)",
+ * with any new page allocations done using the specified allocation flags.
+ * But read_cache_page_gfp() uses the ->readpage() method: which does not
+ * suit tmpfs, since it may have pages in swapcache, and needs to find those
+ * for itself; although drivers/gpu/drm i915 and ttm rely upon this support.
+ *
+ * Provide a stub for those callers to start using now, then later
+ * flesh it out to call shmem_getpage() with additional gfp mask, when
+ * shmem_file_splice_read() is added and shmem_readpage() is removed.
+ */
+struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
+					 pgoff_t index, gfp_t gfp)
+{
+	return read_cache_page_gfp(mapping, index, gfp);
+}
+EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index d537d29e9b7b..ff8dc1a18cb4 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -14,7 +14,7 @@
 #include <linux/vmalloc.h>
 #include <linux/pagemap.h>
 #include <linux/namei.h>
-#include <linux/shm.h>
+#include <linux/shmem_fs.h>
 #include <linux/blkdev.h>
 #include <linux/random.h>
 #include <linux/writeback.h>
diff --git a/mm/truncate.c b/mm/truncate.c
index 3a29a6180212..e13f22efaad7 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -304,6 +304,11 @@ EXPORT_SYMBOL(truncate_inode_pages_range);
  * @lstart: offset from which to truncate
  *
  * Called under (and serialised by) inode->i_mutex.
+ *
+ * Note: When this function returns, there can be a page in the process of
+ * deletion (inside __delete_from_page_cache()) in the specified range.  Thus
+ * mapping->nrpages can be non-zero when this function returns even after
+ * truncation of the whole mapping.
  */
 void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
 {
@@ -603,3 +608,27 @@ int vmtruncate(struct inode *inode, loff_t offset)
 	return 0;
 }
 EXPORT_SYMBOL(vmtruncate);
+
+int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
+{
+	struct address_space *mapping = inode->i_mapping;
+
+	/*
+	 * If the underlying filesystem is not going to provide
+	 * a way to truncate a range of blocks (punch a hole) -
+	 * we should return failure right now.
+	 */
+	if (!inode->i_op->truncate_range)
+		return -ENOSYS;
+
+	mutex_lock(&inode->i_mutex);
+	down_write(&inode->i_alloc_sem);
+	unmap_mapping_range(mapping, offset, (end - offset), 1);
+	inode->i_op->truncate_range(inode, offset, end);
+	/* unmap again to remove racily COWed private pages */
+	unmap_mapping_range(mapping, offset, (end - offset), 1);
+	up_write(&inode->i_alloc_sem);
+	mutex_unlock(&inode->i_mutex);
+
+	return 0;
+}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8ff834e19c24..4f49535d4cd3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1995,14 +1995,13 @@ restart:
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
+static void shrink_zones(int priority, struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
-	unsigned long total_scanned = 0;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask), sc->nodemask) {
@@ -2017,19 +2016,23 @@ static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
 				continue;
 			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;	/* Let kswapd poll it */
+			/*
+			 * This steals pages from memory cgroups over softlimit
+			 * and returns the number of reclaimed pages and
+			 * scanned pages. This works for global memory pressure
+			 * and balancing, not for a memcg's limit.
+			 */
+			nr_soft_scanned = 0;
+			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+						sc->order, sc->gfp_mask,
+						&nr_soft_scanned);
+			sc->nr_reclaimed += nr_soft_reclaimed;
+			sc->nr_scanned += nr_soft_scanned;
+			/* need some check for avoid more shrink_zone() */
 		}
 
-		nr_soft_scanned = 0;
-		nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
-							sc->order, sc->gfp_mask,
-							&nr_soft_scanned);
-		sc->nr_reclaimed += nr_soft_reclaimed;
-		total_scanned += nr_soft_scanned;
-
 		shrink_zone(priority, zone, sc);
 	}
-
-	return total_scanned;
 }
 
 static bool zone_reclaimable(struct zone *zone)
@@ -2094,7 +2097,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token(sc->mem_cgroup);
-		total_scanned += shrink_zones(priority, zonelist, sc);
+		shrink_zones(priority, zonelist, sc);
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups