Merge branch 'block-for-2.6.39-core' of ssh://master.kernel.org/pub/scm/linux/kernel/git/tj/misc into for-2.6.39/core

8 files changed, 34 insertions, 21 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 8e8c1832486..5823698c2b7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2648,6 +2648,7 @@ void unmap_mapping_range(struct address_space *mapping,
 		details.last_index = ULONG_MAX;
 	details.i_mmap_lock = &mapping->i_mmap_lock;
 
+	mutex_lock(&mapping->unmap_mutex);
 	spin_lock(&mapping->i_mmap_lock);
 
 	/* Protect against endless unmapping loops */
@@ -2664,6 +2665,7 @@ void unmap_mapping_range(struct address_space *mapping,
 	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->unmap_mutex);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 368fc9d2361..49355a970be 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1830,7 +1830,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
 		unsigned nid;
 
-		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
+		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
 		mpol_cond_put(pol);
 		page = alloc_page_interleave(gfp, order, nid);
 		put_mems_allowed();
diff --git a/mm/migrate.c b/mm/migrate.c
index 76611525380..352de555626 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1287,14 +1287,14 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 		return -EPERM;
 
 	/* Find the mm_struct */
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	task = pid ? find_task_by_vpid(pid) : current;
 	if (!task) {
-		read_unlock(&tasklist_lock);
+		rcu_read_unlock();
 		return -ESRCH;
 	}
 	mm = get_task_mm(task);
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	if (!mm)
 		return -EINVAL;
diff --git a/mm/mremap.c b/mm/mremap.c
index 9925b6391b8..1de98d492dd 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -94,9 +94,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 		 */
 		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;
+		new_vma->vm_truncate_count = 0;
 	}
 
 	/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a873e61e312..cdef1d4b4e4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5376,10 +5376,9 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count)
 	for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) {
 		unsigned long check = pfn + iter;
 
-		if (!pfn_valid_within(check)) {
-			iter++;
+		if (!pfn_valid_within(check))
 			continue;
-		}
+
 		page = pfn_to_page(check);
 		if (!page_count(page)) {
 			if (PageBuddy(page))
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 07a458d72fa..0341c5700e3 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1940,7 +1940,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 
 	error = -EINVAL;
 	if (S_ISBLK(inode->i_mode)) {
-		bdev = I_BDEV(inode);
+		bdev = bdgrab(I_BDEV(inode));
 		error = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL,
 				   sys_swapon);
 		if (error < 0) {
diff --git a/mm/truncate.c b/mm/truncate.c
index 49feb46e77b..d64296be00d 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -225,6 +225,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	next = start;
 	while (next <= end &&
 	       pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
+		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 			pgoff_t page_index = page->index;
@@ -247,6 +248,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			unlock_page(page);
 		}
 		pagevec_release(&pvec);
+		mem_cgroup_uncharge_end();
 		cond_resched();
 	}
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 17497d0cd8b..6771ea70bfe 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1841,16 +1841,28 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	if (!(sc->reclaim_mode & RECLAIM_MODE_COMPACTION))
 		return false;
 
-	/*
-	 * If we failed to reclaim and have scanned the full list, stop.
-	 * NOTE: Checking just nr_reclaimed would exit reclaim/compaction far
-	 *       faster but obviously would be less likely to succeed
-	 *       allocation. If this is desirable, use GFP_REPEAT to decide
-	 *       if both reclaimed and scanned should be checked or just
-	 *       reclaimed
-	 */
-	if (!nr_reclaimed && !nr_scanned)
-		return false;
+	/* Consider stopping depending on scan and reclaim activity */
+	if (sc->gfp_mask & __GFP_REPEAT) {
+		/*
+		 * For __GFP_REPEAT allocations, stop reclaiming if the
+		 * full LRU list has been scanned and we are still failing
+		 * to reclaim pages. This full LRU scan is potentially
+		 * expensive but a __GFP_REPEAT caller really wants to succeed
+		 */
+		if (!nr_reclaimed && !nr_scanned)
+			return false;
+	} else {
+		/*
+		 * For non-__GFP_REPEAT allocations which can presumably
+		 * fail without consequence, stop if we failed to reclaim
+		 * any pages from the last SWAP_CLUSTER_MAX number of
+		 * pages that were scanned. This will return to the
+		 * caller faster at the risk reclaim/compaction and
+		 * the resulting allocation attempt fails
+		 */
+		if (!nr_reclaimed)
+			return false;
+	}
 
 	/*
 	 * If we have not reclaimed enough pages for compaction and the