Merge branch 'topic/hw-constraint-single' into for-next

5 files changed, 27 insertions, 25 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 72940fb38666..1cc5467cf36c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2473,6 +2473,21 @@ ssize_t generic_perform_write(struct file *file,
 						iov_iter_count(i));
 
 again:
+		/*
+		 * Bring in the user page that we will copy from _first_.
+		 * Otherwise there's a nasty deadlock on copying from the
+		 * same page as we're writing to, without it being marked
+		 * up-to-date.
+		 *
+		 * Not only is this an optimisation, but it is also required
+		 * to check that the address is actually valid, when atomic
+		 * usercopies are used, below.
+		 */
+		if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
+			status = -EFAULT;
+			break;
+		}
+
 		status = a_ops->write_begin(file, mapping, pos, bytes, flags,
 						&page, &fsdata);
 		if (unlikely(status < 0))
@@ -2480,17 +2495,8 @@ again:
 
 		if (mapping_writably_mapped(mapping))
 			flush_dcache_page(page);
-		/*
-		 * 'page' is now locked.  If we are trying to copy from a
-		 * mapping of 'page' in userspace, the copy might fault and
-		 * would need PageUptodate() to complete.  But, page can not be
-		 * made Uptodate without acquiring the page lock, which we hold.
-		 * Deadlock.  Avoid with pagefault_disable().  Fix up below with
-		 * iov_iter_fault_in_readable().
-		 */
-		pagefault_disable();
+
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
-		pagefault_enable();
 		flush_dcache_page(page);
 
 		status = a_ops->write_end(file, mapping, pos, bytes, copied,
@@ -2513,14 +2519,6 @@ again:
 			 */
 			bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
 						iov_iter_single_seg_count(i));
-			/*
-			 * This is the fallback to recover if the copy from
-			 * userspace above faults.
-			 */
-			if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
-				status = -EFAULT;
-				break;
-			}
 			goto again;
 		}
 		pos += copied;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1fedbde68f59..d9b5c817dce8 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3387,6 +3387,7 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
 	ret = page_counter_memparse(args, "-1", &threshold);
 	if (ret)
 		return ret;
+	threshold <<= PAGE_SHIFT;
 
 	mutex_lock(&memcg->thresholds_lock);
 
diff --git a/mm/memory.c b/mm/memory.c
index 9cb27470fee9..deb679c31f2a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2426,6 +2426,8 @@ void unmap_mapping_range(struct address_space *mapping,
 	if (details.last_index < details.first_index)
 		details.last_index = ULONG_MAX;
 
+
+	/* DAX uses i_mmap_lock to serialise file truncate vs page fault */
 	i_mmap_lock_write(mapping);
 	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
 		unmap_mapping_range_tree(&mapping->i_mmap, &details);
diff --git a/mm/readahead.c b/mm/readahead.c
index 60cd846a9a44..24682f6f4cfd 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -89,8 +89,8 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
 	while (!list_empty(pages)) {
 		page = list_to_page(pages);
 		list_del(&page->lru);
-		if (add_to_page_cache_lru(page, mapping,
-					page->index, GFP_KERNEL)) {
+		if (add_to_page_cache_lru(page, mapping, page->index,
+				GFP_KERNEL & mapping_gfp_mask(mapping))) {
 			read_cache_pages_invalidate_page(mapping, page);
 			continue;
 		}
@@ -127,8 +127,8 @@ static int read_pages(struct address_space *mapping, struct file *filp,
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
 		struct page *page = list_to_page(pages);
 		list_del(&page->lru);
-		if (!add_to_page_cache_lru(page, mapping,
-					page->index, GFP_KERNEL)) {
+		if (!add_to_page_cache_lru(page, mapping, page->index,
+				GFP_KERNEL & mapping_gfp_mask(mapping))) {
 			mapping->a_ops->readpage(filp, page);
 		}
 		page_cache_release(page);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 4f5cd974e11a..fbf14485a049 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1363,15 +1363,16 @@ static cpumask_var_t cpu_stat_off;
 
 static void vmstat_update(struct work_struct *w)
 {
-	if (refresh_cpu_vm_stats())
+	if (refresh_cpu_vm_stats()) {
 		/*
 		 * Counters were updated so we expect more updates
 		 * to occur in the future. Keep on running the
 		 * update worker thread.
 		 */
-		schedule_delayed_work(this_cpu_ptr(&vmstat_work),
+		schedule_delayed_work_on(smp_processor_id(),
+			this_cpu_ptr(&vmstat_work),
 			round_jiffies_relative(sysctl_stat_interval));
-	else {
+	} else {
 		/*
 		 * We did not update any counters so the app may be in
 		 * a mode where it does not cause counter updates.