mm: pagecache add lock

Add a per address space lock around adding pages to the pagecache - making it
possible for fallocate INSERT_RANGE/COLLAPSE_RANGE to work correctly, and also
hopefully making truncate and dio a bit saner.

1 files changed, 89 insertions, 10 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 45f1c6d73b5b..b147e55a8d67 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -111,6 +111,73 @@
  *   ->tasklist_lock            (memory_failure, collect_procs_ao)
  */
 
+static void __pagecache_lock_put(struct pagecache_lock *lock, long i)
+{
+	BUG_ON(atomic_long_read(&lock->v) == 0);
+
+	if (atomic_long_sub_return_release(i, &lock->v) == 0)
+		wake_up_all(&lock->wait);
+}
+
+static bool __pagecache_lock_tryget(struct pagecache_lock *lock, long i)
+{
+	long v = atomic_long_read(&lock->v), old;
+
+	do {
+		old = v;
+
+		if (i > 0 ? v < 0 : v > 0)
+			return false;
+	} while ((v = atomic_long_cmpxchg_acquire(&lock->v,
+					old, old + i)) != old);
+	return true;
+}
+
+static void __pagecache_lock_get(struct pagecache_lock *lock, long i)
+{
+	wait_event(lock->wait, __pagecache_lock_tryget(lock, i));
+}
+
+void pagecache_add_put(struct pagecache_lock *lock)
+{
+	__pagecache_lock_put(lock, 1);
+}
+EXPORT_SYMBOL(pagecache_add_put);
+
+void pagecache_add_get(struct pagecache_lock *lock)
+{
+	__pagecache_lock_get(lock, 1);
+}
+EXPORT_SYMBOL(pagecache_add_get);
+
+void __pagecache_block_put(struct pagecache_lock *lock)
+{
+	__pagecache_lock_put(lock, -1);
+}
+EXPORT_SYMBOL(__pagecache_block_put);
+
+void __pagecache_block_get(struct pagecache_lock *lock)
+{
+	__pagecache_lock_get(lock, -1);
+}
+EXPORT_SYMBOL(__pagecache_block_get);
+
+void pagecache_block_put(struct pagecache_lock *lock)
+{
+	BUG_ON(current->pagecache_lock != lock);
+	current->pagecache_lock = NULL;
+	__pagecache_lock_put(lock, -1);
+}
+EXPORT_SYMBOL(pagecache_block_put);
+
+void pagecache_block_get(struct pagecache_lock *lock)
+{
+	__pagecache_lock_get(lock, -1);
+	BUG_ON(current->pagecache_lock);
+	current->pagecache_lock = lock;
+}
+EXPORT_SYMBOL(pagecache_block_get);
+
 static int page_cache_tree_insert(struct address_space *mapping,
 				  struct page *page, void **shadowp)
 {
@@ -858,19 +925,19 @@ static int __add_to_page_cache_locked(struct page *page,
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageSwapBacked(page), page);
 
+	if (current->pagecache_lock != &mapping->add_lock)
+		pagecache_add_get(&mapping->add_lock);
+
 	if (!huge) {
 		error = mem_cgroup_try_charge(page, current->mm,
 					      gfp_mask, &memcg, false);
 		if (error)
-			return error;
+			goto err;
 	}
 
 	error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
-	if (error) {
-		if (!huge)
-			mem_cgroup_cancel_charge(page, memcg, false);
-		return error;
-	}
+	if (error)
+		goto err_uncharge;
 
 	get_page(page);
 	page->mapping = mapping;
@@ -889,15 +956,20 @@ static int __add_to_page_cache_locked(struct page *page,
 	if (!huge)
 		mem_cgroup_commit_charge(page, memcg, false, false);
 	trace_mm_filemap_add_to_page_cache(page);
-	return 0;
+err:
+	if (current->pagecache_lock != &mapping->add_lock)
+		pagecache_add_put(&mapping->add_lock);
+
+	return error;
 err_insert:
 	page->mapping = NULL;
 	/* Leave page->index set: truncation relies upon it */
 	xa_unlock_irq(&mapping->i_pages);
+	put_page(page);
+err_uncharge:
 	if (!huge)
 		mem_cgroup_cancel_charge(page, memcg, false);
-	put_page(page);
-	return error;
+	goto err;
 }
 
 /**
@@ -2532,7 +2604,14 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	 * Do we have something in the page cache already?
 	 */
 	page = find_get_page(mapping, offset);
-	if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
+	if (unlikely(current->pagecache_lock == &mapping->add_lock)) {
+		/*
+		 * fault from e.g. dio -> get_user_pages() - _don't_ want to do
+		 * readahead, only read in page we need:
+		 */
+		if (!page)
+			goto no_cached_page;
+	} else if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
 		/*
 		 * We found the page, so try async readahead before
 		 * waiting for the lock.