1 files changed, 54 insertions, 54 deletions

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 013cdc90f5fd..6a30916b76e5 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -24,6 +24,56 @@ static inline bool mapping_empty(struct address_space *mapping)
 }
 
 /*
+ * mapping_shrinkable - test if page cache state allows inode reclaim
+ * @mapping: the page cache mapping
+ *
+ * This checks the mapping's cache state for the pupose of inode
+ * reclaim and LRU management.
+ *
+ * The caller is expected to hold the i_lock, but is not required to
+ * hold the i_pages lock, which usually protects cache state. That's
+ * because the i_lock and the list_lru lock that protect the inode and
+ * its LRU state don't nest inside the irq-safe i_pages lock.
+ *
+ * Cache deletions are performed under the i_lock, which ensures that
+ * when an inode goes empty, it will reliably get queued on the LRU.
+ *
+ * Cache additions do not acquire the i_lock and may race with this
+ * check, in which case we'll report the inode as shrinkable when it
+ * has cache pages. This is okay: the shrinker also checks the
+ * refcount and the referenced bit, which will be elevated or set in
+ * the process of adding new cache pages to an inode.
+ */
+static inline bool mapping_shrinkable(struct address_space *mapping)
+{
+	void *head;
+
+	/*
+	 * On highmem systems, there could be lowmem pressure from the
+	 * inodes before there is highmem pressure from the page
+	 * cache. Make inodes shrinkable regardless of cache state.
+	 */
+	if (IS_ENABLED(CONFIG_HIGHMEM))
+		return true;
+
+	/* Cache completely empty? Shrink away. */
+	head = rcu_access_pointer(mapping->i_pages.xa_head);
+	if (!head)
+		return true;
+
+	/*
+	 * The xarray stores single offset-0 entries directly in the
+	 * head pointer, which allows non-resident page cache entries
+	 * to escape the shadow shrinker's list of xarray nodes. The
+	 * inode shrinker needs to pick them up under memory pressure.
+	 */
+	if (!xa_is_node(head) && xa_is_value(head))
+		return true;
+
+	return false;
+}
+
+/*
  * Bits in mapping->flags.
  */
 enum mapping_flags {
@@ -824,61 +874,11 @@ int folio_wait_private_2_killable(struct folio *folio);
 void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter);
 
 /*
- * Fault everything in given userspace address range in.
+ * Fault in userspace address range.
  */
-static inline int fault_in_pages_writeable(char __user *uaddr, size_t size)
-{
-	char __user *end = uaddr + size - 1;
-
-	if (unlikely(size == 0))
-		return 0;
-
-	if (unlikely(uaddr > end))
-		return -EFAULT;
-	/*
-	 * Writing zeroes into userspace here is OK, because we know that if
-	 * the zero gets there, we'll be overwriting it.
-	 */
-	do {
-		if (unlikely(__put_user(0, uaddr) != 0))
-			return -EFAULT;
-		uaddr += PAGE_SIZE;
-	} while (uaddr <= end);
-
-	/* Check whether the range spilled into the next page. */
-	if (((unsigned long)uaddr & PAGE_MASK) ==
-			((unsigned long)end & PAGE_MASK))
-		return __put_user(0, end);
-
-	return 0;
-}
-
-static inline int fault_in_pages_readable(const char __user *uaddr, size_t size)
-{
-	volatile char c;
-	const char __user *end = uaddr + size - 1;
-
-	if (unlikely(size == 0))
-		return 0;
-
-	if (unlikely(uaddr > end))
-		return -EFAULT;
-
-	do {
-		if (unlikely(__get_user(c, uaddr) != 0))
-			return -EFAULT;
-		uaddr += PAGE_SIZE;
-	} while (uaddr <= end);
-
-	/* Check whether the range spilled into the next page. */
-	if (((unsigned long)uaddr & PAGE_MASK) ==
-			((unsigned long)end & PAGE_MASK)) {
-		return __get_user(c, end);
-	}
-
-	(void)c;
-	return 0;
-}
+size_t fault_in_writeable(char __user *uaddr, size_t size);
+size_t fault_in_safe_writeable(const char __user *uaddr, size_t size);
+size_t fault_in_readable(const char __user *uaddr, size_t size);
 
 int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 		pgoff_t index, gfp_t gfp);