mm: factor find_get_incore_page out of mincore_page

Patch series "Return head pages from find_*_entry", v2.

This patch series started out as part of the THP patch set, but it has
some nice effects along the way and it seems worth splitting it out and
submitting separately.

Currently find_get_entry() and find_lock_entry() return the page
corresponding to the requested index, but the first thing most callers do
is find the head page, which we just threw away.  As part of auditing all
the callers, I found some misuses of the APIs and some plain
inefficiencies that I've fixed.

The diffstat is unflattering, but I added more kernel-doc and a new wrapper.

This patch (of 8);

Provide this functionality from the swap cache.  It's useful for
more than just mincore().
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Link: https://lkml.kernel.org/r/20200910183318.20139-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200910183318.20139-2-willy@infradead.orgSigned-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/swap.h

@@ -427,6 +427,7 @@ extern void free_pages_and_swap_cache(struct page **, int);
 extern struct page *lookup_swap_cache(swp_entry_t entry,
 				      struct vm_area_struct *vma,
 				      unsigned long addr);
+struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index);
 extern struct page *read_swap_cache_async(swp_entry_t, gfp_t,
 			struct vm_area_struct *vma, unsigned long addr,
 			bool do_poll);
@@ -570,6 +571,12 @@ static inline struct page *lookup_swap_cache(swp_entry_t swp,
 	return NULL;
 }
 
+static inline
+struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index)
+{
+	return find_get_page(mapping, index);
+}
+
 static inline int add_to_swap(struct page *page)
 {
 	return 0;

mm/mincore.c

@@ -48,7 +48,7 @@ static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
  * and is up to date; i.e. that no page-in operation would be required
  * at this time if an application were to map and access this page.
  */
-static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
+static unsigned char mincore_page(struct address_space *mapping, pgoff_t index)
 {
 	unsigned char present = 0;
 	struct page *page;
@@ -59,31 +59,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 	 * any other file mapping (ie. marked !present and faulted in with
 	 * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
 	 */
-#ifdef CONFIG_SWAP
-	if (shmem_mapping(mapping)) {
-		page = find_get_entry(mapping, pgoff);
-		/*
-		 * shmem/tmpfs may return swap: account for swapcache
-		 * page too.
-		 */
-		if (xa_is_value(page)) {
-			swp_entry_t swp = radix_to_swp_entry(page);
-			struct swap_info_struct *si;
-
-			/* Prevent swap device to being swapoff under us */
-			si = get_swap_device(swp);
-			if (si) {
-				page = find_get_page(swap_address_space(swp),
-						     swp_offset(swp));
-				put_swap_device(si);
-			} else
-				page = NULL;
-		}
-	} else
-		page = find_get_page(mapping, pgoff);
-#else
-	page = find_get_page(mapping, pgoff);
-#endif
+	page = find_get_incore_page(mapping, index);
 	if (page) {
 		present = PageUptodate(page);
 		put_page(page);

mm/swap_state.c

@@ -21,6 +21,7 @@
 #include <linux/vmalloc.h>
 #include <linux/swap_slots.h>
 #include <linux/huge_mm.h>
+#include <linux/shmem_fs.h>
 #include "internal.h"
 
 /*
@@ -414,6 +415,37 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,
 	return page;
 }
 
+/**
+ * find_get_incore_page - Find and get a page from the page or swap caches.
+ * @mapping: The address_space to search.
+ * @index: The page cache index.
+ *
+ * This differs from find_get_page() in that it will also look for the
+ * page in the swap cache.
+ *
+ * Return: The found page or %NULL.
+ */
+struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index)
+{
+	swp_entry_t swp;
+	struct swap_info_struct *si;
+	struct page *page = find_get_entry(mapping, index);
+
+	if (!xa_is_value(page))
+		return page;
+	if (!shmem_mapping(mapping))
+		return NULL;
+
+	swp = radix_to_swp_entry(page);
+	/* Prevent swapoff from happening to us */
+	si = get_swap_device(swp);
+	if (!si)
+		return NULL;
+	page = find_get_page(swap_address_space(swp), swp_offset(swp));
+	put_swap_device(si);
+	return page;
+}
+
 struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			struct vm_area_struct *vma, unsigned long addr,
 			bool *new_page_allocated)