mm: page cache: store only head pages in i_pages

Transparent Huge Pages are currently stored in i_pages as pointers to
consecutive subpages.  This patch changes that to storing consecutive
pointers to the head page in preparation for storing huge pages more
efficiently in i_pages.

Large parts of this are "inspired" by Kirill's patch
https://lore.kernel.org/lkml/20170126115819.58875-2-kirill.shutemov@linux.intel.com/

[willy@infradead.org: fix swapcache pages]
  Link: http://lkml.kernel.org/r/20190324155441.GF10344@bombadil.infradead.org
[kirill@shutemov.name: hugetlb stores pages in page cache differently]
  Link: http://lkml.kernel.org/r/20190404134553.vuvhgmghlkiw2hgl@kshutemo-mobl1
Link: http://lkml.kernel.org/r/20190307153051.18815-1-willy@infradead.org
Signed-off-by: Matthew Wilcox <willy@infradead.org>
Acked-by: Jan Kara <jack@suse.cz>
Reviewed-by: Kirill Shutemov <kirill@shutemov.name>
Reviewed-and-tested-by: Song Liu <songliubraving@fb.com>
Tested-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Tested-by: Qian Cai <cai@lca.pw>
Cc: Hugh Dickins <hughd@google.com>
Cc: Song Liu <liu.song.a23@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 62 insertions, 97 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index d78f577baef2..4157f858a9c6 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -279,11 +279,11 @@ EXPORT_SYMBOL(delete_from_page_cache);
  * @pvec: pagevec with pages to delete
  *
  * The function walks over mapping->i_pages and removes pages passed in @pvec
- * from the mapping. The function expects @pvec to be sorted by page index.
+ * from the mapping. The function expects @pvec to be sorted by page index
+ * and is optimised for it to be dense.
  * It tolerates holes in @pvec (mapping entries at those indices are not
  * modified). The function expects only THP head pages to be present in the
- * @pvec and takes care to delete all corresponding tail pages from the
- * mapping as well.
+ * @pvec.
  *
  * The function expects the i_pages lock to be held.
  */
@@ -292,40 +292,44 @@ static void page_cache_delete_batch(struct address_space *mapping,
 {
         XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index);
         int total_pages = 0;
-        int i = 0, tail_pages = 0;
+        int i = 0;
         struct page *page;
 
         mapping_set_update(&xas, mapping);
         xas_for_each(&xas, page, ULONG_MAX) {
-                if (i >= pagevec_count(pvec) && !tail_pages)
+                if (i >= pagevec_count(pvec))
                         break;
+
+                /* A swap/dax/shadow entry got inserted? Skip it. */
                 if (xa_is_value(page))
                         continue;
-                if (!tail_pages) {
-                        /*
-                         * Some page got inserted in our range? Skip it. We
-                         * have our pages locked so they are protected from
-                         * being removed.
-                         */
-                        if (page != pvec->pages[i]) {
-                                VM_BUG_ON_PAGE(page->index >
-                                                pvec->pages[i]->index, page);
-                                continue;
-                        }
-                        WARN_ON_ONCE(!PageLocked(page));
-                        if (PageTransHuge(page) && !PageHuge(page))
-                                tail_pages = HPAGE_PMD_NR - 1;
+                /*
+                 * A page got inserted in our range? Skip it. We have our
+                 * pages locked so they are protected from being removed.
+                 * If we see a page whose index is higher than ours, it
+                 * means our page has been removed, which shouldn't be
+                 * possible because we're holding the PageLock.
+                 */
+                if (page != pvec->pages[i]) {
+                        VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index,
+                                        page);
+                        continue;
+                }
+
+                WARN_ON_ONCE(!PageLocked(page));
+
+                if (page->index == xas.xa_index)
                         page->mapping = NULL;
-                        /*
-                         * Leave page->index set: truncation lookup relies
-                         * upon it
-                         */
+                /* Leave page->index set: truncation lookup relies on it */
+
+                /*
+                 * Move to the next page in the vector if this is a regular
+                 * page or the index is of the last sub-page of this compound
+                 * page.
+                 */
+                if (page->index + (1UL << compound_order(page)) - 1 ==
+                                xas.xa_index)
                         i++;
-                } else {
-                        VM_BUG_ON_PAGE(page->index + HPAGE_PMD_NR - tail_pages
-                                        != pvec->pages[i]->index, page);
-                        tail_pages--;
-                }
                 xas_store(&xas, NULL);
                 total_pages++;
         }
@@ -1491,7 +1495,7 @@ EXPORT_SYMBOL(page_cache_prev_miss);
 struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
 {
         XA_STATE(xas, &mapping->i_pages, offset);
-        struct page *head, *page;
+        struct page *page;
 
         rcu_read_lock();
 repeat:
@@ -1506,25 +1510,19 @@ repeat:
         if (!page || xa_is_value(page))
                 goto out;
 
-        head = compound_head(page);
-        if (!page_cache_get_speculative(head))
+        if (!page_cache_get_speculative(page))
                 goto repeat;
 
-        /* The page was split under us? */
-        if (compound_head(page) != head) {
-                put_page(head);
-                goto repeat;
-        }
-
         /*
-         * Has the page moved?
+         * Has the page moved or been split?
          * This is part of the lockless pagecache protocol. See
          * include/linux/pagemap.h for details.
          */
         if (unlikely(page != xas_reload(&xas))) {
-                put_page(head);
+                put_page(page);
                 goto repeat;
         }
+        page = find_subpage(page, offset);
 out:
         rcu_read_unlock();
 
@@ -1706,7 +1704,6 @@ unsigned find_get_entries(struct address_space *mapping,
 
         rcu_read_lock();
         xas_for_each(&xas, page, ULONG_MAX) {
-                struct page *head;
                 if (xas_retry(&xas, page))
                         continue;
                 /*
@@ -1717,17 +1714,13 @@ unsigned find_get_entries(struct address_space *mapping,
                 if (xa_is_value(page))
                         goto export;
 
-                head = compound_head(page);
-                if (!page_cache_get_speculative(head))
+                if (!page_cache_get_speculative(page))
                         goto retry;
 
-                /* The page was split under us? */
-                if (compound_head(page) != head)
-                        goto put_page;
-
-                /* Has the page moved? */
+                /* Has the page moved or been split? */
                 if (unlikely(page != xas_reload(&xas)))
                         goto put_page;
+                page = find_subpage(page, xas.xa_index);
 
 export:
                 indices[ret] = xas.xa_index;
@@ -1736,7 +1729,7 @@ export:
                         break;
                 continue;
 put_page:
-                put_page(head);
+                put_page(page);
 retry:
                 xas_reset(&xas);
         }
@@ -1778,33 +1771,27 @@ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
 
         rcu_read_lock();
         xas_for_each(&xas, page, end) {
-                struct page *head;
                 if (xas_retry(&xas, page))
                         continue;
                 /* Skip over shadow, swap and DAX entries */
                 if (xa_is_value(page))
                         continue;
 
-                head = compound_head(page);
-                if (!page_cache_get_speculative(head))
+                if (!page_cache_get_speculative(page))
                         goto retry;
 
-                /* The page was split under us? */
-                if (compound_head(page) != head)
-                        goto put_page;
-
-                /* Has the page moved? */
+                /* Has the page moved or been split? */
                 if (unlikely(page != xas_reload(&xas)))
                         goto put_page;
 
-                pages[ret] = page;
+                pages[ret] = find_subpage(page, xas.xa_index);
                 if (++ret == nr_pages) {
                         *start = xas.xa_index + 1;
                         goto out;
                 }
                 continue;
 put_page:
-                put_page(head);
+                put_page(page);
 retry:
                 xas_reset(&xas);
         }
@@ -1849,7 +1836,6 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
 
         rcu_read_lock();
         for (page = xas_load(&xas); page; page = xas_next(&xas)) {
-                struct page *head;
                 if (xas_retry(&xas, page))
                         continue;
                 /*
@@ -1859,24 +1845,19 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
                 if (xa_is_value(page))
                         break;
 
-                head = compound_head(page);
-                if (!page_cache_get_speculative(head))
+                if (!page_cache_get_speculative(page))
                         goto retry;
 
-                /* The page was split under us? */
-                if (compound_head(page) != head)
-                        goto put_page;
-
-                /* Has the page moved? */
+                /* Has the page moved or been split? */
                 if (unlikely(page != xas_reload(&xas)))
                         goto put_page;
 
-                pages[ret] = page;
+                pages[ret] = find_subpage(page, xas.xa_index);
                 if (++ret == nr_pages)
                         break;
                 continue;
 put_page:
-                put_page(head);
+                put_page(page);
 retry:
                 xas_reset(&xas);
         }
@@ -1912,7 +1893,6 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
 
         rcu_read_lock();
         xas_for_each_marked(&xas, page, end, tag) {
-                struct page *head;
                 if (xas_retry(&xas, page))
                         continue;
                 /*
@@ -1923,26 +1903,21 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
                 if (xa_is_value(page))
                         continue;
 
-                head = compound_head(page);
-                if (!page_cache_get_speculative(head))
+                if (!page_cache_get_speculative(page))
                         goto retry;
 
-                /* The page was split under us? */
-                if (compound_head(page) != head)
-                        goto put_page;
-
-                /* Has the page moved? */
+                /* Has the page moved or been split? */
                 if (unlikely(page != xas_reload(&xas)))
                         goto put_page;
 
-                pages[ret] = page;
+                pages[ret] = find_subpage(page, xas.xa_index);
                 if (++ret == nr_pages) {
                         *index = xas.xa_index + 1;
                         goto out;
                 }
                 continue;
 put_page:
-                put_page(head);
+                put_page(page);
 retry:
                 xas_reset(&xas);
         }
@@ -1991,7 +1966,6 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
 
         rcu_read_lock();
         xas_for_each_marked(&xas, page, ULONG_MAX, tag) {
-                struct page *head;
                 if (xas_retry(&xas, page))
                         continue;
                 /*
@@ -2002,17 +1976,13 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
                 if (xa_is_value(page))
                         goto export;
 
-                head = compound_head(page);
-                if (!page_cache_get_speculative(head))
+                if (!page_cache_get_speculative(page))
                         goto retry;
 
-                /* The page was split under us? */
-                if (compound_head(page) != head)
-                        goto put_page;
-
-                /* Has the page moved? */
+                /* Has the page moved or been split? */
                 if (unlikely(page != xas_reload(&xas)))
                         goto put_page;
+                page = find_subpage(page, xas.xa_index);
 
 export:
                 indices[ret] = xas.xa_index;
@@ -2021,7 +1991,7 @@ export:
                         break;
                 continue;
 put_page:
-                put_page(head);
+                put_page(page);
 retry:
                 xas_reset(&xas);
         }
@@ -2691,7 +2661,7 @@ void filemap_map_pages(struct vm_fault *vmf,
         pgoff_t last_pgoff = start_pgoff;
         unsigned long max_idx;
         XA_STATE(xas, &mapping->i_pages, start_pgoff);
-        struct page *head, *page;
+        struct page *page;
 
         rcu_read_lock();
         xas_for_each(&xas, page, end_pgoff) {
@@ -2700,24 +2670,19 @@ void filemap_map_pages(struct vm_fault *vmf,
                 if (xa_is_value(page))
                         goto next;
 
-                head = compound_head(page);
-
                 /*
                  * Check for a locked page first, as a speculative
                  * reference may adversely influence page migration.
                  */
-                if (PageLocked(head))
+                if (PageLocked(page))
                         goto next;
-                if (!page_cache_get_speculative(head))
+                if (!page_cache_get_speculative(page))
                         goto next;
 
-                /* The page was split under us? */
-                if (compound_head(page) != head)
-                        goto skip;
-
-                /* Has the page moved? */
+                /* Has the page moved or been split? */
                 if (unlikely(page != xas_reload(&xas)))
                         goto skip;
+                page = find_subpage(page, xas.xa_index);
 
                 if (!PageUptodate(page) ||
                                 PageReadahead(page) ||