Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Matthew Wilcox <willy@infradead.org>
To:     linux-fsdevel@vger.kernel.org
Cc:     "Matthew Wilcox (Oracle)" <willy@infradead.org>,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: [PATCH v4 22/36] mm: Allow large pages to be added to the page cache
Date:   Fri, 15 May 2020 06:16:42 -0700
Message-Id: <20200515131656.12890-23-willy@infradead.org>
In-Reply-To: <20200515131656.12890-1-willy@infradead.org>
References: <20200515131656.12890-1-willy@infradead.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: "Matthew Wilcox (Oracle)" <willy@infradead.org>

We return -EEXIST if there are any non-shadow entries in the page
cache in the range covered by the large page.  If there are multiple
shadow entries in the range, we set *shadowp to one of them (currently
the one at the highest index).  If that turns out to be the wrong
answer, we can implement something more complex.  This is mostly
modelled after the equivalent function in the shmem code.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 mm/filemap.c | 44 +++++++++++++++++++++++++++++++-------------
 1 file changed, 31 insertions(+), 13 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index 9abba062973a..437484d42b78 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -834,6 +834,7 @@ static int __add_to_page_cache_locked(struct page *page,
 	int huge = PageHuge(page);
 	struct mem_cgroup *memcg;
 	int error;
+	unsigned int nr = 1;
 	void *old;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
@@ -845,31 +846,48 @@ static int __add_to_page_cache_locked(struct page *page,
 					      gfp_mask, &memcg, false);
 		if (error)
 			return error;
+		xas_set_order(&xas, offset, thp_order(page));
+		nr = hpage_nr_pages(page);
 	}
 
-	get_page(page);
+	page_ref_add(page, nr);
 	page->mapping = mapping;
 	page->index = offset;
 
 	do {
+		unsigned long exceptional = 0;
+		unsigned int i = 0;
+
 		xas_lock_irq(&xas);
-		old = xas_load(&xas);
-		if (old && !xa_is_value(old))
-			xas_set_err(&xas, -EEXIST);
-		xas_store(&xas, page);
+		xas_for_each_conflict(&xas, old) {
+			if (!xa_is_value(old)) {
+				xas_set_err(&xas, -EEXIST);
+				break;
+			}
+			exceptional++;
+			if (shadowp)
+				*shadowp = old;
+		}
+		xas_create_range(&xas);
 		if (xas_error(&xas))
 			goto unlock;
 
-		if (xa_is_value(old)) {
-			mapping->nrexceptional--;
-			if (shadowp)
-				*shadowp = old;
+next:
+		xas_store(&xas, page);
+		if (++i < nr) {
+			xas_next(&xas);
+			goto next;
 		}
-		mapping->nrpages++;
+		mapping->nrexceptional -= exceptional;
+		mapping->nrpages += nr;
 
 		/* hugetlb pages do not participate in page cache accounting */
-		if (!huge)
-			__inc_node_page_state(page, NR_FILE_PAGES);
+		if (!huge) {
+			__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES,
+						nr);
+			if (nr > 1)
+				__inc_node_page_state(page, NR_FILE_THPS);
+		}
 unlock:
 		xas_unlock_irq(&xas);
 	} while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK));
@@ -886,7 +904,7 @@ static int __add_to_page_cache_locked(struct page *page,
 	/* Leave page->index set: truncation relies upon it */
 	if (!huge)
 		mem_cgroup_cancel_charge(page, memcg, false);
-	put_page(page);
+	page_ref_sub(page, nr);
 	return xas_error(&xas);
 }
 ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO);
-- 
2.26.2