[PATCH v9 04/14] mm/gup: check for isolation errors

From: Pavel Tatashin <pasha.tatashin@soleen.com>
To: pasha.tatashin@soleen.com, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, akpm@linux-foundation.org, vbabka@suse.cz,
	mhocko@suse.com, david@redhat.com, osalvador@suse.de,
	dan.j.williams@intel.com, sashal@kernel.org,
	tyhicks@linux.microsoft.com, iamjoonsoo.kim@lge.com,
	mike.kravetz@oracle.com, rostedt@goodmis.org, mingo@redhat.com,
	jgg@ziepe.ca, peterz@infradead.org, mgorman@suse.de,
	willy@infradead.org, rientjes@google.com, jhubbard@nvidia.com,
	linux-doc@vger.kernel.org, ira.weiny@intel.com,
	linux-kselftest@vger.kernel.org, jmorris@namei.org
Subject: [PATCH v9 04/14] mm/gup: check for isolation errors
Date: Mon,  1 Feb 2021 10:38:17 -0500	[thread overview]
Message-ID: <20210201153827.444374-5-pasha.tatashin@soleen.com> (raw)
In-Reply-To: <20210201153827.444374-1-pasha.tatashin@soleen.com>

It is still possible that we pin movable CMA pages if there are isolation
errors and cma_page_list stays empty when we check again.

Check for isolation errors, and return success only when there are no
isolation errors, and cma_page_list is empty after checking.

Because isolation errors are transient, we retry indefinitely.

Fixes: 9a4e9f3b2d73 ("mm: update get_user_pages_longterm to migrate pages allocated from CMA region")
Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
---
 mm/gup.c | 60 ++++++++++++++++++++++++++++++++------------------------
 1 file changed, 34 insertions(+), 26 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 88ce41f41543..7ecca2d66dff 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1555,8 +1555,8 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm,
 					struct vm_area_struct **vmas,
 					unsigned int gup_flags)
 {
-	unsigned long i;
-	bool drain_allow = true;
+	unsigned long i, isolation_error_count;
+	bool drain_allow;
 	LIST_HEAD(cma_page_list);
 	long ret = nr_pages;
 	struct page *prev_head, *head;
@@ -1567,6 +1567,8 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm,
 
 check_again:
 	prev_head = NULL;
+	isolation_error_count = 0;
+	drain_allow = true;
 	for (i = 0; i < nr_pages; i++) {
 		head = compound_head(pages[i]);
 		if (head == prev_head)
@@ -1578,25 +1580,35 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm,
 		 * of the CMA zone if possible.
 		 */
 		if (is_migrate_cma_page(head)) {
-			if (PageHuge(head))
-				isolate_huge_page(head, &cma_page_list);
-			else {
+			if (PageHuge(head)) {
+				if (!isolate_huge_page(head, &cma_page_list))
+					isolation_error_count++;
+			} else {
 				if (!PageLRU(head) && drain_allow) {
 					lru_add_drain_all();
 					drain_allow = false;
 				}
 
-				if (!isolate_lru_page(head)) {
-					list_add_tail(&head->lru, &cma_page_list);
-					mod_node_page_state(page_pgdat(head),
-							    NR_ISOLATED_ANON +
-							    page_is_file_lru(head),
-							    thp_nr_pages(head));
+				if (isolate_lru_page(head)) {
+					isolation_error_count++;
+					continue;
 				}
+				list_add_tail(&head->lru, &cma_page_list);
+				mod_node_page_state(page_pgdat(head),
+						    NR_ISOLATED_ANON +
+						    page_is_file_lru(head),
+						    thp_nr_pages(head));
 			}
 		}
 	}
 
+	/*
+	 * If list is empty, and no isolation errors, means that all pages are
+	 * in the correct zone.
+	 */
+	if (list_empty(&cma_page_list) && !isolation_error_count)
+		return ret;
+
 	if (!list_empty(&cma_page_list)) {
 		/*
 		 * drop the above get_user_pages reference.
@@ -1616,23 +1628,19 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm,
 			return ret > 0 ? -ENOMEM : ret;
 		}
 
-		/*
-		 * We did migrate all the pages, Try to get the page references
-		 * again migrating any new CMA pages which we failed to isolate
-		 * earlier.
-		 */
-		ret = __get_user_pages_locked(mm, start, nr_pages,
-						   pages, vmas, NULL,
-						   gup_flags);
-
-		if (ret > 0) {
-			nr_pages = ret;
-			drain_allow = true;
-			goto check_again;
-		}
+		/* We unpinned pages before migration, pin them again */
+		ret = __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
+					      NULL, gup_flags);
+		if (ret <= 0)
+			return ret;
+		nr_pages = ret;
 	}
 
-	return ret;
+	/*
+	 * check again because pages were unpinned, and we also might have
+	 * had isolation errors and need more pages to migrate.
+	 */
+	goto check_again;
 }
 #else
 static long check_and_migrate_cma_pages(struct mm_struct *mm,
-- 
2.25.1

