[Devel] [PATCH vz8 18/42] mm/gup: allow VM_FAULT_RETRY for multiple times

[Andrey Ryabinin]

From: Peter Xu <peterx at redhat.com>

This is the gup counterpart of the change that allows the VM_FAULT_RETRY
to happen for more than once.  One thing to mention is that we must check
the fatal signal here before retry because the GUP can be interrupted by
that, otherwise we can loop forever.

Signed-off-by: Peter Xu <peterx at redhat.com>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Tested-by: Brian Geffon <bgeffon at google.com>
Cc: Andrea Arcangeli <aarcange at redhat.com>
Cc: Bobby Powers <bobbypowers at gmail.com>
Cc: David Hildenbrand <david at redhat.com>
Cc: Denis Plotnikov <dplotnikov at virtuozzo.com>
Cc: "Dr . David Alan Gilbert" <dgilbert at redhat.com>
Cc: Hugh Dickins <hughd at google.com>
Cc: Jerome Glisse <jglisse at redhat.com>
Cc: Johannes Weiner <hannes at cmpxchg.org>
Cc: "Kirill A . Shutemov" <kirill at shutemov.name>
Cc: Martin Cracauer <cracauer at cons.org>
Cc: Marty McFadden <mcfadden8 at llnl.gov>
Cc: Matthew Wilcox <willy at infradead.org>
Cc: Maya Gokhale <gokhale2 at llnl.gov>
Cc: Mel Gorman <mgorman at suse.de>
Cc: Mike Kravetz <mike.kravetz at oracle.com>
Cc: Mike Rapoport <rppt at linux.vnet.ibm.com>
Cc: Pavel Emelyanov <xemul at openvz.org>
Link: http://lkml.kernel.org/r/20200220195357.16371-1-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>

https://jira.sw.ru/browse/PSBM-102938
(cherry picked from commit 4426e945df588f2878affddf88a51259200f7e29)
Signed-off-by: Andrey Ryabinin <aryabinin at virtuozzo.com>
---
 mm/gup.c     | 27 +++++++++++++++++++++------
 mm/hugetlb.c |  6 ++++--
 2 files changed, 25 insertions(+), 8 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index e06aa55b65b2..cdf438ea8621 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -511,7 +511,10 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 	if (*flags & FOLL_NOWAIT)
 		fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;
 	if (*flags & FOLL_TRIED) {
-		VM_WARN_ON_ONCE(fault_flags & FAULT_FLAG_ALLOW_RETRY);
+		/*
+		 * Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED
+		 * can co-exist
+		 */
 		fault_flags |= FAULT_FLAG_TRIED;
 	}
 
@@ -853,7 +856,6 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 		down_read(&mm->mmap_sem);
 		if (!(fault_flags & FAULT_FLAG_TRIED)) {
 			*unlocked = true;
-			fault_flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			fault_flags |= FAULT_FLAG_TRIED;
 			goto retry;
 		}
@@ -928,17 +930,30 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 		/* VM_FAULT_RETRY triggered, so seek to the faulting offset */
 		pages += ret;
 		start += ret << PAGE_SHIFT;
+		lock_dropped = true;
 
+retry:
 		/*
 		 * Repeat on the address that fired VM_FAULT_RETRY
-		 * without FAULT_FLAG_ALLOW_RETRY but with
-		 * FAULT_FLAG_TRIED.
+		 * with both FAULT_FLAG_ALLOW_RETRY and
+		 * FAULT_FLAG_TRIED.  Note that GUP can be interrupted
+		 * by fatal signals, so we need to check it before we
+		 * start trying again otherwise it can loop forever.
 		 */
+
+		if (fatal_signal_pending(current))
+			break;
+
 		*locked = 1;
-		lock_dropped = true;
 		down_read(&mm->mmap_sem);
+
 		ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED,
-				       pages, NULL, NULL);
+				       pages, NULL, locked);
+		if (!*locked) {
+			/* Continue to retry until we succeeded */
+			BUG_ON(ret != 0);
+			goto retry;
+		}
 		if (ret != 1) {
 			BUG_ON(ret > 1);
 			if (!pages_done)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1c6584c8e78e..417b96f4aa14 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4228,8 +4228,10 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				fault_flags |= FAULT_FLAG_ALLOW_RETRY |
 					FAULT_FLAG_RETRY_NOWAIT;
 			if (flags & FOLL_TRIED) {
-				VM_WARN_ON_ONCE(fault_flags &
-						FAULT_FLAG_ALLOW_RETRY);
+				/*
+				 * Note: FAULT_FLAG_ALLOW_RETRY and
+				 * FAULT_FLAG_TRIED can co-exist
+				 */
 				fault_flags |= FAULT_FLAG_TRIED;
 			}
 			ret = hugetlb_fault(mm, vma, vaddr, fault_flags);
-- 
2.25.3