[PATCH] mm/mlock: skip __mm_populate() for MLOCK_ONFAULT

[Wandun Chen]

From: Wandun Chen <chenwandun@xxxxxxxxxxx>

MLOCK_ONFAULT only locks pages on future faults, so there is no need to
fault in non-present pages during the mlock2/mlockall syscall.
populate_vma_page_range() already returns immediately for VMAs with
VM_LOCKONFAULT, which means __mm_populate() just loops over VMAs and
holds mmap_read_lock without doing useful work.

Skip __mm_populate() when MLOCK_ONFAULT is set to avoid this unnecessary
work.

Signed-off-by: Wandun Chen <chenwandun@xxxxxxxxxxx>
---
 mm/mlock.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/mm/mlock.c b/mm/mlock.c
index efa6716e4dfb..784bd4bfc3bb 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -658,9 +658,11 @@ static __must_check int do_mlock(unsigned long start, size_t len,
 	if (error)
 		return error;
 
-	error = __mm_populate(start, len, 0);
-	if (error)
-		return __mlock_posix_error_return(error);
+	if (!vma_flags_test(flags, VMA_LOCKONFAULT_BIT)) {
+		error = __mm_populate(start, len, 0);
+		if (error)
+			return __mlock_posix_error_return(error);
+	}
 	return 0;
 }
 
@@ -778,7 +780,7 @@ SYSCALL_DEFINE1(mlockall, int, flags)
 	    capable(CAP_IPC_LOCK))
 		ret = apply_mlockall_flags(flags);
 	mmap_write_unlock(current->mm);
-	if (!ret && (flags & MCL_CURRENT))
+	if (!ret && (flags & MCL_CURRENT) && !(flags & MCL_ONFAULT))
 		mm_populate(0, TASK_SIZE);
 
 	return ret;
-- 
2.43.0