If we need to increase the number of huge pages, drop caches first
to reduce fragmentation and then check that we actually allocated
as many as we wanted.  Retry once if that doesn't work.

Signed-off-by: Ben Hutchings <ben-/+tVBieCtBitmTQ+vhA3Yw@public.gmane.org>
---
The test always fails for me in a 1 GB VM without this.

Ben.

 tools/testing/selftests/vm/run_vmtests | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index 9179ce8..97ed1b2 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests

@@ -20,13 +20,26 @@ done < /proc/meminfo

 if [ -n "$freepgs" ] && [ -n "$pgsize" ]; then
 	nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
 	needpgs=`expr $needmem / $pgsize`
-	if [ $freepgs -lt $needpgs ]; then
+	tries=2
+	while [ $tries -gt 0 ] && [ $freepgs -lt $needpgs ]; do
 		lackpgs=$(( $needpgs - $freepgs ))
+		echo 3 > /proc/sys/vm/drop_caches
 		echo $(( $lackpgs + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
 		if [ $? -ne 0 ]; then
 			echo "Please run this test as root"
 			exit 1
 		fi
+		while read name size unit; do
+			if [ "$name" = "HugePages_Free:" ]; then
+				freepgs=$size
+			fi
+		done < /proc/meminfo
+		tries=$((tries - 1))
+	done
+	if [ $freepgs -lt $needpgs ]; then
+		printf "Not enough huge pages available (%d < %d)\n" \
+		       $freepgs $needpgs
+		exit 1
 	fi
 else
 	echo "no hugetlbfs support in kernel?"

-- 
Ben Hutchings
All extremists should be taken out and shot.