Adding upstream version 6.7.7.upstream/6.7.7

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

5 files changed, 610 insertions, 142 deletions

diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore
index af8c3f30b9..2732e0b292 100644
--- a/tools/testing/selftests/cgroup/.gitignore
+++ b/tools/testing/selftests/cgroup/.gitignore
@@ -7,4 +7,5 @@ test_kill
 test_cpu
 test_cpuset
 test_zswap
+test_hugetlb_memcg
 wait_inotify
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
index c27f05f6ce..00b4419289 100644
--- a/tools/testing/selftests/cgroup/Makefile
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -14,6 +14,7 @@ TEST_GEN_PROGS += test_kill
 TEST_GEN_PROGS += test_cpu
 TEST_GEN_PROGS += test_cpuset
 TEST_GEN_PROGS += test_zswap
+TEST_GEN_PROGS += test_hugetlb_memcg
 
 LOCAL_HDRS += $(selfdir)/clone3/clone3_selftests.h $(selfdir)/pidfd/pidfd.h
 
@@ -27,3 +28,4 @@ $(OUTPUT)/test_kill: cgroup_util.c
 $(OUTPUT)/test_cpu: cgroup_util.c
 $(OUTPUT)/test_cpuset: cgroup_util.c
 $(OUTPUT)/test_zswap: cgroup_util.c
+$(OUTPUT)/test_hugetlb_memcg: cgroup_util.c
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 4afb132e4e..a6e9848189 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -3,7 +3,7 @@
 #
 # Test for cpuset v2 partition root state (PRS)
 #
-# The sched verbose flag is set, if available, so that the console log
+# The sched verbose flag can be optionally set so that the console log
 # can be examined for the correct setting of scheduling domain.
 #
 
@@ -22,27 +22,27 @@ WAIT_INOTIFY=$(cd $(dirname $0); pwd)/wait_inotify
 # Find cgroup v2 mount point
 CGROUP2=$(mount -t cgroup2 | head -1 | awk -e '{print $3}')
 [[ -n "$CGROUP2" ]] || skip_test "Cgroup v2 mount point not found!"
+SUBPARTS_CPUS=$CGROUP2/.__DEBUG__.cpuset.cpus.subpartitions
+CPULIST=$(cat $CGROUP2/cpuset.cpus.effective)
 
-CPUS=$(lscpu | grep "^CPU(s):" | sed -e "s/.*:[[:space:]]*//")
-[[ $CPUS -lt 8 ]] && skip_test "Test needs at least 8 cpus available!"
+NR_CPUS=$(lscpu | grep "^CPU(s):" | sed -e "s/.*:[[:space:]]*//")
+[[ $NR_CPUS -lt 8 ]] && skip_test "Test needs at least 8 cpus available!"
 
 # Set verbose flag and delay factor
 PROG=$1
-VERBOSE=
+VERBOSE=0
 DELAY_FACTOR=1
 SCHED_DEBUG=
 while [[ "$1" = -* ]]
 do
 	case "$1" in
-		-v) VERBOSE=1
+		-v) ((VERBOSE++))
 		    # Enable sched/verbose can slow thing down
 		    [[ $DELAY_FACTOR -eq 1 ]] &&
 			DELAY_FACTOR=2
-		    break
 		    ;;
 		-d) DELAY_FACTOR=$2
 		    shift
-		    break
 		    ;;
 		*)  echo "Usage: $PROG [-v] [-d <delay-factor>"
 		    exit
@@ -52,7 +52,7 @@ do
 done
 
 # Set sched verbose flag if available when "-v" option is specified
-if [[ -n "$VERBOSE" && -d /sys/kernel/debug/sched ]]
+if [[ $VERBOSE -gt 0 && -d /sys/kernel/debug/sched ]]
 then
 	# Used to restore the original setting during cleanup
 	SCHED_DEBUG=$(cat /sys/kernel/debug/sched/verbose)
@@ -61,14 +61,26 @@ fi
 
 cd $CGROUP2
 echo +cpuset > cgroup.subtree_control
+
+#
+# If cpuset has been set up and used in child cgroups, we may not be able to
+# create partition under root cgroup because of the CPU exclusivity rule.
+# So we are going to skip the test if this is the case.
+#
 [[ -d test ]] || mkdir test
-cd test
+echo 0-6 > test/cpuset.cpus
+echo root > test/cpuset.cpus.partition
+cat test/cpuset.cpus.partition | grep -q invalid
+RESULT=$?
+echo member > test/cpuset.cpus.partition
+echo "" > test/cpuset.cpus
+[[ $RESULT -eq 0 ]] && skip_test "Child cgroups are using cpuset!"
 
 cleanup()
 {
 	online_cpus
+	cd $CGROUP2
 	rmdir A1/A2/A3 A1/A2 A1 B1 > /dev/null 2>&1
-	cd ..
 	rmdir test > /dev/null 2>&1
 	[[ -n "$SCHED_DEBUG" ]] &&
 		echo "$SCHED_DEBUG" > /sys/kernel/debug/sched/verbose
@@ -103,7 +115,7 @@ test_partition()
 	[[ $? -eq 0 ]] || exit 1
 	ACTUAL_VAL=$(cat cpuset.cpus.partition)
 	[[ $ACTUAL_VAL != $EXPECTED_VAL ]] && {
-		echo "cpuset.cpus.partition: expect $EXPECTED_VAL, found $EXPECTED_VAL"
+		echo "cpuset.cpus.partition: expect $EXPECTED_VAL, found $ACTUAL_VAL"
 		echo "Test FAILED"
 		exit 1
 	}
@@ -114,7 +126,7 @@ test_effective_cpus()
 	EXPECTED_VAL=$1
 	ACTUAL_VAL=$(cat cpuset.cpus.effective)
 	[[ "$ACTUAL_VAL" != "$EXPECTED_VAL" ]] && {
-		echo "cpuset.cpus.effective: expect '$EXPECTED_VAL', found '$EXPECTED_VAL'"
+		echo "cpuset.cpus.effective: expect '$EXPECTED_VAL', found '$ACTUAL_VAL'"
 		echo "Test FAILED"
 		exit 1
 	}
@@ -139,6 +151,7 @@ test_add_proc()
 #
 test_isolated()
 {
+	cd $CGROUP2/test
 	echo 2-3 > cpuset.cpus
 	TYPE=$(cat cpuset.cpus.partition)
 	[[ $TYPE = member ]] || echo member > cpuset.cpus.partition
@@ -203,125 +216,220 @@ test_isolated()
 #
 # Cgroup test hierarchy
 #
-# test -- A1 -- A2 -- A3
-#      \- B1
+# root -- A1 -- A2 -- A3
+#      +- B1
 #
-#  P<v> = set cpus.partition (0:member, 1:root, 2:isolated, -1:root invalid)
-#  C<l> = add cpu-list
+#  P<v> = set cpus.partition (0:member, 1:root, 2:isolated)
+#  C<l> = add cpu-list to cpuset.cpus
+#  X<l> = add cpu-list to cpuset.cpus.exclusive
 #  S<p> = use prefix in subtree_control
 #  T    = put a task into cgroup
-#  O<c>-<v> = Write <v> to CPU online file of <c>
+#  O<c>=<v> = Write <v> to CPU online file of <c>
 #
 SETUP_A123_PARTITIONS="C1-3:P1:S+ C2-3:P1:S+ C3:P1"
 TEST_MATRIX=(
-	# test  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate
-	# ----  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------
-	"  S+    C0-1     .      .    C2-3    S+    C4-5     .      .     0 A2:0-1"
-	"  S+    C0-1     .      .    C2-3    P1      .      .      .     0 "
-	"  S+    C0-1     .      .    C2-3   P1:S+ C0-1:P1   .      .     0 "
-	"  S+    C0-1     .      .    C2-3   P1:S+  C1:P1    .      .     0 "
-	"  S+   C0-1:S+   .      .    C2-3     .      .      .     P1     0 "
-	"  S+   C0-1:P1   .      .    C2-3    S+     C1      .      .     0 "
-	"  S+   C0-1:P1   .      .    C2-3    S+    C1:P1    .      .     0 "
-	"  S+   C0-1:P1   .      .    C2-3    S+    C1:P1    .     P1     0 "
-	"  S+   C0-1:P1   .      .    C2-3   C4-5     .      .      .     0 A1:4-5"
-	"  S+   C0-1:P1   .      .    C2-3  S+:C4-5   .      .      .     0 A1:4-5"
-	"  S+    C0-1     .      .   C2-3:P1   .      .      .     C2     0 "
-	"  S+    C0-1     .      .   C2-3:P1   .      .      .    C4-5    0 B1:4-5"
-	"  S+ C0-3:P1:S+ C2-3:P1 .      .      .      .      .      .     0 A1:0-1,A2:2-3"
-	"  S+ C0-3:P1:S+ C2-3:P1 .      .     C1-3    .      .      .     0 A1:1,A2:2-3"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     C3      .      .      .     0 A1:,A2:3 A1:P1,A2:P1"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     C3      P0     .      .     0 A1:3,A2:3 A1:P1,A2:P0"
-	"  S+ C2-3:P1:S+  C2:P1  .      .     C2-4    .      .      .     0 A1:3-4,A2:2"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     C3      .      .     C0-2   0 A1:,B1:0-2 A1:P1,A2:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .     C2-3    .      .      .     0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
+	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
+	"   C0-1     .      .    C2-3    S+    C4-5     .      .     0 A2:0-1"
+	"   C0-1     .      .    C2-3    P1      .      .      .     0 "
+	"   C0-1     .      .    C2-3   P1:S+ C0-1:P1   .      .     0 "
+	"   C0-1     .      .    C2-3   P1:S+  C1:P1    .      .     0 "
+	"  C0-1:S+   .      .    C2-3     .      .      .     P1     0 "
+	"  C0-1:P1   .      .    C2-3    S+     C1      .      .     0 "
+	"  C0-1:P1   .      .    C2-3    S+    C1:P1    .      .     0 "
+	"  C0-1:P1   .      .    C2-3    S+    C1:P1    .     P1     0 "
+	"  C0-1:P1   .      .    C2-3   C4-5     .      .      .     0 A1:4-5"
+	"  C0-1:P1   .      .    C2-3  S+:C4-5   .      .      .     0 A1:4-5"
+	"   C0-1     .      .   C2-3:P1   .      .      .     C2     0 "
+	"   C0-1     .      .   C2-3:P1   .      .      .    C4-5    0 B1:4-5"
+	"C0-3:P1:S+ C2-3:P1 .      .      .      .      .      .     0 A1:0-1,A2:2-3"
+	"C0-3:P1:S+ C2-3:P1 .      .     C1-3    .      .      .     0 A1:1,A2:2-3"
+	"C2-3:P1:S+  C3:P1  .      .     C3      .      .      .     0 A1:,A2:3 A1:P1,A2:P1"
+	"C2-3:P1:S+  C3:P1  .      .     C3      P0     .      .     0 A1:3,A2:3 A1:P1,A2:P0"
+	"C2-3:P1:S+  C2:P1  .      .     C2-4    .      .      .     0 A1:3-4,A2:2"
+	"C2-3:P1:S+  C3:P1  .      .     C3      .      .     C0-2   0 A1:,B1:0-2 A1:P1,A2:P1"
+	"$SETUP_A123_PARTITIONS    .     C2-3    .      .      .     0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
 
 	# CPU offlining cases:
-	"  S+    C0-1     .      .    C2-3    S+    C4-5     .     O2-0   0 A1:0-1,B1:3"
-	"  S+ C0-3:P1:S+ C2-3:P1 .      .     O2-0    .      .      .     0 A1:0-1,A2:3"
-	"  S+ C0-3:P1:S+ C2-3:P1 .      .     O2-0   O2-1    .      .     0 A1:0-1,A2:2-3"
-	"  S+ C0-3:P1:S+ C2-3:P1 .      .     O1-0    .      .      .     0 A1:0,A2:2-3"
-	"  S+ C0-3:P1:S+ C2-3:P1 .      .     O1-0   O1-1    .      .     0 A1:0-1,A2:2-3"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     O3-0   O3-1    .      .     0 A1:2,A2:3 A1:P1,A2:P1"
-	"  S+ C2-3:P1:S+  C3:P2  .      .     O3-0   O3-1    .      .     0 A1:2,A2:3 A1:P1,A2:P2"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     O2-0   O2-1    .      .     0 A1:2,A2:3 A1:P1,A2:P1"
-	"  S+ C2-3:P1:S+  C3:P2  .      .     O2-0   O2-1    .      .     0 A1:2,A2:3 A1:P1,A2:P2"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     O2-0    .      .      .     0 A1:,A2:3 A1:P1,A2:P1"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     O3-0    .      .      .     0 A1:2,A2: A1:P1,A2:P1"
-	"  S+ C2-3:P1:S+  C3:P1  .      .    T:O2-0   .      .      .     0 A1:3,A2:3 A1:P1,A2:P-1"
-	"  S+ C2-3:P1:S+  C3:P1  .      .      .    T:O3-0   .      .     0 A1:2,A2:2 A1:P1,A2:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    .     O1-0    .      .      .     0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .     O2-0    .      .      .     0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .     O3-0    .      .      .     0 A1:1,A2:2,A3: A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .    T:O1-0   .      .      .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    .      .    T:O2-0   .      .     0 A1:1,A2:3,A3:3 A1:P1,A2:P1,A3:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    .      .      .    T:O3-0   .     0 A1:1,A2:2,A3:2 A1:P1,A2:P1,A3:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    .    T:O1-0  O1-1    .      .     0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .      .    T:O2-0  O2-1    .     0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .      .      .    T:O3-0  O3-1   0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .    T:O1-0  O2-0   O1-1    .     0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .    T:O1-0  O2-0   O2-1    .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
-
-	# test  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate
-	# ----  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------
+	"   C0-1     .      .    C2-3    S+    C4-5     .     O2=0   0 A1:0-1,B1:3"
+	"C0-3:P1:S+ C2-3:P1 .      .     O2=0    .      .      .     0 A1:0-1,A2:3"
+	"C0-3:P1:S+ C2-3:P1 .      .     O2=0   O2=1    .      .     0 A1:0-1,A2:2-3"
+	"C0-3:P1:S+ C2-3:P1 .      .     O1=0    .      .      .     0 A1:0,A2:2-3"
+	"C0-3:P1:S+ C2-3:P1 .      .     O1=0   O1=1    .      .     0 A1:0-1,A2:2-3"
+	"C2-3:P1:S+  C3:P1  .      .     O3=0   O3=1    .      .     0 A1:2,A2:3 A1:P1,A2:P1"
+	"C2-3:P1:S+  C3:P2  .      .     O3=0   O3=1    .      .     0 A1:2,A2:3 A1:P1,A2:P2"
+	"C2-3:P1:S+  C3:P1  .      .     O2=0   O2=1    .      .     0 A1:2,A2:3 A1:P1,A2:P1"
+	"C2-3:P1:S+  C3:P2  .      .     O2=0   O2=1    .      .     0 A1:2,A2:3 A1:P1,A2:P2"
+	"C2-3:P1:S+  C3:P1  .      .     O2=0    .      .      .     0 A1:,A2:3 A1:P1,A2:P1"
+	"C2-3:P1:S+  C3:P1  .      .     O3=0    .      .      .     0 A1:2,A2: A1:P1,A2:P1"
+	"C2-3:P1:S+  C3:P1  .      .    T:O2=0   .      .      .     0 A1:3,A2:3 A1:P1,A2:P-1"
+	"C2-3:P1:S+  C3:P1  .      .      .    T:O3=0   .      .     0 A1:2,A2:2 A1:P1,A2:P-1"
+	"$SETUP_A123_PARTITIONS    .     O1=0    .      .      .     0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
+	"$SETUP_A123_PARTITIONS    .     O2=0    .      .      .     0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1"
+	"$SETUP_A123_PARTITIONS    .     O3=0    .      .      .     0 A1:1,A2:2,A3: A1:P1,A2:P1,A3:P1"
+	"$SETUP_A123_PARTITIONS    .    T:O1=0   .      .      .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
+	"$SETUP_A123_PARTITIONS    .      .    T:O2=0   .      .     0 A1:1,A2:3,A3:3 A1:P1,A2:P1,A3:P-1"
+	"$SETUP_A123_PARTITIONS    .      .      .    T:O3=0   .     0 A1:1,A2:2,A3:2 A1:P1,A2:P1,A3:P-1"
+	"$SETUP_A123_PARTITIONS    .    T:O1=0  O1=1    .      .     0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
+	"$SETUP_A123_PARTITIONS    .      .    T:O2=0  O2=1    .     0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
+	"$SETUP_A123_PARTITIONS    .      .      .    T:O3=0  O3=1   0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
+	"$SETUP_A123_PARTITIONS    .    T:O1=0  O2=0   O1=1    .     0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1"
+	"$SETUP_A123_PARTITIONS    .    T:O1=0  O2=0   O2=1    .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
+
+	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
+	#
+	# Remote partition and cpuset.cpus.exclusive tests
+	#
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3     .      .      .     0 A1:0-3,A2:1-3,A3:2-3,XA1:2-3"
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3  X2-3:P2   .      .     0 A1:0-1,A2:2-3,A3:2-3 A1:P0,A2:P2 2-3"
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X3:P2    .      .     0 A1:0-2,A2:3,A3:3 A1:P0,A2:P2 3"
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3  X2-3:P2   .     0 A1:0-1,A2:1,A3:2-3 A1:P0,A3:P2 2-3"
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:C3 .     0 A1:0-2,A2:1-2,A3:3 A1:P0,A3:P2 3"
+	" C0-3:S+ C1-3:S+ C2-3   C2-3     .      .      .      P2    0 A1:0-3,A2:1-3,A3:2-3,B1:2-3 A1:P0,A3:P0,B1:P-2"
+	" C0-3:S+ C1-3:S+ C2-3   C4-5     .      .      .      P2    0 B1:4-5 B1:P2 4-5"
+	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3  X2-3:P2   P2    0 A3:2-3,B1:4 A3:P2,B1:P2 2-4"
+	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3 X2-3:P2:C1-3 P2  0 A3:2-3,B1:4 A3:P2,B1:P2 2-4"
+	" C0-3:S+ C1-3:S+ C2-3    C4    X1-3  X1-3:P2   P2     .     0 A2:1,A3:2-3 A2:P2,A3:P2 1-3"
+	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3  X2-3:P2 P2:C4-5 0 A3:2-3,B1:4-5 A3:P2,B1:P2 2-5"
+
+	# Nested remote/local partition tests
+	" C0-3:S+ C1-3:S+ C2-3   C4-5   X2-3  X2-3:P1   P2     P1    0 A1:0-1,A2:,A3:2-3,B1:4-5 \
+								       A1:P0,A2:P1,A3:P2,B1:P1 2-3"
+	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1,A2:,A3:2-3,B1:4 \
+								       A1:P0,A2:P1,A3:P2,B1:P1 2-4"
+	" C0-3:S+ C1-3:S+  C3     C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1,A2:2,A3:3,B1:4 \
+								       A1:P0,A2:P1,A3:P2,B1:P1 2-4"
+	" C0-4:S+ C1-4:S+ C2-4     .    X2-4  X2-4:P2  X4:P1    .    0 A1:0-1,A2:2-3,A3:4 \
+								       A1:P0,A2:P2,A3:P1 2-4"
+	" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
+				   .      .      X5      .      .    0 A1:0-4,A2:1-4,A3:2-4 \
+								       A1:P0,A2:P-2,A3:P-1 ."
+	" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
+				   .      .      .      X1      .    0 A1:0-1,A2:2-4,A3:2-4 \
+								       A1:P0,A2:P2,A3:P-1 2-4"
+
+	# Remote partition offline tests
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 .   0 A1:0-1,A2:1,A3:3 A1:P0,A3:P2 2-3"
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1,A2:1,A3:2-3 A1:P0,A3:P2 2-3"
+	" C0-3:S+ C1-3:S+  C3      .    X2-3   X2-3    P2:O3=0   .   0 A1:0-2,A2:1-2,A3: A1:P0,A3:P2 3"
+	" C0-3:S+ C1-3:S+  C3      .    X2-3   X2-3   T:P2:O3=0  .   0 A1:0-2,A2:1-2,A3:1-2 A1:P0,A3:P-2 3"
+
+	# An invalidated remote partition cannot self-recover from hotplug
+	" C0-3:S+ C1-3:S+  C2      .    X2-3   X2-3   T:P2:O2=0 O2=1 0 A1:0-3,A2:1-3,A3:2 A1:P0,A3:P-2"
+
+	# cpus.exclusive.effective clearing test
+	" C0-3:S+ C1-3:S+  C2      .   X2-3:X    .      .      .     0 A1:0-3,A2:1-3,A3:2,XA1:"
+
+	# Invalid to valid remote partition transition test
+	" C0-3:S+   C1-3    .      .      .    X3:P2    .      .     0 A1:0-3,A2:1-3,XA2: A2:P-2"
+	" C0-3:S+ C1-3:X3:P2
+			    .      .    X2-3    P2      .      .     0 A1:0-2,A2:3,XA2:3 A2:P2 3"
+
+	# Invalid to valid local partition direct transition tests
+	" C1-3:S+:P2 C2-3:X1:P2 .  .      .      .      .      .     0 A1:1-3,XA1:1-3,A2:2-3:XA2: A1:P2,A2:P-2 1-3"
+	" C1-3:S+:P2 C2-3:X1:P2 .  .      .    X3:P2    .      .     0 A1:1-2,XA1:1-3,A2:3:XA2:3 A1:P2,A2:P2 1-3"
+	"  C0-3:P2   .      .    C4-6   C0-4     .      .      .     0 A1:0-4,B1:4-6 A1:P-2,B1:P0"
+	"  C0-3:P2   .      .    C4-6 C0-4:C0-3  .      .      .     0 A1:0-3,B1:4-6 A1:P2,B1:P0 0-3"
+	"  C0-3:P2   .      .  C3-5:C4-5  .      .      .      .     0 A1:0-3,B1:4-5 A1:P2,B1:P0 0-3"
+
+	# Local partition invalidation tests
+	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+				   .      .      .      .      .     0 A1:1,A2:2,A3:3 A1:P2,A2:P2,A3:P2 1-3"
+	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+				   .      .     X4      .      .     0 A1:1-3,A2:1-3,A3:2-3,XA2:,XA3: A1:P2,A2:P-2,A3:P-2 1-3"
+	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+				   .      .     C4      .      .     0 A1:1-3,A2:1-3,A3:2-3,XA2:,XA3: A1:P2,A2:P-2,A3:P-2 1-3"
+	# Local partition CPU change tests
+	" C0-5:S+:P2 C4-5:S+:P1 .  .      .    C3-5     .      .     0 A1:0-2,A2:3-5 A1:P2,A2:P1 0-2"
+	" C0-5:S+:P2 C4-5:S+:P1 .  .    C1-5     .      .      .     0 A1:1-3,A2:4-5 A1:P2,A2:P1 1-3"
+
+	# cpus_allowed/exclusive_cpus update tests
+	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+				   .     C4      .      P2     .     0 A1:4,A2:4,XA2:,XA3:,A3:4 \
+								       A1:P0,A3:P-2 ."
+	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+				   .     X1      .      P2     .     0 A1:0-3,A2:1-3,XA1:1,XA2:,XA3:,A3:2-3 \
+								       A1:P0,A3:P-2 ."
+	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+				   .      .     C3      P2     .     0 A1:0-2,A2:0-2,XA2:3,XA3:3,A3:3 \
+								       A1:P0,A3:P2 3"
+	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+				   .      .     X3      P2     .     0 A1:0-2,A2:1-2,XA2:3,XA3:3,A3:3 \
+								       A1:P0,A3:P2 3"
+	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
+				   .      .     X3      .      .     0 A1:0-3,A2:1-3,XA2:3,XA3:3,A3:2-3 \
+								       A1:P0,A3:P-2 ."
+	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
+				   .      .     C3      .      .     0 A1:0-3,A2:3,XA2:3,XA3:3,A3:3 \
+								       A1:P0,A3:P-2 ."
+	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
+				   .     C4      .      .      .     0 A1:4,A2:4,A3:4,XA1:,XA2:,XA3 \
+								       A1:P0,A3:P-2 ."
+
+	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
 	#
 	# Incorrect change to cpuset.cpus invalidates partition root
 	#
 	# Adding CPUs to partition root that are not in parent's
 	# cpuset.cpus is allowed, but those extra CPUs are ignored.
-	"  S+ C2-3:P1:S+ C3:P1   .      .      .     C2-4    .      .     0 A1:,A2:2-3 A1:P1,A2:P1"
+	"C2-3:P1:S+ C3:P1   .      .      .     C2-4    .      .     0 A1:,A2:2-3 A1:P1,A2:P1"
 
 	# Taking away all CPUs from parent or itself if there are tasks
 	# will make the partition invalid.
-	"  S+ C2-3:P1:S+  C3:P1  .      .      T     C2-3    .      .     0 A1:2-3,A2:2-3 A1:P1,A2:P-1"
-	"  S+  C3:P1:S+    C3    .      .      T      P1     .      .     0 A1:3,A2:3 A1:P1,A2:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    .    T:C2-3   .      .      .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    . T:C2-3:C1-3 .      .      .     0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
+	"C2-3:P1:S+  C3:P1  .      .      T     C2-3    .      .     0 A1:2-3,A2:2-3 A1:P1,A2:P-1"
+	" C3:P1:S+    C3    .      .      T      P1     .      .     0 A1:3,A2:3 A1:P1,A2:P-1"
+	"$SETUP_A123_PARTITIONS    .    T:C2-3   .      .      .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
+	"$SETUP_A123_PARTITIONS    . T:C2-3:C1-3 .      .      .     0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
 
 	# Changing a partition root to member makes child partitions invalid
-	"  S+ C2-3:P1:S+  C3:P1  .      .      P0     .      .      .     0 A1:2-3,A2:3 A1:P0,A2:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    .     C2-3    P0     .      .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P0,A3:P-1"
+	"C2-3:P1:S+  C3:P1  .      .      P0     .      .      .     0 A1:2-3,A2:3 A1:P0,A2:P-1"
+	"$SETUP_A123_PARTITIONS    .     C2-3    P0     .      .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P0,A3:P-1"
 
 	# cpuset.cpus can contains cpus not in parent's cpuset.cpus as long
 	# as they overlap.
-	"  S+ C2-3:P1:S+  .      .      .      .   C3-4:P1   .      .     0 A1:2,A2:3 A1:P1,A2:P1"
+	"C2-3:P1:S+  .      .      .      .   C3-4:P1   .      .     0 A1:2,A2:3 A1:P1,A2:P1"
 
 	# Deletion of CPUs distributed to child cgroup is allowed.
-	"  S+ C0-1:P1:S+ C1      .    C2-3   C4-5     .      .      .     0 A1:4-5,A2:4-5"
+	"C0-1:P1:S+ C1      .    C2-3   C4-5     .      .      .     0 A1:4-5,A2:4-5"
 
 	# To become a valid partition root, cpuset.cpus must overlap parent's
 	# cpuset.cpus.
-	"  S+   C0-1:P1   .      .    C2-3    S+   C4-5:P1   .      .     0 A1:0-1,A2:0-1 A1:P1,A2:P-1"
+	"  C0-1:P1   .      .    C2-3    S+   C4-5:P1   .      .     0 A1:0-1,A2:0-1 A1:P1,A2:P-1"
 
 	# Enabling partition with child cpusets is allowed
-	"  S+   C0-1:S+  C1      .    C2-3    P1      .      .      .     0 A1:0-1,A2:1 A1:P1"
+	"  C0-1:S+  C1      .    C2-3    P1      .      .      .     0 A1:0-1,A2:1 A1:P1"
 
 	# A partition root with non-partition root parent is invalid, but it
 	# can be made valid if its parent becomes a partition root too.
-	"  S+   C0-1:S+  C1      .    C2-3     .      P2     .      .     0 A1:0-1,A2:1 A1:P0,A2:P-2"
-	"  S+   C0-1:S+ C1:P2    .    C2-3     P1     .      .      .     0 A1:0,A2:1 A1:P1,A2:P2"
+	"  C0-1:S+  C1      .    C2-3     .      P2     .      .     0 A1:0-1,A2:1 A1:P0,A2:P-2"
+	"  C0-1:S+ C1:P2    .    C2-3     P1     .      .      .     0 A1:0,A2:1 A1:P1,A2:P2"
 
 	# A non-exclusive cpuset.cpus change will invalidate partition and its siblings
-	"  S+   C0-1:P1   .      .    C2-3   C0-2     .      .      .     0 A1:0-2,B1:2-3 A1:P-1,B1:P0"
-	"  S+   C0-1:P1   .      .  P1:C2-3  C0-2   .      .      .     0 A1:0-2,B1:2-3 A1:P-1,B1:P-1"
-	"  S+    C0-1     .      .  P1:C2-3  C0-2   .      .      .     0 A1:0-2,B1:2-3 A1:P0,B1:P-1"
+	"  C0-1:P1   .      .    C2-3   C0-2     .      .      .     0 A1:0-2,B1:2-3 A1:P-1,B1:P0"
+	"  C0-1:P1   .      .  P1:C2-3  C0-2     .      .      .     0 A1:0-2,B1:2-3 A1:P-1,B1:P-1"
+	"   C0-1     .      .  P1:C2-3  C0-2     .      .      .     0 A1:0-2,B1:2-3 A1:P0,B1:P-1"
 
-	# test  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate
-	# ----  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------
+	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
 	# Failure cases:
 
 	# A task cannot be added to a partition with no cpu
-	"  S+ C2-3:P1:S+  C3:P1  .      .    O2-0:T   .      .      .     1 A1:,A2:3 A1:P1,A2:P1"
+	"C2-3:P1:S+  C3:P1  .      .    O2=0:T   .      .      .     1 A1:,A2:3 A1:P1,A2:P1"
+
+	# Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected
+	"   C0-3     .      .    C4-5   X0-3     .      .     X3-5   1 A1:0-3,B1:4-5"
 )
 
 #
 # Write to the cpu online file
-#  $1 - <c>-<v> where <c> = cpu number, <v> value to be written
+#  $1 - <c>=<v> where <c> = cpu number, <v> value to be written
 #
 write_cpu_online()
 {
-	CPU=${1%-*}
-	VAL=${1#*-}
+	CPU=${1%=*}
+	VAL=${1#*=}
 	CPUFILE=//sys/devices/system/cpu/cpu${CPU}/online
 	if [[ $VAL -eq 0 ]]
 	then
@@ -349,11 +457,12 @@ set_ctrl_state()
 	TMPMSG=/tmp/.msg_$$
 	CGRP=$1
 	STATE=$2
-	SHOWERR=${3}${VERBOSE}
+	SHOWERR=${3}
 	CTRL=${CTRL:=$CONTROLLER}
 	HASERR=0
 	REDIRECT="2> $TMPMSG"
 	[[ -z "$STATE" || "$STATE" = '.' ]] && return 0
+	[[ $VERBOSE -gt 0 ]] && SHOWERR=1
 
 	rm -f $TMPMSG
 	for CMD in $(echo $STATE | sed -e "s/:/ /g")
@@ -362,12 +471,18 @@ set_ctrl_state()
 		SFILE=$CGRP/cgroup.subtree_control
 		PFILE=$CGRP/cpuset.cpus.partition
 		CFILE=$CGRP/cpuset.cpus
+		XFILE=$CGRP/cpuset.cpus.exclusive
 		S=$(expr substr $CMD 1 1)
 		if [[ $S = S ]]
 		then
 			PREFIX=${CMD#?}
 			COMM="echo ${PREFIX}${CTRL} > $SFILE"
 			eval $COMM $REDIRECT
+		elif [[ $S = X ]]
+		then
+			CPUS=${CMD#?}
+			COMM="echo $CPUS > $XFILE"
+			eval $COMM $REDIRECT
 		elif [[ $S = C ]]
 		then
 			CPUS=${CMD#?}
@@ -430,7 +545,7 @@ online_cpus()
 	[[ -n "OFFLINE_CPUS" ]] && {
 		for C in $OFFLINE_CPUS
 		do
-			write_cpu_online ${C}-1
+			write_cpu_online ${C}=1
 		done
 	}
 }
@@ -443,18 +558,27 @@ reset_cgroup_states()
 	echo 0 > $CGROUP2/cgroup.procs
 	online_cpus
 	rmdir A1/A2/A3 A1/A2 A1 B1 > /dev/null 2>&1
-	set_ctrl_state . S-
+	pause 0.02
+	set_ctrl_state . R-
 	pause 0.01
 }
 
 dump_states()
 {
-	for DIR in A1 A1/A2 A1/A2/A3 B1
+	for DIR in . A1 A1/A2 A1/A2/A3 B1
 	do
+		CPUS=$DIR/cpuset.cpus
 		ECPUS=$DIR/cpuset.cpus.effective
+		XCPUS=$DIR/cpuset.cpus.exclusive
+		XECPUS=$DIR/cpuset.cpus.exclusive.effective
 		PRS=$DIR/cpuset.cpus.partition
-		[[ -e $ECPUS ]] && echo "$ECPUS: $(cat $ECPUS)"
-		[[ -e $PRS   ]] && echo "$PRS: $(cat $PRS)"
+		PCPUS=$DIR/.__DEBUG__.cpuset.cpus.subpartitions
+		[[ -e $CPUS   ]] && echo "$CPUS: $(cat $CPUS)"
+		[[ -e $XCPUS  ]] && echo "$XCPUS: $(cat $XCPUS)"
+		[[ -e $ECPUS  ]] && echo "$ECPUS: $(cat $ECPUS)"
+		[[ -e $XECPUS ]] && echo "$XECPUS: $(cat $XECPUS)"
+		[[ -e $PRS    ]] && echo "$PRS: $(cat $PRS)"
+		[[ -e $PCPUS  ]] && echo "$PCPUS: $(cat $PCPUS)"
 	done
 }
 
@@ -470,11 +594,17 @@ check_effective_cpus()
 		set -- $(echo $CHK | sed -e "s/:/ /g")
 		CGRP=$1
 		CPUS=$2
+		if [[ $CGRP = X* ]]
+		then
+			CGRP=${CGRP#X}
+			FILE=cpuset.cpus.exclusive.effective
+		else
+			FILE=cpuset.cpus.effective
+		fi
 		[[ $CGRP = A2 ]] && CGRP=A1/A2
 		[[ $CGRP = A3 ]] && CGRP=A1/A2/A3
-		FILE=$CGRP/cpuset.cpus.effective
-		[[ -e $FILE ]] || return 1
-		[[ $CPUS = $(cat $FILE) ]] || return 1
+		[[ -e $CGRP/$FILE ]] || return 1
+		[[ $CPUS = $(cat $CGRP/$FILE) ]] || return 1
 	done
 }
 
@@ -525,6 +655,65 @@ check_cgroup_states()
 }
 
 #
+# Get isolated (including offline) CPUs by looking at
+# /sys/kernel/debug/sched/domains and compare that with the expected value.
+#
+# Note that a sched domain of just 1 CPU will be considered isolated.
+#
+# $1 - expected isolated cpu list
+#
+check_isolcpus()
+{
+	EXPECT_VAL=$1
+	ISOLCPUS=
+	LASTISOLCPU=
+	SCHED_DOMAINS=/sys/kernel/debug/sched/domains
+	[[ -d $SCHED_DOMAINS ]] || return 0
+	[[ $EXPECT_VAL = . ]] && EXPECT_VAL=
+
+	for ((CPU=0; CPU < $NR_CPUS; CPU++))
+	do
+		[[ -n "$(ls ${SCHED_DOMAINS}/cpu$CPU)" ]] && continue
+
+		if [[ -z "$LASTISOLCPU" ]]
+		then
+			ISOLCPUS=$CPU
+			LASTISOLCPU=$CPU
+		elif [[ "$LASTISOLCPU" -eq $((CPU - 1)) ]]
+		then
+			echo $ISOLCPUS | grep -q "\<$LASTISOLCPU\$"
+			if [[ $? -eq 0 ]]
+			then
+				ISOLCPUS=${ISOLCPUS}-
+			fi
+			LASTISOLCPU=$CPU
+		else
+			if [[ $ISOLCPUS = *- ]]
+			then
+				ISOLCPUS=${ISOLCPUS}$LASTISOLCPU
+			fi
+			ISOLCPUS=${ISOLCPUS},$CPU
+			LASTISOLCPU=$CPU
+		fi
+	done
+	[[ "$ISOLCPUS" = *- ]] && ISOLCPUS=${ISOLCPUS}$LASTISOLCPU
+	[[ "$EXPECT_VAL" = "$ISOLCPUS" ]]
+}
+
+test_fail()
+{
+	TESTNUM=$1
+	TESTTYPE=$2
+	ADDINFO=$3
+	echo "Test $TEST[$TESTNUM] failed $TESTTYPE check!"
+	[[ -n "$ADDINFO" ]] && echo "*** $ADDINFO ***"
+	eval echo \${$TEST[$I]}
+	echo
+	dump_states
+	exit 1
+}
+
+#
 # Run cpuset state transition test
 #  $1 - test matrix name
 #
@@ -536,88 +725,83 @@ run_state_test()
 {
 	TEST=$1
 	CONTROLLER=cpuset
-	CPULIST=0-6
 	I=0
 	eval CNT="\${#$TEST[@]}"
 
 	reset_cgroup_states
-	echo $CPULIST > cpuset.cpus
-	echo root > cpuset.cpus.partition
 	console_msg "Running state transition test ..."
 
 	while [[ $I -lt $CNT ]]
 	do
 		echo "Running test $I ..." > /dev/console
+		[[ $VERBOSE -gt 1 ]] && {
+			echo ""
+			eval echo \${$TEST[$I]}
+		}
 		eval set -- "\${$TEST[$I]}"
-		ROOT=$1
-		OLD_A1=$2
-		OLD_A2=$3
-		OLD_A3=$4
-		OLD_B1=$5
-		NEW_A1=$6
-		NEW_A2=$7
-		NEW_A3=$8
-		NEW_B1=$9
-		RESULT=${10}
-		ECPUS=${11}
-		STATES=${12}
-
-		set_ctrl_state_noerr .        $ROOT
+		OLD_A1=$1
+		OLD_A2=$2
+		OLD_A3=$3
+		OLD_B1=$4
+		NEW_A1=$5
+		NEW_A2=$6
+		NEW_A3=$7
+		NEW_B1=$8
+		RESULT=$9
+		ECPUS=${10}
+		STATES=${11}
+		ICPUS=${12}
+
+		set_ctrl_state_noerr B1       $OLD_B1
 		set_ctrl_state_noerr A1       $OLD_A1
 		set_ctrl_state_noerr A1/A2    $OLD_A2
 		set_ctrl_state_noerr A1/A2/A3 $OLD_A3
-		set_ctrl_state_noerr B1       $OLD_B1
 		RETVAL=0
 		set_ctrl_state A1       $NEW_A1; ((RETVAL += $?))
 		set_ctrl_state A1/A2    $NEW_A2; ((RETVAL += $?))
 		set_ctrl_state A1/A2/A3 $NEW_A3; ((RETVAL += $?))
 		set_ctrl_state B1       $NEW_B1; ((RETVAL += $?))
 
-		[[ $RETVAL -ne $RESULT ]] && {
-			echo "Test $TEST[$I] failed result check!"
-			eval echo \"\${$TEST[$I]}\"
-			dump_states
-			exit 1
-		}
+		[[ $RETVAL -ne $RESULT ]] && test_fail $I result
 
 		[[ -n "$ECPUS" && "$ECPUS" != . ]] && {
 			check_effective_cpus $ECPUS
-			[[ $? -ne 0 ]] && {
-				echo "Test $TEST[$I] failed effective CPU check!"
-				eval echo \"\${$TEST[$I]}\"
-				echo
-				dump_states
-				exit 1
-			}
+			[[ $? -ne 0 ]] && test_fail $I "effective CPU"
 		}
 
-		[[ -n "$STATES" ]] && {
+		[[ -n "$STATES" && "$STATES" != . ]] && {
 			check_cgroup_states $STATES
-			[[ $? -ne 0 ]] && {
-				echo "FAILED: Test $TEST[$I] failed states check!"
-				eval echo \"\${$TEST[$I]}\"
-				echo
-				dump_states
-				exit 1
-			}
+			[[ $? -ne 0 ]] && test_fail $I states
 		}
 
+		# Compare the expected isolated CPUs with the actual ones,
+		# if available
+		[[ -n "$ICPUS" ]] && {
+			check_isolcpus $ICPUS
+			[[ $? -ne 0 ]] && test_fail $I "isolated CPU" \
+				"Expect $ICPUS, get $ISOLCPUS instead"
+		}
 		reset_cgroup_states
 		#
 		# Check to see if effective cpu list changes
 		#
-		pause 0.05
 		NEWLIST=$(cat cpuset.cpus.effective)
+		RETRY=0
+		while [[ $NEWLIST != $CPULIST && $RETRY -lt 5 ]]
+		do
+			# Wait a bit longer & recheck a few times
+			pause 0.01
+			((RETRY++))
+			NEWLIST=$(cat cpuset.cpus.effective)
+		done
 		[[ $NEWLIST != $CPULIST ]] && {
 			echo "Effective cpus changed to $NEWLIST after test $I!"
 			exit 1
 		}
-		[[ -n "$VERBOSE" ]] && echo "Test $I done."
+		[[ $VERBOSE -gt 0 ]] && echo "Test $I done."
 		((I++))
 	done
 	echo "All $I tests of $TEST PASSED."
-
-	echo member > cpuset.cpus.partition
 }
 
 #
@@ -642,6 +826,7 @@ test_inotify()
 {
 	ERR=0
 	PRS=/tmp/.prs_$$
+	cd $CGROUP2/test
 	[[ -f $WAIT_INOTIFY ]] || {
 		echo "wait_inotify not found, inotify test SKIPPED."
 		return
@@ -655,7 +840,7 @@ test_inotify()
 	rm -f $PRS
 	wait_inotify $PWD/cpuset.cpus.partition $PRS &
 	pause 0.01
-	set_ctrl_state . "O1-0"
+	set_ctrl_state . "O1=0"
 	pause 0.01
 	check_cgroup_states ".:P-1"
 	if [[ $? -ne 0 ]]
@@ -689,5 +874,3 @@ run_state_test TEST_MATRIX
 test_isolated
 test_inotify
 echo "All tests PASSED."
-cd ..
-rmdir test
diff --git a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
new file mode 100644
index 0000000000..f0fefeb4cc
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <linux/limits.h>
+#include <sys/mman.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <fcntl.h>
+#include "../kselftest.h"
+#include "cgroup_util.h"
+
+#define ADDR ((void *)(0x0UL))
+#define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
+/* mapping 8 MBs == 4 hugepages */
+#define LENGTH (8UL*1024*1024)
+#define PROTECTION (PROT_READ | PROT_WRITE)
+
+/* borrowed from mm/hmm-tests.c */
+static long get_hugepage_size(void)
+{
+	int fd;
+	char buf[2048];
+	int len;
+	char *p, *q, *path = "/proc/meminfo", *tag = "Hugepagesize:";
+	long val;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0) {
+		/* Error opening the file */
+		return -1;
+	}
+
+	len = read(fd, buf, sizeof(buf));
+	close(fd);
+	if (len < 0) {
+		/* Error in reading the file */
+		return -1;
+	}
+	if (len == sizeof(buf)) {
+		/* Error file is too large */
+		return -1;
+	}
+	buf[len] = '\0';
+
+	/* Search for a tag if provided */
+	if (tag) {
+		p = strstr(buf, tag);
+		if (!p)
+			return -1; /* looks like the line we want isn't there */
+		p += strlen(tag);
+	} else
+		p = buf;
+
+	val = strtol(p, &q, 0);
+	if (*q != ' ') {
+		/* Error parsing the file */
+		return -1;
+	}
+
+	return val;
+}
+
+static int set_file(const char *path, long value)
+{
+	FILE *file;
+	int ret;
+
+	file = fopen(path, "w");
+	if (!file)
+		return -1;
+	ret = fprintf(file, "%ld\n", value);
+	fclose(file);
+	return ret;
+}
+
+static int set_nr_hugepages(long value)
+{
+	return set_file("/proc/sys/vm/nr_hugepages", value);
+}
+
+static unsigned int check_first(char *addr)
+{
+	return *(unsigned int *)addr;
+}
+
+static void write_data(char *addr)
+{
+	unsigned long i;
+
+	for (i = 0; i < LENGTH; i++)
+		*(addr + i) = (char)i;
+}
+
+static int hugetlb_test_program(const char *cgroup, void *arg)
+{
+	char *test_group = (char *)arg;
+	void *addr;
+	long old_current, expected_current, current;
+	int ret = EXIT_FAILURE;
+
+	old_current = cg_read_long(test_group, "memory.current");
+	set_nr_hugepages(20);
+	current = cg_read_long(test_group, "memory.current");
+	if (current - old_current >= MB(2)) {
+		ksft_print_msg(
+			"setting nr_hugepages should not increase hugepage usage.\n");
+		ksft_print_msg("before: %ld, after: %ld\n", old_current, current);
+		return EXIT_FAILURE;
+	}
+
+	addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, 0, 0);
+	if (addr == MAP_FAILED) {
+		ksft_print_msg("fail to mmap.\n");
+		return EXIT_FAILURE;
+	}
+	current = cg_read_long(test_group, "memory.current");
+	if (current - old_current >= MB(2)) {
+		ksft_print_msg("mmap should not increase hugepage usage.\n");
+		ksft_print_msg("before: %ld, after: %ld\n", old_current, current);
+		goto out_failed_munmap;
+	}
+	old_current = current;
+
+	/* read the first page */
+	check_first(addr);
+	expected_current = old_current + MB(2);
+	current = cg_read_long(test_group, "memory.current");
+	if (!values_close(expected_current, current, 5)) {
+		ksft_print_msg("memory usage should increase by around 2MB.\n");
+		ksft_print_msg(
+			"expected memory: %ld, actual memory: %ld\n",
+			expected_current, current);
+		goto out_failed_munmap;
+	}
+
+	/* write to the whole range */
+	write_data(addr);
+	current = cg_read_long(test_group, "memory.current");
+	expected_current = old_current + MB(8);
+	if (!values_close(expected_current, current, 5)) {
+		ksft_print_msg("memory usage should increase by around 8MB.\n");
+		ksft_print_msg(
+			"expected memory: %ld, actual memory: %ld\n",
+			expected_current, current);
+		goto out_failed_munmap;
+	}
+
+	/* unmap the whole range */
+	munmap(addr, LENGTH);
+	current = cg_read_long(test_group, "memory.current");
+	expected_current = old_current;
+	if (!values_close(expected_current, current, 5)) {
+		ksft_print_msg("memory usage should go back down.\n");
+		ksft_print_msg(
+			"expected memory: %ld, actual memory: %ld\n",
+			expected_current, current);
+		return ret;
+	}
+
+	ret = EXIT_SUCCESS;
+	return ret;
+
+out_failed_munmap:
+	munmap(addr, LENGTH);
+	return ret;
+}
+
+static int test_hugetlb_memcg(char *root)
+{
+	int ret = KSFT_FAIL;
+	char *test_group;
+
+	test_group = cg_name(root, "hugetlb_memcg_test");
+	if (!test_group || cg_create(test_group)) {
+		ksft_print_msg("fail to create cgroup.\n");
+		goto out;
+	}
+
+	if (cg_write(test_group, "memory.max", "100M")) {
+		ksft_print_msg("fail to set cgroup memory limit.\n");
+		goto out;
+	}
+
+	/* disable swap */
+	if (cg_write(test_group, "memory.swap.max", "0")) {
+		ksft_print_msg("fail to disable swap.\n");
+		goto out;
+	}
+
+	if (!cg_run(test_group, hugetlb_test_program, (void *)test_group))
+		ret = KSFT_PASS;
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+int main(int argc, char **argv)
+{
+	char root[PATH_MAX];
+	int ret = EXIT_SUCCESS, has_memory_hugetlb_acc;
+
+	has_memory_hugetlb_acc = proc_mount_contains("memory_hugetlb_accounting");
+	if (has_memory_hugetlb_acc < 0)
+		ksft_exit_skip("Failed to query cgroup mount option\n");
+	else if (!has_memory_hugetlb_acc)
+		ksft_exit_skip("memory hugetlb accounting is disabled\n");
+
+	/* Unit is kB! */
+	if (get_hugepage_size() != 2048) {
+		ksft_print_msg("test_hugetlb_memcg requires 2MB hugepages\n");
+		ksft_test_result_skip("test_hugetlb_memcg\n");
+		return ret;
+	}
+
+	if (cg_find_unified_root(root, sizeof(root)))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	switch (test_hugetlb_memcg(root)) {
+	case KSFT_PASS:
+		ksft_test_result_pass("test_hugetlb_memcg\n");
+		break;
+	case KSFT_SKIP:
+		ksft_test_result_skip("test_hugetlb_memcg\n");
+		break;
+	default:
+		ret = EXIT_FAILURE;
+		ksft_test_result_fail("test_hugetlb_memcg\n");
+		break;
+	}
+
+	return ret;
+}
diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c
index 49def87a90..c99d2adaca 100644
--- a/tools/testing/selftests/cgroup/test_zswap.c
+++ b/tools/testing/selftests/cgroup/test_zswap.c
@@ -55,6 +55,11 @@ static int get_zswap_written_back_pages(size_t *value)
 	return read_int("/sys/kernel/debug/zswap/written_back_pages", value);
 }
 
+static long get_zswpout(const char *cgroup)
+{
+	return cg_read_key_long(cgroup, "memory.stat", "zswpout ");
+}
+
 static int allocate_bytes(const char *cgroup, void *arg)
 {
 	size_t size = (size_t)arg;
@@ -69,6 +74,48 @@ static int allocate_bytes(const char *cgroup, void *arg)
 }
 
 /*
+ * Sanity test to check that pages are written into zswap.
+ */
+static int test_zswap_usage(const char *root)
+{
+	long zswpout_before, zswpout_after;
+	int ret = KSFT_FAIL;
+	char *test_group;
+
+	/* Set up */
+	test_group = cg_name(root, "no_shrink_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.max", "1M"))
+		goto out;
+
+	zswpout_before = get_zswpout(test_group);
+	if (zswpout_before < 0) {
+		ksft_print_msg("Failed to get zswpout\n");
+		goto out;
+	}
+
+	/* Allocate more than memory.max to push memory into zswap */
+	if (cg_run(test_group, allocate_bytes, (void *)MB(4)))
+		goto out;
+
+	/* Verify that pages come into zswap */
+	zswpout_after = get_zswpout(test_group);
+	if (zswpout_after <= zswpout_before) {
+		ksft_print_msg("zswpout does not increase after test program\n");
+		goto out;
+	}
+	ret = KSFT_PASS;
+
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+/*
  * When trying to store a memcg page in zswap, if the memcg hits its memory
  * limit in zswap, writeback should not be triggered.
  *
@@ -235,6 +282,7 @@ struct zswap_test {
 	int (*fn)(const char *root);
 	const char *name;
 } tests[] = {
+	T(test_zswap_usage),
 	T(test_no_kmem_bypass),
 	T(test_no_invasive_cgroup_shrink),
 };