Merging upstream version 6.10.3.

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

7 files changed, 186 insertions, 12 deletions

diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
index 00b4419289..16461dc0ff 100644
--- a/tools/testing/selftests/cgroup/Makefile
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -4,7 +4,7 @@ CFLAGS += -Wall -pthread
 all: ${HELPER_PROGS}
 
 TEST_FILES     := with_stress.sh
-TEST_PROGS     := test_stress.sh test_cpuset_prs.sh
+TEST_PROGS     := test_stress.sh test_cpuset_prs.sh test_cpuset_v1_hp.sh
 TEST_GEN_FILES := wait_inotify
 TEST_GEN_PROGS = test_memcontrol
 TEST_GEN_PROGS += test_kmem
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
index 89e8519fb2..e8d04ac9e3 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -18,7 +18,7 @@
  */
 static inline int values_close(long a, long b, int err)
 {
-	return abs(a - b) <= (a + b) / 100 * err;
+	return labs(a - b) <= (a + b) / 100 * err;
 }
 
 extern int cg_find_unified_root(char *root, size_t len, bool *nsdelegate);
diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c
index 186bf96f6a..dad2ed82f3 100644
--- a/tools/testing/selftests/cgroup/test_cpu.c
+++ b/tools/testing/selftests/cgroup/test_cpu.c
@@ -237,7 +237,7 @@ run_cpucg_weight_test(
 {
 	int ret = KSFT_FAIL, i;
 	char *parent = NULL;
-	struct cpu_hogger children[3] = {NULL};
+	struct cpu_hogger children[3] = {};
 
 	parent = cg_name(root, "cpucg_test_0");
 	if (!parent)
@@ -408,7 +408,7 @@ run_cpucg_nested_weight_test(const char *root, bool overprovisioned)
 {
 	int ret = KSFT_FAIL, i;
 	char *parent = NULL, *child = NULL;
-	struct cpu_hogger leaf[3] = {NULL};
+	struct cpu_hogger leaf[3] = {};
 	long nested_leaf_usage, child_usage;
 	int nprocs = get_nprocs();
 
diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh
new file mode 100755
index 0000000000..3f45512fb5
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh
@@ -0,0 +1,46 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test the special cpuset v1 hotplug case where a cpuset become empty of
+# CPUs will force migration of tasks out to an ancestor.
+#
+
+skip_test() {
+	echo "$1"
+	echo "Test SKIPPED"
+	exit 4 # ksft_skip
+}
+
+[[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!"
+
+# Find cpuset v1 mount point
+CPUSET=$(mount -t cgroup | grep cpuset | head -1 | awk -e '{print $3}')
+[[ -n "$CPUSET" ]] || skip_test "cpuset v1 mount point not found!"
+
+#
+# Create a test cpuset, put a CPU and a task there and offline that CPU
+#
+TDIR=test$$
+[[ -d $CPUSET/$TDIR ]] || mkdir $CPUSET/$TDIR
+echo 1 > $CPUSET/$TDIR/cpuset.cpus
+echo 0 > $CPUSET/$TDIR/cpuset.mems
+sleep 10&
+TASK=$!
+echo $TASK > $CPUSET/$TDIR/tasks
+NEWCS=$(cat /proc/$TASK/cpuset)
+[[ $NEWCS != "/$TDIR" ]] && {
+	echo "Unexpected cpuset $NEWCS, test FAILED!"
+	exit 1
+}
+
+echo 0 > /sys/devices/system/cpu/cpu1/online
+sleep 0.5
+echo 1 > /sys/devices/system/cpu/cpu1/online
+NEWCS=$(cat /proc/$TASK/cpuset)
+rmdir $CPUSET/$TDIR
+[[ $NEWCS != "/" ]] && {
+	echo "cpuset $NEWCS, test FAILED!"
+	exit 1
+}
+echo "Test PASSED"
+exit 0
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
index 137506db03..96693d8772 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -192,7 +192,7 @@ static int test_kmem_memcg_deletion(const char *root)
 		goto cleanup;
 
 	sum = anon + file + kernel + sock;
-	if (abs(sum - current) < MAX_VMSTAT_ERROR) {
+	if (labs(sum - current) < MAX_VMSTAT_ERROR) {
 		ret = KSFT_PASS;
 	} else {
 		printf("memory.current = %ld\n", current);
@@ -380,7 +380,7 @@ static int test_percpu_basic(const char *root)
 	current = cg_read_long(parent, "memory.current");
 	percpu = cg_read_key_long(parent, "memory.stat", "percpu ");
 
-	if (current > 0 && percpu > 0 && abs(current - percpu) <
+	if (current > 0 && percpu > 0 && labs(current - percpu) <
 	    MAX_VMSTAT_ERROR)
 		ret = KSFT_PASS;
 	else
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index b462416b38..41ae8047b8 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -716,7 +716,9 @@ static bool reclaim_until(const char *memcg, long goal)
  */
 static int test_memcg_reclaim(const char *root)
 {
-	int ret = KSFT_FAIL, fd, retries;
+	int ret = KSFT_FAIL;
+	int fd = -1;
+	int retries;
 	char *memcg;
 	long current, expected_usage;
 
diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c
index ef7f395453..190096017f 100644
--- a/tools/testing/selftests/cgroup/test_zswap.c
+++ b/tools/testing/selftests/cgroup/test_zswap.c
@@ -50,7 +50,7 @@ static int get_zswap_stored_pages(size_t *value)
 	return read_int("/sys/kernel/debug/zswap/stored_pages", value);
 }
 
-static int get_cg_wb_count(const char *cg)
+static long get_cg_wb_count(const char *cg)
 {
 	return cg_read_key_long(cg, "memory.stat", "zswpwb");
 }
@@ -249,6 +249,132 @@ out:
 }
 
 /*
+ * Attempt writeback with the following steps:
+ * 1. Allocate memory.
+ * 2. Reclaim memory equal to the amount that was allocated in step 1.
+      This will move it into zswap.
+ * 3. Save current zswap usage.
+ * 4. Move the memory allocated in step 1 back in from zswap.
+ * 5. Set zswap.max to half the amount that was recorded in step 3.
+ * 6. Attempt to reclaim memory equal to the amount that was allocated,
+      this will either trigger writeback if it's enabled, or reclamation
+      will fail if writeback is disabled as there isn't enough zswap space.
+ */
+static int attempt_writeback(const char *cgroup, void *arg)
+{
+	long pagesize = sysconf(_SC_PAGESIZE);
+	char *test_group = arg;
+	size_t memsize = MB(4);
+	char buf[pagesize];
+	long zswap_usage;
+	bool wb_enabled;
+	int ret = -1;
+	char *mem;
+
+	wb_enabled = cg_read_long(test_group, "memory.zswap.writeback");
+	mem = (char *)malloc(memsize);
+	if (!mem)
+		return ret;
+
+	/*
+	 * Fill half of each page with increasing data, and keep other
+	 * half empty, this will result in data that is still compressible
+	 * and ends up in zswap, with material zswap usage.
+	 */
+	for (int i = 0; i < pagesize; i++)
+		buf[i] = i < pagesize/2 ? (char) i : 0;
+
+	for (int i = 0; i < memsize; i += pagesize)
+		memcpy(&mem[i], buf, pagesize);
+
+	/* Try and reclaim allocated memory */
+	if (cg_write_numeric(test_group, "memory.reclaim", memsize)) {
+		ksft_print_msg("Failed to reclaim all of the requested memory\n");
+		goto out;
+	}
+
+	zswap_usage = cg_read_long(test_group, "memory.zswap.current");
+
+	/* zswpin */
+	for (int i = 0; i < memsize; i += pagesize) {
+		if (memcmp(&mem[i], buf, pagesize)) {
+			ksft_print_msg("invalid memory\n");
+			goto out;
+		}
+	}
+
+	if (cg_write_numeric(test_group, "memory.zswap.max", zswap_usage/2))
+		goto out;
+
+	/*
+	 * If writeback is enabled, trying to reclaim memory now will trigger a
+	 * writeback as zswap.max is half of what was needed when reclaim ran the first time.
+	 * If writeback is disabled, memory reclaim will fail as zswap is limited and
+	 * it can't writeback to swap.
+	 */
+	ret = cg_write_numeric(test_group, "memory.reclaim", memsize);
+	if (!wb_enabled)
+		ret = (ret == -EAGAIN) ? 0 : -1;
+
+out:
+	free(mem);
+	return ret;
+}
+
+/* Test to verify the zswap writeback path */
+static int test_zswap_writeback(const char *root, bool wb)
+{
+	long zswpwb_before, zswpwb_after;
+	int ret = KSFT_FAIL;
+	char *test_group;
+
+	test_group = cg_name(root, "zswap_writeback_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.zswap.writeback", wb ? "1" : "0"))
+		goto out;
+
+	zswpwb_before = get_cg_wb_count(test_group);
+	if (zswpwb_before != 0) {
+		ksft_print_msg("zswpwb_before = %ld instead of 0\n", zswpwb_before);
+		goto out;
+	}
+
+	if (cg_run(test_group, attempt_writeback, (void *) test_group))
+		goto out;
+
+	/* Verify that zswap writeback occurred only if writeback was enabled */
+	zswpwb_after = get_cg_wb_count(test_group);
+	if (zswpwb_after < 0)
+		goto out;
+
+	if (wb != !!zswpwb_after) {
+		ksft_print_msg("zswpwb_after is %ld while wb is %s",
+				zswpwb_after, wb ? "enabled" : "disabled");
+		goto out;
+	}
+
+	ret = KSFT_PASS;
+
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+static int test_zswap_writeback_enabled(const char *root)
+{
+	return test_zswap_writeback(root, true);
+}
+
+static int test_zswap_writeback_disabled(const char *root)
+{
+	return test_zswap_writeback(root, false);
+}
+
+/*
  * When trying to store a memcg page in zswap, if the memcg hits its memory
  * limit in zswap, writeback should affect only the zswapped pages of that
  * memcg.
@@ -257,7 +383,7 @@ static int test_no_invasive_cgroup_shrink(const char *root)
 {
 	int ret = KSFT_FAIL;
 	size_t control_allocation_size = MB(10);
-	char *control_allocation, *wb_group = NULL, *control_group = NULL;
+	char *control_allocation = NULL, *wb_group = NULL, *control_group = NULL;
 
 	wb_group = setup_test_group_1M(root, "per_memcg_wb_test1");
 	if (!wb_group)
@@ -342,7 +468,7 @@ static int test_no_kmem_bypass(const char *root)
 	struct sysinfo sys_info;
 	int ret = KSFT_FAIL;
 	int child_status;
-	char *test_group;
+	char *test_group = NULL;
 	pid_t child_pid;
 
 	/* Read sys info and compute test values accordingly */
@@ -364,8 +490,6 @@ static int test_no_kmem_bypass(const char *root)
 	trigger_allocation_size = sys_info.totalram / 20;
 
 	/* Set up test memcg */
-	if (cg_write(root, "cgroup.subtree_control", "+memory"))
-		goto out;
 	test_group = cg_name(root, "kmem_bypass_test");
 	if (!test_group)
 		goto out;
@@ -425,6 +549,8 @@ struct zswap_test {
 	T(test_zswap_usage),
 	T(test_swapin_nozswap),
 	T(test_zswapin),
+	T(test_zswap_writeback_enabled),
+	T(test_zswap_writeback_disabled),
 	T(test_no_kmem_bypass),
 	T(test_no_invasive_cgroup_shrink),
 };