[PATCH v9 5/6] selftests/mm: add a swap tier configuration test

[Youngjun Park]

This commit adds a test program for the global swap tier interface at
/sys/kernel/mm/swap/tiers. It checks the add, split and remove
operations and the documented error and batch atomicity rules. It also
checks that a tier with an active swap device cannot be removed until
the device is swapped off. That device is a zram device, and the check
is skipped when zram is not available.

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Youngjun Park <youngjun.park@xxxxxxx>
---
 tools/testing/selftests/mm/.gitignore     |   1 +
 tools/testing/selftests/mm/Makefile       |   1 +
 tools/testing/selftests/mm/config         |   2 +
 tools/testing/selftests/mm/run_vmtests.sh |   5 +
 tools/testing/selftests/mm/swap_tier.c    | 323 ++++++++++++++++++++++
 5 files changed, 332 insertions(+)
 create mode 100644 tools/testing/selftests/mm/swap_tier.c

diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore
index 9ccd9e1447e6..a6e588c7979e 100644
--- a/tools/testing/selftests/mm/.gitignore
+++ b/tools/testing/selftests/mm/.gitignore
@@ -46,6 +46,7 @@ hmm-tests
 memfd_secret
 soft-dirty
 split_huge_page_test
+swap_tier
 ksm_tests
 local_config.h
 local_config.mk
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index e6df968f0971..1836127df092 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -105,6 +105,7 @@ TEST_GEN_FILES += guard-regions
 TEST_GEN_FILES += merge
 TEST_GEN_FILES += rmap
 TEST_GEN_FILES += folio_split_race_test
+TEST_GEN_FILES += swap_tier
 
 ifneq ($(ARCH),arm64)
 TEST_GEN_FILES += soft-dirty
diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config
index 06f78bd232e2..de3752e1bbd2 100644
--- a/tools/testing/selftests/mm/config
+++ b/tools/testing/selftests/mm/config
@@ -14,3 +14,5 @@ CONFIG_UPROBES=y
 CONFIG_MEMORY_FAILURE=y
 CONFIG_HWPOISON_INJECT=m
 CONFIG_PROC_MEM_ALWAYS_FORCE=y
+CONFIG_SWAP=y
+CONFIG_ZRAM=y
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index 8c296dedf047..1b0b8ec185a9 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -71,6 +71,8 @@ separated by spaces:
 	tests for VM_PFNMAP handling
 - process_madv
 	test for process_madv
+- swap_tier
+	test the /sys/kernel/mm/swap/tiers configuration interface
 - cow
 	test copy-on-write semantics
 - thp
@@ -353,6 +355,9 @@ CATEGORY="process_madv" run_test ./process_madv
 
 CATEGORY="vma_merge" run_test ./merge
 
+# swap tier configuration interface (/sys/kernel/mm/swap/tiers)
+CATEGORY="swap_tier" run_test ./swap_tier
+
 if [ -x ./memfd_secret ]
 then
 if [ -f /proc/sys/kernel/yama/ptrace_scope ]; then
diff --git a/tools/testing/selftests/mm/swap_tier.c b/tools/testing/selftests/mm/swap_tier.c
new file mode 100644
index 000000000000..b4fe21b0eb5d
--- /dev/null
+++ b/tools/testing/selftests/mm/swap_tier.c
@@ -0,0 +1,323 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/swap.h>
+#include <unistd.h>
+
+#include "kselftest.h"
+
+#define TIERS_PATH "/sys/kernel/mm/swap/tiers"
+
+static int tiers_write(const char *cmd)
+{
+	int fd, ret = 0;
+
+	fd = open(TIERS_PATH, O_WRONLY);
+	if (fd < 0)
+		return -errno;
+	if (write(fd, cmd, strlen(cmd)) < 0)
+		ret = -errno;
+	close(fd);
+	return ret;
+}
+
+static int tier_range(const char *name, int *start, int *end)
+{
+	char buf[4096], *line, *save;
+	int fd;
+	ssize_t n;
+
+	fd = open(TIERS_PATH, O_RDONLY);
+	if (fd < 0)
+		return -1;
+	n = read(fd, buf, sizeof(buf) - 1);
+	close(fd);
+	if (n < 0)
+		return -1;
+	buf[n] = '\0';
+
+	for (line = strtok_r(buf, "\n", &save); line;
+	     line = strtok_r(NULL, "\n", &save)) {
+		char tname[64];
+		int idx, s, e;
+
+		/* The header line has no integer columns, so sscanf skips it. */
+		if (sscanf(line, "%63s %d %d %d", tname, &idx, &s, &e) != 4)
+			continue;
+		if (!strcmp(tname, name)) {
+			*start = s;
+			*end = e;
+			return 0;
+		}
+	}
+	return -1;
+}
+
+static bool tier_exists(const char *name)
+{
+	int s, e;
+
+	return tier_range(name, &s, &e) == 0;
+}
+
+static bool range_is(const char *name, int start, int end)
+{
+	int s, e;
+
+	if (tier_range(name, &s, &e))
+		return false;
+	return s == start && e == end;
+}
+
+static int tier_count(void)
+{
+	char buf[4096], *line, *save;
+	int fd, count = 0;
+	ssize_t n;
+
+	fd = open(TIERS_PATH, O_RDONLY);
+	if (fd < 0)
+		return -1;
+	n = read(fd, buf, sizeof(buf) - 1);
+	close(fd);
+	if (n < 0)
+		return -1;
+	buf[n] = '\0';
+
+	for (line = strtok_r(buf, "\n", &save); line;
+	     line = strtok_r(NULL, "\n", &save)) {
+		char tname[64];
+		int idx, s, e;
+
+		if (sscanf(line, "%63s %d %d %d", tname, &idx, &s, &e) == 4)
+			count++;
+	}
+	return count;
+}
+
+/*
+ * A single add at a priority above -1, from the empty set, leaves the range
+ * below it uncovered and must be rejected. the set stays empty.
+ */
+static int test_coverage(void)
+{
+	if (tiers_write("+orphan:100") != -EINVAL)
+		return KSFT_FAIL;
+	if (tier_exists("orphan"))
+		return KSFT_FAIL;
+	return KSFT_PASS;
+}
+
+/*
+ * Add two tiers covering the full range. The end priority of a tier is the
+ * start of the next higher tier minus one.
+ */
+static int test_add(void)
+{
+	if (tiers_write("+lo:-1 +hi:50"))
+		return KSFT_FAIL;
+	if (!range_is("hi", 50, SHRT_MAX) || !range_is("lo", -1, 49))
+		return KSFT_FAIL;
+	return KSFT_PASS;
+}
+
+/* Adding a tier inside an existing range splits it. the lower part shrinks. */
+static int test_split(void)
+{
+	if (tiers_write("+mid:100"))
+		return KSFT_FAIL;
+	if (!range_is("mid", 100, SHRT_MAX) ||
+	    !range_is("hi", 50, 99) ||
+	    !range_is("lo", -1, 49))
+		return KSFT_FAIL;
+	return KSFT_PASS;
+}
+
+/* Removing a tier merges its range into the adjacent (lower) tier. */
+static int test_remove(void)
+{
+	/* Remove the top tier: 'hi' re-expands upward to SHRT_MAX. */
+	if (tiers_write("-mid"))
+		return KSFT_FAIL;
+	if (tier_exists("mid") || !range_is("hi", 50, SHRT_MAX))
+		return KSFT_FAIL;
+
+	/* Remove the lowest tier: 'hi' shifts its start down to -1. */
+	if (tiers_write("-lo"))
+		return KSFT_FAIL;
+	if (tier_exists("lo") || !range_is("hi", -1, SHRT_MAX))
+		return KSFT_FAIL;
+
+	return KSFT_PASS;
+}
+
+/* Each invalid operation must fail with its documented errno. State: hi[-1,MAX]. */
+static int test_errors(void)
+{
+	if (tiers_write("+hi:100") != -EEXIST)		/* duplicate name */
+		return KSFT_FAIL;
+	if (tiers_write("+bad.name:100") != -EINVAL)	/* illegal name */
+		return KSFT_FAIL;
+	if (tiers_write("+dup:-1") != -EBUSY)		/* priority in use */
+		return KSFT_FAIL;
+	if (tiers_write("+low:-2") != -EINVAL)		/* prio < DEF_SWAP_PRIO */
+		return KSFT_FAIL;
+	return KSFT_PASS;
+}
+
+/*
+ * A write carrying several operations is atomic: if any operation fails, the
+ * whole batch is rolled back. The second '+a' duplicates the first and fails,
+ * so neither must take effect. State before/after: hi[-1,MAX].
+ */
+static int test_atomic(void)
+{
+	if (tiers_write("+a:50 +a:60") != -EEXIST)
+		return KSFT_FAIL;
+	if (tier_exists("a") || !range_is("hi", -1, SHRT_MAX))
+		return KSFT_FAIL;
+	return KSFT_PASS;
+}
+
+static int zram_add(long size)
+{
+	char path[128], val[64];
+	ssize_t n;
+	int idx, fd;
+
+	fd = open("/sys/class/zram-control/hot_add", O_RDONLY);
+	if (fd < 0)
+		return -1;
+	n = read(fd, val, sizeof(val) - 1);
+	close(fd);
+	if (n <= 0)
+		return -1;
+	val[n] = '\0';
+	idx = atoi(val);
+
+	snprintf(path, sizeof(path), "/sys/block/zram%d/disksize", idx);
+	fd = open(path, O_WRONLY);
+	if (fd < 0)
+		return -1;
+	snprintf(val, sizeof(val), "%ld", size);
+	n = write(fd, val, strlen(val));
+	close(fd);
+	return n < 0 ? -1 : idx;
+}
+
+static void zram_remove(int idx)
+{
+	char val[16];
+	int fd;
+
+	fd = open("/sys/class/zram-control/hot_remove", O_WRONLY);
+	if (fd < 0)
+		return;
+	snprintf(val, sizeof(val), "%d", idx);
+	if (write(fd, val, strlen(val)) < 0)
+		; /* ignore: best-effort cleanup */
+	close(fd);
+}
+
+static int swap_setup(const char *dev, int prio)
+{
+	char cmd[128];
+
+	snprintf(cmd, sizeof(cmd), "mkswap %s >/dev/null 2>&1", dev);
+	if (system(cmd))
+		return -1;
+	return swapon(dev, SWAP_FLAG_PREFER | (prio & SWAP_FLAG_PRIO_MASK));
+}
+
+/* A tier holding an active swap device can't be removed until swapoff. */
+static int test_device_pins_tier(void)
+{
+	char dev[32];
+	int zidx, ret = KSFT_FAIL;
+
+	if (tiers_write("+top:50"))
+		return KSFT_FAIL;
+
+	zidx = zram_add(64 << 20);
+	if (zidx < 0) {
+		ret = KSFT_SKIP;
+		goto out_tier;
+	}
+	snprintf(dev, sizeof(dev), "/dev/zram%d", zidx);
+	if (swap_setup(dev, 50)) {
+		ret = KSFT_SKIP;
+		goto out_zram;
+	}
+
+	if (tiers_write("-top") == -EBUSY) {		/* blocked while active */
+		swapoff(dev);
+		if (!tiers_write("-top"))		/* removable after swapoff */
+			ret = KSFT_PASS;
+	} else {
+		swapoff(dev);
+	}
+out_zram:
+	zram_remove(zidx);
+out_tier:
+	tiers_write("-top");
+	return ret;
+}
+
+/* Remove all remaining tiers, so a mid-test failure still leaves them empty. */
+static void tiers_clear(void)
+{
+	char buf[4096], *line, *save;
+	int fd;
+	ssize_t n;
+
+	fd = open(TIERS_PATH, O_RDONLY);
+	if (fd < 0)
+		return;
+	n = read(fd, buf, sizeof(buf) - 1);
+	close(fd);
+	if (n < 0)
+		return;
+	buf[n] = '\0';
+
+	for (line = strtok_r(buf, "\n", &save); line;
+	     line = strtok_r(NULL, "\n", &save)) {
+		char name[64], cmd[80];
+		int idx, s, e;
+
+		if (sscanf(line, "%63s %d %d %d", name, &idx, &s, &e) != 4)
+			continue;
+		snprintf(cmd, sizeof(cmd), "-%s", name);
+		tiers_write(cmd);
+	}
+}
+
+int main(void)
+{
+	ksft_print_header();
+	ksft_set_plan(7);
+
+	if (geteuid() != 0)
+		ksft_exit_skip("test requires root\n");
+	if (access(TIERS_PATH, F_OK))
+		ksft_exit_skip("%s not present (CONFIG_SWAP/tiers)\n", TIERS_PATH);
+	if (tier_count() != 0)
+		ksft_exit_skip("swap tiers already configured; run on a clean system\n");
+
+	ksft_test_result(test_coverage() == KSFT_PASS, "coverage rule\n");
+	ksft_test_result(test_add() == KSFT_PASS, "add tiers\n");
+	ksft_test_result(test_split() == KSFT_PASS, "split tier\n");
+	ksft_test_result(test_remove() == KSFT_PASS, "remove and merge\n");
+	ksft_test_result(test_errors() == KSFT_PASS, "invalid operations\n");
+	ksft_test_result(test_atomic() == KSFT_PASS, "batch atomicity\n");
+
+	ksft_test_result_code(test_device_pins_tier(), "device pins its tier", NULL);
+
+	tiers_clear();
+
+	ksft_finished();
+}
-- 
2.48.1