MADV_COLD and MADV_PAGEOUT share a page-table walker covering ordinary
PTEs, PTE-mapped large folios and huge PMDs. Existing selftests provide
little coverage of its range, folio-state and permission decisions.

Add a kselftest harness test for both hints, starting with the most basic
behavior userspace relies on: MADV_COLD neither populates a PTE hole nor
faults a swapped page back in, and neither hint may be applied to a locked
VMA.

The swapped-page test skips when swap is unavailable.

Signed-off-by: Gregory Price (Meta) <[email protected]>
---
 tools/testing/selftests/mm/Makefile        |   2 +
 tools/testing/selftests/mm/ksft_madvise.sh |   4 +
 tools/testing/selftests/mm/madvise.c       | 134 +++++++++++++++++++++
 tools/testing/selftests/mm/run_vmtests.sh  |   5 +
 4 files changed, 145 insertions(+)
 create mode 100755 tools/testing/selftests/mm/ksft_madvise.sh
 create mode 100644 tools/testing/selftests/mm/madvise.c

diff --git a/tools/testing/selftests/mm/Makefile 
b/tools/testing/selftests/mm/Makefile
index beacc0f87304..07d61110eb24 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -69,6 +69,7 @@ TEST_GEN_FILES += hugetlb-shm
 TEST_GEN_FILES += hugetlb-soft-offline
 TEST_GEN_FILES += khugepaged
 TEST_GEN_FILES += madv_populate
+TEST_GEN_FILES += madvise
 TEST_GEN_FILES += map_fixed_noreplace
 TEST_GEN_FILES += map_populate
 ifneq (,$(filter $(ARCH),arm64 riscv riscv64 x86 x86_64 loongarch32 
loongarch64))
@@ -156,6 +157,7 @@ TEST_PROGS += ksft_ksm.sh
 TEST_PROGS += ksft_ksm_numa.sh
 TEST_PROGS += ksft_madv_guard.sh
 TEST_PROGS += ksft_madv_populate.sh
+TEST_PROGS += ksft_madvise.sh
 TEST_PROGS += ksft_memfd_secret.sh
 TEST_PROGS += ksft_memory_failure.sh
 TEST_PROGS += ksft_migration.sh
diff --git a/tools/testing/selftests/mm/ksft_madvise.sh 
b/tools/testing/selftests/mm/ksft_madvise.sh
new file mode 100755
index 000000000000..29cbbca800f2
--- /dev/null
+++ b/tools/testing/selftests/mm/ksft_madvise.sh
@@ -0,0 +1,4 @@
+#!/bin/sh -e
+# SPDX-License-Identifier: GPL-2.0
+
+./run_vmtests.sh -t madvise
diff --git a/tools/testing/selftests/mm/madvise.c 
b/tools/testing/selftests/mm/madvise.c
new file mode 100644
index 000000000000..bb4efb92e6da
--- /dev/null
+++ b/tools/testing/selftests/mm/madvise.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * MADV_COLD and MADV_PAGEOUT tests.
+ */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <stdbool.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include "kselftest_harness.h"
+#include "vm_util.h"
+
+/* Reclaim can fail transiently, so retry for up to a second. */
+#define PAGEOUT_RETRIES 100
+
+static size_t page_size;
+
+FIXTURE(madvise)
+{
+       int pagemap_fd;
+};
+
+FIXTURE_SETUP(madvise)
+{
+       page_size = getpagesize();
+
+       self->pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+       ASSERT_GE(self->pagemap_fd, 0);
+}
+
+FIXTURE_TEARDOWN(madvise)
+{
+       close(self->pagemap_fd);
+}
+
+/* Page out the range until its first page is swapped. */
+static bool pageout_until_swapped(struct __test_metadata *_metadata,
+                                 char *mapping, size_t size, int pagemap_fd)
+{
+       int retry;
+
+       for (retry = 0; retry < PAGEOUT_RETRIES; retry++) {
+               ASSERT_EQ(madvise(mapping, size, MADV_PAGEOUT), 0);
+               if (pagemap_is_swapped(pagemap_fd, mapping))
+                       return true;
+               usleep(10000);
+       }
+
+       return false;
+}
+
+/*
+ * Both hints are best effort, so these tests check what userspace can rely
+ * on: which mappings are accepted, which pages must never be reclaimed, and
+ * that neither hint changes memory contents or populates the range. A test
+ * that needs a page to be reclaimed first checks that reclaim works at all,
+ * and skips if it does not.
+ */
+
+/* Neither hint may populate a hole between two populated pages. */
+static void check_skips_pte_hole(struct __test_metadata *_metadata,
+                                int pagemap_fd, int advice)
+{
+       char *mapping;
+
+       mapping = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE,
+                      MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+       ASSERT_NE(mapping, MAP_FAILED);
+       mapping[0] = 1;
+       mapping[2 * page_size] = 1;
+       ASSERT_FALSE(pagemap_is_populated(pagemap_fd, mapping + page_size));
+
+       ASSERT_EQ(madvise(mapping, 3 * page_size, advice), 0);
+       ASSERT_FALSE(pagemap_is_populated(pagemap_fd, mapping + page_size));
+       ASSERT_EQ(mapping[0], 1);
+       ASSERT_EQ(mapping[2 * page_size], 1);
+
+       ASSERT_EQ(munmap(mapping, 3 * page_size), 0);
+}
+
+TEST_F(madvise, cold_skips_pte_hole)
+{
+       check_skips_pte_hole(_metadata, self->pagemap_fd, MADV_COLD);
+}
+
+/* Neither hint may be applied to locked memory. */
+TEST_F(madvise, locked_vma_is_rejected)
+{
+       char *mapping;
+
+       mapping = mmap(NULL, page_size, PROT_READ | PROT_WRITE,
+                      MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+       ASSERT_NE(mapping, MAP_FAILED);
+       mapping[0] = 1;
+       if (mlock(mapping, page_size))
+               SKIP(return, "could not lock a page");
+
+       ASSERT_EQ(madvise(mapping, page_size, MADV_COLD), -1);
+       ASSERT_EQ(errno, EINVAL);
+       ASSERT_EQ(madvise(mapping, page_size, MADV_PAGEOUT), -1);
+       ASSERT_EQ(errno, EINVAL);
+       ASSERT_EQ(mapping[0], 1);
+
+       ASSERT_EQ(munmap(mapping, page_size), 0);
+}
+
+/* Neither hint may fault a swapped page back in. */
+static void check_skips_swapped_pte(struct __test_metadata *_metadata,
+                                   int pagemap_fd, int advice)
+{
+       char *mapping;
+
+       mapping = mmap(NULL, page_size, PROT_READ | PROT_WRITE,
+                      MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+       ASSERT_NE(mapping, MAP_FAILED);
+       mapping[0] = 1;
+       if (!pageout_until_swapped(_metadata, mapping, page_size, pagemap_fd))
+               SKIP(return, "MADV_PAGEOUT did not swap the page");
+
+       ASSERT_EQ(madvise(mapping, page_size, advice), 0);
+       ASSERT_TRUE(pagemap_is_swapped(pagemap_fd, mapping));
+       ASSERT_EQ(mapping[0], 1);
+
+       ASSERT_EQ(munmap(mapping, page_size), 0);
+}
+
+TEST_F(madvise, cold_skips_swapped_pte)
+{
+       check_skips_swapped_pte(_metadata, self->pagemap_fd, MADV_COLD);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/mm/run_vmtests.sh 
b/tools/testing/selftests/mm/run_vmtests.sh
index a1b45a3dedae..0e6a24659d12 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -53,6 +53,8 @@ separated by spaces:
        test madvise(2) MADV_GUARD_INSTALL and MADV_GUARD_REMOVE options
 - madv_populate
        test memadvise(2) MADV_POPULATE_{READ,WRITE} options
+- madvise
+       test madvise(2) MADV_COLD and MADV_PAGEOUT
 - memfd_secret
        test memfd_secret(2)
 - process_mrelease
@@ -330,6 +332,9 @@ CATEGORY="madv_guard" run_test ./guard-regions
 # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests
 CATEGORY="madv_populate" run_test ./madv_populate
 
+# MADV_COLD and MADV_PAGEOUT tests
+CATEGORY="madvise" run_test ./madvise
+
 # PROCESS_MADV test
 CATEGORY="process_madv" run_test ./process_madv
 
-- 
2.56.0


Reply via email to