+ selftests-mm-add-process_madvise-tests.patch added to mm-new branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: selftests/mm: add process_madvise() tests
has been added to the -mm mm-new branch.  Its filename is
     selftests-mm-add-process_madvise-tests.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/selftests-mm-add-process_madvise-tests.patch

This patch will later appear in the mm-new branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Note, mm-new is a provisional staging ground for work-in-progress
patches, and acceptance into mm-new is a notification for others take
notice and to finish up reviews.  Please do not hesitate to respond to
review feedback and post updated versions to replace or incrementally
fixup patches in mm-new.

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: wang lian <lianux.mm@gmail.com>
Subject: selftests/mm: add process_madvise() tests
Date: Mon, 21 Jul 2025 19:46:14 +0800

Add tests for process_madvise(), focusing on verifying behavior under
various conditions including valid usage and error cases.

Link: https://lkml.kernel.org/r/20250721114614.40996-1-lianux.mm@gmail.com
Signed-off-by: wang lian <lianux.mm@gmail.com>
Suggested-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Suggested-by: Zi Yan <ziy@nvidia.com>
Suggested-by: Mark Brown <broonie@kernel.org>
Acked-by: SeongJae Park <sj@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jann Horn <jannh@google.com>
Cc: Kairui Song <ryncsn@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 tools/testing/selftests/mm/.gitignore     |    1 
 tools/testing/selftests/mm/Makefile       |    1 
 tools/testing/selftests/mm/process_madv.c |  302 ++++++++++++++++++++
 tools/testing/selftests/mm/run_vmtests.sh |    5 
 4 files changed, 309 insertions(+)

--- a/tools/testing/selftests/mm/.gitignore~selftests-mm-add-process_madvise-tests
+++ a/tools/testing/selftests/mm/.gitignore
@@ -21,6 +21,7 @@ on-fault-limit
 transhuge-stress
 pagemap_ioctl
 pfnmap
+process_madv
 *.tmp*
 protection_keys
 protection_keys_32
--- a/tools/testing/selftests/mm/Makefile~selftests-mm-add-process_madvise-tests
+++ a/tools/testing/selftests/mm/Makefile
@@ -85,6 +85,7 @@ TEST_GEN_FILES += mseal_test
 TEST_GEN_FILES += on-fault-limit
 TEST_GEN_FILES += pagemap_ioctl
 TEST_GEN_FILES += pfnmap
+TEST_GEN_FILES += process_madv
 TEST_GEN_FILES += thuge-gen
 TEST_GEN_FILES += transhuge-stress
 TEST_GEN_FILES += uffd-stress
diff --git a/tools/testing/selftests/mm/process_madv.c a/tools/testing/selftests/mm/process_madv.c
new file mode 100644
--- /dev/null
+++ a/tools/testing/selftests/mm/process_madv.c
@@ -0,0 +1,302 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#define _GNU_SOURCE
+#include "../kselftest_harness.h"
+#include <errno.h>
+#include <setjmp.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/mman.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <sched.h>
+#include "vm_util.h"
+
+#include "../pidfd/pidfd.h"
+
+FIXTURE(process_madvise)
+{
+	unsigned long page_size;
+	pid_t child_pid;
+	int remote_pidfd;
+	int pidfd;
+};
+
+FIXTURE_SETUP(process_madvise)
+{
+	self->page_size = (unsigned long)sysconf(_SC_PAGESIZE);
+	self->pidfd = PIDFD_SELF;
+	self->remote_pidfd = -1;
+	self->child_pid = -1;
+};
+
+FIXTURE_TEARDOWN_PARENT(process_madvise)
+{
+	/* This teardown is guaranteed to run, even if tests SKIP or ASSERT */
+	if (self->child_pid > 0) {
+		kill(self->child_pid, SIGKILL);
+		waitpid(self->child_pid, NULL, 0);
+	}
+
+	if (self->remote_pidfd >= 0)
+		close(self->remote_pidfd);
+}
+
+static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec,
+				   size_t vlen, int advice, unsigned int flags)
+{
+	return syscall(__NR_process_madvise, pidfd, iovec, vlen, advice, flags);
+}
+
+/*
+ * This test uses PIDFD_SELF to target the current process. The main
+ * goal is to verify the basic behavior of process_madvise() with
+ * a vector of non-contiguous memory ranges, not its cross-process
+ * capabilities.
+ */
+TEST_F(process_madvise, basic)
+{
+	const unsigned long pagesize = self->page_size;
+	const int madvise_pages = 4;
+	struct iovec vec[madvise_pages];
+	int pidfd = self->pidfd;
+	ssize_t ret;
+	char *map;
+
+	/*
+	 * Create a single large mapping. We will pick pages from this
+	 * mapping to advise on. This ensures we test non-contiguous iovecs.
+	 */
+	map = mmap(NULL, pagesize * 10, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	if (map == MAP_FAILED)
+		SKIP(return, "mmap failed, not enough memory.\n");
+
+	/* Fill the entire region with a known pattern. */
+	memset(map, 'A', pagesize * 10);
+
+	/*
+	 * Setup the iovec to point to 4 non-contiguous pages
+	 * within the mapping.
+	 */
+	vec[0].iov_base = &map[0 * pagesize];
+	vec[0].iov_len = pagesize;
+	vec[1].iov_base = &map[3 * pagesize];
+	vec[1].iov_len = pagesize;
+	vec[2].iov_base = &map[5 * pagesize];
+	vec[2].iov_len = pagesize;
+	vec[3].iov_base = &map[8 * pagesize];
+	vec[3].iov_len = pagesize;
+
+	ret = sys_process_madvise(pidfd, vec, madvise_pages, MADV_DONTNEED, 0);
+	if (ret == -1 && errno == EPERM)
+		SKIP(return,
+			   "process_madvise() unsupported or permission denied, try running as root.\n");
+	else if (errno == EINVAL)
+		SKIP(return,
+			   "process_madvise() unsupported or parameter invalid, please check arguments.\n");
+
+	/* The call should succeed and report the total bytes processed. */
+	ASSERT_EQ(ret, madvise_pages * pagesize);
+
+	/* Check that advised pages are now zero. */
+	for (int i = 0; i < madvise_pages; i++) {
+		char *advised_page = (char *)vec[i].iov_base;
+
+		/* Content must be 0, not 'A'. */
+		ASSERT_EQ(*advised_page, '\0');
+	}
+
+	/* Check that an un-advised page in between is still 'A'. */
+	char *unadvised_page = &map[1 * pagesize];
+
+	for (int i = 0; i < pagesize; i++)
+		ASSERT_EQ(unadvised_page[i], 'A');
+
+	/* Cleanup. */
+	ASSERT_EQ(munmap(map, pagesize * 10), 0);
+}
+
+/*
+ * This test deterministically validates process_madvise() with MADV_COLLAPSE
+ * on a remote process, other advices are difficult to verify reliably.
+ *
+ * The test verifies that a memory region in a child process,
+ * focus on process_madv remote result, only check addresses and lengths.
+ * The correctness of the MADV_COLLAPSE can be found in the relevant test examples in khugepaged.
+ */
+TEST_F(process_madvise, remote_collapse)
+{
+	const unsigned long pagesize = self->page_size;
+	long huge_page_size;
+	int pipe_info[2];
+	ssize_t ret;
+	struct iovec vec;
+
+	struct child_info {
+		pid_t pid;
+		void *map_addr;
+	} info;
+
+	huge_page_size = default_huge_page_size();
+	if (huge_page_size <= 0)
+		SKIP(return, "Could not determine a valid huge page size.\n");
+
+	ASSERT_EQ(pipe(pipe_info), 0);
+
+	self->child_pid = fork();
+	ASSERT_NE(self->child_pid, -1);
+
+	if (self->child_pid == 0) {
+		char *map;
+		size_t map_size = 2 * huge_page_size;
+
+		close(pipe_info[0]);
+
+		map = mmap(NULL, map_size, PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+		ASSERT_NE(map, MAP_FAILED);
+
+		/* Fault in as small pages */
+		for (size_t i = 0; i < map_size; i += pagesize)
+			map[i] = 'A';
+
+		/* Send info and pause */
+		info.pid = getpid();
+		info.map_addr = map;
+		ret = write(pipe_info[1], &info, sizeof(info));
+		ASSERT_EQ(ret, sizeof(info));
+		close(pipe_info[1]);
+
+		pause();
+		exit(0);
+	}
+
+	close(pipe_info[1]);
+
+	/* Receive child info */
+	ret = read(pipe_info[0], &info, sizeof(info));
+	if (ret <= 0) {
+		waitpid(self->child_pid, NULL, 0);
+		SKIP(return, "Failed to read child info from pipe.\n");
+	}
+	ASSERT_EQ(ret, sizeof(info));
+	close(pipe_info[0]);
+	self->child_pid = info.pid;
+
+	self->remote_pidfd = syscall(__NR_pidfd_open, self->child_pid, 0);
+	ASSERT_GE(self->remote_pidfd, 0);
+
+	vec.iov_base = info.map_addr;
+	vec.iov_len = huge_page_size;
+
+	ret = sys_process_madvise(self->remote_pidfd, &vec, 1, MADV_COLLAPSE, 0);
+	if (ret == -1) {
+		if (errno == EINVAL)
+			SKIP(return, "PROCESS_MADV_ADVISE is not supported.\n");
+		else if (errno == EPERM)
+			SKIP(return,
+				   "No process_madvise() permissions, try running as root.\n");
+		return;
+	}
+
+	ASSERT_EQ(ret, huge_page_size);
+}
+
+/*
+ * Test process_madvise() with a pidfd for a process that has already
+ * exited to ensure correct error handling.
+ */
+TEST_F(process_madvise, exited_process_pidfd)
+{
+	struct iovec vec;
+	ssize_t ret;
+	int pidfd;
+
+	vec.iov_base = (void *)0x1234;
+	vec.iov_len = 4096;
+
+	/*
+	 * Using a pidfd for a process that has already exited should fail
+	 * with ESRCH.
+	 */
+	self->child_pid = fork();
+	ASSERT_NE(self->child_pid, -1);
+
+	if (self->child_pid == 0)
+		exit(0);
+
+	pidfd = syscall(__NR_pidfd_open, self->child_pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	/* Wait for the child to ensure it has terminated. */
+	waitpid(self->child_pid, NULL, 0);
+
+	ret = sys_process_madvise(pidfd, &vec, 1, MADV_DONTNEED, 0);
+	ASSERT_EQ(ret, -1);
+	ASSERT_EQ(errno, ESRCH);
+	close(pidfd);
+}
+
+/*
+ * Test process_madvise() with bad pidfds to ensure correct error
+ * handling.
+ */
+TEST_F(process_madvise, bad_pidfd)
+{
+	struct iovec vec;
+	ssize_t ret;
+
+	vec.iov_base = (void *)0x1234;
+	vec.iov_len = 4096;
+
+	/* Using an invalid fd number (-1) should fail with EBADF. */
+	ret = sys_process_madvise(-1, &vec, 1, MADV_DONTNEED, 0);
+	ASSERT_EQ(ret, -1);
+	ASSERT_EQ(errno, EBADF);
+
+	/*
+	 * Using a valid fd that is not a pidfd (e.g. stdin) should fail
+	 * with EBADF.
+	 */
+	ret = sys_process_madvise(STDIN_FILENO, &vec, 1, MADV_DONTNEED, 0);
+	ASSERT_EQ(ret, -1);
+	ASSERT_EQ(errno, EBADF);
+}
+
+/*
+ * Test process_madvise() with an invalid flag value. Currently, only a flag
+ * value of 0 is supported. This test is reserved for the future, e.g., if
+ * synchronous flags are added.
+ */
+TEST_F(process_madvise, flag)
+{
+	const unsigned long pagesize = self->page_size;
+	unsigned int invalid_flag;
+	int pidfd = self->pidfd;
+	struct iovec vec;
+	char *map;
+	ssize_t ret;
+
+	map = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1,
+		   0);
+	if (map == MAP_FAILED)
+		SKIP(return, "mmap failed, not enough memory.\n");
+
+	vec.iov_base = map;
+	vec.iov_len = pagesize;
+
+	invalid_flag = 0x80000000;
+
+	ret = sys_process_madvise(pidfd, &vec, 1, MADV_DONTNEED, invalid_flag);
+	ASSERT_EQ(ret, -1);
+	ASSERT_EQ(errno, EINVAL);
+
+	/* Cleanup. */
+	ASSERT_EQ(munmap(map, pagesize), 0);
+}
+
+TEST_HARNESS_MAIN
--- a/tools/testing/selftests/mm/run_vmtests.sh~selftests-mm-add-process_madvise-tests
+++ a/tools/testing/selftests/mm/run_vmtests.sh
@@ -65,6 +65,8 @@ separated by spaces:
 	test pagemap_scan IOCTL
 - pfnmap
 	tests for VM_PFNMAP handling
+- process_madv
+	test for process_madv
 - cow
 	test copy-on-write semantics
 - thp
@@ -425,6 +427,9 @@ CATEGORY="madv_guard" run_test ./guard-r
 # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests
 CATEGORY="madv_populate" run_test ./madv_populate
 
+# PROCESS_MADV test
+CATEGORY="process_madv" run_test ./process_madv
+
 CATEGORY="vma_merge" run_test ./merge
 
 if [ -x ./memfd_secret ]
_

Patches currently in -mm which might be from lianux.mm@gmail.com are

selftests-mm-reuse-force_read-to-replace-asm-volatile-r-xxx.patch
selftests-mm-guard-regions-use-skip-instead-of-ksft_exit_skip.patch
selftests-mm-add-process_madvise-tests.patch