[PATCH v6 1/1] thp04: Add ptrace mode and fix tracee stop synchronization

This patch adds support for CONFIG_PROC_MEM_FORCE_PTRACE=y kernels where
direct writes to /proc/self/mem are disabled. The test now probes the
kernel policy at runtime and adapts its execution strategy accordingly.

Test Modes:

PROC_MEM_ALWAYS (default on most systems):
- Child process writes to its own memory via /proc/self/mem
- Concurrent execution: writes race with madvise() calls
- Uses fuzzy-sync to maximize race window
- This is the original CVE-2017-1000405 race condition test

PROC_MEM_PTRACE (CONFIG_PROC_MEM_FORCE_PTRACE=y):
- Parent writes to tracee's memory via /proc/pid/mem
- Write-stop-continue cycle: tracee must be STOPPED for writes
- Alternating execution: parent writes → tracee runs madvise → stops
- Required because /proc/pid/mem writes need PTRACE_MODE_ATTACH
- Note: Serialization eliminates the race; tests write functionality

The test automatically detects which mode to use by attempting a direct
write to /proc/self/mem during setup. If that fails with EIO, it falls
back to ptrace mode.

Kernel command line override: proc_mem.force_override=always|ptrace|never

Signed-off-by: Jan Polensky <[email protected]>
---
Link: https://lore.kernel.org/all/[email protected]/

Changes since v5:
- Remove unreachable tst_brk() in setup() (dead code)
- Fix misleading TBROK when tracee exits with TFAIL
  Add explicit WIFEXITED check in run_proc_mem_ptrace_serialized()
  to distinguish test failures from infrastructure problems

Changes since v4:
- Fix ptrace cleanup ownership by freeing only shared parent state.
- Add second checkpoint to serialize PTRACE_SEIZE before tracee SIGSTOP.
- Rename ptrace runner to reflect serialized execution.
- Clarify subject and commit text around tracee-stop synchronization.
- Fix LTP documentation block opening for catalog export.

Changes since v3:
- Move tracee lifecycle into run() to support re-invocation with -i N (Andrea Cervesato)
  * Each run() invocation spawns fresh tracee via setup_ptrace_tracee()
  * Tracee runs infinite loop, parent controls termination
  * After 1000 iterations: PTRACE_DETACH → SIGKILL → SAFE_WAITPID
  * cleanup() only handles error cases (uses tst_reap_children())
- Validated on s390x with -i 2 and -i 5 (both PASS)

Changes since v2:
- Added documentation clarifying that ptrace mode serialization eliminates the CVE race
- Fixed missing newline at end of file
- Addressed review feedback on race condition testing limitations

Changes since v1:
- detect proc_mem.force_override / kernel config instead of relying only on a probe write
- fix kernel parameter naming per review
- address feedback from Cyril Hrubis in previous thread

 testcases/kernel/mem/thp/thp04.c | 434 +++++++++++++++++++++++++++----
 1 file changed, 381 insertions(+), 53 deletions(-)

diff --git a/testcases/kernel/mem/thp/thp04.c b/testcases/kernel/mem/thp/thp04.c
index 16d766c349b7..dba47e295d9c 100644
--- a/testcases/kernel/mem/thp/thp04.c
+++ b/testcases/kernel/mem/thp/thp04.c
@@ -3,7 +3,7 @@
  * Copyright (c) 2019 SUSE LLC <[email protected]>
  */

-/*
+/*\
  * CVE-2017-1000405
  *
  * Check for the Huge Dirty Cow vulnerability which allows a userspace process
@@ -21,27 +21,67 @@
  * On old kernel such as 4.9, it has fixed the Dirty Cow bug but a similar check
  * in huge_memory.c was forgotten.  As a result, remote memory writes to ro regions
  * of memory backed by transparent huge pages cause an infinite loop in the kernel.
- * While in this state the process is stil SIGKILLable, but little else works.
+ * While in this state the process is still SIGKILLable, but little else works.
  * It is also a regression test about kernel
  * commit 8310d48b125d("huge_memory.c: respect FOLL_FORCE/FOLL_COW for thp").
+ *
+ * Test Modes (controlled by proc_mem.force_override=always|ptrace|never):
+ *
+ * PROC_MEM_ALWAYS: Direct writes to /proc/self/mem (default on most systems)
+ *   - Child process writes to its own memory via /proc/self/mem
+ *   - Concurrent execution: writes race with madvise() calls
+ *   - Uses fuzzy-sync to maximize race window
+ *
+ * PROC_MEM_PTRACE: Ptrace-based writes to /proc/pid/mem (CONFIG_PROC_MEM_FORCE_PTRACE=y)
+ *   - Parent writes to tracee's memory via /proc/pid/mem
+ *   - Write-stop-continue cycle: tracee must be STOPPED for writes to succeed
+ *   - Alternating execution: parent writes → tracee runs madvise → tracee stops → repeat
+ *   - Required because /proc/pid/mem writes need PTRACE_MODE_ATTACH (stopped state)
+ *   - Note: Serialization eliminates the race; tests write functionality, not the CVE race
  */

-#include "tst_test.h"
+#include <signal.h>
+#include <sys/ptrace.h>
+#include <sys/wait.h>
+
 #include "lapi/mmap.h"
+
+/* PTRACE mode is serialized and therefore uses fewer iterations. */
+#define PTRACE_TEST_ITERATIONS 1000
+#include "tst_checkpoint.h"
 #include "tst_fuzzy_sync.h"
+#include "tst_kconfig.h"
+#include "tst_test.h"

-static char *write_thp, *read_thp;
-static int *write_ptr, *read_ptr;
-static size_t thp_size;
-static int writefd = -1, readfd = -1;
-static struct tst_fzsync_pair fzsync_pair;
+enum proc_mem_mode {
+	PROC_MEM_ALWAYS,
+	PROC_MEM_PTRACE,
+	PROC_MEM_NEVER,
+};

-static void *alloc_zero_page(void *baseaddr)
+struct child_state {
+	char *write_thp;
+	char *read_thp;
+	int *write_ptr;
+	int *read_ptr;
+	size_t thp_size;
+	int writefd;
+	int readfd;
+	struct tst_fzsync_pair fzsync_pair;
+};
+
+static pid_t tracee_pid;
+/* Mode requested by kernel command line parsing. Do not mutate during probing. */
+static enum proc_mem_mode user_mode = PROC_MEM_ALWAYS;
+/* Runtime mode selected after checking whether direct /proc/self/mem writes work. */
+static enum proc_mem_mode effective_mode = PROC_MEM_ALWAYS;
+static struct child_state *child;
+
+static void *alloc_zero_page(void *baseaddr, size_t thp_size)
 {
 	int i;
 	void *ret;

-	/* Find aligned chunk of address space. MAP_HUGETLB doesn't work. */
 	for (i = 0; i < 16; i++, baseaddr += thp_size) {
 		ret = mmap(baseaddr, thp_size, PROT_READ,
 			MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
@@ -67,47 +107,86 @@ static void *alloc_zero_page(void *baseaddr)
 	}

 	tst_brk(TBROK, "Cannot map huge zero page near the specified address");
-	return NULL;	/* Silence compiler warning */
+	return NULL;
 }

-static void setup(void)
+static void free_child_state(void)
+{
+	if (child) {
+		SAFE_MUNMAP(child, sizeof(*child));
+		child = NULL;
+	}
+}
+
+static void child_cleanup(void)
+{
+	if (!child)
+		return;
+
+	if (effective_mode == PROC_MEM_ALWAYS)
+		tst_fzsync_pair_cleanup(&child->fzsync_pair);
+
+	if (child->readfd >= 0)
+		SAFE_CLOSE(child->readfd);
+
+	if (child->writefd >= 0)
+		SAFE_CLOSE(child->writefd);
+
+	if (child->read_thp)
+		SAFE_MUNMAP(child->read_thp, child->thp_size);
+
+	if (child->write_thp)
+		SAFE_MUNMAP(child->write_thp, child->thp_size);
+}
+
+static void child_setup(void)
 {
 	size_t i;

-	thp_size = tst_get_hugepage_size();
+	child->thp_size = tst_get_hugepage_size();

-	if (!thp_size)
+	if (!child->thp_size)
 		tst_brk(TCONF, "Kernel does not support huge pages");

-	write_thp = alloc_zero_page((void *)thp_size);
+	child->write_thp = alloc_zero_page((void *)child->thp_size,
+		child->thp_size);

-	for (i = 0; i < thp_size; i++) {
-		if (write_thp[i])
+	for (i = 0; i < child->thp_size; i++) {
+		if (child->write_thp[i])
 			tst_brk(TCONF, "Huge zero page is pre-polluted");
 	}

-	/* leave a hole between read and write THP to prevent merge */
-	read_thp = alloc_zero_page(write_thp + 2 * thp_size);
-	write_ptr = (int *)(write_thp + thp_size - sizeof(int));
-	read_ptr = (int *)(read_thp + thp_size - sizeof(int));
-	writefd = SAFE_OPEN("/proc/self/mem", O_RDWR);
-	readfd = SAFE_OPEN("/proc/self/mem", O_RDWR);
+	child->read_thp = alloc_zero_page(child->write_thp + 2 * child->thp_size,
+		child->thp_size);
+	/* write_ptr points to last int in write_thp page */
+	child->write_ptr = (int *)(child->write_thp + child->thp_size - sizeof(int));
+	/* read_ptr points to last int in read_thp page */
+	child->read_ptr = (int *)(child->read_thp + child->thp_size - sizeof(int));

-	fzsync_pair.exec_loops = 100000;
-	tst_fzsync_pair_init(&fzsync_pair);
+	/* In ptrace mode, parent opens /proc/<pid>/mem, not child */
+	if (effective_mode == PROC_MEM_ALWAYS) {
+		child->writefd = SAFE_OPEN("/proc/self/mem", O_RDWR);
+		child->readfd = SAFE_OPEN("/proc/self/mem", O_RDWR);
+		child->fzsync_pair.exec_loops = 100000;
+		tst_fzsync_pair_init(&child->fzsync_pair);
+	} else {
+		child->writefd = -1;
+		child->readfd = -1;
+	}
 }

-static void *thread_run(void *arg)
+/* Preserve the original fuzzy-sync race: this is the actual CVE trigger mechanism. */
+static void *thread_run_always(void *arg)
 {
 	int c;

-	while (tst_fzsync_run_b(&fzsync_pair)) {
-		tst_fzsync_start_race_b(&fzsync_pair);
-		madvise(write_thp, thp_size, MADV_DONTNEED);
-		memcpy(&c, write_ptr, sizeof(c));
-		SAFE_LSEEK(readfd, (off_t)write_ptr, SEEK_SET);
-		SAFE_READ(1, readfd, &c, sizeof(int));
-		tst_fzsync_end_race_b(&fzsync_pair);
+	while (tst_fzsync_run_b(&child->fzsync_pair)) {
+		tst_fzsync_start_race_b(&child->fzsync_pair);
+		madvise(child->write_thp, child->thp_size, MADV_DONTNEED);
+		memcpy(&c, child->write_ptr, sizeof(c));
+		SAFE_LSEEK(child->readfd, (off_t)child->write_ptr, SEEK_SET);
+		SAFE_READ(1, child->readfd, &c, sizeof(int));
+		tst_fzsync_end_race_b(&child->fzsync_pair);
 		/* Wait for dirty page handling before next madvise() */
 		usleep(10);
 	}
@@ -115,24 +194,24 @@ static void *thread_run(void *arg)
 	return arg;
 }

-static void run(void)
+static void run_proc_mem_always_race(void)
 {
 	int c = 0xdeadbeef;

-	tst_fzsync_pair_reset(&fzsync_pair, thread_run);
+	tst_fzsync_pair_reset(&child->fzsync_pair, thread_run_always);

-	while (tst_fzsync_run_a(&fzsync_pair)) {
+	while (tst_fzsync_run_a(&child->fzsync_pair)) {
 		/* Write into the main huge page */
-		tst_fzsync_start_race_a(&fzsync_pair);
-		SAFE_LSEEK(writefd, (off_t)write_ptr, SEEK_SET);
-		madvise(write_thp, thp_size, MADV_DONTNEED);
-		SAFE_WRITE(SAFE_WRITE_ALL, writefd, &c, sizeof(int));
-		tst_fzsync_end_race_a(&fzsync_pair);
+		tst_fzsync_start_race_a(&child->fzsync_pair);
+		SAFE_LSEEK(child->writefd, (off_t)child->write_ptr, SEEK_SET);
+		madvise(child->write_thp, child->thp_size, MADV_DONTNEED);
+		SAFE_WRITE(SAFE_WRITE_ALL, child->writefd, &c, sizeof(int));
+		tst_fzsync_end_race_a(&child->fzsync_pair);

 		/* Check the other huge zero page for pollution */
-		madvise(read_thp, thp_size, MADV_DONTNEED);
+		madvise(child->read_thp, child->thp_size, MADV_DONTNEED);

-		if (*read_ptr != 0) {
+		if (*child->read_ptr != 0) {
 			tst_res(TFAIL, "Huge zero page was polluted");
 			return;
 		}
@@ -141,20 +220,267 @@ static void run(void)
 	tst_res(TPASS, "Huge zero page is still clean");
 }

+static void tracee_main(void)
+{
+	/* child struct is already mapped by parent before fork */
+	child->writefd = -1;
+	child->readfd = -1;
+
+	child_setup();
+
+	TST_CHECKPOINT_WAKE(0);
+
+	/* Wait for parent to complete PTRACE_SEIZE before first raise(SIGSTOP) */
+	TST_CHECKPOINT_WAIT(1);
+
+	/*
+	 * Ptrace mode: writes and madvise are serialized (no race).
+	 * Tests kernel handling of writes to stopped processes, not the CVE race.
+	 * The stop/continue cycle is required because /proc/pid/mem writes need
+	 * PTRACE_MODE_ATTACH (tracee must be in stopped state).
+	 *
+	 * Run indefinitely - parent controls termination via PTRACE_DETACH.
+	 */
+	for (;;) {
+		madvise(child->write_thp, child->thp_size, MADV_DONTNEED);
+		madvise(child->read_thp, child->thp_size, MADV_DONTNEED);
+
+		if (*child->read_ptr != 0) {
+			tst_res(TFAIL, "Huge zero page was polluted");
+			child_cleanup();
+			exit(1);
+		}
+
+		/* Stop self to let parent write next iteration */
+		raise(SIGSTOP);
+	}
+}
+
+static int setup_ptrace_tracee(void)
+{
+	int status;
+
+	/* Test-loop state is initialized once and read-only afterwards. */
+	child = SAFE_MMAP(NULL, sizeof(*child), PROT_READ | PROT_WRITE,
+		MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	memset(child, 0, sizeof(*child));
+	child->writefd = -1;
+	child->readfd = -1;
+
+	tracee_pid = SAFE_FORK();
+	if (!tracee_pid) {
+		tracee_main();
+		exit(0);
+	}
+
+	TST_CHECKPOINT_WAIT(0);
+
+	SAFE_PTRACE(PTRACE_SEIZE, tracee_pid, NULL, NULL);
+
+	/* Signal tracee that PTRACE_SEIZE completed - safe to raise(SIGSTOP) now */
+	TST_CHECKPOINT_WAKE(1);
+
+	/*
+	 * Tracee will run first iteration (madvise + check) and self-stop with raise(SIGSTOP).
+	 * Wait for that SIGSTOP - this is iteration 0.
+	 */
+	SAFE_WAITPID(tracee_pid, &status, 0);
+
+	if (WIFEXITED(status)) {
+		if (WEXITSTATUS(status) != 0) {
+			/* Tracee reported result and exited early - already handled */
+			tracee_pid = 0;
+			free_child_state();
+			return 1;
+		}
+		tst_brk(TBROK, "Tracee exited unexpectedly before first SIGSTOP: %s",
+			tst_strstatus(status));
+	}
+
+	if (WIFSIGNALED(status))
+		tst_brk(TBROK, "Tracee was killed by signal before first SIGSTOP: %s",
+			tst_strstatus(status));
+
+	if (!WIFSTOPPED(status) || WSTOPSIG(status) != SIGSTOP)
+		tst_brk(TBROK, "Tracee did not self-stop with SIGSTOP: %s",
+			tst_strstatus(status));
+
+	return 0;
+}
+
+static void setup(void)
+{
+	int test_val = 0;
+	int explicit_mode = 0;
+
+	static struct tst_kcmdline_var params[] = {
+		TST_KCMDLINE_INIT("proc_mem.force_override"),
+	};
+
+	tst_kcmdline_parse(params, ARRAY_SIZE(params));
+
+	if (params[0].found) {
+		explicit_mode = 1;
+
+		if (!strcmp(params[0].value, "always")) {
+			user_mode = PROC_MEM_ALWAYS;
+		} else if (!strcmp(params[0].value, "ptrace")) {
+			user_mode = PROC_MEM_PTRACE;
+		} else {
+			user_mode = PROC_MEM_NEVER;
+			tst_brk(TCONF,
+				"Writes to /proc/self/mem disabled on kernel cmdline");
+		}
+	}
+
+	effective_mode = user_mode;
+
+	/* Probe direct /proc/self/mem writes only if not explicitly set to ptrace */
+	if (!explicit_mode || user_mode == PROC_MEM_ALWAYS) {
+		child = SAFE_MMAP(NULL, sizeof(*child), PROT_READ | PROT_WRITE,
+			MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+		memset(child, 0, sizeof(*child));
+		child->writefd = -1;
+		child->readfd = -1;
+
+		child_setup();
+
+		TEST(lseek(child->writefd, (off_t)child->write_ptr, SEEK_SET));
+		if (TST_RET == -1)
+			tst_brk(TBROK | TTERRNO, "lseek on /proc/self/mem failed");
+
+		TEST(write(child->writefd, &test_val, sizeof(test_val)));
+
+		if (TST_RET == sizeof(test_val)) {
+			/* Direct write succeeded */
+			effective_mode = PROC_MEM_ALWAYS;
+			return;
+		}
+
+		if (TST_RET == -1 && TST_ERR != EIO)
+			tst_brk(TBROK | TTERRNO, "test write to /proc/self/mem failed");
+
+		if (TST_RET != -1)
+			tst_brk(TBROK, "short write to /proc/self/mem: %ld bytes", TST_RET);
+
+		/* /proc/self/mem write failed, cleanup and try ptrace mode */
+		child_cleanup();
+		SAFE_MUNMAP(child, sizeof(*child));
+		child = NULL;
+
+		if (explicit_mode && user_mode == PROC_MEM_ALWAYS)
+			tst_brk(TCONF,
+				"Writes to /proc/self/mem disabled despite always mode");
+
+		effective_mode = PROC_MEM_PTRACE;
+	}
+
+	/* Ptrace mode: tracee will be spawned in run() for each iteration */
+	if (effective_mode == PROC_MEM_PTRACE)
+		return;
+}
+
+static void run_proc_mem_ptrace_serialized(void)
+{
+	char path[64];
+	int writefd;
+	int c = 0xdeadbeef;
+	int i;
+	int status;
+	int tracee_exited = 0;
+
+	snprintf(path, sizeof(path), "/proc/%d/mem", tracee_pid);
+	writefd = SAFE_OPEN(path, O_RDWR);
+
+	/*
+	 * Tracee is already in SIGSTOP state from setup_ptrace_tracee().
+	 * Write-stop-continue cycle: tracee is stopped, ready for writes.
+	 */
+	for (i = 0; i < PTRACE_TEST_ITERATIONS; i++) {
+		/* Write to /proc/pid/mem while tracee is stopped */
+		SAFE_LSEEK(writefd, (off_t)child->write_ptr, SEEK_SET);
+		SAFE_WRITE(SAFE_WRITE_ALL, writefd, &c, sizeof(int));
+
+		/* Let tracee run one iteration (madvise + check + raise(SIGSTOP)) */
+		SAFE_PTRACE(PTRACE_CONT, tracee_pid, NULL, NULL);
+
+		/* Wait for tracee to stop itself with raise(SIGSTOP) */
+		SAFE_WAITPID(tracee_pid, &status, 0);
+
+		if (WIFEXITED(status)) {
+			if (WEXITSTATUS(status) == 0)
+				tst_brk(TBROK, "Tracee exited unexpectedly: %s",
+						tst_strstatus(status));
+
+			/* Tracee reported result and exited, this is expected for TFAIL */
+			tracee_exited = 1;
+			break;
+		}
+
+		if (WIFSIGNALED(status))
+			tst_brk(TBROK, "Tracee was killed by signal: %s",
+				tst_strstatus(status));
+
+		if (!WIFSTOPPED(status) || WSTOPSIG(status) != SIGSTOP)
+			tst_brk(TBROK, "Tracee did not stop with SIGSTOP: %s",
+				tst_strstatus(status));
+	}
+
+	SAFE_CLOSE(writefd);
+
+	if (tracee_exited) {
+		/* Tracee already reported its result and exited - cleanup and return */
+		tracee_pid = 0;
+		free_child_state();
+		return;
+	}
+
+	/* Test passed - huge zero page remained clean through PTRACE_TEST_ITERATIONS iterations */
+	tst_res(TPASS, "Huge zero page is still clean after serialized ptrace writes");
+
+	/* Detach and terminate tracee */
+	SAFE_PTRACE(PTRACE_DETACH, tracee_pid, NULL, NULL);
+	SAFE_WAITPID(tracee_pid, &status, WNOHANG);
+	SAFE_KILL(tracee_pid, SIGKILL);
+	SAFE_WAITPID(tracee_pid, &status, 0);
+	tracee_pid = 0;
+
+	/* Tracee is fully reaped - free shared child state */
+	free_child_state();
+}
+
+static void run(void)
+{
+	if (effective_mode == PROC_MEM_ALWAYS) {
+		run_proc_mem_always_race();
+	} else if (effective_mode == PROC_MEM_PTRACE) {
+		/* Spawn fresh tracee for each iteration */
+		if (setup_ptrace_tracee())
+			return; /* Tracee exited early, already reported result */
+		run_proc_mem_ptrace_serialized();
+	} else {
+		tst_brk(TBROK, "Unknown proc mem mode");
+	}
+}
+
 static void cleanup(void)
 {
-	tst_fzsync_pair_cleanup(&fzsync_pair);
+	if (tracee_pid > 0) {
+		/*
+		 * Tracee is normally reaped in run_proc_mem_ptrace_serialized().
+		 * Only kill if still alive (e.g., test aborted with TBROK).
+		 */
+		if (kill(tracee_pid, 0) == 0) {
+			SAFE_KILL(tracee_pid, SIGKILL);
+			tst_reap_children();
+		}
+		tracee_pid = 0;
+	}

-	if (readfd >= 0)
-		SAFE_CLOSE(readfd);
+	if (effective_mode == PROC_MEM_ALWAYS)
+		child_cleanup();

-	if (writefd >= 0)
-		SAFE_CLOSE(writefd);
-
-	if (read_thp)
-		SAFE_MUNMAP(read_thp, thp_size);
-	if (write_thp)
-		SAFE_MUNMAP(write_thp, thp_size);
+	free_child_state();
 }

 static struct tst_test test = {
@@ -162,6 +488,8 @@ static struct tst_test test = {
 	.setup = setup,
 	.cleanup = cleanup,
 	.runtime = 150,
+	.forks_child = 1,
+	.needs_checkpoints = 1,
 	.tags = (const struct tst_tag[]) {
 		{"linux-git", "a8f97366452e"},
 		{"linux-git", "8310d48b125d"},
--
2.55.0


-- 
Mailing list info: https://lists.linux.it/listinfo/ltp