Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
To:     linux-kernel@vger.kernel.org
Cc:     Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>, Will Deacon <will@kernel.org>,
        Dmitry Vyukov <dvyukov@google.com>
From:   Alexey Kardashevskiy <aik@ozlabs.ru>
Subject: BUG: MAX_LOCKDEP_KEYS too low!
Message-ID: <c099ad52-0c2c-b886-bae2-c64bd8626452@ozlabs.ru>
Date:   Fri, 22 Jan 2021 14:43:44 +1100
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:85.0) Gecko/20100101
 Thunderbird/85.0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Precedence: bulk

Hi!

Syzkaller found this bug and it has a repro (below). I googled a similar 
bug in 2019 which was fixed so this seems new.

The repro takes about a half a minute to produce the message,  "grep 
lock-classes /proc/lockdep_stats" reports 8177 of 8192, before running 
the repro it is 702. It is a POWER8 box.

The offender is htab->lockdep_key. If I run repro at the slow rate, no 
problems appears, traces show lockdep_unregister_key() is called and the 
leak is quite slow.

Is this something known? Any hints how to debug this further? I'd give 
it a try since I have an easy reproducer. Thanks,


root@le-dbg:~# egrep "BD.*htab->lockdep_key" /proc/lockdep | wc -l
7449
root@le-dbg:~# egrep "BD.*htab->lockdep_key" /proc/lockdep | tail -n 3
(____ptrval____) FD:    1 BD:    1 ....: &htab->lockdep_key#9531
(____ptrval____) FD:    1 BD:    1 ....: &htab->lockdep_key#9532
(____ptrval____) FD:    1 BD:    1 ....: &htab->lockdep_key#9533


// autogenerated by syzkaller (https://github.com/google/syzkaller)

#define __unix__ 1
#define __gnu_linux__ 1
#define __linux__ 1

#define _GNU_SOURCE

#include <dirent.h>
#include <endian.h>
#include <errno.h>
#include <fcntl.h>
#include <signal.h>
#include <stdarg.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/prctl.h>
#include <sys/stat.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <time.h>
#include <unistd.h>

static unsigned long long procid;

static void sleep_ms(uint64_t ms)
{
	usleep(ms * 1000);
}

static uint64_t current_time_ms(void)
{
	struct timespec ts;
	if (clock_gettime(CLOCK_MONOTONIC, &ts))
	exit(1);
	return (uint64_t)ts.tv_sec * 1000 + (uint64_t)ts.tv_nsec / 1000000;
}

static bool write_file(const char* file, const char* what, ...)
{
	char buf[1024];
	va_list args;
	va_start(args, what);
	vsnprintf(buf, sizeof(buf), what, args);
	va_end(args);
	buf[sizeof(buf) - 1] = 0;
	int len = strlen(buf);
	int fd = open(file, O_WRONLY | O_CLOEXEC);
	if (fd == -1)
		return false;
	if (write(fd, buf, len) != len) {
		int err = errno;
		close(fd);
		errno = err;
		return false;
	}
	close(fd);
	return true;
}

static void kill_and_wait(int pid, int* status)
{
	kill(-pid, SIGKILL);
	kill(pid, SIGKILL);
	for (int i = 0; i < 100; i++) {
		if (waitpid(-1, status, WNOHANG | __WALL) == pid)
			return;
		usleep(1000);
	}
	DIR* dir = opendir("/sys/fs/fuse/connections");
	if (dir) {
		for (;;) {
			struct dirent* ent = readdir(dir);
			if (!ent)
				break;
			if (strcmp(ent->d_name, ".") == 0 || strcmp(ent->d_name, "..") == 0)
				continue;
			char abort[300];
			snprintf(abort, sizeof(abort), "/sys/fs/fuse/connections/%s/abort", 
ent->d_name);
			int fd = open(abort, O_WRONLY);
			if (fd == -1) {
				continue;
			}
			if (write(fd, abort, 1) < 0) {
			}
			close(fd);
		}
		closedir(dir);
	} else {
	}
	while (waitpid(-1, status, __WALL) != pid) {
	}
}

static void setup_test()
{
	prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
	setpgrp();
	write_file("/proc/self/oom_score_adj", "1000");
}

static void execute_one(void);

#define WAIT_FLAGS __WALL

static void loop(void)
{
	int iter = 0;
	for (;; iter++) {
		int pid = fork();
		if (pid < 0)
	exit(1);
		if (pid == 0) {
			setup_test();
			execute_one();
			exit(0);
		}
		int status = 0;
		uint64_t start = current_time_ms();
		for (;;) {
			if (waitpid(-1, &status, WNOHANG | WAIT_FLAGS) == pid)
				break;
			sleep_ms(1);
		if (current_time_ms() - start < 5000) {
			continue;
		}
			kill_and_wait(pid, &status);
			break;
		}
	}
}

#ifndef __NR_bpf
#define __NR_bpf 361
#endif
#ifndef __NR_mmap
#define __NR_mmap 90
#endif

uint64_t r[1] = {0xffffffffffffffff};

void execute_one(void)
{
		intptr_t res = 0;
*(uint32_t*)0x20000280 = 9;
*(uint32_t*)0x20000284 = 1;
*(uint32_t*)0x20000288 = 6;
*(uint32_t*)0x2000028c = 5;
*(uint32_t*)0x20000290 = 0;
*(uint32_t*)0x20000294 = -1;
*(uint32_t*)0x20000298 = 0;
*(uint8_t*)0x2000029c = 0;
*(uint8_t*)0x2000029d = 0;
*(uint8_t*)0x2000029e = 0;
*(uint8_t*)0x2000029f = 0;
*(uint8_t*)0x200002a0 = 0;
*(uint8_t*)0x200002a1 = 0;
*(uint8_t*)0x200002a2 = 0;
*(uint8_t*)0x200002a3 = 0;
*(uint8_t*)0x200002a4 = 0;
*(uint8_t*)0x200002a5 = 0;
*(uint8_t*)0x200002a6 = 0;
*(uint8_t*)0x200002a7 = 0;
*(uint8_t*)0x200002a8 = 0;
*(uint8_t*)0x200002a9 = 0;
*(uint8_t*)0x200002aa = 0;
*(uint8_t*)0x200002ab = 0;
*(uint32_t*)0x200002ac = 0;
*(uint32_t*)0x200002b0 = -1;
*(uint32_t*)0x200002b4 = 0;
*(uint32_t*)0x200002b8 = 0;
*(uint32_t*)0x200002bc = 0;
	res = syscall(__NR_bpf, 0ul, 0x20000280ul, 0x40ul);
	if (res != -1)
		r[0] = res;
*(uint64_t*)0x20000100 = 0;
*(uint64_t*)0x20000108 = 0;
*(uint64_t*)0x20000110 = 0x200002c0;
*(uint64_t*)0x20000118 = 0x20000000;
*(uint32_t*)0x20000120 = 0x1000;
*(uint32_t*)0x20000124 = r[0];
*(uint64_t*)0x20000128 = 0;
*(uint64_t*)0x20000130 = 0;
	syscall(__NR_bpf, 0x1aul, 0x20000100ul, 0x38ul);

}
int main(void)
{
		syscall(__NR_mmap, 0x1fff0000ul, 0x10000ul, 0ul, 0x32ul, -1, 0ul);
	syscall(__NR_mmap, 0x20000000ul, 0x1000000ul, 7ul, 0x32ul, -1, 0ul);
	syscall(__NR_mmap, 0x21000000ul, 0x10000ul, 0ul, 0x32ul, -1, 0ul);
	for (procid = 0; procid < 16; procid++) {
		if (fork() == 0) {
			loop();
		}
	}
	sleep(1000000);
	return 0;
}


-- 
Alexey