Reading a child process's /proc/pid/mem file from the parent - linux

In the program below, I am trying to cause the following to happen:
Process A assigns a value to a stack variable a.
Process A (parent) creates process B (child) with PID child_pid.
Process B calls function func1, passing a pointer to a.
Process B changes the value of variable a through the pointer.
Process B opens its /proc/self/mem file, seeks to the page containing a, and prints the new value of a.
Process A (at the same time) opens /proc/child_pid/mem, seeks to the right page, and prints the new value of a.
The problem is that, in step 6, the parent only sees the old value of a in /proc/child_pid/mem, while the child can indeed see the new value in its /proc/self/mem. Why is this the case? Is there any way that I can get the parent to to see the child's changes to its address space through the /proc filesystem?
#include <fcntl.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/wait.h>
#include <unistd.h>
#define PAGE_SIZE 0x1000
#define LOG_PAGE_SIZE 0xc
#define PAGE_ROUND_DOWN(v) ((v) & (~(PAGE_SIZE - 1)))
#define PAGE_ROUND_UP(v) (((v) + PAGE_SIZE - 1) & (~(PAGE_SIZE - 1)))
#define OFFSET_IN_PAGE(v) ((v) & (PAGE_SIZE - 1))
# if defined ARCH && ARCH == 32
#define BP "ebp"
#define SP "esp"
#else
#define BP "rbp"
#define SP "rsp"
#endif
typedef struct arg_t {
int a;
} arg_t;
void func1(void * data) {
arg_t * arg_ptr = (arg_t *)data;
printf("func1: old value: %d\n", arg_ptr->a);
arg_ptr->a = 53;
printf("func1: address: %p\n", &arg_ptr->a);
printf("func1: new value: %d\n", arg_ptr->a);
}
void expore_proc_mem(void (*fn)(void *), void * data) {
off_t frame_pointer, stack_start;
char buffer[PAGE_SIZE];
const char * path = "/proc/self/mem";
int child_pid, status;
int parent_to_child[2];
int child_to_parent[2];
arg_t * arg_ptr;
off_t child_offset;
asm volatile ("mov %%"BP", %0" : "=m" (frame_pointer));
stack_start = PAGE_ROUND_DOWN(frame_pointer);
printf("Stack_start: %lx\n",
(unsigned long)stack_start);
arg_ptr = (arg_t *)data;
child_offset =
OFFSET_IN_PAGE((off_t)&arg_ptr->a);
printf("Address of arg_ptr->a: %p\n",
&arg_ptr->a);
pipe(parent_to_child);
pipe(child_to_parent);
bool msg;
int child_mem_fd;
char child_path[0x20];
child_pid = fork();
if (child_pid == -1) {
perror("fork");
exit(EXIT_FAILURE);
}
if (!child_pid) {
close(child_to_parent[0]);
close(parent_to_child[1]);
printf("CHILD (pid %d, parent pid %d).\n",
getpid(), getppid());
fn(data);
msg = true;
write(child_to_parent[1], &msg, 1);
child_mem_fd = open("/proc/self/mem", O_RDONLY);
if (child_mem_fd == -1) {
perror("open (child)");
exit(EXIT_FAILURE);
}
printf("CHILD: child_mem_fd: %d\n", child_mem_fd);
if (lseek(child_mem_fd, stack_start, SEEK_SET) == (off_t)-1) {
perror("lseek");
exit(EXIT_FAILURE);
}
if (read(child_mem_fd, buffer, sizeof(buffer))
!= sizeof(buffer)) {
perror("read");
exit(EXIT_FAILURE);
}
printf("CHILD: new value %d\n",
*(int *)(buffer + child_offset));
read(parent_to_child[0], &msg, 1);
exit(EXIT_SUCCESS);
}
else {
printf("PARENT (pid %d, child pid %d)\n",
getpid(), child_pid);
printf("PARENT: child_offset: %lx\n",
child_offset);
read(child_to_parent[0], &msg, 1);
printf("PARENT: message from child: %d\n", msg);
snprintf(child_path, 0x20, "/proc/%d/mem", child_pid);
printf("PARENT: child_path: %s\n", child_path);
child_mem_fd = open(path, O_RDONLY);
if (child_mem_fd == -1) {
perror("open (child)");
exit(EXIT_FAILURE);
}
printf("PARENT: child_mem_fd: %d\n", child_mem_fd);
if (lseek(child_mem_fd, stack_start, SEEK_SET) == (off_t)-1) {
perror("lseek");
exit(EXIT_FAILURE);
}
if (read(child_mem_fd, buffer, sizeof(buffer))
!= sizeof(buffer)) {
perror("read");
exit(EXIT_FAILURE);
}
printf("PARENT: new value %d\n",
*(int *)(buffer + child_offset));
close(child_mem_fd);
printf("ENDING CHILD PROCESS.\n");
write(parent_to_child[1], &msg, 1);
if (waitpid(child_pid, &status, 0) == -1) {
perror("waitpid");
exit(EXIT_FAILURE);
}
}
}
int main(void) {
arg_t arg;
arg.a = 42;
printf("In main: address of arg.a: %p\n", &arg.a);
explore_proc_mem(&func1, &arg.a);
return EXIT_SUCCESS;
}
This program produces the output below. Notice that the value of a (boldfaced) differs between parent's and child's reading of the /proc/child_pid/mem file.
In main: address of arg.a: 0x7ffffe1964f0
Stack_start: 7ffffe196000
Address of arg_ptr->a: 0x7ffffe1964f0
PARENT (pid 20376, child pid 20377)
PARENT: child_offset: 4f0
CHILD (pid 20377, parent pid 20376).
func1: old value: 42
func1: address: 0x7ffffe1964f0
func1: new value: 53
PARENT: message from child: 1
CHILD: child_mem_fd: 4
PARENT: child_path: /proc/20377/mem
CHILD: new value 53
PARENT: child_mem_fd: 7
PARENT: new value 42
ENDING CHILD PROCESS.

There's one silly mistake in this code:
const char * path = "/proc/self/mem";
...
snprintf(child_path, 0x20, "/proc/%d/mem", child_pid);
printf("PARENT: child_path: %s\n", child_path);
child_mem_fd = open(path, O_RDONLY);
So you always end up reading parent's memory here. However after changing this, I get:
CHILD: child_mem_fd: 4
CHILD: new value 53
read (parent): No such process
And I don't know why it could happen - maybe /proc is too slow in refreshing the entries? (it's from perror("read") in the parent - had to add a comment to see which one fails) But that seems weird, since the seek worked - as well as open itself.
That question doesn't seem to be new either: http://lkml.indiana.edu/hypermail/linux/kernel/0007.1/0939.html (ESRCH is "no such process")
Actually a better link is: http://www.webservertalk.com/archive242-2004-7-295131.html - there was an issue with marking processes pthread-attach-safe. You can find there Alan Cox sending someone to Solar Designer... for me that spells "here be dragons" and that it's not solvable if you don't hack kernels in your sleep :(
Maybe it's enough for you to check what is gdb doing in that case and replicating it? (Probably it just goes via ptrace(PTRACE_PEEKDATA,...))

The solution is to use ptrace to synchronize parent with child. Even though I am already communicating between parent and child (and the man page for ptrace says that it causes the two processes to behave as if they were parent and child), and even though the child is blocking on the read call, the child has apparently not "stopped" enough for Linux to allow the parent to read the child's /proc/child_pid/mem file. But if the parent first calls ptrace (after it receives the message over the pipe) with PTRACE_ATTACH, then it can open the file--and get the correct contents! Then the parent calls ptrace again, with PTRACE_DETACH, before sending the message back to the child to terminate.

Related

Is this a bug in linux kernel concerning write to /proc/self/loginuid?

There is a possibility that i found a bug in linux kernel. Let's consider application that write to /proc/self/loginuid from main thread and one auxiliary thread. The code is below:
#include <stdio.h>
#include <pthread.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
void write_loginuid(char *str)
{
int fd;
printf("%s\n", str);
fd = open("/proc/self/loginuid", O_RDWR);
if (fd < 0) {
perror(str);
return;
}
if (write(fd, "0", 2) != 2) {
printf("write\n");
perror(str);
}
close(fd);
}
void *thread_function(void *arg)
{
fprintf(stderr, "Hello from thread! my pid = %u, tid = %u, parent pid = %u\n", getpid(), syscall(SYS_gettid), getppid());
write_loginuid("thread");
return NULL;
}
int main()
{
pthread_t thread;
pthread_create(&thread, NULL, thread_function, NULL);
write_loginuid("main process");
fprintf(stderr, "test my pid = %u, tid = %u, parent pid = %u\n", getpid(), syscall(SYS_gettid), getppid());
pthread_join(thread, NULL);
return 0;
}
After executing this application we get:
main process
test my pid = 3487, tid = 3487, parent pid = 3283
Hello from thread! my pid = 3487, tid = 3488, parent pid = 3283
thread
write
thread: Operation not permitted
That tells us the thread write failed by -EPERM.
Looking at the kernel file fs/proc/base.c and function proc_loginuid_write() we see at the beginning check:
static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
size_t count, loff_t *ppos)
{
struct inode * inode = file_inode(file);
uid_t loginuid;
kuid_t kloginuid;
int rv;
/* this is the probably buggy check */
rcu_read_lock();
if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) {
rcu_read_unlock();
return -EPERM;
}
rcu_read_unlock();
So, looking at the code above we see that only for exact PID (checked by me with printks) we pass through.Thread doesn't satisfy the condition, because compared pids differs.
So my question is: is this a bug ? Why to not allow thread's of particular process to change the loginuid? I encountered this in login application that spawned another thread for PAM login.
Whether this is bug or not i written a fix that extends writing permission to this file by threads:
rcu_read_lock();
/*
* I changed the condition that it checks now the tgid as returned in sys_getpid()
* rather than task_struct pointers
*/
if (task_tgid_vnr(current) != task_tgid_vnr(pid_task(proc_pid(inode), PIDTYPE_PID))) {
rcu_read_unlock();
return -EPERM;
}
rcu_read_unlock();
What do you think about it? Does it affects security?

Can't write to pseudo terminal master

I'm able to open a new pseudo terminal, and start a shell on the slave, but writing to the master doesn't seem to do anything, and trying to read after the shell has started ends in failure (-1). What am i doing wrong:
#include <stdlib.h>
#include <stdio.h>
#include <fcntl.h>
#include <unistd.h>
#include <signal.h>
#include <sys/ioctl.h>
int posix_openpt(int flags);
int grantpt(int fd);
int unlockpt(int fd);
char *ptsname(int fd);
static void execsh(void);
int main(int argc, char *argv[]) {
printf("Hiya\n");
// Open the Master Clone Device /dev/ptmx, return the fd
int master_fd = posix_openpt(O_RDWR);
printf("PTMaster = %d\n", master_fd);
// Change the permissions and ownership of the slave device
int grant_success = grantpt(master_fd);
printf("Grant success = %d\n", grant_success);
// Unlock the slave pseudoterminal device corresponding to master_fd
int unlock_success = unlockpt(master_fd);
printf("Unlock success = %d\n", unlock_success);
// Grab the name of the slave device
char *slave_name = ptsname(master_fd);
printf("Slave name = %s\n", slave_name);
// Open the slave pseudoterminal device
int slave_fd = open(slave_name, O_WRONLY);
printf("Slave fd = %d\n", slave_fd);
// Exec shell
pid_t pid;
switch (pid = fork()) {
case -1:
printf("Failed to fork\n");
break;
case 0:
// Child
setsid(); /* create a new process group */
dup2(slave_fd, STDIN_FILENO);
dup2(slave_fd, STDOUT_FILENO);
dup2(slave_fd, STDERR_FILENO);
ioctl(slave_fd, TIOCSCTTY, NULL); /* make this the controlling terminal for this process */
close(slave_fd);
close(master_fd);
// Start Shell
execsh();
break;
default:
// Parent
close(slave_fd);
}
// Read from master
sleep(1);
char buffer[200];
ssize_t read_bytes = read(master_fd, buffer, 200);
printf("read %ld from master\n", read_bytes);
printf("buffer = %s\n", buffer);
// ls
ssize_t written = write(master_fd, "ls\n", 3);
printf("wrote %ld to master\n", written);
// Read from master
read_bytes = read(master_fd, buffer, 200);
printf("read %ld from master\n", read_bytes);
printf("buffer = %s\n", buffer);
close(master_fd);
kill(pid, SIGKILL); // Kill the child, biblical
return 0;
}
void
execsh(void) {
char **args;
char *envshell = getenv("SHELL");
unsetenv("COLUMNS");
unsetenv("LINES");
unsetenv("TERMCAP");
signal(SIGCHLD, SIG_DFL);
signal(SIGHUP, SIG_DFL);
signal(SIGINT, SIG_DFL);
signal(SIGQUIT, SIG_DFL);
signal(SIGTERM, SIG_DFL);
signal(SIGALRM, SIG_DFL);
args = (char *[]){envshell, "-i", NULL};
printf("\nforked child starting terminal\n");
execvp(args[0], args);
printf("\nExited the shell\n");
exit(EXIT_FAILURE);
}
output looks like this:
Hiya
PTMaster = 3
Grant success = 0
Unlock success = 0
Slave name = /dev/pts/19
Slave fd = 4
read 130 from master
buffer =
forked child starting terminal
eric#vbox:~/Desktop/terminal$ exit
wrote 3 to master
read -1 from master
buffer =
forked child starting terminal
eric#vbox:~/Desktop/terminal$ exit
I'm not sure why it has the word exit there either. Thanks in advance for any pointers you might have!
ninjalj was right. I had the slave opened for writing only.
Thank you very much!

Does the CHILD_SUBREAPER bit persist across fork()?

When a process sets the child subreaper bit with prctl(PR_SET_CHILD_SUBREAPER, 1) (documented here), does it need to use prctl(PR_SET_CHILD_SUBREAPER, 0) to clear it after a fork?
No, the child subreaper bit does not persist across forks.
The relevant Linux kernel code is in copy_signal() in kernel/fork.c: the signal struct is initialized to all zeros, and the is_child_subreaper bit is never set.
However, has_child_subreaper is set:
sig->has_child_subreaper = current->signal->has_child_subreaper ||
current->signal->is_child_subreaper;
This test program demonstrates the behavior:
#include <stdio.h>
#include <stdlib.h>
#include <sys/prctl.h>
int main(int argc, char** argv) {
int pid;
int i;
prctl(PR_SET_CHILD_SUBREAPER, 1);
prctl(PR_GET_CHILD_SUBREAPER, &i);
printf("Before fork: %d\n", i);
pid = fork();
if (pid < 0) {
return 1;
} else if (pid == 0) {
prctl(PR_GET_CHILD_SUBREAPER, &i);
printf("In child: %d\n", i);
return 0;
}
return 0;
}
Outputs:
Before fork: 1
In child: 0

How can i make sure that only a single instance of the process on Linux? [duplicate]

What would be your suggestion in order to create a single instance application, so that only one process is allowed to run at a time? File lock, mutex or what?
A good way is:
#include <sys/file.h>
#include <errno.h>
int pid_file = open("/var/run/whatever.pid", O_CREAT | O_RDWR, 0666);
int rc = flock(pid_file, LOCK_EX | LOCK_NB);
if(rc) {
if(EWOULDBLOCK == errno)
; // another instance is running
}
else {
// this is the first instance
}
Note that locking allows you to ignore stale pid files (i.e. you don't have to delete them). When the application terminates for any reason the OS releases the file lock for you.
Pid files are not terribly useful because they can be stale (the file exists but the process does not). Hence, the application executable itself can be locked instead of creating and locking a pid file.
A more advanced method is to create and bind a unix domain socket using a predefined socket name. Bind succeeds for the first instance of your application. Again, the OS unbinds the socket when the application terminates for any reason. When bind() fails another instance of the application can connect() and use this socket to pass its command line arguments to the first instance.
Here is a solution in C++. It uses the socket recommendation of Maxim. I like this solution better than the file based locking solution, because the file based one fails if the process crashes and does not delete the lock file. Another user will not be able to delete the file and lock it. The sockets are automatically deleted when the process exits.
Usage:
int main()
{
SingletonProcess singleton(5555); // pick a port number to use that is specific to this app
if (!singleton())
{
cerr << "process running already. See " << singleton.GetLockFileName() << endl;
return 1;
}
... rest of the app
}
Code:
#include <netinet/in.h>
class SingletonProcess
{
public:
SingletonProcess(uint16_t port0)
: socket_fd(-1)
, rc(1)
, port(port0)
{
}
~SingletonProcess()
{
if (socket_fd != -1)
{
close(socket_fd);
}
}
bool operator()()
{
if (socket_fd == -1 || rc)
{
socket_fd = -1;
rc = 1;
if ((socket_fd = socket(AF_INET, SOCK_DGRAM, 0)) < 0)
{
throw std::runtime_error(std::string("Could not create socket: ") + strerror(errno));
}
else
{
struct sockaddr_in name;
name.sin_family = AF_INET;
name.sin_port = htons (port);
name.sin_addr.s_addr = htonl (INADDR_ANY);
rc = bind (socket_fd, (struct sockaddr *) &name, sizeof (name));
}
}
return (socket_fd != -1 && rc == 0);
}
std::string GetLockFileName()
{
return "port " + std::to_string(port);
}
private:
int socket_fd = -1;
int rc;
uint16_t port;
};
For windows, a named kernel object (e.g. CreateEvent, CreateMutex). For unix, a pid-file - create a file and write your process ID to it.
You can create an "anonymous namespace" AF_UNIX socket. This is completely Linux-specific, but has the advantage that no filesystem actually has to exist.
Read the man page for unix(7) for more info.
Avoid file-based locking
It is always good to avoid a file based locking mechanism to implement the singleton instance of an application. The user can always rename the lock file to a different name and run the application again as follows:
mv lockfile.pid lockfile1.pid
Where lockfile.pid is the lock file based on which is checked for existence before running the application.
So, it is always preferable to use a locking scheme on object directly visible to only the kernel. So, anything which has to do with a file system is not reliable.
So the best option would be to bind to a inet socket. Note that unix domain sockets reside in the filesystem and are not reliable.
Alternatively, you can also do it using DBUS.
It's seems to not be mentioned - it is possible to create a mutex in shared memory but it needs to be marked as shared by attributes (not tested):
pthread_mutexattr_t attr;
pthread_mutexattr_init(&attr);
pthread_mutexattr_setpshared(&attr, PTHREAD_PROCESS_SHARED);
pthread_mutex_t *mutex = shmat(SHARED_MEMORY_ID, NULL, 0);
pthread_mutex_init(mutex, &attr);
There is also shared memory semaphores (but I failed to find out how to lock one):
int sem_id = semget(SHARED_MEMORY_KEY, 1, 0);
No one has mentioned it, but sem_open() creates a real named semaphore under modern POSIX-compliant OSes. If you give a semaphore an initial value of 1, it becomes a mutex (as long as it is strictly released only if a lock was successfully obtained).
With several sem_open()-based objects, you can create all of the common equivalent Windows named objects - named mutexes, named semaphores, and named events. Named events with "manual" set to true is a bit more difficult to emulate (it requires four semaphore objects to properly emulate CreateEvent(), SetEvent(), and ResetEvent()). Anyway, I digress.
Alternatively, there is named shared memory. You can initialize a pthread mutex with the "shared process" attribute in named shared memory and then all processes can safely access that mutex object after opening a handle to the shared memory with shm_open()/mmap(). sem_open() is easier if it is available for your platform (if it isn't, it should be for sanity's sake).
Regardless of the method you use, to test for a single instance of your application, use the trylock() variant of the wait function (e.g. sem_trywait()). If the process is the only one running, it will successfully lock the mutex. If it isn't, it will fail immediately.
Don't forget to unlock and close the mutex on application exit.
It will depend on which problem you want to avoid by forcing your application to have only one instance and the scope on which you consider instances.
For a daemon — the usual way is to have a /var/run/app.pid file.
For user application, I've had more problems with applications which prevented me to run them twice than with being able to run twice an application which shouldn't have been run so. So the answer on "why and on which scope" is very important and will probably bring answer specific on the why and the intended scope.
Here is a solution based on sem_open
/*
*compile with :
*gcc single.c -o single -pthread
*/
/*
* run multiple instance on 'single', and check the behavior
*/
#include <stdio.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <semaphore.h>
#include <unistd.h>
#include <errno.h>
#define SEM_NAME "/mysem_911"
int main()
{
sem_t *sem;
int rc;
sem = sem_open(SEM_NAME, O_CREAT, S_IRWXU, 1);
if(sem==SEM_FAILED){
printf("sem_open: failed errno:%d\n", errno);
}
rc=sem_trywait(sem);
if(rc == 0){
printf("Obtained lock !!!\n");
sleep(10);
//sem_post(sem);
sem_unlink(SEM_NAME);
}else{
printf("Lock not obtained\n");
}
}
One of the comments on a different answer says "I found sem_open() rather lacking". I am not sure about the specifics of what's lacking
Based on the hints in maxim's answer here is my POSIX solution of a dual-role daemon (i.e. a single application that can act as daemon and as a client communicating with that daemon). This scheme has the advantage of providing an elegant solution of the problem when the instance started first should be the daemon and all following executions should just load off the work at that daemon. It is a complete example but lacks a lot of stuff a real daemon should do (e.g. using syslog for logging and fork to put itself into background correctly, dropping privileges etc.), but it is already quite long and is fully working as is. I have only tested this on Linux so far but IIRC it should be all POSIX-compatible.
In the example the clients can send integers passed to them as first command line argument and parsed by atoi via the socket to the daemon which prints it to stdout. With this kind of sockets it is also possible to transfer arrays, structs and even file descriptors (see man 7 unix).
#include <stdio.h>
#include <stddef.h>
#include <stdbool.h>
#include <stdlib.h>
#include <unistd.h>
#include <errno.h>
#include <signal.h>
#include <sys/socket.h>
#include <sys/un.h>
#define SOCKET_NAME "/tmp/exampled"
static int socket_fd = -1;
static bool isdaemon = false;
static bool run = true;
/* returns
* -1 on errors
* 0 on successful server bindings
* 1 on successful client connects
*/
int singleton_connect(const char *name) {
int len, tmpd;
struct sockaddr_un addr = {0};
if ((tmpd = socket(AF_UNIX, SOCK_DGRAM, 0)) < 0) {
printf("Could not create socket: '%s'.\n", strerror(errno));
return -1;
}
/* fill in socket address structure */
addr.sun_family = AF_UNIX;
strcpy(addr.sun_path, name);
len = offsetof(struct sockaddr_un, sun_path) + strlen(name);
int ret;
unsigned int retries = 1;
do {
/* bind the name to the descriptor */
ret = bind(tmpd, (struct sockaddr *)&addr, len);
/* if this succeeds there was no daemon before */
if (ret == 0) {
socket_fd = tmpd;
isdaemon = true;
return 0;
} else {
if (errno == EADDRINUSE) {
ret = connect(tmpd, (struct sockaddr *) &addr, sizeof(struct sockaddr_un));
if (ret != 0) {
if (errno == ECONNREFUSED) {
printf("Could not connect to socket - assuming daemon died.\n");
unlink(name);
continue;
}
printf("Could not connect to socket: '%s'.\n", strerror(errno));
continue;
}
printf("Daemon is already running.\n");
socket_fd = tmpd;
return 1;
}
printf("Could not bind to socket: '%s'.\n", strerror(errno));
continue;
}
} while (retries-- > 0);
printf("Could neither connect to an existing daemon nor become one.\n");
close(tmpd);
return -1;
}
static void cleanup(void) {
if (socket_fd >= 0) {
if (isdaemon) {
if (unlink(SOCKET_NAME) < 0)
printf("Could not remove FIFO.\n");
} else
close(socket_fd);
}
}
static void handler(int sig) {
run = false;
}
int main(int argc, char **argv) {
switch (singleton_connect(SOCKET_NAME)) {
case 0: { /* Daemon */
struct sigaction sa;
sa.sa_handler = &handler;
sigemptyset(&sa.sa_mask);
if (sigaction(SIGINT, &sa, NULL) != 0 || sigaction(SIGQUIT, &sa, NULL) != 0 || sigaction(SIGTERM, &sa, NULL) != 0) {
printf("Could not set up signal handlers!\n");
cleanup();
return EXIT_FAILURE;
}
struct msghdr msg = {0};
struct iovec iovec;
int client_arg;
iovec.iov_base = &client_arg;
iovec.iov_len = sizeof(client_arg);
msg.msg_iov = &iovec;
msg.msg_iovlen = 1;
while (run) {
int ret = recvmsg(socket_fd, &msg, MSG_DONTWAIT);
if (ret != sizeof(client_arg)) {
if (errno != EAGAIN && errno != EWOULDBLOCK) {
printf("Error while accessing socket: %s\n", strerror(errno));
exit(1);
}
printf("No further client_args in socket.\n");
} else {
printf("received client_arg=%d\n", client_arg);
}
/* do daemon stuff */
sleep(1);
}
printf("Dropped out of daemon loop. Shutting down.\n");
cleanup();
return EXIT_FAILURE;
}
case 1: { /* Client */
if (argc < 2) {
printf("Usage: %s <int>\n", argv[0]);
return EXIT_FAILURE;
}
struct iovec iovec;
struct msghdr msg = {0};
int client_arg = atoi(argv[1]);
iovec.iov_base = &client_arg;
iovec.iov_len = sizeof(client_arg);
msg.msg_iov = &iovec;
msg.msg_iovlen = 1;
int ret = sendmsg(socket_fd, &msg, 0);
if (ret != sizeof(client_arg)) {
if (ret < 0)
printf("Could not send device address to daemon: '%s'!\n", strerror(errno));
else
printf("Could not send device address to daemon completely!\n");
cleanup();
return EXIT_FAILURE;
}
printf("Sent client_arg (%d) to daemon.\n", client_arg);
break;
}
default:
cleanup();
return EXIT_FAILURE;
}
cleanup();
return EXIT_SUCCESS;
}
All credits go to Mark Lakata. I merely did some very minor touch up only.
main.cpp
#include "singleton.hpp"
#include <iostream>
using namespace std;
int main()
{
SingletonProcess singleton(5555); // pick a port number to use that is specific to this app
if (!singleton())
{
cerr << "process running already. See " << singleton.GetLockFileName() << endl;
return 1;
}
// ... rest of the app
}
singleton.hpp
#include <netinet/in.h>
#include <unistd.h>
#include <cerrno>
#include <string>
#include <cstring>
#include <stdexcept>
using namespace std;
class SingletonProcess
{
public:
SingletonProcess(uint16_t port0)
: socket_fd(-1)
, rc(1)
, port(port0)
{
}
~SingletonProcess()
{
if (socket_fd != -1)
{
close(socket_fd);
}
}
bool operator()()
{
if (socket_fd == -1 || rc)
{
socket_fd = -1;
rc = 1;
if ((socket_fd = socket(AF_INET, SOCK_DGRAM, 0)) < 0)
{
throw std::runtime_error(std::string("Could not create socket: ") + strerror(errno));
}
else
{
struct sockaddr_in name;
name.sin_family = AF_INET;
name.sin_port = htons (port);
name.sin_addr.s_addr = htonl (INADDR_ANY);
rc = bind (socket_fd, (struct sockaddr *) &name, sizeof (name));
}
}
return (socket_fd != -1 && rc == 0);
}
std::string GetLockFileName()
{
return "port " + std::to_string(port);
}
private:
int socket_fd = -1;
int rc;
uint16_t port;
};
#include <windows.h>
int main(int argc, char *argv[])
{
// ensure only one running instance
HANDLE hMutexH`enter code here`andle = CreateMutex(NULL, TRUE, L"my.mutex.name");
if (GetLastError() == ERROR_ALREADY_EXISTS)
{
return 0;
}
// rest of the program
ReleaseMutex(hMutexHandle);
CloseHandle(hMutexHandle);
return 0;
}
FROM: HERE
On Windows you could also create a shared data segment and use an interlocked function to test for the first occurence, e.g.
#include <Windows.h>
#include <stdio.h>
#include <conio.h>
#pragma data_seg("Shared")
volatile LONG lock = 0;
#pragma data_seg()
#pragma comment(linker, "/SECTION:Shared,RWS")
void main()
{
if (InterlockedExchange(&lock, 1) == 0)
printf("first\n");
else
printf("other\n");
getch();
}
I have just written one, and tested.
#define PID_FILE "/tmp/pidfile"
static void create_pidfile(void) {
int fd = open(PID_FILE, O_RDWR | O_CREAT | O_EXCL, 0);
close(fd);
}
int main(void) {
int fd = open(PID_FILE, O_RDONLY);
if (fd > 0) {
close(fd);
return 0;
}
// make sure only one instance is running
create_pidfile();
}
Just run this code on a seperate thread:
void lock() {
while(1) {
ofstream closer("myapplock.locker", ios::trunc);
closer << "locked";
closer.close();
}
}
Run this as your main code:
int main() {
ifstream reader("myapplock.locker");
string s;
reader >> s;
if (s != "locked") {
//your code
}
return 0;
}

Debugging segmentation fault in a multi-threaded (using clone) program

I wrote a code to create some threads and whenever one of the threads finish a new thread is created to replace it. As I was not able to create very large number of threads (>450) using pthreads, I used clone system call instead. (Please note that I am aware of the implication of having such a huge number of threads, but this program is meant to only stress the system).
As clone() requires the stack space for the child thread to be specified as parameter, I malloc the required chunk of stack space for each thread and free it up when the thread finishes. When a thread finishes I send a signal to the parent to notify it of the same.
The code is given below:
#include <sched.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <signal.h>
#include <unistd.h>
#include <errno.h>
#define NUM_THREADS 5
unsigned long long total_count=0;
int num_threads = NUM_THREADS;
static int thread_pids[NUM_THREADS];
static void *thread_stacks[NUM_THREADS];
int ppid;
int worker() {
int i;
union sigval s={0};
for(i=0;i!=99999999;i++);
if(sigqueue(ppid, SIGUSR1, s)!=0)
fprintf(stderr, "ERROR sigqueue");
fprintf(stderr, "Child [%d] done\n", getpid());
return 0;
}
void sigint_handler(int signal) {
char fname[35]="";
FILE *fp;
int ch;
if(signal == SIGINT) {
fprintf(stderr, "Caught SIGINT\n");
sprintf(fname, "/proc/%d/status", getpid());
fp = fopen(fname,"r");
while((ch=fgetc(fp))!=EOF)
fprintf(stderr, "%c", (char)ch);
fclose(fp);
fprintf(stderr, "No. of threads created so far = %llu\n", total_count);
exit(0);
} else
fprintf(stderr, "Unhandled signal (%d) received\n", signal);
}
int main(int argc, char *argv[]) {
int rc, i; long t;
void *chld_stack, *chld_stack2;
siginfo_t siginfo;
sigset_t sigset, oldsigset;
if(argc>1) {
num_threads = atoi(argv[1]);
if(num_threads<1) {
fprintf(stderr, "Number of threads must be >0\n");
return -1;
}
}
signal(SIGINT, sigint_handler);
/* Block SIGUSR1 */
sigemptyset(&sigset);
sigaddset(&sigset, SIGUSR1);
if(sigprocmask(SIG_BLOCK, &sigset, &oldsigset)==-1)
fprintf(stderr, "ERROR: cannot block SIGUSR1 \"%s\"\n", strerror(errno));
printf("Number of threads = %d\n", num_threads);
ppid = getpid();
for(t=0,i=0;t<num_threads;t++,i++) {
chld_stack = (void *) malloc(148*512);
chld_stack2 = ((char *)chld_stack + 148*512 - 1);
if(chld_stack == NULL) {
fprintf(stderr, "ERROR[%ld]: malloc for stack-space failed\n", t);
break;
}
rc = clone(worker, chld_stack2, CLONE_VM|CLONE_FS|CLONE_FILES, NULL);
if(rc == -1) {
fprintf(stderr, "ERROR[%ld]: return code from pthread_create() is %d\n", t, errno);
break;
}
thread_pids[i]=rc;
thread_stacks[i]=chld_stack;
fprintf(stderr, " [index:%d] = [pid:%d] ; [stack:0x%p]\n", i, thread_pids[i], thread_stacks[i]);
total_count++;
}
sigemptyset(&sigset);
sigaddset(&sigset, SIGUSR1);
while(1) {
fprintf(stderr, "Waiting for signal from childs\n");
if(sigwaitinfo(&sigset, &siginfo) == -1)
fprintf(stderr, "- ERROR returned by sigwaitinfo : \"%s\"\n", strerror(errno));
fprintf(stderr, "Got some signal from pid:%d\n", siginfo.si_pid);
/* A child finished, free the stack area allocated for it */
for(i=0;i<NUM_THREADS;i++) {
fprintf(stderr, " [index:%d] = [pid:%d] ; [stack:%p]\n", i, thread_pids[i], thread_stacks[i]);
if(thread_pids[i]==siginfo.si_pid) {
free(thread_stacks[i]);
thread_stacks[i]=NULL;
break;
}
}
fprintf(stderr, "Search for child ended with i=%d\n",i);
if(i==NUM_THREADS)
continue;
/* Create a new thread in its place */
chld_stack = (void *) malloc(148*512);
chld_stack2 = ((char *)chld_stack + 148*512 - 1);
if(chld_stack == NULL) {
fprintf(stderr, "ERROR[%ld]: malloc for stack-space failed\n", t);
break;
}
rc = clone(worker, chld_stack2, CLONE_VM|CLONE_FS|CLONE_FILES, NULL);
if(rc == -1) {
fprintf(stderr, "ERROR[%ld]: return code from clone() is %d\n", t, errno);
break;
}
thread_pids[i]=rc;
thread_stacks[i]=chld_stack;
total_count++;
}
fprintf(stderr, "Broke out of infinite loop. [total_count=%llu] [i=%d]\n",total_count, i);
return 0;
}
I have used couple of arrays to keep track of the child processes' pid and the stack area base address (for freeing it).
When I run this program it terminates after sometime. Running with gdb tells me that one of the thread gets a SIGSEGV (segmentation fault). But it doesn't gives me any location, the output is similar to the following:
Program received signal SIGSEGV, Segmentation fault.
[Switching to LWP 15864]
0x00000000 in ?? ()
I tried running it under valgrind with the following commandline:
valgrind --tool=memcheck --leak-check=yes --show-reachable=yes -v --num-callers=20 --track-fds=yes ./a.out
But it keeps running without any issues under valgrind.
I am puzzled as to how to debug this program. I felt that this might be some stack overflow or something but increasing the stack size (upto 74KB) didn't solved the problem.
My only query is why and where is the segmentation fault or how to debug this program.
Found the actual issue.
When the worker thread signals the parent process using sigqueue(), the parent sometimes gets the control immediately and frees up the stack before the child executes the return statement. When the same child thread uses return statement, it causes segmentation fault as the stack got corrupted.
To solve this I replaced
exit(0)
instead of
return 0;
I think i found the answer
Step 1
Replace this:
static int thread_pids[NUM_THREADS];
static void *thread_stacks[NUM_THREADS];
By this:
static int *thread_pids;
static void **thread_stacks;
Step 2
Add this in the main function (after checking arguments):
thread_pids = malloc(sizeof(int) * num_threads);
thread_stacks = malloc(sizeof(void *) * num_threads);
Step 3
Replace this:
chld_stack2 = ((char *)chld_stack + 148*512 - 1);
By this:
chld_stack2 = ((char *)chld_stack + 148*512);
In both places you use it.
I dont know if its really your problem, but after testing it i didnt get any segmentation fault. Btw i did only get segmentation faults when using more than 5 threads.
Hope i helped!
edit: tested with 1000 threads and runs perfectly
edit2: Explanation why the static allocation of thread_pids and thread_stacks causes an error.
The best way to do this is with an example.
Assume num_threads = 10;
The problem occurs in the following code:
for(t=0,i=0;t<num_threads;t++,i++) {
...
thread_pids[i]=rc;
thread_stacks[i]=chld_stack;
...
}
Here you try to access memory which does not belong to you (0 <= i <= 9, but both arrays have a size of 5). That can cause either segmentation fault or data corruption. Data corruption may happen if both arrays are allocated one after the other, resulting in writing to the other array. Segmentation can happen if you write in memory you dont have allocated (statically or dynamically).
You may be lucky and have no errors at all, but the code is surely not safe.
About the non-aligned pointer: I think i dont have to explain more than in my comment.

Resources