Assume the code below demonstrating a binary semaphore example.
In this example, we have a pthread that reads the source.txt and attempts to copy the content to destination.txt while locking it using a binary semaphore.
What happens in the comment section below without the semaphore?
#include <cstdlib>
#include <memory>
#include <filesystem>
#define _TIMESPEC_DEFINED
#include <pthread.h>
#include <semaphore.h>
#include <thread>
#include <valarray>
pthread_t StartFileAccessThread();
void *CopyFile(void *parameters);
int main(int argc, char* argv[])
{
pthread_t thread = StartFileAccessThread();
void *returnValue;
pthread_join(thread, &returnValue);
getchar();
return EXIT_SUCCESS;
}
pthread_t StartFileAccessThread()
{
std::string sourcePath("source.txt");
std::string destinationPath("dest.txt");
sem_t semaphore;
sem_init(&semaphore, 0, 0);
pthread_t thread;
void *parameters[3];
parameters[0] = &semaphore;
parameters[1] = &sourcePath;
parameters[2] = &destinationPath;
pthread_create(&thread, nullptr, &CopyFile, parameters);
// What happens without the binary semaphore?
sem_wait(&semaphore);
sem_destroy(&semaphore);
printf("Freeing ressources.\n");
return thread;
}
void *CopyFile(void *rawParameter)
{
void **parameters = static_cast<void **>(rawParameter);
sem_t *semaphore = static_cast<sem_t *>(parameters[0]);
std::string sourcePath(*static_cast<std::string *>(parameters[1]));
std::string destinationPath(*static_cast<std::string *>(parameters[2]));
sem_post(semaphore);
std::this_thread::sleep_for(std::chrono::seconds(2));
copy_file(sourcePath, destinationPath, std::experimental::filesystem::copy_options::overwrite_existing);
printf("File copied \n");
return nullptr;
}
What happens in the comment section below without the semaphore?
Without the semaphore, function startFileAccessThread() may return before the new thread finishes (or starts) copying its parameters from the argument object. That object is local to startFileAccessThread(), so its lifetime ends when that function returns. Undefined behavior results if the copy thread's accesses to it do not happen before that.
In the book Operating System Concepts, it designs a kernel module, the module seems to create an additional entry named hello in the /proc file system in Linux, the module code is shown below, then it uses cat /proc/hello command, it says "Each time the /proc/hello file is read, the proc_read() function is called repeatedly until it returns 0", I can't understand why proc_read() is called repeatedly, also I don't know who is the caller of the function proc_read().
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <asm/uaccess.h>
#define BUFFER_SIZE 128
#define PROC_NAME "hello"
ssize_t proc_read(struct file *file, char _user *usr_buf, size_t count, loff_t *pos);
static struct file_operations proc_ops = {
.owner = THIS MODULE,
.read = proc_read,
};
/* This function is called when the module is loaded. */
int proc_init(void)
{
/* creates the /proc/hello entry */
proc_create(PROC_NAME, 0666, NULL, &proc_ops);
return 0;
}
/* This function is called when the module is removed. */
void proc_exit(void)
{
/* removes the /proc/hello entry */
remove_proc_entry(PROC_NAME, NULL);
}
I'm debugging a select loop that normally works OK but dies with segmentation fault under heavy load. I've figured out that the program is sometimes invoking FD_ISSET() for a (correct) descriptor that was not added to the select set. Like in a following snippet:
#include <sys/select.h>
#include <sys/time.h>
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
void die(const char* msg)
{
fprintf(stderr, "fatal %s", msg);
exit(1);
}
int main(void)
{
FILE* file = fopen("/tmp/test", "r");
if (file == NULL)
die("fopen");
int file_fd = fileno(file);
fd_set read_fds;
int max_fd = 0;
FD_ZERO(&read_fds);
// Only stdin is added to read_fds.
FD_SET(0, &read_fds);
if (select(max_fd + 1, &read_fds, NULL, NULL, NULL) < 0)
die("select");
if (FD_ISSET(0, &read_fds))
printf("Can read from 0");
// !!! Here FD_ISSET is called with a valid descriptor that was
// not added to read_fds.
if (FD_ISSET(file_fd, &read_fds))
printf("Can read from file_fd");
return 0;
}
It is obvious that the check marked with !!! should never return true, but is it possible that it can be the cause of the SEGFAULT? When I run this snippet under valgrind, no errors are reported, but when I run my load test under valgrind I'm ocasionnaly seing errors like:
==25513== Syscall param select(writefds) points to uninitialised byte(s)
==25513== at 0x435DD2D: ___newselect_nocancel (syscall-template.S:82)
FD_ISSET() tests to see if a file descriptor is a part of the set read_fds. This means that FD_ISSET should not cause the segmentation fault.
Try checking for errno value set prior to calling the FD_ISSET. The select should be causing the segfault.
Also check that the file_fd value isn't greater than FD_MAX.
i want to catch information from user defined function using ptrace() calls.
but function address is not stable(because ASLR).
how can i get another program's function information like gdb programmatically?
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/user.h>
#include <sys/wait.h>
#include <sys/ptrace.h>
#include <dlfcn.h>
#include <errno.h>
void error(char *msg)
{
perror(msg);
exit(-1);
}
int main(int argc, char **argv)
{
long ret = 0;
void *handle;
pid_t pid = 0;
struct user_regs_struct regs;
int *hackme_addr = 0;
pid = atoi(argv[1]);
ret = ptrace(PTRACE_ATTACH, pid, NULL, NULL);
if(ret<0)
{
error("ptrace() error");
}
ret = waitpid(pid, NULL, WUNTRACED);
if(ret<0)
{
error("waitpid ()");
}
ret = ptrace(PTRACE_GETREGS, pid, NULL, ®s);
if(ret<0)
{
error("GETREGS error");
}
printf("EIP : 0x%x\n", (int)regs.eip);
ptrace(PTRACE_DETACH, pid, NULL, NULL);
return 0;
}
ptrace is a bit ugly, but it can be useful.
Here's a ptrace example program; it's used to make I/O-related system calls pause.
http://stromberg.dnsalias.org/~strombrg/slowdown/
You could of course also study gdb, but ISTR it's pretty huge.
You might also check out strace and ltrace, perhaps especially ltrace since it lists symbols.
HTH
You probably want to call a function that resides in a specific executable (probably, a shared object). So, first, you will have to find the base address this executable is mapped on using
/proc/pid/maps
After that, you need to find the local offset of the function you are interested in, and you can do this in two ways:
Understand the ELF file format (Linux native executable format), and searching the desired function using the mapped file (This requires some specialty)
Using a ready to use elfparser (probably readelf tool) to get the function offset under the executable. Note that you will have to figure out the real local offset since this tool usually gives you the address as if the executable was mapped to a specific address
So I'm trying to write a kernel module that uses the linux/timer.h file. I got it to work inside just the module, and now I am trying to get it to work from a user program.
Here is my kernel module:
//Necessary Includes For Device Drivers.
#include <linux/init.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/errno.h>
#include <linux/proc_fs.h>
#include <asm/uaccess.h>
#include <linux/timer.h>
#include <linux/ioctl.h>
#define DEVICE_NAME "mytimer"
#define DEVICE_FILE_NAME "mytimer"
#define MAJOR_NUM 61
#define MINOR_NUM 0
MODULE_LICENSE("Dual BSD/GPL");
static struct timer_list my_timer;
struct file_operations FileOps =
{
//No File Operations for this timer.
};
//Function to perform when timer expires.
void TimerExpire(int data)
{
printk("Timer Data: %d\n", data);
}
//Function to set up timers.
void TimerSetup(void)
{
setup_timer(&my_timer, TimerExpire, 5678);
mod_timer(&my_timer, jiffies + msecs_to_jiffies(5000));
}
//Module Init and Exit Functions.
int init_module(void)
{
int initResult = register_chrdev(MAJOR_NUM, "mytimer", &FileOps);
if (initResult < 0)
{
printk("Cannot obtain major number %d\n", MAJOR_NUM);
return initResult;
}
printk("Loading MyTimer Kernel Module...\n");
return 0;
}
void cleanup_module(void)
{
unregister_chrdev(MAJOR_NUM, "mytimer");
printk("Unloading MyTimer Kernel Module...\n");
}
More specifically, I want my user program to call the TimerSetup() function. I know that I'll need to use ioctl() but I'm not sure how to specify in my MODULE FILE that TimerSetup() should be callable via ioctl().
Also, my second question: I was able to insmod my module and also mknod into /dev/mytimer with the correct major number. But when I tried to open() it so that I can get the file descriptor from it, it kept returning -1, which I'm assuming is wrong. I made sure the permissions were fine (in fact, I made it 777 just to be sure)... It still doesn't work... Is there something I'm missing?
Here is the user program just in case:
#include <stdio.h>
int main(int argc, char* argv[])
{
int fd = open("/dev/mytimer", "r");
printf("fd: %d\n", fd);
return 0;
}
The example code you need can be found in drivers/watchdog/softdog.c (from Linux 2.6.33 at the time this was written), which illustrates proper file operations as well as how to permit userland to fill a structure with ioctl().
It's actually a great, working tutorial for anyone who needs to write trivial character device drivers.
I dissected softdog's ioctl interface when answering my own question, which may be helpful to you.
Here's the gist of it (though far from exhaustive) ...
In softdog_ioctl() you see a simple initialization of struct watchdog_info that advertises functionality, version and device information:
static const struct watchdog_info ident = {
.options = WDIOF_SETTIMEOUT |
WDIOF_KEEPALIVEPING |
WDIOF_MAGICCLOSE,
.firmware_version = 0,
.identity = "Software Watchdog",
};
We then look at a simple case where the user just wants to obtain these capabilities:
switch (cmd) {
case WDIOC_GETSUPPORT:
return copy_to_user(argp, &ident, sizeof(ident)) ? -EFAULT : 0;
... which of course, will fill the corresponding userspace watchdog_info with the initialized values above. If copy_to_user() fails, -EFAULT is returned which causes the corresponding userspace ioctl() call to return -1 with a meaningful errno being set.
Note, the magic requests are actually defined in linux/watchdog.h , so that the kernel and userspace share them:
#define WDIOC_GETSUPPORT _IOR(WATCHDOG_IOCTL_BASE, 0, struct watchdog_info)
#define WDIOC_GETSTATUS _IOR(WATCHDOG_IOCTL_BASE, 1, int)
#define WDIOC_GETBOOTSTATUS _IOR(WATCHDOG_IOCTL_BASE, 2, int)
#define WDIOC_GETTEMP _IOR(WATCHDOG_IOCTL_BASE, 3, int)
#define WDIOC_SETOPTIONS _IOR(WATCHDOG_IOCTL_BASE, 4, int)
#define WDIOC_KEEPALIVE _IOR(WATCHDOG_IOCTL_BASE, 5, int)
#define WDIOC_SETTIMEOUT _IOWR(WATCHDOG_IOCTL_BASE, 6, int)
#define WDIOC_GETTIMEOUT _IOR(WATCHDOG_IOCTL_BASE, 7, int)
#define WDIOC_SETPRETIMEOUT _IOWR(WATCHDOG_IOCTL_BASE, 8, int)
#define WDIOC_GETPRETIMEOUT _IOR(WATCHDOG_IOCTL_BASE, 9, int)
#define WDIOC_GETTIMELEFT _IOR(WATCHDOG_IOCTL_BASE, 10, int)
WDIOC obviously signifying "Watchdog ioctl"
You can easily take that a step further, having your driver do something and place the result of that something in the structure and copy it to userspace. For instance, if struct watchdog_info also had a member __u32 result_code. Note, __u32 is just the kernel's version of uint32_t.
With ioctl(), the user passes the address of an object, be it a structure, integer, whatever to the kernel expecting the kernel to write its reply in an identical object and copy the results to the address that was provided.
The second thing you are going to need to do is make sure your device knows what to do when someone opens, reads from it, writes to it, or uses a hook like ioctl(), which you can easily see by studying softdog.
Of interest is:
static const struct file_operations softdog_fops = {
.owner = THIS_MODULE,
.llseek = no_llseek,
.write = softdog_write,
.unlocked_ioctl = softdog_ioctl,
.open = softdog_open,
.release = softdog_release,
};
Where you see the unlocked_ioctl handler going to ... you guessed it, softdog_ioctl().
I think you might be juxtaposing a layer of complexity that really doesn't exist when dealing with ioctl(), it really is that simple. For that same reason, most kernel developers frown on new ioctl interfaces being added unless they are absolutely necessary. Its just too easy to lose track of the type that ioctl() is going to fill vs the magic you use to do it, which is the primary reason that copy_to_user() fails often resulting in the kernel rotting with hordes of userspace processes stuck in disk sleep.
For a timer, I agree, ioctl() is the shortest path to sanity.
You are missing a .open function pointer in your file_operations structure to specify the function to be called when a process attempts to open the device file. You will need to specify a .ioctl function pointer for your ioctl function as well.
Try reading through The Linux Kernel Module Programming Guide, specifically chapters 4 (Character Device Files) and 7 (Talking to Device Files).
Chapter 4 introduces the file_operations structure, which holds pointers to functions defined by the module/driver that perform various operations such as open or ioctl.
Chapter 7 provides information on communicating with a module/drive via ioctls.
Linux Device Drivers, Third Edition is another good resource.
Minimal runnable example
Tested in a fully reproducible QEMU + Buildroot environment, so might help others get their ioctl working. GitHub upstream:
kernel module |
shared header |
userland.
The most annoying part was understanding that some low ids are hijacked: ioctl is not called if cmd = 2 , you have to use _IOx macros.
Kernel module:
#include <asm/uaccess.h> /* copy_from_user, copy_to_user */
#include <linux/debugfs.h>
#include <linux/module.h>
#include <linux/printk.h> /* printk */
#include "ioctl.h"
MODULE_LICENSE("GPL");
static struct dentry *dir;
static long unlocked_ioctl(struct file *filp, unsigned int cmd, unsigned long argp)
{
void __user *arg_user;
union {
int i;
lkmc_ioctl_struct s;
} arg_kernel;
arg_user = (void __user *)argp;
pr_info("cmd = %x\n", cmd);
switch (cmd) {
case LKMC_IOCTL_INC:
if (copy_from_user(&arg_kernel.i, arg_user, sizeof(arg_kernel.i))) {
return -EFAULT;
}
pr_info("0 arg = %d\n", arg_kernel.i);
arg_kernel.i += 1;
if (copy_to_user(arg_user, &arg_kernel.i, sizeof(arg_kernel.i))) {
return -EFAULT;
}
break;
case LKMC_IOCTL_INC_DEC:
if (copy_from_user(&arg_kernel.s, arg_user, sizeof(arg_kernel.s))) {
return -EFAULT;
}
pr_info("1 arg = %d %d\n", arg_kernel.s.i, arg_kernel.s.j);
arg_kernel.s.i += 1;
arg_kernel.s.j -= 1;
if (copy_to_user(arg_user, &arg_kernel.s, sizeof(arg_kernel.s))) {
return -EFAULT;
}
break;
default:
return -EINVAL;
break;
}
return 0;
}
static const struct file_operations fops = {
.owner = THIS_MODULE,
.unlocked_ioctl = unlocked_ioctl
};
static int myinit(void)
{
dir = debugfs_create_dir("lkmc_ioctl", 0);
/* ioctl permissions are not automatically restricted by rwx as for read / write,
* but we could of course implement that ourselves:
* https://stackoverflow.com/questions/29891803/user-permission-check-on-ioctl-command */
debugfs_create_file("f", 0, dir, NULL, &fops);
return 0;
}
static void myexit(void)
{
debugfs_remove_recursive(dir);
}
module_init(myinit)
module_exit(myexit)
Shared header between the kernel module and userland:
ioctl.h
#ifndef IOCTL_H
#define IOCTL_H
#include <linux/ioctl.h>
typedef struct {
int i;
int j;
} lkmc_ioctl_struct;
#define LKMC_IOCTL_MAGIC 0x33
#define LKMC_IOCTL_INC _IOWR(LKMC_IOCTL_MAGIC, 0, int)
#define LKMC_IOCTL_INC_DEC _IOWR(LKMC_IOCTL_MAGIC, 1, lkmc_ioctl_struct)
#endif
Userland:
#define _GNU_SOURCE
#include <errno.h>
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <sys/ioctl.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <unistd.h>
#include "../ioctl.h"
int main(int argc, char **argv)
{
int fd, arg_int, ret;
lkmc_ioctl_struct arg_struct;
if (argc < 2) {
puts("Usage: ./prog <ioctl-file>");
return EXIT_FAILURE;
}
fd = open(argv[1], O_RDONLY);
if (fd == -1) {
perror("open");
return EXIT_FAILURE;
}
/* 0 */
{
arg_int = 1;
ret = ioctl(fd, LKMC_IOCTL_INC, &arg_int);
if (ret == -1) {
perror("ioctl");
return EXIT_FAILURE;
}
printf("arg = %d\n", arg_int);
printf("ret = %d\n", ret);
printf("errno = %d\n", errno);
}
puts("");
/* 1 */
{
arg_struct.i = 1;
arg_struct.j = 1;
ret = ioctl(fd, LKMC_IOCTL_INC_DEC, &arg_struct);
if (ret == -1) {
perror("ioctl");
return EXIT_FAILURE;
}
printf("arg = %d %d\n", arg_struct.i, arg_struct.j);
printf("ret = %d\n", ret);
printf("errno = %d\n", errno);
}
close(fd);
return EXIT_SUCCESS;
}