Why linux sys_unlinkat get param dfd/dirfd always -100? - linux

Can't get fd or dirfd from params, they are always be -100.
The kernel module is developed under CentOS 8.3, Linux kernel version 4.18.
The result is -100
I am a little confused why this will happen.
The reason why I need dfd is I want to get the absolute path, when input pathname alike "../".
asmlinkage int modified_unlinkat(const struct pt_regs *regs) {
int result;
int dfd = (int)regs->di;
char *tmp = (char*)__get_free_page(256);
struct file *files = fget(dfd);
if (!files) {
conivent_printf("%d", dfd);
return -EACCES;
}
char *path = d_path(&files->f_path, tmp, PAGE_SIZE);
conivent_printf("%s", path);
return -EACCESS;
}
If anyone could provide help, I will be extremely appreciate.

Related

Change read_proc_t read_proc and write_proc_t write_proc of an existing file in /proc

I'm actually working lkm on linux 2.6.32, and I don't to understand one thing. I'm trying to change the original read_proc and write_proc of /proc/version with my functions. Thus I can to change the original value of read_proc and write_proc, with values of my function. I can see it, because values of read_proc and write_proc change to NULL to adress of my functions, but that have no effect... And I don't understand why. I don't arrive to find if version is protected (I tried to change the value of file's right with chmod), or why even after change the value, I can't write in /proc/version with echo XXXX > /proc/version. I'll be grateful for your help.
Code where I try to change values of read_proc and write_proc:
static void Proc_init()
{
int find = 0;
pde = create_proc_entry("test", 0444, NULL); //that permit to create new file in /proc, only to get some useful values
ptdir = pde->parent; //affect to ptdir the value of the pointer on /proc
if(strcmp(ptdir->name, "/proc")!=0)
{
Erreur=1;
}
else
{
root = ptdir;
remove_proc_entry("test", NULL);
ptr_subdir=root->subdir;
while(find==0)
{
printk("%s \n", ptr_subdir->name);
if(strcmp("version", ptr_subdir->name)==0)
find=1;
else
ptr_subdir=ptr_subdir->next;
}
//Save original write et read proc
old_read_proc=ptr_subdir->read_proc;
old_write_proc=ptr_subdir->write_proc;
// Before I have null values for prt_subdir->read_proc and ptr_subdir->write_proc
ptr_subdir->read_proc=&new_read_proc_t;
ptr_subdir->write_proc=&new_write_proc_t;
// after that, values of prt_subdir->read_proc and ptr_subdir- >write_proc are egual to values of &new_write_proc_t and &new_read_proc_t
}
}
static int new_read_proc_t (char *page, char **start, off_t off,int count, int *eof, void *data)
{
int len;
/* For example - when content of our_buf is "hello" - when user executes command "cat /proc/test_proc"
he will see content of our_buf(in our example "hello" */
len = snprintf(page, count, "%s", our_buf);
return len;
}
static int new_write_proc_t(struct file *file, const char __user *buf,unsigned long count, void *data)
{
/* If count is bigger than 255, data which user wants to write is too big to fit in our_buf. We don't want
any buffer overflows, so we read only 255 bytes */
if(count > 255)
count = 255;
/* Here we read from buf to our_buf */
copy_from_user(our_buf, buf, count);
/* we write NULL to end the string */
our_buf[count] = '\0';
return count;
}

jprobe do_execve does not work with kernel 4.1

I want to set a jprobe hook on do_execve to catch every executed program.
My code is working on <= 3.2 linux kernel (debian). This is my output on linux kernel 3.2:
[ 628.534037] registered: do_execve, ret: 0
[ 723.995797] execve: /usr/bin/vi
[ 726.807025] execve: /bin/dmesg
on 4.1 kernel I the same result (everything is registered) but there is no "execve":
[ 8621.430568] registered: do_execve, ret: 0
And this is my code:
static struct jprobe jprobe_hooks[] = {
{
.entry = jdo_execve,
.kp = { .symbol_name = "do_execve" }
}};
static long jdo_execve(const char *filename, const char __user *const __user *argv, const char __user *const __user *envp, struct pt_regs *regs)
{
printk(KERN_INFO "execve: %s", filename );
}
//
// registration
//
int ret, x, reg_error;
reg_error = 0;
for (x = 0; x < sizeof(jprobe_hooks) / sizeof(jprobe_hooks[0]); x++)
{
ret = register_jprobe(&jprobe_hooks[x]);
if (ret < 0)
{
printk(KERN_INFO "register_jprobe failed, returned %d, item: %s\n", ret, jprobe_hooks[x].kp.symbol_name);
reg_error++;
}
else
{
printk(KERN_INFO "registered: %s, ret: %u\n", jprobe_hooks[x].kp.symbol_name, ret);
}
}
When I do a grep on kallsyms I get on 3.2:
grep do_execv /proc/kallsyms
ffffffff81100650 T do_execve
and on 4.2:
grep do_execv /proc/kallsyms
ffffffff811d2950 T do_execve
ffffffff811d2980 T do_execveat
I even tried to change the function (because do_execve prototype has changed) to this:
static int jdo_execve(struct filename *fname, const char __user *const __user *__argv, const char __user *const __user *__envp)
{
int i = 0;
printk(KERN_INFO "execve: %s ", fname->name );
}
and even that didn't help.
I can set hooks on other functions like do_fork or sys_open, but not on do_execve. Why? Anybody has ideas? Why is it not working anymore?
Edit:
I'm also hooking do_execveat:
static int jdo_execveat(int fd, struct filename *fname, const char __user *const __user *__argv, const char __user *const __user *__envp, int flags)
There are several problems that may prevent you jprobe messages:
You don't end print messages printk(KERN_INFO "execve: %s", filename ); with newline, thus you log buffer is not flushed.
API had changed. Now do_execve has filename parameter as struct filename.
Your jprobe code is silly: you don't have module entry, jprobe routine must end with jprobe_return() call and so on. Look at the samples in kernel source tree at "samples/kprobes"
Try to fix it - maybe it will help.
Anyway, I tried it by myself - here is the code - and things is, indeed, looks strange. When I load the module it registers 2 jprobes - one for do_execve, another for do_execveat. But I don't see any messages when I execute programs. BUT what I do see is periodical messages like this:
jprobe: execve: /usr/lib/systemd/systemd-cgroups-agent
It means that jprobe itself works, but not for every execve call.
So I wrote a simple C program to call execve just to be sure it's really called and I still nothing happens execpt systemd-cgroups-agent.

IOCTL Method - Linux

I have an exam question and I can't quite see how to solve it.
A driver that needs the ioctl method to be implemented and tested.
I have to write the ioctl() method, the associated test program as well as the common IOCTL definitions.
The ioctl() method should only handle one command. In this command, I need to transmit a data structure from user space to kernel space.
Below is the structure shown:
struct data
{
     char label [10];
     int value;
}
The driver must print the IOCTL command data, using printk();
Device name is "/dev/mydevice"
The test program must validate driver mode using an initialized data structure.
Hope there are some that can help
thanks in advance
My suggestion:
static int f_on_ioctl(struct inode *inode, struct file *file, unsigned int cmd,
unsigned long arg)
{
int ret;
switch (cmd)
{
case PASS_STRUCT:
struct data pass_data;
ret = copy_from_user(&pass_data, arg, sizeof(*pass_data));
if(ret < 0)
{
printk("PASS_STRUCT\n");
return -1;
}
printk(KERN ALERT "Message PASS_STRUCT : %d and %c\n",pass_data.value, pass_data.label);
break;
default:
return ENOTTY;
}
return 0;
}
Definitions:
Common.h
#define SYSLED_IOC_MAGIC 'k'
#define PASS_STRUCT _IOW(SYSLED_IOC_MAGIC, 1, struct data)
The test program:
int main()
{
int fd = open("/dev/mydevice", O_RDWR);
data data_pass;
data_pass.value = 2;
data_pass.label = "hej";
ioctl(fd, PASS_STRUCT, &data_pass);
close(fd);
return 0;
}
Is this completely wrong??

Getting list of network devices inside the Linux kernel

I've been looking through net/core/dev.c and other files to try to find out how to get the list of network devices that are currently configured and it's proving to be a little difficult to find.
The end goal is to be able to get network device statistics using dev_get_stats in dev.c, but I need to know the current interfaces so I can grab the net_device struct to pass in. I'm having to do this inside the kernel as I'm writing a module which adds in a new /proc/ entry which relates to some statistics from the current network devices so from what I can gather this must be done inside the kernel.
If someone could point me to how to get the interfaces it would be much appreciated.
This ought to do the trick:
#include <linux/netdevice.h>
struct net_device *dev;
read_lock(&dev_base_lock);
dev = first_net_device(&init_net);
while (dev) {
printk(KERN_INFO "found [%s]\n", dev->name);
dev = next_net_device(dev);
}
read_unlock(&dev_base_lock);
Given a struct net *net identifying the net namespace that you are interested in, you should grab the dev_base_lock and use for_each_netdev():
read_lock(&dev_base_lock);
for_each_netdev(net, dev) {
/* Inspect dev */
}
read_unlock(&dev_base_lock);
(In newer kernels, you can use RCU instead, but that is probably an overcomplication in this case).
To obtain the net namespace to use, you should be registering your proc file with register_pernet_subsys():
static const struct file_operations foostats_seq_fops = {
.owner = THIS_MODULE,
.open = foostats_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = foostats_seq_release,
};
static int foo_proc_init_net(struct net *net)
{
if (!proc_net_fops_create(net, "foostats", S_IRUGO,
&foostats_seq_fops))
return -ENOMEM;
return 0;
}
static void foo_proc_exit_net(struct net *net)
{
proc_net_remove(net, "foostats");
}
static struct pernet_operations foo_proc_ops = {
.init = foo_proc_init_net,
.exit = foo_proc_exit_net,
};
register_pernet_subsys(&foo_proc_ops)
In your foostats_seq_open() function, you take a reference on the net namespace, and drop it in the release function:
static int foostats_seq_open(struct inode *inode, struct file *file)
{
int err;
struct net *net;
err = -ENXIO;
net = get_proc_net(inode);
if (net == NULL)
goto err_net;
err = single_open(file, foostats_seq_show, net);
if (err < 0)
goto err_open;
return 0;
err_open:
put_net(net);
err_net:
return err;
}
static int foostats_seq_release(struct inode *inode, struct file *file)
{
struct net *net = ((struct seq_file *)file->private_data)->private;
put_net(net);
return single_release(inode, file);
}
The foostats_seq_show() function can then obtain the net, walk the devices, gather the statistics and produce the output:
static int sockstat6_seq_show(struct seq_file *seq, void *v)
{
struct net *net = seq->private;
struct net_device *dev;
int foostat, barstat;
read_lock(&dev_base_lock);
for_each_netdev(net, dev) {
/* Inspect dev */
}
read_unlock(&dev_base_lock);
seq_printf(seq, "Foo: %d\n", foostat);
seq_printf(seq, "Bar: %d\n", barstat);
return 0;
}

Kernel Panic after changes in sys_close

I'm doing a course on operating systems and we work in Linux Red Hat 8.0
AS part of an assignment I had to change sys close and sys open. Changes to sys close passed without an incident, but when I introduce the changes to sys close suddenly the OS encounters an error during booting, claiming it cannot mount root fs, and invokes panic. EIP is reportedly at sys close when this happens.
Here are the changes I made (look for the "HW1 additions" comment):
In fs/open.c:
asmlinkage long sys_open(const char * filename, int flags, int mode)
{
char * tmp;
int fd, error;
event_t* new_event;
#if BITS_PER_LONG != 32
flags |= O_LARGEFILE;
#endif
tmp = getname(filename);
fd = PTR_ERR(tmp);
if (!IS_ERR(tmp)) {
fd = get_unused_fd();
if (fd >= 0) {
struct file *f = filp_open(tmp, flags, mode);
error = PTR_ERR(f);
if (IS_ERR(f))
goto out_error;
fd_install(fd, f);
}
/* HW1 additions */
if (current->record_flag==1){
new_event=(event_t*)kmalloc(sizeof(event_t), GFP_KERNEL);
if (!new_event){
new_event->type=Open;
strcpy(new_event->filename, tmp);
file_queue_add(*new_event, current->queue);
}
}
/* End HW1 additions */
out:
putname(tmp);
}
return fd;
out_error:
put_unused_fd(fd);
fd = error;
goto out;
}
asmlinkage long sys_close(unsigned int fd)
{
struct file * filp;
struct files_struct *files = current->files;
event_t* new_event;
char* tmp = files->fd[fd]->f_dentry->d_name.name;
write_lock(&files->file_lock);
if (fd >= files->max_fds)
goto out_unlock;
filp = files->fd[fd];
if (!filp)
goto out_unlock;
files->fd[fd] = NULL;
FD_CLR(fd, files->close_on_exec);
__put_unused_fd(files, fd);
write_unlock(&files->file_lock);
/* HW1 additions */
if(current->record_flag == 1){
new_event=(event_t*)kmalloc(sizeof(event_t), GFP_KERNEL);
if (!new_event){
new_event->type=Close;
strcpy(new_event->filename, tmp);
file_queue_add(*new_event, current->queue);
}
}
/* End HW1 additions */
return filp_close(filp, files);
out_unlock:
write_unlock(&files->file_lock);
return -EBADF;
}
The task_struct defined in schedule.h was changed at the end to include:
unsigned int record_flag; /* when zero: do not record. when one: record. */
file_queue* queue;
And file queue as well as event t are defined in a separate file as follows:
typedef enum {Open, Close} EventType;
typedef struct event_t{
EventType type;
char filename[256];
}event_t;
typedef struct file_quque_t{
event_t queue[101];
int head, tail;
}file_queue;
file queue add works like this:
void file_queue_add(event_t event, file_queue* queue){
queue->queue[queue->head]=event;
queue->head = (queue->head+1) % 101;
if (queue->head==queue->tail){
queue->tail=(queue->tail+1) % 101;
}
}
if (!new_event) {
new_event->type = …
That's equivalent to if (new_event == NULL). I think you mean if (new_event != NULL), which the kernel folks typically write as if (new_event).
Can you please post the stackdump of the error. I don't see a place where queue_info structure is allocated memory. One more thing is you cannot be sure that process record_flag will be always zero if unassigned in kernel, because kernel is a long running program and memory contains garbage.
Its also possible to check the exact location in the function is occurring by looking at the stack trace.

Resources