From ccfad514c493333e8bf81d124842526f07a813b5 Mon Sep 17 00:00:00 2001 From: jserv Date: Mon, 9 Aug 2021 13:38:20 +0000 Subject: [PATCH] deploy: 53ef0614e8395af59a3478d0f4f6e1db62cf9177 --- index.html | 1763 ++++++++++++++++++++++---------------------- lkmpg-for-ht.html | 1763 ++++++++++++++++++++++---------------------- lkmpg-for-ht0x.svg | 22 +- 3 files changed, 1781 insertions(+), 1767 deletions(-) diff --git a/index.html b/index.html index b879ef2..721e556 100644 --- a/index.html +++ b/index.html @@ -226,10 +226,10 @@ thereafter.

Modules can not print to the screen like printf() can, but they can log information and warnings, which ends up being - printed on your screen, but only on a console. If you insmod a module - from an xterm, the information and warnings will be logged, but only to - your systemd journal. You will not see it unless you look through your - journalctl + printed on your screen, but only on a console. If you insmod + a module from an xterm, the information and warnings will be logged, but + only to your systemd journal. You will not see it unless you look through + your journalctl . See 0.4 for details. To have immediate access to this information, do all your work from the console.

@@ -569,11 +569,13 @@ used to.

To allow arguments to be passed to your module, declare the variables that will take the values of the command line arguments as global and then use the module_param() - macro, (defined in linux/moduleparam.h) to set the mechanism up. At runtime, -insmod will fill the variables with any command line arguments that are given, like -insmod ./mymodule.ko myvariable=5. The variable declarations and macros should -be placed at the beginning of the module for clarity. The example code should clear -up my admittedly lousy explanation. + macro, (defined in include/linux/moduleparam.h) to set the mechanism up. At +runtime, insmod + will fill the variables with any command line arguments that are given, like + insmod ./mymodule.ko myvariable=5 +. The variable declarations and macros should be placed at the beginning of the +module for clarity. The example code should clear up my admittedly lousy +explanation.

The module_param() macro takes 3 arguments: the name of the variable, its type and permissions for the corresponding file in sysfs. Integer types can be signed @@ -582,12 +584,12 @@ as usual or unsigned. If you’d like to use arrays of integers or strings see and module_param_string() .

-

- 
1int myint = 3; 
-2module_param(myint, int, 0);
+

+ 
1int myint = 3; 
+2module_param(myint, int, 0);

Arrays are supported too, but things are a bit different now than they were in the olden days. To keep track of the number of parameters you need to pass a pointer to a count variable as third parameter. At your option, you could @@ -595,12 +597,12 @@ also ignore the count and pass NULL instead. We show both possibilities here:

- 
1int myintarray[2]; 
-2module_param_array(myintarray, int, NULL, 0); /* not interested in count */ 
-3 
-4short myshortarray[4]; 
-5int count; 
-6module_param_array(myshortarray, short, &count, 0); /* put count into "count" variable */
+ 
1int myintarray[2]; 
+2module_param_array(myintarray, int, NULL, 0); /* not interested in count */ 
+3 
+4short myshortarray[4]; 
+5int count; 
+6module_param_array(myshortarray, short, &count, 0); /* put count into "count" variable */

A good use for this is to have the module variable’s default values set, like an port or IO address. If the variables contain the default values, then perform autodetection (explained elsewhere). Otherwise, keep the current value. This will be made clear @@ -610,100 +612,100 @@ later on. parameters: a variable name and a free form string describing that variable.

- 
1/* 
-2 * hello-5.c - Demonstrates command line argument passing to a module. 
-3 */ 
-4#include <linux/init.h> 
-5#include <linux/kernel.h> 
-6#include <linux/module.h> 
-7#include <linux/moduleparam.h> 
-8#include <linux/stat.h> 
-9 
-10MODULE_LICENSE("GPL"); 
-11 
-12static short int myshort = 1; 
-13static int myint = 420; 
-14static long int mylong = 9999; 
-15static char *mystring = "blah"; 
-16static int myintArray[2] = {420, 420}; 
-17static int arr_argc = 0; 
-18 
-19/* module_param(foo, int, 0000) 
-20 * The first param is the parameters name. 
-21 * The second param is its data type. 
-22 * The final argument is the permissions bits, 
-23 * for exposing parameters in sysfs (if non-zero) at a later stage. 
-24 */ 
-25module_param(myshort, short, S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP); 
-26MODULE_PARM_DESC(myshort, "A short integer"); 
-27module_param(myint, int, S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH); 
-28MODULE_PARM_DESC(myint, "An integer"); 
-29module_param(mylong, long, S_IRUSR); 
-30MODULE_PARM_DESC(mylong, "A long integer"); 
-31module_param(mystring, charp, 0000); 
-32MODULE_PARM_DESC(mystring, "A character string"); 
-33 
-34/* module_param_array(name, type, num, perm); 
-35 * The first param is the parameter's (in this case the array's) name. 
-36 * The second param is the data type of the elements of the array. 
-37 * The third argument is a pointer to the variable that will store the number. 
-38 * of elements of the array initialized by the user at module loading time. 
-39 * The fourth argument is the permission bits. 
-40 */ 
-41module_param_array(myintArray, int, &arr_argc, 0000); 
-42MODULE_PARM_DESC(myintArray, "An array of integers"); 
-43 
-44static int __init hello_5_init(void) 
-45{ 
-46    int i; 
-47    pr_info("Hello, world 5\n=============\n"); 
-48    pr_info("myshort is a short integer: %hd\n", myshort); 
-49    pr_info("myint is an integer: %d\n", myint); 
-50    pr_info("mylong is a long integer: %ld\n", mylong); 
-51    pr_info("mystring is a string: %s\n", mystring); 
-52 
-53    for (i = 0; i < (sizeof myintArray / sizeof(int)); i++) 
-54        pr_info("myintArray[%d] = %d\n", i, myintArray[i]); 
-55 
-56    pr_info("got %d arguments for myintArray.\n", arr_argc); 
-57    return 0; 
-58} 
-59 
-60static void __exit hello_5_exit(void) 
-61{ 
-62    pr_info("Goodbye, world 5\n"); 
-63} 
-64 
-65module_init(hello_5_init); 
-66module_exit(hello_5_exit);
+ 
1/* 
+2 * hello-5.c - Demonstrates command line argument passing to a module. 
+3 */ 
+4#include <linux/init.h> 
+5#include <linux/kernel.h> 
+6#include <linux/module.h> 
+7#include <linux/moduleparam.h> 
+8#include <linux/stat.h> 
+9 
+10MODULE_LICENSE("GPL"); 
+11 
+12static short int myshort = 1; 
+13static int myint = 420; 
+14static long int mylong = 9999; 
+15static char *mystring = "blah"; 
+16static int myintArray[2] = {420, 420}; 
+17static int arr_argc = 0; 
+18 
+19/* module_param(foo, int, 0000) 
+20 * The first param is the parameters name. 
+21 * The second param is its data type. 
+22 * The final argument is the permissions bits, 
+23 * for exposing parameters in sysfs (if non-zero) at a later stage. 
+24 */ 
+25module_param(myshort, short, S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP); 
+26MODULE_PARM_DESC(myshort, "A short integer"); 
+27module_param(myint, int, S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH); 
+28MODULE_PARM_DESC(myint, "An integer"); 
+29module_param(mylong, long, S_IRUSR); 
+30MODULE_PARM_DESC(mylong, "A long integer"); 
+31module_param(mystring, charp, 0000); 
+32MODULE_PARM_DESC(mystring, "A character string"); 
+33 
+34/* module_param_array(name, type, num, perm); 
+35 * The first param is the parameter's (in this case the array's) name. 
+36 * The second param is the data type of the elements of the array. 
+37 * The third argument is a pointer to the variable that will store the number. 
+38 * of elements of the array initialized by the user at module loading time. 
+39 * The fourth argument is the permission bits. 
+40 */ 
+41module_param_array(myintArray, int, &arr_argc, 0000); 
+42MODULE_PARM_DESC(myintArray, "An array of integers"); 
+43 
+44static int __init hello_5_init(void) 
+45{ 
+46    int i; 
+47    pr_info("Hello, world 5\n=============\n"); 
+48    pr_info("myshort is a short integer: %hd\n", myshort); 
+49    pr_info("myint is an integer: %d\n", myint); 
+50    pr_info("mylong is a long integer: %ld\n", mylong); 
+51    pr_info("mystring is a string: %s\n", mystring); 
+52 
+53    for (i = 0; i < (sizeof myintArray / sizeof(int)); i++) 
+54        pr_info("myintArray[%d] = %d\n", i, myintArray[i]); 
+55 
+56    pr_info("got %d arguments for myintArray.\n", arr_argc); 
+57    return 0; 
+58} 
+59 
+60static void __exit hello_5_exit(void) 
+61{ 
+62    pr_info("Goodbye, world 5\n"); 
+63} 
+64 
+65module_init(hello_5_init); 
+66module_exit(hello_5_exit);

I would recommend playing around with this code:

- 
1$ sudo insmod hello-5.ko mystring="bebop" myintArray=-1 
-2myshort is a short integer: 1 
-3myint is an integer: 420 
-4mylong is a long integer: 9999 
-5mystring is a string: bebop 
-6myintArray[0] = -1 
-7myintArray[1] = 420 
-8got 1 arguments for myintArray. 
-9 
-10$ sudo rmmod hello-5 
-11Goodbye, world 5 
-12 
-13$ sudo insmod hello-5.ko mystring="supercalifragilisticexpialidocious" myintArray=-1,-1 
-14myshort is a short integer: 1 
-15myint is an integer: 420 
-16mylong is a long integer: 9999 
-17mystring is a string: supercalifragilisticexpialidocious 
-18myintArray[0] = -1 
-19myintArray[1] = -1 
-20got 2 arguments for myintArray. 
-21 
-22$ sudo rmmod hello-5 
-23Goodbye, world 5 
-24 
-25$ sudo insmod hello-5.ko mylong=hello 
-26hello-5.o: invalid argument syntax for mylong: 'h'
+ 
1$ sudo insmod hello-5.ko mystring="bebop" myintArray=-1 
+2myshort is a short integer: 1 
+3myint is an integer: 420 
+4mylong is a long integer: 9999 
+5mystring is a string: bebop 
+6myintArray[0] = -1 
+7myintArray[1] = 420 
+8got 1 arguments for myintArray. 
+9 
+10$ sudo rmmod hello-5 
+11Goodbye, world 5 
+12 
+13$ sudo insmod hello-5.ko mystring="supercalifragilisticexpialidocious" myintArray=-1,-1 
+14myshort is a short integer: 1 
+15myint is an integer: 420 
+16mylong is a long integer: 9999 
+17mystring is a string: supercalifragilisticexpialidocious 
+18myintArray[0] = -1 
+19myintArray[1] = -1 
+20got 2 arguments for myintArray. 
+21 
+22$ sudo rmmod hello-5 
+23Goodbye, world 5 
+24 
+25$ sudo insmod hello-5.ko mylong=hello 
+26hello-5.o: invalid argument syntax for mylong: 'h'

0.4.6 Modules Spanning Multiple Files

@@ -756,13 +758,13 @@ files. 11 12clean: 13    make -C /lib/modules/$(shell uname -r)/build M=$(PWD) clean + + +

This is the complete makefile for all the examples we have seen so far. The first five lines are nothing special, but for the last example we will need two lines. First we invent an object name for our combined module, second we tell make what object files are part of that module. - - -

0.4.7 Building modules for a precompiled kernel

@@ -806,11 +808,12 @@ REGPARM 4KSTACKS gcc-3.3' should be '2.6.5-1.358 686 REGPARM 4KSTACKS g

In other words, your kernel refuses to accept your module because version strings -(more precisely, version magics) do not match. Incidentally, version magics are stored -in the module object in the form of a static string, starting with vermagic:. Version -data are inserted in your module when it is linked against the init/vermagic.o file. -To inspect version magics and other strings stored in a given module, issue the -modinfo module.ko command: +(more precisely, version magics) do not match. Incidentally, version magics are stored in +the module object in the form of a static string, starting with vermagic:. Version data +are inserted in your module when it is linked against the init/vermagic.o file. To +inspect version magics and other strings stored in a given module, issue the command + modinfo module.ko +: @@ -1058,7 +1061,7 @@ careful. operating system which uses a monolithic kernel. This is not quite the same thing as "building all your modules into the kernel", although the idea is the same. There are things called microkernels which have modules which get their own codespace. The -GNU Hurd and the Zircon kernel of Google Fuchsia are two examples of a +GNU Hurd and the Zircon kernel of Google Fuchsia are two examples of a microkernel.

@@ -1097,16 +1100,17 @@ them as being different pieces of hardware.

Devices are divided into two types: character devices and block devices. The difference is that block devices have a buffer for requests, so they can choose the best order in which to respond to the requests. This is important in the case of storage -devices, where it is faster to read or write sectors which are close to each other, -rather than those which are further apart. Another difference is that block devices -can only accept input and return output in blocks (whose size can vary according to -the device), whereas character devices are allowed to use as many or as few bytes -as they like. Most devices in the world are character, because they don’t -need this type of buffering, and they don’t operate with a fixed block size. -You can tell whether a device file is for a block device or a character device -by looking at the first character in the output of ls -l. If it is ‘b’ then it -is a block device, and if it is ‘c’ then it is a character device. The devices -you see above are block devices. Here are some character devices (the serial +devices, where it is faster to read or write sectors which are close to each +other, rather than those which are further apart. Another difference is that +block devices can only accept input and return output in blocks (whose size +can vary according to the device), whereas character devices are allowed +to use as many or as few bytes as they like. Most devices in the world are +character, because they don’t need this type of buffering, and they don’t +operate with a fixed block size. You can tell whether a device file is for a block +device or a character device by looking at the first character in the output of + ls -l +. If it is ‘b’ then it is a block device, and if it is ‘c’ then it is a character device. The +devices you see above are block devices. Here are some character devices (the serial ports): @@ -1119,24 +1123,25 @@ crw-rw----  1 root  dial 4, 66 Jul  5  2000 /dev/ttyS2 crw-rw----  1 root  dial 4, 67 Jul  5  2000 /dev/ttyS3

-

If you want to see which major numbers have been assigned, you can look at +

If you want to see which major numbers have been assigned, you can look at Documentation/admin-guide/devices.txt. -

When the system was installed, all of those device files were created by the -mknod command. To create a new char device named ‘coffee’ with major/minor -number 12 and 2, simply do mknod /dev/coffee c 12 2. You do not have to put your -device files into /dev, but it is done by convention. Linus put his device files in /dev, -and so should you. However, when creating a device file for testing purposes, it is -probably OK to place it in your working directory where you compile the kernel -module. Just be sure to put it in the right place when you’re done writing the device -driver. -

I would like to make a few last points which are implicit from the above +

When the system was installed, all of those device files were created by the + mknod + command. To create a new char device named coffee with major/minor number 12 and 2, +simply do mknod /dev/coffee c 12 2 +. You do not have to put your device files into /dev, but it is done by convention. +Linus put his device files in /dev, and so should you. However, when creating a +device file for testing purposes, it is probably OK to place it in your working +directory where you compile the kernel module. Just be sure to put it in the right +place when you’re done writing the device driver. +

I would like to make a few last points which are implicit from the above discussion, but I would like to make them explicit just in case. When a device file is accessed, the kernel uses the major number of the file to determine which driver should be used to handle the access. This means that the kernel doesn’t really need to use or even know about the minor number. The driver itself is the only thing that cares about the minor number. It uses the minor number to distinguish between different pieces of hardware. -

By the way, when I say "hardware", I mean something a bit more abstract +

By the way, when I say "hardware", I mean something a bit more abstract than a PCI card that you can hold in your hand. Look at these two device files: @@ -1148,24 +1153,24 @@ $ ls -l /dev/sda /dev/sdb brw-rw---- 1 root disk 8,  0 Jan  3 09:02 /dev/sda brw-rw---- 1 root disk 8, 16 Jan  3 09:02 /dev/sdb -

-

By now you can look at these two device files and know instantly that they are +

+

By now you can look at these two device files and know instantly that they are block devices and are handled by same driver (block major 8). Sometimes two device files with the same major but different minor number can actually represent the same piece of physical hardware. So just be aware that the word “hardware” in our discussion can mean something very abstract. -

+

0.6 Character Device drivers

-

+

0.6.1 The file_operations Structure

-

The file_operations - structure is defined in /usr/include/linux/fs.h, and holds pointers to functions -defined by the driver that perform various operations on the device. Each field of the +

The file_operations + structure is defined in include/linux/fs.h, and holds pointers to functions defined +by the driver that perform various operations on the device. Each field of the structure corresponds to the address of some function defined by the driver to handle a requested operation. -

For example, every character driver needs to define a function that reads from the +

For example, every character driver needs to define a function that reads from the device. The file_operations structure holds the address of the module’s function that performs that operation. Here is what the definition looks like for kernel 5.4: @@ -1209,11 +1214,11 @@ Here is what the definition looks like for kernel 5.4: 36             loff_t len, unsigned int remap_flags); 37    int (*fadvise)(struct file *, loff_t, loff_t, int); 38} __randomize_layout; -

Some operations are not implemented by a driver. For example, a driver that handles +

Some operations are not implemented by a driver. For example, a driver that handles a video card will not need to read from a directory structure. The corresponding entries in the file_operations structure should be set to NULL. -

There is a gcc extension that makes assigning to this structure more convenient. +

There is a gcc extension that makes assigning to this structure more convenient. You will see it in modern drivers, and may catch you by surprise. This is what the new way of assigning to the structure looks like:

@@ -1227,7 +1232,7 @@ new way of assigning to the structure looks like: 4    open: device_open, 5    release: device_release 6}; -

However, there is also a C99 way of assigning to elements of a structure, +

However, there is also a C99 way of assigning to elements of a structure, designated initializers, and this is definitely preferred over using the GNU extension. You should use this syntax in case someone wants to port your driver. It will help with compatibility: @@ -1239,36 +1244,36 @@ with compatibility: 4    .open = device_open, 5    .release = device_release 6}; -

The meaning is clear, and you should be aware that any member of the +

The meaning is clear, and you should be aware that any member of the structure which you do not explicitly assign will be initialized to NULL by gcc. -

An instance of struct file_operations +

An instance of struct file_operations containing pointers to functions that are used to implement read, write, open, … syscalls is commonly named fops. -

Sin Linux v5.6, the proc_ops +

Sin Linux v5.6, the proc_ops structure was introduced to replace the use of the file_operations structure when registering proc handlers. -

+

0.6.2 The file structure

-

Each device is represented in the kernel by a file structure, which is defined +

Each device is represented in the kernel by a file structure, which is defined in linux/fs.h. Be aware that a file is a kernel level structure and never appears in a user space program. It is not the same thing as a FILE , which is defined by glibc and would never appear in a kernel space function. Also, its name is a bit misleading; it represents an abstract open ‘file’, not a file on a disk, which is represented by a structure named inode. -

An instance of struct file is commonly named filp. You’ll also see it refered to as +

An instance of struct file is commonly named filp. You’ll also see it refered to as struct file file. Resist the temptation. -

Go ahead and look at the definition of file. Most of the entries you see, like struct +

Go ahead and look at the definition of file. Most of the entries you see, like struct dentry are not used by device drivers, and you can ignore them. This is because drivers do not fill file directly; they only use structures contained in file which are created elsewhere. -

+

0.6.3 Registering A Device

-

As discussed earlier, char devices are accessed through device files, usually located in +

As discussed earlier, char devices are accessed through device files, usually located in /dev. This is by convention. When writing a driver, it is OK to put the @@ -1278,14 +1283,14 @@ production driver. The major number tells you which driver handles which device file. The minor number is used only by the driver itself to differentiate which device it is operating on, just in case the driver handles more than one device. -

Adding a driver to your system means registering it with the kernel. This is synonymous +

Adding a driver to your system means registering it with the kernel. This is synonymous with assigning it a major number during the module’s initialization. You do this by using the register_chrdev function, defined by linux/fs.h. 

1int register_chrdev(unsigned int major, const char *name, struct file_operations *fops);
-

where unsigned int major is the major number you want to request, +

where unsigned int major is the major number you want to request, const char *name is the name of the device as it will appear in /proc/devices and struct file_operations *fops @@ -1295,13 +1300,13 @@ registration failed. Note that we didn’t pass the minor number to register_chrdev . That is because the kernel doesn’t care about the minor number; only our driver uses it. -

Now the question is, how do you get a major number without hijacking +

Now the question is, how do you get a major number without hijacking one that’s already in use? The easiest way would be to look through Documentation/admin-guide/devices.txt and pick an unused one. That is a bad way of doing things because you will never be sure if the number you picked will be assigned later. The answer is that you can ask the kernel to assign you a dynamic major number. -

If you pass a major number of 0 to register_chrdev +

If you pass a major number of 0 to register_chrdev , the return value will be the dynamically allocated major number. The downside is that you can not make a device file in advance, since you do not know what the major number will be. There are a couple of ways to do @@ -1315,13 +1320,13 @@ third method is we can have our driver make the the device file using the device_destroy during the call to cleanup_module . -

+

0.6.4 Unregistering A Device

-

We can not allow the kernel module to be rmmod’ed whenever root feels like it. If the +

We can not allow the kernel module to be rmmod’ed whenever root feels like it. If the device file is opened by a process and then we remove the kernel module, using the file would cause a call to the memory location where the appropriate function (read/write) used to be. If we are lucky, no other code was loaded there, and we’ll get @@ -1329,13 +1334,14 @@ an ugly error message. If we are unlucky, another kernel module was loaded into same location, which means a jump into the middle of another function within the kernel. The results of this would be impossible to predict, but they can not be very positive. -

Normally, when you do not want to allow something, you return an error code +

Normally, when you do not want to allow something, you return an error code (a negative number) from the function which is supposed to do it. With cleanup_module that’s impossible because it is a void function. However, there is a counter which keeps track of how many processes are using your module. You can see what its value is by looking at the 3rd field of /proc/modules. If this number isn’t zero, -rmmod will fail. Note that you do not have to check the counter from within + rmmod + will fail. Note that you do not have to check the counter from within cleanup_module because the check will be performed for you by the system call sys_delete_module @@ -1349,22 +1355,22 @@ this counter:

  • module_put(THIS_MODULE) : Decrement the use count.
    • -

    It is important to keep the counter accurate; if you ever do lose track of the +

    It is important to keep the counter accurate; if you ever do lose track of the correct usage count, you will never be able to unload the module; it’s now reboot time, boys and girls. This is bound to happen to you sooner or later during a module’s development. -

    -

    +

    +

    0.6.5 chardev.c

    -

    The next code sample creates a char driver named chardev. You can cat its device +

    The next code sample creates a char driver named chardev. You can cat its device file. 

    1cat /proc/devices
    -

    (or open the file with a program) and the driver will put the number of times the +

    (or open the file with a program) and the driver will put the number of times the device file has been read from into the file. We do not support writing to the file (like echo "hi" > /dev/hello ), but catch these attempts and tell the user that the operation is not supported. @@ -1522,39 +1528,39 @@ acknowledging that we received it. 147module_exit(chardev_exit); 148 149MODULE_LICENSE("GPL"); -

    +

    0.6.6 Writing Modules for Multiple Kernel Versions

    -

    The system calls, which are the major interface the kernel shows to the processes, +

    The system calls, which are the major interface the kernel shows to the processes, generally stay the same across versions. A new system call may be added, but usually the old ones will behave exactly like they used to. This is necessary for backward compatibility – a new kernel version is not supposed to break regular processes. In most cases, the device files will also remain the same. On the other hand, the internal interfaces within the kernel can and do change between versions. -

    There are differences between different kernel versions, and if you want +

    There are differences between different kernel versions, and if you want to support multiple kernel versions, you will find yourself having to code conditional compilation directives. The way to do this to compare the macro LINUX_VERSION_CODE to the macro KERNEL_VERSION . In version a.b.c of the kernel, the value of this macro would be 216a+ 28b+ c . -

    While previous versions of this guide showed how you can write backward +

    While previous versions of this guide showed how you can write backward compatible code with such constructs in great detail, we decided to break with this tradition for the better. People interested in doing such might now use a LKMPG with a version matching to their kernel. -

    -

    +

    +

    0.7 The /proc File System

    -

    In Linux, there is an additional mechanism for the kernel and kernel modules to send +

    In Linux, there is an additional mechanism for the kernel and kernel modules to send information to processes — the /proc file system. Originally designed to allow easy access to information about processes (hence the name), it is now used by every bit of the kernel which has something interesting to report, such as /proc/modules which provides the list of modules and /proc/meminfo which stats memory usage statistics. -

    The method to use the proc file system is very similar to the one used with device +

    The method to use the proc file system is very similar to the one used with device drivers — a structure is created with all the information needed for the /proc file, including pointers to any handler functions (in our case there is only one, the one called when somebody attempts to read from the /proc file). Then, @@ -1562,18 +1568,18 @@ one called when somebody attempts to read from the registers the structure with the kernel and cleanup_module unregisters it. -

    Normal file systems are located on a disk, rather than just in memory (which is +

    Normal file systems are located on a disk, rather than just in memory (which is where /proc is), and in that case the inode number is a pointer to a disk location where the file’s index-node (inode for short) is located. The inode contains information about the file, for example the file’s permissions, together with a pointer to the disk location or locations where the file’s data can be found. -

    Because we don’t get called when the file is opened or closed, there’s nowhere for +

    Because we don’t get called when the file is opened or closed, there’s nowhere for us to put try_module_get and try_module_put in this module, and if the file is opened and then the module is removed, there’s no way to avoid the consequences. -

    Here a simple example showing how to use a /proc file. This is the HelloWorld for +

    Here a simple example showing how to use a /proc file. This is the HelloWorld for the /proc filesystem. There are three parts: create the file /proc/helloworld in the function init_module , return a value (and a buffer) when the file /proc/helloworld is read in the callback @@ -1581,23 +1587,23 @@ function procfile_read , and delete the file /proc/helloworld in the function cleanup_module . -

    The /proc/helloworld is created when the module is loaded with the function +

    The /proc/helloworld is created when the module is loaded with the function proc_create . The return value is a struct proc_dir_entry , and it will be used to configure the file /proc/helloworld (for example, the owner of this file). A null return value means that the creation has failed. -

    Each time, everytime the file /proc/helloworld is read, the function +

    Each time, everytime the file /proc/helloworld is read, the function procfile_read is called. Two parameters of this function are very important: the buffer (the second parameter) and the offset (the fourth one). The content of the buffer will be returned to the application which read it (for example the -cat command). The offset is the current position in the file. If the return -value of the function is not null, then this function is called again. So be -careful with this function, if it never returns zero, the read function is called -endlessly. + cat + command). The offset is the current position in the file. If the return value of the +function is not null, then this function is called again. So be careful with this +function, if it never returns zero, the read function is called endlessly. @@ -1606,85 +1612,85 @@ endlessly. $ cat /proc/helloworld HelloWorld! -

    +

    - 
    1/* 
-2 * procfs1.c 
-3 */ 
-4 
-5#include <linux/kernel.h> 
-6#include <linux/module.h> 
-7#include <linux/proc_fs.h> 
-8#include <linux/uaccess.h> 
-9#include <linux/version.h> 
-10 
-11#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0) 
-12#define HAVE_PROC_OPS 
-13#endif 
-14 
-15#define procfs_name "helloworld" 
-16 
-17struct proc_dir_entry *Our_Proc_File; 
-18 
-19 
-20ssize_t procfile_read(struct file *filePointer, 
-21                      char *buffer, 
-22                      size_t buffer_length, 
-23                      loff_t *offset) 
-24{ 
-25    char s[13] = "HelloWorld!\n"; 
-26    int len = sizeof(s); 
-27    ssize_t ret = len; 
-28 
-29    if (*offset >= len || copy_to_user(buffer, s, len)) { 
-30        pr_info("copy_to_user failed\n"); 
-31        ret = 0; 
-32    } else { 
-33        pr_info("procfile read %s\n", filePointer->f_path.dentry->d_name.name); 
-34        *offset += len; 
-35    } 
-36 
-37    return ret; 
-38} 
-39 
-40#ifdef HAVE_PROC_OPS 
-41static const struct proc_ops proc_file_fops = { 
-42    .proc_read = procfile_read, 
-43}; 
-44#else 
-45static const struct file_operations proc_file_fops = { 
-46    .read = procfile_read, 
-47}; 
-48#endif 
-49 
-50static int __init procfs1_init(void) 
-51{ 
-52    Our_Proc_File = proc_create(procfs_name, 0644, NULL, &proc_file_fops); 
-53    if (NULL == Our_Proc_File) { 
-54        proc_remove(Our_Proc_File); 
-55        pr_alert("Error:Could not initialize /proc/%s\n", procfs_name); 
-56        return -ENOMEM; 
-57    } 
-58 
-59    pr_info("/proc/%s created\n", procfs_name); 
-60    return 0; 
-61} 
-62 
-63static void __exit procfs1_exit(void) 
-64{ 
-65    proc_remove(Our_Proc_File); 
-66    pr_info("/proc/%s removed\n", procfs_name); 
-67} 
-68 
-69module_init(procfs1_init); 
-70module_exit(procfs1_exit); 
-71 
-72MODULE_LICENSE("GPL");
    -

    + 

    1/* 
+2 * procfs1.c 
+3 */ 
+4 
+5#include <linux/kernel.h> 
+6#include <linux/module.h> 
+7#include <linux/proc_fs.h> 
+8#include <linux/uaccess.h> 
+9#include <linux/version.h> 
+10 
+11#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0) 
+12#define HAVE_PROC_OPS 
+13#endif 
+14 
+15#define procfs_name "helloworld" 
+16 
+17struct proc_dir_entry *Our_Proc_File; 
+18 
+19 
+20ssize_t procfile_read(struct file *filePointer, 
+21                      char *buffer, 
+22                      size_t buffer_length, 
+23                      loff_t *offset) 
+24{ 
+25    char s[13] = "HelloWorld!\n"; 
+26    int len = sizeof(s); 
+27    ssize_t ret = len; 
+28 
+29    if (*offset >= len || copy_to_user(buffer, s, len)) { 
+30        pr_info("copy_to_user failed\n"); 
+31        ret = 0; 
+32    } else { 
+33        pr_info("procfile read %s\n", filePointer->f_path.dentry->d_name.name); 
+34        *offset += len; 
+35    } 
+36 
+37    return ret; 
+38} 
+39 
+40#ifdef HAVE_PROC_OPS 
+41static const struct proc_ops proc_file_fops = { 
+42    .proc_read = procfile_read, 
+43}; 
+44#else 
+45static const struct file_operations proc_file_fops = { 
+46    .read = procfile_read, 
+47}; 
+48#endif 
+49 
+50static int __init procfs1_init(void) 
+51{ 
+52    Our_Proc_File = proc_create(procfs_name, 0644, NULL, &proc_file_fops); 
+53    if (NULL == Our_Proc_File) { 
+54        proc_remove(Our_Proc_File); 
+55        pr_alert("Error:Could not initialize /proc/%s\n", procfs_name); 
+56        return -ENOMEM; 
+57    } 
+58 
+59    pr_info("/proc/%s created\n", procfs_name); 
+60    return 0; 
+61} 
+62 
+63static void __exit procfs1_exit(void) 
+64{ 
+65    proc_remove(Our_Proc_File); 
+66    pr_info("/proc/%s removed\n", procfs_name); 
+67} 
+68 
+69module_init(procfs1_init); 
+70module_exit(procfs1_exit); 
+71 
+72MODULE_LICENSE("GPL");
    +

    0.7.1 The proc_ops Structure

    -

    The proc_ops +

    The proc_ops structure is defined in include/linux/proc_fs.h in Linux v5.6+. In older kernels, it used file_operations for custom hooks in /proc file system, but it contains some @@ -1696,10 +1702,10 @@ performance. For example, the file which never disappears in proc_flag as PROC_ENTRY_PERMANENT to save 2 atomic ops, 1 allocation, 1 free in per open/read/close sequence. -

    +

    0.7.2 Read and Write a /proc File

    -

    We have seen a very simple example for a /proc file where we only read +

    We have seen a very simple example for a /proc file where we only read the file /proc/helloworld. It is also possible to write in a /proc file. It works the same way as read, a function is called when the /proc file is written. But there is a little difference with read, data comes from @@ -1707,7 +1713,7 @@ user, so you have to import data from user space to kernel space (with copy_from_user or get_user ) -

    The reason for copy_from_user +

    The reason for copy_from_user or get_user is that Linux memory (on Intel architecture, it may be different under some @@ -1718,7 +1724,7 @@ not reference a unique location in memory, only a location in a memory segment, and you need to know which memory segment it is to be able to use it. There is one memory segment for the kernel, and one for each of the processes. -

    The only memory segment accessible to a process is its own, so when +

    The only memory segment accessible to a process is its own, so when writing regular programs to run as processes, there is no need to worry about segments. When you write a kernel module, normally you want to access the kernel memory segment, which is handled automatically by the system. @@ -1835,22 +1841,22 @@ because data is already in kernel space. 97module_exit(procfs2_exit); 98 99MODULE_LICENSE("GPL"); -

    +

    0.7.3 Manage /proc file with standard filesystem

    -

    We have seen how to read and write a /proc file with the /proc interface. But it is +

    We have seen how to read and write a /proc file with the /proc interface. But it is also possible to manage /proc file with inodes. The main concern is to use advanced functions, like permissions. -

    In Linux, there is a standard mechanism for file system registration. +

    In Linux, there is a standard mechanism for file system registration. Since every file system has to have its own functions to handle inode and file operations, there is a special structure to hold pointers to all those functions, struct inode_operations , which includes a pointer to struct proc_ops . -

    The difference between file and inode operations is that file operations deal with +

    The difference between file and inode operations is that file operations deal with the file itself whereas inode operations deal with ways of referencing the file, such as creating links to it. -

    In /proc, whenever we register a new file, we’re allowed to specify which +

    In /proc, whenever we register a new file, we’re allowed to specify which struct inode_operations will be used to access to it. This is the mechanism we use, a struct inode_operations @@ -1861,7 +1867,7 @@ creating links to it. which includes pointers to our procf_read and procfs_write functions. -

    Another interesting point here is the +

    Another interesting point here is the module_permission function. This function is called whenever a process tries to do something with the /proc file, and it can decide whether to allow access or not. Right now it is only @@ -1870,7 +1876,7 @@ pointer to a structure which includes information on the currently running process), but it could be based on anything we like, such as what other processes are doing with the same file, the time of day, or the last input we received. -

    It is important to note that the standard roles of read and write are reversed in +

    It is important to note that the standard roles of read and write are reversed in the kernel. Read functions are used for output, whereas write functions are used for input. The reason for that is that read and write refer to the user’s point of view — if a process reads something from the kernel, then the kernel needs to output it, and @@ -1985,21 +1991,21 @@ input. 105module_exit(procfs3_exit); 106 107MODULE_LICENSE("GPL"); -

    Still hungry for procfs examples? Well, first of all keep in mind, there are rumors +

    Still hungry for procfs examples? Well, first of all keep in mind, there are rumors around, claiming that procfs is on its way out, consider using sysfs instead. Consider using this mechanism, in case you want to document something kernel related yourself. -

    +

    0.7.4 Manage /proc file with seq_file

    -

    As we have seen, writing a /proc file may be quite “complex”. +

    As we have seen, writing a /proc file may be quite “complex”. So to help people writting /proc file, there is an API named seq_file - that helps formating a /proc file for output. It is based on sequence, + that helps formating a /proc file for output. It is based on sequence, which is composed of 3 functions: start(), next(), and stop(). The seq_file API starts a sequence when a user read the /proc file. -

    A sequence begins with the call of the function start(). If the return is a non +

    A sequence begins with the call of the function start(). If the return is a non NULL value, the function next() is called. This function is an iterator, the goal is to go through all the data. Each time next() is called, the function show() is also called. It writes data values in the buffer read by the user. The function next() is called until @@ -2008,7 +2014,7 @@ stop() is called. -

    BE CAREFUL: when a sequence is finished, another one starts. That means that +

    BE CAREFUL: when a sequence is finished, another one starts. That means that at the end of function stop(), the function start() is called again. This loop finishes when the function start() returns NULL. You can see a scheme of this in the Figure 1. @@ -2022,14 +2028,14 @@ Figure 1

    srYrsNNYtaeenetoooertusetupstrxr((ntn))( tis)istrr teeaNreNatUaUtmLtLmeLmLen?e?ntntt +

    srYrsNNYtaeenetoooertusetupstrxr((ntn))( tis)istrr teeaNreNatUaUtmLtLmeLmLen?e?ntntt

    Figure 1:How seq_file works
    -

    The seq_file +

    The seq_file provides basic functions for proc_ops , such as seq_read , seq_lseek @@ -2153,23 +2159,23 @@ the same way as in the previous example. 115module_exit(procfs4_exit); 116 117MODULE_LICENSE("GPL"); -

    If you want more information, you can read this web page: +

    If you want more information, you can read this web page:

    -

    You can also read the code of fs/seq_file.c in the linux kernel. +

    You can also read the code of fs/seq_file.c in the linux kernel.

    0.8 sysfs: Interacting with your module

    -

    sysfs allows you to interact with the running kernel from userspace by reading or +

    sysfs allows you to interact with the running kernel from userspace by reading or setting variables inside of modules. This can be useful for debugging purposes, or just as an interface for applications or scripts. You can find sysfs directories and files under the /sys directory on your system. 

    1ls -l /sys
    -

    An example of a hello world module which includes the creation of a variable +

    An example of a hello world module which includes the creation of a variable accessible via sysfs is given below.

    @@ -2238,7 +2244,7 @@ accessible via sysfs is given below. 63module_exit(mymodule_exit); 64 65MODULE_LICENSE("GPL"); -

    Make and install the module: +

    Make and install the module: 

    1make 
@@ -2246,36 +2252,36 @@ accessible via sysfs is given below.
                                                                   
 
                                                                   
-
       Check that it exists:
+
       Check that it exists:
 
    
 
    
    
    1sudo lsmod | grep hello_sysfs
    
-
       What is the current value of   myvariable
+
       What is the current value of   myvariable
  ?
 
    
 
    
    
    1cat /sys/kernel/mymodule/myvariable
    
-
       Set the value of   myvariable
+
       Set the value of   myvariable
  and check that it changed.
 
    
 
    
    
    1echo "32" > /sys/kernel/mymodule/myvariable 
 2cat /sys/kernel/mymodule/myvariable
    
-
       Finally, remove the test module:
+
       Finally, remove the test module:
 
    
 
    
    
    1sudo rmmod hello_sysfs
    
-
    
+
    
 
    
    
    0.9    Talking To Device Files
    
-
    Device files are supposed to represent physical devices. Most physical devices are
+
    Device files are supposed to represent physical devices. Most physical devices are
 used for output as well as input, so there has to be some mechanism for
 device drivers in the kernel to get the output to send to the device from
 processes. This is done by opening the device file for output and writing to it,
 just like writing to a file. In the following example, this is implemented by
  device_write
 .
-
       This is not always enough. Imagine you had a serial port connected to a modem
+
       This is not always enough. Imagine you had a serial port connected to a modem
 (even if you have an internal modem, it is still implemented from the CPU’s
 perspective as a serial port connected to a modem, so you don’t have to tax
 your imagination too hard). The natural thing to do would be to use the
@@ -2288,20 +2294,21 @@ received.
                                                                   
 
                                                                   
-
       The answer in Unix is to use a special function called
+
       The answer in Unix is to use a special function called
  ioctl
- (short for Input Output ConTroL). Every device can have its own ioctl commands,
-which can be read ioctl’s (to send information from a process to the kernel),
-write ioctl’s (to return information to a process), both or neither. Notice
+ (short for Input Output ConTroL). Every device can have its own
+ ioctl
+ commands, which can be read ioctl’s (to send information from a process to the
+kernel), write ioctl’s (to return information to a process), both or neither. Notice
 here the roles of read and write are reversed again, so in ioctl’s read is to
 send information to the kernel and write is to receive information from the
 kernel.
-
       The ioctl function is called with three parameters: the file descriptor of the
+
       The ioctl function is called with three parameters: the file descriptor of the
 appropriate device file, the ioctl number, and a parameter, which is of type
 long so you can use a cast to use it to pass anything. You will not be able
 to pass a structure this way, but you will be able to pass a pointer to the
 structure.
-
       The ioctl number encodes the major device number, the type of the ioctl, the
+
       The ioctl number encodes the major device number, the type of the ioctl, the
 command, and the type of the parameter. This ioctl number is usually created by a macro
 call (  _IO
 ,   _IOR
@@ -2312,504 +2319,504 @@ included both by the programs which will use ioctl (so they can generate the
 appropriate ioctl’s) and by the kernel module (so it can understand it). In the
 example below, the header file is chardev.h and the program which uses it is
 ioctl.c.
-
       If you want to use ioctls in your own kernel modules, it is best to receive an
+
       If you want to use ioctls in your own kernel modules, it is best to receive an
 official ioctl assignment, so if you accidentally get somebody else’s ioctls, or if they
 get yours, you’ll know something is wrong. For more information, consult the kernel
 source tree at Documentation/driver-api/ioctl.rst.
 
    
 
    
-   
    1/* 
-2 * chardev2.c - Create an input/output character device 
-3 */ 
-4 
-5#include <linux/cdev.h> 
-6#include <linux/delay.h> 
-7#include <linux/device.h> 
-8#include <linux/fs.h> 
-9#include <linux/init.h> 
-10#include <linux/irq.h> 
-11#include <linux/kernel.h> /* We are doing kernel work */ 
-12#include <linux/module.h> /* Specifically, a module */ 
-13#include <linux/poll.h> 
-14 
-15#include "chardev.h" 
-16#define SUCCESS 0 
-17#define DEVICE_NAME "char_dev" 
-18#define BUF_LEN 80 
-19 
-20/* Is the device open right now? Used to prevent concurent access into 
-21 * the same device 
-22 */ 
-23static int Device_Open = 0; 
-24 
-25/* The message the device will give when asked */ 
-26static char Message[BUF_LEN]; 
-27 
-28/* How far did the process reading the message get? Useful if the message 
-29 * is larger than the size of the buffer we get to fill in device_read. 
-30 */ 
-31static char *Message_Ptr; 
-32 
-33/* Major number assigned to our device driver */ 
-34static int Major; 
-35static struct class *cls; 
-36 
-37/* This is called whenever a process attempts to open the device file */ 
-38static int device_open(struct inode *inode, struct file *file) 
-39{ 
-40    pr_info("device_open(%p)\n", file); 
-41 
-42    /* We don't want to talk to two processes at the same time. */ 
-43    if (Device_Open) 
-44        return -EBUSY; 
-45 
-46    Device_Open++; 
-47    /* Initialize the message */ 
-48    Message_Ptr = Message; 
-49    try_module_get(THIS_MODULE); 
-50    return SUCCESS; 
-51} 
-52 
-53static int device_release(struct inode *inode, struct file *file) 
-54{ 
-55    pr_info("device_release(%p,%p)\n", inode, file); 
-56 
-57    /* We're now ready for our next caller */ 
-58    Device_Open--; 
-59 
-60    module_put(THIS_MODULE); 
-61    return SUCCESS; 
-62} 
-63 
-64/* This function is called whenever a process which has already opened the 
-65 * device file attempts to read from it. 
-66 */ 
-67static ssize_t device_read(struct file *file,   /* see include/linux/fs.h   */ 
-68                           char __user *buffer, /* buffer to be filled  */ 
-69                           size_t length,       /* length of the buffer     */ 
-70                           loff_t *offset) 
-71{ 
-72    /* Number of bytes actually written to the buffer */ 
-73    int bytes_read = 0; 
-74 
-75    pr_info("device_read(%p,%p,%ld)\n", file, buffer, length); 
-76 
-77    /* If at the end of message, return 0 (which signifies end of file). */ 
-78    if (*Message_Ptr == 0) 
-79        return 0; 
-80 
-81    /* Actually put the data into the buffer */ 
-82    while (length && *Message_Ptr) { 
-83        /* Because the buffer is in the user data segment, not the kernel 
-84         * data segment, assignment would not work. Instead, we have to 
-85         * use put_user which copies data from the kernel data segment to 
-86         * the user data segment. 
-87         */ 
-88        put_user(*(Message_Ptr++), buffer++); 
-89        length--; 
-90        bytes_read++; 
-91    } 
-92 
-93    pr_info("Read %d bytes, %ld left\n", bytes_read, length); 
-94 
-95    /* Read functions are supposed to return the number of bytes actually 
-96     * inserted into the buffer. 
-97     */ 
-98    return bytes_read; 
-99} 
-100 
-101/* called when somebody tries to write into our device file. */ 
-102static ssize_t device_write(struct file *file, 
-103                            const char __user *buffer, 
-104                            size_t length, 
-105                            loff_t *offset) 
-106{ 
-107    int i; 
-108 
-109    pr_info("device_write(%p,%s,%ld)", file, buffer, length); 
-110 
-111    for (i = 0; i < length && i < BUF_LEN; i++) 
-112        get_user(Message[i], buffer + i); 
-113 
-114    Message_Ptr = Message; 
-115 
-116    /* Again, return the number of input characters used. */ 
-117    return i; 
-118} 
-119 
-120/* This function is called whenever a process tries to do an ioctl on our 
-121 * device file. We get two extra parameters (additional to the inode and file 
-122 * structures, which all device functions get): the number of the ioctl called 
-123 * and the parameter given to the ioctl function. 
-124 * 
-125 * If the ioctl is write or read/write (meaning output is returned to the 
-126 * calling process), the ioctl call returns the output of this function. 
-127 */ 
-128long device_ioctl(struct file *file,      /* ditto */ 
-129                  unsigned int ioctl_num, /* number and param for ioctl */ 
-130                  unsigned long ioctl_param) 
-131{ 
-132    int i; 
-133    char *temp; 
-134    char ch; 
-135 
-136    /* Switch according to the ioctl called */ 
-137    switch (ioctl_num) { 
-138    case IOCTL_SET_MSG: 
-139        /* Receive a pointer to a message (in user space) and set that to 
-140         * be the device's message.  Get the parameter given to ioctl by 
-141         * the process. 
-142         */ 
-143        temp = (char *) ioctl_param; 
-144 
-145        /* Find the length of the message */ 
-146        get_user(ch, temp); 
-147        for (i = 0; ch && i < BUF_LEN; i++, temp++) 
-148            get_user(ch, temp); 
-149 
-150        device_write(file, (char *) ioctl_param, i, 0); 
-151        break; 
-152 
-153    case IOCTL_GET_MSG: 
-154        /* Give the current message to the calling process - the parameter 
-155         * we got is a pointer, fill it. 
-156         */ 
-157        i = device_read(file, (char *) ioctl_param, 99, 0); 
-158 
-159        /* Put a zero at the end of the buffer, so it will be properly 
-160         * terminated. 
-161         */ 
-162        put_user('\0', (char *) ioctl_param + i); 
-163        break; 
-164 
-165    case IOCTL_GET_NTH_BYTE: 
-166        /* This ioctl is both input (ioctl_param) and output (the return 
-167         * value of this function). 
-168         */ 
-169        return Message[ioctl_param]; 
-170        break; 
-171    } 
-172 
-173    return SUCCESS; 
-174} 
-175 
-176/* Module Declarations */ 
-177 
-178/* This structure will hold the functions to be called when a process does 
-179 * something to the device we created. Since a pointer to this structure 
-180 * is kept in the devices table, it can't be local to init_module. NULL is 
-181 * for unimplemented functions. 
-182 */ 
-183struct file_operations Fops = { 
-184    .read = device_read, 
-185    .write = device_write, 
-186    .unlocked_ioctl = device_ioctl, 
-187    .open = device_open, 
-188    .release = device_release, /* a.k.a. close */ 
-189}; 
-190 
-191/* Initialize the module - Register the character device */ 
-192static int __init chardev2_init(void) 
-193{ 
-194    /* Register the character device (atleast try) */ 
-195    int ret_val = register_chrdev(MAJOR_NUM, DEVICE_NAME, &Fops); 
-196 
-197    /* Negative values signify an error */ 
-198    if (ret_val < 0) { 
-199        pr_alert("%s failed with %d\n", 
-200                 "Sorry, registering the character device ", ret_val); 
-201        return ret_val; 
-202    } 
-203 
-204    Major = ret_val; 
-205 
-206    cls = class_create(THIS_MODULE, DEVICE_FILE_NAME); 
-207    device_create(cls, NULL, MKDEV(Major, MAJOR_NUM), NULL, DEVICE_FILE_NAME); 
-208 
-209    pr_info("Device created on /dev/%s\n", DEVICE_FILE_NAME); 
-210 
-211    return 0; 
-212} 
-213 
-214/* Cleanup - unregister the appropriate file from /proc */ 
-215static void __exit chardev2_exit(void) 
-216{ 
-217    device_destroy(cls, MKDEV(Major, 0)); 
-218    class_destroy(cls); 
-219 
-220    /* Unregister the device */ 
-221    unregister_chrdev(Major, DEVICE_NAME); 
-222} 
-223 
-224module_init(chardev2_init); 
-225module_exit(chardev2_exit); 
-226 
-227MODULE_LICENSE("GPL");
    
+   
    1/* 
+2 * chardev2.c - Create an input/output character device 
+3 */ 
+4 
+5#include <linux/cdev.h> 
+6#include <linux/delay.h> 
+7#include <linux/device.h> 
+8#include <linux/fs.h> 
+9#include <linux/init.h> 
+10#include <linux/irq.h> 
+11#include <linux/kernel.h> /* We are doing kernel work */ 
+12#include <linux/module.h> /* Specifically, a module */ 
+13#include <linux/poll.h> 
+14 
+15#include "chardev.h" 
+16#define SUCCESS 0 
+17#define DEVICE_NAME "char_dev" 
+18#define BUF_LEN 80 
+19 
+20/* Is the device open right now? Used to prevent concurent access into 
+21 * the same device 
+22 */ 
+23static int Device_Open = 0; 
+24 
+25/* The message the device will give when asked */ 
+26static char Message[BUF_LEN]; 
+27 
+28/* How far did the process reading the message get? Useful if the message 
+29 * is larger than the size of the buffer we get to fill in device_read. 
+30 */ 
+31static char *Message_Ptr; 
+32 
+33/* Major number assigned to our device driver */ 
+34static int Major; 
+35static struct class *cls; 
+36 
+37/* This is called whenever a process attempts to open the device file */ 
+38static int device_open(struct inode *inode, struct file *file) 
+39{ 
+40    pr_info("device_open(%p)\n", file); 
+41 
+42    /* We don't want to talk to two processes at the same time. */ 
+43    if (Device_Open) 
+44        return -EBUSY; 
+45 
+46    Device_Open++; 
+47    /* Initialize the message */ 
+48    Message_Ptr = Message; 
+49    try_module_get(THIS_MODULE); 
+50    return SUCCESS; 
+51} 
+52 
+53static int device_release(struct inode *inode, struct file *file) 
+54{ 
+55    pr_info("device_release(%p,%p)\n", inode, file); 
+56 
+57    /* We're now ready for our next caller */ 
+58    Device_Open--; 
+59 
+60    module_put(THIS_MODULE); 
+61    return SUCCESS; 
+62} 
+63 
+64/* This function is called whenever a process which has already opened the 
+65 * device file attempts to read from it. 
+66 */ 
+67static ssize_t device_read(struct file *file,   /* see include/linux/fs.h   */ 
+68                           char __user *buffer, /* buffer to be filled  */ 
+69                           size_t length,       /* length of the buffer     */ 
+70                           loff_t *offset) 
+71{ 
+72    /* Number of bytes actually written to the buffer */ 
+73    int bytes_read = 0; 
+74 
+75    pr_info("device_read(%p,%p,%ld)\n", file, buffer, length); 
+76 
+77    /* If at the end of message, return 0 (which signifies end of file). */ 
+78    if (*Message_Ptr == 0) 
+79        return 0; 
+80 
+81    /* Actually put the data into the buffer */ 
+82    while (length && *Message_Ptr) { 
+83        /* Because the buffer is in the user data segment, not the kernel 
+84         * data segment, assignment would not work. Instead, we have to 
+85         * use put_user which copies data from the kernel data segment to 
+86         * the user data segment. 
+87         */ 
+88        put_user(*(Message_Ptr++), buffer++); 
+89        length--; 
+90        bytes_read++; 
+91    } 
+92 
+93    pr_info("Read %d bytes, %ld left\n", bytes_read, length); 
+94 
+95    /* Read functions are supposed to return the number of bytes actually 
+96     * inserted into the buffer. 
+97     */ 
+98    return bytes_read; 
+99} 
+100 
+101/* called when somebody tries to write into our device file. */ 
+102static ssize_t device_write(struct file *file, 
+103                            const char __user *buffer, 
+104                            size_t length, 
+105                            loff_t *offset) 
+106{ 
+107    int i; 
+108 
+109    pr_info("device_write(%p,%s,%ld)", file, buffer, length); 
+110 
+111    for (i = 0; i < length && i < BUF_LEN; i++) 
+112        get_user(Message[i], buffer + i); 
+113 
+114    Message_Ptr = Message; 
+115 
+116    /* Again, return the number of input characters used. */ 
+117    return i; 
+118} 
+119 
+120/* This function is called whenever a process tries to do an ioctl on our 
+121 * device file. We get two extra parameters (additional to the inode and file 
+122 * structures, which all device functions get): the number of the ioctl called 
+123 * and the parameter given to the ioctl function. 
+124 * 
+125 * If the ioctl is write or read/write (meaning output is returned to the 
+126 * calling process), the ioctl call returns the output of this function. 
+127 */ 
+128long device_ioctl(struct file *file,      /* ditto */ 
+129                  unsigned int ioctl_num, /* number and param for ioctl */ 
+130                  unsigned long ioctl_param) 
+131{ 
+132    int i; 
+133    char *temp; 
+134    char ch; 
+135 
+136    /* Switch according to the ioctl called */ 
+137    switch (ioctl_num) { 
+138    case IOCTL_SET_MSG: 
+139        /* Receive a pointer to a message (in user space) and set that to 
+140         * be the device's message.  Get the parameter given to ioctl by 
+141         * the process. 
+142         */ 
+143        temp = (char *) ioctl_param; 
+144 
+145        /* Find the length of the message */ 
+146        get_user(ch, temp); 
+147        for (i = 0; ch && i < BUF_LEN; i++, temp++) 
+148            get_user(ch, temp); 
+149 
+150        device_write(file, (char *) ioctl_param, i, 0); 
+151        break; 
+152 
+153    case IOCTL_GET_MSG: 
+154        /* Give the current message to the calling process - the parameter 
+155         * we got is a pointer, fill it. 
+156         */ 
+157        i = device_read(file, (char *) ioctl_param, 99, 0); 
+158 
+159        /* Put a zero at the end of the buffer, so it will be properly 
+160         * terminated. 
+161         */ 
+162        put_user('\0', (char *) ioctl_param + i); 
+163        break; 
+164 
+165    case IOCTL_GET_NTH_BYTE: 
+166        /* This ioctl is both input (ioctl_param) and output (the return 
+167         * value of this function). 
+168         */ 
+169        return Message[ioctl_param]; 
+170        break; 
+171    } 
+172 
+173    return SUCCESS; 
+174} 
+175 
+176/* Module Declarations */ 
+177 
+178/* This structure will hold the functions to be called when a process does 
+179 * something to the device we created. Since a pointer to this structure 
+180 * is kept in the devices table, it can't be local to init_module. NULL is 
+181 * for unimplemented functions. 
+182 */ 
+183struct file_operations Fops = { 
+184    .read = device_read, 
+185    .write = device_write, 
+186    .unlocked_ioctl = device_ioctl, 
+187    .open = device_open, 
+188    .release = device_release, /* a.k.a. close */ 
+189}; 
+190 
+191/* Initialize the module - Register the character device */ 
+192static int __init chardev2_init(void) 
+193{ 
+194    /* Register the character device (atleast try) */ 
+195    int ret_val = register_chrdev(MAJOR_NUM, DEVICE_NAME, &Fops); 
+196 
+197    /* Negative values signify an error */ 
+198    if (ret_val < 0) { 
+199        pr_alert("%s failed with %d\n", 
+200                 "Sorry, registering the character device ", ret_val); 
+201        return ret_val; 
+202    } 
+203 
+204    Major = ret_val; 
+205 
+206    cls = class_create(THIS_MODULE, DEVICE_FILE_NAME); 
+207    device_create(cls, NULL, MKDEV(Major, MAJOR_NUM), NULL, DEVICE_FILE_NAME); 
+208 
+209    pr_info("Device created on /dev/%s\n", DEVICE_FILE_NAME); 
+210 
+211    return 0; 
+212} 
+213 
+214/* Cleanup - unregister the appropriate file from /proc */ 
+215static void __exit chardev2_exit(void) 
+216{ 
+217    device_destroy(cls, MKDEV(Major, 0)); 
+218    class_destroy(cls); 
+219 
+220    /* Unregister the device */ 
+221    unregister_chrdev(Major, DEVICE_NAME); 
+222} 
+223 
+224module_init(chardev2_init); 
+225module_exit(chardev2_exit); 
+226 
+227MODULE_LICENSE("GPL");
    
 
 
    
 
    
-   
    1/* 
-2 * chardev.h - the header file with the ioctl definitions. 
-3 * 
-4 * The declarations here have to be in a header file, because they need 
-5 * to be known both to the kernel module (in chardev.c) and the process 
-6 * calling ioctl (ioctl.c). 
-7 */ 
-8 
-9#ifndef CHARDEV_H 
-10#define CHARDEV_H 
-11 
-12#include <linux/ioctl.h> 
-13 
-14/* The major device number. We can not rely on dynamic registration 
-15 * any more, because ioctls need to know it. 
-16 */ 
-17#define MAJOR_NUM 100 
-18 
-19/* Set the message of the device driver */ 
-20#define IOCTL_SET_MSG _IOW(MAJOR_NUM, 0, char *) 
-21/* _IOW means that we are creating an ioctl command number for passing 
-22 * information from a user process to the kernel module. 
-23 * 
-24 * The first arguments, MAJOR_NUM, is the major device number we are using. 
-25 * 
-26 * The second argument is the number of the command (there could be several 
-27 * with different meanings). 
-28 * 
-29 * The third argument is the type we want to get from the process to the 
-30 * kernel. 
-31 */ 
-32 
-33/* Get the message of the device driver */ 
-34#define IOCTL_GET_MSG _IOR(MAJOR_NUM, 1, char *) 
-35/* This IOCTL is used for output, to get the message of the device driver. 
-36 * However, we still need the buffer to place the message in to be input, 
-37 * as it is allocated by the process. 
-38 */ 
-39 
-40/* Get the n'th byte of the message */ 
-41#define IOCTL_GET_NTH_BYTE _IOWR(MAJOR_NUM, 2, int) 
-42/* The IOCTL is used for both input and output. It receives from the user 
-43 * a number, n, and returns Message[n]. 
-44 */ 
-45 
-46/* The name of the device file */ 
-47#define DEVICE_FILE_NAME "char_dev" 
-48 
-49#endif
    
+   
    1/* 
+2 * chardev.h - the header file with the ioctl definitions. 
+3 * 
+4 * The declarations here have to be in a header file, because they need 
+5 * to be known both to the kernel module (in chardev.c) and the process 
+6 * calling ioctl (ioctl.c). 
+7 */ 
+8 
+9#ifndef CHARDEV_H 
+10#define CHARDEV_H 
+11 
+12#include <linux/ioctl.h> 
+13 
+14/* The major device number. We can not rely on dynamic registration 
+15 * any more, because ioctls need to know it. 
+16 */ 
+17#define MAJOR_NUM 100 
+18 
+19/* Set the message of the device driver */ 
+20#define IOCTL_SET_MSG _IOW(MAJOR_NUM, 0, char *) 
+21/* _IOW means that we are creating an ioctl command number for passing 
+22 * information from a user process to the kernel module. 
+23 * 
+24 * The first arguments, MAJOR_NUM, is the major device number we are using. 
+25 * 
+26 * The second argument is the number of the command (there could be several 
+27 * with different meanings). 
+28 * 
+29 * The third argument is the type we want to get from the process to the 
+30 * kernel. 
+31 */ 
+32 
+33/* Get the message of the device driver */ 
+34#define IOCTL_GET_MSG _IOR(MAJOR_NUM, 1, char *) 
+35/* This IOCTL is used for output, to get the message of the device driver. 
+36 * However, we still need the buffer to place the message in to be input, 
+37 * as it is allocated by the process. 
+38 */ 
+39 
+40/* Get the n'th byte of the message */ 
+41#define IOCTL_GET_NTH_BYTE _IOWR(MAJOR_NUM, 2, int) 
+42/* The IOCTL is used for both input and output. It receives from the user 
+43 * a number, n, and returns Message[n]. 
+44 */ 
+45 
+46/* The name of the device file */ 
+47#define DEVICE_FILE_NAME "char_dev" 
+48 
+49#endif
    
 
 
    
 
    
-   
    1/* 
-2 * ioctl.c 
-3 */ 
-4#include <linux/cdev.h> 
-5#include <linux/fs.h> 
-6#include <linux/init.h> 
-7#include <linux/ioctl.h> 
-8#include <linux/module.h> 
-9#include <linux/slab.h> 
-10#include <linux/uaccess.h> 
-11 
-12struct ioctl_arg { 
-13    unsigned int reg; 
-14    unsigned int val; 
-15}; 
-16 
-17/* Documentation/ioctl/ioctl-number.txt */ 
-18#define IOC_MAGIC '\x66' 
-19 
-20#define IOCTL_VALSET _IOW(IOC_MAGIC, 0, struct ioctl_arg) 
-21#define IOCTL_VALGET _IOR(IOC_MAGIC, 1, struct ioctl_arg) 
-22#define IOCTL_VALGET_NUM _IOR(IOC_MAGIC, 2, int) 
-23#define IOCTL_VALSET_NUM _IOW(IOC_MAGIC, 3, int) 
-24 
-25#define IOCTL_VAL_MAXNR 3 
-26#define DRIVER_NAME "ioctltest" 
-27 
-28static unsigned int test_ioctl_major = 0; 
-29static unsigned int num_of_dev = 1; 
-30static struct cdev test_ioctl_cdev; 
-31static int ioctl_num = 0; 
-32 
-33struct test_ioctl_data { 
-34    unsigned char val; 
-35    rwlock_t lock; 
-36}; 
-37 
-38static long test_ioctl_ioctl(struct file *filp, 
-39                             unsigned int cmd, 
-40                             unsigned long arg) 
-41{ 
-42    struct test_ioctl_data *ioctl_data = filp->private_data; 
-43    int retval = 0; 
-44    unsigned char val; 
-45    struct ioctl_arg data; 
-46    memset(&data, 0, sizeof(data)); 
-47 
-48    switch (cmd) { 
-49    case IOCTL_VALSET: 
-50        if (copy_from_user(&data, (int __user *) arg, sizeof(data))) { 
-51            retval = -EFAULT; 
-52            goto done; 
-53        } 
-54 
-55        pr_alert("IOCTL set val:%x .\n", data.val); 
-56        write_lock(&ioctl_data->lock); 
-57        ioctl_data->val = data.val; 
-58        write_unlock(&ioctl_data->lock); 
-59        break; 
-60 
-61    case IOCTL_VALGET: 
-62        read_lock(&ioctl_data->lock); 
-63        val = ioctl_data->val; 
-64        read_unlock(&ioctl_data->lock); 
-65        data.val = val; 
-66 
-67        if (copy_to_user((int __user *) arg, &data, sizeof(data))) { 
-68            retval = -EFAULT; 
-69            goto done; 
-70        } 
-71 
-72        break; 
-73 
-74    case IOCTL_VALGET_NUM: 
-75        retval = __put_user(ioctl_num, (int __user *) arg); 
-76        break; 
-77 
-78    case IOCTL_VALSET_NUM: 
-79        ioctl_num = arg; 
-80        break; 
-81 
-82    default: 
-83        retval = -ENOTTY; 
-84    } 
-85 
-86done: 
-87    return retval; 
-88} 
-89 
-90ssize_t test_ioctl_read(struct file *filp, 
-91                        char __user *buf, 
-92                        size_t count, 
-93                        loff_t *f_pos) 
-94{ 
-95    struct test_ioctl_data *ioctl_data = filp->private_data; 
-96    unsigned char val; 
-97    int retval; 
-98    int i = 0; 
-99    read_lock(&ioctl_data->lock); 
-100    val = ioctl_data->val; 
-101    read_unlock(&ioctl_data->lock); 
-102 
-103    for (; i < count; i++) { 
-104        if (copy_to_user(&buf[i], &val, 1)) { 
-105            retval = -EFAULT; 
-106            goto out; 
-107        } 
-108    } 
-109 
-110    retval = count; 
-111out: 
-112    return retval; 
-113} 
-114 
-115static int test_ioctl_close(struct inode *inode, struct file *filp) 
-116{ 
-117    pr_alert("%s call.\n", __func__); 
-118 
-119    if (filp->private_data) { 
-120        kfree(filp->private_data); 
-121        filp->private_data = NULL; 
-122    } 
-123 
-124    return 0; 
-125} 
-126 
-127static int test_ioctl_open(struct inode *inode, struct file *filp) 
-128{ 
-129    struct test_ioctl_data *ioctl_data; 
-130    pr_alert("%s call.\n", __func__); 
-131    ioctl_data = kmalloc(sizeof(struct test_ioctl_data), GFP_KERNEL); 
-132 
-133    if (ioctl_data == NULL) { 
-134        return -ENOMEM; 
-135    } 
-136 
-137    rwlock_init(&ioctl_data->lock); 
-138    ioctl_data->val = 0xFF; 
-139    filp->private_data = ioctl_data; 
-140    return 0; 
-141} 
-142 
-143struct file_operations fops = { 
-144    .owner = THIS_MODULE, 
-145    .open = test_ioctl_open, 
-146    .release = test_ioctl_close, 
-147    .read = test_ioctl_read, 
-148    .unlocked_ioctl = test_ioctl_ioctl, 
-149}; 
-150 
-151static int ioctl_init(void) 
-152{ 
-153    dev_t dev = MKDEV(test_ioctl_major, 0); 
-154    int alloc_ret = 0; 
-155    int cdev_ret = 0; 
-156    alloc_ret = alloc_chrdev_region(&dev, 0, num_of_dev, DRIVER_NAME); 
-157 
-158    if (alloc_ret) { 
-159        goto error; 
-160    } 
-161 
-162    test_ioctl_major = MAJOR(dev); 
-163    cdev_init(&test_ioctl_cdev, &fops); 
-164    cdev_ret = cdev_add(&test_ioctl_cdev, dev, num_of_dev); 
-165 
-166    if (cdev_ret) { 
-167        goto error; 
-168    } 
-169 
-170    pr_alert("%s driver(major: %d) installed.\n", DRIVER_NAME, 
-171             test_ioctl_major); 
-172    return 0; 
-173error: 
-174 
-175    if (cdev_ret == 0) { 
-176        cdev_del(&test_ioctl_cdev); 
-177    } 
-178 
-179    if (alloc_ret == 0) { 
-180        unregister_chrdev_region(dev, num_of_dev); 
-181    } 
-182 
-183    return -1; 
-184} 
-185 
-186static void ioctl_exit(void) 
-187{ 
-188    dev_t dev = MKDEV(test_ioctl_major, 0); 
-189    cdev_del(&test_ioctl_cdev); 
-190    unregister_chrdev_region(dev, num_of_dev); 
-191    pr_alert("%s driver removed.\n", DRIVER_NAME); 
-192} 
-193 
-194module_init(ioctl_init); 
-195module_exit(ioctl_exit); 
-196 
-197MODULE_LICENSE("GPL"); 
-198MODULE_DESCRIPTION("This is test_ioctl module");
    
-
    
+   
    1/* 
+2 * ioctl.c 
+3 */ 
+4#include <linux/cdev.h> 
+5#include <linux/fs.h> 
+6#include <linux/init.h> 
+7#include <linux/ioctl.h> 
+8#include <linux/module.h> 
+9#include <linux/slab.h> 
+10#include <linux/uaccess.h> 
+11 
+12struct ioctl_arg { 
+13    unsigned int reg; 
+14    unsigned int val; 
+15}; 
+16 
+17/* Documentation/ioctl/ioctl-number.txt */ 
+18#define IOC_MAGIC '\x66' 
+19 
+20#define IOCTL_VALSET _IOW(IOC_MAGIC, 0, struct ioctl_arg) 
+21#define IOCTL_VALGET _IOR(IOC_MAGIC, 1, struct ioctl_arg) 
+22#define IOCTL_VALGET_NUM _IOR(IOC_MAGIC, 2, int) 
+23#define IOCTL_VALSET_NUM _IOW(IOC_MAGIC, 3, int) 
+24 
+25#define IOCTL_VAL_MAXNR 3 
+26#define DRIVER_NAME "ioctltest" 
+27 
+28static unsigned int test_ioctl_major = 0; 
+29static unsigned int num_of_dev = 1; 
+30static struct cdev test_ioctl_cdev; 
+31static int ioctl_num = 0; 
+32 
+33struct test_ioctl_data { 
+34    unsigned char val; 
+35    rwlock_t lock; 
+36}; 
+37 
+38static long test_ioctl_ioctl(struct file *filp, 
+39                             unsigned int cmd, 
+40                             unsigned long arg) 
+41{ 
+42    struct test_ioctl_data *ioctl_data = filp->private_data; 
+43    int retval = 0; 
+44    unsigned char val; 
+45    struct ioctl_arg data; 
+46    memset(&data, 0, sizeof(data)); 
+47 
+48    switch (cmd) { 
+49    case IOCTL_VALSET: 
+50        if (copy_from_user(&data, (int __user *) arg, sizeof(data))) { 
+51            retval = -EFAULT; 
+52            goto done; 
+53        } 
+54 
+55        pr_alert("IOCTL set val:%x .\n", data.val); 
+56        write_lock(&ioctl_data->lock); 
+57        ioctl_data->val = data.val; 
+58        write_unlock(&ioctl_data->lock); 
+59        break; 
+60 
+61    case IOCTL_VALGET: 
+62        read_lock(&ioctl_data->lock); 
+63        val = ioctl_data->val; 
+64        read_unlock(&ioctl_data->lock); 
+65        data.val = val; 
+66 
+67        if (copy_to_user((int __user *) arg, &data, sizeof(data))) { 
+68            retval = -EFAULT; 
+69            goto done; 
+70        } 
+71 
+72        break; 
+73 
+74    case IOCTL_VALGET_NUM: 
+75        retval = __put_user(ioctl_num, (int __user *) arg); 
+76        break; 
+77 
+78    case IOCTL_VALSET_NUM: 
+79        ioctl_num = arg; 
+80        break; 
+81 
+82    default: 
+83        retval = -ENOTTY; 
+84    } 
+85 
+86done: 
+87    return retval; 
+88} 
+89 
+90ssize_t test_ioctl_read(struct file *filp, 
+91                        char __user *buf, 
+92                        size_t count, 
+93                        loff_t *f_pos) 
+94{ 
+95    struct test_ioctl_data *ioctl_data = filp->private_data; 
+96    unsigned char val; 
+97    int retval; 
+98    int i = 0; 
+99    read_lock(&ioctl_data->lock); 
+100    val = ioctl_data->val; 
+101    read_unlock(&ioctl_data->lock); 
+102 
+103    for (; i < count; i++) { 
+104        if (copy_to_user(&buf[i], &val, 1)) { 
+105            retval = -EFAULT; 
+106            goto out; 
+107        } 
+108    } 
+109 
+110    retval = count; 
+111out: 
+112    return retval; 
+113} 
+114 
+115static int test_ioctl_close(struct inode *inode, struct file *filp) 
+116{ 
+117    pr_alert("%s call.\n", __func__); 
+118 
+119    if (filp->private_data) { 
+120        kfree(filp->private_data); 
+121        filp->private_data = NULL; 
+122    } 
+123 
+124    return 0; 
+125} 
+126 
+127static int test_ioctl_open(struct inode *inode, struct file *filp) 
+128{ 
+129    struct test_ioctl_data *ioctl_data; 
+130    pr_alert("%s call.\n", __func__); 
+131    ioctl_data = kmalloc(sizeof(struct test_ioctl_data), GFP_KERNEL); 
+132 
+133    if (ioctl_data == NULL) { 
+134        return -ENOMEM; 
+135    } 
+136 
+137    rwlock_init(&ioctl_data->lock); 
+138    ioctl_data->val = 0xFF; 
+139    filp->private_data = ioctl_data; 
+140    return 0; 
+141} 
+142 
+143struct file_operations fops = { 
+144    .owner = THIS_MODULE, 
+145    .open = test_ioctl_open, 
+146    .release = test_ioctl_close, 
+147    .read = test_ioctl_read, 
+148    .unlocked_ioctl = test_ioctl_ioctl, 
+149}; 
+150 
+151static int ioctl_init(void) 
+152{ 
+153    dev_t dev = MKDEV(test_ioctl_major, 0); 
+154    int alloc_ret = 0; 
+155    int cdev_ret = 0; 
+156    alloc_ret = alloc_chrdev_region(&dev, 0, num_of_dev, DRIVER_NAME); 
+157 
+158    if (alloc_ret) { 
+159        goto error; 
+160    } 
+161 
+162    test_ioctl_major = MAJOR(dev); 
+163    cdev_init(&test_ioctl_cdev, &fops); 
+164    cdev_ret = cdev_add(&test_ioctl_cdev, dev, num_of_dev); 
+165 
+166    if (cdev_ret) { 
+167        goto error; 
+168    } 
+169 
+170    pr_alert("%s driver(major: %d) installed.\n", DRIVER_NAME, 
+171             test_ioctl_major); 
+172    return 0; 
+173error: 
+174 
+175    if (cdev_ret == 0) { 
+176        cdev_del(&test_ioctl_cdev); 
+177    } 
+178 
+179    if (alloc_ret == 0) { 
+180        unregister_chrdev_region(dev, num_of_dev); 
+181    } 
+182 
+183    return -1; 
+184} 
+185 
+186static void ioctl_exit(void) 
+187{ 
+188    dev_t dev = MKDEV(test_ioctl_major, 0); 
+189    cdev_del(&test_ioctl_cdev); 
+190    unregister_chrdev_region(dev, num_of_dev); 
+191    pr_alert("%s driver removed.\n", DRIVER_NAME); 
+192} 
+193 
+194module_init(ioctl_init); 
+195module_exit(ioctl_exit); 
+196 
+197MODULE_LICENSE("GPL"); 
+198MODULE_DESCRIPTION("This is test_ioctl module");
    
+
    
 
    
                                                                   
 
                                                                   
    
    0.10    System Calls
    
-
    So far, the only thing we’ve done was to use well defined kernel mechanisms to
+
    So far, the only thing we’ve done was to use well defined kernel mechanisms to
 register /proc files and device handlers. This is fine if you want to do something the
 kernel programmers thought you’d want, such as write a device driver. But what if
 you want to do something unusual, to change the behavior of the system in some
 way? Then, you are mostly on your own.
-
       If you are not being sensible and using a virtual machine then this is where kernel
+
       If you are not being sensible and using a virtual machine then this is where kernel
 programming can become hazardous. While writing the example below, I killed the
  open()
  system call. This meant I could not open any files, I could not run any
@@ -2821,7 +2828,7 @@ ensure you do not lose any files, even within a test environment, please run
  right before you do the   insmod
  and the   rmmod
 .
-
       Forget about /proc files, forget about device files. They are just minor details.
+
       Forget about /proc files, forget about device files. They are just minor details.
 Minutiae in the vast expanse of the universe. The real process to kernel
 communication mechanism, the one used by all processes, is system calls. When a
 process requests a service from the kernel (such as opening a file, forking to a new
@@ -2830,11 +2837,11 @@ change the behaviour of the kernel in interesting ways, this is the place to do
 it. By the way, if you want to see which system calls a program uses, run
  strace <arguments>
 .
-
       In general, a process is not supposed to be able to access the kernel. It can not
+
       In general, a process is not supposed to be able to access the kernel. It can not
 access kernel memory and it can’t call kernel functions. The hardware of the CPU
 enforces this (that is the reason why it is called “protected mode” or “page
 protection”).
-
       System calls are an exception to this general rule. What happens is that the
+
       System calls are an exception to this general rule. What happens is that the
 process fills the registers with the appropriate values and then calls a special
 instruction which jumps to a previously defined location in the kernel (of course, that
 location is readable by user processes, it is not writable by them). Under Intel CPUs,
@@ -2842,7 +2849,7 @@ this is done by means of interrupt 0x80. The hardware knows that once you jump t
 this location, you are no longer running in restricted user mode, but as the
 operating system kernel — and therefore you’re allowed to do whatever you
 want.
-
       The location in the kernel a process can jump to is called system_call. The
+
       The location in the kernel a process can jump to is called system_call. The
 procedure at that location checks the system call number, which tells the kernel what
 service the process requested. Then, it looks at the table of system calls
 (  sys_call_table
@@ -2855,7 +2862,7 @@ different process, if the process time ran out). If you want to read this code,
 at the source file arch/$(architecture)/kernel/entry.S, after the line
  ENTRY(system_call)
 .
-
       So, if we want to change the way a certain system call works, what we need to do
+
       So, if we want to change the way a certain system call works, what we need to do
 is to write our own function to implement it (usually by adding a bit of our own
 code, and then calling the original function) and then change the pointer at
  sys_call_table
@@ -2863,7 +2870,7 @@ code, and then calling the original function) and then change the pointer at
 don’t want to leave the system in an unstable state, it’s important for
  cleanup_module
  to restore the table to its original state.
-
       The source code here is an example of such a kernel module. We want to “spy” on a certain
+
       The source code here is an example of such a kernel module. We want to “spy” on a certain
 user, and to   pr_info()
  a message whenever that user opens a file. Towards this end, we
 replace the system call to open a file with our own function, called
@@ -2873,7 +2880,7 @@ spy on, it calls   pr_info()
  to display the name of the file to be opened. Then, either way, it calls the
 original open() function with the same parameters, to actually open the
 file.
-
       The   init_module
+
       The   init_module
  function replaces the appropriate location in
  sys_call_table
  and keeps the original pointer in a variable. The
@@ -2891,7 +2898,7 @@ with   B_open
 , which will call what it thinks is the original system call,
  A_open
 , when it’s done.
-
       Now, if B is removed first, everything will be well — it will simply restore the system
+
       Now, if B is removed first, everything will be well — it will simply restore the system
 call to   A_open
 , which calls the original. However, if A is removed and then B is removed, the
 system will crash. A’s removal will restore the system call to the original,
@@ -2914,7 +2921,7 @@ problem. When A is removed, it sees that the system call was changed to
  will still try to call   A_open
  which is no longer there, so that even without removing B the system would
 crash.
-
       Note that all the related problems make syscall stealing unfeasiable for
+
       Note that all the related problems make syscall stealing unfeasiable for
 production use. In order to keep people from doing potential harmful things
  sys_call_table
  is no longer exported. This means, if you want to do something more than a mere
@@ -3065,13 +3072,13 @@ hand apply the patch.
 135module_exit(syscall_end); 
 136 
 137MODULE_LICENSE("GPL");
    -

    +

    0.11 Blocking Processes and threads

    -

    +

    0.11.1 Sleep

    -

    What do you do when somebody asks you for something you can not do right +

    What do you do when somebody asks you for something you can not do right away? If you are a human being and you are bothered by a human being, the only thing you can say is: "Not right now, I’m busy. Go away!". But if you are a kernel module and you are bothered by a process, you have another @@ -3082,21 +3089,21 @@ processes are being put to sleep by the kernel and woken up all the time (that is the way multiple processes appear to run on the same time on a single CPU). -

    This kernel module is an example of this. The file (called /proc/sleep) can only +

    This kernel module is an example of this. The file (called /proc/sleep) can only be opened by a single process at a time. If the file is already open, the kernel module calls wait_event_interruptible . The easiest way to keep a file open is to open it with: 

    1tail -f
    -

    This function changes the status of the task (a task is the kernel data structure +

    This function changes the status of the task (a task is the kernel data structure which holds information about a process and the system call it is in, if any) to TASK_INTERRUPTIBLE , which means that the task will not run until it is woken up somehow, and adds it to WaitQ, the queue of tasks waiting to access the file. Then, the function calls the scheduler to context switch to a different process, one which has some use for the CPU. -

    When a process is done with the file, it closes it, and +

    When a process is done with the file, it closes it, and module_close is called. That function wakes up all the processes in the queue (there’s no mechanism to only wake up one of them). It then returns and the process which just @@ -3106,20 +3113,20 @@ Eventually, one of the processes which was in the queue will be given control of the CPU by the scheduler. It starts at the point right after the call to module_interruptible_sleep_on . -

    This means that the process is still in kernel mode - as far as the process +

    This means that the process is still in kernel mode - as far as the process is concerned, it issued the open system call and the system call has not returned yet. The process does not know somebody else used the CPU for most of the time between the moment it issued the call and the moment it returned. -

    It can then proceed to set a global variable to tell all the other processes that the +

    It can then proceed to set a global variable to tell all the other processes that the file is still open and go on with its life. When the other processes get a piece of the CPU, they’ll see that global variable and go back to sleep. -

    So we will use tail -f +

    So we will use tail -f to keep the file open in the background, while trying to access it with another process (again in the background, so that we need not switch to a different vt). As soon as the first background process is killed with kill %1 , the second is woken up, is able to access the file and finally terminates. -

    To make our life more interesting, module_close +

    To make our life more interesting, module_close does not have a monopoly on waking up the processes which wait to access the file. A signal, such as Ctrl +c (SIGINT) can also wake up a process. This is because we used module_interruptible_sleep_on @@ -3129,11 +3136,11 @@ used module_interruptible_sleep_on instead, but that would have resulted in extremely angry users whose Ctrl+c’s are ignored. -

    In that case, we want to return with +

    In that case, we want to return with -EINTR immediately. This is important so users can, for example, kill the process before it receives the file. -

    There is one more point to remember. Some times processes don’t want to sleep, they want +

    There is one more point to remember. Some times processes don’t want to sleep, they want either to get what they want immediately, or to be told it cannot be done. Such processes use the O_NONBLOCK flag when opening the file. The kernel is supposed to respond by returning with the error @@ -3169,7 +3176,7 @@ $ cat_nonblock /proc/sleep Last input: $ -

    +

    1/* 
@@ -3453,14 +3460,14 @@ $
 57 
 58    return 0; 
 59}
    -

    +

    0.11.2 Completions

    -

    Sometimes one thing should happen before another within a module having multiple threads. +

    Sometimes one thing should happen before another within a module having multiple threads. Rather than using /bin/sleep commands, the kernel has another way to do this which allows timeouts or interrupts to also happen. -

    In the following example two threads are started, but one needs to start before +

    In the following example two threads are started, but one needs to start before another.

    @@ -3543,31 +3550,31 @@ another. 74 75MODULE_DESCRIPTION("Completions example"); 76MODULE_LICENSE("GPL"); -

    The machine +

    The machine structure stores the completion states for the two threads. At the exit point of each thread the respective completion state is updated, and wait_for_completion is used by the flywheel thread to ensure that it does not begin prematurely. -

    So even though flywheel_thread +

    So even though flywheel_thread is started first you should notice if you load this module and run dmesg that turning the crank always happens first because the flywheel thread waits for it to complete. -

    There are other variations upon the +

    There are other variations upon the wait_for_completion function, which include timeouts or being interrupted, but this basic mechanism is enough for many common situations without adding a lot of complexity. -

    +

    0.12 Avoiding Collisions and Deadlocks

    -

    If processes running on different CPUs or in different threads try to access the same +

    If processes running on different CPUs or in different threads try to access the same memory, then it is possible that strange things can happen or your system can lock up. To avoid this, various types of mutual exclusion kernel functions are available. These indicate if a section of code is "locked" or "unlocked" so that simultaneous attempts to run it can not happen.

    0.12.1 Mutex

    -

    You can use kernel mutexes (mutual exclusions) in much the same manner that you +

    You can use kernel mutexes (mutual exclusions) in much the same manner that you might deploy them in userland. This may be all that is needed to avoid collisions in most cases.

    @@ -3613,10 +3620,10 @@ most cases. 39 40MODULE_DESCRIPTION("Mutex example"); 41MODULE_LICENSE("GPL"); -

    +

    0.12.2 Spinlocks

    -

    As the name suggests, spinlocks lock up the CPU that the code is running on, +

    As the name suggests, spinlocks lock up the CPU that the code is running on, taking 100% of its resources. Because of this you should only use the spinlock @@ -3624,7 +3631,7 @@ taking 100% of its resources. Because of this you should only use the spinlock mechanism around code which is likely to take no more than a few milliseconds to run and so will not noticably slow anything down from the user’s point of view. -

    The example here is "irq safe" in that if interrupts happen during the lock then +

    The example here is "irq safe" in that if interrupts happen during the lock then they will not be forgotten and will activate when the unlock happens, using the flags variable to retain their state. @@ -3693,10 +3700,10 @@ they will not be forgotten and will activate when the unlock happens, using the 61 62MODULE_DESCRIPTION("Spinlock example"); 63MODULE_LICENSE("GPL"); -

    +

    0.12.3 Read and write locks

    -

    Read and write locks are specialised kinds of spinlocks so that you can exclusively +

    Read and write locks are specialised kinds of spinlocks so that you can exclusively read from something or write to something. Like the earlier spinlocks example the one below shows an "irq safe" situation in which if other functions were triggered from irqs which might also read and write to whatever you are concerned with @@ -3761,14 +3768,14 @@ module. 53 54MODULE_DESCRIPTION("Read/Write locks example"); 55MODULE_LICENSE("GPL"); -

    Of course, if you know for sure that there are no functions triggered by irqs +

    Of course, if you know for sure that there are no functions triggered by irqs which could possibly interfere with your logic then you can use the simpler read_lock(&myrwlock) and read_unlock(&myrwlock) or the corresponding write functions.

    0.12.4 Atomic operations

    -

    If you are doing simple arithmetic: adding, subtracting or bitwise operations then +

    If you are doing simple arithmetic: adding, subtracting or bitwise operations then there is another way in the multi-CPU and multi-hyperthreaded world to stop other parts of the system from messing with your mojo. By using atomic operations you can be confident that your addition, subtraction or bit flip did actually happen @@ -3853,21 +3860,21 @@ below. -

    +

    0.13 Replacing Print Macros

    -

    +

    0.13.1 Replacement

    -

    In Section 2, I said that X Window System and kernel module programming do not +

    In Section 2, I said that X Window System and kernel module programming do not mix. That is true for developing kernel modules, but in actual use, you want to be able to send messages to whichever tty the command to load the module came from. -

    "tty" is an abbreviation of teletype: originally a combination keyboard-printer +

    "tty" is an abbreviation of teletype: originally a combination keyboard-printer used to communicate with a Unix system, and today an abstraction for the text stream used for a Unix program, whether it is a physical terminal, an xterm on an X display, a network connection used with ssh, etc. -

    The way this is done is by using current, a pointer to the currently running task, +

    The way this is done is by using current, a pointer to the currently running task, to get the current task’s tty structure. Then, we look inside that tty structure to find a pointer to a string write function, which we use to write a string to the tty. @@ -3950,16 +3957,16 @@ tty. 75module_exit(print_string_exit); 76 77MODULE_LICENSE("GPL"); -

    +

    0.13.2 Flashing keyboard LEDs

    -

    In certain conditions, you may desire a simpler and more direct way to communicate +

    In certain conditions, you may desire a simpler and more direct way to communicate to the external world. Flashing keyboard LEDs can be such a solution: It is an immediate way to attract attention or to display a status condition. Keyboard LEDs are present on every hardware, they are always visible, they do not need any setup, and their use is rather simple and non-intrusive, compared to writing to a tty or a file. -

    The following source code illustrates a minimal kernel module which, when +

    The following source code illustrates a minimal kernel module which, when loaded, starts blinking the keyboard LEDs until it is unloaded.

    @@ -4055,7 +4062,7 @@ loaded, starts blinking the keyboard LEDs until it is unloaded. -

    If none of the examples in this chapter fit your debugging needs +

    If none of the examples in this chapter fit your debugging needs there might yet be some other tricks to try. Ever wondered what CONFIG_LL_DEBUG in make menuconfig is good for? If you activate that you get low level access to the @@ -4066,22 +4073,22 @@ over a serial line. If you find yourself porting the kernel to some new and former unsupported architecture, this is usually amongst the first things that should be implemented. Logging over a netconsole might also be worth a try. -

    While you have seen lots of stuff that can be used to aid debugging here, there are +

    While you have seen lots of stuff that can be used to aid debugging here, there are some things to be aware of. Debugging is almost always intrusive. Adding debug code can change the situation enough to make the bug seem to dissappear. Thus you should try to keep debug code to a minimum and make sure it does not show up in production code. -

    +

    0.14 Scheduling Tasks

    -

    There are two main ways of running tasks: tasklets and work queues. Tasklets are a +

    There are two main ways of running tasks: tasklets and work queues. Tasklets are a quick and easy way of scheduling a single function to be run, for example when triggered from an interrupt, whereas work queues are more complicated but also better suited to running multiple things in a sequence. -

    +

    0.14.1 Tasklets

    -

    Here is an example tasklet module. The +

    Here is an example tasklet module. The tasklet_fn function runs for a few seconds and in the mean time execution of the example_tasklet_init @@ -4125,7 +4132,7 @@ better suited to running multiple things in a sequence. 35 36MODULE_DESCRIPTION("Tasklet example"); 37MODULE_LICENSE("GPL"); -

    So with this example loaded dmesg +

    So with this example loaded dmesg should show: @@ -4137,11 +4144,11 @@ Example tasklet starts Example tasklet init continues... Example tasklet ends -

    -

    +

    +

    0.14.2 Work queues

    -

    To add a task to the scheduler we can use a workqueue. The kernel then uses the +

    To add a task to the scheduler we can use a workqueue. The kernel then uses the Completely Fair Scheduler (CFS) to execute work within the queue.

    @@ -4179,19 +4186,19 @@ Completely Fair Scheduler (CFS) to execute work within the queue. 32 33MODULE_LICENSE("GPL"); 34MODULE_DESCRIPTION("Workqueue example"); -

    +

    0.15 Interrupt Handlers

    -

    +

    0.15.1 Interrupt Handlers

    -

    Except for the last chapter, everything we did in the kernel so far we have done as a +

    Except for the last chapter, everything we did in the kernel so far we have done as a response to a process asking for it, either by dealing with a special file, sending an ioctl() , or issuing a system call. But the job of the kernel is not just to respond to process requests. Another job, which is every bit as important, is to speak to the hardware connected to the machine. -

    There are two types of interaction between the CPU and the rest of the +

    There are two types of interaction between the CPU and the rest of the computer’s hardware. The first type is when the CPU gives orders to the hardware, the other is when the hardware needs to tell the CPU something. The second, called interrupts, is much harder to implement because it has to be dealt with when @@ -4201,14 +4208,14 @@ lost. -

    Under Linux, hardware interrupts are called IRQ’s (Interrupt ReQuests). There +

    Under Linux, hardware interrupts are called IRQ’s (Interrupt ReQuests). There are two types of IRQ’s, short and long. A short IRQ is one which is expected to take a very short period of time, during which the rest of the machine will be blocked and no other interrupts will be handled. A long IRQ is one which can take longer, and during which other interrupts may occur (but not interrupts from the same device). If at all possible, it is better to declare an interrupt handler to be long. -

    When the CPU receives an interrupt, it stops whatever it is doing (unless it is +

    When the CPU receives an interrupt, it stops whatever it is doing (unless it is processing a more important interrupt, in which case it will deal with this one only when the more important one is done), saves certain parameters on the stack and calls the interrupt handler. This means that certain things @@ -4220,10 +4227,10 @@ the new information at a later time (this is called the "bottom half") and return. The kernel is then guaranteed to call the bottom half as soon as possible – and when it does, everything allowed in kernel modules will be allowed. -

    The way to implement this is to call +

    The way to implement this is to call request_irq() to get your interrupt handler called when the relevant IRQ is received. -

    In practice IRQ handling can be a bit more complex. Hardware is often +

    In practice IRQ handling can be a bit more complex. Hardware is often designed in a way that chains two interrupt controllers, so that all the IRQs from interrupt controller B are cascaded to a certain IRQ from interrupt controller A. Of course, that requires that the kernel finds out which IRQ it @@ -4237,7 +4244,7 @@ need to solve another truckload of problems. It is not enough to know if a certain IRQs has happend, it’s also important for what CPU(s) it was for. People still interested in more details, might want to refer to "APIC" now. -

    This function receives the IRQ number, the name of the function, +

    This function receives the IRQ number, the name of the function, flags, a name for /proc/interrupts and a parameter to pass to the interrupt handler. Usually there is a certain number of IRQs available. How many IRQs there are is hardware-dependent. The flags can include @@ -4250,16 +4257,16 @@ already a handler on this IRQ, or if you are both willing to share. -

    +

    0.15.2 Detecting button presses

    -

    Many popular single board computers, such as Raspberry Pi or Beagleboards, have a +

    Many popular single board computers, such as Raspberry Pi or Beagleboards, have a bunch of GPIO pins. Attaching buttons to those and then having a button press do something is a classic case in which you might need to use interrupts, so that instead of having the CPU waste time and battery power polling for a change in input state it is better for the input to trigger the CPU to then run a particular handling function. -

    Here is an example where buttons are connected to GPIO numbers 17 and 18 and +

    Here is an example where buttons are connected to GPIO numbers 17 and 18 and an LED is connected to GPIO 4. You can change those numbers to whatever is appropriate for your board.

    @@ -4409,14 +4416,14 @@ appropriate for your board. 143 144MODULE_LICENSE("GPL"); 145MODULE_DESCRIPTION("Handle some GPIO interrupts"); -

    +

    0.15.3 Bottom Half

    -

    Suppose you want to do a bunch of stuff inside of an interrupt routine. A common +

    Suppose you want to do a bunch of stuff inside of an interrupt routine. A common way to do that without rendering the interrupt unavailable for a significant duration is to combine it with a tasklet. This pushes the bulk of the work off into the scheduler. -

    The example below modifies the previous example to also run an additional task +

    The example below modifies the previous example to also run an additional task when an interrupt is triggered.

    @@ -4581,10 +4588,10 @@ when an interrupt is triggered. 159 160MODULE_LICENSE("GPL"); 161MODULE_DESCRIPTION("Interrupt with top and bottom half"); -

    +

    0.16 Crypto

    -

    At the dawn of the internet everybody trusted everybody completely…but that did +

    At the dawn of the internet everybody trusted everybody completely…but that did not work out so well. When this guide was originally written it was a more innocent era in which almost nobody actually gave a damn about crypto - least of all kernel developers. That is certainly no longer the case now. To handle crypto stuff the @@ -4593,10 +4600,10 @@ favourite hash functions. -

    +

    0.16.1 Hash functions

    -

    Calculating and checking the hashes of things is a common operation. Here is a +

    Calculating and checking the hashes of things is a common operation. Here is a demonstration of how to calculate a sha256 hash within a kernel module.

    @@ -4662,21 +4669,21 @@ demonstration of how to calculate a sha256 hash within a kernel module. 60 61MODULE_DESCRIPTION("sha256 hash test"); 62MODULE_LICENSE("GPL"); -

    Make and install the module: +

    Make and install the module: 

    1make 
 2sudo insmod cryptosha256.ko 
 3dmesg
    -

    And you should see that the hash was calculated for the test string. -

    Finally, remove the test module: +

    And you should see that the hash was calculated for the test string. +

    Finally, remove the test module: 

    1sudo rmmod cryptosha256
    -

    +

    0.16.2 Symmetric key encryption

    -

    Here is an example of symmetrically encrypting a string using the AES algorithm +

    Here is an example of symmetrically encrypting a string using the AES algorithm and a password.

    @@ -4877,10 +4884,10 @@ and a password. 195 196MODULE_DESCRIPTION("Symmetric key encryption example"); 197MODULE_LICENSE("GPL"); -

    +

    0.17 Standardizing the interfaces: The Device Model

    -

    Up to this point we have seen all kinds of modules doing all kinds of things, but there +

    Up to this point we have seen all kinds of modules doing all kinds of things, but there was no consistency in their interfaces with the rest of the kernel. To impose some consistency such that there is at minimum a standardized way to start, suspend and resume a device a device model was added. An example is show below, and you can @@ -4990,13 +4997,13 @@ functions. -

    +

    0.18 Optimizations

    -

    +

    0.18.1 Likely and Unlikely conditions

    -

    Sometimes you might want your code to run as quickly as possible, +

    Sometimes you might want your code to run as quickly as possible, especially if it is handling an interrupt or doing something which might cause noticible latency. If your code contains boolean conditions and if you know that the conditions are almost always likely to evaluate as either @@ -5006,7 +5013,7 @@ know that the conditions are almost always likely to evaluate as either likely and unlikely macros. -

    For example, when allocating memory you are almost always expecting this to +

    For example, when allocating memory you are almost always expecting this to succeed.

    @@ -5016,50 +5023,50 @@ succeed. 4    bio = NULL; 5    goto out; 6} -

    When the unlikely +

    When the unlikely macro is used, the compiler alters its machine instruction output, so that it continues along the false branch and only jumps if the condition is true. That avoids flushing the processor pipeline. The opposite happens if you use the likely macro. -

    +

    0.19 Common Pitfalls

    -

    +

    0.19.1 Using standard libraries

    -

    You can not do that. In a kernel module you can only use kernel functions, which are +

    You can not do that. In a kernel module you can only use kernel functions, which are the functions you can see in /proc/kallsyms. -

    +

    0.19.2 Disabling interrupts

    -

    You might need to do this for a short time and that is OK, but if you do not enable +

    You might need to do this for a short time and that is OK, but if you do not enable them afterwards, your system will be stuck and you will have to power it off. -

    +

    0.20 Where To Go From Here?

    -

    For people seriously interested in kernel programming, I recommend kernelnewbies.org +

    For people seriously interested in kernel programming, I recommend kernelnewbies.org and the Documentation subdirectory within the kernel source code which is not always easy to understand but can be a starting point for further investigation. Also, as Linus Torvalds said, the best way to learn the kernel is to read the source code yourself. -

    If you are interested in more examples of short kernel modules then searching on +

    If you are interested in more examples of short kernel modules then searching on sites such as Github and Gitlab is a good way to start, although there is a lot of duplication of older LKMPG examples which may not compile with newer kernel versions. You will also be able to find examples of the use of kernel modules to attack or compromise systems or exfiltrate data and those can be useful for thinking about how to defend systems and learning about existing security mechanisms within the kernel. -

    I hope I have helped you in your quest to become a better programmer, or at +

    I hope I have helped you in your quest to become a better programmer, or at least to have fun through technology. And, if you do write useful kernel modules, I hope you publish them under the GPL, so I can use them too. -

    If you would like to contribute to this guide or notice anything glaringly wrong, +

    If you would like to contribute to this guide or notice anything glaringly wrong, please create an issue at https://github.com/sysprog21/lkmpg. -

    Happy hacking! +

    Happy hacking!

    diff --git a/lkmpg-for-ht.html b/lkmpg-for-ht.html index b879ef2..721e556 100644 --- a/lkmpg-for-ht.html +++ b/lkmpg-for-ht.html @@ -226,10 +226,10 @@ thereafter.

    Modules can not print to the screen like printf() can, but they can log information and warnings, which ends up being - printed on your screen, but only on a console. If you insmod a module - from an xterm, the information and warnings will be logged, but only to - your systemd journal. You will not see it unless you look through your - journalctl + printed on your screen, but only on a console. If you insmod + a module from an xterm, the information and warnings will be logged, but + only to your systemd journal. You will not see it unless you look through + your journalctl . See 0.4 for details. To have immediate access to this information, do all your work from the console.

    @@ -569,11 +569,13 @@ used to.

    To allow arguments to be passed to your module, declare the variables that will take the values of the command line arguments as global and then use the module_param() - macro, (defined in linux/moduleparam.h) to set the mechanism up. At runtime, -insmod will fill the variables with any command line arguments that are given, like -insmod ./mymodule.ko myvariable=5. The variable declarations and macros should -be placed at the beginning of the module for clarity. The example code should clear -up my admittedly lousy explanation. + macro, (defined in include/linux/moduleparam.h) to set the mechanism up. At +runtime, insmod + will fill the variables with any command line arguments that are given, like + insmod ./mymodule.ko myvariable=5 +. The variable declarations and macros should be placed at the beginning of the +module for clarity. The example code should clear up my admittedly lousy +explanation.

    The module_param() macro takes 3 arguments: the name of the variable, its type and permissions for the corresponding file in sysfs. Integer types can be signed @@ -582,12 +584,12 @@ as usual or unsigned. If you’d like to use arrays of integers or strings see and module_param_string() .

    -

    - 
    1int myint = 3; 
-2module_param(myint, int, 0);
    +

    + 
    1int myint = 3; 
+2module_param(myint, int, 0);

    Arrays are supported too, but things are a bit different now than they were in the olden days. To keep track of the number of parameters you need to pass a pointer to a count variable as third parameter. At your option, you could @@ -595,12 +597,12 @@ also ignore the count and pass NULL instead. We show both possibilities here:

    - 
    1int myintarray[2]; 
-2module_param_array(myintarray, int, NULL, 0); /* not interested in count */ 
-3 
-4short myshortarray[4]; 
-5int count; 
-6module_param_array(myshortarray, short, &count, 0); /* put count into "count" variable */
    + 
    1int myintarray[2]; 
+2module_param_array(myintarray, int, NULL, 0); /* not interested in count */ 
+3 
+4short myshortarray[4]; 
+5int count; 
+6module_param_array(myshortarray, short, &count, 0); /* put count into "count" variable */

    A good use for this is to have the module variable’s default values set, like an port or IO address. If the variables contain the default values, then perform autodetection (explained elsewhere). Otherwise, keep the current value. This will be made clear @@ -610,100 +612,100 @@ later on. parameters: a variable name and a free form string describing that variable.

    - 
    1/* 
-2 * hello-5.c - Demonstrates command line argument passing to a module. 
-3 */ 
-4#include <linux/init.h> 
-5#include <linux/kernel.h> 
-6#include <linux/module.h> 
-7#include <linux/moduleparam.h> 
-8#include <linux/stat.h> 
-9 
-10MODULE_LICENSE("GPL"); 
-11 
-12static short int myshort = 1; 
-13static int myint = 420; 
-14static long int mylong = 9999; 
-15static char *mystring = "blah"; 
-16static int myintArray[2] = {420, 420}; 
-17static int arr_argc = 0; 
-18 
-19/* module_param(foo, int, 0000) 
-20 * The first param is the parameters name. 
-21 * The second param is its data type. 
-22 * The final argument is the permissions bits, 
-23 * for exposing parameters in sysfs (if non-zero) at a later stage. 
-24 */ 
-25module_param(myshort, short, S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP); 
-26MODULE_PARM_DESC(myshort, "A short integer"); 
-27module_param(myint, int, S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH); 
-28MODULE_PARM_DESC(myint, "An integer"); 
-29module_param(mylong, long, S_IRUSR); 
-30MODULE_PARM_DESC(mylong, "A long integer"); 
-31module_param(mystring, charp, 0000); 
-32MODULE_PARM_DESC(mystring, "A character string"); 
-33 
-34/* module_param_array(name, type, num, perm); 
-35 * The first param is the parameter's (in this case the array's) name. 
-36 * The second param is the data type of the elements of the array. 
-37 * The third argument is a pointer to the variable that will store the number. 
-38 * of elements of the array initialized by the user at module loading time. 
-39 * The fourth argument is the permission bits. 
-40 */ 
-41module_param_array(myintArray, int, &arr_argc, 0000); 
-42MODULE_PARM_DESC(myintArray, "An array of integers"); 
-43 
-44static int __init hello_5_init(void) 
-45{ 
-46    int i; 
-47    pr_info("Hello, world 5\n=============\n"); 
-48    pr_info("myshort is a short integer: %hd\n", myshort); 
-49    pr_info("myint is an integer: %d\n", myint); 
-50    pr_info("mylong is a long integer: %ld\n", mylong); 
-51    pr_info("mystring is a string: %s\n", mystring); 
-52 
-53    for (i = 0; i < (sizeof myintArray / sizeof(int)); i++) 
-54        pr_info("myintArray[%d] = %d\n", i, myintArray[i]); 
-55 
-56    pr_info("got %d arguments for myintArray.\n", arr_argc); 
-57    return 0; 
-58} 
-59 
-60static void __exit hello_5_exit(void) 
-61{ 
-62    pr_info("Goodbye, world 5\n"); 
-63} 
-64 
-65module_init(hello_5_init); 
-66module_exit(hello_5_exit);
    + 
    1/* 
+2 * hello-5.c - Demonstrates command line argument passing to a module. 
+3 */ 
+4#include <linux/init.h> 
+5#include <linux/kernel.h> 
+6#include <linux/module.h> 
+7#include <linux/moduleparam.h> 
+8#include <linux/stat.h> 
+9 
+10MODULE_LICENSE("GPL"); 
+11 
+12static short int myshort = 1; 
+13static int myint = 420; 
+14static long int mylong = 9999; 
+15static char *mystring = "blah"; 
+16static int myintArray[2] = {420, 420}; 
+17static int arr_argc = 0; 
+18 
+19/* module_param(foo, int, 0000) 
+20 * The first param is the parameters name. 
+21 * The second param is its data type. 
+22 * The final argument is the permissions bits, 
+23 * for exposing parameters in sysfs (if non-zero) at a later stage. 
+24 */ 
+25module_param(myshort, short, S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP); 
+26MODULE_PARM_DESC(myshort, "A short integer"); 
+27module_param(myint, int, S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH); 
+28MODULE_PARM_DESC(myint, "An integer"); 
+29module_param(mylong, long, S_IRUSR); 
+30MODULE_PARM_DESC(mylong, "A long integer"); 
+31module_param(mystring, charp, 0000); 
+32MODULE_PARM_DESC(mystring, "A character string"); 
+33 
+34/* module_param_array(name, type, num, perm); 
+35 * The first param is the parameter's (in this case the array's) name. 
+36 * The second param is the data type of the elements of the array. 
+37 * The third argument is a pointer to the variable that will store the number. 
+38 * of elements of the array initialized by the user at module loading time. 
+39 * The fourth argument is the permission bits. 
+40 */ 
+41module_param_array(myintArray, int, &arr_argc, 0000); 
+42MODULE_PARM_DESC(myintArray, "An array of integers"); 
+43 
+44static int __init hello_5_init(void) 
+45{ 
+46    int i; 
+47    pr_info("Hello, world 5\n=============\n"); 
+48    pr_info("myshort is a short integer: %hd\n", myshort); 
+49    pr_info("myint is an integer: %d\n", myint); 
+50    pr_info("mylong is a long integer: %ld\n", mylong); 
+51    pr_info("mystring is a string: %s\n", mystring); 
+52 
+53    for (i = 0; i < (sizeof myintArray / sizeof(int)); i++) 
+54        pr_info("myintArray[%d] = %d\n", i, myintArray[i]); 
+55 
+56    pr_info("got %d arguments for myintArray.\n", arr_argc); 
+57    return 0; 
+58} 
+59 
+60static void __exit hello_5_exit(void) 
+61{ 
+62    pr_info("Goodbye, world 5\n"); 
+63} 
+64 
+65module_init(hello_5_init); 
+66module_exit(hello_5_exit);

    I would recommend playing around with this code:

    - 
    1$ sudo insmod hello-5.ko mystring="bebop" myintArray=-1 
-2myshort is a short integer: 1 
-3myint is an integer: 420 
-4mylong is a long integer: 9999 
-5mystring is a string: bebop 
-6myintArray[0] = -1 
-7myintArray[1] = 420 
-8got 1 arguments for myintArray. 
-9 
-10$ sudo rmmod hello-5 
-11Goodbye, world 5 
-12 
-13$ sudo insmod hello-5.ko mystring="supercalifragilisticexpialidocious" myintArray=-1,-1 
-14myshort is a short integer: 1 
-15myint is an integer: 420 
-16mylong is a long integer: 9999 
-17mystring is a string: supercalifragilisticexpialidocious 
-18myintArray[0] = -1 
-19myintArray[1] = -1 
-20got 2 arguments for myintArray. 
-21 
-22$ sudo rmmod hello-5 
-23Goodbye, world 5 
-24 
-25$ sudo insmod hello-5.ko mylong=hello 
-26hello-5.o: invalid argument syntax for mylong: 'h'
    + 
    1$ sudo insmod hello-5.ko mystring="bebop" myintArray=-1 
+2myshort is a short integer: 1 
+3myint is an integer: 420 
+4mylong is a long integer: 9999 
+5mystring is a string: bebop 
+6myintArray[0] = -1 
+7myintArray[1] = 420 
+8got 1 arguments for myintArray. 
+9 
+10$ sudo rmmod hello-5 
+11Goodbye, world 5 
+12 
+13$ sudo insmod hello-5.ko mystring="supercalifragilisticexpialidocious" myintArray=-1,-1 
+14myshort is a short integer: 1 
+15myint is an integer: 420 
+16mylong is a long integer: 9999 
+17mystring is a string: supercalifragilisticexpialidocious 
+18myintArray[0] = -1 
+19myintArray[1] = -1 
+20got 2 arguments for myintArray. 
+21 
+22$ sudo rmmod hello-5 
+23Goodbye, world 5 
+24 
+25$ sudo insmod hello-5.ko mylong=hello 
+26hello-5.o: invalid argument syntax for mylong: 'h'

    0.4.6 Modules Spanning Multiple Files

    @@ -756,13 +758,13 @@ files. 11 12clean: 13    make -C /lib/modules/$(shell uname -r)/build M=$(PWD) clean + + +

    This is the complete makefile for all the examples we have seen so far. The first five lines are nothing special, but for the last example we will need two lines. First we invent an object name for our combined module, second we tell make what object files are part of that module. - - -

    0.4.7 Building modules for a precompiled kernel

    @@ -806,11 +808,12 @@ REGPARM 4KSTACKS gcc-3.3' should be '2.6.5-1.358 686 REGPARM 4KSTACKS g

    In other words, your kernel refuses to accept your module because version strings -(more precisely, version magics) do not match. Incidentally, version magics are stored -in the module object in the form of a static string, starting with vermagic:. Version -data are inserted in your module when it is linked against the init/vermagic.o file. -To inspect version magics and other strings stored in a given module, issue the -modinfo module.ko command: +(more precisely, version magics) do not match. Incidentally, version magics are stored in +the module object in the form of a static string, starting with vermagic:. Version data +are inserted in your module when it is linked against the init/vermagic.o file. To +inspect version magics and other strings stored in a given module, issue the command + modinfo module.ko +: @@ -1058,7 +1061,7 @@ careful. operating system which uses a monolithic kernel. This is not quite the same thing as "building all your modules into the kernel", although the idea is the same. There are things called microkernels which have modules which get their own codespace. The -GNU Hurd and the Zircon kernel of Google Fuchsia are two examples of a +GNU Hurd and the Zircon kernel of Google Fuchsia are two examples of a microkernel.

    @@ -1097,16 +1100,17 @@ them as being different pieces of hardware.

    Devices are divided into two types: character devices and block devices. The difference is that block devices have a buffer for requests, so they can choose the best order in which to respond to the requests. This is important in the case of storage -devices, where it is faster to read or write sectors which are close to each other, -rather than those which are further apart. Another difference is that block devices -can only accept input and return output in blocks (whose size can vary according to -the device), whereas character devices are allowed to use as many or as few bytes -as they like. Most devices in the world are character, because they don’t -need this type of buffering, and they don’t operate with a fixed block size. -You can tell whether a device file is for a block device or a character device -by looking at the first character in the output of ls -l. If it is ‘b’ then it -is a block device, and if it is ‘c’ then it is a character device. The devices -you see above are block devices. Here are some character devices (the serial +devices, where it is faster to read or write sectors which are close to each +other, rather than those which are further apart. Another difference is that +block devices can only accept input and return output in blocks (whose size +can vary according to the device), whereas character devices are allowed +to use as many or as few bytes as they like. Most devices in the world are +character, because they don’t need this type of buffering, and they don’t +operate with a fixed block size. You can tell whether a device file is for a block +device or a character device by looking at the first character in the output of + ls -l +. If it is ‘b’ then it is a block device, and if it is ‘c’ then it is a character device. The +devices you see above are block devices. Here are some character devices (the serial ports): @@ -1119,24 +1123,25 @@ crw-rw----  1 root  dial 4, 66 Jul  5  2000 /dev/ttyS2 crw-rw----  1 root  dial 4, 67 Jul  5  2000 /dev/ttyS3

    -

    If you want to see which major numbers have been assigned, you can look at +

    If you want to see which major numbers have been assigned, you can look at Documentation/admin-guide/devices.txt. -

    When the system was installed, all of those device files were created by the -mknod command. To create a new char device named ‘coffee’ with major/minor -number 12 and 2, simply do mknod /dev/coffee c 12 2. You do not have to put your -device files into /dev, but it is done by convention. Linus put his device files in /dev, -and so should you. However, when creating a device file for testing purposes, it is -probably OK to place it in your working directory where you compile the kernel -module. Just be sure to put it in the right place when you’re done writing the device -driver. -

    I would like to make a few last points which are implicit from the above +

    When the system was installed, all of those device files were created by the + mknod + command. To create a new char device named coffee with major/minor number 12 and 2, +simply do mknod /dev/coffee c 12 2 +. You do not have to put your device files into /dev, but it is done by convention. +Linus put his device files in /dev, and so should you. However, when creating a +device file for testing purposes, it is probably OK to place it in your working +directory where you compile the kernel module. Just be sure to put it in the right +place when you’re done writing the device driver. +

    I would like to make a few last points which are implicit from the above discussion, but I would like to make them explicit just in case. When a device file is accessed, the kernel uses the major number of the file to determine which driver should be used to handle the access. This means that the kernel doesn’t really need to use or even know about the minor number. The driver itself is the only thing that cares about the minor number. It uses the minor number to distinguish between different pieces of hardware. -

    By the way, when I say "hardware", I mean something a bit more abstract +

    By the way, when I say "hardware", I mean something a bit more abstract than a PCI card that you can hold in your hand. Look at these two device files: @@ -1148,24 +1153,24 @@ $ ls -l /dev/sda /dev/sdb brw-rw---- 1 root disk 8,  0 Jan  3 09:02 /dev/sda brw-rw---- 1 root disk 8, 16 Jan  3 09:02 /dev/sdb -

    -

    By now you can look at these two device files and know instantly that they are +

    +

    By now you can look at these two device files and know instantly that they are block devices and are handled by same driver (block major 8). Sometimes two device files with the same major but different minor number can actually represent the same piece of physical hardware. So just be aware that the word “hardware” in our discussion can mean something very abstract. -

    +

    0.6 Character Device drivers

    -

    +

    0.6.1 The file_operations Structure

    -

    The file_operations - structure is defined in /usr/include/linux/fs.h, and holds pointers to functions -defined by the driver that perform various operations on the device. Each field of the +

    The file_operations + structure is defined in include/linux/fs.h, and holds pointers to functions defined +by the driver that perform various operations on the device. Each field of the structure corresponds to the address of some function defined by the driver to handle a requested operation. -

    For example, every character driver needs to define a function that reads from the +

    For example, every character driver needs to define a function that reads from the device. The file_operations structure holds the address of the module’s function that performs that operation. Here is what the definition looks like for kernel 5.4: @@ -1209,11 +1214,11 @@ Here is what the definition looks like for kernel 5.4: 36             loff_t len, unsigned int remap_flags); 37    int (*fadvise)(struct file *, loff_t, loff_t, int); 38} __randomize_layout; -

    Some operations are not implemented by a driver. For example, a driver that handles +

    Some operations are not implemented by a driver. For example, a driver that handles a video card will not need to read from a directory structure. The corresponding entries in the file_operations structure should be set to NULL. -

    There is a gcc extension that makes assigning to this structure more convenient. +

    There is a gcc extension that makes assigning to this structure more convenient. You will see it in modern drivers, and may catch you by surprise. This is what the new way of assigning to the structure looks like:

    @@ -1227,7 +1232,7 @@ new way of assigning to the structure looks like: 4    open: device_open, 5    release: device_release 6}; -

    However, there is also a C99 way of assigning to elements of a structure, +

    However, there is also a C99 way of assigning to elements of a structure, designated initializers, and this is definitely preferred over using the GNU extension. You should use this syntax in case someone wants to port your driver. It will help with compatibility: @@ -1239,36 +1244,36 @@ with compatibility: 4    .open = device_open, 5    .release = device_release 6}; -

    The meaning is clear, and you should be aware that any member of the +

    The meaning is clear, and you should be aware that any member of the structure which you do not explicitly assign will be initialized to NULL by gcc. -

    An instance of struct file_operations +

    An instance of struct file_operations containing pointers to functions that are used to implement read, write, open, … syscalls is commonly named fops. -

    Sin Linux v5.6, the proc_ops +

    Sin Linux v5.6, the proc_ops structure was introduced to replace the use of the file_operations structure when registering proc handlers. -

    +

    0.6.2 The file structure

    -

    Each device is represented in the kernel by a file structure, which is defined +

    Each device is represented in the kernel by a file structure, which is defined in linux/fs.h. Be aware that a file is a kernel level structure and never appears in a user space program. It is not the same thing as a FILE , which is defined by glibc and would never appear in a kernel space function. Also, its name is a bit misleading; it represents an abstract open ‘file’, not a file on a disk, which is represented by a structure named inode. -

    An instance of struct file is commonly named filp. You’ll also see it refered to as +

    An instance of struct file is commonly named filp. You’ll also see it refered to as struct file file. Resist the temptation. -

    Go ahead and look at the definition of file. Most of the entries you see, like struct +

    Go ahead and look at the definition of file. Most of the entries you see, like struct dentry are not used by device drivers, and you can ignore them. This is because drivers do not fill file directly; they only use structures contained in file which are created elsewhere. -

    +

    0.6.3 Registering A Device

    -

    As discussed earlier, char devices are accessed through device files, usually located in +

    As discussed earlier, char devices are accessed through device files, usually located in /dev. This is by convention. When writing a driver, it is OK to put the @@ -1278,14 +1283,14 @@ production driver. The major number tells you which driver handles which device file. The minor number is used only by the driver itself to differentiate which device it is operating on, just in case the driver handles more than one device. -

    Adding a driver to your system means registering it with the kernel. This is synonymous +

    Adding a driver to your system means registering it with the kernel. This is synonymous with assigning it a major number during the module’s initialization. You do this by using the register_chrdev function, defined by linux/fs.h. 

    1int register_chrdev(unsigned int major, const char *name, struct file_operations *fops);
    -

    where unsigned int major is the major number you want to request, +

    where unsigned int major is the major number you want to request, const char *name is the name of the device as it will appear in /proc/devices and struct file_operations *fops @@ -1295,13 +1300,13 @@ registration failed. Note that we didn’t pass the minor number to register_chrdev . That is because the kernel doesn’t care about the minor number; only our driver uses it. -

    Now the question is, how do you get a major number without hijacking +

    Now the question is, how do you get a major number without hijacking one that’s already in use? The easiest way would be to look through Documentation/admin-guide/devices.txt and pick an unused one. That is a bad way of doing things because you will never be sure if the number you picked will be assigned later. The answer is that you can ask the kernel to assign you a dynamic major number. -

    If you pass a major number of 0 to register_chrdev +

    If you pass a major number of 0 to register_chrdev , the return value will be the dynamically allocated major number. The downside is that you can not make a device file in advance, since you do not know what the major number will be. There are a couple of ways to do @@ -1315,13 +1320,13 @@ third method is we can have our driver make the the device file using the device_destroy during the call to cleanup_module . -

    +

    0.6.4 Unregistering A Device

    -

    We can not allow the kernel module to be rmmod’ed whenever root feels like it. If the +

    We can not allow the kernel module to be rmmod’ed whenever root feels like it. If the device file is opened by a process and then we remove the kernel module, using the file would cause a call to the memory location where the appropriate function (read/write) used to be. If we are lucky, no other code was loaded there, and we’ll get @@ -1329,13 +1334,14 @@ an ugly error message. If we are unlucky, another kernel module was loaded into same location, which means a jump into the middle of another function within the kernel. The results of this would be impossible to predict, but they can not be very positive. -

    Normally, when you do not want to allow something, you return an error code +

    Normally, when you do not want to allow something, you return an error code (a negative number) from the function which is supposed to do it. With cleanup_module that’s impossible because it is a void function. However, there is a counter which keeps track of how many processes are using your module. You can see what its value is by looking at the 3rd field of /proc/modules. If this number isn’t zero, -rmmod will fail. Note that you do not have to check the counter from within + rmmod + will fail. Note that you do not have to check the counter from within cleanup_module because the check will be performed for you by the system call sys_delete_module @@ -1349,22 +1355,22 @@ this counter:

  • module_put(THIS_MODULE) : Decrement the use count.
    • -

    It is important to keep the counter accurate; if you ever do lose track of the +

    It is important to keep the counter accurate; if you ever do lose track of the correct usage count, you will never be able to unload the module; it’s now reboot time, boys and girls. This is bound to happen to you sooner or later during a module’s development. -

    -

    +

    +

    0.6.5 chardev.c

    -

    The next code sample creates a char driver named chardev. You can cat its device +

    The next code sample creates a char driver named chardev. You can cat its device file. 

    1cat /proc/devices
    -

    (or open the file with a program) and the driver will put the number of times the +

    (or open the file with a program) and the driver will put the number of times the device file has been read from into the file. We do not support writing to the file (like echo "hi" > /dev/hello ), but catch these attempts and tell the user that the operation is not supported. @@ -1522,39 +1528,39 @@ acknowledging that we received it. 147module_exit(chardev_exit); 148 149MODULE_LICENSE("GPL"); -

    +

    0.6.6 Writing Modules for Multiple Kernel Versions

    -

    The system calls, which are the major interface the kernel shows to the processes, +

    The system calls, which are the major interface the kernel shows to the processes, generally stay the same across versions. A new system call may be added, but usually the old ones will behave exactly like they used to. This is necessary for backward compatibility – a new kernel version is not supposed to break regular processes. In most cases, the device files will also remain the same. On the other hand, the internal interfaces within the kernel can and do change between versions. -

    There are differences between different kernel versions, and if you want +

    There are differences between different kernel versions, and if you want to support multiple kernel versions, you will find yourself having to code conditional compilation directives. The way to do this to compare the macro LINUX_VERSION_CODE to the macro KERNEL_VERSION . In version a.b.c of the kernel, the value of this macro would be 216a+ 28b+ c . -

    While previous versions of this guide showed how you can write backward +

    While previous versions of this guide showed how you can write backward compatible code with such constructs in great detail, we decided to break with this tradition for the better. People interested in doing such might now use a LKMPG with a version matching to their kernel. -

    -

    +

    +

    0.7 The /proc File System

    -

    In Linux, there is an additional mechanism for the kernel and kernel modules to send +

    In Linux, there is an additional mechanism for the kernel and kernel modules to send information to processes — the /proc file system. Originally designed to allow easy access to information about processes (hence the name), it is now used by every bit of the kernel which has something interesting to report, such as /proc/modules which provides the list of modules and /proc/meminfo which stats memory usage statistics. -

    The method to use the proc file system is very similar to the one used with device +

    The method to use the proc file system is very similar to the one used with device drivers — a structure is created with all the information needed for the /proc file, including pointers to any handler functions (in our case there is only one, the one called when somebody attempts to read from the /proc file). Then, @@ -1562,18 +1568,18 @@ one called when somebody attempts to read from the registers the structure with the kernel and cleanup_module unregisters it. -

    Normal file systems are located on a disk, rather than just in memory (which is +

    Normal file systems are located on a disk, rather than just in memory (which is where /proc is), and in that case the inode number is a pointer to a disk location where the file’s index-node (inode for short) is located. The inode contains information about the file, for example the file’s permissions, together with a pointer to the disk location or locations where the file’s data can be found. -

    Because we don’t get called when the file is opened or closed, there’s nowhere for +

    Because we don’t get called when the file is opened or closed, there’s nowhere for us to put try_module_get and try_module_put in this module, and if the file is opened and then the module is removed, there’s no way to avoid the consequences. -

    Here a simple example showing how to use a /proc file. This is the HelloWorld for +

    Here a simple example showing how to use a /proc file. This is the HelloWorld for the /proc filesystem. There are three parts: create the file /proc/helloworld in the function init_module , return a value (and a buffer) when the file /proc/helloworld is read in the callback @@ -1581,23 +1587,23 @@ function procfile_read , and delete the file /proc/helloworld in the function cleanup_module . -

    The /proc/helloworld is created when the module is loaded with the function +

    The /proc/helloworld is created when the module is loaded with the function proc_create . The return value is a struct proc_dir_entry , and it will be used to configure the file /proc/helloworld (for example, the owner of this file). A null return value means that the creation has failed. -

    Each time, everytime the file /proc/helloworld is read, the function +

    Each time, everytime the file /proc/helloworld is read, the function procfile_read is called. Two parameters of this function are very important: the buffer (the second parameter) and the offset (the fourth one). The content of the buffer will be returned to the application which read it (for example the -cat command). The offset is the current position in the file. If the return -value of the function is not null, then this function is called again. So be -careful with this function, if it never returns zero, the read function is called -endlessly. + cat + command). The offset is the current position in the file. If the return value of the +function is not null, then this function is called again. So be careful with this +function, if it never returns zero, the read function is called endlessly. @@ -1606,85 +1612,85 @@ endlessly. $ cat /proc/helloworld HelloWorld! -

    +

    - 
    1/* 
-2 * procfs1.c 
-3 */ 
-4 
-5#include <linux/kernel.h> 
-6#include <linux/module.h> 
-7#include <linux/proc_fs.h> 
-8#include <linux/uaccess.h> 
-9#include <linux/version.h> 
-10 
-11#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0) 
-12#define HAVE_PROC_OPS 
-13#endif 
-14 
-15#define procfs_name "helloworld" 
-16 
-17struct proc_dir_entry *Our_Proc_File; 
-18 
-19 
-20ssize_t procfile_read(struct file *filePointer, 
-21                      char *buffer, 
-22                      size_t buffer_length, 
-23                      loff_t *offset) 
-24{ 
-25    char s[13] = "HelloWorld!\n"; 
-26    int len = sizeof(s); 
-27    ssize_t ret = len; 
-28 
-29    if (*offset >= len || copy_to_user(buffer, s, len)) { 
-30        pr_info("copy_to_user failed\n"); 
-31        ret = 0; 
-32    } else { 
-33        pr_info("procfile read %s\n", filePointer->f_path.dentry->d_name.name); 
-34        *offset += len; 
-35    } 
-36 
-37    return ret; 
-38} 
-39 
-40#ifdef HAVE_PROC_OPS 
-41static const struct proc_ops proc_file_fops = { 
-42    .proc_read = procfile_read, 
-43}; 
-44#else 
-45static const struct file_operations proc_file_fops = { 
-46    .read = procfile_read, 
-47}; 
-48#endif 
-49 
-50static int __init procfs1_init(void) 
-51{ 
-52    Our_Proc_File = proc_create(procfs_name, 0644, NULL, &proc_file_fops); 
-53    if (NULL == Our_Proc_File) { 
-54        proc_remove(Our_Proc_File); 
-55        pr_alert("Error:Could not initialize /proc/%s\n", procfs_name); 
-56        return -ENOMEM; 
-57    } 
-58 
-59    pr_info("/proc/%s created\n", procfs_name); 
-60    return 0; 
-61} 
-62 
-63static void __exit procfs1_exit(void) 
-64{ 
-65    proc_remove(Our_Proc_File); 
-66    pr_info("/proc/%s removed\n", procfs_name); 
-67} 
-68 
-69module_init(procfs1_init); 
-70module_exit(procfs1_exit); 
-71 
-72MODULE_LICENSE("GPL");
    -

    + 

    1/* 
+2 * procfs1.c 
+3 */ 
+4 
+5#include <linux/kernel.h> 
+6#include <linux/module.h> 
+7#include <linux/proc_fs.h> 
+8#include <linux/uaccess.h> 
+9#include <linux/version.h> 
+10 
+11#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0) 
+12#define HAVE_PROC_OPS 
+13#endif 
+14 
+15#define procfs_name "helloworld" 
+16 
+17struct proc_dir_entry *Our_Proc_File; 
+18 
+19 
+20ssize_t procfile_read(struct file *filePointer, 
+21                      char *buffer, 
+22                      size_t buffer_length, 
+23                      loff_t *offset) 
+24{ 
+25    char s[13] = "HelloWorld!\n"; 
+26    int len = sizeof(s); 
+27    ssize_t ret = len; 
+28 
+29    if (*offset >= len || copy_to_user(buffer, s, len)) { 
+30        pr_info("copy_to_user failed\n"); 
+31        ret = 0; 
+32    } else { 
+33        pr_info("procfile read %s\n", filePointer->f_path.dentry->d_name.name); 
+34        *offset += len; 
+35    } 
+36 
+37    return ret; 
+38} 
+39 
+40#ifdef HAVE_PROC_OPS 
+41static const struct proc_ops proc_file_fops = { 
+42    .proc_read = procfile_read, 
+43}; 
+44#else 
+45static const struct file_operations proc_file_fops = { 
+46    .read = procfile_read, 
+47}; 
+48#endif 
+49 
+50static int __init procfs1_init(void) 
+51{ 
+52    Our_Proc_File = proc_create(procfs_name, 0644, NULL, &proc_file_fops); 
+53    if (NULL == Our_Proc_File) { 
+54        proc_remove(Our_Proc_File); 
+55        pr_alert("Error:Could not initialize /proc/%s\n", procfs_name); 
+56        return -ENOMEM; 
+57    } 
+58 
+59    pr_info("/proc/%s created\n", procfs_name); 
+60    return 0; 
+61} 
+62 
+63static void __exit procfs1_exit(void) 
+64{ 
+65    proc_remove(Our_Proc_File); 
+66    pr_info("/proc/%s removed\n", procfs_name); 
+67} 
+68 
+69module_init(procfs1_init); 
+70module_exit(procfs1_exit); 
+71 
+72MODULE_LICENSE("GPL");
    +

    0.7.1 The proc_ops Structure

    -

    The proc_ops +

    The proc_ops structure is defined in include/linux/proc_fs.h in Linux v5.6+. In older kernels, it used file_operations for custom hooks in /proc file system, but it contains some @@ -1696,10 +1702,10 @@ performance. For example, the file which never disappears in proc_flag as PROC_ENTRY_PERMANENT to save 2 atomic ops, 1 allocation, 1 free in per open/read/close sequence. -

    +

    0.7.2 Read and Write a /proc File

    -

    We have seen a very simple example for a /proc file where we only read +

    We have seen a very simple example for a /proc file where we only read the file /proc/helloworld. It is also possible to write in a /proc file. It works the same way as read, a function is called when the /proc file is written. But there is a little difference with read, data comes from @@ -1707,7 +1713,7 @@ user, so you have to import data from user space to kernel space (with copy_from_user or get_user ) -

    The reason for copy_from_user +

    The reason for copy_from_user or get_user is that Linux memory (on Intel architecture, it may be different under some @@ -1718,7 +1724,7 @@ not reference a unique location in memory, only a location in a memory segment, and you need to know which memory segment it is to be able to use it. There is one memory segment for the kernel, and one for each of the processes. -

    The only memory segment accessible to a process is its own, so when +

    The only memory segment accessible to a process is its own, so when writing regular programs to run as processes, there is no need to worry about segments. When you write a kernel module, normally you want to access the kernel memory segment, which is handled automatically by the system. @@ -1835,22 +1841,22 @@ because data is already in kernel space. 97module_exit(procfs2_exit); 98 99MODULE_LICENSE("GPL"); -

    +

    0.7.3 Manage /proc file with standard filesystem

    -

    We have seen how to read and write a /proc file with the /proc interface. But it is +

    We have seen how to read and write a /proc file with the /proc interface. But it is also possible to manage /proc file with inodes. The main concern is to use advanced functions, like permissions. -

    In Linux, there is a standard mechanism for file system registration. +

    In Linux, there is a standard mechanism for file system registration. Since every file system has to have its own functions to handle inode and file operations, there is a special structure to hold pointers to all those functions, struct inode_operations , which includes a pointer to struct proc_ops . -

    The difference between file and inode operations is that file operations deal with +

    The difference between file and inode operations is that file operations deal with the file itself whereas inode operations deal with ways of referencing the file, such as creating links to it. -

    In /proc, whenever we register a new file, we’re allowed to specify which +

    In /proc, whenever we register a new file, we’re allowed to specify which struct inode_operations will be used to access to it. This is the mechanism we use, a struct inode_operations @@ -1861,7 +1867,7 @@ creating links to it. which includes pointers to our procf_read and procfs_write functions. -

    Another interesting point here is the +

    Another interesting point here is the module_permission function. This function is called whenever a process tries to do something with the /proc file, and it can decide whether to allow access or not. Right now it is only @@ -1870,7 +1876,7 @@ pointer to a structure which includes information on the currently running process), but it could be based on anything we like, such as what other processes are doing with the same file, the time of day, or the last input we received. -

    It is important to note that the standard roles of read and write are reversed in +

    It is important to note that the standard roles of read and write are reversed in the kernel. Read functions are used for output, whereas write functions are used for input. The reason for that is that read and write refer to the user’s point of view — if a process reads something from the kernel, then the kernel needs to output it, and @@ -1985,21 +1991,21 @@ input. 105module_exit(procfs3_exit); 106 107MODULE_LICENSE("GPL"); -

    Still hungry for procfs examples? Well, first of all keep in mind, there are rumors +

    Still hungry for procfs examples? Well, first of all keep in mind, there are rumors around, claiming that procfs is on its way out, consider using sysfs instead. Consider using this mechanism, in case you want to document something kernel related yourself. -

    +

    0.7.4 Manage /proc file with seq_file

    -

    As we have seen, writing a /proc file may be quite “complex”. +

    As we have seen, writing a /proc file may be quite “complex”. So to help people writting /proc file, there is an API named seq_file - that helps formating a /proc file for output. It is based on sequence, + that helps formating a /proc file for output. It is based on sequence, which is composed of 3 functions: start(), next(), and stop(). The seq_file API starts a sequence when a user read the /proc file. -

    A sequence begins with the call of the function start(). If the return is a non +

    A sequence begins with the call of the function start(). If the return is a non NULL value, the function next() is called. This function is an iterator, the goal is to go through all the data. Each time next() is called, the function show() is also called. It writes data values in the buffer read by the user. The function next() is called until @@ -2008,7 +2014,7 @@ stop() is called. -

    BE CAREFUL: when a sequence is finished, another one starts. That means that +

    BE CAREFUL: when a sequence is finished, another one starts. That means that at the end of function stop(), the function start() is called again. This loop finishes when the function start() returns NULL. You can see a scheme of this in the Figure 1. @@ -2022,14 +2028,14 @@ Figure 1

    srYrsNNYtaeenetoooertusetupstrxr((ntn))( tis)istrr teeaNreNatUaUtmLtLmeLmLen?e?ntntt +

    srYrsNNYtaeenetoooertusetupstrxr((ntn))( tis)istrr teeaNreNatUaUtmLtLmeLmLen?e?ntntt

    Figure 1:How seq_file works
    -

    The seq_file +

    The seq_file provides basic functions for proc_ops , such as seq_read , seq_lseek @@ -2153,23 +2159,23 @@ the same way as in the previous example. 115module_exit(procfs4_exit); 116 117MODULE_LICENSE("GPL"); -

    If you want more information, you can read this web page: +

    If you want more information, you can read this web page:

    -

    You can also read the code of fs/seq_file.c in the linux kernel. +

    You can also read the code of fs/seq_file.c in the linux kernel.

    0.8 sysfs: Interacting with your module

    -

    sysfs allows you to interact with the running kernel from userspace by reading or +

    sysfs allows you to interact with the running kernel from userspace by reading or setting variables inside of modules. This can be useful for debugging purposes, or just as an interface for applications or scripts. You can find sysfs directories and files under the /sys directory on your system. 

    1ls -l /sys
    -

    An example of a hello world module which includes the creation of a variable +

    An example of a hello world module which includes the creation of a variable accessible via sysfs is given below.

    @@ -2238,7 +2244,7 @@ accessible via sysfs is given below. 63module_exit(mymodule_exit); 64 65MODULE_LICENSE("GPL"); -

    Make and install the module: +

    Make and install the module: 

    1make 
@@ -2246,36 +2252,36 @@ accessible via sysfs is given below.
                                                                   
 
                                                                   
-
       Check that it exists:
+
       Check that it exists:
 
    
 
    
    
    1sudo lsmod | grep hello_sysfs
    
-
       What is the current value of   myvariable
+
       What is the current value of   myvariable
  ?
 
    
 
    
    
    1cat /sys/kernel/mymodule/myvariable
    
-
       Set the value of   myvariable
+
       Set the value of   myvariable
  and check that it changed.
 
    
 
    
    
    1echo "32" > /sys/kernel/mymodule/myvariable 
 2cat /sys/kernel/mymodule/myvariable
    
-
       Finally, remove the test module:
+
       Finally, remove the test module:
 
    
 
    
    
    1sudo rmmod hello_sysfs
    
-
    
+
    
 
    
    
    0.9    Talking To Device Files
    
-
    Device files are supposed to represent physical devices. Most physical devices are
+
    Device files are supposed to represent physical devices. Most physical devices are
 used for output as well as input, so there has to be some mechanism for
 device drivers in the kernel to get the output to send to the device from
 processes. This is done by opening the device file for output and writing to it,
 just like writing to a file. In the following example, this is implemented by
  device_write
 .
-
       This is not always enough. Imagine you had a serial port connected to a modem
+
       This is not always enough. Imagine you had a serial port connected to a modem
 (even if you have an internal modem, it is still implemented from the CPU’s
 perspective as a serial port connected to a modem, so you don’t have to tax
 your imagination too hard). The natural thing to do would be to use the
@@ -2288,20 +2294,21 @@ received.
                                                                   
 
                                                                   
-
       The answer in Unix is to use a special function called
+
       The answer in Unix is to use a special function called
  ioctl
- (short for Input Output ConTroL). Every device can have its own ioctl commands,
-which can be read ioctl’s (to send information from a process to the kernel),
-write ioctl’s (to return information to a process), both or neither. Notice
+ (short for Input Output ConTroL). Every device can have its own
+ ioctl
+ commands, which can be read ioctl’s (to send information from a process to the
+kernel), write ioctl’s (to return information to a process), both or neither. Notice
 here the roles of read and write are reversed again, so in ioctl’s read is to
 send information to the kernel and write is to receive information from the
 kernel.
-
       The ioctl function is called with three parameters: the file descriptor of the
+
       The ioctl function is called with three parameters: the file descriptor of the
 appropriate device file, the ioctl number, and a parameter, which is of type
 long so you can use a cast to use it to pass anything. You will not be able
 to pass a structure this way, but you will be able to pass a pointer to the
 structure.
-
       The ioctl number encodes the major device number, the type of the ioctl, the
+
       The ioctl number encodes the major device number, the type of the ioctl, the
 command, and the type of the parameter. This ioctl number is usually created by a macro
 call (  _IO
 ,   _IOR
@@ -2312,504 +2319,504 @@ included both by the programs which will use ioctl (so they can generate the
 appropriate ioctl’s) and by the kernel module (so it can understand it). In the
 example below, the header file is chardev.h and the program which uses it is
 ioctl.c.
-
       If you want to use ioctls in your own kernel modules, it is best to receive an
+
       If you want to use ioctls in your own kernel modules, it is best to receive an
 official ioctl assignment, so if you accidentally get somebody else’s ioctls, or if they
 get yours, you’ll know something is wrong. For more information, consult the kernel
 source tree at Documentation/driver-api/ioctl.rst.
 
    
 
    
-   
    1/* 
-2 * chardev2.c - Create an input/output character device 
-3 */ 
-4 
-5#include <linux/cdev.h> 
-6#include <linux/delay.h> 
-7#include <linux/device.h> 
-8#include <linux/fs.h> 
-9#include <linux/init.h> 
-10#include <linux/irq.h> 
-11#include <linux/kernel.h> /* We are doing kernel work */ 
-12#include <linux/module.h> /* Specifically, a module */ 
-13#include <linux/poll.h> 
-14 
-15#include "chardev.h" 
-16#define SUCCESS 0 
-17#define DEVICE_NAME "char_dev" 
-18#define BUF_LEN 80 
-19 
-20/* Is the device open right now? Used to prevent concurent access into 
-21 * the same device 
-22 */ 
-23static int Device_Open = 0; 
-24 
-25/* The message the device will give when asked */ 
-26static char Message[BUF_LEN]; 
-27 
-28/* How far did the process reading the message get? Useful if the message 
-29 * is larger than the size of the buffer we get to fill in device_read. 
-30 */ 
-31static char *Message_Ptr; 
-32 
-33/* Major number assigned to our device driver */ 
-34static int Major; 
-35static struct class *cls; 
-36 
-37/* This is called whenever a process attempts to open the device file */ 
-38static int device_open(struct inode *inode, struct file *file) 
-39{ 
-40    pr_info("device_open(%p)\n", file); 
-41 
-42    /* We don't want to talk to two processes at the same time. */ 
-43    if (Device_Open) 
-44        return -EBUSY; 
-45 
-46    Device_Open++; 
-47    /* Initialize the message */ 
-48    Message_Ptr = Message; 
-49    try_module_get(THIS_MODULE); 
-50    return SUCCESS; 
-51} 
-52 
-53static int device_release(struct inode *inode, struct file *file) 
-54{ 
-55    pr_info("device_release(%p,%p)\n", inode, file); 
-56 
-57    /* We're now ready for our next caller */ 
-58    Device_Open--; 
-59 
-60    module_put(THIS_MODULE); 
-61    return SUCCESS; 
-62} 
-63 
-64/* This function is called whenever a process which has already opened the 
-65 * device file attempts to read from it. 
-66 */ 
-67static ssize_t device_read(struct file *file,   /* see include/linux/fs.h   */ 
-68                           char __user *buffer, /* buffer to be filled  */ 
-69                           size_t length,       /* length of the buffer     */ 
-70                           loff_t *offset) 
-71{ 
-72    /* Number of bytes actually written to the buffer */ 
-73    int bytes_read = 0; 
-74 
-75    pr_info("device_read(%p,%p,%ld)\n", file, buffer, length); 
-76 
-77    /* If at the end of message, return 0 (which signifies end of file). */ 
-78    if (*Message_Ptr == 0) 
-79        return 0; 
-80 
-81    /* Actually put the data into the buffer */ 
-82    while (length && *Message_Ptr) { 
-83        /* Because the buffer is in the user data segment, not the kernel 
-84         * data segment, assignment would not work. Instead, we have to 
-85         * use put_user which copies data from the kernel data segment to 
-86         * the user data segment. 
-87         */ 
-88        put_user(*(Message_Ptr++), buffer++); 
-89        length--; 
-90        bytes_read++; 
-91    } 
-92 
-93    pr_info("Read %d bytes, %ld left\n", bytes_read, length); 
-94 
-95    /* Read functions are supposed to return the number of bytes actually 
-96     * inserted into the buffer. 
-97     */ 
-98    return bytes_read; 
-99} 
-100 
-101/* called when somebody tries to write into our device file. */ 
-102static ssize_t device_write(struct file *file, 
-103                            const char __user *buffer, 
-104                            size_t length, 
-105                            loff_t *offset) 
-106{ 
-107    int i; 
-108 
-109    pr_info("device_write(%p,%s,%ld)", file, buffer, length); 
-110 
-111    for (i = 0; i < length && i < BUF_LEN; i++) 
-112        get_user(Message[i], buffer + i); 
-113 
-114    Message_Ptr = Message; 
-115 
-116    /* Again, return the number of input characters used. */ 
-117    return i; 
-118} 
-119 
-120/* This function is called whenever a process tries to do an ioctl on our 
-121 * device file. We get two extra parameters (additional to the inode and file 
-122 * structures, which all device functions get): the number of the ioctl called 
-123 * and the parameter given to the ioctl function. 
-124 * 
-125 * If the ioctl is write or read/write (meaning output is returned to the 
-126 * calling process), the ioctl call returns the output of this function. 
-127 */ 
-128long device_ioctl(struct file *file,      /* ditto */ 
-129                  unsigned int ioctl_num, /* number and param for ioctl */ 
-130                  unsigned long ioctl_param) 
-131{ 
-132    int i; 
-133    char *temp; 
-134    char ch; 
-135 
-136    /* Switch according to the ioctl called */ 
-137    switch (ioctl_num) { 
-138    case IOCTL_SET_MSG: 
-139        /* Receive a pointer to a message (in user space) and set that to 
-140         * be the device's message.  Get the parameter given to ioctl by 
-141         * the process. 
-142         */ 
-143        temp = (char *) ioctl_param; 
-144 
-145        /* Find the length of the message */ 
-146        get_user(ch, temp); 
-147        for (i = 0; ch && i < BUF_LEN; i++, temp++) 
-148            get_user(ch, temp); 
-149 
-150        device_write(file, (char *) ioctl_param, i, 0); 
-151        break; 
-152 
-153    case IOCTL_GET_MSG: 
-154        /* Give the current message to the calling process - the parameter 
-155         * we got is a pointer, fill it. 
-156         */ 
-157        i = device_read(file, (char *) ioctl_param, 99, 0); 
-158 
-159        /* Put a zero at the end of the buffer, so it will be properly 
-160         * terminated. 
-161         */ 
-162        put_user('\0', (char *) ioctl_param + i); 
-163        break; 
-164 
-165    case IOCTL_GET_NTH_BYTE: 
-166        /* This ioctl is both input (ioctl_param) and output (the return 
-167         * value of this function). 
-168         */ 
-169        return Message[ioctl_param]; 
-170        break; 
-171    } 
-172 
-173    return SUCCESS; 
-174} 
-175 
-176/* Module Declarations */ 
-177 
-178/* This structure will hold the functions to be called when a process does 
-179 * something to the device we created. Since a pointer to this structure 
-180 * is kept in the devices table, it can't be local to init_module. NULL is 
-181 * for unimplemented functions. 
-182 */ 
-183struct file_operations Fops = { 
-184    .read = device_read, 
-185    .write = device_write, 
-186    .unlocked_ioctl = device_ioctl, 
-187    .open = device_open, 
-188    .release = device_release, /* a.k.a. close */ 
-189}; 
-190 
-191/* Initialize the module - Register the character device */ 
-192static int __init chardev2_init(void) 
-193{ 
-194    /* Register the character device (atleast try) */ 
-195    int ret_val = register_chrdev(MAJOR_NUM, DEVICE_NAME, &Fops); 
-196 
-197    /* Negative values signify an error */ 
-198    if (ret_val < 0) { 
-199        pr_alert("%s failed with %d\n", 
-200                 "Sorry, registering the character device ", ret_val); 
-201        return ret_val; 
-202    } 
-203 
-204    Major = ret_val; 
-205 
-206    cls = class_create(THIS_MODULE, DEVICE_FILE_NAME); 
-207    device_create(cls, NULL, MKDEV(Major, MAJOR_NUM), NULL, DEVICE_FILE_NAME); 
-208 
-209    pr_info("Device created on /dev/%s\n", DEVICE_FILE_NAME); 
-210 
-211    return 0; 
-212} 
-213 
-214/* Cleanup - unregister the appropriate file from /proc */ 
-215static void __exit chardev2_exit(void) 
-216{ 
-217    device_destroy(cls, MKDEV(Major, 0)); 
-218    class_destroy(cls); 
-219 
-220    /* Unregister the device */ 
-221    unregister_chrdev(Major, DEVICE_NAME); 
-222} 
-223 
-224module_init(chardev2_init); 
-225module_exit(chardev2_exit); 
-226 
-227MODULE_LICENSE("GPL");
    
+   
    1/* 
+2 * chardev2.c - Create an input/output character device 
+3 */ 
+4 
+5#include <linux/cdev.h> 
+6#include <linux/delay.h> 
+7#include <linux/device.h> 
+8#include <linux/fs.h> 
+9#include <linux/init.h> 
+10#include <linux/irq.h> 
+11#include <linux/kernel.h> /* We are doing kernel work */ 
+12#include <linux/module.h> /* Specifically, a module */ 
+13#include <linux/poll.h> 
+14 
+15#include "chardev.h" 
+16#define SUCCESS 0 
+17#define DEVICE_NAME "char_dev" 
+18#define BUF_LEN 80 
+19 
+20/* Is the device open right now? Used to prevent concurent access into 
+21 * the same device 
+22 */ 
+23static int Device_Open = 0; 
+24 
+25/* The message the device will give when asked */ 
+26static char Message[BUF_LEN]; 
+27 
+28/* How far did the process reading the message get? Useful if the message 
+29 * is larger than the size of the buffer we get to fill in device_read. 
+30 */ 
+31static char *Message_Ptr; 
+32 
+33/* Major number assigned to our device driver */ 
+34static int Major; 
+35static struct class *cls; 
+36 
+37/* This is called whenever a process attempts to open the device file */ 
+38static int device_open(struct inode *inode, struct file *file) 
+39{ 
+40    pr_info("device_open(%p)\n", file); 
+41 
+42    /* We don't want to talk to two processes at the same time. */ 
+43    if (Device_Open) 
+44        return -EBUSY; 
+45 
+46    Device_Open++; 
+47    /* Initialize the message */ 
+48    Message_Ptr = Message; 
+49    try_module_get(THIS_MODULE); 
+50    return SUCCESS; 
+51} 
+52 
+53static int device_release(struct inode *inode, struct file *file) 
+54{ 
+55    pr_info("device_release(%p,%p)\n", inode, file); 
+56 
+57    /* We're now ready for our next caller */ 
+58    Device_Open--; 
+59 
+60    module_put(THIS_MODULE); 
+61    return SUCCESS; 
+62} 
+63 
+64/* This function is called whenever a process which has already opened the 
+65 * device file attempts to read from it. 
+66 */ 
+67static ssize_t device_read(struct file *file,   /* see include/linux/fs.h   */ 
+68                           char __user *buffer, /* buffer to be filled  */ 
+69                           size_t length,       /* length of the buffer     */ 
+70                           loff_t *offset) 
+71{ 
+72    /* Number of bytes actually written to the buffer */ 
+73    int bytes_read = 0; 
+74 
+75    pr_info("device_read(%p,%p,%ld)\n", file, buffer, length); 
+76 
+77    /* If at the end of message, return 0 (which signifies end of file). */ 
+78    if (*Message_Ptr == 0) 
+79        return 0; 
+80 
+81    /* Actually put the data into the buffer */ 
+82    while (length && *Message_Ptr) { 
+83        /* Because the buffer is in the user data segment, not the kernel 
+84         * data segment, assignment would not work. Instead, we have to 
+85         * use put_user which copies data from the kernel data segment to 
+86         * the user data segment. 
+87         */ 
+88        put_user(*(Message_Ptr++), buffer++); 
+89        length--; 
+90        bytes_read++; 
+91    } 
+92 
+93    pr_info("Read %d bytes, %ld left\n", bytes_read, length); 
+94 
+95    /* Read functions are supposed to return the number of bytes actually 
+96     * inserted into the buffer. 
+97     */ 
+98    return bytes_read; 
+99} 
+100 
+101/* called when somebody tries to write into our device file. */ 
+102static ssize_t device_write(struct file *file, 
+103                            const char __user *buffer, 
+104                            size_t length, 
+105                            loff_t *offset) 
+106{ 
+107    int i; 
+108 
+109    pr_info("device_write(%p,%s,%ld)", file, buffer, length); 
+110 
+111    for (i = 0; i < length && i < BUF_LEN; i++) 
+112        get_user(Message[i], buffer + i); 
+113 
+114    Message_Ptr = Message; 
+115 
+116    /* Again, return the number of input characters used. */ 
+117    return i; 
+118} 
+119 
+120/* This function is called whenever a process tries to do an ioctl on our 
+121 * device file. We get two extra parameters (additional to the inode and file 
+122 * structures, which all device functions get): the number of the ioctl called 
+123 * and the parameter given to the ioctl function. 
+124 * 
+125 * If the ioctl is write or read/write (meaning output is returned to the 
+126 * calling process), the ioctl call returns the output of this function. 
+127 */ 
+128long device_ioctl(struct file *file,      /* ditto */ 
+129                  unsigned int ioctl_num, /* number and param for ioctl */ 
+130                  unsigned long ioctl_param) 
+131{ 
+132    int i; 
+133    char *temp; 
+134    char ch; 
+135 
+136    /* Switch according to the ioctl called */ 
+137    switch (ioctl_num) { 
+138    case IOCTL_SET_MSG: 
+139        /* Receive a pointer to a message (in user space) and set that to 
+140         * be the device's message.  Get the parameter given to ioctl by 
+141         * the process. 
+142         */ 
+143        temp = (char *) ioctl_param; 
+144 
+145        /* Find the length of the message */ 
+146        get_user(ch, temp); 
+147        for (i = 0; ch && i < BUF_LEN; i++, temp++) 
+148            get_user(ch, temp); 
+149 
+150        device_write(file, (char *) ioctl_param, i, 0); 
+151        break; 
+152 
+153    case IOCTL_GET_MSG: 
+154        /* Give the current message to the calling process - the parameter 
+155         * we got is a pointer, fill it. 
+156         */ 
+157        i = device_read(file, (char *) ioctl_param, 99, 0); 
+158 
+159        /* Put a zero at the end of the buffer, so it will be properly 
+160         * terminated. 
+161         */ 
+162        put_user('\0', (char *) ioctl_param + i); 
+163        break; 
+164 
+165    case IOCTL_GET_NTH_BYTE: 
+166        /* This ioctl is both input (ioctl_param) and output (the return 
+167         * value of this function). 
+168         */ 
+169        return Message[ioctl_param]; 
+170        break; 
+171    } 
+172 
+173    return SUCCESS; 
+174} 
+175 
+176/* Module Declarations */ 
+177 
+178/* This structure will hold the functions to be called when a process does 
+179 * something to the device we created. Since a pointer to this structure 
+180 * is kept in the devices table, it can't be local to init_module. NULL is 
+181 * for unimplemented functions. 
+182 */ 
+183struct file_operations Fops = { 
+184    .read = device_read, 
+185    .write = device_write, 
+186    .unlocked_ioctl = device_ioctl, 
+187    .open = device_open, 
+188    .release = device_release, /* a.k.a. close */ 
+189}; 
+190 
+191/* Initialize the module - Register the character device */ 
+192static int __init chardev2_init(void) 
+193{ 
+194    /* Register the character device (atleast try) */ 
+195    int ret_val = register_chrdev(MAJOR_NUM, DEVICE_NAME, &Fops); 
+196 
+197    /* Negative values signify an error */ 
+198    if (ret_val < 0) { 
+199        pr_alert("%s failed with %d\n", 
+200                 "Sorry, registering the character device ", ret_val); 
+201        return ret_val; 
+202    } 
+203 
+204    Major = ret_val; 
+205 
+206    cls = class_create(THIS_MODULE, DEVICE_FILE_NAME); 
+207    device_create(cls, NULL, MKDEV(Major, MAJOR_NUM), NULL, DEVICE_FILE_NAME); 
+208 
+209    pr_info("Device created on /dev/%s\n", DEVICE_FILE_NAME); 
+210 
+211    return 0; 
+212} 
+213 
+214/* Cleanup - unregister the appropriate file from /proc */ 
+215static void __exit chardev2_exit(void) 
+216{ 
+217    device_destroy(cls, MKDEV(Major, 0)); 
+218    class_destroy(cls); 
+219 
+220    /* Unregister the device */ 
+221    unregister_chrdev(Major, DEVICE_NAME); 
+222} 
+223 
+224module_init(chardev2_init); 
+225module_exit(chardev2_exit); 
+226 
+227MODULE_LICENSE("GPL");
    
 
 
    
 
    
-   
    1/* 
-2 * chardev.h - the header file with the ioctl definitions. 
-3 * 
-4 * The declarations here have to be in a header file, because they need 
-5 * to be known both to the kernel module (in chardev.c) and the process 
-6 * calling ioctl (ioctl.c). 
-7 */ 
-8 
-9#ifndef CHARDEV_H 
-10#define CHARDEV_H 
-11 
-12#include <linux/ioctl.h> 
-13 
-14/* The major device number. We can not rely on dynamic registration 
-15 * any more, because ioctls need to know it. 
-16 */ 
-17#define MAJOR_NUM 100 
-18 
-19/* Set the message of the device driver */ 
-20#define IOCTL_SET_MSG _IOW(MAJOR_NUM, 0, char *) 
-21/* _IOW means that we are creating an ioctl command number for passing 
-22 * information from a user process to the kernel module. 
-23 * 
-24 * The first arguments, MAJOR_NUM, is the major device number we are using. 
-25 * 
-26 * The second argument is the number of the command (there could be several 
-27 * with different meanings). 
-28 * 
-29 * The third argument is the type we want to get from the process to the 
-30 * kernel. 
-31 */ 
-32 
-33/* Get the message of the device driver */ 
-34#define IOCTL_GET_MSG _IOR(MAJOR_NUM, 1, char *) 
-35/* This IOCTL is used for output, to get the message of the device driver. 
-36 * However, we still need the buffer to place the message in to be input, 
-37 * as it is allocated by the process. 
-38 */ 
-39 
-40/* Get the n'th byte of the message */ 
-41#define IOCTL_GET_NTH_BYTE _IOWR(MAJOR_NUM, 2, int) 
-42/* The IOCTL is used for both input and output. It receives from the user 
-43 * a number, n, and returns Message[n]. 
-44 */ 
-45 
-46/* The name of the device file */ 
-47#define DEVICE_FILE_NAME "char_dev" 
-48 
-49#endif
    
+   
    1/* 
+2 * chardev.h - the header file with the ioctl definitions. 
+3 * 
+4 * The declarations here have to be in a header file, because they need 
+5 * to be known both to the kernel module (in chardev.c) and the process 
+6 * calling ioctl (ioctl.c). 
+7 */ 
+8 
+9#ifndef CHARDEV_H 
+10#define CHARDEV_H 
+11 
+12#include <linux/ioctl.h> 
+13 
+14/* The major device number. We can not rely on dynamic registration 
+15 * any more, because ioctls need to know it. 
+16 */ 
+17#define MAJOR_NUM 100 
+18 
+19/* Set the message of the device driver */ 
+20#define IOCTL_SET_MSG _IOW(MAJOR_NUM, 0, char *) 
+21/* _IOW means that we are creating an ioctl command number for passing 
+22 * information from a user process to the kernel module. 
+23 * 
+24 * The first arguments, MAJOR_NUM, is the major device number we are using. 
+25 * 
+26 * The second argument is the number of the command (there could be several 
+27 * with different meanings). 
+28 * 
+29 * The third argument is the type we want to get from the process to the 
+30 * kernel. 
+31 */ 
+32 
+33/* Get the message of the device driver */ 
+34#define IOCTL_GET_MSG _IOR(MAJOR_NUM, 1, char *) 
+35/* This IOCTL is used for output, to get the message of the device driver. 
+36 * However, we still need the buffer to place the message in to be input, 
+37 * as it is allocated by the process. 
+38 */ 
+39 
+40/* Get the n'th byte of the message */ 
+41#define IOCTL_GET_NTH_BYTE _IOWR(MAJOR_NUM, 2, int) 
+42/* The IOCTL is used for both input and output. It receives from the user 
+43 * a number, n, and returns Message[n]. 
+44 */ 
+45 
+46/* The name of the device file */ 
+47#define DEVICE_FILE_NAME "char_dev" 
+48 
+49#endif
    
 
 
    
 
    
-   
    1/* 
-2 * ioctl.c 
-3 */ 
-4#include <linux/cdev.h> 
-5#include <linux/fs.h> 
-6#include <linux/init.h> 
-7#include <linux/ioctl.h> 
-8#include <linux/module.h> 
-9#include <linux/slab.h> 
-10#include <linux/uaccess.h> 
-11 
-12struct ioctl_arg { 
-13    unsigned int reg; 
-14    unsigned int val; 
-15}; 
-16 
-17/* Documentation/ioctl/ioctl-number.txt */ 
-18#define IOC_MAGIC '\x66' 
-19 
-20#define IOCTL_VALSET _IOW(IOC_MAGIC, 0, struct ioctl_arg) 
-21#define IOCTL_VALGET _IOR(IOC_MAGIC, 1, struct ioctl_arg) 
-22#define IOCTL_VALGET_NUM _IOR(IOC_MAGIC, 2, int) 
-23#define IOCTL_VALSET_NUM _IOW(IOC_MAGIC, 3, int) 
-24 
-25#define IOCTL_VAL_MAXNR 3 
-26#define DRIVER_NAME "ioctltest" 
-27 
-28static unsigned int test_ioctl_major = 0; 
-29static unsigned int num_of_dev = 1; 
-30static struct cdev test_ioctl_cdev; 
-31static int ioctl_num = 0; 
-32 
-33struct test_ioctl_data { 
-34    unsigned char val; 
-35    rwlock_t lock; 
-36}; 
-37 
-38static long test_ioctl_ioctl(struct file *filp, 
-39                             unsigned int cmd, 
-40                             unsigned long arg) 
-41{ 
-42    struct test_ioctl_data *ioctl_data = filp->private_data; 
-43    int retval = 0; 
-44    unsigned char val; 
-45    struct ioctl_arg data; 
-46    memset(&data, 0, sizeof(data)); 
-47 
-48    switch (cmd) { 
-49    case IOCTL_VALSET: 
-50        if (copy_from_user(&data, (int __user *) arg, sizeof(data))) { 
-51            retval = -EFAULT; 
-52            goto done; 
-53        } 
-54 
-55        pr_alert("IOCTL set val:%x .\n", data.val); 
-56        write_lock(&ioctl_data->lock); 
-57        ioctl_data->val = data.val; 
-58        write_unlock(&ioctl_data->lock); 
-59        break; 
-60 
-61    case IOCTL_VALGET: 
-62        read_lock(&ioctl_data->lock); 
-63        val = ioctl_data->val; 
-64        read_unlock(&ioctl_data->lock); 
-65        data.val = val; 
-66 
-67        if (copy_to_user((int __user *) arg, &data, sizeof(data))) { 
-68            retval = -EFAULT; 
-69            goto done; 
-70        } 
-71 
-72        break; 
-73 
-74    case IOCTL_VALGET_NUM: 
-75        retval = __put_user(ioctl_num, (int __user *) arg); 
-76        break; 
-77 
-78    case IOCTL_VALSET_NUM: 
-79        ioctl_num = arg; 
-80        break; 
-81 
-82    default: 
-83        retval = -ENOTTY; 
-84    } 
-85 
-86done: 
-87    return retval; 
-88} 
-89 
-90ssize_t test_ioctl_read(struct file *filp, 
-91                        char __user *buf, 
-92                        size_t count, 
-93                        loff_t *f_pos) 
-94{ 
-95    struct test_ioctl_data *ioctl_data = filp->private_data; 
-96    unsigned char val; 
-97    int retval; 
-98    int i = 0; 
-99    read_lock(&ioctl_data->lock); 
-100    val = ioctl_data->val; 
-101    read_unlock(&ioctl_data->lock); 
-102 
-103    for (; i < count; i++) { 
-104        if (copy_to_user(&buf[i], &val, 1)) { 
-105            retval = -EFAULT; 
-106            goto out; 
-107        } 
-108    } 
-109 
-110    retval = count; 
-111out: 
-112    return retval; 
-113} 
-114 
-115static int test_ioctl_close(struct inode *inode, struct file *filp) 
-116{ 
-117    pr_alert("%s call.\n", __func__); 
-118 
-119    if (filp->private_data) { 
-120        kfree(filp->private_data); 
-121        filp->private_data = NULL; 
-122    } 
-123 
-124    return 0; 
-125} 
-126 
-127static int test_ioctl_open(struct inode *inode, struct file *filp) 
-128{ 
-129    struct test_ioctl_data *ioctl_data; 
-130    pr_alert("%s call.\n", __func__); 
-131    ioctl_data = kmalloc(sizeof(struct test_ioctl_data), GFP_KERNEL); 
-132 
-133    if (ioctl_data == NULL) { 
-134        return -ENOMEM; 
-135    } 
-136 
-137    rwlock_init(&ioctl_data->lock); 
-138    ioctl_data->val = 0xFF; 
-139    filp->private_data = ioctl_data; 
-140    return 0; 
-141} 
-142 
-143struct file_operations fops = { 
-144    .owner = THIS_MODULE, 
-145    .open = test_ioctl_open, 
-146    .release = test_ioctl_close, 
-147    .read = test_ioctl_read, 
-148    .unlocked_ioctl = test_ioctl_ioctl, 
-149}; 
-150 
-151static int ioctl_init(void) 
-152{ 
-153    dev_t dev = MKDEV(test_ioctl_major, 0); 
-154    int alloc_ret = 0; 
-155    int cdev_ret = 0; 
-156    alloc_ret = alloc_chrdev_region(&dev, 0, num_of_dev, DRIVER_NAME); 
-157 
-158    if (alloc_ret) { 
-159        goto error; 
-160    } 
-161 
-162    test_ioctl_major = MAJOR(dev); 
-163    cdev_init(&test_ioctl_cdev, &fops); 
-164    cdev_ret = cdev_add(&test_ioctl_cdev, dev, num_of_dev); 
-165 
-166    if (cdev_ret) { 
-167        goto error; 
-168    } 
-169 
-170    pr_alert("%s driver(major: %d) installed.\n", DRIVER_NAME, 
-171             test_ioctl_major); 
-172    return 0; 
-173error: 
-174 
-175    if (cdev_ret == 0) { 
-176        cdev_del(&test_ioctl_cdev); 
-177    } 
-178 
-179    if (alloc_ret == 0) { 
-180        unregister_chrdev_region(dev, num_of_dev); 
-181    } 
-182 
-183    return -1; 
-184} 
-185 
-186static void ioctl_exit(void) 
-187{ 
-188    dev_t dev = MKDEV(test_ioctl_major, 0); 
-189    cdev_del(&test_ioctl_cdev); 
-190    unregister_chrdev_region(dev, num_of_dev); 
-191    pr_alert("%s driver removed.\n", DRIVER_NAME); 
-192} 
-193 
-194module_init(ioctl_init); 
-195module_exit(ioctl_exit); 
-196 
-197MODULE_LICENSE("GPL"); 
-198MODULE_DESCRIPTION("This is test_ioctl module");
    
-
    
+   
    1/* 
+2 * ioctl.c 
+3 */ 
+4#include <linux/cdev.h> 
+5#include <linux/fs.h> 
+6#include <linux/init.h> 
+7#include <linux/ioctl.h> 
+8#include <linux/module.h> 
+9#include <linux/slab.h> 
+10#include <linux/uaccess.h> 
+11 
+12struct ioctl_arg { 
+13    unsigned int reg; 
+14    unsigned int val; 
+15}; 
+16 
+17/* Documentation/ioctl/ioctl-number.txt */ 
+18#define IOC_MAGIC '\x66' 
+19 
+20#define IOCTL_VALSET _IOW(IOC_MAGIC, 0, struct ioctl_arg) 
+21#define IOCTL_VALGET _IOR(IOC_MAGIC, 1, struct ioctl_arg) 
+22#define IOCTL_VALGET_NUM _IOR(IOC_MAGIC, 2, int) 
+23#define IOCTL_VALSET_NUM _IOW(IOC_MAGIC, 3, int) 
+24 
+25#define IOCTL_VAL_MAXNR 3 
+26#define DRIVER_NAME "ioctltest" 
+27 
+28static unsigned int test_ioctl_major = 0; 
+29static unsigned int num_of_dev = 1; 
+30static struct cdev test_ioctl_cdev; 
+31static int ioctl_num = 0; 
+32 
+33struct test_ioctl_data { 
+34    unsigned char val; 
+35    rwlock_t lock; 
+36}; 
+37 
+38static long test_ioctl_ioctl(struct file *filp, 
+39                             unsigned int cmd, 
+40                             unsigned long arg) 
+41{ 
+42    struct test_ioctl_data *ioctl_data = filp->private_data; 
+43    int retval = 0; 
+44    unsigned char val; 
+45    struct ioctl_arg data; 
+46    memset(&data, 0, sizeof(data)); 
+47 
+48    switch (cmd) { 
+49    case IOCTL_VALSET: 
+50        if (copy_from_user(&data, (int __user *) arg, sizeof(data))) { 
+51            retval = -EFAULT; 
+52            goto done; 
+53        } 
+54 
+55        pr_alert("IOCTL set val:%x .\n", data.val); 
+56        write_lock(&ioctl_data->lock); 
+57        ioctl_data->val = data.val; 
+58        write_unlock(&ioctl_data->lock); 
+59        break; 
+60 
+61    case IOCTL_VALGET: 
+62        read_lock(&ioctl_data->lock); 
+63        val = ioctl_data->val; 
+64        read_unlock(&ioctl_data->lock); 
+65        data.val = val; 
+66 
+67        if (copy_to_user((int __user *) arg, &data, sizeof(data))) { 
+68            retval = -EFAULT; 
+69            goto done; 
+70        } 
+71 
+72        break; 
+73 
+74    case IOCTL_VALGET_NUM: 
+75        retval = __put_user(ioctl_num, (int __user *) arg); 
+76        break; 
+77 
+78    case IOCTL_VALSET_NUM: 
+79        ioctl_num = arg; 
+80        break; 
+81 
+82    default: 
+83        retval = -ENOTTY; 
+84    } 
+85 
+86done: 
+87    return retval; 
+88} 
+89 
+90ssize_t test_ioctl_read(struct file *filp, 
+91                        char __user *buf, 
+92                        size_t count, 
+93                        loff_t *f_pos) 
+94{ 
+95    struct test_ioctl_data *ioctl_data = filp->private_data; 
+96    unsigned char val; 
+97    int retval; 
+98    int i = 0; 
+99    read_lock(&ioctl_data->lock); 
+100    val = ioctl_data->val; 
+101    read_unlock(&ioctl_data->lock); 
+102 
+103    for (; i < count; i++) { 
+104        if (copy_to_user(&buf[i], &val, 1)) { 
+105            retval = -EFAULT; 
+106            goto out; 
+107        } 
+108    } 
+109 
+110    retval = count; 
+111out: 
+112    return retval; 
+113} 
+114 
+115static int test_ioctl_close(struct inode *inode, struct file *filp) 
+116{ 
+117    pr_alert("%s call.\n", __func__); 
+118 
+119    if (filp->private_data) { 
+120        kfree(filp->private_data); 
+121        filp->private_data = NULL; 
+122    } 
+123 
+124    return 0; 
+125} 
+126 
+127static int test_ioctl_open(struct inode *inode, struct file *filp) 
+128{ 
+129    struct test_ioctl_data *ioctl_data; 
+130    pr_alert("%s call.\n", __func__); 
+131    ioctl_data = kmalloc(sizeof(struct test_ioctl_data), GFP_KERNEL); 
+132 
+133    if (ioctl_data == NULL) { 
+134        return -ENOMEM; 
+135    } 
+136 
+137    rwlock_init(&ioctl_data->lock); 
+138    ioctl_data->val = 0xFF; 
+139    filp->private_data = ioctl_data; 
+140    return 0; 
+141} 
+142 
+143struct file_operations fops = { 
+144    .owner = THIS_MODULE, 
+145    .open = test_ioctl_open, 
+146    .release = test_ioctl_close, 
+147    .read = test_ioctl_read, 
+148    .unlocked_ioctl = test_ioctl_ioctl, 
+149}; 
+150 
+151static int ioctl_init(void) 
+152{ 
+153    dev_t dev = MKDEV(test_ioctl_major, 0); 
+154    int alloc_ret = 0; 
+155    int cdev_ret = 0; 
+156    alloc_ret = alloc_chrdev_region(&dev, 0, num_of_dev, DRIVER_NAME); 
+157 
+158    if (alloc_ret) { 
+159        goto error; 
+160    } 
+161 
+162    test_ioctl_major = MAJOR(dev); 
+163    cdev_init(&test_ioctl_cdev, &fops); 
+164    cdev_ret = cdev_add(&test_ioctl_cdev, dev, num_of_dev); 
+165 
+166    if (cdev_ret) { 
+167        goto error; 
+168    } 
+169 
+170    pr_alert("%s driver(major: %d) installed.\n", DRIVER_NAME, 
+171             test_ioctl_major); 
+172    return 0; 
+173error: 
+174 
+175    if (cdev_ret == 0) { 
+176        cdev_del(&test_ioctl_cdev); 
+177    } 
+178 
+179    if (alloc_ret == 0) { 
+180        unregister_chrdev_region(dev, num_of_dev); 
+181    } 
+182 
+183    return -1; 
+184} 
+185 
+186static void ioctl_exit(void) 
+187{ 
+188    dev_t dev = MKDEV(test_ioctl_major, 0); 
+189    cdev_del(&test_ioctl_cdev); 
+190    unregister_chrdev_region(dev, num_of_dev); 
+191    pr_alert("%s driver removed.\n", DRIVER_NAME); 
+192} 
+193 
+194module_init(ioctl_init); 
+195module_exit(ioctl_exit); 
+196 
+197MODULE_LICENSE("GPL"); 
+198MODULE_DESCRIPTION("This is test_ioctl module");
    
+
    
 
    
                                                                   
 
                                                                   
    
    0.10    System Calls
    
-
    So far, the only thing we’ve done was to use well defined kernel mechanisms to
+
    So far, the only thing we’ve done was to use well defined kernel mechanisms to
 register /proc files and device handlers. This is fine if you want to do something the
 kernel programmers thought you’d want, such as write a device driver. But what if
 you want to do something unusual, to change the behavior of the system in some
 way? Then, you are mostly on your own.
-
       If you are not being sensible and using a virtual machine then this is where kernel
+
       If you are not being sensible and using a virtual machine then this is where kernel
 programming can become hazardous. While writing the example below, I killed the
  open()
  system call. This meant I could not open any files, I could not run any
@@ -2821,7 +2828,7 @@ ensure you do not lose any files, even within a test environment, please run
  right before you do the   insmod
  and the   rmmod
 .
-
       Forget about /proc files, forget about device files. They are just minor details.
+
       Forget about /proc files, forget about device files. They are just minor details.
 Minutiae in the vast expanse of the universe. The real process to kernel
 communication mechanism, the one used by all processes, is system calls. When a
 process requests a service from the kernel (such as opening a file, forking to a new
@@ -2830,11 +2837,11 @@ change the behaviour of the kernel in interesting ways, this is the place to do
 it. By the way, if you want to see which system calls a program uses, run
  strace <arguments>
 .
-
       In general, a process is not supposed to be able to access the kernel. It can not
+
       In general, a process is not supposed to be able to access the kernel. It can not
 access kernel memory and it can’t call kernel functions. The hardware of the CPU
 enforces this (that is the reason why it is called “protected mode” or “page
 protection”).
-
       System calls are an exception to this general rule. What happens is that the
+
       System calls are an exception to this general rule. What happens is that the
 process fills the registers with the appropriate values and then calls a special
 instruction which jumps to a previously defined location in the kernel (of course, that
 location is readable by user processes, it is not writable by them). Under Intel CPUs,
@@ -2842,7 +2849,7 @@ this is done by means of interrupt 0x80. The hardware knows that once you jump t
 this location, you are no longer running in restricted user mode, but as the
 operating system kernel — and therefore you’re allowed to do whatever you
 want.
-
       The location in the kernel a process can jump to is called system_call. The
+
       The location in the kernel a process can jump to is called system_call. The
 procedure at that location checks the system call number, which tells the kernel what
 service the process requested. Then, it looks at the table of system calls
 (  sys_call_table
@@ -2855,7 +2862,7 @@ different process, if the process time ran out). If you want to read this code,
 at the source file arch/$(architecture)/kernel/entry.S, after the line
  ENTRY(system_call)
 .
-
       So, if we want to change the way a certain system call works, what we need to do
+
       So, if we want to change the way a certain system call works, what we need to do
 is to write our own function to implement it (usually by adding a bit of our own
 code, and then calling the original function) and then change the pointer at
  sys_call_table
@@ -2863,7 +2870,7 @@ code, and then calling the original function) and then change the pointer at
 don’t want to leave the system in an unstable state, it’s important for
  cleanup_module
  to restore the table to its original state.
-
       The source code here is an example of such a kernel module. We want to “spy” on a certain
+
       The source code here is an example of such a kernel module. We want to “spy” on a certain
 user, and to   pr_info()
  a message whenever that user opens a file. Towards this end, we
 replace the system call to open a file with our own function, called
@@ -2873,7 +2880,7 @@ spy on, it calls   pr_info()
  to display the name of the file to be opened. Then, either way, it calls the
 original open() function with the same parameters, to actually open the
 file.
-
       The   init_module
+
       The   init_module
  function replaces the appropriate location in
  sys_call_table
  and keeps the original pointer in a variable. The
@@ -2891,7 +2898,7 @@ with   B_open
 , which will call what it thinks is the original system call,
  A_open
 , when it’s done.
-
       Now, if B is removed first, everything will be well — it will simply restore the system
+
       Now, if B is removed first, everything will be well — it will simply restore the system
 call to   A_open
 , which calls the original. However, if A is removed and then B is removed, the
 system will crash. A’s removal will restore the system call to the original,
@@ -2914,7 +2921,7 @@ problem. When A is removed, it sees that the system call was changed to
  will still try to call   A_open
  which is no longer there, so that even without removing B the system would
 crash.
-
       Note that all the related problems make syscall stealing unfeasiable for
+
       Note that all the related problems make syscall stealing unfeasiable for
 production use. In order to keep people from doing potential harmful things
  sys_call_table
  is no longer exported. This means, if you want to do something more than a mere
@@ -3065,13 +3072,13 @@ hand apply the patch.
 135module_exit(syscall_end); 
 136 
 137MODULE_LICENSE("GPL");
    -

    +

    0.11 Blocking Processes and threads

    -

    +

    0.11.1 Sleep

    -

    What do you do when somebody asks you for something you can not do right +

    What do you do when somebody asks you for something you can not do right away? If you are a human being and you are bothered by a human being, the only thing you can say is: "Not right now, I’m busy. Go away!". But if you are a kernel module and you are bothered by a process, you have another @@ -3082,21 +3089,21 @@ processes are being put to sleep by the kernel and woken up all the time (that is the way multiple processes appear to run on the same time on a single CPU). -

    This kernel module is an example of this. The file (called /proc/sleep) can only +

    This kernel module is an example of this. The file (called /proc/sleep) can only be opened by a single process at a time. If the file is already open, the kernel module calls wait_event_interruptible . The easiest way to keep a file open is to open it with: 

    1tail -f
    -

    This function changes the status of the task (a task is the kernel data structure +

    This function changes the status of the task (a task is the kernel data structure which holds information about a process and the system call it is in, if any) to TASK_INTERRUPTIBLE , which means that the task will not run until it is woken up somehow, and adds it to WaitQ, the queue of tasks waiting to access the file. Then, the function calls the scheduler to context switch to a different process, one which has some use for the CPU. -

    When a process is done with the file, it closes it, and +

    When a process is done with the file, it closes it, and module_close is called. That function wakes up all the processes in the queue (there’s no mechanism to only wake up one of them). It then returns and the process which just @@ -3106,20 +3113,20 @@ Eventually, one of the processes which was in the queue will be given control of the CPU by the scheduler. It starts at the point right after the call to module_interruptible_sleep_on . -

    This means that the process is still in kernel mode - as far as the process +

    This means that the process is still in kernel mode - as far as the process is concerned, it issued the open system call and the system call has not returned yet. The process does not know somebody else used the CPU for most of the time between the moment it issued the call and the moment it returned. -

    It can then proceed to set a global variable to tell all the other processes that the +

    It can then proceed to set a global variable to tell all the other processes that the file is still open and go on with its life. When the other processes get a piece of the CPU, they’ll see that global variable and go back to sleep. -

    So we will use tail -f +

    So we will use tail -f to keep the file open in the background, while trying to access it with another process (again in the background, so that we need not switch to a different vt). As soon as the first background process is killed with kill %1 , the second is woken up, is able to access the file and finally terminates. -

    To make our life more interesting, module_close +

    To make our life more interesting, module_close does not have a monopoly on waking up the processes which wait to access the file. A signal, such as Ctrl +c (SIGINT) can also wake up a process. This is because we used module_interruptible_sleep_on @@ -3129,11 +3136,11 @@ used module_interruptible_sleep_on instead, but that would have resulted in extremely angry users whose Ctrl+c’s are ignored. -

    In that case, we want to return with +

    In that case, we want to return with -EINTR immediately. This is important so users can, for example, kill the process before it receives the file. -

    There is one more point to remember. Some times processes don’t want to sleep, they want +

    There is one more point to remember. Some times processes don’t want to sleep, they want either to get what they want immediately, or to be told it cannot be done. Such processes use the O_NONBLOCK flag when opening the file. The kernel is supposed to respond by returning with the error @@ -3169,7 +3176,7 @@ $ cat_nonblock /proc/sleep Last input: $ -

    +

    1/* 
@@ -3453,14 +3460,14 @@ $
 57 
 58    return 0; 
 59}
    -

    +

    0.11.2 Completions

    -

    Sometimes one thing should happen before another within a module having multiple threads. +

    Sometimes one thing should happen before another within a module having multiple threads. Rather than using /bin/sleep commands, the kernel has another way to do this which allows timeouts or interrupts to also happen. -

    In the following example two threads are started, but one needs to start before +

    In the following example two threads are started, but one needs to start before another.

    @@ -3543,31 +3550,31 @@ another. 74 75MODULE_DESCRIPTION("Completions example"); 76MODULE_LICENSE("GPL"); -

    The machine +

    The machine structure stores the completion states for the two threads. At the exit point of each thread the respective completion state is updated, and wait_for_completion is used by the flywheel thread to ensure that it does not begin prematurely. -

    So even though flywheel_thread +

    So even though flywheel_thread is started first you should notice if you load this module and run dmesg that turning the crank always happens first because the flywheel thread waits for it to complete. -

    There are other variations upon the +

    There are other variations upon the wait_for_completion function, which include timeouts or being interrupted, but this basic mechanism is enough for many common situations without adding a lot of complexity. -

    +

    0.12 Avoiding Collisions and Deadlocks

    -

    If processes running on different CPUs or in different threads try to access the same +

    If processes running on different CPUs or in different threads try to access the same memory, then it is possible that strange things can happen or your system can lock up. To avoid this, various types of mutual exclusion kernel functions are available. These indicate if a section of code is "locked" or "unlocked" so that simultaneous attempts to run it can not happen.

    0.12.1 Mutex

    -

    You can use kernel mutexes (mutual exclusions) in much the same manner that you +

    You can use kernel mutexes (mutual exclusions) in much the same manner that you might deploy them in userland. This may be all that is needed to avoid collisions in most cases.

    @@ -3613,10 +3620,10 @@ most cases. 39 40MODULE_DESCRIPTION("Mutex example"); 41MODULE_LICENSE("GPL"); -

    +

    0.12.2 Spinlocks

    -

    As the name suggests, spinlocks lock up the CPU that the code is running on, +

    As the name suggests, spinlocks lock up the CPU that the code is running on, taking 100% of its resources. Because of this you should only use the spinlock @@ -3624,7 +3631,7 @@ taking 100% of its resources. Because of this you should only use the spinlock mechanism around code which is likely to take no more than a few milliseconds to run and so will not noticably slow anything down from the user’s point of view. -

    The example here is "irq safe" in that if interrupts happen during the lock then +

    The example here is "irq safe" in that if interrupts happen during the lock then they will not be forgotten and will activate when the unlock happens, using the flags variable to retain their state. @@ -3693,10 +3700,10 @@ they will not be forgotten and will activate when the unlock happens, using the 61 62MODULE_DESCRIPTION("Spinlock example"); 63MODULE_LICENSE("GPL"); -

    +

    0.12.3 Read and write locks

    -

    Read and write locks are specialised kinds of spinlocks so that you can exclusively +

    Read and write locks are specialised kinds of spinlocks so that you can exclusively read from something or write to something. Like the earlier spinlocks example the one below shows an "irq safe" situation in which if other functions were triggered from irqs which might also read and write to whatever you are concerned with @@ -3761,14 +3768,14 @@ module. 53 54MODULE_DESCRIPTION("Read/Write locks example"); 55MODULE_LICENSE("GPL"); -

    Of course, if you know for sure that there are no functions triggered by irqs +

    Of course, if you know for sure that there are no functions triggered by irqs which could possibly interfere with your logic then you can use the simpler read_lock(&myrwlock) and read_unlock(&myrwlock) or the corresponding write functions.

    0.12.4 Atomic operations

    -

    If you are doing simple arithmetic: adding, subtracting or bitwise operations then +

    If you are doing simple arithmetic: adding, subtracting or bitwise operations then there is another way in the multi-CPU and multi-hyperthreaded world to stop other parts of the system from messing with your mojo. By using atomic operations you can be confident that your addition, subtraction or bit flip did actually happen @@ -3853,21 +3860,21 @@ below. -

    +

    0.13 Replacing Print Macros

    -

    +

    0.13.1 Replacement

    -

    In Section 2, I said that X Window System and kernel module programming do not +

    In Section 2, I said that X Window System and kernel module programming do not mix. That is true for developing kernel modules, but in actual use, you want to be able to send messages to whichever tty the command to load the module came from. -

    "tty" is an abbreviation of teletype: originally a combination keyboard-printer +

    "tty" is an abbreviation of teletype: originally a combination keyboard-printer used to communicate with a Unix system, and today an abstraction for the text stream used for a Unix program, whether it is a physical terminal, an xterm on an X display, a network connection used with ssh, etc. -

    The way this is done is by using current, a pointer to the currently running task, +

    The way this is done is by using current, a pointer to the currently running task, to get the current task’s tty structure. Then, we look inside that tty structure to find a pointer to a string write function, which we use to write a string to the tty. @@ -3950,16 +3957,16 @@ tty. 75module_exit(print_string_exit); 76 77MODULE_LICENSE("GPL"); -

    +

    0.13.2 Flashing keyboard LEDs

    -

    In certain conditions, you may desire a simpler and more direct way to communicate +

    In certain conditions, you may desire a simpler and more direct way to communicate to the external world. Flashing keyboard LEDs can be such a solution: It is an immediate way to attract attention or to display a status condition. Keyboard LEDs are present on every hardware, they are always visible, they do not need any setup, and their use is rather simple and non-intrusive, compared to writing to a tty or a file. -

    The following source code illustrates a minimal kernel module which, when +

    The following source code illustrates a minimal kernel module which, when loaded, starts blinking the keyboard LEDs until it is unloaded.

    @@ -4055,7 +4062,7 @@ loaded, starts blinking the keyboard LEDs until it is unloaded. -

    If none of the examples in this chapter fit your debugging needs +

    If none of the examples in this chapter fit your debugging needs there might yet be some other tricks to try. Ever wondered what CONFIG_LL_DEBUG in make menuconfig is good for? If you activate that you get low level access to the @@ -4066,22 +4073,22 @@ over a serial line. If you find yourself porting the kernel to some new and former unsupported architecture, this is usually amongst the first things that should be implemented. Logging over a netconsole might also be worth a try. -

    While you have seen lots of stuff that can be used to aid debugging here, there are +

    While you have seen lots of stuff that can be used to aid debugging here, there are some things to be aware of. Debugging is almost always intrusive. Adding debug code can change the situation enough to make the bug seem to dissappear. Thus you should try to keep debug code to a minimum and make sure it does not show up in production code. -

    +

    0.14 Scheduling Tasks

    -

    There are two main ways of running tasks: tasklets and work queues. Tasklets are a +

    There are two main ways of running tasks: tasklets and work queues. Tasklets are a quick and easy way of scheduling a single function to be run, for example when triggered from an interrupt, whereas work queues are more complicated but also better suited to running multiple things in a sequence. -

    +

    0.14.1 Tasklets

    -

    Here is an example tasklet module. The +

    Here is an example tasklet module. The tasklet_fn function runs for a few seconds and in the mean time execution of the example_tasklet_init @@ -4125,7 +4132,7 @@ better suited to running multiple things in a sequence. 35 36MODULE_DESCRIPTION("Tasklet example"); 37MODULE_LICENSE("GPL"); -

    So with this example loaded dmesg +

    So with this example loaded dmesg should show: @@ -4137,11 +4144,11 @@ Example tasklet starts Example tasklet init continues... Example tasklet ends -

    -

    +

    +

    0.14.2 Work queues

    -

    To add a task to the scheduler we can use a workqueue. The kernel then uses the +

    To add a task to the scheduler we can use a workqueue. The kernel then uses the Completely Fair Scheduler (CFS) to execute work within the queue.

    @@ -4179,19 +4186,19 @@ Completely Fair Scheduler (CFS) to execute work within the queue. 32 33MODULE_LICENSE("GPL"); 34MODULE_DESCRIPTION("Workqueue example"); -

    +

    0.15 Interrupt Handlers

    -

    +

    0.15.1 Interrupt Handlers

    -

    Except for the last chapter, everything we did in the kernel so far we have done as a +

    Except for the last chapter, everything we did in the kernel so far we have done as a response to a process asking for it, either by dealing with a special file, sending an ioctl() , or issuing a system call. But the job of the kernel is not just to respond to process requests. Another job, which is every bit as important, is to speak to the hardware connected to the machine. -

    There are two types of interaction between the CPU and the rest of the +

    There are two types of interaction between the CPU and the rest of the computer’s hardware. The first type is when the CPU gives orders to the hardware, the other is when the hardware needs to tell the CPU something. The second, called interrupts, is much harder to implement because it has to be dealt with when @@ -4201,14 +4208,14 @@ lost. -

    Under Linux, hardware interrupts are called IRQ’s (Interrupt ReQuests). There +

    Under Linux, hardware interrupts are called IRQ’s (Interrupt ReQuests). There are two types of IRQ’s, short and long. A short IRQ is one which is expected to take a very short period of time, during which the rest of the machine will be blocked and no other interrupts will be handled. A long IRQ is one which can take longer, and during which other interrupts may occur (but not interrupts from the same device). If at all possible, it is better to declare an interrupt handler to be long. -

    When the CPU receives an interrupt, it stops whatever it is doing (unless it is +

    When the CPU receives an interrupt, it stops whatever it is doing (unless it is processing a more important interrupt, in which case it will deal with this one only when the more important one is done), saves certain parameters on the stack and calls the interrupt handler. This means that certain things @@ -4220,10 +4227,10 @@ the new information at a later time (this is called the "bottom half") and return. The kernel is then guaranteed to call the bottom half as soon as possible – and when it does, everything allowed in kernel modules will be allowed. -

    The way to implement this is to call +

    The way to implement this is to call request_irq() to get your interrupt handler called when the relevant IRQ is received. -

    In practice IRQ handling can be a bit more complex. Hardware is often +

    In practice IRQ handling can be a bit more complex. Hardware is often designed in a way that chains two interrupt controllers, so that all the IRQs from interrupt controller B are cascaded to a certain IRQ from interrupt controller A. Of course, that requires that the kernel finds out which IRQ it @@ -4237,7 +4244,7 @@ need to solve another truckload of problems. It is not enough to know if a certain IRQs has happend, it’s also important for what CPU(s) it was for. People still interested in more details, might want to refer to "APIC" now. -

    This function receives the IRQ number, the name of the function, +

    This function receives the IRQ number, the name of the function, flags, a name for /proc/interrupts and a parameter to pass to the interrupt handler. Usually there is a certain number of IRQs available. How many IRQs there are is hardware-dependent. The flags can include @@ -4250,16 +4257,16 @@ already a handler on this IRQ, or if you are both willing to share. -

    +

    0.15.2 Detecting button presses

    -

    Many popular single board computers, such as Raspberry Pi or Beagleboards, have a +

    Many popular single board computers, such as Raspberry Pi or Beagleboards, have a bunch of GPIO pins. Attaching buttons to those and then having a button press do something is a classic case in which you might need to use interrupts, so that instead of having the CPU waste time and battery power polling for a change in input state it is better for the input to trigger the CPU to then run a particular handling function. -

    Here is an example where buttons are connected to GPIO numbers 17 and 18 and +

    Here is an example where buttons are connected to GPIO numbers 17 and 18 and an LED is connected to GPIO 4. You can change those numbers to whatever is appropriate for your board.

    @@ -4409,14 +4416,14 @@ appropriate for your board. 143 144MODULE_LICENSE("GPL"); 145MODULE_DESCRIPTION("Handle some GPIO interrupts"); -

    +

    0.15.3 Bottom Half

    -

    Suppose you want to do a bunch of stuff inside of an interrupt routine. A common +

    Suppose you want to do a bunch of stuff inside of an interrupt routine. A common way to do that without rendering the interrupt unavailable for a significant duration is to combine it with a tasklet. This pushes the bulk of the work off into the scheduler. -

    The example below modifies the previous example to also run an additional task +

    The example below modifies the previous example to also run an additional task when an interrupt is triggered.

    @@ -4581,10 +4588,10 @@ when an interrupt is triggered. 159 160MODULE_LICENSE("GPL"); 161MODULE_DESCRIPTION("Interrupt with top and bottom half"); -

    +

    0.16 Crypto

    -

    At the dawn of the internet everybody trusted everybody completely…but that did +

    At the dawn of the internet everybody trusted everybody completely…but that did not work out so well. When this guide was originally written it was a more innocent era in which almost nobody actually gave a damn about crypto - least of all kernel developers. That is certainly no longer the case now. To handle crypto stuff the @@ -4593,10 +4600,10 @@ favourite hash functions. -

    +

    0.16.1 Hash functions

    -

    Calculating and checking the hashes of things is a common operation. Here is a +

    Calculating and checking the hashes of things is a common operation. Here is a demonstration of how to calculate a sha256 hash within a kernel module.

    @@ -4662,21 +4669,21 @@ demonstration of how to calculate a sha256 hash within a kernel module. 60 61MODULE_DESCRIPTION("sha256 hash test"); 62MODULE_LICENSE("GPL"); -

    Make and install the module: +

    Make and install the module: 

    1make 
 2sudo insmod cryptosha256.ko 
 3dmesg
    -

    And you should see that the hash was calculated for the test string. -

    Finally, remove the test module: +

    And you should see that the hash was calculated for the test string. +

    Finally, remove the test module: 

    1sudo rmmod cryptosha256
    -

    +

    0.16.2 Symmetric key encryption

    -

    Here is an example of symmetrically encrypting a string using the AES algorithm +

    Here is an example of symmetrically encrypting a string using the AES algorithm and a password.

    @@ -4877,10 +4884,10 @@ and a password. 195 196MODULE_DESCRIPTION("Symmetric key encryption example"); 197MODULE_LICENSE("GPL"); -

    +

    0.17 Standardizing the interfaces: The Device Model

    -

    Up to this point we have seen all kinds of modules doing all kinds of things, but there +

    Up to this point we have seen all kinds of modules doing all kinds of things, but there was no consistency in their interfaces with the rest of the kernel. To impose some consistency such that there is at minimum a standardized way to start, suspend and resume a device a device model was added. An example is show below, and you can @@ -4990,13 +4997,13 @@ functions. -

    +

    0.18 Optimizations

    -

    +

    0.18.1 Likely and Unlikely conditions

    -

    Sometimes you might want your code to run as quickly as possible, +

    Sometimes you might want your code to run as quickly as possible, especially if it is handling an interrupt or doing something which might cause noticible latency. If your code contains boolean conditions and if you know that the conditions are almost always likely to evaluate as either @@ -5006,7 +5013,7 @@ know that the conditions are almost always likely to evaluate as either likely and unlikely macros. -

    For example, when allocating memory you are almost always expecting this to +

    For example, when allocating memory you are almost always expecting this to succeed.

    @@ -5016,50 +5023,50 @@ succeed. 4    bio = NULL; 5    goto out; 6} -

    When the unlikely +

    When the unlikely macro is used, the compiler alters its machine instruction output, so that it continues along the false branch and only jumps if the condition is true. That avoids flushing the processor pipeline. The opposite happens if you use the likely macro. -

    +

    0.19 Common Pitfalls

    -

    +

    0.19.1 Using standard libraries

    -

    You can not do that. In a kernel module you can only use kernel functions, which are +

    You can not do that. In a kernel module you can only use kernel functions, which are the functions you can see in /proc/kallsyms. -

    +

    0.19.2 Disabling interrupts

    -

    You might need to do this for a short time and that is OK, but if you do not enable +

    You might need to do this for a short time and that is OK, but if you do not enable them afterwards, your system will be stuck and you will have to power it off. -

    +

    0.20 Where To Go From Here?

    -

    For people seriously interested in kernel programming, I recommend kernelnewbies.org +

    For people seriously interested in kernel programming, I recommend kernelnewbies.org and the Documentation subdirectory within the kernel source code which is not always easy to understand but can be a starting point for further investigation. Also, as Linus Torvalds said, the best way to learn the kernel is to read the source code yourself. -

    If you are interested in more examples of short kernel modules then searching on +

    If you are interested in more examples of short kernel modules then searching on sites such as Github and Gitlab is a good way to start, although there is a lot of duplication of older LKMPG examples which may not compile with newer kernel versions. You will also be able to find examples of the use of kernel modules to attack or compromise systems or exfiltrate data and those can be useful for thinking about how to defend systems and learning about existing security mechanisms within the kernel. -

    I hope I have helped you in your quest to become a better programmer, or at +

    I hope I have helped you in your quest to become a better programmer, or at least to have fun through technology. And, if you do write useful kernel modules, I hope you publish them under the GPL, so I can use them too. -

    If you would like to contribute to this guide or notice anything glaringly wrong, +

    If you would like to contribute to this guide or notice anything glaringly wrong, please create an issue at https://github.com/sysprog21/lkmpg. -

    Happy hacking! +

    Happy hacking!

    diff --git a/lkmpg-for-ht0x.svg b/lkmpg-for-ht0x.svg index d64d62d..9ad203b 100644 --- a/lkmpg-for-ht0x.svg +++ b/lkmpg-for-ht0x.svg @@ -1,6 +1,6 @@ - + @@ -12,15 +12,15 @@ - - - - - - - - - - + + + + + + + + + + \ No newline at end of file