cleanup_module
that’s impossible because it is a void function. However, there is a counter
@@ -1407,9 +1453,6 @@ there are functions defined in
-
-
-
try_module_get(THIS_MODULE)
: Increment the reference count of current module.
module_refcount(THIS_MODULE)
: Return the value of reference count of current module.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. -
+
6.5 chardev.c
-The next code sample creates a char driver named chardev. You can dump its device +
The next code sample creates a char driver named chardev. You can dump its device file.
-
1cat /proc/devices-
(or open the file with a program) and the driver will put the number of times the +
1cat /proc/devices+
(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
+ echo "hi" > /dev/hello
), but catch these attempts and tell the user that the operation is not supported.
Don’t worry if you don’t see what we do with the data we read into the buffer; we
don’t do much with it. We simply read in the data and print a message
acknowledging that we received it.
-
In the multiple-threaded environment, without any protection, concurrent access +
In the multiple-threaded environment, without any protection, concurrent access
to the same memory may lead to the race condition, and will not preserve the
performance. In the kernel module, this problem may happen due to multiple
instances accessing the shared resources. Therefore, a solution is to enforce the
exclusive access. We use atomic Compare-And-Swap (CAS) to maintain the states,
CDEV_NOT_USED
+ and CDEV_EXCLUSIVE_OPEN
- and CDEV_EXCLUSIVE_OPEN
, to determine whether the file is currently opened by someone or not. CAS compares
the contents of a memory location with the expected value and, only if they are the
same, modifies the contents of that memory location to the desired value. See more
concurrency details in the 12 section.
-
1/* -2 * chardev.c: Creates a read-only char device that says how many times -3 * you have read from the dev file -4 */ +-1/* +2 * chardev.c: Creates a read-only char device that says how many times +3 * you have read from the dev file +4 */ 5 -6#include <linux/cdev.h> -7#include <linux/delay.h> -8#include <linux/device.h> -9#include <linux/fs.h> -10#include <linux/init.h> -11#include <linux/irq.h> -12#include <linux/kernel.h> -13#include <linux/module.h> -14#include <linux/poll.h> +6#include <linux/cdev.h> +7#include <linux/delay.h> +8#include <linux/device.h> +9#include <linux/fs.h> +10#include <linux/init.h> +11#include <linux/irq.h> +12#include <linux/kernel.h> +13#include <linux/module.h> +14#include <linux/poll.h> 15 -16/* Prototypes - this would normally go in a .h file */ -17static int device_open(struct inode *, struct file *); -18static int device_release(struct inode *, struct file *); -19static ssize_t device_read(struct file *, char __user *, size_t, loff_t *); -20static ssize_t device_write(struct file *, const char __user *, size_t, +16/* Prototypes - this would normally go in a .h file */ +17static int device_open(struct inode *, struct file *); +18static int device_release(struct inode *, struct file *); +19static ssize_t device_read(struct file *, char __user *, size_t, loff_t *); +20static ssize_t device_write(struct file *, const char __user *, size_t, 21 loff_t *); 22 -23#define SUCCESS 0 -24#define DEVICE_NAME "chardev" /* Dev name as it appears in /proc/devices */ -25#define BUF_LEN 80 /* Max length of the message from the device */ +23#define SUCCESS 0 +24#define DEVICE_NAME "chardev" /* Dev name as it appears in /proc/devices */ +25#define BUF_LEN 80 /* Max length of the message from the device */ 26 -27/* Global variables are declared as static, so are global within the file. */ +27/* Global variables are declared as static, so are global within the file. */ 28 -29static int major; /* major number assigned to our device driver */ +29static int major; /* major number assigned to our device driver */ 30 -31enum { +31enum { 32 CDEV_NOT_USED = 0, 33 CDEV_EXCLUSIVE_OPEN = 1, 34}; 35 -36/* Is device open? Used to prevent multiple access to device */ -37static atomic_t already_open = ATOMIC_INIT(CDEV_NOT_USED); +36/* Is device open? Used to prevent multiple access to device */ +37static atomic_t already_open = ATOMIC_INIT(CDEV_NOT_USED); 38 -39static char msg[BUF_LEN]; /* The msg the device will give when asked */ +39static char msg[BUF_LEN]; /* The msg the device will give when asked */ 40 -41static struct class *cls; +41static struct class *cls; 42 -43static struct file_operations chardev_fops = { +43static struct file_operations chardev_fops = { 44 .read = device_read, 45 .write = device_write, 46 .open = device_open, 47 .release = device_release, 48}; 49 -50static int __init chardev_init(void) +50static int __init chardev_init(void) 51{ 52 major = register_chrdev(0, DEVICE_NAME, &chardev_fops); 53 -54 if (major < 0) { -55 pr_alert("Registering char device failed with %d\n", major); -56 return major; +54 if (major < 0) { +55 pr_alert("Registering char device failed with %d\n", major); +56 return major; 57 } 58 -59 pr_info("I was assigned major number %d.\n", major); +59 pr_info("I was assigned major number %d.\n", major); 60 61 cls = class_create(THIS_MODULE, DEVICE_NAME); 62 device_create(cls, NULL, MKDEV(major, 0), NULL, DEVICE_NAME); 63 -64 pr_info("Device created on /dev/%s\n", DEVICE_NAME); +64 pr_info("Device created on /dev/%s\n", DEVICE_NAME); 65 -66 return SUCCESS; +66 return SUCCESS; 67} 68 -69static void __exit chardev_exit(void) +69static void __exit chardev_exit(void) 70{ 71 device_destroy(cls, MKDEV(major, 0)); 72 class_destroy(cls); 73 -74 /* Unregister the device */ +74 /* Unregister the device */ 75 unregister_chrdev(major, DEVICE_NAME); 76} 77 -78/* Methods */ +78/* Methods */ 79 -80/* Called when a process tries to open the device file, like -81 * "sudo cat /dev/chardev" -82 */ -83static int device_open(struct inode *inode, struct file *file) +80/* Called when a process tries to open the device file, like +81 * "sudo cat /dev/chardev" +82 */ +83static int device_open(struct inode *inode, struct file *file) 84{ -85 static int counter = 0; +85 static int counter = 0; 86 -87 if (atomic_cmpxchg(&already_open, CDEV_NOT_USED, CDEV_EXCLUSIVE_OPEN)) -88 return -EBUSY; +87 if (atomic_cmpxchg(&already_open, CDEV_NOT_USED, CDEV_EXCLUSIVE_OPEN)) +88 return -EBUSY; 89 -90 sprintf(msg, "I already told you %d times Hello world!\n", counter++); +90 sprintf(msg, "I already told you %d times Hello world!\n", counter++); 91 try_module_get(THIS_MODULE); 92 -93 return SUCCESS; +93 return SUCCESS; 94} 95 -96/* Called when a process closes the device file. */ -97static int device_release(struct inode *inode, struct file *file) +96/* Called when a process closes the device file. */ +97static int device_release(struct inode *inode, struct file *file) 98{ -99 /* We're now ready for our next caller */ +99 /* We're now ready for our next caller */ 100 atomic_set(&already_open, CDEV_NOT_USED); 101 -102 /* Decrement the usage count, or else once you opened the file, you will -103 * never get get rid of the module. -104 */ +102 /* Decrement the usage count, or else once you opened the file, you will +103 * never get get rid of the module. +104 */ 105 module_put(THIS_MODULE); 106 -107 return SUCCESS; +107 return SUCCESS; 108} 109 -110/* Called when a process, which already opened the dev file, attempts to -111 * read from it. -112 */ -113static ssize_t device_read(struct file *filp, /* see include/linux/fs.h */ -114 char __user *buffer, /* buffer to fill with data */ -115 size_t length, /* length of the buffer */ +110/* Called when a process, which already opened the dev file, attempts to +111 * read from it. +112 */ +113static ssize_t device_read(struct file *filp, /* see include/linux/fs.h */ +114 char __user *buffer, /* buffer to fill with data */ +115 size_t length, /* length of the buffer */ 116 loff_t *offset) 117{ -118 /* Number of bytes actually written to the buffer */ -119 int bytes_read = 0; -120 const char *msg_ptr = msg; +118 /* Number of bytes actually written to the buffer */ +119 int bytes_read = 0; +120 const char *msg_ptr = msg; 121 -122 if (!*(msg_ptr + *offset)) { /* we are at the end of message */ -123 *offset = 0; /* reset the offset */ -124 return 0; /* signify end of file */ +122 if (!*(msg_ptr + *offset)) { /* we are at the end of message */ +123 *offset = 0; /* reset the offset */ +124 return 0; /* signify end of file */ 125 } 126 127 msg_ptr += *offset; 128 -129 /* Actually put the data into the buffer */ -130 while (length && *msg_ptr) { -131 /* The buffer is in the user data segment, not the kernel -132 * segment so "*" assignment won't work. We have to use -133 * put_user which copies data from the kernel data segment to -134 * the user data segment. -135 */ +129 /* Actually put the data into the buffer */ +130 while (length && *msg_ptr) { +131 /* The buffer is in the user data segment, not the kernel +132 * segment so "*" assignment won't work. We have to use +133 * put_user which copies data from the kernel data segment to +134 * the user data segment. +135 */ 136 put_user(*(msg_ptr++), buffer++); 137 length--; 138 bytes_read++; @@ -1595,70 +1638,70 @@ concurrency details in the 12+
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_CODEto the macroKERNEL_VERSION. In version a.b.c of the kernel, the value of this macro would be. -
+
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 gathers 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,
init_moduleregisters the structure with the kernel andcleanup_module +unregisters it. - 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 index-node (inode for short) number is a pointer to a disk location where the file’s inode 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_getandmodule_putin 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 @@ -1666,12 +1709,12 @@ functionprocfile_read, and delete the file /proc/helloworld in the functioncleanup_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 astruct proc_dir_entry +. The return value is astruct 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. -Every time the file /proc/helloworld is read, the function +
Every time the file /proc/helloworld is read, the function
procfile_readis called. Two parameters of this function are very important: the buffer (the second parameter) and the offset (the fourth one). The content of the @@ -1688,82 +1731,82 @@ function, if it never returns zero, the read function is called endlessly. $ cat /proc/helloworld HelloWorld!
+
-
1/* -2 * procfs1.c -3 */ ++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> +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 +11#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0) +12#define HAVE_PROC_OPS +13#endif 14 -15#define procfs_name "helloworld" +15#define procfs_name "helloworld" 16 -17static struct proc_dir_entry *our_proc_file; +17static struct proc_dir_entry *our_proc_file; 18 -19static ssize_t procfile_read(struct file *filePointer, char __user *buffer, -20 size_t buffer_length, loff_t *offset) +19static ssize_t procfile_read(struct file *filePointer, char __user *buffer, +20 size_t buffer_length, loff_t *offset) 21{ -22 char s[13] = "HelloWorld!\n"; -23 int len = sizeof(s); -24 ssize_t ret = len; +22 char s[13] = "HelloWorld!\n"; +23 int len = sizeof(s); +24 ssize_t ret = len; 25 -26 if (*offset >= len || copy_to_user(buffer, s, len)) { -27 pr_info("copy_to_user failed\n"); +26 if (*offset >= len || copy_to_user(buffer, s, len)) { +27 pr_info("copy_to_user failed\n"); 28 ret = 0; -29 } else { -30 pr_info("procfile read %s\n", filePointer->f_path.dentry->d_name.name); +29 } else { +30 pr_info("procfile read %s\n", filePointer->f_path.dentry->d_name.name); 31 *offset += len; 32 } 33 -34 return ret; +34 return ret; 35} 36 -37#ifdef HAVE_PROC_OPS -38static const struct proc_ops proc_file_fops = { +37#ifdef HAVE_PROC_OPS +38static const struct proc_ops proc_file_fops = { 39 .proc_read = procfile_read, 40}; -41#else -42static const struct file_operations proc_file_fops = { +41#else +42static const struct file_operations proc_file_fops = { 43 .read = procfile_read, 44}; -45#endif +45#endif 46 -47static int __init procfs1_init(void) +47static int __init procfs1_init(void) 48{ 49 our_proc_file = proc_create(procfs_name, 0644, NULL, &proc_file_fops); -50 if (NULL == our_proc_file) { +50 if (NULL == our_proc_file) { 51 proc_remove(our_proc_file); -52 pr_alert("Error:Could not initialize /proc/%s\n", procfs_name); -53 return -ENOMEM; +52 pr_alert("Error:Could not initialize /proc/%s\n", procfs_name); +53 return -ENOMEM; 54 } 55 -56 pr_info("/proc/%s created\n", procfs_name); -57 return 0; +56 pr_info("/proc/%s created\n", procfs_name); +57 return 0; 58} 59 -60static void __exit procfs1_exit(void) +60static void __exit procfs1_exit(void) 61{ 62 proc_remove(our_proc_file); -63 pr_info("/proc/%s removed\n", procfs_name); +63 pr_info("/proc/%s removed\n", procfs_name); 64} 65 66module_init(procfs1_init); 67module_exit(procfs1_exit); 68 -69MODULE_LICENSE("GPL");-
7.1 The proc_ops Structure
-The The proc_ops
+ as 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
@@ -1775,10 +1818,10 @@ performance. For example, the file which never disappears in proc_flag
PROC_ENTRY_PERMANENT
to save 2 atomic ops, 1 allocation, 1 free in per open/read/close sequence.
-
+
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
@@ -1786,7 +1829,7 @@ 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
@@ -1797,7 +1840,7 @@ 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. @@ -1815,130 +1858,130 @@ need to import data because it comes from user space, but not for the read funct because data is already in kernel space.
-
1/* -2 * procfs2.c - create a "file" in /proc -3 */ ++1/* +2 * procfs2.c - create a "file" in /proc +3 */ 4 -5#include <linux/kernel.h> /* We're doing kernel work */ -6#include <linux/module.h> /* Specifically, a module */ -7#include <linux/proc_fs.h> /* Necessary because we use the proc fs */ -8#include <linux/uaccess.h> /* for copy_from_user */ -9#include <linux/version.h> +5#include <linux/kernel.h> /* We're doing kernel work */ +6#include <linux/module.h> /* Specifically, a module */ +7#include <linux/proc_fs.h> /* Necessary because we use the proc fs */ +8#include <linux/uaccess.h> /* for copy_from_user */ +9#include <linux/version.h> 10 -11#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0) -12#define HAVE_PROC_OPS -13#endif +11#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0) +12#define HAVE_PROC_OPS +13#endif 14 -15#define PROCFS_MAX_SIZE 1024 -16#define PROCFS_NAME "buffer1k" +15#define PROCFS_MAX_SIZE 1024 +16#define PROCFS_NAME "buffer1k" 17 -18/* This structure hold information about the /proc file */ -19static struct proc_dir_entry *our_proc_file; +18/* This structure hold information about the /proc file */ +19static struct proc_dir_entry *our_proc_file; 20 -21/* The buffer used to store character for this module */ -22static char procfs_buffer[PROCFS_MAX_SIZE]; +21/* The buffer used to store character for this module */ +22static char procfs_buffer[PROCFS_MAX_SIZE]; 23 -24/* The size of the buffer */ -25static unsigned long procfs_buffer_size = 0; +24/* The size of the buffer */ +25static unsigned long procfs_buffer_size = 0; 26 -27/* This function is called then the /proc file is read */ -28static ssize_t procfile_read(struct file *filePointer, char __user *buffer, -29 size_t buffer_length, loff_t *offset) +27/* This function is called then the /proc file is read */ +28static ssize_t procfile_read(struct file *filePointer, char __user *buffer, +29 size_t buffer_length, loff_t *offset) 30{ -31 char s[13] = "HelloWorld!\n"; -32 int len = sizeof(s); -33 ssize_t ret = len; +31 char s[13] = "HelloWorld!\n"; +32 int len = sizeof(s); +33 ssize_t ret = len; 34 -35 if (*offset >= len || copy_to_user(buffer, s, len)) { -36 pr_info("copy_to_user failed\n"); +35 if (*offset >= len || copy_to_user(buffer, s, len)) { +36 pr_info("copy_to_user failed\n"); 37 ret = 0; -38 } else { -39 pr_info("procfile read %s\n", filePointer->f_path.dentry->d_name.name); +38 } else { +39 pr_info("procfile read %s\n", filePointer->f_path.dentry->d_name.name); 40 *offset += len; 41 } 42 -43 return ret; +43 return ret; 44} 45 -46/* This function is called with the /proc file is written. */ -47static ssize_t procfile_write(struct file *file, const char __user *buff, -48 size_t len, loff_t *off) +46/* This function is called with the /proc file is written. */ +47static ssize_t procfile_write(struct file *file, const char __user *buff, +48 size_t len, loff_t *off) 49{ 50 procfs_buffer_size = len; -51 if (procfs_buffer_size > PROCFS_MAX_SIZE) +51 if (procfs_buffer_size > PROCFS_MAX_SIZE) 52 procfs_buffer_size = PROCFS_MAX_SIZE; 53 -54 if (copy_from_user(procfs_buffer, buff, procfs_buffer_size)) -55 return -EFAULT; +54 if (copy_from_user(procfs_buffer, buff, procfs_buffer_size)) +55 return -EFAULT; 56 -57 procfs_buffer[procfs_buffer_size & (PROCFS_MAX_SIZE - 1)] = '\0'; -58 pr_info("procfile write %s\n", procfs_buffer); +57 procfs_buffer[procfs_buffer_size & (PROCFS_MAX_SIZE - 1)] = '\0'; +58 pr_info("procfile write %s\n", procfs_buffer); 59 -60 return procfs_buffer_size; +60 return procfs_buffer_size; 61} 62 -63#ifdef HAVE_PROC_OPS -64static const struct proc_ops proc_file_fops = { +63#ifdef HAVE_PROC_OPS +64static const struct proc_ops proc_file_fops = { 65 .proc_read = procfile_read, 66 .proc_write = procfile_write, 67}; -68#else -69static const struct file_operations proc_file_fops = { +68#else +69static const struct file_operations proc_file_fops = { 70 .read = procfile_read, 71 .write = procfile_write, 72}; -73#endif +73#endif 74 -75static int __init procfs2_init(void) +75static int __init procfs2_init(void) 76{ 77 our_proc_file = proc_create(PROCFS_NAME, 0644, NULL, &proc_file_fops); -78 if (NULL == our_proc_file) { +78 if (NULL == our_proc_file) { 79 proc_remove(our_proc_file); -80 pr_alert("Error:Could not initialize /proc/%s\n", PROCFS_NAME); -81 return -ENOMEM; +80 pr_alert("Error:Could not initialize /proc/%s\n", PROCFS_NAME); +81 return -ENOMEM; 82 } 83 -84 pr_info("/proc/%s created\n", PROCFS_NAME); -85 return 0; +84 pr_info("/proc/%s created\n", PROCFS_NAME); +85 return 0; 86} 87 -88static void __exit procfs2_exit(void) +88static void __exit procfs2_exit(void) 89{ 90 proc_remove(our_proc_file); -91 pr_info("/proc/%s removed\n", PROCFS_NAME); +91 pr_info("/proc/%s removed\n", PROCFS_NAME); 92} 93 94module_init(procfs2_init); 95module_exit(procfs2_exit); 96 -97MODULE_LICENSE("GPL");-
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
+ 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
- struct inode_operations
+
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
+ struct inode_operations
- which includes a pointer to a struct proc_ops
+ which includes a pointer to a struct proc_ops
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
@@ -1947,7 +1990,7 @@ 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 @@ -1955,121 +1998,121 @@ if a process writes something to the kernel, then the kernel receives it as input.
-
1/* -2 * procfs3.c -3 */ ++1/* +2 * procfs3.c +3 */ 4 -5#include <linux/kernel.h> -6#include <linux/module.h> -7#include <linux/proc_fs.h> -8#include <linux/sched.h> -9#include <linux/uaccess.h> -10#include <linux/version.h> +5#include <linux/kernel.h> +6#include <linux/module.h> +7#include <linux/proc_fs.h> +8#include <linux/sched.h> +9#include <linux/uaccess.h> +10#include <linux/version.h> 11 -12#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0) -13#define HAVE_PROC_OPS -14#endif +12#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0) +13#define HAVE_PROC_OPS +14#endif 15 -16#define PROCFS_MAX_SIZE 2048 -17#define PROCFS_ENTRY_FILENAME "buffer2k" +16#define PROCFS_MAX_SIZE 2048 +17#define PROCFS_ENTRY_FILENAME "buffer2k" 18 -19static struct proc_dir_entry *our_proc_file; -20static char procfs_buffer[PROCFS_MAX_SIZE]; -21static unsigned long procfs_buffer_size = 0; +19static struct proc_dir_entry *our_proc_file; +20static char procfs_buffer[PROCFS_MAX_SIZE]; +21static unsigned long procfs_buffer_size = 0; 22 -23static ssize_t procfs_read(struct file *filp, char __user *buffer, -24 size_t length, loff_t *offset) +23static ssize_t procfs_read(struct file *filp, char __user *buffer, +24 size_t length, loff_t *offset) 25{ -26 static int finished = 0; +26 static int finished = 0; 27 -28 if (finished) { -29 pr_debug("procfs_read: END\n"); +28 if (finished) { +29 pr_debug("procfs_read: END\n"); 30 finished = 0; -31 return 0; +31 return 0; 32 } 33 finished = 1; 34 -35 if (copy_to_user(buffer, procfs_buffer, procfs_buffer_size)) -36 return -EFAULT; +35 if (copy_to_user(buffer, procfs_buffer, procfs_buffer_size)) +36 return -EFAULT; 37 -38 pr_debug("procfs_read: read %lu bytes\n", procfs_buffer_size); -39 return procfs_buffer_size; +38 pr_debug("procfs_read: read %lu bytes\n", procfs_buffer_size); +39 return procfs_buffer_size; 40} -41static ssize_t procfs_write(struct file *file, const char __user *buffer, -42 size_t len, loff_t *off) +41static ssize_t procfs_write(struct file *file, const char __user *buffer, +42 size_t len, loff_t *off) 43{ -44 if (len > PROCFS_MAX_SIZE) +44 if (len > PROCFS_MAX_SIZE) 45 procfs_buffer_size = PROCFS_MAX_SIZE; -46 else +46 else 47 procfs_buffer_size = len; -48 if (copy_from_user(procfs_buffer, buffer, procfs_buffer_size)) -49 return -EFAULT; +48 if (copy_from_user(procfs_buffer, buffer, procfs_buffer_size)) +49 return -EFAULT; 50 -51 pr_debug("procfs_write: write %lu bytes\n", procfs_buffer_size); -52 return procfs_buffer_size; +51 pr_debug("procfs_write: write %lu bytes\n", procfs_buffer_size); +52 return procfs_buffer_size; 53} -54static int procfs_open(struct inode *inode, struct file *file) +54static int procfs_open(struct inode *inode, struct file *file) 55{ 56 try_module_get(THIS_MODULE); -57 return 0; +57 return 0; 58} -59static int procfs_close(struct inode *inode, struct file *file) +59static int procfs_close(struct inode *inode, struct file *file) 60{ 61 module_put(THIS_MODULE); -62 return 0; +62 return 0; 63} 64 -65#ifdef HAVE_PROC_OPS -66static struct proc_ops file_ops_4_our_proc_file = { +65#ifdef HAVE_PROC_OPS +66static struct proc_ops file_ops_4_our_proc_file = { 67 .proc_read = procfs_read, 68 .proc_write = procfs_write, 69 .proc_open = procfs_open, 70 .proc_release = procfs_close, 71}; -72#else -73static const struct file_operations file_ops_4_our_proc_file = { +72#else +73static const struct file_operations file_ops_4_our_proc_file = { 74 .read = procfs_read, 75 .write = procfs_write, 76 .open = procfs_open, 77 .release = procfs_close, 78}; -79#endif +79#endif 80 -81static int __init procfs3_init(void) +81static int __init procfs3_init(void) 82{ 83 our_proc_file = proc_create(PROCFS_ENTRY_FILENAME, 0644, NULL, 84 &file_ops_4_our_proc_file); -85 if (our_proc_file == NULL) { +85 if (our_proc_file == NULL) { 86 remove_proc_entry(PROCFS_ENTRY_FILENAME, NULL); -87 pr_debug("Error: Could not initialize /proc/%s\n", +87 pr_debug("Error: Could not initialize /proc/%s\n", 88 PROCFS_ENTRY_FILENAME); -89 return -ENOMEM; +89 return -ENOMEM; 90 } 91 proc_set_size(our_proc_file, 80); 92 proc_set_user(our_proc_file, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID); 93 -94 pr_debug("/proc/%s created\n", PROCFS_ENTRY_FILENAME); -95 return 0; +94 pr_debug("/proc/%s created\n", PROCFS_ENTRY_FILENAME); +95 return 0; 96} 97 -98static void __exit procfs3_exit(void) +98static void __exit procfs3_exit(void) 99{ 100 remove_proc_entry(PROCFS_ENTRY_FILENAME, NULL); -101 pr_debug("/proc/%s removed\n", PROCFS_ENTRY_FILENAME); +101 pr_debug("/proc/%s removed\n", PROCFS_ENTRY_FILENAME); 102} 103 104module_init(procfs3_init); 105module_exit(procfs3_exit); 106 -107MODULE_LICENSE("GPL");-Still hungry for procfs examples? Well, first of all keep in mind, there are rumors +107MODULE_LICENSE("GPL");
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. -
+
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, which is composed of
@@ -2078,7 +2121,7 @@ So to help people writting , 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 +
A sequence begins with the call of the function
start()
. If the return is a non NULL
value, the function next()
@@ -2095,7 +2138,7 @@ time next()
returns NULL
, then the function stop()
is called.
-
BE CAREFUL: when a sequence is finished, another one starts. That means that at the end +
BE CAREFUL: when a sequence is finished, another one starts. That means that at the end
of function The The If you want more information, you can read this web page:
+118MODULE_LICENSE("GPL"); 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.
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.
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.
Make and install the module:
Check that it exists:
+ Check that it exists:
What is the current value of What is the current value of
Set the value of Set the value of
Finally, remove the test module:
+ Finally, remove the test module:
+
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
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
@@ -2375,7 +2418,7 @@ received.
- The answer in Unix is to use a special function called
+ The answer in Unix is to use a special function called
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 ( 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/userspace-api/ioctl/ioctl-number.rst.
- Also, we need to be careful that concurrent access to the shared resources will
+ Also, we need to be careful that concurrent access to the shared resources will
lead to the race condition. The solution is using atomic Compare-And-Swap (CAS),
which we mentioned at 6.5 section, to enforce the exclusive access.
+
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
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
@@ -2911,11 +2954,11 @@ 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
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,
@@ -2923,7 +2966,7 @@ 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
( 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
To modify the content of To modify the content of However, However, Because of the control-flow integrity, which is a technique to prevent the redirect
+ Because of the control-flow integrity, which is a technique to prevent the redirect
execution code from the attacker, for making sure that the indirect calls go to the
expected addresses and the return addresses are not changed. Since Linux v5.7, the
kernel patched the series of control-flow enforcement (CET) for x86, and some
@@ -2986,10 +3029,10 @@ COLLECT_GCC_OPTIONS='-v' '-Q' '-O2' '--help=target' '-mtune=generic' '-marc
GNU C17 (Ubuntu 9.3.0-17ubuntu1~20.04) version 9.3.0 (x86_64-linux-gnu)
...
But CET should not be enabled in the kernel, it may break the Kprobes and bpf.
+ But CET should not be enabled in the kernel, it may break the Kprobes and bpf.
Consequently, CET is disabled since v5.11. To guarantee the manual symbol lookup
worked, we only use up to v5.4.
- Unfortunately, since Linux v5.7 Unfortunately, since Linux v5.7 Otherwise, specify the address of Otherwise, specify the address of
- Using the address from /boot/System.map, be careful about KASLR (Kernel
+
+ Using the address from /boot/System.map, be careful about KASLR (Kernel
Address Space Layout Randomization). KASLR may randomize the address of
kernel code and data at every boot time, such as the static address listed in
/boot/System.map will offset by some entropy. The purpose of KASLR is to protect
@@ -3046,7 +3089,7 @@ ffffffff82000300 R sys_call_table
$ sudo grep sys_call_table /proc/kallsyms
ffffffff86400300 R sys_call_table
- If KASLR is enabled, we have to take care of the address from /proc/kallsyms each
+ If KASLR is enabled, we have to take care of the address from /proc/kallsyms each
time we reboot the machine. In order to use the address from /boot/System.map,
make sure that KASLR is disabled. You can add the nokaslr for disabling KASLR in
next booting time:
@@ -3062,8 +3105,8 @@ $ grep quiet /etc/default/grub
GRUB_CMDLINE_LINUX_DEFAULT="quiet nokaslr splash"
$ sudo update-grub
-
- For more information, check out the following:
+
+ For more information, check out the following:
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 The The 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 Note that all the related problems make syscall stealing unfeasible for
+ Note that all the related problems make syscall stealing unfeasible for
production use. In order to keep people from doing potential harmful things
stop()
, the function start()
is called again. This loop finishes when the function
@@ -2112,257 +2155,257 @@ of function stop()
- exported.
+
seq_file
+ will still try to call seq_file
provides basic functions for proc_ops
, such as seq_read
, seq_lseek
, and some others. But nothing to write in the /proc file. Of course, you can still use
the same way as in the previous example.
1/*
-2 * procfs4.c - create a "file" in /proc
-3 * This program uses the seq_file library to manage the /proc file.
-4 */
+
+1/*
+2 * procfs4.c - create a "file" in /proc
+3 * This program uses the seq_file library to manage the /proc file.
+4 */
5
-6#include <linux/kernel.h> /* We are doing kernel work */
-7#include <linux/module.h> /* Specifically, a module */
-8#include <linux/proc_fs.h> /* Necessary because we use proc fs */
-9#include <linux/seq_file.h> /* for seq_file */
-10#include <linux/version.h>
+6#include <linux/kernel.h> /* We are doing kernel work */
+7#include <linux/module.h> /* Specifically, a module */
+8#include <linux/proc_fs.h> /* Necessary because we use proc fs */
+9#include <linux/seq_file.h> /* for seq_file */
+10#include <linux/version.h>
11
-12#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0)
-13#define HAVE_PROC_OPS
-14#endif
+12#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0)
+13#define HAVE_PROC_OPS
+14#endif
15
-16#define PROC_NAME "iter"
+16#define PROC_NAME "iter"
17
-18/* This function is called at the beginning of a sequence.
-19 * ie, when:
-20 * - the /proc file is read (first time)
-21 * - after the function stop (end of sequence)
-22 */
-23static void *my_seq_start(struct seq_file *s, loff_t *pos)
+18/* This function is called at the beginning of a sequence.
+19 * ie, when:
+20 * - the /proc file is read (first time)
+21 * - after the function stop (end of sequence)
+22 */
+23static void *my_seq_start(struct seq_file *s, loff_t *pos)
24{
-25 static unsigned long counter = 0;
+25 static unsigned long counter = 0;
26
-27 /* beginning a new sequence? */
-28 if (*pos == 0) {
-29 /* yes => return a non null value to begin the sequence */
-30 return &counter;
+27 /* beginning a new sequence? */
+28 if (*pos == 0) {
+29 /* yes => return a non null value to begin the sequence */
+30 return &counter;
31 }
32
-33 /* no => it is the end of the sequence, return end to stop reading */
+33 /* no => it is the end of the sequence, return end to stop reading */
34 *pos = 0;
-35 return NULL;
+35 return NULL;
36}
37
-38/* This function is called after the beginning of a sequence.
-39 * It is called untill the return is NULL (this ends the sequence).
-40 */
-41static void *my_seq_next(struct seq_file *s, void *v, loff_t *pos)
+38/* This function is called after the beginning of a sequence.
+39 * It is called untill the return is NULL (this ends the sequence).
+40 */
+41static void *my_seq_next(struct seq_file *s, void *v, loff_t *pos)
42{
-43 unsigned long *tmp_v = (unsigned long *)v;
+43 unsigned long *tmp_v = (unsigned long *)v;
44 (*tmp_v)++;
45 (*pos)++;
-46 return NULL;
+46 return NULL;
47}
48
-49/* This function is called at the end of a sequence. */
-50static void my_seq_stop(struct seq_file *s, void *v)
+49/* This function is called at the end of a sequence. */
+50static void my_seq_stop(struct seq_file *s, void *v)
51{
-52 /* nothing to do, we use a static value in start() */
+52 /* nothing to do, we use a static value in start() */
53}
54
-55/* This function is called for each "step" of a sequence. */
-56static int my_seq_show(struct seq_file *s, void *v)
+55/* This function is called for each "step" of a sequence. */
+56static int my_seq_show(struct seq_file *s, void *v)
57{
58 loff_t *spos = (loff_t *)v;
59
-60 seq_printf(s, "%Ld\n", *spos);
-61 return 0;
+60 seq_printf(s, "%Ld\n", *spos);
+61 return 0;
62}
63
-64/* This structure gather "function" to manage the sequence */
-65static struct seq_operations my_seq_ops = {
+64/* This structure gather "function" to manage the sequence */
+65static struct seq_operations my_seq_ops = {
66 .start = my_seq_start,
67 .next = my_seq_next,
68 .stop = my_seq_stop,
69 .show = my_seq_show,
70};
71
-72/* This function is called when the /proc file is open. */
-73static int my_open(struct inode *inode, struct file *file)
+72/* This function is called when the /proc file is open. */
+73static int my_open(struct inode *inode, struct file *file)
74{
-75 return seq_open(file, &my_seq_ops);
+75 return seq_open(file, &my_seq_ops);
76};
77
-78/* This structure gather "function" that manage the /proc file */
-79#ifdef HAVE_PROC_OPS
-80static const struct proc_ops my_file_ops = {
+78/* This structure gather "function" that manage the /proc file */
+79#ifdef HAVE_PROC_OPS
+80static const struct proc_ops my_file_ops = {
81 .proc_open = my_open,
82 .proc_read = seq_read,
83 .proc_lseek = seq_lseek,
84 .proc_release = seq_release,
85};
-86#else
-87static const struct file_operations my_file_ops = {
+86#else
+87static const struct file_operations my_file_ops = {
88 .open = my_open,
89 .read = seq_read,
90 .llseek = seq_lseek,
91 .release = seq_release,
92};
-93#endif
+93#endif
94
-95static int __init procfs4_init(void)
+95static int __init procfs4_init(void)
96{
-97 struct proc_dir_entry *entry;
+97 struct proc_dir_entry *entry;
98
99 entry = proc_create(PROC_NAME, 0, NULL, &my_file_ops);
-100 if (entry == NULL) {
+100 if (entry == NULL) {
101 remove_proc_entry(PROC_NAME, NULL);
-102 pr_debug("Error: Could not initialize /proc/%s\n", PROC_NAME);
-103 return -ENOMEM;
+102 pr_debug("Error: Could not initialize /proc/%s\n", PROC_NAME);
+103 return -ENOMEM;
104 }
105
-106 return 0;
+106 return 0;
107}
108
-109static void __exit procfs4_exit(void)
+109static void __exit procfs4_exit(void)
110{
111 remove_proc_entry(PROC_NAME, NULL);
-112 pr_debug("/proc/%s removed\n", PROC_NAME);
+112 pr_debug("/proc/%s removed\n", PROC_NAME);
113}
114
115module_init(procfs4_init);
116module_exit(procfs4_exit);
117
-118MODULE_LICENSE("GPL");
-8 sysfs: Interacting with your module
-1ls -l /sys
-1ls -l /sys
+1/*
-2 * hello-sysfs.c sysfs example
-3 */
-4#include <linux/fs.h>
-5#include <linux/init.h>
-6#include <linux/kobject.h>
-7#include <linux/module.h>
-8#include <linux/string.h>
-9#include <linux/sysfs.h>
+
+1/*
+2 * hello-sysfs.c sysfs example
+3 */
+4#include <linux/fs.h>
+5#include <linux/init.h>
+6#include <linux/kobject.h>
+7#include <linux/module.h>
+8#include <linux/string.h>
+9#include <linux/sysfs.h>
10
-11static struct kobject *mymodule;
+11static struct kobject *mymodule;
12
-13/* the variable you want to be able to change */
-14static int myvariable = 0;
+13/* the variable you want to be able to change */
+14static int myvariable = 0;
15
-16static ssize_t myvariable_show(struct kobject *kobj,
-17 struct kobj_attribute *attr, char *buf)
+16static ssize_t myvariable_show(struct kobject *kobj,
+17 struct kobj_attribute *attr, char *buf)
18{
-19 return sprintf(buf, "%d\n", myvariable);
+19 return sprintf(buf, "%d\n", myvariable);
20}
21
-22static ssize_t myvariable_store(struct kobject *kobj,
-23 struct kobj_attribute *attr, char *buf,
-24 size_t count)
+22static ssize_t myvariable_store(struct kobject *kobj,
+23 struct kobj_attribute *attr, char *buf,
+24 size_t count)
25{
-26 sscanf(buf, "%du", &myvariable);
-27 return count;
+26 sscanf(buf, "%du", &myvariable);
+27 return count;
28}
29
-30static struct kobj_attribute myvariable_attribute =
-31 __ATTR(myvariable, 0660, myvariable_show, (void *)myvariable_store);
+30static struct kobj_attribute myvariable_attribute =
+31 __ATTR(myvariable, 0660, myvariable_show, (void *)myvariable_store);
32
-33static int __init mymodule_init(void)
+33static int __init mymodule_init(void)
34{
-35 int error = 0;
+35 int error = 0;
36
-37 pr_info("mymodule: initialised\n");
+37 pr_info("mymodule: initialised\n");
38
-39 mymodule = kobject_create_and_add("mymodule", kernel_kobj);
-40 if (!mymodule)
-41 return -ENOMEM;
+39 mymodule = kobject_create_and_add("mymodule", kernel_kobj);
+40 if (!mymodule)
+41 return -ENOMEM;
42
43 error = sysfs_create_file(mymodule, &myvariable_attribute.attr);
-44 if (error) {
-45 pr_info("failed to create the myvariable file "
-46 "in /sys/kernel/mymodule\n");
+44 if (error) {
+45 pr_info("failed to create the myvariable file "
+46 "in /sys/kernel/mymodule\n");
47 }
48
-49 return error;
+49 return error;
50}
51
-52static void __exit mymodule_exit(void)
+52static void __exit mymodule_exit(void)
53{
-54 pr_info("mymodule: Exit success\n");
+54 pr_info("mymodule: Exit success\n");
55 kobject_put(mymodule);
56}
57
58module_init(mymodule_init);
59module_exit(mymodule_exit);
60
-61MODULE_LICENSE("GPL");
-1make
+
-1make
2sudo insmod hello-sysfs.ko
-1sudo lsmod | grep hello_sysfs
- myvariable
+ 1sudo lsmod | grep hello_sysfs
+ myvariable
?
1cat /sys/kernel/mymodule/myvariable
- myvariable
+ right before you do the 1cat /sys/kernel/mymodule/myvariable
+ myvariable
and check that it changed.
1echo "32" > /sys/kernel/mymodule/myvariable
+
1echo "32" > /sys/kernel/mymodule/myvariable
2cat /sys/kernel/mymodule/myvariable
-1sudo rmmod hello_sysfs
-1sudo rmmod hello_sysfs
+9 Talking To Device Files
- device_write
.
- ioctl
(short for Input Output ConTroL). Every device can have its own
ioctl
@@ -2384,12 +2427,12 @@ kernel), write ioctl’s (to return information to a process), both or neither.
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.
- _IO
, _IOR
@@ -2400,436 +2443,436 @@ 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.
-1/*
-2 * chardev2.c - Create an input/output character device
-3 */
+
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>
+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
+15#include "chardev.h"
+16#define SUCCESS 0
+17#define DEVICE_NAME "char_dev"
+18#define BUF_LEN 80
19
-20enum {
+20enum {
21 CDEV_NOT_USED = 0,
22 CDEV_EXCLUSIVE_OPEN = 1,
23};
24
-25/* Is the device open right now? Used to prevent concurrent access into
-26 * the same device
-27 */
-28static atomic_t already_open = ATOMIC_INIT(CDEV_NOT_USED);
+25/* Is the device open right now? Used to prevent concurrent access into
+26 * the same device
+27 */
+28static atomic_t already_open = ATOMIC_INIT(CDEV_NOT_USED);
29
-30/* The message the device will give when asked */
-31static char message[BUF_LEN];
+30/* The message the device will give when asked */
+31static char message[BUF_LEN];
32
-33static struct class *cls;
+33static struct class *cls;
34
-35/* This is called whenever a process attempts to open the device file */
-36static int device_open(struct inode *inode, struct file *file)
+35/* This is called whenever a process attempts to open the device file */
+36static int device_open(struct inode *inode, struct file *file)
37{
-38 pr_info("device_open(%p)\n", file);
+38 pr_info("device_open(%p)\n", file);
39
-40 /* We don't want to talk to two processes at the same time. */
-41 if (atomic_cmpxchg(&already_open, CDEV_NOT_USED, CDEV_EXCLUSIVE_OPEN))
-42 return -EBUSY;
+40 /* We don't want to talk to two processes at the same time. */
+41 if (atomic_cmpxchg(&already_open, CDEV_NOT_USED, CDEV_EXCLUSIVE_OPEN))
+42 return -EBUSY;
43
44 try_module_get(THIS_MODULE);
-45 return SUCCESS;
+45 return SUCCESS;
46}
47
-48static int device_release(struct inode *inode, struct file *file)
+48static int device_release(struct inode *inode, struct file *file)
49{
-50 pr_info("device_release(%p,%p)\n", inode, file);
+50 pr_info("device_release(%p,%p)\n", inode, file);
51
-52 /* We're now ready for our next caller */
+52 /* We're now ready for our next caller */
53 atomic_set(&already_open, CDEV_NOT_USED);
54
55 module_put(THIS_MODULE);
-56 return SUCCESS;
+56 return SUCCESS;
57}
58
-59/* This function is called whenever a process which has already opened the
-60 * device file attempts to read from it.
-61 */
-62static ssize_t device_read(struct file *file, /* see include/linux/fs.h */
-63 char __user *buffer, /* buffer to be filled */
-64 size_t length, /* length of the buffer */
+59/* This function is called whenever a process which has already opened the
+60 * device file attempts to read from it.
+61 */
+62static ssize_t device_read(struct file *file, /* see include/linux/fs.h */
+63 char __user *buffer, /* buffer to be filled */
+64 size_t length, /* length of the buffer */
65 loff_t *offset)
66{
-67 /* Number of bytes actually written to the buffer */
-68 int bytes_read = 0;
-69 /* How far did the process reading the message get? Useful if the message
-70 * is larger than the size of the buffer we get to fill in device_read.
-71 */
-72 const char *message_ptr = message;
+67 /* Number of bytes actually written to the buffer */
+68 int bytes_read = 0;
+69 /* How far did the process reading the message get? Useful if the message
+70 * is larger than the size of the buffer we get to fill in device_read.
+71 */
+72 const char *message_ptr = message;
73
-74 if (!*(message_ptr + *offset)) { /* we are at the end of message */
-75 *offset = 0; /* reset the offset */
-76 return 0; /* signify end of file */
+74 if (!*(message_ptr + *offset)) { /* we are at the end of message */
+75 *offset = 0; /* reset the offset */
+76 return 0; /* signify end of file */
77 }
78
79 message_ptr += *offset;
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 */
+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);
+93 pr_info("Read %d bytes, %ld left\n", bytes_read, length);
94
95 *offset += bytes_read;
96
-97 /* Read functions are supposed to return the number of bytes actually
-98 * inserted into the buffer.
-99 */
-100 return bytes_read;
+97 /* Read functions are supposed to return the number of bytes actually
+98 * inserted into the buffer.
+99 */
+100 return bytes_read;
101}
102
-103/* called when somebody tries to write into our device file. */
-104static ssize_t device_write(struct file *file, const char __user *buffer,
-105 size_t length, loff_t *offset)
+103/* called when somebody tries to write into our device file. */
+104static ssize_t device_write(struct file *file, const char __user *buffer,
+105 size_t length, loff_t *offset)
106{
-107 int i;
+107 int i;
108
-109 pr_info("device_write(%p,%p,%ld)", file, buffer, length);
+109 pr_info("device_write(%p,%p,%ld)", file, buffer, length);
110
-111 for (i = 0; i < length && i < BUF_LEN; i++)
+111 for (i = 0; i < length && i < BUF_LEN; i++)
112 get_user(message[i], buffer + i);
113
-114 /* Again, return the number of input characters used. */
-115 return i;
+114 /* Again, return the number of input characters used. */
+115 return i;
116}
117
-118/* This function is called whenever a process tries to do an ioctl on our
-119 * device file. We get two extra parameters (additional to the inode and file
-120 * structures, which all device functions get): the number of the ioctl called
-121 * and the parameter given to the ioctl function.
-122 *
-123 * If the ioctl is write or read/write (meaning output is returned to the
-124 * calling process), the ioctl call returns the output of this function.
-125 */
-126static long
-127device_ioctl(struct file *file, /* ditto */
-128 unsigned int ioctl_num, /* number and param for ioctl */
-129 unsigned long ioctl_param)
+118/* This function is called whenever a process tries to do an ioctl on our
+119 * device file. We get two extra parameters (additional to the inode and file
+120 * structures, which all device functions get): the number of the ioctl called
+121 * and the parameter given to the ioctl function.
+122 *
+123 * If the ioctl is write or read/write (meaning output is returned to the
+124 * calling process), the ioctl call returns the output of this function.
+125 */
+126static long
+127device_ioctl(struct file *file, /* ditto */
+128 unsigned int ioctl_num, /* number and param for ioctl */
+129 unsigned long ioctl_param)
130{
-131 int i;
+131 int i;
132
-133 /* Switch according to the ioctl called */
-134 switch (ioctl_num) {
-135 case IOCTL_SET_MSG: {
-136 /* Receive a pointer to a message (in user space) and set that to
-137 * be the device's message. Get the parameter given to ioctl by
-138 * the process.
-139 */
-140 char __user *tmp = (char __user *)ioctl_param;
-141 char ch;
+133 /* Switch according to the ioctl called */
+134 switch (ioctl_num) {
+135 case IOCTL_SET_MSG: {
+136 /* Receive a pointer to a message (in user space) and set that to
+137 * be the device's message. Get the parameter given to ioctl by
+138 * the process.
+139 */
+140 char __user *tmp = (char __user *)ioctl_param;
+141 char ch;
142
-143 /* Find the length of the message */
+143 /* Find the length of the message */
144 get_user(ch, tmp);
-145 for (i = 0; ch && i < BUF_LEN; i++, tmp++)
+145 for (i = 0; ch && i < BUF_LEN; i++, tmp++)
146 get_user(ch, tmp);
147
-148 device_write(file, (char __user *)ioctl_param, i, NULL);
-149 break;
+148 device_write(file, (char __user *)ioctl_param, i, NULL);
+149 break;
150 }
-151 case IOCTL_GET_MSG: {
+151 case IOCTL_GET_MSG: {
152 loff_t offset = 0;
153
-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 __user *)ioctl_param, 99, &offset);
+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 __user *)ioctl_param, 99, &offset);
158
-159 /* Put a zero at the end of the buffer, so it will be properly
-160 * terminated.
-161 */
-162 put_user('\0', (char __user *)ioctl_param + i);
-163 break;
+159 /* Put a zero at the end of the buffer, so it will be properly
+160 * terminated.
+161 */
+162 put_user('\0', (char __user *)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 (long)message[ioctl_param];
-170 break;
+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 (long)message[ioctl_param];
+170 break;
171 }
172
-173 return SUCCESS;
+173 return SUCCESS;
174}
175
-176/* Module Declarations */
+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 */
-183static struct file_operations fops = {
+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 */
+183static struct 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 */
+188 .release = device_release, /* a.k.a. close */
189};
190
-191/* Initialize the module - Register the character device */
-192static int __init chardev2_init(void)
+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);
+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;
+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 cls = class_create(THIS_MODULE, DEVICE_FILE_NAME);
205 device_create(cls, NULL, MKDEV(MAJOR_NUM, 0), NULL, DEVICE_FILE_NAME);
206
-207 pr_info("Device created on /dev/%s\n", DEVICE_FILE_NAME);
+207 pr_info("Device created on /dev/%s\n", DEVICE_FILE_NAME);
208
-209 return 0;
+209 return 0;
210}
211
-212/* Cleanup - unregister the appropriate file from /proc */
-213static void __exit chardev2_exit(void)
+212/* Cleanup - unregister the appropriate file from /proc */
+213static void __exit chardev2_exit(void)
214{
215 device_destroy(cls, MKDEV(MAJOR_NUM, 0));
216 class_destroy(cls);
217
-218 /* Unregister the device */
+218 /* Unregister the device */
219 unregister_chrdev(MAJOR_NUM, DEVICE_NAME);
220}
221
222module_init(chardev2_init);
223module_exit(chardev2_exit);
224
-225MODULE_LICENSE("GPL");
+225MODULE_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 */
+
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
+9#ifndef CHARDEV_H
+10#define CHARDEV_H
11
-12#include <linux/ioctl.h>
+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
+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 */
+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 */
+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 */
+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"
+46/* The name of the device file */
+47#define DEVICE_FILE_NAME "char_dev"
48
-49#endif
+49#endif1/*
-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>
+
-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 val;
+12struct ioctl_arg {
+13 unsigned int val;
14};
15
-16/* Documentation/ioctl/ioctl-number.txt */
-17#define IOC_MAGIC '\x66'
+16/* Documentation/ioctl/ioctl-number.txt */
+17#define IOC_MAGIC '\x66'
18
-19#define IOCTL_VALSET _IOW(IOC_MAGIC, 0, struct ioctl_arg)
-20#define IOCTL_VALGET _IOR(IOC_MAGIC, 1, struct ioctl_arg)
-21#define IOCTL_VALGET_NUM _IOR(IOC_MAGIC, 2, int)
-22#define IOCTL_VALSET_NUM _IOW(IOC_MAGIC, 3, int)
+19#define IOCTL_VALSET _IOW(IOC_MAGIC, 0, struct ioctl_arg)
+20#define IOCTL_VALGET _IOR(IOC_MAGIC, 1, struct ioctl_arg)
+21#define IOCTL_VALGET_NUM _IOR(IOC_MAGIC, 2, int)
+22#define IOCTL_VALSET_NUM _IOW(IOC_MAGIC, 3, int)
23
-24#define IOCTL_VAL_MAXNR 3
-25#define DRIVER_NAME "ioctltest"
+24#define IOCTL_VAL_MAXNR 3
+25#define DRIVER_NAME "ioctltest"
26
-27static unsigned int test_ioctl_major = 0;
-28static unsigned int num_of_dev = 1;
-29static struct cdev test_ioctl_cdev;
-30static int ioctl_num = 0;
+27static unsigned int test_ioctl_major = 0;
+28static unsigned int num_of_dev = 1;
+29static struct cdev test_ioctl_cdev;
+30static int ioctl_num = 0;
31
-32struct test_ioctl_data {
-33 unsigned char val;
+32struct test_ioctl_data {
+33 unsigned char val;
34 rwlock_t lock;
35};
36
-37static long test_ioctl_ioctl(struct file *filp, unsigned int cmd,
-38 unsigned long arg)
+37static long test_ioctl_ioctl(struct file *filp, unsigned int cmd,
+38 unsigned long arg)
39{
-40 struct test_ioctl_data *ioctl_data = filp->private_data;
-41 int retval = 0;
-42 unsigned char val;
-43 struct ioctl_arg data;
-44 memset(&data, 0, sizeof(data));
+40 struct test_ioctl_data *ioctl_data = filp->private_data;
+41 int retval = 0;
+42 unsigned char val;
+43 struct ioctl_arg data;
+44 memset(&data, 0, sizeof(data));
45
-46 switch (cmd) {
-47 case IOCTL_VALSET:
-48 if (copy_from_user(&data, (int __user *)arg, sizeof(data))) {
+46 switch (cmd) {
+47 case IOCTL_VALSET:
+48 if (copy_from_user(&data, (int __user *)arg, sizeof(data))) {
49 retval = -EFAULT;
-50 goto done;
+50 goto done;
51 }
52
-53 pr_alert("IOCTL set val:%x .\n", data.val);
+53 pr_alert("IOCTL set val:%x .\n", data.val);
54 write_lock(&ioctl_data->lock);
55 ioctl_data->val = data.val;
56 write_unlock(&ioctl_data->lock);
-57 break;
+57 break;
58
-59 case IOCTL_VALGET:
+59 case IOCTL_VALGET:
60 read_lock(&ioctl_data->lock);
61 val = ioctl_data->val;
62 read_unlock(&ioctl_data->lock);
63 data.val = val;
64
-65 if (copy_to_user((int __user *)arg, &data, sizeof(data))) {
+65 if (copy_to_user((int __user *)arg, &data, sizeof(data))) {
66 retval = -EFAULT;
-67 goto done;
+67 goto done;
68 }
69
-70 break;
+70 break;
71
-72 case IOCTL_VALGET_NUM:
-73 retval = __put_user(ioctl_num, (int __user *)arg);
-74 break;
+72 case IOCTL_VALGET_NUM:
+73 retval = __put_user(ioctl_num, (int __user *)arg);
+74 break;
75
-76 case IOCTL_VALSET_NUM:
+76 case IOCTL_VALSET_NUM:
77 ioctl_num = arg;
-78 break;
+78 break;
79
-80 default:
+80 default:
81 retval = -ENOTTY;
82 }
83
84done:
-85 return retval;
+85 return retval;
86}
87
-88static ssize_t test_ioctl_read(struct file *filp, char __user *buf,
-89 size_t count, loff_t *f_pos)
+88static ssize_t test_ioctl_read(struct file *filp, char __user *buf,
+89 size_t count, loff_t *f_pos)
90{
-91 struct test_ioctl_data *ioctl_data = filp->private_data;
-92 unsigned char val;
-93 int retval;
-94 int i = 0;
+91 struct test_ioctl_data *ioctl_data = filp->private_data;
+92 unsigned char val;
+93 int retval;
+94 int i = 0;
95
96 read_lock(&ioctl_data->lock);
97 val = ioctl_data->val;
98 read_unlock(&ioctl_data->lock);
99
-100 for (; i < count; i++) {
-101 if (copy_to_user(&buf[i], &val, 1)) {
+100 for (; i < count; i++) {
+101 if (copy_to_user(&buf[i], &val, 1)) {
102 retval = -EFAULT;
-103 goto out;
+103 goto out;
104 }
105 }
106
107 retval = count;
108out:
-109 return retval;
+109 return retval;
110}
111
-112static int test_ioctl_close(struct inode *inode, struct file *filp)
+112static int test_ioctl_close(struct inode *inode, struct file *filp)
113{
-114 pr_alert("%s call.\n", __func__);
+114 pr_alert("%s call.\n", __func__);
115
-116 if (filp->private_data) {
+116 if (filp->private_data) {
117 kfree(filp->private_data);
118 filp->private_data = NULL;
119 }
120
-121 return 0;
+121 return 0;
122}
123
-124static int test_ioctl_open(struct inode *inode, struct file *filp)
+124static int test_ioctl_open(struct inode *inode, struct file *filp)
125{
-126 struct test_ioctl_data *ioctl_data;
+126 struct test_ioctl_data *ioctl_data;
127
-128 pr_alert("%s call.\n", __func__);
-129 ioctl_data = kmalloc(sizeof(struct test_ioctl_data), GFP_KERNEL);
+128 pr_alert("%s call.\n", __func__);
+129 ioctl_data = kmalloc(sizeof(struct test_ioctl_data), GFP_KERNEL);
130
-131 if (ioctl_data == NULL)
-132 return -ENOMEM;
+131 if (ioctl_data == NULL)
+132 return -ENOMEM;
133
134 rwlock_init(&ioctl_data->lock);
135 ioctl_data->val = 0xFF;
136 filp->private_data = ioctl_data;
137
-138 return 0;
+138 return 0;
139}
140
-141static struct file_operations fops = {
+141static struct file_operations fops = {
142 .owner = THIS_MODULE,
143 .open = test_ioctl_open,
144 .release = test_ioctl_close,
@@ -2837,60 +2880,60 @@ which we mentioned at 6.5
146 .unlocked_ioctl = test_ioctl_ioctl,
147};
148
-149static int ioctl_init(void)
+149static int ioctl_init(void)
150{
-151 dev_t dev;
-152 int alloc_ret = 0;
-153 int cdev_ret = 0;
+151 dev_t dev;
+152 int alloc_ret = 0;
+153 int cdev_ret = 0;
154 alloc_ret = alloc_chrdev_region(&dev, 0, num_of_dev, DRIVER_NAME);
155
-156 if (alloc_ret)
-157 goto error;
+156 if (alloc_ret)
+157 goto error;
158
159 test_ioctl_major = MAJOR(dev);
160 cdev_init(&test_ioctl_cdev, &fops);
161 cdev_ret = cdev_add(&test_ioctl_cdev, dev, num_of_dev);
162
-163 if (cdev_ret)
-164 goto error;
+163 if (cdev_ret)
+164 goto error;
165
-166 pr_alert("%s driver(major: %d) installed.\n", DRIVER_NAME,
+166 pr_alert("%s driver(major: %d) installed.\n", DRIVER_NAME,
167 test_ioctl_major);
-168 return 0;
+168 return 0;
169error:
-170 if (cdev_ret == 0)
+170 if (cdev_ret == 0)
171 cdev_del(&test_ioctl_cdev);
-172 if (alloc_ret == 0)
+172 if (alloc_ret == 0)
173 unregister_chrdev_region(dev, num_of_dev);
-174 return -1;
+174 return -1;
175}
176
-177static void ioctl_exit(void)
+177static void ioctl_exit(void)
178{
-179 dev_t dev = MKDEV(test_ioctl_major, 0);
+179 dev_t dev = MKDEV(test_ioctl_major, 0);
180
181 cdev_del(&test_ioctl_cdev);
182 unregister_chrdev_region(dev, num_of_dev);
-183 pr_alert("%s driver removed.\n", DRIVER_NAME);
+183 pr_alert("%s driver removed.\n", DRIVER_NAME);
184}
185
186module_init(ioctl_init);
187module_exit(ioctl_exit);
188
-189MODULE_LICENSE("GPL");
-190MODULE_DESCRIPTION("This is test_ioctl module");
+189MODULE_LICENSE("GPL");
+190MODULE_DESCRIPTION("This is test_ioctl module");10 System Calls
- open()
system call. This meant I could not open any files, I could not run any
@@ -2902,7 +2945,7 @@ ensure you do not lose any files, even within a test environment, please run
insmod
and the rmmod
.
- strace <arguments>
.
- sys_call_table
@@ -2936,7 +2979,7 @@ 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)
.
- sys_call_table
@@ -2944,7 +2987,7 @@ 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.
- sys_call_table
+ sys_call_table
, we need to consider the control register. A control register is a processor
register that changes or controls the general behavior of the CPU. For x86
architecture, the cr0 register has various control flags that modify the basic
@@ -2957,11 +3000,11 @@ read-only sections Therefore, we must disable the sys_call_table
+ sys_call_table
symbol is unexported to prevent misuse. But there have few ways to get the symbol, manual
symbol lookup and kallsyms_lookup_name
. Here we use both depend on the kernel version.
- kallsyms_lookup_name
+ kallsyms_lookup_name
is also unexported, it needs certain trick to get the address of
kallsyms_lookup_name
. If CONFIG_KPROBES
@@ -3001,7 +3044,7 @@ passes the addresses of the saved registers and the Kprobe struct to the handler
you defined, then executes it. Kprobes can be registered by symbol name
or address. Within the symbol name, the address will be handled by the
kernel.
- sys_call_table
+ sys_call_table
from /proc/kallsyms and /boot/System.map into
sym
parameter. Following is the sample usage for /proc/kallsyms:
@@ -3016,8 +3059,8 @@ ffffffff820013a0 R sys_call_table
ffffffff820023e0 R ia32_sys_call_table
$ sudo insmod syscall.ko sym=0xffffffff820013a0
-
- 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
@@ -3090,7 +3133,7 @@ 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.
- init_module
+ init_module
function replaces the appropriate location in
sys_call_table
and keeps the original pointer in a variable. The
@@ -3108,7 +3151,7 @@ with B_open
, which will call what it thinks is the original system call,
A_open
, when it’s done.
- 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,
@@ -3128,7 +3171,7 @@ problem. When A is removed, it sees that the system call was changed to
A_open
which is no longer there, so that even without removing B the system would
crash.
- sys_call_table
is no longer exported. This means, if you want to do something more than a mere
@@ -3140,226 +3183,226 @@ dry run of this example, you will have to patch your current kernel in order to
-
1/* -2 * syscall.c -3 * -4 * System call "stealing" sample. -5 * -6 * Disables page protection at a processor level by changing the 16th bit -7 * in the cr0 register (could be Intel specific). -8 * -9 * Based on example by Peter Jay Salzman and -10 * https://bbs.archlinux.org/viewtopic.php?id=139406 -11 */ ++1/* +2 * syscall.c +3 * +4 * System call "stealing" sample. +5 * +6 * Disables page protection at a processor level by changing the 16th bit +7 * in the cr0 register (could be Intel specific). +8 * +9 * Based on example by Peter Jay Salzman and +10 * https://bbs.archlinux.org/viewtopic.php?id=139406 +11 */ 12 -13#include <linux/delay.h> -14#include <linux/kernel.h> -15#include <linux/module.h> -16#include <linux/moduleparam.h> /* which will have params */ -17#include <linux/unistd.h> /* The list of system calls */ -18#include <linux/version.h> +13#include <linux/delay.h> +14#include <linux/kernel.h> +15#include <linux/module.h> +16#include <linux/moduleparam.h> /* which will have params */ +17#include <linux/unistd.h> /* The list of system calls */ +18#include <linux/version.h> 19 -20/* For the current (process) structure, we need this to know who the -21 * current user is. -22 */ -23#include <linux/sched.h> -24#include <linux/uaccess.h> +20/* For the current (process) structure, we need this to know who the +21 * current user is. +22 */ +23#include <linux/sched.h> +24#include <linux/uaccess.h> 25 -26/* The way we access "sys_call_table" varies as kernel internal changes. -27 * - ver <= 5.4 : manual symbol lookup -28 * - 5.4 < ver < 5.7 : kallsyms_lookup_name -29 * - 5.7 <= ver : Kprobes or specific kernel module parameter -30 */ +26/* The way we access "sys_call_table" varies as kernel internal changes. +27 * - ver <= 5.4 : manual symbol lookup +28 * - 5.4 < ver < 5.7 : kallsyms_lookup_name +29 * - 5.7 <= ver : Kprobes or specific kernel module parameter +30 */ 31 -32/* The in-kernel calls to the ksys_close() syscall were removed in Linux v5.11+. -33 */ -34#if (LINUX_VERSION_CODE < KERNEL_VERSION(5, 7, 0)) +32/* The in-kernel calls to the ksys_close() syscall were removed in Linux v5.11+. +33 */ +34#if (LINUX_VERSION_CODE < KERNEL_VERSION(5, 7, 0)) 35 -36#if LINUX_VERSION_CODE <= KERNEL_VERSION(5, 4, 0) -37#define HAVE_KSYS_CLOSE 1 -38#include <linux/syscalls.h> /* For ksys_close() */ -39#else -40#include <linux/kallsyms.h> /* For kallsyms_lookup_name */ -41#endif +36#if LINUX_VERSION_CODE <= KERNEL_VERSION(5, 4, 0) +37#define HAVE_KSYS_CLOSE 1 +38#include <linux/syscalls.h> /* For ksys_close() */ +39#else +40#include <linux/kallsyms.h> /* For kallsyms_lookup_name */ +41#endif 42 -43#else +43#else 44 -45#if defined(CONFIG_KPROBES) -46#define HAVE_KPROBES 1 -47#include <linux/kprobes.h> -48#else -49#define HAVE_PARAM 1 -50#include <linux/kallsyms.h> /* For sprint_symbol */ -51/* The address of the sys_call_table, which can be obtained with looking up -52 * "/boot/System.map" or "/proc/kallsyms". When the kernel version is v5.7+, -53 * without CONFIG_KPROBES, you can input the parameter or the module will look -54 * up all the memory. -55 */ -56static unsigned long sym = 0; +45#if defined(CONFIG_KPROBES) +46#define HAVE_KPROBES 1 +47#include <linux/kprobes.h> +48#else +49#define HAVE_PARAM 1 +50#include <linux/kallsyms.h> /* For sprint_symbol */ +51/* The address of the sys_call_table, which can be obtained with looking up +52 * "/boot/System.map" or "/proc/kallsyms". When the kernel version is v5.7+, +53 * without CONFIG_KPROBES, you can input the parameter or the module will look +54 * up all the memory. +55 */ +56static unsigned long sym = 0; 57module_param(sym, ulong, 0644); -58#endif /* CONFIG_KPROBES */ +58#endif /* CONFIG_KPROBES */ 59 -60#endif /* Version < v5.7 */ +60#endif /* Version < v5.7 */ 61 -62static unsigned long **sys_call_table; +62static unsigned long **sys_call_table; 63 -64/* UID we want to spy on - will be filled from the command line. */ -65static int uid; -66module_param(uid, int, 0644); +64/* UID we want to spy on - will be filled from the command line. */ +65static int uid; +66module_param(uid, int, 0644); 67 -68/* A pointer to the original system call. The reason we keep this, rather -69 * than call the original function (sys_open), is because somebody else -70 * might have replaced the system call before us. Note that this is not -71 * 100% safe, because if another module replaced sys_open before us, -72 * then when we are inserted, we will call the function in that module - -73 * and it might be removed before we are. -74 * -75 * Another reason for this is that we can not get sys_open. -76 * It is a static variable, so it is not exported. -77 */ -78static asmlinkage int (*original_call)(const char *, int, int); +68/* A pointer to the original system call. The reason we keep this, rather +69 * than call the original function (sys_open), is because somebody else +70 * might have replaced the system call before us. Note that this is not +71 * 100% safe, because if another module replaced sys_open before us, +72 * then when we are inserted, we will call the function in that module - +73 * and it might be removed before we are. +74 * +75 * Another reason for this is that we can not get sys_open. +76 * It is a static variable, so it is not exported. +77 */ +78static asmlinkage int (*original_call)(const char *, int, int); 79 -80/* The function we will replace sys_open (the function called when you -81 * call the open system call) with. To find the exact prototype, with -82 * the number and type of arguments, we find the original function first -83 * (it is at fs/open.c). -84 * -85 * In theory, this means that we are tied to the current version of the -86 * kernel. In practice, the system calls almost never change (it would -87 * wreck havoc and require programs to be recompiled, since the system -88 * calls are the interface between the kernel and the processes). -89 */ -90static asmlinkage int our_sys_open(const char *filename, int flags, int mode) +80/* The function we will replace sys_open (the function called when you +81 * call the open system call) with. To find the exact prototype, with +82 * the number and type of arguments, we find the original function first +83 * (it is at fs/open.c). +84 * +85 * In theory, this means that we are tied to the current version of the +86 * kernel. In practice, the system calls almost never change (it would +87 * wreck havoc and require programs to be recompiled, since the system +88 * calls are the interface between the kernel and the processes). +89 */ +90static asmlinkage int our_sys_open(const char *filename, int flags, int mode) 91{ -92 int i = 0; -93 char ch; +92 int i = 0; +93 char ch; 94 -95 /* Report the file, if relevant */ -96 pr_info("Opened file by %d: ", uid); -97 do { -98 get_user(ch, (char __user *)filename + i); +95 /* Report the file, if relevant */ +96 pr_info("Opened file by %d: ", uid); +97 do { +98 get_user(ch, (char __user *)filename + i); 99 i++; -100 pr_info("%c", ch); -101 } while (ch != 0); -102 pr_info("\n"); +100 pr_info("%c", ch); +101 } while (ch != 0); +102 pr_info("\n"); 103 -104 /* Call the original sys_open - otherwise, we lose the ability to -105 * open files. -106 */ -107 return original_call(filename, flags, mode); +104 /* Call the original sys_open - otherwise, we lose the ability to +105 * open files. +106 */ +107 return original_call(filename, flags, mode); 108} 109 -110static unsigned long **aquire_sys_call_table(void) +110static unsigned long **aquire_sys_call_table(void) 111{ -112#ifdef HAVE_KSYS_CLOSE -113 unsigned long int offset = PAGE_OFFSET; -114 unsigned long **sct; +112#ifdef HAVE_KSYS_CLOSE +113 unsigned long int offset = PAGE_OFFSET; +114 unsigned long **sct; 115 -116 while (offset < ULLONG_MAX) { -117 sct = (unsigned long **)offset; +116 while (offset < ULLONG_MAX) { +117 sct = (unsigned long **)offset; 118 -119 if (sct[__NR_close] == (unsigned long *)ksys_close) -120 return sct; +119 if (sct[__NR_close] == (unsigned long *)ksys_close) +120 return sct; 121 -122 offset += sizeof(void *); +122 offset += sizeof(void *); 123 } 124 -125 return NULL; -126#endif +125 return NULL; +126#endif 127 -128#ifdef HAVE_PARAM -129 const char sct_name[15] = "sys_call_table"; -130 char symbol[40] = { 0 }; +128#ifdef HAVE_PARAM +129 const char sct_name[15] = "sys_call_table"; +130 char symbol[40] = { 0 }; 131 -132 if (sym == 0) { -133 pr_alert("For Linux v5.7+, Kprobes is the preferable way to get " -134 "symbol.\n"); -135 pr_info("If Kprobes is absent, you have to specify the address of " -136 "sys_call_table symbol\n"); -137 pr_info("by /boot/System.map or /proc/kallsyms, which contains all the " -138 "symbol addresses, into sym parameter.\n"); -139 return NULL; +132 if (sym == 0) { +133 pr_alert("For Linux v5.7+, Kprobes is the preferable way to get " +134 "symbol.\n"); +135 pr_info("If Kprobes is absent, you have to specify the address of " +136 "sys_call_table symbol\n"); +137 pr_info("by /boot/System.map or /proc/kallsyms, which contains all the " +138 "symbol addresses, into sym parameter.\n"); +139 return NULL; 140 } 141 sprint_symbol(symbol, sym); -142 if (!strncmp(sct_name, symbol, sizeof(sct_name) - 1)) -143 return (unsigned long **)sym; +142 if (!strncmp(sct_name, symbol, sizeof(sct_name) - 1)) +143 return (unsigned long **)sym; 144 -145 return NULL; -146#endif +145 return NULL; +146#endif 147 -148#ifdef HAVE_KPROBES -149 unsigned long (*kallsyms_lookup_name)(const char *name); -150 struct kprobe kp = { -151 .symbol_name = "kallsyms_lookup_name", +148#ifdef HAVE_KPROBES +149 unsigned long (*kallsyms_lookup_name)(const char *name); +150 struct kprobe kp = { +151 .symbol_name = "kallsyms_lookup_name", 152 }; 153 -154 if (register_kprobe(&kp) < 0) -155 return NULL; -156 kallsyms_lookup_name = (unsigned long (*)(const char *name))kp.addr; +154 if (register_kprobe(&kp) < 0) +155 return NULL; +156 kallsyms_lookup_name = (unsigned long (*)(const char *name))kp.addr; 157 unregister_kprobe(&kp); -158#endif +158#endif 159 -160 return (unsigned long **)kallsyms_lookup_name("sys_call_table"); +160 return (unsigned long **)kallsyms_lookup_name("sys_call_table"); 161} 162 -163#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 3, 0) -164static inline void __write_cr0(unsigned long cr0) +163#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 3, 0) +164static inline void __write_cr0(unsigned long cr0) 165{ -166 asm volatile("mov %0,%%cr0" : "+r"(cr0) : : "memory"); +166 asm volatile("mov %0,%%cr0" : "+r"(cr0) : : "memory"); 167} -168#else -169#define __write_cr0 write_cr0 -170#endif +168#else +169#define __write_cr0 write_cr0 +170#endif 171 -172static void enable_write_protection(void) +172static void enable_write_protection(void) 173{ -174 unsigned long cr0 = read_cr0(); +174 unsigned long cr0 = read_cr0(); 175 set_bit(16, &cr0); 176 __write_cr0(cr0); 177} 178 -179static void disable_write_protection(void) +179static void disable_write_protection(void) 180{ -181 unsigned long cr0 = read_cr0(); +181 unsigned long cr0 = read_cr0(); 182 clear_bit(16, &cr0); 183 __write_cr0(cr0); 184} 185 -186static int __init syscall_start(void) +186static int __init syscall_start(void) 187{ -188 if (!(sys_call_table = aquire_sys_call_table())) -189 return -1; +188 if (!(sys_call_table = aquire_sys_call_table())) +189 return -1; 190 191 disable_write_protection(); 192 -193 /* keep track of the original open function */ -194 original_call = (void *)sys_call_table[__NR_open]; +193 /* keep track of the original open function */ +194 original_call = (void *)sys_call_table[__NR_open]; 195 -196 /* use our open function instead */ -197 sys_call_table[__NR_open] = (unsigned long *)our_sys_open; +196 /* use our open function instead */ +197 sys_call_table[__NR_open] = (unsigned long *)our_sys_open; 198 199 enable_write_protection(); 200 -201 pr_info("Spying on UID:%d\n", uid); +201 pr_info("Spying on UID:%d\n", uid); 202 -203 return 0; +203 return 0; 204} 205 -206static void __exit syscall_end(void) +206static void __exit syscall_end(void) 207{ -208 if (!sys_call_table) -209 return; +208 if (!sys_call_table) +209 return; 210 -211 /* Return the system call back to normal */ -212 if (sys_call_table[__NR_open] != (unsigned long *)our_sys_open) { -213 pr_alert("Somebody else also played with the "); -214 pr_alert("open system call\n"); -215 pr_alert("The system may be left in "); -216 pr_alert("an unstable state.\n"); +211 /* Return the system call back to normal */ +212 if (sys_call_table[__NR_open] != (unsigned long *)our_sys_open) { +213 pr_alert("Somebody else also played with the "); +214 pr_alert("open system call\n"); +215 pr_alert("The system may be left in "); +216 pr_alert("an unstable state.\n"); 217 } 218 219 disable_write_protection(); -220 sys_call_table[__NR_open] = (unsigned long *)original_call; +220 sys_call_table[__NR_open] = (unsigned long *)original_call; 221 enable_write_protection(); 222 223 msleep(2000); @@ -3368,14 +3411,14 @@ dry run of this example, you will have to patch your current kernel in order to 226module_init(syscall_start); 227module_exit(syscall_end); 228 -229MODULE_LICENSE("GPL");-
11 Blocking Processes and threads
-+
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 @@ -3383,21 +3426,21 @@ possibility. You can put the process to sleep until you can service it. After al 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 +
1tail -f+
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
@@ -3410,31 +3453,31 @@ 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
. We could have used module_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
@@ -3470,449 +3513,449 @@ $ cat_nonblock /proc/sleep
Last input:
$
-
+
-
1/* -2 * sleep.c - create a /proc file, and if several processes try to open it -3 * at the same time, put all but one to sleep. -4 */ +1/* +2 * sleep.c - create a /proc file, and if several processes try to open it +3 * at the same time, put all but one to sleep. +4 */ 5 -6#include <linux/kernel.h> /* We're doing kernel work */ -7#include <linux/module.h> /* Specifically, a module */ -8#include <linux/proc_fs.h> /* Necessary because we use proc fs */ -9#include <linux/sched.h> /* For putting processes to sleep and -10 waking them up */ -11#include <linux/uaccess.h> /* for get_user and put_user */ -12#include <linux/version.h> +6#include <linux/kernel.h> /* We're doing kernel work */ +7#include <linux/module.h> /* Specifically, a module */ +8#include <linux/proc_fs.h> /* Necessary because we use proc fs */ +9#include <linux/sched.h> /* For putting processes to sleep and +10 waking them up */ +11#include <linux/uaccess.h> /* for get_user and put_user */ +12#include <linux/version.h> 13 -14#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0) -15#define HAVE_PROC_OPS -16#endif +14#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0) +15#define HAVE_PROC_OPS +16#endif 17 -18/* Here we keep the last message received, to prove that we can process our -19 * input. -20 */ -21#define MESSAGE_LENGTH 80 -22static char message[MESSAGE_LENGTH]; +18/* Here we keep the last message received, to prove that we can process our +19 * input. +20 */ +21#define MESSAGE_LENGTH 80 +22static char message[MESSAGE_LENGTH]; 23 -24static struct proc_dir_entry *our_proc_file; -25#define PROC_ENTRY_FILENAME "sleep" +24static struct proc_dir_entry *our_proc_file; +25#define PROC_ENTRY_FILENAME "sleep" 26 -27/* Since we use the file operations struct, we can't use the special proc -28 * output provisions - we have to use a standard read function, which is this -29 * function. -30 */ -31static ssize_t module_output(struct file *file, /* see include/linux/fs.h */ -32 char __user *buf, /* The buffer to put data to -33 (in the user segment) */ -34 size_t len, /* The length of the buffer */ +27/* Since we use the file operations struct, we can't use the special proc +28 * output provisions - we have to use a standard read function, which is this +29 * function. +30 */ +31static ssize_t module_output(struct file *file, /* see include/linux/fs.h */ +32 char __user *buf, /* The buffer to put data to +33 (in the user segment) */ +34 size_t len, /* The length of the buffer */ 35 loff_t *offset) 36{ -37 static int finished = 0; -38 int i; -39 char output_msg[MESSAGE_LENGTH + 30]; +37 static int finished = 0; +38 int i; +39 char output_msg[MESSAGE_LENGTH + 30]; 40 -41 /* Return 0 to signify end of file - that we have nothing more to say -42 * at this point. -43 */ -44 if (finished) { +41 /* Return 0 to signify end of file - that we have nothing more to say +42 * at this point. +43 */ +44 if (finished) { 45 finished = 0; -46 return 0; +46 return 0; 47 } 48 -49 sprintf(output_msg, "Last input:%s\n", message); -50 for (i = 0; i < len && output_msg[i]; i++) +49 sprintf(output_msg, "Last input:%s\n", message); +50 for (i = 0; i < len && output_msg[i]; i++) 51 put_user(output_msg[i], buf + i); 52 53 finished = 1; -54 return i; /* Return the number of bytes "read" */ +54 return i; /* Return the number of bytes "read" */ 55} 56 -57/* This function receives input from the user when the user writes to the -58 * /proc file. -59 */ -60static ssize_t module_input(struct file *file, /* The file itself */ -61 const char __user *buf, /* The buffer with input */ -62 size_t length, /* The buffer's length */ -63 loff_t *offset) /* offset to file - ignore */ +57/* This function receives input from the user when the user writes to the +58 * /proc file. +59 */ +60static ssize_t module_input(struct file *file, /* The file itself */ +61 const char __user *buf, /* The buffer with input */ +62 size_t length, /* The buffer's length */ +63 loff_t *offset) /* offset to file - ignore */ 64{ -65 int i; +65 int i; 66 -67 /* Put the input into Message, where module_output will later be able -68 * to use it. -69 */ -70 for (i = 0; i < MESSAGE_LENGTH - 1 && i < length; i++) +67 /* Put the input into Message, where module_output will later be able +68 * to use it. +69 */ +70 for (i = 0; i < MESSAGE_LENGTH - 1 && i < length; i++) 71 get_user(message[i], buf + i); -72 /* we want a standard, zero terminated string */ -73 message[i] = '\0'; +72 /* we want a standard, zero terminated string */ +73 message[i] = '\0'; 74 -75 /* We need to return the number of input characters used */ -76 return i; +75 /* We need to return the number of input characters used */ +76 return i; 77} 78 -79/* 1 if the file is currently open by somebody */ -80static atomic_t already_open = ATOMIC_INIT(0); +79/* 1 if the file is currently open by somebody */ +80static atomic_t already_open = ATOMIC_INIT(0); 81 -82/* Queue of processes who want our file */ -83static DECLARE_WAIT_QUEUE_HEAD(waitq); +82/* Queue of processes who want our file */ +83static DECLARE_WAIT_QUEUE_HEAD(waitq); 84 -85/* Called when the /proc file is opened */ -86static int module_open(struct inode *inode, struct file *file) +85/* Called when the /proc file is opened */ +86static int module_open(struct inode *inode, struct file *file) 87{ -88 /* If the file's flags include O_NONBLOCK, it means the process does not -89 * want to wait for the file. In this case, if the file is already open, -90 * we should fail with -EAGAIN, meaning "you will have to try again", -91 * instead of blocking a process which would rather stay awake. -92 */ -93 if ((file->f_flags & O_NONBLOCK) && atomic_read(&already_open)) -94 return -EAGAIN; +88 /* If the file's flags include O_NONBLOCK, it means the process does not +89 * want to wait for the file. In this case, if the file is already open, +90 * we should fail with -EAGAIN, meaning "you will have to try again", +91 * instead of blocking a process which would rather stay awake. +92 */ +93 if ((file->f_flags & O_NONBLOCK) && atomic_read(&already_open)) +94 return -EAGAIN; 95 -96 /* This is the correct place for try_module_get(THIS_MODULE) because if -97 * a process is in the loop, which is within the kernel module, -98 * the kernel module must not be removed. -99 */ +96 /* This is the correct place for try_module_get(THIS_MODULE) because if +97 * a process is in the loop, which is within the kernel module, +98 * the kernel module must not be removed. +99 */ 100 try_module_get(THIS_MODULE); 101 -102 while (atomic_cmpxchg(&already_open, 0, 1)) { -103 int i, is_sig = 0; +102 while (atomic_cmpxchg(&already_open, 0, 1)) { +103 int i, is_sig = 0; 104 -105 /* This function puts the current process, including any system -106 * calls, such as us, to sleep. Execution will be resumed right -107 * after the function call, either because somebody called -108 * wake_up(&waitq) (only module_close does that, when the file -109 * is closed) or when a signal, such as Ctrl-C, is sent -110 * to the process -111 */ +105 /* This function puts the current process, including any system +106 * calls, such as us, to sleep. Execution will be resumed right +107 * after the function call, either because somebody called +108 * wake_up(&waitq) (only module_close does that, when the file +109 * is closed) or when a signal, such as Ctrl-C, is sent +110 * to the process +111 */ 112 wait_event_interruptible(waitq, !atomic_read(&already_open)); 113 -114 /* If we woke up because we got a signal we're not blocking, -115 * return -EINTR (fail the system call). This allows processes -116 * to be killed or stopped. -117 */ -118 for (i = 0; i < _NSIG_WORDS && !is_sig; i++) +114 /* If we woke up because we got a signal we're not blocking, +115 * return -EINTR (fail the system call). This allows processes +116 * to be killed or stopped. +117 */ +118 for (i = 0; i < _NSIG_WORDS && !is_sig; i++) 119 is_sig = current->pending.signal.sig[i] & ~current->blocked.sig[i]; 120 -121 if (is_sig) { -122 /* It is important to put module_put(THIS_MODULE) here, because -123 * for processes where the open is interrupted there will never -124 * be a corresponding close. If we do not decrement the usage -125 * count here, we will be left with a positive usage count -126 * which we will have no way to bring down to zero, giving us -127 * an immortal module, which can only be killed by rebooting -128 * the machine. -129 */ +121 if (is_sig) { +122 /* It is important to put module_put(THIS_MODULE) here, because +123 * for processes where the open is interrupted there will never +124 * be a corresponding close. If we do not decrement the usage +125 * count here, we will be left with a positive usage count +126 * which we will have no way to bring down to zero, giving us +127 * an immortal module, which can only be killed by rebooting +128 * the machine. +129 */ 130 module_put(THIS_MODULE); -131 return -EINTR; +131 return -EINTR; 132 } 133 } 134 -135 return 0; /* Allow the access */ +135 return 0; /* Allow the access */ 136} 137 -138/* Called when the /proc file is closed */ -139static int module_close(struct inode *inode, struct file *file) +138/* Called when the /proc file is closed */ +139static int module_close(struct inode *inode, struct file *file) 140{ -141 /* Set already_open to zero, so one of the processes in the waitq will -142 * be able to set already_open back to one and to open the file. All -143 * the other processes will be called when already_open is back to one, -144 * so they'll go back to sleep. -145 */ +141 /* Set already_open to zero, so one of the processes in the waitq will +142 * be able to set already_open back to one and to open the file. All +143 * the other processes will be called when already_open is back to one, +144 * so they'll go back to sleep. +145 */ 146 atomic_set(&already_open, 0); 147 -148 /* Wake up all the processes in waitq, so if anybody is waiting for the -149 * file, they can have it. -150 */ +148 /* Wake up all the processes in waitq, so if anybody is waiting for the +149 * file, they can have it. +150 */ 151 wake_up(&waitq); 152 153 module_put(THIS_MODULE); 154 -155 return 0; /* success */ +155 return 0; /* success */ 156} 157 -158/* Structures to register as the /proc file, with pointers to all the relevant -159 * functions. -160 */ +158/* Structures to register as the /proc file, with pointers to all the relevant +159 * functions. +160 */ 161 -162/* File operations for our proc file. This is where we place pointers to all -163 * the functions called when somebody tries to do something to our file. NULL -164 * means we don't want to deal with something. -165 */ -166#ifdef HAVE_PROC_OPS -167static const struct proc_ops file_ops_4_our_proc_file = { -168 .proc_read = module_output, /* "read" from the file */ -169 .proc_write = module_input, /* "write" to the file */ -170 .proc_open = module_open, /* called when the /proc file is opened */ -171 .proc_release = module_close, /* called when it's closed */ +162/* File operations for our proc file. This is where we place pointers to all +163 * the functions called when somebody tries to do something to our file. NULL +164 * means we don't want to deal with something. +165 */ +166#ifdef HAVE_PROC_OPS +167static const struct proc_ops file_ops_4_our_proc_file = { +168 .proc_read = module_output, /* "read" from the file */ +169 .proc_write = module_input, /* "write" to the file */ +170 .proc_open = module_open, /* called when the /proc file is opened */ +171 .proc_release = module_close, /* called when it's closed */ 172}; -173#else -174static const struct file_operations file_ops_4_our_proc_file = { +173#else +174static const struct file_operations file_ops_4_our_proc_file = { 175 .read = module_output, 176 .write = module_input, 177 .open = module_open, 178 .release = module_close, 179}; -180#endif +180#endif 181 -182/* Initialize the module - register the proc file */ -183static int __init sleep_init(void) +182/* Initialize the module - register the proc file */ +183static int __init sleep_init(void) 184{ 185 our_proc_file = 186 proc_create(PROC_ENTRY_FILENAME, 0644, NULL, &file_ops_4_our_proc_file); -187 if (our_proc_file == NULL) { +187 if (our_proc_file == NULL) { 188 remove_proc_entry(PROC_ENTRY_FILENAME, NULL); -189 pr_debug("Error: Could not initialize /proc/%s\n", PROC_ENTRY_FILENAME); -190 return -ENOMEM; +189 pr_debug("Error: Could not initialize /proc/%s\n", PROC_ENTRY_FILENAME); +190 return -ENOMEM; 191 } 192 proc_set_size(our_proc_file, 80); 193 proc_set_user(our_proc_file, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID); 194 -195 pr_info("/proc/%s created\n", PROC_ENTRY_FILENAME); +195 pr_info("/proc/%s created\n", PROC_ENTRY_FILENAME); 196 -197 return 0; +197 return 0; 198} 199 -200/* Cleanup - unregister our file from /proc. This could get dangerous if -201 * there are still processes waiting in waitq, because they are inside our -202 * open function, which will get unloaded. I'll explain how to avoid removal -203 * of a kernel module in such a case in chapter 10. -204 */ -205static void __exit sleep_exit(void) +200/* Cleanup - unregister our file from /proc. This could get dangerous if +201 * there are still processes waiting in waitq, because they are inside our +202 * open function, which will get unloaded. I'll explain how to avoid removal +203 * of a kernel module in such a case in chapter 10. +204 */ +205static void __exit sleep_exit(void) 206{ 207 remove_proc_entry(PROC_ENTRY_FILENAME, NULL); -208 pr_debug("/proc/%s removed\n", PROC_ENTRY_FILENAME); +208 pr_debug("/proc/%s removed\n", PROC_ENTRY_FILENAME); 209} 210 211module_init(sleep_init); 212module_exit(sleep_exit); 213 -214MODULE_LICENSE("GPL");+214MODULE_LICENSE("GPL");
-
1/* -2 * cat_nonblock.c - open a file and display its contents, but exit rather than -3 * wait for input. -4 */ -5#include <errno.h> /* for errno */ -6#include <fcntl.h> /* for open */ -7#include <stdio.h> /* standard I/O */ -8#include <stdlib.h> /* for exit */ -9#include <unistd.h> /* for read */ +1/* +2 * cat_nonblock.c - open a file and display its contents, but exit rather than +3 * wait for input. +4 */ +5#include <errno.h> /* for errno */ +6#include <fcntl.h> /* for open */ +7#include <stdio.h> /* standard I/O */ +8#include <stdlib.h> /* for exit */ +9#include <unistd.h> /* for read */ 10 -11#define MAX_BYTES 1024 * 4 +11#define MAX_BYTES 1024 * 4 12 -13int main(int argc, char *argv[]) +13int main(int argc, char *argv[]) 14{ -15 int fd; /* The file descriptor for the file to read */ -16 size_t bytes; /* The number of bytes read */ -17 char buffer[MAX_BYTES]; /* The buffer for the bytes */ +15 int fd; /* The file descriptor for the file to read */ +16 size_t bytes; /* The number of bytes read */ +17 char buffer[MAX_BYTES]; /* The buffer for the bytes */ 18 -19 /* Usage */ -20 if (argc != 2) { -21 printf("Usage: %s <filename>\n", argv[0]); -22 puts("Reads the content of a file, but doesn't wait for input"); +19 /* Usage */ +20 if (argc != 2) { +21 printf("Usage: %s <filename>\n", argv[0]); +22 puts("Reads the content of a file, but doesn't wait for input"); 23 exit(-1); 24 } 25 -26 /* Open the file for reading in non blocking mode */ +26 /* Open the file for reading in non blocking mode */ 27 fd = open(argv[1], O_RDONLY | O_NONBLOCK); 28 -29 /* If open failed */ -30 if (fd == -1) { -31 puts(errno == EAGAIN ? "Open would block" : "Open failed"); +29 /* If open failed */ +30 if (fd == -1) { +31 puts(errno == EAGAIN ? "Open would block" : "Open failed"); 32 exit(-1); 33 } 34 -35 /* Read the file and output its contents */ -36 do { -37 /* Read characters from the file */ +35 /* Read the file and output its contents */ +36 do { +37 /* Read characters from the file */ 38 bytes = read(fd, buffer, MAX_BYTES); 39 -40 /* If there's an error, report it and die */ -41 if (bytes == -1) { -42 if (errno == EAGAIN) -43 puts("Normally I'd block, but you told me not to"); -44 else -45 puts("Another read error"); +40 /* If there's an error, report it and die */ +41 if (bytes == -1) { +42 if (errno == EAGAIN) +43 puts("Normally I'd block, but you told me not to"); +44 else +45 puts("Another read error"); 46 exit(-1); 47 } 48 -49 /* Print the characters */ -50 if (bytes > 0) { -51 for (int i = 0; i < bytes; i++) +49 /* Print the characters */ +50 if (bytes > 0) { +51 for (int i = 0; i < bytes; i++) 52 putchar(buffer[i]); 53 } 54 -55 /* While there are no errors and the file isn't over */ -56 } while (bytes > 0); +55 /* While there are no errors and the file isn't over */ +56 } while (bytes > 0); 57 -58 return 0; +58 return 0; 59}-+
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/sleepcommands, 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.
-
1/* -2 * completions.c -3 */ -4#include <linux/completion.h> -5#include <linux/init.h> -6#include <linux/kernel.h> -7#include <linux/kthread.h> -8#include <linux/module.h> ++1/* +2 * completions.c +3 */ +4#include <linux/completion.h> +5#include <linux/init.h> +6#include <linux/kernel.h> +7#include <linux/kthread.h> +8#include <linux/module.h> 9 -10static struct { -11 struct completion crank_comp; -12 struct completion flywheel_comp; +10static struct { +11 struct completion crank_comp; +12 struct completion flywheel_comp; 13} machine; 14 -15static int machine_crank_thread(void *arg) +15static int machine_crank_thread(void *arg) 16{ -17 pr_info("Turn the crank\n"); +17 pr_info("Turn the crank\n"); 18 19 complete_all(&machine.crank_comp); 20 complete_and_exit(&machine.crank_comp, 0); 21} 22 -23static int machine_flywheel_spinup_thread(void *arg) +23static int machine_flywheel_spinup_thread(void *arg) 24{ 25 wait_for_completion(&machine.crank_comp); 26 -27 pr_info("Flywheel spins up\n"); +27 pr_info("Flywheel spins up\n"); 28 29 complete_all(&machine.flywheel_comp); 30 complete_and_exit(&machine.flywheel_comp, 0); 31} 32 -33static int completions_init(void) +33static int completions_init(void) 34{ -35 struct task_struct *crank_thread; -36 struct task_struct *flywheel_thread; +35 struct task_struct *crank_thread; +36 struct task_struct *flywheel_thread; 37 -38 pr_info("completions example\n"); +38 pr_info("completions example\n"); 39 40 init_completion(&machine.crank_comp); 41 init_completion(&machine.flywheel_comp); 42 -43 crank_thread = kthread_create(machine_crank_thread, NULL, "KThread Crank"); -44 if (IS_ERR(crank_thread)) -45 goto ERROR_THREAD_1; +43 crank_thread = kthread_create(machine_crank_thread, NULL, "KThread Crank"); +44 if (IS_ERR(crank_thread)) +45 goto ERROR_THREAD_1; 46 47 flywheel_thread = kthread_create(machine_flywheel_spinup_thread, NULL, -48 "KThread Flywheel"); -49 if (IS_ERR(flywheel_thread)) -50 goto ERROR_THREAD_2; +48 "KThread Flywheel"); +49 if (IS_ERR(flywheel_thread)) +50 goto ERROR_THREAD_2; 51 52 wake_up_process(flywheel_thread); 53 wake_up_process(crank_thread); 54 -55 return 0; +55 return 0; 56 57ERROR_THREAD_2: 58 kthread_stop(crank_thread); 59ERROR_THREAD_1: 60 -61 return -1; +61 return -1; 62} 63 -64static void completions_exit(void) +64static void completions_exit(void) 65{ 66 wait_for_completion(&machine.crank_comp); 67 wait_for_completion(&machine.flywheel_comp); 68 -69 pr_info("completions exit\n"); +69 pr_info("completions exit\n"); 70} 71 72module_init(completions_init); 73module_exit(completions_exit); 74 -75MODULE_DESCRIPTION("Completions example"); -76MODULE_LICENSE("GPL");-The
machine +75MODULE_DESCRIPTION("Completions example"); +76MODULE_LICENSE("GPL");The
machinestructure stores the completion states for the two threads. At the exit point of each thread the respective completion state is updated, andwait_for_completionis used by the flywheel thread to ensure that it does not begin prematurely. -So even though
flywheel_thread +So even though
flywheel_threadis started first you should notice if you load this module and rundmesgthat 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_completionfunction, which include timeouts or being interrupted, but this basic mechanism is enough for many common situations without adding a lot of complexity. -+
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.
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.
-
1/* -2 * example_mutex.c -3 */ -4#include <linux/init.h> -5#include <linux/kernel.h> -6#include <linux/module.h> -7#include <linux/mutex.h> ++1/* +2 * example_mutex.c +3 */ +4#include <linux/init.h> +5#include <linux/kernel.h> +6#include <linux/module.h> +7#include <linux/mutex.h> 8 -9static DEFINE_MUTEX(mymutex); +9static DEFINE_MUTEX(mymutex); 10 -11static int example_mutex_init(void) +11static int example_mutex_init(void) 12{ -13 int ret; +13 int ret; 14 -15 pr_info("example_mutex init\n"); +15 pr_info("example_mutex init\n"); 16 17 ret = mutex_trylock(&mymutex); -18 if (ret != 0) { -19 pr_info("mutex is locked\n"); +18 if (ret != 0) { +19 pr_info("mutex is locked\n"); 20 -21 if (mutex_is_locked(&mymutex) == 0) -22 pr_info("The mutex failed to lock!\n"); +21 if (mutex_is_locked(&mymutex) == 0) +22 pr_info("The mutex failed to lock!\n"); 23 24 mutex_unlock(&mymutex); -25 pr_info("mutex is unlocked\n"); -26 } else -27 pr_info("Failed to lock\n"); +25 pr_info("mutex is unlocked\n"); +26 } else +27 pr_info("Failed to lock\n"); 28 -29 return 0; +29 return 0; 30} 31 -32static void example_mutex_exit(void) +32static void example_mutex_exit(void) 33{ -34 pr_info("example_mutex exit\n"); +34 pr_info("example_mutex exit\n"); 35} 36 37module_init(example_mutex_init); 38module_exit(example_mutex_exit); 39 -40MODULE_DESCRIPTION("Mutex example"); -41MODULE_LICENSE("GPL");-+40MODULE_DESCRIPTION("Mutex example"); +41MODULE_LICENSE("GPL");
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 @@ -3920,79 +3963,79 @@ 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 noticeably 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
flagsvariable to retain their state.-
1/* -2 * example_spinlock.c -3 */ -4#include <linux/init.h> -5#include <linux/interrupt.h> -6#include <linux/kernel.h> -7#include <linux/module.h> -8#include <linux/spinlock.h> ++1/* +2 * example_spinlock.c +3 */ +4#include <linux/init.h> +5#include <linux/interrupt.h> +6#include <linux/kernel.h> +7#include <linux/module.h> +8#include <linux/spinlock.h> 9 -10static DEFINE_SPINLOCK(sl_static); -11static spinlock_t sl_dynamic; +10static DEFINE_SPINLOCK(sl_static); +11static spinlock_t sl_dynamic; 12 -13static void example_spinlock_static(void) +13static void example_spinlock_static(void) 14{ -15 unsigned long flags; +15 unsigned long flags; 16 17 spin_lock_irqsave(&sl_static, flags); -18 pr_info("Locked static spinlock\n"); +18 pr_info("Locked static spinlock\n"); 19 -20 /* Do something or other safely. Because this uses 100% CPU time, this -21 * code should take no more than a few milliseconds to run. -22 */ +20 /* Do something or other safely. Because this uses 100% CPU time, this +21 * code should take no more than a few milliseconds to run. +22 */ 23 24 spin_unlock_irqrestore(&sl_static, flags); -25 pr_info("Unlocked static spinlock\n"); +25 pr_info("Unlocked static spinlock\n"); 26} 27 -28static void example_spinlock_dynamic(void) +28static void example_spinlock_dynamic(void) 29{ -30 unsigned long flags; +30 unsigned long flags; 31 32 spin_lock_init(&sl_dynamic); 33 spin_lock_irqsave(&sl_dynamic, flags); -34 pr_info("Locked dynamic spinlock\n"); +34 pr_info("Locked dynamic spinlock\n"); 35 -36 /* Do something or other safely. Because this uses 100% CPU time, this -37 * code should take no more than a few milliseconds to run. -38 */ +36 /* Do something or other safely. Because this uses 100% CPU time, this +37 * code should take no more than a few milliseconds to run. +38 */ 39 40 spin_unlock_irqrestore(&sl_dynamic, flags); -41 pr_info("Unlocked dynamic spinlock\n"); +41 pr_info("Unlocked dynamic spinlock\n"); 42} 43 -44static int example_spinlock_init(void) +44static int example_spinlock_init(void) 45{ -46 pr_info("example spinlock started\n"); +46 pr_info("example spinlock started\n"); 47 48 example_spinlock_static(); 49 example_spinlock_dynamic(); 50 -51 return 0; +51 return 0; 52} 53 -54static void example_spinlock_exit(void) +54static void example_spinlock_exit(void) 55{ -56 pr_info("example spinlock exit\n"); +56 pr_info("example spinlock exit\n"); 57} 58 59module_init(example_spinlock_init); 60module_exit(example_spinlock_exit); 61 -62MODULE_DESCRIPTION("Spinlock example"); -63MODULE_LICENSE("GPL");-+62MODULE_DESCRIPTION("Spinlock example"); +63MODULE_LICENSE("GPL");
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 @@ -4002,69 +4045,69 @@ the system and cause users to start revolting against the tyranny of your module.
-
1/* -2 * example_rwlock.c -3 */ -4#include <linux/interrupt.h> -5#include <linux/kernel.h> -6#include <linux/module.h> ++1/* +2 * example_rwlock.c +3 */ +4#include <linux/interrupt.h> +5#include <linux/kernel.h> +6#include <linux/module.h> 7 -8static DEFINE_RWLOCK(myrwlock); +8static DEFINE_RWLOCK(myrwlock); 9 -10static void example_read_lock(void) +10static void example_read_lock(void) 11{ -12 unsigned long flags; +12 unsigned long flags; 13 14 read_lock_irqsave(&myrwlock, flags); -15 pr_info("Read Locked\n"); +15 pr_info("Read Locked\n"); 16 -17 /* Read from something */ +17 /* Read from something */ 18 19 read_unlock_irqrestore(&myrwlock, flags); -20 pr_info("Read Unlocked\n"); +20 pr_info("Read Unlocked\n"); 21} 22 -23static void example_write_lock(void) +23static void example_write_lock(void) 24{ -25 unsigned long flags; +25 unsigned long flags; 26 27 write_lock_irqsave(&myrwlock, flags); -28 pr_info("Write Locked\n"); +28 pr_info("Write Locked\n"); 29 -30 /* Write to something */ +30 /* Write to something */ 31 32 write_unlock_irqrestore(&myrwlock, flags); -33 pr_info("Write Unlocked\n"); +33 pr_info("Write Unlocked\n"); 34} 35 -36static int example_rwlock_init(void) +36static int example_rwlock_init(void) 37{ -38 pr_info("example_rwlock started\n"); +38 pr_info("example_rwlock started\n"); 39 40 example_read_lock(); 41 example_write_lock(); 42 -43 return 0; +43 return 0; 44} 45 -46static void example_rwlock_exit(void) +46static void example_rwlock_exit(void) 47{ -48 pr_info("example_rwlock exit\n"); +48 pr_info("example_rwlock exit\n"); 49} 50 51module_init(example_rwlock_init); 52module_exit(example_rwlock_exit); 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 +54MODULE_DESCRIPTION("Read/Write locks example"); +55MODULE_LICENSE("GPL");
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)andread_unlock(&myrwlock)or the corresponding write functions.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 @@ -4072,84 +4115,84 @@ and was not overwritten by some other shenanigans. An example is shown below.
-
1/* -2 * example_atomic.c -3 */ -4#include <linux/interrupt.h> -5#include <linux/kernel.h> -6#include <linux/module.h> +-1/* +2 * example_atomic.c +3 */ +4#include <linux/interrupt.h> +5#include <linux/kernel.h> +6#include <linux/module.h> 7 -8#define BYTE_TO_BINARY_PATTERN "%c%c%c%c%c%c%c%c" -9#define BYTE_TO_BINARY(byte) \ -10 ((byte & 0x80) ? '1' : '0'), ((byte & 0x40) ? '1' : '0'), \ -11 ((byte & 0x20) ? '1' : '0'), ((byte & 0x10) ? '1' : '0'), \ -12 ((byte & 0x08) ? '1' : '0'), ((byte & 0x04) ? '1' : '0'), \ -13 ((byte & 0x02) ? '1' : '0'), ((byte & 0x01) ? '1' : '0') +8#define BYTE_TO_BINARY_PATTERN "%c%c%c%c%c%c%c%c" +9#define BYTE_TO_BINARY(byte) \ +10 ((byte & 0x80) ? '1' : '0'), ((byte & 0x40) ? '1' : '0'), \ +11 ((byte & 0x20) ? '1' : '0'), ((byte & 0x10) ? '1' : '0'), \ +12 ((byte & 0x08) ? '1' : '0'), ((byte & 0x04) ? '1' : '0'), \ +13 ((byte & 0x02) ? '1' : '0'), ((byte & 0x01) ? '1' : '0') 14 -15static void atomic_add_subtract(void) +15static void atomic_add_subtract(void) 16{ 17 atomic_t debbie; 18 atomic_t chris = ATOMIC_INIT(50); 19 20 atomic_set(&debbie, 45); 21 -22 /* subtract one */ +22 /* subtract one */ 23 atomic_dec(&debbie); 24 25 atomic_add(7, &debbie); 26 -27 /* add one */ +27 /* add one */ 28 atomic_inc(&debbie); 29 -30 pr_info("chris: %d, debbie: %d\n", atomic_read(&chris), +30 pr_info("chris: %d, debbie: %d\n", atomic_read(&chris), 31 atomic_read(&debbie)); 32} 33 -34static void atomic_bitwise(void) +34static void atomic_bitwise(void) 35{ -36 unsigned long word = 0; +36 unsigned long word = 0; 37 -38 pr_info("Bits 0: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word)); +38 pr_info("Bits 0: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word)); 39 set_bit(3, &word); 40 set_bit(5, &word); -41 pr_info("Bits 1: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word)); +41 pr_info("Bits 1: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word)); 42 clear_bit(5, &word); -43 pr_info("Bits 2: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word)); +43 pr_info("Bits 2: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word)); 44 change_bit(3, &word); 45 -46 pr_info("Bits 3: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word)); -47 if (test_and_set_bit(3, &word)) -48 pr_info("wrong\n"); -49 pr_info("Bits 4: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word)); +46 pr_info("Bits 3: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word)); +47 if (test_and_set_bit(3, &word)) +48 pr_info("wrong\n"); +49 pr_info("Bits 4: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word)); 50 51 word = 255; -52 pr_info("Bits 5: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word)); +52 pr_info("Bits 5: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word)); 53} 54 -55static int example_atomic_init(void) +55static int example_atomic_init(void) 56{ -57 pr_info("example_atomic started\n"); +57 pr_info("example_atomic started\n"); 58 59 atomic_add_subtract(); 60 atomic_bitwise(); 61 -62 return 0; +62 return 0; 63} 64 -65static void example_atomic_exit(void) +65static void example_atomic_exit(void) 66{ -67 pr_info("example_atomic exit\n"); +67 pr_info("example_atomic exit\n"); 68} 69 70module_init(example_atomic_init); 71module_exit(example_atomic_exit); 72 -73MODULE_DESCRIPTION("Atomic operations example"); -74MODULE_LICENSE("GPL");+73MODULE_DESCRIPTION("Atomic operations example"); +74MODULE_LICENSE("GPL");Before the C11 standard adopts the built-in atomic types, the kernel already +
Before the C11 standard adopts the built-in atomic types, the kernel already provided a small set of atomic types by using a bunch of tricky architecture-specific codes. Implementing the atomic types by C11 atomics may allow the kernel to throw away the architecture-specific codes and letting the kernel code be more friendly to @@ -4162,113 +4205,113 @@ For further details, see:
+
13 Replacing Print Macros
-+
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.
-
1/* -2 * print_string.c - Send output to the tty we're running on, regardless if -3 * it is through X11, telnet, etc. We do this by printing the string to the -4 * tty associated with the current task. -5 */ -6#include <linux/init.h> -7#include <linux/kernel.h> -8#include <linux/module.h> -9#include <linux/sched.h> /* For current */ -10#include <linux/tty.h> /* For the tty declarations */ +-1/* +2 * print_string.c - Send output to the tty we're running on, regardless if +3 * it is through X11, telnet, etc. We do this by printing the string to the +4 * tty associated with the current task. +5 */ +6#include <linux/init.h> +7#include <linux/kernel.h> +8#include <linux/module.h> +9#include <linux/sched.h> /* For current */ +10#include <linux/tty.h> /* For the tty declarations */ 11 -12static void print_string(char *str) +12static void print_string(char *str) 13{ -14 /* The tty for the current task */ -15 struct tty_struct *my_tty = get_current_tty(); +14 /* The tty for the current task */ +15 struct tty_struct *my_tty = get_current_tty(); 16 -17 /* If my_tty is NULL, the current task has no tty you can print to (i.e., -18 * if it is a daemon). If so, there is nothing we can do. -19 */ -20 if (my_tty) { -21 const struct tty_operations *ttyops = my_tty->driver->ops; -22 /* my_tty->driver is a struct which holds the tty's functions, -23 * one of which (write) is used to write strings to the tty. -24 * It can be used to take a string either from the user's or -25 * kernel's memory segment. -26 * -27 * The function's 1st parameter is the tty to write to, because the -28 * same function would normally be used for all tty's of a certain -29 * type. -30 * The 2nd parameter is a pointer to a string. -31 * The 3rd parameter is the length of the string. -32 * -33 * As you will see below, sometimes it's necessary to use -34 * preprocessor stuff to create code that works for different -35 * kernel versions. The (naive) approach we've taken here does not -36 * scale well. The right way to deal with this is described in -37 * section 2 of -38 * linux/Documentation/SubmittingPatches -39 */ -40 (ttyops->write)(my_tty, /* The tty itself */ -41 str, /* String */ -42 strlen(str)); /* Length */ +17 /* If my_tty is NULL, the current task has no tty you can print to (i.e., +18 * if it is a daemon). If so, there is nothing we can do. +19 */ +20 if (my_tty) { +21 const struct tty_operations *ttyops = my_tty->driver->ops; +22 /* my_tty->driver is a struct which holds the tty's functions, +23 * one of which (write) is used to write strings to the tty. +24 * It can be used to take a string either from the user's or +25 * kernel's memory segment. +26 * +27 * The function's 1st parameter is the tty to write to, because the +28 * same function would normally be used for all tty's of a certain +29 * type. +30 * The 2nd parameter is a pointer to a string. +31 * The 3rd parameter is the length of the string. +32 * +33 * As you will see below, sometimes it's necessary to use +34 * preprocessor stuff to create code that works for different +35 * kernel versions. The (naive) approach we've taken here does not +36 * scale well. The right way to deal with this is described in +37 * section 2 of +38 * linux/Documentation/SubmittingPatches +39 */ +40 (ttyops->write)(my_tty, /* The tty itself */ +41 str, /* String */ +42 strlen(str)); /* Length */ 43 -44 /* ttys were originally hardware devices, which (usually) strictly -45 * followed the ASCII standard. In ASCII, to move to a new line you -46 * need two characters, a carriage return and a line feed. On Unix, -47 * the ASCII line feed is used for both purposes - so we can not -48 * just use \n, because it would not have a carriage return and the -49 * next line will start at the column right after the line feed. -50 * -51 * This is why text files are different between Unix and MS Windows. -52 * In CP/M and derivatives, like MS-DOS and MS Windows, the ASCII -53 * standard was strictly adhered to, and therefore a newline requirs -54 * both a LF and a CR. -55 */ -56 (ttyops->write)(my_tty, "\015\012", 2); +44 /* ttys were originally hardware devices, which (usually) strictly +45 * followed the ASCII standard. In ASCII, to move to a new line you +46 * need two characters, a carriage return and a line feed. On Unix, +47 * the ASCII line feed is used for both purposes - so we can not +48 * just use \n, because it would not have a carriage return and the +49 * next line will start at the column right after the line feed. +50 * +51 * This is why text files are different between Unix and MS Windows. +52 * In CP/M and derivatives, like MS-DOS and MS Windows, the ASCII +53 * standard was strictly adhered to, and therefore a newline requirs +54 * both a LF and a CR. +55 */ +56 (ttyops->write)(my_tty, "\015\012", 2); 57 } 58} 59 -60static int __init print_string_init(void) +60static int __init print_string_init(void) 61{ -62 print_string("The module has been inserted. Hello world!"); -63 return 0; +62 print_string("The module has been inserted. Hello world!"); +63 return 0; 64} 65 -66static void __exit print_string_exit(void) +66static void __exit print_string_exit(void) 67{ -68 print_string("The module has been removed. Farewell world!"); +68 print_string("The module has been removed. Farewell world!"); 69} 70 71module_init(print_string_init); 72module_exit(print_string_exit); 73 -74MODULE_LICENSE("GPL");+74MODULE_LICENSE("GPL");
+
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. -
From v4.14 to v4.15, the timer API made a series of changes +
From v4.14 to v4.15, the timer API made a series of changes
to improve memory safety. A buffer overflow in the area of a
timer_list
structure may be able to overwrite the
@@ -4276,37 +4319,37 @@ to improve memory safety. A buffer overflow in the area of a
and data
fields, providing the attacker with a way to use return-object programming (ROP)
to call arbitrary functions within the kernel. Also, the function prototype of the callback,
-containing a unsigned long
+containing a unsigned long
argument, will prevent work from any type checking. Furthermore, the function prototype
-with unsigned long
+with unsigned long
argument may be an obstacle to the control-flow integrity. Thus, it is better
to use a unique prototype to separate from the cluster that takes an
- unsigned long
+ unsigned long
argument. The timer callback should be passed a pointer to the
timer_list
- structure rather than an unsigned long
+ structure rather than an unsigned long
argument. Then, it wraps all the information the callback needs, including the
timer_list
structure, into a larger structure, and it can use the
container_of
- macro instead of the unsigned long
+ macro instead of the unsigned long
value.
-
Before Linux v4.14, setup_timer
+
Before Linux v4.14, setup_timer
was used to initialize the timer and the
timer_list
structure looked like:
1struct timer_list { -2 unsigned long expires; -3 void (*function)(unsigned long); -4 unsigned long data; ++1struct timer_list { +2 unsigned long expires; +3 void (*function)(unsigned long); +4 unsigned long data; 5 u32 flags; -6 /* ... */ +6 /* ... */ 7}; 8 -9void setup_timer(struct timer_list *timer, void (*callback)(unsigned long), -10 unsigned long data);-Since Linux v4.14,
timer_setup +9void setup_timer(struct timer_list *timer, void (*callback)(unsigned long), +10 unsigned long data);
Since Linux v4.14, timer_setup
is adopted and the kernel step by step converting to
timer_setup
from setup_timer
@@ -4318,63 +4361,63 @@ Moreover, the timer_setup
was implemented by setup_timer
at first.
1void timer_setup(struct timer_list *timer, -2 void (*callback)(struct timer_list *), unsigned int flags);-
The The 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.
If none of the examples in this chapter fit your debugging needs,
+85MODULE_LICENSE("GPL"); If none of the examples in this chapter fit your debugging needs,
there might yet be some other tricks to try. Ever wondered what
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 disappear. Thus, you
should keep debug code to a minimum and make sure it does not show up in
production code.
-
+
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.
-
+
Here is an example tasklet module. The
+ Here is an example tasklet module. The
So with this example loaded So with this example loaded Although tasklet is easy to use, it comes with several defators, and developers are
+ Although tasklet is easy to use, it comes with several defators, and developers are
discussing about getting rid of tasklet in linux kernel. The tasklet callback
runs in atomic context, inside a software interrupt, meaning that it cannot
sleep or access user-space data, so not all work can be done in a tasklet
handler. Also, the kernel only allows one instance of any given tasklet to be
running at any given time; multiple different tasklet callbacks can run in
parallel.
- In recent kernels, tasklets can be replaced by workqueues, timers, or threaded
+ In recent kernels, tasklets can be replaced by workqueues, timers, or threaded
interrupts.1
While the removal of tasklets remains a longer-term goal, the current kernel contains more
than a hundred uses of tasklets. Now developers are proceeding with the API changes and
the macro
+
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.
+32MODULE_LICENSE("GPL");
+33MODULE_DESCRIPTION("Workqueue example");
+
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
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 order 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
convenient for the hardware, not the CPU. Hardware devices typically have a very
small amount of RAM, and if you do not read their information when available, it is
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 are not allowed in the
@@ -4606,10 +4649,10 @@ heavy work deferred from an interrupt handler. Historically, BH (Linux
naming for Bottom Halves) statistically book-keeps the deferred functions.
Softirq and its higher level abstraction, Tasklet, replace BH since Linux
2.3.
- The way to implement this is to call
+ The way to implement this is to call
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
@@ -4626,7 +4669,7 @@ need to solve another truckload of problems. It is not enough to know if a
certain IRQs has happened, it’s also important to know 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 be passed 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
@@ -4636,128 +4679,128 @@ How many IRQs there are is hardware-dependent. The flags can include
+
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.
+143MODULE_LICENSE("GPL");
+144MODULE_DESCRIPTION("Handle some GPIO interrupts");
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.
+166MODULE_LICENSE("GPL");
+167MODULE_DESCRIPTION("Interrupt with top and bottom half");
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
kernel has its own API enabling common methods of encryption, decryption and your
favourite 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.
Install the module:
+63MODULE_DESCRIPTION("sha256 hash test");
+64MODULE_LICENSE("GPL"); Install the module:
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:
+
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.
+197MODULE_DESCRIPTION("Symmetric key encryption example");
+198MODULE_LICENSE("GPL");
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 shown below, and you can
@@ -5284,59 +5327,59 @@ use this as a template to add your own suspend, resume or other interface
functions.
+98MODULE_LICENSE("GPL");
+99MODULE_DESCRIPTION("Linux Device Model example");
+
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 noticeable latency. If your code contains boolean conditions and if
you know that the conditions are almost always likely to evaluate as either
@@ -5402,52 +5445,52 @@ you know that the conditions are almost always likely to evaluate as either
to succeed.
When the When the
+
+
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.
-
+
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.
-
+
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 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. Your pull requests
will be appreciated.
- Happy hacking!
+ Happy hacking!
1The goal of threaded interrupts is to push more of the work to separate threads, so that the
+ 1The goal of threaded interrupts is to push more of the work to separate threads, so that the
minimum needed for acknowledging an interrupt is reduced, and therefore the time spent handling
the interrupt (where it can’t handle any other interrupts at the same time) is reduced. See
https://lwn.net/Articles/302043/.
+ However, The newer interface completes the char device registration in two distinct steps.
+First, we should register a range of device numbers, which can be completed with
+
+ The choose of two different functions depend on whether you know the major numbers for your
+device. Using Second, we should initialize the data structure
+
+ However, the common usage pattern will embed the
+
+ Once we finish the initialization, we can add the char device to the system by using
+the
+ To find a example using the interface, you can see ioctl.c described in section
+9.
+
We can not allow the kernel module to be
+ We can not allow the kernel module to be
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
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.
-
+
The next code sample creates a char driver named chardev. You can dump its device
+ The next code sample creates a char driver named chardev. You can dump its device
file.
(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
- In the multiple-threaded environment, without any protection, concurrent access
+ In the multiple-threaded environment, without any protection, concurrent access
to the same memory may lead to the race condition, and will not preserve the
performance. In the kernel module, this problem may happen due to multiple
instances accessing the shared resources. Therefore, a solution is to enforce the
exclusive access. We use atomic Compare-And-Swap (CAS) to maintain the states,
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
+
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 gathers 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,
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 index-node (inode for short) number
is a pointer to a disk location where the file’s inode 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 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 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
Every time the file /proc/helloworld is read, the function
+ Every time the file /proc/helloworld is read, the function
+
The The
+
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
@@ -1786,7 +1829,7 @@ user, so you have to import data from user space to kernel space (with
The reason for The reason for 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.
@@ -1815,130 +1858,130 @@ need to import data because it comes from user space, but not for the read funct
because data is already in kernel space.
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,
- 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
+ Another interesting point here is the
+ Another interesting point here is the
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
@@ -1955,121 +1998,121 @@ if a process writes something to the kernel, then the kernel receives it as
input.
Still hungry for procfs examples? Well, first of all keep in mind, there are rumors
+107MODULE_LICENSE("GPL"); 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.
-
+
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
A sequence begins with the call of the function
+ A sequence begins with the call of the function
BE CAREFUL: when a sequence is finished, another one starts. That means that at the end
+ BE CAREFUL: when a sequence is finished, another one starts. That means that at the end
of function The The If you want more information, you can read this web page:
+118MODULE_LICENSE("GPL"); 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.
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.
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.
Make and install the module:
Check that it exists:
+ Check that it exists:
What is the current value of What is the current value of
Set the value of Set the value of
Finally, remove the test module:
+ Finally, remove the test module:
+
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
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
@@ -2375,7 +2418,7 @@ received.
- The answer in Unix is to use a special function called
+ The answer in Unix is to use a special function called
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 ( 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/userspace-api/ioctl/ioctl-number.rst.
- Also, we need to be careful that concurrent access to the shared resources will
+ Also, we need to be careful that concurrent access to the shared resources will
lead to the race condition. The solution is using atomic Compare-And-Swap (CAS),
which we mentioned at 6.5 section, to enforce the exclusive access.
+
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
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
@@ -2911,11 +2954,11 @@ 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
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,
@@ -2923,7 +2966,7 @@ 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
( 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
To modify the content of To modify the content of However, However, Because of the control-flow integrity, which is a technique to prevent the redirect
+ Because of the control-flow integrity, which is a technique to prevent the redirect
execution code from the attacker, for making sure that the indirect calls go to the
expected addresses and the return addresses are not changed. Since Linux v5.7, the
kernel patched the series of control-flow enforcement (CET) for x86, and some
@@ -2986,10 +3029,10 @@ COLLECT_GCC_OPTIONS='-v' '-Q' '-O2' '--help=target' '-mtune=generic' '-marc
GNU C17 (Ubuntu 9.3.0-17ubuntu1~20.04) version 9.3.0 (x86_64-linux-gnu)
...
But CET should not be enabled in the kernel, it may break the Kprobes and bpf.
+ But CET should not be enabled in the kernel, it may break the Kprobes and bpf.
Consequently, CET is disabled since v5.11. To guarantee the manual symbol lookup
worked, we only use up to v5.4.
- Unfortunately, since Linux v5.7 Unfortunately, since Linux v5.7 Otherwise, specify the address of Otherwise, specify the address of
- Using the address from /boot/System.map, be careful about KASLR (Kernel
+
+ Using the address from /boot/System.map, be careful about KASLR (Kernel
Address Space Layout Randomization). KASLR may randomize the address of
kernel code and data at every boot time, such as the static address listed in
/boot/System.map will offset by some entropy. The purpose of KASLR is to protect
@@ -3046,7 +3089,7 @@ ffffffff82000300 R sys_call_table
$ sudo grep sys_call_table /proc/kallsyms
ffffffff86400300 R sys_call_table
- If KASLR is enabled, we have to take care of the address from /proc/kallsyms each
+ If KASLR is enabled, we have to take care of the address from /proc/kallsyms each
time we reboot the machine. In order to use the address from /boot/System.map,
make sure that KASLR is disabled. You can add the nokaslr for disabling KASLR in
next booting time:
@@ -3062,8 +3105,8 @@ $ grep quiet /etc/default/grub
GRUB_CMDLINE_LINUX_DEFAULT="quiet nokaslr splash"
$ sudo update-grub
-
- For more information, check out the following:
+
+ For more information, check out the following:
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 The The 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 Note that all the related problems make syscall stealing unfeasible for
+ Note that all the related problems make syscall stealing unfeasible for
production use. In order to keep people from doing potential harmful things
+
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
@@ -3383,21 +3426,21 @@ possibility. You can put the process to sleep until you can service it. After al
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
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
When a process is done with the file, it closes it, and
+ When a process is done with the file, it closes it, and
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 So we will use To make our life more interesting, To make our life more interesting, In that case, we want to return with
+ In that case, we want to return with
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
+
+
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 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.
The The So even though So even though There are other variations upon the
+ There are other variations upon the
+
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.
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.
+40MODULE_DESCRIPTION("Mutex example");
+41MODULE_LICENSE("GPL");
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
@@ -3920,79 +3963,79 @@ 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 noticeably 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
+62MODULE_DESCRIPTION("Spinlock example");
+63MODULE_LICENSE("GPL");
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
@@ -4002,69 +4045,69 @@ the system and cause users to start revolting against the tyranny of your
module.
Of course, if you know for sure that there are no functions triggered by irqs
+54MODULE_DESCRIPTION("Read/Write locks example");
+55MODULE_LICENSE("GPL"); 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
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
@@ -4072,84 +4115,84 @@ and was not overwritten by some other shenanigans. An example is shown
below.
Before the C11 standard adopts the built-in atomic types, the kernel already
+ Before the C11 standard adopts the built-in atomic types, the kernel already
provided a small set of atomic types by using a bunch of tricky architecture-specific
codes. Implementing the atomic types by C11 atomics may allow the kernel to throw
away the architecture-specific codes and letting the kernel code be more friendly to
@@ -4162,113 +4205,113 @@ For further details, see:
+
+
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.
+
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.
- From v4.14 to v4.15, the timer API made a series of changes
+ From v4.14 to v4.15, the timer API made a series of changes
to improve memory safety. A buffer overflow in the area of a
Before Linux v4.14, Before Linux v4.14, Since Linux v4.14, Since Linux v4.14, The The 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.
If none of the examples in this chapter fit your debugging needs,
+85MODULE_LICENSE("GPL"); If none of the examples in this chapter fit your debugging needs,
there might yet be some other tricks to try. Ever wondered what
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 disappear. Thus, you
should keep debug code to a minimum and make sure it does not show up in
production code.
-
+
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.
-
+
Here is an example tasklet module. The
+ Here is an example tasklet module. The
So with this example loaded So with this example loaded Although tasklet is easy to use, it comes with several defators, and developers are
+ Although tasklet is easy to use, it comes with several defators, and developers are
discussing about getting rid of tasklet in linux kernel. The tasklet callback
runs in atomic context, inside a software interrupt, meaning that it cannot
sleep or access user-space data, so not all work can be done in a tasklet
handler. Also, the kernel only allows one instance of any given tasklet to be
running at any given time; multiple different tasklet callbacks can run in
parallel.
- In recent kernels, tasklets can be replaced by workqueues, timers, or threaded
+ In recent kernels, tasklets can be replaced by workqueues, timers, or threaded
interrupts.1
While the removal of tasklets remains a longer-term goal, the current kernel contains more
than a hundred uses of tasklets. Now developers are proceeding with the API changes and
the macro
+
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.
+32MODULE_LICENSE("GPL");
+33MODULE_DESCRIPTION("Workqueue example");
+
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
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 order 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
convenient for the hardware, not the CPU. Hardware devices typically have a very
small amount of RAM, and if you do not read their information when available, it is
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 are not allowed in the
@@ -4606,10 +4649,10 @@ heavy work deferred from an interrupt handler. Historically, BH (Linux
naming for Bottom Halves) statistically book-keeps the deferred functions.
Softirq and its higher level abstraction, Tasklet, replace BH since Linux
2.3.
- The way to implement this is to call
+ The way to implement this is to call
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
@@ -4626,7 +4669,7 @@ need to solve another truckload of problems. It is not enough to know if a
certain IRQs has happened, it’s also important to know 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 be passed 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
@@ -4636,128 +4679,128 @@ How many IRQs there are is hardware-dependent. The flags can include
+
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.
+143MODULE_LICENSE("GPL");
+144MODULE_DESCRIPTION("Handle some GPIO interrupts");
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.
+166MODULE_LICENSE("GPL");
+167MODULE_DESCRIPTION("Interrupt with top and bottom half");
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
kernel has its own API enabling common methods of encryption, decryption and your
favourite 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.
Install the module:
+63MODULE_DESCRIPTION("sha256 hash test");
+64MODULE_LICENSE("GPL"); Install the module:
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:
+
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.
+197MODULE_DESCRIPTION("Symmetric key encryption example");
+198MODULE_LICENSE("GPL");
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 shown below, and you can
@@ -5284,59 +5327,59 @@ use this as a template to add your own suspend, resume or other interface
functions.
+98MODULE_LICENSE("GPL");
+99MODULE_DESCRIPTION("Linux Device Model example");
+
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 noticeable latency. If your code contains boolean conditions and if
you know that the conditions are almost always likely to evaluate as either
@@ -5402,52 +5445,52 @@ you know that the conditions are almost always likely to evaluate as either
to succeed.
When the When the
+
+
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.
-
+
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.
-
+
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 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. Your pull requests
will be appreciated.
- Happy hacking!
+ Happy hacking!
1The goal of threaded interrupts is to push more of the work to separate threads, so that the
+ 1The goal of threaded interrupts is to push more of the work to separate threads, so that the
minimum needed for acknowledging an interrupt is reduced, and therefore the time spent handling
the interrupt (where it can’t handle any other interrupts at the same time) is reduced. See
https://lwn.net/Articles/302043/. setup_timer
+ 1void timer_setup(struct timer_list *timer,
+2 void (*callback)(struct timer_list *), unsigned int flags);
+ setup_timer
was then removed since v4.15. As a result, the
timer_list
structure had changed to the following.
1struct timer_list {
-2 unsigned long expires;
-3 void (*function)(struct timer_list *);
+
-1struct timer_list {
+2 unsigned long expires;
+3 void (*function)(struct timer_list *);
4 u32 flags;
-5 /* ... */
+5 /* ... */
6};
-1/*
-2 * kbleds.c - Blink keyboard leds until the module is unloaded.
-3 */
+
+1/*
+2 * kbleds.c - Blink keyboard leds until the module is unloaded.
+3 */
4
-5#include <linux/init.h>
-6#include <linux/kd.h> /* For KDSETLED */
-7#include <linux/module.h>
-8#include <linux/tty.h> /* For tty_struct */
-9#include <linux/vt.h> /* For MAX_NR_CONSOLES */
-10#include <linux/vt_kern.h> /* for fg_console */
-11#include <linux/console_struct.h> /* For vc_cons */
+5#include <linux/init.h>
+6#include <linux/kd.h> /* For KDSETLED */
+7#include <linux/module.h>
+8#include <linux/tty.h> /* For tty_struct */
+9#include <linux/vt.h> /* For MAX_NR_CONSOLES */
+10#include <linux/vt_kern.h> /* for fg_console */
+11#include <linux/console_struct.h> /* For vc_cons */
12
-13MODULE_DESCRIPTION("Example module illustrating the use of Keyboard LEDs.");
+13MODULE_DESCRIPTION("Example module illustrating the use of Keyboard LEDs.");
14
-15static struct timer_list my_timer;
-16static struct tty_driver *my_driver;
-17static unsigned long kbledstatus = 0;
+15static struct timer_list my_timer;
+16static struct tty_driver *my_driver;
+17static unsigned long kbledstatus = 0;
18
-19#define BLINK_DELAY HZ / 5
-20#define ALL_LEDS_ON 0x07
-21#define RESTORE_LEDS 0xFF
+19#define BLINK_DELAY HZ / 5
+20#define ALL_LEDS_ON 0x07
+21#define RESTORE_LEDS 0xFF
22
-23/* Function my_timer_func blinks the keyboard LEDs periodically by invoking
-24 * command KDSETLED of ioctl() on the keyboard driver. To learn more on virtual
-25 * terminal ioctl operations, please see file:
-26 * drivers/tty/vt/vt_ioctl.c, function vt_ioctl().
-27 *
-28 * The argument to KDSETLED is alternatively set to 7 (thus causing the led
-29 * mode to be set to LED_SHOW_IOCTL, and all the leds are lit) and to 0xFF
-30 * (any value above 7 switches back the led mode to LED_SHOW_FLAGS, thus
-31 * the LEDs reflect the actual keyboard status). To learn more on this,
-32 * please see file: drivers/tty/vt/keyboard.c, function setledstate().
-33 */
-34static void my_timer_func(struct timer_list *unused)
+23/* Function my_timer_func blinks the keyboard LEDs periodically by invoking
+24 * command KDSETLED of ioctl() on the keyboard driver. To learn more on virtual
+25 * terminal ioctl operations, please see file:
+26 * drivers/tty/vt/vt_ioctl.c, function vt_ioctl().
+27 *
+28 * The argument to KDSETLED is alternatively set to 7 (thus causing the led
+29 * mode to be set to LED_SHOW_IOCTL, and all the leds are lit) and to 0xFF
+30 * (any value above 7 switches back the led mode to LED_SHOW_FLAGS, thus
+31 * the LEDs reflect the actual keyboard status). To learn more on this,
+32 * please see file: drivers/tty/vt/keyboard.c, function setledstate().
+33 */
+34static void my_timer_func(struct timer_list *unused)
35{
-36 struct tty_struct *t = vc_cons[fg_console].d->port.tty;
+36 struct tty_struct *t = vc_cons[fg_console].d->port.tty;
37
-38 if (kbledstatus == ALL_LEDS_ON)
+38 if (kbledstatus == ALL_LEDS_ON)
39 kbledstatus = RESTORE_LEDS;
-40 else
+40 else
41 kbledstatus = ALL_LEDS_ON;
42
43 (my_driver->ops->ioctl)(t, KDSETLED, kbledstatus);
@@ -4383,34 +4426,34 @@ loaded, starts blinking the keyboard LEDs until it is unloaded.
46 add_timer(&my_timer);
47}
48
-49static int __init kbleds_init(void)
+49static int __init kbleds_init(void)
50{
-51 int i;
+51 int i;
52
-53 pr_info("kbleds: loading\n");
-54 pr_info("kbleds: fgconsole is %x\n", fg_console);
-55 for (i = 0; i < MAX_NR_CONSOLES; i++) {
-56 if (!vc_cons[i].d)
-57 break;
-58 pr_info("poet_atkm: console[%i/%i] #%i, tty %p\n", i, MAX_NR_CONSOLES,
-59 vc_cons[i].d->vc_num, (void *)vc_cons[i].d->port.tty);
+53 pr_info("kbleds: loading\n");
+54 pr_info("kbleds: fgconsole is %x\n", fg_console);
+55 for (i = 0; i < MAX_NR_CONSOLES; i++) {
+56 if (!vc_cons[i].d)
+57 break;
+58 pr_info("poet_atkm: console[%i/%i] #%i, tty %p\n", i, MAX_NR_CONSOLES,
+59 vc_cons[i].d->vc_num, (void *)vc_cons[i].d->port.tty);
60 }
-61 pr_info("kbleds: finished scanning consoles\n");
+61 pr_info("kbleds: finished scanning consoles\n");
62
63 my_driver = vc_cons[fg_console].d->port.tty->driver;
-64 pr_info("kbleds: tty driver magic %x\n", my_driver->magic);
+64 pr_info("kbleds: tty driver magic %x\n", my_driver->magic);
65
-66 /* Set up the LED blink timer the first time. */
+66 /* Set up the LED blink timer the first time. */
67 timer_setup(&my_timer, my_timer_func, 0);
68 my_timer.expires = jiffies + BLINK_DELAY;
69 add_timer(&my_timer);
70
-71 return 0;
+71 return 0;
72}
73
-74static void __exit kbleds_cleanup(void)
+74static void __exit kbleds_cleanup(void)
75{
-76 pr_info("kbleds: unloading...\n");
+76 pr_info("kbleds: unloading...\n");
77 del_timer(&my_timer);
78 (my_driver->ops->ioctl)(vc_cons[fg_console].d->port.tty, KDSETLED,
79 RESTORE_LEDS);
@@ -4419,8 +4462,8 @@ loaded, starts blinking the keyboard LEDs until it is unloaded.
82module_init(kbleds_init);
83module_exit(kbleds_cleanup);
84
-85MODULE_LICENSE("GPL");
- CONFIG_LL_DEBUG
in make menuconfig
@@ -4431,76 +4474,76 @@ everything what your code does over a serial line. If you find yourself porting
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.
-14 Scheduling Tasks
-14.1 Tasklets
- tasklet_fn
function runs for a few seconds and in the mean time execution of the
example_tasklet_init
function continues to the exit point.
1/*
-2 * example_tasklet.c
-3 */
-4#include <linux/delay.h>
-5#include <linux/interrupt.h>
-6#include <linux/kernel.h>
-7#include <linux/module.h>
+
+1/*
+2 * example_tasklet.c
+3 */
+4#include <linux/delay.h>
+5#include <linux/interrupt.h>
+6#include <linux/kernel.h>
+7#include <linux/module.h>
8
-9/* Macro DECLARE_TASKLET_OLD exists for compatibiity.
-10 * See https://lwn.net/Articles/830964/
-11 */
-12#ifndef DECLARE_TASKLET_OLD
-13#define DECLARE_TASKLET_OLD(arg1, arg2) DECLARE_TASKLET(arg1, arg2, 0L)
-14#endif
+9/* Macro DECLARE_TASKLET_OLD exists for compatibiity.
+10 * See https://lwn.net/Articles/830964/
+11 */
+12#ifndef DECLARE_TASKLET_OLD
+13#define DECLARE_TASKLET_OLD(arg1, arg2) DECLARE_TASKLET(arg1, arg2, 0L)
+14#endif
15
-16static void tasklet_fn(unsigned long data)
+16static void tasklet_fn(unsigned long data)
17{
-18 pr_info("Example tasklet starts\n");
+18 pr_info("Example tasklet starts\n");
19 mdelay(5000);
-20 pr_info("Example tasklet ends\n");
+20 pr_info("Example tasklet ends\n");
21}
22
-23static DECLARE_TASKLET_OLD(mytask, tasklet_fn);
+23static DECLARE_TASKLET_OLD(mytask, tasklet_fn);
24
-25static int example_tasklet_init(void)
+25static int example_tasklet_init(void)
26{
-27 pr_info("tasklet example init\n");
+27 pr_info("tasklet example init\n");
28 tasklet_schedule(&mytask);
29 mdelay(200);
-30 pr_info("Example tasklet init continues...\n");
-31 return 0;
+30 pr_info("Example tasklet init continues...\n");
+31 return 0;
32}
33
-34static void example_tasklet_exit(void)
+34static void example_tasklet_exit(void)
35{
-36 pr_info("tasklet example exit\n");
+36 pr_info("tasklet example exit\n");
37 tasklet_kill(&mytask);
38}
39
40module_init(example_tasklet_init);
41module_exit(example_tasklet_exit);
42
-43MODULE_DESCRIPTION("Tasklet example");
-44MODULE_LICENSE("GPL");
- dmesg
+43MODULE_DESCRIPTION("Tasklet example");
+44MODULE_LICENSE("GPL"); dmesg
should show:
@@ -4512,50 +4555,50 @@ Example tasklet starts
Example tasklet init continues...
Example tasklet ends
DECLARE_TASKLET_OLD
exists for compatibility. For further information, see https://lwn.net/Articles/830964/.
-14.2 Work queues
-1/*
-2 * sched.c
-3 */
-4#include <linux/init.h>
-5#include <linux/module.h>
-6#include <linux/workqueue.h>
+
+1/*
+2 * sched.c
+3 */
+4#include <linux/init.h>
+5#include <linux/module.h>
+6#include <linux/workqueue.h>
7
-8static struct workqueue_struct *queue = NULL;
-9static struct work_struct work;
+8static struct workqueue_struct *queue = NULL;
+9static struct work_struct work;
10
-11static void work_handler(struct work_struct *data)
+11static void work_handler(struct work_struct *data)
12{
-13 pr_info("work handler function.\n");
+13 pr_info("work handler function.\n");
14}
15
-16static int __init sched_init(void)
+16static int __init sched_init(void)
17{
-18 queue = alloc_workqueue("HELLOWORLD", WQ_UNBOUND, 1);
+18 queue = alloc_workqueue("HELLOWORLD", WQ_UNBOUND, 1);
19 INIT_WORK(&work, work_handler);
20 schedule_work(&work);
-21 return 0;
+21 return 0;
22}
23
-24static void __exit sched_exit(void)
+24static void __exit sched_exit(void)
25{
26 destroy_workqueue(queue);
27}
@@ -4563,38 +4606,38 @@ Completely Fair Scheduler (CFS) to execute work within the queue.
29module_init(sched_init);
30module_exit(sched_exit);
31
-32MODULE_LICENSE("GPL");
-33MODULE_DESCRIPTION("Workqueue example");
-15 Interrupt Handlers
-15.1 Interrupt Handlers
- 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.
- request_irq()
to get your interrupt handler called when the relevant IRQ is received.
- SA_INTERRUPT
to indicate this is a fast interrupt. This function will only succeed if there is not
already a handler on this IRQ, or if you are both willing to share.
-15.2 Detecting button presses
-1/*
-2 * intrpt.c - Handling GPIO with interrupts
-3 *
-4 * Based upon the RPi example by Stefan Wendler (devnull@kaltpost.de)
-5 * from:
-6 * https://github.com/wendlers/rpi-kmod-samples
-7 *
-8 * Press one button to turn on a LED and another to turn it off.
-9 */
+
+1/*
+2 * intrpt.c - Handling GPIO with interrupts
+3 *
+4 * Based upon the RPi example by Stefan Wendler (devnull@kaltpost.de)
+5 * from:
+6 * https://github.com/wendlers/rpi-kmod-samples
+7 *
+8 * Press one button to turn on a LED and another to turn it off.
+9 */
10
-11#include <linux/gpio.h>
-12#include <linux/interrupt.h>
-13#include <linux/kernel.h>
-14#include <linux/module.h>
+11#include <linux/gpio.h>
+12#include <linux/interrupt.h>
+13#include <linux/kernel.h>
+14#include <linux/module.h>
15
-16static int button_irqs[] = { -1, -1 };
+16static int button_irqs[] = { -1, -1 };
17
-18/* Define GPIOs for LEDs.
-19 * TODO: Change the numbers for the GPIO on your board.
-20 */
-21static struct gpio leds[] = { { 4, GPIOF_OUT_INIT_LOW, "LED 1" } };
+18/* Define GPIOs for LEDs.
+19 * TODO: Change the numbers for the GPIO on your board.
+20 */
+21static struct gpio leds[] = { { 4, GPIOF_OUT_INIT_LOW, "LED 1" } };
22
-23/* Define GPIOs for BUTTONS
-24 * TODO: Change the numbers for the GPIO on your board.
-25 */
-26static struct gpio buttons[] = { { 17, GPIOF_IN, "LED 1 ON BUTTON" },
-27 { 18, GPIOF_IN, "LED 1 OFF BUTTON" } };
+23/* Define GPIOs for BUTTONS
+24 * TODO: Change the numbers for the GPIO on your board.
+25 */
+26static struct gpio buttons[] = { { 17, GPIOF_IN, "LED 1 ON BUTTON" },
+27 { 18, GPIOF_IN, "LED 1 OFF BUTTON" } };
28
-29/* interrupt function triggered when a button is pressed. */
-30static irqreturn_t button_isr(int irq, void *data)
+29/* interrupt function triggered when a button is pressed. */
+30static irqreturn_t button_isr(int irq, void *data)
31{
-32 /* first button */
-33 if (irq == button_irqs[0] && !gpio_get_value(leds[0].gpio))
+32 /* first button */
+33 if (irq == button_irqs[0] && !gpio_get_value(leds[0].gpio))
34 gpio_set_value(leds[0].gpio, 1);
-35 /* second button */
-36 else if (irq == button_irqs[1] && gpio_get_value(leds[0].gpio))
+35 /* second button */
+36 else if (irq == button_irqs[1] && gpio_get_value(leds[0].gpio))
37 gpio_set_value(leds[0].gpio, 0);
38
-39 return IRQ_HANDLED;
+39 return IRQ_HANDLED;
40}
41
-42static int __init intrpt_init(void)
+42static int __init intrpt_init(void)
43{
-44 int ret = 0;
+44 int ret = 0;
45
-46 pr_info("%s\n", __func__);
+46 pr_info("%s\n", __func__);
47
-48 /* register LED gpios */
+48 /* register LED gpios */
49 ret = gpio_request_array(leds, ARRAY_SIZE(leds));
50
-51 if (ret) {
-52 pr_err("Unable to request GPIOs for LEDs: %d\n", ret);
-53 return ret;
+51 if (ret) {
+52 pr_err("Unable to request GPIOs for LEDs: %d\n", ret);
+53 return ret;
54 }
55
-56 /* register BUTTON gpios */
+56 /* register BUTTON gpios */
57 ret = gpio_request_array(buttons, ARRAY_SIZE(buttons));
58
-59 if (ret) {
-60 pr_err("Unable to request GPIOs for BUTTONs: %d\n", ret);
-61 goto fail1;
+59 if (ret) {
+60 pr_err("Unable to request GPIOs for BUTTONs: %d\n", ret);
+61 goto fail1;
62 }
63
-64 pr_info("Current button1 value: %d\n", gpio_get_value(buttons[0].gpio));
+64 pr_info("Current button1 value: %d\n", gpio_get_value(buttons[0].gpio));
65
66 ret = gpio_to_irq(buttons[0].gpio);
67
-68 if (ret < 0) {
-69 pr_err("Unable to request IRQ: %d\n", ret);
-70 goto fail2;
+68 if (ret < 0) {
+69 pr_err("Unable to request IRQ: %d\n", ret);
+70 goto fail2;
71 }
72
73 button_irqs[0] = ret;
74
-75 pr_info("Successfully requested BUTTON1 IRQ # %d\n", button_irqs[0]);
+75 pr_info("Successfully requested BUTTON1 IRQ # %d\n", button_irqs[0]);
76
77 ret = request_irq(button_irqs[0], button_isr,
78 IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
-79 "gpiomod#button1", NULL);
+79 "gpiomod#button1", NULL);
80
-81 if (ret) {
-82 pr_err("Unable to request IRQ: %d\n", ret);
-83 goto fail2;
+81 if (ret) {
+82 pr_err("Unable to request IRQ: %d\n", ret);
+83 goto fail2;
84 }
85
86 ret = gpio_to_irq(buttons[1].gpio);
87
-88 if (ret < 0) {
-89 pr_err("Unable to request IRQ: %d\n", ret);
-90 goto fail2;
+88 if (ret < 0) {
+89 pr_err("Unable to request IRQ: %d\n", ret);
+90 goto fail2;
91 }
92
93 button_irqs[1] = ret;
94
-95 pr_info("Successfully requested BUTTON2 IRQ # %d\n", button_irqs[1]);
+95 pr_info("Successfully requested BUTTON2 IRQ # %d\n", button_irqs[1]);
96
97 ret = request_irq(button_irqs[1], button_isr,
98 IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
-99 "gpiomod#button2", NULL);
+99 "gpiomod#button2", NULL);
100
-101 if (ret) {
-102 pr_err("Unable to request IRQ: %d\n", ret);
-103 goto fail3;
+101 if (ret) {
+102 pr_err("Unable to request IRQ: %d\n", ret);
+103 goto fail3;
104 }
105
-106 return 0;
+106 return 0;
107
-108/* cleanup what has been setup so far */
+108/* cleanup what has been setup so far */
109fail3:
110 free_irq(button_irqs[0], NULL);
111
@@ -4767,24 +4810,24 @@ appropriate for your board.
115fail1:
116 gpio_free_array(leds, ARRAY_SIZE(leds));
117
-118 return ret;
+118 return ret;
119}
120
-121static void __exit intrpt_exit(void)
+121static void __exit intrpt_exit(void)
122{
-123 int i;
+123 int i;
124
-125 pr_info("%s\n", __func__);
+125 pr_info("%s\n", __func__);
126
-127 /* free irqs */
+127 /* free irqs */
128 free_irq(button_irqs[0], NULL);
129 free_irq(button_irqs[1], NULL);
130
-131 /* turn all LEDs off */
-132 for (i = 0; i < ARRAY_SIZE(leds); i++)
+131 /* turn all LEDs off */
+132 for (i = 0; i < ARRAY_SIZE(leds); i++)
133 gpio_set_value(leds[i].gpio, 0);
134
-135 /* unregister */
+135 /* unregister */
136 gpio_free_array(leds, ARRAY_SIZE(leds));
137 gpio_free_array(buttons, ARRAY_SIZE(buttons));
138}
@@ -4792,153 +4835,153 @@ appropriate for your board.
140module_init(intrpt_init);
141module_exit(intrpt_exit);
142
-143MODULE_LICENSE("GPL");
-144MODULE_DESCRIPTION("Handle some GPIO interrupts");
-15.3 Bottom Half
-1/*
-2 * bottomhalf.c - Top and bottom half interrupt handling
-3 *
-4 * Based upon the RPi example by Stefan Wendler (devnull@kaltpost.de)
-5 * from:
-6 * https://github.com/wendlers/rpi-kmod-samples
-7 *
-8 * Press one button to turn on a LED and another to turn it off
-9 */
+
+1/*
+2 * bottomhalf.c - Top and bottom half interrupt handling
+3 *
+4 * Based upon the RPi example by Stefan Wendler (devnull@kaltpost.de)
+5 * from:
+6 * https://github.com/wendlers/rpi-kmod-samples
+7 *
+8 * Press one button to turn on a LED and another to turn it off
+9 */
10
-11#include <linux/delay.h>
-12#include <linux/gpio.h>
-13#include <linux/interrupt.h>
-14#include <linux/kernel.h>
-15#include <linux/module.h>
+11#include <linux/delay.h>
+12#include <linux/gpio.h>
+13#include <linux/interrupt.h>
+14#include <linux/kernel.h>
+15#include <linux/module.h>
16
-17/* Macro DECLARE_TASKLET_OLD exists for compatibiity.
-18 * See https://lwn.net/Articles/830964/
-19 */
-20#ifndef DECLARE_TASKLET_OLD
-21#define DECLARE_TASKLET_OLD(arg1, arg2) DECLARE_TASKLET(arg1, arg2, 0L)
-22#endif
+17/* Macro DECLARE_TASKLET_OLD exists for compatibiity.
+18 * See https://lwn.net/Articles/830964/
+19 */
+20#ifndef DECLARE_TASKLET_OLD
+21#define DECLARE_TASKLET_OLD(arg1, arg2) DECLARE_TASKLET(arg1, arg2, 0L)
+22#endif
23
-24static int button_irqs[] = { -1, -1 };
+24static int button_irqs[] = { -1, -1 };
25
-26/* Define GPIOs for LEDs.
-27 * TODO: Change the numbers for the GPIO on your board.
-28 */
-29static struct gpio leds[] = { { 4, GPIOF_OUT_INIT_LOW, "LED 1" } };
+26/* Define GPIOs for LEDs.
+27 * TODO: Change the numbers for the GPIO on your board.
+28 */
+29static struct gpio leds[] = { { 4, GPIOF_OUT_INIT_LOW, "LED 1" } };
30
-31/* Define GPIOs for BUTTONS
-32 * TODO: Change the numbers for the GPIO on your board.
-33 */
-34static struct gpio buttons[] = {
-35 { 17, GPIOF_IN, "LED 1 ON BUTTON" },
-36 { 18, GPIOF_IN, "LED 1 OFF BUTTON" },
+31/* Define GPIOs for BUTTONS
+32 * TODO: Change the numbers for the GPIO on your board.
+33 */
+34static struct gpio buttons[] = {
+35 { 17, GPIOF_IN, "LED 1 ON BUTTON" },
+36 { 18, GPIOF_IN, "LED 1 OFF BUTTON" },
37};
38
-39/* Tasklet containing some non-trivial amount of processing */
-40static void bottomhalf_tasklet_fn(unsigned long data)
+39/* Tasklet containing some non-trivial amount of processing */
+40static void bottomhalf_tasklet_fn(unsigned long data)
41{
-42 pr_info("Bottom half tasklet starts\n");
-43 /* do something which takes a while */
+42 pr_info("Bottom half tasklet starts\n");
+43 /* do something which takes a while */
44 mdelay(500);
-45 pr_info("Bottom half tasklet ends\n");
+45 pr_info("Bottom half tasklet ends\n");
46}
47
-48static DECLARE_TASKLET_OLD(buttontask, bottomhalf_tasklet_fn);
+48static DECLARE_TASKLET_OLD(buttontask, bottomhalf_tasklet_fn);
49
-50/* interrupt function triggered when a button is pressed */
-51static irqreturn_t button_isr(int irq, void *data)
+50/* interrupt function triggered when a button is pressed */
+51static irqreturn_t button_isr(int irq, void *data)
52{
-53 /* Do something quickly right now */
-54 if (irq == button_irqs[0] && !gpio_get_value(leds[0].gpio))
+53 /* Do something quickly right now */
+54 if (irq == button_irqs[0] && !gpio_get_value(leds[0].gpio))
55 gpio_set_value(leds[0].gpio, 1);
-56 else if (irq == button_irqs[1] && gpio_get_value(leds[0].gpio))
+56 else if (irq == button_irqs[1] && gpio_get_value(leds[0].gpio))
57 gpio_set_value(leds[0].gpio, 0);
58
-59 /* Do the rest at leisure via the scheduler */
+59 /* Do the rest at leisure via the scheduler */
60 tasklet_schedule(&buttontask);
61
-62 return IRQ_HANDLED;
+62 return IRQ_HANDLED;
63}
64
-65static int __init bottomhalf_init(void)
+65static int __init bottomhalf_init(void)
66{
-67 int ret = 0;
+67 int ret = 0;
68
-69 pr_info("%s\n", __func__);
+69 pr_info("%s\n", __func__);
70
-71 /* register LED gpios */
+71 /* register LED gpios */
72 ret = gpio_request_array(leds, ARRAY_SIZE(leds));
73
-74 if (ret) {
-75 pr_err("Unable to request GPIOs for LEDs: %d\n", ret);
-76 return ret;
+74 if (ret) {
+75 pr_err("Unable to request GPIOs for LEDs: %d\n", ret);
+76 return ret;
77 }
78
-79 /* register BUTTON gpios */
+79 /* register BUTTON gpios */
80 ret = gpio_request_array(buttons, ARRAY_SIZE(buttons));
81
-82 if (ret) {
-83 pr_err("Unable to request GPIOs for BUTTONs: %d\n", ret);
-84 goto fail1;
+82 if (ret) {
+83 pr_err("Unable to request GPIOs for BUTTONs: %d\n", ret);
+84 goto fail1;
85 }
86
-87 pr_info("Current button1 value: %d\n", gpio_get_value(buttons[0].gpio));
+87 pr_info("Current button1 value: %d\n", gpio_get_value(buttons[0].gpio));
88
89 ret = gpio_to_irq(buttons[0].gpio);
90
-91 if (ret < 0) {
-92 pr_err("Unable to request IRQ: %d\n", ret);
-93 goto fail2;
+91 if (ret < 0) {
+92 pr_err("Unable to request IRQ: %d\n", ret);
+93 goto fail2;
94 }
95
96 button_irqs[0] = ret;
97
-98 pr_info("Successfully requested BUTTON1 IRQ # %d\n", button_irqs[0]);
+98 pr_info("Successfully requested BUTTON1 IRQ # %d\n", button_irqs[0]);
99
100 ret = request_irq(button_irqs[0], button_isr,
101 IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
-102 "gpiomod#button1", NULL);
+102 "gpiomod#button1", NULL);
103
-104 if (ret) {
-105 pr_err("Unable to request IRQ: %d\n", ret);
-106 goto fail2;
+104 if (ret) {
+105 pr_err("Unable to request IRQ: %d\n", ret);
+106 goto fail2;
107 }
108
109 ret = gpio_to_irq(buttons[1].gpio);
110
-111 if (ret < 0) {
-112 pr_err("Unable to request IRQ: %d\n", ret);
-113 goto fail2;
+111 if (ret < 0) {
+112 pr_err("Unable to request IRQ: %d\n", ret);
+113 goto fail2;
114 }
115
116 button_irqs[1] = ret;
117
-118 pr_info("Successfully requested BUTTON2 IRQ # %d\n", button_irqs[1]);
+118 pr_info("Successfully requested BUTTON2 IRQ # %d\n", button_irqs[1]);
119
120 ret = request_irq(button_irqs[1], button_isr,
121 IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
-122 "gpiomod#button2", NULL);
+122 "gpiomod#button2", NULL);
123
-124 if (ret) {
-125 pr_err("Unable to request IRQ: %d\n", ret);
-126 goto fail3;
+124 if (ret) {
+125 pr_err("Unable to request IRQ: %d\n", ret);
+126 goto fail3;
127 }
128
-129 return 0;
+129 return 0;
130
-131/* cleanup what has been setup so far */
+131/* cleanup what has been setup so far */
132fail3:
133 free_irq(button_irqs[0], NULL);
134
@@ -4948,24 +4991,24 @@ when an interrupt is triggered.
138fail1:
139 gpio_free_array(leds, ARRAY_SIZE(leds));
140
-141 return ret;
+141 return ret;
142}
143
-144static void __exit bottomhalf_exit(void)
+144static void __exit bottomhalf_exit(void)
145{
-146 int i;
+146 int i;
147
-148 pr_info("%s\n", __func__);
+148 pr_info("%s\n", __func__);
149
-150 /* free irqs */
+150 /* free irqs */
151 free_irq(button_irqs[0], NULL);
152 free_irq(button_irqs[1], NULL);
153
-154 /* turn all LEDs off */
-155 for (i = 0; i < ARRAY_SIZE(leds); i++)
+154 /* turn all LEDs off */
+155 for (i = 0; i < ARRAY_SIZE(leds); i++)
156 gpio_set_value(leds[i].gpio, 0);
157
-158 /* unregister */
+158 /* unregister */
159 gpio_free_array(leds, ARRAY_SIZE(leds));
160 gpio_free_array(buttons, ARRAY_SIZE(buttons));
161}
@@ -4973,285 +5016,285 @@ when an interrupt is triggered.
163module_init(bottomhalf_init);
164module_exit(bottomhalf_exit);
165
-166MODULE_LICENSE("GPL");
-167MODULE_DESCRIPTION("Interrupt with top and bottom half");
-16 Crypto
-16.1 Hash functions
-1/*
-2 * cryptosha256.c
-3 */
-4#include <crypto/internal/hash.h>
-5#include <linux/module.h>
+
+1/*
+2 * cryptosha256.c
+3 */
+4#include <crypto/internal/hash.h>
+5#include <linux/module.h>
6
-7#define SHA256_LENGTH 32
+7#define SHA256_LENGTH 32
8
-9static void show_hash_result(char *plaintext, char *hash_sha256)
+9static void show_hash_result(char *plaintext, char *hash_sha256)
10{
-11 int i;
-12 char str[SHA256_LENGTH * 2 + 1];
+11 int i;
+12 char str[SHA256_LENGTH * 2 + 1];
13
-14 pr_info("sha256 test for string: \"%s\"\n", plaintext);
-15 for (i = 0; i < SHA256_LENGTH; i++)
-16 sprintf(&str[i * 2], "%02x", (unsigned char)hash_sha256[i]);
+14 pr_info("sha256 test for string: \"%s\"\n", plaintext);
+15 for (i = 0; i < SHA256_LENGTH; i++)
+16 sprintf(&str[i * 2], "%02x", (unsigned char)hash_sha256[i]);
17 str[i * 2] = 0;
-18 pr_info("%s\n", str);
+18 pr_info("%s\n", str);
19}
20
-21static int cryptosha256_init(void)
+21static int cryptosha256_init(void)
22{
-23 char *plaintext = "This is a test";
-24 char hash_sha256[SHA256_LENGTH];
-25 struct crypto_shash *sha256;
-26 struct shash_desc *shash;
+23 char *plaintext = "This is a test";
+24 char hash_sha256[SHA256_LENGTH];
+25 struct crypto_shash *sha256;
+26 struct shash_desc *shash;
27
-28 sha256 = crypto_alloc_shash("sha256", 0, 0);
-29 if (IS_ERR(sha256))
-30 return -1;
+28 sha256 = crypto_alloc_shash("sha256", 0, 0);
+29 if (IS_ERR(sha256))
+30 return -1;
31
-32 shash = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(sha256),
+32 shash = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(sha256),
33 GFP_KERNEL);
-34 if (!shash)
-35 return -ENOMEM;
+34 if (!shash)
+35 return -ENOMEM;
36
37 shash->tfm = sha256;
38
-39 if (crypto_shash_init(shash))
-40 return -1;
+39 if (crypto_shash_init(shash))
+40 return -1;
41
-42 if (crypto_shash_update(shash, plaintext, strlen(plaintext)))
-43 return -1;
+42 if (crypto_shash_update(shash, plaintext, strlen(plaintext)))
+43 return -1;
44
-45 if (crypto_shash_final(shash, hash_sha256))
-46 return -1;
+45 if (crypto_shash_final(shash, hash_sha256))
+46 return -1;
47
48 kfree(shash);
49 crypto_free_shash(sha256);
50
51 show_hash_result(plaintext, hash_sha256);
52
-53 return 0;
+53 return 0;
54}
55
-56static void cryptosha256_exit(void)
+56static void cryptosha256_exit(void)
57{
58}
59
60module_init(cryptosha256_init);
61module_exit(cryptosha256_exit);
62
-63MODULE_DESCRIPTION("sha256 hash test");
-64MODULE_LICENSE("GPL");
-1sudo insmod cryptosha256.ko
+
1sudo insmod cryptosha256.ko
2sudo dmesg
-1sudo rmmod cryptosha256
-1sudo rmmod cryptosha256
+16.2 Symmetric key encryption
-1/*
-2 * cryptosk.c
-3 */
-4#include <crypto/internal/skcipher.h>
-5#include <linux/crypto.h>
-6#include <linux/module.h>
-7#include <linux/random.h>
-8#include <linux/scatterlist.h>
+
+1/*
+2 * cryptosk.c
+3 */
+4#include <crypto/internal/skcipher.h>
+5#include <linux/crypto.h>
+6#include <linux/module.h>
+7#include <linux/random.h>
+8#include <linux/scatterlist.h>
9
-10#define SYMMETRIC_KEY_LENGTH 32
-11#define CIPHER_BLOCK_SIZE 16
+10#define SYMMETRIC_KEY_LENGTH 32
+11#define CIPHER_BLOCK_SIZE 16
12
-13struct tcrypt_result {
-14 struct completion completion;
-15 int err;
+13struct tcrypt_result {
+14 struct completion completion;
+15 int err;
16};
17
-18struct skcipher_def {
-19 struct scatterlist sg;
-20 struct crypto_skcipher *tfm;
-21 struct skcipher_request *req;
-22 struct tcrypt_result result;
-23 char *scratchpad;
-24 char *ciphertext;
-25 char *ivdata;
+18struct skcipher_def {
+19 struct scatterlist sg;
+20 struct crypto_skcipher *tfm;
+21 struct skcipher_request *req;
+22 struct tcrypt_result result;
+23 char *scratchpad;
+24 char *ciphertext;
+25 char *ivdata;
26};
27
-28static struct skcipher_def sk;
+28static struct skcipher_def sk;
29
-30static void test_skcipher_finish(struct skcipher_def *sk)
+30static void test_skcipher_finish(struct skcipher_def *sk)
31{
-32 if (sk->tfm)
+32 if (sk->tfm)
33 crypto_free_skcipher(sk->tfm);
-34 if (sk->req)
+34 if (sk->req)
35 skcipher_request_free(sk->req);
-36 if (sk->ivdata)
+36 if (sk->ivdata)
37 kfree(sk->ivdata);
-38 if (sk->scratchpad)
+38 if (sk->scratchpad)
39 kfree(sk->scratchpad);
-40 if (sk->ciphertext)
+40 if (sk->ciphertext)
41 kfree(sk->ciphertext);
42}
43
-44static int test_skcipher_result(struct skcipher_def *sk, int rc)
+44static int test_skcipher_result(struct skcipher_def *sk, int rc)
45{
-46 switch (rc) {
-47 case 0:
-48 break;
-49 case -EINPROGRESS || -EBUSY:
+46 switch (rc) {
+47 case 0:
+48 break;
+49 case -EINPROGRESS || -EBUSY:
50 rc = wait_for_completion_interruptible(&sk->result.completion);
-51 if (!rc && !sk->result.err) {
+51 if (!rc && !sk->result.err) {
52 reinit_completion(&sk->result.completion);
-53 break;
+53 break;
54 }
-55 pr_info("skcipher encrypt returned with %d result %d\n", rc,
+55 pr_info("skcipher encrypt returned with %d result %d\n", rc,
56 sk->result.err);
-57 break;
-58 default:
-59 pr_info("skcipher encrypt returned with %d result %d\n", rc,
+57 break;
+58 default:
+59 pr_info("skcipher encrypt returned with %d result %d\n", rc,
60 sk->result.err);
-61 break;
+61 break;
62 }
63
64 init_completion(&sk->result.completion);
65
-66 return rc;
+66 return rc;
67}
68
-69static void test_skcipher_callback(struct crypto_async_request *req, int error)
+69static void test_skcipher_callback(struct crypto_async_request *req, int error)
70{
-71 struct tcrypt_result *result = req->data;
+71 struct tcrypt_result *result = req->data;
72
-73 if (error == -EINPROGRESS)
-74 return;
+73 if (error == -EINPROGRESS)
+74 return;
75
76 result->err = error;
77 complete(&result->completion);
-78 pr_info("Encryption finished successfully\n");
+78 pr_info("Encryption finished successfully\n");
79
-80 /* decrypt data */
-81#if 0
-82 memset((void*)sk.scratchpad, '-', CIPHER_BLOCK_SIZE);
-83 ret = crypto_skcipher_decrypt(sk.req);
-84 ret = test_skcipher_result(&sk, ret);
-85 if (ret)
-86 return;
+80 /* decrypt data */
+81#if 0
+82 memset((void*)sk.scratchpad, '-', CIPHER_BLOCK_SIZE);
+83 ret = crypto_skcipher_decrypt(sk.req);
+84 ret = test_skcipher_result(&sk, ret);
+85 if (ret)
+86 return;
87
-88 sg_copy_from_buffer(&sk.sg, 1, sk.scratchpad, CIPHER_BLOCK_SIZE);
-89 sk.scratchpad[CIPHER_BLOCK_SIZE-1] = 0;
+88 sg_copy_from_buffer(&sk.sg, 1, sk.scratchpad, CIPHER_BLOCK_SIZE);
+89 sk.scratchpad[CIPHER_BLOCK_SIZE-1] = 0;
90
-91 pr_info("Decryption request successful\n");
-92 pr_info("Decrypted: %s\n", sk.scratchpad);
-93#endif
+91 pr_info("Decryption request successful\n");
+92 pr_info("Decrypted: %s\n", sk.scratchpad);
+93#endif
94}
95
-96static int test_skcipher_encrypt(char *plaintext, char *password,
-97 struct skcipher_def *sk)
+96static int test_skcipher_encrypt(char *plaintext, char *password,
+97 struct skcipher_def *sk)
98{
-99 int ret = -EFAULT;
-100 unsigned char key[SYMMETRIC_KEY_LENGTH];
+99 int ret = -EFAULT;
+100 unsigned char key[SYMMETRIC_KEY_LENGTH];
101
-102 if (!sk->tfm) {
-103 sk->tfm = crypto_alloc_skcipher("cbc-aes-aesni", 0, 0);
-104 if (IS_ERR(sk->tfm)) {
-105 pr_info("could not allocate skcipher handle\n");
-106 return PTR_ERR(sk->tfm);
+102 if (!sk->tfm) {
+103 sk->tfm = crypto_alloc_skcipher("cbc-aes-aesni", 0, 0);
+104 if (IS_ERR(sk->tfm)) {
+105 pr_info("could not allocate skcipher handle\n");
+106 return PTR_ERR(sk->tfm);
107 }
108 }
109
-110 if (!sk->req) {
+110 if (!sk->req) {
111 sk->req = skcipher_request_alloc(sk->tfm, GFP_KERNEL);
-112 if (!sk->req) {
-113 pr_info("could not allocate skcipher request\n");
+112 if (!sk->req) {
+113 pr_info("could not allocate skcipher request\n");
114 ret = -ENOMEM;
-115 goto out;
+115 goto out;
116 }
117 }
118
119 skcipher_request_set_callback(sk->req, CRYPTO_TFM_REQ_MAY_BACKLOG,
120 test_skcipher_callback, &sk->result);
121
-122 /* clear the key */
-123 memset((void *)key, '\0', SYMMETRIC_KEY_LENGTH);
+122 /* clear the key */
+123 memset((void *)key, '\0', SYMMETRIC_KEY_LENGTH);
124
-125 /* Use the world's favourite password */
-126 sprintf((char *)key, "%s", password);
+125 /* Use the world's favourite password */
+126 sprintf((char *)key, "%s", password);
127
-128 /* AES 256 with given symmetric key */
-129 if (crypto_skcipher_setkey(sk->tfm, key, SYMMETRIC_KEY_LENGTH)) {
-130 pr_info("key could not be set\n");
+128 /* AES 256 with given symmetric key */
+129 if (crypto_skcipher_setkey(sk->tfm, key, SYMMETRIC_KEY_LENGTH)) {
+130 pr_info("key could not be set\n");
131 ret = -EAGAIN;
-132 goto out;
+132 goto out;
133 }
-134 pr_info("Symmetric key: %s\n", key);
-135 pr_info("Plaintext: %s\n", plaintext);
+134 pr_info("Symmetric key: %s\n", key);
+135 pr_info("Plaintext: %s\n", plaintext);
136
-137 if (!sk->ivdata) {
-138 /* see https://en.wikipedia.org/wiki/Initialization_vector */
+137 if (!sk->ivdata) {
+138 /* see https://en.wikipedia.org/wiki/Initialization_vector */
139 sk->ivdata = kmalloc(CIPHER_BLOCK_SIZE, GFP_KERNEL);
-140 if (!sk->ivdata) {
-141 pr_info("could not allocate ivdata\n");
-142 goto out;
+140 if (!sk->ivdata) {
+141 pr_info("could not allocate ivdata\n");
+142 goto out;
143 }
144 get_random_bytes(sk->ivdata, CIPHER_BLOCK_SIZE);
145 }
146
-147 if (!sk->scratchpad) {
-148 /* The text to be encrypted */
+147 if (!sk->scratchpad) {
+148 /* The text to be encrypted */
149 sk->scratchpad = kmalloc(CIPHER_BLOCK_SIZE, GFP_KERNEL);
-150 if (!sk->scratchpad) {
-151 pr_info("could not allocate scratchpad\n");
-152 goto out;
+150 if (!sk->scratchpad) {
+151 pr_info("could not allocate scratchpad\n");
+152 goto out;
153 }
154 }
-155 sprintf((char *)sk->scratchpad, "%s", plaintext);
+155 sprintf((char *)sk->scratchpad, "%s", plaintext);
156
157 sg_init_one(&sk->sg, sk->scratchpad, CIPHER_BLOCK_SIZE);
158 skcipher_request_set_crypt(sk->req, &sk->sg, &sk->sg, CIPHER_BLOCK_SIZE,
159 sk->ivdata);
160 init_completion(&sk->result.completion);
161
-162 /* encrypt data */
+162 /* encrypt data */
163 ret = crypto_skcipher_encrypt(sk->req);
164 ret = test_skcipher_result(sk, ret);
-165 if (ret)
-166 goto out;
+165 if (ret)
+166 goto out;
167
-168 pr_info("Encryption request successful\n");
+168 pr_info("Encryption request successful\n");
169
170out:
-171 return ret;
+171 return ret;
172}
173
-174static int cryptoapi_init(void)
+174static int cryptoapi_init(void)
175{
-176 /* The world's favorite password */
-177 char *password = "password123";
+176 /* The world's favorite password */
+177 char *password = "password123";
178
179 sk.tfm = NULL;
180 sk.req = NULL;
@@ -5259,11 +5302,11 @@ and a password.
182 sk.ciphertext = NULL;
183 sk.ivdata = NULL;
184
-185 test_skcipher_encrypt("Testing", password, &sk);
-186 return 0;
+185 test_skcipher_encrypt("Testing", password, &sk);
+186 return 0;
187}
188
-189static void cryptoapi_exit(void)
+189static void cryptoapi_exit(void)
190{
191 test_skcipher_finish(&sk);
192}
@@ -5271,12 +5314,12 @@ and a password.
194module_init(cryptoapi_init);
195module_exit(cryptoapi_exit);
196
-197MODULE_DESCRIPTION("Symmetric key encryption example");
-198MODULE_LICENSE("GPL");
-17 Standardizing the interfaces: The Device Model
-1/*
-2 * devicemodel.c
-3 */
-4#include <linux/kernel.h>
-5#include <linux/module.h>
-6#include <linux/platform_device.h>
+
+1/*
+2 * devicemodel.c
+3 */
+4#include <linux/kernel.h>
+5#include <linux/module.h>
+6#include <linux/platform_device.h>
7
-8struct devicemodel_data {
-9 char *greeting;
-10 int number;
+8struct devicemodel_data {
+9 char *greeting;
+10 int number;
11};
12
-13static int devicemodel_probe(struct platform_device *dev)
+13static int devicemodel_probe(struct platform_device *dev)
14{
-15 struct devicemodel_data *pd =
-16 (struct devicemodel_data *)(dev->dev.platform_data);
+15 struct devicemodel_data *pd =
+16 (struct devicemodel_data *)(dev->dev.platform_data);
17
-18 pr_info("devicemodel probe\n");
-19 pr_info("devicemodel greeting: %s; %d\n", pd->greeting, pd->number);
+18 pr_info("devicemodel probe\n");
+19 pr_info("devicemodel greeting: %s; %d\n", pd->greeting, pd->number);
20
-21 /* Your device initialization code */
+21 /* Your device initialization code */
22
-23 return 0;
+23 return 0;
24}
25
-26static int devicemodel_remove(struct platform_device *dev)
+26static int devicemodel_remove(struct platform_device *dev)
27{
-28 pr_info("devicemodel example removed\n");
+28 pr_info("devicemodel example removed\n");
29
-30 /* Your device removal code */
+30 /* Your device removal code */
31
-32 return 0;
+32 return 0;
33}
34
-35static int devicemodel_suspend(struct device *dev)
+35static int devicemodel_suspend(struct device *dev)
36{
-37 pr_info("devicemodel example suspend\n");
+37 pr_info("devicemodel example suspend\n");
38
-39 /* Your device suspend code */
+39 /* Your device suspend code */
40
-41 return 0;
+41 return 0;
42}
43
-44static int devicemodel_resume(struct device *dev)
+44static int devicemodel_resume(struct device *dev)
45{
-46 pr_info("devicemodel example resume\n");
+46 pr_info("devicemodel example resume\n");
47
-48 /* Your device resume code */
+48 /* Your device resume code */
49
-50 return 0;
+50 return 0;
51}
52
-53static const struct dev_pm_ops devicemodel_pm_ops = {
+53static const struct dev_pm_ops devicemodel_pm_ops = {
54 .suspend = devicemodel_suspend,
55 .resume = devicemodel_resume,
56 .poweroff = devicemodel_suspend,
@@ -5345,10 +5388,10 @@ functions.
59 .restore = devicemodel_resume,
60};
61
-62static struct platform_driver devicemodel_driver = {
+62static struct platform_driver devicemodel_driver = {
63 .driver =
64 {
-65 .name = "devicemodel_example",
+65 .name = "devicemodel_example",
66 .owner = THIS_MODULE,
67 .pm = &devicemodel_pm_ops,
68 },
@@ -5356,40 +5399,40 @@ functions.
70 .remove = devicemodel_remove,
71};
72
-73static int devicemodel_init(void)
+73static int devicemodel_init(void)
74{
-75 int ret;
+75 int ret;
76
-77 pr_info("devicemodel init\n");
+77 pr_info("devicemodel init\n");
78
79 ret = platform_driver_register(&devicemodel_driver);
80
-81 if (ret) {
-82 pr_err("Unable to register driver\n");
-83 return ret;
+81 if (ret) {
+82 pr_err("Unable to register driver\n");
+83 return ret;
84 }
85
-86 return 0;
+86 return 0;
87}
88
-89static void devicemodel_exit(void)
+89static void devicemodel_exit(void)
90{
-91 pr_info("devicemodel exit\n");
+91 pr_info("devicemodel exit\n");
92 platform_driver_unregister(&devicemodel_driver);
93}
94
95module_init(devicemodel_init);
96module_exit(devicemodel_exit);
97
-98MODULE_LICENSE("GPL");
-99MODULE_DESCRIPTION("Linux Device Model example");
-18 Optimizations
-18.1 Likely and Unlikely conditions
-1bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx);
-2if (unlikely(!bvl)) {
+
1bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx);
+2if (unlikely(!bvl)) {
3 mempool_free(bio, bio_pool);
4 bio = NULL;
-5 goto out;
+5 goto out;
6}
- unlikely
+ 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.
-19 Common Pitfalls
-19.1 Using standard libraries
-19.2 Disabling interrupts
-20 Where To Go From Here?
-The Linux Kernel Module Programming Guide
- device_destroy
during the call to cleanup_module
.
- register_chrdev()
+ would occupy a range of minor numbers associated with the given major. The
+recommended way to reduce waste for char device registration is using cdev
+interface.
+ register_chrdev_region
+ or alloc_chrdev_region
+.
+1int register_chrdev_region(dev_t from, unsigned count, const char *name);
+2int alloc_chrdev_region(dev_t *dev, unsigned baseminor, unsigned count, const char *name);
+ register_chrdev_region
+ if you know the device major number and
+ alloc_chrdev_region
+ if you would like to allocate a dynamicly-allocated major number.
+ struct cdev
+ for our char device and associate it with the device numbers. To initialize the
+ struct cdev
+, we can achieve by the similar sequence of the following codes.
+1struct cdev *my_dev = cdev_alloc();
+2my_cdev->ops = &my_fops;
+ struct cdev
+ within a device-specific structure of your own. In this case, we’ll need
+ cdev_init
+ for the initialization.
+1void cdev_init(struct cdev *cdev, const struct file_operations *fops);
+
+
+
+ cdev_add
+.
+1int cdev_add(struct cdev *p, dev_t dev, unsigned count);
+6.4 Unregistering A Device
- 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
@@ -1389,7 +1435,7 @@ unlucky, another kernel module was loaded into the 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.
- cleanup_module
that’s impossible because it is a void function. However, there is a counter
@@ -1407,9 +1453,6 @@ there are functions defined in
-
-
-
try_module_get(THIS_MODULE)
: Increment the reference count of current module.
module_refcount(THIS_MODULE)
: Return the value of reference count of current module.6.5 chardev.c
-1cat /proc/devices
-1cat /proc/devices
+ echo "hi" > /dev/hello
+ echo "hi" > /dev/hello
), but catch these attempts and tell the user that the operation is not supported.
Don’t worry if you don’t see what we do with the data we read into the buffer; we
don’t do much with it. We simply read in the data and print a message
acknowledging that we received it.
- CDEV_NOT_USED
+ and CDEV_EXCLUSIVE_OPEN
- and CDEV_EXCLUSIVE_OPEN
, to determine whether the file is currently opened by someone or not. CAS compares
the contents of a memory location with the expected value and, only if they are the
same, modifies the contents of that memory location to the desired value. See more
concurrency details in the 12 section.
1/*
-2 * chardev.c: Creates a read-only char device that says how many times
-3 * you have read from the dev file
-4 */
+
-1/*
+2 * chardev.c: Creates a read-only char device that says how many times
+3 * you have read from the dev file
+4 */
5
-6#include <linux/cdev.h>
-7#include <linux/delay.h>
-8#include <linux/device.h>
-9#include <linux/fs.h>
-10#include <linux/init.h>
-11#include <linux/irq.h>
-12#include <linux/kernel.h>
-13#include <linux/module.h>
-14#include <linux/poll.h>
+6#include <linux/cdev.h>
+7#include <linux/delay.h>
+8#include <linux/device.h>
+9#include <linux/fs.h>
+10#include <linux/init.h>
+11#include <linux/irq.h>
+12#include <linux/kernel.h>
+13#include <linux/module.h>
+14#include <linux/poll.h>
15
-16/* Prototypes - this would normally go in a .h file */
-17static int device_open(struct inode *, struct file *);
-18static int device_release(struct inode *, struct file *);
-19static ssize_t device_read(struct file *, char __user *, size_t, loff_t *);
-20static ssize_t device_write(struct file *, const char __user *, size_t,
+16/* Prototypes - this would normally go in a .h file */
+17static int device_open(struct inode *, struct file *);
+18static int device_release(struct inode *, struct file *);
+19static ssize_t device_read(struct file *, char __user *, size_t, loff_t *);
+20static ssize_t device_write(struct file *, const char __user *, size_t,
21 loff_t *);
22
-23#define SUCCESS 0
-24#define DEVICE_NAME "chardev" /* Dev name as it appears in /proc/devices */
-25#define BUF_LEN 80 /* Max length of the message from the device */
+23#define SUCCESS 0
+24#define DEVICE_NAME "chardev" /* Dev name as it appears in /proc/devices */
+25#define BUF_LEN 80 /* Max length of the message from the device */
26
-27/* Global variables are declared as static, so are global within the file. */
+27/* Global variables are declared as static, so are global within the file. */
28
-29static int major; /* major number assigned to our device driver */
+29static int major; /* major number assigned to our device driver */
30
-31enum {
+31enum {
32 CDEV_NOT_USED = 0,
33 CDEV_EXCLUSIVE_OPEN = 1,
34};
35
-36/* Is device open? Used to prevent multiple access to device */
-37static atomic_t already_open = ATOMIC_INIT(CDEV_NOT_USED);
+36/* Is device open? Used to prevent multiple access to device */
+37static atomic_t already_open = ATOMIC_INIT(CDEV_NOT_USED);
38
-39static char msg[BUF_LEN]; /* The msg the device will give when asked */
+39static char msg[BUF_LEN]; /* The msg the device will give when asked */
40
-41static struct class *cls;
+41static struct class *cls;
42
-43static struct file_operations chardev_fops = {
+43static struct file_operations chardev_fops = {
44 .read = device_read,
45 .write = device_write,
46 .open = device_open,
47 .release = device_release,
48};
49
-50static int __init chardev_init(void)
+50static int __init chardev_init(void)
51{
52 major = register_chrdev(0, DEVICE_NAME, &chardev_fops);
53
-54 if (major < 0) {
-55 pr_alert("Registering char device failed with %d\n", major);
-56 return major;
+54 if (major < 0) {
+55 pr_alert("Registering char device failed with %d\n", major);
+56 return major;
57 }
58
-59 pr_info("I was assigned major number %d.\n", major);
+59 pr_info("I was assigned major number %d.\n", major);
60
61 cls = class_create(THIS_MODULE, DEVICE_NAME);
62 device_create(cls, NULL, MKDEV(major, 0), NULL, DEVICE_NAME);
63
-64 pr_info("Device created on /dev/%s\n", DEVICE_NAME);
+64 pr_info("Device created on /dev/%s\n", DEVICE_NAME);
65
-66 return SUCCESS;
+66 return SUCCESS;
67}
68
-69static void __exit chardev_exit(void)
+69static void __exit chardev_exit(void)
70{
71 device_destroy(cls, MKDEV(major, 0));
72 class_destroy(cls);
73
-74 /* Unregister the device */
+74 /* Unregister the device */
75 unregister_chrdev(major, DEVICE_NAME);
76}
77
-78/* Methods */
+78/* Methods */
79
-80/* Called when a process tries to open the device file, like
-81 * "sudo cat /dev/chardev"
-82 */
-83static int device_open(struct inode *inode, struct file *file)
+80/* Called when a process tries to open the device file, like
+81 * "sudo cat /dev/chardev"
+82 */
+83static int device_open(struct inode *inode, struct file *file)
84{
-85 static int counter = 0;
+85 static int counter = 0;
86
-87 if (atomic_cmpxchg(&already_open, CDEV_NOT_USED, CDEV_EXCLUSIVE_OPEN))
-88 return -EBUSY;
+87 if (atomic_cmpxchg(&already_open, CDEV_NOT_USED, CDEV_EXCLUSIVE_OPEN))
+88 return -EBUSY;
89
-90 sprintf(msg, "I already told you %d times Hello world!\n", counter++);
+90 sprintf(msg, "I already told you %d times Hello world!\n", counter++);
91 try_module_get(THIS_MODULE);
92
-93 return SUCCESS;
+93 return SUCCESS;
94}
95
-96/* Called when a process closes the device file. */
-97static int device_release(struct inode *inode, struct file *file)
+96/* Called when a process closes the device file. */
+97static int device_release(struct inode *inode, struct file *file)
98{
-99 /* We're now ready for our next caller */
+99 /* We're now ready for our next caller */
100 atomic_set(&already_open, CDEV_NOT_USED);
101
-102 /* Decrement the usage count, or else once you opened the file, you will
-103 * never get get rid of the module.
-104 */
+102 /* Decrement the usage count, or else once you opened the file, you will
+103 * never get get rid of the module.
+104 */
105 module_put(THIS_MODULE);
106
-107 return SUCCESS;
+107 return SUCCESS;
108}
109
-110/* Called when a process, which already opened the dev file, attempts to
-111 * read from it.
-112 */
-113static ssize_t device_read(struct file *filp, /* see include/linux/fs.h */
-114 char __user *buffer, /* buffer to fill with data */
-115 size_t length, /* length of the buffer */
+110/* Called when a process, which already opened the dev file, attempts to
+111 * read from it.
+112 */
+113static ssize_t device_read(struct file *filp, /* see include/linux/fs.h */
+114 char __user *buffer, /* buffer to fill with data */
+115 size_t length, /* length of the buffer */
116 loff_t *offset)
117{
-118 /* Number of bytes actually written to the buffer */
-119 int bytes_read = 0;
-120 const char *msg_ptr = msg;
+118 /* Number of bytes actually written to the buffer */
+119 int bytes_read = 0;
+120 const char *msg_ptr = msg;
121
-122 if (!*(msg_ptr + *offset)) { /* we are at the end of message */
-123 *offset = 0; /* reset the offset */
-124 return 0; /* signify end of file */
+122 if (!*(msg_ptr + *offset)) { /* we are at the end of message */
+123 *offset = 0; /* reset the offset */
+124 return 0; /* signify end of file */
125 }
126
127 msg_ptr += *offset;
128
-129 /* Actually put the data into the buffer */
-130 while (length && *msg_ptr) {
-131 /* The buffer is in the user data segment, not the kernel
-132 * segment so "*" assignment won't work. We have to use
-133 * put_user which copies data from the kernel data segment to
-134 * the user data segment.
-135 */
+129 /* Actually put the data into the buffer */
+130 while (length && *msg_ptr) {
+131 /* The buffer is in the user data segment, not the kernel
+132 * segment so "*" assignment won't work. We have to use
+133 * put_user which copies data from the kernel data segment to
+134 * the user data segment.
+135 */
136 put_user(*(msg_ptr++), buffer++);
137 length--;
138 bytes_read++;
@@ -1595,70 +1638,70 @@ concurrency details in the 12
+6.6 Writing Modules for Multiple Kernel Versions
- LINUX_VERSION_CODE
to the macro KERNEL_VERSION
. In version a.b.c of the kernel, the value of this macro would be .
-7 The /proc File System
- init_module
registers the structure with the kernel and
cleanup_module
+ unregisters it.
- unregisters it.
- try_module_get
and 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.
- init_module
, return a value (and a buffer) when the file /proc/helloworld is read in the callback
@@ -1666,12 +1709,12 @@ function procfile_read
, and delete the file /proc/helloworld in the function
cleanup_module
.
- proc_create
-. The return value is a struct proc_dir_entry
+. 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.
- 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
@@ -1688,82 +1731,82 @@ function, if it never returns zero, the read function is called endlessly.
$ cat /proc/helloworld
HelloWorld!
1/*
-2 * procfs1.c
-3 */
+
+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>
+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
+11#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0)
+12#define HAVE_PROC_OPS
+13#endif
14
-15#define procfs_name "helloworld"
+15#define procfs_name "helloworld"
16
-17static struct proc_dir_entry *our_proc_file;
+17static struct proc_dir_entry *our_proc_file;
18
-19static ssize_t procfile_read(struct file *filePointer, char __user *buffer,
-20 size_t buffer_length, loff_t *offset)
+19static ssize_t procfile_read(struct file *filePointer, char __user *buffer,
+20 size_t buffer_length, loff_t *offset)
21{
-22 char s[13] = "HelloWorld!\n";
-23 int len = sizeof(s);
-24 ssize_t ret = len;
+22 char s[13] = "HelloWorld!\n";
+23 int len = sizeof(s);
+24 ssize_t ret = len;
25
-26 if (*offset >= len || copy_to_user(buffer, s, len)) {
-27 pr_info("copy_to_user failed\n");
+26 if (*offset >= len || copy_to_user(buffer, s, len)) {
+27 pr_info("copy_to_user failed\n");
28 ret = 0;
-29 } else {
-30 pr_info("procfile read %s\n", filePointer->f_path.dentry->d_name.name);
+29 } else {
+30 pr_info("procfile read %s\n", filePointer->f_path.dentry->d_name.name);
31 *offset += len;
32 }
33
-34 return ret;
+34 return ret;
35}
36
-37#ifdef HAVE_PROC_OPS
-38static const struct proc_ops proc_file_fops = {
+37#ifdef HAVE_PROC_OPS
+38static const struct proc_ops proc_file_fops = {
39 .proc_read = procfile_read,
40};
-41#else
-42static const struct file_operations proc_file_fops = {
+41#else
+42static const struct file_operations proc_file_fops = {
43 .read = procfile_read,
44};
-45#endif
+45#endif
46
-47static int __init procfs1_init(void)
+47static int __init procfs1_init(void)
48{
49 our_proc_file = proc_create(procfs_name, 0644, NULL, &proc_file_fops);
-50 if (NULL == our_proc_file) {
+50 if (NULL == our_proc_file) {
51 proc_remove(our_proc_file);
-52 pr_alert("Error:Could not initialize /proc/%s\n", procfs_name);
-53 return -ENOMEM;
+52 pr_alert("Error:Could not initialize /proc/%s\n", procfs_name);
+53 return -ENOMEM;
54 }
55
-56 pr_info("/proc/%s created\n", procfs_name);
-57 return 0;
+56 pr_info("/proc/%s created\n", procfs_name);
+57 return 0;
58}
59
-60static void __exit procfs1_exit(void)
+60static void __exit procfs1_exit(void)
61{
62 proc_remove(our_proc_file);
-63 pr_info("/proc/%s removed\n", procfs_name);
+63 pr_info("/proc/%s removed\n", procfs_name);
64}
65
66module_init(procfs1_init);
67module_exit(procfs1_exit);
68
-69MODULE_LICENSE("GPL");
-7.1 The proc_ops Structure
- proc_ops
+ as 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
@@ -1775,10 +1818,10 @@ performance. For example, the file which never disappears in proc_flag
PROC_ENTRY_PERMANENT
to save 2 atomic ops, 1 allocation, 1 free in per open/read/close sequence.
-7.2 Read and Write a /proc File
- copy_from_user
or get_user
)
- copy_from_user
+ copy_from_user
or get_user
is that Linux memory (on Intel architecture, it may be different under some
@@ -1797,7 +1840,7 @@ 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.
-1/*
-2 * procfs2.c - create a "file" in /proc
-3 */
+
+1/*
+2 * procfs2.c - create a "file" in /proc
+3 */
4
-5#include <linux/kernel.h> /* We're doing kernel work */
-6#include <linux/module.h> /* Specifically, a module */
-7#include <linux/proc_fs.h> /* Necessary because we use the proc fs */
-8#include <linux/uaccess.h> /* for copy_from_user */
-9#include <linux/version.h>
+5#include <linux/kernel.h> /* We're doing kernel work */
+6#include <linux/module.h> /* Specifically, a module */
+7#include <linux/proc_fs.h> /* Necessary because we use the proc fs */
+8#include <linux/uaccess.h> /* for copy_from_user */
+9#include <linux/version.h>
10
-11#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0)
-12#define HAVE_PROC_OPS
-13#endif
+11#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0)
+12#define HAVE_PROC_OPS
+13#endif
14
-15#define PROCFS_MAX_SIZE 1024
-16#define PROCFS_NAME "buffer1k"
+15#define PROCFS_MAX_SIZE 1024
+16#define PROCFS_NAME "buffer1k"
17
-18/* This structure hold information about the /proc file */
-19static struct proc_dir_entry *our_proc_file;
+18/* This structure hold information about the /proc file */
+19static struct proc_dir_entry *our_proc_file;
20
-21/* The buffer used to store character for this module */
-22static char procfs_buffer[PROCFS_MAX_SIZE];
+21/* The buffer used to store character for this module */
+22static char procfs_buffer[PROCFS_MAX_SIZE];
23
-24/* The size of the buffer */
-25static unsigned long procfs_buffer_size = 0;
+24/* The size of the buffer */
+25static unsigned long procfs_buffer_size = 0;
26
-27/* This function is called then the /proc file is read */
-28static ssize_t procfile_read(struct file *filePointer, char __user *buffer,
-29 size_t buffer_length, loff_t *offset)
+27/* This function is called then the /proc file is read */
+28static ssize_t procfile_read(struct file *filePointer, char __user *buffer,
+29 size_t buffer_length, loff_t *offset)
30{
-31 char s[13] = "HelloWorld!\n";
-32 int len = sizeof(s);
-33 ssize_t ret = len;
+31 char s[13] = "HelloWorld!\n";
+32 int len = sizeof(s);
+33 ssize_t ret = len;
34
-35 if (*offset >= len || copy_to_user(buffer, s, len)) {
-36 pr_info("copy_to_user failed\n");
+35 if (*offset >= len || copy_to_user(buffer, s, len)) {
+36 pr_info("copy_to_user failed\n");
37 ret = 0;
-38 } else {
-39 pr_info("procfile read %s\n", filePointer->f_path.dentry->d_name.name);
+38 } else {
+39 pr_info("procfile read %s\n", filePointer->f_path.dentry->d_name.name);
40 *offset += len;
41 }
42
-43 return ret;
+43 return ret;
44}
45
-46/* This function is called with the /proc file is written. */
-47static ssize_t procfile_write(struct file *file, const char __user *buff,
-48 size_t len, loff_t *off)
+46/* This function is called with the /proc file is written. */
+47static ssize_t procfile_write(struct file *file, const char __user *buff,
+48 size_t len, loff_t *off)
49{
50 procfs_buffer_size = len;
-51 if (procfs_buffer_size > PROCFS_MAX_SIZE)
+51 if (procfs_buffer_size > PROCFS_MAX_SIZE)
52 procfs_buffer_size = PROCFS_MAX_SIZE;
53
-54 if (copy_from_user(procfs_buffer, buff, procfs_buffer_size))
-55 return -EFAULT;
+54 if (copy_from_user(procfs_buffer, buff, procfs_buffer_size))
+55 return -EFAULT;
56
-57 procfs_buffer[procfs_buffer_size & (PROCFS_MAX_SIZE - 1)] = '\0';
-58 pr_info("procfile write %s\n", procfs_buffer);
+57 procfs_buffer[procfs_buffer_size & (PROCFS_MAX_SIZE - 1)] = '\0';
+58 pr_info("procfile write %s\n", procfs_buffer);
59
-60 return procfs_buffer_size;
+60 return procfs_buffer_size;
61}
62
-63#ifdef HAVE_PROC_OPS
-64static const struct proc_ops proc_file_fops = {
+63#ifdef HAVE_PROC_OPS
+64static const struct proc_ops proc_file_fops = {
65 .proc_read = procfile_read,
66 .proc_write = procfile_write,
67};
-68#else
-69static const struct file_operations proc_file_fops = {
+68#else
+69static const struct file_operations proc_file_fops = {
70 .read = procfile_read,
71 .write = procfile_write,
72};
-73#endif
+73#endif
74
-75static int __init procfs2_init(void)
+75static int __init procfs2_init(void)
76{
77 our_proc_file = proc_create(PROCFS_NAME, 0644, NULL, &proc_file_fops);
-78 if (NULL == our_proc_file) {
+78 if (NULL == our_proc_file) {
79 proc_remove(our_proc_file);
-80 pr_alert("Error:Could not initialize /proc/%s\n", PROCFS_NAME);
-81 return -ENOMEM;
+80 pr_alert("Error:Could not initialize /proc/%s\n", PROCFS_NAME);
+81 return -ENOMEM;
82 }
83
-84 pr_info("/proc/%s created\n", PROCFS_NAME);
-85 return 0;
+84 pr_info("/proc/%s created\n", PROCFS_NAME);
+85 return 0;
86}
87
-88static void __exit procfs2_exit(void)
+88static void __exit procfs2_exit(void)
89{
90 proc_remove(our_proc_file);
-91 pr_info("/proc/%s removed\n", PROCFS_NAME);
+91 pr_info("/proc/%s removed\n", PROCFS_NAME);
92}
93
94module_init(procfs2_init);
95module_exit(procfs2_exit);
96
-97MODULE_LICENSE("GPL");
-7.3 Manage /proc file with standard filesystem
- struct inode_operations
-, which includes a pointer to struct proc_ops
+ struct inode_operations
+, which includes a pointer to struct proc_ops
.
- struct inode_operations
+ struct inode_operations
will be used to access to it. This is the mechanism we use, a
- struct inode_operations
+ struct inode_operations
- which includes a pointer to a struct proc_ops
+ which includes a pointer to a struct proc_ops
which includes pointers to our procf_read
and procfs_write
functions.
- 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
@@ -1947,7 +1990,7 @@ 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.
-1/*
-2 * procfs3.c
-3 */
+
+1/*
+2 * procfs3.c
+3 */
4
-5#include <linux/kernel.h>
-6#include <linux/module.h>
-7#include <linux/proc_fs.h>
-8#include <linux/sched.h>
-9#include <linux/uaccess.h>
-10#include <linux/version.h>
+5#include <linux/kernel.h>
+6#include <linux/module.h>
+7#include <linux/proc_fs.h>
+8#include <linux/sched.h>
+9#include <linux/uaccess.h>
+10#include <linux/version.h>
11
-12#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0)
-13#define HAVE_PROC_OPS
-14#endif
+12#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0)
+13#define HAVE_PROC_OPS
+14#endif
15
-16#define PROCFS_MAX_SIZE 2048
-17#define PROCFS_ENTRY_FILENAME "buffer2k"
+16#define PROCFS_MAX_SIZE 2048
+17#define PROCFS_ENTRY_FILENAME "buffer2k"
18
-19static struct proc_dir_entry *our_proc_file;
-20static char procfs_buffer[PROCFS_MAX_SIZE];
-21static unsigned long procfs_buffer_size = 0;
+19static struct proc_dir_entry *our_proc_file;
+20static char procfs_buffer[PROCFS_MAX_SIZE];
+21static unsigned long procfs_buffer_size = 0;
22
-23static ssize_t procfs_read(struct file *filp, char __user *buffer,
-24 size_t length, loff_t *offset)
+23static ssize_t procfs_read(struct file *filp, char __user *buffer,
+24 size_t length, loff_t *offset)
25{
-26 static int finished = 0;
+26 static int finished = 0;
27
-28 if (finished) {
-29 pr_debug("procfs_read: END\n");
+28 if (finished) {
+29 pr_debug("procfs_read: END\n");
30 finished = 0;
-31 return 0;
+31 return 0;
32 }
33 finished = 1;
34
-35 if (copy_to_user(buffer, procfs_buffer, procfs_buffer_size))
-36 return -EFAULT;
+35 if (copy_to_user(buffer, procfs_buffer, procfs_buffer_size))
+36 return -EFAULT;
37
-38 pr_debug("procfs_read: read %lu bytes\n", procfs_buffer_size);
-39 return procfs_buffer_size;
+38 pr_debug("procfs_read: read %lu bytes\n", procfs_buffer_size);
+39 return procfs_buffer_size;
40}
-41static ssize_t procfs_write(struct file *file, const char __user *buffer,
-42 size_t len, loff_t *off)
+41static ssize_t procfs_write(struct file *file, const char __user *buffer,
+42 size_t len, loff_t *off)
43{
-44 if (len > PROCFS_MAX_SIZE)
+44 if (len > PROCFS_MAX_SIZE)
45 procfs_buffer_size = PROCFS_MAX_SIZE;
-46 else
+46 else
47 procfs_buffer_size = len;
-48 if (copy_from_user(procfs_buffer, buffer, procfs_buffer_size))
-49 return -EFAULT;
+48 if (copy_from_user(procfs_buffer, buffer, procfs_buffer_size))
+49 return -EFAULT;
50
-51 pr_debug("procfs_write: write %lu bytes\n", procfs_buffer_size);
-52 return procfs_buffer_size;
+51 pr_debug("procfs_write: write %lu bytes\n", procfs_buffer_size);
+52 return procfs_buffer_size;
53}
-54static int procfs_open(struct inode *inode, struct file *file)
+54static int procfs_open(struct inode *inode, struct file *file)
55{
56 try_module_get(THIS_MODULE);
-57 return 0;
+57 return 0;
58}
-59static int procfs_close(struct inode *inode, struct file *file)
+59static int procfs_close(struct inode *inode, struct file *file)
60{
61 module_put(THIS_MODULE);
-62 return 0;
+62 return 0;
63}
64
-65#ifdef HAVE_PROC_OPS
-66static struct proc_ops file_ops_4_our_proc_file = {
+65#ifdef HAVE_PROC_OPS
+66static struct proc_ops file_ops_4_our_proc_file = {
67 .proc_read = procfs_read,
68 .proc_write = procfs_write,
69 .proc_open = procfs_open,
70 .proc_release = procfs_close,
71};
-72#else
-73static const struct file_operations file_ops_4_our_proc_file = {
+72#else
+73static const struct file_operations file_ops_4_our_proc_file = {
74 .read = procfs_read,
75 .write = procfs_write,
76 .open = procfs_open,
77 .release = procfs_close,
78};
-79#endif
+79#endif
80
-81static int __init procfs3_init(void)
+81static int __init procfs3_init(void)
82{
83 our_proc_file = proc_create(PROCFS_ENTRY_FILENAME, 0644, NULL,
84 &file_ops_4_our_proc_file);
-85 if (our_proc_file == NULL) {
+85 if (our_proc_file == NULL) {
86 remove_proc_entry(PROCFS_ENTRY_FILENAME, NULL);
-87 pr_debug("Error: Could not initialize /proc/%s\n",
+87 pr_debug("Error: Could not initialize /proc/%s\n",
88 PROCFS_ENTRY_FILENAME);
-89 return -ENOMEM;
+89 return -ENOMEM;
90 }
91 proc_set_size(our_proc_file, 80);
92 proc_set_user(our_proc_file, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID);
93
-94 pr_debug("/proc/%s created\n", PROCFS_ENTRY_FILENAME);
-95 return 0;
+94 pr_debug("/proc/%s created\n", PROCFS_ENTRY_FILENAME);
+95 return 0;
96}
97
-98static void __exit procfs3_exit(void)
+98static void __exit procfs3_exit(void)
99{
100 remove_proc_entry(PROCFS_ENTRY_FILENAME, NULL);
-101 pr_debug("/proc/%s removed\n", PROCFS_ENTRY_FILENAME);
+101 pr_debug("/proc/%s removed\n", PROCFS_ENTRY_FILENAME);
102}
103
104module_init(procfs3_init);
105module_exit(procfs3_exit);
106
-107MODULE_LICENSE("GPL");
-7.4 Manage /proc file with seq_file
- seq_file
that helps formating a /proc file for output. It is based on sequence, which is composed of
@@ -2078,7 +2121,7 @@ So to help people writting , and stop()
. The seq_file
API starts a sequence when a user read the /proc file.
- start()
. If the return is a non NULL
value, the function next()
@@ -2095,7 +2138,7 @@ time next()
returns NULL
, then the function stop()
is called.
- stop()
, the function start()
is called again. This loop finishes when the function
@@ -2112,257 +2155,257 @@ of function stop()
- exported.
+
seq_file
+ will still try to call seq_file
provides basic functions for proc_ops
, such as seq_read
, seq_lseek
, and some others. But nothing to write in the /proc file. Of course, you can still use
the same way as in the previous example.
1/*
-2 * procfs4.c - create a "file" in /proc
-3 * This program uses the seq_file library to manage the /proc file.
-4 */
+
+1/*
+2 * procfs4.c - create a "file" in /proc
+3 * This program uses the seq_file library to manage the /proc file.
+4 */
5
-6#include <linux/kernel.h> /* We are doing kernel work */
-7#include <linux/module.h> /* Specifically, a module */
-8#include <linux/proc_fs.h> /* Necessary because we use proc fs */
-9#include <linux/seq_file.h> /* for seq_file */
-10#include <linux/version.h>
+6#include <linux/kernel.h> /* We are doing kernel work */
+7#include <linux/module.h> /* Specifically, a module */
+8#include <linux/proc_fs.h> /* Necessary because we use proc fs */
+9#include <linux/seq_file.h> /* for seq_file */
+10#include <linux/version.h>
11
-12#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0)
-13#define HAVE_PROC_OPS
-14#endif
+12#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0)
+13#define HAVE_PROC_OPS
+14#endif
15
-16#define PROC_NAME "iter"
+16#define PROC_NAME "iter"
17
-18/* This function is called at the beginning of a sequence.
-19 * ie, when:
-20 * - the /proc file is read (first time)
-21 * - after the function stop (end of sequence)
-22 */
-23static void *my_seq_start(struct seq_file *s, loff_t *pos)
+18/* This function is called at the beginning of a sequence.
+19 * ie, when:
+20 * - the /proc file is read (first time)
+21 * - after the function stop (end of sequence)
+22 */
+23static void *my_seq_start(struct seq_file *s, loff_t *pos)
24{
-25 static unsigned long counter = 0;
+25 static unsigned long counter = 0;
26
-27 /* beginning a new sequence? */
-28 if (*pos == 0) {
-29 /* yes => return a non null value to begin the sequence */
-30 return &counter;
+27 /* beginning a new sequence? */
+28 if (*pos == 0) {
+29 /* yes => return a non null value to begin the sequence */
+30 return &counter;
31 }
32
-33 /* no => it is the end of the sequence, return end to stop reading */
+33 /* no => it is the end of the sequence, return end to stop reading */
34 *pos = 0;
-35 return NULL;
+35 return NULL;
36}
37
-38/* This function is called after the beginning of a sequence.
-39 * It is called untill the return is NULL (this ends the sequence).
-40 */
-41static void *my_seq_next(struct seq_file *s, void *v, loff_t *pos)
+38/* This function is called after the beginning of a sequence.
+39 * It is called untill the return is NULL (this ends the sequence).
+40 */
+41static void *my_seq_next(struct seq_file *s, void *v, loff_t *pos)
42{
-43 unsigned long *tmp_v = (unsigned long *)v;
+43 unsigned long *tmp_v = (unsigned long *)v;
44 (*tmp_v)++;
45 (*pos)++;
-46 return NULL;
+46 return NULL;
47}
48
-49/* This function is called at the end of a sequence. */
-50static void my_seq_stop(struct seq_file *s, void *v)
+49/* This function is called at the end of a sequence. */
+50static void my_seq_stop(struct seq_file *s, void *v)
51{
-52 /* nothing to do, we use a static value in start() */
+52 /* nothing to do, we use a static value in start() */
53}
54
-55/* This function is called for each "step" of a sequence. */
-56static int my_seq_show(struct seq_file *s, void *v)
+55/* This function is called for each "step" of a sequence. */
+56static int my_seq_show(struct seq_file *s, void *v)
57{
58 loff_t *spos = (loff_t *)v;
59
-60 seq_printf(s, "%Ld\n", *spos);
-61 return 0;
+60 seq_printf(s, "%Ld\n", *spos);
+61 return 0;
62}
63
-64/* This structure gather "function" to manage the sequence */
-65static struct seq_operations my_seq_ops = {
+64/* This structure gather "function" to manage the sequence */
+65static struct seq_operations my_seq_ops = {
66 .start = my_seq_start,
67 .next = my_seq_next,
68 .stop = my_seq_stop,
69 .show = my_seq_show,
70};
71
-72/* This function is called when the /proc file is open. */
-73static int my_open(struct inode *inode, struct file *file)
+72/* This function is called when the /proc file is open. */
+73static int my_open(struct inode *inode, struct file *file)
74{
-75 return seq_open(file, &my_seq_ops);
+75 return seq_open(file, &my_seq_ops);
76};
77
-78/* This structure gather "function" that manage the /proc file */
-79#ifdef HAVE_PROC_OPS
-80static const struct proc_ops my_file_ops = {
+78/* This structure gather "function" that manage the /proc file */
+79#ifdef HAVE_PROC_OPS
+80static const struct proc_ops my_file_ops = {
81 .proc_open = my_open,
82 .proc_read = seq_read,
83 .proc_lseek = seq_lseek,
84 .proc_release = seq_release,
85};
-86#else
-87static const struct file_operations my_file_ops = {
+86#else
+87static const struct file_operations my_file_ops = {
88 .open = my_open,
89 .read = seq_read,
90 .llseek = seq_lseek,
91 .release = seq_release,
92};
-93#endif
+93#endif
94
-95static int __init procfs4_init(void)
+95static int __init procfs4_init(void)
96{
-97 struct proc_dir_entry *entry;
+97 struct proc_dir_entry *entry;
98
99 entry = proc_create(PROC_NAME, 0, NULL, &my_file_ops);
-100 if (entry == NULL) {
+100 if (entry == NULL) {
101 remove_proc_entry(PROC_NAME, NULL);
-102 pr_debug("Error: Could not initialize /proc/%s\n", PROC_NAME);
-103 return -ENOMEM;
+102 pr_debug("Error: Could not initialize /proc/%s\n", PROC_NAME);
+103 return -ENOMEM;
104 }
105
-106 return 0;
+106 return 0;
107}
108
-109static void __exit procfs4_exit(void)
+109static void __exit procfs4_exit(void)
110{
111 remove_proc_entry(PROC_NAME, NULL);
-112 pr_debug("/proc/%s removed\n", PROC_NAME);
+112 pr_debug("/proc/%s removed\n", PROC_NAME);
113}
114
115module_init(procfs4_init);
116module_exit(procfs4_exit);
117
-118MODULE_LICENSE("GPL");
-8 sysfs: Interacting with your module
-1ls -l /sys
-1ls -l /sys
+1/*
-2 * hello-sysfs.c sysfs example
-3 */
-4#include <linux/fs.h>
-5#include <linux/init.h>
-6#include <linux/kobject.h>
-7#include <linux/module.h>
-8#include <linux/string.h>
-9#include <linux/sysfs.h>
+
+1/*
+2 * hello-sysfs.c sysfs example
+3 */
+4#include <linux/fs.h>
+5#include <linux/init.h>
+6#include <linux/kobject.h>
+7#include <linux/module.h>
+8#include <linux/string.h>
+9#include <linux/sysfs.h>
10
-11static struct kobject *mymodule;
+11static struct kobject *mymodule;
12
-13/* the variable you want to be able to change */
-14static int myvariable = 0;
+13/* the variable you want to be able to change */
+14static int myvariable = 0;
15
-16static ssize_t myvariable_show(struct kobject *kobj,
-17 struct kobj_attribute *attr, char *buf)
+16static ssize_t myvariable_show(struct kobject *kobj,
+17 struct kobj_attribute *attr, char *buf)
18{
-19 return sprintf(buf, "%d\n", myvariable);
+19 return sprintf(buf, "%d\n", myvariable);
20}
21
-22static ssize_t myvariable_store(struct kobject *kobj,
-23 struct kobj_attribute *attr, char *buf,
-24 size_t count)
+22static ssize_t myvariable_store(struct kobject *kobj,
+23 struct kobj_attribute *attr, char *buf,
+24 size_t count)
25{
-26 sscanf(buf, "%du", &myvariable);
-27 return count;
+26 sscanf(buf, "%du", &myvariable);
+27 return count;
28}
29
-30static struct kobj_attribute myvariable_attribute =
-31 __ATTR(myvariable, 0660, myvariable_show, (void *)myvariable_store);
+30static struct kobj_attribute myvariable_attribute =
+31 __ATTR(myvariable, 0660, myvariable_show, (void *)myvariable_store);
32
-33static int __init mymodule_init(void)
+33static int __init mymodule_init(void)
34{
-35 int error = 0;
+35 int error = 0;
36
-37 pr_info("mymodule: initialised\n");
+37 pr_info("mymodule: initialised\n");
38
-39 mymodule = kobject_create_and_add("mymodule", kernel_kobj);
-40 if (!mymodule)
-41 return -ENOMEM;
+39 mymodule = kobject_create_and_add("mymodule", kernel_kobj);
+40 if (!mymodule)
+41 return -ENOMEM;
42
43 error = sysfs_create_file(mymodule, &myvariable_attribute.attr);
-44 if (error) {
-45 pr_info("failed to create the myvariable file "
-46 "in /sys/kernel/mymodule\n");
+44 if (error) {
+45 pr_info("failed to create the myvariable file "
+46 "in /sys/kernel/mymodule\n");
47 }
48
-49 return error;
+49 return error;
50}
51
-52static void __exit mymodule_exit(void)
+52static void __exit mymodule_exit(void)
53{
-54 pr_info("mymodule: Exit success\n");
+54 pr_info("mymodule: Exit success\n");
55 kobject_put(mymodule);
56}
57
58module_init(mymodule_init);
59module_exit(mymodule_exit);
60
-61MODULE_LICENSE("GPL");
-1make
+
-1make
2sudo insmod hello-sysfs.ko
-1sudo lsmod | grep hello_sysfs
- myvariable
+ 1sudo lsmod | grep hello_sysfs
+ myvariable
?
1cat /sys/kernel/mymodule/myvariable
- myvariable
+ right before you do the 1cat /sys/kernel/mymodule/myvariable
+ myvariable
and check that it changed.
1echo "32" > /sys/kernel/mymodule/myvariable
+
1echo "32" > /sys/kernel/mymodule/myvariable
2cat /sys/kernel/mymodule/myvariable
-1sudo rmmod hello_sysfs
-1sudo rmmod hello_sysfs
+9 Talking To Device Files
- device_write
.
- ioctl
(short for Input Output ConTroL). Every device can have its own
ioctl
@@ -2384,12 +2427,12 @@ kernel), write ioctl’s (to return information to a process), both or neither.
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.
- _IO
, _IOR
@@ -2400,436 +2443,436 @@ 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.
-1/*
-2 * chardev2.c - Create an input/output character device
-3 */
+
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>
+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
+15#include "chardev.h"
+16#define SUCCESS 0
+17#define DEVICE_NAME "char_dev"
+18#define BUF_LEN 80
19
-20enum {
+20enum {
21 CDEV_NOT_USED = 0,
22 CDEV_EXCLUSIVE_OPEN = 1,
23};
24
-25/* Is the device open right now? Used to prevent concurrent access into
-26 * the same device
-27 */
-28static atomic_t already_open = ATOMIC_INIT(CDEV_NOT_USED);
+25/* Is the device open right now? Used to prevent concurrent access into
+26 * the same device
+27 */
+28static atomic_t already_open = ATOMIC_INIT(CDEV_NOT_USED);
29
-30/* The message the device will give when asked */
-31static char message[BUF_LEN];
+30/* The message the device will give when asked */
+31static char message[BUF_LEN];
32
-33static struct class *cls;
+33static struct class *cls;
34
-35/* This is called whenever a process attempts to open the device file */
-36static int device_open(struct inode *inode, struct file *file)
+35/* This is called whenever a process attempts to open the device file */
+36static int device_open(struct inode *inode, struct file *file)
37{
-38 pr_info("device_open(%p)\n", file);
+38 pr_info("device_open(%p)\n", file);
39
-40 /* We don't want to talk to two processes at the same time. */
-41 if (atomic_cmpxchg(&already_open, CDEV_NOT_USED, CDEV_EXCLUSIVE_OPEN))
-42 return -EBUSY;
+40 /* We don't want to talk to two processes at the same time. */
+41 if (atomic_cmpxchg(&already_open, CDEV_NOT_USED, CDEV_EXCLUSIVE_OPEN))
+42 return -EBUSY;
43
44 try_module_get(THIS_MODULE);
-45 return SUCCESS;
+45 return SUCCESS;
46}
47
-48static int device_release(struct inode *inode, struct file *file)
+48static int device_release(struct inode *inode, struct file *file)
49{
-50 pr_info("device_release(%p,%p)\n", inode, file);
+50 pr_info("device_release(%p,%p)\n", inode, file);
51
-52 /* We're now ready for our next caller */
+52 /* We're now ready for our next caller */
53 atomic_set(&already_open, CDEV_NOT_USED);
54
55 module_put(THIS_MODULE);
-56 return SUCCESS;
+56 return SUCCESS;
57}
58
-59/* This function is called whenever a process which has already opened the
-60 * device file attempts to read from it.
-61 */
-62static ssize_t device_read(struct file *file, /* see include/linux/fs.h */
-63 char __user *buffer, /* buffer to be filled */
-64 size_t length, /* length of the buffer */
+59/* This function is called whenever a process which has already opened the
+60 * device file attempts to read from it.
+61 */
+62static ssize_t device_read(struct file *file, /* see include/linux/fs.h */
+63 char __user *buffer, /* buffer to be filled */
+64 size_t length, /* length of the buffer */
65 loff_t *offset)
66{
-67 /* Number of bytes actually written to the buffer */
-68 int bytes_read = 0;
-69 /* How far did the process reading the message get? Useful if the message
-70 * is larger than the size of the buffer we get to fill in device_read.
-71 */
-72 const char *message_ptr = message;
+67 /* Number of bytes actually written to the buffer */
+68 int bytes_read = 0;
+69 /* How far did the process reading the message get? Useful if the message
+70 * is larger than the size of the buffer we get to fill in device_read.
+71 */
+72 const char *message_ptr = message;
73
-74 if (!*(message_ptr + *offset)) { /* we are at the end of message */
-75 *offset = 0; /* reset the offset */
-76 return 0; /* signify end of file */
+74 if (!*(message_ptr + *offset)) { /* we are at the end of message */
+75 *offset = 0; /* reset the offset */
+76 return 0; /* signify end of file */
77 }
78
79 message_ptr += *offset;
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 */
+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);
+93 pr_info("Read %d bytes, %ld left\n", bytes_read, length);
94
95 *offset += bytes_read;
96
-97 /* Read functions are supposed to return the number of bytes actually
-98 * inserted into the buffer.
-99 */
-100 return bytes_read;
+97 /* Read functions are supposed to return the number of bytes actually
+98 * inserted into the buffer.
+99 */
+100 return bytes_read;
101}
102
-103/* called when somebody tries to write into our device file. */
-104static ssize_t device_write(struct file *file, const char __user *buffer,
-105 size_t length, loff_t *offset)
+103/* called when somebody tries to write into our device file. */
+104static ssize_t device_write(struct file *file, const char __user *buffer,
+105 size_t length, loff_t *offset)
106{
-107 int i;
+107 int i;
108
-109 pr_info("device_write(%p,%p,%ld)", file, buffer, length);
+109 pr_info("device_write(%p,%p,%ld)", file, buffer, length);
110
-111 for (i = 0; i < length && i < BUF_LEN; i++)
+111 for (i = 0; i < length && i < BUF_LEN; i++)
112 get_user(message[i], buffer + i);
113
-114 /* Again, return the number of input characters used. */
-115 return i;
+114 /* Again, return the number of input characters used. */
+115 return i;
116}
117
-118/* This function is called whenever a process tries to do an ioctl on our
-119 * device file. We get two extra parameters (additional to the inode and file
-120 * structures, which all device functions get): the number of the ioctl called
-121 * and the parameter given to the ioctl function.
-122 *
-123 * If the ioctl is write or read/write (meaning output is returned to the
-124 * calling process), the ioctl call returns the output of this function.
-125 */
-126static long
-127device_ioctl(struct file *file, /* ditto */
-128 unsigned int ioctl_num, /* number and param for ioctl */
-129 unsigned long ioctl_param)
+118/* This function is called whenever a process tries to do an ioctl on our
+119 * device file. We get two extra parameters (additional to the inode and file
+120 * structures, which all device functions get): the number of the ioctl called
+121 * and the parameter given to the ioctl function.
+122 *
+123 * If the ioctl is write or read/write (meaning output is returned to the
+124 * calling process), the ioctl call returns the output of this function.
+125 */
+126static long
+127device_ioctl(struct file *file, /* ditto */
+128 unsigned int ioctl_num, /* number and param for ioctl */
+129 unsigned long ioctl_param)
130{
-131 int i;
+131 int i;
132
-133 /* Switch according to the ioctl called */
-134 switch (ioctl_num) {
-135 case IOCTL_SET_MSG: {
-136 /* Receive a pointer to a message (in user space) and set that to
-137 * be the device's message. Get the parameter given to ioctl by
-138 * the process.
-139 */
-140 char __user *tmp = (char __user *)ioctl_param;
-141 char ch;
+133 /* Switch according to the ioctl called */
+134 switch (ioctl_num) {
+135 case IOCTL_SET_MSG: {
+136 /* Receive a pointer to a message (in user space) and set that to
+137 * be the device's message. Get the parameter given to ioctl by
+138 * the process.
+139 */
+140 char __user *tmp = (char __user *)ioctl_param;
+141 char ch;
142
-143 /* Find the length of the message */
+143 /* Find the length of the message */
144 get_user(ch, tmp);
-145 for (i = 0; ch && i < BUF_LEN; i++, tmp++)
+145 for (i = 0; ch && i < BUF_LEN; i++, tmp++)
146 get_user(ch, tmp);
147
-148 device_write(file, (char __user *)ioctl_param, i, NULL);
-149 break;
+148 device_write(file, (char __user *)ioctl_param, i, NULL);
+149 break;
150 }
-151 case IOCTL_GET_MSG: {
+151 case IOCTL_GET_MSG: {
152 loff_t offset = 0;
153
-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 __user *)ioctl_param, 99, &offset);
+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 __user *)ioctl_param, 99, &offset);
158
-159 /* Put a zero at the end of the buffer, so it will be properly
-160 * terminated.
-161 */
-162 put_user('\0', (char __user *)ioctl_param + i);
-163 break;
+159 /* Put a zero at the end of the buffer, so it will be properly
+160 * terminated.
+161 */
+162 put_user('\0', (char __user *)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 (long)message[ioctl_param];
-170 break;
+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 (long)message[ioctl_param];
+170 break;
171 }
172
-173 return SUCCESS;
+173 return SUCCESS;
174}
175
-176/* Module Declarations */
+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 */
-183static struct file_operations fops = {
+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 */
+183static struct 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 */
+188 .release = device_release, /* a.k.a. close */
189};
190
-191/* Initialize the module - Register the character device */
-192static int __init chardev2_init(void)
+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);
+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;
+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 cls = class_create(THIS_MODULE, DEVICE_FILE_NAME);
205 device_create(cls, NULL, MKDEV(MAJOR_NUM, 0), NULL, DEVICE_FILE_NAME);
206
-207 pr_info("Device created on /dev/%s\n", DEVICE_FILE_NAME);
+207 pr_info("Device created on /dev/%s\n", DEVICE_FILE_NAME);
208
-209 return 0;
+209 return 0;
210}
211
-212/* Cleanup - unregister the appropriate file from /proc */
-213static void __exit chardev2_exit(void)
+212/* Cleanup - unregister the appropriate file from /proc */
+213static void __exit chardev2_exit(void)
214{
215 device_destroy(cls, MKDEV(MAJOR_NUM, 0));
216 class_destroy(cls);
217
-218 /* Unregister the device */
+218 /* Unregister the device */
219 unregister_chrdev(MAJOR_NUM, DEVICE_NAME);
220}
221
222module_init(chardev2_init);
223module_exit(chardev2_exit);
224
-225MODULE_LICENSE("GPL");
+225MODULE_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 */
+
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
+9#ifndef CHARDEV_H
+10#define CHARDEV_H
11
-12#include <linux/ioctl.h>
+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
+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 */
+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 */
+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 */
+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"
+46/* The name of the device file */
+47#define DEVICE_FILE_NAME "char_dev"
48
-49#endif
+49#endif1/*
-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>
+
-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 val;
+12struct ioctl_arg {
+13 unsigned int val;
14};
15
-16/* Documentation/ioctl/ioctl-number.txt */
-17#define IOC_MAGIC '\x66'
+16/* Documentation/ioctl/ioctl-number.txt */
+17#define IOC_MAGIC '\x66'
18
-19#define IOCTL_VALSET _IOW(IOC_MAGIC, 0, struct ioctl_arg)
-20#define IOCTL_VALGET _IOR(IOC_MAGIC, 1, struct ioctl_arg)
-21#define IOCTL_VALGET_NUM _IOR(IOC_MAGIC, 2, int)
-22#define IOCTL_VALSET_NUM _IOW(IOC_MAGIC, 3, int)
+19#define IOCTL_VALSET _IOW(IOC_MAGIC, 0, struct ioctl_arg)
+20#define IOCTL_VALGET _IOR(IOC_MAGIC, 1, struct ioctl_arg)
+21#define IOCTL_VALGET_NUM _IOR(IOC_MAGIC, 2, int)
+22#define IOCTL_VALSET_NUM _IOW(IOC_MAGIC, 3, int)
23
-24#define IOCTL_VAL_MAXNR 3
-25#define DRIVER_NAME "ioctltest"
+24#define IOCTL_VAL_MAXNR 3
+25#define DRIVER_NAME "ioctltest"
26
-27static unsigned int test_ioctl_major = 0;
-28static unsigned int num_of_dev = 1;
-29static struct cdev test_ioctl_cdev;
-30static int ioctl_num = 0;
+27static unsigned int test_ioctl_major = 0;
+28static unsigned int num_of_dev = 1;
+29static struct cdev test_ioctl_cdev;
+30static int ioctl_num = 0;
31
-32struct test_ioctl_data {
-33 unsigned char val;
+32struct test_ioctl_data {
+33 unsigned char val;
34 rwlock_t lock;
35};
36
-37static long test_ioctl_ioctl(struct file *filp, unsigned int cmd,
-38 unsigned long arg)
+37static long test_ioctl_ioctl(struct file *filp, unsigned int cmd,
+38 unsigned long arg)
39{
-40 struct test_ioctl_data *ioctl_data = filp->private_data;
-41 int retval = 0;
-42 unsigned char val;
-43 struct ioctl_arg data;
-44 memset(&data, 0, sizeof(data));
+40 struct test_ioctl_data *ioctl_data = filp->private_data;
+41 int retval = 0;
+42 unsigned char val;
+43 struct ioctl_arg data;
+44 memset(&data, 0, sizeof(data));
45
-46 switch (cmd) {
-47 case IOCTL_VALSET:
-48 if (copy_from_user(&data, (int __user *)arg, sizeof(data))) {
+46 switch (cmd) {
+47 case IOCTL_VALSET:
+48 if (copy_from_user(&data, (int __user *)arg, sizeof(data))) {
49 retval = -EFAULT;
-50 goto done;
+50 goto done;
51 }
52
-53 pr_alert("IOCTL set val:%x .\n", data.val);
+53 pr_alert("IOCTL set val:%x .\n", data.val);
54 write_lock(&ioctl_data->lock);
55 ioctl_data->val = data.val;
56 write_unlock(&ioctl_data->lock);
-57 break;
+57 break;
58
-59 case IOCTL_VALGET:
+59 case IOCTL_VALGET:
60 read_lock(&ioctl_data->lock);
61 val = ioctl_data->val;
62 read_unlock(&ioctl_data->lock);
63 data.val = val;
64
-65 if (copy_to_user((int __user *)arg, &data, sizeof(data))) {
+65 if (copy_to_user((int __user *)arg, &data, sizeof(data))) {
66 retval = -EFAULT;
-67 goto done;
+67 goto done;
68 }
69
-70 break;
+70 break;
71
-72 case IOCTL_VALGET_NUM:
-73 retval = __put_user(ioctl_num, (int __user *)arg);
-74 break;
+72 case IOCTL_VALGET_NUM:
+73 retval = __put_user(ioctl_num, (int __user *)arg);
+74 break;
75
-76 case IOCTL_VALSET_NUM:
+76 case IOCTL_VALSET_NUM:
77 ioctl_num = arg;
-78 break;
+78 break;
79
-80 default:
+80 default:
81 retval = -ENOTTY;
82 }
83
84done:
-85 return retval;
+85 return retval;
86}
87
-88static ssize_t test_ioctl_read(struct file *filp, char __user *buf,
-89 size_t count, loff_t *f_pos)
+88static ssize_t test_ioctl_read(struct file *filp, char __user *buf,
+89 size_t count, loff_t *f_pos)
90{
-91 struct test_ioctl_data *ioctl_data = filp->private_data;
-92 unsigned char val;
-93 int retval;
-94 int i = 0;
+91 struct test_ioctl_data *ioctl_data = filp->private_data;
+92 unsigned char val;
+93 int retval;
+94 int i = 0;
95
96 read_lock(&ioctl_data->lock);
97 val = ioctl_data->val;
98 read_unlock(&ioctl_data->lock);
99
-100 for (; i < count; i++) {
-101 if (copy_to_user(&buf[i], &val, 1)) {
+100 for (; i < count; i++) {
+101 if (copy_to_user(&buf[i], &val, 1)) {
102 retval = -EFAULT;
-103 goto out;
+103 goto out;
104 }
105 }
106
107 retval = count;
108out:
-109 return retval;
+109 return retval;
110}
111
-112static int test_ioctl_close(struct inode *inode, struct file *filp)
+112static int test_ioctl_close(struct inode *inode, struct file *filp)
113{
-114 pr_alert("%s call.\n", __func__);
+114 pr_alert("%s call.\n", __func__);
115
-116 if (filp->private_data) {
+116 if (filp->private_data) {
117 kfree(filp->private_data);
118 filp->private_data = NULL;
119 }
120
-121 return 0;
+121 return 0;
122}
123
-124static int test_ioctl_open(struct inode *inode, struct file *filp)
+124static int test_ioctl_open(struct inode *inode, struct file *filp)
125{
-126 struct test_ioctl_data *ioctl_data;
+126 struct test_ioctl_data *ioctl_data;
127
-128 pr_alert("%s call.\n", __func__);
-129 ioctl_data = kmalloc(sizeof(struct test_ioctl_data), GFP_KERNEL);
+128 pr_alert("%s call.\n", __func__);
+129 ioctl_data = kmalloc(sizeof(struct test_ioctl_data), GFP_KERNEL);
130
-131 if (ioctl_data == NULL)
-132 return -ENOMEM;
+131 if (ioctl_data == NULL)
+132 return -ENOMEM;
133
134 rwlock_init(&ioctl_data->lock);
135 ioctl_data->val = 0xFF;
136 filp->private_data = ioctl_data;
137
-138 return 0;
+138 return 0;
139}
140
-141static struct file_operations fops = {
+141static struct file_operations fops = {
142 .owner = THIS_MODULE,
143 .open = test_ioctl_open,
144 .release = test_ioctl_close,
@@ -2837,60 +2880,60 @@ which we mentioned at 6.5
146 .unlocked_ioctl = test_ioctl_ioctl,
147};
148
-149static int ioctl_init(void)
+149static int ioctl_init(void)
150{
-151 dev_t dev;
-152 int alloc_ret = 0;
-153 int cdev_ret = 0;
+151 dev_t dev;
+152 int alloc_ret = 0;
+153 int cdev_ret = 0;
154 alloc_ret = alloc_chrdev_region(&dev, 0, num_of_dev, DRIVER_NAME);
155
-156 if (alloc_ret)
-157 goto error;
+156 if (alloc_ret)
+157 goto error;
158
159 test_ioctl_major = MAJOR(dev);
160 cdev_init(&test_ioctl_cdev, &fops);
161 cdev_ret = cdev_add(&test_ioctl_cdev, dev, num_of_dev);
162
-163 if (cdev_ret)
-164 goto error;
+163 if (cdev_ret)
+164 goto error;
165
-166 pr_alert("%s driver(major: %d) installed.\n", DRIVER_NAME,
+166 pr_alert("%s driver(major: %d) installed.\n", DRIVER_NAME,
167 test_ioctl_major);
-168 return 0;
+168 return 0;
169error:
-170 if (cdev_ret == 0)
+170 if (cdev_ret == 0)
171 cdev_del(&test_ioctl_cdev);
-172 if (alloc_ret == 0)
+172 if (alloc_ret == 0)
173 unregister_chrdev_region(dev, num_of_dev);
-174 return -1;
+174 return -1;
175}
176
-177static void ioctl_exit(void)
+177static void ioctl_exit(void)
178{
-179 dev_t dev = MKDEV(test_ioctl_major, 0);
+179 dev_t dev = MKDEV(test_ioctl_major, 0);
180
181 cdev_del(&test_ioctl_cdev);
182 unregister_chrdev_region(dev, num_of_dev);
-183 pr_alert("%s driver removed.\n", DRIVER_NAME);
+183 pr_alert("%s driver removed.\n", DRIVER_NAME);
184}
185
186module_init(ioctl_init);
187module_exit(ioctl_exit);
188
-189MODULE_LICENSE("GPL");
-190MODULE_DESCRIPTION("This is test_ioctl module");
+189MODULE_LICENSE("GPL");
+190MODULE_DESCRIPTION("This is test_ioctl module");10 System Calls
- open()
system call. This meant I could not open any files, I could not run any
@@ -2902,7 +2945,7 @@ ensure you do not lose any files, even within a test environment, please run
insmod
and the rmmod
.
- strace <arguments>
.
- sys_call_table
@@ -2936,7 +2979,7 @@ 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)
.
- sys_call_table
@@ -2944,7 +2987,7 @@ 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.
- sys_call_table
+ sys_call_table
, we need to consider the control register. A control register is a processor
register that changes or controls the general behavior of the CPU. For x86
architecture, the cr0 register has various control flags that modify the basic
@@ -2957,11 +3000,11 @@ read-only sections Therefore, we must disable the sys_call_table
+ sys_call_table
symbol is unexported to prevent misuse. But there have few ways to get the symbol, manual
symbol lookup and kallsyms_lookup_name
. Here we use both depend on the kernel version.
- kallsyms_lookup_name
+ kallsyms_lookup_name
is also unexported, it needs certain trick to get the address of
kallsyms_lookup_name
. If CONFIG_KPROBES
@@ -3001,7 +3044,7 @@ passes the addresses of the saved registers and the Kprobe struct to the handler
you defined, then executes it. Kprobes can be registered by symbol name
or address. Within the symbol name, the address will be handled by the
kernel.
- sys_call_table
+ sys_call_table
from /proc/kallsyms and /boot/System.map into
sym
parameter. Following is the sample usage for /proc/kallsyms:
@@ -3016,8 +3059,8 @@ ffffffff820013a0 R sys_call_table
ffffffff820023e0 R ia32_sys_call_table
$ sudo insmod syscall.ko sym=0xffffffff820013a0
-
- 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
@@ -3090,7 +3133,7 @@ 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.
- init_module
+ init_module
function replaces the appropriate location in
sys_call_table
and keeps the original pointer in a variable. The
@@ -3108,7 +3151,7 @@ with B_open
, which will call what it thinks is the original system call,
A_open
, when it’s done.
- 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,
@@ -3128,7 +3171,7 @@ problem. When A is removed, it sees that the system call was changed to
A_open
which is no longer there, so that even without removing B the system would
crash.
- sys_call_table
is no longer exported. This means, if you want to do something more than a mere
@@ -3140,226 +3183,226 @@ dry run of this example, you will have to patch your current kernel in order to
1/*
-2 * syscall.c
-3 *
-4 * System call "stealing" sample.
-5 *
-6 * Disables page protection at a processor level by changing the 16th bit
-7 * in the cr0 register (could be Intel specific).
-8 *
-9 * Based on example by Peter Jay Salzman and
-10 * https://bbs.archlinux.org/viewtopic.php?id=139406
-11 */
+
+1/*
+2 * syscall.c
+3 *
+4 * System call "stealing" sample.
+5 *
+6 * Disables page protection at a processor level by changing the 16th bit
+7 * in the cr0 register (could be Intel specific).
+8 *
+9 * Based on example by Peter Jay Salzman and
+10 * https://bbs.archlinux.org/viewtopic.php?id=139406
+11 */
12
-13#include <linux/delay.h>
-14#include <linux/kernel.h>
-15#include <linux/module.h>
-16#include <linux/moduleparam.h> /* which will have params */
-17#include <linux/unistd.h> /* The list of system calls */
-18#include <linux/version.h>
+13#include <linux/delay.h>
+14#include <linux/kernel.h>
+15#include <linux/module.h>
+16#include <linux/moduleparam.h> /* which will have params */
+17#include <linux/unistd.h> /* The list of system calls */
+18#include <linux/version.h>
19
-20/* For the current (process) structure, we need this to know who the
-21 * current user is.
-22 */
-23#include <linux/sched.h>
-24#include <linux/uaccess.h>
+20/* For the current (process) structure, we need this to know who the
+21 * current user is.
+22 */
+23#include <linux/sched.h>
+24#include <linux/uaccess.h>
25
-26/* The way we access "sys_call_table" varies as kernel internal changes.
-27 * - ver <= 5.4 : manual symbol lookup
-28 * - 5.4 < ver < 5.7 : kallsyms_lookup_name
-29 * - 5.7 <= ver : Kprobes or specific kernel module parameter
-30 */
+26/* The way we access "sys_call_table" varies as kernel internal changes.
+27 * - ver <= 5.4 : manual symbol lookup
+28 * - 5.4 < ver < 5.7 : kallsyms_lookup_name
+29 * - 5.7 <= ver : Kprobes or specific kernel module parameter
+30 */
31
-32/* The in-kernel calls to the ksys_close() syscall were removed in Linux v5.11+.
-33 */
-34#if (LINUX_VERSION_CODE < KERNEL_VERSION(5, 7, 0))
+32/* The in-kernel calls to the ksys_close() syscall were removed in Linux v5.11+.
+33 */
+34#if (LINUX_VERSION_CODE < KERNEL_VERSION(5, 7, 0))
35
-36#if LINUX_VERSION_CODE <= KERNEL_VERSION(5, 4, 0)
-37#define HAVE_KSYS_CLOSE 1
-38#include <linux/syscalls.h> /* For ksys_close() */
-39#else
-40#include <linux/kallsyms.h> /* For kallsyms_lookup_name */
-41#endif
+36#if LINUX_VERSION_CODE <= KERNEL_VERSION(5, 4, 0)
+37#define HAVE_KSYS_CLOSE 1
+38#include <linux/syscalls.h> /* For ksys_close() */
+39#else
+40#include <linux/kallsyms.h> /* For kallsyms_lookup_name */
+41#endif
42
-43#else
+43#else
44
-45#if defined(CONFIG_KPROBES)
-46#define HAVE_KPROBES 1
-47#include <linux/kprobes.h>
-48#else
-49#define HAVE_PARAM 1
-50#include <linux/kallsyms.h> /* For sprint_symbol */
-51/* The address of the sys_call_table, which can be obtained with looking up
-52 * "/boot/System.map" or "/proc/kallsyms". When the kernel version is v5.7+,
-53 * without CONFIG_KPROBES, you can input the parameter or the module will look
-54 * up all the memory.
-55 */
-56static unsigned long sym = 0;
+45#if defined(CONFIG_KPROBES)
+46#define HAVE_KPROBES 1
+47#include <linux/kprobes.h>
+48#else
+49#define HAVE_PARAM 1
+50#include <linux/kallsyms.h> /* For sprint_symbol */
+51/* The address of the sys_call_table, which can be obtained with looking up
+52 * "/boot/System.map" or "/proc/kallsyms". When the kernel version is v5.7+,
+53 * without CONFIG_KPROBES, you can input the parameter or the module will look
+54 * up all the memory.
+55 */
+56static unsigned long sym = 0;
57module_param(sym, ulong, 0644);
-58#endif /* CONFIG_KPROBES */
+58#endif /* CONFIG_KPROBES */
59
-60#endif /* Version < v5.7 */
+60#endif /* Version < v5.7 */
61
-62static unsigned long **sys_call_table;
+62static unsigned long **sys_call_table;
63
-64/* UID we want to spy on - will be filled from the command line. */
-65static int uid;
-66module_param(uid, int, 0644);
+64/* UID we want to spy on - will be filled from the command line. */
+65static int uid;
+66module_param(uid, int, 0644);
67
-68/* A pointer to the original system call. The reason we keep this, rather
-69 * than call the original function (sys_open), is because somebody else
-70 * might have replaced the system call before us. Note that this is not
-71 * 100% safe, because if another module replaced sys_open before us,
-72 * then when we are inserted, we will call the function in that module -
-73 * and it might be removed before we are.
-74 *
-75 * Another reason for this is that we can not get sys_open.
-76 * It is a static variable, so it is not exported.
-77 */
-78static asmlinkage int (*original_call)(const char *, int, int);
+68/* A pointer to the original system call. The reason we keep this, rather
+69 * than call the original function (sys_open), is because somebody else
+70 * might have replaced the system call before us. Note that this is not
+71 * 100% safe, because if another module replaced sys_open before us,
+72 * then when we are inserted, we will call the function in that module -
+73 * and it might be removed before we are.
+74 *
+75 * Another reason for this is that we can not get sys_open.
+76 * It is a static variable, so it is not exported.
+77 */
+78static asmlinkage int (*original_call)(const char *, int, int);
79
-80/* The function we will replace sys_open (the function called when you
-81 * call the open system call) with. To find the exact prototype, with
-82 * the number and type of arguments, we find the original function first
-83 * (it is at fs/open.c).
-84 *
-85 * In theory, this means that we are tied to the current version of the
-86 * kernel. In practice, the system calls almost never change (it would
-87 * wreck havoc and require programs to be recompiled, since the system
-88 * calls are the interface between the kernel and the processes).
-89 */
-90static asmlinkage int our_sys_open(const char *filename, int flags, int mode)
+80/* The function we will replace sys_open (the function called when you
+81 * call the open system call) with. To find the exact prototype, with
+82 * the number and type of arguments, we find the original function first
+83 * (it is at fs/open.c).
+84 *
+85 * In theory, this means that we are tied to the current version of the
+86 * kernel. In practice, the system calls almost never change (it would
+87 * wreck havoc and require programs to be recompiled, since the system
+88 * calls are the interface between the kernel and the processes).
+89 */
+90static asmlinkage int our_sys_open(const char *filename, int flags, int mode)
91{
-92 int i = 0;
-93 char ch;
+92 int i = 0;
+93 char ch;
94
-95 /* Report the file, if relevant */
-96 pr_info("Opened file by %d: ", uid);
-97 do {
-98 get_user(ch, (char __user *)filename + i);
+95 /* Report the file, if relevant */
+96 pr_info("Opened file by %d: ", uid);
+97 do {
+98 get_user(ch, (char __user *)filename + i);
99 i++;
-100 pr_info("%c", ch);
-101 } while (ch != 0);
-102 pr_info("\n");
+100 pr_info("%c", ch);
+101 } while (ch != 0);
+102 pr_info("\n");
103
-104 /* Call the original sys_open - otherwise, we lose the ability to
-105 * open files.
-106 */
-107 return original_call(filename, flags, mode);
+104 /* Call the original sys_open - otherwise, we lose the ability to
+105 * open files.
+106 */
+107 return original_call(filename, flags, mode);
108}
109
-110static unsigned long **aquire_sys_call_table(void)
+110static unsigned long **aquire_sys_call_table(void)
111{
-112#ifdef HAVE_KSYS_CLOSE
-113 unsigned long int offset = PAGE_OFFSET;
-114 unsigned long **sct;
+112#ifdef HAVE_KSYS_CLOSE
+113 unsigned long int offset = PAGE_OFFSET;
+114 unsigned long **sct;
115
-116 while (offset < ULLONG_MAX) {
-117 sct = (unsigned long **)offset;
+116 while (offset < ULLONG_MAX) {
+117 sct = (unsigned long **)offset;
118
-119 if (sct[__NR_close] == (unsigned long *)ksys_close)
-120 return sct;
+119 if (sct[__NR_close] == (unsigned long *)ksys_close)
+120 return sct;
121
-122 offset += sizeof(void *);
+122 offset += sizeof(void *);
123 }
124
-125 return NULL;
-126#endif
+125 return NULL;
+126#endif
127
-128#ifdef HAVE_PARAM
-129 const char sct_name[15] = "sys_call_table";
-130 char symbol[40] = { 0 };
+128#ifdef HAVE_PARAM
+129 const char sct_name[15] = "sys_call_table";
+130 char symbol[40] = { 0 };
131
-132 if (sym == 0) {
-133 pr_alert("For Linux v5.7+, Kprobes is the preferable way to get "
-134 "symbol.\n");
-135 pr_info("If Kprobes is absent, you have to specify the address of "
-136 "sys_call_table symbol\n");
-137 pr_info("by /boot/System.map or /proc/kallsyms, which contains all the "
-138 "symbol addresses, into sym parameter.\n");
-139 return NULL;
+132 if (sym == 0) {
+133 pr_alert("For Linux v5.7+, Kprobes is the preferable way to get "
+134 "symbol.\n");
+135 pr_info("If Kprobes is absent, you have to specify the address of "
+136 "sys_call_table symbol\n");
+137 pr_info("by /boot/System.map or /proc/kallsyms, which contains all the "
+138 "symbol addresses, into sym parameter.\n");
+139 return NULL;
140 }
141 sprint_symbol(symbol, sym);
-142 if (!strncmp(sct_name, symbol, sizeof(sct_name) - 1))
-143 return (unsigned long **)sym;
+142 if (!strncmp(sct_name, symbol, sizeof(sct_name) - 1))
+143 return (unsigned long **)sym;
144
-145 return NULL;
-146#endif
+145 return NULL;
+146#endif
147
-148#ifdef HAVE_KPROBES
-149 unsigned long (*kallsyms_lookup_name)(const char *name);
-150 struct kprobe kp = {
-151 .symbol_name = "kallsyms_lookup_name",
+148#ifdef HAVE_KPROBES
+149 unsigned long (*kallsyms_lookup_name)(const char *name);
+150 struct kprobe kp = {
+151 .symbol_name = "kallsyms_lookup_name",
152 };
153
-154 if (register_kprobe(&kp) < 0)
-155 return NULL;
-156 kallsyms_lookup_name = (unsigned long (*)(const char *name))kp.addr;
+154 if (register_kprobe(&kp) < 0)
+155 return NULL;
+156 kallsyms_lookup_name = (unsigned long (*)(const char *name))kp.addr;
157 unregister_kprobe(&kp);
-158#endif
+158#endif
159
-160 return (unsigned long **)kallsyms_lookup_name("sys_call_table");
+160 return (unsigned long **)kallsyms_lookup_name("sys_call_table");
161}
162
-163#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 3, 0)
-164static inline void __write_cr0(unsigned long cr0)
+163#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 3, 0)
+164static inline void __write_cr0(unsigned long cr0)
165{
-166 asm volatile("mov %0,%%cr0" : "+r"(cr0) : : "memory");
+166 asm volatile("mov %0,%%cr0" : "+r"(cr0) : : "memory");
167}
-168#else
-169#define __write_cr0 write_cr0
-170#endif
+168#else
+169#define __write_cr0 write_cr0
+170#endif
171
-172static void enable_write_protection(void)
+172static void enable_write_protection(void)
173{
-174 unsigned long cr0 = read_cr0();
+174 unsigned long cr0 = read_cr0();
175 set_bit(16, &cr0);
176 __write_cr0(cr0);
177}
178
-179static void disable_write_protection(void)
+179static void disable_write_protection(void)
180{
-181 unsigned long cr0 = read_cr0();
+181 unsigned long cr0 = read_cr0();
182 clear_bit(16, &cr0);
183 __write_cr0(cr0);
184}
185
-186static int __init syscall_start(void)
+186static int __init syscall_start(void)
187{
-188 if (!(sys_call_table = aquire_sys_call_table()))
-189 return -1;
+188 if (!(sys_call_table = aquire_sys_call_table()))
+189 return -1;
190
191 disable_write_protection();
192
-193 /* keep track of the original open function */
-194 original_call = (void *)sys_call_table[__NR_open];
+193 /* keep track of the original open function */
+194 original_call = (void *)sys_call_table[__NR_open];
195
-196 /* use our open function instead */
-197 sys_call_table[__NR_open] = (unsigned long *)our_sys_open;
+196 /* use our open function instead */
+197 sys_call_table[__NR_open] = (unsigned long *)our_sys_open;
198
199 enable_write_protection();
200
-201 pr_info("Spying on UID:%d\n", uid);
+201 pr_info("Spying on UID:%d\n", uid);
202
-203 return 0;
+203 return 0;
204}
205
-206static void __exit syscall_end(void)
+206static void __exit syscall_end(void)
207{
-208 if (!sys_call_table)
-209 return;
+208 if (!sys_call_table)
+209 return;
210
-211 /* Return the system call back to normal */
-212 if (sys_call_table[__NR_open] != (unsigned long *)our_sys_open) {
-213 pr_alert("Somebody else also played with the ");
-214 pr_alert("open system call\n");
-215 pr_alert("The system may be left in ");
-216 pr_alert("an unstable state.\n");
+211 /* Return the system call back to normal */
+212 if (sys_call_table[__NR_open] != (unsigned long *)our_sys_open) {
+213 pr_alert("Somebody else also played with the ");
+214 pr_alert("open system call\n");
+215 pr_alert("The system may be left in ");
+216 pr_alert("an unstable state.\n");
217 }
218
219 disable_write_protection();
-220 sys_call_table[__NR_open] = (unsigned long *)original_call;
+220 sys_call_table[__NR_open] = (unsigned long *)original_call;
221 enable_write_protection();
222
223 msleep(2000);
@@ -3368,14 +3411,14 @@ dry run of this example, you will have to patch your current kernel in order to
226module_init(syscall_start);
227module_exit(syscall_end);
228
-229MODULE_LICENSE("GPL");
-11 Blocking Processes and threads
-11.1 Sleep
- wait_event_interruptible
. The easiest way to keep a file open is to open it with:
1tail -f
-1tail -f
+ 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.
- 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
@@ -3410,31 +3453,31 @@ 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
.
- tail -f
+ 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.
- module_close
+ 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
. We could have used module_sleep_on
instead, but that would have resulted in extremely angry users whose Ctrl+c’s are
ignored.
- -EINTR
immediately. This is important so users can, for example, kill the process before it
receives the file.
- O_NONBLOCK
flag when opening the file. The kernel is supposed to respond by returning with the error
@@ -3470,449 +3513,449 @@ $ cat_nonblock /proc/sleep
Last input:
$
-1/*
-2 * sleep.c - create a /proc file, and if several processes try to open it
-3 * at the same time, put all but one to sleep.
-4 */
+
1/*
+2 * sleep.c - create a /proc file, and if several processes try to open it
+3 * at the same time, put all but one to sleep.
+4 */
5
-6#include <linux/kernel.h> /* We're doing kernel work */
-7#include <linux/module.h> /* Specifically, a module */
-8#include <linux/proc_fs.h> /* Necessary because we use proc fs */
-9#include <linux/sched.h> /* For putting processes to sleep and
-10 waking them up */
-11#include <linux/uaccess.h> /* for get_user and put_user */
-12#include <linux/version.h>
+6#include <linux/kernel.h> /* We're doing kernel work */
+7#include <linux/module.h> /* Specifically, a module */
+8#include <linux/proc_fs.h> /* Necessary because we use proc fs */
+9#include <linux/sched.h> /* For putting processes to sleep and
+10 waking them up */
+11#include <linux/uaccess.h> /* for get_user and put_user */
+12#include <linux/version.h>
13
-14#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0)
-15#define HAVE_PROC_OPS
-16#endif
+14#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 6, 0)
+15#define HAVE_PROC_OPS
+16#endif
17
-18/* Here we keep the last message received, to prove that we can process our
-19 * input.
-20 */
-21#define MESSAGE_LENGTH 80
-22static char message[MESSAGE_LENGTH];
+18/* Here we keep the last message received, to prove that we can process our
+19 * input.
+20 */
+21#define MESSAGE_LENGTH 80
+22static char message[MESSAGE_LENGTH];
23
-24static struct proc_dir_entry *our_proc_file;
-25#define PROC_ENTRY_FILENAME "sleep"
+24static struct proc_dir_entry *our_proc_file;
+25#define PROC_ENTRY_FILENAME "sleep"
26
-27/* Since we use the file operations struct, we can't use the special proc
-28 * output provisions - we have to use a standard read function, which is this
-29 * function.
-30 */
-31static ssize_t module_output(struct file *file, /* see include/linux/fs.h */
-32 char __user *buf, /* The buffer to put data to
-33 (in the user segment) */
-34 size_t len, /* The length of the buffer */
+27/* Since we use the file operations struct, we can't use the special proc
+28 * output provisions - we have to use a standard read function, which is this
+29 * function.
+30 */
+31static ssize_t module_output(struct file *file, /* see include/linux/fs.h */
+32 char __user *buf, /* The buffer to put data to
+33 (in the user segment) */
+34 size_t len, /* The length of the buffer */
35 loff_t *offset)
36{
-37 static int finished = 0;
-38 int i;
-39 char output_msg[MESSAGE_LENGTH + 30];
+37 static int finished = 0;
+38 int i;
+39 char output_msg[MESSAGE_LENGTH + 30];
40
-41 /* Return 0 to signify end of file - that we have nothing more to say
-42 * at this point.
-43 */
-44 if (finished) {
+41 /* Return 0 to signify end of file - that we have nothing more to say
+42 * at this point.
+43 */
+44 if (finished) {
45 finished = 0;
-46 return 0;
+46 return 0;
47 }
48
-49 sprintf(output_msg, "Last input:%s\n", message);
-50 for (i = 0; i < len && output_msg[i]; i++)
+49 sprintf(output_msg, "Last input:%s\n", message);
+50 for (i = 0; i < len && output_msg[i]; i++)
51 put_user(output_msg[i], buf + i);
52
53 finished = 1;
-54 return i; /* Return the number of bytes "read" */
+54 return i; /* Return the number of bytes "read" */
55}
56
-57/* This function receives input from the user when the user writes to the
-58 * /proc file.
-59 */
-60static ssize_t module_input(struct file *file, /* The file itself */
-61 const char __user *buf, /* The buffer with input */
-62 size_t length, /* The buffer's length */
-63 loff_t *offset) /* offset to file - ignore */
+57/* This function receives input from the user when the user writes to the
+58 * /proc file.
+59 */
+60static ssize_t module_input(struct file *file, /* The file itself */
+61 const char __user *buf, /* The buffer with input */
+62 size_t length, /* The buffer's length */
+63 loff_t *offset) /* offset to file - ignore */
64{
-65 int i;
+65 int i;
66
-67 /* Put the input into Message, where module_output will later be able
-68 * to use it.
-69 */
-70 for (i = 0; i < MESSAGE_LENGTH - 1 && i < length; i++)
+67 /* Put the input into Message, where module_output will later be able
+68 * to use it.
+69 */
+70 for (i = 0; i < MESSAGE_LENGTH - 1 && i < length; i++)
71 get_user(message[i], buf + i);
-72 /* we want a standard, zero terminated string */
-73 message[i] = '\0';
+72 /* we want a standard, zero terminated string */
+73 message[i] = '\0';
74
-75 /* We need to return the number of input characters used */
-76 return i;
+75 /* We need to return the number of input characters used */
+76 return i;
77}
78
-79/* 1 if the file is currently open by somebody */
-80static atomic_t already_open = ATOMIC_INIT(0);
+79/* 1 if the file is currently open by somebody */
+80static atomic_t already_open = ATOMIC_INIT(0);
81
-82/* Queue of processes who want our file */
-83static DECLARE_WAIT_QUEUE_HEAD(waitq);
+82/* Queue of processes who want our file */
+83static DECLARE_WAIT_QUEUE_HEAD(waitq);
84
-85/* Called when the /proc file is opened */
-86static int module_open(struct inode *inode, struct file *file)
+85/* Called when the /proc file is opened */
+86static int module_open(struct inode *inode, struct file *file)
87{
-88 /* If the file's flags include O_NONBLOCK, it means the process does not
-89 * want to wait for the file. In this case, if the file is already open,
-90 * we should fail with -EAGAIN, meaning "you will have to try again",
-91 * instead of blocking a process which would rather stay awake.
-92 */
-93 if ((file->f_flags & O_NONBLOCK) && atomic_read(&already_open))
-94 return -EAGAIN;
+88 /* If the file's flags include O_NONBLOCK, it means the process does not
+89 * want to wait for the file. In this case, if the file is already open,
+90 * we should fail with -EAGAIN, meaning "you will have to try again",
+91 * instead of blocking a process which would rather stay awake.
+92 */
+93 if ((file->f_flags & O_NONBLOCK) && atomic_read(&already_open))
+94 return -EAGAIN;
95
-96 /* This is the correct place for try_module_get(THIS_MODULE) because if
-97 * a process is in the loop, which is within the kernel module,
-98 * the kernel module must not be removed.
-99 */
+96 /* This is the correct place for try_module_get(THIS_MODULE) because if
+97 * a process is in the loop, which is within the kernel module,
+98 * the kernel module must not be removed.
+99 */
100 try_module_get(THIS_MODULE);
101
-102 while (atomic_cmpxchg(&already_open, 0, 1)) {
-103 int i, is_sig = 0;
+102 while (atomic_cmpxchg(&already_open, 0, 1)) {
+103 int i, is_sig = 0;
104
-105 /* This function puts the current process, including any system
-106 * calls, such as us, to sleep. Execution will be resumed right
-107 * after the function call, either because somebody called
-108 * wake_up(&waitq) (only module_close does that, when the file
-109 * is closed) or when a signal, such as Ctrl-C, is sent
-110 * to the process
-111 */
+105 /* This function puts the current process, including any system
+106 * calls, such as us, to sleep. Execution will be resumed right
+107 * after the function call, either because somebody called
+108 * wake_up(&waitq) (only module_close does that, when the file
+109 * is closed) or when a signal, such as Ctrl-C, is sent
+110 * to the process
+111 */
112 wait_event_interruptible(waitq, !atomic_read(&already_open));
113
-114 /* If we woke up because we got a signal we're not blocking,
-115 * return -EINTR (fail the system call). This allows processes
-116 * to be killed or stopped.
-117 */
-118 for (i = 0; i < _NSIG_WORDS && !is_sig; i++)
+114 /* If we woke up because we got a signal we're not blocking,
+115 * return -EINTR (fail the system call). This allows processes
+116 * to be killed or stopped.
+117 */
+118 for (i = 0; i < _NSIG_WORDS && !is_sig; i++)
119 is_sig = current->pending.signal.sig[i] & ~current->blocked.sig[i];
120
-121 if (is_sig) {
-122 /* It is important to put module_put(THIS_MODULE) here, because
-123 * for processes where the open is interrupted there will never
-124 * be a corresponding close. If we do not decrement the usage
-125 * count here, we will be left with a positive usage count
-126 * which we will have no way to bring down to zero, giving us
-127 * an immortal module, which can only be killed by rebooting
-128 * the machine.
-129 */
+121 if (is_sig) {
+122 /* It is important to put module_put(THIS_MODULE) here, because
+123 * for processes where the open is interrupted there will never
+124 * be a corresponding close. If we do not decrement the usage
+125 * count here, we will be left with a positive usage count
+126 * which we will have no way to bring down to zero, giving us
+127 * an immortal module, which can only be killed by rebooting
+128 * the machine.
+129 */
130 module_put(THIS_MODULE);
-131 return -EINTR;
+131 return -EINTR;
132 }
133 }
134
-135 return 0; /* Allow the access */
+135 return 0; /* Allow the access */
136}
137
-138/* Called when the /proc file is closed */
-139static int module_close(struct inode *inode, struct file *file)
+138/* Called when the /proc file is closed */
+139static int module_close(struct inode *inode, struct file *file)
140{
-141 /* Set already_open to zero, so one of the processes in the waitq will
-142 * be able to set already_open back to one and to open the file. All
-143 * the other processes will be called when already_open is back to one,
-144 * so they'll go back to sleep.
-145 */
+141 /* Set already_open to zero, so one of the processes in the waitq will
+142 * be able to set already_open back to one and to open the file. All
+143 * the other processes will be called when already_open is back to one,
+144 * so they'll go back to sleep.
+145 */
146 atomic_set(&already_open, 0);
147
-148 /* Wake up all the processes in waitq, so if anybody is waiting for the
-149 * file, they can have it.
-150 */
+148 /* Wake up all the processes in waitq, so if anybody is waiting for the
+149 * file, they can have it.
+150 */
151 wake_up(&waitq);
152
153 module_put(THIS_MODULE);
154
-155 return 0; /* success */
+155 return 0; /* success */
156}
157
-158/* Structures to register as the /proc file, with pointers to all the relevant
-159 * functions.
-160 */
+158/* Structures to register as the /proc file, with pointers to all the relevant
+159 * functions.
+160 */
161
-162/* File operations for our proc file. This is where we place pointers to all
-163 * the functions called when somebody tries to do something to our file. NULL
-164 * means we don't want to deal with something.
-165 */
-166#ifdef HAVE_PROC_OPS
-167static const struct proc_ops file_ops_4_our_proc_file = {
-168 .proc_read = module_output, /* "read" from the file */
-169 .proc_write = module_input, /* "write" to the file */
-170 .proc_open = module_open, /* called when the /proc file is opened */
-171 .proc_release = module_close, /* called when it's closed */
+162/* File operations for our proc file. This is where we place pointers to all
+163 * the functions called when somebody tries to do something to our file. NULL
+164 * means we don't want to deal with something.
+165 */
+166#ifdef HAVE_PROC_OPS
+167static const struct proc_ops file_ops_4_our_proc_file = {
+168 .proc_read = module_output, /* "read" from the file */
+169 .proc_write = module_input, /* "write" to the file */
+170 .proc_open = module_open, /* called when the /proc file is opened */
+171 .proc_release = module_close, /* called when it's closed */
172};
-173#else
-174static const struct file_operations file_ops_4_our_proc_file = {
+173#else
+174static const struct file_operations file_ops_4_our_proc_file = {
175 .read = module_output,
176 .write = module_input,
177 .open = module_open,
178 .release = module_close,
179};
-180#endif
+180#endif
181
-182/* Initialize the module - register the proc file */
-183static int __init sleep_init(void)
+182/* Initialize the module - register the proc file */
+183static int __init sleep_init(void)
184{
185 our_proc_file =
186 proc_create(PROC_ENTRY_FILENAME, 0644, NULL, &file_ops_4_our_proc_file);
-187 if (our_proc_file == NULL) {
+187 if (our_proc_file == NULL) {
188 remove_proc_entry(PROC_ENTRY_FILENAME, NULL);
-189 pr_debug("Error: Could not initialize /proc/%s\n", PROC_ENTRY_FILENAME);
-190 return -ENOMEM;
+189 pr_debug("Error: Could not initialize /proc/%s\n", PROC_ENTRY_FILENAME);
+190 return -ENOMEM;
191 }
192 proc_set_size(our_proc_file, 80);
193 proc_set_user(our_proc_file, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID);
194
-195 pr_info("/proc/%s created\n", PROC_ENTRY_FILENAME);
+195 pr_info("/proc/%s created\n", PROC_ENTRY_FILENAME);
196
-197 return 0;
+197 return 0;
198}
199
-200/* Cleanup - unregister our file from /proc. This could get dangerous if
-201 * there are still processes waiting in waitq, because they are inside our
-202 * open function, which will get unloaded. I'll explain how to avoid removal
-203 * of a kernel module in such a case in chapter 10.
-204 */
-205static void __exit sleep_exit(void)
+200/* Cleanup - unregister our file from /proc. This could get dangerous if
+201 * there are still processes waiting in waitq, because they are inside our
+202 * open function, which will get unloaded. I'll explain how to avoid removal
+203 * of a kernel module in such a case in chapter 10.
+204 */
+205static void __exit sleep_exit(void)
206{
207 remove_proc_entry(PROC_ENTRY_FILENAME, NULL);
-208 pr_debug("/proc/%s removed\n", PROC_ENTRY_FILENAME);
+208 pr_debug("/proc/%s removed\n", PROC_ENTRY_FILENAME);
209}
210
211module_init(sleep_init);
212module_exit(sleep_exit);
213
-214MODULE_LICENSE("GPL");
+214MODULE_LICENSE("GPL");1/*
-2 * cat_nonblock.c - open a file and display its contents, but exit rather than
-3 * wait for input.
-4 */
-5#include <errno.h> /* for errno */
-6#include <fcntl.h> /* for open */
-7#include <stdio.h> /* standard I/O */
-8#include <stdlib.h> /* for exit */
-9#include <unistd.h> /* for read */
+
1/*
+2 * cat_nonblock.c - open a file and display its contents, but exit rather than
+3 * wait for input.
+4 */
+5#include <errno.h> /* for errno */
+6#include <fcntl.h> /* for open */
+7#include <stdio.h> /* standard I/O */
+8#include <stdlib.h> /* for exit */
+9#include <unistd.h> /* for read */
10
-11#define MAX_BYTES 1024 * 4
+11#define MAX_BYTES 1024 * 4
12
-13int main(int argc, char *argv[])
+13int main(int argc, char *argv[])
14{
-15 int fd; /* The file descriptor for the file to read */
-16 size_t bytes; /* The number of bytes read */
-17 char buffer[MAX_BYTES]; /* The buffer for the bytes */
+15 int fd; /* The file descriptor for the file to read */
+16 size_t bytes; /* The number of bytes read */
+17 char buffer[MAX_BYTES]; /* The buffer for the bytes */
18
-19 /* Usage */
-20 if (argc != 2) {
-21 printf("Usage: %s <filename>\n", argv[0]);
-22 puts("Reads the content of a file, but doesn't wait for input");
+19 /* Usage */
+20 if (argc != 2) {
+21 printf("Usage: %s <filename>\n", argv[0]);
+22 puts("Reads the content of a file, but doesn't wait for input");
23 exit(-1);
24 }
25
-26 /* Open the file for reading in non blocking mode */
+26 /* Open the file for reading in non blocking mode */
27 fd = open(argv[1], O_RDONLY | O_NONBLOCK);
28
-29 /* If open failed */
-30 if (fd == -1) {
-31 puts(errno == EAGAIN ? "Open would block" : "Open failed");
+29 /* If open failed */
+30 if (fd == -1) {
+31 puts(errno == EAGAIN ? "Open would block" : "Open failed");
32 exit(-1);
33 }
34
-35 /* Read the file and output its contents */
-36 do {
-37 /* Read characters from the file */
+35 /* Read the file and output its contents */
+36 do {
+37 /* Read characters from the file */
38 bytes = read(fd, buffer, MAX_BYTES);
39
-40 /* If there's an error, report it and die */
-41 if (bytes == -1) {
-42 if (errno == EAGAIN)
-43 puts("Normally I'd block, but you told me not to");
-44 else
-45 puts("Another read error");
+40 /* If there's an error, report it and die */
+41 if (bytes == -1) {
+42 if (errno == EAGAIN)
+43 puts("Normally I'd block, but you told me not to");
+44 else
+45 puts("Another read error");
46 exit(-1);
47 }
48
-49 /* Print the characters */
-50 if (bytes > 0) {
-51 for (int i = 0; i < bytes; i++)
+49 /* Print the characters */
+50 if (bytes > 0) {
+51 for (int i = 0; i < bytes; i++)
52 putchar(buffer[i]);
53 }
54
-55 /* While there are no errors and the file isn't over */
-56 } while (bytes > 0);
+55 /* While there are no errors and the file isn't over */
+56 } while (bytes > 0);
57
-58 return 0;
+58 return 0;
59}
-11.2 Completions
- /bin/sleep
commands, the kernel has another way to do this which allows timeouts or
interrupts to also happen.
-1/*
-2 * completions.c
-3 */
-4#include <linux/completion.h>
-5#include <linux/init.h>
-6#include <linux/kernel.h>
-7#include <linux/kthread.h>
-8#include <linux/module.h>
+
+1/*
+2 * completions.c
+3 */
+4#include <linux/completion.h>
+5#include <linux/init.h>
+6#include <linux/kernel.h>
+7#include <linux/kthread.h>
+8#include <linux/module.h>
9
-10static struct {
-11 struct completion crank_comp;
-12 struct completion flywheel_comp;
+10static struct {
+11 struct completion crank_comp;
+12 struct completion flywheel_comp;
13} machine;
14
-15static int machine_crank_thread(void *arg)
+15static int machine_crank_thread(void *arg)
16{
-17 pr_info("Turn the crank\n");
+17 pr_info("Turn the crank\n");
18
19 complete_all(&machine.crank_comp);
20 complete_and_exit(&machine.crank_comp, 0);
21}
22
-23static int machine_flywheel_spinup_thread(void *arg)
+23static int machine_flywheel_spinup_thread(void *arg)
24{
25 wait_for_completion(&machine.crank_comp);
26
-27 pr_info("Flywheel spins up\n");
+27 pr_info("Flywheel spins up\n");
28
29 complete_all(&machine.flywheel_comp);
30 complete_and_exit(&machine.flywheel_comp, 0);
31}
32
-33static int completions_init(void)
+33static int completions_init(void)
34{
-35 struct task_struct *crank_thread;
-36 struct task_struct *flywheel_thread;
+35 struct task_struct *crank_thread;
+36 struct task_struct *flywheel_thread;
37
-38 pr_info("completions example\n");
+38 pr_info("completions example\n");
39
40 init_completion(&machine.crank_comp);
41 init_completion(&machine.flywheel_comp);
42
-43 crank_thread = kthread_create(machine_crank_thread, NULL, "KThread Crank");
-44 if (IS_ERR(crank_thread))
-45 goto ERROR_THREAD_1;
+43 crank_thread = kthread_create(machine_crank_thread, NULL, "KThread Crank");
+44 if (IS_ERR(crank_thread))
+45 goto ERROR_THREAD_1;
46
47 flywheel_thread = kthread_create(machine_flywheel_spinup_thread, NULL,
-48 "KThread Flywheel");
-49 if (IS_ERR(flywheel_thread))
-50 goto ERROR_THREAD_2;
+48 "KThread Flywheel");
+49 if (IS_ERR(flywheel_thread))
+50 goto ERROR_THREAD_2;
51
52 wake_up_process(flywheel_thread);
53 wake_up_process(crank_thread);
54
-55 return 0;
+55 return 0;
56
57ERROR_THREAD_2:
58 kthread_stop(crank_thread);
59ERROR_THREAD_1:
60
-61 return -1;
+61 return -1;
62}
63
-64static void completions_exit(void)
+64static void completions_exit(void)
65{
66 wait_for_completion(&machine.crank_comp);
67 wait_for_completion(&machine.flywheel_comp);
68
-69 pr_info("completions exit\n");
+69 pr_info("completions exit\n");
70}
71
72module_init(completions_init);
73module_exit(completions_exit);
74
-75MODULE_DESCRIPTION("Completions example");
-76MODULE_LICENSE("GPL");
- machine
+75MODULE_DESCRIPTION("Completions example");
+76MODULE_LICENSE("GPL"); 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.
- flywheel_thread
+ 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.
- 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.
-12 Avoiding Collisions and Deadlocks
-12.1 Mutex
-1/*
-2 * example_mutex.c
-3 */
-4#include <linux/init.h>
-5#include <linux/kernel.h>
-6#include <linux/module.h>
-7#include <linux/mutex.h>
+
+1/*
+2 * example_mutex.c
+3 */
+4#include <linux/init.h>
+5#include <linux/kernel.h>
+6#include <linux/module.h>
+7#include <linux/mutex.h>
8
-9static DEFINE_MUTEX(mymutex);
+9static DEFINE_MUTEX(mymutex);
10
-11static int example_mutex_init(void)
+11static int example_mutex_init(void)
12{
-13 int ret;
+13 int ret;
14
-15 pr_info("example_mutex init\n");
+15 pr_info("example_mutex init\n");
16
17 ret = mutex_trylock(&mymutex);
-18 if (ret != 0) {
-19 pr_info("mutex is locked\n");
+18 if (ret != 0) {
+19 pr_info("mutex is locked\n");
20
-21 if (mutex_is_locked(&mymutex) == 0)
-22 pr_info("The mutex failed to lock!\n");
+21 if (mutex_is_locked(&mymutex) == 0)
+22 pr_info("The mutex failed to lock!\n");
23
24 mutex_unlock(&mymutex);
-25 pr_info("mutex is unlocked\n");
-26 } else
-27 pr_info("Failed to lock\n");
+25 pr_info("mutex is unlocked\n");
+26 } else
+27 pr_info("Failed to lock\n");
28
-29 return 0;
+29 return 0;
30}
31
-32static void example_mutex_exit(void)
+32static void example_mutex_exit(void)
33{
-34 pr_info("example_mutex exit\n");
+34 pr_info("example_mutex exit\n");
35}
36
37module_init(example_mutex_init);
38module_exit(example_mutex_exit);
39
-40MODULE_DESCRIPTION("Mutex example");
-41MODULE_LICENSE("GPL");
-12.2 Spinlocks
- flags
variable to retain their state.
1/*
-2 * example_spinlock.c
-3 */
-4#include <linux/init.h>
-5#include <linux/interrupt.h>
-6#include <linux/kernel.h>
-7#include <linux/module.h>
-8#include <linux/spinlock.h>
+
+1/*
+2 * example_spinlock.c
+3 */
+4#include <linux/init.h>
+5#include <linux/interrupt.h>
+6#include <linux/kernel.h>
+7#include <linux/module.h>
+8#include <linux/spinlock.h>
9
-10static DEFINE_SPINLOCK(sl_static);
-11static spinlock_t sl_dynamic;
+10static DEFINE_SPINLOCK(sl_static);
+11static spinlock_t sl_dynamic;
12
-13static void example_spinlock_static(void)
+13static void example_spinlock_static(void)
14{
-15 unsigned long flags;
+15 unsigned long flags;
16
17 spin_lock_irqsave(&sl_static, flags);
-18 pr_info("Locked static spinlock\n");
+18 pr_info("Locked static spinlock\n");
19
-20 /* Do something or other safely. Because this uses 100% CPU time, this
-21 * code should take no more than a few milliseconds to run.
-22 */
+20 /* Do something or other safely. Because this uses 100% CPU time, this
+21 * code should take no more than a few milliseconds to run.
+22 */
23
24 spin_unlock_irqrestore(&sl_static, flags);
-25 pr_info("Unlocked static spinlock\n");
+25 pr_info("Unlocked static spinlock\n");
26}
27
-28static void example_spinlock_dynamic(void)
+28static void example_spinlock_dynamic(void)
29{
-30 unsigned long flags;
+30 unsigned long flags;
31
32 spin_lock_init(&sl_dynamic);
33 spin_lock_irqsave(&sl_dynamic, flags);
-34 pr_info("Locked dynamic spinlock\n");
+34 pr_info("Locked dynamic spinlock\n");
35
-36 /* Do something or other safely. Because this uses 100% CPU time, this
-37 * code should take no more than a few milliseconds to run.
-38 */
+36 /* Do something or other safely. Because this uses 100% CPU time, this
+37 * code should take no more than a few milliseconds to run.
+38 */
39
40 spin_unlock_irqrestore(&sl_dynamic, flags);
-41 pr_info("Unlocked dynamic spinlock\n");
+41 pr_info("Unlocked dynamic spinlock\n");
42}
43
-44static int example_spinlock_init(void)
+44static int example_spinlock_init(void)
45{
-46 pr_info("example spinlock started\n");
+46 pr_info("example spinlock started\n");
47
48 example_spinlock_static();
49 example_spinlock_dynamic();
50
-51 return 0;
+51 return 0;
52}
53
-54static void example_spinlock_exit(void)
+54static void example_spinlock_exit(void)
55{
-56 pr_info("example spinlock exit\n");
+56 pr_info("example spinlock exit\n");
57}
58
59module_init(example_spinlock_init);
60module_exit(example_spinlock_exit);
61
-62MODULE_DESCRIPTION("Spinlock example");
-63MODULE_LICENSE("GPL");
-12.3 Read and write locks
-1/*
-2 * example_rwlock.c
-3 */
-4#include <linux/interrupt.h>
-5#include <linux/kernel.h>
-6#include <linux/module.h>
+
+1/*
+2 * example_rwlock.c
+3 */
+4#include <linux/interrupt.h>
+5#include <linux/kernel.h>
+6#include <linux/module.h>
7
-8static DEFINE_RWLOCK(myrwlock);
+8static DEFINE_RWLOCK(myrwlock);
9
-10static void example_read_lock(void)
+10static void example_read_lock(void)
11{
-12 unsigned long flags;
+12 unsigned long flags;
13
14 read_lock_irqsave(&myrwlock, flags);
-15 pr_info("Read Locked\n");
+15 pr_info("Read Locked\n");
16
-17 /* Read from something */
+17 /* Read from something */
18
19 read_unlock_irqrestore(&myrwlock, flags);
-20 pr_info("Read Unlocked\n");
+20 pr_info("Read Unlocked\n");
21}
22
-23static void example_write_lock(void)
+23static void example_write_lock(void)
24{
-25 unsigned long flags;
+25 unsigned long flags;
26
27 write_lock_irqsave(&myrwlock, flags);
-28 pr_info("Write Locked\n");
+28 pr_info("Write Locked\n");
29
-30 /* Write to something */
+30 /* Write to something */
31
32 write_unlock_irqrestore(&myrwlock, flags);
-33 pr_info("Write Unlocked\n");
+33 pr_info("Write Unlocked\n");
34}
35
-36static int example_rwlock_init(void)
+36static int example_rwlock_init(void)
37{
-38 pr_info("example_rwlock started\n");
+38 pr_info("example_rwlock started\n");
39
40 example_read_lock();
41 example_write_lock();
42
-43 return 0;
+43 return 0;
44}
45
-46static void example_rwlock_exit(void)
+46static void example_rwlock_exit(void)
47{
-48 pr_info("example_rwlock exit\n");
+48 pr_info("example_rwlock exit\n");
49}
50
51module_init(example_rwlock_init);
52module_exit(example_rwlock_exit);
53
-54MODULE_DESCRIPTION("Read/Write locks example");
-55MODULE_LICENSE("GPL");
- read_lock(&myrwlock)
and read_unlock(&myrwlock)
or the corresponding write functions.
12.4 Atomic operations
-1/*
-2 * example_atomic.c
-3 */
-4#include <linux/interrupt.h>
-5#include <linux/kernel.h>
-6#include <linux/module.h>
+
-1/*
+2 * example_atomic.c
+3 */
+4#include <linux/interrupt.h>
+5#include <linux/kernel.h>
+6#include <linux/module.h>
7
-8#define BYTE_TO_BINARY_PATTERN "%c%c%c%c%c%c%c%c"
-9#define BYTE_TO_BINARY(byte) \
-10 ((byte & 0x80) ? '1' : '0'), ((byte & 0x40) ? '1' : '0'), \
-11 ((byte & 0x20) ? '1' : '0'), ((byte & 0x10) ? '1' : '0'), \
-12 ((byte & 0x08) ? '1' : '0'), ((byte & 0x04) ? '1' : '0'), \
-13 ((byte & 0x02) ? '1' : '0'), ((byte & 0x01) ? '1' : '0')
+8#define BYTE_TO_BINARY_PATTERN "%c%c%c%c%c%c%c%c"
+9#define BYTE_TO_BINARY(byte) \
+10 ((byte & 0x80) ? '1' : '0'), ((byte & 0x40) ? '1' : '0'), \
+11 ((byte & 0x20) ? '1' : '0'), ((byte & 0x10) ? '1' : '0'), \
+12 ((byte & 0x08) ? '1' : '0'), ((byte & 0x04) ? '1' : '0'), \
+13 ((byte & 0x02) ? '1' : '0'), ((byte & 0x01) ? '1' : '0')
14
-15static void atomic_add_subtract(void)
+15static void atomic_add_subtract(void)
16{
17 atomic_t debbie;
18 atomic_t chris = ATOMIC_INIT(50);
19
20 atomic_set(&debbie, 45);
21
-22 /* subtract one */
+22 /* subtract one */
23 atomic_dec(&debbie);
24
25 atomic_add(7, &debbie);
26
-27 /* add one */
+27 /* add one */
28 atomic_inc(&debbie);
29
-30 pr_info("chris: %d, debbie: %d\n", atomic_read(&chris),
+30 pr_info("chris: %d, debbie: %d\n", atomic_read(&chris),
31 atomic_read(&debbie));
32}
33
-34static void atomic_bitwise(void)
+34static void atomic_bitwise(void)
35{
-36 unsigned long word = 0;
+36 unsigned long word = 0;
37
-38 pr_info("Bits 0: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word));
+38 pr_info("Bits 0: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word));
39 set_bit(3, &word);
40 set_bit(5, &word);
-41 pr_info("Bits 1: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word));
+41 pr_info("Bits 1: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word));
42 clear_bit(5, &word);
-43 pr_info("Bits 2: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word));
+43 pr_info("Bits 2: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word));
44 change_bit(3, &word);
45
-46 pr_info("Bits 3: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word));
-47 if (test_and_set_bit(3, &word))
-48 pr_info("wrong\n");
-49 pr_info("Bits 4: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word));
+46 pr_info("Bits 3: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word));
+47 if (test_and_set_bit(3, &word))
+48 pr_info("wrong\n");
+49 pr_info("Bits 4: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word));
50
51 word = 255;
-52 pr_info("Bits 5: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word));
+52 pr_info("Bits 5: " BYTE_TO_BINARY_PATTERN, BYTE_TO_BINARY(word));
53}
54
-55static int example_atomic_init(void)
+55static int example_atomic_init(void)
56{
-57 pr_info("example_atomic started\n");
+57 pr_info("example_atomic started\n");
58
59 atomic_add_subtract();
60 atomic_bitwise();
61
-62 return 0;
+62 return 0;
63}
64
-65static void example_atomic_exit(void)
+65static void example_atomic_exit(void)
66{
-67 pr_info("example_atomic exit\n");
+67 pr_info("example_atomic exit\n");
68}
69
70module_init(example_atomic_init);
71module_exit(example_atomic_exit);
72
-73MODULE_DESCRIPTION("Atomic operations example");
-74MODULE_LICENSE("GPL");
+73MODULE_DESCRIPTION("Atomic operations example");
+74MODULE_LICENSE("GPL");13 Replacing Print Macros
-13.1 Replacement
-1/*
-2 * print_string.c - Send output to the tty we're running on, regardless if
-3 * it is through X11, telnet, etc. We do this by printing the string to the
-4 * tty associated with the current task.
-5 */
-6#include <linux/init.h>
-7#include <linux/kernel.h>
-8#include <linux/module.h>
-9#include <linux/sched.h> /* For current */
-10#include <linux/tty.h> /* For the tty declarations */
+
-1/*
+2 * print_string.c - Send output to the tty we're running on, regardless if
+3 * it is through X11, telnet, etc. We do this by printing the string to the
+4 * tty associated with the current task.
+5 */
+6#include <linux/init.h>
+7#include <linux/kernel.h>
+8#include <linux/module.h>
+9#include <linux/sched.h> /* For current */
+10#include <linux/tty.h> /* For the tty declarations */
11
-12static void print_string(char *str)
+12static void print_string(char *str)
13{
-14 /* The tty for the current task */
-15 struct tty_struct *my_tty = get_current_tty();
+14 /* The tty for the current task */
+15 struct tty_struct *my_tty = get_current_tty();
16
-17 /* If my_tty is NULL, the current task has no tty you can print to (i.e.,
-18 * if it is a daemon). If so, there is nothing we can do.
-19 */
-20 if (my_tty) {
-21 const struct tty_operations *ttyops = my_tty->driver->ops;
-22 /* my_tty->driver is a struct which holds the tty's functions,
-23 * one of which (write) is used to write strings to the tty.
-24 * It can be used to take a string either from the user's or
-25 * kernel's memory segment.
-26 *
-27 * The function's 1st parameter is the tty to write to, because the
-28 * same function would normally be used for all tty's of a certain
-29 * type.
-30 * The 2nd parameter is a pointer to a string.
-31 * The 3rd parameter is the length of the string.
-32 *
-33 * As you will see below, sometimes it's necessary to use
-34 * preprocessor stuff to create code that works for different
-35 * kernel versions. The (naive) approach we've taken here does not
-36 * scale well. The right way to deal with this is described in
-37 * section 2 of
-38 * linux/Documentation/SubmittingPatches
-39 */
-40 (ttyops->write)(my_tty, /* The tty itself */
-41 str, /* String */
-42 strlen(str)); /* Length */
+17 /* If my_tty is NULL, the current task has no tty you can print to (i.e.,
+18 * if it is a daemon). If so, there is nothing we can do.
+19 */
+20 if (my_tty) {
+21 const struct tty_operations *ttyops = my_tty->driver->ops;
+22 /* my_tty->driver is a struct which holds the tty's functions,
+23 * one of which (write) is used to write strings to the tty.
+24 * It can be used to take a string either from the user's or
+25 * kernel's memory segment.
+26 *
+27 * The function's 1st parameter is the tty to write to, because the
+28 * same function would normally be used for all tty's of a certain
+29 * type.
+30 * The 2nd parameter is a pointer to a string.
+31 * The 3rd parameter is the length of the string.
+32 *
+33 * As you will see below, sometimes it's necessary to use
+34 * preprocessor stuff to create code that works for different
+35 * kernel versions. The (naive) approach we've taken here does not
+36 * scale well. The right way to deal with this is described in
+37 * section 2 of
+38 * linux/Documentation/SubmittingPatches
+39 */
+40 (ttyops->write)(my_tty, /* The tty itself */
+41 str, /* String */
+42 strlen(str)); /* Length */
43
-44 /* ttys were originally hardware devices, which (usually) strictly
-45 * followed the ASCII standard. In ASCII, to move to a new line you
-46 * need two characters, a carriage return and a line feed. On Unix,
-47 * the ASCII line feed is used for both purposes - so we can not
-48 * just use \n, because it would not have a carriage return and the
-49 * next line will start at the column right after the line feed.
-50 *
-51 * This is why text files are different between Unix and MS Windows.
-52 * In CP/M and derivatives, like MS-DOS and MS Windows, the ASCII
-53 * standard was strictly adhered to, and therefore a newline requirs
-54 * both a LF and a CR.
-55 */
-56 (ttyops->write)(my_tty, "\015\012", 2);
+44 /* ttys were originally hardware devices, which (usually) strictly
+45 * followed the ASCII standard. In ASCII, to move to a new line you
+46 * need two characters, a carriage return and a line feed. On Unix,
+47 * the ASCII line feed is used for both purposes - so we can not
+48 * just use \n, because it would not have a carriage return and the
+49 * next line will start at the column right after the line feed.
+50 *
+51 * This is why text files are different between Unix and MS Windows.
+52 * In CP/M and derivatives, like MS-DOS and MS Windows, the ASCII
+53 * standard was strictly adhered to, and therefore a newline requirs
+54 * both a LF and a CR.
+55 */
+56 (ttyops->write)(my_tty, "\015\012", 2);
57 }
58}
59
-60static int __init print_string_init(void)
+60static int __init print_string_init(void)
61{
-62 print_string("The module has been inserted. Hello world!");
-63 return 0;
+62 print_string("The module has been inserted. Hello world!");
+63 return 0;
64}
65
-66static void __exit print_string_exit(void)
+66static void __exit print_string_exit(void)
67{
-68 print_string("The module has been removed. Farewell world!");
+68 print_string("The module has been removed. Farewell world!");
69}
70
71module_init(print_string_init);
72module_exit(print_string_exit);
73
-74MODULE_LICENSE("GPL");
+74MODULE_LICENSE("GPL");13.2 Flashing keyboard LEDs
- timer_list
structure may be able to overwrite the
@@ -4276,37 +4319,37 @@ to improve memory safety. A buffer overflow in the area of a
and data
fields, providing the attacker with a way to use return-object programming (ROP)
to call arbitrary functions within the kernel. Also, the function prototype of the callback,
-containing a unsigned long
+containing a unsigned long
argument, will prevent work from any type checking. Furthermore, the function prototype
-with unsigned long
+with unsigned long
argument may be an obstacle to the control-flow integrity. Thus, it is better
to use a unique prototype to separate from the cluster that takes an
- unsigned long
+ unsigned long
argument. The timer callback should be passed a pointer to the
timer_list
- structure rather than an unsigned long
+ structure rather than an unsigned long
argument. Then, it wraps all the information the callback needs, including the
timer_list
structure, into a larger structure, and it can use the
container_of
- macro instead of the unsigned long
+ macro instead of the unsigned long
value.
- setup_timer
+ setup_timer
was used to initialize the timer and the
timer_list
structure looked like:
1struct timer_list {
-2 unsigned long expires;
-3 void (*function)(unsigned long);
-4 unsigned long data;
+
+1struct timer_list {
+2 unsigned long expires;
+3 void (*function)(unsigned long);
+4 unsigned long data;
5 u32 flags;
-6 /* ... */
+6 /* ... */
7};
8
-9void setup_timer(struct timer_list *timer, void (*callback)(unsigned long),
-10 unsigned long data);
- timer_setup
+9void setup_timer(struct timer_list *timer, void (*callback)(unsigned long),
+10 unsigned long data); timer_setup
is adopted and the kernel step by step converting to
timer_setup
from setup_timer
@@ -4318,63 +4361,63 @@ Moreover, the timer_setup
was implemented by setup_timer
at first.
1void timer_setup(struct timer_list *timer,
-2 void (*callback)(struct timer_list *), unsigned int flags);
- setup_timer
+ 1void timer_setup(struct timer_list *timer,
+2 void (*callback)(struct timer_list *), unsigned int flags);
+ setup_timer
was then removed since v4.15. As a result, the
timer_list
structure had changed to the following.
1struct timer_list {
-2 unsigned long expires;
-3 void (*function)(struct timer_list *);
+
-1struct timer_list {
+2 unsigned long expires;
+3 void (*function)(struct timer_list *);
4 u32 flags;
-5 /* ... */
+5 /* ... */
6};
-1/*
-2 * kbleds.c - Blink keyboard leds until the module is unloaded.
-3 */
+
+1/*
+2 * kbleds.c - Blink keyboard leds until the module is unloaded.
+3 */
4
-5#include <linux/init.h>
-6#include <linux/kd.h> /* For KDSETLED */
-7#include <linux/module.h>
-8#include <linux/tty.h> /* For tty_struct */
-9#include <linux/vt.h> /* For MAX_NR_CONSOLES */
-10#include <linux/vt_kern.h> /* for fg_console */
-11#include <linux/console_struct.h> /* For vc_cons */
+5#include <linux/init.h>
+6#include <linux/kd.h> /* For KDSETLED */
+7#include <linux/module.h>
+8#include <linux/tty.h> /* For tty_struct */
+9#include <linux/vt.h> /* For MAX_NR_CONSOLES */
+10#include <linux/vt_kern.h> /* for fg_console */
+11#include <linux/console_struct.h> /* For vc_cons */
12
-13MODULE_DESCRIPTION("Example module illustrating the use of Keyboard LEDs.");
+13MODULE_DESCRIPTION("Example module illustrating the use of Keyboard LEDs.");
14
-15static struct timer_list my_timer;
-16static struct tty_driver *my_driver;
-17static unsigned long kbledstatus = 0;
+15static struct timer_list my_timer;
+16static struct tty_driver *my_driver;
+17static unsigned long kbledstatus = 0;
18
-19#define BLINK_DELAY HZ / 5
-20#define ALL_LEDS_ON 0x07
-21#define RESTORE_LEDS 0xFF
+19#define BLINK_DELAY HZ / 5
+20#define ALL_LEDS_ON 0x07
+21#define RESTORE_LEDS 0xFF
22
-23/* Function my_timer_func blinks the keyboard LEDs periodically by invoking
-24 * command KDSETLED of ioctl() on the keyboard driver. To learn more on virtual
-25 * terminal ioctl operations, please see file:
-26 * drivers/tty/vt/vt_ioctl.c, function vt_ioctl().
-27 *
-28 * The argument to KDSETLED is alternatively set to 7 (thus causing the led
-29 * mode to be set to LED_SHOW_IOCTL, and all the leds are lit) and to 0xFF
-30 * (any value above 7 switches back the led mode to LED_SHOW_FLAGS, thus
-31 * the LEDs reflect the actual keyboard status). To learn more on this,
-32 * please see file: drivers/tty/vt/keyboard.c, function setledstate().
-33 */
-34static void my_timer_func(struct timer_list *unused)
+23/* Function my_timer_func blinks the keyboard LEDs periodically by invoking
+24 * command KDSETLED of ioctl() on the keyboard driver. To learn more on virtual
+25 * terminal ioctl operations, please see file:
+26 * drivers/tty/vt/vt_ioctl.c, function vt_ioctl().
+27 *
+28 * The argument to KDSETLED is alternatively set to 7 (thus causing the led
+29 * mode to be set to LED_SHOW_IOCTL, and all the leds are lit) and to 0xFF
+30 * (any value above 7 switches back the led mode to LED_SHOW_FLAGS, thus
+31 * the LEDs reflect the actual keyboard status). To learn more on this,
+32 * please see file: drivers/tty/vt/keyboard.c, function setledstate().
+33 */
+34static void my_timer_func(struct timer_list *unused)
35{
-36 struct tty_struct *t = vc_cons[fg_console].d->port.tty;
+36 struct tty_struct *t = vc_cons[fg_console].d->port.tty;
37
-38 if (kbledstatus == ALL_LEDS_ON)
+38 if (kbledstatus == ALL_LEDS_ON)
39 kbledstatus = RESTORE_LEDS;
-40 else
+40 else
41 kbledstatus = ALL_LEDS_ON;
42
43 (my_driver->ops->ioctl)(t, KDSETLED, kbledstatus);
@@ -4383,34 +4426,34 @@ loaded, starts blinking the keyboard LEDs until it is unloaded.
46 add_timer(&my_timer);
47}
48
-49static int __init kbleds_init(void)
+49static int __init kbleds_init(void)
50{
-51 int i;
+51 int i;
52
-53 pr_info("kbleds: loading\n");
-54 pr_info("kbleds: fgconsole is %x\n", fg_console);
-55 for (i = 0; i < MAX_NR_CONSOLES; i++) {
-56 if (!vc_cons[i].d)
-57 break;
-58 pr_info("poet_atkm: console[%i/%i] #%i, tty %p\n", i, MAX_NR_CONSOLES,
-59 vc_cons[i].d->vc_num, (void *)vc_cons[i].d->port.tty);
+53 pr_info("kbleds: loading\n");
+54 pr_info("kbleds: fgconsole is %x\n", fg_console);
+55 for (i = 0; i < MAX_NR_CONSOLES; i++) {
+56 if (!vc_cons[i].d)
+57 break;
+58 pr_info("poet_atkm: console[%i/%i] #%i, tty %p\n", i, MAX_NR_CONSOLES,
+59 vc_cons[i].d->vc_num, (void *)vc_cons[i].d->port.tty);
60 }
-61 pr_info("kbleds: finished scanning consoles\n");
+61 pr_info("kbleds: finished scanning consoles\n");
62
63 my_driver = vc_cons[fg_console].d->port.tty->driver;
-64 pr_info("kbleds: tty driver magic %x\n", my_driver->magic);
+64 pr_info("kbleds: tty driver magic %x\n", my_driver->magic);
65
-66 /* Set up the LED blink timer the first time. */
+66 /* Set up the LED blink timer the first time. */
67 timer_setup(&my_timer, my_timer_func, 0);
68 my_timer.expires = jiffies + BLINK_DELAY;
69 add_timer(&my_timer);
70
-71 return 0;
+71 return 0;
72}
73
-74static void __exit kbleds_cleanup(void)
+74static void __exit kbleds_cleanup(void)
75{
-76 pr_info("kbleds: unloading...\n");
+76 pr_info("kbleds: unloading...\n");
77 del_timer(&my_timer);
78 (my_driver->ops->ioctl)(vc_cons[fg_console].d->port.tty, KDSETLED,
79 RESTORE_LEDS);
@@ -4419,8 +4462,8 @@ loaded, starts blinking the keyboard LEDs until it is unloaded.
82module_init(kbleds_init);
83module_exit(kbleds_cleanup);
84
-85MODULE_LICENSE("GPL");
- CONFIG_LL_DEBUG
in make menuconfig
@@ -4431,76 +4474,76 @@ everything what your code does over a serial line. If you find yourself porting
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.
-14 Scheduling Tasks
-14.1 Tasklets
- tasklet_fn
function runs for a few seconds and in the mean time execution of the
example_tasklet_init
function continues to the exit point.
1/*
-2 * example_tasklet.c
-3 */
-4#include <linux/delay.h>
-5#include <linux/interrupt.h>
-6#include <linux/kernel.h>
-7#include <linux/module.h>
+
+1/*
+2 * example_tasklet.c
+3 */
+4#include <linux/delay.h>
+5#include <linux/interrupt.h>
+6#include <linux/kernel.h>
+7#include <linux/module.h>
8
-9/* Macro DECLARE_TASKLET_OLD exists for compatibiity.
-10 * See https://lwn.net/Articles/830964/
-11 */
-12#ifndef DECLARE_TASKLET_OLD
-13#define DECLARE_TASKLET_OLD(arg1, arg2) DECLARE_TASKLET(arg1, arg2, 0L)
-14#endif
+9/* Macro DECLARE_TASKLET_OLD exists for compatibiity.
+10 * See https://lwn.net/Articles/830964/
+11 */
+12#ifndef DECLARE_TASKLET_OLD
+13#define DECLARE_TASKLET_OLD(arg1, arg2) DECLARE_TASKLET(arg1, arg2, 0L)
+14#endif
15
-16static void tasklet_fn(unsigned long data)
+16static void tasklet_fn(unsigned long data)
17{
-18 pr_info("Example tasklet starts\n");
+18 pr_info("Example tasklet starts\n");
19 mdelay(5000);
-20 pr_info("Example tasklet ends\n");
+20 pr_info("Example tasklet ends\n");
21}
22
-23static DECLARE_TASKLET_OLD(mytask, tasklet_fn);
+23static DECLARE_TASKLET_OLD(mytask, tasklet_fn);
24
-25static int example_tasklet_init(void)
+25static int example_tasklet_init(void)
26{
-27 pr_info("tasklet example init\n");
+27 pr_info("tasklet example init\n");
28 tasklet_schedule(&mytask);
29 mdelay(200);
-30 pr_info("Example tasklet init continues...\n");
-31 return 0;
+30 pr_info("Example tasklet init continues...\n");
+31 return 0;
32}
33
-34static void example_tasklet_exit(void)
+34static void example_tasklet_exit(void)
35{
-36 pr_info("tasklet example exit\n");
+36 pr_info("tasklet example exit\n");
37 tasklet_kill(&mytask);
38}
39
40module_init(example_tasklet_init);
41module_exit(example_tasklet_exit);
42
-43MODULE_DESCRIPTION("Tasklet example");
-44MODULE_LICENSE("GPL");
- dmesg
+43MODULE_DESCRIPTION("Tasklet example");
+44MODULE_LICENSE("GPL"); dmesg
should show:
@@ -4512,50 +4555,50 @@ Example tasklet starts
Example tasklet init continues...
Example tasklet ends
DECLARE_TASKLET_OLD
exists for compatibility. For further information, see https://lwn.net/Articles/830964/.
-14.2 Work queues
-1/*
-2 * sched.c
-3 */
-4#include <linux/init.h>
-5#include <linux/module.h>
-6#include <linux/workqueue.h>
+
+1/*
+2 * sched.c
+3 */
+4#include <linux/init.h>
+5#include <linux/module.h>
+6#include <linux/workqueue.h>
7
-8static struct workqueue_struct *queue = NULL;
-9static struct work_struct work;
+8static struct workqueue_struct *queue = NULL;
+9static struct work_struct work;
10
-11static void work_handler(struct work_struct *data)
+11static void work_handler(struct work_struct *data)
12{
-13 pr_info("work handler function.\n");
+13 pr_info("work handler function.\n");
14}
15
-16static int __init sched_init(void)
+16static int __init sched_init(void)
17{
-18 queue = alloc_workqueue("HELLOWORLD", WQ_UNBOUND, 1);
+18 queue = alloc_workqueue("HELLOWORLD", WQ_UNBOUND, 1);
19 INIT_WORK(&work, work_handler);
20 schedule_work(&work);
-21 return 0;
+21 return 0;
22}
23
-24static void __exit sched_exit(void)
+24static void __exit sched_exit(void)
25{
26 destroy_workqueue(queue);
27}
@@ -4563,38 +4606,38 @@ Completely Fair Scheduler (CFS) to execute work within the queue.
29module_init(sched_init);
30module_exit(sched_exit);
31
-32MODULE_LICENSE("GPL");
-33MODULE_DESCRIPTION("Workqueue example");
-15 Interrupt Handlers
-15.1 Interrupt Handlers
- 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.
- request_irq()
to get your interrupt handler called when the relevant IRQ is received.
- SA_INTERRUPT
to indicate this is a fast interrupt. This function will only succeed if there is not
already a handler on this IRQ, or if you are both willing to share.
-15.2 Detecting button presses
-1/*
-2 * intrpt.c - Handling GPIO with interrupts
-3 *
-4 * Based upon the RPi example by Stefan Wendler (devnull@kaltpost.de)
-5 * from:
-6 * https://github.com/wendlers/rpi-kmod-samples
-7 *
-8 * Press one button to turn on a LED and another to turn it off.
-9 */
+
+1/*
+2 * intrpt.c - Handling GPIO with interrupts
+3 *
+4 * Based upon the RPi example by Stefan Wendler (devnull@kaltpost.de)
+5 * from:
+6 * https://github.com/wendlers/rpi-kmod-samples
+7 *
+8 * Press one button to turn on a LED and another to turn it off.
+9 */
10
-11#include <linux/gpio.h>
-12#include <linux/interrupt.h>
-13#include <linux/kernel.h>
-14#include <linux/module.h>
+11#include <linux/gpio.h>
+12#include <linux/interrupt.h>
+13#include <linux/kernel.h>
+14#include <linux/module.h>
15
-16static int button_irqs[] = { -1, -1 };
+16static int button_irqs[] = { -1, -1 };
17
-18/* Define GPIOs for LEDs.
-19 * TODO: Change the numbers for the GPIO on your board.
-20 */
-21static struct gpio leds[] = { { 4, GPIOF_OUT_INIT_LOW, "LED 1" } };
+18/* Define GPIOs for LEDs.
+19 * TODO: Change the numbers for the GPIO on your board.
+20 */
+21static struct gpio leds[] = { { 4, GPIOF_OUT_INIT_LOW, "LED 1" } };
22
-23/* Define GPIOs for BUTTONS
-24 * TODO: Change the numbers for the GPIO on your board.
-25 */
-26static struct gpio buttons[] = { { 17, GPIOF_IN, "LED 1 ON BUTTON" },
-27 { 18, GPIOF_IN, "LED 1 OFF BUTTON" } };
+23/* Define GPIOs for BUTTONS
+24 * TODO: Change the numbers for the GPIO on your board.
+25 */
+26static struct gpio buttons[] = { { 17, GPIOF_IN, "LED 1 ON BUTTON" },
+27 { 18, GPIOF_IN, "LED 1 OFF BUTTON" } };
28
-29/* interrupt function triggered when a button is pressed. */
-30static irqreturn_t button_isr(int irq, void *data)
+29/* interrupt function triggered when a button is pressed. */
+30static irqreturn_t button_isr(int irq, void *data)
31{
-32 /* first button */
-33 if (irq == button_irqs[0] && !gpio_get_value(leds[0].gpio))
+32 /* first button */
+33 if (irq == button_irqs[0] && !gpio_get_value(leds[0].gpio))
34 gpio_set_value(leds[0].gpio, 1);
-35 /* second button */
-36 else if (irq == button_irqs[1] && gpio_get_value(leds[0].gpio))
+35 /* second button */
+36 else if (irq == button_irqs[1] && gpio_get_value(leds[0].gpio))
37 gpio_set_value(leds[0].gpio, 0);
38
-39 return IRQ_HANDLED;
+39 return IRQ_HANDLED;
40}
41
-42static int __init intrpt_init(void)
+42static int __init intrpt_init(void)
43{
-44 int ret = 0;
+44 int ret = 0;
45
-46 pr_info("%s\n", __func__);
+46 pr_info("%s\n", __func__);
47
-48 /* register LED gpios */
+48 /* register LED gpios */
49 ret = gpio_request_array(leds, ARRAY_SIZE(leds));
50
-51 if (ret) {
-52 pr_err("Unable to request GPIOs for LEDs: %d\n", ret);
-53 return ret;
+51 if (ret) {
+52 pr_err("Unable to request GPIOs for LEDs: %d\n", ret);
+53 return ret;
54 }
55
-56 /* register BUTTON gpios */
+56 /* register BUTTON gpios */
57 ret = gpio_request_array(buttons, ARRAY_SIZE(buttons));
58
-59 if (ret) {
-60 pr_err("Unable to request GPIOs for BUTTONs: %d\n", ret);
-61 goto fail1;
+59 if (ret) {
+60 pr_err("Unable to request GPIOs for BUTTONs: %d\n", ret);
+61 goto fail1;
62 }
63
-64 pr_info("Current button1 value: %d\n", gpio_get_value(buttons[0].gpio));
+64 pr_info("Current button1 value: %d\n", gpio_get_value(buttons[0].gpio));
65
66 ret = gpio_to_irq(buttons[0].gpio);
67
-68 if (ret < 0) {
-69 pr_err("Unable to request IRQ: %d\n", ret);
-70 goto fail2;
+68 if (ret < 0) {
+69 pr_err("Unable to request IRQ: %d\n", ret);
+70 goto fail2;
71 }
72
73 button_irqs[0] = ret;
74
-75 pr_info("Successfully requested BUTTON1 IRQ # %d\n", button_irqs[0]);
+75 pr_info("Successfully requested BUTTON1 IRQ # %d\n", button_irqs[0]);
76
77 ret = request_irq(button_irqs[0], button_isr,
78 IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
-79 "gpiomod#button1", NULL);
+79 "gpiomod#button1", NULL);
80
-81 if (ret) {
-82 pr_err("Unable to request IRQ: %d\n", ret);
-83 goto fail2;
+81 if (ret) {
+82 pr_err("Unable to request IRQ: %d\n", ret);
+83 goto fail2;
84 }
85
86 ret = gpio_to_irq(buttons[1].gpio);
87
-88 if (ret < 0) {
-89 pr_err("Unable to request IRQ: %d\n", ret);
-90 goto fail2;
+88 if (ret < 0) {
+89 pr_err("Unable to request IRQ: %d\n", ret);
+90 goto fail2;
91 }
92
93 button_irqs[1] = ret;
94
-95 pr_info("Successfully requested BUTTON2 IRQ # %d\n", button_irqs[1]);
+95 pr_info("Successfully requested BUTTON2 IRQ # %d\n", button_irqs[1]);
96
97 ret = request_irq(button_irqs[1], button_isr,
98 IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
-99 "gpiomod#button2", NULL);
+99 "gpiomod#button2", NULL);
100
-101 if (ret) {
-102 pr_err("Unable to request IRQ: %d\n", ret);
-103 goto fail3;
+101 if (ret) {
+102 pr_err("Unable to request IRQ: %d\n", ret);
+103 goto fail3;
104 }
105
-106 return 0;
+106 return 0;
107
-108/* cleanup what has been setup so far */
+108/* cleanup what has been setup so far */
109fail3:
110 free_irq(button_irqs[0], NULL);
111
@@ -4767,24 +4810,24 @@ appropriate for your board.
115fail1:
116 gpio_free_array(leds, ARRAY_SIZE(leds));
117
-118 return ret;
+118 return ret;
119}
120
-121static void __exit intrpt_exit(void)
+121static void __exit intrpt_exit(void)
122{
-123 int i;
+123 int i;
124
-125 pr_info("%s\n", __func__);
+125 pr_info("%s\n", __func__);
126
-127 /* free irqs */
+127 /* free irqs */
128 free_irq(button_irqs[0], NULL);
129 free_irq(button_irqs[1], NULL);
130
-131 /* turn all LEDs off */
-132 for (i = 0; i < ARRAY_SIZE(leds); i++)
+131 /* turn all LEDs off */
+132 for (i = 0; i < ARRAY_SIZE(leds); i++)
133 gpio_set_value(leds[i].gpio, 0);
134
-135 /* unregister */
+135 /* unregister */
136 gpio_free_array(leds, ARRAY_SIZE(leds));
137 gpio_free_array(buttons, ARRAY_SIZE(buttons));
138}
@@ -4792,153 +4835,153 @@ appropriate for your board.
140module_init(intrpt_init);
141module_exit(intrpt_exit);
142
-143MODULE_LICENSE("GPL");
-144MODULE_DESCRIPTION("Handle some GPIO interrupts");
-15.3 Bottom Half
-1/*
-2 * bottomhalf.c - Top and bottom half interrupt handling
-3 *
-4 * Based upon the RPi example by Stefan Wendler (devnull@kaltpost.de)
-5 * from:
-6 * https://github.com/wendlers/rpi-kmod-samples
-7 *
-8 * Press one button to turn on a LED and another to turn it off
-9 */
+
+1/*
+2 * bottomhalf.c - Top and bottom half interrupt handling
+3 *
+4 * Based upon the RPi example by Stefan Wendler (devnull@kaltpost.de)
+5 * from:
+6 * https://github.com/wendlers/rpi-kmod-samples
+7 *
+8 * Press one button to turn on a LED and another to turn it off
+9 */
10
-11#include <linux/delay.h>
-12#include <linux/gpio.h>
-13#include <linux/interrupt.h>
-14#include <linux/kernel.h>
-15#include <linux/module.h>
+11#include <linux/delay.h>
+12#include <linux/gpio.h>
+13#include <linux/interrupt.h>
+14#include <linux/kernel.h>
+15#include <linux/module.h>
16
-17/* Macro DECLARE_TASKLET_OLD exists for compatibiity.
-18 * See https://lwn.net/Articles/830964/
-19 */
-20#ifndef DECLARE_TASKLET_OLD
-21#define DECLARE_TASKLET_OLD(arg1, arg2) DECLARE_TASKLET(arg1, arg2, 0L)
-22#endif
+17/* Macro DECLARE_TASKLET_OLD exists for compatibiity.
+18 * See https://lwn.net/Articles/830964/
+19 */
+20#ifndef DECLARE_TASKLET_OLD
+21#define DECLARE_TASKLET_OLD(arg1, arg2) DECLARE_TASKLET(arg1, arg2, 0L)
+22#endif
23
-24static int button_irqs[] = { -1, -1 };
+24static int button_irqs[] = { -1, -1 };
25
-26/* Define GPIOs for LEDs.
-27 * TODO: Change the numbers for the GPIO on your board.
-28 */
-29static struct gpio leds[] = { { 4, GPIOF_OUT_INIT_LOW, "LED 1" } };
+26/* Define GPIOs for LEDs.
+27 * TODO: Change the numbers for the GPIO on your board.
+28 */
+29static struct gpio leds[] = { { 4, GPIOF_OUT_INIT_LOW, "LED 1" } };
30
-31/* Define GPIOs for BUTTONS
-32 * TODO: Change the numbers for the GPIO on your board.
-33 */
-34static struct gpio buttons[] = {
-35 { 17, GPIOF_IN, "LED 1 ON BUTTON" },
-36 { 18, GPIOF_IN, "LED 1 OFF BUTTON" },
+31/* Define GPIOs for BUTTONS
+32 * TODO: Change the numbers for the GPIO on your board.
+33 */
+34static struct gpio buttons[] = {
+35 { 17, GPIOF_IN, "LED 1 ON BUTTON" },
+36 { 18, GPIOF_IN, "LED 1 OFF BUTTON" },
37};
38
-39/* Tasklet containing some non-trivial amount of processing */
-40static void bottomhalf_tasklet_fn(unsigned long data)
+39/* Tasklet containing some non-trivial amount of processing */
+40static void bottomhalf_tasklet_fn(unsigned long data)
41{
-42 pr_info("Bottom half tasklet starts\n");
-43 /* do something which takes a while */
+42 pr_info("Bottom half tasklet starts\n");
+43 /* do something which takes a while */
44 mdelay(500);
-45 pr_info("Bottom half tasklet ends\n");
+45 pr_info("Bottom half tasklet ends\n");
46}
47
-48static DECLARE_TASKLET_OLD(buttontask, bottomhalf_tasklet_fn);
+48static DECLARE_TASKLET_OLD(buttontask, bottomhalf_tasklet_fn);
49
-50/* interrupt function triggered when a button is pressed */
-51static irqreturn_t button_isr(int irq, void *data)
+50/* interrupt function triggered when a button is pressed */
+51static irqreturn_t button_isr(int irq, void *data)
52{
-53 /* Do something quickly right now */
-54 if (irq == button_irqs[0] && !gpio_get_value(leds[0].gpio))
+53 /* Do something quickly right now */
+54 if (irq == button_irqs[0] && !gpio_get_value(leds[0].gpio))
55 gpio_set_value(leds[0].gpio, 1);
-56 else if (irq == button_irqs[1] && gpio_get_value(leds[0].gpio))
+56 else if (irq == button_irqs[1] && gpio_get_value(leds[0].gpio))
57 gpio_set_value(leds[0].gpio, 0);
58
-59 /* Do the rest at leisure via the scheduler */
+59 /* Do the rest at leisure via the scheduler */
60 tasklet_schedule(&buttontask);
61
-62 return IRQ_HANDLED;
+62 return IRQ_HANDLED;
63}
64
-65static int __init bottomhalf_init(void)
+65static int __init bottomhalf_init(void)
66{
-67 int ret = 0;
+67 int ret = 0;
68
-69 pr_info("%s\n", __func__);
+69 pr_info("%s\n", __func__);
70
-71 /* register LED gpios */
+71 /* register LED gpios */
72 ret = gpio_request_array(leds, ARRAY_SIZE(leds));
73
-74 if (ret) {
-75 pr_err("Unable to request GPIOs for LEDs: %d\n", ret);
-76 return ret;
+74 if (ret) {
+75 pr_err("Unable to request GPIOs for LEDs: %d\n", ret);
+76 return ret;
77 }
78
-79 /* register BUTTON gpios */
+79 /* register BUTTON gpios */
80 ret = gpio_request_array(buttons, ARRAY_SIZE(buttons));
81
-82 if (ret) {
-83 pr_err("Unable to request GPIOs for BUTTONs: %d\n", ret);
-84 goto fail1;
+82 if (ret) {
+83 pr_err("Unable to request GPIOs for BUTTONs: %d\n", ret);
+84 goto fail1;
85 }
86
-87 pr_info("Current button1 value: %d\n", gpio_get_value(buttons[0].gpio));
+87 pr_info("Current button1 value: %d\n", gpio_get_value(buttons[0].gpio));
88
89 ret = gpio_to_irq(buttons[0].gpio);
90
-91 if (ret < 0) {
-92 pr_err("Unable to request IRQ: %d\n", ret);
-93 goto fail2;
+91 if (ret < 0) {
+92 pr_err("Unable to request IRQ: %d\n", ret);
+93 goto fail2;
94 }
95
96 button_irqs[0] = ret;
97
-98 pr_info("Successfully requested BUTTON1 IRQ # %d\n", button_irqs[0]);
+98 pr_info("Successfully requested BUTTON1 IRQ # %d\n", button_irqs[0]);
99
100 ret = request_irq(button_irqs[0], button_isr,
101 IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
-102 "gpiomod#button1", NULL);
+102 "gpiomod#button1", NULL);
103
-104 if (ret) {
-105 pr_err("Unable to request IRQ: %d\n", ret);
-106 goto fail2;
+104 if (ret) {
+105 pr_err("Unable to request IRQ: %d\n", ret);
+106 goto fail2;
107 }
108
109 ret = gpio_to_irq(buttons[1].gpio);
110
-111 if (ret < 0) {
-112 pr_err("Unable to request IRQ: %d\n", ret);
-113 goto fail2;
+111 if (ret < 0) {
+112 pr_err("Unable to request IRQ: %d\n", ret);
+113 goto fail2;
114 }
115
116 button_irqs[1] = ret;
117
-118 pr_info("Successfully requested BUTTON2 IRQ # %d\n", button_irqs[1]);
+118 pr_info("Successfully requested BUTTON2 IRQ # %d\n", button_irqs[1]);
119
120 ret = request_irq(button_irqs[1], button_isr,
121 IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
-122 "gpiomod#button2", NULL);
+122 "gpiomod#button2", NULL);
123
-124 if (ret) {
-125 pr_err("Unable to request IRQ: %d\n", ret);
-126 goto fail3;
+124 if (ret) {
+125 pr_err("Unable to request IRQ: %d\n", ret);
+126 goto fail3;
127 }
128
-129 return 0;
+129 return 0;
130
-131/* cleanup what has been setup so far */
+131/* cleanup what has been setup so far */
132fail3:
133 free_irq(button_irqs[0], NULL);
134
@@ -4948,24 +4991,24 @@ when an interrupt is triggered.
138fail1:
139 gpio_free_array(leds, ARRAY_SIZE(leds));
140
-141 return ret;
+141 return ret;
142}
143
-144static void __exit bottomhalf_exit(void)
+144static void __exit bottomhalf_exit(void)
145{
-146 int i;
+146 int i;
147
-148 pr_info("%s\n", __func__);
+148 pr_info("%s\n", __func__);
149
-150 /* free irqs */
+150 /* free irqs */
151 free_irq(button_irqs[0], NULL);
152 free_irq(button_irqs[1], NULL);
153
-154 /* turn all LEDs off */
-155 for (i = 0; i < ARRAY_SIZE(leds); i++)
+154 /* turn all LEDs off */
+155 for (i = 0; i < ARRAY_SIZE(leds); i++)
156 gpio_set_value(leds[i].gpio, 0);
157
-158 /* unregister */
+158 /* unregister */
159 gpio_free_array(leds, ARRAY_SIZE(leds));
160 gpio_free_array(buttons, ARRAY_SIZE(buttons));
161}
@@ -4973,285 +5016,285 @@ when an interrupt is triggered.
163module_init(bottomhalf_init);
164module_exit(bottomhalf_exit);
165
-166MODULE_LICENSE("GPL");
-167MODULE_DESCRIPTION("Interrupt with top and bottom half");
-16 Crypto
-16.1 Hash functions
-1/*
-2 * cryptosha256.c
-3 */
-4#include <crypto/internal/hash.h>
-5#include <linux/module.h>
+
+1/*
+2 * cryptosha256.c
+3 */
+4#include <crypto/internal/hash.h>
+5#include <linux/module.h>
6
-7#define SHA256_LENGTH 32
+7#define SHA256_LENGTH 32
8
-9static void show_hash_result(char *plaintext, char *hash_sha256)
+9static void show_hash_result(char *plaintext, char *hash_sha256)
10{
-11 int i;
-12 char str[SHA256_LENGTH * 2 + 1];
+11 int i;
+12 char str[SHA256_LENGTH * 2 + 1];
13
-14 pr_info("sha256 test for string: \"%s\"\n", plaintext);
-15 for (i = 0; i < SHA256_LENGTH; i++)
-16 sprintf(&str[i * 2], "%02x", (unsigned char)hash_sha256[i]);
+14 pr_info("sha256 test for string: \"%s\"\n", plaintext);
+15 for (i = 0; i < SHA256_LENGTH; i++)
+16 sprintf(&str[i * 2], "%02x", (unsigned char)hash_sha256[i]);
17 str[i * 2] = 0;
-18 pr_info("%s\n", str);
+18 pr_info("%s\n", str);
19}
20
-21static int cryptosha256_init(void)
+21static int cryptosha256_init(void)
22{
-23 char *plaintext = "This is a test";
-24 char hash_sha256[SHA256_LENGTH];
-25 struct crypto_shash *sha256;
-26 struct shash_desc *shash;
+23 char *plaintext = "This is a test";
+24 char hash_sha256[SHA256_LENGTH];
+25 struct crypto_shash *sha256;
+26 struct shash_desc *shash;
27
-28 sha256 = crypto_alloc_shash("sha256", 0, 0);
-29 if (IS_ERR(sha256))
-30 return -1;
+28 sha256 = crypto_alloc_shash("sha256", 0, 0);
+29 if (IS_ERR(sha256))
+30 return -1;
31
-32 shash = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(sha256),
+32 shash = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(sha256),
33 GFP_KERNEL);
-34 if (!shash)
-35 return -ENOMEM;
+34 if (!shash)
+35 return -ENOMEM;
36
37 shash->tfm = sha256;
38
-39 if (crypto_shash_init(shash))
-40 return -1;
+39 if (crypto_shash_init(shash))
+40 return -1;
41
-42 if (crypto_shash_update(shash, plaintext, strlen(plaintext)))
-43 return -1;
+42 if (crypto_shash_update(shash, plaintext, strlen(plaintext)))
+43 return -1;
44
-45 if (crypto_shash_final(shash, hash_sha256))
-46 return -1;
+45 if (crypto_shash_final(shash, hash_sha256))
+46 return -1;
47
48 kfree(shash);
49 crypto_free_shash(sha256);
50
51 show_hash_result(plaintext, hash_sha256);
52
-53 return 0;
+53 return 0;
54}
55
-56static void cryptosha256_exit(void)
+56static void cryptosha256_exit(void)
57{
58}
59
60module_init(cryptosha256_init);
61module_exit(cryptosha256_exit);
62
-63MODULE_DESCRIPTION("sha256 hash test");
-64MODULE_LICENSE("GPL");
-1sudo insmod cryptosha256.ko
+
1sudo insmod cryptosha256.ko
2sudo dmesg
-1sudo rmmod cryptosha256
-1sudo rmmod cryptosha256
+16.2 Symmetric key encryption
-1/*
-2 * cryptosk.c
-3 */
-4#include <crypto/internal/skcipher.h>
-5#include <linux/crypto.h>
-6#include <linux/module.h>
-7#include <linux/random.h>
-8#include <linux/scatterlist.h>
+
+1/*
+2 * cryptosk.c
+3 */
+4#include <crypto/internal/skcipher.h>
+5#include <linux/crypto.h>
+6#include <linux/module.h>
+7#include <linux/random.h>
+8#include <linux/scatterlist.h>
9
-10#define SYMMETRIC_KEY_LENGTH 32
-11#define CIPHER_BLOCK_SIZE 16
+10#define SYMMETRIC_KEY_LENGTH 32
+11#define CIPHER_BLOCK_SIZE 16
12
-13struct tcrypt_result {
-14 struct completion completion;
-15 int err;
+13struct tcrypt_result {
+14 struct completion completion;
+15 int err;
16};
17
-18struct skcipher_def {
-19 struct scatterlist sg;
-20 struct crypto_skcipher *tfm;
-21 struct skcipher_request *req;
-22 struct tcrypt_result result;
-23 char *scratchpad;
-24 char *ciphertext;
-25 char *ivdata;
+18struct skcipher_def {
+19 struct scatterlist sg;
+20 struct crypto_skcipher *tfm;
+21 struct skcipher_request *req;
+22 struct tcrypt_result result;
+23 char *scratchpad;
+24 char *ciphertext;
+25 char *ivdata;
26};
27
-28static struct skcipher_def sk;
+28static struct skcipher_def sk;
29
-30static void test_skcipher_finish(struct skcipher_def *sk)
+30static void test_skcipher_finish(struct skcipher_def *sk)
31{
-32 if (sk->tfm)
+32 if (sk->tfm)
33 crypto_free_skcipher(sk->tfm);
-34 if (sk->req)
+34 if (sk->req)
35 skcipher_request_free(sk->req);
-36 if (sk->ivdata)
+36 if (sk->ivdata)
37 kfree(sk->ivdata);
-38 if (sk->scratchpad)
+38 if (sk->scratchpad)
39 kfree(sk->scratchpad);
-40 if (sk->ciphertext)
+40 if (sk->ciphertext)
41 kfree(sk->ciphertext);
42}
43
-44static int test_skcipher_result(struct skcipher_def *sk, int rc)
+44static int test_skcipher_result(struct skcipher_def *sk, int rc)
45{
-46 switch (rc) {
-47 case 0:
-48 break;
-49 case -EINPROGRESS || -EBUSY:
+46 switch (rc) {
+47 case 0:
+48 break;
+49 case -EINPROGRESS || -EBUSY:
50 rc = wait_for_completion_interruptible(&sk->result.completion);
-51 if (!rc && !sk->result.err) {
+51 if (!rc && !sk->result.err) {
52 reinit_completion(&sk->result.completion);
-53 break;
+53 break;
54 }
-55 pr_info("skcipher encrypt returned with %d result %d\n", rc,
+55 pr_info("skcipher encrypt returned with %d result %d\n", rc,
56 sk->result.err);
-57 break;
-58 default:
-59 pr_info("skcipher encrypt returned with %d result %d\n", rc,
+57 break;
+58 default:
+59 pr_info("skcipher encrypt returned with %d result %d\n", rc,
60 sk->result.err);
-61 break;
+61 break;
62 }
63
64 init_completion(&sk->result.completion);
65
-66 return rc;
+66 return rc;
67}
68
-69static void test_skcipher_callback(struct crypto_async_request *req, int error)
+69static void test_skcipher_callback(struct crypto_async_request *req, int error)
70{
-71 struct tcrypt_result *result = req->data;
+71 struct tcrypt_result *result = req->data;
72
-73 if (error == -EINPROGRESS)
-74 return;
+73 if (error == -EINPROGRESS)
+74 return;
75
76 result->err = error;
77 complete(&result->completion);
-78 pr_info("Encryption finished successfully\n");
+78 pr_info("Encryption finished successfully\n");
79
-80 /* decrypt data */
-81#if 0
-82 memset((void*)sk.scratchpad, '-', CIPHER_BLOCK_SIZE);
-83 ret = crypto_skcipher_decrypt(sk.req);
-84 ret = test_skcipher_result(&sk, ret);
-85 if (ret)
-86 return;
+80 /* decrypt data */
+81#if 0
+82 memset((void*)sk.scratchpad, '-', CIPHER_BLOCK_SIZE);
+83 ret = crypto_skcipher_decrypt(sk.req);
+84 ret = test_skcipher_result(&sk, ret);
+85 if (ret)
+86 return;
87
-88 sg_copy_from_buffer(&sk.sg, 1, sk.scratchpad, CIPHER_BLOCK_SIZE);
-89 sk.scratchpad[CIPHER_BLOCK_SIZE-1] = 0;
+88 sg_copy_from_buffer(&sk.sg, 1, sk.scratchpad, CIPHER_BLOCK_SIZE);
+89 sk.scratchpad[CIPHER_BLOCK_SIZE-1] = 0;
90
-91 pr_info("Decryption request successful\n");
-92 pr_info("Decrypted: %s\n", sk.scratchpad);
-93#endif
+91 pr_info("Decryption request successful\n");
+92 pr_info("Decrypted: %s\n", sk.scratchpad);
+93#endif
94}
95
-96static int test_skcipher_encrypt(char *plaintext, char *password,
-97 struct skcipher_def *sk)
+96static int test_skcipher_encrypt(char *plaintext, char *password,
+97 struct skcipher_def *sk)
98{
-99 int ret = -EFAULT;
-100 unsigned char key[SYMMETRIC_KEY_LENGTH];
+99 int ret = -EFAULT;
+100 unsigned char key[SYMMETRIC_KEY_LENGTH];
101
-102 if (!sk->tfm) {
-103 sk->tfm = crypto_alloc_skcipher("cbc-aes-aesni", 0, 0);
-104 if (IS_ERR(sk->tfm)) {
-105 pr_info("could not allocate skcipher handle\n");
-106 return PTR_ERR(sk->tfm);
+102 if (!sk->tfm) {
+103 sk->tfm = crypto_alloc_skcipher("cbc-aes-aesni", 0, 0);
+104 if (IS_ERR(sk->tfm)) {
+105 pr_info("could not allocate skcipher handle\n");
+106 return PTR_ERR(sk->tfm);
107 }
108 }
109
-110 if (!sk->req) {
+110 if (!sk->req) {
111 sk->req = skcipher_request_alloc(sk->tfm, GFP_KERNEL);
-112 if (!sk->req) {
-113 pr_info("could not allocate skcipher request\n");
+112 if (!sk->req) {
+113 pr_info("could not allocate skcipher request\n");
114 ret = -ENOMEM;
-115 goto out;
+115 goto out;
116 }
117 }
118
119 skcipher_request_set_callback(sk->req, CRYPTO_TFM_REQ_MAY_BACKLOG,
120 test_skcipher_callback, &sk->result);
121
-122 /* clear the key */
-123 memset((void *)key, '\0', SYMMETRIC_KEY_LENGTH);
+122 /* clear the key */
+123 memset((void *)key, '\0', SYMMETRIC_KEY_LENGTH);
124
-125 /* Use the world's favourite password */
-126 sprintf((char *)key, "%s", password);
+125 /* Use the world's favourite password */
+126 sprintf((char *)key, "%s", password);
127
-128 /* AES 256 with given symmetric key */
-129 if (crypto_skcipher_setkey(sk->tfm, key, SYMMETRIC_KEY_LENGTH)) {
-130 pr_info("key could not be set\n");
+128 /* AES 256 with given symmetric key */
+129 if (crypto_skcipher_setkey(sk->tfm, key, SYMMETRIC_KEY_LENGTH)) {
+130 pr_info("key could not be set\n");
131 ret = -EAGAIN;
-132 goto out;
+132 goto out;
133 }
-134 pr_info("Symmetric key: %s\n", key);
-135 pr_info("Plaintext: %s\n", plaintext);
+134 pr_info("Symmetric key: %s\n", key);
+135 pr_info("Plaintext: %s\n", plaintext);
136
-137 if (!sk->ivdata) {
-138 /* see https://en.wikipedia.org/wiki/Initialization_vector */
+137 if (!sk->ivdata) {
+138 /* see https://en.wikipedia.org/wiki/Initialization_vector */
139 sk->ivdata = kmalloc(CIPHER_BLOCK_SIZE, GFP_KERNEL);
-140 if (!sk->ivdata) {
-141 pr_info("could not allocate ivdata\n");
-142 goto out;
+140 if (!sk->ivdata) {
+141 pr_info("could not allocate ivdata\n");
+142 goto out;
143 }
144 get_random_bytes(sk->ivdata, CIPHER_BLOCK_SIZE);
145 }
146
-147 if (!sk->scratchpad) {
-148 /* The text to be encrypted */
+147 if (!sk->scratchpad) {
+148 /* The text to be encrypted */
149 sk->scratchpad = kmalloc(CIPHER_BLOCK_SIZE, GFP_KERNEL);
-150 if (!sk->scratchpad) {
-151 pr_info("could not allocate scratchpad\n");
-152 goto out;
+150 if (!sk->scratchpad) {
+151 pr_info("could not allocate scratchpad\n");
+152 goto out;
153 }
154 }
-155 sprintf((char *)sk->scratchpad, "%s", plaintext);
+155 sprintf((char *)sk->scratchpad, "%s", plaintext);
156
157 sg_init_one(&sk->sg, sk->scratchpad, CIPHER_BLOCK_SIZE);
158 skcipher_request_set_crypt(sk->req, &sk->sg, &sk->sg, CIPHER_BLOCK_SIZE,
159 sk->ivdata);
160 init_completion(&sk->result.completion);
161
-162 /* encrypt data */
+162 /* encrypt data */
163 ret = crypto_skcipher_encrypt(sk->req);
164 ret = test_skcipher_result(sk, ret);
-165 if (ret)
-166 goto out;
+165 if (ret)
+166 goto out;
167
-168 pr_info("Encryption request successful\n");
+168 pr_info("Encryption request successful\n");
169
170out:
-171 return ret;
+171 return ret;
172}
173
-174static int cryptoapi_init(void)
+174static int cryptoapi_init(void)
175{
-176 /* The world's favorite password */
-177 char *password = "password123";
+176 /* The world's favorite password */
+177 char *password = "password123";
178
179 sk.tfm = NULL;
180 sk.req = NULL;
@@ -5259,11 +5302,11 @@ and a password.
182 sk.ciphertext = NULL;
183 sk.ivdata = NULL;
184
-185 test_skcipher_encrypt("Testing", password, &sk);
-186 return 0;
+185 test_skcipher_encrypt("Testing", password, &sk);
+186 return 0;
187}
188
-189static void cryptoapi_exit(void)
+189static void cryptoapi_exit(void)
190{
191 test_skcipher_finish(&sk);
192}
@@ -5271,12 +5314,12 @@ and a password.
194module_init(cryptoapi_init);
195module_exit(cryptoapi_exit);
196
-197MODULE_DESCRIPTION("Symmetric key encryption example");
-198MODULE_LICENSE("GPL");
-17 Standardizing the interfaces: The Device Model
-1/*
-2 * devicemodel.c
-3 */
-4#include <linux/kernel.h>
-5#include <linux/module.h>
-6#include <linux/platform_device.h>
+
+1/*
+2 * devicemodel.c
+3 */
+4#include <linux/kernel.h>
+5#include <linux/module.h>
+6#include <linux/platform_device.h>
7
-8struct devicemodel_data {
-9 char *greeting;
-10 int number;
+8struct devicemodel_data {
+9 char *greeting;
+10 int number;
11};
12
-13static int devicemodel_probe(struct platform_device *dev)
+13static int devicemodel_probe(struct platform_device *dev)
14{
-15 struct devicemodel_data *pd =
-16 (struct devicemodel_data *)(dev->dev.platform_data);
+15 struct devicemodel_data *pd =
+16 (struct devicemodel_data *)(dev->dev.platform_data);
17
-18 pr_info("devicemodel probe\n");
-19 pr_info("devicemodel greeting: %s; %d\n", pd->greeting, pd->number);
+18 pr_info("devicemodel probe\n");
+19 pr_info("devicemodel greeting: %s; %d\n", pd->greeting, pd->number);
20
-21 /* Your device initialization code */
+21 /* Your device initialization code */
22
-23 return 0;
+23 return 0;
24}
25
-26static int devicemodel_remove(struct platform_device *dev)
+26static int devicemodel_remove(struct platform_device *dev)
27{
-28 pr_info("devicemodel example removed\n");
+28 pr_info("devicemodel example removed\n");
29
-30 /* Your device removal code */
+30 /* Your device removal code */
31
-32 return 0;
+32 return 0;
33}
34
-35static int devicemodel_suspend(struct device *dev)
+35static int devicemodel_suspend(struct device *dev)
36{
-37 pr_info("devicemodel example suspend\n");
+37 pr_info("devicemodel example suspend\n");
38
-39 /* Your device suspend code */
+39 /* Your device suspend code */
40
-41 return 0;
+41 return 0;
42}
43
-44static int devicemodel_resume(struct device *dev)
+44static int devicemodel_resume(struct device *dev)
45{
-46 pr_info("devicemodel example resume\n");
+46 pr_info("devicemodel example resume\n");
47
-48 /* Your device resume code */
+48 /* Your device resume code */
49
-50 return 0;
+50 return 0;
51}
52
-53static const struct dev_pm_ops devicemodel_pm_ops = {
+53static const struct dev_pm_ops devicemodel_pm_ops = {
54 .suspend = devicemodel_suspend,
55 .resume = devicemodel_resume,
56 .poweroff = devicemodel_suspend,
@@ -5345,10 +5388,10 @@ functions.
59 .restore = devicemodel_resume,
60};
61
-62static struct platform_driver devicemodel_driver = {
+62static struct platform_driver devicemodel_driver = {
63 .driver =
64 {
-65 .name = "devicemodel_example",
+65 .name = "devicemodel_example",
66 .owner = THIS_MODULE,
67 .pm = &devicemodel_pm_ops,
68 },
@@ -5356,40 +5399,40 @@ functions.
70 .remove = devicemodel_remove,
71};
72
-73static int devicemodel_init(void)
+73static int devicemodel_init(void)
74{
-75 int ret;
+75 int ret;
76
-77 pr_info("devicemodel init\n");
+77 pr_info("devicemodel init\n");
78
79 ret = platform_driver_register(&devicemodel_driver);
80
-81 if (ret) {
-82 pr_err("Unable to register driver\n");
-83 return ret;
+81 if (ret) {
+82 pr_err("Unable to register driver\n");
+83 return ret;
84 }
85
-86 return 0;
+86 return 0;
87}
88
-89static void devicemodel_exit(void)
+89static void devicemodel_exit(void)
90{
-91 pr_info("devicemodel exit\n");
+91 pr_info("devicemodel exit\n");
92 platform_driver_unregister(&devicemodel_driver);
93}
94
95module_init(devicemodel_init);
96module_exit(devicemodel_exit);
97
-98MODULE_LICENSE("GPL");
-99MODULE_DESCRIPTION("Linux Device Model example");
-18 Optimizations
-18.1 Likely and Unlikely conditions
-1bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx);
-2if (unlikely(!bvl)) {
+
1bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx);
+2if (unlikely(!bvl)) {
3 mempool_free(bio, bio_pool);
4 bio = NULL;
-5 goto out;
+5 goto out;
6}
- unlikely
+ 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.
-19 Common Pitfalls
-19.1 Using standard libraries
-19.2 Disabling interrupts
-20 Where To Go From Here?
-