Add RCU section and example

examples/Makefile

@@ -41,6 +41,7 @@ obj-m += dma.o
 obj-m += blkram.o
 obj-m += vnetloop.o
 obj-m += kmem_cache.o
+obj-m += example_rcu.o
 
 KDIR ?= /lib/modules/$(shell uname -r)/build
 PWD := $(CURDIR)

examples/example_rcu.c

@@ -0,0 +1,105 @@
+#include <linux/module.h>
+#include <linux/rcupdate.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
+
+struct my_data {
+    int value;
+};
+
+static struct my_data __rcu *shared_data;
+static DEFINE_SPINLOCK(data_lock);
+static struct task_struct *reader_thread;
+
+static int reader_thread_fn(void *data)
+{
+    while (!kthread_should_stop()) {
+        struct my_data *p;
+        int val;
+        bool valid = false;
+
+        rcu_read_lock();
+        p = rcu_dereference(shared_data);
+        if (p) {
+            val = p->value;
+            valid = true;
+        }
+        rcu_read_unlock();
+
+        if (valid)
+            pr_info("RCU Reader: value = %d\n", val);
+        else
+            pr_info("RCU Reader: data is NULL\n");
+
+        msleep(500);
+    }
+    return 0;
+}
+
+static void update_data(int new_value)
+{
+    struct my_data *new_p, *old_p;
+
+    new_p = kmalloc(sizeof(*new_p), GFP_KERNEL);
+    if (!new_p)
+        return;
+    new_p->value = new_value;
+
+    spin_lock(&data_lock);
+
+    old_p = rcu_dereference_protected(shared_data, lockdep_is_held(&data_lock));
+    rcu_assign_pointer(shared_data, new_p);
+
+    spin_unlock(&data_lock);
+
+    if (old_p) {
+        synchronize_rcu();
+        kfree(old_p);
+        pr_info("RCU Updater: old memory freed\n");
+    }
+}
+
+static int __init example_rcu_init(void)
+{
+    pr_info("Loading RCU example module\n");
+
+    update_data(42);
+
+    reader_thread = kthread_run(reader_thread_fn, NULL, "rcu_reader");
+    if (IS_ERR(reader_thread))
+        return PTR_ERR(reader_thread);
+
+    msleep(1000);
+    update_data(100);
+    msleep(1000);
+
+    return 0;
+}
+
+static void __exit example_rcu_exit(void)
+{
+    struct my_data *old_p;
+
+    pr_info("Unloading RCU example module\n");
+
+    kthread_stop(reader_thread);
+
+    spin_lock(&data_lock);
+    old_p = rcu_dereference_protected(shared_data, lockdep_is_held(&data_lock));
+    RCU_INIT_POINTER(shared_data, NULL);
+    spin_unlock(&data_lock);
+
+    if (old_p) {
+        synchronize_rcu();
+        kfree(old_p);
+    }
+}
+
+module_init(example_rcu_init);
+module_exit(example_rcu_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Kuan-Wei Chiu <visitorckw@gmail.com>");
+MODULE_DESCRIPTION("RCU Example Module");

lkmpg.tex

@@ -2318,6 +2318,36 @@ \subsection{Atomic operations}
   \item \href{https://lwn.net/Articles/698315/}{Atomic usage patterns in the kernel}
 \end{itemize}
 
+\subsection{Read-Copy-Update (RCU)}
+\label{sec:rcu}
+Read-Copy-Update (RCU) is a synchronization mechanism that allows extremely fast, lock-free reads while still permitting concurrent updates.
+It is highly optimized for read-mostly scenarios.
+
+Unlike spinlocks or mutexes, RCU readers do not acquire any locks or write to shared memory.
+This completely avoids cache-line bouncing and results in near-zero overhead for the read path.
+The tradeoff is that the updaters bear the cost of synchronization.
+When modifying a data structure, an updater creates a copy, modifies it, and then publishes the new version by replacing the old pointer in a single atomic operation.
+
+Because concurrent readers might still be accessing the old data, the updater cannot free it immediately.
+Instead, it must wait for a "grace period" to elapse---a duration long enough to ensure that all pre-existing readers have left their critical sections.
+Only then can the old memory be safely reclaimed.
+
+The RCU API relies on a few fundamental primitives:
+\begin{itemize}
+  \item \cpp|rcu_read_lock()| and \cpp|rcu_read_unlock()|: Define a read-side critical section. Readers must not sleep inside this section.
+  \item \cpp|rcu_dereference()|: Safely fetches an RCU-protected pointer for readers, preventing stale or reordered pointer loads.
+  \item \cpp|rcu_assign_pointer()|: Used by updaters to publish a new pointer.
+  \item \cpp|synchronize_rcu()|: Blocks the updater until all pre-existing RCU readers have completed their critical sections.
+\end{itemize}
+
+Keep in mind that RCU only protects the readers.
+Concurrent writers must still serialize among themselves using a standard lock, such as a spinlock or a mutex.
+For more comprehensive details, you can refer to the official Linux kernel documentation on RCU: \url{https://docs.kernel.org/RCU/whatisRCU.html}.
+
+The following example demonstrates a basic RCU implementation where a reader safely accesses shared data while a writer updates it.
+
+\samplec{examples/example_rcu.c}
+
 % FIXME: we should rewrite this section
 \section{Replacing Print Macros}
 \label{sec:print_macros}