[PATCH] kprobes base patch

This patch helps developers to trap at almost any kernel code address,
specifying a handler routine to be invoked when the breakpoint is hit.  

Useful for analysing the Linux kernel by collecting debugging information
non-disruptively.  Employs single-stepping out-of-line to avoid probe
misses on SMP and may be especially useful in aiding debugging elusive
races and problems on live systems.  More elaborate dynamic tracing tools
such as DProbes can be built over the kprobes interface.


Helps developers to trap at almost any kernel code address, specifying a
handler routine to be invoked when the breakpoint is hit.  Useful for
analysing the Linux kernel by collecting debugging information
non-disruptively.  Employs single-stepping out-of-line to avoid probe
misses on SMP and may be especially useful in aiding debugging elusive
races and problems on live systems.  More elaborate dynamic tracing tools
such as DProbes can be built over the kprobes interface.

Sample usage:
	To place a probe on __blockdev_direct_IO:
	static int probe_handler(struct kprobe *p, struct pt_regs *)
	{
		... whatever ...
	}
	struct kprobe kp = {
		.addr = __blockdev_direct_IO,
		.pre_handler = probe_handler
	};
	register_kprobe(&kp);

Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 126 insertions, 0 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 47f98594e9e5..a032595fd58c 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_IKCONFIG_PROC) += configs.o
 obj-$(CONFIG_STOP_MACHINE) += stop_machine.o
 obj-$(CONFIG_AUDIT) += audit.o
 obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
+obj-$(CONFIG_KPROBES) += kprobes.o
 
 ifneq ($(CONFIG_IA64),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
new file mode 100644
index 000000000000..7c5fee08665e
--- /dev/null
+++ b/kernel/kprobes.c
@@ -0,0 +1,125 @@
+/*
+ *  Kernel Probes (KProbes)
+ *  kernel/kprobes.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004
+ *
+ * 2002-Oct	Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
+ *		Probes initial implementation (includes suggestions from
+ *		Rusty Russell).
+ * 2004-Aug	Updated by Prasanna S Panchamukhi <prasanna@in.ibm.com> with
+ *		hlists and exceptions notifier as suggested by Andi Kleen.
+ */
+#include <linux/kprobes.h>
+#include <linux/spinlock.h>
+#include <linux/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <asm/cacheflush.h>
+#include <asm/errno.h>
+#include <asm/kdebug.h>
+
+#define KPROBE_HASH_BITS 6
+#define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS)
+
+static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
+
+unsigned int kprobe_cpu = NR_CPUS;
+static spinlock_t kprobe_lock = SPIN_LOCK_UNLOCKED;
+
+/* Locks kprobe: irqs must be disabled */
+void lock_kprobes(void)
+{
+	spin_lock(&kprobe_lock);
+	kprobe_cpu = smp_processor_id();
+}
+
+void unlock_kprobes(void)
+{
+	kprobe_cpu = NR_CPUS;
+	spin_unlock(&kprobe_lock);
+}
+
+/* You have to be holding the kprobe_lock */
+struct kprobe *get_kprobe(void *addr)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+
+	head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)];
+	hlist_for_each(node, head) {
+		struct kprobe *p = hlist_entry(node, struct kprobe, hlist);
+		if (p->addr == addr)
+			return p;
+	}
+	return NULL;
+}
+
+int register_kprobe(struct kprobe *p)
+{
+	int ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&kprobe_lock, flags);
+	INIT_HLIST_NODE(&p->hlist);
+	if (get_kprobe(p->addr)) {
+		ret = -EEXIST;
+		goto out;
+	}
+	hlist_add_head(&p->hlist,
+		       &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]);
+
+	arch_prepare_kprobe(p);
+	p->opcode = *p->addr;
+	*p->addr = BREAKPOINT_INSTRUCTION;
+	flush_icache_range(p->addr, p->addr + sizeof(kprobe_opcode_t));
+      out:
+	spin_unlock_irqrestore(&kprobe_lock, flags);
+	return ret;
+}
+
+void unregister_kprobe(struct kprobe *p)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&kprobe_lock, flags);
+	*p->addr = p->opcode;
+	hlist_del(&p->hlist);
+	flush_icache_range(p->addr, p->addr + sizeof(kprobe_opcode_t));
+	spin_unlock_irqrestore(&kprobe_lock, flags);
+}
+
+static struct notifier_block kprobe_exceptions_nb = {
+	.notifier_call = kprobe_exceptions_notify,
+};
+
+static int __init init_kprobes(void)
+{
+	int i, err = 0;
+
+	/* FIXME allocate the probe table, currently defined statically */
+	/* initialize all list heads */
+	for (i = 0; i < KPROBE_TABLE_SIZE; i++)
+		INIT_HLIST_HEAD(&kprobe_table[i]);
+
+	err = register_die_notifier(&kprobe_exceptions_nb);
+	return err;
+}
+
+__initcall(init_kprobes);
+
+EXPORT_SYMBOL_GPL(register_kprobe);
+EXPORT_SYMBOL_GPL(unregister_kprobe);