[PATCH] kprobes: function-return probes

This patch adds function-return probes to kprobes for the i386
architecture.  This enables you to establish a handler to be run when a
function returns.

1. API

Two new functions are added to kprobes:

	int register_kretprobe(struct kretprobe *rp);
	void unregister_kretprobe(struct kretprobe *rp);

2. Registration and unregistration

2.1 Register

  To register a function-return probe, the user populates the following
  fields in a kretprobe object and calls register_kretprobe() with the
  kretprobe address as an argument:

  kp.addr - the function's address

  handler - this function is run after the ret instruction executes, but
  before control returns to the return address in the caller.

  maxactive - The maximum number of instances of the probed function that
  can be active concurrently.  For example, if the function is non-
  recursive and is called with a spinlock or mutex held, maxactive = 1
  should be enough.  If the function is non-recursive and can never
  relinquish the CPU (e.g., via a semaphore or preemption), NR_CPUS should
  be enough.  maxactive is used to determine how many kretprobe_instance
  objects to allocate for this particular probed function.  If maxactive <=
  0, it is set to a default value (if CONFIG_PREEMPT maxactive=max(10, 2 *
  NR_CPUS) else maxactive=NR_CPUS)

  For example:

    struct kretprobe rp;
    rp.kp.addr = /* entrypoint address */
    rp.handler = /*return probe handler */
    rp.maxactive = /* e.g., 1 or NR_CPUS or 0, see the above explanation */
    register_kretprobe(&rp);

  The following field may also be of interest:

  nmissed - Initialized to zero when the function-return probe is
  registered, and incremented every time the probed function is entered but
  there is no kretprobe_instance object available for establishing the
  function-return probe (i.e., because maxactive was set too low).

2.2 Unregister

  To unregiter a function-return probe, the user calls
  unregister_kretprobe() with the same kretprobe object as registered
  previously.  If a probed function is running when the return probe is
  unregistered, the function will return as expected, but the handler won't
  be run.

3. Limitations

3.1 This patch supports only the i386 architecture, but patches for
    x86_64 and ppc64 are anticipated soon.

3.2 Return probes operates by replacing the return address in the stack
    (or in a known register, such as the lr register for ppc).  This may
    cause __builtin_return_address(0), when invoked from the return-probed
    function, to return the address of the return-probes trampoline.

3.3 This implementation uses the "Multiprobes at an address" feature in
    2.6.12-rc3-mm3.

3.4 Due to a limitation in multi-probes, you cannot currently establish
    a return probe and a jprobe on the same function.  A patch to remove
    this limitation is being tested.

This feature is required by SystemTap (http://sourceware.org/systemtap),
and reflects ideas contributed by several SystemTap developers, including
Will Cohen and Ananth Mavinakayanahalli.

Signed-off-by: Hien Nguyen <hien@us.ibm.com>
Signed-off-by: Prasanna S Panchamukhi <prasanna@in.ibm.com>
Signed-off-by: Frederik Deweerdt <frederik.deweerdt@laposte.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 116 insertions, 1 deletions

diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index 59ff9b45506915..048f754bbe2337 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -23,6 +23,9 @@
  *		Rusty Russell).
  * 2004-July	Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes
  *		interface to access function arguments.
+ * 2005-May	Hien Nguyen <hien@us.ibm.com>, Jim Keniston
+ *		<jkenisto@us.ibm.com> and Prasanna S Panchamukhi
+ *		<prasanna@in.ibm.com> added function-return probes.
  */
 
 #include <linux/config.h>
@@ -91,6 +94,53 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 		regs->eip = (unsigned long)&p->ainsn.insn;
 }
 
+struct task_struct  *arch_get_kprobe_task(void *ptr)
+{
+	return ((struct thread_info *) (((unsigned long) ptr) &
+					(~(THREAD_SIZE -1))))->task;
+}
+
+void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
+{
+	unsigned long *sara = (unsigned long *)&regs->esp;
+	struct kretprobe_instance *ri;
+	static void *orig_ret_addr;
+
+	/*
+	 * Save the return address when the return probe hits
+	 * the first time, and use it to populate the (krprobe
+	 * instance)->ret_addr for subsequent return probes at
+	 * the same addrress since stack address would have
+	 * the kretprobe_trampoline by then.
+	 */
+	if (((void*) *sara) != kretprobe_trampoline)
+		orig_ret_addr = (void*) *sara;
+
+	if ((ri = get_free_rp_inst(rp)) != NULL) {
+		ri->rp = rp;
+		ri->stack_addr = sara;
+		ri->ret_addr = orig_ret_addr;
+		add_rp_inst(ri);
+		/* Replace the return addr with trampoline addr */
+		*sara = (unsigned long) &kretprobe_trampoline;
+	} else {
+		rp->nmissed++;
+	}
+}
+
+void arch_kprobe_flush_task(struct task_struct *tk, spinlock_t *kp_lock)
+{
+	unsigned long flags = 0;
+	struct kretprobe_instance *ri;
+	spin_lock_irqsave(kp_lock, flags);
+	while ((ri = get_rp_inst_tsk(tk)) != NULL) {
+		*((unsigned long *)(ri->stack_addr)) =
+					(unsigned long) ri->ret_addr;
+		recycle_rp_inst(ri);
+	}
+	spin_unlock_irqrestore(kp_lock, flags);
+}
+
 /*
  * Interrupts are disabled on entry as trap3 is an interrupt gate and they
  * remain disabled thorough out this function.
@@ -184,6 +234,55 @@ no_kprobe:
 }
 
 /*
+ * For function-return probes, init_kprobes() establishes a probepoint
+ * here. When a retprobed function returns, this probe is hit and
+ * trampoline_probe_handler() runs, calling the kretprobe's handler.
+ */
+ void kretprobe_trampoline_holder(void)
+ {
+ 	asm volatile (  ".global kretprobe_trampoline\n"
+ 			"kretprobe_trampoline: \n"
+ 			"nop\n");
+ }
+
+/*
+ * Called when we hit the probe point at kretprobe_trampoline
+ */
+int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct task_struct *tsk;
+	struct kretprobe_instance *ri;
+	struct hlist_head *head;
+	struct hlist_node *node;
+	unsigned long *sara = ((unsigned long *) &regs->esp) - 1;
+
+	tsk = arch_get_kprobe_task(sara);
+	head = kretprobe_inst_table_head(tsk);
+
+	hlist_for_each_entry(ri, node, head, hlist) {
+		if (ri->stack_addr == sara && ri->rp) {
+			if (ri->rp->handler)
+				ri->rp->handler(ri, regs);
+		}
+	}
+	return 0;
+}
+
+void trampoline_post_handler(struct kprobe *p, struct pt_regs *regs,
+						unsigned long flags)
+{
+	struct kretprobe_instance *ri;
+	/* RA already popped */
+	unsigned long *sara = ((unsigned long *)&regs->esp) - 1;
+
+	while ((ri = get_rp_inst(sara))) {
+		regs->eip = (unsigned long)ri->ret_addr;
+		recycle_rp_inst(ri);
+	}
+	regs->eflags &= ~TF_MASK;
+}
+
+/*
  * Called after single-stepping.  p->addr is the address of the
  * instruction whose first byte has been replaced by the "int 3"
  * instruction.  To avoid the SMP problems that can occur when we
@@ -266,7 +365,8 @@ static inline int post_kprobe_handler(struct pt_regs *regs)
 	if (current_kprobe->post_handler)
 		current_kprobe->post_handler(current_kprobe, regs, 0);
 
-	resume_execution(current_kprobe, regs);
+	if (current_kprobe->post_handler != trampoline_post_handler)
+		resume_execution(current_kprobe, regs);
 	regs->eflags |= kprobe_saved_eflags;
 
 	unlock_kprobes();
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index be3efba7caf715..aea2ce1145df73 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -37,6 +37,7 @@
 #include <linux/kallsyms.h>
 #include <linux/ptrace.h>
 #include <linux/random.h>
+#include <linux/kprobes.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -339,6 +340,13 @@ void exit_thread(void)
 	struct task_struct *tsk = current;
 	struct thread_struct *t = &tsk->thread;
 
+	/*
+	 * Remove function-return probe instances associated with this task
+	 * and put them back on the free list. Do not insert an exit probe for
+	 * this function, it will be disabled by kprobe_flush_task if you do.
+	 */
+	kprobe_flush_task(tsk);
+
 	/* The process may have allocated an io port bitmap... nuke it. */
 	if (unlikely(NULL != t->io_bitmap_ptr)) {
 		int cpu = get_cpu();
@@ -362,6 +370,13 @@ void flush_thread(void)
 {
 	struct task_struct *tsk = current;
 
+	/*
+	 * Remove function-return probe instances associated with this task
+	 * and put them back on the free list. Do not insert an exit probe for
+	 * this function, it will be disabled by kprobe_flush_task if you do.
+	 */
+	kprobe_flush_task(tsk);
+
 	memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));	
 	/*