[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, 91 insertions, 2 deletions

diff --git a/include/asm-i386/kprobes.h b/include/asm-i386/kprobes.h
index 4092f68d123a..8b6d3a90cd78 100644
--- a/include/asm-i386/kprobes.h
+++ b/include/asm-i386/kprobes.h
@@ -39,6 +39,9 @@ typedef u8 kprobe_opcode_t;
         : (((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR)))
 
 #define JPROBE_ENTRY(pentry)    (kprobe_opcode_t *)pentry
+#define ARCH_SUPPORTS_KRETPROBES
+
+void kretprobe_trampoline(void);
 
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 99ddba5a4e00..fba39f87efec 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -25,21 +25,31 @@
  *              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> and Jim Keniston
+ *              <jkenisto@us.ibm.com>  and Prasanna S Panchamukhi
+ *              <prasanna@in.ibm.com> added function-return probes.
  */
 #include <linux/config.h>
 #include <linux/list.h>
 #include <linux/notifier.h>
 #include <linux/smp.h>
+#include <linux/spinlock.h>
+
 #include <asm/kprobes.h>
 
 struct kprobe;
 struct pt_regs;
+struct kretprobe;
+struct kretprobe_instance;
 typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *);
 typedef int (*kprobe_break_handler_t) (struct kprobe *, struct pt_regs *);
 typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *,
                                        unsigned long flags);
 typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *,
                                        int trapnr);
+typedef int (*kretprobe_handler_t) (struct kretprobe_instance *,
+                                    struct pt_regs *);
+
 struct kprobe {
         struct hlist_node hlist;
 
@@ -85,6 +95,62 @@ struct jprobe {
         kprobe_opcode_t *entry; /* probe handling code to jump to */
 };
 
+#ifdef ARCH_SUPPORTS_KRETPROBES
+extern int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs);
+extern void trampoline_post_handler(struct kprobe *p, struct pt_regs *regs,
+                                                        unsigned long flags);
+extern struct task_struct *arch_get_kprobe_task(void *ptr);
+extern void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs);
+extern void arch_kprobe_flush_task(struct task_struct *tk, spinlock_t *kp_lock);
+#else /* ARCH_SUPPORTS_KRETPROBES */
+static inline void kretprobe_trampoline(void)
+{
+}
+static inline int trampoline_probe_handler(struct kprobe *p,
+                                                struct pt_regs *regs)
+{
+        return 0;
+}
+static inline void trampoline_post_handler(struct kprobe *p,
+                                struct pt_regs *regs, unsigned long flags)
+{
+}
+static inline void arch_prepare_kretprobe(struct kretprobe *rp,
+                                        struct pt_regs *regs)
+{
+}
+static inline void arch_kprobe_flush_task(struct task_struct *tk)
+{
+}
+#define arch_get_kprobe_task(ptr) ((struct task_struct *)NULL)
+#endif /* ARCH_SUPPORTS_KRETPROBES */
+/*
+ * Function-return probe -
+ * Note:
+ * User needs to provide a handler function, and initialize maxactive.
+ * maxactive - The maximum number of instances of the probed function that
+ * can be active concurrently.
+ * nmissed - tracks the number of times the probed function's return was
+ * ignored, due to maxactive being too low.
+ *
+ */
+struct kretprobe {
+        struct kprobe kp;
+        kretprobe_handler_t handler;
+        int maxactive;
+        int nmissed;
+        struct hlist_head free_instances;
+        struct hlist_head used_instances;
+};
+
+struct kretprobe_instance {
+        struct hlist_node uflist; /* either on free list or used list */
+        struct hlist_node hlist;
+        struct kretprobe *rp;
+        void *ret_addr;
+        void *stack_addr;
+};
+
 #ifdef CONFIG_KPROBES
 /* Locks kprobe: irq must be disabled */
 void lock_kprobes(void);
@@ -104,6 +170,7 @@ extern void show_registers(struct pt_regs *regs);
 
 /* Get the kprobe at this addr (if any).  Must have called lock_kprobes */
 struct kprobe *get_kprobe(void *addr);
+struct hlist_head * kretprobe_inst_table_head(struct task_struct *tsk);
 
 int register_kprobe(struct kprobe *p);
 void unregister_kprobe(struct kprobe *p);
@@ -113,7 +180,16 @@ int register_jprobe(struct jprobe *p);
 void unregister_jprobe(struct jprobe *p);
 void jprobe_return(void);
 
-#else
+int register_kretprobe(struct kretprobe *rp);
+void unregister_kretprobe(struct kretprobe *rp);
+
+struct kretprobe_instance *get_free_rp_inst(struct kretprobe *rp);
+struct kretprobe_instance *get_rp_inst(void *sara);
+struct kretprobe_instance *get_rp_inst_tsk(struct task_struct *tk);
+void add_rp_inst(struct kretprobe_instance *ri);
+void kprobe_flush_task(struct task_struct *tk);
+void recycle_rp_inst(struct kretprobe_instance *ri);
+#else /* CONFIG_KPROBES */
 static inline int kprobe_running(void)
 {
         return 0;
@@ -135,5 +211,15 @@ static inline void unregister_jprobe(struct jprobe *p)
 static inline void jprobe_return(void)
 {
 }
-#endif
+static inline int register_kretprobe(struct kretprobe *rp)
+{
+        return -ENOSYS;
+}
+static inline void unregister_kretprobe(struct kretprobe *rp)
+{
+}
+static inline void kprobe_flush_task(struct task_struct *tk)
+{
+}
+#endif                          /* CONFIG_KPROBES */
 #endif                          /* _LINUX_KPROBES_H */