X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fkprobes.c;h=e5342a344c43bee9140d9127f1fe907b21149e8d;hb=61cf693159d6a968a7014e24905143f71ed8ddcf;hp=ce4915dd683a3f35b120a31e1b1a356beb2fb94c;hpb=4e57b6817880946a3a78d5d8cad1ace363f7e449;p=safe%2Fjmp%2Flinux-2.6

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ce4915d..e5342a3 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -32,27 +32,71 @@
  *		<prasanna@in.ibm.com> added function-return probes.
  */
 #include <linux/kprobes.h>
-#include <linux/spinlock.h>
 #include <linux/hash.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/stddef.h>
 #include <linux/module.h>
 #include <linux/moduleloader.h>
+#include <linux/kallsyms.h>
+#include <linux/freezer.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/kdebug.h>
+#include <linux/memory.h>
+
 #include <asm-generic/sections.h>
 #include <asm/cacheflush.h>
 #include <asm/errno.h>
-#include <asm/kdebug.h>
+#include <asm/uaccess.h>
 
 #define KPROBE_HASH_BITS 6
 #define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS)
 
+
+/*
+ * Some oddball architectures like 64bit powerpc have function descriptors
+ * so this must be overridable.
+ */
+#ifndef kprobe_lookup_name
+#define kprobe_lookup_name(name, addr) \
+	addr = ((kprobe_opcode_t *)(kallsyms_lookup_name(name)))
+#endif
+
+static int kprobes_initialized;
 static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
 static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
 
-unsigned int kprobe_cpu = NR_CPUS;
-static DEFINE_SPINLOCK(kprobe_lock);
-static struct kprobe *curr_kprobe;
+/* NOTE: change this value only with kprobe_mutex held */
+static bool kprobes_all_disarmed;
+
+static DEFINE_MUTEX(kprobe_mutex);	/* Protects kprobe_table */
+static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
+static struct {
+	spinlock_t lock ____cacheline_aligned_in_smp;
+} kretprobe_table_locks[KPROBE_TABLE_SIZE];
+
+static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
+{
+	return &(kretprobe_table_locks[hash].lock);
+}
+
+/*
+ * Normally, functions that we'd want to prohibit kprobes in, are marked
+ * __kprobes. But, there are cases where such functions already belong to
+ * a different section (__sched for preempt_schedule)
+ *
+ * For such cases, we now have a blacklist
+ */
+static struct kprobe_blackpoint kprobe_blacklist[] = {
+	{"preempt_schedule",},
+	{"native_get_debugreg",},
+	{"irq_entries_start",},
+	{"common_interrupt",},
+	{NULL}    /* Terminator */
+};
 
+#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
 /*
  * kprobe->ainsn.insn points to the copy of the instruction to be
  * single-stepped. x86_64, POWER4 and above have no-exec support and
@@ -62,30 +106,63 @@ static struct kprobe *curr_kprobe;
 #define INSNS_PER_PAGE	(PAGE_SIZE/(MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
 
 struct kprobe_insn_page {
-	struct hlist_node hlist;
+	struct list_head list;
 	kprobe_opcode_t *insns;		/* Page of instruction slots */
 	char slot_used[INSNS_PER_PAGE];
 	int nused;
+	int ngarbage;
 };
 
-static struct hlist_head kprobe_insn_pages;
+enum kprobe_slot_state {
+	SLOT_CLEAN = 0,
+	SLOT_DIRTY = 1,
+	SLOT_USED = 2,
+};
+
+static DEFINE_MUTEX(kprobe_insn_mutex);	/* Protects kprobe_insn_pages */
+static LIST_HEAD(kprobe_insn_pages);
+static int kprobe_garbage_slots;
+static int collect_garbage_slots(void);
+
+static int __kprobes check_safety(void)
+{
+	int ret = 0;
+#if defined(CONFIG_PREEMPT) && defined(CONFIG_FREEZER)
+	ret = freeze_processes();
+	if (ret == 0) {
+		struct task_struct *p, *q;
+		do_each_thread(p, q) {
+			if (p != current && p->state == TASK_RUNNING &&
+			    p->pid != 0) {
+				printk("Check failed: %s is running\n",p->comm);
+				ret = -1;
+				goto loop_end;
+			}
+		} while_each_thread(p, q);
+	}
+loop_end:
+	thaw_processes();
+#else
+	synchronize_sched();
+#endif
+	return ret;
+}
 
 /**
- * get_insn_slot() - Find a slot on an executable page for an instruction.
+ * __get_insn_slot() - Find a slot on an executable page for an instruction.
  * We allocate an executable page if there's no room on existing ones.
  */
-kprobe_opcode_t __kprobes *get_insn_slot(void)
+static kprobe_opcode_t __kprobes *__get_insn_slot(void)
 {
 	struct kprobe_insn_page *kip;
-	struct hlist_node *pos;
 
-	hlist_for_each(pos, &kprobe_insn_pages) {
-		kip = hlist_entry(pos, struct kprobe_insn_page, hlist);
+ retry:
+	list_for_each_entry(kip, &kprobe_insn_pages, list) {
 		if (kip->nused < INSNS_PER_PAGE) {
 			int i;
 			for (i = 0; i < INSNS_PER_PAGE; i++) {
-				if (!kip->slot_used[i]) {
-					kip->slot_used[i] = 1;
+				if (kip->slot_used[i] == SLOT_CLEAN) {
+					kip->slot_used[i] = SLOT_USED;
 					kip->nused++;
 					return kip->insns + (i * MAX_INSN_SIZE);
 				}
@@ -95,11 +172,14 @@ kprobe_opcode_t __kprobes *get_insn_slot(void)
 		}
 	}
 
-	/* All out of space.  Need to allocate a new page. Use slot 0.*/
+	/* If there are any garbage slots, collect it and try again. */
+	if (kprobe_garbage_slots && collect_garbage_slots() == 0) {
+		goto retry;
+	}
+	/* All out of space.  Need to allocate a new page. Use slot 0. */
 	kip = kmalloc(sizeof(struct kprobe_insn_page), GFP_KERNEL);
-	if (!kip) {
+	if (!kip)
 		return NULL;
-	}
 
 	/*
 	 * Use module_alloc so this page is within +/- 2GB of where the
@@ -111,98 +191,141 @@ kprobe_opcode_t __kprobes *get_insn_slot(void)
 		kfree(kip);
 		return NULL;
 	}
-	INIT_HLIST_NODE(&kip->hlist);
-	hlist_add_head(&kip->hlist, &kprobe_insn_pages);
-	memset(kip->slot_used, 0, INSNS_PER_PAGE);
-	kip->slot_used[0] = 1;
+	INIT_LIST_HEAD(&kip->list);
+	list_add(&kip->list, &kprobe_insn_pages);
+	memset(kip->slot_used, SLOT_CLEAN, INSNS_PER_PAGE);
+	kip->slot_used[0] = SLOT_USED;
 	kip->nused = 1;
+	kip->ngarbage = 0;
 	return kip->insns;
 }
 
-void __kprobes free_insn_slot(kprobe_opcode_t *slot)
+kprobe_opcode_t __kprobes *get_insn_slot(void)
 {
-	struct kprobe_insn_page *kip;
-	struct hlist_node *pos;
+	kprobe_opcode_t *ret;
+	mutex_lock(&kprobe_insn_mutex);
+	ret = __get_insn_slot();
+	mutex_unlock(&kprobe_insn_mutex);
+	return ret;
+}
 
-	hlist_for_each(pos, &kprobe_insn_pages) {
-		kip = hlist_entry(pos, struct kprobe_insn_page, hlist);
-		if (kip->insns <= slot &&
-		    slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) {
-			int i = (slot - kip->insns) / MAX_INSN_SIZE;
-			kip->slot_used[i] = 0;
-			kip->nused--;
-			if (kip->nused == 0) {
-				/*
-				 * Page is no longer in use.  Free it unless
-				 * it's the last one.  We keep the last one
-				 * so as not to have to set it up again the
-				 * next time somebody inserts a probe.
-				 */
-				hlist_del(&kip->hlist);
-				if (hlist_empty(&kprobe_insn_pages)) {
-					INIT_HLIST_NODE(&kip->hlist);
-					hlist_add_head(&kip->hlist,
-						&kprobe_insn_pages);
-				} else {
-					module_free(NULL, kip->insns);
-					kfree(kip);
-				}
-			}
-			return;
+/* Return 1 if all garbages are collected, otherwise 0. */
+static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
+{
+	kip->slot_used[idx] = SLOT_CLEAN;
+	kip->nused--;
+	if (kip->nused == 0) {
+		/*
+		 * Page is no longer in use.  Free it unless
+		 * it's the last one.  We keep the last one
+		 * so as not to have to set it up again the
+		 * next time somebody inserts a probe.
+		 */
+		if (!list_is_singular(&kprobe_insn_pages)) {
+			list_del(&kip->list);
+			module_free(NULL, kip->insns);
+			kfree(kip);
 		}
+		return 1;
 	}
+	return 0;
 }
 
-/* Locks kprobe: irqs must be disabled */
-void __kprobes lock_kprobes(void)
+static int __kprobes collect_garbage_slots(void)
 {
-	unsigned long flags = 0;
+	struct kprobe_insn_page *kip, *next;
+
+	/* Ensure no-one is preepmted on the garbages */
+	if (check_safety())
+		return -EAGAIN;
+
+	list_for_each_entry_safe(kip, next, &kprobe_insn_pages, list) {
+		int i;
+		if (kip->ngarbage == 0)
+			continue;
+		kip->ngarbage = 0;	/* we will collect all garbages */
+		for (i = 0; i < INSNS_PER_PAGE; i++) {
+			if (kip->slot_used[i] == SLOT_DIRTY &&
+			    collect_one_slot(kip, i))
+				break;
+		}
+	}
+	kprobe_garbage_slots = 0;
+	return 0;
+}
 
-	/* Avoiding local interrupts to happen right after we take the kprobe_lock
-	 * and before we get a chance to update kprobe_cpu, this to prevent
-	 * deadlock when we have a kprobe on ISR routine and a kprobe on task
-	 * routine
-	 */
-	local_irq_save(flags);
+void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
+{
+	struct kprobe_insn_page *kip;
+
+	mutex_lock(&kprobe_insn_mutex);
+	list_for_each_entry(kip, &kprobe_insn_pages, list) {
+		if (kip->insns <= slot &&
+		    slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) {
+			int i = (slot - kip->insns) / MAX_INSN_SIZE;
+			if (dirty) {
+				kip->slot_used[i] = SLOT_DIRTY;
+				kip->ngarbage++;
+			} else
+				collect_one_slot(kip, i);
+			break;
+		}
+	}
 
-	spin_lock(&kprobe_lock);
-	kprobe_cpu = smp_processor_id();
+	if (dirty && ++kprobe_garbage_slots > INSNS_PER_PAGE)
+		collect_garbage_slots();
 
- 	local_irq_restore(flags);
+	mutex_unlock(&kprobe_insn_mutex);
 }
+#endif
 
-void __kprobes unlock_kprobes(void)
+/* We have preemption disabled.. so it is safe to use __ versions */
+static inline void set_kprobe_instance(struct kprobe *kp)
 {
-	unsigned long flags = 0;
-
-	/* Avoiding local interrupts to happen right after we update
-	 * kprobe_cpu and before we get a a chance to release kprobe_lock,
-	 * this to prevent deadlock when we have a kprobe on ISR routine and
-	 * a kprobe on task routine
-	 */
-	local_irq_save(flags);
-
-	kprobe_cpu = NR_CPUS;
-	spin_unlock(&kprobe_lock);
+	__get_cpu_var(kprobe_instance) = kp;
+}
 
- 	local_irq_restore(flags);
+static inline void reset_kprobe_instance(void)
+{
+	__get_cpu_var(kprobe_instance) = NULL;
 }
 
-/* You have to be holding the kprobe_lock */
+/*
+ * This routine is called either:
+ * 	- under the kprobe_mutex - during kprobe_[un]register()
+ * 				OR
+ * 	- with preemption disabled - from arch/xxx/kernel/kprobes.c
+ */
 struct kprobe __kprobes *get_kprobe(void *addr)
 {
 	struct hlist_head *head;
 	struct hlist_node *node;
+	struct kprobe *p;
 
 	head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)];
-	hlist_for_each(node, head) {
-		struct kprobe *p = hlist_entry(node, struct kprobe, hlist);
+	hlist_for_each_entry_rcu(p, node, head, hlist) {
 		if (p->addr == addr)
 			return p;
 	}
 	return NULL;
 }
 
+/* Arm a kprobe with text_mutex */
+static void __kprobes arm_kprobe(struct kprobe *kp)
+{
+	mutex_lock(&text_mutex);
+	arch_arm_kprobe(kp);
+	mutex_unlock(&text_mutex);
+}
+
+/* Disarm a kprobe with text_mutex */
+static void __kprobes disarm_kprobe(struct kprobe *kp)
+{
+	mutex_lock(&text_mutex);
+	arch_disarm_kprobe(kp);
+	mutex_unlock(&text_mutex);
+}
+
 /*
  * Aggregate handlers for multiple kprobes support - these handlers
  * take care of invoking the individual kprobe handlers on p->list
@@ -211,13 +334,13 @@ static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe *kp;
 
-	list_for_each_entry(kp, &p->list, list) {
-		if (kp->pre_handler) {
-			curr_kprobe = kp;
+	list_for_each_entry_rcu(kp, &p->list, list) {
+		if (kp->pre_handler && likely(!kprobe_disabled(kp))) {
+			set_kprobe_instance(kp);
 			if (kp->pre_handler(kp, regs))
 				return 1;
 		}
-		curr_kprobe = NULL;
+		reset_kprobe_instance();
 	}
 	return 0;
 }
@@ -227,25 +350,26 @@ static void __kprobes aggr_post_handler(struct kprobe *p, struct pt_regs *regs,
 {
 	struct kprobe *kp;
 
-	list_for_each_entry(kp, &p->list, list) {
-		if (kp->post_handler) {
-			curr_kprobe = kp;
+	list_for_each_entry_rcu(kp, &p->list, list) {
+		if (kp->post_handler && likely(!kprobe_disabled(kp))) {
+			set_kprobe_instance(kp);
 			kp->post_handler(kp, regs, flags);
-			curr_kprobe = NULL;
+			reset_kprobe_instance();
 		}
 	}
-	return;
 }
 
 static int __kprobes aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
 					int trapnr)
 {
+	struct kprobe *cur = __get_cpu_var(kprobe_instance);
+
 	/*
 	 * if we faulted "during" the execution of a user specified
 	 * probe handler, invoke just that probe's fault handler
 	 */
-	if (curr_kprobe && curr_kprobe->fault_handler) {
-		if (curr_kprobe->fault_handler(curr_kprobe, regs, trapnr))
+	if (cur && cur->fault_handler) {
+		if (cur->fault_handler(cur, regs, trapnr))
 			return 1;
 	}
 	return 0;
@@ -253,117 +377,142 @@ static int __kprobes aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
 
 static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
 {
-	struct kprobe *kp = curr_kprobe;
-	if (curr_kprobe && kp->break_handler) {
-		if (kp->break_handler(kp, regs)) {
-			curr_kprobe = NULL;
-			return 1;
-		}
+	struct kprobe *cur = __get_cpu_var(kprobe_instance);
+	int ret = 0;
+
+	if (cur && cur->break_handler) {
+		if (cur->break_handler(cur, regs))
+			ret = 1;
 	}
-	curr_kprobe = NULL;
-	return 0;
+	reset_kprobe_instance();
+	return ret;
 }
 
-struct kretprobe_instance __kprobes *get_free_rp_inst(struct kretprobe *rp)
+/* Walks the list and increments nmissed count for multiprobe case */
+void __kprobes kprobes_inc_nmissed_count(struct kprobe *p)
 {
-	struct hlist_node *node;
-	struct kretprobe_instance *ri;
-	hlist_for_each_entry(ri, node, &rp->free_instances, uflist)
-		return ri;
-	return NULL;
+	struct kprobe *kp;
+	if (p->pre_handler != aggr_pre_handler) {
+		p->nmissed++;
+	} else {
+		list_for_each_entry_rcu(kp, &p->list, list)
+			kp->nmissed++;
+	}
+	return;
 }
 
-static struct kretprobe_instance __kprobes *get_used_rp_inst(struct kretprobe
-							      *rp)
+void __kprobes recycle_rp_inst(struct kretprobe_instance *ri,
+				struct hlist_head *head)
 {
-	struct hlist_node *node;
-	struct kretprobe_instance *ri;
-	hlist_for_each_entry(ri, node, &rp->used_instances, uflist)
-		return ri;
-	return NULL;
+	struct kretprobe *rp = ri->rp;
+
+	/* remove rp inst off the rprobe_inst_table */
+	hlist_del(&ri->hlist);
+	INIT_HLIST_NODE(&ri->hlist);
+	if (likely(rp)) {
+		spin_lock(&rp->lock);
+		hlist_add_head(&ri->hlist, &rp->free_instances);
+		spin_unlock(&rp->lock);
+	} else
+		/* Unregistering */
+		hlist_add_head(&ri->hlist, head);
 }
 
-void __kprobes add_rp_inst(struct kretprobe_instance *ri)
+void __kprobes kretprobe_hash_lock(struct task_struct *tsk,
+			 struct hlist_head **head, unsigned long *flags)
 {
-	/*
-	 * Remove rp inst off the free list -
-	 * Add it back when probed function returns
-	 */
-	hlist_del(&ri->uflist);
+	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
+	spinlock_t *hlist_lock;
 
-	/* Add rp inst onto table */
-	INIT_HLIST_NODE(&ri->hlist);
-	hlist_add_head(&ri->hlist,
-			&kretprobe_inst_table[hash_ptr(ri->task, KPROBE_HASH_BITS)]);
+	*head = &kretprobe_inst_table[hash];
+	hlist_lock = kretprobe_table_lock_ptr(hash);
+	spin_lock_irqsave(hlist_lock, *flags);
+}
 
-	/* Also add this rp inst to the used list. */
-	INIT_HLIST_NODE(&ri->uflist);
-	hlist_add_head(&ri->uflist, &ri->rp->used_instances);
+static void __kprobes kretprobe_table_lock(unsigned long hash,
+	unsigned long *flags)
+{
+	spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
+	spin_lock_irqsave(hlist_lock, *flags);
 }
 
-void __kprobes recycle_rp_inst(struct kretprobe_instance *ri)
+void __kprobes kretprobe_hash_unlock(struct task_struct *tsk,
+	unsigned long *flags)
 {
-	/* remove rp inst off the rprobe_inst_table */
-	hlist_del(&ri->hlist);
-	if (ri->rp) {
-		/* remove rp inst off the used list */
-		hlist_del(&ri->uflist);
-		/* put rp inst back onto the free list */
-		INIT_HLIST_NODE(&ri->uflist);
-		hlist_add_head(&ri->uflist, &ri->rp->free_instances);
-	} else
-		/* Unregistering */
-		kfree(ri);
+	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
+	spinlock_t *hlist_lock;
+
+	hlist_lock = kretprobe_table_lock_ptr(hash);
+	spin_unlock_irqrestore(hlist_lock, *flags);
 }
 
-struct hlist_head __kprobes *kretprobe_inst_table_head(struct task_struct *tsk)
+void __kprobes kretprobe_table_unlock(unsigned long hash, unsigned long *flags)
 {
-	return &kretprobe_inst_table[hash_ptr(tsk, KPROBE_HASH_BITS)];
+	spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
+	spin_unlock_irqrestore(hlist_lock, *flags);
 }
 
 /*
- * This function is called from exit_thread or flush_thread when task tk's
- * stack is being recycled so that we can recycle any function-return probe
- * instances associated with this task. These left over instances represent
- * probed functions that have been called but will never return.
+ * This function is called from finish_task_switch when task tk becomes dead,
+ * so that we can recycle any function-return probe instances associated
+ * with this task. These left over instances represent probed functions
+ * that have been called but will never return.
  */
 void __kprobes kprobe_flush_task(struct task_struct *tk)
 {
-        struct kretprobe_instance *ri;
-        struct hlist_head *head;
+	struct kretprobe_instance *ri;
+	struct hlist_head *head, empty_rp;
 	struct hlist_node *node, *tmp;
-	unsigned long flags = 0;
-
-	spin_lock_irqsave(&kprobe_lock, flags);
-        head = kretprobe_inst_table_head(current);
-        hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
-                if (ri->task == tk)
-                        recycle_rp_inst(ri);
-        }
-	spin_unlock_irqrestore(&kprobe_lock, flags);
+	unsigned long hash, flags = 0;
+
+	if (unlikely(!kprobes_initialized))
+		/* Early boot.  kretprobe_table_locks not yet initialized. */
+		return;
+
+	hash = hash_ptr(tk, KPROBE_HASH_BITS);
+	head = &kretprobe_inst_table[hash];
+	kretprobe_table_lock(hash, &flags);
+	hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+		if (ri->task == tk)
+			recycle_rp_inst(ri, &empty_rp);
+	}
+	kretprobe_table_unlock(hash, &flags);
+	INIT_HLIST_HEAD(&empty_rp);
+	hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
+		hlist_del(&ri->hlist);
+		kfree(ri);
+	}
 }
 
-/*
- * This kprobe pre_handler is registered with every kretprobe. When probe
- * hits it will set up the return probe.
- */
-static int __kprobes pre_handler_kretprobe(struct kprobe *p,
-					   struct pt_regs *regs)
+static inline void free_rp_inst(struct kretprobe *rp)
 {
-	struct kretprobe *rp = container_of(p, struct kretprobe, kp);
+	struct kretprobe_instance *ri;
+	struct hlist_node *pos, *next;
 
-	/*TODO: consider to only swap the RA after the last pre_handler fired */
-	arch_prepare_kretprobe(rp, regs);
-	return 0;
+	hlist_for_each_entry_safe(ri, pos, next, &rp->free_instances, hlist) {
+		hlist_del(&ri->hlist);
+		kfree(ri);
+	}
 }
 
-static inline void free_rp_inst(struct kretprobe *rp)
+static void __kprobes cleanup_rp_inst(struct kretprobe *rp)
 {
+	unsigned long flags, hash;
 	struct kretprobe_instance *ri;
-	while ((ri = get_free_rp_inst(rp)) != NULL) {
-		hlist_del(&ri->uflist);
-		kfree(ri);
+	struct hlist_node *pos, *next;
+	struct hlist_head *head;
+
+	/* No race here */
+	for (hash = 0; hash < KPROBE_TABLE_SIZE; hash++) {
+		kretprobe_table_lock(hash, &flags);
+		head = &kretprobe_inst_table[hash];
+		hlist_for_each_entry_safe(ri, pos, next, head, hlist) {
+			if (ri->rp == rp)
+				ri->rp = NULL;
+		}
+		kretprobe_table_unlock(hash, &flags);
 	}
+	free_rp_inst(rp);
 }
 
 /*
@@ -376,21 +525,28 @@ static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
 }
 
 /*
-* Add the new probe to old_p->list. Fail if this is the
+* Add the new probe to ap->list. Fail if this is the
 * second jprobe at the address - two jprobes can't coexist
 */
-static int __kprobes add_new_kprobe(struct kprobe *old_p, struct kprobe *p)
+static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 {
-        struct kprobe *kp;
-
+	BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
 	if (p->break_handler) {
-		list_for_each_entry(kp, &old_p->list, list) {
-			if (kp->break_handler)
-				return -EEXIST;
-		}
-		list_add_tail(&p->list, &old_p->list);
+		if (ap->break_handler)
+			return -EEXIST;
+		list_add_tail_rcu(&p->list, &ap->list);
+		ap->break_handler = aggr_break_handler;
 	} else
-		list_add(&p->list, &old_p->list);
+		list_add_rcu(&p->list, &ap->list);
+	if (p->post_handler && !ap->post_handler)
+		ap->post_handler = aggr_post_handler;
+
+	if (kprobe_disabled(ap) && !kprobe_disabled(p)) {
+		ap->flags &= ~KPROBE_FLAG_DISABLED;
+		if (!kprobes_all_disarmed)
+			/* Arm the breakpoint again. */
+			arm_kprobe(ap);
+	}
 	return 0;
 }
 
@@ -401,230 +557,1027 @@ static int __kprobes add_new_kprobe(struct kprobe *old_p, struct kprobe *p)
 static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
 {
 	copy_kprobe(p, ap);
+	flush_insn_slot(ap);
 	ap->addr = p->addr;
+	ap->flags = p->flags;
 	ap->pre_handler = aggr_pre_handler;
-	ap->post_handler = aggr_post_handler;
 	ap->fault_handler = aggr_fault_handler;
-	ap->break_handler = aggr_break_handler;
+	/* We don't care the kprobe which has gone. */
+	if (p->post_handler && !kprobe_gone(p))
+		ap->post_handler = aggr_post_handler;
+	if (p->break_handler && !kprobe_gone(p))
+		ap->break_handler = aggr_break_handler;
 
 	INIT_LIST_HEAD(&ap->list);
-	list_add(&p->list, &ap->list);
+	list_add_rcu(&p->list, &ap->list);
 
-	INIT_HLIST_NODE(&ap->hlist);
-	hlist_del(&p->hlist);
-	hlist_add_head(&ap->hlist,
-		&kprobe_table[hash_ptr(ap->addr, KPROBE_HASH_BITS)]);
+	hlist_replace_rcu(&p->hlist, &ap->hlist);
 }
 
 /*
  * This is the second or subsequent kprobe at the address - handle
  * the intricacies
- * TODO: Move kcalloc outside the spinlock
  */
 static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
 					  struct kprobe *p)
 {
 	int ret = 0;
-	struct kprobe *ap;
+	struct kprobe *ap = old_p;
 
-	if (old_p->pre_handler == aggr_pre_handler) {
-		copy_kprobe(old_p, p);
-		ret = add_new_kprobe(old_p, p);
-	} else {
-		ap = kcalloc(1, sizeof(struct kprobe), GFP_ATOMIC);
+	if (old_p->pre_handler != aggr_pre_handler) {
+		/* If old_p is not an aggr_probe, create new aggr_kprobe. */
+		ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL);
 		if (!ap)
 			return -ENOMEM;
 		add_aggr_kprobe(ap, old_p);
-		copy_kprobe(ap, p);
-		ret = add_new_kprobe(ap, p);
 	}
-	return ret;
-}
 
-/* kprobe removal house-keeping routines */
-static inline void cleanup_kprobe(struct kprobe *p, unsigned long flags)
-{
-	arch_disarm_kprobe(p);
-	hlist_del(&p->hlist);
-	spin_unlock_irqrestore(&kprobe_lock, flags);
-	arch_remove_kprobe(p);
+	if (kprobe_gone(ap)) {
+		/*
+		 * Attempting to insert new probe at the same location that
+		 * had a probe in the module vaddr area which already
+		 * freed. So, the instruction slot has already been
+		 * released. We need a new slot for the new probe.
+		 */
+		ret = arch_prepare_kprobe(ap);
+		if (ret)
+			/*
+			 * Even if fail to allocate new slot, don't need to
+			 * free aggr_probe. It will be used next time, or
+			 * freed by unregister_kprobe.
+			 */
+			return ret;
+
+		/*
+		 * Clear gone flag to prevent allocating new slot again, and
+		 * set disabled flag because it is not armed yet.
+		 */
+		ap->flags = (ap->flags & ~KPROBE_FLAG_GONE)
+			    | KPROBE_FLAG_DISABLED;
+	}
+
+	copy_kprobe(ap, p);
+	return add_new_kprobe(ap, p);
 }
 
-static inline void cleanup_aggr_kprobe(struct kprobe *old_p,
-		struct kprobe *p, unsigned long flags)
+/* Try to disable aggr_kprobe, and return 1 if succeeded.*/
+static int __kprobes try_to_disable_aggr_kprobe(struct kprobe *p)
 {
-	list_del(&p->list);
-	if (list_empty(&old_p->list)) {
-		cleanup_kprobe(old_p, flags);
-		kfree(old_p);
-	} else
-		spin_unlock_irqrestore(&kprobe_lock, flags);
+	struct kprobe *kp;
+
+	list_for_each_entry_rcu(kp, &p->list, list) {
+		if (!kprobe_disabled(kp))
+			/*
+			 * There is an active probe on the list.
+			 * We can't disable aggr_kprobe.
+			 */
+			return 0;
+	}
+	p->flags |= KPROBE_FLAG_DISABLED;
+	return 1;
 }
 
 static int __kprobes in_kprobes_functions(unsigned long addr)
 {
-	if (addr >= (unsigned long)__kprobes_text_start
-		&& addr < (unsigned long)__kprobes_text_end)
+	struct kprobe_blackpoint *kb;
+
+	if (addr >= (unsigned long)__kprobes_text_start &&
+	    addr < (unsigned long)__kprobes_text_end)
 		return -EINVAL;
+	/*
+	 * If there exists a kprobe_blacklist, verify and
+	 * fail any probe registration in the prohibited area
+	 */
+	for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
+		if (kb->start_addr) {
+			if (addr >= kb->start_addr &&
+			    addr < (kb->start_addr + kb->range))
+				return -EINVAL;
+		}
+	}
 	return 0;
 }
 
+/*
+ * If we have a symbol_name argument, look it up and add the offset field
+ * to it. This way, we can specify a relative address to a symbol.
+ */
+static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p)
+{
+	kprobe_opcode_t *addr = p->addr;
+	if (p->symbol_name) {
+		if (addr)
+			return NULL;
+		kprobe_lookup_name(p->symbol_name, addr);
+	}
+
+	if (!addr)
+		return NULL;
+	return (kprobe_opcode_t *)(((char *)addr) + p->offset);
+}
+
+/* Check passed kprobe is valid and return kprobe in kprobe_table. */
+static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p)
+{
+	struct kprobe *old_p, *list_p;
+
+	old_p = get_kprobe(p->addr);
+	if (unlikely(!old_p))
+		return NULL;
+
+	if (p != old_p) {
+		list_for_each_entry_rcu(list_p, &old_p->list, list)
+			if (list_p == p)
+			/* kprobe p is a valid probe */
+				goto valid;
+		return NULL;
+	}
+valid:
+	return old_p;
+}
+
+/* Return error if the kprobe is being re-registered */
+static inline int check_kprobe_rereg(struct kprobe *p)
+{
+	int ret = 0;
+	struct kprobe *old_p;
+
+	mutex_lock(&kprobe_mutex);
+	old_p = __get_valid_kprobe(p);
+	if (old_p)
+		ret = -EINVAL;
+	mutex_unlock(&kprobe_mutex);
+	return ret;
+}
+
 int __kprobes register_kprobe(struct kprobe *p)
 {
 	int ret = 0;
-	unsigned long flags = 0;
 	struct kprobe *old_p;
+	struct module *probed_mod;
+	kprobe_opcode_t *addr;
+
+	addr = kprobe_addr(p);
+	if (!addr)
+		return -EINVAL;
+	p->addr = addr;
 
-	if ((ret = in_kprobes_functions((unsigned long) p->addr)) != 0)
+	ret = check_kprobe_rereg(p);
+	if (ret)
 		return ret;
-	if ((ret = arch_prepare_kprobe(p)) != 0)
-		goto rm_kprobe;
 
-	spin_lock_irqsave(&kprobe_lock, flags);
-	old_p = get_kprobe(p->addr);
+	preempt_disable();
+	if (!kernel_text_address((unsigned long) p->addr) ||
+	    in_kprobes_functions((unsigned long) p->addr)) {
+		preempt_enable();
+		return -EINVAL;
+	}
+
+	/* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */
+	p->flags &= KPROBE_FLAG_DISABLED;
+
+	/*
+	 * Check if are we probing a module.
+	 */
+	probed_mod = __module_text_address((unsigned long) p->addr);
+	if (probed_mod) {
+		/*
+		 * We must hold a refcount of the probed module while updating
+		 * its code to prohibit unexpected unloading.
+		 */
+		if (unlikely(!try_module_get(probed_mod))) {
+			preempt_enable();
+			return -EINVAL;
+		}
+		/*
+		 * If the module freed .init.text, we couldn't insert
+		 * kprobes in there.
+		 */
+		if (within_module_init((unsigned long)p->addr, probed_mod) &&
+		    probed_mod->state != MODULE_STATE_COMING) {
+			module_put(probed_mod);
+			preempt_enable();
+			return -EINVAL;
+		}
+	}
+	preempt_enable();
+
 	p->nmissed = 0;
+	INIT_LIST_HEAD(&p->list);
+	mutex_lock(&kprobe_mutex);
+	old_p = get_kprobe(p->addr);
 	if (old_p) {
 		ret = register_aggr_kprobe(old_p, p);
 		goto out;
 	}
 
-	arch_copy_kprobe(p);
+	mutex_lock(&text_mutex);
+	ret = arch_prepare_kprobe(p);
+	if (ret)
+		goto out_unlock_text;
+
 	INIT_HLIST_NODE(&p->hlist);
-	hlist_add_head(&p->hlist,
+	hlist_add_head_rcu(&p->hlist,
 		       &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]);
 
-  	arch_arm_kprobe(p);
+	if (!kprobes_all_disarmed && !kprobe_disabled(p))
+		arch_arm_kprobe(p);
 
+out_unlock_text:
+	mutex_unlock(&text_mutex);
 out:
-	spin_unlock_irqrestore(&kprobe_lock, flags);
-rm_kprobe:
-	if (ret == -EEXIST)
+	mutex_unlock(&kprobe_mutex);
+
+	if (probed_mod)
+		module_put(probed_mod);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_kprobe);
+
+/*
+ * Unregister a kprobe without a scheduler synchronization.
+ */
+static int __kprobes __unregister_kprobe_top(struct kprobe *p)
+{
+	struct kprobe *old_p, *list_p;
+
+	old_p = __get_valid_kprobe(p);
+	if (old_p == NULL)
+		return -EINVAL;
+
+	if (old_p == p ||
+	    (old_p->pre_handler == aggr_pre_handler &&
+	     list_is_singular(&old_p->list))) {
+		/*
+		 * Only probe on the hash list. Disarm only if kprobes are
+		 * enabled and not gone - otherwise, the breakpoint would
+		 * already have been removed. We save on flushing icache.
+		 */
+		if (!kprobes_all_disarmed && !kprobe_disabled(old_p))
+			disarm_kprobe(p);
+		hlist_del_rcu(&old_p->hlist);
+	} else {
+		if (p->break_handler && !kprobe_gone(p))
+			old_p->break_handler = NULL;
+		if (p->post_handler && !kprobe_gone(p)) {
+			list_for_each_entry_rcu(list_p, &old_p->list, list) {
+				if ((list_p != p) && (list_p->post_handler))
+					goto noclean;
+			}
+			old_p->post_handler = NULL;
+		}
+noclean:
+		list_del_rcu(&p->list);
+		if (!kprobe_disabled(old_p)) {
+			try_to_disable_aggr_kprobe(old_p);
+			if (!kprobes_all_disarmed && kprobe_disabled(old_p))
+				disarm_kprobe(old_p);
+		}
+	}
+	return 0;
+}
+
+static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
+{
+	struct kprobe *old_p;
+
+	if (list_empty(&p->list))
 		arch_remove_kprobe(p);
+	else if (list_is_singular(&p->list)) {
+		/* "p" is the last child of an aggr_kprobe */
+		old_p = list_entry(p->list.next, struct kprobe, list);
+		list_del(&p->list);
+		arch_remove_kprobe(old_p);
+		kfree(old_p);
+	}
+}
+
+int __kprobes register_kprobes(struct kprobe **kps, int num)
+{
+	int i, ret = 0;
+
+	if (num <= 0)
+		return -EINVAL;
+	for (i = 0; i < num; i++) {
+		ret = register_kprobe(kps[i]);
+		if (ret < 0) {
+			if (i > 0)
+				unregister_kprobes(kps, i);
+			break;
+		}
+	}
 	return ret;
 }
+EXPORT_SYMBOL_GPL(register_kprobes);
 
 void __kprobes unregister_kprobe(struct kprobe *p)
 {
-	unsigned long flags;
-	struct kprobe *old_p;
+	unregister_kprobes(&p, 1);
+}
+EXPORT_SYMBOL_GPL(unregister_kprobe);
 
-	spin_lock_irqsave(&kprobe_lock, flags);
-	old_p = get_kprobe(p->addr);
-	if (old_p) {
-		if (old_p->pre_handler == aggr_pre_handler)
-			cleanup_aggr_kprobe(old_p, p, flags);
-		else
-			cleanup_kprobe(p, flags);
-	} else
-		spin_unlock_irqrestore(&kprobe_lock, flags);
+void __kprobes unregister_kprobes(struct kprobe **kps, int num)
+{
+	int i;
+
+	if (num <= 0)
+		return;
+	mutex_lock(&kprobe_mutex);
+	for (i = 0; i < num; i++)
+		if (__unregister_kprobe_top(kps[i]) < 0)
+			kps[i]->addr = NULL;
+	mutex_unlock(&kprobe_mutex);
+
+	synchronize_sched();
+	for (i = 0; i < num; i++)
+		if (kps[i]->addr)
+			__unregister_kprobe_bottom(kps[i]);
 }
+EXPORT_SYMBOL_GPL(unregister_kprobes);
 
 static struct notifier_block kprobe_exceptions_nb = {
 	.notifier_call = kprobe_exceptions_notify,
-	.priority = 0x7fffffff /* we need to notified first */
+	.priority = 0x7fffffff /* we need to be notified first */
 };
 
-int __kprobes register_jprobe(struct jprobe *jp)
+unsigned long __weak arch_deref_entry_point(void *entry)
+{
+	return (unsigned long)entry;
+}
+
+int __kprobes register_jprobes(struct jprobe **jps, int num)
 {
-	/* Todo: Verify probepoint is a function entry point */
-	jp->kp.pre_handler = setjmp_pre_handler;
-	jp->kp.break_handler = longjmp_break_handler;
+	struct jprobe *jp;
+	int ret = 0, i;
 
-	return register_kprobe(&jp->kp);
+	if (num <= 0)
+		return -EINVAL;
+	for (i = 0; i < num; i++) {
+		unsigned long addr;
+		jp = jps[i];
+		addr = arch_deref_entry_point(jp->entry);
+
+		if (!kernel_text_address(addr))
+			ret = -EINVAL;
+		else {
+			/* Todo: Verify probepoint is a function entry point */
+			jp->kp.pre_handler = setjmp_pre_handler;
+			jp->kp.break_handler = longjmp_break_handler;
+			ret = register_kprobe(&jp->kp);
+		}
+		if (ret < 0) {
+			if (i > 0)
+				unregister_jprobes(jps, i);
+			break;
+		}
+	}
+	return ret;
 }
+EXPORT_SYMBOL_GPL(register_jprobes);
+
+int __kprobes register_jprobe(struct jprobe *jp)
+{
+	return register_jprobes(&jp, 1);
+}
+EXPORT_SYMBOL_GPL(register_jprobe);
 
 void __kprobes unregister_jprobe(struct jprobe *jp)
 {
-	unregister_kprobe(&jp->kp);
+	unregister_jprobes(&jp, 1);
 }
+EXPORT_SYMBOL_GPL(unregister_jprobe);
+
+void __kprobes unregister_jprobes(struct jprobe **jps, int num)
+{
+	int i;
+
+	if (num <= 0)
+		return;
+	mutex_lock(&kprobe_mutex);
+	for (i = 0; i < num; i++)
+		if (__unregister_kprobe_top(&jps[i]->kp) < 0)
+			jps[i]->kp.addr = NULL;
+	mutex_unlock(&kprobe_mutex);
+
+	synchronize_sched();
+	for (i = 0; i < num; i++) {
+		if (jps[i]->kp.addr)
+			__unregister_kprobe_bottom(&jps[i]->kp);
+	}
+}
+EXPORT_SYMBOL_GPL(unregister_jprobes);
+
+#ifdef CONFIG_KRETPROBES
+/*
+ * This kprobe pre_handler is registered with every kretprobe. When probe
+ * hits it will set up the return probe.
+ */
+static int __kprobes pre_handler_kretprobe(struct kprobe *p,
+					   struct pt_regs *regs)
+{
+	struct kretprobe *rp = container_of(p, struct kretprobe, kp);
+	unsigned long hash, flags = 0;
+	struct kretprobe_instance *ri;
 
-#ifdef ARCH_SUPPORTS_KRETPROBES
+	/*TODO: consider to only swap the RA after the last pre_handler fired */
+	hash = hash_ptr(current, KPROBE_HASH_BITS);
+	spin_lock_irqsave(&rp->lock, flags);
+	if (!hlist_empty(&rp->free_instances)) {
+		ri = hlist_entry(rp->free_instances.first,
+				struct kretprobe_instance, hlist);
+		hlist_del(&ri->hlist);
+		spin_unlock_irqrestore(&rp->lock, flags);
+
+		ri->rp = rp;
+		ri->task = current;
+
+		if (rp->entry_handler && rp->entry_handler(ri, regs))
+			return 0;
+
+		arch_prepare_kretprobe(ri, regs);
+
+		/* XXX(hch): why is there no hlist_move_head? */
+		INIT_HLIST_NODE(&ri->hlist);
+		kretprobe_table_lock(hash, &flags);
+		hlist_add_head(&ri->hlist, &kretprobe_inst_table[hash]);
+		kretprobe_table_unlock(hash, &flags);
+	} else {
+		rp->nmissed++;
+		spin_unlock_irqrestore(&rp->lock, flags);
+	}
+	return 0;
+}
 
 int __kprobes register_kretprobe(struct kretprobe *rp)
 {
 	int ret = 0;
 	struct kretprobe_instance *inst;
 	int i;
+	void *addr;
+
+	if (kretprobe_blacklist_size) {
+		addr = kprobe_addr(&rp->kp);
+		if (!addr)
+			return -EINVAL;
+
+		for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
+			if (kretprobe_blacklist[i].addr == addr)
+				return -EINVAL;
+		}
+	}
 
 	rp->kp.pre_handler = pre_handler_kretprobe;
+	rp->kp.post_handler = NULL;
+	rp->kp.fault_handler = NULL;
+	rp->kp.break_handler = NULL;
 
 	/* Pre-allocate memory for max kretprobe instances */
 	if (rp->maxactive <= 0) {
 #ifdef CONFIG_PREEMPT
-		rp->maxactive = max(10, 2 * NR_CPUS);
+		rp->maxactive = max(10, 2 * num_possible_cpus());
 #else
-		rp->maxactive = NR_CPUS;
+		rp->maxactive = num_possible_cpus();
 #endif
 	}
-	INIT_HLIST_HEAD(&rp->used_instances);
+	spin_lock_init(&rp->lock);
 	INIT_HLIST_HEAD(&rp->free_instances);
 	for (i = 0; i < rp->maxactive; i++) {
-		inst = kmalloc(sizeof(struct kretprobe_instance), GFP_KERNEL);
+		inst = kmalloc(sizeof(struct kretprobe_instance) +
+			       rp->data_size, GFP_KERNEL);
 		if (inst == NULL) {
 			free_rp_inst(rp);
 			return -ENOMEM;
 		}
-		INIT_HLIST_NODE(&inst->uflist);
-		hlist_add_head(&inst->uflist, &rp->free_instances);
+		INIT_HLIST_NODE(&inst->hlist);
+		hlist_add_head(&inst->hlist, &rp->free_instances);
 	}
 
 	rp->nmissed = 0;
 	/* Establish function entry probe point */
-	if ((ret = register_kprobe(&rp->kp)) != 0)
+	ret = register_kprobe(&rp->kp);
+	if (ret != 0)
 		free_rp_inst(rp);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(register_kretprobe);
 
-#else /* ARCH_SUPPORTS_KRETPROBES */
+int __kprobes register_kretprobes(struct kretprobe **rps, int num)
+{
+	int ret = 0, i;
 
+	if (num <= 0)
+		return -EINVAL;
+	for (i = 0; i < num; i++) {
+		ret = register_kretprobe(rps[i]);
+		if (ret < 0) {
+			if (i > 0)
+				unregister_kretprobes(rps, i);
+			break;
+		}
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_kretprobes);
+
+void __kprobes unregister_kretprobe(struct kretprobe *rp)
+{
+	unregister_kretprobes(&rp, 1);
+}
+EXPORT_SYMBOL_GPL(unregister_kretprobe);
+
+void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
+{
+	int i;
+
+	if (num <= 0)
+		return;
+	mutex_lock(&kprobe_mutex);
+	for (i = 0; i < num; i++)
+		if (__unregister_kprobe_top(&rps[i]->kp) < 0)
+			rps[i]->kp.addr = NULL;
+	mutex_unlock(&kprobe_mutex);
+
+	synchronize_sched();
+	for (i = 0; i < num; i++) {
+		if (rps[i]->kp.addr) {
+			__unregister_kprobe_bottom(&rps[i]->kp);
+			cleanup_rp_inst(rps[i]);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(unregister_kretprobes);
+
+#else /* CONFIG_KRETPROBES */
 int __kprobes register_kretprobe(struct kretprobe *rp)
 {
 	return -ENOSYS;
 }
+EXPORT_SYMBOL_GPL(register_kretprobe);
 
-#endif /* ARCH_SUPPORTS_KRETPROBES */
+int __kprobes register_kretprobes(struct kretprobe **rps, int num)
+{
+	return -ENOSYS;
+}
+EXPORT_SYMBOL_GPL(register_kretprobes);
 
 void __kprobes unregister_kretprobe(struct kretprobe *rp)
 {
-	unsigned long flags;
-	struct kretprobe_instance *ri;
+}
+EXPORT_SYMBOL_GPL(unregister_kretprobe);
 
-	unregister_kprobe(&rp->kp);
-	/* No race here */
-	spin_lock_irqsave(&kprobe_lock, flags);
-	free_rp_inst(rp);
-	while ((ri = get_used_rp_inst(rp)) != NULL) {
-		ri->rp = NULL;
-		hlist_del(&ri->uflist);
+void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
+{
+}
+EXPORT_SYMBOL_GPL(unregister_kretprobes);
+
+static int __kprobes pre_handler_kretprobe(struct kprobe *p,
+					   struct pt_regs *regs)
+{
+	return 0;
+}
+
+#endif /* CONFIG_KRETPROBES */
+
+/* Set the kprobe gone and remove its instruction buffer. */
+static void __kprobes kill_kprobe(struct kprobe *p)
+{
+	struct kprobe *kp;
+
+	p->flags |= KPROBE_FLAG_GONE;
+	if (p->pre_handler == aggr_pre_handler) {
+		/*
+		 * If this is an aggr_kprobe, we have to list all the
+		 * chained probes and mark them GONE.
+		 */
+		list_for_each_entry_rcu(kp, &p->list, list)
+			kp->flags |= KPROBE_FLAG_GONE;
+		p->post_handler = NULL;
+		p->break_handler = NULL;
 	}
-	spin_unlock_irqrestore(&kprobe_lock, flags);
+	/*
+	 * Here, we can remove insn_slot safely, because no thread calls
+	 * the original probed function (which will be freed soon) any more.
+	 */
+	arch_remove_kprobe(p);
 }
 
+void __kprobes dump_kprobe(struct kprobe *kp)
+{
+	printk(KERN_WARNING "Dumping kprobe:\n");
+	printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n",
+	       kp->symbol_name, kp->addr, kp->offset);
+}
+
+/* Module notifier call back, checking kprobes on the module */
+static int __kprobes kprobes_module_callback(struct notifier_block *nb,
+					     unsigned long val, void *data)
+{
+	struct module *mod = data;
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct kprobe *p;
+	unsigned int i;
+	int checkcore = (val == MODULE_STATE_GOING);
+
+	if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE)
+		return NOTIFY_DONE;
+
+	/*
+	 * When MODULE_STATE_GOING was notified, both of module .text and
+	 * .init.text sections would be freed. When MODULE_STATE_LIVE was
+	 * notified, only .init.text section would be freed. We need to
+	 * disable kprobes which have been inserted in the sections.
+	 */
+	mutex_lock(&kprobe_mutex);
+	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+		head = &kprobe_table[i];
+		hlist_for_each_entry_rcu(p, node, head, hlist)
+			if (within_module_init((unsigned long)p->addr, mod) ||
+			    (checkcore &&
+			     within_module_core((unsigned long)p->addr, mod))) {
+				/*
+				 * The vaddr this probe is installed will soon
+				 * be vfreed buy not synced to disk. Hence,
+				 * disarming the breakpoint isn't needed.
+				 */
+				kill_kprobe(p);
+			}
+	}
+	mutex_unlock(&kprobe_mutex);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block kprobe_module_nb = {
+	.notifier_call = kprobes_module_callback,
+	.priority = 0
+};
+
 static int __init init_kprobes(void)
 {
 	int i, err = 0;
+	unsigned long offset = 0, size = 0;
+	char *modname, namebuf[128];
+	const char *symbol_name;
+	void *addr;
+	struct kprobe_blackpoint *kb;
 
 	/* 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]);
 		INIT_HLIST_HEAD(&kretprobe_inst_table[i]);
+		spin_lock_init(&(kretprobe_table_locks[i].lock));
+	}
+
+	/*
+	 * Lookup and populate the kprobe_blacklist.
+	 *
+	 * Unlike the kretprobe blacklist, we'll need to determine
+	 * the range of addresses that belong to the said functions,
+	 * since a kprobe need not necessarily be at the beginning
+	 * of a function.
+	 */
+	for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
+		kprobe_lookup_name(kb->name, addr);
+		if (!addr)
+			continue;
+
+		kb->start_addr = (unsigned long)addr;
+		symbol_name = kallsyms_lookup(kb->start_addr,
+				&size, &offset, &modname, namebuf);
+		if (!symbol_name)
+			kb->range = 0;
+		else
+			kb->range = size;
 	}
 
+	if (kretprobe_blacklist_size) {
+		/* lookup the function address from its name */
+		for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
+			kprobe_lookup_name(kretprobe_blacklist[i].name,
+					   kretprobe_blacklist[i].addr);
+			if (!kretprobe_blacklist[i].addr)
+				printk("kretprobe: lookup failed: %s\n",
+				       kretprobe_blacklist[i].name);
+		}
+	}
+
+	/* By default, kprobes are armed */
+	kprobes_all_disarmed = false;
+
 	err = arch_init_kprobes();
 	if (!err)
 		err = register_die_notifier(&kprobe_exceptions_nb);
+	if (!err)
+		err = register_module_notifier(&kprobe_module_nb);
 
+	kprobes_initialized = (err == 0);
+
+	if (!err)
+		init_test_probes();
 	return err;
 }
 
-__initcall(init_kprobes);
+#ifdef CONFIG_DEBUG_FS
+static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
+		const char *sym, int offset,char *modname)
+{
+	char *kprobe_type;
+
+	if (p->pre_handler == pre_handler_kretprobe)
+		kprobe_type = "r";
+	else if (p->pre_handler == setjmp_pre_handler)
+		kprobe_type = "j";
+	else
+		kprobe_type = "k";
+	if (sym)
+		seq_printf(pi, "%p  %s  %s+0x%x  %s %s%s\n",
+			p->addr, kprobe_type, sym, offset,
+			(modname ? modname : " "),
+			(kprobe_gone(p) ? "[GONE]" : ""),
+			((kprobe_disabled(p) && !kprobe_gone(p)) ?
+			 "[DISABLED]" : ""));
+	else
+		seq_printf(pi, "%p  %s  %p %s%s\n",
+			p->addr, kprobe_type, p->addr,
+			(kprobe_gone(p) ? "[GONE]" : ""),
+			((kprobe_disabled(p) && !kprobe_gone(p)) ?
+			 "[DISABLED]" : ""));
+}
 
-EXPORT_SYMBOL_GPL(register_kprobe);
-EXPORT_SYMBOL_GPL(unregister_kprobe);
-EXPORT_SYMBOL_GPL(register_jprobe);
-EXPORT_SYMBOL_GPL(unregister_jprobe);
-EXPORT_SYMBOL_GPL(jprobe_return);
-EXPORT_SYMBOL_GPL(register_kretprobe);
-EXPORT_SYMBOL_GPL(unregister_kretprobe);
+static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos)
+{
+	return (*pos < KPROBE_TABLE_SIZE) ? pos : NULL;
+}
+
+static void __kprobes *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos)
+{
+	(*pos)++;
+	if (*pos >= KPROBE_TABLE_SIZE)
+		return NULL;
+	return pos;
+}
+
+static void __kprobes kprobe_seq_stop(struct seq_file *f, void *v)
+{
+	/* Nothing to do */
+}
+
+static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct kprobe *p, *kp;
+	const char *sym = NULL;
+	unsigned int i = *(loff_t *) v;
+	unsigned long offset = 0;
+	char *modname, namebuf[128];
+
+	head = &kprobe_table[i];
+	preempt_disable();
+	hlist_for_each_entry_rcu(p, node, head, hlist) {
+		sym = kallsyms_lookup((unsigned long)p->addr, NULL,
+					&offset, &modname, namebuf);
+		if (p->pre_handler == aggr_pre_handler) {
+			list_for_each_entry_rcu(kp, &p->list, list)
+				report_probe(pi, kp, sym, offset, modname);
+		} else
+			report_probe(pi, p, sym, offset, modname);
+	}
+	preempt_enable();
+	return 0;
+}
+
+static const struct seq_operations kprobes_seq_ops = {
+	.start = kprobe_seq_start,
+	.next  = kprobe_seq_next,
+	.stop  = kprobe_seq_stop,
+	.show  = show_kprobe_addr
+};
+
+static int __kprobes kprobes_open(struct inode *inode, struct file *filp)
+{
+	return seq_open(filp, &kprobes_seq_ops);
+}
+
+static const struct file_operations debugfs_kprobes_operations = {
+	.open           = kprobes_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = seq_release,
+};
+
+/* Disable one kprobe */
+int __kprobes disable_kprobe(struct kprobe *kp)
+{
+	int ret = 0;
+	struct kprobe *p;
+
+	mutex_lock(&kprobe_mutex);
+
+	/* Check whether specified probe is valid. */
+	p = __get_valid_kprobe(kp);
+	if (unlikely(p == NULL)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* If the probe is already disabled (or gone), just return */
+	if (kprobe_disabled(kp))
+		goto out;
+
+	kp->flags |= KPROBE_FLAG_DISABLED;
+	if (p != kp)
+		/* When kp != p, p is always enabled. */
+		try_to_disable_aggr_kprobe(p);
+
+	if (!kprobes_all_disarmed && kprobe_disabled(p))
+		disarm_kprobe(p);
+out:
+	mutex_unlock(&kprobe_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(disable_kprobe);
+
+/* Enable one kprobe */
+int __kprobes enable_kprobe(struct kprobe *kp)
+{
+	int ret = 0;
+	struct kprobe *p;
+
+	mutex_lock(&kprobe_mutex);
+
+	/* Check whether specified probe is valid. */
+	p = __get_valid_kprobe(kp);
+	if (unlikely(p == NULL)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (kprobe_gone(kp)) {
+		/* This kprobe has gone, we couldn't enable it. */
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (!kprobes_all_disarmed && kprobe_disabled(p))
+		arm_kprobe(p);
+
+	p->flags &= ~KPROBE_FLAG_DISABLED;
+	if (p != kp)
+		kp->flags &= ~KPROBE_FLAG_DISABLED;
+out:
+	mutex_unlock(&kprobe_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(enable_kprobe);
+
+static void __kprobes arm_all_kprobes(void)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct kprobe *p;
+	unsigned int i;
+
+	mutex_lock(&kprobe_mutex);
+
+	/* If kprobes are armed, just return */
+	if (!kprobes_all_disarmed)
+		goto already_enabled;
+
+	mutex_lock(&text_mutex);
+	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+		head = &kprobe_table[i];
+		hlist_for_each_entry_rcu(p, node, head, hlist)
+			if (!kprobe_disabled(p))
+				arch_arm_kprobe(p);
+	}
+	mutex_unlock(&text_mutex);
+
+	kprobes_all_disarmed = false;
+	printk(KERN_INFO "Kprobes globally enabled\n");
+
+already_enabled:
+	mutex_unlock(&kprobe_mutex);
+	return;
+}
+
+static void __kprobes disarm_all_kprobes(void)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct kprobe *p;
+	unsigned int i;
+
+	mutex_lock(&kprobe_mutex);
+
+	/* If kprobes are already disarmed, just return */
+	if (kprobes_all_disarmed)
+		goto already_disabled;
+
+	kprobes_all_disarmed = true;
+	printk(KERN_INFO "Kprobes globally disabled\n");
+	mutex_lock(&text_mutex);
+	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+		head = &kprobe_table[i];
+		hlist_for_each_entry_rcu(p, node, head, hlist) {
+			if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p))
+				arch_disarm_kprobe(p);
+		}
+	}
 
+	mutex_unlock(&text_mutex);
+	mutex_unlock(&kprobe_mutex);
+	/* Allow all currently running kprobes to complete */
+	synchronize_sched();
+	return;
+
+already_disabled:
+	mutex_unlock(&kprobe_mutex);
+	return;
+}
+
+/*
+ * XXX: The debugfs bool file interface doesn't allow for callbacks
+ * when the bool state is switched. We can reuse that facility when
+ * available
+ */
+static ssize_t read_enabled_file_bool(struct file *file,
+	       char __user *user_buf, size_t count, loff_t *ppos)
+{
+	char buf[3];
+
+	if (!kprobes_all_disarmed)
+		buf[0] = '1';
+	else
+		buf[0] = '0';
+	buf[1] = '\n';
+	buf[2] = 0x00;
+	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static ssize_t write_enabled_file_bool(struct file *file,
+	       const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	char buf[32];
+	int buf_size;
+
+	buf_size = min(count, (sizeof(buf)-1));
+	if (copy_from_user(buf, user_buf, buf_size))
+		return -EFAULT;
+
+	switch (buf[0]) {
+	case 'y':
+	case 'Y':
+	case '1':
+		arm_all_kprobes();
+		break;
+	case 'n':
+	case 'N':
+	case '0':
+		disarm_all_kprobes();
+		break;
+	}
+
+	return count;
+}
+
+static const struct file_operations fops_kp = {
+	.read =         read_enabled_file_bool,
+	.write =        write_enabled_file_bool,
+};
+
+static int __kprobes debugfs_kprobe_init(void)
+{
+	struct dentry *dir, *file;
+	unsigned int value = 1;
+
+	dir = debugfs_create_dir("kprobes", NULL);
+	if (!dir)
+		return -ENOMEM;
+
+	file = debugfs_create_file("list", 0444, dir, NULL,
+				&debugfs_kprobes_operations);
+	if (!file) {
+		debugfs_remove(dir);
+		return -ENOMEM;
+	}
+
+	file = debugfs_create_file("enabled", 0600, dir,
+					&value, &fops_kp);
+	if (!file) {
+		debugfs_remove(dir);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+late_initcall(debugfs_kprobe_init);
+#endif /* CONFIG_DEBUG_FS */
+
+module_init(init_kprobes);
+
+/* defined in arch/.../kernel/kprobes.c */
+EXPORT_SYMBOL_GPL(jprobe_return);