1 files changed, 247 insertions, 99 deletions

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 21eccc961bba..cd9f5a66a690 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -48,6 +48,9 @@
 #define KPROBE_HASH_BITS 6
 #define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS)
 
+#if !defined(CONFIG_OPTPROBES) || !defined(CONFIG_SYSCTL)
+#define kprobe_sysctls_init() do { } while (0)
+#endif
 
 static int kprobes_initialized;
 /* kprobe_table can be accessed by
@@ -938,10 +941,10 @@ static void unoptimize_all_kprobes(void)
 }
 
 static DEFINE_MUTEX(kprobe_sysctl_mutex);
-int sysctl_kprobes_optimization;
-int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
-				      void *buffer, size_t *length,
-				      loff_t *ppos)
+static int sysctl_kprobes_optimization;
+static int proc_kprobes_optimization_handler(struct ctl_table *table,
+					     int write, void *buffer,
+					     size_t *length, loff_t *ppos)
 {
 	int ret;
 
@@ -957,6 +960,24 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
 
 	return ret;
 }
+
+static struct ctl_table kprobe_sysctls[] = {
+	{
+		.procname	= "kprobes-optimization",
+		.data		= &sysctl_kprobes_optimization,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_kprobes_optimization_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{}
+};
+
+static void __init kprobe_sysctls_init(void)
+{
+	register_sysctl_init("debug", kprobe_sysctls);
+}
 #endif /* CONFIG_SYSCTL */
 
 /* Put a breakpoint for a probe. */
@@ -1216,27 +1237,6 @@ void kprobes_inc_nmissed_count(struct kprobe *p)
 }
 NOKPROBE_SYMBOL(kprobes_inc_nmissed_count);
 
-static void free_rp_inst_rcu(struct rcu_head *head)
-{
-	struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu);
-
-	if (refcount_dec_and_test(&ri->rph->ref))
-		kfree(ri->rph);
-	kfree(ri);
-}
-NOKPROBE_SYMBOL(free_rp_inst_rcu);
-
-static void recycle_rp_inst(struct kretprobe_instance *ri)
-{
-	struct kretprobe *rp = get_kretprobe(ri);
-
-	if (likely(rp))
-		freelist_add(&ri->freelist, &rp->freelist);
-	else
-		call_rcu(&ri->rcu, free_rp_inst_rcu);
-}
-NOKPROBE_SYMBOL(recycle_rp_inst);
-
 static struct kprobe kprobe_busy = {
 	.addr = (void *) get_kprobe,
 };
@@ -1257,56 +1257,6 @@ void kprobe_busy_end(void)
 	preempt_enable();
 }
 
-/*
- * This function is called from delayed_put_task_struct() when a task is
- * dead and cleaned up to recycle any kretprobe instances associated with
- * this task. These left over instances represent probed functions that
- * have been called but will never return.
- */
-void kprobe_flush_task(struct task_struct *tk)
-{
-	struct kretprobe_instance *ri;
-	struct llist_node *node;
-
-	/* Early boot, not yet initialized. */
-	if (unlikely(!kprobes_initialized))
-		return;
-
-	kprobe_busy_begin();
-
-	node = __llist_del_all(&tk->kretprobe_instances);
-	while (node) {
-		ri = container_of(node, struct kretprobe_instance, llist);
-		node = node->next;
-
-		recycle_rp_inst(ri);
-	}
-
-	kprobe_busy_end();
-}
-NOKPROBE_SYMBOL(kprobe_flush_task);
-
-static inline void free_rp_inst(struct kretprobe *rp)
-{
-	struct kretprobe_instance *ri;
-	struct freelist_node *node;
-	int count = 0;
-
-	node = rp->freelist.head;
-	while (node) {
-		ri = container_of(node, struct kretprobe_instance, freelist);
-		node = node->next;
-
-		kfree(ri);
-		count++;
-	}
-
-	if (refcount_sub_and_test(count, &rp->rph->ref)) {
-		kfree(rp->rph);
-		rp->rph = NULL;
-	}
-}
-
 /* Add the new probe to 'ap->list'. */
 static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 {
@@ -1468,24 +1418,68 @@ bool within_kprobe_blacklist(unsigned long addr)
 }
 
 /*
+ * arch_adjust_kprobe_addr - adjust the address
+ * @addr: symbol base address
+ * @offset: offset within the symbol
+ * @on_func_entry: was this @addr+@offset on the function entry
+ *
+ * Typically returns @addr + @offset, except for special cases where the
+ * function might be prefixed by a CFI landing pad, in that case any offset
+ * inside the landing pad is mapped to the first 'real' instruction of the
+ * symbol.
+ *
+ * Specifically, for things like IBT/BTI, skip the resp. ENDBR/BTI.C
+ * instruction at +0.
+ */
+kprobe_opcode_t *__weak arch_adjust_kprobe_addr(unsigned long addr,
+						unsigned long offset,
+						bool *on_func_entry)
+{
+	*on_func_entry = !offset;
+	return (kprobe_opcode_t *)(addr + offset);
+}
+
+/*
  * If 'symbol_name' is specified, look it up and add the 'offset'
  * to it. This way, we can specify a relative address to a symbol.
  * This returns encoded errors if it fails to look up symbol or invalid
  * combination of parameters.
  */
-static kprobe_opcode_t *_kprobe_addr(kprobe_opcode_t *addr,
-			const char *symbol_name, unsigned int offset)
+static kprobe_opcode_t *
+_kprobe_addr(kprobe_opcode_t *addr, const char *symbol_name,
+	     unsigned long offset, bool *on_func_entry)
 {
 	if ((symbol_name && addr) || (!symbol_name && !addr))
 		goto invalid;
 
 	if (symbol_name) {
+		/*
+		 * Input: @sym + @offset
+		 * Output: @addr + @offset
+		 *
+		 * NOTE: kprobe_lookup_name() does *NOT* fold the offset
+		 *       argument into it's output!
+		 */
 		addr = kprobe_lookup_name(symbol_name, offset);
 		if (!addr)
 			return ERR_PTR(-ENOENT);
 	}
 
-	addr = (kprobe_opcode_t *)(((char *)addr) + offset);
+	/*
+	 * So here we have @addr + @offset, displace it into a new
+	 * @addr' + @offset' where @addr' is the symbol start address.
+	 */
+	addr = (void *)addr + offset;
+	if (!kallsyms_lookup_size_offset((unsigned long)addr, NULL, &offset))
+		return ERR_PTR(-ENOENT);
+	addr = (void *)addr - offset;
+
+	/*
+	 * Then ask the architecture to re-combine them, taking care of
+	 * magical function entry details while telling us if this was indeed
+	 * at the start of the function.
+	 */
+	addr = arch_adjust_kprobe_addr((unsigned long)addr, offset, on_func_entry);
 	if (addr)
 		return addr;
 
@@ -1495,7 +1489,8 @@ invalid:
 
 static kprobe_opcode_t *kprobe_addr(struct kprobe *p)
 {
-	return _kprobe_addr(p->addr, p->symbol_name, p->offset);
+	bool on_func_entry;
+	return _kprobe_addr(p->addr, p->symbol_name, p->offset, &on_func_entry);
 }
 
 /*
@@ -1541,14 +1536,10 @@ static inline int warn_kprobe_rereg(struct kprobe *p)
 
 static int check_ftrace_location(struct kprobe *p)
 {
-	unsigned long ftrace_addr;
+	unsigned long addr = (unsigned long)p->addr;
 
-	ftrace_addr = ftrace_location((unsigned long)p->addr);
-	if (ftrace_addr) {
+	if (ftrace_location(addr) == addr) {
 #ifdef CONFIG_KPROBES_ON_FTRACE
-		/* Given address is not on the instruction boundary */
-		if ((unsigned long)p->addr != ftrace_addr)
-			return -EILSEQ;
 		p->flags |= KPROBE_FLAG_FTRACE;
 #else	/* !CONFIG_KPROBES_ON_FTRACE */
 		return -EINVAL;
@@ -1569,7 +1560,9 @@ static int check_kprobe_address_safe(struct kprobe *p,
 	preempt_disable();
 
 	/* Ensure it is not in reserved area nor out of text */
-	if (!kernel_text_address((unsigned long) p->addr) ||
+	if (!(core_kernel_text((unsigned long) p->addr) ||
+	    is_module_text_address((unsigned long) p->addr)) ||
+	    in_gate_area_no_mm((unsigned long) p->addr) ||
 	    within_kprobe_blacklist((unsigned long) p->addr) ||
 	    jump_label_text_reserved(p->addr, p->addr) ||
 	    static_call_text_reserved(p->addr, p->addr) ||
@@ -1614,9 +1607,10 @@ int register_kprobe(struct kprobe *p)
 	struct kprobe *old_p;
 	struct module *probed_mod;
 	kprobe_opcode_t *addr;
+	bool on_func_entry;
 
 	/* Adjust probe address from symbol */
-	addr = kprobe_addr(p);
+	addr = _kprobe_addr(p->addr, p->symbol_name, p->offset, &on_func_entry);
 	if (IS_ERR(addr))
 		return PTR_ERR(addr);
 	p->addr = addr;
@@ -1636,6 +1630,9 @@ int register_kprobe(struct kprobe *p)
 
 	mutex_lock(&kprobe_mutex);
 
+	if (on_func_entry)
+		p->flags |= KPROBE_FLAG_ON_FUNC_ENTRY;
+
 	old_p = get_kprobe(p->addr);
 	if (old_p) {
 		/* Since this may unoptimize 'old_p', locking 'text_mutex'. */
@@ -1715,11 +1712,12 @@ static struct kprobe *__disable_kprobe(struct kprobe *p)
 		/* Try to disarm and disable this/parent probe */
 		if (p == orig_p || aggr_kprobe_disabled(orig_p)) {
 			/*
-			 * If 'kprobes_all_disarmed' is set, 'orig_p'
-			 * should have already been disarmed, so
-			 * skip unneed disarming process.
+			 * Don't be lazy here.  Even if 'kprobes_all_disarmed'
+			 * is false, 'orig_p' might not have been armed yet.
+			 * Note arm_all_kprobes() __tries__ to arm all kprobes
+			 * on the best effort basis.
 			 */
-			if (!kprobes_all_disarmed) {
+			if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) {
 				ret = disarm_kprobe(orig_p, true);
 				if (ret) {
 					p->flags &= ~KPROBE_FLAG_DISABLED;
@@ -1863,6 +1861,78 @@ static struct notifier_block kprobe_exceptions_nb = {
 
 #ifdef CONFIG_KRETPROBES
 
+#if !defined(CONFIG_KRETPROBE_ON_RETHOOK)
+static void free_rp_inst_rcu(struct rcu_head *head)
+{
+	struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu);
+
+	if (refcount_dec_and_test(&ri->rph->ref))
+		kfree(ri->rph);
+	kfree(ri);
+}
+NOKPROBE_SYMBOL(free_rp_inst_rcu);
+
+static void recycle_rp_inst(struct kretprobe_instance *ri)
+{
+	struct kretprobe *rp = get_kretprobe(ri);
+
+	if (likely(rp))
+		freelist_add(&ri->freelist, &rp->freelist);
+	else
+		call_rcu(&ri->rcu, free_rp_inst_rcu);
+}
+NOKPROBE_SYMBOL(recycle_rp_inst);
+
+/*
+ * This function is called from delayed_put_task_struct() when a task is
+ * dead and cleaned up to recycle any kretprobe instances associated with
+ * this task. These left over instances represent probed functions that
+ * have been called but will never return.
+ */
+void kprobe_flush_task(struct task_struct *tk)
+{
+	struct kretprobe_instance *ri;
+	struct llist_node *node;
+
+	/* Early boot, not yet initialized. */
+	if (unlikely(!kprobes_initialized))
+		return;
+
+	kprobe_busy_begin();
+
+	node = __llist_del_all(&tk->kretprobe_instances);
+	while (node) {
+		ri = container_of(node, struct kretprobe_instance, llist);
+		node = node->next;
+
+		recycle_rp_inst(ri);
+	}
+
+	kprobe_busy_end();
+}
+NOKPROBE_SYMBOL(kprobe_flush_task);
+
+static inline void free_rp_inst(struct kretprobe *rp)
+{
+	struct kretprobe_instance *ri;
+	struct freelist_node *node;
+	int count = 0;
+
+	node = rp->freelist.head;
+	while (node) {
+		ri = container_of(node, struct kretprobe_instance, freelist);
+		node = node->next;
+
+		kfree(ri);
+		count++;
+	}
+
+	if (refcount_sub_and_test(count, &rp->rph->ref)) {
+		kfree(rp->rph);
+		rp->rph = NULL;
+	}
+}
+
 /* This assumes the 'tsk' is the current task or the is not running. */
 static kprobe_opcode_t *__kretprobe_find_ret_addr(struct task_struct *tsk,
 						  struct llist_node **cur)
@@ -2025,11 +2095,57 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 	return 0;
 }
 NOKPROBE_SYMBOL(pre_handler_kretprobe);
+#else /* CONFIG_KRETPROBE_ON_RETHOOK */
+/*
+ * This kprobe pre_handler is registered with every kretprobe. When probe
+ * hits it will set up the return probe.
+ */
+static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kretprobe *rp = container_of(p, struct kretprobe, kp);
+	struct kretprobe_instance *ri;
+	struct rethook_node *rhn;
+
+	rhn = rethook_try_get(rp->rh);
+	if (!rhn) {
+		rp->nmissed++;
+		return 0;
+	}
 
-bool __weak arch_kprobe_on_func_entry(unsigned long offset)
+	ri = container_of(rhn, struct kretprobe_instance, node);
+
+	if (rp->entry_handler && rp->entry_handler(ri, regs))
+		rethook_recycle(rhn);
+	else
+		rethook_hook(rhn, regs, kprobe_ftrace(p));
+
+	return 0;
+}
+NOKPROBE_SYMBOL(pre_handler_kretprobe);
+
+static void kretprobe_rethook_handler(struct rethook_node *rh, void *data,
+				      struct pt_regs *regs)
 {
-	return !offset;
+	struct kretprobe *rp = (struct kretprobe *)data;
+	struct kretprobe_instance *ri;
+	struct kprobe_ctlblk *kcb;
+
+	/* The data must NOT be null. This means rethook data structure is broken. */
+	if (WARN_ON_ONCE(!data) || !rp->handler)
+		return;
+
+	__this_cpu_write(current_kprobe, &rp->kp);
+	kcb = get_kprobe_ctlblk();
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+
+	ri = container_of(rh, struct kretprobe_instance, node);
+	rp->handler(ri, regs);
+
+	__this_cpu_write(current_kprobe, NULL);
 }
+NOKPROBE_SYMBOL(kretprobe_rethook_handler);
+
+#endif /* !CONFIG_KRETPROBE_ON_RETHOOK */
 
 /**
  * kprobe_on_func_entry() -- check whether given address is function entry
@@ -2046,15 +2162,13 @@ bool __weak arch_kprobe_on_func_entry(unsigned long offset)
  */
 int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset)
 {
-	kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset);
+	bool on_func_entry;
+	kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset, &on_func_entry);
 
 	if (IS_ERR(kp_addr))
 		return PTR_ERR(kp_addr);
 
-	if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset))
-		return -ENOENT;
-
-	if (!arch_kprobe_on_func_entry(offset))
+	if (!on_func_entry)
 		return -EINVAL;
 
 	return 0;
@@ -2100,6 +2214,29 @@ int register_kretprobe(struct kretprobe *rp)
 		rp->maxactive = num_possible_cpus();
 #endif
 	}
+#ifdef CONFIG_KRETPROBE_ON_RETHOOK
+	rp->rh = rethook_alloc((void *)rp, kretprobe_rethook_handler);
+	if (!rp->rh)
+		return -ENOMEM;
+
+	for (i = 0; i < rp->maxactive; i++) {
+		inst = kzalloc(sizeof(struct kretprobe_instance) +
+			       rp->data_size, GFP_KERNEL);
+		if (inst == NULL) {
+			rethook_free(rp->rh);
+			rp->rh = NULL;
+			return -ENOMEM;
+		}
+		rethook_add_node(rp->rh, &inst->node);
+	}
+	rp->nmissed = 0;
+	/* Establish function entry probe point */
+	ret = register_kprobe(&rp->kp);
+	if (ret != 0) {
+		rethook_free(rp->rh);
+		rp->rh = NULL;
+	}
+#else	/* !CONFIG_KRETPROBE_ON_RETHOOK */
 	rp->freelist.head = NULL;
 	rp->rph = kzalloc(sizeof(struct kretprobe_holder), GFP_KERNEL);
 	if (!rp->rph)
@@ -2124,6 +2261,7 @@ int register_kretprobe(struct kretprobe *rp)
 	ret = register_kprobe(&rp->kp);
 	if (ret != 0)
 		free_rp_inst(rp);
+#endif
 	return ret;
 }
 EXPORT_SYMBOL_GPL(register_kretprobe);
@@ -2162,7 +2300,11 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
 	for (i = 0; i < num; i++) {
 		if (__unregister_kprobe_top(&rps[i]->kp) < 0)
 			rps[i]->kp.addr = NULL;
+#ifdef CONFIG_KRETPROBE_ON_RETHOOK
+		rethook_free(rps[i]->rh);
+#else
 		rps[i]->rph->rp = NULL;
+#endif
 	}
 	mutex_unlock(&kprobe_mutex);
 
@@ -2170,7 +2312,9 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
 	for (i = 0; i < num; i++) {
 		if (rps[i]->kp.addr) {
 			__unregister_kprobe_bottom(&rps[i]->kp);
+#ifndef CONFIG_KRETPROBE_ON_RETHOOK
 			free_rp_inst(rps[i]);
+#endif
 		}
 	}
 }
@@ -2285,8 +2429,11 @@ int enable_kprobe(struct kprobe *kp)
 	if (!kprobes_all_disarmed && kprobe_disabled(p)) {
 		p->flags &= ~KPROBE_FLAG_DISABLED;
 		ret = arm_kprobe(p);
-		if (ret)
+		if (ret) {
 			p->flags |= KPROBE_FLAG_DISABLED;
+			if (p != kp)
+				kp->flags |= KPROBE_FLAG_DISABLED;
+		}
 	}
 out:
 	mutex_unlock(&kprobe_mutex);
@@ -2584,6 +2731,7 @@ static int __init init_kprobes(void)
 		err = register_module_notifier(&kprobe_module_nb);
 
 	kprobes_initialized = (err == 0);
+	kprobe_sysctls_init();
 	return err;
 }
 early_initcall(init_kprobes);