[PATCH v4 00/15] livepatch: hybrid consistency model

@@ -709,6 +709,12 @@ config HAVE_STACK_VALIDATION
 	  Architecture supports the 'objtool check' host tool command, which
 	  performs compile-time stack metadata validation.
 
+config HAVE_RELIABLE_STACKTRACE
+	bool
+	help
+	  Architecture has a save_stack_trace_tsk_reliable() function which
+	  only returns a stack trace if it can guarantee the trace is reliable.
+
 config HAVE_ARCH_HASH
 	bool
 	default n

@@ -156,6 +156,7 @@ config X86
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_RELIABLE_STACKTRACE		if X86_64 && FRAME_POINTER && STACK_VALIDATION
 	select HAVE_STACK_VALIDATION		if X86_64
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UNSTABLE_SCHED_CLOCK

@@ -11,6 +11,7 @@ struct unwind_state {
 	unsigned long stack_mask;
 	struct task_struct *task;
 	int graph_idx;
+	bool error;
 #ifdef CONFIG_FRAME_POINTER
 	unsigned long *bp, *orig_sp;
 	struct pt_regs *regs;

@@ -40,6 +41,11 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
 	__unwind_start(state, task, regs, first_frame);
 }
 
+static inline bool unwind_error(struct unwind_state *state)
+{
+	return state->error;
+}
+
 #ifdef CONFIG_FRAME_POINTER
 
 static inline

@@ -74,6 +74,90 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
+#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
+static int __save_stack_trace_reliable(struct stack_trace *trace,
+				       struct task_struct *task)
+{
+	struct unwind_state state;
+	struct pt_regs *regs;
+	unsigned long addr;
+
+	for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state);
+	     unwind_next_frame(&state)) {
+
+		regs = unwind_get_entry_regs(&state);
+		if (regs) {
+			/*
+			 * Kernel mode registers on the stack indicate an
+			 * in-kernel interrupt or exception (e.g., preemption
+			 * or a page fault), which can make frame pointers
+			 * unreliable.
+			 */
+			if (!user_mode(regs))
+				return -1;
+
+			/*
+			 * The last frame contains the user mode syscall
+			 * pt_regs.  Skip it and finish the unwind.
+			 */
+			unwind_next_frame(&state);
+			if (WARN_ON_ONCE(!unwind_done(&state))) {
+				show_stack(task, NULL);
+				return -1;
+			}
+			break;
+		}
+
+		addr = unwind_get_return_address(&state);
+
+		/*
+		 * A NULL or invalid return address probably means there's some
+		 * generated code which __kernel_text_address() doesn't know
+		 * about.
+		 */
+		if (WARN_ON_ONCE(!addr)) {
+			show_stack(task, NULL);
+			return -1;
+		}
+
+		if (save_stack_address(trace, addr, false))
+			return -1;
+	}
+
+	/* Check for stack corruption */
+	if (WARN_ON_ONCE(unwind_error(&state))) {
+		show_stack(task, NULL);
+		return -1;
+	}
+
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+
+	return 0;
+}
+
+/*
+ * This function returns an error if it detects any unreliable features of the
+ * stack.  Otherwise it guarantees that the stack trace is reliable.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
+ */
+int save_stack_trace_tsk_reliable(struct task_struct *tsk,
+				  struct stack_trace *trace)
+{
+	int ret;
+
+	if (!try_get_task_stack(tsk))
+		return -EINVAL;
+
+	ret = __save_stack_trace_reliable(trace, tsk);
+
+	put_task_stack(tsk);
+
+	return ret;
+}
+#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
+
 /* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
 
 struct stack_frame_user {

@@ -136,4 +220,3 @@ void save_stack_trace_user(struct stack_trace *trace)
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
-

@@ -223,6 +223,8 @@ bool unwind_next_frame(struct unwind_state *state)
 	return true;
 
 bad_address:
+	state->error = true;
+
 	/*
 	 * When unwinding a non-current task, the task might actually be
 	 * running on another CPU, in which case it could be modifying its

@@ -18,6 +18,8 @@ extern void save_stack_trace_regs(struct pt_regs *regs,
 				  struct stack_trace *trace);
 extern void save_stack_trace_tsk(struct task_struct *tsk,
 				struct stack_trace *trace);
+extern int save_stack_trace_tsk_reliable(struct task_struct *tsk,
+					 struct stack_trace *trace);
 
 extern void print_stack_trace(struct stack_trace *trace, int spaces);
 extern int snprint_stack_trace(char *buf, size_t size,

@@ -29,12 +31,12 @@ extern void save_stack_trace_user(struct stack_trace *trace);
 # define save_stack_trace_user(trace)              do { } while (0)
 #endif
 
-#else
+#else /* !CONFIG_STACKTRACE */
 # define save_stack_trace(trace)			do { } while (0)
 # define save_stack_trace_tsk(tsk, trace)		do { } while (0)
 # define save_stack_trace_user(trace)			do { } while (0)
 # define print_stack_trace(trace, spaces)		do { } while (0)
 # define snprint_stack_trace(buf, size, trace, spaces)	do { } while (0)
-#endif
+#endif /* CONFIG_STACKTRACE */
 
-#endif
+#endif /* __LINUX_STACKTRACE_H */

@@ -58,8 +58,8 @@ int snprint_stack_trace(char *buf, size_t size,
 EXPORT_SYMBOL_GPL(snprint_stack_trace);
 
 /*
- * Architectures that do not implement save_stack_trace_tsk or
- * save_stack_trace_regs get this weak alias and a once-per-bootup warning
+ * Architectures that do not implement save_stack_trace_*()
+ * get these weak aliases and once-per-bootup warnings
  * (whenever this facility is utilized - for example by procfs):
  */
 __weak void

@@ -73,3 +73,11 @@ save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 {
 	WARN_ONCE(1, KERN_INFO "save_stack_trace_regs() not implemented yet.\n");
 }
+
+__weak int
+save_stack_trace_tsk_reliable(struct task_struct *tsk,
+			      struct stack_trace *trace)
+{
+	WARN_ONCE(1, KERN_INFO "save_stack_tsk_reliable() not implemented yet.\n");
+	return -ENOSYS;
+}

@@ -73,9 +73,6 @@ struct thread_info {
  * thread information flags
  * - these are process state flags that various assembly files
  *   may need to access
- * - pending work-to-be-done flags are in LSW
- * - other flags in MSW
- * Warning: layout of LSW is hardcoded in entry.S
  */
 #define TIF_SYSCALL_TRACE	0	/* syscall trace active */
 #define TIF_NOTIFY_RESUME	1	/* callback before returning to user */

@@ -103,8 +100,8 @@ struct thread_info {
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
-#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)

@@ -133,8 +130,10 @@ struct thread_info {
 
 /* work to do on any return to user space */
 #define _TIF_ALLWORK_MASK						\
-	((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT |	\
-	_TIF_NOHZ)
+	(_TIF_SYSCALL_TRACE | _TIF_NOTIFY_RESUME | _TIF_SIGPENDING |	\
+	 _TIF_NEED_RESCHED | _TIF_SINGLESTEP | _TIF_SYSCALL_EMU |	\
+	 _TIF_SYSCALL_AUDIT | _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE |	\
+	 _TIF_NOHZ | _TIF_SYSCALL_TRACEPOINT)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\

@@ -123,10 +123,13 @@ void arch_klp_init_object_loaded(struct klp_patch *patch,
 int klp_module_coming(struct module *mod);
 void klp_module_going(struct module *mod);
 
+void klp_update_patch_state(struct task_struct *task);
+
 #else /* !CONFIG_LIVEPATCH */
 
 static inline int klp_module_coming(struct module *mod) { return 0; }
-static inline void klp_module_going(struct module *mod) { }
+static inline void klp_module_going(struct module *mod) {}
+static inline void klp_update_patch_state(struct task_struct *task) {}
 
 #endif /* CONFIG_LIVEPATCH */
 

@@ -64,6 +64,9 @@ static LIST_HEAD(klp_ops);
 
 static struct kobject *klp_root_kobj;
 
+/* TODO: temporary stub */
+void klp_update_patch_state(struct task_struct *task) {}
+
 static struct klp_ops *klp_find_ops(unsigned long old_addr)
 {
 	struct klp_ops *ops;

@@ -92,6 +92,7 @@ static inline struct thread_info *current_thread_info(void)
 					   TIF_NEED_RESCHED */
 #define TIF_32BIT		4	/* 32 bit binary */
 #define TIF_RESTORE_TM		5	/* need to restore TM FP/VEC/VSX */
+#define TIF_PATCH_PENDING	6	/* pending live patching update */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SINGLESTEP		8	/* singlestepping active */
 #define TIF_NOHZ		9	/* in adaptive nohz mode */

@@ -115,6 +116,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_32BIT		(1<<TIF_32BIT)
 #define _TIF_RESTORE_TM		(1<<TIF_RESTORE_TM)
+#define _TIF_PATCH_PENDING	(1<<TIF_PATCH_PENDING)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SINGLESTEP		(1<<TIF_SINGLESTEP)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)

@@ -131,7 +133,7 @@ static inline struct thread_info *current_thread_info(void)
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
-				 _TIF_RESTORE_TM)
+				 _TIF_RESTORE_TM | _TIF_PATCH_PENDING)
 #define _TIF_PERSYSCALL_MASK	(_TIF_RESTOREALL|_TIF_NOERROR)
 
 /* Bits in local_flags */

@@ -14,6 +14,7 @@
 #include <linux/uprobes.h>
 #include <linux/key.h>
 #include <linux/context_tracking.h>
+#include <linux/livepatch.h>
 #include <asm/hw_breakpoint.h>
 #include <linux/uaccess.h>
 #include <asm/unistd.h>

@@ -162,6 +163,9 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 		tracehook_notify_resume(regs);
 	}
 
+	if (thread_info_flags & _TIF_PATCH_PENDING)
+		klp_update_patch_state(current);
+
 	user_enter();
 }
 

@@ -467,9 +467,6 @@ static int klp_patch_object(struct klp_object *obj)
 	if (WARN_ON(obj->patched))
 		return -EINVAL;
 
-	if (WARN_ON(!klp_is_object_loaded(obj)))
-		return -EINVAL;
-
 	klp_for_each_func(obj, func) {
 		ret = klp_patch_func(func);
 		if (ret) {

@@ -28,11 +28,6 @@
 
 #include <asm/livepatch.h>
 
-enum klp_state {
-	KLP_DISABLED,
-	KLP_ENABLED
-};
-
 /**
  * struct klp_func - function structure for live patching
  * @old_name:	name of the function to be patched

@@ -41,8 +36,8 @@ enum klp_state {
  *		can be found (optional)
  * @old_addr:	the address of the function being patched
  * @kobj:	kobject for sysfs resources
- * @state:	tracks function-level patch application state
  * @stack_node:	list node for klp_ops func_stack list
+ * @patched:	the func has been added to the klp_ops list
  */
 struct klp_func {
 	/* external */

@@ -60,8 +55,8 @@ struct klp_func {
 	/* internal */
 	unsigned long old_addr;
 	struct kobject kobj;
-	enum klp_state state;
 	struct list_head stack_node;
+	bool patched;
 };
 
 /**

@@ -71,7 +66,7 @@ struct klp_func {
  * @kobj:	kobject for sysfs resources
  * @mod:	kernel module associated with the patched object
  * 		(NULL for vmlinux)
- * @state:	tracks object-level patch application state
+ * @patched:	the object's funcs have been added to the klp_ops list
  */
 struct klp_object {
 	/* external */

@@ -81,7 +76,7 @@ struct klp_object {
 	/* internal */
 	struct kobject kobj;
 	struct module *mod;
-	enum klp_state state;
+	bool patched;
 };
 
 /**

@@ -90,7 +85,7 @@ struct klp_object {
  * @objs:	object entries for kernel objects to be patched
  * @list:	list node for global list of registered patches
  * @kobj:	kobject for sysfs resources
- * @state:	tracks patch-level application state
+ * @enabled:	the patch is enabled (but operation may be incomplete)
  */
 struct klp_patch {
 	/* external */

@@ -100,7 +95,7 @@ struct klp_patch {
 	/* internal */
 	struct list_head list;
 	struct kobject kobj;
-	enum klp_state state;
+	bool enabled;
 };
 
 #define klp_for_each_object(patch, obj) \

@@ -348,11 +348,11 @@ static unsigned long klp_get_ftrace_location(unsigned long faddr)
 }
 #endif
 
-static void klp_disable_func(struct klp_func *func)
+static void klp_unpatch_func(struct klp_func *func)
 {
 	struct klp_ops *ops;
 
-	if (WARN_ON(func->state != KLP_ENABLED))
+	if (WARN_ON(!func->patched))
 		return;
 	if (WARN_ON(!func->old_addr))
 		return;

@@ -378,10 +378,10 @@ static void klp_disable_func(struct klp_func *func)
 		list_del_rcu(&func->stack_node);
 	}
 
-	func->state = KLP_DISABLED;
+	func->patched = false;
 }
 
-static int klp_enable_func(struct klp_func *func)
+static int klp_patch_func(struct klp_func *func)
 {
 	struct klp_ops *ops;
 	int ret;

@@ -389,7 +389,7 @@ static int klp_enable_func(struct klp_func *func)
 	if (WARN_ON(!func->old_addr))
 		return -EINVAL;
 
-	if (WARN_ON(func->state != KLP_DISABLED))
+	if (WARN_ON(func->patched))
 		return -EINVAL;
 
 	ops = klp_find_ops(func->old_addr);

@@ -437,7 +437,7 @@ static int klp_enable_func(struct klp_func *func)
 		list_add_rcu(&func->stack_node, &ops->func_stack);
 	}
 
-	func->state = KLP_ENABLED;
+	func->patched = true;
 
 	return 0;
 

@@ -448,36 +448,36 @@ static int klp_enable_func(struct klp_func *func)
 	return ret;
 }
 
-static void klp_disable_object(struct klp_object *obj)
+static void klp_unpatch_object(struct klp_object *obj)
 {
 	struct klp_func *func;
 
 	klp_for_each_func(obj, func)
-		if (func->state == KLP_ENABLED)
-			klp_disable_func(func);
+		if (func->patched)
+			klp_unpatch_func(func);
 
-	obj->state = KLP_DISABLED;
+	obj->patched = false;
 }
 
-static int klp_enable_object(struct klp_object *obj)
+static int klp_patch_object(struct klp_object *obj)
 {
 	struct klp_func *func;
 	int ret;
 
-	if (WARN_ON(obj->state != KLP_DISABLED))
+	if (WARN_ON(obj->patched))
 		return -EINVAL;
 
 	if (WARN_ON(!klp_is_object_loaded(obj)))
 		return -EINVAL;
 
 	klp_for_each_func(obj, func) {
-		ret = klp_enable_func(func);
+		ret = klp_patch_func(func);
 		if (ret) {
-			klp_disable_object(obj);
+			klp_unpatch_object(obj);
 			return ret;
 		}
 	}
-	obj->state = KLP_ENABLED;
+	obj->patched = true;
 
 	return 0;
 }

@@ -488,17 +488,17 @@ static int __klp_disable_patch(struct klp_patch *patch)
 
 	/* enforce stacking: only the last enabled patch can be disabled */
 	if (!list_is_last(&patch->list, &klp_patches) &&
-	    list_next_entry(patch, list)->state == KLP_ENABLED)
+	    list_next_entry(patch, list)->enabled)
 		return -EBUSY;
 
 	pr_notice("disabling patch '%s'\n", patch->mod->name);
 
 	klp_for_each_object(patch, obj) {
-		if (obj->state == KLP_ENABLED)
-			klp_disable_object(obj);
+		if (obj->patched)
+			klp_unpatch_object(obj);
 	}
 
-	patch->state = KLP_DISABLED;
+	patch->enabled = false;
 
 	return 0;
 }

@@ -522,7 +522,7 @@ int klp_disable_patch(struct klp_patch *patch)
 		goto err;
 	}
 
-	if (patch->state == KLP_DISABLED) {
+	if (!patch->enabled) {
 		ret = -EINVAL;
 		goto err;
 	}

@@ -540,12 +540,12 @@ static int __klp_enable_patch(struct klp_patch *patch)
 	struct klp_object *obj;
 	int ret;
 
-	if (WARN_ON(patch->state != KLP_DISABLED))
+	if (WARN_ON(patch->enabled))
 		return -EINVAL;
 
 	/* enforce stacking: only the first disabled patch can be enabled */
 	if (patch->list.prev != &klp_patches &&
-	    list_prev_entry(patch, list)->state == KLP_DISABLED)
+	    !list_prev_entry(patch, list)->enabled)
 		return -EBUSY;
 
 	pr_notice("enabling patch '%s'\n", patch->mod->name);

@@ -554,12 +554,12 @@ static int __klp_enable_patch(struct klp_patch *patch)
 		if (!klp_is_object_loaded(obj))
 			continue;
 
-		ret = klp_enable_object(obj);
+		ret = klp_patch_object(obj);
 		if (ret)
 			goto unregister;
 	}
 
-	patch->state = KLP_ENABLED;
+	patch->enabled = true;
 
 	return 0;
 

@@ -617,20 +617,20 @@ static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (ret)
 		return -EINVAL;
 
-	if (val != KLP_DISABLED && val != KLP_ENABLED)
+	if (val > 1)
 		return -EINVAL;
 
 	patch = container_of(kobj, struct klp_patch, kobj);
 
 	mutex_lock(&klp_mutex);
 
-	if (val == patch->state) {
+	if (patch->enabled == val) {
 		/* already in requested state */
 		ret = -EINVAL;
 		goto err;
 	}
 
-	if (val == KLP_ENABLED) {
+	if (val) {
 		ret = __klp_enable_patch(patch);
 		if (ret)
 			goto err;

@@ -655,7 +655,7 @@ static ssize_t enabled_show(struct kobject *kobj,
 	struct klp_patch *patch;
 
 	patch = container_of(kobj, struct klp_patch, kobj);
-	return snprintf(buf, PAGE_SIZE-1, "%d\n", patch->state);
+	return snprintf(buf, PAGE_SIZE-1, "%d\n", patch->enabled);
 }
 
 static struct kobj_attribute enabled_kobj_attr = __ATTR_RW(enabled);

@@ -749,7 +749,7 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func)
 		return -EINVAL;
 
 	INIT_LIST_HEAD(&func->stack_node);
-	func->state = KLP_DISABLED;
+	func->patched = false;
 
 	/* The format for the sysfs directory is <function,sympos> where sympos
 	 * is the nth occurrence of this symbol in kallsyms for the patched

@@ -804,7 +804,7 @@ static int klp_init_object(struct klp_patch *patch, struct klp_object *obj)
 	if (!obj->funcs)
 		return -EINVAL;
 
-	obj->state = KLP_DISABLED;
+	obj->patched = false;
 	obj->mod = NULL;
 
 	klp_find_object_module(obj);

@@ -845,7 +845,7 @@ static int klp_init_patch(struct klp_patch *patch)
 
 	mutex_lock(&klp_mutex);
 
-	patch->state = KLP_DISABLED;
+	patch->enabled = false;
 
 	ret = kobject_init_and_add(&patch->kobj, &klp_ktype_patch,
 				   klp_root_kobj, "%s", patch->mod->name);

@@ -891,7 +891,7 @@ int klp_unregister_patch(struct klp_patch *patch)
 		goto out;
 	}
 
-	if (patch->state == KLP_ENABLED) {
+	if (patch->enabled) {
 		ret = -EBUSY;
 		goto out;
 	}

@@ -978,13 +978,13 @@ int klp_module_coming(struct module *mod)
 				goto err;
 			}
 
-			if (patch->state == KLP_DISABLED)
+			if (!patch->enabled)
 				break;
 
 			pr_notice("applying patch '%s' to loading module '%s'\n",
 				  patch->mod->name, obj->mod->name);
 
-			ret = klp_enable_object(obj);
+			ret = klp_patch_object(obj);
 			if (ret) {
 				pr_warn("failed to apply patch '%s' to module '%s' (%d)\n",
 					patch->mod->name, obj->mod->name, ret);

@@ -1035,10 +1035,10 @@ void klp_module_going(struct module *mod)
 			if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
 				continue;
 
-			if (patch->state != KLP_DISABLED) {
+			if (patch->enabled) {
 				pr_notice("reverting patch '%s' on unloading module '%s'\n",
 					  patch->mod->name, obj->mod->name);
-				klp_disable_object(obj);
+				klp_unpatch_object(obj);
 			}
 
 			klp_free_object_loaded(obj);

@@ -408,26 +408,23 @@ static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr,
 {
 	struct klp_patch *patch;
 	int ret;
-	unsigned long val;
+	bool enabled;
 
-	ret = kstrtoul(buf, 10, &val);
+	ret = kstrtobool(buf, &enabled);
 	if (ret)
-		return -EINVAL;
-
-	if (val > 1)
-		return -EINVAL;
+		return ret;
 
 	patch = container_of(kobj, struct klp_patch, kobj);
 
 	mutex_lock(&klp_mutex);
 
-	if (patch->enabled == val) {
+	if (patch->enabled == enabled) {
 		/* already in requested state */
 		ret = -EINVAL;
 		goto err;
 	}
 
-	if (val) {
+	if (enabled) {
 		ret = __klp_enable_patch(patch);
 		if (ret)
 			goto err;

@@ -56,6 +56,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 #define TIF_SIGPENDING		1	/* signal pending */
 #define TIF_NEED_RESCHED	2	/* rescheduling necessary */
 #define TIF_UPROBE		3	/* breakpointed or single-stepping */
+#define TIF_PATCH_PENDING	4	/* pending live patching update */
 
 #define TIF_31BIT		16	/* 32bit process */
 #define TIF_MEMDIE		17	/* is terminating due to OOM killer */

@@ -74,6 +75,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 #define _TIF_SIGPENDING		_BITUL(TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	_BITUL(TIF_NEED_RESCHED)
 #define _TIF_UPROBE		_BITUL(TIF_UPROBE)
+#define _TIF_PATCH_PENDING	_BITUL(TIF_PATCH_PENDING)
 
 #define _TIF_31BIT		_BITUL(TIF_31BIT)
 #define _TIF_SINGLE_STEP	_BITUL(TIF_SINGLE_STEP)

@@ -47,7 +47,7 @@ STACK_SIZE  = 1 << STACK_SHIFT
 STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE
 
 _TIF_WORK	= (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
-		   _TIF_UPROBE)
+		   _TIF_UPROBE | _TIF_PATCH_PENDING)
 _TIF_TRACE	= (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 		   _TIF_SYSCALL_TRACEPOINT)
 _CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE | _CIF_FPU)

@@ -352,6 +352,11 @@ ENTRY(system_call)
 #endif
 	TSTMSK	__PT_FLAGS(%r11),_PIF_PER_TRAP
 	jo	.Lsysc_singlestep
+#ifdef CONFIG_LIVEPATCH
+	TSTMSK	__TI_flags(%r12),_TIF_PATCH_PENDING
+	jo	.Lsysc_patch_pending	# handle live patching just before
+					# signals and possible syscall restart
+#endif
 	TSTMSK	__TI_flags(%r12),_TIF_SIGPENDING
 	jo	.Lsysc_sigpending
 	TSTMSK	__TI_flags(%r12),_TIF_NOTIFY_RESUME

@@ -426,6 +431,16 @@ ENTRY(system_call)
 #endif
 
 #
+# _TIF_PATCH_PENDING is set, call klp_update_patch_state
+#
+#ifdef CONFIG_LIVEPATCH
+.Lsysc_patch_pending:
+	lg	%r2,__LC_CURRENT	# pass pointer to task struct
+	larl	%r14,.Lsysc_return
+	jg	klp_update_patch_state
+#endif
+
+#
 # _PIF_PER_TRAP is set, call do_per_trap
 #
 .Lsysc_singlestep:

@@ -674,6 +689,10 @@ ENTRY(io_int_handler)
 	jo	.Lio_mcck_pending
 	TSTMSK	__TI_flags(%r12),_TIF_NEED_RESCHED
 	jo	.Lio_reschedule
+#ifdef CONFIG_LIVEPATCH
+	TSTMSK	__TI_flags(%r12),_TIF_PATCH_PENDING
+	jo	.Lio_patch_pending
+#endif
 	TSTMSK	__TI_flags(%r12),_TIF_SIGPENDING
 	jo	.Lio_sigpending
 	TSTMSK	__TI_flags(%r12),_TIF_NOTIFY_RESUME

@@ -720,6 +739,16 @@ ENTRY(io_int_handler)
 	j	.Lio_return
 
 #
+# _TIF_PATCH_PENDING is set, call klp_update_patch_state
+#
+#ifdef CONFIG_LIVEPATCH
+.Lio_patch_pending:
+	lg	%r2,__LC_CURRENT	# pass pointer to task struct
+	larl	%r14,.Lio_return
+	jg	klp_update_patch_state
+#endif
+
+#
 # _TIF_SIGPENDING or is set, call do_signal
 #
 .Lio_sigpending:

@@ -44,6 +44,7 @@ Table of Contents
   3.8   /proc/<pid>/fdinfo/<fd> - Information about opened file
   3.9   /proc/<pid>/map_files - Information about memory mapped files
   3.10  /proc/<pid>/timerslack_ns - Task timerslack value
+  3.11	/proc/<pid>/patch_state - Livepatch patch operation state
 
   4	Configuring procfs
   4.1	Mount options

@@ -1886,6 +1887,23 @@ Valid values are from 0 - ULLONG_MAX
 An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level
 permissions on the task specified to change its timerslack_ns value.
 
+3.11	/proc/<pid>/patch_state - Livepatch patch operation state
+-----------------------------------------------------------------
+When CONFIG_LIVEPATCH is enabled, this file displays the value of the
+patch state for the task.
+
+A value of '-1' indicates that no patch is in transition.
+
+A value of '0' indicates that a patch is in transition and the task is
+unpatched.  If the patch is being enabled, then the task hasn't been
+patched yet.  If the patch is being disabled, then the task has already
+been unpatched.
+
+A value of '1' indicates that a patch is in transition and the task is
+patched.  If the patch is being enabled, then the task has already been
+patched.  If the patch is being disabled, then the task hasn't been
+unpatched yet.
+
 
 ------------------------------------------------------------------------------
 Configuring procfs

@@ -2797,6 +2797,15 @@ static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
 	return err;
 }
 
+#ifdef CONFIG_LIVEPATCH
+static int proc_pid_patch_state(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task)
+{
+	seq_printf(m, "%d\n", task->patch_state);
+	return 0;
+}
+#endif /* CONFIG_LIVEPATCH */
+
 /*
  * Thread groups
  */

@@ -2896,6 +2905,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("timers",	  S_IRUGO, proc_timers_operations),
 #endif
 	REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations),
+#ifdef CONFIG_LIVEPATCH
+	ONE("patch_state",  S_IRUSR, proc_pid_patch_state),
+#endif
 };
 
 static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)

@@ -3276,6 +3288,9 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
 	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
+#ifdef CONFIG_LIVEPATCH
+	ONE("patch_state",  S_IRUSR, proc_pid_patch_state),
+#endif
 };
 
 static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx)

@@ -296,8 +296,15 @@ section "Livepatch life-cycle" below for more details about these
 two operations.
 
 Module removal is only safe when there are no users of the underlying
-functions.  The immediate consistency model is not able to detect this;
-therefore livepatch modules cannot be removed. See "Limitations" below.
+functions. The immediate consistency model is not able to detect this. The
+code just redirects the functions at the very beginning and it does not
+check if the functions are in use. In other words, it knows when the
+functions get called but it does not know when the functions return.
+Therefore it cannot be decided when the livepatch module can be safely
+removed. This is solved by a hybrid consistency model. When the system is
+transitioned to a new patch state (patched/unpatched) it is guaranteed that
+no task sleeps or runs in the old code.
+
 
 5. Livepatch life-cycle
 =======================

@@ -449,23 +456,6 @@ The current Livepatch implementation has several limitations:
     by "notrace".
 
 
-  + Livepatch modules can not be removed.
-
-    The current implementation just redirects the functions at the very
-    beginning. It does not check if the functions are in use. In other
-    words, it knows when the functions get called but it does not
-    know when the functions return. Therefore it can not decide when
-    the livepatch module can be safely removed.
-
-    This will get most likely solved once a more complex consistency model
-    is supported. The idea is that a safe state for patching should also
-    mean a safe state for removing the patch.
-
-    Note that the patch itself might get disabled by writing zero
-    to /sys/kernel/livepatch/<patch>/enabled. It causes that the new
-    code will not longer get called. But it does not guarantee
-    that anyone is not sleeping anywhere in the new code.
-
 
   + Livepatch works reliably only when the dynamic ftrace is located at
     the very beginning of the function.

@@ -23,6 +23,7 @@
 
 #include <linux/module.h>
 #include <linux/ftrace.h>
+#include <linux/completion.h>
 
 #if IS_ENABLED(CONFIG_LIVEPATCH)
 

@@ -114,6 +115,7 @@ struct klp_object {
  * @list:	list node for global list of registered patches
  * @kobj:	kobject for sysfs resources
  * @enabled:	the patch is enabled (but operation may be incomplete)
+ * @finish:	for waiting till it is safe to remove the patch module
  */
 struct klp_patch {
 	/* external */

@@ -125,6 +127,7 @@ struct klp_patch {
 	struct list_head list;
 	struct kobject kobj;
 	bool enabled;
+	struct completion finish;
 };
 
 #define klp_for_each_object(patch, obj) \

@@ -29,6 +29,7 @@
 #include <linux/livepatch.h>
 #include <linux/elf.h>
 #include <linux/moduleloader.h>
+#include <linux/completion.h>
 #include <asm/cacheflush.h>
 #include "patch.h"
 #include "transition.h"

@@ -352,6 +353,18 @@ static int __klp_enable_patch(struct klp_patch *patch)
 	    !list_prev_entry(patch, list)->enabled)
 		return -EBUSY;
 
+	/*
+	 * A reference is taken on the patch module to prevent it from being
+	 * unloaded.
+	 *
+	 * Note: For immediate (no consistency model) patches we don't allow
+	 * patch modules to unload since there is no safe/sane method to
+	 * determine if a thread is still running in the patched code contained
+	 * in the patch module once the ftrace registration is successful.
+	 */
+	if (!try_module_get(patch->mod))
+		return -ENODEV;
+
 	pr_notice("enabling patch '%s'\n", patch->mod->name);
 
 	klp_init_transition(patch, KLP_PATCHED);

@@ -441,6 +454,15 @@ static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr,
 
 	mutex_lock(&klp_mutex);
 
+	if (!klp_is_patch_registered(patch)) {
+		/*
+		 * Module with the patch could either disappear meanwhile or is
+		 * not properly initialized yet.
+		 */
+		ret = -EINVAL;
+		goto err;
+	}
+
 	if (patch->enabled == enabled) {
 		/* already in requested state */
 		ret = -EINVAL;

@@ -497,10 +519,10 @@ static struct attribute *klp_patch_attrs[] = {
 
 static void klp_kobj_release_patch(struct kobject *kobj)
 {
-	/*
-	 * Once we have a consistency model we'll need to module_put() the
-	 * patch module here.  See klp_register_patch() for more details.
-	 */
+	struct klp_patch *patch;
+
+	patch = container_of(kobj, struct klp_patch, kobj);
+	complete(&patch->finish);
 }
 
 static struct kobj_type klp_ktype_patch = {

@@ -571,7 +593,6 @@ static void klp_free_patch(struct klp_patch *patch)
 	klp_free_objects_limited(patch, NULL);
 	if (!list_empty(&patch->list))
 		list_del(&patch->list);
-	kobject_put(&patch->kobj);
 }
 
 static int klp_init_func(struct klp_object *obj, struct klp_func *func)

@@ -694,11 +715,14 @@ static int klp_init_patch(struct klp_patch *patch)
 	mutex_lock(&klp_mutex);
 
 	patch->enabled = false;
+	init_completion(&patch->finish);
 
 	ret = kobject_init_and_add(&patch->kobj, &klp_ktype_patch,
 				   klp_root_kobj, "%s", patch->mod->name);
-	if (ret)
-		goto unlock;
+	if (ret) {
+		mutex_unlock(&klp_mutex);
+		return ret;
+	}
 
 	klp_for_each_object(patch, obj) {
 		ret = klp_init_object(patch, obj);

@@ -714,9 +738,12 @@ static int klp_init_patch(struct klp_patch *patch)
 
 free:
 	klp_free_objects_limited(patch, obj);
-	kobject_put(&patch->kobj);
-unlock:
+
 	mutex_unlock(&klp_mutex);
+
+	kobject_put(&patch->kobj);
+	wait_for_completion(&patch->finish);
+
 	return ret;
 }
 

@@ -730,23 +757,29 @@ static int klp_init_patch(struct klp_patch *patch)
  */
 int klp_unregister_patch(struct klp_patch *patch)
 {
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&klp_mutex);
 
 	if (!klp_is_patch_registered(patch)) {
 		ret = -EINVAL;
-		goto out;
+		goto err;
 	}
 
 	if (patch->enabled) {
 		ret = -EBUSY;
-		goto out;
+		goto err;
 	}
 
 	klp_free_patch(patch);
 
-out:
+	mutex_unlock(&klp_mutex);
+
+	kobject_put(&patch->kobj);
+	wait_for_completion(&patch->finish);
+
+	return 0;
+err:
 	mutex_unlock(&klp_mutex);
 	return ret;
 }

@@ -759,12 +792,13 @@ EXPORT_SYMBOL_GPL(klp_unregister_patch);
  * Initializes the data structure associated with the patch and
  * creates the sysfs interface.
  *
+ * There is no need to take the reference on the patch module here. It is done
+ * later when the patch is enabled.
+ *
  * Return: 0 on success, otherwise error
  */
 int klp_register_patch(struct klp_patch *patch)
 {
-	int ret;
-
 	if (!patch || !patch->mod)
 		return -EINVAL;
 

@@ -787,21 +821,7 @@ int klp_register_patch(struct klp_patch *patch)
 		return -ENOSYS;
 	}
 
-	/*
-	 * A reference is taken on the patch module to prevent it from being
-	 * unloaded.  Right now, we don't allow patch modules to unload since
-	 * there is currently no method to determine if a thread is still
-	 * running in the patched code contained in the patch module once
-	 * the ftrace registration is successful.
-	 */
-	if (!try_module_get(patch->mod))
-		return -ENODEV;
-
-	ret = klp_init_patch(patch);
-	if (ret)
-		module_put(patch->mod);
-
-	return ret;
+	return klp_init_patch(patch);
 }
 EXPORT_SYMBOL_GPL(klp_register_patch);
 

@@ -60,13 +60,21 @@ void klp_complete_transition(void)
 	struct klp_func *func;
 	struct task_struct *g, *task;
 	unsigned int cpu;
+	bool is_immediate = false;
 
 	if (klp_transition_patch->immediate)
 		goto done;
 
-	klp_for_each_object(klp_transition_patch, obj)
-		klp_for_each_func(obj, func)
+	klp_for_each_object(klp_transition_patch, obj) {
+		klp_for_each_func(obj, func) {
 			func->transition = false;
+			if (func->immediate)
+				is_immediate = true;
+		}
+	}
+
+	if (klp_target_state == KLP_UNPATCHED && !is_immediate)
+		module_put(klp_transition_patch->mod);
 
 	/* Prevent klp_ftrace_handler() from seeing KLP_UNDEFINED state */
 	if (klp_target_state == KLP_PATCHED)

@@ -99,7 +99,6 @@ static int livepatch_init(void)
 
 static void livepatch_exit(void)
 {
-	WARN_ON(klp_disable_patch(&patch));
 	WARN_ON(klp_unregister_patch(&patch));
 }
 

@@ -25,6 +25,14 @@ Description:
 		code is currently applied.  Writing 0 will disable the patch
 		while writing 1 will re-enable the patch.
 
+What:		/sys/kernel/livepatch/<patch>/transition
+Date:		May 2016
+KernelVersion:	4.11.0
+Contact:	live-patching@vger.kernel.org
+Description:
+		An attribute which indicates whether the patch is currently in
+		transition.
+
 What:		/sys/kernel/livepatch/<patch>/<object>
 Date:		Nov 2014
 KernelVersion:	3.19.0

@@ -72,7 +72,8 @@ example, they add a NULL pointer or a boundary check, fix a race by adding
 a missing memory barrier, or add some locking around a critical section.
 Most of these changes are self contained and the function presents itself
 the same way to the rest of the system. In this case, the functions might
-be updated independently one by one.
+be updated independently one by one.  (This can be done by setting the
+'immediate' flag in the klp_patch struct.)
 
 But there are more complex fixes. For example, a patch might change
 ordering of locking in multiple functions at the same time. Or a patch

@@ -86,20 +87,127 @@ or no data are stored in the modified structures at the moment.
 The theory about how to apply functions a safe way is rather complex.
 The aim is to define a so-called consistency model. It attempts to define
 conditions when the new implementation could be used so that the system
-stays consistent. The theory is not yet finished. See the discussion at
-https://lkml.kernel.org/r/20141107140458.GA21774@suse.cz
-
-The current consistency model is very simple. It guarantees that either
-the old or the new function is called. But various functions get redirected
-one by one without any synchronization.
-
-In other words, the current implementation _never_ modifies the behavior
-in the middle of the call. It is because it does _not_ rewrite the entire
-function in the memory. Instead, the function gets redirected at the
-very beginning. But this redirection is used immediately even when
-some other functions from the same patch have not been redirected yet.
-
-See also the section "Limitations" below.
+stays consistent.
+
+Livepatch has a consistency model which is a hybrid of kGraft and
+kpatch:  it uses kGraft's per-task consistency and syscall barrier
+switching combined with kpatch's stack trace switching.  There are also
+a number of fallback options which make it quite flexible.
+
+Patches are applied on a per-task basis, when the task is deemed safe to
+switch over.  When a patch is enabled, livepatch enters into a
+transition state where tasks are converging to the patched state.
+Usually this transition state can complete in a few seconds.  The same
+sequence occurs when a patch is disabled, except the tasks converge from
+the patched state to the unpatched state.
+
+An interrupt handler inherits the patched state of the task it
+interrupts.  The same is true for forked tasks: the child inherits the
+patched state of the parent.
+
+Livepatch uses several complementary approaches to determine when it's
+safe to patch tasks:
+
+1. The first and most effective approach is stack checking of sleeping
+   tasks.  If no affected functions are on the stack of a given task,
+   the task is patched.  In most cases this will patch most or all of
+   the tasks on the first try.  Otherwise it'll keep trying
+   periodically.  This option is only available if the architecture has
+   reliable stacks (HAVE_RELIABLE_STACKTRACE).
+
+2. The second approach, if needed, is kernel exit switching.  A
+   task is switched when it returns to user space from a system call, a
+   user space IRQ, or a signal.  It's useful in the following cases:
+
+   a) Patching I/O-bound user tasks which are sleeping on an affected
+      function.  In this case you have to send SIGSTOP and SIGCONT to
+      force it to exit the kernel and be patched.
+   b) Patching CPU-bound user tasks.  If the task is highly CPU-bound
+      then it will get patched the next time it gets interrupted by an
+      IRQ.
+   c) In the future it could be useful for applying patches for
+      architectures which don't yet have HAVE_RELIABLE_STACKTRACE.  In
+      this case you would have to signal most of the tasks on the
+      system.  However this isn't supported yet because there's
+      currently no way to patch kthreads without
+      HAVE_RELIABLE_STACKTRACE.
+
+3. For idle "swapper" tasks, since they don't ever exit the kernel, they
+   instead have a klp_update_patch_state() call in the idle loop which
+   allows them to be patched before the CPU enters the idle state.
+
+   (Note there's not yet such an approach for kthreads.)
+
+All the above approaches may be skipped by setting the 'immediate' flag
+in the 'klp_patch' struct, which will disable per-task consistency and
+patch all tasks immediately.  This can be useful if the patch doesn't
+change any function or data semantics.  Note that, even with this flag
+set, it's possible that some tasks may still be running with an old
+version of the function, until that function returns.
+
+There's also an 'immediate' flag in the 'klp_func' struct which allows
+you to specify that certain functions in the patch can be applied
+without per-task consistency.  This might be useful if you want to patch
+a common function like schedule(), and the function change doesn't need
+consistency but the rest of the patch does.
+
+For architectures which don't have HAVE_RELIABLE_STACKTRACE, the user
+must set patch->immediate which causes all tasks to be patched
+immediately.  This option should be used with care, only when the patch
+doesn't change any function or data semantics.
+
+In the future, architectures which don't have HAVE_RELIABLE_STACKTRACE
+may be allowed to use per-task consistency if we can come up with
+another way to patch kthreads.
+
+The /sys/kernel/livepatch/<patch>/transition file shows whether a patch
+is in transition.  Only a single patch (the topmost patch on the stack)
+can be in transition at a given time.  A patch can remain in transition
+indefinitely, if any of the tasks are stuck in the initial patch state.
+
+A transition can be reversed and effectively canceled by writing the
+opposite value to the /sys/kernel/livepatch/<patch>/enabled file while
+the transition is in progress.  Then all the tasks will attempt to
+converge back to the original patch state.
+
+There's also a /proc/<pid>/patch_state file which can be used to
+determine which tasks are blocking completion of a patching operation.
+If a patch is in transition, this file shows 0 to indicate the task is
+unpatched and 1 to indicate it's patched.  Otherwise, if no patch is in
+transition, it shows -1.  Any tasks which are blocking the transition
+can be signaled with SIGSTOP and SIGCONT to force them to change their
+patched state.
+
+
+3.1 Adding consistency model support to new architectures
+---------------------------------------------------------
+
+For adding consistency model support to new architectures, there are a
+few options:
+
+1) Add CONFIG_HAVE_RELIABLE_STACKTRACE.  This means porting objtool, and
+   for non-DWARF unwinders, also making sure there's a way for the stack
+   tracing code to detect interrupts on the stack.
+
+2) Alternatively, figure out a way to patch kthreads without stack
+   checking.  If all kthreads sleep in the same place, then we can
+   designate that place as a patching point.  I think Petr M has been
+   working on that?  In that case, arches without
+   HAVE_RELIABLE_STACKTRACE would still be able to use the
+   non-stack-checking parts of the consistency model:
+
+   a) patching user tasks when they cross the kernel/user space
+      boundary; and
+
+   b) patching kthreads and idle tasks at their designated patch points.
+
+   This option isn't as good as option 1 because it requires signaling
+   most of the tasks to patch them.  But it could still be a good backup
+   option for those architectures which don't have reliable stack traces
+   yet.
+
+In the meantime, patches for such architectures can bypass the
+consistency model by setting klp_patch.immediate to true.
 
 
 4. Livepatch module

@@ -134,7 +242,7 @@ Documentation/livepatch/module-elf-format.txt for more details.
 
 
 4.2. Metadata
-------------
+-------------
 
 The patch is described by several structures that split the information
 into three levels:

@@ -239,9 +347,15 @@ Registered patches might be enabled either by calling klp_enable_patch() or
 by writing '1' to /sys/kernel/livepatch/<name>/enabled. The system will
 start using the new implementation of the patched functions at this stage.
 
-In particular, if an original function is patched for the first time, a
-function specific struct klp_ops is created and an universal ftrace handler
-is registered.
+When a patch is enabled, livepatch enters into a transition state where
+tasks are converging to the patched state.  This is indicated by a value
+of '1' in /sys/kernel/livepatch/<name>/transition.  Once all tasks have
+been patched, the 'transition' value changes to '0'.  For more
+information about this process, see the "Consistency model" section.
+
+If an original function is patched for the first time, a function
+specific struct klp_ops is created and an universal ftrace handler is
+registered.
 
 Functions might be patched multiple times. The ftrace handler is registered
 only once for the given function. Further patches just add an entry to the

@@ -261,6 +375,12 @@ by writing '0' to /sys/kernel/livepatch/<name>/enabled. At this stage
 either the code from the previously enabled patch or even the original
 code gets used.
 
+When a patch is disabled, livepatch enters into a transition state where
+tasks are converging to the unpatched state.  This is indicated by a
+value of '1' in /sys/kernel/livepatch/<name>/transition.  Once all tasks
+have been unpatched, the 'transition' value changes to '0'.  For more
+information about this process, see the "Consistency model" section.
+
 Here all the functions (struct klp_func) associated with the to-be-disabled
 patch are removed from the corresponding struct klp_ops. The ftrace handler
 is unregistered and the struct klp_ops is freed when the func_stack list

@@ -14,6 +14,7 @@
 #include <linux/rbtree.h>
 #include <net/net_namespace.h>
 #include <linux/sched/rt.h>
+#include <linux/livepatch.h>
 
 #include <asm/thread_info.h>