Merge branches 'for-4.12/upstream' and 'for-4.12/klp-hybrid-consistency-model' into for-linus

Documentation/ABI/testing/sysfs-kernel-livepatch

@@ -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:		Feb 2017
+KernelVersion:	4.12.0
+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

Documentation/filesystems/proc.txt

@@ -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
@@ -1887,6 +1888,23 @@ 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

arch/Kconfig

@@ -713,6 +713,12 @@ 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

arch/powerpc/include/asm/thread_info.h

@@ -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 */

arch/powerpc/kernel/signal.c

@@ -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();
 }
 

arch/s390/include/asm/thread_info.h

@@ -51,14 +51,13 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 /*
  * thread information flags bit numbers
  */
+/* _TIF_WORK bits */
 #define TIF_NOTIFY_RESUME	0	/* callback before returning to user */
 #define TIF_SIGPENDING		1	/* signal pending */
 #define TIF_NEED_RESCHED	2	/* rescheduling necessary */
-#define TIF_SYSCALL_TRACE	3	/* syscall trace active */
-#define TIF_SYSCALL_AUDIT	4	/* syscall auditing active */
-#define TIF_SECCOMP		5	/* secure computing */
-#define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
-#define TIF_UPROBE		7	/* breakpointed or single-stepping */
+#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 */
 #define TIF_RESTORE_SIGMASK	18	/* restore signal mask in do_signal() */
@@ -66,15 +65,24 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 #define TIF_BLOCK_STEP		20	/* This task is block stepped */
 #define TIF_UPROBE_SINGLESTEP	21	/* This task is uprobe single stepped */
 
+/* _TIF_TRACE bits */
+#define TIF_SYSCALL_TRACE	24	/* syscall trace active */
+#define TIF_SYSCALL_AUDIT	25	/* syscall auditing active */
+#define TIF_SECCOMP		26	/* secure computing */
+#define TIF_SYSCALL_TRACEPOINT	27	/* syscall tracepoint instrumentation */
+
 #define _TIF_NOTIFY_RESUME	_BITUL(TIF_NOTIFY_RESUME)
 #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)
+
 #define _TIF_SYSCALL_TRACE	_BITUL(TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	_BITUL(TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		_BITUL(TIF_SECCOMP)
 #define _TIF_SYSCALL_TRACEPOINT	_BITUL(TIF_SYSCALL_TRACEPOINT)
-#define _TIF_UPROBE		_BITUL(TIF_UPROBE)
-#define _TIF_31BIT		_BITUL(TIF_31BIT)
-#define _TIF_SINGLE_STEP	_BITUL(TIF_SINGLE_STEP)
 
 #endif /* _ASM_THREAD_INFO_H */

arch/s390/kernel/entry.S

@@ -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_PRIMARY | \
@@ -334,6 +334,11 @@ 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
@@ -408,6 +413,16 @@ ENTRY(system_call)
 	jg	uprobe_notify_resume
 #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
 #
@@ -659,6 +674,10 @@ 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
@@ -707,6 +726,16 @@ ENTRY(io_int_handler)
 	TRACE_IRQS_OFF
 	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
 #

arch/x86/Kconfig

@@ -160,6 +160,7 @@ 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

arch/x86/entry/common.c

@@ -22,6 +22,7 @@
 #include <linux/context_tracking.h>
 #include <linux/user-return-notifier.h>
 #include <linux/uprobes.h>
+#include <linux/livepatch.h>
 
 #include <asm/desc.h>
 #include <asm/traps.h>
@@ -130,14 +131,13 @@ static long syscall_trace_enter(struct pt_regs *regs)
 
 #define EXIT_TO_USERMODE_LOOP_FLAGS				\
 	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |	\
-	 _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY)
+	 _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING)
 
 static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 {
 	/*
 	 * In order to return to user mode, we need to have IRQs off with
-	 * none of _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_USER_RETURN_NOTIFY,
-	 * _TIF_UPROBE, or _TIF_NEED_RESCHED set.  Several of these flags
+	 * none of EXIT_TO_USERMODE_LOOP_FLAGS set.  Several of these flags
 	 * can be set at any time on preemptable kernels if we have IRQs on,
 	 * so we need to loop.  Disabling preemption wouldn't help: doing the
 	 * work to clear some of the flags can sleep.
@@ -164,6 +164,9 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 		if (cached_flags & _TIF_USER_RETURN_NOTIFY)
 			fire_user_return_notifiers();
 
+		if (cached_flags & _TIF_PATCH_PENDING)
+			klp_update_patch_state(current);
+
 		/* Disable IRQs and retry */
 		local_irq_disable();
 

arch/x86/include/asm/thread_info.h

@@ -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 */
@@ -87,6 +84,7 @@ struct thread_info {
 #define TIF_SECCOMP		8	/* secure computing */
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_UPROBE		12	/* breakpointed or singlestepping */
+#define TIF_PATCH_PENDING	13	/* pending live patching update */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
 #define TIF_NOHZ		19	/* in adaptive nohz mode */
@@ -103,13 +101,14 @@ 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)
 #define _TIF_USER_RETURN_NOTIFY	(1 << TIF_USER_RETURN_NOTIFY)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
+#define _TIF_PATCH_PENDING	(1 << TIF_PATCH_PENDING)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
 #define _TIF_NOHZ		(1 << TIF_NOHZ)
@@ -133,8 +132,10 @@ 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_PATCH_PENDING | _TIF_NOHZ | _TIF_SYSCALL_TRACEPOINT)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\

arch/x86/include/asm/unwind.h

@@ -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

arch/x86/kernel/stacktrace.c

@@ -76,6 +76,101 @@ 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
+
+#define STACKTRACE_DUMP_ONCE(task) ({				\
+	static bool __section(.data.unlikely) __dumped;		\
+								\
+	if (!__dumped) {					\
+		__dumped = true;				\
+		WARN_ON(1);					\
+		show_stack(task, NULL);				\
+	}							\
+})
+
+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 -EINVAL;
+
+			/*
+			 * The last frame contains the user mode syscall
+			 * pt_regs.  Skip it and finish the unwind.
+			 */
+			unwind_next_frame(&state);
+			if (!unwind_done(&state)) {
+				STACKTRACE_DUMP_ONCE(task);
+				return -EINVAL;
+			}
+			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 (!addr) {
+			STACKTRACE_DUMP_ONCE(task);
+			return -EINVAL;
+		}
+
+		if (save_stack_address(trace, addr, false))
+			return -EINVAL;
+	}
+
+	/* Check for stack corruption */
+	if (unwind_error(&state)) {
+		STACKTRACE_DUMP_ONCE(task);
+		return -EINVAL;
+	}
+
+	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 {
@@ -138,4 +233,3 @@ void save_stack_trace_user(struct stack_trace *trace)
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
-

arch/x86/kernel/unwind_frame.c

@@ -225,6 +225,8 @@ 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

fs/proc/base.c

@@ -2834,6 +2834,15 @@ 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
  */
@@ -2933,6 +2942,9 @@ 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)
@@ -3315,6 +3327,9 @@ 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)

include/linux/init_task.h

@@ -15,6 +15,7 @@
 #include <linux/sched/autogroup.h>
 #include <net/net_namespace.h>
 #include <linux/sched/rt.h>
+#include <linux/livepatch.h>
 #include <linux/mm_types.h>
 
 #include <asm/thread_info.h>
@@ -202,6 +203,13 @@ extern struct cred init_cred;
 # define INIT_KASAN(tsk)
 #endif
 
+#ifdef CONFIG_LIVEPATCH
+# define INIT_LIVEPATCH(tsk)						\
+	.patch_state = KLP_UNDEFINED,
+#else
+# define INIT_LIVEPATCH(tsk)
+#endif
+
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 # define INIT_TASK_TI(tsk)			\
 	.thread_info = INIT_THREAD_INFO(tsk),	\
@@ -288,6 +296,7 @@ extern struct cred init_cred;
 	INIT_VTIME(tsk)							\
 	INIT_NUMA_BALANCING(tsk)					\
 	INIT_KASAN(tsk)							\
+	INIT_LIVEPATCH(tsk)						\
 }
 
 

include/linux/livepatch.h

@@ -23,15 +23,16 @@
 
 #include <linux/module.h>
 #include <linux/ftrace.h>
+#include <linux/completion.h>
 
 #if IS_ENABLED(CONFIG_LIVEPATCH)
 
 #include <asm/livepatch.h>
 
-enum klp_state {
-	KLP_DISABLED,
-	KLP_ENABLED
-};
+/* task patch states */
+#define KLP_UNDEFINED	-1
+#define KLP_UNPATCHED	 0
+#define KLP_PATCHED	 1
 
 /**
  * struct klp_func - function structure for live patching
@@ -39,10 +40,29 @@ enum klp_state {
  * @new_func:	pointer to the patched function code
  * @old_sympos: a hint indicating which symbol position the old function
  *		can be found (optional)
+ * @immediate:  patch the func immediately, bypassing safety mechanisms
  * @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
+ * @old_size:	size of the old function
+ * @new_size:	size of the new function
+ * @patched:	the func has been added to the klp_ops list
+ * @transition:	the func is currently being applied or reverted
+ *
+ * The patched and transition variables define the func's patching state.  When
+ * patching, a func is always in one of the following states:
+ *
+ *   patched=0 transition=0: unpatched
+ *   patched=0 transition=1: unpatched, temporary starting state
+ *   patched=1 transition=1: patched, may be visible to some tasks
+ *   patched=1 transition=0: patched, visible to all tasks
+ *
+ * And when unpatching, it goes in the reverse order:
+ *
+ *   patched=1 transition=0: patched, visible to all tasks
+ *   patched=1 transition=1: patched, may be visible to some tasks
+ *   patched=0 transition=1: unpatched, temporary ending state
+ *   patched=0 transition=0: unpatched
  */
 struct klp_func {
 	/* external */
@@ -56,12 +76,15 @@ struct klp_func {
 	 * in kallsyms for the given object is used.
 	 */
 	unsigned long old_sympos;
+	bool immediate;
 
 	/* internal */
 	unsigned long old_addr;
 	struct kobject kobj;
-	enum klp_state state;
 	struct list_head stack_node;
+	unsigned long old_size, new_size;
+	bool patched;
+	bool transition;
 };
 
 /**
@@ -71,7 +94,7 @@ 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 */
@@ -81,26 +104,30 @@ struct klp_object {
 	/* internal */
 	struct kobject kobj;
 	struct module *mod;
-	enum klp_state state;
+	bool patched;
 };
 
 /**
  * struct klp_patch - patch structure for live patching
  * @mod:	reference to the live patch module
  * @objs:	object entries for kernel objects to be patched
+ * @immediate:  patch all funcs immediately, bypassing safety mechanisms
  * @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)
+ * @finish:	for waiting till it is safe to remove the patch module
  */
 struct klp_patch {
 	/* external */
 	struct module *mod;
 	struct klp_object *objs;
+	bool immediate;
 
 	/* internal */
 	struct list_head list;
 	struct kobject kobj;
-	enum klp_state state;
+	bool enabled;
+	struct completion finish;
 };
 
 #define klp_for_each_object(patch, obj) \
@@ -123,10 +150,27 @@ 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_copy_process(struct task_struct *child);
+void klp_update_patch_state(struct task_struct *task);
+
+static inline bool klp_patch_pending(struct task_struct *task)
+{
+	return test_tsk_thread_flag(task, TIF_PATCH_PENDING);
+}
+
+static inline bool klp_have_reliable_stack(void)
+{
+	return IS_ENABLED(CONFIG_STACKTRACE) &&
+	       IS_ENABLED(CONFIG_HAVE_RELIABLE_STACKTRACE);
+}
+
 #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 bool klp_patch_pending(struct task_struct *task) { return false; }
+static inline void klp_update_patch_state(struct task_struct *task) {}
+static inline void klp_copy_process(struct task_struct *child) {}
 
 #endif /* CONFIG_LIVEPATCH */
 

include/linux/sched.h

@@ -1037,6 +1037,9 @@ struct task_struct {
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 	/* A live task holds one reference: */
 	atomic_t			stack_refcount;
+#endif
+#ifdef CONFIG_LIVEPATCH
+	int patch_state;
 #endif
 	/* CPU-specific state of this task: */
 	struct thread_struct		thread;

include/linux/stacktrace.h

@@ -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 +31,13 @@ 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
+# define save_stack_trace_tsk_reliable(tsk, trace)	({ -ENOSYS; })
+#endif /* CONFIG_STACKTRACE */
 
-#endif
+#endif /* __LINUX_STACKTRACE_H */

kernel/fork.c

@@ -87,6 +87,7 @@
 #include <linux/compiler.h>
 #include <linux/sysctl.h>
 #include <linux/kcov.h>
+#include <linux/livepatch.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -1797,6 +1798,8 @@ static __latent_entropy struct task_struct *copy_process(
 		p->parent_exec_id = current->self_exec_id;
 	}
 
+	klp_copy_process(p);
+
 	spin_lock(&current->sighand->siglock);
 
 	/*

kernel/livepatch/Makefile

 obj-$(CONFIG_LIVEPATCH) += livepatch.o
 
-livepatch-objs := core.o
+livepatch-objs := core.o patch.o transition.o

kernel/livepatch/core.h

+#ifndef _LIVEPATCH_CORE_H
+#define _LIVEPATCH_CORE_H
+
+extern struct mutex klp_mutex;
+
+#endif /* _LIVEPATCH_CORE_H */

kernel/livepatch/patch.c

+/*
+ * patch.c - livepatch patching functions
+ *
+ * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com>
+ * Copyright (C) 2014 SUSE
+ * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/livepatch.h>
+#include <linux/list.h>
+#include <linux/ftrace.h>
+#include <linux/rculist.h>
+#include <linux/slab.h>
+#include <linux/bug.h>
+#include <linux/printk.h>
+#include "patch.h"
+#include "transition.h"
+
+static LIST_HEAD(klp_ops);
+
+struct klp_ops *klp_find_ops(unsigned long old_addr)
+{
+	struct klp_ops *ops;
+	struct klp_func *func;
+
+	list_for_each_entry(ops, &klp_ops, node) {
+		func = list_first_entry(&ops->func_stack, struct klp_func,
+					stack_node);
+		if (func->old_addr == old_addr)
+			return ops;
+	}
+
+	return NULL;
+}
+
+static void notrace klp_ftrace_handler(unsigned long ip,
+				       unsigned long parent_ip,
+				       struct ftrace_ops *fops,
+				       struct pt_regs *regs)
+{
+	struct klp_ops *ops;
+	struct klp_func *func;
+	int patch_state;
+
+	ops = container_of(fops, struct klp_ops, fops);
+
+	rcu_read_lock();
+
+	func = list_first_or_null_rcu(&ops->func_stack, struct klp_func,
+				      stack_node);
+
+	/*
+	 * func should never be NULL because preemption should be disabled here
+	 * and unregister_ftrace_function() does the equivalent of a
+	 * synchronize_sched() before the func_stack removal.
+	 */
+	if (WARN_ON_ONCE(!func))
+		goto unlock;
+
+	/*
+	 * In the enable path, enforce the order of the ops->func_stack and
+	 * func->transition reads.  The corresponding write barrier is in
+	 * __klp_enable_patch().
+	 *
+	 * (Note that this barrier technically isn't needed in the disable
+	 * path.  In the rare case where klp_update_patch_state() runs before
+	 * this handler, its TIF_PATCH_PENDING read and this func->transition
+	 * read need to be ordered.  But klp_update_patch_state() already
+	 * enforces that.)
+	 */
+	smp_rmb();
+
+	if (unlikely(func->transition)) {
+
+		/*
+		 * Enforce the order of the func->transition and
+		 * current->patch_state reads.  Otherwise we could read an
+		 * out-of-date task state and pick the wrong function.  The
+		 * corresponding write barrier is in klp_init_transition().
+		 */
+		smp_rmb();
+
+		patch_state = current->patch_state;
+
+		WARN_ON_ONCE(patch_state == KLP_UNDEFINED);
+
+		if (patch_state == KLP_UNPATCHED) {
+			/*
+			 * Use the previously patched version of the function.
+			 * If no previous patches exist, continue with the
+			 * original function.
+			 */
+			func = list_entry_rcu(func->stack_node.next,
+					      struct klp_func, stack_node);
+
+			if (&func->stack_node == &ops->func_stack)
+				goto unlock;
+		}
+	}
+
+	klp_arch_set_pc(regs, (unsigned long)func->new_func);
+unlock:
+	rcu_read_unlock();
+}
+
+/*
+ * Convert a function address into the appropriate ftrace location.
+ *
+ * Usually this is just the address of the function, but on some architectures
+ * it's more complicated so allow them to provide a custom behaviour.
+ */
+#ifndef klp_get_ftrace_location
+static unsigned long klp_get_ftrace_location(unsigned long faddr)
+{
+	return faddr;
+}
+#endif
+
+static void klp_unpatch_func(struct klp_func *func)
+{
+	struct klp_ops *ops;
+
+	if (WARN_ON(!func->patched))
+		return;
+	if (WARN_ON(!func->old_addr))
+		return;
+
+	ops = klp_find_ops(func->old_addr);
+	if (WARN_ON(!ops))
+		return;
+
+	if (list_is_singular(&ops->func_stack)) {
+		unsigned long ftrace_loc;
+
+		ftrace_loc = klp_get_ftrace_location(func->old_addr);
+		if (WARN_ON(!ftrace_loc))
+			return;
+
+		WARN_ON(unregister_ftrace_function(&ops->fops));
+		WARN_ON(ftrace_set_filter_ip(&ops->fops, ftrace_loc, 1, 0));
+
+		list_del_rcu(&func->stack_node);
+		list_del(&ops->node);
+		kfree(ops);
+	} else {
+		list_del_rcu(&func->stack_node);
+	}
+
+	func->patched = false;
+}
+
+static int klp_patch_func(struct klp_func *func)
+{
+	struct klp_ops *ops;
+	int ret;
+
+	if (WARN_ON(!func->old_addr))
+		return -EINVAL;
+
+	if (WARN_ON(func->patched))
+		return -EINVAL;
+
+	ops = klp_find_ops(func->old_addr);
+	if (!ops) {
+		unsigned long ftrace_loc;
+
+		ftrace_loc = klp_get_ftrace_location(func->old_addr);
+		if (!ftrace_loc) {
+			pr_err("failed to find location for function '%s'\n",
+				func->old_name);
+			return -EINVAL;
+		}
+
+		ops = kzalloc(sizeof(*ops), GFP_KERNEL);
+		if (!ops)
+			return -ENOMEM;
+
+		ops->fops.func = klp_ftrace_handler;
+		ops->fops.flags = FTRACE_OPS_FL_SAVE_REGS |
+				  FTRACE_OPS_FL_DYNAMIC |
+				  FTRACE_OPS_FL_IPMODIFY;
+
+		list_add(&ops->node, &klp_ops);
+
+		INIT_LIST_HEAD(&ops->func_stack);
+		list_add_rcu(&func->stack_node, &ops->func_stack);
+
+		ret = ftrace_set_filter_ip(&ops->fops, ftrace_loc, 0, 0);
+		if (ret) {
+			pr_err("failed to set ftrace filter for function '%s' (%d)\n",
+			       func->old_name, ret);
+			goto err;
+		}
+
+		ret = register_ftrace_function(&ops->fops);
+		if (ret) {
+			pr_err("failed to register ftrace handler for function '%s' (%d)\n",
+			       func->old_name, ret);
+			ftrace_set_filter_ip(&ops->fops, ftrace_loc, 1, 0);
+			goto err;
+		}
+
+
+	} else {
+		list_add_rcu(&func->stack_node, &ops->func_stack);
+	}
+
+	func->patched = true;
+
+	return 0;
+
+err:
+	list_del_rcu(&func->stack_node);
+	list_del(&ops->node);
+	kfree(ops);
+	return ret;
+}
+
+void klp_unpatch_object(struct klp_object *obj)
+{
+	struct klp_func *func;
+
+	klp_for_each_func(obj, func)
+		if (func->patched)
+			klp_unpatch_func(func);
+
+	obj->patched = false;
+}
+
+int klp_patch_object(struct klp_object *obj)
+{
+	struct klp_func *func;
+	int ret;
+
+	if (WARN_ON(obj->patched))
+		return -EINVAL;
+
+	klp_for_each_func(obj, func) {
+		ret = klp_patch_func(func);
+		if (ret) {
+			klp_unpatch_object(obj);
+			return ret;
+		}
+	}
+	obj->patched = true;
+
+	return 0;
+}
+
+void klp_unpatch_objects(struct klp_patch *patch)
+{
+	struct klp_object *obj;
+
+	klp_for_each_object(patch, obj)
+		if (obj->patched)
+			klp_unpatch_object(obj);
+}

kernel/livepatch/patch.h

+#ifndef _LIVEPATCH_PATCH_H
+#define _LIVEPATCH_PATCH_H
+
+#include <linux/livepatch.h>
+#include <linux/list.h>
+#include <linux/ftrace.h>
+
+/**
+ * struct klp_ops - structure for tracking registered ftrace ops structs
+ *
+ * A single ftrace_ops is shared between all enabled replacement functions
+ * (klp_func structs) which have the same old_addr.  This allows the switch
+ * between function versions to happen instantaneously by updating the klp_ops
+ * struct's func_stack list.  The winner is the klp_func at the top of the
+ * func_stack (front of the list).
+ *
+ * @node:	node for the global klp_ops list
+ * @func_stack:	list head for the stack of klp_func's (active func is on top)
+ * @fops:	registered ftrace ops struct
+ */
+struct klp_ops {
+	struct list_head node;
+	struct list_head func_stack;
+	struct ftrace_ops fops;
+};
+
+struct klp_ops *klp_find_ops(unsigned long old_addr);
+
+int klp_patch_object(struct klp_object *obj);
+void klp_unpatch_object(struct klp_object *obj);
+void klp_unpatch_objects(struct klp_patch *patch);
+
+#endif /* _LIVEPATCH_PATCH_H */

kernel/livepatch/transition.h

+#ifndef _LIVEPATCH_TRANSITION_H
+#define _LIVEPATCH_TRANSITION_H
+
+#include <linux/livepatch.h>
+
+extern struct klp_patch *klp_transition_patch;
+
+void klp_init_transition(struct klp_patch *patch, int state);
+void klp_cancel_transition(void);
+void klp_start_transition(void);
+void klp_try_complete_transition(void);
+void klp_reverse_transition(void);
+
+#endif /* _LIVEPATCH_TRANSITION_H */

kernel/sched/idle.c

@@ -10,6 +10,7 @@
 #include <linux/mm.h>
 #include <linux/stackprotector.h>
 #include <linux/suspend.h>
+#include <linux/livepatch.h>
 
 #include <asm/tlb.h>
 
@@ -265,6 +266,9 @@ static void do_idle(void)
 
 	sched_ttwu_pending();
 	schedule_preempt_disabled();
+
+	if (unlikely(klp_patch_pending(current)))
+		klp_update_patch_state(current);
 }
 
 bool cpu_in_idle(unsigned long pc)

kernel/stacktrace.c

@@ -54,8 +54,8 @@ 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
@@ -69,3 +69,11 @@ 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;
+}

samples/livepatch/livepatch-sample.c

@@ -17,6 +17,8 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/livepatch.h>
@@ -69,6 +71,21 @@ static int livepatch_init(void)
 {
 	int ret;
 
+	if (!klp_have_reliable_stack() && !patch.immediate) {
+		/*
+		 * WARNING: Be very careful when using 'patch.immediate' in
+		 * your patches.  It's ok to use it for simple patches like
+		 * this, but for more complex patches which change function
+		 * semantics, locking semantics, or data structures, it may not
+		 * be safe.  Use of this option will also prevent removal of
+		 * the patch.
+		 *
+		 * See Documentation/livepatch/livepatch.txt for more details.
+		 */
+		patch.immediate = true;
+		pr_notice("The consistency model isn't supported for your architecture.  Bypassing safety mechanisms and applying the patch immediately.\n");
+	}
+
 	ret = klp_register_patch(&patch);
 	if (ret)
 		return ret;
@@ -82,7 +99,6 @@ static int livepatch_init(void)
 
 static void livepatch_exit(void)
 {
-	WARN_ON(klp_disable_patch(&patch));
 	WARN_ON(klp_unregister_patch(&patch));
 }