Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/livepatching

Pull livepatch updates from Jiri Kosina:

 - a per-task consistency model is being added for architectures that
   support reliable stack dumping (extending this, currently rather
   trivial set, is currently in the works).

   This extends the nature of the types of patches that can be applied
   by live patching infrastructure. The code stems from the design
   proposal made [1] back in November 2014. It's a hybrid of SUSE's
   kGraft and RH's kpatch, combining advantages of both: 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.

   Most of the heavy lifting done by Josh Poimboeuf with help from
   Miroslav Benes and Petr Mladek

   [1] https://lkml.kernel.org/r/20141107140458.GA21774@suse.cz

 - module load time patch optimization from Zhou Chengming

 - a few assorted small fixes

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/livepatching:
  livepatch: add missing printk newlines
  livepatch: Cancel transition a safe way for immediate patches
  livepatch: Reduce the time of finding module symbols
  livepatch: make klp_mutex proper part of API
  livepatch: allow removal of a disabled patch
  livepatch: add /proc/<pid>/patch_state
  livepatch: change to a per-task consistency model
  livepatch: store function sizes
  livepatch: use kstrtobool() in enabled_store()
  livepatch: move patching functions into patch.c
  livepatch: remove unnecessary object loaded check
  livepatch: separate enabled and patched states
  livepatch/s390: add TIF_PATCH_PENDING thread flag
  livepatch/s390: reorganize TIF thread flag bits
  livepatch/powerpc: add TIF_PATCH_PENDING thread flag
  livepatch/x86: add TIF_PATCH_PENDING thread flag
  livepatch: create temporary klp_update_patch_state() stub
  x86/entry: define _TIF_ALLWORK_MASK flags explicitly
  stacktrace/x86: add function for detecting reliable stack traces

6 files changed, 117 insertions, 10 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8d4f87e5bba3..cd18994a9555 100644
--- a/arch/x86/Kconfig
+++ b/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
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 370c42c7f046..cdefcfdd9e63 100644
--- a/arch/x86/entry/common.c
+++ b/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();
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index f765a49103fb..e00e1bd6e7b3 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/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_NOCPUID		15	/* CPUID is not accessible in userland */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
@@ -104,13 +102,14 @@ 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_NOCPUID		(1 << TIF_NOCPUID)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
@@ -135,8 +134,10 @@ 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							\
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index 9b10dcd51716..e6676495b125 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/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
 	bool got_irq;
 	unsigned long *bp, *orig_sp;
@@ -42,6 +43,11 @@ 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
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 8e2b79b88e51..8dabd7bf1673 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/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;
 }
-
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index fec70fe3b1ec..82c6d7f1fd73 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -283,6 +283,8 @@ 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