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

Documentation/livepatch/livepatch.txt

@@ -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 +87,141 @@ 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, ensure that every kthread has a call to
+   klp_update_patch_state() in a safe location.  Kthreads are typically
+   in an infinite loop which does some action repeatedly.  The safe
+   location to switch the kthread's patch state would be at a designated
+   point in the loop where there are no locks taken and all data
+   structures are in a well-defined state.
+
+   The location is clear when using workqueues or the kthread worker
+   API.  These kthreads process independent actions in a generic loop.
+
+   It's much more complicated with kthreads which have a custom loop.
+   There the safe location must be carefully selected on a case-by-case
+   basis.
+
+   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
+   user tasks and waking kthreads 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.  This option
+is perfectly fine for patches which don't change the semantics of the
+patched functions.  In practice, this is usable for ~90% of security
+fixes.  Use of this option also means the patch can't be unloaded after
+it has been disabled.
 
 
 4. Livepatch module
@@ -134,7 +256,7 @@ 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:
@@ -156,6 +278,9 @@ into three levels:
     only for a particular object ( vmlinux or a kernel module ). Note that
     kallsyms allows for searching symbols according to the object name.
 
+    There's also an 'immediate' flag which, when set, patches the
+    function immediately, bypassing the consistency model safety checks.
+
   + struct klp_object defines an array of patched functions (struct
     klp_func) in the same object. Where the object is either vmlinux
     (NULL) or a module name.
@@ -172,10 +297,13 @@ into three levels:
     This structure handles all patched functions consistently and eventually,
     synchronously. The whole patch is applied only when all patched
     symbols are found. The only exception are symbols from objects
-    (kernel modules) that have not been loaded yet. Also if a more complex
-    consistency model is supported then a selected unit (thread,
-    kernel as a whole) will see the new code from the entire patch
-    only when it is in a safe state.
+    (kernel modules) that have not been loaded yet.
+
+    Setting the 'immediate' flag applies the patch to all tasks
+    immediately, bypassing the consistency model safety checks.
+
+    For more details on how the patch is applied on a per-task basis,
+    see the "Consistency model" section.
 
 
 4.3. Livepatch module handling
@@ -188,8 +316,15 @@ 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
 =======================
@@ -239,9 +374,15 @@ 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 +402,12 @@ 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
@@ -329,23 +476,6 @@ 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.

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;
 };
 
 /**
@@ -70,8 +93,8 @@ struct klp_func {
  * @funcs:	function entries for functions to be patched in the object
  * @kobj:	kobject for sysfs resources
  * @mod:	kernel module associated with the patched object
- * 		(NULL for vmlinux)
- * @state:	tracks object-level patch application state
+ *		(NULL for vmlinux)
+ * @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.c

@@ -24,61 +24,31 @@
 #include <linux/kernel.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/ftrace.h>
 #include <linux/list.h>
 #include <linux/kallsyms.h>
 #include <linux/livepatch.h>
 #include <linux/elf.h>
 #include <linux/moduleloader.h>
+#include <linux/completion.h>
 #include <asm/cacheflush.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;
-};
+#include "core.h"
+#include "patch.h"
+#include "transition.h"
 
 /*
- * The klp_mutex protects the global lists and state transitions of any
- * structure reachable from them.  References to any structure must be obtained
- * under mutex protection (except in klp_ftrace_handler(), which uses RCU to
- * ensure it gets consistent data).
+ * klp_mutex is a coarse lock which serializes access to klp data.  All
+ * accesses to klp-related variables and structures must have mutex protection,
+ * except within the following functions which carefully avoid the need for it:
+ *
+ * - klp_ftrace_handler()
+ * - klp_update_patch_state()
  */
-static DEFINE_MUTEX(klp_mutex);
+DEFINE_MUTEX(klp_mutex);
 
 static LIST_HEAD(klp_patches);
-static LIST_HEAD(klp_ops);
 
 static struct kobject *klp_root_kobj;
 
-static 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 bool klp_is_module(struct klp_object *obj)
 {
 	return obj->name;
@@ -117,7 +87,6 @@ static void klp_find_object_module(struct klp_object *obj)
 	mutex_unlock(&module_mutex);
 }
 
-/* klp_mutex must be held by caller */
 static bool klp_is_patch_registered(struct klp_patch *patch)
 {
 	struct klp_patch *mypatch;
@@ -314,191 +283,30 @@ static int klp_write_object_relocations(struct module *pmod,
 	return ret;
 }
 
-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;
-
-	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);
-	if (WARN_ON_ONCE(!func))
-		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_disable_func(struct klp_func *func)
-{
-	struct klp_ops *ops;
-
-	if (WARN_ON(func->state != KLP_ENABLED))
-		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->state = KLP_DISABLED;
-}
-
-static int klp_enable_func(struct klp_func *func)
-{
-	struct klp_ops *ops;
-	int ret;
-
-	if (WARN_ON(!func->old_addr))
-		return -EINVAL;
-
-	if (WARN_ON(func->state != KLP_DISABLED))
-		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->state = KLP_ENABLED;
-
-	return 0;
-
-err:
-	list_del_rcu(&func->stack_node);
-	list_del(&ops->node);
-	kfree(ops);
-	return ret;
-}
-
-static void klp_disable_object(struct klp_object *obj)
-{
-	struct klp_func *func;
-
-	klp_for_each_func(obj, func)
-		if (func->state == KLP_ENABLED)
-			klp_disable_func(func);
-
-	obj->state = KLP_DISABLED;
-}
-
-static int klp_enable_object(struct klp_object *obj)
-{
-	struct klp_func *func;
-	int ret;
-
-	if (WARN_ON(obj->state != KLP_DISABLED))
-		return -EINVAL;
-
-	if (WARN_ON(!klp_is_object_loaded(obj)))
-		return -EINVAL;
-
-	klp_for_each_func(obj, func) {
-		ret = klp_enable_func(func);
-		if (ret) {
-			klp_disable_object(obj);
-			return ret;
-		}
-	}
-	obj->state = KLP_ENABLED;
-
-	return 0;
-}
-
 static int __klp_disable_patch(struct klp_patch *patch)
 {
-	struct klp_object *obj;
+	if (klp_transition_patch)
+		return -EBUSY;
 
 	/* 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_init_transition(patch, KLP_UNPATCHED);
 
-	klp_for_each_object(patch, obj) {
-		if (obj->state == KLP_ENABLED)
-			klp_disable_object(obj);
-	}
+	/*
+	 * Enforce the order of the func->transition writes in
+	 * klp_init_transition() and the TIF_PATCH_PENDING writes in
+	 * klp_start_transition().  In the rare case where klp_ftrace_handler()
+	 * is called shortly after klp_update_patch_state() switches the task,
+	 * this ensures the handler sees that func->transition is set.
+	 */
+	smp_wmb();
 
-	patch->state = KLP_DISABLED;
+	klp_start_transition();
+	klp_try_complete_transition();
+	patch->enabled = false;
 
 	return 0;
 }
@@ -522,7 +330,7 @@ int klp_disable_patch(struct klp_patch *patch)
 		goto err;
 	}
 
-	if (patch->state == KLP_DISABLED) {
+	if (!patch->enabled) {
 		ret = -EINVAL;
 		goto err;
 	}
@@ -540,32 +348,61 @@ static int __klp_enable_patch(struct klp_patch *patch)
 	struct klp_object *obj;
 	int ret;
 
-	if (WARN_ON(patch->state != KLP_DISABLED))
+	if (klp_transition_patch)
+		return -EBUSY;
+
+	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;
 
+	/*
+	 * 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);
+
+	/*
+	 * Enforce the order of the func->transition writes in
+	 * klp_init_transition() and the ops->func_stack writes in
+	 * klp_patch_object(), so that klp_ftrace_handler() will see the
+	 * func->transition updates before the handler is registered and the
+	 * new funcs become visible to the handler.
+	 */
+	smp_wmb();
+
 	klp_for_each_object(patch, obj) {
 		if (!klp_is_object_loaded(obj))
 			continue;
 
-		ret = klp_enable_object(obj);
-		if (ret)
-			goto unregister;
+		ret = klp_patch_object(obj);
+		if (ret) {
+			pr_warn("failed to enable patch '%s'\n",
+				patch->mod->name);
+
+			klp_cancel_transition();
+			return ret;
+		}
 	}
 
-	patch->state = KLP_ENABLED;
+	klp_start_transition();
+	klp_try_complete_transition();
+	patch->enabled = true;
 
 	return 0;
-
-unregister:
-	WARN_ON(__klp_disable_patch(patch));
-	return ret;
 }
 
 /**
@@ -602,6 +439,7 @@ EXPORT_SYMBOL_GPL(klp_enable_patch);
  * /sys/kernel/livepatch
  * /sys/kernel/livepatch/<patch>
  * /sys/kernel/livepatch/<patch>/enabled
+ * /sys/kernel/livepatch/<patch>/transition
  * /sys/kernel/livepatch/<patch>/<object>
  * /sys/kernel/livepatch/<patch>/<object>/<function,sympos>
  */
@@ -611,26 +449,34 @@ 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 != KLP_DISABLED && val != KLP_ENABLED)
-		return -EINVAL;
+		return ret;
 
 	patch = container_of(kobj, struct klp_patch, kobj);
 
 	mutex_lock(&klp_mutex);
 
-	if (val == patch->state) {
+	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;
 		goto err;
 	}
 
-	if (val == KLP_ENABLED) {
+	if (patch == klp_transition_patch) {
+		klp_reverse_transition();
+	} else if (enabled) {
 		ret = __klp_enable_patch(patch);
 		if (ret)
 			goto err;
@@ -655,21 +501,33 @@ 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 ssize_t transition_show(struct kobject *kobj,
+			       struct kobj_attribute *attr, char *buf)
+{
+	struct klp_patch *patch;
+
+	patch = container_of(kobj, struct klp_patch, kobj);
+	return snprintf(buf, PAGE_SIZE-1, "%d\n",
+			patch == klp_transition_patch);
 }
 
 static struct kobj_attribute enabled_kobj_attr = __ATTR_RW(enabled);
+static struct kobj_attribute transition_kobj_attr = __ATTR_RO(transition);
 static struct attribute *klp_patch_attrs[] = {
 	&enabled_kobj_attr.attr,
+	&transition_kobj_attr.attr,
 	NULL
 };
 
 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 = {
@@ -740,7 +598,6 @@ 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)
@@ -749,7 +606,8 @@ 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;
+	func->transition = false;
 
 	/* The format for the sysfs directory is <function,sympos> where sympos
 	 * is the nth occurrence of this symbol in kallsyms for the patched
@@ -790,6 +648,22 @@ static int klp_init_object_loaded(struct klp_patch *patch,
 					     &func->old_addr);
 		if (ret)
 			return ret;
+
+		ret = kallsyms_lookup_size_offset(func->old_addr,
+						  &func->old_size, NULL);
+		if (!ret) {
+			pr_err("kallsyms size lookup failed for '%s'\n",
+			       func->old_name);
+			return -ENOENT;
+		}
+
+		ret = kallsyms_lookup_size_offset((unsigned long)func->new_func,
+						  &func->new_size, NULL);
+		if (!ret) {
+			pr_err("kallsyms size lookup failed for '%s' replacement\n",
+			       func->old_name);
+			return -ENOENT;
+		}
 	}
 
 	return 0;
@@ -804,7 +678,7 @@ 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);
@@ -845,12 +719,15 @@ static int klp_init_patch(struct klp_patch *patch)
 
 	mutex_lock(&klp_mutex);
 
-	patch->state = KLP_DISABLED;
+	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);
@@ -866,9 +743,12 @@ 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;
 }
 
@@ -882,23 +762,29 @@ 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->state == KLP_ENABLED) {
+	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;
 }
@@ -911,12 +797,13 @@ 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;
 
@@ -930,20 +817,16 @@ int klp_register_patch(struct klp_patch *patch)
 		return -ENODEV;
 
 	/*
-	 * 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.
+	 * Architectures without reliable stack traces have to set
+	 * patch->immediate because there's currently no way to patch kthreads
+	 * with the consistency model.
 	 */
-	if (!try_module_get(patch->mod))
-		return -ENODEV;
-
-	ret = klp_init_patch(patch);
-	if (ret)
-		module_put(patch->mod);
+	if (!klp_have_reliable_stack() && !patch->immediate) {
+		pr_err("This architecture doesn't have support for the livepatch consistency model.\n");
+		return -ENOSYS;
+	}
 
-	return ret;
+	return klp_init_patch(patch);
 }
 EXPORT_SYMBOL_GPL(klp_register_patch);
 
@@ -978,13 +861,17 @@ int klp_module_coming(struct module *mod)
 				goto err;
 			}
 
-			if (patch->state == KLP_DISABLED)
+			/*
+			 * Only patch the module if the patch is enabled or is
+			 * in transition.
+			 */
+			if (!patch->enabled && patch != klp_transition_patch)
 				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 +922,14 @@ void klp_module_going(struct module *mod)
 			if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
 				continue;
 
-			if (patch->state != KLP_DISABLED) {
+			/*
+			 * Only unpatch the module if the patch is enabled or
+			 * is in transition.
+			 */
+			if (patch->enabled || patch == klp_transition_patch) {
 				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);

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.c

+/*
+ * transition.c - Kernel Live Patching transition functions
+ *
+ * Copyright (C) 2015-2016 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/cpu.h>
+#include <linux/stacktrace.h>
+#include "core.h"
+#include "patch.h"
+#include "transition.h"
+#include "../sched/sched.h"
+
+#define MAX_STACK_ENTRIES  100
+#define STACK_ERR_BUF_SIZE 128
+
+struct klp_patch *klp_transition_patch;
+
+static int klp_target_state = KLP_UNDEFINED;
+
+/*
+ * This work can be performed periodically to finish patching or unpatching any
+ * "straggler" tasks which failed to transition in the first attempt.
+ */
+static void klp_transition_work_fn(struct work_struct *work)
+{
+	mutex_lock(&klp_mutex);
+
+	if (klp_transition_patch)
+		klp_try_complete_transition();
+
+	mutex_unlock(&klp_mutex);
+}
+static DECLARE_DELAYED_WORK(klp_transition_work, klp_transition_work_fn);
+
+/*
+ * The transition to the target patch state is complete.  Clean up the data
+ * structures.
+ */
+static void klp_complete_transition(void)
+{
+	struct klp_object *obj;
+	struct klp_func *func;
+	struct task_struct *g, *task;
+	unsigned int cpu;
+	bool immediate_func = false;
+
+	if (klp_target_state == KLP_UNPATCHED) {
+		/*
+		 * All tasks have transitioned to KLP_UNPATCHED so we can now
+		 * remove the new functions from the func_stack.
+		 */
+		klp_unpatch_objects(klp_transition_patch);
+
+		/*
+		 * Make sure klp_ftrace_handler() can no longer see functions
+		 * from this patch on the ops->func_stack.  Otherwise, after
+		 * func->transition gets cleared, the handler may choose a
+		 * removed function.
+		 */
+		synchronize_rcu();
+	}
+
+	if (klp_transition_patch->immediate)
+		goto done;
+
+	klp_for_each_object(klp_transition_patch, obj) {
+		klp_for_each_func(obj, func) {
+			func->transition = false;
+			if (func->immediate)
+				immediate_func = true;
+		}
+	}
+
+	if (klp_target_state == KLP_UNPATCHED && !immediate_func)
+		module_put(klp_transition_patch->mod);
+
+	/* Prevent klp_ftrace_handler() from seeing KLP_UNDEFINED state */
+	if (klp_target_state == KLP_PATCHED)
+		synchronize_rcu();
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, task) {
+		WARN_ON_ONCE(test_tsk_thread_flag(task, TIF_PATCH_PENDING));
+		task->patch_state = KLP_UNDEFINED;
+	}
+	read_unlock(&tasklist_lock);
+
+	for_each_possible_cpu(cpu) {
+		task = idle_task(cpu);
+		WARN_ON_ONCE(test_tsk_thread_flag(task, TIF_PATCH_PENDING));
+		task->patch_state = KLP_UNDEFINED;
+	}
+
+done:
+	klp_target_state = KLP_UNDEFINED;
+	klp_transition_patch = NULL;
+}
+
+/*
+ * This is called in the error path, to cancel a transition before it has
+ * started, i.e. klp_init_transition() has been called but
+ * klp_start_transition() hasn't.  If the transition *has* been started,
+ * klp_reverse_transition() should be used instead.
+ */
+void klp_cancel_transition(void)
+{
+	if (WARN_ON_ONCE(klp_target_state != KLP_PATCHED))
+		return;
+
+	klp_target_state = KLP_UNPATCHED;
+	klp_complete_transition();
+}
+
+/*
+ * Switch the patched state of the task to the set of functions in the target
+ * patch state.
+ *
+ * NOTE: If task is not 'current', the caller must ensure the task is inactive.
+ * Otherwise klp_ftrace_handler() might read the wrong 'patch_state' value.
+ */
+void klp_update_patch_state(struct task_struct *task)
+{
+	rcu_read_lock();
+
+	/*
+	 * This test_and_clear_tsk_thread_flag() call also serves as a read
+	 * barrier (smp_rmb) for two cases:
+	 *
+	 * 1) Enforce the order of the TIF_PATCH_PENDING read and the
+	 *    klp_target_state read.  The corresponding write barrier is in
+	 *    klp_init_transition().
+	 *
+	 * 2) Enforce the order of the TIF_PATCH_PENDING read and a future read
+	 *    of func->transition, if klp_ftrace_handler() is called later on
+	 *    the same CPU.  See __klp_disable_patch().
+	 */
+	if (test_and_clear_tsk_thread_flag(task, TIF_PATCH_PENDING))
+		task->patch_state = READ_ONCE(klp_target_state);
+
+	rcu_read_unlock();
+}
+
+/*
+ * Determine whether the given stack trace includes any references to a
+ * to-be-patched or to-be-unpatched function.
+ */
+static int klp_check_stack_func(struct klp_func *func,
+				struct stack_trace *trace)
+{
+	unsigned long func_addr, func_size, address;
+	struct klp_ops *ops;
+	int i;
+
+	if (func->immediate)
+		return 0;
+
+	for (i = 0; i < trace->nr_entries; i++) {
+		address = trace->entries[i];
+
+		if (klp_target_state == KLP_UNPATCHED) {
+			 /*
+			  * Check for the to-be-unpatched function
+			  * (the func itself).
+			  */
+			func_addr = (unsigned long)func->new_func;
+			func_size = func->new_size;
+		} else {
+			/*
+			 * Check for the to-be-patched function
+			 * (the previous func).
+			 */
+			ops = klp_find_ops(func->old_addr);
+
+			if (list_is_singular(&ops->func_stack)) {
+				/* original function */
+				func_addr = func->old_addr;
+				func_size = func->old_size;
+			} else {
+				/* previously patched function */
+				struct klp_func *prev;
+
+				prev = list_next_entry(func, stack_node);
+				func_addr = (unsigned long)prev->new_func;
+				func_size = prev->new_size;
+			}
+		}
+
+		if (address >= func_addr && address < func_addr + func_size)
+			return -EAGAIN;
+	}
+
+	return 0;
+}
+
+/*
+ * Determine whether it's safe to transition the task to the target patch state
+ * by looking for any to-be-patched or to-be-unpatched functions on its stack.
+ */
+static int klp_check_stack(struct task_struct *task, char *err_buf)
+{
+	static unsigned long entries[MAX_STACK_ENTRIES];
+	struct stack_trace trace;
+	struct klp_object *obj;
+	struct klp_func *func;
+	int ret;
+
+	trace.skip = 0;
+	trace.nr_entries = 0;
+	trace.max_entries = MAX_STACK_ENTRIES;
+	trace.entries = entries;
+	ret = save_stack_trace_tsk_reliable(task, &trace);
+	WARN_ON_ONCE(ret == -ENOSYS);
+	if (ret) {
+		snprintf(err_buf, STACK_ERR_BUF_SIZE,
+			 "%s: %s:%d has an unreliable stack\n",
+			 __func__, task->comm, task->pid);
+		return ret;
+	}
+
+	klp_for_each_object(klp_transition_patch, obj) {
+		if (!obj->patched)
+			continue;
+		klp_for_each_func(obj, func) {
+			ret = klp_check_stack_func(func, &trace);
+			if (ret) {
+				snprintf(err_buf, STACK_ERR_BUF_SIZE,
+					 "%s: %s:%d is sleeping on function %s\n",
+					 __func__, task->comm, task->pid,
+					 func->old_name);
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Try to safely switch a task to the target patch state.  If it's currently
+ * running, or it's sleeping on a to-be-patched or to-be-unpatched function, or
+ * if the stack is unreliable, return false.
+ */
+static bool klp_try_switch_task(struct task_struct *task)
+{
+	struct rq *rq;
+	struct rq_flags flags;
+	int ret;
+	bool success = false;
+	char err_buf[STACK_ERR_BUF_SIZE];
+
+	err_buf[0] = '\0';
+
+	/* check if this task has already switched over */
+	if (task->patch_state == klp_target_state)
+		return true;
+
+	/*
+	 * For arches which don't have reliable stack traces, we have to rely
+	 * on other methods (e.g., switching tasks at kernel exit).
+	 */
+	if (!klp_have_reliable_stack())
+		return false;
+
+	/*
+	 * Now try to check the stack for any to-be-patched or to-be-unpatched
+	 * functions.  If all goes well, switch the task to the target patch
+	 * state.
+	 */
+	rq = task_rq_lock(task, &flags);
+
+	if (task_running(rq, task) && task != current) {
+		snprintf(err_buf, STACK_ERR_BUF_SIZE,
+			 "%s: %s:%d is running\n", __func__, task->comm,
+			 task->pid);
+		goto done;
+	}
+
+	ret = klp_check_stack(task, err_buf);
+	if (ret)
+		goto done;
+
+	success = true;
+
+	clear_tsk_thread_flag(task, TIF_PATCH_PENDING);
+	task->patch_state = klp_target_state;
+
+done:
+	task_rq_unlock(rq, task, &flags);
+
+	/*
+	 * Due to console deadlock issues, pr_debug() can't be used while
+	 * holding the task rq lock.  Instead we have to use a temporary buffer
+	 * and print the debug message after releasing the lock.
+	 */
+	if (err_buf[0] != '\0')
+		pr_debug("%s", err_buf);
+
+	return success;
+
+}
+
+/*
+ * Try to switch all remaining tasks to the target patch state by walking the
+ * stacks of sleeping tasks and looking for any to-be-patched or
+ * to-be-unpatched functions.  If such functions are found, the task can't be
+ * switched yet.
+ *
+ * If any tasks are still stuck in the initial patch state, schedule a retry.
+ */
+void klp_try_complete_transition(void)
+{
+	unsigned int cpu;
+	struct task_struct *g, *task;
+	bool complete = true;
+
+	WARN_ON_ONCE(klp_target_state == KLP_UNDEFINED);
+
+	/*
+	 * If the patch can be applied or reverted immediately, skip the
+	 * per-task transitions.
+	 */
+	if (klp_transition_patch->immediate)
+		goto success;
+
+	/*
+	 * Try to switch the tasks to the target patch state by walking their
+	 * stacks and looking for any to-be-patched or to-be-unpatched
+	 * functions.  If such functions are found on a stack, or if the stack
+	 * is deemed unreliable, the task can't be switched yet.
+	 *
+	 * Usually this will transition most (or all) of the tasks on a system
+	 * unless the patch includes changes to a very common function.
+	 */
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, task)
+		if (!klp_try_switch_task(task))
+			complete = false;
+	read_unlock(&tasklist_lock);
+
+	/*
+	 * Ditto for the idle "swapper" tasks.
+	 */
+	get_online_cpus();
+	for_each_possible_cpu(cpu) {
+		task = idle_task(cpu);
+		if (cpu_online(cpu)) {
+			if (!klp_try_switch_task(task))
+				complete = false;
+		} else if (task->patch_state != klp_target_state) {
+			/* offline idle tasks can be switched immediately */
+			clear_tsk_thread_flag(task, TIF_PATCH_PENDING);
+			task->patch_state = klp_target_state;
+		}
+	}
+	put_online_cpus();
+
+	if (!complete) {
+		/*
+		 * Some tasks weren't able to be switched over.  Try again
+		 * later and/or wait for other methods like kernel exit
+		 * switching.
+		 */
+		schedule_delayed_work(&klp_transition_work,
+				      round_jiffies_relative(HZ));
+		return;
+	}
+
+success:
+	pr_notice("'%s': %s complete\n", klp_transition_patch->mod->name,
+		  klp_target_state == KLP_PATCHED ? "patching" : "unpatching");
+
+	/* we're done, now cleanup the data structures */
+	klp_complete_transition();
+}
+
+/*
+ * Start the transition to the specified target patch state so tasks can begin
+ * switching to it.
+ */
+void klp_start_transition(void)
+{
+	struct task_struct *g, *task;
+	unsigned int cpu;
+
+	WARN_ON_ONCE(klp_target_state == KLP_UNDEFINED);
+
+	pr_notice("'%s': %s...\n", klp_transition_patch->mod->name,
+		  klp_target_state == KLP_PATCHED ? "patching" : "unpatching");
+
+	/*
+	 * If the patch can be applied or reverted immediately, skip the
+	 * per-task transitions.
+	 */
+	if (klp_transition_patch->immediate)
+		return;
+
+	/*
+	 * Mark all normal tasks as needing a patch state update.  They'll
+	 * switch either in klp_try_complete_transition() or as they exit the
+	 * kernel.
+	 */
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, task)
+		if (task->patch_state != klp_target_state)
+			set_tsk_thread_flag(task, TIF_PATCH_PENDING);
+	read_unlock(&tasklist_lock);
+
+	/*
+	 * Mark all idle tasks as needing a patch state update.  They'll switch
+	 * either in klp_try_complete_transition() or at the idle loop switch
+	 * point.
+	 */
+	for_each_possible_cpu(cpu) {
+		task = idle_task(cpu);
+		if (task->patch_state != klp_target_state)
+			set_tsk_thread_flag(task, TIF_PATCH_PENDING);
+	}
+}
+
+/*
+ * Initialize the global target patch state and all tasks to the initial patch
+ * state, and initialize all function transition states to true in preparation
+ * for patching or unpatching.
+ */
+void klp_init_transition(struct klp_patch *patch, int state)
+{
+	struct task_struct *g, *task;
+	unsigned int cpu;
+	struct klp_object *obj;
+	struct klp_func *func;
+	int initial_state = !state;
+
+	WARN_ON_ONCE(klp_target_state != KLP_UNDEFINED);
+
+	klp_transition_patch = patch;
+
+	/*
+	 * Set the global target patch state which tasks will switch to.  This
+	 * has no effect until the TIF_PATCH_PENDING flags get set later.
+	 */
+	klp_target_state = state;
+
+	/*
+	 * If the patch can be applied or reverted immediately, skip the
+	 * per-task transitions.
+	 */
+	if (patch->immediate)
+		return;
+
+	/*
+	 * Initialize all tasks to the initial patch state to prepare them for
+	 * switching to the target state.
+	 */
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, task) {
+		WARN_ON_ONCE(task->patch_state != KLP_UNDEFINED);
+		task->patch_state = initial_state;
+	}
+	read_unlock(&tasklist_lock);
+
+	/*
+	 * Ditto for the idle "swapper" tasks.
+	 */
+	for_each_possible_cpu(cpu) {
+		task = idle_task(cpu);
+		WARN_ON_ONCE(task->patch_state != KLP_UNDEFINED);
+		task->patch_state = initial_state;
+	}
+
+	/*
+	 * Enforce the order of the task->patch_state initializations and the
+	 * func->transition updates to ensure that klp_ftrace_handler() doesn't
+	 * see a func in transition with a task->patch_state of KLP_UNDEFINED.
+	 *
+	 * Also enforce the order of the klp_target_state write and future
+	 * TIF_PATCH_PENDING writes to ensure klp_update_patch_state() doesn't
+	 * set a task->patch_state to KLP_UNDEFINED.
+	 */
+	smp_wmb();
+
+	/*
+	 * Set the func transition states so klp_ftrace_handler() will know to
+	 * switch to the transition logic.
+	 *
+	 * When patching, the funcs aren't yet in the func_stack and will be
+	 * made visible to the ftrace handler shortly by the calls to
+	 * klp_patch_object().
+	 *
+	 * When unpatching, the funcs are already in the func_stack and so are
+	 * already visible to the ftrace handler.
+	 */
+	klp_for_each_object(patch, obj)
+		klp_for_each_func(obj, func)
+			func->transition = true;
+}
+
+/*
+ * This function can be called in the middle of an existing transition to
+ * reverse the direction of the target patch state.  This can be done to
+ * effectively cancel an existing enable or disable operation if there are any
+ * tasks which are stuck in the initial patch state.
+ */
+void klp_reverse_transition(void)
+{
+	unsigned int cpu;
+	struct task_struct *g, *task;
+
+	klp_transition_patch->enabled = !klp_transition_patch->enabled;
+
+	klp_target_state = !klp_target_state;
+
+	/*
+	 * Clear all TIF_PATCH_PENDING flags to prevent races caused by
+	 * klp_update_patch_state() running in parallel with
+	 * klp_start_transition().
+	 */
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, task)
+		clear_tsk_thread_flag(task, TIF_PATCH_PENDING);
+	read_unlock(&tasklist_lock);
+
+	for_each_possible_cpu(cpu)
+		clear_tsk_thread_flag(idle_task(cpu), TIF_PATCH_PENDING);
+
+	/* Let any remaining calls to klp_update_patch_state() complete */
+	synchronize_rcu();
+
+	klp_start_transition();
+}
+
+/* Called from copy_process() during fork */
+void klp_copy_process(struct task_struct *child)
+{
+	child->patch_state = current->patch_state;
+
+	/* TIF_PATCH_PENDING gets copied in setup_thread_stack() */
+}

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));
 }