blacknode
diff --git a/‎Documentation/ABI/testing/sysfs-kernel-livepatch‎
Lines changed: 8 additions & 0 deletions b/‎Documentation/ABI/testing/sysfs-kernel-livepatch‎
Lines changed: 8 additions & 0 deletions
diff --git a/‎Documentation/filesystems/proc.txt‎
Lines changed: 18 additions & 0 deletions b/‎Documentation/filesystems/proc.txt‎
Lines changed: 18 additions & 0 deletions
diff --git a/‎Documentation/livepatch/livepatch.txt‎
Lines changed: 172 additions & 42 deletions b/‎Documentation/livepatch/livepatch.txt‎
Lines changed: 172 additions & 42 deletions
diff --git a/‎arch/Kconfig‎
Lines changed: 6 additions & 0 deletions b/‎arch/Kconfig‎
Lines changed: 6 additions & 0 deletions
diff --git a/‎arch/powerpc/include/asm/thread_info.h‎
Lines changed: 3 additions & 1 deletion b/‎arch/powerpc/include/asm/thread_info.h‎
Lines changed: 3 additions & 1 deletion
diff --git a/‎arch/powerpc/kernel/signal.c‎
Lines changed: 4 additions & 0 deletions b/‎arch/powerpc/kernel/signal.c‎
Lines changed: 4 additions & 0 deletions
@@ -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
 
@@ -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
 
@@ -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.
 
@@ -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
 
@@ -92,6 +92,7 @@ static inline struct thread_info *current_thread_info(void)
 					   TIF_NEED_RESCHED */
 #define TIF_32BIT		4	/* 32 bit binary */
 #define TIF_RESTORE_TM		5	/* need to restore TM FP/VEC/VSX */
+#define TIF_PATCH_PENDING	6	/* pending live patching update */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SINGLESTEP		8	/* singlestepping active */
 #define TIF_NOHZ		9	/* in adaptive nohz mode */
@@ -115,6 +116,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_32BIT		(1<<TIF_32BIT)
 #define _TIF_RESTORE_TM		(1<<TIF_RESTORE_TM)
+#define _TIF_PATCH_PENDING	(1<<TIF_PATCH_PENDING)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SINGLESTEP		(1<<TIF_SINGLESTEP)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
@@ -131,7 +133,7 @@ static inline struct thread_info *current_thread_info(void)
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
-				 _TIF_RESTORE_TM)
+				 _TIF_RESTORE_TM | _TIF_PATCH_PENDING)
 #define _TIF_PERSYSCALL_MASK	(_TIF_RESTOREALL|_TIF_NOERROR)
 
 /* Bits in local_flags */
 
@@ -14,6 +14,7 @@
 #include <linux/uprobes.h>
 #include <linux/key.h>
 #include <linux/context_tracking.h>
+#include <linux/livepatch.h>
 #include <asm/hw_breakpoint.h>
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -162,6 +163,9 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 		tracehook_notify_resume(regs);
 	}
 
+	if (thread_info_flags & _TIF_PATCH_PENDING)
+		klp_update_patch_state(current);
+
 	user_enter();
 }