Initial commit: Linux kernel 4.19 for Unplugged OS

kernel/livepatch/Kconfig

@@ -0,0 +1,19 @@
+config HAVE_LIVEPATCH
+	bool
+	help
+	  Arch supports kernel live patching
+
+config LIVEPATCH
+	bool "Kernel Live Patching"
+	depends on DYNAMIC_FTRACE_WITH_REGS
+	depends on MODULES
+	depends on SYSFS
+	depends on KALLSYMS_ALL
+	depends on HAVE_LIVEPATCH
+	depends on !TRIM_UNUSED_KSYMS
+	help
+	  Say Y here if you want to support kernel live patching.
+	  This option has no runtime impact until a kernel "patch"
+	  module uses the interface provided by this option to register
+	  a patch, causing calls to patched functions to be redirected
+	  to new function code contained in the patch module.

kernel/livepatch/Makefile

@@ -0,0 +1,3 @@
+obj-$(CONFIG_LIVEPATCH) += livepatch.o
+
+livepatch-objs := core.o patch.o shadow.o transition.o

kernel/livepatch/core.h

@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LIVEPATCH_CORE_H
+#define _LIVEPATCH_CORE_H
+
+#include <linux/livepatch.h>
+
+extern struct mutex klp_mutex;
+
+static inline bool klp_is_object_loaded(struct klp_object *obj)
+{
+	return !obj->name || obj->mod;
+}
+
+static inline int klp_pre_patch_callback(struct klp_object *obj)
+{
+	int ret = 0;
+
+	if (obj->callbacks.pre_patch)
+		ret = (*obj->callbacks.pre_patch)(obj);
+
+	obj->callbacks.post_unpatch_enabled = !ret;
+
+	return ret;
+}
+
+static inline void klp_post_patch_callback(struct klp_object *obj)
+{
+	if (obj->callbacks.post_patch)
+		(*obj->callbacks.post_patch)(obj);
+}
+
+static inline void klp_pre_unpatch_callback(struct klp_object *obj)
+{
+	if (obj->callbacks.pre_unpatch)
+		(*obj->callbacks.pre_unpatch)(obj);
+}
+
+static inline void klp_post_unpatch_callback(struct klp_object *obj)
+{
+	if (obj->callbacks.post_unpatch_enabled &&
+	    obj->callbacks.post_unpatch)
+		(*obj->callbacks.post_unpatch)(obj);
+
+	obj->callbacks.post_unpatch_enabled = false;
+}
+
+#endif /* _LIVEPATCH_CORE_H */

kernel/livepatch/patch.c

@@ -0,0 +1,277 @@
+/*
+ * 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 "core.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);
+
+	/*
+	 * A variant of synchronize_sched() is used to allow patching functions
+	 * where RCU is not watching, see klp_synchronize_transition().
+	 */
+	preempt_disable_notrace();
+
+	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:
+	preempt_enable_notrace();
+}
+
+/*
+ * 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

@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#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/shadow.c

@@ -0,0 +1,311 @@
+/*
+ * shadow.c - Shadow Variables
+ *
+ * Copyright (C) 2014 Josh Poimboeuf <jpoimboe@redhat.com>
+ * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com>
+ * Copyright (C) 2017 Joe Lawrence <joe.lawrence@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/>.
+ */
+
+/**
+ * DOC: Shadow variable API concurrency notes:
+ *
+ * The shadow variable API provides a simple relationship between an
+ * <obj, id> pair and a pointer value.  It is the responsibility of the
+ * caller to provide any mutual exclusion required of the shadow data.
+ *
+ * Once a shadow variable is attached to its parent object via the
+ * klp_shadow_*alloc() API calls, it is considered live: any subsequent
+ * call to klp_shadow_get() may then return the shadow variable's data
+ * pointer.  Callers of klp_shadow_*alloc() should prepare shadow data
+ * accordingly.
+ *
+ * The klp_shadow_*alloc() API calls may allocate memory for new shadow
+ * variable structures.  Their implementation does not call kmalloc
+ * inside any spinlocks, but API callers should pass GFP flags according
+ * to their specific needs.
+ *
+ * The klp_shadow_hash is an RCU-enabled hashtable and is safe against
+ * concurrent klp_shadow_free() and klp_shadow_get() operations.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/hashtable.h>
+#include <linux/slab.h>
+#include <linux/livepatch.h>
+
+static DEFINE_HASHTABLE(klp_shadow_hash, 12);
+
+/*
+ * klp_shadow_lock provides exclusive access to the klp_shadow_hash and
+ * the shadow variables it references.
+ */
+static DEFINE_SPINLOCK(klp_shadow_lock);
+
+/**
+ * struct klp_shadow - shadow variable structure
+ * @node:	klp_shadow_hash hash table node
+ * @rcu_head:	RCU is used to safely free this structure
+ * @obj:	pointer to parent object
+ * @id:		data identifier
+ * @data:	data area
+ */
+struct klp_shadow {
+	struct hlist_node node;
+	struct rcu_head rcu_head;
+	void *obj;
+	unsigned long id;
+	char data[];
+};
+
+/**
+ * klp_shadow_match() - verify a shadow variable matches given <obj, id>
+ * @shadow:	shadow variable to match
+ * @obj:	pointer to parent object
+ * @id:		data identifier
+ *
+ * Return: true if the shadow variable matches.
+ */
+static inline bool klp_shadow_match(struct klp_shadow *shadow, void *obj,
+				unsigned long id)
+{
+	return shadow->obj == obj && shadow->id == id;
+}
+
+/**
+ * klp_shadow_get() - retrieve a shadow variable data pointer
+ * @obj:	pointer to parent object
+ * @id:		data identifier
+ *
+ * Return: the shadow variable data element, NULL on failure.
+ */
+void *klp_shadow_get(void *obj, unsigned long id)
+{
+	struct klp_shadow *shadow;
+
+	rcu_read_lock();
+
+	hash_for_each_possible_rcu(klp_shadow_hash, shadow, node,
+				   (unsigned long)obj) {
+
+		if (klp_shadow_match(shadow, obj, id)) {
+			rcu_read_unlock();
+			return shadow->data;
+		}
+	}
+
+	rcu_read_unlock();
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(klp_shadow_get);
+
+static void *__klp_shadow_get_or_alloc(void *obj, unsigned long id,
+				       size_t size, gfp_t gfp_flags,
+				       klp_shadow_ctor_t ctor, void *ctor_data,
+				       bool warn_on_exist)
+{
+	struct klp_shadow *new_shadow;
+	void *shadow_data;
+	unsigned long flags;
+
+	/* Check if the shadow variable already exists */
+	shadow_data = klp_shadow_get(obj, id);
+	if (shadow_data)
+		goto exists;
+
+	/*
+	 * Allocate a new shadow variable.  Fill it with zeroes by default.
+	 * More complex setting can be done by @ctor function.  But it is
+	 * called only when the buffer is really used (under klp_shadow_lock).
+	 */
+	new_shadow = kzalloc(size + sizeof(*new_shadow), gfp_flags);
+	if (!new_shadow)
+		return NULL;
+
+	/* Look for <obj, id> again under the lock */
+	spin_lock_irqsave(&klp_shadow_lock, flags);
+	shadow_data = klp_shadow_get(obj, id);
+	if (unlikely(shadow_data)) {
+		/*
+		 * Shadow variable was found, throw away speculative
+		 * allocation.
+		 */
+		spin_unlock_irqrestore(&klp_shadow_lock, flags);
+		kfree(new_shadow);
+		goto exists;
+	}
+
+	new_shadow->obj = obj;
+	new_shadow->id = id;
+
+	if (ctor) {
+		int err;
+
+		err = ctor(obj, new_shadow->data, ctor_data);
+		if (err) {
+			spin_unlock_irqrestore(&klp_shadow_lock, flags);
+			kfree(new_shadow);
+			pr_err("Failed to construct shadow variable <%p, %lx> (%d)\n",
+			       obj, id, err);
+			return NULL;
+		}
+	}
+
+	/* No <obj, id> found, so attach the newly allocated one */
+	hash_add_rcu(klp_shadow_hash, &new_shadow->node,
+		     (unsigned long)new_shadow->obj);
+	spin_unlock_irqrestore(&klp_shadow_lock, flags);
+
+	return new_shadow->data;
+
+exists:
+	if (warn_on_exist) {
+		WARN(1, "Duplicate shadow variable <%p, %lx>\n", obj, id);
+		return NULL;
+	}
+
+	return shadow_data;
+}
+
+/**
+ * klp_shadow_alloc() - allocate and add a new shadow variable
+ * @obj:	pointer to parent object
+ * @id:		data identifier
+ * @size:	size of attached data
+ * @gfp_flags:	GFP mask for allocation
+ * @ctor:	custom constructor to initialize the shadow data (optional)
+ * @ctor_data:	pointer to any data needed by @ctor (optional)
+ *
+ * Allocates @size bytes for new shadow variable data using @gfp_flags.
+ * The data are zeroed by default.  They are further initialized by @ctor
+ * function if it is not NULL.  The new shadow variable is then added
+ * to the global hashtable.
+ *
+ * If an existing <obj, id> shadow variable can be found, this routine will
+ * issue a WARN, exit early and return NULL.
+ *
+ * This function guarantees that the constructor function is called only when
+ * the variable did not exist before.  The cost is that @ctor is called
+ * in atomic context under a spin lock.
+ *
+ * Return: the shadow variable data element, NULL on duplicate or
+ * failure.
+ */
+void *klp_shadow_alloc(void *obj, unsigned long id,
+		       size_t size, gfp_t gfp_flags,
+		       klp_shadow_ctor_t ctor, void *ctor_data)
+{
+	return __klp_shadow_get_or_alloc(obj, id, size, gfp_flags,
+					 ctor, ctor_data, true);
+}
+EXPORT_SYMBOL_GPL(klp_shadow_alloc);
+
+/**
+ * klp_shadow_get_or_alloc() - get existing or allocate a new shadow variable
+ * @obj:	pointer to parent object
+ * @id:		data identifier
+ * @size:	size of attached data
+ * @gfp_flags:	GFP mask for allocation
+ * @ctor:	custom constructor to initialize the shadow data (optional)
+ * @ctor_data:	pointer to any data needed by @ctor (optional)
+ *
+ * Returns a pointer to existing shadow data if an <obj, id> shadow
+ * variable is already present.  Otherwise, it creates a new shadow
+ * variable like klp_shadow_alloc().
+ *
+ * This function guarantees that only one shadow variable exists with the given
+ * @id for the given @obj.  It also guarantees that the constructor function
+ * will be called only when the variable did not exist before.  The cost is
+ * that @ctor is called in atomic context under a spin lock.
+ *
+ * Return: the shadow variable data element, NULL on failure.
+ */
+void *klp_shadow_get_or_alloc(void *obj, unsigned long id,
+			      size_t size, gfp_t gfp_flags,
+			      klp_shadow_ctor_t ctor, void *ctor_data)
+{
+	return __klp_shadow_get_or_alloc(obj, id, size, gfp_flags,
+					 ctor, ctor_data, false);
+}
+EXPORT_SYMBOL_GPL(klp_shadow_get_or_alloc);
+
+static void klp_shadow_free_struct(struct klp_shadow *shadow,
+				   klp_shadow_dtor_t dtor)
+{
+	hash_del_rcu(&shadow->node);
+	if (dtor)
+		dtor(shadow->obj, shadow->data);
+	kfree_rcu(shadow, rcu_head);
+}
+
+/**
+ * klp_shadow_free() - detach and free a <obj, id> shadow variable
+ * @obj:	pointer to parent object
+ * @id:		data identifier
+ * @dtor:	custom callback that can be used to unregister the variable
+ *		and/or free data that the shadow variable points to (optional)
+ *
+ * This function releases the memory for this <obj, id> shadow variable
+ * instance, callers should stop referencing it accordingly.
+ */
+void klp_shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor)
+{
+	struct klp_shadow *shadow;
+	unsigned long flags;
+
+	spin_lock_irqsave(&klp_shadow_lock, flags);
+
+	/* Delete <obj, id> from hash */
+	hash_for_each_possible(klp_shadow_hash, shadow, node,
+			       (unsigned long)obj) {
+
+		if (klp_shadow_match(shadow, obj, id)) {
+			klp_shadow_free_struct(shadow, dtor);
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&klp_shadow_lock, flags);
+}
+EXPORT_SYMBOL_GPL(klp_shadow_free);
+
+/**
+ * klp_shadow_free_all() - detach and free all <*, id> shadow variables
+ * @id:		data identifier
+ * @dtor:	custom callback that can be used to unregister the variable
+ *		and/or free data that the shadow variable points to (optional)
+ *
+ * This function releases the memory for all <*, id> shadow variable
+ * instances, callers should stop referencing them accordingly.
+ */
+void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor)
+{
+	struct klp_shadow *shadow;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&klp_shadow_lock, flags);
+
+	/* Delete all <*, id> from hash */
+	hash_for_each(klp_shadow_hash, i, shadow, node) {
+		if (klp_shadow_match(shadow, shadow->obj, id))
+			klp_shadow_free_struct(shadow, dtor);
+	}
+
+	spin_unlock_irqrestore(&klp_shadow_lock, flags);
+}
+EXPORT_SYMBOL_GPL(klp_shadow_free_all);

kernel/livepatch/transition.c

@@ -0,0 +1,637 @@
+/*
+ * 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;
+
+static bool klp_forced = false;
+
+/*
+ * 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);
+
+/*
+ * This function is just a stub to implement a hard force
+ * of synchronize_sched(). This requires synchronizing
+ * tasks even in userspace and idle.
+ */
+static void klp_sync(struct work_struct *work)
+{
+}
+
+/*
+ * We allow to patch also functions where RCU is not watching,
+ * e.g. before user_exit(). We can not rely on the RCU infrastructure
+ * to do the synchronization. Instead hard force the sched synchronization.
+ *
+ * This approach allows to use RCU functions for manipulating func_stack
+ * safely.
+ */
+static void klp_synchronize_transition(void)
+{
+	schedule_on_each_cpu(klp_sync);
+}
+
+/*
+ * 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;
+
+	pr_debug("'%s': completing %s transition\n",
+		 klp_transition_patch->mod->name,
+		 klp_target_state == KLP_PATCHED ? "patching" : "unpatching");
+
+	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.
+		 */
+		klp_synchronize_transition();
+	}
+
+	klp_for_each_object(klp_transition_patch, obj)
+		klp_for_each_func(obj, func)
+			func->transition = false;
+
+	/* Prevent klp_ftrace_handler() from seeing KLP_UNDEFINED state */
+	if (klp_target_state == KLP_PATCHED)
+		klp_synchronize_transition();
+
+	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;
+	}
+
+	klp_for_each_object(klp_transition_patch, obj) {
+		if (!klp_is_object_loaded(obj))
+			continue;
+		if (klp_target_state == KLP_PATCHED)
+			klp_post_patch_callback(obj);
+		else if (klp_target_state == KLP_UNPATCHED)
+			klp_post_unpatch_callback(obj);
+	}
+
+	pr_notice("'%s': %s complete\n", klp_transition_patch->mod->name,
+		  klp_target_state == KLP_PATCHED ? "patching" : "unpatching");
+
+	/*
+	 * klp_forced set implies unbounded increase of module's ref count if
+	 * the module is disabled/enabled in a loop.
+	 */
+	if (!klp_forced && klp_target_state == KLP_UNPATCHED)
+		module_put(klp_transition_patch->mod);
+
+	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;
+
+	pr_debug("'%s': canceling patching transition, going to unpatch\n",
+		 klp_transition_patch->mod->name);
+
+	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)
+{
+	/*
+	 * A variant of synchronize_sched() is used to allow patching functions
+	 * where RCU is not watching, see klp_synchronize_transition().
+	 */
+	preempt_disable_notrace();
+
+	/*
+	 * 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);
+
+	preempt_enable_notrace();
+}
+
+/*
+ * 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;
+
+	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;
+
+	/*
+	 * 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);
+
+	/*
+	 * 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;
+	}
+
+	/* 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': starting %s transition\n",
+		  klp_transition_patch->mod->name,
+		  klp_target_state == KLP_PATCHED ? "patching" : "unpatching");
+
+	/*
+	 * 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;
+
+	pr_debug("'%s': initializing %s transition\n", patch->mod->name,
+		 klp_target_state == KLP_PATCHED ? "patching" : "unpatching");
+
+	/*
+	 * 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;
+
+	pr_debug("'%s': reversing transition from %s\n",
+		 klp_transition_patch->mod->name,
+		 klp_target_state == KLP_PATCHED ? "patching to unpatching" :
+						   "unpatching to patching");
+
+	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 */
+	klp_synchronize_transition();
+
+	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() */
+}
+
+/*
+ * Sends a fake signal to all non-kthread tasks with TIF_PATCH_PENDING set.
+ * Kthreads with TIF_PATCH_PENDING set are woken up. Only admin can request this
+ * action currently.
+ */
+void klp_send_signals(void)
+{
+	struct task_struct *g, *task;
+
+	pr_notice("signaling remaining tasks\n");
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, task) {
+		if (!klp_patch_pending(task))
+			continue;
+
+		/*
+		 * There is a small race here. We could see TIF_PATCH_PENDING
+		 * set and decide to wake up a kthread or send a fake signal.
+		 * Meanwhile the task could migrate itself and the action
+		 * would be meaningless. It is not serious though.
+		 */
+		if (task->flags & PF_KTHREAD) {
+			/*
+			 * Wake up a kthread which sleeps interruptedly and
+			 * still has not been migrated.
+			 */
+			wake_up_state(task, TASK_INTERRUPTIBLE);
+		} else {
+			/*
+			 * Send fake signal to all non-kthread tasks which are
+			 * still not migrated.
+			 */
+			spin_lock_irq(&task->sighand->siglock);
+			signal_wake_up(task, 0);
+			spin_unlock_irq(&task->sighand->siglock);
+		}
+	}
+	read_unlock(&tasklist_lock);
+}
+
+/*
+ * Drop TIF_PATCH_PENDING of all tasks on admin's request. This forces an
+ * existing transition to finish.
+ *
+ * NOTE: klp_update_patch_state(task) requires the task to be inactive or
+ * 'current'. This is not the case here and the consistency model could be
+ * broken. Administrator, who is the only one to execute the
+ * klp_force_transitions(), has to be aware of this.
+ */
+void klp_force_transition(void)
+{
+	struct task_struct *g, *task;
+	unsigned int cpu;
+
+	pr_warn("forcing remaining tasks to the patched state\n");
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, task)
+		klp_update_patch_state(task);
+	read_unlock(&tasklist_lock);
+
+	for_each_possible_cpu(cpu)
+		klp_update_patch_state(idle_task(cpu));
+
+	klp_forced = true;
+}

kernel/livepatch/transition.h

@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#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);
+void klp_send_signals(void);
+void klp_force_transition(void);
+
+#endif /* _LIVEPATCH_TRANSITION_H */