mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-24 02:37:15 +07:00
842c088464
rcu_read_(un)lock(), list_*_rcu(), and synchronize_rcu() are used for a secure access and manipulation of the list of patches that modify the same function. In particular, it is the variable func_stack that is accessible from the ftrace handler via struct ftrace_ops and klp_ops. Of course, it synchronizes also some states of the patch on the top of the stack, e.g. func->transition in klp_ftrace_handler. At the same time, this mechanism guards also the manipulation of task->patch_state. It is modified according to the state of the transition and the state of the process. Now, all this works well as long as RCU works well. Sadly livepatching might get into some corner cases when this is not true. For example, RCU is not watching when rcu_read_lock() is taken in idle threads. It is because they might sleep and prevent reaching the grace period for too long. There are ways how to make RCU watching even in idle threads, see rcu_irq_enter(). But there is a small location inside RCU infrastructure when even this does not work. This small problematic location can be detected either before calling rcu_irq_enter() by rcu_irq_enter_disabled() or later by rcu_is_watching(). Sadly, there is no safe way how to handle it. Once we detect that RCU was not watching, we might see inconsistent state of the function stack and the related variables in klp_ftrace_handler(). Then we could do a wrong decision, use an incompatible implementation of the function and break the consistency of the system. We could warn but we could not avoid the damage. Fortunately, ftrace has similar problems and they seem to be solved well there. It uses a heavy weight implementation of some RCU operations. In particular, it replaces: + rcu_read_lock() with preempt_disable_notrace() + rcu_read_unlock() with preempt_enable_notrace() + synchronize_rcu() with schedule_on_each_cpu(sync_work) My understanding is that this is RCU implementation from a stone age. It meets the core RCU requirements but it is rather ineffective. Especially, it does not allow to batch or speed up the synchronize calls. On the other hand, it is very trivial. It allows to safely trace and/or livepatch even the RCU core infrastructure. And the effectiveness is a not a big issue because using ftrace or livepatches on productive systems is a rare operation. The safety is much more important than a negligible extra load. Note that the alternative implementation follows the RCU principles. Therefore, we could and actually must use list_*_rcu() variants when manipulating the func_stack. These functions allow to access the pointers in the right order and with the right barriers. But they do not use any other information that would be set only by rcu_read_lock(). Also note that there are actually two problems solved in ftrace: First, it cares about the consistency of RCU read sections. It is being solved the way as described and used in this patch. Second, ftrace needs to make sure that nobody is inside the dynamic trampoline when it is being freed. For this, it also calls synchronize_rcu_tasks() in preemptive kernel in ftrace_shutdown(). Livepatch has similar problem but it is solved by ftrace for free. klp_ftrace_handler() is a good guy and never sleeps. In addition, it is registered with FTRACE_OPS_FL_DYNAMIC. It causes that unregister_ftrace_function() calls: * schedule_on_each_cpu(ftrace_sync) - always * synchronize_rcu_tasks() - in preemptive kernel The effect is that nobody is neither inside the dynamic trampoline nor inside the ftrace handler after unregister_ftrace_function() returns. [jkosina@suse.cz: reformat changelog, fix comment] Signed-off-by: Petr Mladek <pmladek@suse.com> Acked-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Miroslav Benes <mbenes@suse.cz> Signed-off-by: Jiri Kosina <jkosina@suse.cz>
277 lines
6.4 KiB
C
277 lines
6.4 KiB
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);
|
|
|
|
/*
|
|
* 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);
|
|
}
|