d83a7cb375
Change livepatch to use a basic per-task consistency model. This is the foundation which will eventually enable us to patch those ~10% of security patches which change function or data semantics. This is the biggest remaining piece needed to make livepatch more generally useful. This code stems from the design proposal made by Vojtech [1] in November 2014. It's 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. [1] https://lkml.kernel.org/r/20141107140458.GA21774@suse.cz Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Miroslav Benes <mbenes@suse.cz> Acked-by: Ingo Molnar <mingo@kernel.org> # for the scheduler changes Signed-off-by: Jiri Kosina <jkosina@suse.cz>
272 lines
6.3 KiB
C
272 lines
6.3 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);
|
|
|
|
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);
|
|
}
|