kernel_optimize_test/kernel/extable.c
Zhou Chengming e846d13958 kprobes, x86/alternatives: Use text_mutex to protect smp_alt_modules
We use alternatives_text_reserved() to check if the address is in
the fixed pieces of alternative reserved, but the problem is that
we don't hold the smp_alt mutex when call this function. So the list
traversal may encounter a deleted list_head if another path is doing
alternatives_smp_module_del().

One solution is that we can hold smp_alt mutex before call this
function, but the difficult point is that the callers of this
functions, arch_prepare_kprobe() and arch_prepare_optimized_kprobe(),
are called inside the text_mutex. So we must hold smp_alt mutex
before we go into these arch dependent code. But we can't now,
the smp_alt mutex is the arch dependent part, only x86 has it.
Maybe we can export another arch dependent callback to solve this.

But there is a simpler way to handle this problem. We can reuse the
text_mutex to protect smp_alt_modules instead of using another mutex.
And all the arch dependent checks of kprobes are inside the text_mutex,
so it's safe now.

Signed-off-by: Zhou Chengming <zhouchengming1@huawei.com>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bp@suse.de
Fixes: 2cfa197 "ftrace/alternatives: Introducing *_text_reserved functions"
Link: http://lkml.kernel.org/r/1509585501-79466-1-git-send-email-zhouchengming1@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-11-07 12:20:09 +01:00

177 lines
4.8 KiB
C

/* Rewritten by Rusty Russell, on the backs of many others...
Copyright (C) 2001 Rusty Russell, 2002 Rusty Russell IBM.
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, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/ftrace.h>
#include <linux/memory.h>
#include <linux/extable.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/init.h>
#include <linux/kprobes.h>
#include <linux/filter.h>
#include <asm/sections.h>
#include <linux/uaccess.h>
/*
* mutex protecting text section modification (dynamic code patching).
* some users need to sleep (allocating memory...) while they hold this lock.
*
* Note: Also protects SMP-alternatives modification on x86.
*
* NOT exported to modules - patching kernel text is a really delicate matter.
*/
DEFINE_MUTEX(text_mutex);
extern struct exception_table_entry __start___ex_table[];
extern struct exception_table_entry __stop___ex_table[];
/* Cleared by build time tools if the table is already sorted. */
u32 __initdata __visible main_extable_sort_needed = 1;
/* Sort the kernel's built-in exception table */
void __init sort_main_extable(void)
{
if (main_extable_sort_needed && __stop___ex_table > __start___ex_table) {
pr_notice("Sorting __ex_table...\n");
sort_extable(__start___ex_table, __stop___ex_table);
}
}
/* Given an address, look for it in the exception tables. */
const struct exception_table_entry *search_exception_tables(unsigned long addr)
{
const struct exception_table_entry *e;
e = search_extable(__start___ex_table,
__stop___ex_table - __start___ex_table, addr);
if (!e)
e = search_module_extables(addr);
return e;
}
static inline int init_kernel_text(unsigned long addr)
{
if (addr >= (unsigned long)_sinittext &&
addr < (unsigned long)_einittext)
return 1;
return 0;
}
int notrace core_kernel_text(unsigned long addr)
{
if (addr >= (unsigned long)_stext &&
addr < (unsigned long)_etext)
return 1;
if (system_state < SYSTEM_RUNNING &&
init_kernel_text(addr))
return 1;
return 0;
}
/**
* core_kernel_data - tell if addr points to kernel data
* @addr: address to test
*
* Returns true if @addr passed in is from the core kernel data
* section.
*
* Note: On some archs it may return true for core RODATA, and false
* for others. But will always be true for core RW data.
*/
int core_kernel_data(unsigned long addr)
{
if (addr >= (unsigned long)_sdata &&
addr < (unsigned long)_edata)
return 1;
return 0;
}
int __kernel_text_address(unsigned long addr)
{
if (kernel_text_address(addr))
return 1;
/*
* There might be init symbols in saved stacktraces.
* Give those symbols a chance to be printed in
* backtraces (such as lockdep traces).
*
* Since we are after the module-symbols check, there's
* no danger of address overlap:
*/
if (init_kernel_text(addr))
return 1;
return 0;
}
int kernel_text_address(unsigned long addr)
{
bool no_rcu;
int ret = 1;
if (core_kernel_text(addr))
return 1;
/*
* If a stack dump happens while RCU is not watching, then
* RCU needs to be notified that it requires to start
* watching again. This can happen either by tracing that
* triggers a stack trace, or a WARN() that happens during
* coming back from idle, or cpu on or offlining.
*
* is_module_text_address() as well as the kprobe slots
* and is_bpf_text_address() require RCU to be watching.
*/
no_rcu = !rcu_is_watching();
/* Treat this like an NMI as it can happen anywhere */
if (no_rcu)
rcu_nmi_enter();
if (is_module_text_address(addr))
goto out;
if (is_ftrace_trampoline(addr))
goto out;
if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
goto out;
if (is_bpf_text_address(addr))
goto out;
ret = 0;
out:
if (no_rcu)
rcu_nmi_exit();
return ret;
}
/*
* On some architectures (PPC64, IA64) function pointers
* are actually only tokens to some data that then holds the
* real function address. As a result, to find if a function
* pointer is part of the kernel text, we need to do some
* special dereferencing first.
*/
int func_ptr_is_kernel_text(void *ptr)
{
unsigned long addr;
addr = (unsigned long) dereference_function_descriptor(ptr);
if (core_kernel_text(addr))
return 1;
return is_module_text_address(addr);
}