linux_dsm_epyc7002/arch/x86/kernel/dumpstack.c
Andrey Ryabinin ef7f0d6a6c x86_64: add KASan support
This patch adds arch specific code for kernel address sanitizer.

16TB of virtual addressed used for shadow memory.  It's located in range
[ffffec0000000000 - fffffc0000000000] between vmemmap and %esp fixup
stacks.

At early stage we map whole shadow region with zero page.  Latter, after
pages mapped to direct mapping address range we unmap zero pages from
corresponding shadow (see kasan_map_shadow()) and allocate and map a real
shadow memory reusing vmemmap_populate() function.

Also replace __pa with __pa_nodebug before shadow initialized.  __pa with
CONFIG_DEBUG_VIRTUAL=y make external function call (__phys_addr)
__phys_addr is instrumented, so __asan_load could be called before shadow
area initialized.

Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: Andrey Konovalov <adech.fo@gmail.com>
Cc: Yuri Gribov <tetra2005@gmail.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Jim Davis <jim.epost@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-13 21:21:41 -08:00

353 lines
7.6 KiB
C

/*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
*/
#include <linux/kallsyms.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/utsname.h>
#include <linux/hardirq.h>
#include <linux/kdebug.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/ftrace.h>
#include <linux/kexec.h>
#include <linux/bug.h>
#include <linux/nmi.h>
#include <linux/sysfs.h>
#include <asm/stacktrace.h>
int panic_on_unrecovered_nmi;
int panic_on_io_nmi;
unsigned int code_bytes = 64;
int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
static int die_counter;
static void printk_stack_address(unsigned long address, int reliable)
{
pr_cont(" [<%p>] %s%pB\n",
(void *)address, reliable ? "" : "? ", (void *)address);
}
void printk_address(unsigned long address)
{
pr_cont(" [<%p>] %pS\n", (void *)address, (void *)address);
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static void
print_ftrace_graph_addr(unsigned long addr, void *data,
const struct stacktrace_ops *ops,
struct thread_info *tinfo, int *graph)
{
struct task_struct *task;
unsigned long ret_addr;
int index;
if (addr != (unsigned long)return_to_handler)
return;
task = tinfo->task;
index = task->curr_ret_stack;
if (!task->ret_stack || index < *graph)
return;
index -= *graph;
ret_addr = task->ret_stack[index].ret;
ops->address(data, ret_addr, 1);
(*graph)++;
}
#else
static inline void
print_ftrace_graph_addr(unsigned long addr, void *data,
const struct stacktrace_ops *ops,
struct thread_info *tinfo, int *graph)
{ }
#endif
/*
* x86-64 can have up to three kernel stacks:
* process stack
* interrupt stack
* severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
*/
static inline int valid_stack_ptr(struct thread_info *tinfo,
void *p, unsigned int size, void *end)
{
void *t = tinfo;
if (end) {
if (p < end && p >= (end-THREAD_SIZE))
return 1;
else
return 0;
}
return p > t && p < t + THREAD_SIZE - size;
}
unsigned long
print_context_stack(struct thread_info *tinfo,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data,
unsigned long *end, int *graph)
{
struct stack_frame *frame = (struct stack_frame *)bp;
while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
unsigned long addr;
addr = *stack;
if (__kernel_text_address(addr)) {
if ((unsigned long) stack == bp + sizeof(long)) {
ops->address(data, addr, 1);
frame = frame->next_frame;
bp = (unsigned long) frame;
} else {
ops->address(data, addr, 0);
}
print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
}
stack++;
}
return bp;
}
EXPORT_SYMBOL_GPL(print_context_stack);
unsigned long
print_context_stack_bp(struct thread_info *tinfo,
unsigned long *stack, unsigned long bp,
const struct stacktrace_ops *ops, void *data,
unsigned long *end, int *graph)
{
struct stack_frame *frame = (struct stack_frame *)bp;
unsigned long *ret_addr = &frame->return_address;
while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) {
unsigned long addr = *ret_addr;
if (!__kernel_text_address(addr))
break;
ops->address(data, addr, 1);
frame = frame->next_frame;
ret_addr = &frame->return_address;
print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
}
return (unsigned long)frame;
}
EXPORT_SYMBOL_GPL(print_context_stack_bp);
static int print_trace_stack(void *data, char *name)
{
printk("%s <%s> ", (char *)data, name);
return 0;
}
/*
* Print one address/symbol entries per line.
*/
static void print_trace_address(void *data, unsigned long addr, int reliable)
{
touch_nmi_watchdog();
printk(data);
printk_stack_address(addr, reliable);
}
static const struct stacktrace_ops print_trace_ops = {
.stack = print_trace_stack,
.address = print_trace_address,
.walk_stack = print_context_stack,
};
void
show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, unsigned long bp, char *log_lvl)
{
printk("%sCall Trace:\n", log_lvl);
dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
}
void show_trace(struct task_struct *task, struct pt_regs *regs,
unsigned long *stack, unsigned long bp)
{
show_trace_log_lvl(task, regs, stack, bp, "");
}
void show_stack(struct task_struct *task, unsigned long *sp)
{
unsigned long bp = 0;
unsigned long stack;
/*
* Stack frames below this one aren't interesting. Don't show them
* if we're printing for %current.
*/
if (!sp && (!task || task == current)) {
sp = &stack;
bp = stack_frame(current, NULL);
}
show_stack_log_lvl(task, NULL, sp, bp, "");
}
static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED;
static int die_owner = -1;
static unsigned int die_nest_count;
unsigned long oops_begin(void)
{
int cpu;
unsigned long flags;
oops_enter();
/* racy, but better than risking deadlock. */
raw_local_irq_save(flags);
cpu = smp_processor_id();
if (!arch_spin_trylock(&die_lock)) {
if (cpu == die_owner)
/* nested oops. should stop eventually */;
else
arch_spin_lock(&die_lock);
}
die_nest_count++;
die_owner = cpu;
console_verbose();
bust_spinlocks(1);
return flags;
}
EXPORT_SYMBOL_GPL(oops_begin);
NOKPROBE_SYMBOL(oops_begin);
void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
{
if (regs && kexec_should_crash(current))
crash_kexec(regs);
bust_spinlocks(0);
die_owner = -1;
add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
die_nest_count--;
if (!die_nest_count)
/* Nest count reaches zero, release the lock. */
arch_spin_unlock(&die_lock);
raw_local_irq_restore(flags);
oops_exit();
if (!signr)
return;
if (in_interrupt())
panic("Fatal exception in interrupt");
if (panic_on_oops)
panic("Fatal exception");
do_exit(signr);
}
NOKPROBE_SYMBOL(oops_end);
int __die(const char *str, struct pt_regs *regs, long err)
{
#ifdef CONFIG_X86_32
unsigned short ss;
unsigned long sp;
#endif
printk(KERN_DEFAULT
"%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
#ifdef CONFIG_PREEMPT
printk("PREEMPT ");
#endif
#ifdef CONFIG_SMP
printk("SMP ");
#endif
#ifdef CONFIG_DEBUG_PAGEALLOC
printk("DEBUG_PAGEALLOC ");
#endif
#ifdef CONFIG_KASAN
printk("KASAN");
#endif
printk("\n");
if (notify_die(DIE_OOPS, str, regs, err,
current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
return 1;
print_modules();
show_regs(regs);
#ifdef CONFIG_X86_32
if (user_mode_vm(regs)) {
sp = regs->sp;
ss = regs->ss & 0xffff;
} else {
sp = kernel_stack_pointer(regs);
savesegment(ss, ss);
}
printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
print_symbol("%s", regs->ip);
printk(" SS:ESP %04x:%08lx\n", ss, sp);
#else
/* Executive summary in case the oops scrolled away */
printk(KERN_ALERT "RIP ");
printk_address(regs->ip);
printk(" RSP <%016lx>\n", regs->sp);
#endif
return 0;
}
NOKPROBE_SYMBOL(__die);
/*
* This is gone through when something in the kernel has done something bad
* and is about to be terminated:
*/
void die(const char *str, struct pt_regs *regs, long err)
{
unsigned long flags = oops_begin();
int sig = SIGSEGV;
if (!user_mode_vm(regs))
report_bug(regs->ip, regs);
if (__die(str, regs, err))
sig = 0;
oops_end(flags, regs, sig);
}
static int __init kstack_setup(char *s)
{
ssize_t ret;
unsigned long val;
if (!s)
return -EINVAL;
ret = kstrtoul(s, 0, &val);
if (ret)
return ret;
kstack_depth_to_print = val;
return 0;
}
early_param("kstack", kstack_setup);
static int __init code_bytes_setup(char *s)
{
ssize_t ret;
unsigned long val;
if (!s)
return -EINVAL;
ret = kstrtoul(s, 0, &val);
if (ret)
return ret;
code_bytes = val;
if (code_bytes > 8192)
code_bytes = 8192;
return 1;
}
__setup("code_bytes=", code_bytes_setup);