linux_dsm_epyc7002/arch/x86/kernel/stacktrace.c
Vlastimil Babka 77072f09ea x86/stacktrace: Avoid recording save_stack_trace() wrappers
The save_stack_trace() and save_stack_trace_tsk() wrappers of
__save_stack_trace() add themselves to the call stack, and thus appear in the
recorded stacktraces. This is redundant and wasteful when we have limited space
to record the useful part of the backtrace with e.g. page_owner functionality.

Fix this by making sure __save_stack_trace() is noinline (which matches the
current gcc decision) and bumping the skip in the wrappers
(save_stack_trace_tsk() only when called for the current task). This is similar
to what was done for arm in 3683f44c42 ("ARM: stacktrace: avoid listing
stacktrace functions in stacktrace") and is pending for arm64.

Also make sure that __save_stack_trace_reliable() doesn't get this problem in
the future by marking it __always_inline (which matches current gcc decision),
per Josh Poimboeuf.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Miroslav Benes <mbenes@suse.cz>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170929092335.2744-1-vbabka@suse.cz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-09-29 19:44:03 +02:00

240 lines
5.3 KiB
C

/*
* Stack trace management functions
*
* Copyright (C) 2006-2009 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
*/
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
#include <linux/stacktrace.h>
#include <linux/export.h>
#include <linux/uaccess.h>
#include <asm/stacktrace.h>
#include <asm/unwind.h>
static int save_stack_address(struct stack_trace *trace, unsigned long addr,
bool nosched)
{
if (nosched && in_sched_functions(addr))
return 0;
if (trace->skip > 0) {
trace->skip--;
return 0;
}
if (trace->nr_entries >= trace->max_entries)
return -1;
trace->entries[trace->nr_entries++] = addr;
return 0;
}
static void noinline __save_stack_trace(struct stack_trace *trace,
struct task_struct *task, struct pt_regs *regs,
bool nosched)
{
struct unwind_state state;
unsigned long addr;
if (regs)
save_stack_address(trace, regs->ip, nosched);
for (unwind_start(&state, task, regs, NULL); !unwind_done(&state);
unwind_next_frame(&state)) {
addr = unwind_get_return_address(&state);
if (!addr || save_stack_address(trace, addr, nosched))
break;
}
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}
/*
* Save stack-backtrace addresses into a stack_trace buffer.
*/
void save_stack_trace(struct stack_trace *trace)
{
trace->skip++;
__save_stack_trace(trace, current, NULL, false);
}
EXPORT_SYMBOL_GPL(save_stack_trace);
void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
{
__save_stack_trace(trace, current, regs, false);
}
void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
if (!try_get_task_stack(tsk))
return;
if (tsk == current)
trace->skip++;
__save_stack_trace(trace, tsk, NULL, true);
put_task_stack(tsk);
}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
#define STACKTRACE_DUMP_ONCE(task) ({ \
static bool __section(.data.unlikely) __dumped; \
\
if (!__dumped) { \
__dumped = true; \
WARN_ON(1); \
show_stack(task, NULL); \
} \
})
static int __always_inline
__save_stack_trace_reliable(struct stack_trace *trace,
struct task_struct *task)
{
struct unwind_state state;
struct pt_regs *regs;
unsigned long addr;
for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state);
unwind_next_frame(&state)) {
regs = unwind_get_entry_regs(&state);
if (regs) {
/*
* Kernel mode registers on the stack indicate an
* in-kernel interrupt or exception (e.g., preemption
* or a page fault), which can make frame pointers
* unreliable.
*/
if (!user_mode(regs))
return -EINVAL;
/*
* The last frame contains the user mode syscall
* pt_regs. Skip it and finish the unwind.
*/
unwind_next_frame(&state);
if (!unwind_done(&state)) {
STACKTRACE_DUMP_ONCE(task);
return -EINVAL;
}
break;
}
addr = unwind_get_return_address(&state);
/*
* A NULL or invalid return address probably means there's some
* generated code which __kernel_text_address() doesn't know
* about.
*/
if (!addr) {
STACKTRACE_DUMP_ONCE(task);
return -EINVAL;
}
if (save_stack_address(trace, addr, false))
return -EINVAL;
}
/* Check for stack corruption */
if (unwind_error(&state)) {
STACKTRACE_DUMP_ONCE(task);
return -EINVAL;
}
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
return 0;
}
/*
* This function returns an error if it detects any unreliable features of the
* stack. Otherwise it guarantees that the stack trace is reliable.
*
* If the task is not 'current', the caller *must* ensure the task is inactive.
*/
int save_stack_trace_tsk_reliable(struct task_struct *tsk,
struct stack_trace *trace)
{
int ret;
if (!try_get_task_stack(tsk))
return -EINVAL;
ret = __save_stack_trace_reliable(trace, tsk);
put_task_stack(tsk);
return ret;
}
#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
/* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
struct stack_frame_user {
const void __user *next_fp;
unsigned long ret_addr;
};
static int
copy_stack_frame(const void __user *fp, struct stack_frame_user *frame)
{
int ret;
if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
return 0;
ret = 1;
pagefault_disable();
if (__copy_from_user_inatomic(frame, fp, sizeof(*frame)))
ret = 0;
pagefault_enable();
return ret;
}
static inline void __save_stack_trace_user(struct stack_trace *trace)
{
const struct pt_regs *regs = task_pt_regs(current);
const void __user *fp = (const void __user *)regs->bp;
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = regs->ip;
while (trace->nr_entries < trace->max_entries) {
struct stack_frame_user frame;
frame.next_fp = NULL;
frame.ret_addr = 0;
if (!copy_stack_frame(fp, &frame))
break;
if ((unsigned long)fp < regs->sp)
break;
if (frame.ret_addr) {
trace->entries[trace->nr_entries++] =
frame.ret_addr;
}
if (fp == frame.next_fp)
break;
fp = frame.next_fp;
}
}
void save_stack_trace_user(struct stack_trace *trace)
{
/*
* Trace user stack if we are not a kernel thread
*/
if (current->mm) {
__save_stack_trace_user(trace);
}
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}