linux/kernel/trace/trace_stack.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2008 Steven Rostedt <[email protected]>
 *
 */
#include <linux/sched/task_stack.h>
#include <linux/stacktrace.h>
#include <linux/security.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/init.h>

#include <asm/setup.h>

#include "trace.h"

#define STACK_TRACE_ENTRIES

static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES];
static unsigned stack_trace_index[STACK_TRACE_ENTRIES];

static unsigned int stack_trace_nr_entries;
static unsigned long stack_trace_max_size;
static arch_spinlock_t stack_trace_max_lock =;

DEFINE_PER_CPU(int, disable_stack_tracer);
static DEFINE_MUTEX(stack_sysctl_mutex);

int stack_tracer_enabled;

static void print_max_stack(void)
{}

/*
 * The stack tracer looks for a maximum stack at each call from a function. It
 * registers a callback from ftrace, and in that callback it examines the stack
 * size. It determines the stack size from the variable passed in, which is the
 * address of a local variable in the stack_trace_call() callback function.
 * The stack size is calculated by the address of the local variable to the top
 * of the current stack. If that size is smaller than the currently saved max
 * stack size, nothing more is done.
 *
 * If the size of the stack is greater than the maximum recorded size, then the
 * following algorithm takes place.
 *
 * For architectures (like x86) that store the function's return address before
 * saving the function's local variables, the stack will look something like
 * this:
 *
 *   [ top of stack ]
 *    0: sys call entry frame
 *   10: return addr to entry code
 *   11: start of sys_foo frame
 *   20: return addr to sys_foo
 *   21: start of kernel_func_bar frame
 *   30: return addr to kernel_func_bar
 *   31: [ do trace stack here ]
 *
 * The save_stack_trace() is called returning all the functions it finds in the
 * current stack. Which would be (from the bottom of the stack to the top):
 *
 *   return addr to kernel_func_bar
 *   return addr to sys_foo
 *   return addr to entry code
 *
 * Now to figure out how much each of these functions' local variable size is,
 * a search of the stack is made to find these values. When a match is made, it
 * is added to the stack_dump_trace[] array. The offset into the stack is saved
 * in the stack_trace_index[] array. The above example would show:
 *
 *        stack_dump_trace[]        |   stack_trace_index[]
 *        ------------------        +   -------------------
 *  return addr to kernel_func_bar  |          30
 *  return addr to sys_foo          |          20
 *  return addr to entry            |          10
 *
 * The print_max_stack() function above, uses these values to print the size of
 * each function's portion of the stack.
 *
 *  for (i = 0; i < nr_entries; i++) {
 *     size = i == nr_entries - 1 ? stack_trace_index[i] :
 *                    stack_trace_index[i] - stack_trace_index[i+1]
 *     print "%d %d %d %s\n", i, stack_trace_index[i], size, stack_dump_trace[i]);
 *  }
 *
 * The above shows
 *
 *     depth size  location
 *     ----- ----  --------
 *  0    30   10   kernel_func_bar
 *  1    20   10   sys_foo
 *  2    10   10   entry code
 *
 * Now for architectures that might save the return address after the functions
 * local variables (saving the link register before calling nested functions),
 * this will cause the stack to look a little different:
 *
 * [ top of stack ]
 *  0: sys call entry frame
 * 10: start of sys_foo_frame
 * 19: return addr to entry code << lr saved before calling kernel_func_bar
 * 20: start of kernel_func_bar frame
 * 29: return addr to sys_foo_frame << lr saved before calling next function
 * 30: [ do trace stack here ]
 *
 * Although the functions returned by save_stack_trace() may be the same, the
 * placement in the stack will be different. Using the same algorithm as above
 * would yield:
 *
 *        stack_dump_trace[]        |   stack_trace_index[]
 *        ------------------        +   -------------------
 *  return addr to kernel_func_bar  |          30
 *  return addr to sys_foo          |          29
 *  return addr to entry            |          19
 *
 * Where the mapping is off by one:
 *
 *   kernel_func_bar stack frame size is 29 - 19 not 30 - 29!
 *
 * To fix this, if the architecture sets ARCH_RET_ADDR_AFTER_LOCAL_VARS the
 * values in stack_trace_index[] are shifted by one to and the number of
 * stack trace entries is decremented by one.
 *
 *        stack_dump_trace[]        |   stack_trace_index[]
 *        ------------------        +   -------------------
 *  return addr to kernel_func_bar  |          29
 *  return addr to sys_foo          |          19
 *
 * Although the entry function is not displayed, the first function (sys_foo)
 * will still include the stack size of it.
 */
static void check_stack(unsigned long ip, unsigned long *stack)
{}

/* Some archs may not define MCOUNT_INSN_SIZE */
#ifndef MCOUNT_INSN_SIZE
#define MCOUNT_INSN_SIZE
#endif

static void
stack_trace_call(unsigned long ip, unsigned long parent_ip,
		 struct ftrace_ops *op, struct ftrace_regs *fregs)
{}

static struct ftrace_ops trace_ops __read_mostly =;

static ssize_t
stack_max_size_read(struct file *filp, char __user *ubuf,
		    size_t count, loff_t *ppos)
{}

static ssize_t
stack_max_size_write(struct file *filp, const char __user *ubuf,
		     size_t count, loff_t *ppos)
{}

static const struct file_operations stack_max_size_fops =;

static void *
__next(struct seq_file *m, loff_t *pos)
{}

static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{}

static void *t_start(struct seq_file *m, loff_t *pos)
{}

static void t_stop(struct seq_file *m, void *p)
{}

static void trace_lookup_stack(struct seq_file *m, long i)
{}

static void print_disabled(struct seq_file *m)
{}

static int t_show(struct seq_file *m, void *v)
{}

static const struct seq_operations stack_trace_seq_ops =;

static int stack_trace_open(struct inode *inode, struct file *file)
{}

static const struct file_operations stack_trace_fops =;

#ifdef CONFIG_DYNAMIC_FTRACE

static int
stack_trace_filter_open(struct inode *inode, struct file *file)
{}

static const struct file_operations stack_trace_filter_fops =;

#endif /* CONFIG_DYNAMIC_FTRACE */

int
stack_trace_sysctl(const struct ctl_table *table, int write, void *buffer,
		   size_t *lenp, loff_t *ppos)
{}

static char stack_trace_filter_buf[COMMAND_LINE_SIZE+1] __initdata;

static __init int enable_stacktrace(char *str)
{}
__setup();

static __init int stack_trace_init(void)
{}

device_initcall(stack_trace_init);