From 878719e831d9e076961aa15d4049a57a6668c67a Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Thu, 23 Oct 2008 10:40:06 -0400 Subject: x86: unify appropriate bits from dumpstack_32 and dumpstack_64 Impact: cleanup As promised, now that dumpstack_32 and dumpstack_64 have so many bits in common, we should merge the in-sync bits into a common file, to prevent them from diverging again. This patch removes bits which are common between dumpstack_32.c and dumpstack_64.c and places them in a common dumpstack.c which is built for both 32 and 64 bit arches. Signed-off-by: Neil Horman Acked-by: Alexander van Heukelum Signed-off-by: Ingo Molnar Makefile | 2 arch/x86/kernel/Makefile | 2 arch/x86/kernel/Makefile | 2 arch/x86/kernel/Makefile | 2 arch/x86/kernel/Makefile | 2 arch/x86/kernel/Makefile | 2 arch/x86/kernel/dumpstack.c | 319 +++++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/dumpstack.h | 39 +++++ arch/x86/kernel/dumpstack_32.c | 294 ------------------------------------- arch/x86/kernel/dumpstack_64.c | 285 ------------------------------------ 5 files changed, 363 insertions(+), 576 deletions(-) --- arch/x86/kernel/dumpstack.c | 319 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 319 insertions(+) create mode 100644 arch/x86/kernel/dumpstack.c (limited to 'arch/x86/kernel/dumpstack.c') diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c new file mode 100644 index 00000000000..5962176dfab --- /dev/null +++ b/arch/x86/kernel/dumpstack.c @@ -0,0 +1,319 @@ +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "dumpstack.h" + +int panic_on_unrecovered_nmi; +unsigned int code_bytes = 64; +int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE; +static int die_counter; + +void printk_address(unsigned long address, int reliable) +{ + printk(" [<%p>] %s%pS\n", (void *) address, + reliable ? "" : "? ", (void *) address); +} + +/* + * 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) +{ + 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, bp == 0); + } + } + stack++; + } + return bp; +} + + +static void +print_trace_warning_symbol(void *data, char *msg, unsigned long symbol) +{ + printk(data); + print_symbol(msg, symbol); + printk("\n"); +} + +static void print_trace_warning(void *data, char *msg) +{ + printk("%s%s\n", (char *)data, msg); +} + +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_address(addr, reliable); +} + +static const struct stacktrace_ops print_trace_ops = { + .warning = print_trace_warning, + .warning_symbol = print_trace_warning_symbol, + .stack = print_trace_stack, + .address = print_trace_address, +}; + +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) +{ + show_stack_log_lvl(task, NULL, sp, 0, ""); +} + +/* + * The architecture-independent dump_stack generator + */ +void dump_stack(void) +{ + unsigned long bp = 0; + unsigned long stack; + +#ifdef CONFIG_FRAME_POINTER + if (!bp) + get_bp(bp); +#endif + + printk("Pid: %d, comm: %.20s %s %s %.*s\n", + current->pid, current->comm, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + show_trace(NULL, NULL, &stack, bp); +} +EXPORT_SYMBOL(dump_stack); + +static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED; +static int die_owner = -1; +static unsigned int die_nest_count; + +unsigned __kprobes 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 (!__raw_spin_trylock(&die_lock)) { + if (cpu == die_owner) + /* nested oops. should stop eventually */; + else + __raw_spin_lock(&die_lock); + } + die_nest_count++; + die_owner = cpu; + console_verbose(); + bust_spinlocks(1); + return flags; +} + +void __kprobes 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); + die_nest_count--; + if (!die_nest_count) + /* Nest count reaches zero, release the lock. */ + __raw_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); +} + +int __kprobes __die(const char *str, struct pt_regs *regs, long err) +{ +#ifdef CONFIG_X86_32 + unsigned short ss; + unsigned long sp; +#endif + printk(KERN_EMERG "%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 + printk("\n"); + sysfs_printk_last_file(); + if (notify_die(DIE_OOPS, str, regs, err, + current->thread.trap_no, SIGSEGV) == NOTIFY_STOP) + return 1; + + show_registers(regs); +#ifdef CONFIG_X86_32 + sp = (unsigned long) (®s->sp); + savesegment(ss, ss); + if (user_mode(regs)) { + sp = regs->sp; + ss = regs->ss & 0xffff; + } + 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, 1); + printk(" RSP <%016lx>\n", regs->sp); +#endif + return 0; +} + +/* + * 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); +} + +void notrace __kprobes +die_nmi(char *str, struct pt_regs *regs, int do_panic) +{ + unsigned long flags; + + if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP) + return; + + /* + * We are in trouble anyway, lets at least try + * to get a message out. + */ + flags = oops_begin(); + printk(KERN_EMERG "%s", str); + printk(" on CPU%d, ip %08lx, registers:\n", + smp_processor_id(), regs->ip); + show_registers(regs); + oops_end(flags, regs, 0); + if (do_panic || panic_on_oops) + panic("Non maskable interrupt"); + nmi_exit(); + local_irq_enable(); + do_exit(SIGBUS); +} + +static int __init oops_setup(char *s) +{ + if (!s) + return -EINVAL; + if (!strcmp(s, "panic")) + panic_on_oops = 1; + return 0; +} +early_param("oops", oops_setup); + +static int __init kstack_setup(char *s) +{ + if (!s) + return -EINVAL; + kstack_depth_to_print = simple_strtoul(s, NULL, 0); + return 0; +} +early_param("kstack", kstack_setup); + +static int __init code_bytes_setup(char *s) +{ + code_bytes = simple_strtoul(s, NULL, 0); + if (code_bytes > 8192) + code_bytes = 8192; + + return 1; +} +__setup("code_bytes=", code_bytes_setup); -- cgit v1.2.3 From 7ee991fbc6f947e9b04f29c9c6c1d057d0671a16 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 2 Dec 2008 23:50:04 -0500 Subject: ftrace: print real return in dumpstack for function graph Impact: better dumpstack output I noticed in my crash dumps and even in the stack tracer that a lot of functions listed in the stack trace are simply return_to_handler which is ftrace graphs way to insert its own call into the return of a function. But we lose out where the actually function was called from. This patch adds in hooks to the dumpstack mechanism that detects this and finds the real function to print. Both are printed to let the user know that a hook is still in place. This does give a funny side effect in the stack tracer output: Depth Size Location (80 entries) ----- ---- -------- 0) 4144 48 save_stack_trace+0x2f/0x4d 1) 4096 128 ftrace_call+0x5/0x2b 2) 3968 16 mempool_alloc_slab+0x16/0x18 3) 3952 384 return_to_handler+0x0/0x73 4) 3568 -240 stack_trace_call+0x11d/0x209 5) 3808 144 return_to_handler+0x0/0x73 6) 3664 -128 mempool_alloc+0x4d/0xfe 7) 3792 128 return_to_handler+0x0/0x73 8) 3664 -32 scsi_sg_alloc+0x48/0x4a [scsi_mod] As you can see, the real functions are now negative. This is due to them not being found inside the stack. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/kernel/dumpstack.c | 34 +++++++++++++++++++++++++++++++++- 1 file changed, 33 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel/dumpstack.c') diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 5962176dfab..6b1f6f6f866 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -30,6 +30,37 @@ void printk_address(unsigned long address, int reliable) reliable ? "" : "? ", (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 = tinfo->task; + unsigned long ret_addr; + int index = task->curr_ret_stack; + + if (addr != (unsigned long)return_to_handler) + return; + + 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 @@ -54,7 +85,7 @@ 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) + unsigned long *end, int *graph) { struct stack_frame *frame = (struct stack_frame *)bp; @@ -70,6 +101,7 @@ print_context_stack(struct thread_info *tinfo, } else { ops->address(data, addr, bp == 0); } + print_ftrace_graph_addr(addr, data, ops, tinfo, graph); } stack++; } -- cgit v1.2.3