lkml.org 
[lkml]   [2008]   [Oct]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH 1/4] Add support for userspace stacktraces in tracing/iter_ctrl
2008/10/12 Török Edwin <edwintorok@gmail.com>:
> Usage example:
> mount -t debugfs nodev /sys/kernel/debug
> cd /sys/kernel/debug/tracing
> echo userstacktrace >iter_ctrl
> echo sched_switch >current_tracer
> echo 1 >tracing_enabled
> .... run application ...
> echo 0 >tracing_enabled
>
> Then read one of 'trace','latency_trace','trace_pipe'
>
> Signed-off-by: Török Edwin <edwintorok@gmail.com>
> ---
> Documentation/ftrace.txt | 5 ++-
> arch/x86/kernel/stacktrace.c | 57 +++++++++++++++++++++++++++++++++++
> include/linux/stacktrace.h | 8 +++++
> kernel/trace/trace.c | 67 ++++++++++++++++++++++++++++++++++++++++++
> kernel/trace/trace.h | 2 +
> 5 files changed, 138 insertions(+), 1 deletions(-)
>
> diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt
> index d330fe3..f39cb68 100644
> --- a/Documentation/ftrace.txt
> +++ b/Documentation/ftrace.txt
> @@ -327,7 +327,7 @@ output. To see what is available, simply cat the file:
>
> cat /debug/tracing/iter_ctrl
> print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \
> - noblock nostacktrace nosched-tree
> + noblock nostacktrace nosched-tree nouserstacktrace
>
> To disable one of the options, echo in the option prepended with "no".
>
> @@ -381,6 +381,9 @@ Here are the available options:
> When a trace is recorded, so is the stack of functions.
> This allows for back traces of trace sites.
>
> + userstacktrace - This option changes the trace.
> + It records a stacktrace of the current userspace thread.
> +
> sched-tree - TBD (any users??)
>
>
> diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
> index d1d850a..000a965 100644
> --- a/arch/x86/kernel/stacktrace.c
> +++ b/arch/x86/kernel/stacktrace.c
> @@ -6,6 +6,7 @@
> #include <linux/sched.h>
> #include <linux/stacktrace.h>
> #include <linux/module.h>
> +#include <linux/uaccess.h>
> #include <asm/stacktrace.h>
>
> static void save_stack_warning(void *data, char *msg)
> @@ -90,3 +91,59 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
> trace->entries[trace->nr_entries++] = ULONG_MAX;
> }
> EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
> +
> +/* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
> +
> +struct stack_frame {
> + const void __user *next_fp;
> + unsigned long return_address;
> +};
> +
> +static int copy_stack_frame(const void __user *fp, struct stack_frame *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;
> +}
> +
> +void save_stack_trace_user(struct stack_trace *trace)
> +{
> + /*
> + * Trace user stack if we are not a kernel thread
> + */
> + if (current->mm) {
> + 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 frame;
> + frame.next_fp = NULL;
> + frame.return_address = 0;
> + if (!copy_stack_frame(fp, &frame))
> + break;
> + if ((unsigned long)fp < regs->sp)
> + break;
> + if (frame.return_address)
> + trace->entries[trace->nr_entries++] =
> + frame.return_address;
> + if (fp == frame.next_fp)
> + break;
> + fp = frame.next_fp;
> + }
> + }
> + if (trace->nr_entries < trace->max_entries)
> + trace->entries[trace->nr_entries++] = ULONG_MAX;
> +}
> +
> diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
> index 6b8e54a..46704a5 100644
> --- a/include/linux/stacktrace.h
> +++ b/include/linux/stacktrace.h
> @@ -18,9 +18,17 @@ extern void save_stack_trace_tsk(struct task_struct *tsk,
> struct stack_trace *trace);
>
> extern void print_stack_trace(struct stack_trace *trace, int spaces);
> +
> +#ifdef CONFIG_X86
> +extern void save_stack_trace_user(struct stack_trace *trace);
> +#else
> +# define save_stack_trace_user(trace) do { } while (0)
> +#endif
> +
> #else
> # define save_stack_trace(trace) do { } while (0)
> # define save_stack_trace_tsk(tsk, trace) do { } while (0)
> +# define save_stack_trace_user(trace) do { } while (0)
> # define print_stack_trace(trace, spaces) do { } while (0)
> #endif
>
> diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
> index d345d64..4c17453 100644
> --- a/kernel/trace/trace.c
> +++ b/kernel/trace/trace.c
> @@ -212,6 +212,7 @@ static const char *trace_options[] = {
> "stacktrace",
> "sched-tree",
> "ftrace_printk",
> + "userstacktrace",
> NULL
> };
>
> @@ -735,6 +736,28 @@ void __trace_stack(struct trace_array *tr,
> ftrace_trace_stack(tr, data, flags, skip, preempt_count());
> }
>
> +static void __trace_userstack(struct trace_array *tr,
> + struct trace_array_cpu *data,
> + unsigned long flags)
> +{
> + struct trace_entry *entry;
> + struct stack_trace trace;
> +
> + if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
> + return;
> +
> + entry = tracing_get_trace_entry(tr, data);
> + tracing_generic_entry_update(entry, flags);
> + entry->type = TRACE_USER_STACK;
> +
> + memset(&entry->field.stack, 0, sizeof(entry->field.stack));
> + trace.nr_entries = 0;
> + trace.max_entries = FTRACE_STACK_ENTRIES;
> + trace.skip = 0;
> + trace.entries = entry->field.stack.caller;
> + save_stack_trace_user(&trace);
> +}
> +
> static void
> ftrace_trace_special(void *__tr, void *__data,
> unsigned long arg1, unsigned long arg2, unsigned long arg3,
> @@ -758,6 +781,7 @@ ftrace_trace_special(void *__tr, void *__data,
> entry->arg3 = arg3;
> ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
> ftrace_trace_stack(tr, data, irq_flags, 4, pc);
> + __trace_userstack(tr, data, irq_flags);
>
> trace_wake_up();
> }
> @@ -1151,6 +1175,31 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
> return ret;
> }
>
> +static int
> +seq_print_userip_objs(const struct trace_entry *entry, struct trace_seq *s,
> + unsigned long sym_flags)
> +{
> + int ret = 1;
> + unsigned i;
> +
> + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
> + unsigned long ip = entry->field.stack.caller[i];
> +
> + if (ip == ULONG_MAX || !ret)
> + break;
> + if (i)
> + ret = trace_seq_puts(s, " <- ");
> + if (!ip) {
> + ret = trace_seq_puts(s, "??");
> + continue;
> + }
> + if (sym_flags & TRACE_ITER_SYM_ADDR)
> + ret = trace_seq_printf(s, " <" IP_FMT ">", ip);
> + }
> +
> + return ret;
> +}
> +
> static void print_lat_help_header(struct seq_file *m)
> {
> seq_puts(m, "# _------=> CPU# \n");
> @@ -1437,6 +1486,10 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
> trace_seq_print_cont(s, iter);
> break;
> }
> + case TRACE_USER_STACK:
> + seq_print_userip_objs(entry, s, sym_flags);
> + trace_seq_putc(s, '\n');
> + break;
> default:
> trace_seq_printf(s, "Unknown type %d\n", entry->type);
> }
> @@ -1572,6 +1625,14 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
> if (entry->flags & TRACE_FLAG_CONT)
> trace_seq_print_cont(s, iter);
> break;
> + case TRACE_USER_STACK:
> + ret = seq_print_userip_objs(entry, s, sym_flags);
> + if (!ret)
> + return 0;
> + ret = trace_seq_putc(s, '\n');
> + if (!ret)
> + return 0;
> + break;
> }
> }
> return TRACE_TYPE_HANDLED;
> @@ -1632,6 +1693,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
> break;
> }
> case TRACE_SPECIAL:
> + case TRACE_USER_STACK:
> case TRACE_STACK: {
> struct special_entry *field;
>
> @@ -1720,6 +1782,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
> break;
> }
> case TRACE_SPECIAL:
> + case TRACE_USER_STACK:
> case TRACE_STACK: {
> struct special_entry *field;
>
> @@ -1774,6 +1837,7 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
> break;
> }
> case TRACE_SPECIAL:
> + case TRACE_USER_STACK:
> case TRACE_STACK: {
> struct special_entry *field;
>
> @@ -3103,6 +3167,9 @@ void ftrace_dump(void)
> atomic_inc(&global_trace.data[cpu]->disabled);
> }
>
> + /* don't look at user memory in panic mode */
> + trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
> +
> printk(KERN_TRACE "Dumping ftrace buffer:\n");
>
> iter.tr = &global_trace;
> diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
> index f1f9957..3ad6343 100644
> --- a/kernel/trace/trace.h
> +++ b/kernel/trace/trace.h
> @@ -22,6 +22,7 @@ enum trace_type {
> TRACE_MMIO_RW,
> TRACE_MMIO_MAP,
> TRACE_BOOT,
> + TRACE_USER_STACK,
>
> __TRACE_LAST_TYPE
> };
> @@ -413,6 +414,7 @@ enum trace_iterator_flags {
> TRACE_ITER_STACKTRACE = 0x100,
> TRACE_ITER_SCHED_TREE = 0x200,
> TRACE_ITER_PRINTK = 0x400,
> + TRACE_ITER_USERSTACKTRACE = 0x800
> };
>
> extern struct tracer nop_trace;
> --


Hi Török,

I just read a bit more those two patches about user stack tracing.
Note that despite the recent changes on the tracing Api
(ring buffer and other stuff), it still applies well, with some little
hunks. But it needs some updates to support the last changes.

I adapted the patch and it builds well, but I didn't tested yet.
However, some parts are "architecture dependent", I guess these
special pieces would find a better place in the arch directory. So it
would let a proper and seperated implementation.

And most arch implement a stacktrace implementation, even if yours
involve special operations such as copy_from_user, I wonder if the
already established code couldn't be reused for your needs.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2008-10-26 05:09    [W:0.158 / U:0.068 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site