On Thu, 25 Apr 2024 13:15:08 -0700
Andrii Nakryiko <andrii.nakryiko@xxxxxxxxx> wrote:
> On Mon, Apr 15, 2024 at 6:25 AM Masami Hiramatsu (Google)
> <mhiramat@xxxxxxxxxx> wrote:
> >
> > From: Masami Hiramatsu (Google) <mhiramat@xxxxxxxxxx>
> >
> > Skip recording calltime and rettime if the fgraph_ops does not need it.
> > This is a kind of performance optimization for fprobe. Since the fprobe
> > user does not use these entries, recording timestamp in fgraph is just
> > a overhead (e.g. eBPF, ftrace). So introduce the skip_timestamp flag,
> > and all fgraph_ops sets this flag, skip recording calltime and rettime.
> >
> > Suggested-by: Jiri Olsa <olsajiri@xxxxxxxxx>
> > Signed-off-by: Masami Hiramatsu (Google) <mhiramat@xxxxxxxxxx>
> > ---
> > Changes in v9:
> > - Newly added.
> > ---
> > include/linux/ftrace.h | 2 ++
> > kernel/trace/fgraph.c | 46 +++++++++++++++++++++++++++++++++++++++-------
> > kernel/trace/fprobe.c | 1 +
> > 3 files changed, 42 insertions(+), 7 deletions(-)
> >
> > diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
> > index d845a80a3d56..06fc7cbef897 100644
> > --- a/include/linux/ftrace.h
> > +++ b/include/linux/ftrace.h
> > @@ -1156,6 +1156,8 @@ struct fgraph_ops {
> > struct ftrace_ops ops; /* for the hash lists */
> > void *private;
> > int idx;
> > + /* If skip_timestamp is true, this does not record timestamps. */
> > + bool skip_timestamp;
> > };
> >
> > void *fgraph_reserve_data(int idx, int size_bytes);
> > diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
> > index 7556fbbae323..a5722537bb79 100644
> > --- a/kernel/trace/fgraph.c
> > +++ b/kernel/trace/fgraph.c
> > @@ -131,6 +131,7 @@ DEFINE_STATIC_KEY_FALSE(kill_ftrace_graph);
> > int ftrace_graph_active;
> >
> > static struct fgraph_ops *fgraph_array[FGRAPH_ARRAY_SIZE];
> > +static bool fgraph_skip_timestamp;
> >
> > /* LRU index table for fgraph_array */
> > static int fgraph_lru_table[FGRAPH_ARRAY_SIZE];
> > @@ -475,7 +476,7 @@ void ftrace_graph_stop(void)
> > static int
> > ftrace_push_return_trace(unsigned long ret, unsigned long func,
> > unsigned long frame_pointer, unsigned long *retp,
> > - int fgraph_idx)
> > + int fgraph_idx, bool skip_ts)
> > {
> > struct ftrace_ret_stack *ret_stack;
> > unsigned long long calltime;
> > @@ -498,8 +499,12 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
> > ret_stack = get_ret_stack(current, current->curr_ret_stack, &index);
> > if (ret_stack && ret_stack->func == func &&
> > get_fgraph_type(current, index + FGRAPH_RET_INDEX) == FGRAPH_TYPE_BITMAP &&
> > - !is_fgraph_index_set(current, index + FGRAPH_RET_INDEX, fgraph_idx))
> > + !is_fgraph_index_set(current, index + FGRAPH_RET_INDEX, fgraph_idx)) {
> > + /* If previous one skips calltime, update it. */
> > + if (!skip_ts && !ret_stack->calltime)
> > + ret_stack->calltime = trace_clock_local();
> > return index + FGRAPH_RET_INDEX;
> > + }
> >
> > val = (FGRAPH_TYPE_RESERVED << FGRAPH_TYPE_SHIFT) | FGRAPH_RET_INDEX;
> >
> > @@ -517,7 +522,10 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
> > return -EBUSY;
> > }
> >
> > - calltime = trace_clock_local();
> > + if (skip_ts)
>
> would it be ok to add likely() here to keep the least-overhead code path linear?
It's not "likely", but hmm, yes as you said. We can keep the least overhead.
OK, let me add likely.
Thank you,
>
> > + calltime = 0LL;
> > + else
> > + calltime = trace_clock_local();
> >
> > index = READ_ONCE(current->curr_ret_stack);
> > ret_stack = RET_STACK(current, index);
> > @@ -601,7 +609,8 @@ int function_graph_enter_regs(unsigned long ret, unsigned long func,
> > trace.func = func;
> > trace.depth = ++current->curr_ret_depth;
> >
> > - index = ftrace_push_return_trace(ret, func, frame_pointer, retp, 0);
> > + index = ftrace_push_return_trace(ret, func, frame_pointer, retp, 0,
> > + fgraph_skip_timestamp);
> > if (index < 0)
> > goto out;
> >
> > @@ -654,7 +663,8 @@ int function_graph_enter_ops(unsigned long ret, unsigned long func,
> > return -ENODEV;
> >
> > /* Use start for the distance to ret_stack (skipping over reserve) */
> > - index = ftrace_push_return_trace(ret, func, frame_pointer, retp, gops->idx);
> > + index = ftrace_push_return_trace(ret, func, frame_pointer, retp, gops->idx,
> > + gops->skip_timestamp);
> > if (index < 0)
> > return index;
> > type = get_fgraph_type(current, index);
> > @@ -732,6 +742,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
> > *ret = ret_stack->ret;
> > trace->func = ret_stack->func;
> > trace->calltime = ret_stack->calltime;
> > + trace->rettime = 0;
> > trace->overrun = atomic_read(¤t->trace_overrun);
> > trace->depth = current->curr_ret_depth;
> > /*
> > @@ -792,7 +803,6 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe
> > return (unsigned long)panic;
> > }
> >
> > - trace.rettime = trace_clock_local();
> > if (fregs)
> > ftrace_regs_set_instruction_pointer(fregs, ret);
> >
> > @@ -808,6 +818,8 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe
> > continue;
> > if (gops == &fgraph_stub)
> > continue;
> > + if (!trace.rettime && !gops->skip_timestamp)
>
> In addition to the above, do you mind adding unlikely() here as well?
>
> > + trace.rettime = trace_clock_local();
> >
> > gops->retfunc(&trace, gops, fregs);
> > }
>
> [...]
--
Masami Hiramatsu (Google) <mhiramat@xxxxxxxxxx>
