From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/kernel/trace/trace_functions_graph.c | 403 ++++++++++++---------------------------------------------
1 files changed, 88 insertions(+), 315 deletions(-)
diff --git a/kernel/kernel/trace/trace_functions_graph.c b/kernel/kernel/trace/trace_functions_graph.c
index 086af4f..60d6627 100644
--- a/kernel/kernel/trace/trace_functions_graph.c
+++ b/kernel/kernel/trace/trace_functions_graph.c
@@ -16,33 +16,6 @@
#include "trace.h"
#include "trace_output.h"
-static bool kill_ftrace_graph;
-
-/**
- * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called
- *
- * ftrace_graph_stop() is called when a severe error is detected in
- * the function graph tracing. This function is called by the critical
- * paths of function graph to keep those paths from doing any more harm.
- */
-bool ftrace_graph_is_dead(void)
-{
- return kill_ftrace_graph;
-}
-
-/**
- * ftrace_graph_stop - set to permanently disable function graph tracincg
- *
- * In case of an error int function graph tracing, this is called
- * to try to keep function graph tracing from causing any more harm.
- * Usually this is pretty severe and this is called to try to at least
- * get a warning out to the user.
- */
-void ftrace_graph_stop(void)
-{
- kill_ftrace_graph = true;
-}
-
/* When set, irq functions will be ignored */
static int ftrace_graph_skip_irqs;
@@ -87,8 +60,12 @@
{ TRACER_OPT(funcgraph-tail, TRACE_GRAPH_PRINT_TAIL) },
/* Include sleep time (scheduled out) between entry and return */
{ TRACER_OPT(sleep-time, TRACE_GRAPH_SLEEP_TIME) },
+
+#ifdef CONFIG_FUNCTION_PROFILER
/* Include time within nested functions */
{ TRACER_OPT(graph-time, TRACE_GRAPH_GRAPH_TIME) },
+#endif
+
{ } /* Empty entry */
};
@@ -117,258 +94,6 @@
print_graph_duration(struct trace_array *tr, unsigned long long duration,
struct trace_seq *s, u32 flags);
-/* Add a function return address to the trace stack on thread info.*/
-static int
-ftrace_push_return_trace(unsigned long ret, unsigned long func,
- unsigned long frame_pointer, unsigned long *retp)
-{
- unsigned long long calltime;
- int index;
-
- if (unlikely(ftrace_graph_is_dead()))
- return -EBUSY;
-
- if (!current->ret_stack)
- return -EBUSY;
-
- /*
- * We must make sure the ret_stack is tested before we read
- * anything else.
- */
- smp_rmb();
-
- /* The return trace stack is full */
- if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
- atomic_inc(¤t->trace_overrun);
- return -EBUSY;
- }
-
- /*
- * The curr_ret_stack is an index to ftrace return stack of
- * current task. Its value should be in [0, FTRACE_RETFUNC_
- * DEPTH) when the function graph tracer is used. To support
- * filtering out specific functions, it makes the index
- * negative by subtracting huge value (FTRACE_NOTRACE_DEPTH)
- * so when it sees a negative index the ftrace will ignore
- * the record. And the index gets recovered when returning
- * from the filtered function by adding the FTRACE_NOTRACE_
- * DEPTH and then it'll continue to record functions normally.
- *
- * The curr_ret_stack is initialized to -1 and get increased
- * in this function. So it can be less than -1 only if it was
- * filtered out via ftrace_graph_notrace_addr() which can be
- * set from set_graph_notrace file in tracefs by user.
- */
- if (current->curr_ret_stack < -1)
- return -EBUSY;
-
- calltime = trace_clock_local();
-
- index = ++current->curr_ret_stack;
- if (ftrace_graph_notrace_addr(func))
- current->curr_ret_stack -= FTRACE_NOTRACE_DEPTH;
- barrier();
- current->ret_stack[index].ret = ret;
- current->ret_stack[index].func = func;
- current->ret_stack[index].calltime = calltime;
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
- current->ret_stack[index].fp = frame_pointer;
-#endif
-#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
- current->ret_stack[index].retp = retp;
-#endif
- return 0;
-}
-
-int function_graph_enter(unsigned long ret, unsigned long func,
- unsigned long frame_pointer, unsigned long *retp)
-{
- struct ftrace_graph_ent trace;
-
- trace.func = func;
- trace.depth = ++current->curr_ret_depth;
-
- if (ftrace_push_return_trace(ret, func,
- frame_pointer, retp))
- goto out;
-
- /* Only trace if the calling function expects to */
- if (!ftrace_graph_entry(&trace))
- goto out_ret;
-
- return 0;
- out_ret:
- current->curr_ret_stack--;
- out:
- current->curr_ret_depth--;
- return -EBUSY;
-}
-
-/* Retrieve a function return address to the trace stack on thread info.*/
-static void
-ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
- unsigned long frame_pointer)
-{
- int index;
-
- index = current->curr_ret_stack;
-
- /*
- * A negative index here means that it's just returned from a
- * notrace'd function. Recover index to get an original
- * return address. See ftrace_push_return_trace().
- *
- * TODO: Need to check whether the stack gets corrupted.
- */
- if (index < 0)
- index += FTRACE_NOTRACE_DEPTH;
-
- if (unlikely(index < 0 || index >= FTRACE_RETFUNC_DEPTH)) {
- ftrace_graph_stop();
- WARN_ON(1);
- /* Might as well panic, otherwise we have no where to go */
- *ret = (unsigned long)panic;
- return;
- }
-
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
- /*
- * The arch may choose to record the frame pointer used
- * and check it here to make sure that it is what we expect it
- * to be. If gcc does not set the place holder of the return
- * address in the frame pointer, and does a copy instead, then
- * the function graph trace will fail. This test detects this
- * case.
- *
- * Currently, x86_32 with optimize for size (-Os) makes the latest
- * gcc do the above.
- *
- * Note, -mfentry does not use frame pointers, and this test
- * is not needed if CC_USING_FENTRY is set.
- */
- if (unlikely(current->ret_stack[index].fp != frame_pointer)) {
- ftrace_graph_stop();
- WARN(1, "Bad frame pointer: expected %lx, received %lx\n"
- " from func %ps return to %lx\n",
- current->ret_stack[index].fp,
- frame_pointer,
- (void *)current->ret_stack[index].func,
- current->ret_stack[index].ret);
- *ret = (unsigned long)panic;
- return;
- }
-#endif
-
- *ret = current->ret_stack[index].ret;
- trace->func = current->ret_stack[index].func;
- trace->calltime = current->ret_stack[index].calltime;
- trace->overrun = atomic_read(¤t->trace_overrun);
- trace->depth = current->curr_ret_depth--;
- /*
- * We still want to trace interrupts coming in if
- * max_depth is set to 1. Make sure the decrement is
- * seen before ftrace_graph_return.
- */
- barrier();
-}
-
-/*
- * Send the trace to the ring-buffer.
- * @return the original return address.
- */
-unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
-{
- struct ftrace_graph_ret trace;
- unsigned long ret;
-
- ftrace_pop_return_trace(&trace, &ret, frame_pointer);
- trace.rettime = trace_clock_local();
- ftrace_graph_return(&trace);
- /*
- * The ftrace_graph_return() may still access the current
- * ret_stack structure, we need to make sure the update of
- * curr_ret_stack is after that.
- */
- barrier();
- current->curr_ret_stack--;
- /*
- * The curr_ret_stack can be less than -1 only if it was
- * filtered out and it's about to return from the function.
- * Recover the index and continue to trace normal functions.
- */
- if (current->curr_ret_stack < -1) {
- current->curr_ret_stack += FTRACE_NOTRACE_DEPTH;
- return ret;
- }
-
- if (unlikely(!ret)) {
- ftrace_graph_stop();
- WARN_ON(1);
- /* Might as well panic. What else to do? */
- ret = (unsigned long)panic;
- }
-
- return ret;
-}
-
-/**
- * ftrace_graph_ret_addr - convert a potentially modified stack return address
- * to its original value
- *
- * This function can be called by stack unwinding code to convert a found stack
- * return address ('ret') to its original value, in case the function graph
- * tracer has modified it to be 'return_to_handler'. If the address hasn't
- * been modified, the unchanged value of 'ret' is returned.
- *
- * 'idx' is a state variable which should be initialized by the caller to zero
- * before the first call.
- *
- * 'retp' is a pointer to the return address on the stack. It's ignored if
- * the arch doesn't have HAVE_FUNCTION_GRAPH_RET_ADDR_PTR defined.
- */
-#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
-unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
- unsigned long ret, unsigned long *retp)
-{
- int index = task->curr_ret_stack;
- int i;
-
- if (ret != (unsigned long)return_to_handler)
- return ret;
-
- if (index < -1)
- index += FTRACE_NOTRACE_DEPTH;
-
- if (index < 0)
- return ret;
-
- for (i = 0; i <= index; i++)
- if (task->ret_stack[i].retp == retp)
- return task->ret_stack[i].ret;
-
- return ret;
-}
-#else /* !HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */
-unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
- unsigned long ret, unsigned long *retp)
-{
- int task_idx;
-
- if (ret != (unsigned long)return_to_handler)
- return ret;
-
- task_idx = task->curr_ret_stack;
-
- if (!task->ret_stack || task_idx < *idx)
- return ret;
-
- task_idx -= *idx;
- (*idx)++;
-
- return task->ret_stack[task_idx].ret;
-}
-#endif /* HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */
-
int __trace_graph_entry(struct trace_array *tr,
struct ftrace_graph_ent *trace,
unsigned long flags,
@@ -376,7 +101,7 @@
{
struct trace_event_call *call = &event_funcgraph_entry;
struct ring_buffer_event *event;
- struct ring_buffer *buffer = tr->trace_buffer.buffer;
+ struct trace_buffer *buffer = tr->array_buffer.buffer;
struct ftrace_graph_ent_entry *entry;
event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
@@ -409,6 +134,25 @@
int cpu;
int pc;
+ if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT))
+ return 0;
+
+ /*
+ * Do not trace a function if it's filtered by set_graph_notrace.
+ * Make the index of ret stack negative to indicate that it should
+ * ignore further functions. But it needs its own ret stack entry
+ * to recover the original index in order to continue tracing after
+ * returning from the function.
+ */
+ if (ftrace_graph_notrace_addr(trace->func)) {
+ trace_recursion_set(TRACE_GRAPH_NOTRACE_BIT);
+ /*
+ * Need to return 1 to have the return called
+ * that will clear the NOTRACE bit.
+ */
+ return 1;
+ }
+
if (!ftrace_trace_task(tr))
return 0;
@@ -419,16 +163,6 @@
return 0;
/*
- * Do not trace a function if it's filtered by set_graph_notrace.
- * Make the index of ret stack negative to indicate that it should
- * ignore further functions. But it needs its own ret stack entry
- * to recover the original index in order to continue tracing after
- * returning from the function.
- */
- if (ftrace_graph_notrace_addr(trace->func))
- return 1;
-
- /*
* Stop here if tracing_threshold is set. We only write function return
* events to the ring buffer.
*/
@@ -437,7 +171,7 @@
local_irq_save(flags);
cpu = raw_smp_processor_id();
- data = per_cpu_ptr(tr->trace_buffer.data, cpu);
+ data = per_cpu_ptr(tr->array_buffer.data, cpu);
disabled = atomic_inc_return(&data->disabled);
if (likely(disabled == 1)) {
pc = preempt_count();
@@ -487,7 +221,7 @@
{
struct trace_event_call *call = &event_funcgraph_exit;
struct ring_buffer_event *event;
- struct ring_buffer *buffer = tr->trace_buffer.buffer;
+ struct trace_buffer *buffer = tr->array_buffer.buffer;
struct ftrace_graph_ret_entry *entry;
event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
@@ -511,9 +245,14 @@
ftrace_graph_addr_finish(trace);
+ if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) {
+ trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT);
+ return;
+ }
+
local_irq_save(flags);
cpu = raw_smp_processor_id();
- data = per_cpu_ptr(tr->trace_buffer.data, cpu);
+ data = per_cpu_ptr(tr->array_buffer.data, cpu);
disabled = atomic_inc_return(&data->disabled);
if (likely(disabled == 1)) {
pc = preempt_count();
@@ -536,6 +275,11 @@
{
ftrace_graph_addr_finish(trace);
+ if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) {
+ trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT);
+ return;
+ }
+
if (tracing_thresh &&
(trace->rettime - trace->calltime < tracing_thresh))
return;
@@ -543,17 +287,25 @@
trace_graph_return(trace);
}
+static struct fgraph_ops funcgraph_thresh_ops = {
+ .entryfunc = &trace_graph_entry,
+ .retfunc = &trace_graph_thresh_return,
+};
+
+static struct fgraph_ops funcgraph_ops = {
+ .entryfunc = &trace_graph_entry,
+ .retfunc = &trace_graph_return,
+};
+
static int graph_trace_init(struct trace_array *tr)
{
int ret;
set_graph_array(tr);
if (tracing_thresh)
- ret = register_ftrace_graph(&trace_graph_thresh_return,
- &trace_graph_entry);
+ ret = register_ftrace_graph(&funcgraph_thresh_ops);
else
- ret = register_ftrace_graph(&trace_graph_return,
- &trace_graph_entry);
+ ret = register_ftrace_graph(&funcgraph_ops);
if (ret)
return ret;
tracing_start_cmdline_record();
@@ -564,7 +316,10 @@
static void graph_trace_reset(struct trace_array *tr)
{
tracing_stop_cmdline_record();
- unregister_ftrace_graph();
+ if (tracing_thresh)
+ unregister_ftrace_graph(&funcgraph_thresh_ops);
+ else
+ unregister_ftrace_graph(&funcgraph_ops);
}
static int graph_trace_update_thresh(struct trace_array *tr)
@@ -622,6 +377,7 @@
{
trace_seq_putc(s, ' ');
trace_print_lat_fmt(s, entry);
+ trace_seq_puts(s, " | ");
}
/* If the pid changed since the last trace, output this event */
@@ -688,9 +444,9 @@
* We need to consume the current entry to see
* the next one.
*/
- ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu,
+ ring_buffer_consume(iter->array_buffer->buffer, iter->cpu,
NULL, NULL);
- event = ring_buffer_peek(iter->trace_buffer->buffer, iter->cpu,
+ event = ring_buffer_peek(iter->array_buffer->buffer, iter->cpu,
NULL, NULL);
}
@@ -726,7 +482,7 @@
/* this is a leaf, now advance the iterator */
if (ring_iter)
- ring_buffer_read(ring_iter, NULL);
+ ring_buffer_iter_advance(ring_iter);
return next;
}
@@ -740,6 +496,17 @@
trace_seq_printf(s, "%5lu.%06lu | ",
(unsigned long)t, usecs_rem);
+}
+
+static void
+print_graph_rel_time(struct trace_iterator *iter, struct trace_seq *s)
+{
+ unsigned long long usecs;
+
+ usecs = iter->ts - iter->array_buffer->time_start;
+ do_div(usecs, NSEC_PER_USEC);
+
+ trace_seq_printf(s, "%9llu us | ", usecs);
}
static void
@@ -758,6 +525,10 @@
/* Absolute time */
if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
print_graph_abs_time(iter->ts, s);
+
+ /* Relative time */
+ if (flags & TRACE_GRAPH_PRINT_REL_TIME)
+ print_graph_rel_time(iter, s);
/* Cpu */
if (flags & TRACE_GRAPH_PRINT_CPU)
@@ -874,10 +645,6 @@
cpu_data = per_cpu_ptr(data->cpu_data, cpu);
- /* If a graph tracer ignored set_graph_notrace */
- if (call->depth < -1)
- call->depth += FTRACE_NOTRACE_DEPTH;
-
/*
* Comments display at + 1 to depth. Since
* this is a leaf function, keep the comments
@@ -919,10 +686,6 @@
if (data) {
struct fgraph_cpu_data *cpu_data;
int cpu = iter->cpu;
-
- /* If a graph tracer ignored set_graph_notrace */
- if (call->depth < -1)
- call->depth += FTRACE_NOTRACE_DEPTH;
cpu_data = per_cpu_ptr(data->cpu_data, cpu);
cpu_data->depth = call->depth;
@@ -974,6 +737,10 @@
/* Absolute time */
if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
print_graph_abs_time(iter->ts, s);
+
+ /* Relative time */
+ if (flags & TRACE_GRAPH_PRINT_REL_TIME)
+ print_graph_rel_time(iter, s);
/* Cpu */
if (flags & TRACE_GRAPH_PRINT_CPU)
@@ -1351,6 +1118,8 @@
if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
size += 16;
+ if (flags & TRACE_GRAPH_PRINT_REL_TIME)
+ size += 16;
if (flags & TRACE_GRAPH_PRINT_CPU)
size += 4;
if (flags & TRACE_GRAPH_PRINT_PROC)
@@ -1375,12 +1144,14 @@
seq_putc(s, '#');
if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
seq_puts(s, " TIME ");
+ if (flags & TRACE_GRAPH_PRINT_REL_TIME)
+ seq_puts(s, " REL TIME ");
if (flags & TRACE_GRAPH_PRINT_CPU)
seq_puts(s, " CPU");
if (flags & TRACE_GRAPH_PRINT_PROC)
seq_puts(s, " TASK/PID ");
if (lat)
- seq_puts(s, "||||");
+ seq_puts(s, "|||| ");
if (flags & TRACE_GRAPH_PRINT_DURATION)
seq_puts(s, " DURATION ");
seq_puts(s, " FUNCTION CALLS\n");
@@ -1389,12 +1160,14 @@
seq_putc(s, '#');
if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
seq_puts(s, " | ");
+ if (flags & TRACE_GRAPH_PRINT_REL_TIME)
+ seq_puts(s, " | ");
if (flags & TRACE_GRAPH_PRINT_CPU)
seq_puts(s, " | ");
if (flags & TRACE_GRAPH_PRINT_PROC)
seq_puts(s, " | | ");
if (lat)
- seq_puts(s, "||||");
+ seq_puts(s, "|||| ");
if (flags & TRACE_GRAPH_PRINT_DURATION)
seq_puts(s, " | | ");
seq_puts(s, " | | | |\n");
@@ -1563,13 +1336,13 @@
static __init int init_graph_tracefs(void)
{
- struct dentry *d_tracer;
+ int ret;
- d_tracer = tracing_init_dentry();
- if (IS_ERR(d_tracer))
+ ret = tracing_init_dentry();
+ if (ret)
return 0;
- trace_create_file("max_graph_depth", 0644, d_tracer,
+ trace_create_file("max_graph_depth", 0644, NULL,
NULL, &graph_depth_fops);
return 0;
--
Gitblit v1.6.2