user/sven/linux.git/kernel/trace/trace_functions.c, branch v6.15.1

ftrace: Fix preemption accounting for stacktrace filter command

2025-05-14T17:53:23Z

The preemption count of the stacktrace filter command to trace ksys_read is consistently incorrect: $ echo ksys_read:stacktrace > set_ftrace_filter <...>-453 [004] ...1. 38.308956: => ksys_read => do_syscall_64 => entry_SYSCALL_64_after_hwframe The root cause is that the trace framework disables preemption when invoking the filter command callback in function_trace_probe_call: preempt_disable_notrace(); probe_ops->func(ip, parent_ip, probe_opsbe->tr, probe_ops, probe->data); preempt_enable_notrace(); Use tracing_gen_ctx_dec() to account for the preempt_disable_notrace(), which will output the correct preemption count: $ echo ksys_read:stacktrace > set_ftrace_filter <...>-410 [006] ..... 31.420396: => ksys_read => do_syscall_64 => entry_SYSCALL_64_after_hwframe Cc: stable@vger.kernel.org Fixes: 36590c50b2d07 ("tracing: Merge irqflags + preempt counter.") Link: https://lore.kernel.org/20250512094246.1167956-2-dolinux.peng@gmail.com Signed-off-by: pengdonglin Signed-off-by: Steven Rostedt (Google)

ftrace: Add arguments to function tracer

2025-03-04T16:27:24Z

Wire up the code to print function arguments in the function tracer. This functionality can be enabled/disabled during runtime with options/func-args. ping-689 [004] b.... 77.170220: dummy_xmit(skb = 0x82904800, dev = 0x882d0000) <-dev_hard_start_xmit Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Guo Ren Cc: Donglin Peng Cc: Zheng Yejian Link: https://lore.kernel.org/20250227185823.154996172@goodmis.org Reviewed-by: Masami Hiramatsu (Google) Co-developed-by: Steven Rostedt (Google) Signed-off-by: Sven Schnelle Signed-off-by: Steven Rostedt (Google)

ftrace: Correct preemption accounting for function tracing.

2025-02-21T14:36:12Z

The function tracer should record the preemption level at the point when the function is invoked. If the tracing subsystem decrement the preemption counter it needs to correct this before feeding the data into the trace buffer. This was broken in the commit cited below while shifting the preempt-disabled section. Use tracing_gen_ctx_dec() which properly subtracts one from the preemption counter on a preemptible kernel. Cc: stable@vger.kernel.org Cc: Wander Lairson Costa Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Thomas Gleixner Link: https://lore.kernel.org/20250220140749.pfw8qoNZ@linutronix.de Fixes: ce5e48036c9e7 ("ftrace: disable preemption when recursion locked") Signed-off-by: Sebastian Andrzej Siewior Tested-by: Wander Lairson Costa Signed-off-by: Steven Rostedt (Google)

ftrace: Do not find "true_parent" if HAVE_DYNAMIC_FTRACE_WITH_ARGS is not set

2024-12-16T22:22:26Z

When function tracing and function graph tracing are both enabled (in different instances) the "parent" of some of the function tracing events is "return_to_handler" which is the trampoline used by function graph tracing. To fix this, ftrace_get_true_parent_ip() was introduced that returns the "true" parent ip instead of the trampoline. To do this, the ftrace_regs_get_stack_pointer() is used, which uses kernel_stack_pointer(). The problem is that microblaze does not implement kerenl_stack_pointer() so when function graph tracing is enabled, the build fails. But microblaze also does not enabled HAVE_DYNAMIC_FTRACE_WITH_ARGS. That option has to be enabled by the architecture to reliably get the values from the fregs parameter passed in. When that config is not set, the architecture can also pass in NULL, which is not tested for in that function and could cause the kernel to crash. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Mark Rutland Cc: Al Viro Cc: Michal Simek Cc: Jeff Xie Link: https://lore.kernel.org/20241216164633.6df18e87@gandalf.local.home Fixes: 60b1f578b578 ("ftrace: Get the true parent ip for function tracer") Reported-by: Al Viro Signed-off-by: Steven Rostedt (Google)

ftrace: Get the true parent ip for function tracer

2024-11-18T17:02:43Z

When using both function tracer and function graph simultaneously, it is found that function tracer sometimes captures a fake parent ip (return_to_handler) instead of the true parent ip. This issue is easy to reproduce. Below are my reproduction steps: jeff-labs:~/bin # ./trace-net.sh jeff-labs:~/bin # cat /sys/kernel/debug/tracing/instances/foo/trace | grep return_to_handler trace-net.sh-405 [001] ...2. 31.859501: avc_has_perm+0x4/0x190 <-return_to_handler+0x0/0x40 trace-net.sh-405 [001] ...2. 31.859503: simple_setattr+0x4/0x70 <-return_to_handler+0x0/0x40 trace-net.sh-405 [001] ...2. 31.859503: truncate_pagecache+0x4/0x60 <-return_to_handler+0x0/0x40 trace-net.sh-405 [001] ...2. 31.859505: unmap_mapping_range+0x4/0x140 <-return_to_handler+0x0/0x40 trace-net.sh-405 [001] ...3. 31.859508: _raw_spin_unlock+0x4/0x30 <-return_to_handler+0x0/0x40 [...] The following is my simple trace script: jeff-labs:~/bin # cat ./trace-net.sh TRACE_PATH="/sys/kernel/tracing" set_events() { echo 1 > $1/events/net/enable echo 1 > $1/events/tcp/enable echo 1 > $1/events/sock/enable echo 1 > $1/events/napi/enable echo 1 > $1/events/fib/enable echo 1 > $1/events/neigh/enable } set_events ${TRACE_PATH} echo 1 > ${TRACE_PATH}/options/sym-offset echo 1 > ${TRACE_PATH}/options/funcgraph-tail echo 1 > ${TRACE_PATH}/options/funcgraph-proc echo 1 > ${TRACE_PATH}/options/funcgraph-abstime echo 'tcp_orphan*' > ${TRACE_PATH}/set_ftrace_notrace echo function_graph > ${TRACE_PATH}/current_tracer INSTANCE_FOO=${TRACE_PATH}/instances/foo if [ ! -e $INSTANCE_FOO ]; then mkdir ${INSTANCE_FOO} fi set_events ${INSTANCE_FOO} echo 1 > ${INSTANCE_FOO}/options/sym-offset echo 'tcp_orphan*' > ${INSTANCE_FOO}/set_ftrace_notrace echo function > ${INSTANCE_FOO}/current_tracer echo 1 > ${TRACE_PATH}/tracing_on echo 1 > ${INSTANCE_FOO}/tracing_on echo > ${TRACE_PATH}/trace echo > ${INSTANCE_FOO}/trace Link: https://lore.kernel.org/20241008033159.22459-1-jeff.xie@linux.dev Acked-by: Masami Hiramatsu (Google) Signed-off-by: Jeff Xie Signed-off-by: Steven Rostedt (Google)

ftrace: Use this_cpu_ptr() instead of per_cpu_ptr(smp_processor_id())

2024-10-08T19:24:22Z

Use this_cpu_ptr() instead of open coding the equivalent in various ftrace functions. Cc: Mathieu Desnoyers Cc: Masami Hiramatsu Link: https://lore.kernel.org/87y14t6ofi.wl-me@linux.beauty Signed-off-by: Li Chen Signed-off-by: Steven Rostedt (Google)

ftrace: Hide one more entry in stack trace when ftrace_pid is enabled

2024-06-06T19:22:18Z

On setting set_ftrace_pid, a extra entry generated by ftrace_pid_func() is shown on stack trace(CONFIG_UNWINDER_FRAME_POINTER=y). [004] ..... 68.459382: => 0xffffffffa00090af => ksys_read => __x64_sys_read => x64_sys_call => do_syscall_64 => entry_SYSCALL_64_after_hwframe To resolve this issue, increment skip count in function_stack_trace_call() if pids are set. Link: https://lore.kernel.org/linux-trace-kernel/20240528032604.6813-3-tatsuya.s2862@gmail.com Signed-off-by: Tatsuya S [ Rebased to current tree ] Signed-off-by: Steven Rostedt (Google)

function_graph: Have the instances use their own ftrace_ops for filtering

2024-06-04T14:36:52Z

Allow for instances to have their own ftrace_ops part of the fgraph_ops that makes the funtion_graph tracer filter on the set_ftrace_filter file of the instance and not the top instance. This uses the new ftrace_startup_subops(), by using graph_ops as the "manager ops" that defines the callback function and adds the functions defined by the filters of the ops for each trace instance. The callback defined by the manager ops will call the registered fgraph ops that were added to the fgraph_array. Co-developed with Masami Hiramatsu: Link: https://lore.kernel.org/linux-trace-kernel/171509102088.162236.15758883237657317789.stgit@devnote2 Link: https://lore.kernel.org/linux-trace-kernel/20240603190822.832946261@goodmis.org Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Sven Schnelle Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Daniel Borkmann Cc: Alan Maguire Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Guo Ren Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google)

ftrace: Allow function_graph tracer to be enabled in instances

2024-06-04T14:36:28Z

Now that function graph tracing can handle more than one user, allow it to be enabled in the ftrace instances. Note, the filtering of the functions is still joined by the top level set_ftrace_filter and friends, as well as the graph and nograph files. Co-developed with Masami Hiramatsu: Link: https://lore.kernel.org/linux-trace-kernel/171509099743.162236.1699959255446248163.stgit@devnote2 Link: https://lore.kernel.org/linux-trace-kernel/20240603190822.190630762@goodmis.org Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Alexei Starovoitov Cc: Florent Revest Cc: Martin KaFai Lau Cc: bpf Cc: Sven Schnelle Cc: Alexei Starovoitov Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Daniel Borkmann Cc: Alan Maguire Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Guo Ren Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google)

ftrace: disable preemption when recursion locked

2021-10-27T15:21:49Z

As the documentation explained, ftrace_test_recursion_trylock() and ftrace_test_recursion_unlock() were supposed to disable and enable preemption properly, however currently this work is done outside of the function, which could be missing by mistake. And since the internal using of trace_test_and_set_recursion() and trace_clear_recursion() also require preemption disabled, we can just merge the logical. This patch will make sure the preemption has been disabled when trace_test_and_set_recursion() return bit >= 0, and trace_clear_recursion() will enable the preemption if previously enabled. Link: https://lkml.kernel.org/r/13bde807-779c-aa4c-0672-20515ae365ea@linux.alibaba.com CC: Petr Mladek Cc: Guo Ren Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Thomas Gleixner Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Josh Poimboeuf Cc: Jiri Kosina Cc: Joe Lawrence Cc: Masami Hiramatsu Cc: Nicholas Piggin Cc: Jisheng Zhang CC: Steven Rostedt CC: Miroslav Benes Reported-by: Abaci Suggested-by: Peter Zijlstra Signed-off-by: Michael Wang [ Removed extra line in comment - SDR ] Signed-off-by: Steven Rostedt (VMware)