From 12117f3307b63f287756d7ec8cc4f11b94e1206a Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 3 Jun 2024 15:07:20 -0400 Subject: [PATCH] function_graph: Move set_graph_function tests to shadow stack global var The use of the task->trace_recursion for the logic used for the set_graph_function was a bit of an abuse of that variable. Now that there exists global vars that are per stack for registered graph traces, use that instead. Link: https://lore.kernel.org/linux-trace-kernel/171509105520.162236.10339831553995971290.stgit@devnote2 Link: https://lore.kernel.org/linux-trace-kernel/20240603190823.472955399@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) --- include/linux/trace_recursion.h | 5 +---- kernel/trace/trace.h | 32 ++++++++++++++++++---------- kernel/trace/trace_functions_graph.c | 6 +++--- kernel/trace/trace_irqsoff.c | 4 ++-- kernel/trace/trace_sched_wakeup.c | 4 ++-- 5 files changed, 29 insertions(+), 22 deletions(-) diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index 24ea8ac049b4..02e6afc6d7fe 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -44,9 +44,6 @@ enum { */ TRACE_IRQ_BIT, - /* Set if the function is in the set_graph_function file */ - TRACE_GRAPH_BIT, - /* * In the very unlikely case that an interrupt came in * at a start of graph tracing, and we want to trace @@ -60,7 +57,7 @@ enum { * that preempted a softirq start of a function that * preempted normal context!!!! Luckily, it can't be * greater than 3, so the next two bits are a mask - * of what the depth is when we set TRACE_GRAPH_BIT + * of what the depth is when we set TRACE_GRAPH_FL */ TRACE_GRAPH_DEPTH_START_BIT, diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f06b5ddd3580..73919129e57c 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -898,11 +898,16 @@ extern void init_array_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops extern int allocate_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops); extern void free_fgraph_ops(struct trace_array *tr); +enum { + TRACE_GRAPH_FL = 1, +}; + #ifdef CONFIG_DYNAMIC_FTRACE extern struct ftrace_hash __rcu *ftrace_graph_hash; extern struct ftrace_hash __rcu *ftrace_graph_notrace_hash; -static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) +static inline int +ftrace_graph_addr(unsigned long *task_var, struct ftrace_graph_ent *trace) { unsigned long addr = trace->func; int ret = 0; @@ -924,12 +929,11 @@ static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) } if (ftrace_lookup_ip(hash, addr)) { - /* * This needs to be cleared on the return functions * when the depth is zero. */ - trace_recursion_set(TRACE_GRAPH_BIT); + *task_var |= TRACE_GRAPH_FL; trace_recursion_set_depth(trace->depth); /* @@ -949,11 +953,14 @@ out: return ret; } -static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) +static inline void +ftrace_graph_addr_finish(struct fgraph_ops *gops, struct ftrace_graph_ret *trace) { - if (trace_recursion_test(TRACE_GRAPH_BIT) && + unsigned long *task_var = fgraph_get_task_var(gops); + + if ((*task_var & TRACE_GRAPH_FL) && trace->depth == trace_recursion_depth()) - trace_recursion_clear(TRACE_GRAPH_BIT); + *task_var &= ~TRACE_GRAPH_FL; } static inline int ftrace_graph_notrace_addr(unsigned long addr) @@ -979,7 +986,7 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr) return ret; } #else -static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) +static inline int ftrace_graph_addr(unsigned long *task_var, struct ftrace_graph_ent *trace) { return 1; } @@ -988,17 +995,20 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr) { return 0; } -static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) +static inline void ftrace_graph_addr_finish(struct fgraph_ops *gops, struct ftrace_graph_ret *trace) { } #endif /* CONFIG_DYNAMIC_FTRACE */ extern unsigned int fgraph_max_depth; -static inline bool ftrace_graph_ignore_func(struct ftrace_graph_ent *trace) +static inline bool +ftrace_graph_ignore_func(struct fgraph_ops *gops, struct ftrace_graph_ent *trace) { + unsigned long *task_var = fgraph_get_task_var(gops); + /* trace it when it is-nested-in or is a function enabled. */ - return !(trace_recursion_test(TRACE_GRAPH_BIT) || - ftrace_graph_addr(trace)) || + return !((*task_var & TRACE_GRAPH_FL) || + ftrace_graph_addr(task_var, trace)) || (trace->depth < 0) || (fgraph_max_depth && trace->depth >= fgraph_max_depth); } diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 7f30652f0e97..66cce73e94f8 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -160,7 +160,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace, if (!ftrace_trace_task(tr)) return 0; - if (ftrace_graph_ignore_func(trace)) + if (ftrace_graph_ignore_func(gops, trace)) return 0; if (ftrace_graph_ignore_irqs()) @@ -247,7 +247,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace, long disabled; int cpu; - ftrace_graph_addr_finish(trace); + ftrace_graph_addr_finish(gops, trace); if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) { trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT); @@ -269,7 +269,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace, static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops) { - ftrace_graph_addr_finish(trace); + ftrace_graph_addr_finish(gops, trace); if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) { trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 5478f4c4f708..fce064e20570 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -184,7 +184,7 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace, unsigned int trace_ctx; int ret; - if (ftrace_graph_ignore_func(trace)) + if (ftrace_graph_ignore_func(gops, trace)) return 0; /* * Do not trace a function if it's filtered by set_graph_notrace. @@ -214,7 +214,7 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace, unsigned long flags; unsigned int trace_ctx; - ftrace_graph_addr_finish(trace); + ftrace_graph_addr_finish(gops, trace); if (!func_prolog_dec(tr, &data, &flags)) return; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 49bcc812652c..130ca7e7787e 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -120,7 +120,7 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace, unsigned int trace_ctx; int ret = 0; - if (ftrace_graph_ignore_func(trace)) + if (ftrace_graph_ignore_func(gops, trace)) return 0; /* * Do not trace a function if it's filtered by set_graph_notrace. @@ -149,7 +149,7 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace, struct trace_array_cpu *data; unsigned int trace_ctx; - ftrace_graph_addr_finish(trace); + ftrace_graph_addr_finish(gops, trace); if (!func_prolog_preempt_disable(tr, &data, &trace_ctx)) return;