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 <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Florent Revest <revest@chromium.org>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: bpf <bpf@vger.kernel.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alan Maguire <alan.maguire@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Guo Ren <guoren@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index 24ea8ac049b40877e71094b43b839e15a1b8d212..02e6afc6d7fe5845b06496a1796cb0cfc7c7b084 100644 (file)
--- 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 f06b5ddd3580505cc08e0f4f6aa7c970b3ad90d2..73919129e57c76f69f9fe3e717831a4066fe94ed 100644 (file)
--- 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 7f30652f0e97d774011d3ccb01cfbfb1fa9b4627..66cce73e94f8966702282b524045811328887da6 100644 (file)
--- 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 5478f4c4f7081266280a45296f19feb9b6545467..fce064e205706f50e3b64f345b53c0f23bb226ee 100644 (file)
--- 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 49bcc812652c71735eee9fc5661e4f5efa2eb8ee..130ca7e7787efb4df7e14f528d0023bd1d12e2cd 100644 (file)
--- 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;