From 37238abe3cb47b8daaa8706c9949f67b2a705cf1 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 3 Jun 2024 15:07:11 -0400 Subject: ftrace/function_graph: Pass fgraph_ops to function graph callbacks Pass the fgraph_ops structure to the function graph callbacks. This will allow callbacks to add a descriptor to a fgraph_ops private field that wil be added in the future and use it for the callbacks. This will be useful when more than one callback can be registered to the function graph tracer. Co-developed with Masami Hiramatsu: Link: https://lore.kernel.org/linux-trace-kernel/171509098588.162236.4787930115997357578.stgit@devnote2 Link: https://lore.kernel.org/linux-trace-kernel/20240603190822.035147698@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) --- kernel/trace/trace_functions_graph.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'kernel/trace/trace_functions_graph.c') diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index c35fbaab2a47..b7b142b65299 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -129,7 +129,8 @@ static inline int ftrace_graph_ignore_irqs(void) return in_hardirq(); } -int trace_graph_entry(struct ftrace_graph_ent *trace) +int trace_graph_entry(struct ftrace_graph_ent *trace, + struct fgraph_ops *gops) { struct trace_array *tr = graph_array; struct trace_array_cpu *data; @@ -238,7 +239,8 @@ void __trace_graph_return(struct trace_array *tr, trace_buffer_unlock_commit_nostack(buffer, event); } -void trace_graph_return(struct ftrace_graph_ret *trace) +void trace_graph_return(struct ftrace_graph_ret *trace, + struct fgraph_ops *gops) { struct trace_array *tr = graph_array; struct trace_array_cpu *data; @@ -275,7 +277,8 @@ void set_graph_array(struct trace_array *tr) smp_mb(); } -static void trace_graph_thresh_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); @@ -288,7 +291,7 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace) (trace->rettime - trace->calltime < tracing_thresh)) return; else - trace_graph_return(trace); + trace_graph_return(trace, gops); } static struct fgraph_ops funcgraph_thresh_ops = { -- cgit v1.2.3 From 26dda5631d1bb2f254f4c94aa87ee6c92a89cfdb Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 3 Jun 2024 15:07:12 -0400 Subject: ftrace: Allow function_graph tracer to be enabled in instances 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) --- include/linux/ftrace.h | 1 + kernel/trace/ftrace.c | 1 + kernel/trace/trace.h | 13 +++++++- kernel/trace/trace_functions.c | 8 +++++ kernel/trace/trace_functions_graph.c | 65 ++++++++++++++++++++++-------------- kernel/trace/trace_selftest.c | 4 +-- 6 files changed, 64 insertions(+), 28 deletions(-) (limited to 'kernel/trace/trace_functions_graph.c') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 4d817b85ac0d..fd656e6d6b7c 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1042,6 +1042,7 @@ extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, struct fgraph struct fgraph_ops { trace_func_graph_ent_t entryfunc; trace_func_graph_ret_t retfunc; + void *private; int idx; }; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index d18387c0642d..b85f00b0ffe7 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7327,6 +7327,7 @@ __init void ftrace_init_global_array_ops(struct trace_array *tr) tr->ops = &global_ops; tr->ops->private = tr; ftrace_init_trace_array(tr); + init_array_fgraph_ops(tr); } void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 2575ec243350..a5070f9b977b 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -397,6 +397,9 @@ struct trace_array { struct ftrace_ops *ops; struct trace_pid_list __rcu *function_pids; struct trace_pid_list __rcu *function_no_pids; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + struct fgraph_ops *gops; +#endif #ifdef CONFIG_DYNAMIC_FTRACE /* All of these are protected by the ftrace_lock */ struct list_head func_probes; @@ -681,7 +684,6 @@ void print_trace_header(struct seq_file *m, struct trace_iterator *iter); void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops); int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops); -void set_graph_array(struct trace_array *tr); void tracing_start_cmdline_record(void); void tracing_stop_cmdline_record(void); @@ -892,6 +894,9 @@ extern int __trace_graph_entry(struct trace_array *tr, extern void __trace_graph_return(struct trace_array *tr, struct ftrace_graph_ret *trace, unsigned int trace_ctx); +extern void init_array_fgraph_ops(struct trace_array *tr); +extern int allocate_fgraph_ops(struct trace_array *tr); +extern void free_fgraph_ops(struct trace_array *tr); #ifdef CONFIG_DYNAMIC_FTRACE extern struct ftrace_hash __rcu *ftrace_graph_hash; @@ -1004,6 +1009,12 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags) { return TRACE_TYPE_UNHANDLED; } +static inline void init_array_fgraph_ops(struct trace_array *tr) { } +static inline int allocate_fgraph_ops(struct trace_array *tr) +{ + return 0; +} +static inline void free_fgraph_ops(struct trace_array *tr) { } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ extern struct list_head ftrace_pids; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 9f1bfbe105e8..8e8da0d0ee52 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -80,6 +80,7 @@ void ftrace_free_ftrace_ops(struct trace_array *tr) int ftrace_create_function_files(struct trace_array *tr, struct dentry *parent) { + int ret; /* * The top level array uses the "global_ops", and the files are * created on boot up. @@ -90,6 +91,12 @@ int ftrace_create_function_files(struct trace_array *tr, if (!tr->ops) return -EINVAL; + ret = allocate_fgraph_ops(tr); + if (ret) { + kfree(tr->ops); + return ret; + } + ftrace_create_filter_files(tr->ops, parent); return 0; @@ -99,6 +106,7 @@ void ftrace_destroy_function_files(struct trace_array *tr) { ftrace_destroy_filter_files(tr->ops); ftrace_free_ftrace_ops(tr); + free_fgraph_ops(tr); } static ftrace_func_t select_trace_function(u32 flags_val) diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index b7b142b65299..9ccc904a7703 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -83,8 +83,6 @@ static struct tracer_flags tracer_flags = { .opts = trace_opts }; -static struct trace_array *graph_array; - /* * DURATION column is being also used to display IRQ signs, * following values are used by print_graph_irq and others @@ -132,7 +130,7 @@ static inline int ftrace_graph_ignore_irqs(void) int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops) { - struct trace_array *tr = graph_array; + struct trace_array *tr = gops->private; struct trace_array_cpu *data; unsigned long flags; unsigned int trace_ctx; @@ -242,7 +240,7 @@ void __trace_graph_return(struct trace_array *tr, void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops) { - struct trace_array *tr = graph_array; + struct trace_array *tr = gops->private; struct trace_array_cpu *data; unsigned long flags; unsigned int trace_ctx; @@ -268,15 +266,6 @@ void trace_graph_return(struct ftrace_graph_ret *trace, local_irq_restore(flags); } -void set_graph_array(struct trace_array *tr) -{ - graph_array = tr; - - /* Make graph_array visible before we start tracing */ - - smp_mb(); -} - static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops) { @@ -294,25 +283,53 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, trace_graph_return(trace, gops); } -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, }; +int allocate_fgraph_ops(struct trace_array *tr) +{ + struct fgraph_ops *gops; + + gops = kzalloc(sizeof(*gops), GFP_KERNEL); + if (!gops) + return -ENOMEM; + + gops->entryfunc = &trace_graph_entry; + gops->retfunc = &trace_graph_return; + + tr->gops = gops; + gops->private = tr; + return 0; +} + +void free_fgraph_ops(struct trace_array *tr) +{ + kfree(tr->gops); +} + +__init void init_array_fgraph_ops(struct trace_array *tr) +{ + tr->gops = &funcgraph_ops; + funcgraph_ops.private = tr; +} + static int graph_trace_init(struct trace_array *tr) { int ret; - set_graph_array(tr); + tr->gops->entryfunc = trace_graph_entry; + if (tracing_thresh) - ret = register_ftrace_graph(&funcgraph_thresh_ops); + tr->gops->retfunc = trace_graph_thresh_return; else - ret = register_ftrace_graph(&funcgraph_ops); + tr->gops->retfunc = trace_graph_return; + + /* Make gops functions are visible before we start tracing */ + smp_mb(); + + ret = register_ftrace_graph(tr->gops); if (ret) return ret; tracing_start_cmdline_record(); @@ -323,10 +340,7 @@ static int graph_trace_init(struct trace_array *tr) static void graph_trace_reset(struct trace_array *tr) { tracing_stop_cmdline_record(); - if (tracing_thresh) - unregister_ftrace_graph(&funcgraph_thresh_ops); - else - unregister_ftrace_graph(&funcgraph_ops); + unregister_ftrace_graph(tr->gops); } static int graph_trace_update_thresh(struct trace_array *tr) @@ -1365,6 +1379,7 @@ static struct tracer graph_trace __tracer_data = { .print_header = print_graph_headers, .flags = &tracer_flags, .set_flag = func_graph_set_flag, + .allow_instances = true, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_function_graph, #endif diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 56f269c0560a..f8f55fd79e53 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -813,7 +813,7 @@ trace_selftest_startup_function_graph(struct tracer *trace, * to detect and recover from possible hangs */ tracing_reset_online_cpus(&tr->array_buffer); - set_graph_array(tr); + fgraph_ops.private = tr; ret = register_ftrace_graph(&fgraph_ops); if (ret) { warn_failed_init_tracer(trace, ret); @@ -856,7 +856,7 @@ trace_selftest_startup_function_graph(struct tracer *trace, cond_resched(); tracing_reset_online_cpus(&tr->array_buffer); - set_graph_array(tr); + fgraph_ops.private = tr; /* * Some archs *cough*PowerPC*cough* add characters to the -- cgit v1.2.3 From c132be2c4fcc1150ad0791c2a85dd4c9ad0bd0c8 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 3 Jun 2024 15:07:16 -0400 Subject: function_graph: Have the instances use their own ftrace_ops for filtering 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) --- include/linux/ftrace.h | 1 + kernel/trace/fgraph.c | 81 +++++++++++++++++++++++------------- kernel/trace/ftrace.c | 2 +- kernel/trace/trace.h | 15 +++---- kernel/trace/trace_functions.c | 2 +- kernel/trace/trace_functions_graph.c | 8 +++- 6 files changed, 68 insertions(+), 41 deletions(-) (limited to 'kernel/trace/trace_functions_graph.c') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 63238a9a9270..8f865689e868 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1046,6 +1046,7 @@ extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, struct fgraph struct fgraph_ops { trace_func_graph_ent_t entryfunc; trace_func_graph_ret_t retfunc; + struct ftrace_ops ops; /* for the hash lists */ void *private; int idx; }; diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index e39042c40937..3ef6db53c0bf 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -18,15 +18,6 @@ #include "ftrace_internal.h" #include "trace.h" -#ifdef CONFIG_DYNAMIC_FTRACE -#define ASSIGN_OPS_HASH(opsname, val) \ - .func_hash = val, \ - .local_hash.regex_lock = __MUTEX_INITIALIZER(opsname.local_hash.regex_lock), \ - .subop_list = LIST_HEAD_INIT(opsname.subop_list), -#else -#define ASSIGN_OPS_HASH(opsname, val) -#endif - /* * FGRAPH_FRAME_SIZE: Size in bytes of the meta data on the shadow stack * FGRAPH_FRAME_OFFSET: Size in long words of the meta data frame @@ -156,6 +147,13 @@ get_bitmap_bits(struct task_struct *t, int offset) return (t->ret_stack[offset] >> FGRAPH_INDEX_SHIFT) & FGRAPH_INDEX_MASK; } +/* For BITMAP type: set the bits in the bitmap bitmask at @offset on ret_stack */ +static inline void +set_bitmap_bits(struct task_struct *t, int offset, unsigned long bitmap) +{ + t->ret_stack[offset] |= (bitmap << FGRAPH_INDEX_SHIFT); +} + /* Write the bitmap to the ret_stack at @offset (does index, offset and bitmask) */ static inline void set_bitmap(struct task_struct *t, int offset, unsigned long bitmap) @@ -382,7 +380,8 @@ int function_graph_enter(unsigned long ret, unsigned long func, if (gops == &fgraph_stub) continue; - if (gops->entryfunc(&trace, gops)) + if (ftrace_ops_test(&gops->ops, func, NULL) && + gops->entryfunc(&trace, gops)) bitmap |= BIT(i); } @@ -665,16 +664,28 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, static struct ftrace_ops graph_ops = { .func = ftrace_graph_func, - .flags = FTRACE_OPS_FL_INITIALIZED | - FTRACE_OPS_FL_PID | - FTRACE_OPS_GRAPH_STUB, + .flags = FTRACE_OPS_GRAPH_STUB, #ifdef FTRACE_GRAPH_TRAMP_ADDR .trampoline = FTRACE_GRAPH_TRAMP_ADDR, /* trampoline_size is only needed for dynamically allocated tramps */ #endif - ASSIGN_OPS_HASH(graph_ops, &global_ops.local_hash) }; +void fgraph_init_ops(struct ftrace_ops *dst_ops, + struct ftrace_ops *src_ops) +{ + dst_ops->flags = FTRACE_OPS_FL_PID | FTRACE_OPS_GRAPH_STUB; + +#ifdef CONFIG_DYNAMIC_FTRACE + if (src_ops) { + dst_ops->func_hash = &src_ops->local_hash; + mutex_init(&dst_ops->local_hash.regex_lock); + INIT_LIST_HEAD(&dst_ops->subop_list); + dst_ops->flags |= FTRACE_OPS_FL_INITIALIZED; + } +#endif +} + void ftrace_graph_sleep_time_control(bool enable) { fgraph_sleep_time = enable; @@ -877,6 +888,7 @@ static int start_graph_tracing(void) int register_ftrace_graph(struct fgraph_ops *gops) { + int command = 0; int ret = 0; int i; @@ -894,7 +906,7 @@ int register_ftrace_graph(struct fgraph_ops *gops) break; } if (i >= FGRAPH_ARRAY_SIZE) { - ret = -EBUSY; + ret = -ENOSPC; goto out; } @@ -908,18 +920,22 @@ int register_ftrace_graph(struct fgraph_ops *gops) if (ftrace_graph_active == 1) { register_pm_notifier(&ftrace_suspend_notifier); ret = start_graph_tracing(); - if (ret) { - ftrace_graph_active--; - goto out; - } + if (ret) + goto error; /* * Some archs just test to see if these are not * the default function */ ftrace_graph_return = return_run; ftrace_graph_entry = entry_run; + command = FTRACE_START_FUNC_RET; + } - ret = ftrace_startup(&graph_ops, FTRACE_START_FUNC_RET); + ret = ftrace_startup_subops(&graph_ops, &gops->ops, command); +error: + if (ret) { + fgraph_array[i] = &fgraph_stub; + ftrace_graph_active--; } out: mutex_unlock(&ftrace_lock); @@ -928,6 +944,7 @@ out: void unregister_ftrace_graph(struct fgraph_ops *gops) { + int command = 0; int i; mutex_lock(&ftrace_lock); @@ -935,25 +952,29 @@ void unregister_ftrace_graph(struct fgraph_ops *gops) if (unlikely(!ftrace_graph_active)) goto out; - for (i = 0; i < fgraph_array_cnt; i++) - if (gops == fgraph_array[i]) - break; - if (i >= fgraph_array_cnt) + if (unlikely(gops->idx < 0 || gops->idx >= fgraph_array_cnt)) goto out; - fgraph_array[i] = &fgraph_stub; - if (i + 1 == fgraph_array_cnt) { - for (; i >= 0; i--) - if (fgraph_array[i] != &fgraph_stub) - break; + WARN_ON_ONCE(fgraph_array[gops->idx] != gops); + + fgraph_array[gops->idx] = &fgraph_stub; + if (gops->idx + 1 == fgraph_array_cnt) { + i = gops->idx; + while (i >= 0 && fgraph_array[i] == &fgraph_stub) + i--; fgraph_array_cnt = i + 1; } ftrace_graph_active--; + + if (!ftrace_graph_active) + command = FTRACE_STOP_FUNC_RET; + + ftrace_shutdown_subops(&graph_ops, &gops->ops, command); + if (!ftrace_graph_active) { ftrace_graph_return = ftrace_stub_graph; ftrace_graph_entry = ftrace_graph_entry_stub; - ftrace_shutdown(&graph_ops, FTRACE_STOP_FUNC_RET); unregister_pm_notifier(&ftrace_suspend_notifier); unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index cbb91b0afcc8..58e0f4bc0241 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7811,7 +7811,7 @@ __init void ftrace_init_global_array_ops(struct trace_array *tr) tr->ops = &global_ops; tr->ops->private = tr; ftrace_init_trace_array(tr); - init_array_fgraph_ops(tr); + init_array_fgraph_ops(tr, tr->ops); } void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 9a70beb2cc46..f06b5ddd3580 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -894,8 +894,8 @@ extern int __trace_graph_entry(struct trace_array *tr, extern void __trace_graph_return(struct trace_array *tr, struct ftrace_graph_ret *trace, unsigned int trace_ctx); -extern void init_array_fgraph_ops(struct trace_array *tr); -extern int allocate_fgraph_ops(struct trace_array *tr); +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); #ifdef CONFIG_DYNAMIC_FTRACE @@ -1003,18 +1003,19 @@ static inline bool ftrace_graph_ignore_func(struct ftrace_graph_ent *trace) (fgraph_max_depth && trace->depth >= fgraph_max_depth); } +void fgraph_init_ops(struct ftrace_ops *dst_ops, + struct ftrace_ops *src_ops); + #else /* CONFIG_FUNCTION_GRAPH_TRACER */ static inline enum print_line_t print_graph_function_flags(struct trace_iterator *iter, u32 flags) { return TRACE_TYPE_UNHANDLED; } -static inline void init_array_fgraph_ops(struct trace_array *tr) { } -static inline int allocate_fgraph_ops(struct trace_array *tr) -{ - return 0; -} static inline void free_fgraph_ops(struct trace_array *tr) { } +/* ftrace_ops may not be defined */ +#define init_array_fgraph_ops(tr, ops) do { } while (0) +#define allocate_fgraph_ops(tr, ops) ({ 0; }) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ extern struct list_head ftrace_pids; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 8e8da0d0ee52..13bf2415245d 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -91,7 +91,7 @@ int ftrace_create_function_files(struct trace_array *tr, if (!tr->ops) return -EINVAL; - ret = allocate_fgraph_ops(tr); + ret = allocate_fgraph_ops(tr, tr->ops); if (ret) { kfree(tr->ops); return ret; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 9ccc904a7703..7f30652f0e97 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -288,7 +288,7 @@ static struct fgraph_ops funcgraph_ops = { .retfunc = &trace_graph_return, }; -int allocate_fgraph_ops(struct trace_array *tr) +int allocate_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops) { struct fgraph_ops *gops; @@ -301,6 +301,9 @@ int allocate_fgraph_ops(struct trace_array *tr) tr->gops = gops; gops->private = tr; + + fgraph_init_ops(&gops->ops, ops); + return 0; } @@ -309,10 +312,11 @@ void free_fgraph_ops(struct trace_array *tr) kfree(tr->gops); } -__init void init_array_fgraph_ops(struct trace_array *tr) +__init void init_array_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops) { tr->gops = &funcgraph_ops; funcgraph_ops.private = tr; + fgraph_init_ops(&tr->gops->ops, ops); } static int graph_trace_init(struct trace_array *tr) -- cgit v1.2.3 From 12117f3307b63f287756d7ec8cc4f11b94e1206a Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 3 Jun 2024 15:07:20 -0400 Subject: 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(-) (limited to 'kernel/trace/trace_functions_graph.c') 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; -- cgit v1.2.3 From b84214890a9bc56f0fe4ec4fc72f2307ed05096d Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 3 Jun 2024 15:07:22 -0400 Subject: function_graph: Move graph notrace bit to shadow stack global var The use of the task->trace_recursion for the logic used for the function graph no-trace 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/171509107907.162236.6564679266777519065.stgit@devnote2 Link: https://lore.kernel.org/linux-trace-kernel/20240603190823.796709456@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 | 7 ------- kernel/trace/trace.h | 9 +++++++++ kernel/trace/trace_functions_graph.c | 10 ++++++---- 3 files changed, 15 insertions(+), 11 deletions(-) (limited to 'kernel/trace/trace_functions_graph.c') diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index fdfb6f66718a..ae04054a1be3 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -44,13 +44,6 @@ enum { */ TRACE_IRQ_BIT, - /* - * To implement set_graph_notrace, if this bit is set, we ignore - * function graph tracing of called functions, until the return - * function is called to clear it. - */ - TRACE_GRAPH_NOTRACE_BIT, - /* Used to prevent recursion recording from recursing. */ TRACE_RECORD_RECURSION_BIT, }; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 82d879dc63ff..b37402e3f0c9 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -919,8 +919,17 @@ enum { TRACE_GRAPH_DEPTH_START_BIT, TRACE_GRAPH_DEPTH_END_BIT, + + /* + * To implement set_graph_notrace, if this bit is set, we ignore + * function graph tracing of called functions, until the return + * function is called to clear it. + */ + TRACE_GRAPH_NOTRACE_BIT, }; +#define TRACE_GRAPH_NOTRACE (1 << TRACE_GRAPH_NOTRACE_BIT) + static inline unsigned long ftrace_graph_depth(unsigned long *task_var) { return (*task_var >> TRACE_GRAPH_DEPTH_START_BIT) & 3; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 66cce73e94f8..13d0387ac6a6 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -130,6 +130,7 @@ static inline int ftrace_graph_ignore_irqs(void) int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops) { + unsigned long *task_var = fgraph_get_task_var(gops); struct trace_array *tr = gops->private; struct trace_array_cpu *data; unsigned long flags; @@ -138,7 +139,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace, int ret; int cpu; - if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) + if (*task_var & TRACE_GRAPH_NOTRACE) return 0; /* @@ -149,7 +150,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace, * returning from the function. */ if (ftrace_graph_notrace_addr(trace->func)) { - trace_recursion_set(TRACE_GRAPH_NOTRACE_BIT); + *task_var |= TRACE_GRAPH_NOTRACE_BIT; /* * Need to return 1 to have the return called * that will clear the NOTRACE bit. @@ -240,6 +241,7 @@ void __trace_graph_return(struct trace_array *tr, void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops) { + unsigned long *task_var = fgraph_get_task_var(gops); struct trace_array *tr = gops->private; struct trace_array_cpu *data; unsigned long flags; @@ -249,8 +251,8 @@ void trace_graph_return(struct ftrace_graph_ret *trace, ftrace_graph_addr_finish(gops, trace); - if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) { - trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT); + if (*task_var & TRACE_GRAPH_NOTRACE) { + *task_var &= ~TRACE_GRAPH_NOTRACE; return; } -- cgit v1.2.3