From 2f5f6ad9390c1ebbf738d130dbfe80b60eaa167e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 8 Aug 2011 16:57:47 -0400 Subject: ftrace: Pass ftrace_ops as third parameter to function trace callback Currently the function trace callback receives only the ip and parent_ip of the function that it traced. It would be more powerful to also return the ops that registered the function as well. This allows the same function to act differently depending on what ftrace_ops registered it. Link: http://lkml.kernel.org/r/20120612225424.267254552@goodmis.org Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 101 ++++++++++++++++++++++++++------------ kernel/trace/trace_event_perf.c | 3 +- kernel/trace/trace_events.c | 3 +- kernel/trace/trace_functions.c | 9 ++-- kernel/trace/trace_irqsoff.c | 3 +- kernel/trace/trace_sched_wakeup.c | 2 +- kernel/trace/trace_selftest.c | 15 ++++-- kernel/trace/trace_stack.c | 2 +- 8 files changed, 94 insertions(+), 44 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b4f20fba09f..4f2ab9352a6 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -64,12 +64,19 @@ #define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL) +static struct ftrace_ops ftrace_list_end __read_mostly = { + .func = ftrace_stub, +}; + /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; static int last_ftrace_enabled; /* Quick disabling of function tracer. */ -int function_trace_stop; +int function_trace_stop __read_mostly; + +/* Current function tracing op */ +struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end; /* List for set_ftrace_pid's pids. */ LIST_HEAD(ftrace_pids); @@ -86,10 +93,6 @@ static int ftrace_disabled __read_mostly; static DEFINE_MUTEX(ftrace_lock); -static struct ftrace_ops ftrace_list_end __read_mostly = { - .func = ftrace_stub, -}; - static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; @@ -100,8 +103,14 @@ ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; static struct ftrace_ops control_ops; -static void -ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); +#if ARCH_SUPPORTS_FTRACE_OPS +static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op); +#else +/* See comment below, where ftrace_ops_list_func is defined */ +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); +#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops) +#endif /* * Traverse the ftrace_global_list, invoking all entries. The reason that we @@ -112,29 +121,29 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); * * Silly Alpha and silly pointer-speculation compiler optimizations! */ -static void ftrace_global_list_func(unsigned long ip, - unsigned long parent_ip) +static void +ftrace_global_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op) { - struct ftrace_ops *op; - if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT))) return; trace_recursion_set(TRACE_GLOBAL_BIT); op = rcu_dereference_raw(ftrace_global_list); /*see above*/ while (op != &ftrace_list_end) { - op->func(ip, parent_ip); + op->func(ip, parent_ip, op); op = rcu_dereference_raw(op->next); /*see above*/ }; trace_recursion_clear(TRACE_GLOBAL_BIT); } -static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip) +static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op) { if (!test_tsk_trace_trace(current)) return; - ftrace_pid_function(ip, parent_ip); + ftrace_pid_function(ip, parent_ip, op); } static void set_ftrace_pid_function(ftrace_func_t func) @@ -163,12 +172,13 @@ void clear_ftrace_function(void) * For those archs that do not test ftrace_trace_stop in their * mcount call site, we need to do it from C. */ -static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip) +static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op) { if (function_trace_stop) return; - __ftrace_trace_function(ip, parent_ip); + __ftrace_trace_function(ip, parent_ip, op); } #endif @@ -230,15 +240,24 @@ static void update_ftrace_function(void) /* * If we are at the end of the list and this ops is - * not dynamic, then have the mcount trampoline call - * the function directly + * not dynamic and the arch supports passing ops, then have the + * mcount trampoline call the function directly. */ if (ftrace_ops_list == &ftrace_list_end || (ftrace_ops_list->next == &ftrace_list_end && - !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC))) + !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) && + ARCH_SUPPORTS_FTRACE_OPS)) { + /* Set the ftrace_ops that the arch callback uses */ + if (ftrace_ops_list == &global_ops) + function_trace_op = ftrace_global_list; + else + function_trace_op = ftrace_ops_list; func = ftrace_ops_list->func; - else + } else { + /* Just use the default ftrace_ops */ + function_trace_op = &ftrace_list_end; func = ftrace_ops_list_func; + } #ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST ftrace_trace_function = func; @@ -773,7 +792,8 @@ ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip) } static void -function_profile_call(unsigned long ip, unsigned long parent_ip) +function_profile_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops) { struct ftrace_profile_stat *stat; struct ftrace_profile *rec; @@ -803,7 +823,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip) #ifdef CONFIG_FUNCTION_GRAPH_TRACER static int profile_graph_entry(struct ftrace_graph_ent *trace) { - function_profile_call(trace->func, 0); + function_profile_call(trace->func, 0, NULL); return 1; } @@ -2790,8 +2810,8 @@ static int __init ftrace_mod_cmd_init(void) } device_initcall(ftrace_mod_cmd_init); -static void -function_trace_probe_call(unsigned long ip, unsigned long parent_ip) +static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op) { struct ftrace_func_probe *entry; struct hlist_head *hhd; @@ -3942,10 +3962,9 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) #endif /* CONFIG_DYNAMIC_FTRACE */ static void -ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip) +ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op) { - struct ftrace_ops *op; - if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT))) return; @@ -3959,7 +3978,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip) while (op != &ftrace_list_end) { if (!ftrace_function_local_disabled(op) && ftrace_ops_test(op, ip)) - op->func(ip, parent_ip); + op->func(ip, parent_ip, op); op = rcu_dereference_raw(op->next); }; @@ -3971,8 +3990,9 @@ static struct ftrace_ops control_ops = { .func = ftrace_ops_control_func, }; -static void -ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) +static inline void +__ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ignored) { struct ftrace_ops *op; @@ -3988,13 +4008,32 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) op = rcu_dereference_raw(ftrace_ops_list); while (op != &ftrace_list_end) { if (ftrace_ops_test(op, ip)) - op->func(ip, parent_ip); + op->func(ip, parent_ip, op); op = rcu_dereference_raw(op->next); }; preempt_enable_notrace(); trace_recursion_clear(TRACE_INTERNAL_BIT); } +/* + * Some archs only support passing ip and parent_ip. Even though + * the list function ignores the op parameter, we do not want any + * C side effects, where a function is called without the caller + * sending a third parameter. + */ +#if ARCH_SUPPORTS_FTRACE_OPS +static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op) +{ + __ftrace_ops_list_func(ip, parent_ip, NULL); +} +#else +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) +{ + __ftrace_ops_list_func(ip, parent_ip, NULL); +} +#endif + static void clear_ftrace_swapper(void) { struct task_struct *p; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index fee3752ae8f..a872a9a298a 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -258,7 +258,8 @@ EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); #ifdef CONFIG_FUNCTION_TRACER static void -perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip) +perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops) { struct ftrace_entry *entry; struct hlist_head *head; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 29111da1d10..88daa5177bf 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1681,7 +1681,8 @@ static __init void event_trace_self_tests(void) static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable); static void -function_test_events_call(unsigned long ip, unsigned long parent_ip) +function_test_events_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op) { struct ring_buffer_event *event; struct ring_buffer *buffer; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index c7b0c6a7db0..fceb7a9aa06 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -48,7 +48,8 @@ static void function_trace_start(struct trace_array *tr) } static void -function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) +function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op) { struct trace_array *tr = func_trace; struct trace_array_cpu *data; @@ -75,7 +76,8 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) } static void -function_trace_call(unsigned long ip, unsigned long parent_ip) +function_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op) { struct trace_array *tr = func_trace; struct trace_array_cpu *data; @@ -106,7 +108,8 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) } static void -function_stack_trace_call(unsigned long ip, unsigned long parent_ip) +function_stack_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op) { struct trace_array *tr = func_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 99d20e92036..2862c77f95d 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -136,7 +136,8 @@ static int func_prolog_dec(struct trace_array *tr, * irqsoff uses its own tracer function to keep the overhead down: */ static void -irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip) +irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index ff791ea48b5..0caf4f5da56 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -108,7 +108,7 @@ out_enable: * wakeup uses its own tracer function to keep the overhead down: */ static void -wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) +wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 288541f977f..9ae40c823af 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -103,35 +103,40 @@ static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret) static int trace_selftest_test_probe1_cnt; static void trace_selftest_test_probe1_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op) { trace_selftest_test_probe1_cnt++; } static int trace_selftest_test_probe2_cnt; static void trace_selftest_test_probe2_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op) { trace_selftest_test_probe2_cnt++; } static int trace_selftest_test_probe3_cnt; static void trace_selftest_test_probe3_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op) { trace_selftest_test_probe3_cnt++; } static int trace_selftest_test_global_cnt; static void trace_selftest_test_global_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op) { trace_selftest_test_global_cnt++; } static int trace_selftest_test_dyn_cnt; static void trace_selftest_test_dyn_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op) { trace_selftest_test_dyn_cnt++; } diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index d4545f49242..e20006d5fb6 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -111,7 +111,7 @@ static inline void check_stack(void) } static void -stack_trace_call(unsigned long ip, unsigned long parent_ip) +stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op) { int cpu; -- cgit v1.2.3-70-g09d2 From ccf3672d530170c98c734dfc5db07d64bcbad2ad Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 5 Jun 2012 09:44:25 -0400 Subject: ftrace: Consolidate arch dependent functions with 'list' function As the function tracer starts to get more features, the support for theses features will spread out throughout the different architectures over time. These features boil down to what each arch does in the mcount trampoline (the ftrace_caller). Currently there's two features that are not the same throughout the archs. 1) Support to stop function tracing before the callback 2) passing of the ftrace ops Both of these require placing an indirect function to support the features if the mcount trampoline does not. On a side note, for all architectures, when more than one callback is registered to the function tracer, an intermediate 'list' function is called by the mcount trampoline to iterate through the callbacks that are registered. Instead of making a separate function for each of these features, and requiring several indirect calls, just use the single 'list' function as the intermediate, to handle all cases. If an arch does not support the 'stop function tracing' or the passing of ftrace ops, just force it to use the list function that will handle the features required. This makes the code cleaner and simpler and removes a lot of #ifdefs in the code. Link: http://lkml.kernel.org/r/20120612225424.495625483@goodmis.org Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 13 +++++++++++++ kernel/trace/ftrace.c | 45 ++++----------------------------------------- 2 files changed, 17 insertions(+), 41 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 2d596411988..3651fdc3bec 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -27,6 +27,19 @@ #define ARCH_SUPPORTS_FTRACE_OPS 0 #endif +/* + * If the arch's mcount caller does not support all of ftrace's + * features, then it must call an indirect function that + * does. Or at least does enough to prevent any unwelcomed side effects. + */ +#if !defined(CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST) || \ + !ARCH_SUPPORTS_FTRACE_OPS +# define FTRACE_FORCE_LIST_FUNC 1 +#else +# define FTRACE_FORCE_LIST_FUNC 0 +#endif + + struct module; struct ftrace_hash; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4f2ab9352a6..4cbca2e6eb7 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -97,8 +97,6 @@ static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; -static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub; -ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; static struct ftrace_ops control_ops; @@ -162,26 +160,9 @@ static void set_ftrace_pid_function(ftrace_func_t func) void clear_ftrace_function(void) { ftrace_trace_function = ftrace_stub; - __ftrace_trace_function = ftrace_stub; - __ftrace_trace_function_delay = ftrace_stub; ftrace_pid_function = ftrace_stub; } -#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST -/* - * For those archs that do not test ftrace_trace_stop in their - * mcount call site, we need to do it from C. - */ -static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op) -{ - if (function_trace_stop) - return; - - __ftrace_trace_function(ip, parent_ip, op); -} -#endif - static void control_ops_disable_all(struct ftrace_ops *ops) { int cpu; @@ -246,7 +227,7 @@ static void update_ftrace_function(void) if (ftrace_ops_list == &ftrace_list_end || (ftrace_ops_list->next == &ftrace_list_end && !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) && - ARCH_SUPPORTS_FTRACE_OPS)) { + !FTRACE_FORCE_LIST_FUNC)) { /* Set the ftrace_ops that the arch callback uses */ if (ftrace_ops_list == &global_ops) function_trace_op = ftrace_global_list; @@ -259,18 +240,7 @@ static void update_ftrace_function(void) func = ftrace_ops_list_func; } -#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST ftrace_trace_function = func; -#else -#ifdef CONFIG_DYNAMIC_FTRACE - /* do not update till all functions have been modified */ - __ftrace_trace_function_delay = func; -#else - __ftrace_trace_function = func; -#endif - ftrace_trace_function = - (func == ftrace_stub) ? func : ftrace_test_stop_func; -#endif } static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) @@ -1902,16 +1872,6 @@ static void ftrace_run_update_code(int command) */ arch_ftrace_update_code(command); -#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - /* - * For archs that call ftrace_test_stop_func(), we must - * wait till after we update all the function callers - * before we update the callback. This keeps different - * ops that record different functions from corrupting - * each other. - */ - __ftrace_trace_function = __ftrace_trace_function_delay; -#endif function_trace_stop--; ret = ftrace_arch_code_modify_post_process(); @@ -3996,6 +3956,9 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, { struct ftrace_ops *op; + if (function_trace_stop) + return; + if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT))) return; -- cgit v1.2.3-70-g09d2 From a1e2e31d175a1349274eba3465d17616c6725f8c Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 9 Aug 2011 12:50:46 -0400 Subject: ftrace: Return pt_regs to function trace callback Return as the 4th paramater to the function tracer callback the pt_regs. Later patches that implement regs passing for the architectures will require having the ftrace_ops set the SAVE_REGS flag, which will tell the arch to take the time to pass a full set of pt_regs to the ftrace_ops callback function. If the arch does not support it then it should pass NULL. If an arch can pass full regs, then it should define: ARCH_SUPPORTS_FTRACE_SAVE_REGS to 1 Link: http://lkml.kernel.org/r/20120702201821.019966811@goodmis.org Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 6 ++++-- kernel/trace/ftrace.c | 37 ++++++++++++++++++++++--------------- kernel/trace/trace_event_perf.c | 2 +- kernel/trace/trace_events.c | 2 +- kernel/trace/trace_functions.c | 7 ++++--- kernel/trace/trace_irqsoff.c | 2 +- kernel/trace/trace_sched_wakeup.c | 3 ++- kernel/trace/trace_selftest.c | 15 ++++++++++----- kernel/trace/trace_stack.c | 3 ++- 9 files changed, 47 insertions(+), 30 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 3651fdc3bec..e4202881fb0 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -54,7 +55,7 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, struct ftrace_ops; typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op); + struct ftrace_ops *op, struct pt_regs *regs); /* * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are @@ -188,7 +189,8 @@ static inline int ftrace_function_local_disabled(struct ftrace_ops *ops) return *this_cpu_ptr(ops->disabled); } -extern void ftrace_stub(unsigned long a0, unsigned long a1, struct ftrace_ops *op); +extern void ftrace_stub(unsigned long a0, unsigned long a1, + struct ftrace_ops *op, struct pt_regs *regs); #else /* !CONFIG_FUNCTION_TRACER */ /* diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4cbca2e6eb7..6ff07ad0ede 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -103,7 +103,7 @@ static struct ftrace_ops control_ops; #if ARCH_SUPPORTS_FTRACE_OPS static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op); + struct ftrace_ops *op, struct pt_regs *regs); #else /* See comment below, where ftrace_ops_list_func is defined */ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); @@ -121,7 +121,7 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); */ static void ftrace_global_list_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op) + struct ftrace_ops *op, struct pt_regs *regs) { if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT))) return; @@ -129,19 +129,19 @@ ftrace_global_list_func(unsigned long ip, unsigned long parent_ip, trace_recursion_set(TRACE_GLOBAL_BIT); op = rcu_dereference_raw(ftrace_global_list); /*see above*/ while (op != &ftrace_list_end) { - op->func(ip, parent_ip, op); + op->func(ip, parent_ip, op, regs); op = rcu_dereference_raw(op->next); /*see above*/ }; trace_recursion_clear(TRACE_GLOBAL_BIT); } static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op) + struct ftrace_ops *op, struct pt_regs *regs) { if (!test_tsk_trace_trace(current)) return; - ftrace_pid_function(ip, parent_ip, op); + ftrace_pid_function(ip, parent_ip, op, regs); } static void set_ftrace_pid_function(ftrace_func_t func) @@ -763,7 +763,7 @@ ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip) static void function_profile_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops) + struct ftrace_ops *ops, struct pt_regs *regs) { struct ftrace_profile_stat *stat; struct ftrace_profile *rec; @@ -793,7 +793,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip, #ifdef CONFIG_FUNCTION_GRAPH_TRACER static int profile_graph_entry(struct ftrace_graph_ent *trace) { - function_profile_call(trace->func, 0, NULL); + function_profile_call(trace->func, 0, NULL, NULL); return 1; } @@ -2771,7 +2771,7 @@ static int __init ftrace_mod_cmd_init(void) device_initcall(ftrace_mod_cmd_init); static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op) + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct ftrace_func_probe *entry; struct hlist_head *hhd; @@ -3923,7 +3923,7 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) static void ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op) + struct ftrace_ops *op, struct pt_regs *regs) { if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT))) return; @@ -3938,7 +3938,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, while (op != &ftrace_list_end) { if (!ftrace_function_local_disabled(op) && ftrace_ops_test(op, ip)) - op->func(ip, parent_ip, op); + op->func(ip, parent_ip, op, regs); op = rcu_dereference_raw(op->next); }; @@ -3952,7 +3952,7 @@ static struct ftrace_ops control_ops = { static inline void __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ignored) + struct ftrace_ops *ignored, struct pt_regs *regs) { struct ftrace_ops *op; @@ -3971,7 +3971,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, op = rcu_dereference_raw(ftrace_ops_list); while (op != &ftrace_list_end) { if (ftrace_ops_test(op, ip)) - op->func(ip, parent_ip, op); + op->func(ip, parent_ip, op, regs); op = rcu_dereference_raw(op->next); }; preempt_enable_notrace(); @@ -3983,17 +3983,24 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, * the list function ignores the op parameter, we do not want any * C side effects, where a function is called without the caller * sending a third parameter. + * Archs are to support both the regs and ftrace_ops at the same time. + * If they support ftrace_ops, it is assumed they support regs. + * If call backs want to use regs, they must either check for regs + * being NULL, or ARCH_SUPPORTS_FTRACE_SAVE_REGS. + * Note, ARCH_SUPPORT_SAVE_REGS expects a full regs to be saved. + * An architecture can pass partial regs with ftrace_ops and still + * set the ARCH_SUPPORT_FTARCE_OPS. */ #if ARCH_SUPPORTS_FTRACE_OPS static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op) + struct ftrace_ops *op, struct pt_regs *regs) { - __ftrace_ops_list_func(ip, parent_ip, NULL); + __ftrace_ops_list_func(ip, parent_ip, NULL, regs); } #else static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) { - __ftrace_ops_list_func(ip, parent_ip, NULL); + __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); } #endif diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index a872a9a298a..9824419c840 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -259,7 +259,7 @@ EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); #ifdef CONFIG_FUNCTION_TRACER static void perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops) + struct ftrace_ops *ops, struct pt_regs *pt_regs) { struct ftrace_entry *entry; struct hlist_head *head; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 88daa5177bf..8c669683368 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1682,7 +1682,7 @@ static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable); static void function_test_events_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op) + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct ring_buffer_event *event; struct ring_buffer *buffer; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index fceb7a9aa06..5675ebd541f 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -49,7 +49,7 @@ static void function_trace_start(struct trace_array *tr) static void function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op) + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = func_trace; struct trace_array_cpu *data; @@ -77,7 +77,8 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip, static void function_trace_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op) + struct ftrace_ops *op, struct pt_regs *pt_regs) + { struct trace_array *tr = func_trace; struct trace_array_cpu *data; @@ -109,7 +110,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, static void function_stack_trace_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op) + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = func_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 2862c77f95d..c7a9ba936de 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -137,7 +137,7 @@ static int func_prolog_dec(struct trace_array *tr, */ static void irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op) + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 0caf4f5da56..7547e36d483 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -108,7 +108,8 @@ out_enable: * wakeup uses its own tracer function to keep the overhead down: */ static void -wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op) +wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 9ae40c823af..add37e019fd 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -104,7 +104,8 @@ static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret) static int trace_selftest_test_probe1_cnt; static void trace_selftest_test_probe1_func(unsigned long ip, unsigned long pip, - struct ftrace_ops *op) + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_probe1_cnt++; } @@ -112,7 +113,8 @@ static void trace_selftest_test_probe1_func(unsigned long ip, static int trace_selftest_test_probe2_cnt; static void trace_selftest_test_probe2_func(unsigned long ip, unsigned long pip, - struct ftrace_ops *op) + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_probe2_cnt++; } @@ -120,7 +122,8 @@ static void trace_selftest_test_probe2_func(unsigned long ip, static int trace_selftest_test_probe3_cnt; static void trace_selftest_test_probe3_func(unsigned long ip, unsigned long pip, - struct ftrace_ops *op) + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_probe3_cnt++; } @@ -128,7 +131,8 @@ static void trace_selftest_test_probe3_func(unsigned long ip, static int trace_selftest_test_global_cnt; static void trace_selftest_test_global_func(unsigned long ip, unsigned long pip, - struct ftrace_ops *op) + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_global_cnt++; } @@ -136,7 +140,8 @@ static void trace_selftest_test_global_func(unsigned long ip, static int trace_selftest_test_dyn_cnt; static void trace_selftest_test_dyn_func(unsigned long ip, unsigned long pip, - struct ftrace_ops *op) + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_dyn_cnt++; } diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index e20006d5fb6..2fa5328e889 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -111,7 +111,8 @@ static inline void check_stack(void) } static void -stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op) +stack_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { int cpu; -- cgit v1.2.3-70-g09d2 From 08f6fba503111e0336f2b4d6915a4a18f9b60e51 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 30 Apr 2012 16:20:23 -0400 Subject: ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt --- arch/x86/include/asm/ftrace.h | 47 +++++++++++-------- arch/x86/kernel/entry_32.S | 4 +- arch/x86/kernel/entry_64.S | 94 +++++++++++++++++++++++++++++++++---- arch/x86/kernel/ftrace.c | 77 ++++++++++++++++++++++++++++-- include/linux/ftrace.h | 107 +++++++++++++++++++++++++++++++++++++++--- kernel/trace/ftrace.c | 91 +++++++++++++++++++++++++++++++---- 6 files changed, 373 insertions(+), 47 deletions(-) (limited to 'kernel/trace') diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index b3bb1f3f277..a8475014c4a 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -3,27 +3,33 @@ #ifdef __ASSEMBLY__ - .macro MCOUNT_SAVE_FRAME - /* taken from glibc */ - subq $0x38, %rsp - movq %rax, (%rsp) - movq %rcx, 8(%rsp) - movq %rdx, 16(%rsp) - movq %rsi, 24(%rsp) - movq %rdi, 32(%rsp) - movq %r8, 40(%rsp) - movq %r9, 48(%rsp) + /* skip is set if the stack was already partially adjusted */ + .macro MCOUNT_SAVE_FRAME skip=0 + /* + * We add enough stack to save all regs. + */ + subq $(SS+8-\skip), %rsp + movq %rax, RAX(%rsp) + movq %rcx, RCX(%rsp) + movq %rdx, RDX(%rsp) + movq %rsi, RSI(%rsp) + movq %rdi, RDI(%rsp) + movq %r8, R8(%rsp) + movq %r9, R9(%rsp) + /* Move RIP to its proper location */ + movq SS+8(%rsp), %rdx + movq %rdx, RIP(%rsp) .endm - .macro MCOUNT_RESTORE_FRAME - movq 48(%rsp), %r9 - movq 40(%rsp), %r8 - movq 32(%rsp), %rdi - movq 24(%rsp), %rsi - movq 16(%rsp), %rdx - movq 8(%rsp), %rcx - movq (%rsp), %rax - addq $0x38, %rsp + .macro MCOUNT_RESTORE_FRAME skip=0 + movq R9(%rsp), %r9 + movq R8(%rsp), %r8 + movq RDI(%rsp), %rdi + movq RSI(%rsp), %rsi + movq RDX(%rsp), %rdx + movq RCX(%rsp), %rcx + movq RAX(%rsp), %rax + addq $(SS+8-\skip), %rsp .endm #endif @@ -34,6 +40,9 @@ #ifdef CONFIG_DYNAMIC_FTRACE #define ARCH_SUPPORTS_FTRACE_OPS 1 +#ifdef CONFIG_X86_64 +#define ARCH_SUPPORTS_FTRACE_SAVE_REGS +#endif #endif #ifndef __ASSEMBLY__ diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index e3e17a0b7ff..5da11d1b85a 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1109,7 +1109,8 @@ ENTRY(ftrace_caller) pushl %eax pushl %ecx pushl %edx - movl 0xc(%esp), %eax + pushl $0 /* Pass NULL as regs pointer */ + movl 4*4(%esp), %eax movl 0x4(%ebp), %edx leal function_trace_op, %ecx subl $MCOUNT_INSN_SIZE, %eax @@ -1118,6 +1119,7 @@ ENTRY(ftrace_caller) ftrace_call: call ftrace_stub + addl $4,%esp /* skip NULL pointer */ popl %edx popl %ecx popl %eax diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 2b4f94c5dc6..52bda2e8f7a 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -73,21 +73,34 @@ ENTRY(mcount) retq END(mcount) +/* skip is set if stack has been adjusted */ +.macro ftrace_caller_setup skip=0 + MCOUNT_SAVE_FRAME \skip + + /* Load the ftrace_ops into the 3rd parameter */ + leaq function_trace_op, %rdx + + /* Load ip into the first parameter */ + movq RIP(%rsp), %rdi + subq $MCOUNT_INSN_SIZE, %rdi + /* Load the parent_ip into the second parameter */ + movq 8(%rbp), %rsi +.endm + ENTRY(ftrace_caller) + /* Check if tracing was disabled (quick check) */ cmpl $0, function_trace_stop jne ftrace_stub - MCOUNT_SAVE_FRAME - - leaq function_trace_op, %rdx - movq 0x38(%rsp), %rdi - movq 8(%rbp), %rsi - subq $MCOUNT_INSN_SIZE, %rdi + ftrace_caller_setup + /* regs go into 4th parameter (but make it NULL) */ + movq $0, %rcx GLOBAL(ftrace_call) call ftrace_stub MCOUNT_RESTORE_FRAME +ftrace_return: #ifdef CONFIG_FUNCTION_GRAPH_TRACER GLOBAL(ftrace_graph_call) @@ -98,6 +111,71 @@ GLOBAL(ftrace_stub) retq END(ftrace_caller) +ENTRY(ftrace_regs_caller) + /* Save the current flags before compare (in SS location)*/ + pushfq + + /* Check if tracing was disabled (quick check) */ + cmpl $0, function_trace_stop + jne ftrace_restore_flags + + /* skip=8 to skip flags saved in SS */ + ftrace_caller_setup 8 + + /* Save the rest of pt_regs */ + movq %r15, R15(%rsp) + movq %r14, R14(%rsp) + movq %r13, R13(%rsp) + movq %r12, R12(%rsp) + movq %r11, R11(%rsp) + movq %r10, R10(%rsp) + movq %rbp, RBP(%rsp) + movq %rbx, RBX(%rsp) + /* Copy saved flags */ + movq SS(%rsp), %rcx + movq %rcx, EFLAGS(%rsp) + /* Kernel segments */ + movq $__KERNEL_DS, %rcx + movq %rcx, SS(%rsp) + movq $__KERNEL_CS, %rcx + movq %rcx, CS(%rsp) + /* Stack - skipping return address */ + leaq SS+16(%rsp), %rcx + movq %rcx, RSP(%rsp) + + /* regs go into 4th parameter */ + leaq (%rsp), %rcx + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + /* Copy flags back to SS, to restore them */ + movq EFLAGS(%rsp), %rax + movq %rax, SS(%rsp) + + /* restore the rest of pt_regs */ + movq R15(%rsp), %r15 + movq R14(%rsp), %r14 + movq R13(%rsp), %r13 + movq R12(%rsp), %r12 + movq R10(%rsp), %r10 + movq RBP(%rsp), %rbp + movq RBX(%rsp), %rbx + + /* skip=8 to skip flags saved in SS */ + MCOUNT_RESTORE_FRAME 8 + + /* Restore flags */ + popfq + + jmp ftrace_return +ftrace_restore_flags: + popfq + jmp ftrace_stub + +END(ftrace_regs_caller) + + #else /* ! CONFIG_DYNAMIC_FTRACE */ ENTRY(mcount) cmpl $0, function_trace_stop @@ -120,7 +198,7 @@ GLOBAL(ftrace_stub) trace: MCOUNT_SAVE_FRAME - movq 0x38(%rsp), %rdi + movq RIP(%rsp), %rdi movq 8(%rbp), %rsi subq $MCOUNT_INSN_SIZE, %rdi @@ -141,7 +219,7 @@ ENTRY(ftrace_graph_caller) MCOUNT_SAVE_FRAME leaq 8(%rbp), %rdi - movq 0x38(%rsp), %rsi + movq RIP(%rsp), %rsi movq (%rbp), %rdx subq $MCOUNT_INSN_SIZE, %rsi diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index c3a7cb4bf6e..b90eb1a1307 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -206,6 +206,23 @@ static int ftrace_modify_code(unsigned long ip, unsigned const char *old_code, unsigned const char *new_code); +#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS +/* + * Should never be called: + * As it is only called by __ftrace_replace_code() which is called by + * ftrace_replace_code() that x86 overrides, and by ftrace_update_code() + * which is called to turn mcount into nops or nops into function calls + * but not to convert a function from not using regs to one that uses + * regs, which ftrace_modify_call() is for. + */ +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + WARN_ON(1); + return -EINVAL; +} +#endif + int ftrace_update_ftrace_func(ftrace_func_t func) { unsigned long ip = (unsigned long)(&ftrace_call); @@ -220,6 +237,16 @@ int ftrace_update_ftrace_func(ftrace_func_t func) ret = ftrace_modify_code(ip, old, new); +#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS + /* Also update the regs callback function */ + if (!ret) { + ip = (unsigned long)(&ftrace_regs_call); + memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE); + new = ftrace_call_replace(ip, (unsigned long)func); + ret = ftrace_modify_code(ip, old, new); + } +#endif + atomic_dec(&modifying_ftrace_code); return ret; @@ -299,6 +326,32 @@ static int add_brk_on_nop(struct dyn_ftrace *rec) return add_break(rec->ip, old); } +/* + * If the record has the FTRACE_FL_REGS set, that means that it + * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS + * is not not set, then it wants to convert to the normal callback. + */ +static unsigned long get_ftrace_addr(struct dyn_ftrace *rec) +{ + if (rec->flags & FTRACE_FL_REGS) + return (unsigned long)FTRACE_REGS_ADDR; + else + return (unsigned long)FTRACE_ADDR; +} + +/* + * The FTRACE_FL_REGS_EN is set when the record already points to + * a function that saves all the regs. Basically the '_EN' version + * represents the current state of the function. + */ +static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec) +{ + if (rec->flags & FTRACE_FL_REGS_EN) + return (unsigned long)FTRACE_REGS_ADDR; + else + return (unsigned long)FTRACE_ADDR; +} + static int add_breakpoints(struct dyn_ftrace *rec, int enable) { unsigned long ftrace_addr; @@ -306,7 +359,7 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable) ret = ftrace_test_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: @@ -316,6 +369,10 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable) /* converting nop to call */ return add_brk_on_nop(rec); + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: + ftrace_addr = get_ftrace_old_addr(rec); + /* fall through */ case FTRACE_UPDATE_MAKE_NOP: /* converting a call to a nop */ return add_brk_on_call(rec, ftrace_addr); @@ -360,13 +417,21 @@ static int remove_breakpoint(struct dyn_ftrace *rec) * If not, don't touch the breakpoint, we make just create * a disaster. */ - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); + nop = ftrace_call_replace(ip, ftrace_addr); + + if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0) + goto update; + + /* Check both ftrace_addr and ftrace_old_addr */ + ftrace_addr = get_ftrace_old_addr(rec); nop = ftrace_call_replace(ip, ftrace_addr); if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) return -EINVAL; } + update: return probe_kernel_write((void *)ip, &nop[0], 1); } @@ -405,12 +470,14 @@ static int add_update(struct dyn_ftrace *rec, int enable) ret = ftrace_test_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ return add_update_call(rec, ftrace_addr); @@ -455,12 +522,14 @@ static int finish_update(struct dyn_ftrace *rec, int enable) ret = ftrace_update_record(rec, enable); - ftrace_addr = (unsigned long)FTRACE_ADDR; + ftrace_addr = get_ftrace_addr(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ return finish_update_call(rec, ftrace_addr); diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e4202881fb0..ab39990cc43 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -71,12 +71,28 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, * could be controled by following calls: * ftrace_function_local_enable * ftrace_function_local_disable + * SAVE_REGS - The ftrace_ops wants regs saved at each function called + * and passed to the callback. If this flag is set, but the + * architecture does not support passing regs + * (ARCH_SUPPORTS_FTRACE_SAVE_REGS is not defined), then the + * ftrace_ops will fail to register, unless the next flag + * is set. + * SAVE_REGS_IF_SUPPORTED - This is the same as SAVE_REGS, but if the + * handler can handle an arch that does not save regs + * (the handler tests if regs == NULL), then it can set + * this flag instead. It will not fail registering the ftrace_ops + * but, the regs field will be NULL if the arch does not support + * passing regs to the handler. + * Note, if this flag is set, the SAVE_REGS flag will automatically + * get set upon registering the ftrace_ops, if the arch supports it. */ enum { - FTRACE_OPS_FL_ENABLED = 1 << 0, - FTRACE_OPS_FL_GLOBAL = 1 << 1, - FTRACE_OPS_FL_DYNAMIC = 1 << 2, - FTRACE_OPS_FL_CONTROL = 1 << 3, + FTRACE_OPS_FL_ENABLED = 1 << 0, + FTRACE_OPS_FL_GLOBAL = 1 << 1, + FTRACE_OPS_FL_DYNAMIC = 1 << 2, + FTRACE_OPS_FL_CONTROL = 1 << 3, + FTRACE_OPS_FL_SAVE_REGS = 1 << 4, + FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 5, }; struct ftrace_ops { @@ -254,12 +270,31 @@ extern void unregister_ftrace_function_probe_all(char *glob); extern int ftrace_text_reserved(void *start, void *end); +/* + * The dyn_ftrace record's flags field is split into two parts. + * the first part which is '0-FTRACE_REF_MAX' is a counter of + * the number of callbacks that have registered the function that + * the dyn_ftrace descriptor represents. + * + * The second part is a mask: + * ENABLED - the function is being traced + * REGS - the record wants the function to save regs + * REGS_EN - the function is set up to save regs. + * + * When a new ftrace_ops is registered and wants a function to save + * pt_regs, the rec->flag REGS is set. When the function has been + * set up to save regs, the REG_EN flag is set. Once a function + * starts saving regs it will do so until all ftrace_ops are removed + * from tracing that function. + */ enum { - FTRACE_FL_ENABLED = (1 << 30), + FTRACE_FL_ENABLED = (1UL << 29), + FTRACE_FL_REGS = (1UL << 30), + FTRACE_FL_REGS_EN = (1UL << 31) }; -#define FTRACE_FL_MASK (0x3UL << 30) -#define FTRACE_REF_MAX ((1 << 30) - 1) +#define FTRACE_FL_MASK (0x7UL << 29) +#define FTRACE_REF_MAX ((1UL << 29) - 1) struct dyn_ftrace { union { @@ -290,9 +325,23 @@ enum { FTRACE_STOP_FUNC_RET = (1 << 4), }; +/* + * The FTRACE_UPDATE_* enum is used to pass information back + * from the ftrace_update_record() and ftrace_test_record() + * functions. These are called by the code update routines + * to find out what is to be done for a given function. + * + * IGNORE - The function is already what we want it to be + * MAKE_CALL - Start tracing the function + * MODIFY_CALL - Stop saving regs for the function + * MODIFY_CALL_REGS - Start saving regs for the function + * MAKE_NOP - Stop tracing the function + */ enum { FTRACE_UPDATE_IGNORE, FTRACE_UPDATE_MAKE_CALL, + FTRACE_UPDATE_MODIFY_CALL, + FTRACE_UPDATE_MODIFY_CALL_REGS, FTRACE_UPDATE_MAKE_NOP, }; @@ -344,7 +393,9 @@ extern int ftrace_dyn_arch_init(void *data); extern void ftrace_replace_code(int enable); extern int ftrace_update_ftrace_func(ftrace_func_t func); extern void ftrace_caller(void); +extern void ftrace_regs_caller(void); extern void ftrace_call(void); +extern void ftrace_regs_call(void); extern void mcount_call(void); void ftrace_modify_all_code(int command); @@ -352,6 +403,15 @@ void ftrace_modify_all_code(int command); #ifndef FTRACE_ADDR #define FTRACE_ADDR ((unsigned long)ftrace_caller) #endif + +#ifndef FTRACE_REGS_ADDR +#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS +# define FTRACE_REGS_ADDR ((unsigned long)ftrace_regs_caller) +#else +# define FTRACE_REGS_ADDR FTRACE_ADDR +#endif +#endif + #ifdef CONFIG_FUNCTION_GRAPH_TRACER extern void ftrace_graph_caller(void); extern int ftrace_enable_ftrace_graph_caller(void); @@ -407,6 +467,39 @@ extern int ftrace_make_nop(struct module *mod, */ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); +#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS +/** + * ftrace_modify_call - convert from one addr to another (no nop) + * @rec: the mcount call site record + * @old_addr: the address expected to be currently called to + * @addr: the address to change to + * + * This is a very sensitive operation and great care needs + * to be taken by the arch. The operation should carefully + * read the location, check to see if what is read is indeed + * what we expect it to be, and then on success of the compare, + * it should write to the location. + * + * The code segment at @rec->ip should be a caller to @old_addr + * + * Return must be: + * 0 on success + * -EFAULT on error reading the location + * -EINVAL on a failed compare of the contents + * -EPERM on error writing to the location + * Any other value will be considered a failure. + */ +extern int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr); +#else +/* Should never be called */ +static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + return -EINVAL; +} +#endif + /* May be defined in arch */ extern int ftrace_arch_read_dyn_info(char *buf, int size); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6ff07ad0ede..c55f7e27461 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -314,6 +314,20 @@ static int __register_ftrace_function(struct ftrace_ops *ops) if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK) return -EINVAL; +#ifndef ARCH_SUPPORTS_FTRACE_SAVE_REGS + /* + * If the ftrace_ops specifies SAVE_REGS, then it only can be used + * if the arch supports it, or SAVE_REGS_IF_SUPPORTED is also set. + * Setting SAVE_REGS_IF_SUPPORTED makes SAVE_REGS irrelevant. + */ + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS && + !(ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED)) + return -EINVAL; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED) + ops->flags |= FTRACE_OPS_FL_SAVE_REGS; +#endif + if (!core_kernel_data((unsigned long)ops)) ops->flags |= FTRACE_OPS_FL_DYNAMIC; @@ -1515,6 +1529,12 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, rec->flags++; if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == FTRACE_REF_MAX)) return; + /* + * If any ops wants regs saved for this function + * then all ops will get saved regs. + */ + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) + rec->flags |= FTRACE_FL_REGS; } else { if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == 0)) return; @@ -1606,18 +1626,59 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) if (enable && (rec->flags & ~FTRACE_FL_MASK)) flag = FTRACE_FL_ENABLED; + /* + * If enabling and the REGS flag does not match the REGS_EN, then + * do not ignore this record. Set flags to fail the compare against + * ENABLED. + */ + if (flag && + (!(rec->flags & FTRACE_FL_REGS) != !(rec->flags & FTRACE_FL_REGS_EN))) + flag |= FTRACE_FL_REGS; + /* If the state of this record hasn't changed, then do nothing */ if ((rec->flags & FTRACE_FL_ENABLED) == flag) return FTRACE_UPDATE_IGNORE; if (flag) { - if (update) + /* Save off if rec is being enabled (for return value) */ + flag ^= rec->flags & FTRACE_FL_ENABLED; + + if (update) { rec->flags |= FTRACE_FL_ENABLED; - return FTRACE_UPDATE_MAKE_CALL; + if (flag & FTRACE_FL_REGS) { + if (rec->flags & FTRACE_FL_REGS) + rec->flags |= FTRACE_FL_REGS_EN; + else + rec->flags &= ~FTRACE_FL_REGS_EN; + } + } + + /* + * If this record is being updated from a nop, then + * return UPDATE_MAKE_CALL. + * Otherwise, if the EN flag is set, then return + * UPDATE_MODIFY_CALL_REGS to tell the caller to convert + * from the non-save regs, to a save regs function. + * Otherwise, + * return UPDATE_MODIFY_CALL to tell the caller to convert + * from the save regs, to a non-save regs function. + */ + if (flag & FTRACE_FL_ENABLED) + return FTRACE_UPDATE_MAKE_CALL; + else if (rec->flags & FTRACE_FL_REGS_EN) + return FTRACE_UPDATE_MODIFY_CALL_REGS; + else + return FTRACE_UPDATE_MODIFY_CALL; } - if (update) - rec->flags &= ~FTRACE_FL_ENABLED; + if (update) { + /* If there's no more users, clear all flags */ + if (!(rec->flags & ~FTRACE_FL_MASK)) + rec->flags = 0; + else + /* Just disable the record (keep REGS state) */ + rec->flags &= ~FTRACE_FL_ENABLED; + } return FTRACE_UPDATE_MAKE_NOP; } @@ -1652,13 +1713,17 @@ int ftrace_test_record(struct dyn_ftrace *rec, int enable) static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) { + unsigned long ftrace_old_addr; unsigned long ftrace_addr; int ret; - ftrace_addr = (unsigned long)FTRACE_ADDR; - ret = ftrace_update_record(rec, enable); + if (rec->flags & FTRACE_FL_REGS) + ftrace_addr = (unsigned long)FTRACE_REGS_ADDR; + else + ftrace_addr = (unsigned long)FTRACE_ADDR; + switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; @@ -1668,6 +1733,15 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) case FTRACE_UPDATE_MAKE_NOP: return ftrace_make_nop(NULL, rec, ftrace_addr); + + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: + if (rec->flags & FTRACE_FL_REGS) + ftrace_old_addr = (unsigned long)FTRACE_ADDR; + else + ftrace_old_addr = (unsigned long)FTRACE_REGS_ADDR; + + return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr); } return -1; /* unknow ftrace bug */ @@ -2421,8 +2495,9 @@ static int t_show(struct seq_file *m, void *v) seq_printf(m, "%ps", (void *)rec->ip); if (iter->flags & FTRACE_ITER_ENABLED) - seq_printf(m, " (%ld)", - rec->flags & ~FTRACE_FL_MASK); + seq_printf(m, " (%ld)%s", + rec->flags & ~FTRACE_FL_MASK, + rec->flags & FTRACE_FL_REGS ? " R" : ""); seq_printf(m, "\n"); return 0; -- cgit v1.2.3-70-g09d2 From 4740974a6844156c14d741b0080b59d275679a23 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 20 Jul 2012 11:04:44 -0400 Subject: ftrace: Add default recursion protection for function tracing As more users of the function tracer utility are being added, they do not always add the necessary recursion protection. To protect from function recursion due to tracing, if the callback ftrace_ops does not specifically specify that it protects against recursion (by setting the FTRACE_OPS_FL_RECURSION_SAFE flag), the list operation will be called by the mcount trampoline which adds recursion protection. If the flag is set, then the function will be called directly with no extra protection. Note, the list operation is called if more than one function callback is registered, or if the arch does not support all of the function tracer features. Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 5 +++++ kernel/trace/ftrace.c | 10 ++++++++-- kernel/trace/trace_events.c | 1 + kernel/trace/trace_functions.c | 4 ++-- kernel/trace/trace_irqsoff.c | 2 +- kernel/trace/trace_sched_wakeup.c | 2 +- kernel/trace/trace_selftest.c | 7 +++++-- kernel/trace/trace_stack.c | 1 + 8 files changed, 24 insertions(+), 8 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ab39990cc43..65a14e47a0d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -85,6 +85,10 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, * passing regs to the handler. * Note, if this flag is set, the SAVE_REGS flag will automatically * get set upon registering the ftrace_ops, if the arch supports it. + * RECURSION_SAFE - The ftrace_ops can set this to tell the ftrace infrastructure + * that the call back has its own recursion protection. If it does + * not set this, then the ftrace infrastructure will add recursion + * protection for the caller. */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, @@ -93,6 +97,7 @@ enum { FTRACE_OPS_FL_CONTROL = 1 << 3, FTRACE_OPS_FL_SAVE_REGS = 1 << 4, FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 5, + FTRACE_OPS_FL_RECURSION_SAFE = 1 << 6, }; struct ftrace_ops { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index c55f7e27461..ad765b4ba42 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -66,6 +66,7 @@ static struct ftrace_ops ftrace_list_end __read_mostly = { .func = ftrace_stub, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; /* ftrace_enabled is a method to turn ftrace on or off */ @@ -221,12 +222,13 @@ static void update_ftrace_function(void) /* * If we are at the end of the list and this ops is - * not dynamic and the arch supports passing ops, then have the - * mcount trampoline call the function directly. + * recursion safe and not dynamic and the arch supports passing ops, + * then have the mcount trampoline call the function directly. */ if (ftrace_ops_list == &ftrace_list_end || (ftrace_ops_list->next == &ftrace_list_end && !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) && + (ftrace_ops_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) && !FTRACE_FORCE_LIST_FUNC)) { /* Set the ftrace_ops that the arch callback uses */ if (ftrace_ops_list == &global_ops) @@ -867,6 +869,7 @@ static void unregister_ftrace_profiler(void) #else static struct ftrace_ops ftrace_profile_ops __read_mostly = { .func = function_profile_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static int register_ftrace_profiler(void) @@ -1049,6 +1052,7 @@ static struct ftrace_ops global_ops = { .func = ftrace_stub, .notrace_hash = EMPTY_HASH, .filter_hash = EMPTY_HASH, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static DEFINE_MUTEX(ftrace_regex_lock); @@ -3967,6 +3971,7 @@ void __init ftrace_init(void) static struct ftrace_ops global_ops = { .func = ftrace_stub, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static int __init ftrace_nodyn_init(void) @@ -4023,6 +4028,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, static struct ftrace_ops control_ops = { .func = ftrace_ops_control_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static inline void diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 8c669683368..6825d833a25 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1721,6 +1721,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip, static struct ftrace_ops trace_ops __initdata = { .func = function_test_events_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static __init void event_trace_self_test_with_function(void) diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 5675ebd541f..fdff65dff1b 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -153,13 +153,13 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip, static struct ftrace_ops trace_ops __read_mostly = { .func = function_trace_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops trace_stack_ops __read_mostly = { .func = function_stack_trace_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; /* Our two options */ diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index c7a9ba936de..d98ee8283b2 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -154,7 +154,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip, static struct ftrace_ops trace_ops __read_mostly = { .func = irqsoff_tracer_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 7547e36d483..02170c00c41 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -130,7 +130,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, static struct ftrace_ops trace_ops __read_mostly = { .func = wakeup_tracer_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index add37e019fd..1fb6da85ff8 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -148,19 +148,22 @@ static void trace_selftest_test_dyn_func(unsigned long ip, static struct ftrace_ops test_probe1 = { .func = trace_selftest_test_probe1_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_probe2 = { .func = trace_selftest_test_probe2_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_probe3 = { .func = trace_selftest_test_probe3_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_global = { - .func = trace_selftest_test_global_func, - .flags = FTRACE_OPS_FL_GLOBAL, + .func = trace_selftest_test_global_func, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; static void print_counts(void) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 2fa5328e889..0c1b165778e 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -137,6 +137,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip, static struct ftrace_ops trace_ops __read_mostly = { .func = stack_trace_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static ssize_t -- cgit v1.2.3-70-g09d2 From 47239c4d8d6a24796039cada69d477a2b8cac9d6 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 20 Jul 2012 11:13:07 -0400 Subject: ftrace: Only compile ftrace selftest if selftests are enabled No need to compile in the ftrace selftest helper file if selftests are not being executed. Signed-off-by: Steven Rostedt --- kernel/trace/Makefile | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index b831087c820..837090808aa 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -5,10 +5,12 @@ ifdef CONFIG_FUNCTION_TRACER ORIG_CFLAGS := $(KBUILD_CFLAGS) KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS)) +ifdef CONFIG_FTRACE_SELFTEST # selftest needs instrumentation CFLAGS_trace_selftest_dynamic.o = -pg obj-y += trace_selftest_dynamic.o endif +endif # If unlikely tracing is enabled, do not trace these files ifdef CONFIG_TRACING_BRANCHES -- cgit v1.2.3-70-g09d2 From ea701f11da44b44907af226fe5a5f57d2f26eeb2 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 20 Jul 2012 13:08:05 -0400 Subject: ftrace: Add selftest to test function trace recursion protection Add selftests to test the function tracing recursion protection actually does work. It also tests if a ftrace_ops states it will perform its own protection. Although, even if the ftrace_ops states it will protect itself, the ftrace infrastructure may still provide protection if the arch does not support all features or another ftrace_ops is registered. Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 6 ++ kernel/trace/ftrace.c | 21 +++++++ kernel/trace/trace_selftest.c | 136 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 163 insertions(+) (limited to 'kernel/trace') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 65a14e47a0d..9962e954a63 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -220,6 +220,10 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1, */ #define register_ftrace_function(ops) ({ 0; }) #define unregister_ftrace_function(ops) ({ 0; }) +static inline int ftrace_nr_registered_ops(void) +{ + return 0; +} static inline void clear_ftrace_function(void) { } static inline void ftrace_kill(void) { } static inline void ftrace_stop(void) { } @@ -275,6 +279,8 @@ extern void unregister_ftrace_function_probe_all(char *glob); extern int ftrace_text_reserved(void *start, void *end); +extern int ftrace_nr_registered_ops(void); + /* * The dyn_ftrace record's flags field is split into two parts. * the first part which is '0-FTRACE_REF_MAX' is a counter of diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ad765b4ba42..528d997c7f9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -111,6 +111,27 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); #define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops) #endif +/** + * ftrace_nr_registered_ops - return number of ops registered + * + * Returns the number of ftrace_ops registered and tracing functions + */ +int ftrace_nr_registered_ops(void) +{ + struct ftrace_ops *ops; + int cnt = 0; + + mutex_lock(&ftrace_lock); + + for (ops = ftrace_ops_list; + ops != &ftrace_list_end; ops = ops->next) + cnt++; + + mutex_unlock(&ftrace_lock); + + return cnt; +} + /* * Traverse the ftrace_global_list, invoking all entries. The reason that we * can use rcu_dereference_raw() is that elements removed from this list diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 1fb6da85ff8..86422f91dbe 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -406,8 +406,141 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, return ret; } + +static int trace_selftest_recursion_cnt; +static void trace_selftest_test_recursion_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + /* + * This function is registered without the recursion safe flag. + * The ftrace infrastructure should provide the recursion + * protection. If not, this will crash the kernel! + */ + trace_selftest_recursion_cnt++; + DYN_FTRACE_TEST_NAME(); +} + +static void trace_selftest_test_recursion_safe_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + /* + * We said we would provide our own recursion. By calling + * this function again, we should recurse back into this function + * and count again. But this only happens if the arch supports + * all of ftrace features and nothing else is using the function + * tracing utility. + */ + if (trace_selftest_recursion_cnt++) + return; + DYN_FTRACE_TEST_NAME(); +} + +static struct ftrace_ops test_rec_probe = { + .func = trace_selftest_test_recursion_func, +}; + +static struct ftrace_ops test_recsafe_probe = { + .func = trace_selftest_test_recursion_safe_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, +}; + +static int +trace_selftest_function_recursion(void) +{ + int save_ftrace_enabled = ftrace_enabled; + int save_tracer_enabled = tracer_enabled; + char *func_name; + int len; + int ret; + int cnt; + + /* The previous test PASSED */ + pr_cont("PASSED\n"); + pr_info("Testing ftrace recursion: "); + + + /* enable tracing, and record the filter function */ + ftrace_enabled = 1; + tracer_enabled = 1; + + /* Handle PPC64 '.' name */ + func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); + len = strlen(func_name); + + ret = ftrace_set_filter(&test_rec_probe, func_name, len, 1); + if (ret) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_rec_probe); + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_rec_probe); + + ret = -1; + if (trace_selftest_recursion_cnt != 1) { + pr_cont("*callback not called once (%d)* ", + trace_selftest_recursion_cnt); + goto out; + } + + trace_selftest_recursion_cnt = 1; + + pr_cont("PASSED\n"); + pr_info("Testing ftrace recursion safe: "); + + ret = ftrace_set_filter(&test_recsafe_probe, func_name, len, 1); + if (ret) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_recsafe_probe); + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_recsafe_probe); + + /* + * If arch supports all ftrace features, and no other task + * was on the list, we should be fine. + */ + if (!ftrace_nr_registered_ops() && !FTRACE_FORCE_LIST_FUNC) + cnt = 2; /* Should have recursed */ + else + cnt = 1; + + ret = -1; + if (trace_selftest_recursion_cnt != cnt) { + pr_cont("*callback not called expected %d times (%d)* ", + cnt, trace_selftest_recursion_cnt); + goto out; + } + + ret = 0; +out: + ftrace_enabled = save_ftrace_enabled; + tracer_enabled = save_tracer_enabled; + + return ret; +} #else # define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; }) +# define trace_selftest_function_recursion() ({ 0; }) #endif /* CONFIG_DYNAMIC_FTRACE */ /* @@ -455,7 +588,10 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) ret = trace_selftest_startup_dynamic_tracing(trace, tr, DYN_FTRACE_TEST_NAME); + if (ret) + goto out; + ret = trace_selftest_function_recursion(); out: ftrace_enabled = save_ftrace_enabled; tracer_enabled = save_tracer_enabled; -- cgit v1.2.3-70-g09d2 From ad97772ad82f57c83968079d0880c71ab126ab04 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 20 Jul 2012 13:45:59 -0400 Subject: ftrace: Add selftest to test function save-regs support Add selftests to test the save-regs functionality of ftrace. If the arch supports saving regs, then it will make sure that regs is at least not NULL in the callback. If the arch does not support saving regs, it makes sure that the registering of the ftrace_ops that requests saving regs fails. It then tests the registering of the ftrace_ops succeeds if the 'IF_SUPPORTED' flag is set. Then it makes sure that the regs passed to the function is NULL. Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 2 +- kernel/trace/trace_selftest.c | 114 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 115 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 55e1f7f0db1..593debefc4e 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -472,11 +472,11 @@ extern void trace_find_cmdline(int pid, char comm[]); #ifdef CONFIG_DYNAMIC_FTRACE extern unsigned long ftrace_update_tot_cnt; +#endif #define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func extern int DYN_FTRACE_TEST_NAME(void); #define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2 extern int DYN_FTRACE_TEST_NAME2(void); -#endif extern int ring_buffer_expanded; extern bool tracing_selftest_disabled; diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 86422f91dbe..1003a4d5eb2 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -543,6 +543,116 @@ out: # define trace_selftest_function_recursion() ({ 0; }) #endif /* CONFIG_DYNAMIC_FTRACE */ +static enum { + TRACE_SELFTEST_REGS_START, + TRACE_SELFTEST_REGS_FOUND, + TRACE_SELFTEST_REGS_NOT_FOUND, +} trace_selftest_regs_stat; + +static void trace_selftest_test_regs_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + if (pt_regs) + trace_selftest_regs_stat = TRACE_SELFTEST_REGS_FOUND; + else + trace_selftest_regs_stat = TRACE_SELFTEST_REGS_NOT_FOUND; +} + +static struct ftrace_ops test_regs_probe = { + .func = trace_selftest_test_regs_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_SAVE_REGS, +}; + +static int +trace_selftest_function_regs(void) +{ + int save_ftrace_enabled = ftrace_enabled; + int save_tracer_enabled = tracer_enabled; + char *func_name; + int len; + int ret; + int supported = 0; + +#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS + supported = 1; +#endif + + /* The previous test PASSED */ + pr_cont("PASSED\n"); + pr_info("Testing ftrace regs%s: ", + !supported ? "(no arch support)" : ""); + + /* enable tracing, and record the filter function */ + ftrace_enabled = 1; + tracer_enabled = 1; + + /* Handle PPC64 '.' name */ + func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); + len = strlen(func_name); + + ret = ftrace_set_filter(&test_regs_probe, func_name, len, 1); + /* + * If DYNAMIC_FTRACE is not set, then we just trace all functions. + * This test really doesn't care. + */ + if (ret && ret != -ENODEV) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_regs_probe); + /* + * Now if the arch does not support passing regs, then this should + * have failed. + */ + if (!supported) { + if (!ret) { + pr_cont("*registered save-regs without arch support* "); + goto out; + } + test_regs_probe.flags |= FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED; + ret = register_ftrace_function(&test_regs_probe); + } + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_regs_probe); + + ret = -1; + + switch (trace_selftest_regs_stat) { + case TRACE_SELFTEST_REGS_START: + pr_cont("*callback never called* "); + goto out; + + case TRACE_SELFTEST_REGS_FOUND: + if (supported) + break; + pr_cont("*callback received regs without arch support* "); + goto out; + + case TRACE_SELFTEST_REGS_NOT_FOUND: + if (!supported) + break; + pr_cont("*callback received NULL regs* "); + goto out; + } + + ret = 0; +out: + ftrace_enabled = save_ftrace_enabled; + tracer_enabled = save_tracer_enabled; + + return ret; +} + /* * Simple verification test of ftrace function tracer. * Enable ftrace, sleep 1/10 second, and then read the trace @@ -592,6 +702,10 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) goto out; ret = trace_selftest_function_recursion(); + if (ret) + goto out; + + ret = trace_selftest_function_regs(); out: ftrace_enabled = save_ftrace_enabled; tracer_enabled = save_tracer_enabled; -- cgit v1.2.3-70-g09d2 From 647664eaf4033501739ac1f42dd52ce8c9266ccc Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 5 Jun 2012 19:28:08 +0900 Subject: ftrace: add ftrace_set_filter_ip() for address based filter Add a new filter update interface ftrace_set_filter_ip() to set ftrace filter by ip address, not only glob pattern. Link: http://lkml.kernel.org/r/20120605102808.27845.67952.stgit@localhost.localdomain Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Ananth N Mavinakayanahalli Cc: "Frank Ch. Eigler" Cc: Andrew Morton Cc: Frederic Weisbecker Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 3 +++ kernel/trace/ftrace.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 60 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9962e954a63..3e711122f66 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -317,6 +317,8 @@ struct dyn_ftrace { }; int ftrace_force_update(void); +int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, + int remove, int reset); int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset); int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, @@ -544,6 +546,7 @@ static inline int ftrace_text_reserved(void *start, void *end) */ #define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; }) #define ftrace_set_early_filter(ops, buf, enable) do { } while (0) +#define ftrace_set_filter_ip(ops, ip, remove, reset) ({ -ENODEV; }) #define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_free_filter(ops) do { } while (0) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 528d997c7f9..9dcf15d3838 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3242,8 +3242,27 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf, } static int -ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, - int reset, int enable) +ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) +{ + struct ftrace_func_entry *entry; + + if (!ftrace_location(ip)) + return -EINVAL; + + if (remove) { + entry = ftrace_lookup_ip(hash, ip); + if (!entry) + return -ENOENT; + free_hash_entry(hash, entry); + return 0; + } + + return add_hash_entry(hash, ip); +} + +static int +ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, + unsigned long ip, int remove, int reset, int enable) { struct ftrace_hash **orig_hash; struct ftrace_hash *hash; @@ -3272,6 +3291,11 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, ret = -EINVAL; goto out_regex_unlock; } + if (ip) { + ret = ftrace_match_addr(hash, ip, remove); + if (ret < 0) + goto out_regex_unlock; + } mutex_lock(&ftrace_lock); ret = ftrace_hash_move(ops, enable, orig_hash, hash); @@ -3288,6 +3312,37 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, return ret; } +static int +ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove, + int reset, int enable) +{ + return ftrace_set_hash(ops, 0, 0, ip, remove, reset, enable); +} + +/** + * ftrace_set_filter_ip - set a function to filter on in ftrace by address + * @ops - the ops to set the filter with + * @ip - the address to add to or remove from the filter. + * @remove - non zero to remove the ip from the filter + * @reset - non zero to reset all filters before applying this filter. + * + * Filters denote which functions should be enabled when tracing is enabled + * If @ip is NULL, it failes to update filter. + */ +int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, + int remove, int reset) +{ + return ftrace_set_addr(ops, ip, remove, reset, 1); +} +EXPORT_SYMBOL_GPL(ftrace_set_filter_ip); + +static int +ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, + int reset, int enable) +{ + return ftrace_set_hash(ops, buf, len, 0, 0, reset, enable); +} + /** * ftrace_set_filter - set a function to filter on in ftrace * @ops - the ops to set the filter with -- cgit v1.2.3-70-g09d2 From 3c18c10bde65b6dcaffab7a4d040285e4defa49b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 31 Jul 2012 10:23:37 -0400 Subject: tracing: Fix wakeup_rt self test on virtual machines The warkeup_rt self test used msleep() calls to wait for real time tasks to wake up and run. On bare-metal hardware, this was enough as the scheduler should let the RT task run way before the non-RT task wakes up from the msleep(). If it did not, then that would mean the scheduler was broken. But when dealing with virtual machines, this is a different story. If the RT task wakes up on a VCPU, it's up to the host to decide when that task gets to schedule, which can be far behind the time that the non-RT task wakes up. In this case, the test would fail incorrectly. As we are not testing the scheduler, but instead the wake up tracing, we can use completions to wait and not depend on scheduler timings to see if events happen on time. Link: http://lkml.kernel.org/r/1343663105.3847.7.camel@fedora Reported-by: Fengguang Wu Tested-by: Fengguang Wu Signed-off-by: Steven Rostedt --- kernel/trace/trace_selftest.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 1003a4d5eb2..2c00a691a54 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -1041,6 +1041,8 @@ static int trace_wakeup_test_thread(void *data) set_current_state(TASK_INTERRUPTIBLE); schedule(); + complete(x); + /* we are awake, now wait to disappear */ while (!kthread_should_stop()) { /* @@ -1084,24 +1086,21 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) /* reset the max latency */ tracing_max_latency = 0; - /* sleep to let the RT thread sleep too */ - msleep(100); + while (p->on_rq) { + /* + * Sleep to make sure the RT thread is asleep too. + * On virtual machines we can't rely on timings, + * but we want to make sure this test still works. + */ + msleep(100); + } - /* - * Yes this is slightly racy. It is possible that for some - * strange reason that the RT thread we created, did not - * call schedule for 100ms after doing the completion, - * and we do a wakeup on a task that already is awake. - * But that is extremely unlikely, and the worst thing that - * happens in such a case, is that we disable tracing. - * Honestly, if this race does happen something is horrible - * wrong with the system. - */ + init_completion(&isrt); wake_up_process(p); - /* give a little time to let the thread wake up */ - msleep(100); + /* Wait for the task to wake up */ + wait_for_completion(&isrt); /* stop the tracing. */ tracing_stop(); -- cgit v1.2.3-70-g09d2 From 92d8d4a8b0f4c6eba70f6e62b48e38bd005a56e6 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 19 Jun 2012 17:47:52 +0200 Subject: tracing/filter: Add missing initialization Add missing initialization for ret variable. Its initialization is based on the re_cnt variable, which is being set deep down in the ftrace_function_filter_re function. I'm not sure compilers would be smart enough to see this in near future, so killing the warning this way. Link: http://lkml.kernel.org/r/1340120894-9465-2-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_filter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 431dba8b754..c154797a7ff 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -2002,7 +2002,7 @@ static int ftrace_function_set_regexp(struct ftrace_ops *ops, int filter, static int __ftrace_function_set_filter(int filter, char *buf, int len, struct function_filter_data *data) { - int i, re_cnt, ret; + int i, re_cnt, ret = -EINVAL; int *reset; char **re; -- cgit v1.2.3-70-g09d2 From 87abb3b15c62033409f5bf2ffb5620c94f91cf2c Mon Sep 17 00:00:00 2001 From: Wang Tianhong Date: Thu, 2 Aug 2012 14:02:00 +0800 Subject: tracing/trivial: Fix some typos in kernel/trace Fix some typos in kernel/trace. Link: http://lkml.kernel.org/r/1343887320.2228.9.camel@louis-ThinkPad-T410 Signed-off-by: Wang Tianhong Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 4 ++-- kernel/trace/trace.c | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 49491fa7daa..b32ed0e385a 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2816,7 +2816,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_enable); * to the buffer after this will fail and return NULL. * * This is different than ring_buffer_record_disable() as - * it works like an on/off switch, where as the disable() verison + * it works like an on/off switch, where as the disable() version * must be paired with a enable(). */ void ring_buffer_record_off(struct ring_buffer *buffer) @@ -2839,7 +2839,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_off); * ring_buffer_record_off(). * * This is different than ring_buffer_record_enable() as - * it works like an on/off switch, where as the enable() verison + * it works like an on/off switch, where as the enable() version * must be paired with a disable(). */ void ring_buffer_record_on(struct ring_buffer *buffer) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a120f98c411..d1a8d07ec86 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -426,15 +426,15 @@ __setup("trace_buf_size=", set_buf_size); static int __init set_tracing_thresh(char *str) { - unsigned long threshhold; + unsigned long threshold; int ret; if (!str) return 0; - ret = strict_strtoul(str, 0, &threshhold); + ret = strict_strtoul(str, 0, &threshold); if (ret < 0) return 0; - tracing_thresh = threshhold * 1000; + tracing_thresh = threshold * 1000; return 1; } __setup("tracing_thresh=", set_tracing_thresh); -- cgit v1.2.3-70-g09d2 From a2546fae01124fb8063747439300fcf39bac033a Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 9 Feb 2011 13:15:59 -0500 Subject: ftrace: Add -mfentry to Makefile on function tracer Thanks to Andi Kleen, gcc 4.6.0 now supports -mfentry for x86 (and hopefully soon for other archs). What this does is to have the function profiler start at the beginning of the function instead of after the stack is set up. As plain -pg (mcount) is called after the stack is set up, and in some cases can have issues with the function graph tracer. It also requires frame pointers to be enabled. The -mfentry now calls __fentry__ at the beginning of the function. This allows for compiling without frame pointers and even has the ability to access parameters if needed. If the architecture and the compiler both support -mfentry then use that instead. Link: http://lkml.kernel.org/r/20120807194059.392617243@goodmis.org Acked-by: H. Peter Anvin Acked-by: Ingo Molnar Cc: Michal Marek Cc: Andi Kleen Signed-off-by: Steven Rostedt --- Makefile | 6 +++++- kernel/trace/Kconfig | 5 +++++ 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/Makefile b/Makefile index ddf5be952e4..e7ca93f1785 100644 --- a/Makefile +++ b/Makefile @@ -609,7 +609,11 @@ KBUILD_CFLAGS += $(call cc-option, -femit-struct-debug-baseonly) endif ifdef CONFIG_FUNCTION_TRACER -KBUILD_CFLAGS += -pg +ifdef CONFIG_HAVE_FENTRY +CC_USING_FENTRY := $(call cc-option, -mfentry -DCC_USING_FENTRY) +endif +KBUILD_CFLAGS += -pg $(CC_USING_FENTRY) +KBUILD_AFLAGS += $(CC_USING_FENTRY) ifdef CONFIG_DYNAMIC_FTRACE ifdef CONFIG_HAVE_C_RECORDMCOUNT BUILD_C_RECORDMCOUNT := y diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 8c4c07071cc..9301a0e35e0 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -49,6 +49,11 @@ config HAVE_SYSCALL_TRACEPOINTS help See Documentation/trace/ftrace-design.txt +config HAVE_FENTRY + bool + help + Arch supports the gcc options -pg with -mfentry + config HAVE_C_RECORDMCOUNT bool help -- cgit v1.2.3-70-g09d2 From 781d06248234e221edb560a18461d65808a8a942 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 9 Feb 2011 13:27:22 -0500 Subject: ftrace: Do not test frame pointers if -mfentry is used The function graph has a test to check if the frame pointer is corrupted, which can happen with various options of gcc with mcount. But this is not an issue with -mfentry as -mfentry does not need nor use frame pointers for function graph tracing. Link: http://lkml.kernel.org/r/20120807194059.773895870@goodmis.org Acked-by: H. Peter Anvin Acked-by: Ingo Molnar Cc: Andi Kleen Signed-off-by: Steven Rostedt --- kernel/trace/trace_functions_graph.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index ce27c8ba8d3..99b4378393d 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -143,7 +143,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, return; } -#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST +#if defined(CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST) && !defined(CC_USING_FENTRY) /* * The arch may choose to record the frame pointer used * and check it here to make sure that it is what we expect it @@ -154,6 +154,9 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, * * 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(); -- cgit v1.2.3-70-g09d2 From 65f8c95e46a1827ae8bbc52a817ea308dd7d65ae Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Tue, 17 Jul 2012 14:26:15 -0700 Subject: pstore/ftrace: Convert to its own enable/disable debugfs knob With this patch we no longer reuse function tracer infrastructure, now we register our own tracer back-end via a debugfs knob. It's a bit more code, but that is the only downside. On the bright side we have: - Ability to make persistent_ram module removable (when needed, we can move ftrace_ops struct into a module). Note that persistent_ram is still not removable for other reasons, but with this patch it's just one thing less to worry about; - Pstore part is more isolated from the generic function tracer. We tried it already by registering our own tracer in available_tracers, but that way we're loosing ability to see the traces while we record them to pstore. This solution is somewhere in the middle: we only register "internal ftracer" back-end, but not the "front-end"; - When there is only pstore tracing enabled, the kernel will only write to the pstore buffer, omitting function tracer buffer (which, of course, still can be enabled via 'echo function > current_tracer'). Suggested-by: Steven Rostedt Signed-off-by: Anton Vorontsov --- Documentation/ramoops.txt | 4 +- fs/pstore/Kconfig | 1 + fs/pstore/ftrace.c | 96 +++++++++++++++++++++++++++++++++++++++++- fs/pstore/internal.h | 6 +++ fs/pstore/platform.c | 1 + include/linux/pstore.h | 8 ---- kernel/trace/trace_functions.c | 15 +------ 7 files changed, 105 insertions(+), 26 deletions(-) (limited to 'kernel/trace') diff --git a/Documentation/ramoops.txt b/Documentation/ramoops.txt index 197ad59ab9b..69b3cac4749 100644 --- a/Documentation/ramoops.txt +++ b/Documentation/ramoops.txt @@ -102,9 +102,7 @@ related hangs. The functions call chain log is stored in a "ftrace-ramoops" file. Here is an example of usage: # mount -t debugfs debugfs /sys/kernel/debug/ - # cd /sys/kernel/debug/tracing - # echo function > current_tracer - # echo 1 > options/func_pstore + # echo 1 > /sys/kernel/debug/pstore/record_ftrace # reboot -f [...] # mount -t pstore pstore /mnt/ diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index d39bb5cce88..ca71db69da0 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -23,6 +23,7 @@ config PSTORE_FTRACE bool "Persistent function tracer" depends on PSTORE depends on FUNCTION_TRACER + depends on DEBUG_FS help With this option kernel traces function calls into a persistent ram buffer that can be decoded and dumped after reboot through diff --git a/fs/pstore/ftrace.c b/fs/pstore/ftrace.c index a130d484b7d..2d57e1ac011 100644 --- a/fs/pstore/ftrace.c +++ b/fs/pstore/ftrace.c @@ -17,19 +17,113 @@ #include #include #include +#include +#include +#include +#include +#include +#include +#include #include #include "internal.h" -void notrace pstore_ftrace_call(unsigned long ip, unsigned long parent_ip) +static void notrace pstore_ftrace_call(unsigned long ip, + unsigned long parent_ip) { + unsigned long flags; struct pstore_ftrace_record rec = {}; if (unlikely(oops_in_progress)) return; + local_irq_save(flags); + rec.ip = ip; rec.parent_ip = parent_ip; pstore_ftrace_encode_cpu(&rec, raw_smp_processor_id()); psinfo->write_buf(PSTORE_TYPE_FTRACE, 0, NULL, 0, (void *)&rec, sizeof(rec), psinfo); + + local_irq_restore(flags); +} + +static struct ftrace_ops pstore_ftrace_ops __read_mostly = { + .func = pstore_ftrace_call, +}; + +static DEFINE_MUTEX(pstore_ftrace_lock); +static bool pstore_ftrace_enabled; + +static ssize_t pstore_ftrace_knob_write(struct file *f, const char __user *buf, + size_t count, loff_t *ppos) +{ + u8 on; + ssize_t ret; + + ret = kstrtou8_from_user(buf, count, 2, &on); + if (ret) + return ret; + + mutex_lock(&pstore_ftrace_lock); + + if (!on ^ pstore_ftrace_enabled) + goto out; + + if (on) + ret = register_ftrace_function(&pstore_ftrace_ops); + else + ret = unregister_ftrace_function(&pstore_ftrace_ops); + if (ret) { + pr_err("%s: unable to %sregister ftrace ops: %zd\n", + __func__, on ? "" : "un", ret); + goto err; + } + + pstore_ftrace_enabled = on; +out: + ret = count; +err: + mutex_unlock(&pstore_ftrace_lock); + + return ret; +} + +static ssize_t pstore_ftrace_knob_read(struct file *f, char __user *buf, + size_t count, loff_t *ppos) +{ + char val[] = { '0' + pstore_ftrace_enabled, '\n' }; + + return simple_read_from_buffer(buf, count, ppos, val, sizeof(val)); +} + +static const struct file_operations pstore_knob_fops = { + .open = simple_open, + .read = pstore_ftrace_knob_read, + .write = pstore_ftrace_knob_write, +}; + +void pstore_register_ftrace(void) +{ + struct dentry *dir; + struct dentry *file; + + if (!psinfo->write_buf) + return; + + dir = debugfs_create_dir("pstore", NULL); + if (!dir) { + pr_err("%s: unable to create pstore directory\n", __func__); + return; + } + + file = debugfs_create_file("record_ftrace", 0600, dir, NULL, + &pstore_knob_fops); + if (!file) { + pr_err("%s: unable to create record_ftrace file\n", __func__); + goto err_file; + } + + return; +err_file: + debugfs_remove(dir); } diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index 0d0d3b7d5f1..4847f588b7d 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -39,6 +39,12 @@ pstore_ftrace_decode_cpu(struct pstore_ftrace_record *rec) #endif } +#ifdef CONFIG_PSTORE_FTRACE +extern void pstore_register_ftrace(void); +#else +static inline void pstore_register_ftrace(void) {} +#endif + extern struct pstore_info *psinfo; extern void pstore_set_kmsg_bytes(int); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 29996e8793a..6c23eab7f76 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -236,6 +236,7 @@ int pstore_register(struct pstore_info *psi) kmsg_dump_register(&pstore_dumper); pstore_register_console(); + pstore_register_ftrace(); if (pstore_update_ms >= 0) { pstore_timer.expires = jiffies + diff --git a/include/linux/pstore.h b/include/linux/pstore.h index c892587d9b8..ee3034a4088 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -64,14 +64,6 @@ struct pstore_info { void *data; }; - -#ifdef CONFIG_PSTORE_FTRACE -extern void pstore_ftrace_call(unsigned long ip, unsigned long parent_ip); -#else -static inline void pstore_ftrace_call(unsigned long ip, unsigned long parent_ip) -{ } -#endif - #ifdef CONFIG_PSTORE extern int pstore_register(struct pstore_info *); #else diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index a426f410c06..0ad83e3929d 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include "trace.h" @@ -75,10 +74,9 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) preempt_enable_notrace(); } -/* Our two options */ +/* Our option */ enum { TRACE_FUNC_OPT_STACK = 0x1, - TRACE_FUNC_OPT_PSTORE = 0x2, }; static struct tracer_flags func_flags; @@ -106,12 +104,6 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { - /* - * So far tracing doesn't support multiple buffers, so - * we make an explicit call for now. - */ - if (unlikely(func_flags.val & TRACE_FUNC_OPT_PSTORE)) - pstore_ftrace_call(ip, parent_ip); pc = preempt_count(); trace_function(tr, ip, parent_ip, flags, pc); } @@ -176,9 +168,6 @@ static struct ftrace_ops trace_stack_ops __read_mostly = static struct tracer_opt func_opts[] = { #ifdef CONFIG_STACKTRACE { TRACER_OPT(func_stack_trace, TRACE_FUNC_OPT_STACK) }, -#endif -#ifdef CONFIG_PSTORE_FTRACE - { TRACER_OPT(func_pstore, TRACE_FUNC_OPT_PSTORE) }, #endif { } /* Always set a last empty entry */ }; @@ -231,8 +220,6 @@ static int func_set_flag(u32 old_flags, u32 bit, int set) register_ftrace_function(&trace_ops); } - break; - case TRACE_FUNC_OPT_PSTORE: break; default: return -EINVAL; -- cgit v1.2.3-70-g09d2 From 76bab1b78ab6f25d5f74165f94526c25fc93d984 Mon Sep 17 00:00:00 2001 From: Yuanhan Liu Date: Mon, 27 Aug 2012 15:13:45 +0800 Subject: tracing: Skip printing "OK" if failed to disable event No acutal case found. But logically, we should skip "OK" in case any error met. Link: http://lkml.kernel.org/r/1346051625-25231-1-git-send-email-yuanhan.liu@linux.intel.com Signed-off-by: Yuanhan Liu Signed-off-by: Steven Rostedt --- kernel/trace/trace_events.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 6825d833a25..bbb0e63d78e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1646,9 +1646,11 @@ static __init void event_trace_self_tests(void) event_test_stuff(); ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0); - if (WARN_ON_ONCE(ret)) + if (WARN_ON_ONCE(ret)) { pr_warning("error disabling system %s\n", system->name); + continue; + } pr_cont("OK\n"); } -- cgit v1.2.3-70-g09d2 From ea632e9f12033346cc68247faa3b924d54936b8b Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Sun, 2 Sep 2012 19:45:14 -0700 Subject: trace: Stop compiling in trace_clock unconditionally Commit 56449f437 "tracing: make the trace clocks available generally", in April 2009, made trace_clock available unconditionally, since CONFIG_X86_DS used it too. Commit faa4602e47 "x86, perf, bts, mm: Delete the never used BTS-ptrace code", in March 2010, removed CONFIG_X86_DS, and now only CONFIG_RING_BUFFER (split out from CONFIG_TRACING for general use) has a dependency on trace_clock. So, only compile in trace_clock with CONFIG_RING_BUFFER or CONFIG_TRACING enabled. Link: http://lkml.kernel.org/r/20120903024513.GA19583@leaf Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Andrew Morton Cc: "Eric W. Biederman" Cc: Al Viro Signed-off-by: Josh Triplett Signed-off-by: Steven Rostedt --- kernel/Makefile | 2 +- kernel/trace/Kconfig | 5 +++++ kernel/trace/Makefile | 6 +----- 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/Makefile b/kernel/Makefile index c0cc67ad764..29d993be7db 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -98,7 +98,7 @@ obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ -obj-$(CONFIG_X86_DS) += trace/ +obj-$(CONFIG_TRACE_CLOCK) += trace/ obj-$(CONFIG_RING_BUFFER) += trace/ obj-$(CONFIG_TRACEPOINTS) += trace/ obj-$(CONFIG_IRQ_WORK) += irq_work.o diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 9301a0e35e0..4cea4f41c1d 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -62,8 +62,12 @@ config HAVE_C_RECORDMCOUNT config TRACER_MAX_TRACE bool +config TRACE_CLOCK + bool + config RING_BUFFER bool + select TRACE_CLOCK config FTRACE_NMI_ENTER bool @@ -114,6 +118,7 @@ config TRACING select NOP_TRACER select BINARY_PRINTF select EVENT_TRACING + select TRACE_CLOCK config GENERIC_TRACER bool diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 837090808aa..d7e2068e4b7 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -19,11 +19,7 @@ endif CFLAGS_trace_events_filter.o := -I$(src) -# -# Make the trace clocks available generally: it's infrastructure -# relied on by ptrace for example: -# -obj-y += trace_clock.o +obj-$(CONFIG_TRACE_CLOCK) += trace_clock.o obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o obj-$(CONFIG_RING_BUFFER) += ring_buffer.o -- cgit v1.2.3-70-g09d2 From d20b92ab668cc44fc84bba0001839c5a8013a5cd Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 13 Mar 2012 16:02:19 -0700 Subject: userns: Teach trace to use from_kuid - When tracing capture the kuid. - When displaying the data to user space convert the kuid into the user namespace of the process that opened the report file. Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Ingo Molnar Signed-off-by: Eric W. Biederman --- init/Kconfig | 1 - kernel/trace/trace.c | 3 ++- kernel/trace/trace.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/trace') diff --git a/init/Kconfig b/init/Kconfig index 6de46ef12e3..2a388e569a2 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -927,7 +927,6 @@ config UIDGID_CONVERTED # Features depends on IMA = n depends on EVM = n - depends on TRACING = n depends on FS_POSIX_ACL = n depends on QUOTA = n depends on QUOTACTL = n diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5c38c81496c..c9ace838d50 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2060,7 +2060,8 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) seq_puts(m, "# -----------------\n"); seq_printf(m, "# | task: %.16s-%d " "(uid:%d nice:%ld policy:%ld rt_prio:%ld)\n", - data->comm, data->pid, data->uid, data->nice, + data->comm, data->pid, + from_kuid_munged(seq_user_ns(m), data->uid), data->nice, data->policy, data->rt_priority); seq_puts(m, "# -----------------\n"); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 55e1f7f0db1..40a6f30c985 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -147,7 +147,7 @@ struct trace_array_cpu { unsigned long skipped_entries; cycle_t preempt_timestamp; pid_t pid; - uid_t uid; + kuid_t uid; char comm[TASK_COMM_LEN]; }; -- cgit v1.2.3-70-g09d2 From 5224c3a31549f1c056039545b289e1b01ed02f12 Mon Sep 17 00:00:00 2001 From: Mandeep Singh Baines Date: Fri, 7 Sep 2012 18:12:19 -0700 Subject: tracing: Add an option for disabling markers In our application, we have trace markers spread through user-space. We have markers in GL, X, etc. These are super handy for Chrome's about:tracing feature (Chrome + system + kernel trace view), but can be very distracting when you're trying to debug a kernel issue. I normally, use "grep -v tracing_mark_write" but it would be nice if I could just temporarily disable markers all together. Link: http://lkml.kernel.org/r/1347066739-26285-1-git-send-email-msb@chromium.org CC: Frederic Weisbecker Signed-off-by: Mandeep Singh Baines Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 6 +++++- kernel/trace/trace.h | 1 + 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 08acf42e325..1ec5c1dab62 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -328,7 +328,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait); unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME | TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | - TRACE_ITER_IRQ_INFO; + TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS; static int trace_stop_count; static DEFINE_RAW_SPINLOCK(tracing_start_lock); @@ -470,6 +470,7 @@ static const char *trace_options[] = { "overwrite", "disable_on_free", "irq-info", + "markers", NULL }; @@ -3886,6 +3887,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (tracing_disabled) return -EINVAL; + if (!(trace_flags & TRACE_ITER_MARKERS)) + return -EINVAL; + if (cnt > TRACE_BUF_SIZE) cnt = TRACE_BUF_SIZE; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 593debefc4e..63a2da0b9a6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -680,6 +680,7 @@ enum trace_iterator_flags { TRACE_ITER_OVERWRITE = 0x200000, TRACE_ITER_STOP_ON_FREE = 0x400000, TRACE_ITER_IRQ_INFO = 0x800000, + TRACE_ITER_MARKERS = 0x1000000, }; /* -- cgit v1.2.3-70-g09d2 From 8781915ad2716adcd8cd5cc52cee791fc8b00fdf Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Wed, 12 Sep 2012 11:47:57 -0300 Subject: trace: Move trace event enable from fs_initcall to core_initcall This patch splits trace event initialization in two stages: * ftrace enable * sysfs event entry creation This allows to capture trace events from an earlier point by using 'trace_event' kernel parameter and is important to trace boot-up allocations. Note that, in order to enable events at core_initcall, it's necessary to move init_ftrace_syscalls() from core_initcall to early_initcall. Link: http://lkml.kernel.org/r/1347461277-25302-1-git-send-email-elezegarcia@gmail.com Signed-off-by: Ezequiel Garcia Signed-off-by: Steven Rostedt --- kernel/trace/trace_events.c | 108 ++++++++++++++++++++++++++++-------------- kernel/trace/trace_syscalls.c | 2 +- 2 files changed, 73 insertions(+), 37 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index bbb0e63d78e..d608d09d08c 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1199,6 +1199,31 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, return 0; } +static void event_remove(struct ftrace_event_call *call) +{ + ftrace_event_enable_disable(call, 0); + if (call->event.funcs) + __unregister_ftrace_event(&call->event); + list_del(&call->list); +} + +static int event_init(struct ftrace_event_call *call) +{ + int ret = 0; + + if (WARN_ON(!call->name)) + return -EINVAL; + + if (call->class->raw_init) { + ret = call->class->raw_init(call); + if (ret < 0 && ret != -ENOSYS) + pr_warn("Could not initialize trace events/%s\n", + call->name); + } + + return ret; +} + static int __trace_add_event_call(struct ftrace_event_call *call, struct module *mod, const struct file_operations *id, @@ -1209,19 +1234,9 @@ __trace_add_event_call(struct ftrace_event_call *call, struct module *mod, struct dentry *d_events; int ret; - /* The linker may leave blanks */ - if (!call->name) - return -EINVAL; - - if (call->class->raw_init) { - ret = call->class->raw_init(call); - if (ret < 0) { - if (ret != -ENOSYS) - pr_warning("Could not initialize trace events/%s\n", - call->name); - return ret; - } - } + ret = event_init(call); + if (ret < 0) + return ret; d_events = event_trace_events_dir(); if (!d_events) @@ -1272,13 +1287,10 @@ static void remove_subsystem_dir(const char *name) */ static void __trace_remove_event_call(struct ftrace_event_call *call) { - ftrace_event_enable_disable(call, 0); - if (call->event.funcs) - __unregister_ftrace_event(&call->event); - debugfs_remove_recursive(call->dir); - list_del(&call->list); + event_remove(call); trace_destroy_fields(call); destroy_preds(call); + debugfs_remove_recursive(call->dir); remove_subsystem_dir(call->class->system); } @@ -1450,15 +1462,43 @@ static __init int setup_trace_event(char *str) } __setup("trace_event=", setup_trace_event); +static __init int event_trace_enable(void) +{ + struct ftrace_event_call **iter, *call; + char *buf = bootup_event_buf; + char *token; + int ret; + + for_each_event(iter, __start_ftrace_events, __stop_ftrace_events) { + + call = *iter; + ret = event_init(call); + if (!ret) + list_add(&call->list, &ftrace_events); + } + + while (true) { + token = strsep(&buf, ","); + + if (!token) + break; + if (!*token) + continue; + + ret = ftrace_set_clr_event(token, 1); + if (ret) + pr_warn("Failed to enable trace event: %s\n", token); + } + return 0; +} + static __init int event_trace_init(void) { - struct ftrace_event_call **call; + struct ftrace_event_call *call; struct dentry *d_tracer; struct dentry *entry; struct dentry *d_events; int ret; - char *buf = bootup_event_buf; - char *token; d_tracer = tracing_init_dentry(); if (!d_tracer) @@ -1497,24 +1537,19 @@ static __init int event_trace_init(void) if (trace_define_common_fields()) pr_warning("tracing: Failed to allocate common fields"); - for_each_event(call, __start_ftrace_events, __stop_ftrace_events) { - __trace_add_event_call(*call, NULL, &ftrace_event_id_fops, + /* + * Early initialization already enabled ftrace event. + * Now it's only necessary to create the event directory. + */ + list_for_each_entry(call, &ftrace_events, list) { + + ret = event_create_dir(call, d_events, + &ftrace_event_id_fops, &ftrace_enable_fops, &ftrace_event_filter_fops, &ftrace_event_format_fops); - } - - while (true) { - token = strsep(&buf, ","); - - if (!token) - break; - if (!*token) - continue; - - ret = ftrace_set_clr_event(token, 1); - if (ret) - pr_warning("Failed to enable trace event: %s\n", token); + if (ret < 0) + event_remove(call); } ret = register_module_notifier(&trace_module_nb); @@ -1523,6 +1558,7 @@ static __init int event_trace_init(void) return 0; } +core_initcall(event_trace_enable); fs_initcall(event_trace_init); #ifdef CONFIG_FTRACE_STARTUP_TEST diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 6b245f64c8d..2485a7d09b1 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -487,7 +487,7 @@ int __init init_ftrace_syscalls(void) return 0; } -core_initcall(init_ftrace_syscalls); +early_initcall(init_ftrace_syscalls); #ifdef CONFIG_PERF_EVENTS -- cgit v1.2.3-70-g09d2 From d55cb6cf143ae16eaa415baab520b8eaf4a1012f Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 9 Aug 2012 21:31:10 +0900 Subject: ftrace: Allow stealing pages from pipe buffer Use generic steal operation on pipe buffer to allow stealing ring buffer's read page from pipe buffer. Note that this could reduce the performance of splice on the splice_write side operation without affinity setting. Since the ring buffer's read pages are allocated on the tracing-node, but the splice user does not always execute splice write side operation on the same node. In this case, the page will be accessed from the another node. Thus, it is strongly recommended to assign the splicing thread to corresponding node. Signed-off-by: Masami Hiramatsu Acked-by: Steven Rostedt Signed-off-by: Rusty Russell --- kernel/trace/trace.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5c38c81496c..adde0994911 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4195,12 +4195,6 @@ static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, buf->private = 0; } -static int buffer_pipe_buf_steal(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) -{ - return 1; -} - static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { @@ -4216,7 +4210,7 @@ static const struct pipe_buf_operations buffer_pipe_buf_ops = { .unmap = generic_pipe_buf_unmap, .confirm = generic_pipe_buf_confirm, .release = buffer_pipe_buf_release, - .steal = buffer_pipe_buf_steal, + .steal = generic_pipe_buf_steal, .get = buffer_pipe_buf_get, }; -- cgit v1.2.3-70-g09d2 From 8e49f418c9632790bf456634742d34d97120a784 Mon Sep 17 00:00:00 2001 From: Vaibhav Nagarnaik Date: Wed, 10 Oct 2012 16:40:27 -0700 Subject: ring-buffer: Check for uninitialized cpu buffer before resizing With a system where, num_present_cpus < num_possible_cpus, even if all CPUs are online, non-present CPUs don't have per_cpu buffers allocated. If per_cpu//buffer_size_kb is modified for such a CPU, it can cause a panic due to NULL dereference in ring_buffer_resize(). To fix this, resize operation is allowed only if the per-cpu buffer has been initialized. Link: http://lkml.kernel.org/r/1349912427-6486-1-git-send-email-vnagarnaik@google.com Cc: stable@vger.kernel.org # 3.5+ Signed-off-by: Vaibhav Nagarnaik Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b32ed0e385a..b979426d16c 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1567,6 +1567,10 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, put_online_cpus(); } else { + /* Make sure this CPU has been intitialized */ + if (!cpumask_test_cpu(cpu_id, buffer->cpumask)) + goto out; + cpu_buffer = buffer->buffers[cpu_id]; if (nr_pages == cpu_buffer->nr_pages) -- cgit v1.2.3-70-g09d2