From bd3bff9e20f454b242d979ec2f9a4dca0d5fa06f Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:20:41 +0200 Subject: sched: add latency tracer callbacks to the scheduler add 3 lightweight callbacks to the tracer backend. zero impact if tracing is turned off. Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5395a6176f4b..717cab8a0c83 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2117,6 +2117,32 @@ static inline void arch_pick_mmap_layout(struct mm_struct *mm) } #endif +#ifdef CONFIG_CONTEXT_SWITCH_TRACER +extern void +ftrace_ctx_switch(struct task_struct *prev, struct task_struct *next); +#else +static inline void +ftrace_ctx_switch(struct task_struct *prev, struct task_struct *next) +{ +} +#endif + +#ifdef CONFIG_SCHED_TRACER +extern void +ftrace_wake_up_task(struct task_struct *wakee, struct task_struct *curr); +extern void +ftrace_wake_up_new_task(struct task_struct *wakee, struct task_struct *curr); +#else +static inline void +ftrace_wake_up_task(struct task_struct *wakee, struct task_struct *curr) +{ +} +static inline void +ftrace_wake_up_new_task(struct task_struct *wakee, struct task_struct *curr) +{ +} +#endif + extern long sched_setaffinity(pid_t pid, const cpumask_t *new_mask); extern long sched_getaffinity(pid_t pid, cpumask_t *mask); -- cgit v1.2.3 From 7c731e0a495e25e79dc1e9e68772a67a55721a65 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:41 +0200 Subject: ftrace: make the task state char-string visible to all The tracer wants to be able to convert the state number into a user visible character. This patch pulls that conversion string out the scheduler into the header. This way if it were to ever change, other parts of the kernel will know. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 717cab8a0c83..6e26f1fdbfe2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2237,6 +2237,8 @@ static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p) } #endif /* CONFIG_MM_OWNER */ +#define TASK_STATE_TO_CHAR_STR "RSDTtZX" + #endif /* __KERNEL__ */ #endif -- cgit v1.2.3 From 502825282e6f79c975a644afc124432ec1744de4 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:41 +0200 Subject: ftrace: add preempt_enable/disable notrace macros The tracer may need to call preempt_enable and disable functions for time keeping and such. The trace gets ugly when we see these functions show up for all traces. To make the output cleaner this patch adds preempt_enable_notrace and preempt_disable_notrace to be used by tracer (and debugging) functions. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/preempt.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include') diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 23f0c54175cd..36b03d50bf40 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -52,6 +52,34 @@ do { \ preempt_check_resched(); \ } while (0) +/* For debugging and tracer internals only! */ +#define add_preempt_count_notrace(val) \ + do { preempt_count() += (val); } while (0) +#define sub_preempt_count_notrace(val) \ + do { preempt_count() -= (val); } while (0) +#define inc_preempt_count_notrace() add_preempt_count_notrace(1) +#define dec_preempt_count_notrace() sub_preempt_count_notrace(1) + +#define preempt_disable_notrace() \ +do { \ + inc_preempt_count_notrace(); \ + barrier(); \ +} while (0) + +#define preempt_enable_no_resched_notrace() \ +do { \ + barrier(); \ + dec_preempt_count_notrace(); \ +} while (0) + +/* preempt_check_resched is OK to trace */ +#define preempt_enable_notrace() \ +do { \ + preempt_enable_no_resched_notrace(); \ + barrier(); \ + preempt_check_resched(); \ +} while (0) + #else #define preempt_disable() do { } while (0) @@ -59,6 +87,10 @@ do { \ #define preempt_enable() do { } while (0) #define preempt_check_resched() do { } while (0) +#define preempt_disable_notrace() do { } while (0) +#define preempt_enable_no_resched_notrace() do { } while (0) +#define preempt_enable_notrace() do { } while (0) + #endif #ifdef CONFIG_PREEMPT_NOTIFIERS -- cgit v1.2.3 From ffdc1a09ae7e2cbd714a446ee38a27f625b5f1c8 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:20:41 +0200 Subject: tracing: add notrace to linkage.h notrace signals that a function should not be traced. Most of the time this is used by tracers to annotate code that cannot be traced - it's in a volatile state (such as in user vdso context or NMI context) or it's in the tracer internals. Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/linkage.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 2119610b24f8..14f329c64ba8 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -3,6 +3,8 @@ #include +#define notrace __attribute__((no_instrument_function)) + #ifdef __cplusplus #define CPP_ASMLINKAGE extern "C" #else -- cgit v1.2.3 From 23adec554a7648f99c8acc0caf49c66320cd2b84 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:41 +0200 Subject: x86: add notrace annotations to vsyscall. Add the notrace annotations to the vsyscall functions - there we are not in kernel context yet, so the tracer function cannot (and must not) be called. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/asm-x86/vsyscall.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-x86/vsyscall.h b/include/asm-x86/vsyscall.h index 17b3700949bf..6b66ff905af0 100644 --- a/include/asm-x86/vsyscall.h +++ b/include/asm-x86/vsyscall.h @@ -24,7 +24,8 @@ enum vsyscall_num { ((unused, __section__ (".vsyscall_gtod_data"),aligned(16))) #define __section_vsyscall_clock __attribute__ \ ((unused, __section__ (".vsyscall_clock"),aligned(16))) -#define __vsyscall_fn __attribute__ ((unused,__section__(".vsyscall_fn"))) +#define __vsyscall_fn \ + __attribute__ ((unused, __section__(".vsyscall_fn"))) notrace #define VGETCPU_RDTSCP 1 #define VGETCPU_LSL 2 -- cgit v1.2.3 From 16444a8a40d4c7b4f6de34af0cae1f76a4f6c901 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 12 May 2008 21:20:42 +0200 Subject: ftrace: add basic support for gcc profiler instrumentation If CONFIG_FTRACE is selected and /proc/sys/kernel/ftrace_enabled is set to a non-zero value the ftrace routine will be called everytime we enter a kernel function that is not marked with the "notrace" attribute. The ftrace routine will then call a registered function if a function happens to be registered. [ This code has been highly hacked by Steven Rostedt and Ingo Molnar, so don't blame Arnaldo for all of this ;-) ] Update: It is now possible to register more than one ftrace function. If only one ftrace function is registered, that will be the function that ftrace calls directly. If more than one function is registered, then ftrace will call a function that will loop through the functions to call. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 include/linux/ftrace.h (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h new file mode 100644 index 000000000000..b96ef14c249a --- /dev/null +++ b/include/linux/ftrace.h @@ -0,0 +1,38 @@ +#ifndef _LINUX_FTRACE_H +#define _LINUX_FTRACE_H + +#ifdef CONFIG_FTRACE + +#include + +#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) +#define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1)) +#define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2)) + +typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); + +struct ftrace_ops { + ftrace_func_t func; + struct ftrace_ops *next; +}; + +/* + * The ftrace_ops must be a static and should also + * be read_mostly. These functions do modify read_mostly variables + * so use them sparely. Never free an ftrace_op or modify the + * next pointer after it has been registered. Even after unregistering + * it, the next pointer may still be used internally. + */ +int register_ftrace_function(struct ftrace_ops *ops); +int unregister_ftrace_function(struct ftrace_ops *ops); +void clear_ftrace_function(void); + +extern void ftrace_stub(unsigned long a0, unsigned long a1); +extern void mcount(void); + +#else /* !CONFIG_FTRACE */ +# define register_ftrace_function(ops) do { } while (0) +# define unregister_ftrace_function(ops) do { } while (0) +# define clear_ftrace_function(ops) do { } while (0) +#endif /* CONFIG_FTRACE */ +#endif /* _LINUX_FTRACE_H */ -- cgit v1.2.3 From 352ad25aa4a189c667cb2af333948d34692a2d27 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:42 +0200 Subject: ftrace: tracer for scheduler wakeup latency This patch adds the tracer that tracks the wakeup latency of the highest priority waking task. "wakeup" is added to /debugfs/tracing/available_tracers Also added to /debugfs/tracing tracing_max_latency holds the current max latency for the wakeup wakeup_thresh if set to other than zero, a log will be recorded for every wakeup that takes longer than the number entered in here (usecs for all counters) (deletes previous trace) Examples: (with ftrace_enabled = 0) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 Signed-off-by: Ingo Molnar -------------------------------------------------------------------- latency: 26 us, #2/2, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/0-3 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / quilt-8551 0d..3 0us+: wake_up_process+0x15/0x17 (sched_exec+0xc9/0x100 ) quilt-8551 0d..4 26us : sched_switch_callback+0x73/0x81 (schedule+0x483/0x6d5 ) vim:ft=help ============ (with ftrace_enabled = 1) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 -------------------------------------------------------------------- latency: 36 us, #45/45, CPU#0 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/1-5 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / bash-10653 1d..3 0us : wake_up_process+0x15/0x17 (sched_exec+0xc9/0x100 ) bash-10653 1d..3 1us : try_to_wake_up+0x271/0x2e7 (sub_preempt_count+0xc/0x7a ) bash-10653 1d..2 2us : try_to_wake_up+0x296/0x2e7 (update_rq_clock+0x9/0x20 ) bash-10653 1d..2 2us : update_rq_clock+0x1e/0x20 (__update_rq_clock+0xc/0x90 ) bash-10653 1d..2 3us : __update_rq_clock+0x1b/0x90 (sched_clock+0x9/0x29 ) bash-10653 1d..2 4us : try_to_wake_up+0x2a6/0x2e7 (activate_task+0xc/0x3f ) bash-10653 1d..2 4us : activate_task+0x2d/0x3f (enqueue_task+0xe/0x66 ) bash-10653 1d..2 5us : enqueue_task+0x5b/0x66 (enqueue_task_rt+0x9/0x3c ) bash-10653 1d..2 6us : try_to_wake_up+0x2ba/0x2e7 (check_preempt_wakeup+0x12/0x99 ) [...] bash-10653 1d..5 33us : tracing_record_cmdline+0xcf/0xd4 (_spin_unlock+0x9/0x33 ) bash-10653 1d..5 34us : _spin_unlock+0x19/0x33 (sub_preempt_count+0xc/0x7a ) bash-10653 1d..4 35us : wakeup_sched_switch+0x65/0x2ff (_spin_lock_irqsave+0xc/0xa9 ) bash-10653 1d..4 35us : _spin_lock_irqsave+0x19/0xa9 (add_preempt_count+0xe/0x77 ) bash-10653 1d..4 36us : sched_switch_callback+0x73/0x81 (schedule+0x483/0x6d5 ) vim:ft=help ============ The [...] was added here to not waste your email box space. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index b96ef14c249a..db8a5e7abe41 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -5,10 +5,6 @@ #include -#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) -#define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1)) -#define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2)) - typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); struct ftrace_ops { @@ -35,4 +31,23 @@ extern void mcount(void); # define unregister_ftrace_function(ops) do { } while (0) # define clear_ftrace_function(ops) do { } while (0) #endif /* CONFIG_FTRACE */ + + +#ifdef CONFIG_FRAME_POINTER +/* TODO: need to fix this for ARM */ +# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) +# define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1)) +# define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2)) +# define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3)) +# define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4)) +# define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5)) +#else +# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) +# define CALLER_ADDR1 0UL +# define CALLER_ADDR2 0UL +# define CALLER_ADDR3 0UL +# define CALLER_ADDR4 0UL +# define CALLER_ADDR5 0UL +#endif + #endif /* _LINUX_FTRACE_H */ -- cgit v1.2.3 From 81d68a96a39844853b37f20cc8282d9b65b78ef3 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:42 +0200 Subject: ftrace: trace irq disabled critical timings This patch adds latency tracing for critical timings (how long interrupts are disabled for). "irqsoff" is added to /debugfs/tracing/available_tracers Note: tracing_max_latency also holds the max latency for irqsoff (in usecs). (default to large number so one must start latency tracing) tracing_thresh threshold (in usecs) to always print out if irqs off is detected to be longer than stated here. If irq_thresh is non-zero, then max_irq_latency is ignored. Here's an example of a trace with ftrace_enabled = 0 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 Signed-off-by: Ingo Molnar -------------------------------------------------------------------- latency: 100 us, #3/3, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1d.s3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1d.s3 100us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1d.s3 100us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= And this is a trace with ftrace_enabled == 1 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 -------------------------------------------------------------------- latency: 102 us, #12/12, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1dNs3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_read_phy_reg+0x16/0x225 [e1000] (e1000_update_stats+0x5e2/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_swfw_sync_acquire+0x10/0x99 [e1000] (e1000_read_phy_reg+0x49/0x225 [e1000]) swapper-0 1dNs3 46us : e1000_get_hw_eeprom_semaphore+0x12/0xa6 [e1000] (e1000_swfw_sync_acquire+0x36/0x99 [e1000]) swapper-0 1dNs3 47us : __const_udelay+0x9/0x47 (e1000_read_phy_reg+0x116/0x225 [e1000]) swapper-0 1dNs3 47us+: __delay+0x9/0x50 (__const_udelay+0x45/0x47) swapper-0 1dNs3 97us : preempt_schedule+0xc/0x84 (__delay+0x4e/0x50) swapper-0 1dNs3 98us : e1000_swfw_sync_release+0xc/0x55 [e1000] (e1000_read_phy_reg+0x211/0x225 [e1000]) swapper-0 1dNs3 99us+: e1000_put_hw_eeprom_semaphore+0x9/0x35 [e1000] (e1000_swfw_sync_release+0x50/0x55 [e1000]) swapper-0 1dNs3 101us : _spin_unlock_irqrestore+0xe/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/asm-x86/irqflags.h | 24 ++---------------------- include/linux/ftrace.h | 8 ++++++++ include/linux/irqflags.h | 12 ++++++++++-- 3 files changed, 20 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/asm-x86/irqflags.h b/include/asm-x86/irqflags.h index c242527f970e..24d71b1eb189 100644 --- a/include/asm-x86/irqflags.h +++ b/include/asm-x86/irqflags.h @@ -179,8 +179,6 @@ static inline void trace_hardirqs_fixup(void) * have a reliable stack. x86_64 only. */ #define SWAPGS_UNSAFE_STACK swapgs -#define ARCH_TRACE_IRQS_ON call trace_hardirqs_on_thunk -#define ARCH_TRACE_IRQS_OFF call trace_hardirqs_off_thunk #define ARCH_LOCKDEP_SYS_EXIT call lockdep_sys_exit_thunk #define ARCH_LOCKDEP_SYS_EXIT_IRQ \ TRACE_IRQS_ON; \ @@ -192,24 +190,6 @@ static inline void trace_hardirqs_fixup(void) TRACE_IRQS_OFF; #else -#define ARCH_TRACE_IRQS_ON \ - pushl %eax; \ - pushl %ecx; \ - pushl %edx; \ - call trace_hardirqs_on; \ - popl %edx; \ - popl %ecx; \ - popl %eax; - -#define ARCH_TRACE_IRQS_OFF \ - pushl %eax; \ - pushl %ecx; \ - pushl %edx; \ - call trace_hardirqs_off; \ - popl %edx; \ - popl %ecx; \ - popl %eax; - #define ARCH_LOCKDEP_SYS_EXIT \ pushl %eax; \ pushl %ecx; \ @@ -223,8 +203,8 @@ static inline void trace_hardirqs_fixup(void) #endif #ifdef CONFIG_TRACE_IRQFLAGS -# define TRACE_IRQS_ON ARCH_TRACE_IRQS_ON -# define TRACE_IRQS_OFF ARCH_TRACE_IRQS_OFF +# define TRACE_IRQS_ON call trace_hardirqs_on_thunk; +# define TRACE_IRQS_OFF call trace_hardirqs_off_thunk; #else # define TRACE_IRQS_ON # define TRACE_IRQS_OFF diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index db8a5e7abe41..0a20445dcbcc 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -50,4 +50,12 @@ extern void mcount(void); # define CALLER_ADDR5 0UL #endif +#ifdef CONFIG_IRQSOFF_TRACER + extern void notrace time_hardirqs_on(unsigned long a0, unsigned long a1); + extern void notrace time_hardirqs_off(unsigned long a0, unsigned long a1); +#else +# define time_hardirqs_on(a0, a1) do { } while (0) +# define time_hardirqs_off(a0, a1) do { } while (0) +#endif + #endif /* _LINUX_FTRACE_H */ diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index e600c4e9b8c5..5b711d4e9fd9 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -12,10 +12,10 @@ #define _LINUX_TRACE_IRQFLAGS_H #ifdef CONFIG_TRACE_IRQFLAGS - extern void trace_hardirqs_on(void); - extern void trace_hardirqs_off(void); extern void trace_softirqs_on(unsigned long ip); extern void trace_softirqs_off(unsigned long ip); + extern void trace_hardirqs_on(void); + extern void trace_hardirqs_off(void); # define trace_hardirq_context(p) ((p)->hardirq_context) # define trace_softirq_context(p) ((p)->softirq_context) # define trace_hardirqs_enabled(p) ((p)->hardirqs_enabled) @@ -41,6 +41,14 @@ # define INIT_TRACE_IRQFLAGS #endif +#ifdef CONFIG_IRQSOFF_TRACER + extern void stop_critical_timings(void); + extern void start_critical_timings(void); +#else +# define stop_critical_timings() do { } while (0) +# define start_critical_timings() do { } while (0) +#endif + #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT #include -- cgit v1.2.3 From 6cd8a4bb2f97527a9ceb30bc77ea4e959c6a95e3 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:42 +0200 Subject: ftrace: trace preempt off critical timings Add preempt off timings. A lot of kernel core code is taken from the RT patch latency trace that was written by Ingo Molnar. This adds "preemptoff" and "preemptirqsoff" to /debugfs/tracing/available_tracers Now instead of just tracing irqs off, preemption off can be selected to be recorded. When this is selected, it shares the same files as irqs off timings. One can either trace preemption off, irqs off, or one or the other off. By echoing "preemptoff" into /debugfs/tracing/current_tracer, recording of preempt off only is performed. "irqsoff" will only record the time irqs are disabled, but "preemptirqsoff" will take the total time irqs or preemption are disabled. Runtime switching of these options is now supported by simpling echoing in the appropriate trace name into /debugfs/tracing/current_tracer. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 8 ++++++++ include/linux/irqflags.h | 3 ++- include/linux/preempt.h | 2 +- 3 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 0a20445dcbcc..740c97dcf9cb 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -58,4 +58,12 @@ extern void mcount(void); # define time_hardirqs_off(a0, a1) do { } while (0) #endif +#ifdef CONFIG_PREEMPT_TRACER + extern void notrace trace_preempt_on(unsigned long a0, unsigned long a1); + extern void notrace trace_preempt_off(unsigned long a0, unsigned long a1); +#else +# define trace_preempt_on(a0, a1) do { } while (0) +# define trace_preempt_off(a0, a1) do { } while (0) +#endif + #endif /* _LINUX_FTRACE_H */ diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 5b711d4e9fd9..2b1c2e58566e 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -41,7 +41,8 @@ # define INIT_TRACE_IRQFLAGS #endif -#ifdef CONFIG_IRQSOFF_TRACER +#if defined(CONFIG_IRQSOFF_TRACER) || \ + defined(CONFIG_PREEMPT_TRACER) extern void stop_critical_timings(void); extern void start_critical_timings(void); #else diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 36b03d50bf40..72b1a10a59b6 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -10,7 +10,7 @@ #include #include -#ifdef CONFIG_DEBUG_PREEMPT +#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER) extern void add_preempt_count(int val); extern void sub_preempt_count(int val); #else -- cgit v1.2.3 From 3d0833953e1b98b79ddf491dd49229eef9baeac1 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:42 +0200 Subject: ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 740c97dcf9cb..90dbc0ee2046 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -32,6 +32,24 @@ extern void mcount(void); # define clear_ftrace_function(ops) do { } while (0) #endif /* CONFIG_FTRACE */ +#ifdef CONFIG_DYNAMIC_FTRACE +# define FTRACE_HASHBITS 10 +# define FTRACE_HASHSIZE (1< Date: Mon, 12 May 2008 21:20:43 +0200 Subject: ftrace: add ftrace_enabled sysctl to disable mcount function This patch adds back the sysctl ftrace_enabled. This time it is defaulted to on, if DYNAMIC_FTRACE is configured. When ftrace_enabled is disabled, the ftrace function is set to the stub return. If DYNAMIC_FTRACE is also configured, on ftrace_enabled = 0, the registered ftrace functions will all be set to jmps, but no more new calls to ftrace recording (used to find the ftrace calling sites) will be called. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 90dbc0ee2046..ccd8537dbdb7 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -5,6 +5,12 @@ #include +extern int ftrace_enabled; +extern int +ftrace_enable_sysctl(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos); + typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); struct ftrace_ops { -- cgit v1.2.3 From dfa60aba04dae7833d75b2e2be124bb7cfb8239f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:43 +0200 Subject: ftrace: use nops instead of jmp This patch patches the call to mcount with nops instead of a jmp over the mcount call. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/asm-x86/alternative.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/asm-x86/alternative.h b/include/asm-x86/alternative.h index 1f6a9ca10126..f6aa18eadf71 100644 --- a/include/asm-x86/alternative.h +++ b/include/asm-x86/alternative.h @@ -72,6 +72,8 @@ static inline void alternatives_smp_module_del(struct module *mod) {} static inline void alternatives_smp_switch(int smp) {} #endif /* CONFIG_SMP */ +const unsigned char *const *find_nop_table(void); + /* * Alternative instructions for different CPU types or capabilities. * -- cgit v1.2.3 From 3c1720f00bb619302ba19d55986ab565e74d06db Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:43 +0200 Subject: ftrace: move memory management out of arch code This patch moves the memory management of the ftrace records out of the arch code and into the generic code making the arch code simpler. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ccd8537dbdb7..d509ad6c9cb8 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -42,19 +42,23 @@ extern void mcount(void); # define FTRACE_HASHBITS 10 # define FTRACE_HASHSIZE (1< Date: Mon, 12 May 2008 21:20:43 +0200 Subject: ftrace: use dynamic patching for updating mcount calls This patch replaces the indirect call to the mcount function pointer with a direct call that will be patched by the dynamic ftrace routines. On boot up, the mcount function calls the ftace_stub function. When the dynamic ftrace code is initialized, the ftrace_stub is replaced with a call to the ftrace_record_ip, which records the instruction pointers of the locations that call it. Later, the ftraced daemon will call kstop_machine and patch all the locations to nops. When a ftrace is enabled, the original calls to mcount will now be set top call ftrace_caller, which will do a direct call to the registered ftrace function. This direct call is also patched when the function that should be called is updated. All patching is performed by a kstop_machine routine to prevent any type of race conditions that is associated with modifying code on the fly. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index d509ad6c9cb8..b0dd0093058f 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -56,9 +56,14 @@ struct dyn_ftrace { extern int ftrace_ip_converted(unsigned long ip); extern unsigned char *ftrace_nop_replace(void); extern unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr); -extern int ftrace_dyn_arch_init(void); +extern int ftrace_dyn_arch_init(void *data); +extern int ftrace_mcount_set(unsigned long *data); extern int ftrace_modify_code(unsigned long ip, unsigned char *old_code, unsigned char *new_code); +extern int ftrace_update_ftrace_func(ftrace_func_t func); +extern void ftrace_caller(void); +extern void ftrace_call(void); +extern void mcount_call(void); #endif #ifdef CONFIG_FRAME_POINTER -- cgit v1.2.3 From 5072c59fd45e9976d02ee6f18c7336ef97623cbc Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:43 +0200 Subject: ftrace: add filter select functions to trace This patch adds two files to the debugfs system: /debugfs/tracing/available_filter_functions and /debugfs/tracing/set_ftrace_filter The available_filter_functions lists all functions that has been recorded by the ftraced that has called the ftrace_record_ip function. This is to allow users to see what functions have been converted to nops and can be enabled for tracing. To enable functions, simply echo the names (whitespace delimited) into set_ftrace_filter. Simple wildcards are also allowed. echo 'scheduler' > /debugfs/tracing/set_ftrace_filter Will have only the scheduler be activated when tracing is enabled. echo 'sched_*' > /debugfs/tracing/set_ftrace_filter Will have only the functions starting with 'sched_' be activated. echo '*lock' > /debugfs/tracing/set_ftrace_filter Will have only functions ending with 'lock' be activated. echo '*lock*' > /debugfs/tracing/set_ftrace_filter Will have only functions with 'lock' in its name be activated. Note: 'sched*lock' will not work. The only wildcards that are allowed is an asterisk and the beginning and or end of the string passed in. Multiple names can be passed in with whitespace delimited: echo 'scheduler *lock *acpi*' > /debugfs/tracing/set_ftrace_filter is also the same as: echo 'scheduler' > /debugfs/tracing/set_ftrace_filter echo '*lock' >> /debugfs/tracing/set_ftrace_filter echo '*acpi*' >> /debugfs/tracing/set_ftrace_filter Appending does just that. It appends to the list. To disable all filters simply echo an empty line in: echo > /debugfs/tracing/set_ftrace_filter Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index b0dd0093058f..f5911d2d42c3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -43,7 +43,9 @@ extern void mcount(void); # define FTRACE_HASHSIZE (1< Date: Mon, 12 May 2008 21:20:43 +0200 Subject: ftrace: fix kexec disable the tracer while kexec pulls the rug from under the old kernel. Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index f5911d2d42c3..a42390c1d6e1 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -68,6 +68,13 @@ extern void ftrace_call(void); extern void mcount_call(void); #endif +static inline void tracer_disable(void) +{ +#ifdef CONFIG_FTRACE + ftrace_enabled = 0; +#endif +} + #ifdef CONFIG_FRAME_POINTER /* TODO: need to fix this for ARM */ # define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) -- cgit v1.2.3 From e1c08bdd9fa73e44096e5a82c0d5928b04ab02c8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:44 +0200 Subject: ftrace: force recording Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index a42390c1d6e1..2c1670c65236 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -54,6 +54,8 @@ struct dyn_ftrace { unsigned long flags; }; +int ftrace_force_update(void); + /* defined in arch */ extern int ftrace_ip_converted(unsigned long ip); extern unsigned char *ftrace_nop_replace(void); @@ -66,6 +68,8 @@ extern int ftrace_update_ftrace_func(ftrace_func_t func); extern void ftrace_caller(void); extern void ftrace_call(void); extern void mcount_call(void); +#else +# define ftrace_force_update() do { } while (0) #endif static inline void tracer_disable(void) -- cgit v1.2.3 From c7aafc549766b87819285d3480648fc652a47bc4 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:20:45 +0200 Subject: ftrace: cleanups factor out code and clean it up. Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 2c1670c65236..953a36d6a199 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -69,7 +69,7 @@ extern void ftrace_caller(void); extern void ftrace_call(void); extern void mcount_call(void); #else -# define ftrace_force_update() do { } while (0) +# define ftrace_force_update() ({ 0; }) #endif static inline void tracer_disable(void) -- cgit v1.2.3 From 77a2b37d227483fe52aead242652aee406c25bf0 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:45 +0200 Subject: ftrace: startup tester on dynamic tracing. This patch adds a startup self test on dynamic code modification and filters. The test filters on a specific function, makes sure that no other function is traced, exectutes the function, then makes sure that the function is traced. This patch also fixes a slight bug with the ftrace selftest, where tracer_enabled was not being set. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 953a36d6a199..a842d96c6343 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -55,6 +55,7 @@ struct dyn_ftrace { }; int ftrace_force_update(void); +void ftrace_set_filter(unsigned char *buf, int len, int reset); /* defined in arch */ extern int ftrace_ip_converted(unsigned long ip); @@ -70,6 +71,7 @@ extern void ftrace_call(void); extern void mcount_call(void); #else # define ftrace_force_update() ({ 0; }) +# define ftrace_set_filter(buf, len, reset) do { } while (0) #endif static inline void tracer_disable(void) -- cgit v1.2.3 From 37ad508419f0fdfda7b378756eb1f35cfd26d96d Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:48 +0200 Subject: ftrace - fix dynamic ftrace memory leak The ftrace dynamic function update allocates a record to store the instruction pointers that are being modified. If the modified instruction pointer fails to update, then the record is marked as failed and nothing more is done. Worse, if the modification fails, but the record ip function is still called, it will allocate a new record and try again. In just a matter of time, will this cause a serious memory leak and crash the system. This patch plugs this memory leak. When a record fails, it is included back into the pool of records to be used. Now a record may fail over and over again, but the number of allocated records will not increase. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index a842d96c6343..61e757bd2350 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -43,9 +43,10 @@ extern void mcount(void); # define FTRACE_HASHSIZE (1< Date: Mon, 12 May 2008 21:20:48 +0200 Subject: ftrace: disable tracing on failure Since ftrace touches practically every function. If we detect any anomaly, we want to fully disable ftrace. This patch adds code to try shutdown ftrace as much as possible without doing any more harm is something is detected not quite correct. This only kills ftrace, this patch does have checks for other parts of the tracer (irqsoff, wakeup, etc.). Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 61e757bd2350..4650a3160b7f 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -58,6 +58,9 @@ struct dyn_ftrace { int ftrace_force_update(void); void ftrace_set_filter(unsigned char *buf, int len, int reset); +/* totally disable ftrace - can not re-enable after this */ +void ftrace_kill(void); + /* defined in arch */ extern int ftrace_ip_converted(unsigned long ip); extern unsigned char *ftrace_nop_replace(void); -- cgit v1.2.3 From aeaee8a2c9cb4489f166ca0e39c568e8254faaa6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:20:49 +0200 Subject: ftrace: build fix Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 4650a3160b7f..08fbef1744cc 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -58,9 +58,6 @@ struct dyn_ftrace { int ftrace_force_update(void); void ftrace_set_filter(unsigned char *buf, int len, int reset); -/* totally disable ftrace - can not re-enable after this */ -void ftrace_kill(void); - /* defined in arch */ extern int ftrace_ip_converted(unsigned long ip); extern unsigned char *ftrace_nop_replace(void); @@ -74,10 +71,13 @@ extern void ftrace_caller(void); extern void ftrace_call(void); extern void mcount_call(void); #else -# define ftrace_force_update() ({ 0; }) -# define ftrace_set_filter(buf, len, reset) do { } while (0) +# define ftrace_force_update() ({ 0; }) +# define ftrace_set_filter(buf, len, reset) do { } while (0) #endif +/* totally disable ftrace - can not re-enable after this */ +void ftrace_kill(void); + static inline void tracer_disable(void) { #ifdef CONFIG_FTRACE -- cgit v1.2.3 From 86387f7ee5d3273ff4859e2c64ce656639b6ca65 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:20:51 +0200 Subject: ftrace: add stack tracing Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 08fbef1744cc..0d3714e7110b 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -93,6 +93,7 @@ static inline void tracer_disable(void) # define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3)) # define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4)) # define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5)) +# define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6)) #else # define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) # define CALLER_ADDR1 0UL @@ -100,6 +101,7 @@ static inline void tracer_disable(void) # define CALLER_ADDR3 0UL # define CALLER_ADDR4 0UL # define CALLER_ADDR5 0UL +# define CALLER_ADDR6 0UL #endif #ifdef CONFIG_IRQSOFF_TRACER -- cgit v1.2.3 From 8ac0fca4ccb355ce50471d7aa3f10f5900b28b95 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:20:51 +0200 Subject: ftrace: sched tracer fix Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6e26f1fdbfe2..05744f9cb096 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2130,17 +2130,11 @@ ftrace_ctx_switch(struct task_struct *prev, struct task_struct *next) #ifdef CONFIG_SCHED_TRACER extern void ftrace_wake_up_task(struct task_struct *wakee, struct task_struct *curr); -extern void -ftrace_wake_up_new_task(struct task_struct *wakee, struct task_struct *curr); #else static inline void ftrace_wake_up_task(struct task_struct *wakee, struct task_struct *curr) { } -static inline void -ftrace_wake_up_new_task(struct task_struct *wakee, struct task_struct *curr) -{ -} #endif extern long sched_setaffinity(pid_t pid, const cpumask_t *new_mask); -- cgit v1.2.3 From 4e65551905fb0300ae7e667cbaa41ee2e3f29a13 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:20:52 +0200 Subject: ftrace: sched tracer, trace full rbtree Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 32 +++++++++++++++++++++++--------- 1 file changed, 23 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 05744f9cb096..652d380ae563 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2119,20 +2119,34 @@ static inline void arch_pick_mmap_layout(struct mm_struct *mm) #ifdef CONFIG_CONTEXT_SWITCH_TRACER extern void -ftrace_ctx_switch(struct task_struct *prev, struct task_struct *next); +ftrace_ctx_switch(void *rq, struct task_struct *prev, struct task_struct *next); +extern void +ftrace_wake_up_task(void *rq, struct task_struct *wakee, + struct task_struct *curr); +extern void ftrace_all_fair_tasks(void *__rq, void *__tr, void *__data); +extern void +__trace_special(void *__tr, void *__data, + unsigned long arg1, unsigned long arg2, unsigned long arg3); #else static inline void -ftrace_ctx_switch(struct task_struct *prev, struct task_struct *next) +ftrace_ctx_switch(void *rq, struct task_struct *prev, struct task_struct *next) +{ +} +static inline void +sched_trace_special(unsigned long p1, unsigned long p2, unsigned long p3) +{ +} +static inline void +ftrace_wake_up_task(void *rq, struct task_struct *wakee, + struct task_struct *curr) +{ +} +static inline void ftrace_all_fair_tasks(void *__rq, void *__tr, void *__data) { } -#endif - -#ifdef CONFIG_SCHED_TRACER -extern void -ftrace_wake_up_task(struct task_struct *wakee, struct task_struct *curr); -#else static inline void -ftrace_wake_up_task(struct task_struct *wakee, struct task_struct *curr) +__trace_special(void *__tr, void *__data, + unsigned long arg1, unsigned long arg2, unsigned long arg3) { } #endif -- cgit v1.2.3 From 017730c11241e26577673eb9d957cfc66172ea91 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:20:52 +0200 Subject: ftrace: fix wakeups Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 652d380ae563..a3970b563757 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -246,6 +246,8 @@ extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern void init_idle_bootup_task(struct task_struct *idle); +extern int runqueue_is_locked(void); + extern cpumask_t nohz_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) extern int select_nohz_load_balancer(int cpu); -- cgit v1.2.3 From 1a3c3034336320554a3342572dae98d69e054fc7 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:20:52 +0200 Subject: ftrace: fix __trace_special() Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index a3970b563757..5b186bed54bc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2119,6 +2119,18 @@ static inline void arch_pick_mmap_layout(struct mm_struct *mm) } #endif +#ifdef CONFIG_TRACING +extern void +__trace_special(void *__tr, void *__data, + unsigned long arg1, unsigned long arg2, unsigned long arg3); +#else +static inline void +__trace_special(void *__tr, void *__data, + unsigned long arg1, unsigned long arg2, unsigned long arg3) +{ +} +#endif + #ifdef CONFIG_CONTEXT_SWITCH_TRACER extern void ftrace_ctx_switch(void *rq, struct task_struct *prev, struct task_struct *next); @@ -2126,9 +2138,6 @@ extern void ftrace_wake_up_task(void *rq, struct task_struct *wakee, struct task_struct *curr); extern void ftrace_all_fair_tasks(void *__rq, void *__tr, void *__data); -extern void -__trace_special(void *__tr, void *__data, - unsigned long arg1, unsigned long arg2, unsigned long arg3); #else static inline void ftrace_ctx_switch(void *rq, struct task_struct *prev, struct task_struct *next) @@ -2146,11 +2155,6 @@ ftrace_wake_up_task(void *rq, struct task_struct *wakee, static inline void ftrace_all_fair_tasks(void *__rq, void *__tr, void *__data) { } -static inline void -__trace_special(void *__tr, void *__data, - unsigned long arg1, unsigned long arg2, unsigned long arg3) -{ -} #endif extern long sched_setaffinity(pid_t pid, const cpumask_t *new_mask); -- cgit v1.2.3 From 88a4216c3ec4281fc7e6725cc3a3ccd01fb1aa14 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:20:53 +0200 Subject: ftrace: sched special Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5b186bed54bc..360ca99033d2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2138,6 +2138,8 @@ extern void ftrace_wake_up_task(void *rq, struct task_struct *wakee, struct task_struct *curr); extern void ftrace_all_fair_tasks(void *__rq, void *__tr, void *__data); +extern void +ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3); #else static inline void ftrace_ctx_switch(void *rq, struct task_struct *prev, struct task_struct *next) @@ -2155,6 +2157,10 @@ ftrace_wake_up_task(void *rq, struct task_struct *wakee, static inline void ftrace_all_fair_tasks(void *__rq, void *__tr, void *__data) { } +static inline void +ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) +{ +} #endif extern long sched_setaffinity(pid_t pid, const cpumask_t *new_mask); -- cgit v1.2.3 From 86069782d62e731b4835a0cf8eb7d1d0e17cf306 Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Mon, 12 May 2008 21:20:56 +0200 Subject: x86: add a list for custom page fault handlers. Provides kernel modules a way to register custom page fault handlers. On every page fault this will call a list of registered functions. The functions may handle the fault and force do_page_fault() to return immediately. This functionality is similar to the now removed page fault notifiers. Custom page fault handlers are used by debugging and reverse engineering tools. Mmiotrace is one such tool and a patch to add it into the tree will follow. The custom page fault handlers are called earlier in do_page_fault() than the page fault notifiers were. Signed-off-by: Pekka Paalanen Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/asm-x86/kdebug.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/asm-x86/kdebug.h b/include/asm-x86/kdebug.h index 96651bb59ba1..a80f2d6cc737 100644 --- a/include/asm-x86/kdebug.h +++ b/include/asm-x86/kdebug.h @@ -35,4 +35,13 @@ extern void show_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); +struct pf_handler { + struct hlist_node hlist; + int (*handler)(struct pt_regs *regs, unsigned long error_code, + unsigned long address); +}; + +extern void register_page_fault_handler(struct pf_handler *new_pfh); +extern void unregister_page_fault_handler(struct pf_handler *old_pfh); + #endif -- cgit v1.2.3 From 3eefae994d9224fb7771a3ddb683868363c23510 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:21:04 +0200 Subject: ftrace: limit trace entries Currently there is no protection from the root user to use up all of memory for trace buffers. If the root user allocates too many entries, the OOM killer might start kill off all tasks. This patch adds an algorith to check the following condition: pages_requested > (freeable_memory + current_trace_buffer_pages) / 4 If the above is met then the allocation fails. The above prevents more than 1/4th of freeable memory from being used by trace buffers. To determine the freeable_memory, I made determine_dirtyable_memory in mm/page-writeback.c global. Special thanks goes to Peter Zijlstra for suggesting the above calculation. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/writeback.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index f462439cc288..bd91987c065f 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -105,6 +105,8 @@ extern int vm_highmem_is_dirtyable; extern int block_dump; extern int laptop_mode; +extern unsigned long determine_dirtyable_memory(void); + extern int dirty_ratio_handler(struct ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos); -- cgit v1.2.3 From dc102a8fae2d0d6bf5223fc549247f2e23959ae6 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Mon, 12 May 2008 21:21:09 +0200 Subject: Markers - remove extra format argument Denys Vlasenko : > Not in this patch, but I noticed: > > #define __trace_mark(name, call_private, format, args...) \ > do { \ > static const char __mstrtab_##name[] \ > __attribute__((section("__markers_strings"))) \ > = #name "\0" format; \ > static struct marker __mark_##name \ > __attribute__((section("__markers"), aligned(8))) = \ > { __mstrtab_##name, &__mstrtab_##name[sizeof(#name)], \ > 0, 0, marker_probe_cb, \ > { __mark_empty_function, NULL}, NULL }; \ > __mark_check_format(format, ## args); \ > if (unlikely(__mark_##name.state)) { \ > (*__mark_##name.call) \ > (&__mark_##name, call_private, \ > format, ## args); \ > } \ > } while (0) > > In this call: > > (*__mark_##name.call) \ > (&__mark_##name, call_private, \ > format, ## args); \ > > you make gcc allocate duplicate format string. You can use > &__mstrtab_##name[sizeof(#name)] instead since it holds the same string, > or drop ", format," above and "const char *fmt" from here: > > void (*call)(const struct marker *mdata, /* Probe wrapper */ > void *call_private, const char *fmt, ...); > > since mdata->format is the same and all callees which need it can take it there. Very good point. I actually thought about dropping it, since it would remove an unnecessary argument from the stack. And actually, since I now have the marker_probe_cb sitting between the marker site and the callbacks, there is no API change required. Thanks :) Mathieu Signed-off-by: Mathieu Desnoyers CC: Denys Vlasenko Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/marker.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/marker.h b/include/linux/marker.h index 430f6adf9762..338533abb47b 100644 --- a/include/linux/marker.h +++ b/include/linux/marker.h @@ -44,8 +44,8 @@ struct marker { */ char state; /* Marker state. */ char ptype; /* probe type : 0 : single, 1 : multi */ - void (*call)(const struct marker *mdata, /* Probe wrapper */ - void *call_private, const char *fmt, ...); + /* Probe wrapper */ + void (*call)(const struct marker *mdata, void *call_private, ...); struct marker_probe_closure single; struct marker_probe_closure *multi; } __attribute__((aligned(8))); @@ -72,8 +72,7 @@ struct marker { __mark_check_format(format, ## args); \ if (unlikely(__mark_##name.state)) { \ (*__mark_##name.call) \ - (&__mark_##name, call_private, \ - format, ## args); \ + (&__mark_##name, call_private, ## args);\ } \ } while (0) @@ -117,9 +116,9 @@ static inline void __printf(1, 2) ___mark_check_format(const char *fmt, ...) extern marker_probe_func __mark_empty_function; extern void marker_probe_cb(const struct marker *mdata, - void *call_private, const char *fmt, ...); + void *call_private, ...); extern void marker_probe_cb_noarg(const struct marker *mdata, - void *call_private, const char *fmt, ...); + void *call_private, ...); /* * Connect a probe to a marker. -- cgit v1.2.3 From 0aa977f592f17004f9d1d545f2e1bb9ea71896c3 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Mon, 12 May 2008 21:21:10 +0200 Subject: Markers - define non optimized marker To support the forthcoming "immediate values" marker optimization, we must have a way to declare markers in few code paths that does not use instruction modification based enable. This will be the case of printk(), some traps and eventually lockdep instrumentation. Changelog : - Fix reversed boolean logic of "generic". Signed-off-by: Mathieu Desnoyers Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/marker.h | 29 ++++++++++++++++++++++++----- 1 file changed, 24 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/marker.h b/include/linux/marker.h index 338533abb47b..1290653f9241 100644 --- a/include/linux/marker.h +++ b/include/linux/marker.h @@ -58,8 +58,12 @@ struct marker { * Make sure the alignment of the structure in the __markers section will * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. + * + * The "generic" argument controls which marker enabling mechanism must be used. + * If generic is true, a variable read is used. + * If generic is false, immediate values are used. */ -#define __trace_mark(name, call_private, format, args...) \ +#define __trace_mark(generic, name, call_private, format, args...) \ do { \ static const char __mstrtab_##name[] \ __attribute__((section("__markers_strings"))) \ @@ -79,7 +83,7 @@ struct marker { extern void marker_update_probe_range(struct marker *begin, struct marker *end); #else /* !CONFIG_MARKERS */ -#define __trace_mark(name, call_private, format, args...) \ +#define __trace_mark(generic, name, call_private, format, args...) \ __mark_check_format(format, ## args) static inline void marker_update_probe_range(struct marker *begin, struct marker *end) @@ -87,15 +91,30 @@ static inline void marker_update_probe_range(struct marker *begin, #endif /* CONFIG_MARKERS */ /** - * trace_mark - Marker + * trace_mark - Marker using code patching * @name: marker name, not quoted. * @format: format string * @args...: variable argument list * - * Places a marker. + * Places a marker using optimized code patching technique (imv_read()) + * to be enabled when immediate values are present. */ #define trace_mark(name, format, args...) \ - __trace_mark(name, NULL, format, ## args) + __trace_mark(0, name, NULL, format, ## args) + +/** + * _trace_mark - Marker using variable read + * @name: marker name, not quoted. + * @format: format string + * @args...: variable argument list + * + * Places a marker using a standard memory read (_imv_read()) to be + * enabled. Should be used for markers in code paths where instruction + * modification based enabling is not welcome. (__init and __exit functions, + * lockdep, some traps, printk). + */ +#define _trace_mark(name, format, args...) \ + __trace_mark(1, name, NULL, format, ## args) /** * MARK_NOARGS - Format string for a marker with no argument. -- cgit v1.2.3 From 5b82a1b08a00b2adca3d9dd9777efff40b7aaaa1 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Mon, 12 May 2008 21:21:10 +0200 Subject: Port ftrace to markers Porting ftrace to the marker infrastructure. Don't need to chain to the wakeup tracer from the sched tracer, because markers support multiple probes connected. Signed-off-by: Mathieu Desnoyers CC: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 32 -------------------------------- 1 file changed, 32 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 360ca99033d2..c0b1c69b55ce 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2131,38 +2131,6 @@ __trace_special(void *__tr, void *__data, } #endif -#ifdef CONFIG_CONTEXT_SWITCH_TRACER -extern void -ftrace_ctx_switch(void *rq, struct task_struct *prev, struct task_struct *next); -extern void -ftrace_wake_up_task(void *rq, struct task_struct *wakee, - struct task_struct *curr); -extern void ftrace_all_fair_tasks(void *__rq, void *__tr, void *__data); -extern void -ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3); -#else -static inline void -ftrace_ctx_switch(void *rq, struct task_struct *prev, struct task_struct *next) -{ -} -static inline void -sched_trace_special(unsigned long p1, unsigned long p2, unsigned long p3) -{ -} -static inline void -ftrace_wake_up_task(void *rq, struct task_struct *wakee, - struct task_struct *curr) -{ -} -static inline void ftrace_all_fair_tasks(void *__rq, void *__tr, void *__data) -{ -} -static inline void -ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) -{ -} -#endif - extern long sched_setaffinity(pid_t pid, const cpumask_t *new_mask); extern long sched_getaffinity(pid_t pid, cpumask_t *mask); -- cgit v1.2.3 From 74f4e369fc5b52433ad824cef32d3bf1304549be Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:21:15 +0200 Subject: ftrace: stacktrace fix Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 0d3714e7110b..017ab44d572a 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -120,4 +120,12 @@ static inline void tracer_disable(void) # define trace_preempt_off(a0, a1) do { } while (0) #endif +#ifdef CONFIG_CONTEXT_SWITCH_TRACER +extern void +ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3); +#else +static inline void +ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { } +#endif + #endif /* _LINUX_FTRACE_H */ -- cgit v1.2.3 From d49dbf33f0bf8748ee3662b973eb57e60525d622 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 16 May 2008 10:41:53 +0200 Subject: ftrace: fix include file dependency Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 017ab44d572a..911d5d80b49f 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -4,6 +4,7 @@ #ifdef CONFIG_FTRACE #include +#include extern int ftrace_enabled; extern int -- cgit v1.2.3 From 489f139614596cbc956a06f5e4bb41288e276fe3 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 25 Feb 2008 13:38:05 +0100 Subject: ftrace: fix build bug Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 911d5d80b49f..922e23d0196f 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -106,16 +106,16 @@ static inline void tracer_disable(void) #endif #ifdef CONFIG_IRQSOFF_TRACER - extern void notrace time_hardirqs_on(unsigned long a0, unsigned long a1); - extern void notrace time_hardirqs_off(unsigned long a0, unsigned long a1); + extern void time_hardirqs_on(unsigned long a0, unsigned long a1); + extern void time_hardirqs_off(unsigned long a0, unsigned long a1); #else # define time_hardirqs_on(a0, a1) do { } while (0) # define time_hardirqs_off(a0, a1) do { } while (0) #endif #ifdef CONFIG_PREEMPT_TRACER - extern void notrace trace_preempt_on(unsigned long a0, unsigned long a1); - extern void notrace trace_preempt_off(unsigned long a0, unsigned long a1); + extern void trace_preempt_on(unsigned long a0, unsigned long a1); + extern void trace_preempt_off(unsigned long a0, unsigned long a1); #else # define trace_preempt_on(a0, a1) do { } while (0) # define trace_preempt_off(a0, a1) do { } while (0) -- cgit v1.2.3 From e0eca07badc023a675a61906020b397da20f07c3 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 14 May 2008 23:49:43 -0400 Subject: ftrace, POWERPC: add irqs_disabled_flags to ppc PPC doesn't have the irqs_disabled_flags needed by ftrace. This patch adds it. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/asm-powerpc/hw_irq.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/asm-powerpc/hw_irq.h b/include/asm-powerpc/hw_irq.h index ad8c9f7fd0e3..f75a5fc64d2e 100644 --- a/include/asm-powerpc/hw_irq.h +++ b/include/asm-powerpc/hw_irq.h @@ -59,6 +59,11 @@ extern void iseries_handle_interrupts(void); get_paca()->hard_enabled = 0; \ } while(0) +static inline int irqs_disabled_flags(unsigned long flags) +{ + return flags == 0; +} + #else #if defined(CONFIG_BOOKE) @@ -113,6 +118,11 @@ static inline void local_irq_save_ptr(unsigned long *flags) #define hard_irq_enable() local_irq_enable() #define hard_irq_disable() local_irq_disable() +static inline int irqs_disabled_flags(unsigned long flags) +{ + return (flags & MSR_EE) == 0; +} + #endif /* CONFIG_PPC64 */ /* -- cgit v1.2.3 From 8b7d89d02ef3c6a7c73d6596f28cea7632850af4 Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Mon, 12 May 2008 21:20:56 +0200 Subject: x86: mmiotrace - trace memory mapped IO Mmiotrace is a tool for trapping memory mapped IO (MMIO) accesses within the kernel. It is used for debugging and especially for reverse engineering evil binary drivers. Mmiotrace works by wrapping the ioremap family of kernel functions and marking the returned pages as not present. Access to the IO memory triggers a page fault, which will be handled by mmiotrace's custom page fault handler. This will single-step the faulted instruction with the MMIO page marked as present. Access logs are directed to user space via relay and debug_fs. This page fault approach is necessary, because binary drivers have readl/writel etc. calls inlined and therefore extremely difficult to trap with with e.g. kprobes. This patch depends on the custom page fault handlers patch. Signed-off-by: Pekka Paalanen Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/mmiotrace.h | 62 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) create mode 100644 include/linux/mmiotrace.h (limited to 'include') diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h new file mode 100644 index 000000000000..cb247825f3ec --- /dev/null +++ b/include/linux/mmiotrace.h @@ -0,0 +1,62 @@ +#ifndef MMIOTRACE_H +#define MMIOTRACE_H + +#include + +#define MMIO_VERSION 0x04 + +/* mm_io_header.type */ +#define MMIO_OPCODE_MASK 0xff +#define MMIO_OPCODE_SHIFT 0 +#define MMIO_WIDTH_MASK 0xff00 +#define MMIO_WIDTH_SHIFT 8 +#define MMIO_MAGIC (0x6f000000 | (MMIO_VERSION<<16)) +#define MMIO_MAGIC_MASK 0xffff0000 + +enum mm_io_opcode { /* payload type: */ + MMIO_READ = 0x1, /* struct mm_io_rw */ + MMIO_WRITE = 0x2, /* struct mm_io_rw */ + MMIO_PROBE = 0x3, /* struct mm_io_map */ + MMIO_UNPROBE = 0x4, /* struct mm_io_map */ + MMIO_MARKER = 0x5, /* raw char data */ + MMIO_UNKNOWN_OP = 0x6, /* struct mm_io_rw */ +}; + +struct mm_io_header { + __u32 type; + __u32 sec; /* timestamp */ + __u32 nsec; + __u32 pid; /* PID of the process, or 0 for kernel core */ + __u16 data_len; /* length of the following payload */ +}; + +struct mm_io_rw { + __u64 address; /* virtual address of register */ + __u64 value; + __u64 pc; /* optional program counter */ +}; + +struct mm_io_map { + __u64 phys; /* base address in PCI space */ + __u64 addr; /* base virtual address */ + __u64 len; /* mapping size */ + __u64 pc; /* optional program counter */ +}; + + +/* + * These structures are used to allow a single relay_write() + * call to write a full packet. + */ + +struct mm_io_header_rw { + struct mm_io_header header; + struct mm_io_rw rw; +} __attribute__((packed)); + +struct mm_io_header_map { + struct mm_io_header header; + struct mm_io_map map; +} __attribute__((packed)); + +#endif /* MMIOTRACE_H */ -- cgit v1.2.3 From 63ffa3e456c1a9884a3ebac997d91e3fdae18d78 Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Mon, 12 May 2008 21:20:57 +0200 Subject: x86 mmiotrace: comment about user space ABI Signed-off-by: Pekka Paalanen Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/mmiotrace.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h index cb247825f3ec..6ec288f1fe24 100644 --- a/include/linux/mmiotrace.h +++ b/include/linux/mmiotrace.h @@ -3,6 +3,10 @@ #include +/* + * If you change anything here, you must bump MMIO_VERSION. + * This is the relay data format for user space. + */ #define MMIO_VERSION 0x04 /* mm_io_header.type */ @@ -23,7 +27,7 @@ enum mm_io_opcode { /* payload type: */ }; struct mm_io_header { - __u32 type; + __u32 type; /* see MMIO_* macros above */ __u32 sec; /* timestamp */ __u32 nsec; __u32 pid; /* PID of the process, or 0 for kernel core */ -- cgit v1.2.3 From 10c43d2eb50c9a5ad60388b9d3c41c31150049e6 Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Mon, 12 May 2008 21:20:57 +0200 Subject: x86: explicit call to mmiotrace in do_page_fault() The custom page fault handler list is replaced with a single function pointer. All related functions and variables are renamed for mmiotrace. Signed-off-by: Pekka Paalanen Cc: Christoph Hellwig Cc: Arjan van de Ven Cc: pq@iki.fi Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/asm-x86/kdebug.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/asm-x86/kdebug.h b/include/asm-x86/kdebug.h index a80f2d6cc737..7063281040da 100644 --- a/include/asm-x86/kdebug.h +++ b/include/asm-x86/kdebug.h @@ -35,13 +35,11 @@ extern void show_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); -struct pf_handler { - struct hlist_node hlist; - int (*handler)(struct pt_regs *regs, unsigned long error_code, - unsigned long address); -}; +typedef int (*pf_handler_func)(struct pt_regs *regs, + unsigned long error_code, + unsigned long address); -extern void register_page_fault_handler(struct pf_handler *new_pfh); -extern void unregister_page_fault_handler(struct pf_handler *old_pfh); +extern int mmiotrace_register_pf(pf_handler_func new_pfh); +extern int mmiotrace_unregister_pf(pf_handler_func old_pfh); #endif -- cgit v1.2.3 From 0fd0e3da4557c479b820b9a4a7afa25b4637ddf2 Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Mon, 12 May 2008 21:20:57 +0200 Subject: x86: mmiotrace full patch, preview 1 kmmio.c handles the list of mmio probes with callbacks, list of traced pages, and attaching into the page fault handler and die notifier. It arms, traps and disarms the given pages, this is the core of mmiotrace. mmio-mod.c is a user interface, hooking into ioremap functions and registering the mmio probes. It also decodes the required information from trapped mmio accesses via the pre and post callbacks in each probe. Currently, hooking into ioremap functions works by redefining the symbols of the target (binary) kernel module, so that it calls the traced versions of the functions. The most notable changes done since the last discussion are: - kmmio.c is a built-in, not part of the module - direct call from fault.c to kmmio.c, removing all dynamic hooks - prepare for unregistering probes at any time - make kmmio re-initializable and accessible to more than one user - rewrite kmmio locking to remove all spinlocks from page fault path Can I abuse call_rcu() like I do in kmmio.c:unregister_kmmio_probe() or is there a better way? The function called via call_rcu() itself calls call_rcu() again, will this work or break? There I need a second grace period for RCU after the first grace period for page faults. Mmiotrace itself (mmio-mod.c) is still a module, I am going to attack that next. At some point I will start looking into how to make mmiotrace a tracer component of ftrace (thanks for the hint, Ingo). Ftrace should make the user space part of mmiotracing as simple as 'cat /debug/trace/mmio > dump.txt'. Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/asm-x86/kdebug.h | 7 ------- include/linux/mmiotrace.h | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/asm-x86/kdebug.h b/include/asm-x86/kdebug.h index 7063281040da..96651bb59ba1 100644 --- a/include/asm-x86/kdebug.h +++ b/include/asm-x86/kdebug.h @@ -35,11 +35,4 @@ extern void show_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); -typedef int (*pf_handler_func)(struct pt_regs *regs, - unsigned long error_code, - unsigned long address); - -extern int mmiotrace_register_pf(pf_handler_func new_pfh); -extern int mmiotrace_unregister_pf(pf_handler_func old_pfh); - #endif diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h index 6ec288f1fe24..d87a6cd8b686 100644 --- a/include/linux/mmiotrace.h +++ b/include/linux/mmiotrace.h @@ -3,6 +3,44 @@ #include +#ifdef __KERNEL__ + +#include + +struct kmmio_probe; +struct pt_regs; + +typedef void (*kmmio_pre_handler_t)(struct kmmio_probe *, + struct pt_regs *, unsigned long addr); +typedef void (*kmmio_post_handler_t)(struct kmmio_probe *, + unsigned long condition, struct pt_regs *); + +struct kmmio_probe { + struct list_head list; + unsigned long addr; /* start location of the probe point */ + unsigned long len; /* length of the probe region */ + kmmio_pre_handler_t pre_handler; /* Called before addr is executed. */ + kmmio_post_handler_t post_handler; /* Called after addr is executed */ +}; + +/* kmmio is active by some kmmio_probes? */ +static inline int is_kmmio_active(void) +{ + extern unsigned int kmmio_count; + return kmmio_count; +} + +extern void reference_kmmio(void); +extern void unreference_kmmio(void); +extern int register_kmmio_probe(struct kmmio_probe *p); +extern void unregister_kmmio_probe(struct kmmio_probe *p); + +/* Called from page fault handler. */ +extern int kmmio_handler(struct pt_regs *regs, unsigned long addr); + +#endif /* __KERNEL__ */ + + /* * If you change anything here, you must bump MMIO_VERSION. * This is the relay data format for user space. -- cgit v1.2.3 From d61fc44853f46fb002228b18aa5f30db21fcd4ac Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Mon, 12 May 2008 21:20:57 +0200 Subject: x86: mmiotrace, preview 2 Kconfig.debug, Makefile and testmmiotrace.c style fixes. Use real mutex instead of mutex. Fix failure path in register probe func. kmmio: RCU read-locked over single stepping. Generate mapping id's. Make mmio-mod.c built-in and rewrite its locking. Add debugfs file to enable/disable mmiotracing. kmmio: use irqsave spinlocks. Lots of cleanups in mmio-mod.c Marker file moved from /proc into debugfs. Call mmiotrace entrypoints directly from ioremap.c. Signed-off-by: Pekka Paalanen Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/mmiotrace.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h index d87a6cd8b686..cb5efd0c7f51 100644 --- a/include/linux/mmiotrace.h +++ b/include/linux/mmiotrace.h @@ -16,11 +16,12 @@ typedef void (*kmmio_post_handler_t)(struct kmmio_probe *, unsigned long condition, struct pt_regs *); struct kmmio_probe { - struct list_head list; + struct list_head list; /* kmmio internal list */ unsigned long addr; /* start location of the probe point */ unsigned long len; /* length of the probe region */ kmmio_pre_handler_t pre_handler; /* Called before addr is executed. */ kmmio_post_handler_t post_handler; /* Called after addr is executed */ + void *user_data; }; /* kmmio is active by some kmmio_probes? */ @@ -38,6 +39,21 @@ extern void unregister_kmmio_probe(struct kmmio_probe *p); /* Called from page fault handler. */ extern int kmmio_handler(struct pt_regs *regs, unsigned long addr); +/* Called from ioremap.c */ +#ifdef CONFIG_MMIOTRACE +extern void +mmiotrace_ioremap(unsigned long offset, unsigned long size, void __iomem *addr); +extern void mmiotrace_iounmap(volatile void __iomem *addr); +#else +static inline void +mmiotrace_ioremap(unsigned long offset, unsigned long size, void __iomem *addr) +{ +} +static inline void mmiotrace_iounmap(volatile void __iomem *addr) +{ +} +#endif /* CONFIG_MMIOTRACE_HOOKS */ + #endif /* __KERNEL__ */ -- cgit v1.2.3 From f984b51e0779a6dd30feedc41404013ca54e5d05 Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Mon, 12 May 2008 21:20:57 +0200 Subject: ftrace: add mmiotrace plugin On Sat, 22 Mar 2008 13:07:47 +0100 Ingo Molnar wrote: > > > i'd suggest the following: pull x86.git and sched-devel.git into a > > > single tree [the two will combine without rejects]. Then try to add a > > > kernel/tracing/trace_mmiotrace.c ftrace plugin. The trace_sysprof.c > > > plugin might be a good example. > > > > I did this and now I have mmiotrace enabled/disabled via the tracing > > framework (what do we call this, since ftrace is one of the tracers?). > > cool! could you send the patches for that? (even if they are not fully > functional yet) Patch attached in the end. Nice to see how much code disappeared. I tried to mark all the features I had to break with XXX-comments. Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/mmiotrace.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h index cb5efd0c7f51..579b3b06c90e 100644 --- a/include/linux/mmiotrace.h +++ b/include/linux/mmiotrace.h @@ -54,6 +54,12 @@ static inline void mmiotrace_iounmap(volatile void __iomem *addr) } #endif /* CONFIG_MMIOTRACE_HOOKS */ +/* in kernel/trace/trace_mmiotrace.c */ +extern int __init init_mmiotrace(void); +extern void enable_mmiotrace(void); +extern void disable_mmiotrace(void); +extern void mmio_trace_record(u32 type, unsigned long addr, unsigned long arg); + #endif /* __KERNEL__ */ -- cgit v1.2.3 From bd8ac686c73c7e925fcfe0b02dc4e7b947127864 Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Mon, 12 May 2008 21:20:57 +0200 Subject: ftrace: mmiotrace, updates here is a patch that makes mmiotrace work almost well within the tracing framework. The patch applies on top of my previous patch. I have my own output formatting in place now. Summary of changes: - fix the NULL dereference that was due to not calling tracing_reset() - add print_line() callback into struct tracer - implement print_line() for mmiotrace, producing up-to-spec text - add my output header, but that is not really called in the right place - rewrote the main structs in mmiotrace - added two new trace entry types: TRACE_MMIO_RW and TRACE_MMIO_MAP - made some functions in trace.c non-static - check current==NULL in tracing_generic_entry_update() - fix(?) comparison in trace_seq_printf() Things seem to work fine except a few issues. Markers (text lines injected into mmiotrace log) are missing, I did not feel hacking them in before we have variable length entries. My output header is printed only for 'trace' file, but not 'trace_pipe'. For some reason, despite my quick fix, iter->trace is NULL in print_trace_line() when called from 'trace_pipe' file, which means I don't get proper output formatting. I only tried by loading nouveau.ko, which just detects the card, and that is traced fine. I didn't try further. Map, two reads and unmap. Works perfectly. I am missing the information about overflows, I'd prefer to have a counter for lost events. I didn't try, but I guess currently there is no way of knowning when it overflows? So, not too far from being fully operational, it seems :-) And looking at the diffstat, there also is some 700-900 lines of user space code that just became obsolete. Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/mmiotrace.h | 85 ++++++++++++++--------------------------------- 1 file changed, 25 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h index 579b3b06c90e..c88a9c197d22 100644 --- a/include/linux/mmiotrace.h +++ b/include/linux/mmiotrace.h @@ -54,73 +54,38 @@ static inline void mmiotrace_iounmap(volatile void __iomem *addr) } #endif /* CONFIG_MMIOTRACE_HOOKS */ -/* in kernel/trace/trace_mmiotrace.c */ -extern int __init init_mmiotrace(void); -extern void enable_mmiotrace(void); -extern void disable_mmiotrace(void); -extern void mmio_trace_record(u32 type, unsigned long addr, unsigned long arg); - -#endif /* __KERNEL__ */ - - -/* - * If you change anything here, you must bump MMIO_VERSION. - * This is the relay data format for user space. - */ -#define MMIO_VERSION 0x04 - -/* mm_io_header.type */ -#define MMIO_OPCODE_MASK 0xff -#define MMIO_OPCODE_SHIFT 0 -#define MMIO_WIDTH_MASK 0xff00 -#define MMIO_WIDTH_SHIFT 8 -#define MMIO_MAGIC (0x6f000000 | (MMIO_VERSION<<16)) -#define MMIO_MAGIC_MASK 0xffff0000 - -enum mm_io_opcode { /* payload type: */ - MMIO_READ = 0x1, /* struct mm_io_rw */ - MMIO_WRITE = 0x2, /* struct mm_io_rw */ - MMIO_PROBE = 0x3, /* struct mm_io_map */ - MMIO_UNPROBE = 0x4, /* struct mm_io_map */ +enum mm_io_opcode { + MMIO_READ = 0x1, /* struct mmiotrace_rw */ + MMIO_WRITE = 0x2, /* struct mmiotrace_rw */ + MMIO_PROBE = 0x3, /* struct mmiotrace_map */ + MMIO_UNPROBE = 0x4, /* struct mmiotrace_map */ MMIO_MARKER = 0x5, /* raw char data */ - MMIO_UNKNOWN_OP = 0x6, /* struct mm_io_rw */ + MMIO_UNKNOWN_OP = 0x6, /* struct mmiotrace_rw */ }; -struct mm_io_header { - __u32 type; /* see MMIO_* macros above */ - __u32 sec; /* timestamp */ - __u32 nsec; - __u32 pid; /* PID of the process, or 0 for kernel core */ - __u16 data_len; /* length of the following payload */ +struct mmiotrace_rw { + unsigned long phys; /* PCI address of register */ + unsigned long value; + unsigned long pc; /* optional program counter */ + int map_id; + unsigned char opcode; /* one of MMIO_{READ,WRITE,UNKNOWN_OP} */ + unsigned char width; /* size of register access in bytes */ }; -struct mm_io_rw { - __u64 address; /* virtual address of register */ - __u64 value; - __u64 pc; /* optional program counter */ +struct mmiotrace_map { + unsigned long phys; /* base address in PCI space */ + unsigned long virt; /* base virtual address */ + unsigned long len; /* mapping size */ + int map_id; + unsigned char opcode; /* MMIO_PROBE or MMIO_UNPROBE */ }; -struct mm_io_map { - __u64 phys; /* base address in PCI space */ - __u64 addr; /* base virtual address */ - __u64 len; /* mapping size */ - __u64 pc; /* optional program counter */ -}; - - -/* - * These structures are used to allow a single relay_write() - * call to write a full packet. - */ - -struct mm_io_header_rw { - struct mm_io_header header; - struct mm_io_rw rw; -} __attribute__((packed)); +/* in kernel/trace/trace_mmiotrace.c */ +extern void enable_mmiotrace(void); +extern void disable_mmiotrace(void); +extern void mmio_trace_rw(struct mmiotrace_rw *rw); +extern void mmio_trace_mapping(struct mmiotrace_map *map); -struct mm_io_header_map { - struct mm_io_header header; - struct mm_io_map map; -} __attribute__((packed)); +#endif /* __KERNEL__ */ #endif /* MMIOTRACE_H */ -- cgit v1.2.3 From 138295373ccf7625fcb0218dfea114837983bc39 Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Mon, 12 May 2008 21:20:58 +0200 Subject: ftrace: mmiotrace update, #2 another weekend, another patch. This should apply on top of my previous patch from March 23rd. Summary of changes: - Print PCI device list in output header - work around recursive probe hits on SMP - refactor dis/arm_kmmio_fault_page() and add check for page levels - remove un/reference_kmmio(), the die notifier hook is registered permanently into the list - explicitly check for single stepping in die notifier callback I have tested this version on my UP Athlon64 desktop with Nouveau, and SMP Core 2 Duo laptop with the proprietary nvidia driver. Both systems are 64-bit. One previously unknown bug crept into daylight: the ftrace framework's output routines print the first entry last after buffer has wrapped around. The most important regressions compared to non-ftrace mmiotrace at this time are: - failure of trace_pipe file - illegal lines in output file - unaware of losing data due to buffer full Personally I'd like to see these three solved before submitting to mainline. Other issues may come up once we know when we lose events. Signed-off-by: Pekka Paalanen Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- include/linux/mmiotrace.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h index c88a9c197d22..dd6b64b160fc 100644 --- a/include/linux/mmiotrace.h +++ b/include/linux/mmiotrace.h @@ -31,8 +31,6 @@ static inline int is_kmmio_active(void) return kmmio_count; } -extern void reference_kmmio(void); -extern void unreference_kmmio(void); extern int register_kmmio_probe(struct kmmio_probe *p); extern void unregister_kmmio_probe(struct kmmio_probe *p); -- cgit v1.2.3 From 970e6fa03885f32cc43e42cb08c73a5f54cd8bd9 Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Mon, 12 May 2008 21:21:03 +0200 Subject: mmiotrace: code style cleanups From c2da03771e29159627c5c7b9509ec70bce9f91ee Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Mon, 28 Apr 2008 21:25:22 +0300 Signed-off-by: Pekka Paalanen Signed-off-by: Ingo Molnar --- include/linux/mmiotrace.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h index dd6b64b160fc..de8e91258da7 100644 --- a/include/linux/mmiotrace.h +++ b/include/linux/mmiotrace.h @@ -1,9 +1,7 @@ #ifndef MMIOTRACE_H #define MMIOTRACE_H -#include - -#ifdef __KERNEL__ +#include #include @@ -84,6 +82,4 @@ extern void disable_mmiotrace(void); extern void mmio_trace_rw(struct mmiotrace_rw *rw); extern void mmio_trace_mapping(struct mmiotrace_map *map); -#endif /* __KERNEL__ */ - #endif /* MMIOTRACE_H */ -- cgit v1.2.3 From dee310d0adf41019aca476052ac3085ff286d9be Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Mon, 12 May 2008 21:21:03 +0200 Subject: x86 mmiotrace: use resource_size_t for phys addresses Signed-off-by: Pekka Paalanen Signed-off-by: Ingo Molnar --- include/linux/mmiotrace.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h index de8e91258da7..5cbbc374e945 100644 --- a/include/linux/mmiotrace.h +++ b/include/linux/mmiotrace.h @@ -2,7 +2,6 @@ #define MMIOTRACE_H #include - #include struct kmmio_probe; @@ -37,14 +36,15 @@ extern int kmmio_handler(struct pt_regs *regs, unsigned long addr); /* Called from ioremap.c */ #ifdef CONFIG_MMIOTRACE -extern void -mmiotrace_ioremap(unsigned long offset, unsigned long size, void __iomem *addr); +extern void mmiotrace_ioremap(resource_size_t offset, unsigned long size, + void __iomem *addr); extern void mmiotrace_iounmap(volatile void __iomem *addr); #else -static inline void -mmiotrace_ioremap(unsigned long offset, unsigned long size, void __iomem *addr) +static inline void mmiotrace_ioremap(resource_size_t offset, + unsigned long size, void __iomem *addr) { } + static inline void mmiotrace_iounmap(volatile void __iomem *addr) { } @@ -60,7 +60,7 @@ enum mm_io_opcode { }; struct mmiotrace_rw { - unsigned long phys; /* PCI address of register */ + resource_size_t phys; /* PCI address of register */ unsigned long value; unsigned long pc; /* optional program counter */ int map_id; @@ -69,7 +69,7 @@ struct mmiotrace_rw { }; struct mmiotrace_map { - unsigned long phys; /* base address in PCI space */ + resource_size_t phys; /* base address in PCI space */ unsigned long virt; /* base virtual address */ unsigned long len; /* mapping size */ int map_id; -- cgit v1.2.3 From a50445d76c22a34ae149704ea5adaef171c8acb7 Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Mon, 12 May 2008 21:21:03 +0200 Subject: mmiotrace: rename kmmio_probe::user_data to :private. Signed-off-by: Pekka Paalanen Signed-off-by: Ingo Molnar --- include/linux/mmiotrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h index 5cbbc374e945..61d19e1b7a0b 100644 --- a/include/linux/mmiotrace.h +++ b/include/linux/mmiotrace.h @@ -18,7 +18,7 @@ struct kmmio_probe { unsigned long len; /* length of the probe region */ kmmio_pre_handler_t pre_handler; /* Called before addr is executed. */ kmmio_post_handler_t post_handler; /* Called after addr is executed */ - void *user_data; + void *private; }; /* kmmio is active by some kmmio_probes? */ -- cgit v1.2.3 From 41c52c0db9607e59f90da7da5309489fa06e887f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 22 May 2008 11:46:33 -0400 Subject: ftrace: set_ftrace_notrace feature While debugging latencies in the RT kernel, I found that it would be nice to be able to filter away functions from the trace than just to filter on functions. I added a new interface to the debugfs tracing directory called set_ftrace_notrace When dynamic frace is enabled, this lets you filter away functions that will not be recorded in the trace. It is similar to adding 'notrace' to those functions but by doing it without recompiling the kernel. Here's how set_ftrace_filter and set_ftrace_notrace interact. Remember, if set_ftrace_filter is set, it removes all functions from the trace execpt for those listed in the set_ftrace_filter. set_ftrace_notrace will prevent those functions from being traced. If you were to set one function in both set_ftrace_filter and set_ftrace_notrace and that function was the same, then you would end up with an empty trace. the set of functions to trace is: set_ftrace_filter == empty then all functions not in set_ftrace_notrace else set of the set_ftrace_filter and not in set of set_ftrace_notrace. Signed-off-by: Steven Rostedt Signed-off-by: Thomas Gleixner --- include/linux/ftrace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 922e23d0196f..ffbbd54a720e 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -48,6 +48,7 @@ enum { FTRACE_FL_FAILED = (1 << 1), FTRACE_FL_FILTER = (1 << 2), FTRACE_FL_ENABLED = (1 << 3), + FTRACE_FL_NOTRACE = (1 << 4), }; struct dyn_ftrace { -- cgit v1.2.3 From ccbfac2923c9febaeaf07a50054027a92b502718 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 22 May 2008 14:31:07 -0400 Subject: ftrace: powerpc clean ups This patch cleans up the ftrace code in PowerPC based on the comments from Michael Ellerman. Signed-off-by: Steven Rostedt Cc: Michael Ellerman Cc: proski@gnu.org Cc: a.p.zijlstra@chello.nl Cc: Pekka Paalanen Cc: Steven Rostedt Cc: linuxppc-dev@ozlabs.org Cc: Soeren Sandmann Pedersen Cc: paulus@samba.org Signed-off-by: Thomas Gleixner --- include/asm-powerpc/ftrace.h | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 include/asm-powerpc/ftrace.h (limited to 'include') diff --git a/include/asm-powerpc/ftrace.h b/include/asm-powerpc/ftrace.h new file mode 100644 index 000000000000..b1bfa704b6e5 --- /dev/null +++ b/include/asm-powerpc/ftrace.h @@ -0,0 +1,6 @@ +#ifndef _ASM_POWERPC_FTRACE +#define _ASM_POWERPC_FTRACE + +extern void _mcount(void); + +#endif -- cgit v1.2.3 From b1829d2705daa7cb72eb1e08bdc8b7e9fad34266 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 28 May 2008 01:22:08 +0200 Subject: ftrace: fix merge Signed-off-by: Ingo Molnar --- include/linux/ftrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ffbbd54a720e..b482fe88bc04 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -122,7 +122,7 @@ static inline void tracer_disable(void) # define trace_preempt_off(a0, a1) do { } while (0) #endif -#ifdef CONFIG_CONTEXT_SWITCH_TRACER +#ifdef CONFIG_TRACING extern void ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3); #else -- cgit v1.2.3 From ad90c0e3ce8d20d6873b57e36181ef6d7a0097fe Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 27 May 2008 20:48:37 -0400 Subject: ftrace: user update and disable dynamic ftrace daemon In dynamic ftrace, the mcount function starts off pointing to a stub function that just returns. On start up, the call to the stub is modified to point to a "record_ip" function. The job of the record_ip function is to add the function to a pre-allocated hash list. If the function is already there, it simply is ignored, otherwise it is added to the list. Later, a ftraced daemon wakes up and calls kstop_machine if any functions have been recorded, and changes the calls to the recorded functions to a simple nop. If no functions were recorded, the daemon goes back to sleep. The daemon wakes up once a second to see if it needs to update any newly recorded functions into nops. Usually it does not, but if a lot of code has been executed for the first time in the kernel, the ftraced daemon will call kstop_machine to update those into nops. The problem currently is that there's no way to stop the daemon from doing this, and it can cause unneeded latencies (800us which for some is bothersome). This patch adds a new file /debugfs/tracing/ftraced_enabled. If the daemon is active, reading this will return "enabled\n" and "disabled\n" when the daemon is not running. To disable the daemon, the user can echo "0" or "disable" into this file, and "1" or "enable" to re-enable the daemon. Since the daemon is used to convert the functions into nops to increase the performance of the system, I also added that anytime something is written into the ftraced_enabled file, kstop_machine will run if there are new functions that have been detected that need to be converted. This way the user can disable the daemon but still be able to control the conversion of the mcount calls to nops by simply, "echo 0 > /debugfs/tracing/ftraced_enabled" when they need to do more conversions. To see the number of converted functions: "cat /debugfs/tracing/dyn_ftrace_total_info" Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/ftrace.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index b482fe88bc04..623819433ed5 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -72,9 +72,15 @@ extern int ftrace_update_ftrace_func(ftrace_func_t func); extern void ftrace_caller(void); extern void ftrace_call(void); extern void mcount_call(void); + +void ftrace_disable_daemon(void); +void ftrace_enable_daemon(void); + #else # define ftrace_force_update() ({ 0; }) # define ftrace_set_filter(buf, len, reset) do { } while (0) +# define ftrace_disable_daemon() do { } while (0) +# define ftrace_enable_daemon() do { } while (0) #endif /* totally disable ftrace - can not re-enable after this */ -- cgit v1.2.3 From e0773410247f1e5fc6f7c52a4c5f3c6c9873d527 Mon Sep 17 00:00:00 2001 From: Abhishek Sagar Date: Sat, 31 May 2008 14:24:02 +0530 Subject: ftrace: export kretprobe_trampoline for function tracer Follow suit from kprobe implementations on other archs and make kretprobe_trampoline non-static. Ftrace implmentation (more specifically, kernel/trace/trace.c) requires access to it (see-> http://kerneltrap.org/mailarchive/linux-kernel/2008/5/27/1955234). Signed-off-by: Abhishek Sagar Signed-off-by: Ingo Molnar --- include/asm-arm/kprobes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/asm-arm/kprobes.h b/include/asm-arm/kprobes.h index c042194d3ab5..b1a37876942d 100644 --- a/include/asm-arm/kprobes.h +++ b/include/asm-arm/kprobes.h @@ -59,6 +59,7 @@ struct kprobe_ctlblk { }; void arch_remove_kprobe(struct kprobe *); +void kretprobe_trampoline(void); int kprobe_trap_handler(struct pt_regs *regs, unsigned int instr); int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr); -- cgit v1.2.3 From 0eb967012ea15e6e8cfab483d9fa37bc602d400c Mon Sep 17 00:00:00 2001 From: Abhishek Sagar Date: Sun, 1 Jun 2008 21:47:30 +0530 Subject: ftrace: prevent freeing of all failed updates Prevent freeing of records which cause problems and correspond to function from core kernel text. A new flag, FTRACE_FL_CONVERTED is used to mark a record as "converted". All other records are patched lazily to NOPs. Failed records now also remain on frace_hash table. Each invocation of ftrace_record_ip now checks whether the traced function has ever been recorded (including past failures) and doesn't re-record it again. Signed-off-by: Abhishek Sagar Signed-off-by: Ingo Molnar --- include/linux/ftrace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 623819433ed5..20e14d0093c7 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -49,6 +49,7 @@ enum { FTRACE_FL_FILTER = (1 << 2), FTRACE_FL_ENABLED = (1 << 3), FTRACE_FL_NOTRACE = (1 << 4), + FTRACE_FL_CONVERTED = (1 << 5), }; struct dyn_ftrace { -- cgit v1.2.3 From 395a59d0f8e86bb39cd700c3d185d30c670bb958 Mon Sep 17 00:00:00 2001 From: Abhishek Sagar Date: Sat, 21 Jun 2008 23:47:27 +0530 Subject: ftrace: store mcount address in rec->ip Record the address of the mcount call-site. Currently all archs except sparc64 record the address of the instruction following the mcount call-site. Some general cleanups are entailed. Storing mcount addresses in rec->ip enables looking them up in the kprobe hash table later on to check if they're kprobe'd. Signed-off-by: Abhishek Sagar Cc: davem@davemloft.net Cc: Steven Rostedt Signed-off-by: Ingo Molnar --- include/asm-arm/ftrace.h | 14 ++++++++++++++ include/asm-powerpc/ftrace.h | 8 ++++++++ include/asm-sparc64/ftrace.h | 14 ++++++++++++++ include/asm-x86/ftrace.h | 14 ++++++++++++++ include/linux/ftrace.h | 3 +-- 5 files changed, 51 insertions(+), 2 deletions(-) create mode 100644 include/asm-arm/ftrace.h create mode 100644 include/asm-sparc64/ftrace.h create mode 100644 include/asm-x86/ftrace.h (limited to 'include') diff --git a/include/asm-arm/ftrace.h b/include/asm-arm/ftrace.h new file mode 100644 index 000000000000..584ef9a8e5a5 --- /dev/null +++ b/include/asm-arm/ftrace.h @@ -0,0 +1,14 @@ +#ifndef _ASM_ARM_FTRACE +#define _ASM_ARM_FTRACE + +#ifdef CONFIG_FTRACE +#define MCOUNT_ADDR ((long)(mcount)) +#define MCOUNT_INSN_SIZE 4 /* sizeof mcount call */ + +#ifndef __ASSEMBLY__ +extern void mcount(void); +#endif + +#endif + +#endif /* _ASM_ARM_FTRACE */ diff --git a/include/asm-powerpc/ftrace.h b/include/asm-powerpc/ftrace.h index b1bfa704b6e5..de921326cca8 100644 --- a/include/asm-powerpc/ftrace.h +++ b/include/asm-powerpc/ftrace.h @@ -1,6 +1,14 @@ #ifndef _ASM_POWERPC_FTRACE #define _ASM_POWERPC_FTRACE +#ifdef CONFIG_FTRACE +#define MCOUNT_ADDR ((long)(_mcount)) +#define MCOUNT_INSN_SIZE 4 /* sizeof mcount call */ + +#ifndef __ASSEMBLY__ extern void _mcount(void); +#endif #endif + +#endif /* _ASM_POWERPC_FTRACE */ diff --git a/include/asm-sparc64/ftrace.h b/include/asm-sparc64/ftrace.h new file mode 100644 index 000000000000..f76a40a338bb --- /dev/null +++ b/include/asm-sparc64/ftrace.h @@ -0,0 +1,14 @@ +#ifndef _ASM_SPARC64_FTRACE +#define _ASM_SPARC64_FTRACE + +#ifdef CONFIG_FTRACE +#define MCOUNT_ADDR ((long)(_mcount)) +#define MCOUNT_INSN_SIZE 4 /* sizeof mcount call */ + +#ifndef __ASSEMBLY__ +extern void _mcount(void); +#endif + +#endif + +#endif /* _ASM_SPARC64_FTRACE */ diff --git a/include/asm-x86/ftrace.h b/include/asm-x86/ftrace.h new file mode 100644 index 000000000000..c184441133f2 --- /dev/null +++ b/include/asm-x86/ftrace.h @@ -0,0 +1,14 @@ +#ifndef _ASM_X86_FTRACE +#define _ASM_SPARC64_FTRACE + +#ifdef CONFIG_FTRACE +#define MCOUNT_ADDR ((long)(mcount)) +#define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ + +#ifndef __ASSEMBLY__ +extern void mcount(void); +#endif + +#endif /* CONFIG_FTRACE */ + +#endif /* _ASM_X86_FTRACE */ diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 20e14d0093c7..366098d591de 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -31,7 +31,6 @@ int unregister_ftrace_function(struct ftrace_ops *ops); void clear_ftrace_function(void); extern void ftrace_stub(unsigned long a0, unsigned long a1); -extern void mcount(void); #else /* !CONFIG_FTRACE */ # define register_ftrace_function(ops) do { } while (0) @@ -54,7 +53,7 @@ enum { struct dyn_ftrace { struct hlist_node node; - unsigned long ip; + unsigned long ip; /* address of mcount call-site */ unsigned long flags; }; -- cgit v1.2.3 From 785656a41f9a9c0e843a23d1ae05d900b5158f8f Mon Sep 17 00:00:00 2001 From: Abhishek Sagar Date: Sat, 21 Jun 2008 23:47:39 +0530 Subject: kprobes: enable clean usage of get_kprobe Allow clean use of get_kprobe() outside of core kprobe code. Ftrace makes use of get_kprobe to identify probes installed on mcount call-sites. Signed-off-by: Abhishek Sagar Acked-by: Ananth N Mavinakayanahalli Cc: Masami Hiramatsu Cc: jkenisto@us.ibm.com Cc: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 1036631ff4fa..04a3556bdea6 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -259,6 +259,10 @@ void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); struct jprobe; struct kretprobe; +static inline struct kprobe *get_kprobe(void *addr) +{ + return NULL; +} static inline struct kprobe *kprobe_running(void) { return NULL; -- cgit v1.2.3 From ecea656d1d5e912d2f3d332657ea4a6d8380f891 Mon Sep 17 00:00:00 2001 From: Abhishek Sagar Date: Sat, 21 Jun 2008 23:47:53 +0530 Subject: ftrace: freeze kprobe'd records Let records identified as being kprobe'd be marked as "frozen". The trouble with records which have a kprobe installed on their mcount call-site is that they don't get updated. So if such a function which is currently being traced gets its tracing disabled due to a new filter rule (or because it was added to the notrace list) then it won't be updated and continue being traced. This patch allows scanning of all frozen records during tracing to check if they should be traced. Signed-off-by: Abhishek Sagar Cc: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/ftrace.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 366098d591de..3121b95443d9 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -49,6 +49,7 @@ enum { FTRACE_FL_ENABLED = (1 << 3), FTRACE_FL_NOTRACE = (1 << 4), FTRACE_FL_CONVERTED = (1 << 5), + FTRACE_FL_FROZEN = (1 << 6), }; struct dyn_ftrace { @@ -73,15 +74,18 @@ extern void ftrace_caller(void); extern void ftrace_call(void); extern void mcount_call(void); +extern int skip_trace(unsigned long ip); + void ftrace_disable_daemon(void); void ftrace_enable_daemon(void); #else +# define skip_trace(ip) ({ 0; }) # define ftrace_force_update() ({ 0; }) # define ftrace_set_filter(buf, len, reset) do { } while (0) # define ftrace_disable_daemon() do { } while (0) # define ftrace_enable_daemon() do { } while (0) -#endif +#endif /* CONFIG_DYNAMIC_FTRACE */ /* totally disable ftrace - can not re-enable after this */ void ftrace_kill(void); -- cgit v1.2.3 From 760378e1497841246ea7e42abad617d8a8ac0bcc Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 1 Jul 2008 17:35:06 +0200 Subject: fix "ftrace: store mcount address in rec->ip" Alexander Beregalov reported this build failure: $ make CROSS_COMPILE=sparc64-unknown-linux-gnu- image modules && sudo make modules_install CHK include/linux/version.h CHK include/linux/utsrelease.h CALL scripts/checksyscalls.sh CHK include/linux/compile.h dnsdomainname: Unknown host CC arch/sparc64/kernel/sparc64_ksyms.o arch/sparc64/kernel/sparc64_ksyms.c:116: error: '_mcount' undeclared here (not in a function) cc1: warnings being treated as errors arch/sparc64/kernel/sparc64_ksyms.c:116: error: type defaults to 'int' in declaration of '_mcount' And bisected it back to: | commit 395a59d0f8e86bb39cd700c3d185d30c670bb958 | Author: Abhishek Sagar | Date: Sat Jun 21 23:47:27 2008 +0530 | | ftrace: store mcount address in rec->ip the mcount prototype is only available under CONFIG_FTRACE, extend it to CONFIG_MCOUNT as well. Reported-and-bisected-by: Alexander Beregalov Signed-off-by: Ingo Molnar --- include/asm-sparc64/ftrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-sparc64/ftrace.h b/include/asm-sparc64/ftrace.h index f76a40a338bb..d27716cd38c1 100644 --- a/include/asm-sparc64/ftrace.h +++ b/include/asm-sparc64/ftrace.h @@ -1,7 +1,7 @@ #ifndef _ASM_SPARC64_FTRACE #define _ASM_SPARC64_FTRACE -#ifdef CONFIG_FTRACE +#ifdef CONFIG_MCOUNT #define MCOUNT_ADDR ((long)(_mcount)) #define MCOUNT_INSN_SIZE 4 /* sizeof mcount call */ -- cgit v1.2.3 From a2bb6a3d85ef3124cd336403a95abc0540d3fbe2 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 10 Jul 2008 20:58:15 -0400 Subject: ftrace: add ftrace_kill_atomic It has been suggested that I add a way to disable the function tracer on an oops. This code adds a ftrace_kill_atomic. It is not meant to be used in normal situations. It will disable the ftrace tracer, but will not perform the nice shutdown that requires scheduling. Signed-off-by: Steven Rostedt Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/ftrace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 3121b95443d9..f368d041e02d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -89,6 +89,7 @@ void ftrace_enable_daemon(void); /* totally disable ftrace - can not re-enable after this */ void ftrace_kill(void); +void ftrace_kill_atomic(void); static inline void tracer_disable(void) { -- cgit v1.2.3