Merge branch 'tracing-core-for-linus' of git://git.kernel.org/pub/scm…

…/linux/kernel/git/tip/linux-2.6-tip

* 'tracing-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (28 commits)
  ftrace: Add function names to dangling } in function graph tracer
  tracing: Simplify memory recycle of trace_define_field
  tracing: Remove unnecessary variable in print_graph_return
  tracing: Fix typo of info text in trace_kprobe.c
  tracing: Fix typo in prof_sysexit_enable()
  tracing: Remove CONFIG_TRACE_POWER from kernel config
  tracing: Fix ftrace_event_call alignment for use with gcc 4.5
  ftrace: Remove memory barriers from NMI code when not needed
  tracing/kprobes: Add short documentation for HAVE_REGS_AND_STACK_ACCESS_API
  s390: Add pt_regs register and stack access API
  tracing/kprobes: Make Kconfig dependencies generic
  tracing: Unify arch_syscall_addr() implementations
  tracing: Add notrace to TRACE_EVENT implementation functions
  ftrace: Allow to remove a single function from function graph filter
  tracing: Add correct/incorrect to sort keys for branch annotation output
  tracing: Simplify test for function_graph tracing start point
  tracing: Drop the tr check from the graph tracing path
  tracing: Add stack dump to trace_printk if stacktrace option is set
  tracing: Use appropriate perl constructs in recordmcount.pl
  tracing: optimize recordmcount.pl for offsets-handling
  ...

Documentation/trace/ftrace-design.txt

@@ -238,11 +238,10 @@ HAVE_SYSCALL_TRACEPOINTS
 
 You need very few things to get the syscalls tracing in an arch.
 
+- Support HAVE_ARCH_TRACEHOOK (see arch/Kconfig).
 - Have a NR_syscalls variable in <asm/unistd.h> that provides the number
   of syscalls supported by the arch.
-- Implement arch_syscall_addr() that resolves a syscall address from a
-  syscall number.
-- Support the TIF_SYSCALL_TRACEPOINT thread flags
+- Support the TIF_SYSCALL_TRACEPOINT thread flags.
 - Put the trace_sys_enter() and trace_sys_exit() tracepoints calls from ptrace
   in the ptrace syscalls tracing path.
 - Tag this arch as HAVE_SYSCALL_TRACEPOINTS.

arch/Kconfig

@@ -105,6 +105,14 @@ config HAVE_DMA_ATTRS
 config USE_GENERIC_SMP_HELPERS
 	bool
 
+config HAVE_REGS_AND_STACK_ACCESS_API
+	bool
+	help
+	  This symbol should be selected by an architecure if it supports
+	  the API needed to access registers and stack entries from pt_regs,
+	  declared in asm/ptrace.h
+	  For example the kprobes-based event tracer needs this API.
+
 config HAVE_CLK
 	bool
 	help

arch/s390/Kconfig

@@ -90,6 +90,7 @@ config S390
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_DEFAULT_NO_SPIN_MUTEXES
 	select HAVE_OPROFILE
 	select HAVE_KPROBES

arch/s390/include/asm/ptrace.h

@@ -492,13 +492,24 @@ struct user_regs_struct
 struct task_struct;
 extern void user_enable_single_step(struct task_struct *);
 extern void user_disable_single_step(struct task_struct *);
+extern void show_regs(struct pt_regs * regs);
 
 #define user_mode(regs) (((regs)->psw.mask & PSW_MASK_PSTATE) != 0)
 #define instruction_pointer(regs) ((regs)->psw.addr & PSW_ADDR_INSN)
 #define user_stack_pointer(regs)((regs)->gprs[15])
 #define regs_return_value(regs)((regs)->gprs[2])
 #define profile_pc(regs) instruction_pointer(regs)
-extern void show_regs(struct pt_regs * regs);
+
+int regs_query_register_offset(const char *name);
+const char *regs_query_register_name(unsigned int offset);
+unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset);
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n);
+
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	return regs->gprs[15] & PSW_ADDR_INSN;
+}
+
 #endif /* __KERNEL__ */
 #endif /* __ASSEMBLY__ */
 

arch/s390/include/asm/syscall.h

@@ -15,6 +15,13 @@
 #include <linux/sched.h>
 #include <asm/ptrace.h>
 
+/*
+ * The syscall table always contains 32 bit pointers since we know that the
+ * address of the function to be called is (way) below 4GB.  So the "int"
+ * type here is what we want [need] for both 32 bit and 64 bit systems.
+ */
+extern const unsigned int sys_call_table[];
+
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
 {

arch/s390/kernel/ftrace.c

@@ -200,13 +200,3 @@ unsigned long prepare_ftrace_return(unsigned long ip, unsigned long parent)
 	return parent;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
-#ifdef CONFIG_FTRACE_SYSCALLS
-
-extern unsigned int sys_call_table[];
-
-unsigned long __init arch_syscall_addr(int nr)
-{
-	return (unsigned long)sys_call_table[nr];
-}
-#endif

arch/s390/kernel/ptrace.c

@@ -992,3 +992,61 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 #endif
 	return &user_s390_view;
 }
+
+static const char *gpr_names[NUM_GPRS] = {
+	"r0", "r1",  "r2",  "r3",  "r4",  "r5",  "r6",  "r7",
+	"r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15",
+};
+
+unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset)
+{
+	if (offset >= NUM_GPRS)
+		return 0;
+	return regs->gprs[offset];
+}
+
+int regs_query_register_offset(const char *name)
+{
+	unsigned long offset;
+
+	if (!name || *name != 'r')
+		return -EINVAL;
+	if (strict_strtoul(name + 1, 10, &offset))
+		return -EINVAL;
+	if (offset >= NUM_GPRS)
+		return -EINVAL;
+	return offset;
+}
+
+const char *regs_query_register_name(unsigned int offset)
+{
+	if (offset >= NUM_GPRS)
+		return NULL;
+	return gpr_names[offset];
+}
+
+static int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
+{
+	unsigned long ksp = kernel_stack_pointer(regs);
+
+	return (addr & ~(THREAD_SIZE - 1)) == (ksp & ~(THREAD_SIZE - 1));
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:pt_regs which contains kernel stack pointer.
+ * @n:stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specifined by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+	unsigned long addr;
+
+	addr = kernel_stack_pointer(regs) + n * sizeof(long);
+	if (!regs_within_kernel_stack(regs, addr))
+		return 0;
+	return *(unsigned long *)addr;
+}

arch/sh/include/asm/syscall.h

@@ -1,6 +1,8 @@
 #ifndef __ASM_SH_SYSCALL_H
 #define __ASM_SH_SYSCALL_H
 
+extern const unsigned long sys_call_table[];
+
 #ifdef CONFIG_SUPERH32
 # include "syscall_32.h"
 #else

arch/sh/kernel/ftrace.c

@@ -399,12 +399,3 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	}
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
-#ifdef CONFIG_FTRACE_SYSCALLS
-extern unsigned long *sys_call_table;
-
-unsigned long __init arch_syscall_addr(int nr)
-{
-	return (unsigned long)sys_call_table[nr];
-}
-#endif /* CONFIG_FTRACE_SYSCALLS */

arch/sparc/include/asm/syscall.h

@@ -5,6 +5,13 @@
 #include <linux/sched.h>
 #include <asm/ptrace.h>
 
+/*
+ * The syscall table always contains 32 bit pointers since we know that the
+ * address of the function to be called is (way) below 4GB.  So the "int"
+ * type here is what we want [need] for both 32 bit and 64 bit systems.
+ */
+extern const unsigned int sys_call_table[];
+
 /* The system call number is given by the user in %g1 */
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)

arch/sparc/kernel/ftrace.c

@@ -91,14 +91,3 @@ int __init ftrace_dyn_arch_init(void *data)
 	return 0;
 }
 #endif
-
-#ifdef CONFIG_FTRACE_SYSCALLS
-
-extern unsigned int sys_call_table[];
-
-unsigned long __init arch_syscall_addr(int nr)
-{
-	return (unsigned long)sys_call_table[nr];
-}
-
-#endif

arch/x86/Kconfig

@@ -45,6 +45,7 @@ config X86
 	select HAVE_GENERIC_DMA_COHERENT if X86_32
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select USER_STACKTRACE_SUPPORT
+	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_DMA_API_DEBUG
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_BZIP2

arch/x86/include/asm/syscall.h

@@ -16,6 +16,8 @@
 #include <linux/sched.h>
 #include <linux/err.h>
 
+extern const unsigned long sys_call_table[];
+
 /*
  * Only the low 32 bits of orig_ax are meaningful, so we return int.
  * This importantly ignores the high bits on 64-bit, so comparisons

arch/x86/kernel/ftrace.c

@@ -30,14 +30,32 @@
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
+/*
+ * modifying_code is set to notify NMIs that they need to use
+ * memory barriers when entering or exiting. But we don't want
+ * to burden NMIs with unnecessary memory barriers when code
+ * modification is not being done (which is most of the time).
+ *
+ * A mutex is already held when ftrace_arch_code_modify_prepare
+ * and post_process are called. No locks need to be taken here.
+ *
+ * Stop machine will make sure currently running NMIs are done
+ * and new NMIs will see the updated variable before we need
+ * to worry about NMIs doing memory barriers.
+ */
+static int modifying_code __read_mostly;
+static DEFINE_PER_CPU(int, save_modifying_code);
+
 int ftrace_arch_code_modify_prepare(void)
 {
 	set_kernel_text_rw();
+	modifying_code = 1;
 	return 0;
 }
 
 int ftrace_arch_code_modify_post_process(void)
 {
+	modifying_code = 0;
 	set_kernel_text_ro();
 	return 0;
 }
@@ -149,6 +167,11 @@ static void ftrace_mod_code(void)
 
 void ftrace_nmi_enter(void)
 {
+	__get_cpu_var(save_modifying_code) = modifying_code;
+
+	if (!__get_cpu_var(save_modifying_code))
+		return;
+
 	if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) {
 		smp_rmb();
 		ftrace_mod_code();
@@ -160,6 +183,9 @@ void ftrace_nmi_enter(void)
 
 void ftrace_nmi_exit(void)
 {
+	if (!__get_cpu_var(save_modifying_code))
+		return;
+
 	/* Finish all executions before clearing nmi_running */
 	smp_mb();
 	atomic_dec(&nmi_running);
@@ -484,13 +510,3 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	}
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
-#ifdef CONFIG_FTRACE_SYSCALLS
-
-extern unsigned long *sys_call_table;
-
-unsigned long __init arch_syscall_addr(int nr)
-{
-	return (unsigned long)(&sys_call_table)[nr];
-}
-#endif

include/linux/ftrace.h

@@ -511,4 +511,10 @@ static inline void trace_hw_branch_oops(void) {}
 
 #endif /* CONFIG_HW_BRANCH_TRACER */
 
+#ifdef CONFIG_FTRACE_SYSCALLS
+
+unsigned long arch_syscall_addr(int nr);
+
+#endif /* CONFIG_FTRACE_SYSCALLS */
+
 #endif /* _LINUX_FTRACE_H */

include/linux/ftrace_event.h

@@ -121,9 +121,8 @@ struct ftrace_event_call {
 	int			(*regfunc)(struct ftrace_event_call *);
 	void			(*unregfunc)(struct ftrace_event_call *);
 	int			id;
+	const char		*print_fmt;
 	int			(*raw_init)(struct ftrace_event_call *);
-	int			(*show_format)(struct ftrace_event_call *,
-					       struct trace_seq *);
 	int			(*define_fields)(struct ftrace_event_call *);
 	struct list_head	fields;
 	int			filter_active;

include/linux/syscalls.h

@@ -132,7 +132,8 @@ struct perf_event_attr;
 
 #define SYSCALL_TRACE_ENTER_EVENT(sname)				\
 	static const struct syscall_metadata __syscall_meta_##sname;	\
-	static struct ftrace_event_call event_enter_##sname;		\
+	static struct ftrace_event_call					\
+	__attribute__((__aligned__(4))) event_enter_##sname;		\
 	static struct trace_event enter_syscall_print_##sname = {	\
 		.trace                  = print_syscall_enter,		\
 	};								\
@@ -143,8 +144,7 @@ struct perf_event_attr;
 		.name                   = "sys_enter"#sname,		\
 		.system                 = "syscalls",			\
 		.event                  = &enter_syscall_print_##sname,	\
-		.raw_init		= trace_event_raw_init,		\
-		.show_format		= syscall_enter_format,		\
+		.raw_init		= init_syscall_trace,		\
 		.define_fields		= syscall_enter_define_fields,	\
 		.regfunc		= reg_event_syscall_enter,	\
 		.unregfunc		= unreg_event_syscall_enter,	\
@@ -154,7 +154,8 @@ struct perf_event_attr;
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
 	static const struct syscall_metadata __syscall_meta_##sname;	\
-	static struct ftrace_event_call event_exit_##sname;		\
+	static struct ftrace_event_call					\
+	__attribute__((__aligned__(4))) event_exit_##sname;		\
 	static struct trace_event exit_syscall_print_##sname = {	\
 		.trace                  = print_syscall_exit,		\
 	};								\
@@ -165,8 +166,7 @@ struct perf_event_attr;
 		.name                   = "sys_exit"#sname,		\
 		.system                 = "syscalls",			\
 		.event                  = &exit_syscall_print_##sname,	\
-		.raw_init		= trace_event_raw_init,		\
-		.show_format		= syscall_exit_format,		\
+		.raw_init		= init_syscall_trace,		\
 		.define_fields		= syscall_exit_define_fields,	\
 		.regfunc		= reg_event_syscall_exit,	\
 		.unregfunc		= unreg_event_syscall_exit,	\