Merge branch 'tracing-core-for-linus' of...

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: (40 commits)
  tracing: Separate raw syscall from syscall tracer
  ring-buffer-benchmark: Add parameters to set produce/consumer priorities
  tracing, function tracer: Clean up strstrip() usage
  ring-buffer benchmark: Run producer/consumer threads at nice +19
  tracing: Remove the stale include/trace/power.h
  tracing: Only print objcopy version warning once from recordmcount
  tracing: Prevent build warning: 'ftrace_graph_buf' defined but not used
  ring-buffer: Move access to commit_page up into function used
  tracing: do not disable interrupts for trace_clock_local
  ring-buffer: Add multiple iterations between benchmark timestamps
  kprobes: Sanitize struct kretprobe_instance allocations
  tracing: Fix to use __always_unused attribute
  compiler: Introduce __always_unused
  tracing: Exit with error if a weak function is used in recordmcount.pl
  tracing: Move conditional into update_funcs() in recordmcount.pl
  tracing: Add regex for weak functions in recordmcount.pl
  tracing: Move mcount section search to front of loop in recordmcount.pl
  tracing: Fix objcopy revision check in recordmcount.pl
  tracing: Check absolute path of input file in recordmcount.pl
  tracing: Correct the check for number of arguments in recordmcount.pl
  ...

Documentation/kernel-parameters.txt

@@ -778,6 +778,13 @@ and is between 256 and 4096 characters. It is defined in the file
 			by the set_ftrace_notrace file in the debugfs
 			tracing directory.
 
+	ftrace_graph_filter=[function-list]
+			[FTRACE] Limit the top level callers functions traced
+			by the function graph tracer at boot up.
+			function-list is a comma separated list of functions
+			that can be changed at run time by the
+			set_graph_function file in the debugfs tracing directory.
+
 	gamecon.map[2|3]=
 			[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
 			support via parallel port (up to 5 devices per port)

Documentation/trace/ftrace-design.txt

@@ -213,10 +213,19 @@ If you can't trace NMI functions, then skip this option.
 <details to be filled>
 
 
-HAVE_FTRACE_SYSCALLS
+HAVE_SYSCALL_TRACEPOINTS
 ---------------------
 
-<details to be filled>
+You need very few things to get the syscalls tracing in an arch.
+
+- 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
+- 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.
 
 
 HAVE_FTRACE_MCOUNT_RECORD

Makefile

@@ -379,6 +379,7 @@ export RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn --exc
 PHONY += scripts_basic
 scripts_basic:
 	$(Q)$(MAKE) $(build)=scripts/basic
+	$(Q)rm -f .tmp_quiet_recordmcount
 
 # To avoid any implicit rule to kick in, define an empty command.
 scripts/basic/%: scripts_basic ;

arch/s390/kernel/ftrace.c

@@ -203,73 +203,10 @@ out:
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 
-extern unsigned long __start_syscalls_metadata[];
-extern unsigned long __stop_syscalls_metadata[];
 extern unsigned int sys_call_table[];
 
-static struct syscall_metadata **syscalls_metadata;
-
-struct syscall_metadata *syscall_nr_to_meta(int nr)
-{
-	if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
-		return NULL;
-
-	return syscalls_metadata[nr];
-}
-
-int syscall_name_to_nr(char *name)
-{
-	int i;
-
-	if (!syscalls_metadata)
-		return -1;
-	for (i = 0; i < NR_syscalls; i++)
-		if (syscalls_metadata[i])
-			if (!strcmp(syscalls_metadata[i]->name, name))
-				return i;
-	return -1;
-}
-
-void set_syscall_enter_id(int num, int id)
-{
-	syscalls_metadata[num]->enter_id = id;
-}
-
-void set_syscall_exit_id(int num, int id)
+unsigned long __init arch_syscall_addr(int nr)
 {
-	syscalls_metadata[num]->exit_id = id;
-}
-
-static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
-{
-	struct syscall_metadata *start;
-	struct syscall_metadata *stop;
-	char str[KSYM_SYMBOL_LEN];
-
-	start = (struct syscall_metadata *)__start_syscalls_metadata;
-	stop = (struct syscall_metadata *)__stop_syscalls_metadata;
-	kallsyms_lookup(syscall, NULL, NULL, NULL, str);
-
-	for ( ; start < stop; start++) {
-		if (start->name && !strcmp(start->name + 3, str + 3))
-			return start;
-	}
-	return NULL;
-}
-
-static int __init arch_init_ftrace_syscalls(void)
-{
-	struct syscall_metadata *meta;
-	int i;
-	syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * NR_syscalls,
-				    GFP_KERNEL);
-	if (!syscalls_metadata)
-		return -ENOMEM;
-	for (i = 0; i < NR_syscalls; i++) {
-		meta = find_syscall_meta((unsigned long)sys_call_table[i]);
-		syscalls_metadata[i] = meta;
-	}
-	return 0;
+	return (unsigned long)sys_call_table[nr];
 }
-arch_initcall(arch_init_ftrace_syscalls);
 #endif

arch/x86/kernel/entry_32.S

@@ -1185,17 +1185,14 @@ END(ftrace_graph_caller)
 
 .globl return_to_handler
 return_to_handler:
-	pushl $0
 	pushl %eax
-	pushl %ecx
 	pushl %edx
 	movl %ebp, %eax
 	call ftrace_return_to_handler
-	movl %eax, 0xc(%esp)
+	movl %eax, %ecx
 	popl %edx
-	popl %ecx
 	popl %eax
-	ret
+	jmp *%ecx
 #endif
 
 .section .rodata,"a"

arch/x86/kernel/entry_64.S

@@ -155,11 +155,11 @@ GLOBAL(return_to_handler)
 
 	call ftrace_return_to_handler
 
-	movq %rax, 16(%rsp)
+	movq %rax, %rdi
 	movq 8(%rsp), %rdx
 	movq (%rsp), %rax
-	addq $16, %rsp
-	retq
+	addq $24, %rsp
+	jmp *%rdi
 #endif
 
 

arch/x86/kernel/ftrace.c

@@ -9,6 +9,8 @@
  * the dangers of modifying code on the run.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
 #include <linux/uaccess.h>
@@ -336,15 +338,15 @@ int __init ftrace_dyn_arch_init(void *data)
 
 	switch (faulted) {
 	case 0:
-		pr_info("ftrace: converting mcount calls to 0f 1f 44 00 00\n");
+		pr_info("converting mcount calls to 0f 1f 44 00 00\n");
 		memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE);
 		break;
 	case 1:
-		pr_info("ftrace: converting mcount calls to 66 66 66 66 90\n");
+		pr_info("converting mcount calls to 66 66 66 66 90\n");
 		memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE);
 		break;
 	case 2:
-		pr_info("ftrace: converting mcount calls to jmp . + 5\n");
+		pr_info("converting mcount calls to jmp . + 5\n");
 		memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE);
 		break;
 	}
@@ -468,82 +470,10 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 
-extern unsigned long __start_syscalls_metadata[];
-extern unsigned long __stop_syscalls_metadata[];
 extern unsigned long *sys_call_table;
 
-static struct syscall_metadata **syscalls_metadata;
-
-static struct syscall_metadata *find_syscall_meta(unsigned long *syscall)
-{
-	struct syscall_metadata *start;
-	struct syscall_metadata *stop;
-	char str[KSYM_SYMBOL_LEN];
-
-
-	start = (struct syscall_metadata *)__start_syscalls_metadata;
-	stop = (struct syscall_metadata *)__stop_syscalls_metadata;
-	kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str);
-
-	for ( ; start < stop; start++) {
-		if (start->name && !strcmp(start->name, str))
-			return start;
-	}
-	return NULL;
-}
-
-struct syscall_metadata *syscall_nr_to_meta(int nr)
-{
-	if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
-		return NULL;
-
-	return syscalls_metadata[nr];
-}
-
-int syscall_name_to_nr(char *name)
+unsigned long __init arch_syscall_addr(int nr)
 {
-	int i;
-
-	if (!syscalls_metadata)
-		return -1;
-
-	for (i = 0; i < NR_syscalls; i++) {
-		if (syscalls_metadata[i]) {
-			if (!strcmp(syscalls_metadata[i]->name, name))
-				return i;
-		}
-	}
-	return -1;
-}
-
-void set_syscall_enter_id(int num, int id)
-{
-	syscalls_metadata[num]->enter_id = id;
-}
-
-void set_syscall_exit_id(int num, int id)
-{
-	syscalls_metadata[num]->exit_id = id;
-}
-
-static int __init arch_init_ftrace_syscalls(void)
-{
-	int i;
-	struct syscall_metadata *meta;
-	unsigned long **psys_syscall_table = &sys_call_table;
-
-	syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
-					NR_syscalls, GFP_KERNEL);
-	if (!syscalls_metadata) {
-		WARN_ON(1);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < NR_syscalls; i++) {
-		meta = find_syscall_meta(psys_syscall_table[i]);
-		syscalls_metadata[i] = meta;
-	}
-	return 0;
+	return (unsigned long)(&sys_call_table)[nr];
 }
-arch_initcall(arch_init_ftrace_syscalls);
 #endif

arch/x86/mm/testmmiotrace.c

 /*
  * Written by Pekka Paalanen, 2008-2009 <pq@iki.fi>
  */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/io.h>
 #include <linux/mmiotrace.h>
 
-#define MODULE_NAME "testmmiotrace"
-
 static unsigned long mmio_address;
 module_param(mmio_address, ulong, 0);
 MODULE_PARM_DESC(mmio_address, " Start address of the mapping of 16 kB "
@@ -30,7 +31,7 @@ static unsigned v32(unsigned i)
 static void do_write_test(void __iomem *p)
 {
 	unsigned int i;
-	pr_info(MODULE_NAME ": write test.\n");
+	pr_info("write test.\n");
 	mmiotrace_printk("Write test.\n");
 
 	for (i = 0; i < 256; i++)
@@ -47,7 +48,7 @@ static void do_read_test(void __iomem *p)
 {
 	unsigned int i;
 	unsigned errs[3] = { 0 };
-	pr_info(MODULE_NAME ": read test.\n");
+	pr_info("read test.\n");
 	mmiotrace_printk("Read test.\n");
 
 	for (i = 0; i < 256; i++)
@@ -68,7 +69,7 @@ static void do_read_test(void __iomem *p)
 
 static void do_read_far_test(void __iomem *p)
 {
-	pr_info(MODULE_NAME ": read far test.\n");
+	pr_info("read far test.\n");
 	mmiotrace_printk("Read far test.\n");
 
 	ioread32(p + read_far);
@@ -78,7 +79,7 @@ static void do_test(unsigned long size)
 {
 	void __iomem *p = ioremap_nocache(mmio_address, size);
 	if (!p) {
-		pr_err(MODULE_NAME ": could not ioremap, aborting.\n");
+		pr_err("could not ioremap, aborting.\n");
 		return;
 	}
 	mmiotrace_printk("ioremap returned %p.\n", p);
@@ -94,24 +95,22 @@ static int __init init(void)
 	unsigned long size = (read_far) ? (8 << 20) : (16 << 10);
 
 	if (mmio_address == 0) {
-		pr_err(MODULE_NAME ": you have to use the module argument "
-							"mmio_address.\n");
-		pr_err(MODULE_NAME ": DO NOT LOAD THIS MODULE UNLESS"
-				" YOU REALLY KNOW WHAT YOU ARE DOING!\n");
+		pr_err("you have to use the module argument mmio_address.\n");
+		pr_err("DO NOT LOAD THIS MODULE UNLESS YOU REALLY KNOW WHAT YOU ARE DOING!\n");
 		return -ENXIO;
 	}
 
-	pr_warning(MODULE_NAME ": WARNING: mapping %lu kB @ 0x%08lx in PCI "
-		"address space, and writing 16 kB of rubbish in there.\n",
-		 size >> 10, mmio_address);
+	pr_warning("WARNING: mapping %lu kB @ 0x%08lx in PCI address space, "
+		   "and writing 16 kB of rubbish in there.\n",
+		   size >> 10, mmio_address);
 	do_test(size);
-	pr_info(MODULE_NAME ": All done.\n");
+	pr_info("All done.\n");
 	return 0;
 }
 
 static void __exit cleanup(void)
 {
-	pr_debug(MODULE_NAME ": unloaded.\n");
+	pr_debug("unloaded.\n");
 }
 
 module_init(init);

include/linux/compiler-gcc.h

@@ -79,6 +79,7 @@
 #define  noinline			__attribute__((noinline))
 #define __attribute_const__		__attribute__((__const__))
 #define __maybe_unused			__attribute__((unused))
+#define __always_unused			__attribute__((unused))
 
 #define __gcc_header(x) #x
 #define _gcc_header(x) __gcc_header(linux/compiler-gcc##x.h)

include/linux/compiler.h

@@ -218,6 +218,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 # define __maybe_unused		/* unimplemented */
 #endif
 
+#ifndef __always_unused
+# define __always_unused	/* unimplemented */
+#endif
+
 #ifndef noinline
 #define noinline
 #endif

include/linux/smp_lock.h

@@ -24,8 +24,21 @@ static inline int reacquire_kernel_lock(struct task_struct *task)
 	return 0;
 }
 
-extern void __lockfunc lock_kernel(void)	__acquires(kernel_lock);
-extern void __lockfunc unlock_kernel(void)	__releases(kernel_lock);
+extern void __lockfunc
+_lock_kernel(const char *func, const char *file, int line)
+__acquires(kernel_lock);
+
+extern void __lockfunc
+_unlock_kernel(const char *func, const char *file, int line)
+__releases(kernel_lock);
+
+#define lock_kernel() do {					\
+	_lock_kernel(__func__, __FILE__, __LINE__);		\
+} while (0)
+
+#define unlock_kernel()	do {					\
+	_unlock_kernel(__func__, __FILE__, __LINE__);		\
+} while (0)
 
 /*
  * Various legacy drivers don't really need the BKL in a specific
@@ -41,8 +54,8 @@ static inline void cycle_kernel_lock(void)
 
 #else
 
-#define lock_kernel()				do { } while(0)
-#define unlock_kernel()				do { } while(0)
+#define lock_kernel()
+#define unlock_kernel()
 #define release_kernel_lock(task)		do { } while(0)
 #define cycle_kernel_lock()			do { } while(0)
 #define reacquire_kernel_lock(task)		0

include/trace/events/bkl.h

+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM bkl
+
+#if !defined(_TRACE_BKL_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BKL_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(lock_kernel,
+
+	TP_PROTO(const char *func, const char *file, int line),
+
+	TP_ARGS(func, file, line),
+
+	TP_STRUCT__entry(
+		__field(	int,		lock_depth		)
+		__field_ext(	const char *,	func, FILTER_PTR_STRING	)
+		__field_ext(	const char *,	file, FILTER_PTR_STRING	)
+		__field(	int,		line			)
+	),
+
+	TP_fast_assign(
+		/* We want to record the lock_depth after lock is acquired */
+		__entry->lock_depth = current->lock_depth + 1;
+		__entry->func = func;
+		__entry->file = file;
+		__entry->line = line;
+	),
+
+	TP_printk("depth: %d, %s:%d %s()", __entry->lock_depth,
+		  __entry->file, __entry->line, __entry->func)
+);
+
+TRACE_EVENT(unlock_kernel,
+
+	TP_PROTO(const char *func, const char *file, int line),
+
+	TP_ARGS(func, file, line),
+
+	TP_STRUCT__entry(
+		__field(int,		lock_depth)
+		__field(const char *,	func)
+		__field(const char *,	file)
+		__field(int,		line)
+	),
+
+	TP_fast_assign(
+		__entry->lock_depth = current->lock_depth;
+		__entry->func = func;
+		__entry->file = file;
+		__entry->line = line;
+	),
+
+	TP_printk("depth: %d, %s:%d %s()", __entry->lock_depth,
+		  __entry->file, __entry->line, __entry->func)
+);
+
+#endif /* _TRACE_BKL_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

include/trace/events/syscalls.h

 #undef TRACE_SYSTEM
-#define TRACE_SYSTEM syscalls
+#define TRACE_SYSTEM raw_syscalls
+#define TRACE_INCLUDE_FILE syscalls
 
 #if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_EVENTS_SYSCALLS_H

include/trace/power.h

-#ifndef _TRACE_POWER_H
-#define _TRACE_POWER_H
-
-#include <linux/ktime.h>
-#include <linux/tracepoint.h>
-
-enum {
-	POWER_NONE = 0,
-	POWER_CSTATE = 1,
-	POWER_PSTATE = 2,
-};
-
-struct power_trace {
-	ktime_t			stamp;
-	ktime_t			end;
-	int			type;
-	int			state;
-};
-
-DECLARE_TRACE(power_start,
-	TP_PROTO(struct power_trace *it, unsigned int type, unsigned int state),
-	      TP_ARGS(it, type, state));
-
-DECLARE_TRACE(power_mark,
-	TP_PROTO(struct power_trace *it, unsigned int type, unsigned int state),
-	      TP_ARGS(it, type, state));
-
-DECLARE_TRACE(power_end,
-	TP_PROTO(struct power_trace *it),
-	      TP_ARGS(it));
-
-#endif /* _TRACE_POWER_H */

include/trace/syscall.h

@@ -33,7 +33,7 @@ struct syscall_metadata {
 };
 
 #ifdef CONFIG_FTRACE_SYSCALLS
-extern struct syscall_metadata *syscall_nr_to_meta(int nr);
+extern unsigned long arch_syscall_addr(int nr);
 extern int syscall_name_to_nr(char *name);
 void set_syscall_enter_id(int num, int id);
 void set_syscall_exit_id(int num, int id);

kernel/kprobes.c

@@ -1014,9 +1014,9 @@ int __kprobes register_kretprobe(struct kretprobe *rp)
 	/* Pre-allocate memory for max kretprobe instances */
 	if (rp->maxactive <= 0) {
 #ifdef CONFIG_PREEMPT
-		rp->maxactive = max(10, 2 * NR_CPUS);
+		rp->maxactive = max(10, 2 * num_possible_cpus());
 #else
-		rp->maxactive = NR_CPUS;
+		rp->maxactive = num_possible_cpus();
 #endif
 	}
 	spin_lock_init(&rp->lock);

kernel/trace/ring_buffer.c

@@ -1787,9 +1787,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 static struct ring_buffer_event *
 rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	     unsigned long length, unsigned long tail,
-	     struct buffer_page *commit_page,
 	     struct buffer_page *tail_page, u64 *ts)
 {
+	struct buffer_page *commit_page = cpu_buffer->commit_page;
 	struct ring_buffer *buffer = cpu_buffer->buffer;
 	struct buffer_page *next_page;
 	int ret;
@@ -1892,13 +1892,10 @@ static struct ring_buffer_event *
 __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		  unsigned type, unsigned long length, u64 *ts)
 {
-	struct buffer_page *tail_page, *commit_page;
+	struct buffer_page *tail_page;
 	struct ring_buffer_event *event;
 	unsigned long tail, write;
 
-	commit_page = cpu_buffer->commit_page;
-	/* we just need to protect against interrupts */
-	barrier();
 	tail_page = cpu_buffer->tail_page;
 	write = local_add_return(length, &tail_page->write);
 
@@ -1909,7 +1906,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	/* See if we shot pass the end of this buffer page */
 	if (write > BUF_PAGE_SIZE)
 		return rb_move_tail(cpu_buffer, length, tail,
-				    commit_page, tail_page, ts);
+				    tail_page, ts);
 
 	/* We reserved something on the buffer */
 

kernel/trace/ring_buffer_benchmark.c

@@ -35,6 +35,28 @@ static int disable_reader;
 module_param(disable_reader, uint, 0644);
 MODULE_PARM_DESC(disable_reader, "only run producer");
 
+static int write_iteration = 50;
+module_param(write_iteration, uint, 0644);
+MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
+
+static int producer_nice = 19;
+static int consumer_nice = 19;
+
+static int producer_fifo = -1;
+static int consumer_fifo = -1;
+
+module_param(producer_nice, uint, 0644);
+MODULE_PARM_DESC(producer_nice, "nice prio for producer");
+
+module_param(consumer_nice, uint, 0644);
+MODULE_PARM_DESC(consumer_nice, "nice prio for consumer");
+
+module_param(producer_fifo, uint, 0644);
+MODULE_PARM_DESC(producer_fifo, "fifo prio for producer");
+
+module_param(consumer_fifo, uint, 0644);
+MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer");
+
 static int read_events;
 
 static int kill_test;
@@ -208,15 +230,18 @@ static void ring_buffer_producer(void)
 	do {
 		struct ring_buffer_event *event;
 		int *entry;
-
-		event = ring_buffer_lock_reserve(buffer, 10);
-		if (!event) {
-			missed++;
-		} else {
-			hit++;
-			entry = ring_buffer_event_data(event);
-			*entry = smp_processor_id();
-			ring_buffer_unlock_commit(buffer, event);
+		int i;
+
+		for (i = 0; i < write_iteration; i++) {
+			event = ring_buffer_lock_reserve(buffer, 10);
+			if (!event) {
+				missed++;
+			} else {
+				hit++;
+				entry = ring_buffer_event_data(event);
+				*entry = smp_processor_id();
+				ring_buffer_unlock_commit(buffer, event);
+			}
 		}
 		do_gettimeofday(&end_tv);
 
@@ -263,6 +288,27 @@ static void ring_buffer_producer(void)
 
 	if (kill_test)
 		trace_printk("ERROR!\n");
+
+	if (!disable_reader) {
+		if (consumer_fifo < 0)
+			trace_printk("Running Consumer at nice: %d\n",
+				     consumer_nice);
+		else
+			trace_printk("Running Consumer at SCHED_FIFO %d\n",
+				     consumer_fifo);
+	}
+	if (producer_fifo < 0)
+		trace_printk("Running Producer at nice: %d\n",
+			     producer_nice);
+	else
+		trace_printk("Running Producer at SCHED_FIFO %d\n",
+			     producer_fifo);
+
+	/* Let the user know that the test is running at low priority */
+	if (producer_fifo < 0 && consumer_fifo < 0 &&
+	    producer_nice == 19 && consumer_nice == 19)
+		trace_printk("WARNING!!! This test is running at lowest priority.\n");
+
 	trace_printk("Time:     %lld (usecs)\n", time);
 	trace_printk("Overruns: %lld\n", overruns);
 	if (disable_reader)
@@ -392,6 +438,27 @@ static int __init ring_buffer_benchmark_init(void)
 	if (IS_ERR(producer))
 		goto out_kill;
 
+	/*
+	 * Run them as low-prio background tasks by default:
+	 */
+	if (!disable_reader) {
+		if (consumer_fifo >= 0) {
+			struct sched_param param = {
+				.sched_priority = consumer_fifo
+			};
+			sched_setscheduler(consumer, SCHED_FIFO, &param);
+		} else
+			set_user_nice(consumer, consumer_nice);
+	}
+
+	if (producer_fifo >= 0) {
+		struct sched_param param = {
+			.sched_priority = consumer_fifo
+		};
+		sched_setscheduler(producer, SCHED_FIFO, &param);
+	} else
+		set_user_nice(producer, producer_nice);
+
 	return 0;
 
  out_kill:

kernel/trace/trace.c

@@ -129,7 +129,7 @@ static int tracing_set_tracer(const char *buf);
 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
 static char *default_bootup_tracer;
 
-static int __init set_ftrace(char *str)
+static int __init set_cmdline_ftrace(char *str)
 {
 	strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
 	default_bootup_tracer = bootup_tracer_buf;
@@ -137,7 +137,7 @@ static int __init set_ftrace(char *str)
 	ring_buffer_expanded = 1;
 	return 1;
 }
-__setup("ftrace=", set_ftrace);
+__setup("ftrace=", set_cmdline_ftrace);
 
 static int __init set_ftrace_dump_on_oops(char *str)
 {

kernel/trace/trace.h

@@ -483,10 +483,6 @@ static inline int ftrace_graph_addr(unsigned long addr)
 	return 0;
 }
 #else
-static inline int ftrace_trace_addr(unsigned long addr)
-{
-	return 1;
-}
 static inline int ftrace_graph_addr(unsigned long addr)
 {
 	return 1;
@@ -500,12 +496,12 @@ print_graph_function(struct trace_iterator *iter)
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
-extern struct pid *ftrace_pid_trace;
+extern struct list_head ftrace_pids;
 
 #ifdef CONFIG_FUNCTION_TRACER
 static inline int ftrace_trace_task(struct task_struct *task)
 {
-	if (!ftrace_pid_trace)
+	if (list_empty(&ftrace_pids))
 		return 1;
 
 	return test_tsk_trace_trace(task);
@@ -699,22 +695,40 @@ struct event_subsystem {
 };
 
 struct filter_pred;
+struct regex;
 
 typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
 				 int val1, int val2);
 
+typedef int (*regex_match_func)(char *str, struct regex *r, int len);
+
+enum regex_type {
+	MATCH_FULL,
+	MATCH_FRONT_ONLY,
+	MATCH_MIDDLE_ONLY,
+	MATCH_END_ONLY,
+};
+
+struct regex {
+	char			pattern[MAX_FILTER_STR_VAL];
+	int			len;
+	int			field_len;
+	regex_match_func	match;
+};
+
 struct filter_pred {
-	filter_pred_fn_t fn;
-	u64 val;
-	char str_val[MAX_FILTER_STR_VAL];
-	int str_len;
-	char *field_name;
-	int offset;
-	int not;
-	int op;
-	int pop_n;
+	filter_pred_fn_t 	fn;
+	u64 			val;
+	struct regex		regex;
+	char 			*field_name;
+	int 			offset;
+	int 			not;
+	int 			op;
+	int 			pop_n;
 };
 
+extern enum regex_type
+filter_parse_regex(char *buff, int len, char **search, int *not);
 extern void print_event_filter(struct ftrace_event_call *call,
 			       struct trace_seq *s);
 extern int apply_event_filter(struct ftrace_event_call *call,

kernel/trace/trace_clock.c

@@ -20,6 +20,8 @@
 #include <linux/ktime.h>
 #include <linux/trace_clock.h>
 
+#include "trace.h"
+
 /*
  * trace_clock_local(): the simplest and least coherent tracing clock.
  *
@@ -28,17 +30,17 @@
  */
 u64 notrace trace_clock_local(void)
 {
-	unsigned long flags;
 	u64 clock;
+	int resched;
 
 	/*
 	 * sched_clock() is an architecture implemented, fast, scalable,
 	 * lockless clock. It is not guaranteed to be coherent across
 	 * CPUs, nor across CPU idle events.
 	 */
-	raw_local_irq_save(flags);
+	resched = ftrace_preempt_disable();
 	clock = sched_clock();
-	raw_local_irq_restore(flags);
+	ftrace_preempt_enable(resched);
 
 	return clock;
 }

kernel/trace/trace_events.c

@@ -878,9 +878,9 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 			   "'%s/filter' entry\n", name);
 	}
 
-	entry = trace_create_file("enable", 0644, system->entry,
-				  (void *)system->name,
-				  &ftrace_system_enable_fops);
+	trace_create_file("enable", 0644, system->entry,
+			  (void *)system->name,
+			  &ftrace_system_enable_fops);
 
 	return system->entry;
 }
@@ -892,7 +892,6 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		 const struct file_operations *filter,
 		 const struct file_operations *format)
 {
-	struct dentry *entry;
 	int ret;
 
 	/*
@@ -910,12 +909,12 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 	}
 
 	if (call->regfunc)
-		entry = trace_create_file("enable", 0644, call->dir, call,
-					  enable);
+		trace_create_file("enable", 0644, call->dir, call,
+				  enable);
 
 	if (call->id && call->profile_enable)
-		entry = trace_create_file("id", 0444, call->dir, call,
-					  id);
+		trace_create_file("id", 0444, call->dir, call,
+		 		  id);
 
 	if (call->define_fields) {
 		ret = call->define_fields(call);
@@ -924,16 +923,16 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 				   " events/%s\n", call->name);
 			return ret;
 		}
-		entry = trace_create_file("filter", 0644, call->dir, call,
-					  filter);
+		trace_create_file("filter", 0644, call->dir, call,
+				  filter);
 	}
 
 	/* A trace may not want to export its format */
 	if (!call->show_format)
 		return 0;
 
-	entry = trace_create_file("format", 0444, call->dir, call,
-				  format);
+	trace_create_file("format", 0444, call->dir, call,
+			  format);
 
 	return 0;
 }

kernel/trace/trace_events_filter.c

@@ -18,8 +18,6 @@
  * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
  */
 
-#include <linux/debugfs.h>
-#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/mutex.h>
@@ -197,9 +195,9 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
 	char *addr = (char *)(event + pred->offset);
 	int cmp, match;
 
-	cmp = strncmp(addr, pred->str_val, pred->str_len);
+	cmp = pred->regex.match(addr, &pred->regex, pred->regex.field_len);
 
-	match = (!cmp) ^ pred->not;
+	match = cmp ^ pred->not;
 
 	return match;
 }
@@ -211,9 +209,9 @@ static int filter_pred_pchar(struct filter_pred *pred, void *event,
 	char **addr = (char **)(event + pred->offset);
 	int cmp, match;
 
-	cmp = strncmp(*addr, pred->str_val, pred->str_len);
+	cmp = pred->regex.match(*addr, &pred->regex, pred->regex.field_len);
 
-	match = (!cmp) ^ pred->not;
+	match = cmp ^ pred->not;
 
 	return match;
 }
@@ -237,9 +235,9 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event,
 	char *addr = (char *)(event + str_loc);
 	int cmp, match;
 
-	cmp = strncmp(addr, pred->str_val, str_len);
+	cmp = pred->regex.match(addr, &pred->regex, str_len);
 
-	match = (!cmp) ^ pred->not;
+	match = cmp ^ pred->not;
 
 	return match;
 }
@@ -250,6 +248,124 @@ static int filter_pred_none(struct filter_pred *pred, void *event,
 	return 0;
 }
 
+/* Basic regex callbacks */
+static int regex_match_full(char *str, struct regex *r, int len)
+{
+	if (strncmp(str, r->pattern, len) == 0)
+		return 1;
+	return 0;
+}
+
+static int regex_match_front(char *str, struct regex *r, int len)
+{
+	if (strncmp(str, r->pattern, len) == 0)
+		return 1;
+	return 0;
+}
+
+static int regex_match_middle(char *str, struct regex *r, int len)
+{
+	if (strstr(str, r->pattern))
+		return 1;
+	return 0;
+}
+
+static int regex_match_end(char *str, struct regex *r, int len)
+{
+	char *ptr = strstr(str, r->pattern);
+
+	if (ptr && (ptr[r->len] == 0))
+		return 1;
+	return 0;
+}
+
+/**
+ * filter_parse_regex - parse a basic regex
+ * @buff:   the raw regex
+ * @len:    length of the regex
+ * @search: will point to the beginning of the string to compare
+ * @not:    tell whether the match will have to be inverted
+ *
+ * This passes in a buffer containing a regex and this function will
+ * set search to point to the search part of the buffer and
+ * return the type of search it is (see enum above).
+ * This does modify buff.
+ *
+ * Returns enum type.
+ *  search returns the pointer to use for comparison.
+ *  not returns 1 if buff started with a '!'
+ *     0 otherwise.
+ */
+enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not)
+{
+	int type = MATCH_FULL;
+	int i;
+
+	if (buff[0] == '!') {
+		*not = 1;
+		buff++;
+		len--;
+	} else
+		*not = 0;
+
+	*search = buff;
+
+	for (i = 0; i < len; i++) {
+		if (buff[i] == '*') {
+			if (!i) {
+				*search = buff + 1;
+				type = MATCH_END_ONLY;
+			} else {
+				if (type == MATCH_END_ONLY)
+					type = MATCH_MIDDLE_ONLY;
+				else
+					type = MATCH_FRONT_ONLY;
+				buff[i] = 0;
+				break;
+			}
+		}
+	}
+
+	return type;
+}
+
+static int filter_build_regex(struct filter_pred *pred)
+{
+	struct regex *r = &pred->regex;
+	char *search, *dup;
+	enum regex_type type;
+	int not;
+
+	type = filter_parse_regex(r->pattern, r->len, &search, &not);
+	dup = kstrdup(search, GFP_KERNEL);
+	if (!dup)
+		return -ENOMEM;
+
+	strcpy(r->pattern, dup);
+	kfree(dup);
+
+	r->len = strlen(r->pattern);
+
+	switch (type) {
+	case MATCH_FULL:
+		r->match = regex_match_full;
+		break;
+	case MATCH_FRONT_ONLY:
+		r->match = regex_match_front;
+		break;
+	case MATCH_MIDDLE_ONLY:
+		r->match = regex_match_middle;
+		break;
+	case MATCH_END_ONLY:
+		r->match = regex_match_end;
+		break;
+	}
+
+	pred->not ^= not;
+
+	return 0;
+}
+
 /* return 1 if event matches, 0 otherwise (discard) */
 int filter_match_preds(struct ftrace_event_call *call, void *rec)
 {
@@ -396,7 +512,7 @@ static void filter_clear_pred(struct filter_pred *pred)
 {
 	kfree(pred->field_name);
 	pred->field_name = NULL;
-	pred->str_len = 0;
+	pred->regex.len = 0;
 }
 
 static int filter_set_pred(struct filter_pred *dest,
@@ -660,21 +776,24 @@ static int filter_add_pred(struct filter_parse_state *ps,
 	}
 
 	if (is_string_field(field)) {
-		pred->str_len = field->size;
+		ret = filter_build_regex(pred);
+		if (ret)
+			return ret;
 
-		if (field->filter_type == FILTER_STATIC_STRING)
+		if (field->filter_type == FILTER_STATIC_STRING) {
 			fn = filter_pred_string;
-		else if (field->filter_type == FILTER_DYN_STRING)
-			fn = filter_pred_strloc;
+			pred->regex.field_len = field->size;
+		} else if (field->filter_type == FILTER_DYN_STRING)
+				fn = filter_pred_strloc;
 		else {
 			fn = filter_pred_pchar;
-			pred->str_len = strlen(pred->str_val);
+			pred->regex.field_len = strlen(pred->regex.pattern);
 		}
 	} else {
 		if (field->is_signed)
-			ret = strict_strtoll(pred->str_val, 0, &val);
+			ret = strict_strtoll(pred->regex.pattern, 0, &val);
 		else
-			ret = strict_strtoull(pred->str_val, 0, &val);
+			ret = strict_strtoull(pred->regex.pattern, 0, &val);
 		if (ret) {
 			parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0);
 			return -EINVAL;
@@ -1045,8 +1164,8 @@ static struct filter_pred *create_pred(int op, char *operand1, char *operand2)
 		return NULL;
 	}
 
-	strcpy(pred->str_val, operand2);
-	pred->str_len = strlen(operand2);
+	strcpy(pred->regex.pattern, operand2);
+	pred->regex.len = strlen(pred->regex.pattern);
 
 	pred->op = op;
 

kernel/trace/trace_export.c

@@ -48,11 +48,11 @@
 struct ____ftrace_##name {					\
 	tstruct							\
 };								\
-static void __used ____ftrace_check_##name(void)		\
+static void __always_unused ____ftrace_check_##name(void)	\
 {								\
 	struct ____ftrace_##name *__entry = NULL;		\
 								\
-	/* force cmpile-time check on F_printk() */		\
+	/* force compile-time check on F_printk() */		\
 	printk(print);						\
 }
 

kernel/trace/trace_syscalls.c

@@ -14,6 +14,69 @@ static int sys_refcount_exit;
 static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
 static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
 
+extern unsigned long __start_syscalls_metadata[];
+extern unsigned long __stop_syscalls_metadata[];
+
+static struct syscall_metadata **syscalls_metadata;
+
+static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
+{
+	struct syscall_metadata *start;
+	struct syscall_metadata *stop;
+	char str[KSYM_SYMBOL_LEN];
+
+
+	start = (struct syscall_metadata *)__start_syscalls_metadata;
+	stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+	kallsyms_lookup(syscall, NULL, NULL, NULL, str);
+
+	for ( ; start < stop; start++) {
+		/*
+		 * Only compare after the "sys" prefix. Archs that use
+		 * syscall wrappers may have syscalls symbols aliases prefixed
+		 * with "SyS" instead of "sys", leading to an unwanted
+		 * mismatch.
+		 */
+		if (start->name && !strcmp(start->name + 3, str + 3))
+			return start;
+	}
+	return NULL;
+}
+
+static struct syscall_metadata *syscall_nr_to_meta(int nr)
+{
+	if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
+		return NULL;
+
+	return syscalls_metadata[nr];
+}
+
+int syscall_name_to_nr(char *name)
+{
+	int i;
+
+	if (!syscalls_metadata)
+		return -1;
+
+	for (i = 0; i < NR_syscalls; i++) {
+		if (syscalls_metadata[i]) {
+			if (!strcmp(syscalls_metadata[i]->name, name))
+				return i;
+		}
+	}
+	return -1;
+}
+
+void set_syscall_enter_id(int num, int id)
+{
+	syscalls_metadata[num]->enter_id = id;
+}
+
+void set_syscall_exit_id(int num, int id)
+{
+	syscalls_metadata[num]->exit_id = id;
+}
+
 enum print_line_t
 print_syscall_enter(struct trace_iterator *iter, int flags)
 {
@@ -375,6 +438,29 @@ struct trace_event event_syscall_exit = {
 	.trace			= print_syscall_exit,
 };
 
+int __init init_ftrace_syscalls(void)
+{
+	struct syscall_metadata *meta;
+	unsigned long addr;
+	int i;
+
+	syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
+					NR_syscalls, GFP_KERNEL);
+	if (!syscalls_metadata) {
+		WARN_ON(1);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < NR_syscalls; i++) {
+		addr = arch_syscall_addr(i);
+		meta = find_syscall_meta(addr);
+		syscalls_metadata[i] = meta;
+	}
+
+	return 0;
+}
+core_initcall(init_ftrace_syscalls);
+
 #ifdef CONFIG_EVENT_PROFILE
 
 static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);

lib/kernel_lock.c

@@ -5,10 +5,13 @@
  * relegated to obsolescence, but used by various less
  * important (or lazy) subsystems.
  */
-#include <linux/smp_lock.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/semaphore.h>
+#include <linux/smp_lock.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/bkl.h>
 
 /*
  * The 'big kernel lock'
@@ -113,21 +116,26 @@ static inline void __unlock_kernel(void)
  * This cannot happen asynchronously, so we only need to
  * worry about other CPU's.
  */
-void __lockfunc lock_kernel(void)
+void __lockfunc _lock_kernel(const char *func, const char *file, int line)
 {
-	int depth = current->lock_depth+1;
+	int depth = current->lock_depth + 1;
+
+	trace_lock_kernel(func, file, line);
+
 	if (likely(!depth))
 		__lock_kernel();
 	current->lock_depth = depth;
 }
 
-void __lockfunc unlock_kernel(void)
+void __lockfunc _unlock_kernel(const char *func, const char *file, int line)
 {
 	BUG_ON(current->lock_depth < 0);
 	if (likely(--current->lock_depth < 0))
 		__unlock_kernel();
+
+	trace_unlock_kernel(func, file, line);
 }
 
-EXPORT_SYMBOL(lock_kernel);
-EXPORT_SYMBOL(unlock_kernel);
+EXPORT_SYMBOL(_lock_kernel);
+EXPORT_SYMBOL(_unlock_kernel);