Commit 96fa2b50 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

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
  ...
parents 7a797cdc b8007ef7
......@@ -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)
......
......@@ -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
......
......@@ -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 ;
......
......@@ -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
......@@ -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"
......
......@@ -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
......
......@@ -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
/*
* 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);
......
......@@ -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)
......
......@@ -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
......
......@@ -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
......
#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>
#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
......
#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 */
......@@ -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);
......
......@@ -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);
......
......@@ -60,6 +60,13 @@ static int last_ftrace_enabled;
/* Quick disabling of function tracer. */
int function_trace_stop;
/* List for set_ftrace_pid's pids. */
LIST_HEAD(ftrace_pids);
struct ftrace_pid {
struct list_head list;
struct pid *pid;
};
/*
* ftrace_disabled is set when an anomaly is discovered.
* ftrace_disabled is much stronger than ftrace_enabled.
......@@ -78,6 +85,10 @@ ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
#endif
static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
{
struct ftrace_ops *op = ftrace_list;
......@@ -155,7 +166,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
else
func = ftrace_list_func;
if (ftrace_pid_trace) {
if (!list_empty(&ftrace_pids)) {
set_ftrace_pid_function(func);
func = ftrace_pid_func;
}
......@@ -203,7 +214,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
if (ftrace_list->next == &ftrace_list_end) {
ftrace_func_t func = ftrace_list->func;
if (ftrace_pid_trace) {
if (!list_empty(&ftrace_pids)) {
set_ftrace_pid_function(func);
func = ftrace_pid_func;
}
......@@ -231,7 +242,7 @@ static void ftrace_update_pid_func(void)
func = __ftrace_trace_function;
#endif
if (ftrace_pid_trace) {
if (!list_empty(&ftrace_pids)) {
set_ftrace_pid_function(func);
func = ftrace_pid_func;
} else {
......@@ -821,8 +832,6 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
}
#endif /* CONFIG_FUNCTION_PROFILER */
/* set when tracing only a pid */
struct pid *ftrace_pid_trace;
static struct pid * const ftrace_swapper_pid = &init_struct_pid;
#ifdef CONFIG_DYNAMIC_FTRACE
......@@ -1261,12 +1270,34 @@ static int ftrace_update_code(struct module *mod)
ftrace_new_addrs = p->newlist;
p->flags = 0L;
/* convert record (i.e, patch mcount-call with NOP) */
if (ftrace_code_disable(mod, p)) {
p->flags |= FTRACE_FL_CONVERTED;
ftrace_update_cnt++;
} else
/*
* Do the initial record convertion from mcount jump
* to the NOP instructions.
*/
if (!ftrace_code_disable(mod, p)) {
ftrace_free_rec(p);
continue;
}
p->flags |= FTRACE_FL_CONVERTED;
ftrace_update_cnt++;
/*
* If the tracing is enabled, go ahead and enable the record.
*
* The reason not to enable the record immediatelly is the
* inherent check of ftrace_make_nop/ftrace_make_call for
* correct previous instructions. Making first the NOP
* conversion puts the module to the correct state, thus