Merge branches 'tracing/branch-tracer', 'tracing/fastboot', 'tracing/ftrace', 'tracing/function-return-tracer', 'tracing/power-tracer', 'tracing/powerpc', 'tracing/ring-buffer', 'tracing/stack-tracer' and 'tracing/urgent' into tracing/core

This commit is contained in:
Ingo Molnar 2008-11-24 17:46:24 +01:00
32 changed files with 1044 additions and 148 deletions

View File

@ -324,7 +324,7 @@ output. To see what is available, simply cat the file:
cat /debug/tracing/trace_options
print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \
noblock nostacktrace nosched-tree
noblock nostacktrace nosched-tree nouserstacktrace nosym-userobj
To disable one of the options, echo in the option prepended with "no".
@ -378,6 +378,20 @@ Here are the available options:
When a trace is recorded, so is the stack of functions.
This allows for back traces of trace sites.
userstacktrace - This option changes the trace.
It records a stacktrace of the current userspace thread.
sym-userobj - when user stacktrace are enabled, look up which object the
address belongs to, and print a relative address
This is especially useful when ASLR is on, otherwise you don't
get a chance to resolve the address to object/file/line after the app is no
longer running
The lookup is performed when you read trace,trace_pipe,latency_trace. Example:
a.out-1623 [000] 40874.465068: /root/a.out[+0x480] <-/root/a.out[+0
x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6]
sched-tree - TBD (any users??)

View File

@ -37,7 +37,7 @@ $ echo mmiotrace > /debug/tracing/current_tracer
$ cat /debug/tracing/trace_pipe > mydump.txt &
Start X or whatever.
$ echo "X is up" > /debug/tracing/trace_marker
$ echo none > /debug/tracing/current_tracer
$ echo nop > /debug/tracing/current_tracer
Check for lost events.
@ -66,7 +66,7 @@ which action. It is recommended to place descriptive markers about what you
do.
Shut down mmiotrace (requires root privileges):
$ echo none > /debug/tracing/current_tracer
$ echo nop > /debug/tracing/current_tracer
The 'cat' process exits. If it does not, kill it by issuing 'fg' command and
pressing ctrl+c.
@ -81,7 +81,9 @@ are:
$ cat /debug/tracing/trace_entries
gives you a number. Approximately double this number and write it back, for
instance:
$ echo 0 > /debug/tracing/tracing_enabled
$ echo 128000 > /debug/tracing/trace_entries
$ echo 1 > /debug/tracing/tracing_enabled
Then start again from the top.
If you are doing a trace for a driver project, e.g. Nouveau, you should also

View File

@ -7,7 +7,19 @@
#ifndef __ASSEMBLY__
extern void _mcount(void);
#endif
#ifdef CONFIG_DYNAMIC_FTRACE
static inline unsigned long ftrace_call_adjust(unsigned long addr)
{
/* reloction of mcount call site is the same as the address */
return addr;
}
struct dyn_arch_ftrace {
struct module *mod;
};
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* __ASSEMBLY__ */
#endif

View File

@ -34,11 +34,19 @@ struct mod_arch_specific {
#ifdef __powerpc64__
unsigned int stubs_section; /* Index of stubs section in module */
unsigned int toc_section; /* What section is the TOC? */
#else
#ifdef CONFIG_DYNAMIC_FTRACE
unsigned long toc;
unsigned long tramp;
#endif
#else /* powerpc64 */
/* Indices of PLT sections within module. */
unsigned int core_plt_section;
unsigned int init_plt_section;
#ifdef CONFIG_DYNAMIC_FTRACE
unsigned long tramp;
#endif
#endif /* powerpc64 */
/* List of BUG addresses, source line numbers and filenames */
struct list_head bug_list;
@ -68,6 +76,12 @@ struct mod_arch_specific {
# endif /* MODULE */
#endif
#ifdef CONFIG_DYNAMIC_FTRACE
# ifdef MODULE
asm(".section .ftrace.tramp,\"ax\",@nobits; .align 3; .previous");
# endif /* MODULE */
#endif
struct exception_table_entry;
void sort_ex_table(struct exception_table_entry *start,

View File

@ -9,22 +9,30 @@
#include <linux/spinlock.h>
#include <linux/hardirq.h>
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ftrace.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/list.h>
#include <asm/cacheflush.h>
#include <asm/code-patching.h>
#include <asm/ftrace.h>
#if 0
#define DEBUGP printk
#else
#define DEBUGP(fmt , ...) do { } while (0)
#endif
static unsigned int ftrace_nop = 0x60000000;
static unsigned int ftrace_nop = PPC_NOP_INSTR;
#ifdef CONFIG_PPC32
# define GET_ADDR(addr) addr
#else
/* PowerPC64's functions are data that points to the functions */
# define GET_ADDR(addr) *(unsigned long *)addr
# define GET_ADDR(addr) (*(unsigned long *)addr)
#endif
@ -33,12 +41,12 @@ static unsigned int ftrace_calc_offset(long ip, long addr)
return (int)(addr - ip);
}
unsigned char *ftrace_nop_replace(void)
static unsigned char *ftrace_nop_replace(void)
{
return (char *)&ftrace_nop;
}
unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
{
static unsigned int op;
@ -68,49 +76,434 @@ unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
# define _ASM_PTR " .long "
#endif
int
static int
ftrace_modify_code(unsigned long ip, unsigned char *old_code,
unsigned char *new_code)
{
unsigned replaced;
unsigned old = *(unsigned *)old_code;
unsigned new = *(unsigned *)new_code;
int faulted = 0;
unsigned char replaced[MCOUNT_INSN_SIZE];
/*
* Note: Due to modules and __init, code can
* disappear and change, we need to protect against faulting
* as well as code changing.
* as well as code changing. We do this by using the
* probe_kernel_* functions.
*
* No real locking needed, this code is run through
* kstop_machine.
* kstop_machine, or before SMP starts.
*/
asm volatile (
"1: lwz %1, 0(%2)\n"
" cmpw %1, %5\n"
" bne 2f\n"
" stwu %3, 0(%2)\n"
"2:\n"
".section .fixup, \"ax\"\n"
"3: li %0, 1\n"
" b 2b\n"
".previous\n"
".section __ex_table,\"a\"\n"
_ASM_ALIGN "\n"
_ASM_PTR "1b, 3b\n"
".previous"
: "=r"(faulted), "=r"(replaced)
: "r"(ip), "r"(new),
"0"(faulted), "r"(old)
: "memory");
if (replaced != old && replaced != new)
faulted = 2;
/* read the text we want to modify */
if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
return -EFAULT;
if (!faulted)
flush_icache_range(ip, ip + 8);
/* Make sure it is what we expect it to be */
if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
return -EINVAL;
return faulted;
/* replace the text with the new text */
if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
return -EPERM;
flush_icache_range(ip, ip + 8);
return 0;
}
/*
* Helper functions that are the same for both PPC64 and PPC32.
*/
static int test_24bit_addr(unsigned long ip, unsigned long addr)
{
long diff;
/*
* Can we get to addr from ip in 24 bits?
* (26 really, since we mulitply by 4 for 4 byte alignment)
*/
diff = addr - ip;
/*
* Return true if diff is less than 1 << 25
* and greater than -1 << 26.
*/
return (diff < (1 << 25)) && (diff > (-1 << 26));
}
static int is_bl_op(unsigned int op)
{
return (op & 0xfc000003) == 0x48000001;
}
static int test_offset(unsigned long offset)
{
return (offset + 0x2000000 > 0x3ffffff) || ((offset & 3) != 0);
}
static unsigned long find_bl_target(unsigned long ip, unsigned int op)
{
static int offset;
offset = (op & 0x03fffffc);
/* make it signed */
if (offset & 0x02000000)
offset |= 0xfe000000;
return ip + (long)offset;
}
static unsigned int branch_offset(unsigned long offset)
{
/* return "bl ip+offset" */
return 0x48000001 | (offset & 0x03fffffc);
}
#ifdef CONFIG_PPC64
static int
__ftrace_make_nop(struct module *mod,
struct dyn_ftrace *rec, unsigned long addr)
{
unsigned char replaced[MCOUNT_INSN_SIZE * 2];
unsigned int *op = (unsigned *)&replaced;
unsigned char jmp[8];
unsigned long *ptr = (unsigned long *)&jmp;
unsigned long ip = rec->ip;
unsigned long tramp;
int offset;
/* read where this goes */
if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
return -EFAULT;
/* Make sure that that this is still a 24bit jump */
if (!is_bl_op(*op)) {
printk(KERN_ERR "Not expected bl: opcode is %x\n", *op);
return -EINVAL;
}
/* lets find where the pointer goes */
tramp = find_bl_target(ip, *op);
/*
* On PPC64 the trampoline looks like:
* 0x3d, 0x82, 0x00, 0x00, addis r12,r2, <high>
* 0x39, 0x8c, 0x00, 0x00, addi r12,r12, <low>
* Where the bytes 2,3,6 and 7 make up the 32bit offset
* to the TOC that holds the pointer.
* to jump to.
* 0xf8, 0x41, 0x00, 0x28, std r2,40(r1)
* 0xe9, 0x6c, 0x00, 0x20, ld r11,32(r12)
* The actually address is 32 bytes from the offset
* into the TOC.
* 0xe8, 0x4c, 0x00, 0x28, ld r2,40(r12)
*/
DEBUGP("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc);
/* Find where the trampoline jumps to */
if (probe_kernel_read(jmp, (void *)tramp, 8)) {
printk(KERN_ERR "Failed to read %lx\n", tramp);
return -EFAULT;
}
DEBUGP(" %08x %08x",
(unsigned)(*ptr >> 32),
(unsigned)*ptr);
offset = (unsigned)jmp[2] << 24 |
(unsigned)jmp[3] << 16 |
(unsigned)jmp[6] << 8 |
(unsigned)jmp[7];
DEBUGP(" %x ", offset);
/* get the address this jumps too */
tramp = mod->arch.toc + offset + 32;
DEBUGP("toc: %lx", tramp);
if (probe_kernel_read(jmp, (void *)tramp, 8)) {
printk(KERN_ERR "Failed to read %lx\n", tramp);
return -EFAULT;
}
DEBUGP(" %08x %08x\n",
(unsigned)(*ptr >> 32),
(unsigned)*ptr);
/* This should match what was called */
if (*ptr != GET_ADDR(addr)) {
printk(KERN_ERR "addr does not match %lx\n", *ptr);
return -EINVAL;
}
/*
* We want to nop the line, but the next line is
* 0xe8, 0x41, 0x00, 0x28 ld r2,40(r1)
* This needs to be turned to a nop too.
*/
if (probe_kernel_read(replaced, (void *)(ip+4), MCOUNT_INSN_SIZE))
return -EFAULT;
if (*op != 0xe8410028) {
printk(KERN_ERR "Next line is not ld! (%08x)\n", *op);
return -EINVAL;
}
/*
* Milton Miller pointed out that we can not blindly do nops.
* If a task was preempted when calling a trace function,
* the nops will remove the way to restore the TOC in r2
* and the r2 TOC will get corrupted.
*/
/*
* Replace:
* bl <tramp> <==== will be replaced with "b 1f"
* ld r2,40(r1)
* 1:
*/
op[0] = 0x48000008; /* b +8 */
if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE))
return -EPERM;
return 0;
}
#else /* !PPC64 */
static int
__ftrace_make_nop(struct module *mod,
struct dyn_ftrace *rec, unsigned long addr)
{
unsigned char replaced[MCOUNT_INSN_SIZE];
unsigned int *op = (unsigned *)&replaced;
unsigned char jmp[8];
unsigned int *ptr = (unsigned int *)&jmp;
unsigned long ip = rec->ip;
unsigned long tramp;
int offset;
if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
return -EFAULT;
/* Make sure that that this is still a 24bit jump */
if (!is_bl_op(*op)) {
printk(KERN_ERR "Not expected bl: opcode is %x\n", *op);
return -EINVAL;
}
/* lets find where the pointer goes */
tramp = find_bl_target(ip, *op);
/*
* On PPC32 the trampoline looks like:
* lis r11,sym@ha
* addi r11,r11,sym@l
* mtctr r11
* bctr
*/
DEBUGP("ip:%lx jumps to %lx", ip, tramp);
/* Find where the trampoline jumps to */
if (probe_kernel_read(jmp, (void *)tramp, 8)) {
printk(KERN_ERR "Failed to read %lx\n", tramp);
return -EFAULT;
}
DEBUGP(" %08x %08x ", ptr[0], ptr[1]);
tramp = (ptr[1] & 0xffff) |
((ptr[0] & 0xffff) << 16);
if (tramp & 0x8000)
tramp -= 0x10000;
DEBUGP(" %x ", tramp);
if (tramp != addr) {
printk(KERN_ERR
"Trampoline location %08lx does not match addr\n",
tramp);
return -EINVAL;
}
op[0] = PPC_NOP_INSTR;
if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE))
return -EPERM;
return 0;
}
#endif /* PPC64 */
int ftrace_make_nop(struct module *mod,
struct dyn_ftrace *rec, unsigned long addr)
{
unsigned char *old, *new;
unsigned long ip = rec->ip;
/*
* If the calling address is more that 24 bits away,
* then we had to use a trampoline to make the call.
* Otherwise just update the call site.
*/
if (test_24bit_addr(ip, addr)) {
/* within range */
old = ftrace_call_replace(ip, addr);
new = ftrace_nop_replace();
return ftrace_modify_code(ip, old, new);
}
/*
* Out of range jumps are called from modules.
* We should either already have a pointer to the module
* or it has been passed in.
*/
if (!rec->arch.mod) {
if (!mod) {
printk(KERN_ERR "No module loaded addr=%lx\n",
addr);
return -EFAULT;
}
rec->arch.mod = mod;
} else if (mod) {
if (mod != rec->arch.mod) {
printk(KERN_ERR
"Record mod %p not equal to passed in mod %p\n",
rec->arch.mod, mod);
return -EINVAL;
}
/* nothing to do if mod == rec->arch.mod */
} else
mod = rec->arch.mod;
return __ftrace_make_nop(mod, rec, addr);
}
#ifdef CONFIG_PPC64
static int
__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned char replaced[MCOUNT_INSN_SIZE * 2];
unsigned int *op = (unsigned *)&replaced;
unsigned long ip = rec->ip;
unsigned long offset;
/* read where this goes */
if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE * 2))
return -EFAULT;
/*
* It should be pointing to two nops or
* b +8; ld r2,40(r1)
*/
if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) &&
((op[0] != PPC_NOP_INSTR) || (op[1] != PPC_NOP_INSTR))) {
printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]);
return -EINVAL;
}
/* If we never set up a trampoline to ftrace_caller, then bail */
if (!rec->arch.mod->arch.tramp) {
printk(KERN_ERR "No ftrace trampoline\n");
return -EINVAL;
}
/* now calculate a jump to the ftrace caller trampoline */
offset = rec->arch.mod->arch.tramp - ip;
if (test_offset(offset)) {
printk(KERN_ERR "REL24 %li out of range!\n",
(long int)offset);
return -EINVAL;
}
/* Set to "bl addr" */
op[0] = branch_offset(offset);
/* ld r2,40(r1) */
op[1] = 0xe8410028;
DEBUGP("write to %lx\n", rec->ip);
if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE * 2))
return -EPERM;
return 0;
}
#else
static int
__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned char replaced[MCOUNT_INSN_SIZE];
unsigned int *op = (unsigned *)&replaced;
unsigned long ip = rec->ip;
unsigned long offset;
/* read where this goes */
if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
return -EFAULT;
/* It should be pointing to a nop */
if (op[0] != PPC_NOP_INSTR) {
printk(KERN_ERR "Expected NOP but have %x\n", op[0]);
return -EINVAL;
}
/* If we never set up a trampoline to ftrace_caller, then bail */
if (!rec->arch.mod->arch.tramp) {
printk(KERN_ERR "No ftrace trampoline\n");
return -EINVAL;
}
/* now calculate a jump to the ftrace caller trampoline */
offset = rec->arch.mod->arch.tramp - ip;
if (test_offset(offset)) {
printk(KERN_ERR "REL24 %li out of range!\n",
(long int)offset);
return -EINVAL;
}
/* Set to "bl addr" */
op[0] = branch_offset(offset);
DEBUGP("write to %lx\n", rec->ip);
if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE))
return -EPERM;
return 0;
}
#endif /* CONFIG_PPC64 */
int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned char *old, *new;
unsigned long ip = rec->ip;
/*
* If the calling address is more that 24 bits away,
* then we had to use a trampoline to make the call.
* Otherwise just update the call site.
*/
if (test_24bit_addr(ip, addr)) {
/* within range */
old = ftrace_nop_replace();
new = ftrace_call_replace(ip, addr);
return ftrace_modify_code(ip, old, new);
}
/*
* Out of range jumps are called from modules.
* Being that we are converting from nop, it had better
* already have a module defined.
*/
if (!rec->arch.mod) {
printk(KERN_ERR "No module loaded\n");
return -EINVAL;
}
return __ftrace_make_call(rec, addr);
}
int ftrace_update_ftrace_func(ftrace_func_t func)
@ -128,10 +521,10 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
int __init ftrace_dyn_arch_init(void *data)
{
/* This is running in kstop_machine */
/* caller expects data to be zero */
unsigned long *p = data;
ftrace_mcount_set(data);
*p = 0;
return 0;
}

View File

@ -69,10 +69,15 @@ void cpu_idle(void)
smp_mb();
local_irq_disable();
/* Don't trace irqs off for idle */
stop_critical_timings();
/* check again after disabling irqs */
if (!need_resched() && !cpu_should_die())
ppc_md.power_save();
start_critical_timings();
local_irq_enable();
set_thread_flag(TIF_POLLING_NRFLAG);

View File

@ -22,6 +22,7 @@
#include <linux/fs.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/ftrace.h>
#include <linux/cache.h>
#include <linux/bug.h>
#include <linux/sort.h>
@ -53,6 +54,9 @@ static unsigned int count_relocs(const Elf32_Rela *rela, unsigned int num)
r_addend = rela[i].r_addend;
}
#ifdef CONFIG_DYNAMIC_FTRACE
_count_relocs++; /* add one for ftrace_caller */
#endif
return _count_relocs;
}
@ -306,5 +310,11 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
return -ENOEXEC;
}
}
#ifdef CONFIG_DYNAMIC_FTRACE
module->arch.tramp =
do_plt_call(module->module_core,
(unsigned long)ftrace_caller,
sechdrs, module);
#endif
return 0;
}

View File

@ -20,6 +20,7 @@
#include <linux/moduleloader.h>
#include <linux/err.h>
#include <linux/vmalloc.h>
#include <linux/ftrace.h>
#include <linux/bug.h>
#include <asm/module.h>
#include <asm/firmware.h>
@ -163,6 +164,11 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
}
}
#ifdef CONFIG_DYNAMIC_FTRACE
/* make the trampoline to the ftrace_caller */
relocs++;
#endif
DEBUGP("Looks like a total of %lu stubs, max\n", relocs);
return relocs * sizeof(struct ppc64_stub_entry);
}
@ -441,5 +447,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
}
}
#ifdef CONFIG_DYNAMIC_FTRACE
me->arch.toc = my_r2(sechdrs, me);
me->arch.tramp = stub_for_addr(sechdrs,
(unsigned long)ftrace_caller,
me);
#endif
return 0;
}

View File

@ -36,6 +36,7 @@ config X86
select HAVE_ARCH_TRACEHOOK
select HAVE_GENERIC_DMA_COHERENT if X86_32
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select USER_STACKTRACE_SUPPORT
config ARCH_DEFCONFIG
string

View File

@ -29,7 +29,6 @@ struct dyn_arch_ftrace {
#endif /* CONFIG_FUNCTION_TRACER */
#ifdef CONFIG_FUNCTION_RET_TRACER
#define FTRACE_RET_STACK_SIZE 20
#ifndef __ASSEMBLY__

View File

@ -40,36 +40,8 @@ struct thread_info {
*/
__u8 supervisor_stack[0];
#endif
#ifdef CONFIG_FUNCTION_RET_TRACER
/* Index of current stored adress in ret_stack */
int curr_ret_stack;
/* Stack of return addresses for return function tracing */
struct ftrace_ret_stack ret_stack[FTRACE_RET_STACK_SIZE];
/*
* Number of functions that haven't been traced
* because of depth overrun.
*/
atomic_t trace_overrun;
#endif
};
#ifdef CONFIG_FUNCTION_RET_TRACER
#define INIT_THREAD_INFO(tsk) \
{ \
.task = &tsk, \
.exec_domain = &default_exec_domain, \
.flags = 0, \
.cpu = 0, \
.preempt_count = 1, \
.addr_limit = KERNEL_DS, \
.restart_block = { \
.fn = do_no_restart_syscall, \
}, \
.curr_ret_stack = -1,\
.trace_overrun = ATOMIC_INIT(0) \
}
#else
#define INIT_THREAD_INFO(tsk) \
{ \
.task = &tsk, \
@ -82,7 +54,6 @@ struct thread_info {
.fn = do_no_restart_syscall, \
}, \
}
#endif
#define init_thread_info (init_thread_union.thread_info)
#define init_stack (init_thread_union.stack)

View File

@ -350,19 +350,21 @@ static int push_return_trace(unsigned long ret, unsigned long long time,
unsigned long func)
{
int index;
struct thread_info *ti = current_thread_info();
if (!current->ret_stack)
return -EBUSY;
/* The return trace stack is full */
if (ti->curr_ret_stack == FTRACE_RET_STACK_SIZE - 1) {
atomic_inc(&ti->trace_overrun);
if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
atomic_inc(&current->trace_overrun);
return -EBUSY;
}
index = ++ti->curr_ret_stack;
index = ++current->curr_ret_stack;
barrier();
ti->ret_stack[index].ret = ret;
ti->ret_stack[index].func = func;
ti->ret_stack[index].calltime = time;
current->ret_stack[index].ret = ret;
current->ret_stack[index].func = func;
current->ret_stack[index].calltime = time;
return 0;
}
@ -373,13 +375,12 @@ static void pop_return_trace(unsigned long *ret, unsigned long long *time,
{
int index;
struct thread_info *ti = current_thread_info();
index = ti->curr_ret_stack;
*ret = ti->ret_stack[index].ret;
*func = ti->ret_stack[index].func;
*time = ti->ret_stack[index].calltime;
*overrun = atomic_read(&ti->trace_overrun);
ti->curr_ret_stack--;
index = current->curr_ret_stack;
*ret = current->ret_stack[index].ret;
*func = current->ret_stack[index].func;
*time = current->ret_stack[index].calltime;
*overrun = atomic_read(&current->trace_overrun);
current->curr_ret_stack--;
}
/*

View File

@ -6,6 +6,7 @@
#include <linux/sched.h>
#include <linux/stacktrace.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <asm/stacktrace.h>
static void save_stack_warning(void *data, char *msg)
@ -83,3 +84,66 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
/* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
struct stack_frame {
const void __user *next_fp;
unsigned long ret_addr;
};
static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
{
int ret;
if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
return 0;
ret = 1;
pagefault_disable();
if (__copy_from_user_inatomic(frame, fp, sizeof(*frame)))
ret = 0;
pagefault_enable();
return ret;
}
static inline void __save_stack_trace_user(struct stack_trace *trace)
{
const struct pt_regs *regs = task_pt_regs(current);
const void __user *fp = (const void __user *)regs->bp;
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = regs->ip;
while (trace->nr_entries < trace->max_entries) {
struct stack_frame frame;
frame.next_fp = NULL;
frame.ret_addr = 0;
if (!copy_stack_frame(fp, &frame))
break;
if ((unsigned long)fp < regs->sp)
break;
if (frame.ret_addr) {
trace->entries[trace->nr_entries++] =
frame.ret_addr;
}
if (fp == frame.next_fp)
break;
fp = frame.next_fp;
}
}
void save_stack_trace_user(struct stack_trace *trace)
{
/*
* Trace user stack if we are not a kernel thread
*/
if (current->mm) {
__save_stack_trace_user(trace);
}
if (trace->nr_entries < trace->max_entries)
trace->entries[trace->nr_entries++] = ULONG_MAX;
}

View File

@ -357,7 +357,18 @@ int seq_printf(struct seq_file *m, const char *f, ...)
}
EXPORT_SYMBOL(seq_printf);
static char *mangle_path(char *s, char *p, char *esc)
/**
* mangle_path - mangle and copy path to buffer beginning
* @s: buffer start
* @p: beginning of path in above buffer
* @esc: set of characters that need escaping
*
* Copy the path from @p to @s, replacing each occurrence of character from
* @esc with usual octal escape.
* Returns pointer past last written character in @s, or NULL in case of
* failure.
*/
char *mangle_path(char *s, char *p, char *esc)
{
while (s <= p) {
char c = *p++;
@ -376,6 +387,7 @@ static char *mangle_path(char *s, char *p, char *esc)
}
return NULL;
}
EXPORT_SYMBOL_GPL(mangle_path);
/*
* return the absolute path of 'dentry' residing in mount 'mnt'.

View File

@ -257,6 +257,7 @@ extern int ftrace_dump_on_oops;
extern void tracing_start(void);
extern void tracing_stop(void);
extern void ftrace_off_permanent(void);
extern void
ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
@ -290,6 +291,7 @@ ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 0)));
static inline void tracing_start(void) { }
static inline void tracing_stop(void) { }
static inline void ftrace_off_permanent(void) { }
static inline int
ftrace_printk(const char *fmt, ...)
{
@ -323,6 +325,8 @@ struct ftrace_retfunc {
};
#ifdef CONFIG_FUNCTION_RET_TRACER
#define FTRACE_RETFUNC_DEPTH 50
#define FTRACE_RETSTACK_ALLOC_SIZE 32
/* Type of a callback handler of tracing return function */
typedef void (*trace_function_return_t)(struct ftrace_retfunc *);
@ -330,6 +334,12 @@ extern int register_ftrace_return(trace_function_return_t func);
/* The current handler in use */
extern trace_function_return_t ftrace_function_return;
extern void unregister_ftrace_return(void);
extern void ftrace_retfunc_init_task(struct task_struct *t);
extern void ftrace_retfunc_exit_task(struct task_struct *t);
#else
static inline void ftrace_retfunc_init_task(struct task_struct *t) { }
static inline void ftrace_retfunc_exit_task(struct task_struct *t) { }
#endif
#endif /* _LINUX_FTRACE_H */

View File

@ -122,6 +122,7 @@ void ring_buffer_normalize_time_stamp(int cpu, u64 *ts);
void tracing_on(void);
void tracing_off(void);
void tracing_off_permanent(void);
enum ring_buffer_flags {
RB_FL_OVERWRITE = 1 << 0,

View File

@ -1352,6 +1352,17 @@ struct task_struct {
unsigned long default_timer_slack_ns;
struct list_head *scm_work_list;
#ifdef CONFIG_FUNCTION_RET_TRACER
/* Index of current stored adress in ret_stack */
int curr_ret_stack;
/* Stack of return addresses for return function tracing */
struct ftrace_ret_stack *ret_stack;
/*
* Number of functions that haven't been traced
* because of depth overrun.
*/
atomic_t trace_overrun;
#endif
};
/*
@ -2006,18 +2017,6 @@ static inline void setup_thread_stack(struct task_struct *p, struct task_struct
{
*task_thread_info(p) = *task_thread_info(org);
task_thread_info(p)->task = p;
#ifdef CONFIG_FUNCTION_RET_TRACER
/*
* When fork() creates a child process, this function is called.
* But the child task may not inherit the return adresses traced
* by the return function tracer because it will directly execute
* in userspace and will not return to kernel functions its parent
* used.
*/
task_thread_info(p)->curr_ret_stack = -1;
atomic_set(&task_thread_info(p)->trace_overrun, 0);
#endif
}
static inline unsigned long *end_of_stack(struct task_struct *p)

View File

@ -34,6 +34,7 @@ struct seq_operations {
#define SEQ_SKIP 1
char *mangle_path(char *s, char *p, char *esc);
int seq_open(struct file *, const struct seq_operations *);
ssize_t seq_read(struct file *, char __user *, size_t, loff_t *);
loff_t seq_lseek(struct file *, loff_t, int);

View File

@ -15,9 +15,17 @@ extern void save_stack_trace_tsk(struct task_struct *tsk,
struct stack_trace *trace);
extern void print_stack_trace(struct stack_trace *trace, int spaces);
#ifdef CONFIG_USER_STACKTRACE_SUPPORT
extern void save_stack_trace_user(struct stack_trace *trace);
#else
# define save_stack_trace_user(trace) do { } while (0)
#endif
#else
# define save_stack_trace(trace) do { } while (0)
# define save_stack_trace_tsk(tsk, trace) do { } while (0)
# define save_stack_trace_user(trace) do { } while (0)
# define print_stack_trace(trace, spaces) do { } while (0)
#endif

View File

@ -723,7 +723,7 @@ int do_one_initcall(initcall_t fn)
disable_boot_trace();
rettime = ktime_get();
delta = ktime_sub(rettime, calltime);
ret.duration = (unsigned long long) delta.tv64 >> 10;
ret.duration = (unsigned long long) ktime_to_ns(delta) >> 10;
trace_boot_ret(&ret, fn);
printk("initcall %pF returned %d after %Ld usecs\n", fn,
ret.result, ret.duration);

View File

@ -1127,7 +1127,6 @@ NORET_TYPE void do_exit(long code)
preempt_disable();
/* causes final put_task_struct in finish_task_switch(). */
tsk->state = TASK_DEAD;
schedule();
BUG();
/* Avoid "noreturn function does return". */

View File

@ -47,6 +47,7 @@
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/acct.h>
@ -139,6 +140,7 @@ void free_task(struct task_struct *tsk)
prop_local_destroy_single(&tsk->dirties);
free_thread_info(tsk->stack);
rt_mutex_debug_task_free(tsk);
ftrace_retfunc_exit_task(tsk);
free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);
@ -1269,6 +1271,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
total_forks++;
spin_unlock(&current->sighand->siglock);
write_unlock_irq(&tasklist_lock);
ftrace_retfunc_init_task(p);
proc_fork_connector(p);
cgroup_post_fork(p);
return p;

View File

@ -22,7 +22,6 @@
#include <linux/console.h>
#include <linux/cpu.h>
#include <linux/freezer.h>
#include <linux/ftrace.h>
#include "power.h"
@ -257,7 +256,7 @@ static int create_image(int platform_mode)
int hibernation_snapshot(int platform_mode)
{
int error, ftrace_save;
int error;
/* Free memory before shutting down devices. */
error = swsusp_shrink_memory();
@ -269,7 +268,6 @@ int hibernation_snapshot(int platform_mode)
goto Close;
suspend_console();
ftrace_save = __ftrace_enabled_save();
error = device_suspend(PMSG_FREEZE);
if (error)
goto Recover_platform;
@ -299,7 +297,6 @@ int hibernation_snapshot(int platform_mode)
Resume_devices:
device_resume(in_suspend ?
(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
__ftrace_enabled_restore(ftrace_save);
resume_console();
Close:
platform_end(platform_mode);
@ -370,11 +367,10 @@ static int resume_target_kernel(void)
int hibernation_restore(int platform_mode)
{
int error, ftrace_save;
int error;
pm_prepare_console();
suspend_console();
ftrace_save = __ftrace_enabled_save();
error = device_suspend(PMSG_QUIESCE);
if (error)
goto Finish;
@ -389,7 +385,6 @@ int hibernation_restore(int platform_mode)
platform_restore_cleanup(platform_mode);
device_resume(PMSG_RECOVER);
Finish:
__ftrace_enabled_restore(ftrace_save);
resume_console();
pm_restore_console();
return error;
@ -402,7 +397,7 @@ int hibernation_restore(int platform_mode)
int hibernation_platform_enter(void)
{
int error, ftrace_save;
int error;
if (!hibernation_ops)
return -ENOSYS;
@ -417,7 +412,6 @@ int hibernation_platform_enter(void)
goto Close;
suspend_console();
ftrace_save = __ftrace_enabled_save();
error = device_suspend(PMSG_HIBERNATE);
if (error) {
if (hibernation_ops->recover)
@ -452,7 +446,6 @@ int hibernation_platform_enter(void)
hibernation_ops->finish();
Resume_devices:
device_resume(PMSG_RESTORE);
__ftrace_enabled_restore(ftrace_save);
resume_console();
Close:
hibernation_ops->end();

View File

@ -22,7 +22,6 @@
#include <linux/freezer.h>
#include <linux/vmstat.h>
#include <linux/syscalls.h>
#include <linux/ftrace.h>
#include "power.h"
@ -317,7 +316,7 @@ static int suspend_enter(suspend_state_t state)
*/
int suspend_devices_and_enter(suspend_state_t state)
{
int error, ftrace_save;
int error;
if (!suspend_ops)
return -ENOSYS;
@ -328,7 +327,6 @@ int suspend_devices_and_enter(suspend_state_t state)
goto Close;
}
suspend_console();
ftrace_save = __ftrace_enabled_save();
suspend_test_start();
error = device_suspend(PMSG_SUSPEND);
if (error) {
@ -360,7 +358,6 @@ int suspend_devices_and_enter(suspend_state_t state)
suspend_test_start();
device_resume(PMSG_RESUME);
suspend_test_finish("resume devices");
__ftrace_enabled_restore(ftrace_save);
resume_console();
Close:
if (suspend_ops->end)

View File

@ -5901,6 +5901,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
* The idle tasks have their own, simple scheduling class:
*/
idle->sched_class = &idle_sched_class;
ftrace_retfunc_init_task(idle);
}
/*

View File

@ -3,6 +3,9 @@
# select HAVE_FUNCTION_TRACER:
#
config USER_STACKTRACE_SUPPORT
bool
config NOP_TRACER
bool

View File

@ -1498,10 +1498,77 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
#ifdef CONFIG_FUNCTION_RET_TRACER
static atomic_t ftrace_retfunc_active;
/* The callback that hooks the return of a function */
trace_function_return_t ftrace_function_return =
(trace_function_return_t)ftrace_stub;
/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
{
int i;
int ret = 0;
unsigned long flags;
int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE;
struct task_struct *g, *t;
for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) {
ret_stack_list[i] = kmalloc(FTRACE_RETFUNC_DEPTH
* sizeof(struct ftrace_ret_stack),
GFP_KERNEL);
if (!ret_stack_list[i]) {
start = 0;
end = i;
ret = -ENOMEM;
goto free;
}
}
read_lock_irqsave(&tasklist_lock, flags);
do_each_thread(g, t) {
if (start == end) {
ret = -EAGAIN;
goto unlock;
}
if (t->ret_stack == NULL) {
t->ret_stack = ret_stack_list[start++];
t->curr_ret_stack = -1;
atomic_set(&t->trace_overrun, 0);
}
} while_each_thread(g, t);
unlock:
read_unlock_irqrestore(&tasklist_lock, flags);
free:
for (i = start; i < end; i++)
kfree(ret_stack_list[i]);
return ret;
}
/* Allocate a return stack for each task */
static int start_return_tracing(void)
{
struct ftrace_ret_stack **ret_stack_list;
int ret;
ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE *
sizeof(struct ftrace_ret_stack *),
GFP_KERNEL);
if (!ret_stack_list)
return -ENOMEM;
do {
ret = alloc_retstack_tasklist(ret_stack_list);
} while (ret == -EAGAIN);
kfree(ret_stack_list);
return ret;
}
int register_ftrace_return(trace_function_return_t func)
{
int ret = 0;
@ -1516,7 +1583,12 @@ int register_ftrace_return(trace_function_return_t func)
ret = -EBUSY;
goto out;
}
atomic_inc(&ftrace_retfunc_active);
ret = start_return_tracing();
if (ret) {
atomic_dec(&ftrace_retfunc_active);
goto out;
}
ftrace_tracing_type = FTRACE_TYPE_RETURN;
ftrace_function_return = func;
ftrace_startup();
@ -1530,6 +1602,7 @@ void unregister_ftrace_return(void)
{
mutex_lock(&ftrace_sysctl_lock);
atomic_dec(&ftrace_retfunc_active);
ftrace_function_return = (trace_function_return_t)ftrace_stub;
ftrace_shutdown();
/* Restore normal tracing type */
@ -1537,6 +1610,32 @@ void unregister_ftrace_return(void)
mutex_unlock(&ftrace_sysctl_lock);
}
/* Allocate a return stack for newly created task */
void ftrace_retfunc_init_task(struct task_struct *t)
{
if (atomic_read(&ftrace_retfunc_active)) {
t->ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
* sizeof(struct ftrace_ret_stack),
GFP_KERNEL);
if (!t->ret_stack)
return;
t->curr_ret_stack = -1;
atomic_set(&t->trace_overrun, 0);
} else
t->ret_stack = NULL;
}
void ftrace_retfunc_exit_task(struct task_struct *t)
{
struct ftrace_ret_stack *ret_stack = t->ret_stack;
t->ret_stack = NULL;
/* NULL must become visible to IRQs before we free it: */
barrier();
kfree(ret_stack);
}
#endif

View File

@ -18,8 +18,46 @@
#include "trace.h"
/* Global flag to disable all recording to ring buffers */
static int ring_buffers_off __read_mostly;
/*
* A fast way to enable or disable all ring buffers is to
* call tracing_on or tracing_off. Turning off the ring buffers
* prevents all ring buffers from being recorded to.
* Turning this switch on, makes it OK to write to the
* ring buffer, if the ring buffer is enabled itself.
*
* There's three layers that must be on in order to write
* to the ring buffer.
*
* 1) This global flag must be set.
* 2) The ring buffer must be enabled for recording.
* 3) The per cpu buffer must be enabled for recording.
*
* In case of an anomaly, this global flag has a bit set that
* will permantly disable all ring buffers.
*/
/*
* Global flag to disable all recording to ring buffers
* This has two bits: ON, DISABLED
*
* ON DISABLED
* ---- ----------
* 0 0 : ring buffers are off
* 1 0 : ring buffers are on
* X 1 : ring buffers are permanently disabled
*/
enum {
RB_BUFFERS_ON_BIT = 0,
RB_BUFFERS_DISABLED_BIT = 1,
};
enum {
RB_BUFFERS_ON = 1 << RB_BUFFERS_ON_BIT,
RB_BUFFERS_DISABLED = 1 << RB_BUFFERS_DISABLED_BIT,
};
static long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
/**
* tracing_on - enable all tracing buffers
@ -29,7 +67,7 @@ static int ring_buffers_off __read_mostly;
*/
void tracing_on(void)
{
ring_buffers_off = 0;
set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
}
/**
@ -42,7 +80,18 @@ void tracing_on(void)
*/
void tracing_off(void)
{
ring_buffers_off = 1;
clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
}
/**
* tracing_off_permanent - permanently disable ring buffers
*
* This function, once called, will disable all ring buffers
* permanenty.
*/
void tracing_off_permanent(void)
{
set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags);
}
#include "trace.h"
@ -1185,7 +1234,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
struct ring_buffer_event *event;
int cpu, resched;
if (ring_buffers_off)
if (ring_buffer_flags != RB_BUFFERS_ON)
return NULL;
if (atomic_read(&buffer->record_disabled))
@ -1297,7 +1346,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
int ret = -EBUSY;
int cpu, resched;
if (ring_buffers_off)
if (ring_buffer_flags != RB_BUFFERS_ON)
return -EBUSY;
if (atomic_read(&buffer->record_disabled))
@ -2178,12 +2227,14 @@ static ssize_t
rb_simple_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
int *p = filp->private_data;
long *p = filp->private_data;
char buf[64];
int r;
/* !ring_buffers_off == tracing_on */
r = sprintf(buf, "%d\n", !*p);
if (test_bit(RB_BUFFERS_DISABLED_BIT, p))
r = sprintf(buf, "permanently disabled\n");
else
r = sprintf(buf, "%d\n", test_bit(RB_BUFFERS_ON_BIT, p));
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
@ -2192,7 +2243,7 @@ static ssize_t
rb_simple_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
int *p = filp->private_data;
long *p = filp->private_data;
char buf[64];
long val;
int ret;
@ -2209,8 +2260,10 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
if (ret < 0)
return ret;
/* !ring_buffers_off == tracing_on */
*p = !val;
if (val)
set_bit(RB_BUFFERS_ON_BIT, p);
else
clear_bit(RB_BUFFERS_ON_BIT, p);
(*ppos)++;
@ -2232,7 +2285,7 @@ static __init int rb_init_debugfs(void)
d_tracer = tracing_init_dentry();
entry = debugfs_create_file("tracing_on", 0644, d_tracer,
&ring_buffers_off, &rb_simple_fops);
&ring_buffer_flags, &rb_simple_fops);
if (!entry)
pr_warning("Could not create debugfs 'tracing_on' entry\n");

View File

@ -30,6 +30,7 @@
#include <linux/gfp.h>
#include <linux/fs.h>
#include <linux/kprobes.h>
#include <linux/seq_file.h>
#include <linux/writeback.h>
#include <linux/stacktrace.h>
@ -275,6 +276,8 @@ static const char *trace_options[] = {
"ftrace_preempt",
"branch",
"annotate",
"userstacktrace",
"sym-userobj",
NULL
};
@ -421,6 +424,28 @@ trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
return trace_seq_putmem(s, hex, j);
}
static int
trace_seq_path(struct trace_seq *s, struct path *path)
{
unsigned char *p;
if (s->len >= (PAGE_SIZE - 1))
return 0;
p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len);
if (!IS_ERR(p)) {
p = mangle_path(s->buffer + s->len, p, "\n");
if (p) {
s->len = p - s->buffer;
return 1;
}
} else {
s->buffer[s->len++] = '?';
return 1;
}
return 0;
}
static void
trace_seq_reset(struct trace_seq *s)
{
@ -660,6 +685,21 @@ static void trace_init_cmdlines(void)
static int trace_stop_count;
static DEFINE_SPINLOCK(tracing_start_lock);
/**
* ftrace_off_permanent - disable all ftrace code permanently
*
* This should only be called when a serious anomally has
* been detected. This will turn off the function tracing,
* ring buffers, and other tracing utilites. It takes no
* locks and can be called from any context.
*/
void ftrace_off_permanent(void)
{
tracing_disabled = 1;
ftrace_stop();
tracing_off_permanent();
}
/**
* tracing_start - quick start of the tracer
*
@ -801,6 +841,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
entry->preempt_count = pc & 0xff;
entry->pid = (tsk) ? tsk->pid : 0;
entry->tgid = (tsk) ? tsk->tgid : 0;
entry->flags =
#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@ -918,6 +959,44 @@ void __trace_stack(struct trace_array *tr,
ftrace_trace_stack(tr, data, flags, skip, preempt_count());
}
static void ftrace_trace_userstack(struct trace_array *tr,
struct trace_array_cpu *data,
unsigned long flags, int pc)
{
struct ring_buffer_event *event;
struct userstack_entry *entry;
struct stack_trace trace;
unsigned long irq_flags;
if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
return;
event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
&irq_flags);
if (!event)
return;
entry = ring_buffer_event_data(event);
tracing_generic_entry_update(&entry->ent, flags, pc);
entry->ent.type = TRACE_USER_STACK;
memset(&entry->caller, 0, sizeof(entry->caller));
trace.nr_entries = 0;
trace.max_entries = FTRACE_STACK_ENTRIES;
trace.skip = 0;
trace.entries = entry->caller;
save_stack_trace_user(&trace);
ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
}
void __trace_userstack(struct trace_array *tr,
struct trace_array_cpu *data,
unsigned long flags)
{
ftrace_trace_userstack(tr, data, flags, preempt_count());
}
static void
ftrace_trace_special(void *__tr, void *__data,
unsigned long arg1, unsigned long arg2, unsigned long arg3,
@ -941,6 +1020,7 @@ ftrace_trace_special(void *__tr, void *__data,
entry->arg3 = arg3;
ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
ftrace_trace_stack(tr, data, irq_flags, 4, pc);
ftrace_trace_userstack(tr, data, irq_flags, pc);
trace_wake_up();
}
@ -979,6 +1059,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
entry->next_cpu = task_cpu(next);
ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
ftrace_trace_stack(tr, data, flags, 5, pc);
ftrace_trace_userstack(tr, data, flags, pc);
}
void
@ -1008,6 +1089,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
entry->next_cpu = task_cpu(wakee);
ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
ftrace_trace_stack(tr, data, flags, 6, pc);
ftrace_trace_userstack(tr, data, flags, pc);
trace_wake_up();
}
@ -1387,6 +1469,78 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
return ret;
}
static inline int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
unsigned long ip, unsigned long sym_flags)
{
struct file *file = NULL;
unsigned long vmstart = 0;
int ret = 1;
if (mm) {
const struct vm_area_struct *vma;
down_read(&mm->mmap_sem);
vma = find_vma(mm, ip);
if (vma) {
file = vma->vm_file;
vmstart = vma->vm_start;
}
if (file) {
ret = trace_seq_path(s, &file->f_path);
if (ret)
ret = trace_seq_printf(s, "[+0x%lx]", ip - vmstart);
}
up_read(&mm->mmap_sem);
}
if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file))
ret = trace_seq_printf(s, " <" IP_FMT ">", ip);
return ret;
}
static int
seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
unsigned long sym_flags)
{
struct mm_struct *mm = NULL;
int ret = 1;
unsigned int i;
if (trace_flags & TRACE_ITER_SYM_USEROBJ) {
struct task_struct *task;
/*
* we do the lookup on the thread group leader,
* since individual threads might have already quit!
*/
rcu_read_lock();
task = find_task_by_vpid(entry->ent.tgid);
if (task)
mm = get_task_mm(task);
rcu_read_unlock();
}
for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
unsigned long ip = entry->caller[i];
if (ip == ULONG_MAX || !ret)
break;
if (i && ret)
ret = trace_seq_puts(s, " <- ");
if (!ip) {
if (ret)
ret = trace_seq_puts(s, "??");
continue;
}
if (!ret)
break;
if (ret)
ret = seq_print_user_ip(s, mm, ip, sym_flags);
}
if (mm)
mmput(mm);
return ret;
}
static void print_lat_help_header(struct seq_file *m)
{
seq_puts(m, "# _------=> CPU# \n");
@ -1702,6 +1856,15 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
field->line);
break;
}
case TRACE_USER_STACK: {
struct userstack_entry *field;
trace_assign_type(field, entry);
seq_print_userip_objs(field, s, sym_flags);
trace_seq_putc(s, '\n');
break;
}
default:
trace_seq_printf(s, "Unknown type %d\n", entry->type);
}
@ -1853,6 +2016,19 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
field->line);
break;
}
case TRACE_USER_STACK: {
struct userstack_entry *field;
trace_assign_type(field, entry);
ret = seq_print_userip_objs(field, s, sym_flags);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
ret = trace_seq_putc(s, '\n');
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
break;
}
}
return TRACE_TYPE_HANDLED;
}
@ -1912,6 +2088,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
break;
}
case TRACE_SPECIAL:
case TRACE_USER_STACK:
case TRACE_STACK: {
struct special_entry *field;
@ -2000,6 +2177,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
break;
}
case TRACE_SPECIAL:
case TRACE_USER_STACK:
case TRACE_STACK: {
struct special_entry *field;
@ -2054,6 +2232,7 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
break;
}
case TRACE_SPECIAL:
case TRACE_USER_STACK:
case TRACE_STACK: {
struct special_entry *field;
@ -3488,6 +3667,9 @@ void ftrace_dump(void)
atomic_inc(&global_trace.data[cpu]->disabled);
}
/* don't look at user memory in panic mode */
trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
printk(KERN_TRACE "Dumping ftrace buffer:\n");
iter.tr = &global_trace;

View File

@ -26,6 +26,7 @@ enum trace_type {
TRACE_BOOT_CALL,
TRACE_BOOT_RET,
TRACE_FN_RET,
TRACE_USER_STACK,
__TRACE_LAST_TYPE
};
@ -42,6 +43,7 @@ struct trace_entry {
unsigned char flags;
unsigned char preempt_count;
int pid;
int tgid;
};
/*
@ -99,6 +101,11 @@ struct stack_entry {
unsigned long caller[FTRACE_STACK_ENTRIES];
};
struct userstack_entry {
struct trace_entry ent;
unsigned long caller[FTRACE_STACK_ENTRIES];
};
/*
* ftrace_printk entry:
*/
@ -240,6 +247,7 @@ extern void __ftrace_bad_type(void);
IF_ASSIGN(var, ent, struct ctx_switch_entry, 0); \
IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \
IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK); \
IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \
IF_ASSIGN(var, ent, struct special_entry, 0); \
IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \
@ -500,6 +508,8 @@ enum trace_iterator_flags {
TRACE_ITER_PREEMPTONLY = 0x800,
TRACE_ITER_BRANCH = 0x1000,
TRACE_ITER_ANNOTATE = 0x2000,
TRACE_ITER_USERSTACKTRACE = 0x4000,
TRACE_ITER_SYM_USEROBJ = 0x8000
};
/*

View File

@ -18,12 +18,14 @@ struct header_iter {
static struct trace_array *mmio_trace_array;
static bool overrun_detected;
static unsigned long prev_overruns;
static void mmio_reset_data(struct trace_array *tr)
{
int cpu;
overrun_detected = false;
prev_overruns = 0;
tr->time_start = ftrace_now(tr->cpu);
for_each_online_cpu(cpu)
@ -123,16 +125,12 @@ static void mmio_close(struct trace_iterator *iter)
static unsigned long count_overruns(struct trace_iterator *iter)
{
int cpu;
unsigned long cnt = 0;
/* FIXME: */
#if 0
for_each_online_cpu(cpu) {
cnt += iter->overrun[cpu];
iter->overrun[cpu] = 0;
}
#endif
(void)cpu;
unsigned long over = ring_buffer_overruns(iter->tr->buffer);
if (over > prev_overruns)
cnt = over - prev_overruns;
prev_overruns = over;
return cnt;
}

View File

@ -130,11 +130,13 @@ my %weak; # List of weak functions
my %convert; # List of local functions used that needs conversion
my $type;
my $nm_regex; # Find the local functions (return function)
my $section_regex; # Find the start of a section
my $function_regex; # Find the name of a function
# (return offset and func name)
my $mcount_regex; # Find the call site to mcount (return offset)
my $alignment; # The .align value to use for $mcount_section
my $alignment; # The .align value to use for $mcount_section
my $section_type; # Section header plus possible alignment command
if ($arch eq "x86") {
if ($bits == 64) {
@ -144,9 +146,18 @@ if ($arch eq "x86") {
}
}
#
# We base the defaults off of i386, the other archs may
# feel free to change them in the below if statements.
#
$nm_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\S+)";
$section_regex = "Disassembly of section\\s+(\\S+):";
$function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
$mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$";
$section_type = '@progbits';
$type = ".long";
if ($arch eq "x86_64") {
$section_regex = "Disassembly of section\\s+(\\S+):";
$function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
$mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount([+-]0x[0-9a-zA-Z]+)?\$";
$type = ".quad";
$alignment = 8;
@ -158,10 +169,6 @@ if ($arch eq "x86_64") {
$cc .= " -m64";
} elsif ($arch eq "i386") {
$section_regex = "Disassembly of section\\s+(\\S+):";
$function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
$mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$";
$type = ".long";
$alignment = 4;
# force flags for this arch
@ -170,6 +177,27 @@ if ($arch eq "x86_64") {
$objcopy .= " -O elf32-i386";
$cc .= " -m32";
} elsif ($arch eq "sh") {
$alignment = 2;
# force flags for this arch
$ld .= " -m shlelf_linux";
$objcopy .= " -O elf32-sh-linux";
$cc .= " -m32";
} elsif ($arch eq "powerpc") {
$nm_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)";
$function_regex = "^([0-9a-fA-F]+)\\s+<(\\.?.*?)>:";
$mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s\\.?_mcount\$";
if ($bits == 64) {
$type = ".quad";
}
} elsif ($arch eq "arm") {
$alignment = 2;
$section_type = '%progbits';
} else {
die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD";
}
@ -239,7 +267,7 @@ if (!$found_version) {
#
open (IN, "$nm $inputfile|") || die "error running $nm";
while (<IN>) {
if (/^[0-9a-fA-F]+\s+t\s+(\S+)/) {
if (/$nm_regex/) {
$locals{$1} = 1;
} elsif (/^[0-9a-fA-F]+\s+([wW])\s+(\S+)/) {
$weak{$2} = $1;
@ -290,8 +318,8 @@ sub update_funcs
if (!$opened) {
open(FILE, ">$mcount_s") || die "can't create $mcount_s\n";
$opened = 1;
print FILE "\t.section $mcount_section,\"a\",\@progbits\n";
print FILE "\t.align $alignment\n";
print FILE "\t.section $mcount_section,\"a\",$section_type\n";
print FILE "\t.align $alignment\n" if (defined($alignment));
}
printf FILE "\t%s %s + %d\n", $type, $ref_func, $offsets[$i] - $offset;
}