linux/arch/x86/kernel/mcount_64.S
Steven Rostedt (Red Hat) 79922b8009 ftrace: Optimize function graph to be called directly
Function graph tracing is a bit different than the function tracers, as
it is processed after either the ftrace_caller or ftrace_regs_caller
and we only have one place to modify the jump to ftrace_graph_caller,
the jump needs to happen after the restore of registeres.

The function graph tracer is dependent on the function tracer, where
even if the function graph tracing is going on by itself, the save and
restore of registers is still done for function tracing regardless of
if function tracing is happening, before it calls the function graph
code.

If there's no function tracing happening, it is possible to just call
the function graph tracer directly, and avoid the wasted effort to save
and restore regs for function tracing.

This requires adding new flags to the dyn_ftrace records:

  FTRACE_FL_TRAMP
  FTRACE_FL_TRAMP_EN

The first is set if the count for the record is one, and the ftrace_ops
associated to that record has its own trampoline. That way the mcount code
can call that trampoline directly.

In the future, trampolines can be added to arbitrary ftrace_ops, where you
can have two or more ftrace_ops registered to ftrace (like kprobes and perf)
and if they are not tracing the same functions, then instead of doing a
loop to check all registered ftrace_ops against their hashes, just call the
ftrace_ops trampoline directly, which would call the registered ftrace_ops
function directly.

Without this patch perf showed:

  0.05%  hackbench  [kernel.kallsyms]  [k] ftrace_caller
  0.05%  hackbench  [kernel.kallsyms]  [k] arch_local_irq_save
  0.05%  hackbench  [kernel.kallsyms]  [k] native_sched_clock
  0.04%  hackbench  [kernel.kallsyms]  [k] __buffer_unlock_commit
  0.04%  hackbench  [kernel.kallsyms]  [k] preempt_trace
  0.04%  hackbench  [kernel.kallsyms]  [k] prepare_ftrace_return
  0.04%  hackbench  [kernel.kallsyms]  [k] __this_cpu_preempt_check
  0.04%  hackbench  [kernel.kallsyms]  [k] ftrace_graph_caller

See that the ftrace_caller took up more time than the ftrace_graph_caller
did.

With this patch:

  0.05%  hackbench  [kernel.kallsyms]  [k] __buffer_unlock_commit
  0.04%  hackbench  [kernel.kallsyms]  [k] call_filter_check_discard
  0.04%  hackbench  [kernel.kallsyms]  [k] ftrace_graph_caller
  0.04%  hackbench  [kernel.kallsyms]  [k] sched_clock

The ftrace_caller is no where to be found and ftrace_graph_caller still
takes up the same percentage.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-07-01 07:13:31 -04:00

223 lines
4.0 KiB
ArmAsm

/*
* linux/arch/x86_64/mcount_64.S
*
* Copyright (C) 2014 Steven Rostedt, Red Hat Inc
*/
#include <linux/linkage.h>
#include <asm/ptrace.h>
#include <asm/ftrace.h>
.code64
.section .entry.text, "ax"
#ifdef CONFIG_FUNCTION_TRACER
#ifdef CC_USING_FENTRY
# define function_hook __fentry__
#else
# define function_hook mcount
#endif
#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(function_hook)
retq
END(function_hook)
/* skip is set if stack has been adjusted */
.macro ftrace_caller_setup skip=0
MCOUNT_SAVE_FRAME \skip
/* Load the ftrace_ops into the 3rd parameter */
movq function_trace_op(%rip), %rdx
/* Load ip into the first parameter */
movq RIP(%rsp), %rdi
subq $MCOUNT_INSN_SIZE, %rdi
/* Load the parent_ip into the second parameter */
#ifdef CC_USING_FENTRY
movq SS+16(%rsp), %rsi
#else
movq 8(%rbp), %rsi
#endif
.endm
ENTRY(ftrace_caller)
/* Check if tracing was disabled (quick check) */
cmpl $0, function_trace_stop
jne ftrace_stub
ftrace_caller_setup
/* regs go into 4th parameter (but make it NULL) */
movq $0, %rcx
GLOBAL(ftrace_call)
call ftrace_stub
MCOUNT_RESTORE_FRAME
ftrace_return:
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
GLOBAL(ftrace_graph_call)
jmp ftrace_stub
#endif
GLOBAL(ftrace_stub)
retq
END(ftrace_caller)
ENTRY(ftrace_regs_caller)
/* Save the current flags before compare (in SS location)*/
pushfq
/* Check if tracing was disabled (quick check) */
cmpl $0, function_trace_stop
jne ftrace_restore_flags
/* skip=8 to skip flags saved in SS */
ftrace_caller_setup 8
/* Save the rest of pt_regs */
movq %r15, R15(%rsp)
movq %r14, R14(%rsp)
movq %r13, R13(%rsp)
movq %r12, R12(%rsp)
movq %r11, R11(%rsp)
movq %r10, R10(%rsp)
movq %rbp, RBP(%rsp)
movq %rbx, RBX(%rsp)
/* Copy saved flags */
movq SS(%rsp), %rcx
movq %rcx, EFLAGS(%rsp)
/* Kernel segments */
movq $__KERNEL_DS, %rcx
movq %rcx, SS(%rsp)
movq $__KERNEL_CS, %rcx
movq %rcx, CS(%rsp)
/* Stack - skipping return address */
leaq SS+16(%rsp), %rcx
movq %rcx, RSP(%rsp)
/* regs go into 4th parameter */
leaq (%rsp), %rcx
GLOBAL(ftrace_regs_call)
call ftrace_stub
/* Copy flags back to SS, to restore them */
movq EFLAGS(%rsp), %rax
movq %rax, SS(%rsp)
/* Handlers can change the RIP */
movq RIP(%rsp), %rax
movq %rax, SS+8(%rsp)
/* restore the rest of pt_regs */
movq R15(%rsp), %r15
movq R14(%rsp), %r14
movq R13(%rsp), %r13
movq R12(%rsp), %r12
movq R10(%rsp), %r10
movq RBP(%rsp), %rbp
movq RBX(%rsp), %rbx
/* skip=8 to skip flags saved in SS */
MCOUNT_RESTORE_FRAME 8
/* Restore flags */
popfq
jmp ftrace_return
ftrace_restore_flags:
popfq
jmp ftrace_stub
END(ftrace_regs_caller)
#else /* ! CONFIG_DYNAMIC_FTRACE */
ENTRY(function_hook)
cmpl $0, function_trace_stop
jne ftrace_stub
cmpq $ftrace_stub, ftrace_trace_function
jnz trace
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
cmpq $ftrace_stub, ftrace_graph_return
jnz ftrace_graph_caller
cmpq $ftrace_graph_entry_stub, ftrace_graph_entry
jnz ftrace_graph_caller
#endif
GLOBAL(ftrace_stub)
retq
trace:
MCOUNT_SAVE_FRAME
movq RIP(%rsp), %rdi
#ifdef CC_USING_FENTRY
movq SS+16(%rsp), %rsi
#else
movq 8(%rbp), %rsi
#endif
subq $MCOUNT_INSN_SIZE, %rdi
call *ftrace_trace_function
MCOUNT_RESTORE_FRAME
jmp ftrace_stub
END(function_hook)
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_FUNCTION_TRACER */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ENTRY(ftrace_graph_caller)
MCOUNT_SAVE_FRAME
/* Check if tracing was disabled (quick check) */
cmpl $0, function_trace_stop
jne fgraph_skip
#ifdef CC_USING_FENTRY
leaq SS+16(%rsp), %rdi
movq $0, %rdx /* No framepointers needed */
#else
leaq 8(%rbp), %rdi
movq (%rbp), %rdx
#endif
movq RIP(%rsp), %rsi
subq $MCOUNT_INSN_SIZE, %rsi
call prepare_ftrace_return
fgraph_skip:
MCOUNT_RESTORE_FRAME
retq
END(ftrace_graph_caller)
GLOBAL(return_to_handler)
subq $24, %rsp
/* Save the return values */
movq %rax, (%rsp)
movq %rdx, 8(%rsp)
movq %rbp, %rdi
call ftrace_return_to_handler
movq %rax, %rdi
movq 8(%rsp), %rdx
movq (%rsp), %rax
addq $24, %rsp
jmp *%rdi
#endif