linux/arch/x86/kernel/mcount_64.S
Steven Rostedt (Red Hat) f3bea49115 ftrace/x86: Add dynamic allocated trampoline for ftrace_ops
The current method of handling multiple function callbacks is to register
a list function callback that calls all the other callbacks based on
their hash tables and compare it to the function that the callback was
called on. But this is very inefficient.

For example, if you are tracing all functions in the kernel and then
add a kprobe to a function such that the kprobe uses ftrace, the
mcount trampoline will switch from calling the function trace callback
to calling the list callback that will iterate over all registered
ftrace_ops (in this case, the function tracer and the kprobes callback).
That means for every function being traced it checks the hash of the
ftrace_ops for function tracing and kprobes, even though the kprobes
is only set at a single function. The kprobes ftrace_ops is checked
for every function being traced!

Instead of calling the list function for functions that are only being
traced by a single callback, we can call a dynamically allocated
trampoline that calls the callback directly. The function graph tracer
already uses a direct call trampoline when it is being traced by itself
but it is not dynamically allocated. It's trampoline is static in the
kernel core. The infrastructure that called the function graph trampoline
can also be used to call a dynamically allocated one.

For now, only ftrace_ops that are not dynamically allocated can have
a trampoline. That is, users such as function tracer or stack tracer.
kprobes and perf allocate their ftrace_ops, and until there's a safe
way to free the trampoline, it can not be used. The dynamically allocated
ftrace_ops may, although, use the trampoline if the kernel is not
compiled with CONFIG_PREEMPT. But that will come later.

Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-10-31 12:22:35 -04:00

224 lines
4.1 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 trace_label skip=0
MCOUNT_SAVE_FRAME \skip
/* Save this location */
GLOBAL(\trace_label)
/* 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)
ftrace_caller_setup ftrace_caller_op_ptr
/* regs go into 4th parameter (but make it NULL) */
movq $0, %rcx
GLOBAL(ftrace_call)
call ftrace_stub
MCOUNT_RESTORE_FRAME
/*
* The copied trampoline must call ftrace_return as it
* still may need to call the function graph tracer.
*/
GLOBAL(ftrace_caller_end)
GLOBAL(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
/* skip=8 to skip flags saved in SS */
ftrace_caller_setup ftrace_regs_caller_op_ptr 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
/*
* As this jmp to ftrace_return can be a short jump
* it must not be copied into the trampoline.
* The trampoline will add the code to jump
* to the return.
*/
GLOBAL(ftrace_regs_caller_end)
jmp ftrace_return
popfq
jmp ftrace_stub
END(ftrace_regs_caller)
#else /* ! CONFIG_DYNAMIC_FTRACE */
ENTRY(function_hook)
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
#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
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