linux-sg2042/arch/x86/kernel/mcount_64.S

301 lines
6.3 KiB
ArmAsm
Raw Normal View History

/*
* 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
/* Size of stack used to save mcount regs in save_mcount_regs */
#define MCOUNT_REG_SIZE (SS+8)
/*
* gcc -pg option adds a call to 'mcount' in most functions.
* When -mfentry is used, the call is to 'fentry' and not 'mcount'
* and is done before the function's stack frame is set up.
* They both require a set of regs to be saved before calling
* any C code and restored before returning back to the function.
*
* On boot up, all these calls are converted into nops. When tracing
* is enabled, the call can jump to either ftrace_caller or
* ftrace_regs_caller. Callbacks (tracing functions) that require
* ftrace_regs_caller (like kprobes) need to have pt_regs passed to
* it. For this reason, the size of the pt_regs structure will be
* allocated on the stack and the required mcount registers will
* be saved in the locations that pt_regs has them in.
*/
/* @added: the amount of stack added before calling this */
.macro save_mcount_regs added=0
/*
* We add enough stack to save all regs.
*/
subq $MCOUNT_REG_SIZE, %rsp
movq %rax, RAX(%rsp)
movq %rcx, RCX(%rsp)
movq %rdx, RDX(%rsp)
movq %rsi, RSI(%rsp)
movq %rdi, RDI(%rsp)
movq %r8, R8(%rsp)
movq %r9, R9(%rsp)
/* Move RIP to its proper location */
movq MCOUNT_REG_SIZE+\added(%rsp), %rdi
movq %rdi, RIP(%rsp)
.endm
.macro restore_mcount_regs
movq R9(%rsp), %r9
movq R8(%rsp), %r8
movq RDI(%rsp), %rdi
movq RSI(%rsp), %rsi
movq RDX(%rsp), %rdx
movq RCX(%rsp), %rcx
movq RAX(%rsp), %rax
addq $MCOUNT_REG_SIZE, %rsp
.endm
/* skip is set if stack has been adjusted */
.macro ftrace_caller_setup trace_label added=0
save_mcount_regs \added
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>
2014-07-03 11:23:31 +08:00
/* Save this location */
GLOBAL(\trace_label)
/* Load the ftrace_ops into the 3rd parameter */
movq function_trace_op(%rip), %rdx
/* %rdi already has %rip from the save_mcount_regs macro */
subq $MCOUNT_INSN_SIZE, %rdi
/* Load the parent_ip into the second parameter */
#ifdef CC_USING_FENTRY
movq MCOUNT_REG_SIZE+8+\added(%rsp), %rsi
#else
movq 8+\added(%rbp), %rsi
#endif
.endm
#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(function_hook)
retq
END(function_hook)
#ifdef CONFIG_FRAME_POINTER
/*
* Stack traces will stop at the ftrace trampoline if the frame pointer
* is not set up properly. If fentry is used, we need to save a frame
* pointer for the parent as well as the function traced, because the
* fentry is called before the stack frame is set up, where as mcount
* is called afterward.
*/
.macro create_frame parent rip
#ifdef CC_USING_FENTRY
pushq \parent
pushq %rbp
movq %rsp, %rbp
#endif
pushq \rip
pushq %rbp
movq %rsp, %rbp
.endm
.macro restore_frame
#ifdef CC_USING_FENTRY
addq $16, %rsp
#endif
popq %rbp
addq $8, %rsp
.endm
#else
.macro create_frame parent rip
.endm
.macro restore_frame
.endm
#endif /* CONFIG_FRAME_POINTER */
ENTRY(ftrace_caller)
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>
2014-07-03 11:23:31 +08:00
ftrace_caller_setup ftrace_caller_op_ptr
/* regs go into 4th parameter (but make it NULL) */
movq $0, %rcx
create_frame %rsi, %rdi
GLOBAL(ftrace_call)
call ftrace_stub
restore_frame
restore_mcount_regs
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>
2014-07-03 11:23:31 +08:00
/*
* 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 any operations that can change them */
pushfq
/* added 8 bytes to save flags */
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>
2014-07-03 11:23:31 +08:00
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 MCOUNT_REG_SIZE(%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 and flags */
leaq MCOUNT_REG_SIZE+8*2(%rsp), %rcx
movq %rcx, RSP(%rsp)
/* regs go into 4th parameter */
leaq (%rsp), %rcx
create_frame %rsi, %rdi
GLOBAL(ftrace_regs_call)
call ftrace_stub
restore_frame
/* Copy flags back to SS, to restore them */
movq EFLAGS(%rsp), %rax
movq %rax, MCOUNT_REG_SIZE(%rsp)
/* Handlers can change the RIP */
movq RIP(%rsp), %rax
movq %rax, MCOUNT_REG_SIZE+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
restore_mcount_regs
/* Restore flags */
popfq
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>
2014-07-03 11:23:31 +08:00
/*
* 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
END(ftrace_regs_caller)
#else /* ! CONFIG_DYNAMIC_FTRACE */
ENTRY(function_hook)
cmpq $ftrace_stub, ftrace_trace_function
jnz trace
fgraph_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:
ftrace_caller_setup ftrace_caller_op_ptr
call *ftrace_trace_function
restore_mcount_regs
jmp fgraph_trace
END(function_hook)
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_FUNCTION_TRACER */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ENTRY(ftrace_graph_caller)
save_mcount_regs
#ifdef CC_USING_FENTRY
leaq MCOUNT_REG_SIZE+8(%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
restore_mcount_regs
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