diff mbox series

[V9,2/4] riscv: ftrace: Add ftrace_graph_func

Message ID 20230510101857.2953955-3-suagrfillet@gmail.com (mailing list archive)
State Superseded
Delegated to: Palmer Dabbelt
Headers show
Series riscv: Optimize function trace | expand

Checks

Context Check Description
conchuod/cover_letter success Series has a cover letter
conchuod/tree_selection success Guessed tree name to be for-next at HEAD ac9a78681b92
conchuod/fixes_present success Fixes tag not required for -next series
conchuod/maintainers_pattern success MAINTAINERS pattern errors before the patch: 6 and now 6
conchuod/verify_signedoff success Signed-off-by tag matches author and committer
conchuod/kdoc success Errors and warnings before: 0 this patch: 0
conchuod/build_rv64_clang_allmodconfig success Errors and warnings before: 269 this patch: 269
conchuod/module_param success Was 0 now: 0
conchuod/build_rv64_gcc_allmodconfig success Errors and warnings before: 5107 this patch: 5107
conchuod/build_rv32_defconfig success Build OK
conchuod/dtb_warn_rv64 success Errors and warnings before: 3 this patch: 3
conchuod/header_inline success No static functions without inline keyword in header files
conchuod/checkpatch success total: 0 errors, 0 warnings, 0 checks, 266 lines checked
conchuod/build_rv64_nommu_k210_defconfig success Build OK
conchuod/verify_fixes success No Fixes tag
conchuod/build_rv64_nommu_virt_defconfig success Build OK

Commit Message

Song Shuai May 10, 2023, 10:18 a.m. UTC 
Here implements ftrace_graph_func as the function graph tracing function
with FTRACE_WITH_REGS defined.

function_graph_func gets the point of the parent IP and the frame pointer
from fregs and call prepare_ftrace_return for function graph tracing.

If FTRACE_WITH_REGS isn't defined, the enable/disable helpers of
ftrace_graph_[regs]_call are revised for serving only ftrace_graph_call
in the !FTRACE_WITH_REGS version ftrace_caller.

Signed-off-by: Song Shuai <suagrfillet@gmail.com>
Tested-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Guo Ren <guoren@kernel.org>
---
 arch/riscv/include/asm/ftrace.h |  11 ++-
 arch/riscv/kernel/ftrace.c      |  30 +++---
 arch/riscv/kernel/mcount-dyn.S  | 166 +++++++++++++++++++++++++++-----
 3 files changed, 163 insertions(+), 44 deletions(-)

Comments

Björn Töpel May 11, 2023, 7:08 a.m. UTC | #1 
Song Shuai <suagrfillet@gmail.com> writes:

> Here implements ftrace_graph_func as the function graph tracing function
> with FTRACE_WITH_REGS defined.
>
> function_graph_func gets the point of the parent IP and the frame pointer
> from fregs and call prepare_ftrace_return for function graph tracing.
>
> If FTRACE_WITH_REGS isn't defined, the enable/disable helpers of
> ftrace_graph_[regs]_call are revised for serving only ftrace_graph_call
> in the !FTRACE_WITH_REGS version ftrace_caller.
>
> Signed-off-by: Song Shuai <suagrfillet@gmail.com>
> Tested-by: Guo Ren <guoren@kernel.org>
> Signed-off-by: Guo Ren <guoren@kernel.org>

[...]

> +
> +	// always save the ABI regs
> +
> +	REG_S x10, PT_A0(sp)
> +	REG_S x11, PT_A1(sp)
> +	REG_S x12, PT_A2(sp)
> +	REG_S x13, PT_A3(sp)
> +	REG_S x14, PT_A4(sp)
> +	REG_S x15, PT_A5(sp)
> +	REG_S x16, PT_A6(sp)
> +	REG_S x17, PT_A7(sp)

Really a nit/more general comment; the RISC-V assembly files is a bit
all over the place in terms of style; When doing changes, try to
prettify it with proper tabs, and maybe we'll have eventual
consistency. ;-)

No tabs ^^^...

> +
> +	// save the leftover regs
> +
> +	.if \all == 1
>  	REG_S x2,  PT_SP(sp)
>  	REG_S x3,  PT_GP(sp)
>  	REG_S x4,  PT_TP(sp)
>  	REG_S x5,  PT_T0(sp)
> -	save_from_x6_to_x31
> +	REG_S x6,  PT_T1(sp)
> +	REG_S x7,  PT_T2(sp)
> +	REG_S x8,  PT_S0(sp)
> +	REG_S x9,  PT_S1(sp)
> +	REG_S x18, PT_S2(sp)
> +	REG_S x19, PT_S3(sp)
> +	REG_S x20, PT_S4(sp)
> +	REG_S x21, PT_S5(sp)
> +	REG_S x22, PT_S6(sp)
> +	REG_S x23, PT_S7(sp)
> +	REG_S x24, PT_S8(sp)
> +	REG_S x25, PT_S9(sp)
> +	REG_S x26, PT_S10(sp)
> +	REG_S x27, PT_S11(sp)
> +	REG_S x28, PT_T3(sp)
> +	REG_S x29, PT_T4(sp)
> +	REG_S x30, PT_T5(sp)
> +	REG_S x31, PT_T6(sp)
> +
> +	// save s0 if FP_TEST defined
> +
> +	.else
> +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
> +	REG_S x8,  PT_S0(sp)
> +#endif
> +	.endif
>  	.endm
>  
> -	.macro RESTORE_ALL
> +	.macro RESTORE_ABI_REGS, all=0
> +	REG_L t0,  PT_EPC(sp)
>  	REG_L x1,  PT_RA(sp)
> +	REG_L x10, PT_A0(sp)
> +	REG_L x11, PT_A1(sp)
> +	REG_L x12, PT_A2(sp)
> +	REG_L x13, PT_A3(sp)
> +	REG_L x14, PT_A4(sp)
> +	REG_L x15, PT_A5(sp)
> +	REG_L x16, PT_A6(sp)
> +	REG_L x17, PT_A7(sp)
> +
> +	.if \all == 1
>  	REG_L x2,  PT_SP(sp)
>  	REG_L x3,  PT_GP(sp)
>  	REG_L x4,  PT_TP(sp)
> -	/* Restore t0 with PT_EPC */
> -	REG_L x5,  PT_EPC(sp)
> -	restore_from_x6_to_x31
> +	REG_L x6,  PT_T1(sp)
> +	REG_L x7,  PT_T2(sp)
> +	REG_L x8,  PT_S0(sp)
> +	REG_L x9,  PT_S1(sp)
> +	REG_L x18, PT_S2(sp)
> +	REG_L x19, PT_S3(sp)
> +	REG_L x20, PT_S4(sp)
> +	REG_L x21, PT_S5(sp)
> +	REG_L x22, PT_S6(sp)
> +	REG_L x23, PT_S7(sp)
> +	REG_L x24, PT_S8(sp)
> +	REG_L x25, PT_S9(sp)
> +	REG_L x26, PT_S10(sp)
> +	REG_L x27, PT_S11(sp)
> +	REG_L x28, PT_T3(sp)
> +	REG_L x29, PT_T4(sp)
> +	REG_L x30, PT_T5(sp)
> +	REG_L x31, PT_T6(sp)
>  
> +	.else
> +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
> +	REG_L x8,  PT_S0(sp)
> +#endif
> +	.endif
>  	addi	sp, sp, PT_SIZE_ON_STACK
>  	.endm
> +
> +	.macro PREPARE_ARGS
> +	addi	a0, t0, -FENTRY_RA_OFFSET	// ip
> +	la	a1, function_trace_op
> +	REG_L	a2, 0(a1)			// op
> +	mv	a1, ra				// parent_ip
> +	mv	a3, sp				// fregs
> +	.endm

...but here...

> +
>  #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
>  
> +#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
>  ENTRY(ftrace_caller)
>  	SAVE_ABI
>  
> @@ -110,33 +229,28 @@ ftrace_graph_call:
>  	jr t0
>  ENDPROC(ftrace_caller)
>  
> -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
> +#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
>  ENTRY(ftrace_regs_caller)
> -	SAVE_ALL
> -
> -	addi	a0, t0, -FENTRY_RA_OFFSET
> -	la	a1, function_trace_op
> -	REG_L	a2, 0(a1)
> -	mv	a1, ra
> -	mv	a3, sp
> +	SAVE_ABI_REGS 1
> +	PREPARE_ARGS
>  
>  ftrace_regs_call:
>  	.global ftrace_regs_call
>  	call	ftrace_stub
>  
> -#ifdef CONFIG_FUNCTION_GRAPH_TRACER
> -	addi	a0, sp, PT_RA
> -	REG_L	a1, PT_EPC(sp)
> -	addi	a1, a1, -FENTRY_RA_OFFSET
> -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
> -	mv	a2, s0
> -#endif
> -ftrace_graph_regs_call:
> -	.global ftrace_graph_regs_call
> +	RESTORE_ABI_REGS 1
> +	jr t0

...and not here.

Not a biggie! Nice cleanup!

Acked-by: Björn Töpel <bjorn@rivosinc.com>
diff mbox series

Patch

diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index d47d87c2d7e3..84f856a3286e 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -107,7 +107,16 @@  do {									\
 struct dyn_ftrace;
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
 #define ftrace_init_nop ftrace_init_nop
-#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+struct ftrace_ops;
+struct ftrace_regs;
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs);
+#define ftrace_graph_func ftrace_graph_func
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+#endif /* __ASSEMBLY__ */
 
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 03a6434a8cdd..f5aa24d9e1c1 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -178,32 +178,28 @@  void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+	struct pt_regs *regs = arch_ftrace_get_regs(fregs);
+	unsigned long *parent = (unsigned long *)&regs->ra;
+
+	prepare_ftrace_return(parent, ip, frame_pointer(regs));
+}
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 extern void ftrace_graph_call(void);
-extern void ftrace_graph_regs_call(void);
 int ftrace_enable_ftrace_graph_caller(void)
 {
-	int ret;
-
-	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
-				    (unsigned long)&prepare_ftrace_return, true, true);
-	if (ret)
-		return ret;
-
-	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
 				    (unsigned long)&prepare_ftrace_return, true, true);
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
-	int ret;
-
-	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
-				    (unsigned long)&prepare_ftrace_return, false, true);
-	if (ret)
-		return ret;
-
-	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
 				    (unsigned long)&prepare_ftrace_return, false, true);
 }
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index 669b8697aa38..f26e9f6e2fed 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -57,31 +57,150 @@ 
 	.endm
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-	.macro SAVE_ALL
+
+/**
+* SAVE_ABI_REGS - save regs against the pt_regs struct
+*
+* @all: tell if saving all the regs
+*
+* If all is set, all the regs will be saved, otherwise only ABI
+* related regs (a0-a7,epc,ra and optional s0) will be saved.
+*
+* After the stack is established,
+*
+* 0(sp) stores the PC of the traced function which can be accessed
+* by &(fregs)->regs->epc in tracing function. Note that the real
+* function entry address should be computed with -FENTRY_RA_OFFSET.
+*
+* 8(sp) stores the function return address (i.e. parent IP) that
+* can be accessed by &(fregs)->regs->ra in tracing function.
+*
+* The other regs are saved at the respective localtion and accessed
+* by the respective pt_regs member.
+*
+* Here is the layout of stack for your reference.
+*
+* PT_SIZE_ON_STACK  ->  +++++++++
+*                       + ..... +
+*                       + t3-t6 +
+*                       + s2-s11+
+*                       + a0-a7 + --++++-> ftrace_caller saved
+*                       + s1    +   +
+*                       + s0    + --+
+*                       + t0-t2 +   +
+*                       + tp    +   +
+*                       + gp    +   +
+*                       + sp    +   +
+*                       + ra    + --+ // parent IP
+*               sp  ->  + epc   + --+ // PC
+*                       +++++++++
+**/
+	.macro SAVE_ABI_REGS, all=0
 	addi	sp, sp, -PT_SIZE_ON_STACK
 
 	REG_S t0,  PT_EPC(sp)
 	REG_S x1,  PT_RA(sp)
+
+	// always save the ABI regs
+
+	REG_S x10, PT_A0(sp)
+	REG_S x11, PT_A1(sp)
+	REG_S x12, PT_A2(sp)
+	REG_S x13, PT_A3(sp)
+	REG_S x14, PT_A4(sp)
+	REG_S x15, PT_A5(sp)
+	REG_S x16, PT_A6(sp)
+	REG_S x17, PT_A7(sp)
+
+	// save the leftover regs
+
+	.if \all == 1
 	REG_S x2,  PT_SP(sp)
 	REG_S x3,  PT_GP(sp)
 	REG_S x4,  PT_TP(sp)
 	REG_S x5,  PT_T0(sp)
-	save_from_x6_to_x31
+	REG_S x6,  PT_T1(sp)
+	REG_S x7,  PT_T2(sp)
+	REG_S x8,  PT_S0(sp)
+	REG_S x9,  PT_S1(sp)
+	REG_S x18, PT_S2(sp)
+	REG_S x19, PT_S3(sp)
+	REG_S x20, PT_S4(sp)
+	REG_S x21, PT_S5(sp)
+	REG_S x22, PT_S6(sp)
+	REG_S x23, PT_S7(sp)
+	REG_S x24, PT_S8(sp)
+	REG_S x25, PT_S9(sp)
+	REG_S x26, PT_S10(sp)
+	REG_S x27, PT_S11(sp)
+	REG_S x28, PT_T3(sp)
+	REG_S x29, PT_T4(sp)
+	REG_S x30, PT_T5(sp)
+	REG_S x31, PT_T6(sp)
+
+	// save s0 if FP_TEST defined
+
+	.else
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	REG_S x8,  PT_S0(sp)
+#endif
+	.endif
 	.endm
 
-	.macro RESTORE_ALL
+	.macro RESTORE_ABI_REGS, all=0
+	REG_L t0,  PT_EPC(sp)
 	REG_L x1,  PT_RA(sp)
+	REG_L x10, PT_A0(sp)
+	REG_L x11, PT_A1(sp)
+	REG_L x12, PT_A2(sp)
+	REG_L x13, PT_A3(sp)
+	REG_L x14, PT_A4(sp)
+	REG_L x15, PT_A5(sp)
+	REG_L x16, PT_A6(sp)
+	REG_L x17, PT_A7(sp)
+
+	.if \all == 1
 	REG_L x2,  PT_SP(sp)
 	REG_L x3,  PT_GP(sp)
 	REG_L x4,  PT_TP(sp)
-	/* Restore t0 with PT_EPC */
-	REG_L x5,  PT_EPC(sp)
-	restore_from_x6_to_x31
+	REG_L x6,  PT_T1(sp)
+	REG_L x7,  PT_T2(sp)
+	REG_L x8,  PT_S0(sp)
+	REG_L x9,  PT_S1(sp)
+	REG_L x18, PT_S2(sp)
+	REG_L x19, PT_S3(sp)
+	REG_L x20, PT_S4(sp)
+	REG_L x21, PT_S5(sp)
+	REG_L x22, PT_S6(sp)
+	REG_L x23, PT_S7(sp)
+	REG_L x24, PT_S8(sp)
+	REG_L x25, PT_S9(sp)
+	REG_L x26, PT_S10(sp)
+	REG_L x27, PT_S11(sp)
+	REG_L x28, PT_T3(sp)
+	REG_L x29, PT_T4(sp)
+	REG_L x30, PT_T5(sp)
+	REG_L x31, PT_T6(sp)
 
+	.else
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	REG_L x8,  PT_S0(sp)
+#endif
+	.endif
 	addi	sp, sp, PT_SIZE_ON_STACK
 	.endm
+
+	.macro PREPARE_ARGS
+	addi	a0, t0, -FENTRY_RA_OFFSET	// ip
+	la	a1, function_trace_op
+	REG_L	a2, 0(a1)			// op
+	mv	a1, ra				// parent_ip
+	mv	a3, sp				// fregs
+	.endm
+
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
+#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 ENTRY(ftrace_caller)
 	SAVE_ABI
 
@@ -110,33 +229,28 @@  ftrace_graph_call:
 	jr t0
 ENDPROC(ftrace_caller)
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 ENTRY(ftrace_regs_caller)
-	SAVE_ALL
-
-	addi	a0, t0, -FENTRY_RA_OFFSET
-	la	a1, function_trace_op
-	REG_L	a2, 0(a1)
-	mv	a1, ra
-	mv	a3, sp
+	SAVE_ABI_REGS 1
+	PREPARE_ARGS
 
 ftrace_regs_call:
 	.global ftrace_regs_call
 	call	ftrace_stub
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	addi	a0, sp, PT_RA
-	REG_L	a1, PT_EPC(sp)
-	addi	a1, a1, -FENTRY_RA_OFFSET
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	mv	a2, s0
-#endif
-ftrace_graph_regs_call:
-	.global ftrace_graph_regs_call
+	RESTORE_ABI_REGS 1
+	jr t0
+ENDPROC(ftrace_regs_caller)
+
+ENTRY(ftrace_caller)
+	SAVE_ABI_REGS 0
+	PREPARE_ARGS
+
+ftrace_call:
+	.global ftrace_call
 	call	ftrace_stub
-#endif
 
-	RESTORE_ALL
+	RESTORE_ABI_REGS 0
 	jr t0
-ENDPROC(ftrace_regs_caller)
+ENDPROC(ftrace_caller)
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */