[PATCH v4 0/2] riscv/ftrace: make function graph use ftrace directly

[PATCH v4 0/2] riscv/ftrace: make function graph use ftrace directly

[Song Shuai]

In RISC-V architecture, when we enable the ftrace_graph tracer on some
functions, the function tracings on other functions will suffer extra
graph tracing work. In essence, graph_ops isn't limited by its func_hash
due to the global ftrace_graph_[regs]_call label. That should be corrected.

What inspires me is the commit 0c0593b45c9b ("x86/ftrace: Make function
graph use ftrace directly") that uses graph_ops::func function to install
return_hooker and makes the function called against its func_hash.

This series of patches makes function graph use ftrace directly for riscv.

If FTRACE_WITH_REGS isn't defined, ftrace_caller keeps ftrace_graph_call
so that it can be replaced with the calling of prepare_ftrace_return by
the enable/disable helper.

As for defining FTRACE_WITH_REGS, ftrace_caller is adjusted to save the
necessary regs against the pt_regs layout, so it can reasonably call the
graph_ops::func function - ftrace_graph_func. And ftrace_graph_[regs]_call
and its enable/disable helper aren't needed.

The tests generated by CONFIG_FTRACE_STARTUP_TEST have passed in the local
qemu-system-riscv64 virt machine. The following is the log during startup.

```
Nov 15 03:07:13 stage4 kernel: Testing tracer function: PASSED
Nov 15 03:07:13 stage4 kernel: Testing dynamic ftrace: PASSED
Nov 15 03:07:13 stage4 kernel: Testing dynamic ftrace ops #1: 
Nov 15 03:07:13 stage4 kernel: (1 0 1 0 0)  
Nov 15 03:07:13 stage4 kernel: (1 1 2 0 0)  
Nov 15 03:07:13 stage4 kernel: (2 1 3 0 365) 
Nov 15 03:07:13 stage4 kernel: (2 2 4 0 399) 
Nov 15 03:07:13 stage4 kernel: (3 2 4 0 146071) 
Nov 15 03:07:13 stage4 kernel: (3 3 5 0 146105) PASSED
Nov 15 03:07:13 stage4 kernel: Testing dynamic ftrace ops #2: 
Nov 15 03:07:13 stage4 kernel: (1 0 1 589 0)  
Nov 15 03:07:13 stage4 kernel: (1 1 2 635 0)  
Nov 15 03:07:13 stage4 kernel: (2 1 3 1 2)  
Nov 15 03:07:13 stage4 kernel: (2 2 4 125 126) 
Nov 15 03:07:13 stage4 kernel: (3 2 4 146001 146078) 
Nov 15 03:07:13 stage4 kernel: (3 3 5 146035 146112) PASSED
Nov 15 03:07:13 stage4 kernel: Testing ftrace recursion: PASSED
Nov 15 03:07:13 stage4 kernel: Testing ftrace recursion safe: PASSED
Nov 15 03:07:13 stage4 kernel: Testing ftrace regs: PASSED
Nov 15 03:07:13 stage4 kernel: Testing tracer nop: PASSED
Nov 15 03:07:13 stage4 kernel: Testing tracer irqsoff: PASSED
Nov 15 03:07:13 stage4 kernel: Testing tracer wakeup:
Nov 15 03:07:13 stage4 kernel: sched: DL replenish lagged too much
Nov 15 03:07:13 stage4 kernel: PASSED
Nov 15 03:07:13 stage4 kernel: Testing tracer wakeup_rt: PASSED
Nov 15 03:07:13 stage4 kernel: Testing tracer wakeup_dl: PASSED
Nov 15 03:07:13 stage4 kernel: Testing tracer function_graph: PASSED
```

Note that the changes of mcount-dyn.S conflicts with this unmerged
commit (riscv: entry: consolidate general regs saving/restoring).
https://lore.kernel.org/linux-riscv/20221103075047.1634923-15-guoren@kernel.org

Changes since v3:
- separate parameters preparation as PREPARE_ARGS [Guo Ren]
v3 link: https://lore.kernel.org/linux-riscv/20221118173217.888077-1-suagrfillet@gmail.com/

Changes since v2:
- line up the comments [Andrew]
- rename SAVE_ALL as SAVE_ABI_REGS [Guo Ren]
- consolidate the modifications of mcount-dyn.S into one patch [Guo Ren]
- adapt this series based on [riscv: ftrace: Fixup ftrace detour code][1] [Guo Ren]

[1]: https://lore.kernel.org/linux-riscv/20220921034910.3142465-1-guoren@kernel.org/
v2 Link: https://lore.kernel.org/linux-riscv/20221116031305.286634-1-suagrfillet@gmail.com/

Changes since v1:
- fix the checkpatch warnings in patch 1
v1 Link: https://lore.kernel.org/linux-riscv/20221115061525.112757-1-suagrfillet@gmail.com

Song Shuai (2):
  riscv/ftrace: add ftrace_graph_func
  riscv/ftrace: make ftrace_caller call ftrace_graph_func

 arch/riscv/include/asm/ftrace.h |  13 ++-
 arch/riscv/kernel/ftrace.c      |  30 +++----
 arch/riscv/kernel/mcount-dyn.S  | 142 +++++++++++++++++++++++---------
 3 files changed, 128 insertions(+), 57 deletions(-)

-- 
2.20.1

[PATCH v4 1/2] riscv/ftrace: add ftrace_graph_func

[Song Shuai]

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>
---
 arch/riscv/include/asm/ftrace.h | 13 +++++++++++--
 arch/riscv/kernel/ftrace.c      | 30 +++++++++++++-----------------
 2 files changed, 24 insertions(+), 19 deletions(-)

diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 34b0b523865a..01bebb28eabe 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -107,8 +107,17 @@ do {									\
 struct dyn_ftrace;
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
 #define ftrace_init_nop ftrace_init_nop
-#endif
 
-#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 */
 
 #endif /* _ASM_RISCV_FTRACE_H */
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 8c77f236fc71..651ce5808b77 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -169,32 +169,28 @@ 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 */
-- 
2.20.1

[PATCH v4 2/2] riscv/ftrace: make ftrace_caller call ftrace_graph_func

[Song Shuai]

In order to make the function graph use ftrace directly, ftrace_caller
should be adjusted to save the necessary regs against the pt_regs layout
so it can call ftrace_graph_func reasonably.

SAVE_ALL now saves all the regs according to the pt_regs struct. Here
supersedes SAVE_ALL by SAVE_ABI_REGS which has an extra option to allow
saving only the necessary ABI-related regs for ftrace_caller.

ftrace_caller and ftrace_regs_caller save their regs with the respective
option of SAVE_ABI_REGS, then call the tracing function, especially
graph_ops's ftrace_graph_func. So the ftrace_graph_[regs]_call labels
aren't needed anymore if FTRACE_WITH_REGS is defined.

As the previous patch described, the ftrace_caller remains with its
ftrace_graph_call if FTRACE_WITH_REGS isn't defined,

For convenience, the original argument setup for the tracing function in
ftrace_[regs]_caller is separated as PREPARE_ARGS.

Signed-off-by: Song Shuai <suagrfillet@gmail.com>
---
 arch/riscv/kernel/mcount-dyn.S | 142 ++++++++++++++++++++++++---------
 1 file changed, 104 insertions(+), 38 deletions(-)

diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index 64bc79816f5e..466c6ef217b1 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -57,19 +57,52 @@
 	.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)
-	REG_S x2,  PT_SP(sp)
-	REG_S x3,  PT_GP(sp)
-	REG_S x4,  PT_TP(sp)
-	REG_S x5,  PT_T0(sp)
-	REG_S x6,  PT_T1(sp)
-	REG_S x7,  PT_T2(sp)
-	REG_S x8,  PT_S0(sp)
-	REG_S x9,  PT_S1(sp)
+
+	// always save the ABI regs
+
 	REG_S x10, PT_A0(sp)
 	REG_S x11, PT_A1(sp)
 	REG_S x12, PT_A2(sp)
@@ -78,6 +111,18 @@
 	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)
+	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)
@@ -92,19 +137,19 @@
 	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 x2,  PT_SP(sp)
-	REG_L x3,  PT_GP(sp)
-	REG_L x4,  PT_TP(sp)
-	REG_L x5,  PT_T0(sp)
-	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 x10, PT_A0(sp)
 	REG_L x11, PT_A1(sp)
 	REG_L x12, PT_A2(sp)
@@ -113,6 +158,16 @@
 	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)
+	REG_L x5,  PT_T0(sp)
+	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)
@@ -128,10 +183,25 @@
 	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
+	REG_L	a1, PT_RA(sp)			// parent_ip
+	mv	a3, sp				// fregs
+	.endm
+
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
+#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 ENTRY(ftrace_caller)
 	SAVE_ABI
 
@@ -160,33 +230,29 @@ 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)
-	REG_L	a1, PT_RA(sp)
-	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_T0(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
-	call	ftrace_stub
-#endif
 
-	RESTORE_ALL
+	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
+
+	RESTORE_ABI_REGS 0
+	jr t0
+ENDPROC(ftrace_caller)
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
-- 
2.20.1