Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Song Shuai <suagrfillet@gmail.com>
To:     guoren@kernel.org, rostedt@goodmis.org, mhiramat@kernel.org,
        mark.rutland@arm.com, paul.walmsley@sifive.com, palmer@dabbelt.com,
        aou@eecs.berkeley.edu
Cc:     linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org,
        Song Shuai <suagrfillet@gmail.com>
Subject: [PATCH 2/3] riscv/ftrace: SAVE_ALL supports lightweight save
Date:   Tue, 15 Nov 2022 14:15:24 +0800
Message-Id: <20221115061525.112757-3-suagrfillet@gmail.com>
In-Reply-To: <20221115061525.112757-1-suagrfillet@gmail.com>
References: <20221115061525.112757-1-suagrfillet@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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
introduces a lightweight option for SAVE_ALL to save only the necessary
regs for ftrace_caller.

For convenience, the original argument setup for the tracing function in
ftrace_[regs]_caller is killed and appended to the tail of SAVE_ALL.

Signed-off-by: Song Shuai <suagrfillet@gmail.com>
---
 arch/riscv/kernel/mcount-dyn.S | 110 +++++++++++++++++++++++++++------
 1 file changed, 92 insertions(+), 18 deletions(-)

diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index d171eca623b6..2f0a280bd7a0 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -56,7 +56,51 @@
 	.endm
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-	.macro SAVE_ALL
+
+/**
+* SAVE_ALL - 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.
+*
+* For convenience the argument setup for tracing function is appended here.
+* Especially $sp is passed as the 4th argument of the tracing function.
+*
+* 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.
+*
+*
+*			=========
+*			|  pip  |
+* 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 of the traced function
+*			+++++++++
+**/
+	.macro SAVE_ALL, all=0
 	addi	sp, sp, -SZREG
 	addi	sp, sp, -PT_SIZE_ON_STACK
 
@@ -67,14 +111,8 @@
 	REG_S x1,  PT_RA(sp)
 	REG_L x1,  PT_EPC(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)
@@ -83,6 +121,18 @@
 	REG_S x15, PT_A5(sp)
 	REG_S x16, PT_A6(sp)
 	REG_S x17, PT_A7(sp)
+
+	/* save leftover regs for ftrace_regs_caller*/
+
+	.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)
@@ -97,22 +147,31 @@
 	REG_S x29, PT_T4(sp)
 	REG_S x30, PT_T5(sp)
 	REG_S x31, PT_T6(sp)
+	.else
+
+	/* save s0 for ftrace_caller if FP_TEST defined */
+
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	REG_S x8,  PT_S0(sp)
+#endif
+	.endif
+
+	/* setup 4 args for tracing functions  */
+
+	addi	a0, ra, -FENTRY_RA_OFFSET // ip
+	la	a1, function_trace_op
+	REG_L	a2, 0(a1)		// op
+	REG_L	a1, PT_SIZE_ON_STACK(sp) // parent_ip
+	mv	a3, sp			// fregs
 	.endm
 
-	.macro RESTORE_ALL
+	.macro RESTORE_ALL, all=0
 	REG_L x1,  PT_RA(sp)
 	addi	sp, sp, PT_SIZE_ON_STACK
 	REG_S x1,  (sp)
 	addi	sp, sp, -PT_SIZE_ON_STACK
 	REG_L x1,  PT_EPC(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)
@@ -121,6 +180,16 @@
 	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)
@@ -136,6 +205,11 @@
 	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
 	addi	sp, sp, SZREG
 	.endm
-- 
2.20.1