diff options
Diffstat (limited to 'arch/riscv/kernel/mcount-dyn.S')
| -rw-r--r-- | arch/riscv/kernel/mcount-dyn.S | 373 |
1 files changed, 172 insertions, 201 deletions
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S index 35a6ed76cb8b..48f6c4f7dca0 100644 --- a/arch/riscv/kernel/mcount-dyn.S +++ b/arch/riscv/kernel/mcount-dyn.S @@ -3,237 +3,208 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <linux/export.h> #include <asm/asm.h> #include <asm/csr.h> #include <asm/unistd.h> #include <asm/thread_info.h> #include <asm/asm-offsets.h> -#include <asm-generic/export.h> #include <asm/ftrace.h> .text - .macro SAVE_ABI_STATE -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - addi sp, sp, -48 - sd s0, 32(sp) - sd ra, 40(sp) - addi s0, sp, 48 - sd t0, 24(sp) - sd t1, 16(sp) -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - sd t2, 8(sp) -#endif -#else - addi sp, sp, -16 - sd s0, 0(sp) - sd ra, 8(sp) - addi s0, sp, 16 -#endif +#define ABI_SIZE_ON_STACK 80 +#define ABI_A0 0 +#define ABI_A1 8 +#define ABI_A2 16 +#define ABI_A3 24 +#define ABI_A4 32 +#define ABI_A5 40 +#define ABI_A6 48 +#define ABI_A7 56 +#define ABI_T0 64 +#define ABI_RA 72 + + .macro SAVE_ABI + addi sp, sp, -ABI_SIZE_ON_STACK + + REG_S a0, ABI_A0(sp) + REG_S a1, ABI_A1(sp) + REG_S a2, ABI_A2(sp) + REG_S a3, ABI_A3(sp) + REG_S a4, ABI_A4(sp) + REG_S a5, ABI_A5(sp) + REG_S a6, ABI_A6(sp) + REG_S a7, ABI_A7(sp) + REG_S t0, ABI_T0(sp) + REG_S ra, ABI_RA(sp) .endm - .macro RESTORE_ABI_STATE -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - ld s0, 32(sp) - ld ra, 40(sp) - addi sp, sp, 48 -#else - ld ra, 8(sp) - ld s0, 0(sp) - addi sp, sp, 16 -#endif + .macro RESTORE_ABI + REG_L a0, ABI_A0(sp) + REG_L a1, ABI_A1(sp) + REG_L a2, ABI_A2(sp) + REG_L a3, ABI_A3(sp) + REG_L a4, ABI_A4(sp) + REG_L a5, ABI_A5(sp) + REG_L a6, ABI_A6(sp) + REG_L a7, ABI_A7(sp) + REG_L t0, ABI_T0(sp) + REG_L ra, ABI_RA(sp) + + addi sp, sp, ABI_SIZE_ON_STACK .endm - .macro RESTORE_GRAPH_ARGS - ld a0, 24(sp) - ld a1, 16(sp) +/** +* SAVE_ABI_REGS - save regs against the ftrace_regs struct +* +* After the stack is established, +* +* 0(sp) stores the PC of the traced function which can be accessed +* by &(fregs)->epc in tracing function. +* +* 8(sp) stores the function return address (i.e. parent IP) that +* can be accessed by &(fregs)->ra in tracing function. +* +* The other regs are saved at the respective localtion and accessed +* by the respective ftrace_regs member. +* +* Here is the layout of stack for your reference. +* +* PT_SIZE_ON_STACK -> +++++++++ +* + ..... + +* + a0-a7 + --++++-> ftrace_caller saved +* + t1 + --++++-> direct tramp address +* + s0 + --+ // frame pointer +* + sp + + +* + ra + --+ // parent IP +* sp -> + epc + --+ // PC +* +++++++++ +**/ + .macro SAVE_ABI_REGS + addi sp, sp, -FREGS_SIZE_ON_STACK + REG_S t0, FREGS_EPC(sp) + REG_S x1, FREGS_RA(sp) #ifdef HAVE_FUNCTION_GRAPH_FP_TEST - ld a2, 8(sp) + REG_S x8, FREGS_S0(sp) +#endif + REG_S x6, FREGS_T1(sp) +#ifdef CONFIG_CC_IS_CLANG + REG_S x7, FREGS_T2(sp) + REG_S x28, FREGS_T3(sp) + REG_S x29, FREGS_T4(sp) + REG_S x30, FREGS_T5(sp) + REG_S x31, FREGS_T6(sp) #endif + // save the arguments + REG_S x10, FREGS_A0(sp) + REG_S x11, FREGS_A1(sp) + REG_S x12, FREGS_A2(sp) + REG_S x13, FREGS_A3(sp) + REG_S x14, FREGS_A4(sp) + REG_S x15, FREGS_A5(sp) + REG_S x16, FREGS_A6(sp) + REG_S x17, FREGS_A7(sp) + mv a0, sp + addi a0, a0, FREGS_SIZE_ON_STACK + REG_S a0, FREGS_SP(sp) // Put original SP on stack .endm -ENTRY(ftrace_graph_caller) - addi sp, sp, -16 - sd s0, 0(sp) - sd ra, 8(sp) - addi s0, sp, 16 -ftrace_graph_call: - .global ftrace_graph_call - /* - * Calling ftrace_enable/disable_ftrace_graph_caller would overwrite the - * call below. Check ftrace_modify_all_code for details. - */ - call ftrace_stub - ld ra, 8(sp) - ld s0, 0(sp) - addi sp, sp, 16 - ret -ENDPROC(ftrace_graph_caller) - -ENTRY(ftrace_caller) - /* - * a0: the address in the caller when calling ftrace_caller - * a1: the caller's return address - * a2: the address of global variable function_trace_op - */ - ld a1, -8(s0) - addi a0, ra, -MCOUNT_INSN_SIZE - la t5, function_trace_op - ld a2, 0(t5) - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* - * the graph tracer (specifically, prepare_ftrace_return) needs these - * arguments but for now the function tracer occupies the regs, so we - * save them in temporary regs to recover later. - */ - addi t0, s0, -8 - mv t1, a0 + .macro RESTORE_ABI_REGS + REG_L t0, FREGS_EPC(sp) + REG_L x1, FREGS_RA(sp) #ifdef HAVE_FUNCTION_GRAPH_FP_TEST - ld t2, -16(s0) + REG_L x8, FREGS_S0(sp) #endif + REG_L x6, FREGS_T1(sp) +#ifdef CONFIG_CC_IS_CLANG + REG_L x7, FREGS_T2(sp) + REG_L x28, FREGS_T3(sp) + REG_L x29, FREGS_T4(sp) + REG_L x30, FREGS_T5(sp) + REG_L x31, FREGS_T6(sp) #endif - - SAVE_ABI_STATE -ftrace_call: - .global ftrace_call - /* - * For the dynamic ftrace to work, here we should reserve at least - * 8 bytes for a functional auipc-jalr pair. The following call - * serves this purpose. - * - * Calling ftrace_update_ftrace_func would overwrite the nops below. - * Check ftrace_modify_all_code for details. - */ - call ftrace_stub - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - RESTORE_GRAPH_ARGS - call ftrace_graph_caller -#endif - - RESTORE_ABI_STATE - ret -ENDPROC(ftrace_caller) - -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS - .macro SAVE_ALL - addi sp, sp, -(PT_SIZE_ON_STACK+16) - sd s0, (PT_SIZE_ON_STACK)(sp) - sd ra, (PT_SIZE_ON_STACK+8)(sp) - addi s0, sp, (PT_SIZE_ON_STACK+16) - - sd x1, PT_RA(sp) - sd x2, PT_SP(sp) - sd x3, PT_GP(sp) - sd x4, PT_TP(sp) - sd x5, PT_T0(sp) - sd x6, PT_T1(sp) - sd x7, PT_T2(sp) - sd x8, PT_S0(sp) - sd x9, PT_S1(sp) - sd x10, PT_A0(sp) - sd x11, PT_A1(sp) - sd x12, PT_A2(sp) - sd x13, PT_A3(sp) - sd x14, PT_A4(sp) - sd x15, PT_A5(sp) - sd x16, PT_A6(sp) - sd x17, PT_A7(sp) - sd x18, PT_S2(sp) - sd x19, PT_S3(sp) - sd x20, PT_S4(sp) - sd x21, PT_S5(sp) - sd x22, PT_S6(sp) - sd x23, PT_S7(sp) - sd x24, PT_S8(sp) - sd x25, PT_S9(sp) - sd x26, PT_S10(sp) - sd x27, PT_S11(sp) - sd x28, PT_T3(sp) - sd x29, PT_T4(sp) - sd x30, PT_T5(sp) - sd x31, PT_T6(sp) - .endm - - .macro RESTORE_ALL - ld x1, PT_RA(sp) - ld x2, PT_SP(sp) - ld x3, PT_GP(sp) - ld x4, PT_TP(sp) - ld x5, PT_T0(sp) - ld x6, PT_T1(sp) - ld x7, PT_T2(sp) - ld x8, PT_S0(sp) - ld x9, PT_S1(sp) - ld x10, PT_A0(sp) - ld x11, PT_A1(sp) - ld x12, PT_A2(sp) - ld x13, PT_A3(sp) - ld x14, PT_A4(sp) - ld x15, PT_A5(sp) - ld x16, PT_A6(sp) - ld x17, PT_A7(sp) - ld x18, PT_S2(sp) - ld x19, PT_S3(sp) - ld x20, PT_S4(sp) - ld x21, PT_S5(sp) - ld x22, PT_S6(sp) - ld x23, PT_S7(sp) - ld x24, PT_S8(sp) - ld x25, PT_S9(sp) - ld x26, PT_S10(sp) - ld x27, PT_S11(sp) - ld x28, PT_T3(sp) - ld x29, PT_T4(sp) - ld x30, PT_T5(sp) - ld x31, PT_T6(sp) - - ld s0, (PT_SIZE_ON_STACK)(sp) - ld ra, (PT_SIZE_ON_STACK+8)(sp) - addi sp, sp, (PT_SIZE_ON_STACK+16) + // restore the arguments + REG_L x10, FREGS_A0(sp) + REG_L x11, FREGS_A1(sp) + REG_L x12, FREGS_A2(sp) + REG_L x13, FREGS_A3(sp) + REG_L x14, FREGS_A4(sp) + REG_L x15, FREGS_A5(sp) + REG_L x16, FREGS_A6(sp) + REG_L x17, FREGS_A7(sp) + + addi sp, sp, FREGS_SIZE_ON_STACK .endm - .macro RESTORE_GRAPH_REG_ARGS - ld a0, PT_T0(sp) - ld a1, PT_T1(sp) -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - ld a2, PT_T2(sp) + .macro PREPARE_ARGS + addi a0, t0, -MCOUNT_JALR_SIZE // ip (callsite's jalr insn) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + mv a1, ra // parent_ip + REG_L a2, -16(t0) // op + REG_L ra, FTRACE_OPS_FUNC(a2) // op->func +#else + la a1, function_trace_op + REG_L a2, 0(a1) // op + mv a1, ra // parent_ip #endif + mv a3, sp // regs .endm -/* - * Most of the contents are the same as ftrace_caller. - */ -ENTRY(ftrace_regs_caller) +SYM_FUNC_START(ftrace_caller) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS /* - * a3: the address of all registers in the stack + * When CALL_OPS is enabled (2 or 4) nops [8B] are placed before the + * function entry, these are later overwritten with the pointer to the + * associated struct ftrace_ops. + * + * -8: &ftrace_ops of the associated tracer function. + *<ftrace enable>: + * 0: auipc t0/ra, 0x? + * 4: jalr t0/ra, ?(t0/ra) + * + * -8: &ftrace_nop_ops + *<ftrace disable>: + * 0: nop + * 4: nop + * + * t0 is set to ip+8 after the jalr is executed at the callsite, + * so we find the associated op at t0-16. */ - ld a1, -8(s0) - addi a0, ra, -MCOUNT_INSN_SIZE - la t5, function_trace_op - ld a2, 0(t5) - addi a3, sp, -(PT_SIZE_ON_STACK+16) + REG_L t1, -16(t0) // op Should be SZ_REG instead of 16 -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - addi t0, s0, -8 - mv t1, a0 -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - ld t2, -16(s0) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + /* + * If the op has a direct call, handle it immediately without + * saving/restoring registers. + */ + REG_L t1, FTRACE_OPS_DIRECT_CALL(t1) + bnez t1, ftrace_caller_direct #endif #endif - SAVE_ALL + SAVE_ABI_REGS + PREPARE_ARGS -ftrace_regs_call: - .global ftrace_regs_call - call ftrace_stub - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - RESTORE_GRAPH_REG_ARGS - call ftrace_graph_caller +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + jalr ra +#else +SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) + REG_L ra, ftrace_call_dest + jalr ra, 0(ra) +#endif + RESTORE_ABI_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + bnez t1, ftrace_caller_direct +#endif + jr t0 +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_INNER_LABEL(ftrace_caller_direct, SYM_L_LOCAL) + jr t1 #endif +SYM_FUNC_END(ftrace_caller) - RESTORE_ALL - ret -ENDPROC(ftrace_regs_caller) -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_CODE_START(ftrace_stub_direct_tramp) + jr t0 +SYM_CODE_END(ftrace_stub_direct_tramp) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ |