diff options
Diffstat (limited to 'arch/arm64/kernel/entry-ftrace.S')
| -rw-r--r-- | arch/arm64/kernel/entry-ftrace.S | 282 |
1 files changed, 153 insertions, 129 deletions
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index bd5df50e4643..f0c16640ef21 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -7,95 +7,109 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/asm-offsets.h> #include <asm/assembler.h> #include <asm/ftrace.h> #include <asm/insn.h> -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS /* * Due to -fpatchable-function-entry=2, the compiler has placed two NOPs before * the regular function prologue. For an enabled callsite, ftrace_init_nop() and * ftrace_make_call() have patched those NOPs to: * * MOV X9, LR - * BL <entry> - * - * ... where <entry> is either ftrace_caller or ftrace_regs_caller. + * BL ftrace_caller * * Each instrumented function follows the AAPCS, so here x0-x8 and x18-x30 are * live (x18 holds the Shadow Call Stack pointer), and x9-x17 are safe to * clobber. * - * We save the callsite's context into a pt_regs before invoking any ftrace - * callbacks. So that we can get a sensible backtrace, we create a stack record - * for the callsite and the ftrace entry assembly. This is not sufficient for - * reliable stacktrace: until we create the callsite stack record, its caller - * is missing from the LR and existing chain of frame records. + * We save the callsite's context into a struct ftrace_regs before invoking any + * ftrace callbacks. So that we can get a sensible backtrace, we create frame + * records for the callsite and the ftrace entry assembly. This is not + * sufficient for reliable stacktrace: until we create the callsite stack + * record, its caller is missing from the LR and existing chain of frame + * records. */ - .macro ftrace_regs_entry, allregs=0 - /* Make room for pt_regs, plus a callee frame */ - sub sp, sp, #(PT_REGS_SIZE + 16) - - /* Save function arguments (and x9 for simplicity) */ - stp x0, x1, [sp, #S_X0] - stp x2, x3, [sp, #S_X2] - stp x4, x5, [sp, #S_X4] - stp x6, x7, [sp, #S_X6] - stp x8, x9, [sp, #S_X8] - - /* Optionally save the callee-saved registers, always save the FP */ - .if \allregs == 1 - stp x10, x11, [sp, #S_X10] - stp x12, x13, [sp, #S_X12] - stp x14, x15, [sp, #S_X14] - stp x16, x17, [sp, #S_X16] - stp x18, x19, [sp, #S_X18] - stp x20, x21, [sp, #S_X20] - stp x22, x23, [sp, #S_X22] - stp x24, x25, [sp, #S_X24] - stp x26, x27, [sp, #S_X26] - stp x28, x29, [sp, #S_X28] - .else - str x29, [sp, #S_FP] - .endif - - /* Save the callsite's SP and LR */ - add x10, sp, #(PT_REGS_SIZE + 16) - stp x9, x10, [sp, #S_LR] +SYM_CODE_START(ftrace_caller) + bti c + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + /* + * The literal pointer to the ops is at an 8-byte aligned boundary + * which is either 12 or 16 bytes before the BL instruction in the call + * site. See ftrace_call_adjust() for details. + * + * Therefore here the LR points at `literal + 16` or `literal + 20`, + * and we can find the address of the literal in either case by + * aligning to an 8-byte boundary and subtracting 16. We do the + * alignment first as this allows us to fold the subtraction into the + * LDR. + */ + bic x11, x30, 0x7 + ldr x11, [x11, #-(4 * AARCH64_INSN_SIZE)] // op + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + /* + * If the op has a direct call, handle it immediately without + * saving/restoring registers. + */ + ldr x17, [x11, #FTRACE_OPS_DIRECT_CALL] // op->direct_call + cbnz x17, ftrace_caller_direct +#endif +#endif + + /* Save original SP */ + mov x10, sp + + /* Make room for ftrace regs, plus two frame records */ + sub sp, sp, #(FREGS_SIZE + 32) + + /* Save function arguments */ + stp x0, x1, [sp, #FREGS_X0] + stp x2, x3, [sp, #FREGS_X2] + stp x4, x5, [sp, #FREGS_X4] + stp x6, x7, [sp, #FREGS_X6] + str x8, [sp, #FREGS_X8] + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + str xzr, [sp, #FREGS_DIRECT_TRAMP] +#endif + + /* Save the callsite's FP, LR, SP */ + str x29, [sp, #FREGS_FP] + str x9, [sp, #FREGS_LR] + str x10, [sp, #FREGS_SP] /* Save the PC after the ftrace callsite */ - str x30, [sp, #S_PC] + str x30, [sp, #FREGS_PC] - /* Create a frame record for the callsite above pt_regs */ - stp x29, x9, [sp, #PT_REGS_SIZE] - add x29, sp, #PT_REGS_SIZE + /* Create a frame record for the callsite above the ftrace regs */ + stp x29, x9, [sp, #FREGS_SIZE + 16] + add x29, sp, #FREGS_SIZE + 16 - /* Create our frame record within pt_regs. */ - stp x29, x30, [sp, #S_STACKFRAME] - add x29, sp, #S_STACKFRAME - .endm + /* Create our frame record above the ftrace regs */ + stp x29, x30, [sp, #FREGS_SIZE] + add x29, sp, #FREGS_SIZE -SYM_CODE_START(ftrace_regs_caller) - bti c - ftrace_regs_entry 1 - b ftrace_common -SYM_CODE_END(ftrace_regs_caller) + /* Prepare arguments for the the tracer func */ + sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn) + mov x1, x9 // parent_ip (callsite's LR) + mov x3, sp // regs -SYM_CODE_START(ftrace_caller) - bti c - ftrace_regs_entry 0 - b ftrace_common -SYM_CODE_END(ftrace_caller) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + mov x2, x11 // op + ldr x4, [x2, #FTRACE_OPS_FUNC] // op->func + blr x4 // op->func(ip, parent_ip, op, regs) -SYM_CODE_START(ftrace_common) - sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn) - mov x1, x9 // parent_ip (callsite's LR) - ldr_l x2, function_trace_op // op - mov x3, sp // regs +#else + ldr_l x2, function_trace_op // op SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) - bl ftrace_stub + bl ftrace_stub // func(ip, parent_ip, op, regs) +#endif /* * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved @@ -103,24 +117,68 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) * to restore x0-x8, x29, and x30. */ /* Restore function arguments */ - ldp x0, x1, [sp] - ldp x2, x3, [sp, #S_X2] - ldp x4, x5, [sp, #S_X4] - ldp x6, x7, [sp, #S_X6] - ldr x8, [sp, #S_X8] + ldp x0, x1, [sp, #FREGS_X0] + ldp x2, x3, [sp, #FREGS_X2] + ldp x4, x5, [sp, #FREGS_X4] + ldp x6, x7, [sp, #FREGS_X6] + ldr x8, [sp, #FREGS_X8] + + /* Restore the callsite's FP */ + ldr x29, [sp, #FREGS_FP] + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + ldr x17, [sp, #FREGS_DIRECT_TRAMP] + cbnz x17, ftrace_caller_direct_late +#endif - /* Restore the callsite's FP, LR, PC */ - ldr x29, [sp, #S_FP] - ldr x30, [sp, #S_LR] - ldr x9, [sp, #S_PC] + /* Restore the callsite's LR and PC */ + ldr x30, [sp, #FREGS_LR] + ldr x9, [sp, #FREGS_PC] /* Restore the callsite's SP */ - add sp, sp, #PT_REGS_SIZE + 16 + add sp, sp, #FREGS_SIZE + 32 ret x9 -SYM_CODE_END(ftrace_common) -#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_INNER_LABEL(ftrace_caller_direct_late, SYM_L_LOCAL) + /* + * Head to a direct trampoline in x17 after having run other tracers. + * The ftrace_regs are live, and x0-x8 and FP have been restored. The + * LR, PC, and SP have not been restored. + */ + + /* + * Restore the callsite's LR and PC matching the trampoline calling + * convention. + */ + ldr x9, [sp, #FREGS_LR] + ldr x30, [sp, #FREGS_PC] + + /* Restore the callsite's SP */ + add sp, sp, #FREGS_SIZE + 32 + +SYM_INNER_LABEL(ftrace_caller_direct, SYM_L_LOCAL) + /* + * Head to a direct trampoline in x17. + * + * We use `BR X17` as this can safely land on a `BTI C` or `PACIASP` in + * the trampoline, and will not unbalance any return stack. + */ + br x17 +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ +SYM_CODE_END(ftrace_caller) + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_CODE_START(ftrace_stub_direct_tramp) + bti c + mov x10, x30 + mov x30, x9 + ret x10 +SYM_CODE_END(ftrace_stub_direct_tramp) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + +#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ /* * Gcc with -pg will put the following code in the beginning of each function: @@ -194,44 +252,6 @@ SYM_CODE_END(ftrace_common) add \reg, \reg, #8 .endm -#ifndef CONFIG_DYNAMIC_FTRACE -/* - * void _mcount(unsigned long return_address) - * @return_address: return address to instrumented function - * - * This function makes calls, if enabled, to: - * - tracer function to probe instrumented function's entry, - * - ftrace_graph_caller to set up an exit hook - */ -SYM_FUNC_START(_mcount) - mcount_enter - - ldr_l x2, ftrace_trace_function - adr x0, ftrace_stub - cmp x0, x2 // if (ftrace_trace_function - b.eq skip_ftrace_call // != ftrace_stub) { - - mcount_get_pc x0 // function's pc - mcount_get_lr x1 // function's lr (= parent's pc) - blr x2 // (*ftrace_trace_function)(pc, lr); - -skip_ftrace_call: // } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - ldr_l x2, ftrace_graph_return - cmp x0, x2 // if ((ftrace_graph_return - b.ne ftrace_graph_caller // != ftrace_stub) - - ldr_l x2, ftrace_graph_entry // || (ftrace_graph_entry - adr_l x0, ftrace_graph_entry_stub // != ftrace_graph_entry_stub)) - cmp x0, x2 - b.ne ftrace_graph_caller // ftrace_graph_caller(); -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - mcount_exit -SYM_FUNC_END(_mcount) -EXPORT_SYMBOL(_mcount) -NOKPROBE(_mcount) - -#else /* CONFIG_DYNAMIC_FTRACE */ /* * _mcount() is used to build the kernel with -pg option, but all the branch * instructions to _mcount() are replaced to NOP initially at kernel start up, @@ -271,7 +291,6 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller(); mcount_exit SYM_FUNC_END(ftrace_caller) -#endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* @@ -292,13 +311,17 @@ SYM_FUNC_START(ftrace_graph_caller) mcount_exit SYM_FUNC_END(ftrace_graph_caller) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ -SYM_FUNC_START(ftrace_stub) +SYM_TYPED_FUNC_START(ftrace_stub) ret SYM_FUNC_END(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER +SYM_TYPED_FUNC_START(ftrace_stub_graph) + ret +SYM_FUNC_END(ftrace_stub_graph) + /* * void return_to_handler(void) * @@ -307,22 +330,23 @@ SYM_FUNC_END(ftrace_stub) */ SYM_CODE_START(return_to_handler) /* save return value regs */ - sub sp, sp, #64 - stp x0, x1, [sp] - stp x2, x3, [sp, #16] - stp x4, x5, [sp, #32] - stp x6, x7, [sp, #48] + sub sp, sp, #FGRET_REGS_SIZE + stp x0, x1, [sp, #FGRET_REGS_X0] + stp x2, x3, [sp, #FGRET_REGS_X2] + stp x4, x5, [sp, #FGRET_REGS_X4] + stp x6, x7, [sp, #FGRET_REGS_X6] + str x29, [sp, #FGRET_REGS_FP] // parent's fp - mov x0, x29 // parent's fp - bl ftrace_return_to_handler// addr = ftrace_return_to_hander(fp); - mov x30, x0 // restore the original return address + mov x0, sp + bl ftrace_return_to_handler // addr = ftrace_return_to_hander(regs); + mov x30, x0 // restore the original return address /* restore return value regs */ - ldp x0, x1, [sp] - ldp x2, x3, [sp, #16] - ldp x4, x5, [sp, #32] - ldp x6, x7, [sp, #48] - add sp, sp, #64 + ldp x0, x1, [sp, #FGRET_REGS_X0] + ldp x2, x3, [sp, #FGRET_REGS_X2] + ldp x4, x5, [sp, #FGRET_REGS_X4] + ldp x6, x7, [sp, #FGRET_REGS_X6] + add sp, sp, #FGRET_REGS_SIZE ret SYM_CODE_END(return_to_handler) |