diff options
author | Athira Rajeev <atrajeev@linux.vnet.ibm.com> | 2024-07-18 10:43:45 +0200 |
---|---|---|
committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2024-07-31 21:12:59 +0200 |
commit | 782959ac248ac3cbac80f7476d4e0410662ff400 (patch) | |
tree | 90867a20d63378b0449558de3ceffad26590ab09 /tools/perf/arch | |
parent | perf annotate: Move the data structures related to register type to header file (diff) | |
download | linux-782959ac248ac3cbac80f7476d4e0410662ff400.tar.xz linux-782959ac248ac3cbac80f7476d4e0410662ff400.zip |
perf annotate: Add "update_insn_state" callback function to handle arch specific instruction tracking
Add "update_insn_state" callback to "struct arch" to handle instruction
tracking. Currently updating instruction state is handled by static
function "update_insn_state_x86" which is defined in "annotate-data.c".
Make this as a callback for specific arch and move to archs specific
file "arch/x86/annotate/instructions.c" . This will help to add helper
function for other platforms in file:
"arch/<platform>/annotate/instructions.c" and make changes/updates
easier.
Define callback "update_insn_state" as part of "struct arch", also make
some of the debug functions non-static so that it can be referenced from
other places.
Reviewed-by: Kajol Jain <kjain@linux.ibm.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Tested-by: Kajol Jain <kjain@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Akanksha J N <akanksha@linux.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Disha Goel <disgoel@linux.vnet.ibm.com>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Segher Boessenkool <segher@kernel.crashing.org>
Link: https://lore.kernel.org/lkml/20240718084358.72242-3-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/arch')
-rw-r--r-- | tools/perf/arch/x86/annotate/instructions.c | 377 |
1 files changed, 377 insertions, 0 deletions
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 5cdf457f5cbe..7b7d462c6c6b 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -206,3 +206,380 @@ static int x86__annotate_init(struct arch *arch, char *cpuid) arch->initialized = true; return err; } + +#ifdef HAVE_DWARF_SUPPORT +static void update_insn_state_x86(struct type_state *state, + struct data_loc_info *dloc, Dwarf_Die *cu_die, + struct disasm_line *dl) +{ + struct annotated_insn_loc loc; + struct annotated_op_loc *src = &loc.ops[INSN_OP_SOURCE]; + struct annotated_op_loc *dst = &loc.ops[INSN_OP_TARGET]; + struct type_state_reg *tsr; + Dwarf_Die type_die; + u32 insn_offset = dl->al.offset; + int fbreg = dloc->fbreg; + int fboff = 0; + + if (annotate_get_insn_location(dloc->arch, dl, &loc) < 0) + return; + + if (ins__is_call(&dl->ins)) { + struct symbol *func = dl->ops.target.sym; + + if (func == NULL) + return; + + /* __fentry__ will preserve all registers */ + if (!strcmp(func->name, "__fentry__")) + return; + + pr_debug_dtp("call [%x] %s\n", insn_offset, func->name); + + /* Otherwise invalidate caller-saved registers after call */ + for (unsigned i = 0; i < ARRAY_SIZE(state->regs); i++) { + if (state->regs[i].caller_saved) + state->regs[i].ok = false; + } + + /* Update register with the return type (if any) */ + if (die_find_func_rettype(cu_die, func->name, &type_die)) { + tsr = &state->regs[state->ret_reg]; + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + + pr_debug_dtp("call [%x] return -> reg%d", + insn_offset, state->ret_reg); + pr_debug_type_name(&type_die, tsr->kind); + } + return; + } + + if (!strncmp(dl->ins.name, "add", 3)) { + u64 imm_value = -1ULL; + int offset; + const char *var_name = NULL; + struct map_symbol *ms = dloc->ms; + u64 ip = ms->sym->start + dl->al.offset; + + if (!has_reg_type(state, dst->reg1)) + return; + + tsr = &state->regs[dst->reg1]; + + if (src->imm) + imm_value = src->offset; + else if (has_reg_type(state, src->reg1) && + state->regs[src->reg1].kind == TSR_KIND_CONST) + imm_value = state->regs[src->reg1].imm_value; + else if (src->reg1 == DWARF_REG_PC) { + u64 var_addr = annotate_calc_pcrel(dloc->ms, ip, + src->offset, dl); + + if (get_global_var_info(dloc, var_addr, + &var_name, &offset) && + !strcmp(var_name, "this_cpu_off") && + tsr->kind == TSR_KIND_CONST) { + tsr->kind = TSR_KIND_PERCPU_BASE; + imm_value = tsr->imm_value; + } + } + else + return; + + if (tsr->kind != TSR_KIND_PERCPU_BASE) + return; + + if (get_global_var_type(cu_die, dloc, ip, imm_value, &offset, + &type_die) && offset == 0) { + /* + * This is not a pointer type, but it should be treated + * as a pointer. + */ + tsr->type = type_die; + tsr->kind = TSR_KIND_POINTER; + tsr->ok = true; + + pr_debug_dtp("add [%x] percpu %#"PRIx64" -> reg%d", + insn_offset, imm_value, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + return; + } + + if (strncmp(dl->ins.name, "mov", 3)) + return; + + if (dloc->fb_cfa) { + u64 ip = dloc->ms->sym->start + dl->al.offset; + u64 pc = map__rip_2objdump(dloc->ms->map, ip); + + if (die_get_cfa(dloc->di->dbg, pc, &fbreg, &fboff) < 0) + fbreg = -1; + } + + /* Case 1. register to register or segment:offset to register transfers */ + if (!src->mem_ref && !dst->mem_ref) { + if (!has_reg_type(state, dst->reg1)) + return; + + tsr = &state->regs[dst->reg1]; + if (dso__kernel(map__dso(dloc->ms->map)) && + src->segment == INSN_SEG_X86_GS && src->imm) { + u64 ip = dloc->ms->sym->start + dl->al.offset; + u64 var_addr; + int offset; + + /* + * In kernel, %gs points to a per-cpu region for the + * current CPU. Access with a constant offset should + * be treated as a global variable access. + */ + var_addr = src->offset; + + if (var_addr == 40) { + tsr->kind = TSR_KIND_CANARY; + tsr->ok = true; + + pr_debug_dtp("mov [%x] stack canary -> reg%d\n", + insn_offset, dst->reg1); + return; + } + + if (!get_global_var_type(cu_die, dloc, ip, var_addr, + &offset, &type_die) || + !die_get_member_type(&type_die, offset, &type_die)) { + tsr->ok = false; + return; + } + + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + + pr_debug_dtp("mov [%x] this-cpu addr=%#"PRIx64" -> reg%d", + insn_offset, var_addr, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + return; + } + + if (src->imm) { + tsr->kind = TSR_KIND_CONST; + tsr->imm_value = src->offset; + tsr->ok = true; + + pr_debug_dtp("mov [%x] imm=%#x -> reg%d\n", + insn_offset, tsr->imm_value, dst->reg1); + return; + } + + if (!has_reg_type(state, src->reg1) || + !state->regs[src->reg1].ok) { + tsr->ok = false; + return; + } + + tsr->type = state->regs[src->reg1].type; + tsr->kind = state->regs[src->reg1].kind; + tsr->ok = true; + + pr_debug_dtp("mov [%x] reg%d -> reg%d", + insn_offset, src->reg1, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* Case 2. memory to register transers */ + if (src->mem_ref && !dst->mem_ref) { + int sreg = src->reg1; + + if (!has_reg_type(state, dst->reg1)) + return; + + tsr = &state->regs[dst->reg1]; + +retry: + /* Check stack variables with offset */ + if (sreg == fbreg) { + struct type_state_stack *stack; + int offset = src->offset - fboff; + + stack = find_stack_state(state, offset); + if (stack == NULL) { + tsr->ok = false; + return; + } else if (!stack->compound) { + tsr->type = stack->type; + tsr->kind = stack->kind; + tsr->ok = true; + } else if (die_get_member_type(&stack->type, + offset - stack->offset, + &type_die)) { + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + } else { + tsr->ok = false; + return; + } + + pr_debug_dtp("mov [%x] -%#x(stack) -> reg%d", + insn_offset, -offset, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* And then dereference the pointer if it has one */ + else if (has_reg_type(state, sreg) && state->regs[sreg].ok && + state->regs[sreg].kind == TSR_KIND_TYPE && + die_deref_ptr_type(&state->regs[sreg].type, + src->offset, &type_die)) { + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + + pr_debug_dtp("mov [%x] %#x(reg%d) -> reg%d", + insn_offset, src->offset, sreg, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* Or check if it's a global variable */ + else if (sreg == DWARF_REG_PC) { + struct map_symbol *ms = dloc->ms; + u64 ip = ms->sym->start + dl->al.offset; + u64 addr; + int offset; + + addr = annotate_calc_pcrel(ms, ip, src->offset, dl); + + if (!get_global_var_type(cu_die, dloc, ip, addr, &offset, + &type_die) || + !die_get_member_type(&type_die, offset, &type_die)) { + tsr->ok = false; + return; + } + + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + + pr_debug_dtp("mov [%x] global addr=%"PRIx64" -> reg%d", + insn_offset, addr, dst->reg1); + pr_debug_type_name(&type_die, tsr->kind); + } + /* And check percpu access with base register */ + else if (has_reg_type(state, sreg) && + state->regs[sreg].kind == TSR_KIND_PERCPU_BASE) { + u64 ip = dloc->ms->sym->start + dl->al.offset; + u64 var_addr = src->offset; + int offset; + + if (src->multi_regs) { + int reg2 = (sreg == src->reg1) ? src->reg2 : src->reg1; + + if (has_reg_type(state, reg2) && state->regs[reg2].ok && + state->regs[reg2].kind == TSR_KIND_CONST) + var_addr += state->regs[reg2].imm_value; + } + + /* + * In kernel, %gs points to a per-cpu region for the + * current CPU. Access with a constant offset should + * be treated as a global variable access. + */ + if (get_global_var_type(cu_die, dloc, ip, var_addr, + &offset, &type_die) && + die_get_member_type(&type_die, offset, &type_die)) { + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + + if (src->multi_regs) { + pr_debug_dtp("mov [%x] percpu %#x(reg%d,reg%d) -> reg%d", + insn_offset, src->offset, src->reg1, + src->reg2, dst->reg1); + } else { + pr_debug_dtp("mov [%x] percpu %#x(reg%d) -> reg%d", + insn_offset, src->offset, sreg, dst->reg1); + } + pr_debug_type_name(&tsr->type, tsr->kind); + } else { + tsr->ok = false; + } + } + /* And then dereference the calculated pointer if it has one */ + else if (has_reg_type(state, sreg) && state->regs[sreg].ok && + state->regs[sreg].kind == TSR_KIND_POINTER && + die_get_member_type(&state->regs[sreg].type, + src->offset, &type_die)) { + tsr->type = type_die; + tsr->kind = TSR_KIND_TYPE; + tsr->ok = true; + + pr_debug_dtp("mov [%x] pointer %#x(reg%d) -> reg%d", + insn_offset, src->offset, sreg, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* Or try another register if any */ + else if (src->multi_regs && sreg == src->reg1 && + src->reg1 != src->reg2) { + sreg = src->reg2; + goto retry; + } + else { + int offset; + const char *var_name = NULL; + + /* it might be per-cpu variable (in kernel) access */ + if (src->offset < 0) { + if (get_global_var_info(dloc, (s64)src->offset, + &var_name, &offset) && + !strcmp(var_name, "__per_cpu_offset")) { + tsr->kind = TSR_KIND_PERCPU_BASE; + + pr_debug_dtp("mov [%x] percpu base reg%d\n", + insn_offset, dst->reg1); + } + } + + tsr->ok = false; + } + } + /* Case 3. register to memory transfers */ + if (!src->mem_ref && dst->mem_ref) { + if (!has_reg_type(state, src->reg1) || + !state->regs[src->reg1].ok) + return; + + /* Check stack variables with offset */ + if (dst->reg1 == fbreg) { + struct type_state_stack *stack; + int offset = dst->offset - fboff; + + tsr = &state->regs[src->reg1]; + + stack = find_stack_state(state, offset); + if (stack) { + /* + * The source register is likely to hold a type + * of member if it's a compound type. Do not + * update the stack variable type since we can + * get the member type later by using the + * die_get_member_type(). + */ + if (!stack->compound) + set_stack_state(stack, offset, tsr->kind, + &tsr->type); + } else { + findnew_stack_state(state, offset, tsr->kind, + &tsr->type); + } + + pr_debug_dtp("mov [%x] reg%d -> -%#x(stack)", + insn_offset, src->reg1, -offset); + pr_debug_type_name(&tsr->type, tsr->kind); + } + /* + * Ignore other transfers since it'd set a value in a struct + * and won't change the type. + */ + } + /* Case 4. memory to memory transfers (not handled for now) */ +} +#endif |