@@ -46,5 +46,7 @@ extern char * __must_check skip_spaces(const char *);
extern char *strim(char *);
+extern void remove_spaces(char *s);
+
extern void *memchr_inv(const void *start, int c, size_t bytes);
#endif /* _TOOLS_LINUX_STRING_H_ */
@@ -153,6 +153,19 @@ char *strim(char *s)
return skip_spaces(s);
}
+/*
+ * remove_spaces - Removes whitespaces from @s
+ */
+void remove_spaces(char *s)
+{
+ char *d = s;
+
+ do {
+ while (*d == ' ')
+ ++d;
+ } while ((*s++ = *d++));
+}
+
/**
* strreplace - Replace all occurrences of character in string.
* @s: The string to operate on.
@@ -55,6 +55,7 @@ static int powerpc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
arch->initialized = true;
arch->associate_instruction_ops = powerpc__associate_instruction_ops;
arch->objdump.comment_char = '#';
+ annotate_opts.show_asm_raw = true;
}
return 0;
@@ -98,3 +98,12 @@ int regs_query_register_offset(const char *name)
return roff->ptregs_offset;
return -EINVAL;
}
+
+#define PPC_OP(op) (((op) >> 26) & 0x3F)
+#define PPC_RA(a) (((a) >> 16) & 0x1f)
+#define PPC_RT(t) (((t) >> 21) & 0x1f)
+#define PPC_RB(b) (((b) >> 11) & 0x1f)
+#define PPC_D(D) ((D) & 0xfffe)
+#define PPC_DS(DS) ((DS) & 0xfffc)
+#define OP_LD 58
+#define OP_STD 62
@@ -113,7 +113,10 @@ struct annotation_line {
struct disasm_line {
struct ins ins;
struct ins_operands ops;
-
+ union {
+ u8 bytes[4];
+ u32 raw_insn;
+ } raw;
/* This needs to be at the end. */
struct annotation_line al;
};
@@ -45,6 +45,7 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size,
static void ins__sort(struct arch *arch);
static int disasm_line__parse(char *line, const char **namep, char **rawp);
+static int disasm_line__parse_powerpc(struct disasm_line *dl);
static __attribute__((constructor)) void symbol__init_regexpr(void)
{
@@ -844,6 +845,59 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp)
return -1;
}
+/*
+ * Parses the result captured from symbol__disassemble_*
+ * Example, line read from DSO file in powerpc:
+ * line: 38 01 81 e8
+ * opcode: fetched from arch specific get_opcode_insn
+ * rawp_insn: e8810138
+ *
+ * rawp_insn is used later to extract the reg/offset fields
+ */
+#define PPC_OP(op) (((op) >> 26) & 0x3F)
+
+static int disasm_line__parse_powerpc(struct disasm_line *dl)
+{
+ char *line = dl->al.line;
+ const char **namep = &dl->ins.name;
+ char **rawp = &dl->ops.raw;
+ char tmp, *tmp_raw_insn, *name_raw_insn = skip_spaces(line);
+ char *name = skip_spaces(name_raw_insn + 11);
+ int objdump = 0;
+
+ if (strlen(line) > 11)
+ objdump = 1;
+
+ if (name_raw_insn[0] == '\0')
+ return -1;
+
+ if (objdump) {
+ *rawp = name + 1;
+ while ((*rawp)[0] != '\0' && !isspace((*rawp)[0]))
+ ++*rawp;
+ tmp = (*rawp)[0];
+ (*rawp)[0] = '\0';
+
+ *namep = strdup(name);
+ if (*namep == NULL)
+ return -1;
+
+ (*rawp)[0] = tmp;
+ *rawp = strim(*rawp);
+ } else
+ *namep = "";
+
+ tmp_raw_insn = strdup(name_raw_insn);
+ tmp_raw_insn[11] = '\0';
+ remove_spaces(tmp_raw_insn);
+
+ dl->raw.raw_insn = strtol(tmp_raw_insn, NULL, 16);
+ if (objdump)
+ dl->raw.raw_insn = be32_to_cpu(strtol(tmp_raw_insn, NULL, 16));
+
+ return 0;
+}
+
static void annotation_line__init(struct annotation_line *al,
struct annotate_args *args,
int nr)
@@ -897,7 +951,10 @@ struct disasm_line *disasm_line__new(struct annotate_args *args)
goto out_delete;
if (args->offset != -1) {
- if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
+ if (arch__is(args->arch, "powerpc")) {
+ if (disasm_line__parse_powerpc(dl) < 0)
+ goto out_free_line;
+ } else if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
goto out_free_line;
disasm_line__init_ins(dl, args->arch, &args->ms);
Currently, the perf tool infrastructure disasm_line__parse function to parse disassembled line. Example snippet from objdump: objdump --start-address=<address> --stop-address=<address> -d --no-show-raw-insn -C <vmlinux> c0000000010224b4: lwz r10,0(r9) This line "lwz r10,0(r9)" is parsed to extract instruction name, registers names and offset. In powerpc, the approach for data type profiling uses raw instruction instead of result from objdump to identify the instruction category and extract the source/target registers. Example: 38 01 81 e8 ld r4,312(r1) Here "38 01 81 e8" is the raw instruction representation. Add function "disasm_line__parse_powerpc" to handle parsing of raw instruction. Also update "struct disasm_line" to save the binary code/ With the change, function captures: line -> "38 01 81 e8 ld r4,312(r1)" raw instruction "38 01 81 e8" Raw instruction is used later to extract the reg/offset fields. Macros are added to extract opcode and register fields. "struct disasm_line" is updated to carry union of "bytes" and "raw_insn" of 32 bit to carry raw code (raw). Function "disasm_line__parse_powerpc fills the raw instruction hex value and can use macros to get opcode. There is no changes in existing code paths, which parses the disassembled code. The architecture using the instruction name and present approach is not altered. Since this approach targets powerpc, the macro implementation is added for powerpc as of now. Since the disasm_line__parse is used in other cases (perf annotate) and not only data tye profiling, the powerpc callback includes changes to work with binary code as well as mneumonic representation. Also in case if the DSO read fails and libcapstone is not supported, the approach fallback to use objdump as option. Hence as option, patch has changes to ensure objdump option also works well. Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com> --- tools/include/linux/string.h | 2 + tools/lib/string.c | 13 ++++ .../perf/arch/powerpc/annotate/instructions.c | 1 + tools/perf/arch/powerpc/util/dwarf-regs.c | 9 +++ tools/perf/util/annotate.h | 5 +- tools/perf/util/disasm.c | 59 ++++++++++++++++++- 6 files changed, 87 insertions(+), 2 deletions(-)