@@ -25,6 +25,7 @@
#include "srcline.h"
#include "symbol.h"
#include "util.h"
+#include "sort.h"
static regex_t file_lineno;
@@ -1634,6 +1635,91 @@ static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
}
#endif
+static int symbol__disassemble_raw(char *filename, struct symbol *sym,
+ struct annotate_args *args)
+{
+ struct annotation *notes = symbol__annotation(sym);
+ struct map *map = args->ms.map;
+ struct dso *dso = map__dso(map);
+ u64 start = map__rip_2objdump(map, sym->start);
+ u64 end = map__rip_2objdump(map, sym->end);
+ u64 len = end - start;
+ u64 offset;
+ int i, count;
+ u8 *buf = NULL;
+ char disasm_buf[512];
+ struct disasm_line *dl;
+ u32 *line;
+
+ /* Return if objdump is specified explicitly */
+ if (args->options->objdump_path)
+ return -1;
+
+ pr_debug("Reading raw instruction from : %s using dso__data_read_offset\n", filename);
+
+ buf = malloc(len);
+ if (buf == NULL)
+ goto err;
+
+ count = dso__data_read_offset(dso, NULL, sym->start, buf, len);
+
+ line = (u32 *)buf;
+
+ if ((u64)count != len)
+ goto err;
+
+ /* add the function address and name */
+ scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:",
+ start, sym->name);
+
+ args->offset = -1;
+ args->line = disasm_buf;
+ args->line_nr = 0;
+ args->fileloc = NULL;
+ args->ms.sym = sym;
+
+ dl = disasm_line__new(args);
+ if (dl == NULL)
+ goto err;
+
+ annotation_line__add(&dl->al, ¬es->src->source);
+
+ /* Each raw instruction is 4 byte */
+ count = len/4;
+
+ for (i = 0, offset = 0; i < count; i++) {
+ args->offset = offset;
+ sprintf(args->line, "%x", line[i]);
+ dl = disasm_line__new(args);
+ if (dl == NULL)
+ goto err;
+
+ annotation_line__add(&dl->al, ¬es->src->source);
+ offset += 4;
+ }
+
+ /* It failed in the middle */
+ if (offset != len) {
+ struct list_head *list = ¬es->src->source;
+
+ /* Discard all lines and fallback to objdump */
+ while (!list_empty(list)) {
+ dl = list_first_entry(list, struct disasm_line, al.node);
+
+ list_del_init(&dl->al.node);
+ disasm_line__free(dl);
+ }
+ count = -1;
+ }
+
+out:
+ free(buf);
+ return count < 0 ? count : 0;
+
+err:
+ count = -1;
+ goto out;
+}
/*
* Possibly create a new version of line with tabs expanded. Returns the
* existing or new line, storage is updated if a new line is allocated. If
@@ -1758,6 +1844,21 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
strcpy(symfs_filename, tmp);
}
+ /*
+ * For powerpc data type profiling, use the dso__data_read_offset
+ * to read raw instruction directly and interpret the binary code
+ * to understand instructions and register fields. For sort keys as
+ * type and typeoff, disassemble to mnemonic notation is
+ * not required in case of powerpc.
+ */
+ if (arch__is(args->arch, "powerpc")) {
+ if (sort_order && !strstr(sort_order, "sym")) {
+ err = symbol__disassemble_raw(symfs_filename, sym, args);
+ if (err == 0)
+ goto out_remove_tmp;
+ }
+ }
+
#ifdef HAVE_LIBCAPSTONE_SUPPORT
err = symbol__disassemble_capstone(symfs_filename, sym, args);
if (err == 0)
Add support to capture and parse raw instruction in powerpc. Currently, the perf tool infrastructure uses two ways to disassemble and understand the instruction. One is objdump and other option is via libcapstone. Currently, the perf tool infrastructure uses "--no-show-raw-insn" option with "objdump" while disassemble. Example from powerpc with this option for an instruction address is: Snippet from: 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. Also to find whether there is a memory reference in the operands, "memory_ref_char" field of objdump is used. For x86, "(" is used as memory_ref_char to tackle instructions of the form "mov (%rax), %rcx". In case of powerpc, not all instructions using "(" are the only memory instructions. Example, above instruction can also be of extended form (X form) "lwzx r10,0,r19". Inorder to easy identify the instruction category and extract the source/target registers, patch adds support to use raw instruction for powerpc. Approach used is to read the raw instruction directly from the DSO file using "dso__data_read_offset" utility which is already implemented in perf infrastructure in "util/dso.c". Example: 38 01 81 e8 ld r4,312(r1) Here "38 01 81 e8" is the raw instruction representation. In powerpc, this translates to instruction form: "ld RT,DS(RA)" and binary code as: | 58 | RT | RA | DS | | ------------------------------------- 0 6 11 16 30 31 Function "symbol__disassemble_dso" is updated to read raw instruction directly from DSO using dso__data_read_offset utility. In case of above example, this captures: line: 38 01 81 e8 The above works well when perf report is invoked with only sort keys for data type ie type and typeoff. Because there is no instruction level annotation needed if only data type information is requested for. For annotating sample, along with type and typeoff sort key, "sym" sort key is also needed. And by default invoking just "perf report" uses sort key "sym" that displays the symbol information. With approach changes in powerpc which first reads DSO for raw instruction, "perf annotate" and "perf report" + a key breaks since it doesn't do the instruction level disassembly. Snippet of result from perf report: Samples: 1K of event 'mem-loads', 4000 Hz, Event count (approx.): 937238 do_work /usr/bin/pmlogger [Percent: local period] Percent│ ea230010 │ 3a550010 │ 3a600000 │ 38f60001 │ 39490008 │ 42400438 51.44 │ 81290008 │ 7d485378 Here, raw instruction is displayed in the output instead of human readable annotated form. One way to get the appropriate data is to specify "--objdump path", by which code annotation will be done. But the default behaviour will be changed. To fix this breakage, check if "sym" sort key is set. If so fallback and use the libcapstone/objdump way of disassmbling the sample. With the changes and "perf report" Samples: 1K of event 'mem-loads', 4000 Hz, Event count (approx.): 937238 do_work /usr/bin/pmlogger [Percent: local period] Percent│ ld r17,16(r3) │ addi r18,r21,16 │ li r19,0 │ 8b0: rldicl r10,r10,63,33 │ addi r10,r10,1 │ mtctr r10 │ ↓ b 8e4 │ 8c0: addi r7,r22,1 │ addi r10,r9,8 │ ↓ bdz d00 51.44 │ lwz r9,8(r9) │ mr r8,r10 │ cmpw r20,r9 Reviewed-and-tested-by: Kajol Jain <kjain@linux.ibm.com> Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com> --- tools/perf/util/disasm.c | 101 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+)