Re: [PATCH 4/4] perf annotate: Use libcapstone to disassemble

Re: [PATCH 4/4] perf annotate: Use libcapstone to disassemble

[duchangbin]

Hi, Namhyung,
On Thu, Mar 28, 2024 at 04:20:09PM -0700, Namhyung Kim wrote:
> Now it can use the capstone library to disassemble the instructions.
> Let's use that (if available) for perf annotate to speed up.  Currently
> it only supports x86 architecture.  With this change I can see ~3x speed
> up in data type profiling.
>
> But note that capstone cannot give the source file and line number info.
> For now, users should use the external objdump for that by specifying
> the --objdump option explicitly.
>
> Cc: Changbin Du <changbin.du@huawei.com>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
>  tools/perf/util/disasm.c | 153 +++++++++++++++++++++++++++++++++++++++
>  1 file changed, 153 insertions(+)
>
> diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
> index 59ac37723990..c58ea6d822ed 100644
> --- a/tools/perf/util/disasm.c
> +++ b/tools/perf/util/disasm.c
> @@ -1,6 +1,7 @@
>  // SPDX-License-Identifier: GPL-2.0-only
>  #include <ctype.h>
>  #include <errno.h>
> +#include <fcntl.h>
>  #include <inttypes.h>
>  #include <libgen.h>
>  #include <regex.h>
> @@ -18,6 +19,7 @@
>  #include "evsel.h"
>  #include "map.h"
>  #include "maps.h"
> +#include "namespaces.h"
>  #include "srcline.h"
>  #include "symbol.h"
>
> @@ -1341,6 +1343,151 @@ symbol__disassemble_bpf_image(struct symbol *sym,
>       return 0;
>  }
>
> +#ifdef HAVE_LIBCAPSTONE_SUPPORT
> +#include <capstone/capstone.h>
> +
> +static int open_capstone_handle(struct annotate_args *args, bool is_64bit,
> +                             csh *handle)
> +{
> +     struct annotation_options *opt = args->options;
> +     cs_mode mode = is_64bit ? CS_MODE_64 : CS_MODE_32;
> +
> +     /* TODO: support more architectures */
> +     if (!arch__is(args->arch, "x86"))
> +             return -1;
> +
> +     if (cs_open(CS_ARCH_X86, mode, handle) != CS_ERR_OK)
> +             return -1;
> +
> +     if (!opt->disassembler_style ||
> +         !strcmp(opt->disassembler_style, "att"))
> +             cs_option(*handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT);
> +
> +     /*
> +      * Resolving address operands to symbols is implemented
> +      * on x86 by investigating instruction details.
> +      */
> +     cs_option(*handle, CS_OPT_DETAIL, CS_OPT_ON);
Enabling CS_OPT_DETAIL is to symbolize branch target address. You can refer to
print_insn_x86() in print_insn.c.

> +
> +     return 0;
> +}
> +

--
Cheers,
Changbin Du

Re: [PATCH 4/4] perf annotate: Use libcapstone to disassemble

[Namhyung Kim]

On Thu, Mar 28, 2024 at 7:53 PM duchangbin <changbin.du@huawei.com> wrote:
>
> Hi, Namhyung,
> On Thu, Mar 28, 2024 at 04:20:09PM -0700, Namhyung Kim wrote:
> > Now it can use the capstone library to disassemble the instructions.
> > Let's use that (if available) for perf annotate to speed up.  Currently
> > it only supports x86 architecture.  With this change I can see ~3x speed
> > up in data type profiling.
> >
> > But note that capstone cannot give the source file and line number info.
> > For now, users should use the external objdump for that by specifying
> > the --objdump option explicitly.
> >
> > Cc: Changbin Du <changbin.du@huawei.com>
> > Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> > ---
> >  tools/perf/util/disasm.c | 153 +++++++++++++++++++++++++++++++++++++++
> >  1 file changed, 153 insertions(+)
> >
> > diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
> > index 59ac37723990..c58ea6d822ed 100644
> > --- a/tools/perf/util/disasm.c
> > +++ b/tools/perf/util/disasm.c
> > @@ -1,6 +1,7 @@
> >  // SPDX-License-Identifier: GPL-2.0-only
> >  #include <ctype.h>
> >  #include <errno.h>
> > +#include <fcntl.h>
> >  #include <inttypes.h>
> >  #include <libgen.h>
> >  #include <regex.h>
> > @@ -18,6 +19,7 @@
> >  #include "evsel.h"
> >  #include "map.h"
> >  #include "maps.h"
> > +#include "namespaces.h"
> >  #include "srcline.h"
> >  #include "symbol.h"
> >
> > @@ -1341,6 +1343,151 @@ symbol__disassemble_bpf_image(struct symbol *sym,
> >       return 0;
> >  }
> >
> > +#ifdef HAVE_LIBCAPSTONE_SUPPORT
> > +#include <capstone/capstone.h>
> > +
> > +static int open_capstone_handle(struct annotate_args *args, bool is_64bit,
> > +                             csh *handle)
> > +{
> > +     struct annotation_options *opt = args->options;
> > +     cs_mode mode = is_64bit ? CS_MODE_64 : CS_MODE_32;
> > +
> > +     /* TODO: support more architectures */
> > +     if (!arch__is(args->arch, "x86"))
> > +             return -1;
> > +
> > +     if (cs_open(CS_ARCH_X86, mode, handle) != CS_ERR_OK)
> > +             return -1;
> > +
> > +     if (!opt->disassembler_style ||
> > +         !strcmp(opt->disassembler_style, "att"))
> > +             cs_option(*handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT);
> > +
> > +     /*
> > +      * Resolving address operands to symbols is implemented
> > +      * on x86 by investigating instruction details.
> > +      */
> > +     cs_option(*handle, CS_OPT_DETAIL, CS_OPT_ON);
> Enabling CS_OPT_DETAIL is to symbolize branch target address. You can refer to
> print_insn_x86() in print_insn.c.

Right, I think we can add it as a comment.

Thanks,
Namhyung

[PATCH 0/4] perf annotate: Use libcapstone as a disasssembler

[Namhyung Kim]

Hello,

As we've added libcapstone support, it's natural to use it for perf annotate
as well.  This change added the capstone support on x86 first.  Other archs
can be added later (by someone who can verify it doesn't break things).

For now it tries to use capstone (if available) before objdump.  But it
doesn't support source file and line number info.  So users should use the
objdump (by passing --objdump=PATH option) if they need them.  For example,
this command line will keep the existing behavior (i.e. using objdump).

  # not to use capstone for disassembly
  $ perf annotate --objdump=objdump

The capstone uses LLVM objdump style output which is slightly different than
the GNU objdump.  But it should not have differences besides that.  I've
verified the result of data type profiling and it produced the same output
but gave me ~3x speedups.

Thanks,
Namhyung


Cc: Changbin Du <changbin.du@huawei.com>


Namhyung Kim (4):
  perf annotate: Use ins__is_xxx() if possible
  perf annotate: Add and use ins__is_nop()
  perf annotate: Split out util/disasm.c
  perf annotate: Use libcapstone to disassemble

 tools/perf/util/Build      |    1 +
 tools/perf/util/annotate.c | 1711 ++---------------------------------
 tools/perf/util/annotate.h |   59 +-
 tools/perf/util/disasm.c   | 1739 ++++++++++++++++++++++++++++++++++++
 tools/perf/util/disasm.h   |  112 +++
 5 files changed, 1914 insertions(+), 1708 deletions(-)
 create mode 100644 tools/perf/util/disasm.c
 create mode 100644 tools/perf/util/disasm.h

-- 
2.44.0.478.gd926399ef9-goog

[PATCH 4/4] perf annotate: Use libcapstone to disassemble

[Namhyung Kim]

Now it can use the capstone library to disassemble the instructions.
Let's use that (if available) for perf annotate to speed up.  Currently
it only supports x86 architecture.  With this change I can see ~3x speed
up in data type profiling.

But note that capstone cannot give the source file and line number info.
For now, users should use the external objdump for that by specifying
the --objdump option explicitly.

Cc: Changbin Du <changbin.du@huawei.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/disasm.c | 153 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 153 insertions(+)

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index 59ac37723990..c58ea6d822ed 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <ctype.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <inttypes.h>
 #include <libgen.h>
 #include <regex.h>
@@ -18,6 +19,7 @@
 #include "evsel.h"
 #include "map.h"
 #include "maps.h"
+#include "namespaces.h"
 #include "srcline.h"
 #include "symbol.h"
 
@@ -1341,6 +1343,151 @@ symbol__disassemble_bpf_image(struct symbol *sym,
 	return 0;
 }
 
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+#include <capstone/capstone.h>
+
+static int open_capstone_handle(struct annotate_args *args, bool is_64bit,
+				csh *handle)
+{
+	struct annotation_options *opt = args->options;
+	cs_mode mode = is_64bit ? CS_MODE_64 : CS_MODE_32;
+
+	/* TODO: support more architectures */
+	if (!arch__is(args->arch, "x86"))
+		return -1;
+
+	if (cs_open(CS_ARCH_X86, mode, handle) != CS_ERR_OK)
+		return -1;
+
+	if (!opt->disassembler_style ||
+	    !strcmp(opt->disassembler_style, "att"))
+		cs_option(*handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT);
+
+	/*
+	 * Resolving address operands to symbols is implemented
+	 * on x86 by investigating instruction details.
+	 */
+	cs_option(*handle, CS_OPT_DETAIL, CS_OPT_ON);
+
+	return 0;
+}
+
+struct find_file_offset_data {
+	u64 ip;
+	u64 offset;
+};
+
+/* This will be called for each PHDR in an ELF binary */
+static int find_file_offset(u64 start, u64 len, u64 pgoff, void *arg)
+{
+	struct find_file_offset_data *data = arg;
+
+	if (start <= data->ip && data->ip < start + len) {
+		data->offset = pgoff + data->ip - start;
+		return 1;
+	}
+	return 0;
+}
+
+static int symbol__disassemble_capstone(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);
+	struct nscookie nsc;
+	u64 start = map__rip_2objdump(map, sym->start);
+	u64 end = map__rip_2objdump(map, sym->end);
+	u64 len = end - start;
+	u64 offset;
+	int i, fd, count;
+	bool is_64bit = false;
+	bool needs_cs_close = false;
+	u8 *buf = NULL;
+	struct find_file_offset_data data = {
+		.ip = start,
+	};
+	csh handle;
+	cs_insn *insn;
+
+	if (args->options->objdump_path)
+		return -1;
+
+	nsinfo__mountns_enter(dso->nsinfo, &nsc);
+	fd = open(filename, O_RDONLY);
+	nsinfo__mountns_exit(&nsc);
+	if (fd < 0)
+		return -1;
+
+	if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data,
+			    &is_64bit) == 0)
+		goto err;
+
+	if (open_capstone_handle(args, is_64bit, &handle) < 0)
+		goto err;
+
+	needs_cs_close = true;
+
+	buf = malloc(len);
+	if (buf == NULL)
+		goto err;
+
+	count = pread(fd, buf, len, data.offset);
+	close(fd);
+	fd = -1;
+
+	if ((u64)count != len)
+		goto err;
+
+	count = cs_disasm(handle, buf, len, start, len, &insn);
+	for (i = 0, offset = 0; i < count; i++) {
+		char disasm_buf[256];
+		struct disasm_line *dl;
+
+		scnprintf(disasm_buf, sizeof(disasm_buf), "%s %s",
+			  insn[i].mnemonic, insn[i].op_str);
+
+		args->offset = offset;
+		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, &notes->src->source);
+
+		offset += insn[i].size;
+	}
+
+out:
+	if (needs_cs_close)
+		cs_close(&handle);
+	free(buf);
+	return count < 0 ? count : 0;
+
+err:
+	if (fd >= 0)
+		close(fd);
+	if (needs_cs_close) {
+		struct disasm_line *dl, *tmp;
+
+		/*
+		 * It probably failed in the middle of the above loop.
+		 * Release any resources it might add.
+		 */
+		list_for_each_entry_safe(dl, tmp, &notes->src->source, al.node) {
+			list_del(&dl->al.node);
+			free(dl);
+		}
+	}
+	count = -1;
+	goto out;
+}
+#endif
+
 /*
  * 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
@@ -1463,6 +1610,12 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		strcpy(symfs_filename, tmp);
 	}
 
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+	err = symbol__disassemble_capstone(symfs_filename, sym, args);
+	if (err == 0)
+		goto out_remove_tmp;
+#endif
+
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-- 
2.44.0.478.gd926399ef9-goog