OpenCloudOS-Kernel/tools/perf/util/probe-finder.c

2025 lines
50 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
/*
* probe-finder.c : C expression to kprobe event converter
*
* Written by Masami Hiramatsu <mhiramat@redhat.com>
*/
#include <inttypes.h>
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
#include <sys/utsname.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <errno.h>
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <string.h>
#include <stdarg.h>
#include <dwarf-regs.h>
#include <linux/bitops.h>
#include <linux/zalloc.h>
#include "event.h"
#include "dso.h"
#include "debug.h"
#include "intlist.h"
#include "strbuf.h"
#include "strlist.h"
#include "symbol.h"
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
#include "probe-finder.h"
#include "probe-file.h"
#include "string2.h"
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
/* Kprobe tracer basic type is up to u64 */
#define MAX_BASIC_TYPE_BITS 64
2010-10-21 18:13:41 +08:00
/* Dwarf FL wrappers */
static char *debuginfo_path; /* Currently dummy */
static const Dwfl_Callbacks offline_callbacks = {
.find_debuginfo = dwfl_standard_find_debuginfo,
.debuginfo_path = &debuginfo_path,
.section_address = dwfl_offline_section_address,
/* We use this table for core files too. */
.find_elf = dwfl_build_id_find_elf,
};
/* Get a Dwarf from offline image */
static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
const char *path)
2010-10-21 18:13:41 +08:00
{
int fd;
2010-10-21 18:13:41 +08:00
fd = open(path, O_RDONLY);
if (fd < 0)
return fd;
2010-10-21 18:13:41 +08:00
dbg->dwfl = dwfl_begin(&offline_callbacks);
if (!dbg->dwfl)
goto error;
2010-10-21 18:13:41 +08:00
dwfl_report_begin(dbg->dwfl);
dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd);
if (!dbg->mod)
2010-10-21 18:13:41 +08:00
goto error;
dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias);
if (!dbg->dbg)
goto error;
dwfl_report_end(dbg->dwfl, NULL, NULL);
return 0;
2010-10-21 18:13:41 +08:00
error:
if (dbg->dwfl)
dwfl_end(dbg->dwfl);
else
close(fd);
memset(dbg, 0, sizeof(*dbg));
return -ENOENT;
2010-10-21 18:13:41 +08:00
}
static struct debuginfo *__debuginfo__new(const char *path)
{
struct debuginfo *dbg = zalloc(sizeof(*dbg));
if (!dbg)
return NULL;
if (debuginfo__init_offline_dwarf(dbg, path) < 0)
zfree(&dbg);
if (dbg)
pr_debug("Open Debuginfo file: %s\n", path);
return dbg;
}
enum dso_binary_type distro_dwarf_types[] = {
DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
DSO_BINARY_TYPE__NOT_FOUND,
};
struct debuginfo *debuginfo__new(const char *path)
{
enum dso_binary_type *type;
char buf[PATH_MAX], nil = '\0';
struct dso *dso;
struct debuginfo *dinfo = NULL;
/* Try to open distro debuginfo files */
dso = dso__new(path);
if (!dso)
goto out;
for (type = distro_dwarf_types;
!dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND;
type++) {
if (dso__read_binary_type_filename(dso, *type, &nil,
buf, PATH_MAX) < 0)
continue;
dinfo = __debuginfo__new(buf);
}
dso__put(dso);
out:
/* if failed to open all distro debuginfo, open given binary */
return dinfo ? : __debuginfo__new(path);
}
void debuginfo__delete(struct debuginfo *dbg)
{
if (dbg) {
if (dbg->dwfl)
dwfl_end(dbg->dwfl);
free(dbg);
}
}
2010-10-21 18:13:41 +08:00
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
/*
* Probe finder related functions
*/
static struct probe_trace_arg_ref *alloc_trace_arg_ref(long offs)
{
struct probe_trace_arg_ref *ref;
ref = zalloc(sizeof(struct probe_trace_arg_ref));
if (ref != NULL)
ref->offset = offs;
return ref;
}
/*
* Convert a location into trace_arg.
* If tvar == NULL, this just checks variable can be converted.
* If fentry == true and vr_die is a parameter, do huristic search
* for the location fuzzed by function entry mcount.
*/
static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
Dwarf_Op *fb_ops, Dwarf_Die *sp_die,
unsigned int machine,
struct probe_trace_arg *tvar)
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
{
Dwarf_Attribute attr;
Dwarf_Addr tmp = 0;
Dwarf_Op *op;
size_t nops;
unsigned int regn;
Dwarf_Word offs = 0;
bool ref = false;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
const char *regs;
perf probe: Add --range option to show a variable's location range It is not easy for users to get the accurate byte offset or the line number where a local variable can be probed. With '--range' option, local variables in the scope of the probe point are showed with a byte offset range, and can be added according to this range information. For example, there are some variables in the function generic_perform_write(): <generic_perform_write@mm/filemap.c:0> 0 ssize_t generic_perform_write(struct file *file, 1 struct iov_iter *i, loff_t pos) 2 { 3 struct address_space *mapping = file->f_mapping; 4 const struct address_space_operations *a_ops = mapping->a_ops; ... 42 status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); 44 if (unlikely(status < 0)) But we fail when we try to probe the variable 'a_ops' at line 42 or 44. $ perf probe --add 'generic_perform_write:42 a_ops' Failed to find the location of a_ops at this address. Perhaps, it has been optimized out. This is because the source code do not match the assembly, so a variable may not be available in the source code line where it appears. After this patch, we can lookup the accurate byte offset range of a variable, 'INV' indicates that this variable is not valid at the given point, but available in the scope: $ perf probe --vars 'generic_perform_write:42' --range Available variables at generic_perform_write:42 @<generic_perform_write+141> [INV] ssize_t written @<generic_perform_write+[324-331]> [INV] struct address_space_operations* a_ops @<generic_perform_write+[55-61,170-176,223-246]> [VAL] (unknown_type) fsdata @<generic_perform_write+[70-307,346-411]> [VAL] loff_t pos @<generic_perform_write+[0-286,286-336,346-411]> [VAL] long int status @<generic_perform_write+[83-342,346-411]> [VAL] long unsigned int bytes @<generic_perform_write+[122-311,320-338,346-403,403-411]> [VAL] struct address_space* mapping @<generic_perform_write+[35-344,346-411]> [VAL] struct iov_iter* i @<generic_perform_write+[0-340,346-411]> [VAL] struct page* page @<generic_perform_write+[70-307,346-411]> Then it is more clear for us to add a probe with this variable: $ perf probe --add 'generic_perform_write+170 a_ops' Added new event: probe:generic_perform_write (on generic_perform_write+170 with a_ops) Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1431336304-16863-2-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-11 17:25:03 +08:00
int ret, ret2 = 0;
if (dwarf_attr(vr_die, DW_AT_external, &attr) != NULL)
goto static_var;
/* Constant value */
if (dwarf_attr(vr_die, DW_AT_const_value, &attr) &&
immediate_value_is_supported()) {
Dwarf_Sword snum;
dwarf_formsdata(&attr, &snum);
ret = asprintf(&tvar->value, "\\%ld", (long)snum);
return ret < 0 ? -ENOMEM : 0;
}
/* TODO: handle more than 1 exprs */
if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
return -EINVAL; /* Broken DIE ? */
if (dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0) {
ret = dwarf_entrypc(sp_die, &tmp);
perf probe: Add --range option to show a variable's location range It is not easy for users to get the accurate byte offset or the line number where a local variable can be probed. With '--range' option, local variables in the scope of the probe point are showed with a byte offset range, and can be added according to this range information. For example, there are some variables in the function generic_perform_write(): <generic_perform_write@mm/filemap.c:0> 0 ssize_t generic_perform_write(struct file *file, 1 struct iov_iter *i, loff_t pos) 2 { 3 struct address_space *mapping = file->f_mapping; 4 const struct address_space_operations *a_ops = mapping->a_ops; ... 42 status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); 44 if (unlikely(status < 0)) But we fail when we try to probe the variable 'a_ops' at line 42 or 44. $ perf probe --add 'generic_perform_write:42 a_ops' Failed to find the location of a_ops at this address. Perhaps, it has been optimized out. This is because the source code do not match the assembly, so a variable may not be available in the source code line where it appears. After this patch, we can lookup the accurate byte offset range of a variable, 'INV' indicates that this variable is not valid at the given point, but available in the scope: $ perf probe --vars 'generic_perform_write:42' --range Available variables at generic_perform_write:42 @<generic_perform_write+141> [INV] ssize_t written @<generic_perform_write+[324-331]> [INV] struct address_space_operations* a_ops @<generic_perform_write+[55-61,170-176,223-246]> [VAL] (unknown_type) fsdata @<generic_perform_write+[70-307,346-411]> [VAL] loff_t pos @<generic_perform_write+[0-286,286-336,346-411]> [VAL] long int status @<generic_perform_write+[83-342,346-411]> [VAL] long unsigned int bytes @<generic_perform_write+[122-311,320-338,346-403,403-411]> [VAL] struct address_space* mapping @<generic_perform_write+[35-344,346-411]> [VAL] struct iov_iter* i @<generic_perform_write+[0-340,346-411]> [VAL] struct page* page @<generic_perform_write+[70-307,346-411]> Then it is more clear for us to add a probe with this variable: $ perf probe --add 'generic_perform_write+170 a_ops' Added new event: probe:generic_perform_write (on generic_perform_write+170 with a_ops) Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1431336304-16863-2-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-11 17:25:03 +08:00
if (ret)
return -ENOENT;
if (probe_conf.show_location_range &&
(dwarf_tag(vr_die) == DW_TAG_variable)) {
ret2 = -ERANGE;
} else if (addr != tmp ||
dwarf_tag(vr_die) != DW_TAG_formal_parameter) {
return -ENOENT;
}
ret = dwarf_highpc(sp_die, &tmp);
if (ret)
return -ENOENT;
/*
* This is fuzzed by fentry mcount. We try to find the
* parameter location at the earliest address.
*/
for (addr += 1; addr <= tmp; addr++) {
if (dwarf_getlocation_addr(&attr, addr, &op,
&nops, 1) > 0)
goto found;
}
return -ENOENT;
}
found:
if (nops == 0)
/* TODO: Support const_value */
return -ENOENT;
if (op->atom == DW_OP_addr) {
static_var:
if (!tvar)
perf probe: Add --range option to show a variable's location range It is not easy for users to get the accurate byte offset or the line number where a local variable can be probed. With '--range' option, local variables in the scope of the probe point are showed with a byte offset range, and can be added according to this range information. For example, there are some variables in the function generic_perform_write(): <generic_perform_write@mm/filemap.c:0> 0 ssize_t generic_perform_write(struct file *file, 1 struct iov_iter *i, loff_t pos) 2 { 3 struct address_space *mapping = file->f_mapping; 4 const struct address_space_operations *a_ops = mapping->a_ops; ... 42 status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); 44 if (unlikely(status < 0)) But we fail when we try to probe the variable 'a_ops' at line 42 or 44. $ perf probe --add 'generic_perform_write:42 a_ops' Failed to find the location of a_ops at this address. Perhaps, it has been optimized out. This is because the source code do not match the assembly, so a variable may not be available in the source code line where it appears. After this patch, we can lookup the accurate byte offset range of a variable, 'INV' indicates that this variable is not valid at the given point, but available in the scope: $ perf probe --vars 'generic_perform_write:42' --range Available variables at generic_perform_write:42 @<generic_perform_write+141> [INV] ssize_t written @<generic_perform_write+[324-331]> [INV] struct address_space_operations* a_ops @<generic_perform_write+[55-61,170-176,223-246]> [VAL] (unknown_type) fsdata @<generic_perform_write+[70-307,346-411]> [VAL] loff_t pos @<generic_perform_write+[0-286,286-336,346-411]> [VAL] long int status @<generic_perform_write+[83-342,346-411]> [VAL] long unsigned int bytes @<generic_perform_write+[122-311,320-338,346-403,403-411]> [VAL] struct address_space* mapping @<generic_perform_write+[35-344,346-411]> [VAL] struct iov_iter* i @<generic_perform_write+[0-340,346-411]> [VAL] struct page* page @<generic_perform_write+[70-307,346-411]> Then it is more clear for us to add a probe with this variable: $ perf probe --add 'generic_perform_write+170 a_ops' Added new event: probe:generic_perform_write (on generic_perform_write+170 with a_ops) Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1431336304-16863-2-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-11 17:25:03 +08:00
return ret2;
/* Static variables on memory (not stack), make @varname */
ret = strlen(dwarf_diename(vr_die));
tvar->value = zalloc(ret + 2);
if (tvar->value == NULL)
return -ENOMEM;
snprintf(tvar->value, ret + 2, "@%s", dwarf_diename(vr_die));
tvar->ref = alloc_trace_arg_ref((long)offs);
if (tvar->ref == NULL)
return -ENOMEM;
perf probe: Add --range option to show a variable's location range It is not easy for users to get the accurate byte offset or the line number where a local variable can be probed. With '--range' option, local variables in the scope of the probe point are showed with a byte offset range, and can be added according to this range information. For example, there are some variables in the function generic_perform_write(): <generic_perform_write@mm/filemap.c:0> 0 ssize_t generic_perform_write(struct file *file, 1 struct iov_iter *i, loff_t pos) 2 { 3 struct address_space *mapping = file->f_mapping; 4 const struct address_space_operations *a_ops = mapping->a_ops; ... 42 status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); 44 if (unlikely(status < 0)) But we fail when we try to probe the variable 'a_ops' at line 42 or 44. $ perf probe --add 'generic_perform_write:42 a_ops' Failed to find the location of a_ops at this address. Perhaps, it has been optimized out. This is because the source code do not match the assembly, so a variable may not be available in the source code line where it appears. After this patch, we can lookup the accurate byte offset range of a variable, 'INV' indicates that this variable is not valid at the given point, but available in the scope: $ perf probe --vars 'generic_perform_write:42' --range Available variables at generic_perform_write:42 @<generic_perform_write+141> [INV] ssize_t written @<generic_perform_write+[324-331]> [INV] struct address_space_operations* a_ops @<generic_perform_write+[55-61,170-176,223-246]> [VAL] (unknown_type) fsdata @<generic_perform_write+[70-307,346-411]> [VAL] loff_t pos @<generic_perform_write+[0-286,286-336,346-411]> [VAL] long int status @<generic_perform_write+[83-342,346-411]> [VAL] long unsigned int bytes @<generic_perform_write+[122-311,320-338,346-403,403-411]> [VAL] struct address_space* mapping @<generic_perform_write+[35-344,346-411]> [VAL] struct iov_iter* i @<generic_perform_write+[0-340,346-411]> [VAL] struct page* page @<generic_perform_write+[70-307,346-411]> Then it is more clear for us to add a probe with this variable: $ perf probe --add 'generic_perform_write+170 a_ops' Added new event: probe:generic_perform_write (on generic_perform_write+170 with a_ops) Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1431336304-16863-2-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-11 17:25:03 +08:00
return ret2;
}
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
/* If this is based on frame buffer, set the offset */
if (op->atom == DW_OP_fbreg) {
if (fb_ops == NULL)
return -ENOTSUP;
ref = true;
offs = op->number;
op = &fb_ops[0];
}
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
if (op->atom >= DW_OP_breg0 && op->atom <= DW_OP_breg31) {
regn = op->atom - DW_OP_breg0;
offs += op->number;
ref = true;
} else if (op->atom >= DW_OP_reg0 && op->atom <= DW_OP_reg31) {
regn = op->atom - DW_OP_reg0;
} else if (op->atom == DW_OP_bregx) {
regn = op->number;
offs += op->number2;
ref = true;
} else if (op->atom == DW_OP_regx) {
regn = op->number;
} else {
pr_debug("DW_OP %x is not supported.\n", op->atom);
return -ENOTSUP;
}
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
if (!tvar)
perf probe: Add --range option to show a variable's location range It is not easy for users to get the accurate byte offset or the line number where a local variable can be probed. With '--range' option, local variables in the scope of the probe point are showed with a byte offset range, and can be added according to this range information. For example, there are some variables in the function generic_perform_write(): <generic_perform_write@mm/filemap.c:0> 0 ssize_t generic_perform_write(struct file *file, 1 struct iov_iter *i, loff_t pos) 2 { 3 struct address_space *mapping = file->f_mapping; 4 const struct address_space_operations *a_ops = mapping->a_ops; ... 42 status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); 44 if (unlikely(status < 0)) But we fail when we try to probe the variable 'a_ops' at line 42 or 44. $ perf probe --add 'generic_perform_write:42 a_ops' Failed to find the location of a_ops at this address. Perhaps, it has been optimized out. This is because the source code do not match the assembly, so a variable may not be available in the source code line where it appears. After this patch, we can lookup the accurate byte offset range of a variable, 'INV' indicates that this variable is not valid at the given point, but available in the scope: $ perf probe --vars 'generic_perform_write:42' --range Available variables at generic_perform_write:42 @<generic_perform_write+141> [INV] ssize_t written @<generic_perform_write+[324-331]> [INV] struct address_space_operations* a_ops @<generic_perform_write+[55-61,170-176,223-246]> [VAL] (unknown_type) fsdata @<generic_perform_write+[70-307,346-411]> [VAL] loff_t pos @<generic_perform_write+[0-286,286-336,346-411]> [VAL] long int status @<generic_perform_write+[83-342,346-411]> [VAL] long unsigned int bytes @<generic_perform_write+[122-311,320-338,346-403,403-411]> [VAL] struct address_space* mapping @<generic_perform_write+[35-344,346-411]> [VAL] struct iov_iter* i @<generic_perform_write+[0-340,346-411]> [VAL] struct page* page @<generic_perform_write+[70-307,346-411]> Then it is more clear for us to add a probe with this variable: $ perf probe --add 'generic_perform_write+170 a_ops' Added new event: probe:generic_perform_write (on generic_perform_write+170 with a_ops) Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1431336304-16863-2-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-11 17:25:03 +08:00
return ret2;
regs = get_dwarf_regstr(regn, machine);
if (!regs) {
/* This should be a bug in DWARF or this tool */
pr_warning("Mapping for the register number %u "
"missing on this architecture.\n", regn);
perf probe: Add --range option to show a variable's location range It is not easy for users to get the accurate byte offset or the line number where a local variable can be probed. With '--range' option, local variables in the scope of the probe point are showed with a byte offset range, and can be added according to this range information. For example, there are some variables in the function generic_perform_write(): <generic_perform_write@mm/filemap.c:0> 0 ssize_t generic_perform_write(struct file *file, 1 struct iov_iter *i, loff_t pos) 2 { 3 struct address_space *mapping = file->f_mapping; 4 const struct address_space_operations *a_ops = mapping->a_ops; ... 42 status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); 44 if (unlikely(status < 0)) But we fail when we try to probe the variable 'a_ops' at line 42 or 44. $ perf probe --add 'generic_perform_write:42 a_ops' Failed to find the location of a_ops at this address. Perhaps, it has been optimized out. This is because the source code do not match the assembly, so a variable may not be available in the source code line where it appears. After this patch, we can lookup the accurate byte offset range of a variable, 'INV' indicates that this variable is not valid at the given point, but available in the scope: $ perf probe --vars 'generic_perform_write:42' --range Available variables at generic_perform_write:42 @<generic_perform_write+141> [INV] ssize_t written @<generic_perform_write+[324-331]> [INV] struct address_space_operations* a_ops @<generic_perform_write+[55-61,170-176,223-246]> [VAL] (unknown_type) fsdata @<generic_perform_write+[70-307,346-411]> [VAL] loff_t pos @<generic_perform_write+[0-286,286-336,346-411]> [VAL] long int status @<generic_perform_write+[83-342,346-411]> [VAL] long unsigned int bytes @<generic_perform_write+[122-311,320-338,346-403,403-411]> [VAL] struct address_space* mapping @<generic_perform_write+[35-344,346-411]> [VAL] struct iov_iter* i @<generic_perform_write+[0-340,346-411]> [VAL] struct page* page @<generic_perform_write+[70-307,346-411]> Then it is more clear for us to add a probe with this variable: $ perf probe --add 'generic_perform_write+170 a_ops' Added new event: probe:generic_perform_write (on generic_perform_write+170 with a_ops) Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1431336304-16863-2-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-11 17:25:03 +08:00
return -ENOTSUP;
}
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
tvar->value = strdup(regs);
if (tvar->value == NULL)
return -ENOMEM;
if (ref) {
tvar->ref = alloc_trace_arg_ref((long)offs);
if (tvar->ref == NULL)
return -ENOMEM;
}
perf probe: Add --range option to show a variable's location range It is not easy for users to get the accurate byte offset or the line number where a local variable can be probed. With '--range' option, local variables in the scope of the probe point are showed with a byte offset range, and can be added according to this range information. For example, there are some variables in the function generic_perform_write(): <generic_perform_write@mm/filemap.c:0> 0 ssize_t generic_perform_write(struct file *file, 1 struct iov_iter *i, loff_t pos) 2 { 3 struct address_space *mapping = file->f_mapping; 4 const struct address_space_operations *a_ops = mapping->a_ops; ... 42 status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); 44 if (unlikely(status < 0)) But we fail when we try to probe the variable 'a_ops' at line 42 or 44. $ perf probe --add 'generic_perform_write:42 a_ops' Failed to find the location of a_ops at this address. Perhaps, it has been optimized out. This is because the source code do not match the assembly, so a variable may not be available in the source code line where it appears. After this patch, we can lookup the accurate byte offset range of a variable, 'INV' indicates that this variable is not valid at the given point, but available in the scope: $ perf probe --vars 'generic_perform_write:42' --range Available variables at generic_perform_write:42 @<generic_perform_write+141> [INV] ssize_t written @<generic_perform_write+[324-331]> [INV] struct address_space_operations* a_ops @<generic_perform_write+[55-61,170-176,223-246]> [VAL] (unknown_type) fsdata @<generic_perform_write+[70-307,346-411]> [VAL] loff_t pos @<generic_perform_write+[0-286,286-336,346-411]> [VAL] long int status @<generic_perform_write+[83-342,346-411]> [VAL] long unsigned int bytes @<generic_perform_write+[122-311,320-338,346-403,403-411]> [VAL] struct address_space* mapping @<generic_perform_write+[35-344,346-411]> [VAL] struct iov_iter* i @<generic_perform_write+[0-340,346-411]> [VAL] struct page* page @<generic_perform_write+[70-307,346-411]> Then it is more clear for us to add a probe with this variable: $ perf probe --add 'generic_perform_write+170 a_ops' Added new event: probe:generic_perform_write (on generic_perform_write+170 with a_ops) Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1431336304-16863-2-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-11 17:25:03 +08:00
return ret2;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
}
#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_LONG / sizeof(long))
static int convert_variable_type(Dwarf_Die *vr_die,
struct probe_trace_arg *tvar,
const char *cast, bool user_access)
{
struct probe_trace_arg_ref **ref_ptr = &tvar->ref;
Dwarf_Die type;
char buf[16];
char sbuf[STRERR_BUFSIZE];
int bsize, boffs, total;
int ret;
char prefix;
/* TODO: check all types */
perf probe: Add ustring support for perf probe command Kernel commit 88903c464321 ("tracing/probe: Add ustring type for user-space string") adds support for user-space strings when type 'ustring' is specified. Here is an example using sysfs command line interface for kprobes: Function to probe: struct filename * getname_flags(const char __user *filename, int flags, int *empty) Setup: # cd /sys/kernel/debug/tracing/ # echo 'p:tmr1 getname_flags +0(%r2):ustring' > kprobe_events # cat events/kprobes/tmr1/format | fgrep print print fmt: "(%lx) arg1=\"%s\"", REC->__probe_ip, REC->arg1 # echo 1 > events/kprobes/tmr1/enable # touch /tmp/111 # echo 0 > events/kprobes/tmr1/enable # cat trace|fgrep /tmp/111 touch-5846 [005] d..2 255520.717960: tmr1:\ (getname_flags+0x0/0x400) arg1="/tmp/111" Doing the same with the perf tool fails. Using type 'string' succeeds: # perf probe "vfs_getname=getname_flags:72 pathname=filename:string" Added new event: probe:vfs_getname (on getname_flags:72 with pathname=filename:string) .... # perf probe -d probe:vfs_getname Removed event: probe:vfs_getname However using type 'ustring' fails (output before): # perf probe "vfs_getname=getname_flags:72 pathname=filename:ustring" Failed to write event: Invalid argument Error: Failed to add events. # Fix this by adding type 'ustring' in function convert_variable_type(). Using ustring succeeds (output after): # ./perf probe "vfs_getname=getname_flags:72 pathname=filename:ustring" Added new event: probe:vfs_getname (on getname_flags:72 with pathname=filename:ustring) You can now use it in all perf tools, such as: perf record -e probe:vfs_getname -aR sleep 1 # Note: This issue also exists on x86, it is not s390 specific. Signed-off-by: Thomas Richter <tmricht@linux.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: sumanthk@linux.ibm.com Link: http://lore.kernel.org/lkml/20200120132011.64698-2-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-01-20 21:20:10 +08:00
if (cast && strcmp(cast, "string") != 0 && strcmp(cast, "ustring") &&
strcmp(cast, "x") != 0 &&
perf probe: Support signedness casting The 'perf probe' tool detects a variable's type and use the detected type to add a new probe. Then, kprobes prints its variable in hexadecimal format if the variable is unsigned and prints in decimal if it is signed. We sometimes want to see unsigned variable in decimal format (i.e. sector_t or size_t). In that case, we need to investigate the variable's size manually to specify just signedness. This patch add signedness casting support. By specifying "s" or "u" as a type, perf-probe will investigate variable size as usual and use the specified signedness. E.g. without this: $ perf probe -a 'submit_bio bio->bi_iter.bi_sector' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 $ cat trace_pipe|head dbench-9692 [003] d..1 971.096633: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x3a3d00 dbench-9692 [003] d..1 971.096685: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x1a3d80 dbench-9692 [003] d..1 971.096687: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x3a3d80 ... // need to investigate the variable size $ perf probe -a 'submit_bio bio->bi_iter.bi_sector:s64' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s64) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 With this: // just use "s" to cast its signedness $ perf probe -v -a 'submit_bio bio->bi_iter.bi_sector:s' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 $ cat trace_pipe|head dbench-9689 [001] d..1 1212.391237: submit_bio: (submit_bio+0x0/0x140) bi_sector=128 dbench-9689 [001] d..1 1212.391252: submit_bio: (submit_bio+0x0/0x140) bi_sector=131072 dbench-9697 [006] d..1 1212.398611: submit_bio: (submit_bio+0x0/0x140) bi_sector=30208 This commit also update perf-probe.txt to describe "types". Most parts are based on existing documentation: Documentation/trace/kprobetrace.txt Committer note: Testing using 'perf trace': # perf probe -a 'submit_bio bio->bi_iter.bi_sector' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 # trace --no-syscalls --ev probe:submit_bio 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=0xc133c0) 3181.861 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffb8) 3181.881 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffc0) 3184.488 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffc8) <SNIP> 4717.927 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x4dc7a88) 4717.970 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x4dc7880) ^C[root@jouet ~]# Now, using this new feature: [root@jouet ~]# perf probe -a 'submit_bio bio->bi_iter.bi_sector:s' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 [root@jouet ~]# trace --no-syscalls --ev probe:submit_bio 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145704) 0.017 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145712) 0.019 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145720) 2.567 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145728) 5631.919 probe:submit_bio:(ffffffffac3aee00) bi_sector=0) 5631.941 probe:submit_bio:(ffffffffac3aee00) bi_sector=8) 5631.945 probe:submit_bio:(ffffffffac3aee00) bi_sector=16) 5631.948 probe:submit_bio:(ffffffffac3aee00) bi_sector=24) ^C# With callchains: # trace --no-syscalls --ev probe:submit_bio/max-stack=10/ 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662544) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 0.023 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662552) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 0.027 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662560) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 2.593 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662568) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) journal_submit_commit_record+0xa82001ac ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa82012e8 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) ^C# Signed-off-by: Naohiro Aota <naohiro.aota@hgst.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1470710408-23515-1-git-send-email-naohiro.aota@hgst.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-08-09 10:40:08 +08:00
strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) {
/* Non string type is OK */
/* and respect signedness/hexadecimal cast */
tvar->type = strdup(cast);
return (tvar->type == NULL) ? -ENOMEM : 0;
}
bsize = dwarf_bitsize(vr_die);
if (bsize > 0) {
/* This is a bitfield */
boffs = dwarf_bitoffset(vr_die);
total = dwarf_bytesize(vr_die);
if (boffs < 0 || total < 0)
return -ENOENT;
ret = snprintf(buf, 16, "b%d@%d/%zd", bsize, boffs,
BYTES_TO_BITS(total));
goto formatted;
}
if (die_get_real_type(vr_die, &type) == NULL) {
pr_warning("Failed to get a type information of %s.\n",
dwarf_diename(vr_die));
return -ENOENT;
}
pr_debug("%s type is %s.\n",
dwarf_diename(vr_die), dwarf_diename(&type));
if (cast && (!strcmp(cast, "string") || !strcmp(cast, "ustring"))) {
/* String type */
ret = dwarf_tag(&type);
if (ret != DW_TAG_pointer_type &&
ret != DW_TAG_array_type) {
pr_warning("Failed to cast into string: "
"%s(%s) is not a pointer nor array.\n",
dwarf_diename(vr_die), dwarf_diename(&type));
return -EINVAL;
}
if (die_get_real_type(&type, &type) == NULL) {
pr_warning("Failed to get a type"
" information.\n");
return -ENOENT;
}
if (ret == DW_TAG_pointer_type) {
while (*ref_ptr)
ref_ptr = &(*ref_ptr)->next;
/* Add new reference with offset +0 */
*ref_ptr = zalloc(sizeof(struct probe_trace_arg_ref));
if (*ref_ptr == NULL) {
pr_warning("Out of memory error\n");
return -ENOMEM;
}
(*ref_ptr)->user_access = user_access;
}
if (!die_compare_name(&type, "char") &&
!die_compare_name(&type, "unsigned char")) {
pr_warning("Failed to cast into string: "
"%s is not (unsigned) char *.\n",
dwarf_diename(vr_die));
return -EINVAL;
}
tvar->type = strdup(cast);
return (tvar->type == NULL) ? -ENOMEM : 0;
}
perf probe: Support signedness casting The 'perf probe' tool detects a variable's type and use the detected type to add a new probe. Then, kprobes prints its variable in hexadecimal format if the variable is unsigned and prints in decimal if it is signed. We sometimes want to see unsigned variable in decimal format (i.e. sector_t or size_t). In that case, we need to investigate the variable's size manually to specify just signedness. This patch add signedness casting support. By specifying "s" or "u" as a type, perf-probe will investigate variable size as usual and use the specified signedness. E.g. without this: $ perf probe -a 'submit_bio bio->bi_iter.bi_sector' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 $ cat trace_pipe|head dbench-9692 [003] d..1 971.096633: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x3a3d00 dbench-9692 [003] d..1 971.096685: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x1a3d80 dbench-9692 [003] d..1 971.096687: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x3a3d80 ... // need to investigate the variable size $ perf probe -a 'submit_bio bio->bi_iter.bi_sector:s64' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s64) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 With this: // just use "s" to cast its signedness $ perf probe -v -a 'submit_bio bio->bi_iter.bi_sector:s' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 $ cat trace_pipe|head dbench-9689 [001] d..1 1212.391237: submit_bio: (submit_bio+0x0/0x140) bi_sector=128 dbench-9689 [001] d..1 1212.391252: submit_bio: (submit_bio+0x0/0x140) bi_sector=131072 dbench-9697 [006] d..1 1212.398611: submit_bio: (submit_bio+0x0/0x140) bi_sector=30208 This commit also update perf-probe.txt to describe "types". Most parts are based on existing documentation: Documentation/trace/kprobetrace.txt Committer note: Testing using 'perf trace': # perf probe -a 'submit_bio bio->bi_iter.bi_sector' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 # trace --no-syscalls --ev probe:submit_bio 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=0xc133c0) 3181.861 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffb8) 3181.881 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffc0) 3184.488 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffc8) <SNIP> 4717.927 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x4dc7a88) 4717.970 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x4dc7880) ^C[root@jouet ~]# Now, using this new feature: [root@jouet ~]# perf probe -a 'submit_bio bio->bi_iter.bi_sector:s' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 [root@jouet ~]# trace --no-syscalls --ev probe:submit_bio 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145704) 0.017 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145712) 0.019 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145720) 2.567 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145728) 5631.919 probe:submit_bio:(ffffffffac3aee00) bi_sector=0) 5631.941 probe:submit_bio:(ffffffffac3aee00) bi_sector=8) 5631.945 probe:submit_bio:(ffffffffac3aee00) bi_sector=16) 5631.948 probe:submit_bio:(ffffffffac3aee00) bi_sector=24) ^C# With callchains: # trace --no-syscalls --ev probe:submit_bio/max-stack=10/ 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662544) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 0.023 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662552) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 0.027 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662560) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 2.593 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662568) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) journal_submit_commit_record+0xa82001ac ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa82012e8 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) ^C# Signed-off-by: Naohiro Aota <naohiro.aota@hgst.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1470710408-23515-1-git-send-email-naohiro.aota@hgst.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-08-09 10:40:08 +08:00
if (cast && (strcmp(cast, "u") == 0))
prefix = 'u';
perf probe: Support signedness casting The 'perf probe' tool detects a variable's type and use the detected type to add a new probe. Then, kprobes prints its variable in hexadecimal format if the variable is unsigned and prints in decimal if it is signed. We sometimes want to see unsigned variable in decimal format (i.e. sector_t or size_t). In that case, we need to investigate the variable's size manually to specify just signedness. This patch add signedness casting support. By specifying "s" or "u" as a type, perf-probe will investigate variable size as usual and use the specified signedness. E.g. without this: $ perf probe -a 'submit_bio bio->bi_iter.bi_sector' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 $ cat trace_pipe|head dbench-9692 [003] d..1 971.096633: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x3a3d00 dbench-9692 [003] d..1 971.096685: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x1a3d80 dbench-9692 [003] d..1 971.096687: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x3a3d80 ... // need to investigate the variable size $ perf probe -a 'submit_bio bio->bi_iter.bi_sector:s64' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s64) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 With this: // just use "s" to cast its signedness $ perf probe -v -a 'submit_bio bio->bi_iter.bi_sector:s' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 $ cat trace_pipe|head dbench-9689 [001] d..1 1212.391237: submit_bio: (submit_bio+0x0/0x140) bi_sector=128 dbench-9689 [001] d..1 1212.391252: submit_bio: (submit_bio+0x0/0x140) bi_sector=131072 dbench-9697 [006] d..1 1212.398611: submit_bio: (submit_bio+0x0/0x140) bi_sector=30208 This commit also update perf-probe.txt to describe "types". Most parts are based on existing documentation: Documentation/trace/kprobetrace.txt Committer note: Testing using 'perf trace': # perf probe -a 'submit_bio bio->bi_iter.bi_sector' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 # trace --no-syscalls --ev probe:submit_bio 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=0xc133c0) 3181.861 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffb8) 3181.881 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffc0) 3184.488 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffc8) <SNIP> 4717.927 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x4dc7a88) 4717.970 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x4dc7880) ^C[root@jouet ~]# Now, using this new feature: [root@jouet ~]# perf probe -a 'submit_bio bio->bi_iter.bi_sector:s' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 [root@jouet ~]# trace --no-syscalls --ev probe:submit_bio 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145704) 0.017 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145712) 0.019 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145720) 2.567 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145728) 5631.919 probe:submit_bio:(ffffffffac3aee00) bi_sector=0) 5631.941 probe:submit_bio:(ffffffffac3aee00) bi_sector=8) 5631.945 probe:submit_bio:(ffffffffac3aee00) bi_sector=16) 5631.948 probe:submit_bio:(ffffffffac3aee00) bi_sector=24) ^C# With callchains: # trace --no-syscalls --ev probe:submit_bio/max-stack=10/ 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662544) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 0.023 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662552) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 0.027 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662560) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 2.593 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662568) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) journal_submit_commit_record+0xa82001ac ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa82012e8 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) ^C# Signed-off-by: Naohiro Aota <naohiro.aota@hgst.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1470710408-23515-1-git-send-email-naohiro.aota@hgst.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-08-09 10:40:08 +08:00
else if (cast && (strcmp(cast, "s") == 0))
prefix = 's';
else if (cast && (strcmp(cast, "x") == 0) &&
probe_type_is_available(PROBE_TYPE_X))
prefix = 'x';
perf probe: Support signedness casting The 'perf probe' tool detects a variable's type and use the detected type to add a new probe. Then, kprobes prints its variable in hexadecimal format if the variable is unsigned and prints in decimal if it is signed. We sometimes want to see unsigned variable in decimal format (i.e. sector_t or size_t). In that case, we need to investigate the variable's size manually to specify just signedness. This patch add signedness casting support. By specifying "s" or "u" as a type, perf-probe will investigate variable size as usual and use the specified signedness. E.g. without this: $ perf probe -a 'submit_bio bio->bi_iter.bi_sector' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 $ cat trace_pipe|head dbench-9692 [003] d..1 971.096633: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x3a3d00 dbench-9692 [003] d..1 971.096685: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x1a3d80 dbench-9692 [003] d..1 971.096687: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x3a3d80 ... // need to investigate the variable size $ perf probe -a 'submit_bio bio->bi_iter.bi_sector:s64' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s64) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 With this: // just use "s" to cast its signedness $ perf probe -v -a 'submit_bio bio->bi_iter.bi_sector:s' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 $ cat trace_pipe|head dbench-9689 [001] d..1 1212.391237: submit_bio: (submit_bio+0x0/0x140) bi_sector=128 dbench-9689 [001] d..1 1212.391252: submit_bio: (submit_bio+0x0/0x140) bi_sector=131072 dbench-9697 [006] d..1 1212.398611: submit_bio: (submit_bio+0x0/0x140) bi_sector=30208 This commit also update perf-probe.txt to describe "types". Most parts are based on existing documentation: Documentation/trace/kprobetrace.txt Committer note: Testing using 'perf trace': # perf probe -a 'submit_bio bio->bi_iter.bi_sector' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 # trace --no-syscalls --ev probe:submit_bio 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=0xc133c0) 3181.861 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffb8) 3181.881 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffc0) 3184.488 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffc8) <SNIP> 4717.927 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x4dc7a88) 4717.970 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x4dc7880) ^C[root@jouet ~]# Now, using this new feature: [root@jouet ~]# perf probe -a 'submit_bio bio->bi_iter.bi_sector:s' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 [root@jouet ~]# trace --no-syscalls --ev probe:submit_bio 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145704) 0.017 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145712) 0.019 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145720) 2.567 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145728) 5631.919 probe:submit_bio:(ffffffffac3aee00) bi_sector=0) 5631.941 probe:submit_bio:(ffffffffac3aee00) bi_sector=8) 5631.945 probe:submit_bio:(ffffffffac3aee00) bi_sector=16) 5631.948 probe:submit_bio:(ffffffffac3aee00) bi_sector=24) ^C# With callchains: # trace --no-syscalls --ev probe:submit_bio/max-stack=10/ 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662544) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 0.023 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662552) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 0.027 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662560) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 2.593 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662568) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) journal_submit_commit_record+0xa82001ac ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa82012e8 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) ^C# Signed-off-by: Naohiro Aota <naohiro.aota@hgst.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1470710408-23515-1-git-send-email-naohiro.aota@hgst.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-08-09 10:40:08 +08:00
else
prefix = die_is_signed_type(&type) ? 's' :
probe_type_is_available(PROBE_TYPE_X) ? 'x' : 'u';
perf probe: Support signedness casting The 'perf probe' tool detects a variable's type and use the detected type to add a new probe. Then, kprobes prints its variable in hexadecimal format if the variable is unsigned and prints in decimal if it is signed. We sometimes want to see unsigned variable in decimal format (i.e. sector_t or size_t). In that case, we need to investigate the variable's size manually to specify just signedness. This patch add signedness casting support. By specifying "s" or "u" as a type, perf-probe will investigate variable size as usual and use the specified signedness. E.g. without this: $ perf probe -a 'submit_bio bio->bi_iter.bi_sector' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 $ cat trace_pipe|head dbench-9692 [003] d..1 971.096633: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x3a3d00 dbench-9692 [003] d..1 971.096685: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x1a3d80 dbench-9692 [003] d..1 971.096687: submit_bio: (submit_bio+0x0/0x140) bi_sector=0x3a3d80 ... // need to investigate the variable size $ perf probe -a 'submit_bio bio->bi_iter.bi_sector:s64' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s64) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 With this: // just use "s" to cast its signedness $ perf probe -v -a 'submit_bio bio->bi_iter.bi_sector:s' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 $ cat trace_pipe|head dbench-9689 [001] d..1 1212.391237: submit_bio: (submit_bio+0x0/0x140) bi_sector=128 dbench-9689 [001] d..1 1212.391252: submit_bio: (submit_bio+0x0/0x140) bi_sector=131072 dbench-9697 [006] d..1 1212.398611: submit_bio: (submit_bio+0x0/0x140) bi_sector=30208 This commit also update perf-probe.txt to describe "types". Most parts are based on existing documentation: Documentation/trace/kprobetrace.txt Committer note: Testing using 'perf trace': # perf probe -a 'submit_bio bio->bi_iter.bi_sector' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 # trace --no-syscalls --ev probe:submit_bio 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=0xc133c0) 3181.861 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffb8) 3181.881 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffc0) 3184.488 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x6cffc8) <SNIP> 4717.927 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x4dc7a88) 4717.970 probe:submit_bio:(ffffffffac3aee00) bi_sector=0x4dc7880) ^C[root@jouet ~]# Now, using this new feature: [root@jouet ~]# perf probe -a 'submit_bio bio->bi_iter.bi_sector:s' Added new event: probe:submit_bio (on submit_bio with bi_sector=bio->bi_iter.bi_sector:s) You can now use it in all perf tools, such as: perf record -e probe:submit_bio -aR sleep 1 [root@jouet ~]# trace --no-syscalls --ev probe:submit_bio 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145704) 0.017 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145712) 0.019 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145720) 2.567 probe:submit_bio:(ffffffffac3aee00) bi_sector=7145728) 5631.919 probe:submit_bio:(ffffffffac3aee00) bi_sector=0) 5631.941 probe:submit_bio:(ffffffffac3aee00) bi_sector=8) 5631.945 probe:submit_bio:(ffffffffac3aee00) bi_sector=16) 5631.948 probe:submit_bio:(ffffffffac3aee00) bi_sector=24) ^C# With callchains: # trace --no-syscalls --ev probe:submit_bio/max-stack=10/ 0.000 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662544) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 0.023 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662552) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 0.027 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662560) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa8200691 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) 2.593 probe:submit_bio:(ffffffffac3aee00) bi_sector=50662568) submit_bio+0xa8200001 ([kernel.kallsyms]) submit_bh+0xa8200013 ([kernel.kallsyms]) journal_submit_commit_record+0xa82001ac ([kernel.kallsyms]) jbd2_journal_commit_transaction+0xa82012e8 ([kernel.kallsyms]) kjournald2+0xa82000ca ([kernel.kallsyms]) kthread+0xa82000d8 ([kernel.kallsyms]) ret_from_fork+0xa820001f ([kernel.kallsyms]) ^C# Signed-off-by: Naohiro Aota <naohiro.aota@hgst.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1470710408-23515-1-git-send-email-naohiro.aota@hgst.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-08-09 10:40:08 +08:00
ret = dwarf_bytesize(&type);
if (ret <= 0)
/* No size ... try to use default type */
return 0;
ret = BYTES_TO_BITS(ret);
/* Check the bitwidth */
if (ret > MAX_BASIC_TYPE_BITS) {
pr_info("%s exceeds max-bitwidth. Cut down to %d bits.\n",
dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
ret = MAX_BASIC_TYPE_BITS;
}
ret = snprintf(buf, 16, "%c%d", prefix, ret);
formatted:
if (ret < 0 || ret >= 16) {
if (ret >= 16)
ret = -E2BIG;
pr_warning("Failed to convert variable type: %s\n",
str_error_r(-ret, sbuf, sizeof(sbuf)));
return ret;
}
tvar->type = strdup(buf);
if (tvar->type == NULL)
return -ENOMEM;
return 0;
}
static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
struct perf_probe_arg_field *field,
struct probe_trace_arg_ref **ref_ptr,
Dwarf_Die *die_mem, bool user_access)
{
struct probe_trace_arg_ref *ref = *ref_ptr;
Dwarf_Die type;
Dwarf_Word offs;
int ret, tag;
pr_debug("converting %s in %s\n", field->name, varname);
if (die_get_real_type(vr_die, &type) == NULL) {
pr_warning("Failed to get the type of %s.\n", varname);
return -ENOENT;
}
pr_debug2("Var real type: %s (%x)\n", dwarf_diename(&type),
(unsigned)dwarf_dieoffset(&type));
tag = dwarf_tag(&type);
if (field->name[0] == '[' &&
(tag == DW_TAG_array_type || tag == DW_TAG_pointer_type)) {
/* Save original type for next field or type */
memcpy(die_mem, &type, sizeof(*die_mem));
/* Get the type of this array */
if (die_get_real_type(&type, &type) == NULL) {
pr_warning("Failed to get the type of %s.\n", varname);
return -ENOENT;
}
pr_debug2("Array real type: %s (%x)\n", dwarf_diename(&type),
(unsigned)dwarf_dieoffset(&type));
if (tag == DW_TAG_pointer_type) {
ref = zalloc(sizeof(struct probe_trace_arg_ref));
if (ref == NULL)
return -ENOMEM;
if (*ref_ptr)
(*ref_ptr)->next = ref;
else
*ref_ptr = ref;
}
ref->offset += dwarf_bytesize(&type) * field->index;
ref->user_access = user_access;
goto next;
} else if (tag == DW_TAG_pointer_type) {
/* Check the pointer and dereference */
if (!field->ref) {
pr_err("Semantic error: %s must be referred by '->'\n",
field->name);
return -EINVAL;
}
/* Get the type pointed by this pointer */
if (die_get_real_type(&type, &type) == NULL) {
pr_warning("Failed to get the type of %s.\n", varname);
return -ENOENT;
}
/* Verify it is a data structure */
tag = dwarf_tag(&type);
if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) {
pr_warning("%s is not a data structure nor a union.\n",
varname);
return -EINVAL;
}
ref = zalloc(sizeof(struct probe_trace_arg_ref));
if (ref == NULL)
return -ENOMEM;
if (*ref_ptr)
(*ref_ptr)->next = ref;
else
*ref_ptr = ref;
} else {
/* Verify it is a data structure */
if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) {
pr_warning("%s is not a data structure nor a union.\n",
varname);
return -EINVAL;
}
if (field->name[0] == '[') {
pr_err("Semantic error: %s is not a pointer"
" nor array.\n", varname);
return -EINVAL;
}
perf probe: Fix to track down unnamed union/structure members Fix 'perf probe' to track down unnamed union/structure members. perf probe did not track down the tree of unnamed union/structure members, since it just failed to find given "name" in a parent structure/union. To solve this issue, I've introduced 2 changes. - Fix die_find_member() to track down the type-DIE if it is unnamed, and if it contains the specified member, returns the unnamed member. (note that we don't return found member, since unnamed member has the offset in the parent structure) - Fix convert_variable_fields() to track down the unnamed union/ structure (one-by-one). With this patch, perf probe can access unnamed fields: ----- #./perf probe -nfx ./perf lock__delete ops 'locked_ops=ops->locked.ops' Added new event: probe_perf:lock__delete (on lock__delete in /home/mhiramat/ksrc/linux-3/tools/perf/perf with ops locked_ops=ops->locked.ops) You can now use it in all perf tools, such as: perf record -e probe_perf:lock__delete -aR sleep 1 ----- Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org> Report-Link: https://lkml.org/lkml/2015/3/5/431 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150402073312.14482.37942.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-02 15:33:12 +08:00
/* While prcessing unnamed field, we don't care about this */
if (field->ref && dwarf_diename(vr_die)) {
pr_err("Semantic error: %s must be referred by '.'\n",
field->name);
return -EINVAL;
}
if (!ref) {
pr_warning("Structure on a register is not "
"supported yet.\n");
return -ENOTSUP;
}
}
if (die_find_member(&type, field->name, die_mem) == NULL) {
pr_warning("%s(type:%s) has no member %s.\n", varname,
dwarf_diename(&type), field->name);
return -EINVAL;
}
/* Get the offset of the field */
if (tag == DW_TAG_union_type) {
offs = 0;
} else {
ret = die_get_data_member_location(die_mem, &offs);
if (ret < 0) {
pr_warning("Failed to get the offset of %s.\n",
field->name);
return ret;
}
}
ref->offset += (long)offs;
ref->user_access = user_access;
perf probe: Fix to track down unnamed union/structure members Fix 'perf probe' to track down unnamed union/structure members. perf probe did not track down the tree of unnamed union/structure members, since it just failed to find given "name" in a parent structure/union. To solve this issue, I've introduced 2 changes. - Fix die_find_member() to track down the type-DIE if it is unnamed, and if it contains the specified member, returns the unnamed member. (note that we don't return found member, since unnamed member has the offset in the parent structure) - Fix convert_variable_fields() to track down the unnamed union/ structure (one-by-one). With this patch, perf probe can access unnamed fields: ----- #./perf probe -nfx ./perf lock__delete ops 'locked_ops=ops->locked.ops' Added new event: probe_perf:lock__delete (on lock__delete in /home/mhiramat/ksrc/linux-3/tools/perf/perf with ops locked_ops=ops->locked.ops) You can now use it in all perf tools, such as: perf record -e probe_perf:lock__delete -aR sleep 1 ----- Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org> Report-Link: https://lkml.org/lkml/2015/3/5/431 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150402073312.14482.37942.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-02 15:33:12 +08:00
/* If this member is unnamed, we need to reuse this field */
if (!dwarf_diename(die_mem))
return convert_variable_fields(die_mem, varname, field,
&ref, die_mem, user_access);
perf probe: Fix to track down unnamed union/structure members Fix 'perf probe' to track down unnamed union/structure members. perf probe did not track down the tree of unnamed union/structure members, since it just failed to find given "name" in a parent structure/union. To solve this issue, I've introduced 2 changes. - Fix die_find_member() to track down the type-DIE if it is unnamed, and if it contains the specified member, returns the unnamed member. (note that we don't return found member, since unnamed member has the offset in the parent structure) - Fix convert_variable_fields() to track down the unnamed union/ structure (one-by-one). With this patch, perf probe can access unnamed fields: ----- #./perf probe -nfx ./perf lock__delete ops 'locked_ops=ops->locked.ops' Added new event: probe_perf:lock__delete (on lock__delete in /home/mhiramat/ksrc/linux-3/tools/perf/perf with ops locked_ops=ops->locked.ops) You can now use it in all perf tools, such as: perf record -e probe_perf:lock__delete -aR sleep 1 ----- Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org> Report-Link: https://lkml.org/lkml/2015/3/5/431 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150402073312.14482.37942.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-02 15:33:12 +08:00
next:
/* Converting next field */
if (field->next)
return convert_variable_fields(die_mem, field->name,
field->next, &ref, die_mem, user_access);
else
return 0;
}
perf probe: Trace a magic number if variable is not found Trace a magic number as immediate value if the target variable is not found at some probe points which is based on one probe event. This feature is good for the case if you trace a source code line with some local variables, which is compiled into several instructions and some of the variables are optimized out on some instructions. Even if so, with this feature, perf probe trace a magic number instead of such disappeared variables and fold those probes on one event. E.g. without this patch: # perf probe -D "pud_page_vaddr pud" Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+23558082 pud=%ax:x64 p:probe/pud_page_vaddr _text+328373 pud=%r8:x64 p:probe/pud_page_vaddr _text+348448 pud=%bx:x64 p:probe/pud_page_vaddr _text+23816818 pud=%bx:x64 With this patch: # perf probe -D "pud_page_vaddr pud" | head spurious_kernel_fault is blacklisted function, skip it. vmalloc_fault is blacklisted function, skip it. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+149051 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+315926 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23807209 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23557365 pud=%ax:x64 p:probe/pud_page_vaddr _text+314097 pud=%di:x64 p:probe/pud_page_vaddr _text+314015 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+313893 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+324083 pud=\deade12d:x64 Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Link: http://lore.kernel.org/lkml/157406476931.24476.6261475888681844285.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-18 16:12:49 +08:00
static void print_var_not_found(const char *varname)
{
pr_err("Failed to find the location of the '%s' variable at this address.\n"
" Perhaps it has been optimized out.\n"
" Use -V with the --range option to show '%s' location range.\n",
varname, varname);
}
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
/* Show a variables in kprobe event format */
static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
{
Dwarf_Die die_mem;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
int ret;
pr_debug("Converting variable %s into trace event.\n",
dwarf_diename(vr_die));
ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
&pf->sp_die, pf->machine, pf->tvar);
perf probe: Trace a magic number if variable is not found Trace a magic number as immediate value if the target variable is not found at some probe points which is based on one probe event. This feature is good for the case if you trace a source code line with some local variables, which is compiled into several instructions and some of the variables are optimized out on some instructions. Even if so, with this feature, perf probe trace a magic number instead of such disappeared variables and fold those probes on one event. E.g. without this patch: # perf probe -D "pud_page_vaddr pud" Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+23558082 pud=%ax:x64 p:probe/pud_page_vaddr _text+328373 pud=%r8:x64 p:probe/pud_page_vaddr _text+348448 pud=%bx:x64 p:probe/pud_page_vaddr _text+23816818 pud=%bx:x64 With this patch: # perf probe -D "pud_page_vaddr pud" | head spurious_kernel_fault is blacklisted function, skip it. vmalloc_fault is blacklisted function, skip it. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+149051 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+315926 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23807209 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23557365 pud=%ax:x64 p:probe/pud_page_vaddr _text+314097 pud=%di:x64 p:probe/pud_page_vaddr _text+314015 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+313893 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+324083 pud=\deade12d:x64 Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Link: http://lore.kernel.org/lkml/157406476931.24476.6261475888681844285.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-18 16:12:49 +08:00
if (ret == -ENOENT && pf->skip_empty_arg)
/* This can be found in other place. skip it */
return 0;
if (ret == -ENOENT || ret == -EINVAL) {
perf probe: Trace a magic number if variable is not found Trace a magic number as immediate value if the target variable is not found at some probe points which is based on one probe event. This feature is good for the case if you trace a source code line with some local variables, which is compiled into several instructions and some of the variables are optimized out on some instructions. Even if so, with this feature, perf probe trace a magic number instead of such disappeared variables and fold those probes on one event. E.g. without this patch: # perf probe -D "pud_page_vaddr pud" Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+23558082 pud=%ax:x64 p:probe/pud_page_vaddr _text+328373 pud=%r8:x64 p:probe/pud_page_vaddr _text+348448 pud=%bx:x64 p:probe/pud_page_vaddr _text+23816818 pud=%bx:x64 With this patch: # perf probe -D "pud_page_vaddr pud" | head spurious_kernel_fault is blacklisted function, skip it. vmalloc_fault is blacklisted function, skip it. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+149051 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+315926 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23807209 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23557365 pud=%ax:x64 p:probe/pud_page_vaddr _text+314097 pud=%di:x64 p:probe/pud_page_vaddr _text+314015 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+313893 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+324083 pud=\deade12d:x64 Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Link: http://lore.kernel.org/lkml/157406476931.24476.6261475888681844285.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-18 16:12:49 +08:00
print_var_not_found(pf->pvar->var);
} else if (ret == -ENOTSUP)
pr_err("Sorry, we don't support this variable location yet.\n");
else if (ret == 0 && pf->pvar->field) {
ret = convert_variable_fields(vr_die, pf->pvar->var,
pf->pvar->field, &pf->tvar->ref,
&die_mem, pf->pvar->user_access);
vr_die = &die_mem;
}
if (ret == 0)
ret = convert_variable_type(vr_die, pf->tvar, pf->pvar->type,
pf->pvar->user_access);
/* *expr will be cached in libdw. Don't free it. */
return ret;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
}
/* Find a variable in a scope DIE */
static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
{
perf probe: Avoid searching variables in intermediate scopes Fix variable searching logic to search one in inner than local scope or global(CU) scope. In the other words, skip searching in intermediate scopes. e.g., in the following code, int var1; void inline infunc(int i) { i++; <--- [A] } void func(void) { int var1, var2; infunc(var2); } At [A], "var1" should point the global variable "var1", however, if user mis-typed as "var2", variable search should be failed. However, current logic searches variable infunc() scope, global scope, and then func() scope. Thus, it can find "var2" variable in func() scope. This may not be what user expects. So, it would better not search outer scopes except outermost (compile unit) scope which contains only global variables, when it failed to find given variable in local scope. E.g. Without this: $ perf probe -V pre_schedule --externs > without.vars With this: $ perf probe -V pre_schedule --externs > with.vars Check the diff: $ diff without.vars with.vars 88d87 < int cpu 133d131 < long unsigned int* switch_count These vars are actually in the scope of schedule(), the caller of pre_schedule(). Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20110811110305.19900.94374.stgit@fedora15 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-08-11 19:03:05 +08:00
Dwarf_Die vr_die;
char *buf, *ptr;
perf probe: Avoid searching variables in intermediate scopes Fix variable searching logic to search one in inner than local scope or global(CU) scope. In the other words, skip searching in intermediate scopes. e.g., in the following code, int var1; void inline infunc(int i) { i++; <--- [A] } void func(void) { int var1, var2; infunc(var2); } At [A], "var1" should point the global variable "var1", however, if user mis-typed as "var2", variable search should be failed. However, current logic searches variable infunc() scope, global scope, and then func() scope. Thus, it can find "var2" variable in func() scope. This may not be what user expects. So, it would better not search outer scopes except outermost (compile unit) scope which contains only global variables, when it failed to find given variable in local scope. E.g. Without this: $ perf probe -V pre_schedule --externs > without.vars With this: $ perf probe -V pre_schedule --externs > with.vars Check the diff: $ diff without.vars with.vars 88d87 < int cpu 133d131 < long unsigned int* switch_count These vars are actually in the scope of schedule(), the caller of pre_schedule(). Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20110811110305.19900.94374.stgit@fedora15 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-08-11 19:03:05 +08:00
int ret = 0;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
perf probe: Support probing at absolute address It should be useful to allow 'perf probe' probe at absolute offset of a target. For example, when (u)probing at a instruction of a shared object in a embedded system where debuginfo is not avaliable but we know the offset of that instruction by manually digging. This patch enables following perf probe command syntax: # perf probe 0xffffffff811e6615 And # perf probe /lib/x86_64-linux-gnu/libc-2.19.so 0xeb860 In the above example, we don't need a anchor symbol, so it is possible to compute absolute addresses using other methods and then use 'perf probe' to create the probing points. v1 -> v2: Drop the leading '+' in cmdline; Allow uprobing at offset 0x0; Improve 'perf probe -l' result when uprobe at area without debuginfo. v2 -> v3: Split bugfix to a separated patch. Test result: # perf probe 0xffffffff8119d175 %ax # perf probe sys_write %ax # perf probe /lib64/libc-2.18.so 0x0 %ax # perf probe /lib64/libc-2.18.so 0x5 %ax # perf probe /lib64/libc-2.18.so 0xd8e40 %ax # perf probe /lib64/libc-2.18.so __write %ax # perf probe /lib64/libc-2.18.so 0xd8e49 %ax # cat /sys/kernel/debug/tracing/uprobe_events p:probe_libc/abs_0 /lib64/libc-2.18.so:0x (null) arg1=%ax p:probe_libc/abs_5 /lib64/libc-2.18.so:0x0000000000000005 arg1=%ax p:probe_libc/abs_d8e40 /lib64/libc-2.18.so:0x00000000000d8e40 arg1=%ax p:probe_libc/__write /lib64/libc-2.18.so:0x00000000000d8e40 arg1=%ax p:probe_libc/abs_d8e49 /lib64/libc-2.18.so:0x00000000000d8e49 arg1=%ax # cat /sys/kernel/debug/tracing/kprobe_events p:probe/abs_ffffffff8119d175 0xffffffff8119d175 arg1=%ax p:probe/sys_write _text+1692016 arg1=%ax # perf probe -l Failed to find debug information for address 5 probe:abs_ffffffff8119d175 (on sys_write+5 with arg1) probe:sys_write (on sys_write with arg1) probe_libc:__write (on @unix/syscall-template.S:81 in /lib64/libc-2.18.so with arg1) probe_libc:abs_0 (on 0x0 in /lib64/libc-2.18.so with arg1) probe_libc:abs_5 (on 0x5 in /lib64/libc-2.18.so with arg1) probe_libc:abs_d8e40 (on @unix/syscall-template.S:81 in /lib64/libc-2.18.so with arg1) probe_libc:abs_d8e49 (on __GI___libc_write+9 in /lib64/libc-2.18.so with arg1) Signed-off-by: Wang Nan <wangnan0@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1440586666-235233-7-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-26 18:57:45 +08:00
/* Copy raw parameters */
if (!is_c_varname(pf->pvar->var))
return copy_to_probe_trace_arg(pf->tvar, pf->pvar);
if (pf->pvar->name)
pf->tvar->name = strdup(pf->pvar->name);
else {
buf = synthesize_perf_probe_arg(pf->pvar);
if (!buf)
return -ENOMEM;
ptr = strchr(buf, ':'); /* Change type separator to _ */
if (ptr)
*ptr = '_';
pf->tvar->name = buf;
}
if (pf->tvar->name == NULL)
return -ENOMEM;
perf probe: Avoid searching variables in intermediate scopes Fix variable searching logic to search one in inner than local scope or global(CU) scope. In the other words, skip searching in intermediate scopes. e.g., in the following code, int var1; void inline infunc(int i) { i++; <--- [A] } void func(void) { int var1, var2; infunc(var2); } At [A], "var1" should point the global variable "var1", however, if user mis-typed as "var2", variable search should be failed. However, current logic searches variable infunc() scope, global scope, and then func() scope. Thus, it can find "var2" variable in func() scope. This may not be what user expects. So, it would better not search outer scopes except outermost (compile unit) scope which contains only global variables, when it failed to find given variable in local scope. E.g. Without this: $ perf probe -V pre_schedule --externs > without.vars With this: $ perf probe -V pre_schedule --externs > with.vars Check the diff: $ diff without.vars with.vars 88d87 < int cpu 133d131 < long unsigned int* switch_count These vars are actually in the scope of schedule(), the caller of pre_schedule(). Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20110811110305.19900.94374.stgit@fedora15 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-08-11 19:03:05 +08:00
pr_debug("Searching '%s' variable in context.\n", pf->pvar->var);
/* Search child die for local variables and parameters. */
perf probe: Avoid searching variables in intermediate scopes Fix variable searching logic to search one in inner than local scope or global(CU) scope. In the other words, skip searching in intermediate scopes. e.g., in the following code, int var1; void inline infunc(int i) { i++; <--- [A] } void func(void) { int var1, var2; infunc(var2); } At [A], "var1" should point the global variable "var1", however, if user mis-typed as "var2", variable search should be failed. However, current logic searches variable infunc() scope, global scope, and then func() scope. Thus, it can find "var2" variable in func() scope. This may not be what user expects. So, it would better not search outer scopes except outermost (compile unit) scope which contains only global variables, when it failed to find given variable in local scope. E.g. Without this: $ perf probe -V pre_schedule --externs > without.vars With this: $ perf probe -V pre_schedule --externs > with.vars Check the diff: $ diff without.vars with.vars 88d87 < int cpu 133d131 < long unsigned int* switch_count These vars are actually in the scope of schedule(), the caller of pre_schedule(). Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20110811110305.19900.94374.stgit@fedora15 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-08-11 19:03:05 +08:00
if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) {
/* Search again in global variables */
perf probe: Fix bug with global variables handling There are missing curly braces which causes find_variable() return wrong value when probing with global variables. This problem can be reproduced as following: $ perf probe -v --add='generic_perform_write global_variable_for_test' ... Try to find probe point from debuginfo. Probe point found: generic_perform_write+0 Searching 'global_variable_for_test' variable in context. An error occurred in debuginfo analysis (-2). Error: Failed to add events. Reason: No such file or directory (Code: -2) After this patch: $ perf probe -v --add='generic_perform_write global_variable_for_test' ... Converting variable global_variable_for_test into trace event. global_variable_for_test type is int. Found 1 probe_trace_events. Opening /sys/kernel/debug/tracing/kprobe_events write=1 Added new event: Writing event: p:probe/generic_perform_write _stext+1237464 global_variable_for_test=@global_variable_for_test+0:s32 probe:generic_perform_write (on generic_perform_write with global_variable_for_test) You can now use it in all perf tools, such as: perf record -e probe:generic_perform_write -aR sleep 1 Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1429949338-18678-1-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-25 16:08:58 +08:00
if (!die_find_variable_at(&pf->cu_die, pf->pvar->var,
0, &vr_die)) {
perf probe: Trace a magic number if variable is not found Trace a magic number as immediate value if the target variable is not found at some probe points which is based on one probe event. This feature is good for the case if you trace a source code line with some local variables, which is compiled into several instructions and some of the variables are optimized out on some instructions. Even if so, with this feature, perf probe trace a magic number instead of such disappeared variables and fold those probes on one event. E.g. without this patch: # perf probe -D "pud_page_vaddr pud" Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+23558082 pud=%ax:x64 p:probe/pud_page_vaddr _text+328373 pud=%r8:x64 p:probe/pud_page_vaddr _text+348448 pud=%bx:x64 p:probe/pud_page_vaddr _text+23816818 pud=%bx:x64 With this patch: # perf probe -D "pud_page_vaddr pud" | head spurious_kernel_fault is blacklisted function, skip it. vmalloc_fault is blacklisted function, skip it. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+149051 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+315926 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23807209 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23557365 pud=%ax:x64 p:probe/pud_page_vaddr _text+314097 pud=%di:x64 p:probe/pud_page_vaddr _text+314015 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+313893 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+324083 pud=\deade12d:x64 Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Link: http://lore.kernel.org/lkml/157406476931.24476.6261475888681844285.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-18 16:12:49 +08:00
if (pf->skip_empty_arg)
return 0;
pr_warning("Failed to find '%s' in this function.\n",
pf->pvar->var);
perf probe: Avoid searching variables in intermediate scopes Fix variable searching logic to search one in inner than local scope or global(CU) scope. In the other words, skip searching in intermediate scopes. e.g., in the following code, int var1; void inline infunc(int i) { i++; <--- [A] } void func(void) { int var1, var2; infunc(var2); } At [A], "var1" should point the global variable "var1", however, if user mis-typed as "var2", variable search should be failed. However, current logic searches variable infunc() scope, global scope, and then func() scope. Thus, it can find "var2" variable in func() scope. This may not be what user expects. So, it would better not search outer scopes except outermost (compile unit) scope which contains only global variables, when it failed to find given variable in local scope. E.g. Without this: $ perf probe -V pre_schedule --externs > without.vars With this: $ perf probe -V pre_schedule --externs > with.vars Check the diff: $ diff without.vars with.vars 88d87 < int cpu 133d131 < long unsigned int* switch_count These vars are actually in the scope of schedule(), the caller of pre_schedule(). Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20110811110305.19900.94374.stgit@fedora15 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-08-11 19:03:05 +08:00
ret = -ENOENT;
perf probe: Fix bug with global variables handling There are missing curly braces which causes find_variable() return wrong value when probing with global variables. This problem can be reproduced as following: $ perf probe -v --add='generic_perform_write global_variable_for_test' ... Try to find probe point from debuginfo. Probe point found: generic_perform_write+0 Searching 'global_variable_for_test' variable in context. An error occurred in debuginfo analysis (-2). Error: Failed to add events. Reason: No such file or directory (Code: -2) After this patch: $ perf probe -v --add='generic_perform_write global_variable_for_test' ... Converting variable global_variable_for_test into trace event. global_variable_for_test type is int. Found 1 probe_trace_events. Opening /sys/kernel/debug/tracing/kprobe_events write=1 Added new event: Writing event: p:probe/generic_perform_write _stext+1237464 global_variable_for_test=@global_variable_for_test+0:s32 probe:generic_perform_write (on generic_perform_write with global_variable_for_test) You can now use it in all perf tools, such as: perf record -e probe:generic_perform_write -aR sleep 1 Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1429949338-18678-1-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-25 16:08:58 +08:00
}
}
if (ret >= 0)
perf probe: Avoid searching variables in intermediate scopes Fix variable searching logic to search one in inner than local scope or global(CU) scope. In the other words, skip searching in intermediate scopes. e.g., in the following code, int var1; void inline infunc(int i) { i++; <--- [A] } void func(void) { int var1, var2; infunc(var2); } At [A], "var1" should point the global variable "var1", however, if user mis-typed as "var2", variable search should be failed. However, current logic searches variable infunc() scope, global scope, and then func() scope. Thus, it can find "var2" variable in func() scope. This may not be what user expects. So, it would better not search outer scopes except outermost (compile unit) scope which contains only global variables, when it failed to find given variable in local scope. E.g. Without this: $ perf probe -V pre_schedule --externs > without.vars With this: $ perf probe -V pre_schedule --externs > with.vars Check the diff: $ diff without.vars with.vars 88d87 < int cpu 133d131 < long unsigned int* switch_count These vars are actually in the scope of schedule(), the caller of pre_schedule(). Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20110811110305.19900.94374.stgit@fedora15 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-08-11 19:03:05 +08:00
ret = convert_variable(&vr_die, pf);
return ret;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
}
/* Convert subprogram DIE to trace point */
perf probe: Fix probing symbols with optimization suffix Fix perf probe to probe on some symbols which have some optimzation suffixes, e.g. ".part", ".isra", and ".constprop". To fix this issue, instead of using the DIE name, perf probe uses the symbol name found by dwfl_module_addrsym(). This also involves a perf probe --vars operation update which now shows the symbol name instead of the DIE name. Without this patch, putting a probe on an inlined function which was compiled with a suffixed symbol will fail like this: $ perf probe -v getname_flags probe-definition(0): getname_flags symbol:getname_flags file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments Looking at the vmlinux_path (6 entries long) Using /lib/modules/3.11.0+/build/vmlinux for symbols found inline addr: 0xffffffff8119bb70 Probe point found: getname_flags+0 found inline addr: 0xffffffff8119bcb6 Probe point found: getname+6 found inline addr: 0xffffffff811a06a6 Probe point found: user_path_at_empty+6 find 3 probe_trace_events. Opening /sys/kernel/debug//tracing/kprobe_events write=1 Added new events: Writing event: p:probe/getname_flags getname_flags+0 Failed to write event: No such file or directory Error: Failed to add events. (-1) Because the debuginfo knows only the original (non suffix) symbol name, it uses the original symbol for probe address but the kernel (kallsyms) knows only suffixed symbol. Then, the kernel rejects that original symbol. This patch uses dwfl_module_addrsym() to get the correct (suffixed) symbol from symtab when a probe point is found. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130925131616.31632.46658.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-25 21:16:16 +08:00
static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
Dwarf_Addr paddr, bool retprobe,
const char *function,
perf probe: Fix probing symbols with optimization suffix Fix perf probe to probe on some symbols which have some optimzation suffixes, e.g. ".part", ".isra", and ".constprop". To fix this issue, instead of using the DIE name, perf probe uses the symbol name found by dwfl_module_addrsym(). This also involves a perf probe --vars operation update which now shows the symbol name instead of the DIE name. Without this patch, putting a probe on an inlined function which was compiled with a suffixed symbol will fail like this: $ perf probe -v getname_flags probe-definition(0): getname_flags symbol:getname_flags file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments Looking at the vmlinux_path (6 entries long) Using /lib/modules/3.11.0+/build/vmlinux for symbols found inline addr: 0xffffffff8119bb70 Probe point found: getname_flags+0 found inline addr: 0xffffffff8119bcb6 Probe point found: getname+6 found inline addr: 0xffffffff811a06a6 Probe point found: user_path_at_empty+6 find 3 probe_trace_events. Opening /sys/kernel/debug//tracing/kprobe_events write=1 Added new events: Writing event: p:probe/getname_flags getname_flags+0 Failed to write event: No such file or directory Error: Failed to add events. (-1) Because the debuginfo knows only the original (non suffix) symbol name, it uses the original symbol for probe address but the kernel (kallsyms) knows only suffixed symbol. Then, the kernel rejects that original symbol. This patch uses dwfl_module_addrsym() to get the correct (suffixed) symbol from symtab when a probe point is found. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130925131616.31632.46658.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-25 21:16:16 +08:00
struct probe_trace_point *tp)
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
{
perf probe: Fix wrong address verification Since there are some DIE which has only ranges instead of the combination of entrypc/highpc, address verification must use dwarf_haspc() instead of dwarf_entrypc/dwarf_highpc. Also, the ranges only DIE will have a partial code in different section (e.g. unlikely code will be in text.unlikely as "FUNC.cold" symbol). In that case, we can not use dwarf_entrypc() or die_entrypc(), because the offset from original DIE can be a minus value. Instead, this simply gets the symbol and offset from symtab. Without this patch; # perf probe -D clear_tasks_mm_cpumask:1 Failed to get entry address of clear_tasks_mm_cpumask Error: Failed to add events. And with this patch: # perf probe -D clear_tasks_mm_cpumask:1 p:probe/clear_tasks_mm_cpumask clear_tasks_mm_cpumask+0 p:probe/clear_tasks_mm_cpumask_1 clear_tasks_mm_cpumask+5 p:probe/clear_tasks_mm_cpumask_2 clear_tasks_mm_cpumask+8 p:probe/clear_tasks_mm_cpumask_3 clear_tasks_mm_cpumask+16 p:probe/clear_tasks_mm_cpumask_4 clear_tasks_mm_cpumask+82 Committer testing: I managed to reproduce the above: [root@quaco ~]# perf probe -D clear_tasks_mm_cpumask:1 p:probe/clear_tasks_mm_cpumask _text+919968 p:probe/clear_tasks_mm_cpumask_1 _text+919973 p:probe/clear_tasks_mm_cpumask_2 _text+919976 [root@quaco ~]# But then when trying to actually put the probe in place, it fails if I use :0 as the offset: [root@quaco ~]# perf probe -L clear_tasks_mm_cpumask | head -5 <clear_tasks_mm_cpumask@/usr/src/debug/kernel-5.2.fc30/linux-5.2.18-200.fc30.x86_64/kernel/cpu.c:0> 0 void clear_tasks_mm_cpumask(int cpu) 1 { 2 struct task_struct *p; [root@quaco ~]# perf probe clear_tasks_mm_cpumask:0 Probe point 'clear_tasks_mm_cpumask' not found. Error: Failed to add events. [root@quaco The next patch is needed to fix this case. Fixes: 576b523721b7 ("perf probe: Fix probing symbols with optimization suffix") Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lore.kernel.org/lkml/157199318513.8075.10463906803299647907.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-10-25 16:46:25 +08:00
Dwarf_Addr eaddr;
perf probe: Fix probing symbols with optimization suffix Fix perf probe to probe on some symbols which have some optimzation suffixes, e.g. ".part", ".isra", and ".constprop". To fix this issue, instead of using the DIE name, perf probe uses the symbol name found by dwfl_module_addrsym(). This also involves a perf probe --vars operation update which now shows the symbol name instead of the DIE name. Without this patch, putting a probe on an inlined function which was compiled with a suffixed symbol will fail like this: $ perf probe -v getname_flags probe-definition(0): getname_flags symbol:getname_flags file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments Looking at the vmlinux_path (6 entries long) Using /lib/modules/3.11.0+/build/vmlinux for symbols found inline addr: 0xffffffff8119bb70 Probe point found: getname_flags+0 found inline addr: 0xffffffff8119bcb6 Probe point found: getname+6 found inline addr: 0xffffffff811a06a6 Probe point found: user_path_at_empty+6 find 3 probe_trace_events. Opening /sys/kernel/debug//tracing/kprobe_events write=1 Added new events: Writing event: p:probe/getname_flags getname_flags+0 Failed to write event: No such file or directory Error: Failed to add events. (-1) Because the debuginfo knows only the original (non suffix) symbol name, it uses the original symbol for probe address but the kernel (kallsyms) knows only suffixed symbol. Then, the kernel rejects that original symbol. This patch uses dwfl_module_addrsym() to get the correct (suffixed) symbol from symtab when a probe point is found. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130925131616.31632.46658.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-25 21:16:16 +08:00
GElf_Sym sym;
const char *symbol;
/* Verify the address is correct */
perf probe: Fix wrong address verification Since there are some DIE which has only ranges instead of the combination of entrypc/highpc, address verification must use dwarf_haspc() instead of dwarf_entrypc/dwarf_highpc. Also, the ranges only DIE will have a partial code in different section (e.g. unlikely code will be in text.unlikely as "FUNC.cold" symbol). In that case, we can not use dwarf_entrypc() or die_entrypc(), because the offset from original DIE can be a minus value. Instead, this simply gets the symbol and offset from symtab. Without this patch; # perf probe -D clear_tasks_mm_cpumask:1 Failed to get entry address of clear_tasks_mm_cpumask Error: Failed to add events. And with this patch: # perf probe -D clear_tasks_mm_cpumask:1 p:probe/clear_tasks_mm_cpumask clear_tasks_mm_cpumask+0 p:probe/clear_tasks_mm_cpumask_1 clear_tasks_mm_cpumask+5 p:probe/clear_tasks_mm_cpumask_2 clear_tasks_mm_cpumask+8 p:probe/clear_tasks_mm_cpumask_3 clear_tasks_mm_cpumask+16 p:probe/clear_tasks_mm_cpumask_4 clear_tasks_mm_cpumask+82 Committer testing: I managed to reproduce the above: [root@quaco ~]# perf probe -D clear_tasks_mm_cpumask:1 p:probe/clear_tasks_mm_cpumask _text+919968 p:probe/clear_tasks_mm_cpumask_1 _text+919973 p:probe/clear_tasks_mm_cpumask_2 _text+919976 [root@quaco ~]# But then when trying to actually put the probe in place, it fails if I use :0 as the offset: [root@quaco ~]# perf probe -L clear_tasks_mm_cpumask | head -5 <clear_tasks_mm_cpumask@/usr/src/debug/kernel-5.2.fc30/linux-5.2.18-200.fc30.x86_64/kernel/cpu.c:0> 0 void clear_tasks_mm_cpumask(int cpu) 1 { 2 struct task_struct *p; [root@quaco ~]# perf probe clear_tasks_mm_cpumask:0 Probe point 'clear_tasks_mm_cpumask' not found. Error: Failed to add events. [root@quaco The next patch is needed to fix this case. Fixes: 576b523721b7 ("perf probe: Fix probing symbols with optimization suffix") Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lore.kernel.org/lkml/157199318513.8075.10463906803299647907.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-10-25 16:46:25 +08:00
if (!dwarf_haspc(sp_die, paddr)) {
pr_warning("Specified offset is out of %s\n",
perf probe: Fix probing symbols with optimization suffix Fix perf probe to probe on some symbols which have some optimzation suffixes, e.g. ".part", ".isra", and ".constprop". To fix this issue, instead of using the DIE name, perf probe uses the symbol name found by dwfl_module_addrsym(). This also involves a perf probe --vars operation update which now shows the symbol name instead of the DIE name. Without this patch, putting a probe on an inlined function which was compiled with a suffixed symbol will fail like this: $ perf probe -v getname_flags probe-definition(0): getname_flags symbol:getname_flags file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments Looking at the vmlinux_path (6 entries long) Using /lib/modules/3.11.0+/build/vmlinux for symbols found inline addr: 0xffffffff8119bb70 Probe point found: getname_flags+0 found inline addr: 0xffffffff8119bcb6 Probe point found: getname+6 found inline addr: 0xffffffff811a06a6 Probe point found: user_path_at_empty+6 find 3 probe_trace_events. Opening /sys/kernel/debug//tracing/kprobe_events write=1 Added new events: Writing event: p:probe/getname_flags getname_flags+0 Failed to write event: No such file or directory Error: Failed to add events. (-1) Because the debuginfo knows only the original (non suffix) symbol name, it uses the original symbol for probe address but the kernel (kallsyms) knows only suffixed symbol. Then, the kernel rejects that original symbol. This patch uses dwfl_module_addrsym() to get the correct (suffixed) symbol from symtab when a probe point is found. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130925131616.31632.46658.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-25 21:16:16 +08:00
dwarf_diename(sp_die));
return -EINVAL;
}
perf probe: Fix wrong address verification Since there are some DIE which has only ranges instead of the combination of entrypc/highpc, address verification must use dwarf_haspc() instead of dwarf_entrypc/dwarf_highpc. Also, the ranges only DIE will have a partial code in different section (e.g. unlikely code will be in text.unlikely as "FUNC.cold" symbol). In that case, we can not use dwarf_entrypc() or die_entrypc(), because the offset from original DIE can be a minus value. Instead, this simply gets the symbol and offset from symtab. Without this patch; # perf probe -D clear_tasks_mm_cpumask:1 Failed to get entry address of clear_tasks_mm_cpumask Error: Failed to add events. And with this patch: # perf probe -D clear_tasks_mm_cpumask:1 p:probe/clear_tasks_mm_cpumask clear_tasks_mm_cpumask+0 p:probe/clear_tasks_mm_cpumask_1 clear_tasks_mm_cpumask+5 p:probe/clear_tasks_mm_cpumask_2 clear_tasks_mm_cpumask+8 p:probe/clear_tasks_mm_cpumask_3 clear_tasks_mm_cpumask+16 p:probe/clear_tasks_mm_cpumask_4 clear_tasks_mm_cpumask+82 Committer testing: I managed to reproduce the above: [root@quaco ~]# perf probe -D clear_tasks_mm_cpumask:1 p:probe/clear_tasks_mm_cpumask _text+919968 p:probe/clear_tasks_mm_cpumask_1 _text+919973 p:probe/clear_tasks_mm_cpumask_2 _text+919976 [root@quaco ~]# But then when trying to actually put the probe in place, it fails if I use :0 as the offset: [root@quaco ~]# perf probe -L clear_tasks_mm_cpumask | head -5 <clear_tasks_mm_cpumask@/usr/src/debug/kernel-5.2.fc30/linux-5.2.18-200.fc30.x86_64/kernel/cpu.c:0> 0 void clear_tasks_mm_cpumask(int cpu) 1 { 2 struct task_struct *p; [root@quaco ~]# perf probe clear_tasks_mm_cpumask:0 Probe point 'clear_tasks_mm_cpumask' not found. Error: Failed to add events. [root@quaco The next patch is needed to fix this case. Fixes: 576b523721b7 ("perf probe: Fix probing symbols with optimization suffix") Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lore.kernel.org/lkml/157199318513.8075.10463906803299647907.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-10-25 16:46:25 +08:00
/* Try to get actual symbol name from symtab */
symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
perf probe: Fix probing symbols with optimization suffix Fix perf probe to probe on some symbols which have some optimzation suffixes, e.g. ".part", ".isra", and ".constprop". To fix this issue, instead of using the DIE name, perf probe uses the symbol name found by dwfl_module_addrsym(). This also involves a perf probe --vars operation update which now shows the symbol name instead of the DIE name. Without this patch, putting a probe on an inlined function which was compiled with a suffixed symbol will fail like this: $ perf probe -v getname_flags probe-definition(0): getname_flags symbol:getname_flags file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments Looking at the vmlinux_path (6 entries long) Using /lib/modules/3.11.0+/build/vmlinux for symbols found inline addr: 0xffffffff8119bb70 Probe point found: getname_flags+0 found inline addr: 0xffffffff8119bcb6 Probe point found: getname+6 found inline addr: 0xffffffff811a06a6 Probe point found: user_path_at_empty+6 find 3 probe_trace_events. Opening /sys/kernel/debug//tracing/kprobe_events write=1 Added new events: Writing event: p:probe/getname_flags getname_flags+0 Failed to write event: No such file or directory Error: Failed to add events. (-1) Because the debuginfo knows only the original (non suffix) symbol name, it uses the original symbol for probe address but the kernel (kallsyms) knows only suffixed symbol. Then, the kernel rejects that original symbol. This patch uses dwfl_module_addrsym() to get the correct (suffixed) symbol from symtab when a probe point is found. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130925131616.31632.46658.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-25 21:16:16 +08:00
if (!symbol) {
perf probe: Fix wrong address verification Since there are some DIE which has only ranges instead of the combination of entrypc/highpc, address verification must use dwarf_haspc() instead of dwarf_entrypc/dwarf_highpc. Also, the ranges only DIE will have a partial code in different section (e.g. unlikely code will be in text.unlikely as "FUNC.cold" symbol). In that case, we can not use dwarf_entrypc() or die_entrypc(), because the offset from original DIE can be a minus value. Instead, this simply gets the symbol and offset from symtab. Without this patch; # perf probe -D clear_tasks_mm_cpumask:1 Failed to get entry address of clear_tasks_mm_cpumask Error: Failed to add events. And with this patch: # perf probe -D clear_tasks_mm_cpumask:1 p:probe/clear_tasks_mm_cpumask clear_tasks_mm_cpumask+0 p:probe/clear_tasks_mm_cpumask_1 clear_tasks_mm_cpumask+5 p:probe/clear_tasks_mm_cpumask_2 clear_tasks_mm_cpumask+8 p:probe/clear_tasks_mm_cpumask_3 clear_tasks_mm_cpumask+16 p:probe/clear_tasks_mm_cpumask_4 clear_tasks_mm_cpumask+82 Committer testing: I managed to reproduce the above: [root@quaco ~]# perf probe -D clear_tasks_mm_cpumask:1 p:probe/clear_tasks_mm_cpumask _text+919968 p:probe/clear_tasks_mm_cpumask_1 _text+919973 p:probe/clear_tasks_mm_cpumask_2 _text+919976 [root@quaco ~]# But then when trying to actually put the probe in place, it fails if I use :0 as the offset: [root@quaco ~]# perf probe -L clear_tasks_mm_cpumask | head -5 <clear_tasks_mm_cpumask@/usr/src/debug/kernel-5.2.fc30/linux-5.2.18-200.fc30.x86_64/kernel/cpu.c:0> 0 void clear_tasks_mm_cpumask(int cpu) 1 { 2 struct task_struct *p; [root@quaco ~]# perf probe clear_tasks_mm_cpumask:0 Probe point 'clear_tasks_mm_cpumask' not found. Error: Failed to add events. [root@quaco The next patch is needed to fix this case. Fixes: 576b523721b7 ("perf probe: Fix probing symbols with optimization suffix") Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lore.kernel.org/lkml/157199318513.8075.10463906803299647907.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-10-25 16:46:25 +08:00
pr_warning("Failed to find symbol at 0x%lx\n",
(unsigned long)paddr);
return -ENOENT;
perf probe: Fix probing symbols with optimization suffix Fix perf probe to probe on some symbols which have some optimzation suffixes, e.g. ".part", ".isra", and ".constprop". To fix this issue, instead of using the DIE name, perf probe uses the symbol name found by dwfl_module_addrsym(). This also involves a perf probe --vars operation update which now shows the symbol name instead of the DIE name. Without this patch, putting a probe on an inlined function which was compiled with a suffixed symbol will fail like this: $ perf probe -v getname_flags probe-definition(0): getname_flags symbol:getname_flags file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments Looking at the vmlinux_path (6 entries long) Using /lib/modules/3.11.0+/build/vmlinux for symbols found inline addr: 0xffffffff8119bb70 Probe point found: getname_flags+0 found inline addr: 0xffffffff8119bcb6 Probe point found: getname+6 found inline addr: 0xffffffff811a06a6 Probe point found: user_path_at_empty+6 find 3 probe_trace_events. Opening /sys/kernel/debug//tracing/kprobe_events write=1 Added new events: Writing event: p:probe/getname_flags getname_flags+0 Failed to write event: No such file or directory Error: Failed to add events. (-1) Because the debuginfo knows only the original (non suffix) symbol name, it uses the original symbol for probe address but the kernel (kallsyms) knows only suffixed symbol. Then, the kernel rejects that original symbol. This patch uses dwfl_module_addrsym() to get the correct (suffixed) symbol from symtab when a probe point is found. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130925131616.31632.46658.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-25 21:16:16 +08:00
}
perf probe: Fix wrong address verification Since there are some DIE which has only ranges instead of the combination of entrypc/highpc, address verification must use dwarf_haspc() instead of dwarf_entrypc/dwarf_highpc. Also, the ranges only DIE will have a partial code in different section (e.g. unlikely code will be in text.unlikely as "FUNC.cold" symbol). In that case, we can not use dwarf_entrypc() or die_entrypc(), because the offset from original DIE can be a minus value. Instead, this simply gets the symbol and offset from symtab. Without this patch; # perf probe -D clear_tasks_mm_cpumask:1 Failed to get entry address of clear_tasks_mm_cpumask Error: Failed to add events. And with this patch: # perf probe -D clear_tasks_mm_cpumask:1 p:probe/clear_tasks_mm_cpumask clear_tasks_mm_cpumask+0 p:probe/clear_tasks_mm_cpumask_1 clear_tasks_mm_cpumask+5 p:probe/clear_tasks_mm_cpumask_2 clear_tasks_mm_cpumask+8 p:probe/clear_tasks_mm_cpumask_3 clear_tasks_mm_cpumask+16 p:probe/clear_tasks_mm_cpumask_4 clear_tasks_mm_cpumask+82 Committer testing: I managed to reproduce the above: [root@quaco ~]# perf probe -D clear_tasks_mm_cpumask:1 p:probe/clear_tasks_mm_cpumask _text+919968 p:probe/clear_tasks_mm_cpumask_1 _text+919973 p:probe/clear_tasks_mm_cpumask_2 _text+919976 [root@quaco ~]# But then when trying to actually put the probe in place, it fails if I use :0 as the offset: [root@quaco ~]# perf probe -L clear_tasks_mm_cpumask | head -5 <clear_tasks_mm_cpumask@/usr/src/debug/kernel-5.2.fc30/linux-5.2.18-200.fc30.x86_64/kernel/cpu.c:0> 0 void clear_tasks_mm_cpumask(int cpu) 1 { 2 struct task_struct *p; [root@quaco ~]# perf probe clear_tasks_mm_cpumask:0 Probe point 'clear_tasks_mm_cpumask' not found. Error: Failed to add events. [root@quaco The next patch is needed to fix this case. Fixes: 576b523721b7 ("perf probe: Fix probing symbols with optimization suffix") Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lore.kernel.org/lkml/157199318513.8075.10463906803299647907.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-10-25 16:46:25 +08:00
eaddr = sym.st_value;
tp->offset = (unsigned long)(paddr - eaddr);
perf probe: Support basic dwarf-based operations on uprobe events Support basic dwarf(debuginfo) based operations for uprobe events. With this change, perf probe can analyze debuginfo of user application binary to set up new uprobe event. This allows perf-probe --add(with local variables, line numbers) and --line works with -x option. (Actually, --vars has already accepted -x option) For example, the following command shows the probe-able lines of a given user space function. Something that so far was only available in the 'perf probe' tool for kernel space functions: # ./perf probe -x perf --line map__load <map__load@/home/fedora/ksrc/linux-2.6/tools/perf/util/map.c:0> 0 int map__load(struct map *map, symbol_filter_t filter) 1 { 2 const char *name = map->dso->long_name; int nr; 5 if (dso__loaded(map->dso, map->type)) 6 return 0; 8 nr = dso__load(map->dso, map, filter); 9 if (nr < 0) { 10 if (map->dso->has_build_id) { And this shows the available variables at the given line of the function. # ./perf probe -x perf --vars map__load:8 Available variables at map__load:8 @<map__load+96> char* name struct map* map symbol_filter_t filter @<map__find_symbol+112> char* name symbol_filter_t filter @<map__find_symbol_by_name+136> char* name symbol_filter_t filter @<map_groups__find_symbol_by_name+176> char* name struct map* map symbol_filter_t filter And lastly, we can now define probe(s) with all available variables on the given line: # ./perf probe -x perf --add 'map__load:8 $vars' Added new events: probe_perf:map__load (on map__load:8 with $vars) probe_perf:map__load_1 (on map__load:8 with $vars) probe_perf:map__load_2 (on map__load:8 with $vars) probe_perf:map__load_3 (on map__load:8 with $vars) You can now use it in all perf tools, such as: perf record -e probe_perf:map__load_3 -aR sleep 1 Changes from previous version: - Add examples in the patch description. - Use .text section start address and dwarf symbol address for calculating the offset of given symbol, instead of searching the symbol in symtab again. With this change, we can safely handle multiple local function instances (e.g. scnprintf in perf). Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: David Ahern <dsahern@gmail.com> Cc: David A. Long <dave.long@linaro.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: systemtap@sourceware.org Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20131226054152.22364.47021.stgit@kbuild-fedora.novalocal Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-12-26 13:41:53 +08:00
tp->address = (unsigned long)paddr;
perf probe: Fix probing symbols with optimization suffix Fix perf probe to probe on some symbols which have some optimzation suffixes, e.g. ".part", ".isra", and ".constprop". To fix this issue, instead of using the DIE name, perf probe uses the symbol name found by dwfl_module_addrsym(). This also involves a perf probe --vars operation update which now shows the symbol name instead of the DIE name. Without this patch, putting a probe on an inlined function which was compiled with a suffixed symbol will fail like this: $ perf probe -v getname_flags probe-definition(0): getname_flags symbol:getname_flags file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments Looking at the vmlinux_path (6 entries long) Using /lib/modules/3.11.0+/build/vmlinux for symbols found inline addr: 0xffffffff8119bb70 Probe point found: getname_flags+0 found inline addr: 0xffffffff8119bcb6 Probe point found: getname+6 found inline addr: 0xffffffff811a06a6 Probe point found: user_path_at_empty+6 find 3 probe_trace_events. Opening /sys/kernel/debug//tracing/kprobe_events write=1 Added new events: Writing event: p:probe/getname_flags getname_flags+0 Failed to write event: No such file or directory Error: Failed to add events. (-1) Because the debuginfo knows only the original (non suffix) symbol name, it uses the original symbol for probe address but the kernel (kallsyms) knows only suffixed symbol. Then, the kernel rejects that original symbol. This patch uses dwfl_module_addrsym() to get the correct (suffixed) symbol from symtab when a probe point is found. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130925131616.31632.46658.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-25 21:16:16 +08:00
tp->symbol = strdup(symbol);
if (!tp->symbol)
return -ENOMEM;
/* Return probe must be on the head of a subprogram */
if (retprobe) {
if (eaddr != paddr) {
pr_warning("Failed to find \"%s%%return\",\n"
" because %s is an inlined function and"
" has no return point.\n", function,
function);
return -EINVAL;
}
tp->retprobe = true;
}
return 0;
}
/* Call probe_finder callback with scope DIE */
static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
{
Dwarf_Attribute fb_attr;
Dwarf_Frame *frame = NULL;
size_t nops;
int ret;
if (!sc_die) {
pr_err("Caller must pass a scope DIE. Program error.\n");
return -EINVAL;
}
/* If not a real subprogram, find a real one */
if (!die_is_func_def(sc_die)) {
if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
perf probe: Ignore tail calls to probed functions perf probe currently errors out if there are any tail calls to probed functions: [root@rhel71be]# perf probe do_fork Failed to find probe point in any functions. Error: Failed to add events. Fix this by teaching perf to ignore tail calls. Without patch: [root@rhel71be perf]# ./perf probe -v do_fork probe-definition(0): do_fork symbol:do_fork file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments Looking at the vmlinux_path (7 entries long) symsrc__init: build id mismatch for /boot/vmlinux. Using /usr/lib/debug/lib/modules/3.10.0-201.el7.ppc64/vmlinux for symbols Open Debuginfo file: /usr/lib/debug/lib/modules/3.10.0-201.el7.ppc64/vmlinux Try to find probe point from debuginfo. found inline addr: 0xc0000000000bb9b0 Probe point found: do_fork+0 found inline addr: 0xc0000000000bbe20 Probe point found: kernel_thread+48 found inline addr: 0xc0000000000bbe5c Probe point found: sys_fork+28 found inline addr: 0xc0000000000bbfac Probe point found: sys_vfork+44 found inline addr: 0xc0000000000bc27c Failed to find probe point in any functions. An error occurred in debuginfo analysis (-2). Error: Failed to add events. Reason: No such file or directory (Code: -2) With patch: [root@rhel71be perf]# ./perf probe -v do_fork probe-definition(0): do_fork symbol:do_fork file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments Looking at the vmlinux_path (7 entries long) symsrc__init: build id mismatch for /boot/vmlinux. Using /usr/lib/debug/lib/modules/3.10.0-201.el7.ppc64/vmlinux for symbols Open Debuginfo file: /usr/lib/debug/lib/modules/3.10.0-201.el7.ppc64/vmlinux Try to find probe point from debuginfo. found inline addr: 0xc0000000000bb9b0 Probe point found: do_fork+0 found inline addr: 0xc0000000000bbe20 Probe point found: kernel_thread+48 found inline addr: 0xc0000000000bbe5c Probe point found: sys_fork+28 found inline addr: 0xc0000000000bbfac Probe point found: sys_vfork+44 found inline addr: 0xc0000000000bc27c Ignoring tail call from SyS_clone Found 4 probe_trace_events. Opening /sys/kernel/debug/tracing/kprobe_events write=1 No kprobe blacklist support, ignored Added new events: Writing event: p:probe/do_fork _text+768432 Failed to write event: Invalid argument Error: Failed to add events. Reason: Invalid argument (Code: -22) [Ignore the error about failure to write event - this kernel is missing a patch to resolve _text properly] The reason to ignore tail calls is that the address does not belong to any function frame. In the example above, the address in SyS_clone is 0xc0000000000bc27c, but looking at the debug-info: <1><830081>: Abbrev Number: 133 (DW_TAG_subprogram) <830083> DW_AT_external : 1 <830083> DW_AT_name : (indirect string, offset: 0x3cea3): SyS_clone <830087> DW_AT_decl_file : 7 <830088> DW_AT_decl_line : 1689 <83008a> DW_AT_prototyped : 1 <83008a> DW_AT_type : <0x8110eb> <83008e> DW_AT_low_pc : 0xc0000000000bc270 <830096> DW_AT_high_pc : 0xc <83009e> DW_AT_frame_base : 1 byte block: 9c (DW_OP_call_frame_cfa) <8300a0> DW_AT_GNU_all_call_sites: 1 <8300a0> DW_AT_sibling : <0x830178> <snip> <3><830147>: Abbrev Number: 125 (DW_TAG_GNU_call_site) <830148> DW_AT_low_pc : 0xc0000000000bc27c <830150> DW_AT_GNU_tail_call: 1 <830150> DW_AT_abstract_origin: <0x82e7e1> The frame ends at 0xc0000000000bc27c. I suppose this is why this particular call is a "tail" call. FWIW, systemtap seems to ignore these as well and requires users to explicitly place probes at these call sites if necessary. I print out the caller so that users know. Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Link: http://lkml.kernel.org/r/1430394151-15928-1-git-send-email-naveen.n.rao@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-30 19:42:31 +08:00
if (die_find_tailfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
pr_warning("Ignoring tail call from %s\n",
dwarf_diename(&pf->sp_die));
return 0;
} else {
pr_warning("Failed to find probe point in any "
"functions.\n");
return -ENOENT;
}
}
} else
memcpy(&pf->sp_die, sc_die, sizeof(Dwarf_Die));
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
/* Get the frame base attribute/ops from subprogram */
dwarf_attr(&pf->sp_die, DW_AT_frame_base, &fb_attr);
ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
if (ret <= 0 || nops == 0) {
pf->fb_ops = NULL;
#if _ELFUTILS_PREREQ(0, 142)
} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
perf probe: Search both .eh_frame and .debug_frame sections for probe location 'perf probe' through debuginfo__find_probes() in util/probe-finder.c checks for the functions' frame descriptions in either .eh_frame section of an ELF or the .debug_frame. The check is based on whether either one of these sections is present. Depending on distro, toolchain defaults, architetcutre, build flags, etc., CFI might be found in either .eh_frame and/or .debug_frame. Sometimes, it may happen that, .eh_frame, even if present, may not be complete and may miss some descriptions. Therefore, to be sure, to find the CFI covering an address we will always have to investigate both if available. For e.g., in powerpc, this may happen: $ gcc -g bin.c -o bin $ objdump --dwarf ./bin <1><145>: Abbrev Number: 7 (DW_TAG_subprogram) <146> DW_AT_external : 1 <146> DW_AT_name : (indirect string, offset: 0x9e): main <14a> DW_AT_decl_file : 1 <14b> DW_AT_decl_line : 39 <14c> DW_AT_prototyped : 1 <14c> DW_AT_type : <0x57> <150> DW_AT_low_pc : 0x100007b8 If the .eh_frame and .debug_frame are checked for the same binary, we will find that, .eh_frame (although present) doesn't contain a description for "main" function. But, .debug_frame has a description: 000000d8 00000024 00000000 FDE cie=00000000 pc=100007b8..10000838 DW_CFA_advance_loc: 16 to 100007c8 DW_CFA_def_cfa_offset: 144 DW_CFA_offset_extended_sf: r65 at cfa+16 ... Due to this (since, perf checks whether .eh_frame is present and goes on searching for that address inside that frame), perf is unable to process the probes: # perf probe -x ./bin main Failed to get call frame on 0x100007b8 Error: Failed to add events. To avoid this issue, we need to check both the sections (.eh_frame and .debug_frame), which is done in this patch. Note that, we can always force everything into both .eh_frame and .debug_frame by: $ gcc bin.c -fasynchronous-unwind-tables -fno-dwarf2-cfi-asm -g -o bin Signed-off-by: Hemant Kumar <hemant@linux.vnet.ibm.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: linuxppc-dev@lists.ozlabs.org Cc: Mark Wielaard <mjw@redhat.com> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1454426806-13974-1-git-send-email-hemant@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-02 23:26:46 +08:00
(pf->cfi_eh != NULL || pf->cfi_dbg != NULL)) {
if ((dwarf_cfi_addrframe(pf->cfi_eh, pf->addr, &frame) != 0 &&
(dwarf_cfi_addrframe(pf->cfi_dbg, pf->addr, &frame) != 0)) ||
dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
pr_warning("Failed to get call frame on 0x%jx\n",
(uintmax_t)pf->addr);
free(frame);
return -ENOENT;
}
#endif
}
/* Call finder's callback handler */
ret = pf->callback(sc_die, pf);
/* Since *pf->fb_ops can be a part of frame. we should free it here. */
free(frame);
pf->fb_ops = NULL;
return ret;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
}
struct find_scope_param {
const char *function;
const char *file;
int line;
int diff;
Dwarf_Die *die_mem;
bool found;
};
static int find_best_scope_cb(Dwarf_Die *fn_die, void *data)
{
struct find_scope_param *fsp = data;
const char *file;
int lno;
/* Skip if declared file name does not match */
if (fsp->file) {
file = dwarf_decl_file(fn_die);
if (!file || strcmp(fsp->file, file) != 0)
return 0;
}
/* If the function name is given, that's what user expects */
if (fsp->function) {
if (die_match_name(fn_die, fsp->function)) {
memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die));
fsp->found = true;
return 1;
}
} else {
/* With the line number, find the nearest declared DIE */
dwarf_decl_line(fn_die, &lno);
if (lno < fsp->line && fsp->diff > fsp->line - lno) {
/* Keep a candidate and continue */
fsp->diff = fsp->line - lno;
memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die));
fsp->found = true;
}
}
return 0;
}
/* Return innermost DIE */
static int find_inner_scope_cb(Dwarf_Die *fn_die, void *data)
{
struct find_scope_param *fsp = data;
memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die));
fsp->found = true;
return 1;
}
/* Find an appropriate scope fits to given conditions */
static Dwarf_Die *find_best_scope(struct probe_finder *pf, Dwarf_Die *die_mem)
{
struct find_scope_param fsp = {
.function = pf->pev->point.function,
.file = pf->fname,
.line = pf->lno,
.diff = INT_MAX,
.die_mem = die_mem,
.found = false,
};
int ret;
ret = cu_walk_functions_at(&pf->cu_die, pf->addr, find_best_scope_cb,
&fsp);
if (!ret && !fsp.found)
cu_walk_functions_at(&pf->cu_die, pf->addr,
find_inner_scope_cb, &fsp);
return fsp.found ? die_mem : NULL;
}
perf probe: Verify given line is a representive line Verify user given probe line is a representive line (which doesn't share the address with other lines or the line is the least line among the lines which shares same address), and if not, it shows what is the representive line. Without this fix, user can put a probe on the lines which is not a a representive line. But since this is not a representive line, perf probe -l shows a representive line number instead of user given line number. e.g. (put kernel_read:3, but listed as kernel_read:2) # perf probe -a kernel_read:3 Added new event: probe:kernel_read (on kernel_read:3) You can now use it in all perf tools, such as: perf record -e probe:kernel_read -aR sleep 1 # perf probe -l probe:kernel_read (on kernel_read:2@linux-5.0.0/fs/read_write.c) With this fix, perf probe doesn't allow user to put a probe on a representive line, and tell what is the representive line. # perf probe -a kernel_read:3 This line is sharing the addrees with other lines. Please try to probe at kernel_read:2 instead. Error: Failed to add events. Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Link: http://lore.kernel.org/lkml/157406472071.24476.14915451439785001021.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-18 16:12:00 +08:00
static int verify_representive_line(struct probe_finder *pf, const char *fname,
int lineno, Dwarf_Addr addr)
{
const char *__fname, *__func = NULL;
Dwarf_Die die_mem;
int __lineno;
/* Verify line number and address by reverse search */
if (cu_find_lineinfo(&pf->cu_die, addr, &__fname, &__lineno) < 0)
return 0;
pr_debug2("Reversed line: %s:%d\n", __fname, __lineno);
if (strcmp(fname, __fname) || lineno == __lineno)
return 0;
pr_warning("This line is sharing the address with other lines.\n");
perf probe: Verify given line is a representive line Verify user given probe line is a representive line (which doesn't share the address with other lines or the line is the least line among the lines which shares same address), and if not, it shows what is the representive line. Without this fix, user can put a probe on the lines which is not a a representive line. But since this is not a representive line, perf probe -l shows a representive line number instead of user given line number. e.g. (put kernel_read:3, but listed as kernel_read:2) # perf probe -a kernel_read:3 Added new event: probe:kernel_read (on kernel_read:3) You can now use it in all perf tools, such as: perf record -e probe:kernel_read -aR sleep 1 # perf probe -l probe:kernel_read (on kernel_read:2@linux-5.0.0/fs/read_write.c) With this fix, perf probe doesn't allow user to put a probe on a representive line, and tell what is the representive line. # perf probe -a kernel_read:3 This line is sharing the addrees with other lines. Please try to probe at kernel_read:2 instead. Error: Failed to add events. Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Link: http://lore.kernel.org/lkml/157406472071.24476.14915451439785001021.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-18 16:12:00 +08:00
if (pf->pev->point.function) {
/* Find best match function name and lines */
pf->addr = addr;
if (find_best_scope(pf, &die_mem)
&& die_match_name(&die_mem, pf->pev->point.function)
&& dwarf_decl_line(&die_mem, &lineno) == 0) {
__func = dwarf_diename(&die_mem);
__lineno -= lineno;
}
}
pr_warning("Please try to probe at %s:%d instead.\n",
__func ? : __fname, __lineno);
return -ENOENT;
}
static int probe_point_line_walker(const char *fname, int lineno,
Dwarf_Addr addr, void *data)
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
{
struct probe_finder *pf = data;
Dwarf_Die *sc_die, die_mem;
int ret;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
if (lineno != pf->lno || strtailcmp(fname, pf->fname) != 0)
return 0;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
perf probe: Verify given line is a representive line Verify user given probe line is a representive line (which doesn't share the address with other lines or the line is the least line among the lines which shares same address), and if not, it shows what is the representive line. Without this fix, user can put a probe on the lines which is not a a representive line. But since this is not a representive line, perf probe -l shows a representive line number instead of user given line number. e.g. (put kernel_read:3, but listed as kernel_read:2) # perf probe -a kernel_read:3 Added new event: probe:kernel_read (on kernel_read:3) You can now use it in all perf tools, such as: perf record -e probe:kernel_read -aR sleep 1 # perf probe -l probe:kernel_read (on kernel_read:2@linux-5.0.0/fs/read_write.c) With this fix, perf probe doesn't allow user to put a probe on a representive line, and tell what is the representive line. # perf probe -a kernel_read:3 This line is sharing the addrees with other lines. Please try to probe at kernel_read:2 instead. Error: Failed to add events. Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Link: http://lore.kernel.org/lkml/157406472071.24476.14915451439785001021.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-18 16:12:00 +08:00
if (verify_representive_line(pf, fname, lineno, addr))
return -ENOENT;
pf->addr = addr;
sc_die = find_best_scope(pf, &die_mem);
if (!sc_die) {
pr_warning("Failed to find scope of probe point.\n");
return -ENOENT;
}
ret = call_probe_finder(sc_die, pf);
/* Continue if no error, because the line will be in inline function */
perf probe: Fix error propagation leading to segfault There are two hunks in this patch that stops probe processing as soon as one error is found, breaking out of loops, the other fix an error propagation that should return a negative error number but instead was returning the result of "ret < 0", which is 1 and thus made several error checks fail because they test agains < 0. The problem could be triggered by asking for a variable that was optimized out, fact that should stop the whole probe processing but instead was segfaulting while installing broken probes: [root@emilia ~]# probe perf_mmap:55 user_lock_limit Failed to find the location of user_lock_limit at this address. Perhaps, it has been optimized out. Failed to find 'user_lock_limit' in this function. Add new events: probe:perf_mmap (on perf_mmap:55 with user_lock_limit) probe:perf_mmap_1 (on perf_mmap:55 with user_lock_limit) Segmentation fault (core dumped) [root@emilia ~]# perf probe -l probe:perf_mmap (on perf_mmap:55@git/linux/kernel/perf_event.c with user_lock_limit) probe:perf_mmap_1 (on perf_mmap:55@git/linux/kernel/perf_event.c with user_lock_limit) [root@emilia ~]# After the fix: [root@emilia ~]# probe perf_mmap:55 user_lock_limit Failed to find the location of user_lock_limit at this address. Perhaps, it has been optimized out. Failed to find 'user_lock_limit' in this function. Error: Failed to add events. (-2) [root@emilia ~]# Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-02-22 00:23:57 +08:00
return ret < 0 ? ret : 0;
}
/* Find probe point from its line number */
static int find_probe_point_by_line(struct probe_finder *pf)
{
return die_walk_lines(&pf->cu_die, probe_point_line_walker, pf);
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
}
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
/* Find lines which match lazy pattern */
static int find_lazy_match_lines(struct intlist *list,
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
const char *fname, const char *pat)
{
FILE *fp;
char *line = NULL;
size_t line_len;
ssize_t len;
int count = 0, linenum = 1;
char sbuf[STRERR_BUFSIZE];
fp = fopen(fname, "r");
if (!fp) {
pr_warning("Failed to open %s: %s\n", fname,
str_error_r(errno, sbuf, sizeof(sbuf)));
return -errno;
}
while ((len = getline(&line, &line_len, fp)) > 0) {
if (line[len - 1] == '\n')
line[len - 1] = '\0';
if (strlazymatch(line, pat)) {
intlist__add(list, linenum);
count++;
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
}
linenum++;
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
}
if (ferror(fp))
count = -errno;
free(line);
fclose(fp);
if (count == 0)
pr_debug("No matched lines found in %s.\n", fname);
return count;
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
}
static int probe_point_lazy_walker(const char *fname, int lineno,
Dwarf_Addr addr, void *data)
{
struct probe_finder *pf = data;
Dwarf_Die *sc_die, die_mem;
int ret;
if (!intlist__has_entry(pf->lcache, lineno) ||
strtailcmp(fname, pf->fname) != 0)
return 0;
pr_debug("Probe line found: line:%d addr:0x%llx\n",
lineno, (unsigned long long)addr);
pf->addr = addr;
pf->lno = lineno;
sc_die = find_best_scope(pf, &die_mem);
if (!sc_die) {
pr_warning("Failed to find scope of probe point.\n");
return -ENOENT;
}
ret = call_probe_finder(sc_die, pf);
/*
* Continue if no error, because the lazy pattern will match
* to other lines
*/
return ret < 0 ? ret : 0;
}
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
/* Find probe points from lazy pattern */
static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
{
int ret = 0;
char *fpath;
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
if (intlist__empty(pf->lcache)) {
const char *comp_dir;
comp_dir = cu_get_comp_dir(&pf->cu_die);
ret = get_real_path(pf->fname, comp_dir, &fpath);
if (ret < 0) {
pr_warning("Failed to find source file path.\n");
return ret;
}
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
/* Matching lazy line pattern */
ret = find_lazy_match_lines(pf->lcache, fpath,
pf->pev->point.lazy_line);
free(fpath);
if (ret <= 0)
return ret;
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
}
return die_walk_lines(sp_die, probe_point_lazy_walker, pf);
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
}
perf uprobe: Skip prologue if program compiled without optimization The function prologue prepares stack and registers before executing function logic. When target program is compiled without optimization, function parameter information is only valid after the prologue. When we probe entrypc of the function, and try to record a function parameter, it contains a garbage value. For example: $ vim test.c #include <stdio.h> void foo(int i) { printf("i: %d\n", i); } int main() { foo(42); return 0; } $ gcc -g test.c -o test $ objdump -dl test | less foo(): /home/ravi/test.c:4 400536: 55 push %rbp 400537: 48 89 e5 mov %rsp,%rbp 40053a: 48 83 ec 10 sub -bashx10,%rsp 40053e: 89 7d fc mov %edi,-0x4(%rbp) /home/ravi/test.c:5 400541: 8b 45 fc mov -0x4(%rbp),%eax ... ... main(): /home/ravi/test.c:9 400558: 55 push %rbp 400559: 48 89 e5 mov %rsp,%rbp /home/ravi/test.c:10 40055c: bf 2a 00 00 00 mov -bashx2a,%edi 400561: e8 d0 ff ff ff callq 400536 <foo> $ perf probe -x ./test 'foo i' $ cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/ravi/test:0x0000000000000536 i=-12(%sp):s32 $ perf record -e probe_test:foo ./test $ perf script test 5778 [001] 4918.562027: probe_test:foo: (400536) i=0 Here variable 'i' is passed via stack which is pushed on stack at 0x40053e. But we are probing at 0x400536. To resolve this issues, we need to probe on next instruction after prologue. gdb and systemtap also does same thing. I've implemented this patch based on approach systemtap has used. After applying patch: $ perf probe -x ./test 'foo i' $ cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/ravi/test:0x0000000000000541 i=-4(%bp):s32 $ perf record -e probe_test:foo ./test $ perf script test 6300 [001] 5877.879327: probe_test:foo: (400541) i=42 No need to skip prologue for optimized case since debug info is correct for each instructions for -O2 -g. For more details please visit: https://bugzilla.redhat.com/show_bug.cgi?id=612253#c6 Changes in v2: - Skipping prologue only when any ARG is either C variable, $params or $vars. - Probe on line(:1) may not be always possible. Recommend only address to force probe on function entry. Committer notes: Testing it with 'perf trace': # perf probe -x ./test foo i Added new event: probe_test:foo (on foo in /home/acme/c/test with i) You can now use it in all perf tools, such as: perf record -e probe_test:foo -aR sleep 1 # cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/acme/c/test:0x0000000000000526 i=-12(%sp):s32 # trace --no-sys --event probe_*:* ./test i: 42 0.000 probe_test:foo:(400526) i=0) # After the patch: # perf probe -d *:* Removed event: probe_test:foo # perf probe -x ./test foo i Target program is compiled without optimization. Skipping prologue. Probe on address 0x400526 to force probing at the function entry. Added new event: probe_test:foo (on foo in /home/acme/c/test with i) You can now use it in all perf tools, such as: perf record -e probe_test:foo -aR sleep 1 # cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/acme/c/test:0x0000000000000531 i=-4(%bp):s32 # trace --no-sys --event probe_*:* ./test i: 42 0.000 probe_test:foo:(400531) i=42) # Reported-by: Michael Petlan <mpetlan@redhat.com> Report-Link: https://www.mail-archive.com/linux-perf-users@vger.kernel.org/msg02348.html Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Cc: Yauheni Kaliuta <yauheni.kaliuta@redhat.com> Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1299021 Link: http://lkml.kernel.org/r/1470214725-5023-2-git-send-email-ravi.bangoria@linux.vnet.ibm.com [ Rename 'die' to 'cu_die' to avoid shadowing a die() definition on at least centos 5, Debian 7 and ubuntu:12.04.5] [ Use PRIx64 instead of lx to format a Dwarf_Addr, aka long long unsigned int, fixing the build on 32-bit systems ] [ dwarf_getsrclines() expects a size_t * argument ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-08-03 16:58:45 +08:00
static void skip_prologue(Dwarf_Die *sp_die, struct probe_finder *pf)
{
struct perf_probe_point *pp = &pf->pev->point;
/* Not uprobe? */
if (!pf->pev->uprobes)
return;
/* Compiled with optimization? */
if (die_is_optimized_target(&pf->cu_die))
perf uprobe: Skip prologue if program compiled without optimization The function prologue prepares stack and registers before executing function logic. When target program is compiled without optimization, function parameter information is only valid after the prologue. When we probe entrypc of the function, and try to record a function parameter, it contains a garbage value. For example: $ vim test.c #include <stdio.h> void foo(int i) { printf("i: %d\n", i); } int main() { foo(42); return 0; } $ gcc -g test.c -o test $ objdump -dl test | less foo(): /home/ravi/test.c:4 400536: 55 push %rbp 400537: 48 89 e5 mov %rsp,%rbp 40053a: 48 83 ec 10 sub -bashx10,%rsp 40053e: 89 7d fc mov %edi,-0x4(%rbp) /home/ravi/test.c:5 400541: 8b 45 fc mov -0x4(%rbp),%eax ... ... main(): /home/ravi/test.c:9 400558: 55 push %rbp 400559: 48 89 e5 mov %rsp,%rbp /home/ravi/test.c:10 40055c: bf 2a 00 00 00 mov -bashx2a,%edi 400561: e8 d0 ff ff ff callq 400536 <foo> $ perf probe -x ./test 'foo i' $ cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/ravi/test:0x0000000000000536 i=-12(%sp):s32 $ perf record -e probe_test:foo ./test $ perf script test 5778 [001] 4918.562027: probe_test:foo: (400536) i=0 Here variable 'i' is passed via stack which is pushed on stack at 0x40053e. But we are probing at 0x400536. To resolve this issues, we need to probe on next instruction after prologue. gdb and systemtap also does same thing. I've implemented this patch based on approach systemtap has used. After applying patch: $ perf probe -x ./test 'foo i' $ cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/ravi/test:0x0000000000000541 i=-4(%bp):s32 $ perf record -e probe_test:foo ./test $ perf script test 6300 [001] 5877.879327: probe_test:foo: (400541) i=42 No need to skip prologue for optimized case since debug info is correct for each instructions for -O2 -g. For more details please visit: https://bugzilla.redhat.com/show_bug.cgi?id=612253#c6 Changes in v2: - Skipping prologue only when any ARG is either C variable, $params or $vars. - Probe on line(:1) may not be always possible. Recommend only address to force probe on function entry. Committer notes: Testing it with 'perf trace': # perf probe -x ./test foo i Added new event: probe_test:foo (on foo in /home/acme/c/test with i) You can now use it in all perf tools, such as: perf record -e probe_test:foo -aR sleep 1 # cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/acme/c/test:0x0000000000000526 i=-12(%sp):s32 # trace --no-sys --event probe_*:* ./test i: 42 0.000 probe_test:foo:(400526) i=0) # After the patch: # perf probe -d *:* Removed event: probe_test:foo # perf probe -x ./test foo i Target program is compiled without optimization. Skipping prologue. Probe on address 0x400526 to force probing at the function entry. Added new event: probe_test:foo (on foo in /home/acme/c/test with i) You can now use it in all perf tools, such as: perf record -e probe_test:foo -aR sleep 1 # cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/acme/c/test:0x0000000000000531 i=-4(%bp):s32 # trace --no-sys --event probe_*:* ./test i: 42 0.000 probe_test:foo:(400531) i=42) # Reported-by: Michael Petlan <mpetlan@redhat.com> Report-Link: https://www.mail-archive.com/linux-perf-users@vger.kernel.org/msg02348.html Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Cc: Yauheni Kaliuta <yauheni.kaliuta@redhat.com> Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1299021 Link: http://lkml.kernel.org/r/1470214725-5023-2-git-send-email-ravi.bangoria@linux.vnet.ibm.com [ Rename 'die' to 'cu_die' to avoid shadowing a die() definition on at least centos 5, Debian 7 and ubuntu:12.04.5] [ Use PRIx64 instead of lx to format a Dwarf_Addr, aka long long unsigned int, fixing the build on 32-bit systems ] [ dwarf_getsrclines() expects a size_t * argument ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-08-03 16:58:45 +08:00
return;
/* Don't know entrypc? */
if (!pf->addr)
return;
/* Only FUNC and FUNC@SRC are eligible. */
if (!pp->function || pp->line || pp->retprobe || pp->lazy_line ||
pp->offset || pp->abs_address)
return;
/* Not interested in func parameter? */
if (!perf_probe_with_var(pf->pev))
return;
pr_info("Target program is compiled without optimization. Skipping prologue.\n"
"Probe on address 0x%" PRIx64 " to force probing at the function entry.\n\n",
pf->addr);
die_skip_prologue(sp_die, &pf->cu_die, &pf->addr);
perf uprobe: Skip prologue if program compiled without optimization The function prologue prepares stack and registers before executing function logic. When target program is compiled without optimization, function parameter information is only valid after the prologue. When we probe entrypc of the function, and try to record a function parameter, it contains a garbage value. For example: $ vim test.c #include <stdio.h> void foo(int i) { printf("i: %d\n", i); } int main() { foo(42); return 0; } $ gcc -g test.c -o test $ objdump -dl test | less foo(): /home/ravi/test.c:4 400536: 55 push %rbp 400537: 48 89 e5 mov %rsp,%rbp 40053a: 48 83 ec 10 sub -bashx10,%rsp 40053e: 89 7d fc mov %edi,-0x4(%rbp) /home/ravi/test.c:5 400541: 8b 45 fc mov -0x4(%rbp),%eax ... ... main(): /home/ravi/test.c:9 400558: 55 push %rbp 400559: 48 89 e5 mov %rsp,%rbp /home/ravi/test.c:10 40055c: bf 2a 00 00 00 mov -bashx2a,%edi 400561: e8 d0 ff ff ff callq 400536 <foo> $ perf probe -x ./test 'foo i' $ cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/ravi/test:0x0000000000000536 i=-12(%sp):s32 $ perf record -e probe_test:foo ./test $ perf script test 5778 [001] 4918.562027: probe_test:foo: (400536) i=0 Here variable 'i' is passed via stack which is pushed on stack at 0x40053e. But we are probing at 0x400536. To resolve this issues, we need to probe on next instruction after prologue. gdb and systemtap also does same thing. I've implemented this patch based on approach systemtap has used. After applying patch: $ perf probe -x ./test 'foo i' $ cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/ravi/test:0x0000000000000541 i=-4(%bp):s32 $ perf record -e probe_test:foo ./test $ perf script test 6300 [001] 5877.879327: probe_test:foo: (400541) i=42 No need to skip prologue for optimized case since debug info is correct for each instructions for -O2 -g. For more details please visit: https://bugzilla.redhat.com/show_bug.cgi?id=612253#c6 Changes in v2: - Skipping prologue only when any ARG is either C variable, $params or $vars. - Probe on line(:1) may not be always possible. Recommend only address to force probe on function entry. Committer notes: Testing it with 'perf trace': # perf probe -x ./test foo i Added new event: probe_test:foo (on foo in /home/acme/c/test with i) You can now use it in all perf tools, such as: perf record -e probe_test:foo -aR sleep 1 # cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/acme/c/test:0x0000000000000526 i=-12(%sp):s32 # trace --no-sys --event probe_*:* ./test i: 42 0.000 probe_test:foo:(400526) i=0) # After the patch: # perf probe -d *:* Removed event: probe_test:foo # perf probe -x ./test foo i Target program is compiled without optimization. Skipping prologue. Probe on address 0x400526 to force probing at the function entry. Added new event: probe_test:foo (on foo in /home/acme/c/test with i) You can now use it in all perf tools, such as: perf record -e probe_test:foo -aR sleep 1 # cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/acme/c/test:0x0000000000000531 i=-4(%bp):s32 # trace --no-sys --event probe_*:* ./test i: 42 0.000 probe_test:foo:(400531) i=42) # Reported-by: Michael Petlan <mpetlan@redhat.com> Report-Link: https://www.mail-archive.com/linux-perf-users@vger.kernel.org/msg02348.html Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Cc: Yauheni Kaliuta <yauheni.kaliuta@redhat.com> Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1299021 Link: http://lkml.kernel.org/r/1470214725-5023-2-git-send-email-ravi.bangoria@linux.vnet.ibm.com [ Rename 'die' to 'cu_die' to avoid shadowing a die() definition on at least centos 5, Debian 7 and ubuntu:12.04.5] [ Use PRIx64 instead of lx to format a Dwarf_Addr, aka long long unsigned int, fixing the build on 32-bit systems ] [ dwarf_getsrclines() expects a size_t * argument ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-08-03 16:58:45 +08:00
}
static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
{
struct probe_finder *pf = data;
struct perf_probe_point *pp = &pf->pev->point;
Dwarf_Addr addr;
int ret;
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
if (pp->lazy_line)
ret = find_probe_point_lazy(in_die, pf);
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
else {
/* Get probe address */
2019-10-25 16:46:43 +08:00
if (die_entrypc(in_die, &addr) != 0) {
pr_warning("Failed to get entry address of %s.\n",
dwarf_diename(in_die));
return -ENOENT;
}
perf probe: Skip if the function address is 0 Skip probes if the entry address of the target function is 0. This can happen when we're handling C++ debuginfo files. E.g. without this fix, below case still fail. ---- $ ./perf probe -x /usr/lib64/libstdc++.so.6 -vD is_open probe-definition(0): is_open symbol:is_open file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments symbol:catch file:(null) line:0 offset:0 return:0 lazy:(null) symbol:throw file:(null) line:0 offset:0 return:0 lazy:(null) symbol:rethrow file:(null) line:0 offset:0 return:0 lazy:(null) Open Debuginfo file: /usr/lib/debug/usr/lib64/libstdc++.so.6.0.22.debug Try to find probe point from debuginfo. Matched function: is_open [295df] found inline addr: 0x8ca80 Probe point found: is_open+0 found inline addr: 0x8ca70 Probe point found: is_open+0 found inline addr: 0x8ca60 Probe point found: is_open+0 Matched function: is_open [6527f] Matched function: is_open [9fe8a] Probe point found: is_open+0 Matched function: is_open [19710b] found inline addr: 0xecca9 Probe point found: stdio_filebuf+57 found inline addr: 0x0 Probe point found: swap+0 Matched function: is_open [19fc9d] Probe point found: is_open+0 Found 7 probe_trace_events. p:probe_libstdc++/is_open /usr/lib64/libstdc++.so.6.0.22:0x8ca80 p:probe_libstdc++/is_open_1 /usr/lib64/libstdc++.so.6.0.22:0x8ca70 p:probe_libstdc++/is_open_2 /usr/lib64/libstdc++.so.6.0.22:0x8ca60 p:probe_libstdc++/is_open_3 /usr/lib64/libstdc++.so.6.0.22:0xb0ad0 p:probe_libstdc++/is_open_4 /usr/lib64/libstdc++.so.6.0.22:0xecca9 Failed to synthesize probe trace event. Error: Failed to add events. Reason: Invalid argument (Code: -22) ---- This is because some instances have entry_pc == 0 (see 19710b and 19fc9d). With this fix, those are skipped. ---- $ ./perf probe -x /usr/lib64/libstdc++.so.6 -D is_open p:probe_libstdc++/is_open /usr/lib64/libstdc++.so.6.0.22:0x8ca80 p:probe_libstdc++/is_open_1 /usr/lib64/libstdc++.so.6.0.22:0x8ca70 p:probe_libstdc++/is_open_2 /usr/lib64/libstdc++.so.6.0.22:0x8ca60 p:probe_libstdc++/is_open_3 /usr/lib64/libstdc++.so.6.0.22:0xb0ad0 p:probe_libstdc++/is_open_4 /usr/lib64/libstdc++.so.6.0.22:0xecca9 ---- Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/147464490707.29804.14277897643725143867.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-23 23:35:07 +08:00
if (addr == 0) {
pr_debug("%s has no valid entry address. skipped.\n",
dwarf_diename(in_die));
return -ENOENT;
}
pf->addr = addr;
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
pf->addr += pp->offset;
pr_debug("found inline addr: 0x%jx\n",
(uintmax_t)pf->addr);
ret = call_probe_finder(in_die, pf);
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
}
return ret;
}
/* Callback parameter with return value for libdw */
struct dwarf_callback_param {
void *data;
int retval;
};
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
/* Search function from function name */
static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
{
struct dwarf_callback_param *param = data;
struct probe_finder *pf = param->data;
struct perf_probe_point *pp = &pf->pev->point;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
/* Check tag and diename */
if (!die_is_func_def(sp_die) ||
!die_match_name(sp_die, pp->function))
return DWARF_CB_OK;
/* Check declared file */
if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die)))
return DWARF_CB_OK;
perf probe: Ignore the error of finding inline instance Ignore the error when the perf probe failed to find inline function instances. This can happen when we search a method in C++ debuginfo. If there is completely no instance in target, perf probe can return an error. E.g. without this fix: ---- $ perf probe -x /usr/lib64/libstdc++.so.6 -vD showmanyc probe-definition(0): showmanyc symbol:showmanyc file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments symbol:catch file:(null) line:0 offset:0 return:0 lazy:(null) symbol:throw file:(null) line:0 offset:0 return:0 lazy:(null) symbol:rethrow file:(null) line:0 offset:0 return:0 lazy:(null) Open Debuginfo file: /usr/lib/debug/usr/lib64/libstdc++.so.6.0.22.debug Try to find probe point from debuginfo. Matched function: showmanyc An error occurred in debuginfo analysis (-2). Trying to use symbols. Failed to find symbol showmanyc in /usr/lib64/libstdc++.so.6.0.22 Error: Failed to add events. Reason: No such file or directory (Code: -2) ---- This is because one of showmanyc is defined as inline but no instance found. With this fix, it is succeeded to show as below. ---- $ perf probe -x /usr/lib64/libstdc++.so.6 -D showmanyc p:probe_libstdc++/showmanyc /usr/lib64/libstdc++.so.6.0.22:0xb0e50 p:probe_libstdc++/showmanyc_1 /usr/lib64/libstdc++.so.6.0.22:0xc7c40 p:probe_libstdc++/showmanyc_2 /usr/lib64/libstdc++.so.6.0.22:0xecfa0 p:probe_libstdc++/showmanyc_3 /usr/lib64/libstdc++.so.6.0.22:0x115fc0 p:probe_libstdc++/showmanyc_4 /usr/lib64/libstdc++.so.6.0.22:0x121a90 ---- Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/147464489775.29804.3190419491209875936.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-23 23:34:57 +08:00
pr_debug("Matched function: %s [%lx]\n", dwarf_diename(sp_die),
(unsigned long)dwarf_dieoffset(sp_die));
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
pf->fname = dwarf_decl_file(sp_die);
if (pp->line) { /* Function relative line */
dwarf_decl_line(sp_die, &pf->lno);
pf->lno += pp->line;
param->retval = find_probe_point_by_line(pf);
} else if (die_is_func_instance(sp_die)) {
/* Instances always have the entry address */
perf probe: Fix to probe a function which has no entry pc Fix 'perf probe' to probe a function which has no entry pc or low pc but only has ranges attribute. probe_point_search_cb() uses dwarf_entrypc() to get the probe address, but that doesn't work for the function DIE which has only ranges attribute. Use die_entrypc() instead. Without this fix: # perf probe -k ../build-x86_64/vmlinux -D clear_tasks_mm_cpumask:0 Probe point 'clear_tasks_mm_cpumask' not found. Error: Failed to add events. With this: # perf probe -k ../build-x86_64/vmlinux -D clear_tasks_mm_cpumask:0 p:probe/clear_tasks_mm_cpumask clear_tasks_mm_cpumask+0 Committer testing: Before: [root@quaco ~]# perf probe clear_tasks_mm_cpumask:0 Probe point 'clear_tasks_mm_cpumask' not found. Error: Failed to add events. [root@quaco ~]# After: [root@quaco ~]# perf probe clear_tasks_mm_cpumask:0 Added new event: probe:clear_tasks_mm_cpumask (on clear_tasks_mm_cpumask) You can now use it in all perf tools, such as: perf record -e probe:clear_tasks_mm_cpumask -aR sleep 1 [root@quaco ~]# Using it with 'perf trace': [root@quaco ~]# perf trace -e probe:clear_tasks_mm_cpumask Doesn't seem to be used in x86_64: $ find . -name "*.c" | xargs grep clear_tasks_mm_cpumask ./kernel/cpu.c: * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU ./kernel/cpu.c:void clear_tasks_mm_cpumask(int cpu) ./arch/xtensa/kernel/smp.c: clear_tasks_mm_cpumask(cpu); ./arch/csky/kernel/smp.c: clear_tasks_mm_cpumask(cpu); ./arch/sh/kernel/smp.c: clear_tasks_mm_cpumask(cpu); ./arch/arm/kernel/smp.c: clear_tasks_mm_cpumask(cpu); ./arch/powerpc/mm/nohash/mmu_context.c: clear_tasks_mm_cpumask(cpu); $ find . -name "*.h" | xargs grep clear_tasks_mm_cpumask ./include/linux/cpu.h:void clear_tasks_mm_cpumask(int cpu); $ find . -name "*.S" | xargs grep clear_tasks_mm_cpumask $ Fixes: e1ecbbc3fa83 ("perf probe: Fix to handle optimized not-inlined functions") Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lore.kernel.org/lkml/157199319438.8075.4695576954550638618.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-10-25 16:46:34 +08:00
die_entrypc(sp_die, &pf->addr);
perf probe: Skip if the function address is 0 Skip probes if the entry address of the target function is 0. This can happen when we're handling C++ debuginfo files. E.g. without this fix, below case still fail. ---- $ ./perf probe -x /usr/lib64/libstdc++.so.6 -vD is_open probe-definition(0): is_open symbol:is_open file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments symbol:catch file:(null) line:0 offset:0 return:0 lazy:(null) symbol:throw file:(null) line:0 offset:0 return:0 lazy:(null) symbol:rethrow file:(null) line:0 offset:0 return:0 lazy:(null) Open Debuginfo file: /usr/lib/debug/usr/lib64/libstdc++.so.6.0.22.debug Try to find probe point from debuginfo. Matched function: is_open [295df] found inline addr: 0x8ca80 Probe point found: is_open+0 found inline addr: 0x8ca70 Probe point found: is_open+0 found inline addr: 0x8ca60 Probe point found: is_open+0 Matched function: is_open [6527f] Matched function: is_open [9fe8a] Probe point found: is_open+0 Matched function: is_open [19710b] found inline addr: 0xecca9 Probe point found: stdio_filebuf+57 found inline addr: 0x0 Probe point found: swap+0 Matched function: is_open [19fc9d] Probe point found: is_open+0 Found 7 probe_trace_events. p:probe_libstdc++/is_open /usr/lib64/libstdc++.so.6.0.22:0x8ca80 p:probe_libstdc++/is_open_1 /usr/lib64/libstdc++.so.6.0.22:0x8ca70 p:probe_libstdc++/is_open_2 /usr/lib64/libstdc++.so.6.0.22:0x8ca60 p:probe_libstdc++/is_open_3 /usr/lib64/libstdc++.so.6.0.22:0xb0ad0 p:probe_libstdc++/is_open_4 /usr/lib64/libstdc++.so.6.0.22:0xecca9 Failed to synthesize probe trace event. Error: Failed to add events. Reason: Invalid argument (Code: -22) ---- This is because some instances have entry_pc == 0 (see 19710b and 19fc9d). With this fix, those are skipped. ---- $ ./perf probe -x /usr/lib64/libstdc++.so.6 -D is_open p:probe_libstdc++/is_open /usr/lib64/libstdc++.so.6.0.22:0x8ca80 p:probe_libstdc++/is_open_1 /usr/lib64/libstdc++.so.6.0.22:0x8ca70 p:probe_libstdc++/is_open_2 /usr/lib64/libstdc++.so.6.0.22:0x8ca60 p:probe_libstdc++/is_open_3 /usr/lib64/libstdc++.so.6.0.22:0xb0ad0 p:probe_libstdc++/is_open_4 /usr/lib64/libstdc++.so.6.0.22:0xecca9 ---- Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/147464490707.29804.14277897643725143867.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-23 23:35:07 +08:00
/* But in some case the entry address is 0 */
if (pf->addr == 0) {
pr_debug("%s has no entry PC. Skipped\n",
dwarf_diename(sp_die));
param->retval = 0;
/* Real function */
perf probe: Skip if the function address is 0 Skip probes if the entry address of the target function is 0. This can happen when we're handling C++ debuginfo files. E.g. without this fix, below case still fail. ---- $ ./perf probe -x /usr/lib64/libstdc++.so.6 -vD is_open probe-definition(0): is_open symbol:is_open file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments symbol:catch file:(null) line:0 offset:0 return:0 lazy:(null) symbol:throw file:(null) line:0 offset:0 return:0 lazy:(null) symbol:rethrow file:(null) line:0 offset:0 return:0 lazy:(null) Open Debuginfo file: /usr/lib/debug/usr/lib64/libstdc++.so.6.0.22.debug Try to find probe point from debuginfo. Matched function: is_open [295df] found inline addr: 0x8ca80 Probe point found: is_open+0 found inline addr: 0x8ca70 Probe point found: is_open+0 found inline addr: 0x8ca60 Probe point found: is_open+0 Matched function: is_open [6527f] Matched function: is_open [9fe8a] Probe point found: is_open+0 Matched function: is_open [19710b] found inline addr: 0xecca9 Probe point found: stdio_filebuf+57 found inline addr: 0x0 Probe point found: swap+0 Matched function: is_open [19fc9d] Probe point found: is_open+0 Found 7 probe_trace_events. p:probe_libstdc++/is_open /usr/lib64/libstdc++.so.6.0.22:0x8ca80 p:probe_libstdc++/is_open_1 /usr/lib64/libstdc++.so.6.0.22:0x8ca70 p:probe_libstdc++/is_open_2 /usr/lib64/libstdc++.so.6.0.22:0x8ca60 p:probe_libstdc++/is_open_3 /usr/lib64/libstdc++.so.6.0.22:0xb0ad0 p:probe_libstdc++/is_open_4 /usr/lib64/libstdc++.so.6.0.22:0xecca9 Failed to synthesize probe trace event. Error: Failed to add events. Reason: Invalid argument (Code: -22) ---- This is because some instances have entry_pc == 0 (see 19710b and 19fc9d). With this fix, those are skipped. ---- $ ./perf probe -x /usr/lib64/libstdc++.so.6 -D is_open p:probe_libstdc++/is_open /usr/lib64/libstdc++.so.6.0.22:0x8ca80 p:probe_libstdc++/is_open_1 /usr/lib64/libstdc++.so.6.0.22:0x8ca70 p:probe_libstdc++/is_open_2 /usr/lib64/libstdc++.so.6.0.22:0x8ca60 p:probe_libstdc++/is_open_3 /usr/lib64/libstdc++.so.6.0.22:0xb0ad0 p:probe_libstdc++/is_open_4 /usr/lib64/libstdc++.so.6.0.22:0xecca9 ---- Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/147464490707.29804.14277897643725143867.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-23 23:35:07 +08:00
} else if (pp->lazy_line)
param->retval = find_probe_point_lazy(sp_die, pf);
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
else {
perf uprobe: Skip prologue if program compiled without optimization The function prologue prepares stack and registers before executing function logic. When target program is compiled without optimization, function parameter information is only valid after the prologue. When we probe entrypc of the function, and try to record a function parameter, it contains a garbage value. For example: $ vim test.c #include <stdio.h> void foo(int i) { printf("i: %d\n", i); } int main() { foo(42); return 0; } $ gcc -g test.c -o test $ objdump -dl test | less foo(): /home/ravi/test.c:4 400536: 55 push %rbp 400537: 48 89 e5 mov %rsp,%rbp 40053a: 48 83 ec 10 sub -bashx10,%rsp 40053e: 89 7d fc mov %edi,-0x4(%rbp) /home/ravi/test.c:5 400541: 8b 45 fc mov -0x4(%rbp),%eax ... ... main(): /home/ravi/test.c:9 400558: 55 push %rbp 400559: 48 89 e5 mov %rsp,%rbp /home/ravi/test.c:10 40055c: bf 2a 00 00 00 mov -bashx2a,%edi 400561: e8 d0 ff ff ff callq 400536 <foo> $ perf probe -x ./test 'foo i' $ cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/ravi/test:0x0000000000000536 i=-12(%sp):s32 $ perf record -e probe_test:foo ./test $ perf script test 5778 [001] 4918.562027: probe_test:foo: (400536) i=0 Here variable 'i' is passed via stack which is pushed on stack at 0x40053e. But we are probing at 0x400536. To resolve this issues, we need to probe on next instruction after prologue. gdb and systemtap also does same thing. I've implemented this patch based on approach systemtap has used. After applying patch: $ perf probe -x ./test 'foo i' $ cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/ravi/test:0x0000000000000541 i=-4(%bp):s32 $ perf record -e probe_test:foo ./test $ perf script test 6300 [001] 5877.879327: probe_test:foo: (400541) i=42 No need to skip prologue for optimized case since debug info is correct for each instructions for -O2 -g. For more details please visit: https://bugzilla.redhat.com/show_bug.cgi?id=612253#c6 Changes in v2: - Skipping prologue only when any ARG is either C variable, $params or $vars. - Probe on line(:1) may not be always possible. Recommend only address to force probe on function entry. Committer notes: Testing it with 'perf trace': # perf probe -x ./test foo i Added new event: probe_test:foo (on foo in /home/acme/c/test with i) You can now use it in all perf tools, such as: perf record -e probe_test:foo -aR sleep 1 # cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/acme/c/test:0x0000000000000526 i=-12(%sp):s32 # trace --no-sys --event probe_*:* ./test i: 42 0.000 probe_test:foo:(400526) i=0) # After the patch: # perf probe -d *:* Removed event: probe_test:foo # perf probe -x ./test foo i Target program is compiled without optimization. Skipping prologue. Probe on address 0x400526 to force probing at the function entry. Added new event: probe_test:foo (on foo in /home/acme/c/test with i) You can now use it in all perf tools, such as: perf record -e probe_test:foo -aR sleep 1 # cat /sys/kernel/debug/tracing/uprobe_events p:probe_test/foo /home/acme/c/test:0x0000000000000531 i=-4(%bp):s32 # trace --no-sys --event probe_*:* ./test i: 42 0.000 probe_test:foo:(400531) i=42) # Reported-by: Michael Petlan <mpetlan@redhat.com> Report-Link: https://www.mail-archive.com/linux-perf-users@vger.kernel.org/msg02348.html Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Cc: Yauheni Kaliuta <yauheni.kaliuta@redhat.com> Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1299021 Link: http://lkml.kernel.org/r/1470214725-5023-2-git-send-email-ravi.bangoria@linux.vnet.ibm.com [ Rename 'die' to 'cu_die' to avoid shadowing a die() definition on at least centos 5, Debian 7 and ubuntu:12.04.5] [ Use PRIx64 instead of lx to format a Dwarf_Addr, aka long long unsigned int, fixing the build on 32-bit systems ] [ dwarf_getsrclines() expects a size_t * argument ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-08-03 16:58:45 +08:00
skip_prologue(sp_die, pf);
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
pf->addr += pp->offset;
/* TODO: Check the address in this function */
param->retval = call_probe_finder(sp_die, pf);
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
}
} else if (!probe_conf.no_inlines) {
/* Inlined function: search instances */
param->retval = die_walk_instances(sp_die,
probe_point_inline_cb, (void *)pf);
/* This could be a non-existed inline definition */
perf probe: Ignore the error of finding inline instance Ignore the error when the perf probe failed to find inline function instances. This can happen when we search a method in C++ debuginfo. If there is completely no instance in target, perf probe can return an error. E.g. without this fix: ---- $ perf probe -x /usr/lib64/libstdc++.so.6 -vD showmanyc probe-definition(0): showmanyc symbol:showmanyc file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments symbol:catch file:(null) line:0 offset:0 return:0 lazy:(null) symbol:throw file:(null) line:0 offset:0 return:0 lazy:(null) symbol:rethrow file:(null) line:0 offset:0 return:0 lazy:(null) Open Debuginfo file: /usr/lib/debug/usr/lib64/libstdc++.so.6.0.22.debug Try to find probe point from debuginfo. Matched function: showmanyc An error occurred in debuginfo analysis (-2). Trying to use symbols. Failed to find symbol showmanyc in /usr/lib64/libstdc++.so.6.0.22 Error: Failed to add events. Reason: No such file or directory (Code: -2) ---- This is because one of showmanyc is defined as inline but no instance found. With this fix, it is succeeded to show as below. ---- $ perf probe -x /usr/lib64/libstdc++.so.6 -D showmanyc p:probe_libstdc++/showmanyc /usr/lib64/libstdc++.so.6.0.22:0xb0e50 p:probe_libstdc++/showmanyc_1 /usr/lib64/libstdc++.so.6.0.22:0xc7c40 p:probe_libstdc++/showmanyc_2 /usr/lib64/libstdc++.so.6.0.22:0xecfa0 p:probe_libstdc++/showmanyc_3 /usr/lib64/libstdc++.so.6.0.22:0x115fc0 p:probe_libstdc++/showmanyc_4 /usr/lib64/libstdc++.so.6.0.22:0x121a90 ---- Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/147464489775.29804.3190419491209875936.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-23 23:34:57 +08:00
if (param->retval == -ENOENT)
param->retval = 0;
}
/* We need to find other candidates */
if (strisglob(pp->function) && param->retval >= 0) {
param->retval = 0; /* We have to clear the result */
return DWARF_CB_OK;
}
return DWARF_CB_ABORT; /* Exit; no same symbol in this CU. */
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
}
static int find_probe_point_by_func(struct probe_finder *pf)
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
{
struct dwarf_callback_param _param = {.data = (void *)pf,
.retval = 0};
dwarf_getfuncs(&pf->cu_die, probe_point_search_cb, &_param, 0);
return _param.retval;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
}
perf probe: Add fastpath to do lookup by function name v3 -> v2: - Make pubname_search_cb more generic - Add fastpath to find_probes also v2 -> v1: - Don't compare file names with cu_find_realpath(...), instead, compare them with the name returned by dwarf_decl_file(sp_die) The vmlinux file may have thousands of CUs. We can lookup function name from .debug_pubnames section to avoid the slow loop on CUs. 1. Improvement data for find_line_range ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --line csum_partial_copy_to_user > tmp.log before patch applied ===================== 847,988,276 cycles 0.355075856 seconds time elapsed after patch applied ===================== 206,102,622 cycles 0.086883555 seconds time elapsed 2. Improvement data for find_probes ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --vars csum_partial_copy_to_user > tmp.log before patch applied ===================== 848,490,844 cycles 0.355307901 seconds time elapsed after patch applied ===================== 205,684,469 cycles 0.086694010 seconds time elapsed Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-kernel <linux-kernel@vger.kernel.org> LKML-Reference: <1301041668.14111.52.camel@minggr.sh.intel.com> Signed-off-by: Lin Ming <ming.m.lin@intel.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-03-25 16:27:48 +08:00
struct pubname_callback_param {
char *function;
char *file;
Dwarf_Die *cu_die;
Dwarf_Die *sp_die;
int found;
};
static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data)
{
struct pubname_callback_param *param = data;
if (dwarf_offdie(dbg, gl->die_offset, param->sp_die)) {
if (dwarf_tag(param->sp_die) != DW_TAG_subprogram)
return DWARF_CB_OK;
if (die_match_name(param->sp_die, param->function)) {
perf probe: Add fastpath to do lookup by function name v3 -> v2: - Make pubname_search_cb more generic - Add fastpath to find_probes also v2 -> v1: - Don't compare file names with cu_find_realpath(...), instead, compare them with the name returned by dwarf_decl_file(sp_die) The vmlinux file may have thousands of CUs. We can lookup function name from .debug_pubnames section to avoid the slow loop on CUs. 1. Improvement data for find_line_range ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --line csum_partial_copy_to_user > tmp.log before patch applied ===================== 847,988,276 cycles 0.355075856 seconds time elapsed after patch applied ===================== 206,102,622 cycles 0.086883555 seconds time elapsed 2. Improvement data for find_probes ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --vars csum_partial_copy_to_user > tmp.log before patch applied ===================== 848,490,844 cycles 0.355307901 seconds time elapsed after patch applied ===================== 205,684,469 cycles 0.086694010 seconds time elapsed Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-kernel <linux-kernel@vger.kernel.org> LKML-Reference: <1301041668.14111.52.camel@minggr.sh.intel.com> Signed-off-by: Lin Ming <ming.m.lin@intel.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-03-25 16:27:48 +08:00
if (!dwarf_offdie(dbg, gl->cu_offset, param->cu_die))
return DWARF_CB_OK;
if (param->file &&
strtailcmp(param->file, dwarf_decl_file(param->sp_die)))
return DWARF_CB_OK;
param->found = 1;
return DWARF_CB_ABORT;
}
}
return DWARF_CB_OK;
}
perf probe: Search both .eh_frame and .debug_frame sections for probe location 'perf probe' through debuginfo__find_probes() in util/probe-finder.c checks for the functions' frame descriptions in either .eh_frame section of an ELF or the .debug_frame. The check is based on whether either one of these sections is present. Depending on distro, toolchain defaults, architetcutre, build flags, etc., CFI might be found in either .eh_frame and/or .debug_frame. Sometimes, it may happen that, .eh_frame, even if present, may not be complete and may miss some descriptions. Therefore, to be sure, to find the CFI covering an address we will always have to investigate both if available. For e.g., in powerpc, this may happen: $ gcc -g bin.c -o bin $ objdump --dwarf ./bin <1><145>: Abbrev Number: 7 (DW_TAG_subprogram) <146> DW_AT_external : 1 <146> DW_AT_name : (indirect string, offset: 0x9e): main <14a> DW_AT_decl_file : 1 <14b> DW_AT_decl_line : 39 <14c> DW_AT_prototyped : 1 <14c> DW_AT_type : <0x57> <150> DW_AT_low_pc : 0x100007b8 If the .eh_frame and .debug_frame are checked for the same binary, we will find that, .eh_frame (although present) doesn't contain a description for "main" function. But, .debug_frame has a description: 000000d8 00000024 00000000 FDE cie=00000000 pc=100007b8..10000838 DW_CFA_advance_loc: 16 to 100007c8 DW_CFA_def_cfa_offset: 144 DW_CFA_offset_extended_sf: r65 at cfa+16 ... Due to this (since, perf checks whether .eh_frame is present and goes on searching for that address inside that frame), perf is unable to process the probes: # perf probe -x ./bin main Failed to get call frame on 0x100007b8 Error: Failed to add events. To avoid this issue, we need to check both the sections (.eh_frame and .debug_frame), which is done in this patch. Note that, we can always force everything into both .eh_frame and .debug_frame by: $ gcc bin.c -fasynchronous-unwind-tables -fno-dwarf2-cfi-asm -g -o bin Signed-off-by: Hemant Kumar <hemant@linux.vnet.ibm.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: linuxppc-dev@lists.ozlabs.org Cc: Mark Wielaard <mjw@redhat.com> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1454426806-13974-1-git-send-email-hemant@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-02 23:26:46 +08:00
static int debuginfo__find_probe_location(struct debuginfo *dbg,
struct probe_finder *pf)
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
{
struct perf_probe_point *pp = &pf->pev->point;
Dwarf_Off off, noff;
size_t cuhl;
Dwarf_Die *diep;
int ret = 0;
off = 0;
pf->lcache = intlist__new(NULL);
if (!pf->lcache)
return -ENOMEM;
perf probe: Add fastpath to do lookup by function name v3 -> v2: - Make pubname_search_cb more generic - Add fastpath to find_probes also v2 -> v1: - Don't compare file names with cu_find_realpath(...), instead, compare them with the name returned by dwarf_decl_file(sp_die) The vmlinux file may have thousands of CUs. We can lookup function name from .debug_pubnames section to avoid the slow loop on CUs. 1. Improvement data for find_line_range ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --line csum_partial_copy_to_user > tmp.log before patch applied ===================== 847,988,276 cycles 0.355075856 seconds time elapsed after patch applied ===================== 206,102,622 cycles 0.086883555 seconds time elapsed 2. Improvement data for find_probes ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --vars csum_partial_copy_to_user > tmp.log before patch applied ===================== 848,490,844 cycles 0.355307901 seconds time elapsed after patch applied ===================== 205,684,469 cycles 0.086694010 seconds time elapsed Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-kernel <linux-kernel@vger.kernel.org> LKML-Reference: <1301041668.14111.52.camel@minggr.sh.intel.com> Signed-off-by: Lin Ming <ming.m.lin@intel.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-03-25 16:27:48 +08:00
/* Fastpath: lookup by function name from .debug_pubnames section */
if (pp->function && !strisglob(pp->function)) {
perf probe: Add fastpath to do lookup by function name v3 -> v2: - Make pubname_search_cb more generic - Add fastpath to find_probes also v2 -> v1: - Don't compare file names with cu_find_realpath(...), instead, compare them with the name returned by dwarf_decl_file(sp_die) The vmlinux file may have thousands of CUs. We can lookup function name from .debug_pubnames section to avoid the slow loop on CUs. 1. Improvement data for find_line_range ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --line csum_partial_copy_to_user > tmp.log before patch applied ===================== 847,988,276 cycles 0.355075856 seconds time elapsed after patch applied ===================== 206,102,622 cycles 0.086883555 seconds time elapsed 2. Improvement data for find_probes ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --vars csum_partial_copy_to_user > tmp.log before patch applied ===================== 848,490,844 cycles 0.355307901 seconds time elapsed after patch applied ===================== 205,684,469 cycles 0.086694010 seconds time elapsed Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-kernel <linux-kernel@vger.kernel.org> LKML-Reference: <1301041668.14111.52.camel@minggr.sh.intel.com> Signed-off-by: Lin Ming <ming.m.lin@intel.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-03-25 16:27:48 +08:00
struct pubname_callback_param pubname_param = {
.function = pp->function,
.file = pp->file,
.cu_die = &pf->cu_die,
.sp_die = &pf->sp_die,
.found = 0,
perf probe: Add fastpath to do lookup by function name v3 -> v2: - Make pubname_search_cb more generic - Add fastpath to find_probes also v2 -> v1: - Don't compare file names with cu_find_realpath(...), instead, compare them with the name returned by dwarf_decl_file(sp_die) The vmlinux file may have thousands of CUs. We can lookup function name from .debug_pubnames section to avoid the slow loop on CUs. 1. Improvement data for find_line_range ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --line csum_partial_copy_to_user > tmp.log before patch applied ===================== 847,988,276 cycles 0.355075856 seconds time elapsed after patch applied ===================== 206,102,622 cycles 0.086883555 seconds time elapsed 2. Improvement data for find_probes ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --vars csum_partial_copy_to_user > tmp.log before patch applied ===================== 848,490,844 cycles 0.355307901 seconds time elapsed after patch applied ===================== 205,684,469 cycles 0.086694010 seconds time elapsed Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-kernel <linux-kernel@vger.kernel.org> LKML-Reference: <1301041668.14111.52.camel@minggr.sh.intel.com> Signed-off-by: Lin Ming <ming.m.lin@intel.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-03-25 16:27:48 +08:00
};
struct dwarf_callback_param probe_param = {
.data = pf,
};
dwarf_getpubnames(dbg->dbg, pubname_search_cb,
&pubname_param, 0);
perf probe: Add fastpath to do lookup by function name v3 -> v2: - Make pubname_search_cb more generic - Add fastpath to find_probes also v2 -> v1: - Don't compare file names with cu_find_realpath(...), instead, compare them with the name returned by dwarf_decl_file(sp_die) The vmlinux file may have thousands of CUs. We can lookup function name from .debug_pubnames section to avoid the slow loop on CUs. 1. Improvement data for find_line_range ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --line csum_partial_copy_to_user > tmp.log before patch applied ===================== 847,988,276 cycles 0.355075856 seconds time elapsed after patch applied ===================== 206,102,622 cycles 0.086883555 seconds time elapsed 2. Improvement data for find_probes ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --vars csum_partial_copy_to_user > tmp.log before patch applied ===================== 848,490,844 cycles 0.355307901 seconds time elapsed after patch applied ===================== 205,684,469 cycles 0.086694010 seconds time elapsed Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-kernel <linux-kernel@vger.kernel.org> LKML-Reference: <1301041668.14111.52.camel@minggr.sh.intel.com> Signed-off-by: Lin Ming <ming.m.lin@intel.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-03-25 16:27:48 +08:00
if (pubname_param.found) {
ret = probe_point_search_cb(&pf->sp_die, &probe_param);
if (ret)
goto found;
}
}
/* Loop on CUs (Compilation Unit) */
while (!dwarf_nextcu(dbg->dbg, off, &noff, &cuhl, NULL, NULL, NULL)) {
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
/* Get the DIE(Debugging Information Entry) of this CU */
diep = dwarf_offdie(dbg->dbg, off + cuhl, &pf->cu_die);
if (!diep)
continue;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
/* Check if target file is included. */
if (pp->file)
pf->fname = cu_find_realpath(&pf->cu_die, pp->file);
else
pf->fname = NULL;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
if (!pp->file || pf->fname) {
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
if (pp->function)
ret = find_probe_point_by_func(pf);
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
else if (pp->lazy_line)
ret = find_probe_point_lazy(&pf->cu_die, pf);
else {
pf->lno = pp->line;
ret = find_probe_point_by_line(pf);
}
if (ret < 0)
perf probe: Fix error propagation leading to segfault There are two hunks in this patch that stops probe processing as soon as one error is found, breaking out of loops, the other fix an error propagation that should return a negative error number but instead was returning the result of "ret < 0", which is 1 and thus made several error checks fail because they test agains < 0. The problem could be triggered by asking for a variable that was optimized out, fact that should stop the whole probe processing but instead was segfaulting while installing broken probes: [root@emilia ~]# probe perf_mmap:55 user_lock_limit Failed to find the location of user_lock_limit at this address. Perhaps, it has been optimized out. Failed to find 'user_lock_limit' in this function. Add new events: probe:perf_mmap (on perf_mmap:55 with user_lock_limit) probe:perf_mmap_1 (on perf_mmap:55 with user_lock_limit) Segmentation fault (core dumped) [root@emilia ~]# perf probe -l probe:perf_mmap (on perf_mmap:55@git/linux/kernel/perf_event.c with user_lock_limit) probe:perf_mmap_1 (on perf_mmap:55@git/linux/kernel/perf_event.c with user_lock_limit) [root@emilia ~]# After the fix: [root@emilia ~]# probe perf_mmap:55 user_lock_limit Failed to find the location of user_lock_limit at this address. Perhaps, it has been optimized out. Failed to find 'user_lock_limit' in this function. Error: Failed to add events. (-2) [root@emilia ~]# Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-02-22 00:23:57 +08:00
break;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
}
off = noff;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
}
perf probe: Add fastpath to do lookup by function name v3 -> v2: - Make pubname_search_cb more generic - Add fastpath to find_probes also v2 -> v1: - Don't compare file names with cu_find_realpath(...), instead, compare them with the name returned by dwarf_decl_file(sp_die) The vmlinux file may have thousands of CUs. We can lookup function name from .debug_pubnames section to avoid the slow loop on CUs. 1. Improvement data for find_line_range ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --line csum_partial_copy_to_user > tmp.log before patch applied ===================== 847,988,276 cycles 0.355075856 seconds time elapsed after patch applied ===================== 206,102,622 cycles 0.086883555 seconds time elapsed 2. Improvement data for find_probes ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --vars csum_partial_copy_to_user > tmp.log before patch applied ===================== 848,490,844 cycles 0.355307901 seconds time elapsed after patch applied ===================== 205,684,469 cycles 0.086694010 seconds time elapsed Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-kernel <linux-kernel@vger.kernel.org> LKML-Reference: <1301041668.14111.52.camel@minggr.sh.intel.com> Signed-off-by: Lin Ming <ming.m.lin@intel.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-03-25 16:27:48 +08:00
found:
intlist__delete(pf->lcache);
pf->lcache = NULL;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
return ret;
}
perf probe: Search both .eh_frame and .debug_frame sections for probe location 'perf probe' through debuginfo__find_probes() in util/probe-finder.c checks for the functions' frame descriptions in either .eh_frame section of an ELF or the .debug_frame. The check is based on whether either one of these sections is present. Depending on distro, toolchain defaults, architetcutre, build flags, etc., CFI might be found in either .eh_frame and/or .debug_frame. Sometimes, it may happen that, .eh_frame, even if present, may not be complete and may miss some descriptions. Therefore, to be sure, to find the CFI covering an address we will always have to investigate both if available. For e.g., in powerpc, this may happen: $ gcc -g bin.c -o bin $ objdump --dwarf ./bin <1><145>: Abbrev Number: 7 (DW_TAG_subprogram) <146> DW_AT_external : 1 <146> DW_AT_name : (indirect string, offset: 0x9e): main <14a> DW_AT_decl_file : 1 <14b> DW_AT_decl_line : 39 <14c> DW_AT_prototyped : 1 <14c> DW_AT_type : <0x57> <150> DW_AT_low_pc : 0x100007b8 If the .eh_frame and .debug_frame are checked for the same binary, we will find that, .eh_frame (although present) doesn't contain a description for "main" function. But, .debug_frame has a description: 000000d8 00000024 00000000 FDE cie=00000000 pc=100007b8..10000838 DW_CFA_advance_loc: 16 to 100007c8 DW_CFA_def_cfa_offset: 144 DW_CFA_offset_extended_sf: r65 at cfa+16 ... Due to this (since, perf checks whether .eh_frame is present and goes on searching for that address inside that frame), perf is unable to process the probes: # perf probe -x ./bin main Failed to get call frame on 0x100007b8 Error: Failed to add events. To avoid this issue, we need to check both the sections (.eh_frame and .debug_frame), which is done in this patch. Note that, we can always force everything into both .eh_frame and .debug_frame by: $ gcc bin.c -fasynchronous-unwind-tables -fno-dwarf2-cfi-asm -g -o bin Signed-off-by: Hemant Kumar <hemant@linux.vnet.ibm.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: linuxppc-dev@lists.ozlabs.org Cc: Mark Wielaard <mjw@redhat.com> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1454426806-13974-1-git-send-email-hemant@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-02 23:26:46 +08:00
/* Find probe points from debuginfo */
static int debuginfo__find_probes(struct debuginfo *dbg,
struct probe_finder *pf)
{
int ret = 0;
Elf *elf;
GElf_Ehdr ehdr;
if (pf->cfi_eh || pf->cfi_dbg)
return debuginfo__find_probe_location(dbg, pf);
/* Get the call frame information from this dwarf */
elf = dwarf_getelf(dbg->dbg);
if (elf == NULL)
return -EINVAL;
if (gelf_getehdr(elf, &ehdr) == NULL)
return -EINVAL;
pf->machine = ehdr.e_machine;
#if _ELFUTILS_PREREQ(0, 142)
do {
GElf_Shdr shdr;
if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
shdr.sh_type == SHT_PROGBITS)
pf->cfi_eh = dwarf_getcfi_elf(elf);
perf probe: Search both .eh_frame and .debug_frame sections for probe location 'perf probe' through debuginfo__find_probes() in util/probe-finder.c checks for the functions' frame descriptions in either .eh_frame section of an ELF or the .debug_frame. The check is based on whether either one of these sections is present. Depending on distro, toolchain defaults, architetcutre, build flags, etc., CFI might be found in either .eh_frame and/or .debug_frame. Sometimes, it may happen that, .eh_frame, even if present, may not be complete and may miss some descriptions. Therefore, to be sure, to find the CFI covering an address we will always have to investigate both if available. For e.g., in powerpc, this may happen: $ gcc -g bin.c -o bin $ objdump --dwarf ./bin <1><145>: Abbrev Number: 7 (DW_TAG_subprogram) <146> DW_AT_external : 1 <146> DW_AT_name : (indirect string, offset: 0x9e): main <14a> DW_AT_decl_file : 1 <14b> DW_AT_decl_line : 39 <14c> DW_AT_prototyped : 1 <14c> DW_AT_type : <0x57> <150> DW_AT_low_pc : 0x100007b8 If the .eh_frame and .debug_frame are checked for the same binary, we will find that, .eh_frame (although present) doesn't contain a description for "main" function. But, .debug_frame has a description: 000000d8 00000024 00000000 FDE cie=00000000 pc=100007b8..10000838 DW_CFA_advance_loc: 16 to 100007c8 DW_CFA_def_cfa_offset: 144 DW_CFA_offset_extended_sf: r65 at cfa+16 ... Due to this (since, perf checks whether .eh_frame is present and goes on searching for that address inside that frame), perf is unable to process the probes: # perf probe -x ./bin main Failed to get call frame on 0x100007b8 Error: Failed to add events. To avoid this issue, we need to check both the sections (.eh_frame and .debug_frame), which is done in this patch. Note that, we can always force everything into both .eh_frame and .debug_frame by: $ gcc bin.c -fasynchronous-unwind-tables -fno-dwarf2-cfi-asm -g -o bin Signed-off-by: Hemant Kumar <hemant@linux.vnet.ibm.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: linuxppc-dev@lists.ozlabs.org Cc: Mark Wielaard <mjw@redhat.com> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1454426806-13974-1-git-send-email-hemant@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-02 23:26:46 +08:00
pf->cfi_dbg = dwarf_getcfi(dbg->dbg);
} while (0);
perf probe: Search both .eh_frame and .debug_frame sections for probe location 'perf probe' through debuginfo__find_probes() in util/probe-finder.c checks for the functions' frame descriptions in either .eh_frame section of an ELF or the .debug_frame. The check is based on whether either one of these sections is present. Depending on distro, toolchain defaults, architetcutre, build flags, etc., CFI might be found in either .eh_frame and/or .debug_frame. Sometimes, it may happen that, .eh_frame, even if present, may not be complete and may miss some descriptions. Therefore, to be sure, to find the CFI covering an address we will always have to investigate both if available. For e.g., in powerpc, this may happen: $ gcc -g bin.c -o bin $ objdump --dwarf ./bin <1><145>: Abbrev Number: 7 (DW_TAG_subprogram) <146> DW_AT_external : 1 <146> DW_AT_name : (indirect string, offset: 0x9e): main <14a> DW_AT_decl_file : 1 <14b> DW_AT_decl_line : 39 <14c> DW_AT_prototyped : 1 <14c> DW_AT_type : <0x57> <150> DW_AT_low_pc : 0x100007b8 If the .eh_frame and .debug_frame are checked for the same binary, we will find that, .eh_frame (although present) doesn't contain a description for "main" function. But, .debug_frame has a description: 000000d8 00000024 00000000 FDE cie=00000000 pc=100007b8..10000838 DW_CFA_advance_loc: 16 to 100007c8 DW_CFA_def_cfa_offset: 144 DW_CFA_offset_extended_sf: r65 at cfa+16 ... Due to this (since, perf checks whether .eh_frame is present and goes on searching for that address inside that frame), perf is unable to process the probes: # perf probe -x ./bin main Failed to get call frame on 0x100007b8 Error: Failed to add events. To avoid this issue, we need to check both the sections (.eh_frame and .debug_frame), which is done in this patch. Note that, we can always force everything into both .eh_frame and .debug_frame by: $ gcc bin.c -fasynchronous-unwind-tables -fno-dwarf2-cfi-asm -g -o bin Signed-off-by: Hemant Kumar <hemant@linux.vnet.ibm.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: linuxppc-dev@lists.ozlabs.org Cc: Mark Wielaard <mjw@redhat.com> Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1454426806-13974-1-git-send-email-hemant@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-02 23:26:46 +08:00
#endif
ret = debuginfo__find_probe_location(dbg, pf);
return ret;
}
struct local_vars_finder {
struct probe_finder *pf;
struct perf_probe_arg *args;
perf probe: Support $params special probe argument $params is similar to $vars but matches only function parameters not local variables. Thus, this is useful for tracing function parameter changing or tracing function call with parameters. Testing it: # perf probe tcp_sendmsg '$params' Added new event: probe:tcp_sendmsg (on tcp_sendmsg with $params) You can now use it in all perf tools, such as: perf record -e probe:tcp_sendmsg -aR sleep 1 # perf probe -l probe:tcp_sendmsg (on tcp_sendmsg@acme/git/linux/net/ipv4/tcp.c with iocb sk msg size) # perf record -a -e probe:* press some random letters to generate TCP (sshd) traffic... ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.223 MB perf.data (6 samples) ] # perf script sshd 6385 [2] 3.907529: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.138973: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.378966: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.603681: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.818455: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 5.043603: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 # cat /sys/kernel/debug/tracing/events/probe/tcp_sendmsg/format name: tcp_sendmsg ID: 1927 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1; signed:0; field:int common_pid; offset:4; size:4; signed:1; field:unsigned long __probe_ip; offset:8; size:8; signed:0; field:u64 iocb; offset:16; size:8; signed:0; field:u64 sk; offset:24; size:8; signed:0; field:u64 msg; offset:32; size:8; signed:0; field:u64 size; offset:40; size:8; signed:0; print fmt: "(%lx) iocb=0x%Lx sk=0x%Lx msg=0x%Lx size=0x%Lx", REC->__probe_ip, REC->iocb, REC->sk, REC->msg, REC->size # Do some system wide tracing of this probe + write syscalls: # perf trace -e write --ev probe:* --filter-pids 6385 462.612 (0.010 ms): bash/19153 write(fd: 1</dev/pts/1>, buf: 0x7f7556c78000, count: 29 ) = 29 462.701 (0.027 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.701 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.710 (0.035 ms): sshd/19152 ... [continued]: write()) = 68 462.787 (0.009 ms): bash/19153 write(fd: 2</dev/pts/1>, buf: 0x7f7556c77000, count: 22 ) = 22 462.865 (0.002 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.865 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.873 (0.010 ms): sshd/19152 ... [continued]: write()) = 68 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150506124653.4961.59806.stgit@localhost.localdomain [ Add some examples to the changelog message showing how to use it ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-06 20:46:53 +08:00
bool vars;
int max_args;
int nargs;
int ret;
};
/* Collect available variables in this scope */
static int copy_variables_cb(Dwarf_Die *die_mem, void *data)
{
struct local_vars_finder *vf = data;
struct probe_finder *pf = vf->pf;
int tag;
tag = dwarf_tag(die_mem);
if (tag == DW_TAG_formal_parameter ||
perf probe: Support $params special probe argument $params is similar to $vars but matches only function parameters not local variables. Thus, this is useful for tracing function parameter changing or tracing function call with parameters. Testing it: # perf probe tcp_sendmsg '$params' Added new event: probe:tcp_sendmsg (on tcp_sendmsg with $params) You can now use it in all perf tools, such as: perf record -e probe:tcp_sendmsg -aR sleep 1 # perf probe -l probe:tcp_sendmsg (on tcp_sendmsg@acme/git/linux/net/ipv4/tcp.c with iocb sk msg size) # perf record -a -e probe:* press some random letters to generate TCP (sshd) traffic... ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.223 MB perf.data (6 samples) ] # perf script sshd 6385 [2] 3.907529: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.138973: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.378966: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.603681: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.818455: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 5.043603: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 # cat /sys/kernel/debug/tracing/events/probe/tcp_sendmsg/format name: tcp_sendmsg ID: 1927 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1; signed:0; field:int common_pid; offset:4; size:4; signed:1; field:unsigned long __probe_ip; offset:8; size:8; signed:0; field:u64 iocb; offset:16; size:8; signed:0; field:u64 sk; offset:24; size:8; signed:0; field:u64 msg; offset:32; size:8; signed:0; field:u64 size; offset:40; size:8; signed:0; print fmt: "(%lx) iocb=0x%Lx sk=0x%Lx msg=0x%Lx size=0x%Lx", REC->__probe_ip, REC->iocb, REC->sk, REC->msg, REC->size # Do some system wide tracing of this probe + write syscalls: # perf trace -e write --ev probe:* --filter-pids 6385 462.612 (0.010 ms): bash/19153 write(fd: 1</dev/pts/1>, buf: 0x7f7556c78000, count: 29 ) = 29 462.701 (0.027 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.701 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.710 (0.035 ms): sshd/19152 ... [continued]: write()) = 68 462.787 (0.009 ms): bash/19153 write(fd: 2</dev/pts/1>, buf: 0x7f7556c77000, count: 22 ) = 22 462.865 (0.002 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.865 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.873 (0.010 ms): sshd/19152 ... [continued]: write()) = 68 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150506124653.4961.59806.stgit@localhost.localdomain [ Add some examples to the changelog message showing how to use it ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-06 20:46:53 +08:00
(tag == DW_TAG_variable && vf->vars)) {
if (convert_variable_location(die_mem, vf->pf->addr,
vf->pf->fb_ops, &pf->sp_die,
pf->machine, NULL) == 0) {
vf->args[vf->nargs].var = (char *)dwarf_diename(die_mem);
if (vf->args[vf->nargs].var == NULL) {
vf->ret = -ENOMEM;
return DIE_FIND_CB_END;
}
pr_debug(" %s", vf->args[vf->nargs].var);
vf->nargs++;
}
}
if (dwarf_haspc(die_mem, vf->pf->addr))
return DIE_FIND_CB_CONTINUE;
else
return DIE_FIND_CB_SIBLING;
}
static int expand_probe_args(Dwarf_Die *sc_die, struct probe_finder *pf,
struct perf_probe_arg *args)
{
Dwarf_Die die_mem;
int i;
int n = 0;
perf probe: Support $params special probe argument $params is similar to $vars but matches only function parameters not local variables. Thus, this is useful for tracing function parameter changing or tracing function call with parameters. Testing it: # perf probe tcp_sendmsg '$params' Added new event: probe:tcp_sendmsg (on tcp_sendmsg with $params) You can now use it in all perf tools, such as: perf record -e probe:tcp_sendmsg -aR sleep 1 # perf probe -l probe:tcp_sendmsg (on tcp_sendmsg@acme/git/linux/net/ipv4/tcp.c with iocb sk msg size) # perf record -a -e probe:* press some random letters to generate TCP (sshd) traffic... ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.223 MB perf.data (6 samples) ] # perf script sshd 6385 [2] 3.907529: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.138973: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.378966: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.603681: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.818455: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 5.043603: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 # cat /sys/kernel/debug/tracing/events/probe/tcp_sendmsg/format name: tcp_sendmsg ID: 1927 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1; signed:0; field:int common_pid; offset:4; size:4; signed:1; field:unsigned long __probe_ip; offset:8; size:8; signed:0; field:u64 iocb; offset:16; size:8; signed:0; field:u64 sk; offset:24; size:8; signed:0; field:u64 msg; offset:32; size:8; signed:0; field:u64 size; offset:40; size:8; signed:0; print fmt: "(%lx) iocb=0x%Lx sk=0x%Lx msg=0x%Lx size=0x%Lx", REC->__probe_ip, REC->iocb, REC->sk, REC->msg, REC->size # Do some system wide tracing of this probe + write syscalls: # perf trace -e write --ev probe:* --filter-pids 6385 462.612 (0.010 ms): bash/19153 write(fd: 1</dev/pts/1>, buf: 0x7f7556c78000, count: 29 ) = 29 462.701 (0.027 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.701 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.710 (0.035 ms): sshd/19152 ... [continued]: write()) = 68 462.787 (0.009 ms): bash/19153 write(fd: 2</dev/pts/1>, buf: 0x7f7556c77000, count: 22 ) = 22 462.865 (0.002 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.865 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.873 (0.010 ms): sshd/19152 ... [continued]: write()) = 68 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150506124653.4961.59806.stgit@localhost.localdomain [ Add some examples to the changelog message showing how to use it ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-06 20:46:53 +08:00
struct local_vars_finder vf = {.pf = pf, .args = args, .vars = false,
.max_args = MAX_PROBE_ARGS, .ret = 0};
for (i = 0; i < pf->pev->nargs; i++) {
/* var never be NULL */
perf probe: Support $params special probe argument $params is similar to $vars but matches only function parameters not local variables. Thus, this is useful for tracing function parameter changing or tracing function call with parameters. Testing it: # perf probe tcp_sendmsg '$params' Added new event: probe:tcp_sendmsg (on tcp_sendmsg with $params) You can now use it in all perf tools, such as: perf record -e probe:tcp_sendmsg -aR sleep 1 # perf probe -l probe:tcp_sendmsg (on tcp_sendmsg@acme/git/linux/net/ipv4/tcp.c with iocb sk msg size) # perf record -a -e probe:* press some random letters to generate TCP (sshd) traffic... ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.223 MB perf.data (6 samples) ] # perf script sshd 6385 [2] 3.907529: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.138973: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.378966: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.603681: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.818455: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 5.043603: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 # cat /sys/kernel/debug/tracing/events/probe/tcp_sendmsg/format name: tcp_sendmsg ID: 1927 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1; signed:0; field:int common_pid; offset:4; size:4; signed:1; field:unsigned long __probe_ip; offset:8; size:8; signed:0; field:u64 iocb; offset:16; size:8; signed:0; field:u64 sk; offset:24; size:8; signed:0; field:u64 msg; offset:32; size:8; signed:0; field:u64 size; offset:40; size:8; signed:0; print fmt: "(%lx) iocb=0x%Lx sk=0x%Lx msg=0x%Lx size=0x%Lx", REC->__probe_ip, REC->iocb, REC->sk, REC->msg, REC->size # Do some system wide tracing of this probe + write syscalls: # perf trace -e write --ev probe:* --filter-pids 6385 462.612 (0.010 ms): bash/19153 write(fd: 1</dev/pts/1>, buf: 0x7f7556c78000, count: 29 ) = 29 462.701 (0.027 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.701 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.710 (0.035 ms): sshd/19152 ... [continued]: write()) = 68 462.787 (0.009 ms): bash/19153 write(fd: 2</dev/pts/1>, buf: 0x7f7556c77000, count: 22 ) = 22 462.865 (0.002 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.865 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.873 (0.010 ms): sshd/19152 ... [continued]: write()) = 68 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150506124653.4961.59806.stgit@localhost.localdomain [ Add some examples to the changelog message showing how to use it ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-06 20:46:53 +08:00
if (strcmp(pf->pev->args[i].var, PROBE_ARG_VARS) == 0)
vf.vars = true;
else if (strcmp(pf->pev->args[i].var, PROBE_ARG_PARAMS) != 0) {
/* Copy normal argument */
args[n] = pf->pev->args[i];
n++;
perf probe: Support $params special probe argument $params is similar to $vars but matches only function parameters not local variables. Thus, this is useful for tracing function parameter changing or tracing function call with parameters. Testing it: # perf probe tcp_sendmsg '$params' Added new event: probe:tcp_sendmsg (on tcp_sendmsg with $params) You can now use it in all perf tools, such as: perf record -e probe:tcp_sendmsg -aR sleep 1 # perf probe -l probe:tcp_sendmsg (on tcp_sendmsg@acme/git/linux/net/ipv4/tcp.c with iocb sk msg size) # perf record -a -e probe:* press some random letters to generate TCP (sshd) traffic... ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.223 MB perf.data (6 samples) ] # perf script sshd 6385 [2] 3.907529: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.138973: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.378966: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.603681: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.818455: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 5.043603: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 # cat /sys/kernel/debug/tracing/events/probe/tcp_sendmsg/format name: tcp_sendmsg ID: 1927 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1; signed:0; field:int common_pid; offset:4; size:4; signed:1; field:unsigned long __probe_ip; offset:8; size:8; signed:0; field:u64 iocb; offset:16; size:8; signed:0; field:u64 sk; offset:24; size:8; signed:0; field:u64 msg; offset:32; size:8; signed:0; field:u64 size; offset:40; size:8; signed:0; print fmt: "(%lx) iocb=0x%Lx sk=0x%Lx msg=0x%Lx size=0x%Lx", REC->__probe_ip, REC->iocb, REC->sk, REC->msg, REC->size # Do some system wide tracing of this probe + write syscalls: # perf trace -e write --ev probe:* --filter-pids 6385 462.612 (0.010 ms): bash/19153 write(fd: 1</dev/pts/1>, buf: 0x7f7556c78000, count: 29 ) = 29 462.701 (0.027 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.701 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.710 (0.035 ms): sshd/19152 ... [continued]: write()) = 68 462.787 (0.009 ms): bash/19153 write(fd: 2</dev/pts/1>, buf: 0x7f7556c77000, count: 22 ) = 22 462.865 (0.002 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.865 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.873 (0.010 ms): sshd/19152 ... [continued]: write()) = 68 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150506124653.4961.59806.stgit@localhost.localdomain [ Add some examples to the changelog message showing how to use it ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-06 20:46:53 +08:00
continue;
}
perf probe: Support $params special probe argument $params is similar to $vars but matches only function parameters not local variables. Thus, this is useful for tracing function parameter changing or tracing function call with parameters. Testing it: # perf probe tcp_sendmsg '$params' Added new event: probe:tcp_sendmsg (on tcp_sendmsg with $params) You can now use it in all perf tools, such as: perf record -e probe:tcp_sendmsg -aR sleep 1 # perf probe -l probe:tcp_sendmsg (on tcp_sendmsg@acme/git/linux/net/ipv4/tcp.c with iocb sk msg size) # perf record -a -e probe:* press some random letters to generate TCP (sshd) traffic... ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.223 MB perf.data (6 samples) ] # perf script sshd 6385 [2] 3.907529: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.138973: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.378966: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.603681: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 4.818455: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 sshd 6385 [2] 5.043603: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24 # cat /sys/kernel/debug/tracing/events/probe/tcp_sendmsg/format name: tcp_sendmsg ID: 1927 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1; signed:0; field:int common_pid; offset:4; size:4; signed:1; field:unsigned long __probe_ip; offset:8; size:8; signed:0; field:u64 iocb; offset:16; size:8; signed:0; field:u64 sk; offset:24; size:8; signed:0; field:u64 msg; offset:32; size:8; signed:0; field:u64 size; offset:40; size:8; signed:0; print fmt: "(%lx) iocb=0x%Lx sk=0x%Lx msg=0x%Lx size=0x%Lx", REC->__probe_ip, REC->iocb, REC->sk, REC->msg, REC->size # Do some system wide tracing of this probe + write syscalls: # perf trace -e write --ev probe:* --filter-pids 6385 462.612 (0.010 ms): bash/19153 write(fd: 1</dev/pts/1>, buf: 0x7f7556c78000, count: 29 ) = 29 462.701 (0.027 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.701 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.710 (0.035 ms): sshd/19152 ... [continued]: write()) = 68 462.787 (0.009 ms): bash/19153 write(fd: 2</dev/pts/1>, buf: 0x7f7556c77000, count: 22 ) = 22 462.865 (0.002 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ... 462.865 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44) 462.873 (0.010 ms): sshd/19152 ... [continued]: write()) = 68 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Hemant Kumar <hemant@linux.vnet.ibm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20150506124653.4961.59806.stgit@localhost.localdomain [ Add some examples to the changelog message showing how to use it ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-06 20:46:53 +08:00
pr_debug("Expanding %s into:", pf->pev->args[i].var);
vf.nargs = n;
/* Special local variables */
die_find_child(sc_die, copy_variables_cb, (void *)&vf,
&die_mem);
pr_debug(" (%d)\n", vf.nargs - n);
if (vf.ret < 0)
return vf.ret;
n = vf.nargs;
}
return n;
}
static bool trace_event_finder_overlap(struct trace_event_finder *tf)
{
int i;
for (i = 0; i < tf->ntevs; i++) {
if (tf->pf.addr == tf->tevs[i].point.address)
return true;
}
return false;
}
/* Add a found probe point into trace event list */
static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
{
struct trace_event_finder *tf =
container_of(pf, struct trace_event_finder, pf);
struct perf_probe_point *pp = &pf->pev->point;
struct probe_trace_event *tev;
perf probe: Clear probe_trace_event when add_probe_trace_event() fails When probing with a glob, errors in add_probe_trace_event() won't be passed to debuginfo__find_trace_events() because it would be modified by probe_point_search_cb(). It causes a segfault if perf fails to find an argument for a probe point matched by the glob. For example: # ./perf probe -v -n 'SyS_dup? oldfd' probe-definition(0): SyS_dup? oldfd symbol:SyS_dup? file:(null) line:0 offset:0 return:0 lazy:(null) parsing arg: oldfd into oldfd 1 arguments Looking at the vmlinux_path (7 entries long) Using /lib/modules/4.3.0-rc4+/build/vmlinux for symbols Open Debuginfo file: /lib/modules/4.3.0-rc4+/build/vmlinux Try to find probe point from debuginfo. Matched function: SyS_dup3 found inline addr: 0xffffffff812095c0 Probe point found: SyS_dup3+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. found inline addr: 0xffffffff812096d4 Probe point found: SyS_dup2+36 Searching 'oldfd' variable in context. Failed to find 'oldfd' in this function. Matched function: SyS_dup3 Probe point found: SyS_dup3+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. Matched function: SyS_dup2 Probe point found: SyS_dup2+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. Found 4 probe_trace_events. Opening /sys/kernel/debug/tracing//kprobe_events write=1 Writing event: p:probe/SyS_dup3 _text+2135488 oldfd=%di:s64 Segmentation fault (core dumped) # This patch ensures that add_probe_trace_event() doesn't touches tf->ntevs and tf->tevs if those functions fail. After the patch: # perf probe 'SyS_dup? oldfd' Failed to find 'oldfd' in this function. Added new events: probe:SyS_dup3 (on SyS_dup? with oldfd) probe:SyS_dup3_1 (on SyS_dup? with oldfd) probe:SyS_dup2 (on SyS_dup? with oldfd) You can now use it in all perf tools, such as: perf record -e probe:SyS_dup2 -aR sleep 1 Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447417761-156094-3-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-13 20:29:11 +08:00
struct perf_probe_arg *args = NULL;
int ret, i;
/*
* For some reason (e.g. different column assigned to same address)
* This callback can be called with the address which already passed.
* Ignore it first.
*/
if (trace_event_finder_overlap(tf))
return 0;
/* Check number of tevs */
if (tf->ntevs == tf->max_tevs) {
pr_warning("Too many( > %d) probe point found.\n",
tf->max_tevs);
return -ERANGE;
}
tev = &tf->tevs[tf->ntevs++];
/* Trace point should be converted from subprogram DIE */
perf probe: Fix probing symbols with optimization suffix Fix perf probe to probe on some symbols which have some optimzation suffixes, e.g. ".part", ".isra", and ".constprop". To fix this issue, instead of using the DIE name, perf probe uses the symbol name found by dwfl_module_addrsym(). This also involves a perf probe --vars operation update which now shows the symbol name instead of the DIE name. Without this patch, putting a probe on an inlined function which was compiled with a suffixed symbol will fail like this: $ perf probe -v getname_flags probe-definition(0): getname_flags symbol:getname_flags file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments Looking at the vmlinux_path (6 entries long) Using /lib/modules/3.11.0+/build/vmlinux for symbols found inline addr: 0xffffffff8119bb70 Probe point found: getname_flags+0 found inline addr: 0xffffffff8119bcb6 Probe point found: getname+6 found inline addr: 0xffffffff811a06a6 Probe point found: user_path_at_empty+6 find 3 probe_trace_events. Opening /sys/kernel/debug//tracing/kprobe_events write=1 Added new events: Writing event: p:probe/getname_flags getname_flags+0 Failed to write event: No such file or directory Error: Failed to add events. (-1) Because the debuginfo knows only the original (non suffix) symbol name, it uses the original symbol for probe address but the kernel (kallsyms) knows only suffixed symbol. Then, the kernel rejects that original symbol. This patch uses dwfl_module_addrsym() to get the correct (suffixed) symbol from symtab when a probe point is found. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130925131616.31632.46658.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-25 21:16:16 +08:00
ret = convert_to_trace_point(&pf->sp_die, tf->mod, pf->addr,
pp->retprobe, pp->function, &tev->point);
if (ret < 0)
perf probe: Clear probe_trace_event when add_probe_trace_event() fails When probing with a glob, errors in add_probe_trace_event() won't be passed to debuginfo__find_trace_events() because it would be modified by probe_point_search_cb(). It causes a segfault if perf fails to find an argument for a probe point matched by the glob. For example: # ./perf probe -v -n 'SyS_dup? oldfd' probe-definition(0): SyS_dup? oldfd symbol:SyS_dup? file:(null) line:0 offset:0 return:0 lazy:(null) parsing arg: oldfd into oldfd 1 arguments Looking at the vmlinux_path (7 entries long) Using /lib/modules/4.3.0-rc4+/build/vmlinux for symbols Open Debuginfo file: /lib/modules/4.3.0-rc4+/build/vmlinux Try to find probe point from debuginfo. Matched function: SyS_dup3 found inline addr: 0xffffffff812095c0 Probe point found: SyS_dup3+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. found inline addr: 0xffffffff812096d4 Probe point found: SyS_dup2+36 Searching 'oldfd' variable in context. Failed to find 'oldfd' in this function. Matched function: SyS_dup3 Probe point found: SyS_dup3+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. Matched function: SyS_dup2 Probe point found: SyS_dup2+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. Found 4 probe_trace_events. Opening /sys/kernel/debug/tracing//kprobe_events write=1 Writing event: p:probe/SyS_dup3 _text+2135488 oldfd=%di:s64 Segmentation fault (core dumped) # This patch ensures that add_probe_trace_event() doesn't touches tf->ntevs and tf->tevs if those functions fail. After the patch: # perf probe 'SyS_dup? oldfd' Failed to find 'oldfd' in this function. Added new events: probe:SyS_dup3 (on SyS_dup? with oldfd) probe:SyS_dup3_1 (on SyS_dup? with oldfd) probe:SyS_dup2 (on SyS_dup? with oldfd) You can now use it in all perf tools, such as: perf record -e probe:SyS_dup2 -aR sleep 1 Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447417761-156094-3-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-13 20:29:11 +08:00
goto end;
tev->point.realname = strdup(dwarf_diename(sc_die));
perf probe: Clear probe_trace_event when add_probe_trace_event() fails When probing with a glob, errors in add_probe_trace_event() won't be passed to debuginfo__find_trace_events() because it would be modified by probe_point_search_cb(). It causes a segfault if perf fails to find an argument for a probe point matched by the glob. For example: # ./perf probe -v -n 'SyS_dup? oldfd' probe-definition(0): SyS_dup? oldfd symbol:SyS_dup? file:(null) line:0 offset:0 return:0 lazy:(null) parsing arg: oldfd into oldfd 1 arguments Looking at the vmlinux_path (7 entries long) Using /lib/modules/4.3.0-rc4+/build/vmlinux for symbols Open Debuginfo file: /lib/modules/4.3.0-rc4+/build/vmlinux Try to find probe point from debuginfo. Matched function: SyS_dup3 found inline addr: 0xffffffff812095c0 Probe point found: SyS_dup3+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. found inline addr: 0xffffffff812096d4 Probe point found: SyS_dup2+36 Searching 'oldfd' variable in context. Failed to find 'oldfd' in this function. Matched function: SyS_dup3 Probe point found: SyS_dup3+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. Matched function: SyS_dup2 Probe point found: SyS_dup2+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. Found 4 probe_trace_events. Opening /sys/kernel/debug/tracing//kprobe_events write=1 Writing event: p:probe/SyS_dup3 _text+2135488 oldfd=%di:s64 Segmentation fault (core dumped) # This patch ensures that add_probe_trace_event() doesn't touches tf->ntevs and tf->tevs if those functions fail. After the patch: # perf probe 'SyS_dup? oldfd' Failed to find 'oldfd' in this function. Added new events: probe:SyS_dup3 (on SyS_dup? with oldfd) probe:SyS_dup3_1 (on SyS_dup? with oldfd) probe:SyS_dup2 (on SyS_dup? with oldfd) You can now use it in all perf tools, such as: perf record -e probe:SyS_dup2 -aR sleep 1 Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447417761-156094-3-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-13 20:29:11 +08:00
if (!tev->point.realname) {
ret = -ENOMEM;
goto end;
}
pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
tev->point.offset);
/* Expand special probe argument if exist */
args = zalloc(sizeof(struct perf_probe_arg) * MAX_PROBE_ARGS);
perf probe: Clear probe_trace_event when add_probe_trace_event() fails When probing with a glob, errors in add_probe_trace_event() won't be passed to debuginfo__find_trace_events() because it would be modified by probe_point_search_cb(). It causes a segfault if perf fails to find an argument for a probe point matched by the glob. For example: # ./perf probe -v -n 'SyS_dup? oldfd' probe-definition(0): SyS_dup? oldfd symbol:SyS_dup? file:(null) line:0 offset:0 return:0 lazy:(null) parsing arg: oldfd into oldfd 1 arguments Looking at the vmlinux_path (7 entries long) Using /lib/modules/4.3.0-rc4+/build/vmlinux for symbols Open Debuginfo file: /lib/modules/4.3.0-rc4+/build/vmlinux Try to find probe point from debuginfo. Matched function: SyS_dup3 found inline addr: 0xffffffff812095c0 Probe point found: SyS_dup3+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. found inline addr: 0xffffffff812096d4 Probe point found: SyS_dup2+36 Searching 'oldfd' variable in context. Failed to find 'oldfd' in this function. Matched function: SyS_dup3 Probe point found: SyS_dup3+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. Matched function: SyS_dup2 Probe point found: SyS_dup2+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. Found 4 probe_trace_events. Opening /sys/kernel/debug/tracing//kprobe_events write=1 Writing event: p:probe/SyS_dup3 _text+2135488 oldfd=%di:s64 Segmentation fault (core dumped) # This patch ensures that add_probe_trace_event() doesn't touches tf->ntevs and tf->tevs if those functions fail. After the patch: # perf probe 'SyS_dup? oldfd' Failed to find 'oldfd' in this function. Added new events: probe:SyS_dup3 (on SyS_dup? with oldfd) probe:SyS_dup3_1 (on SyS_dup? with oldfd) probe:SyS_dup2 (on SyS_dup? with oldfd) You can now use it in all perf tools, such as: perf record -e probe:SyS_dup2 -aR sleep 1 Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447417761-156094-3-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-13 20:29:11 +08:00
if (args == NULL) {
ret = -ENOMEM;
goto end;
}
ret = expand_probe_args(sc_die, pf, args);
if (ret < 0)
goto end;
tev->nargs = ret;
tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
if (tev->args == NULL) {
ret = -ENOMEM;
goto end;
}
/* Find each argument */
for (i = 0; i < tev->nargs; i++) {
pf->pvar = &args[i];
pf->tvar = &tev->args[i];
/* Variable should be found from scope DIE */
ret = find_variable(sc_die, pf);
if (ret != 0)
break;
}
end:
perf probe: Clear probe_trace_event when add_probe_trace_event() fails When probing with a glob, errors in add_probe_trace_event() won't be passed to debuginfo__find_trace_events() because it would be modified by probe_point_search_cb(). It causes a segfault if perf fails to find an argument for a probe point matched by the glob. For example: # ./perf probe -v -n 'SyS_dup? oldfd' probe-definition(0): SyS_dup? oldfd symbol:SyS_dup? file:(null) line:0 offset:0 return:0 lazy:(null) parsing arg: oldfd into oldfd 1 arguments Looking at the vmlinux_path (7 entries long) Using /lib/modules/4.3.0-rc4+/build/vmlinux for symbols Open Debuginfo file: /lib/modules/4.3.0-rc4+/build/vmlinux Try to find probe point from debuginfo. Matched function: SyS_dup3 found inline addr: 0xffffffff812095c0 Probe point found: SyS_dup3+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. found inline addr: 0xffffffff812096d4 Probe point found: SyS_dup2+36 Searching 'oldfd' variable in context. Failed to find 'oldfd' in this function. Matched function: SyS_dup3 Probe point found: SyS_dup3+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. Matched function: SyS_dup2 Probe point found: SyS_dup2+0 Searching 'oldfd' variable in context. Converting variable oldfd into trace event. oldfd type is long int. Found 4 probe_trace_events. Opening /sys/kernel/debug/tracing//kprobe_events write=1 Writing event: p:probe/SyS_dup3 _text+2135488 oldfd=%di:s64 Segmentation fault (core dumped) # This patch ensures that add_probe_trace_event() doesn't touches tf->ntevs and tf->tevs if those functions fail. After the patch: # perf probe 'SyS_dup? oldfd' Failed to find 'oldfd' in this function. Added new events: probe:SyS_dup3 (on SyS_dup? with oldfd) probe:SyS_dup3_1 (on SyS_dup? with oldfd) probe:SyS_dup2 (on SyS_dup? with oldfd) You can now use it in all perf tools, such as: perf record -e probe:SyS_dup2 -aR sleep 1 Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1447417761-156094-3-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-13 20:29:11 +08:00
if (ret) {
clear_probe_trace_event(tev);
tf->ntevs--;
}
free(args);
return ret;
}
perf probe: Trace a magic number if variable is not found Trace a magic number as immediate value if the target variable is not found at some probe points which is based on one probe event. This feature is good for the case if you trace a source code line with some local variables, which is compiled into several instructions and some of the variables are optimized out on some instructions. Even if so, with this feature, perf probe trace a magic number instead of such disappeared variables and fold those probes on one event. E.g. without this patch: # perf probe -D "pud_page_vaddr pud" Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+23558082 pud=%ax:x64 p:probe/pud_page_vaddr _text+328373 pud=%r8:x64 p:probe/pud_page_vaddr _text+348448 pud=%bx:x64 p:probe/pud_page_vaddr _text+23816818 pud=%bx:x64 With this patch: # perf probe -D "pud_page_vaddr pud" | head spurious_kernel_fault is blacklisted function, skip it. vmalloc_fault is blacklisted function, skip it. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+149051 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+315926 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23807209 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23557365 pud=%ax:x64 p:probe/pud_page_vaddr _text+314097 pud=%di:x64 p:probe/pud_page_vaddr _text+314015 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+313893 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+324083 pud=\deade12d:x64 Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Link: http://lore.kernel.org/lkml/157406476931.24476.6261475888681844285.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-18 16:12:49 +08:00
static int fill_empty_trace_arg(struct perf_probe_event *pev,
struct probe_trace_event *tevs, int ntevs)
{
char **valp;
char *type;
int i, j, ret;
for (i = 0; i < pev->nargs; i++) {
type = NULL;
for (j = 0; j < ntevs; j++) {
if (tevs[j].args[i].value) {
type = tevs[j].args[i].type;
break;
}
}
if (j == ntevs) {
print_var_not_found(pev->args[i].var);
return -ENOENT;
}
for (j = 0; j < ntevs; j++) {
valp = &tevs[j].args[i].value;
if (*valp)
continue;
ret = asprintf(valp, "\\%lx", probe_conf.magic_num);
if (ret < 0)
return -ENOMEM;
/* Note that type can be NULL */
if (type) {
tevs[j].args[i].type = strdup(type);
if (!tevs[j].args[i].type)
return -ENOMEM;
}
}
}
return 0;
}
/* Find probe_trace_events specified by perf_probe_event from debuginfo */
int debuginfo__find_trace_events(struct debuginfo *dbg,
struct perf_probe_event *pev,
struct probe_trace_event **tevs)
{
struct trace_event_finder tf = {
.pf = {.pev = pev, .callback = add_probe_trace_event},
.max_tevs = probe_conf.max_probes, .mod = dbg->mod};
int ret, i;
/* Allocate result tevs array */
*tevs = zalloc(sizeof(struct probe_trace_event) * tf.max_tevs);
if (*tevs == NULL)
return -ENOMEM;
tf.tevs = *tevs;
tf.ntevs = 0;
perf probe: Trace a magic number if variable is not found Trace a magic number as immediate value if the target variable is not found at some probe points which is based on one probe event. This feature is good for the case if you trace a source code line with some local variables, which is compiled into several instructions and some of the variables are optimized out on some instructions. Even if so, with this feature, perf probe trace a magic number instead of such disappeared variables and fold those probes on one event. E.g. without this patch: # perf probe -D "pud_page_vaddr pud" Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+23558082 pud=%ax:x64 p:probe/pud_page_vaddr _text+328373 pud=%r8:x64 p:probe/pud_page_vaddr _text+348448 pud=%bx:x64 p:probe/pud_page_vaddr _text+23816818 pud=%bx:x64 With this patch: # perf probe -D "pud_page_vaddr pud" | head spurious_kernel_fault is blacklisted function, skip it. vmalloc_fault is blacklisted function, skip it. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+149051 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+315926 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23807209 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23557365 pud=%ax:x64 p:probe/pud_page_vaddr _text+314097 pud=%di:x64 p:probe/pud_page_vaddr _text+314015 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+313893 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+324083 pud=\deade12d:x64 Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Link: http://lore.kernel.org/lkml/157406476931.24476.6261475888681844285.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-18 16:12:49 +08:00
if (pev->nargs != 0 && immediate_value_is_supported())
tf.pf.skip_empty_arg = true;
ret = debuginfo__find_probes(dbg, &tf.pf);
perf probe: Trace a magic number if variable is not found Trace a magic number as immediate value if the target variable is not found at some probe points which is based on one probe event. This feature is good for the case if you trace a source code line with some local variables, which is compiled into several instructions and some of the variables are optimized out on some instructions. Even if so, with this feature, perf probe trace a magic number instead of such disappeared variables and fold those probes on one event. E.g. without this patch: # perf probe -D "pud_page_vaddr pud" Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. Failed to find 'pud' in this function. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+23558082 pud=%ax:x64 p:probe/pud_page_vaddr _text+328373 pud=%r8:x64 p:probe/pud_page_vaddr _text+348448 pud=%bx:x64 p:probe/pud_page_vaddr _text+23816818 pud=%bx:x64 With this patch: # perf probe -D "pud_page_vaddr pud" | head spurious_kernel_fault is blacklisted function, skip it. vmalloc_fault is blacklisted function, skip it. p:probe/pud_page_vaddr _text+23480787 pud=%ax:x64 p:probe/pud_page_vaddr _text+149051 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23808453 pud=%bp:x64 p:probe/pud_page_vaddr _text+315926 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23807209 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+23557365 pud=%ax:x64 p:probe/pud_page_vaddr _text+314097 pud=%di:x64 p:probe/pud_page_vaddr _text+314015 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+313893 pud=\deade12d:x64 p:probe/pud_page_vaddr _text+324083 pud=\deade12d:x64 Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Link: http://lore.kernel.org/lkml/157406476931.24476.6261475888681844285.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-18 16:12:49 +08:00
if (ret >= 0 && tf.pf.skip_empty_arg)
ret = fill_empty_trace_arg(pev, tf.tevs, tf.ntevs);
if (ret < 0) {
for (i = 0; i < tf.ntevs; i++)
clear_probe_trace_event(&tf.tevs[i]);
zfree(tevs);
return ret;
}
return (ret < 0) ? ret : tf.ntevs;
}
/* Collect available variables in this scope */
static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
{
struct available_var_finder *af = data;
struct variable_list *vl;
struct strbuf buf = STRBUF_INIT;
int tag, ret;
vl = &af->vls[af->nvls - 1];
tag = dwarf_tag(die_mem);
if (tag == DW_TAG_formal_parameter ||
tag == DW_TAG_variable) {
ret = convert_variable_location(die_mem, af->pf.addr,
af->pf.fb_ops, &af->pf.sp_die,
af->pf.machine, NULL);
perf probe: Add --range option to show a variable's location range It is not easy for users to get the accurate byte offset or the line number where a local variable can be probed. With '--range' option, local variables in the scope of the probe point are showed with a byte offset range, and can be added according to this range information. For example, there are some variables in the function generic_perform_write(): <generic_perform_write@mm/filemap.c:0> 0 ssize_t generic_perform_write(struct file *file, 1 struct iov_iter *i, loff_t pos) 2 { 3 struct address_space *mapping = file->f_mapping; 4 const struct address_space_operations *a_ops = mapping->a_ops; ... 42 status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); 44 if (unlikely(status < 0)) But we fail when we try to probe the variable 'a_ops' at line 42 or 44. $ perf probe --add 'generic_perform_write:42 a_ops' Failed to find the location of a_ops at this address. Perhaps, it has been optimized out. This is because the source code do not match the assembly, so a variable may not be available in the source code line where it appears. After this patch, we can lookup the accurate byte offset range of a variable, 'INV' indicates that this variable is not valid at the given point, but available in the scope: $ perf probe --vars 'generic_perform_write:42' --range Available variables at generic_perform_write:42 @<generic_perform_write+141> [INV] ssize_t written @<generic_perform_write+[324-331]> [INV] struct address_space_operations* a_ops @<generic_perform_write+[55-61,170-176,223-246]> [VAL] (unknown_type) fsdata @<generic_perform_write+[70-307,346-411]> [VAL] loff_t pos @<generic_perform_write+[0-286,286-336,346-411]> [VAL] long int status @<generic_perform_write+[83-342,346-411]> [VAL] long unsigned int bytes @<generic_perform_write+[122-311,320-338,346-403,403-411]> [VAL] struct address_space* mapping @<generic_perform_write+[35-344,346-411]> [VAL] struct iov_iter* i @<generic_perform_write+[0-340,346-411]> [VAL] struct page* page @<generic_perform_write+[70-307,346-411]> Then it is more clear for us to add a probe with this variable: $ perf probe --add 'generic_perform_write+170 a_ops' Added new event: probe:generic_perform_write (on generic_perform_write+170 with a_ops) Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1431336304-16863-2-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-11 17:25:03 +08:00
if (ret == 0 || ret == -ERANGE) {
int ret2;
bool externs = !af->child;
if (strbuf_init(&buf, 64) < 0)
goto error;
perf probe: Add --range option to show a variable's location range It is not easy for users to get the accurate byte offset or the line number where a local variable can be probed. With '--range' option, local variables in the scope of the probe point are showed with a byte offset range, and can be added according to this range information. For example, there are some variables in the function generic_perform_write(): <generic_perform_write@mm/filemap.c:0> 0 ssize_t generic_perform_write(struct file *file, 1 struct iov_iter *i, loff_t pos) 2 { 3 struct address_space *mapping = file->f_mapping; 4 const struct address_space_operations *a_ops = mapping->a_ops; ... 42 status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); 44 if (unlikely(status < 0)) But we fail when we try to probe the variable 'a_ops' at line 42 or 44. $ perf probe --add 'generic_perform_write:42 a_ops' Failed to find the location of a_ops at this address. Perhaps, it has been optimized out. This is because the source code do not match the assembly, so a variable may not be available in the source code line where it appears. After this patch, we can lookup the accurate byte offset range of a variable, 'INV' indicates that this variable is not valid at the given point, but available in the scope: $ perf probe --vars 'generic_perform_write:42' --range Available variables at generic_perform_write:42 @<generic_perform_write+141> [INV] ssize_t written @<generic_perform_write+[324-331]> [INV] struct address_space_operations* a_ops @<generic_perform_write+[55-61,170-176,223-246]> [VAL] (unknown_type) fsdata @<generic_perform_write+[70-307,346-411]> [VAL] loff_t pos @<generic_perform_write+[0-286,286-336,346-411]> [VAL] long int status @<generic_perform_write+[83-342,346-411]> [VAL] long unsigned int bytes @<generic_perform_write+[122-311,320-338,346-403,403-411]> [VAL] struct address_space* mapping @<generic_perform_write+[35-344,346-411]> [VAL] struct iov_iter* i @<generic_perform_write+[0-340,346-411]> [VAL] struct page* page @<generic_perform_write+[70-307,346-411]> Then it is more clear for us to add a probe with this variable: $ perf probe --add 'generic_perform_write+170 a_ops' Added new event: probe:generic_perform_write (on generic_perform_write+170 with a_ops) Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1431336304-16863-2-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-11 17:25:03 +08:00
if (probe_conf.show_location_range) {
if (!externs)
ret2 = strbuf_add(&buf,
ret ? "[INV]\t" : "[VAL]\t", 6);
else
ret2 = strbuf_add(&buf, "[EXT]\t", 6);
if (ret2)
goto error;
perf probe: Add --range option to show a variable's location range It is not easy for users to get the accurate byte offset or the line number where a local variable can be probed. With '--range' option, local variables in the scope of the probe point are showed with a byte offset range, and can be added according to this range information. For example, there are some variables in the function generic_perform_write(): <generic_perform_write@mm/filemap.c:0> 0 ssize_t generic_perform_write(struct file *file, 1 struct iov_iter *i, loff_t pos) 2 { 3 struct address_space *mapping = file->f_mapping; 4 const struct address_space_operations *a_ops = mapping->a_ops; ... 42 status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); 44 if (unlikely(status < 0)) But we fail when we try to probe the variable 'a_ops' at line 42 or 44. $ perf probe --add 'generic_perform_write:42 a_ops' Failed to find the location of a_ops at this address. Perhaps, it has been optimized out. This is because the source code do not match the assembly, so a variable may not be available in the source code line where it appears. After this patch, we can lookup the accurate byte offset range of a variable, 'INV' indicates that this variable is not valid at the given point, but available in the scope: $ perf probe --vars 'generic_perform_write:42' --range Available variables at generic_perform_write:42 @<generic_perform_write+141> [INV] ssize_t written @<generic_perform_write+[324-331]> [INV] struct address_space_operations* a_ops @<generic_perform_write+[55-61,170-176,223-246]> [VAL] (unknown_type) fsdata @<generic_perform_write+[70-307,346-411]> [VAL] loff_t pos @<generic_perform_write+[0-286,286-336,346-411]> [VAL] long int status @<generic_perform_write+[83-342,346-411]> [VAL] long unsigned int bytes @<generic_perform_write+[122-311,320-338,346-403,403-411]> [VAL] struct address_space* mapping @<generic_perform_write+[35-344,346-411]> [VAL] struct iov_iter* i @<generic_perform_write+[0-340,346-411]> [VAL] struct page* page @<generic_perform_write+[70-307,346-411]> Then it is more clear for us to add a probe with this variable: $ perf probe --add 'generic_perform_write+170 a_ops' Added new event: probe:generic_perform_write (on generic_perform_write+170 with a_ops) Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1431336304-16863-2-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-11 17:25:03 +08:00
}
ret2 = die_get_varname(die_mem, &buf);
if (!ret2 && probe_conf.show_location_range &&
!externs) {
if (strbuf_addch(&buf, '\t') < 0)
goto error;
perf probe: Add --range option to show a variable's location range It is not easy for users to get the accurate byte offset or the line number where a local variable can be probed. With '--range' option, local variables in the scope of the probe point are showed with a byte offset range, and can be added according to this range information. For example, there are some variables in the function generic_perform_write(): <generic_perform_write@mm/filemap.c:0> 0 ssize_t generic_perform_write(struct file *file, 1 struct iov_iter *i, loff_t pos) 2 { 3 struct address_space *mapping = file->f_mapping; 4 const struct address_space_operations *a_ops = mapping->a_ops; ... 42 status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); 44 if (unlikely(status < 0)) But we fail when we try to probe the variable 'a_ops' at line 42 or 44. $ perf probe --add 'generic_perform_write:42 a_ops' Failed to find the location of a_ops at this address. Perhaps, it has been optimized out. This is because the source code do not match the assembly, so a variable may not be available in the source code line where it appears. After this patch, we can lookup the accurate byte offset range of a variable, 'INV' indicates that this variable is not valid at the given point, but available in the scope: $ perf probe --vars 'generic_perform_write:42' --range Available variables at generic_perform_write:42 @<generic_perform_write+141> [INV] ssize_t written @<generic_perform_write+[324-331]> [INV] struct address_space_operations* a_ops @<generic_perform_write+[55-61,170-176,223-246]> [VAL] (unknown_type) fsdata @<generic_perform_write+[70-307,346-411]> [VAL] loff_t pos @<generic_perform_write+[0-286,286-336,346-411]> [VAL] long int status @<generic_perform_write+[83-342,346-411]> [VAL] long unsigned int bytes @<generic_perform_write+[122-311,320-338,346-403,403-411]> [VAL] struct address_space* mapping @<generic_perform_write+[35-344,346-411]> [VAL] struct iov_iter* i @<generic_perform_write+[0-340,346-411]> [VAL] struct page* page @<generic_perform_write+[70-307,346-411]> Then it is more clear for us to add a probe with this variable: $ perf probe --add 'generic_perform_write+170 a_ops' Added new event: probe:generic_perform_write (on generic_perform_write+170 with a_ops) Signed-off-by: He Kuang <hekuang@huawei.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1431336304-16863-2-git-send-email-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-11 17:25:03 +08:00
ret2 = die_get_var_range(&af->pf.sp_die,
die_mem, &buf);
}
pr_debug("Add new var: %s\n", buf.buf);
if (ret2 == 0) {
strlist__add(vl->vars,
strbuf_detach(&buf, NULL));
}
strbuf_release(&buf);
}
}
if (af->child && dwarf_haspc(die_mem, af->pf.addr))
return DIE_FIND_CB_CONTINUE;
else
return DIE_FIND_CB_SIBLING;
error:
strbuf_release(&buf);
pr_debug("Error in strbuf\n");
return DIE_FIND_CB_END;
}
static bool available_var_finder_overlap(struct available_var_finder *af)
{
int i;
for (i = 0; i < af->nvls; i++) {
if (af->pf.addr == af->vls[i].point.address)
return true;
}
return false;
}
/* Add a found vars into available variables list */
static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf)
{
struct available_var_finder *af =
container_of(pf, struct available_var_finder, pf);
struct perf_probe_point *pp = &pf->pev->point;
struct variable_list *vl;
perf probe: Avoid searching variables in intermediate scopes Fix variable searching logic to search one in inner than local scope or global(CU) scope. In the other words, skip searching in intermediate scopes. e.g., in the following code, int var1; void inline infunc(int i) { i++; <--- [A] } void func(void) { int var1, var2; infunc(var2); } At [A], "var1" should point the global variable "var1", however, if user mis-typed as "var2", variable search should be failed. However, current logic searches variable infunc() scope, global scope, and then func() scope. Thus, it can find "var2" variable in func() scope. This may not be what user expects. So, it would better not search outer scopes except outermost (compile unit) scope which contains only global variables, when it failed to find given variable in local scope. E.g. Without this: $ perf probe -V pre_schedule --externs > without.vars With this: $ perf probe -V pre_schedule --externs > with.vars Check the diff: $ diff without.vars with.vars 88d87 < int cpu 133d131 < long unsigned int* switch_count These vars are actually in the scope of schedule(), the caller of pre_schedule(). Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20110811110305.19900.94374.stgit@fedora15 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-08-11 19:03:05 +08:00
Dwarf_Die die_mem;
int ret;
/*
* For some reason (e.g. different column assigned to same address),
* this callback can be called with the address which already passed.
* Ignore it first.
*/
if (available_var_finder_overlap(af))
return 0;
/* Check number of tevs */
if (af->nvls == af->max_vls) {
pr_warning("Too many( > %d) probe point found.\n", af->max_vls);
return -ERANGE;
}
vl = &af->vls[af->nvls++];
/* Trace point should be converted from subprogram DIE */
perf probe: Fix probing symbols with optimization suffix Fix perf probe to probe on some symbols which have some optimzation suffixes, e.g. ".part", ".isra", and ".constprop". To fix this issue, instead of using the DIE name, perf probe uses the symbol name found by dwfl_module_addrsym(). This also involves a perf probe --vars operation update which now shows the symbol name instead of the DIE name. Without this patch, putting a probe on an inlined function which was compiled with a suffixed symbol will fail like this: $ perf probe -v getname_flags probe-definition(0): getname_flags symbol:getname_flags file:(null) line:0 offset:0 return:0 lazy:(null) 0 arguments Looking at the vmlinux_path (6 entries long) Using /lib/modules/3.11.0+/build/vmlinux for symbols found inline addr: 0xffffffff8119bb70 Probe point found: getname_flags+0 found inline addr: 0xffffffff8119bcb6 Probe point found: getname+6 found inline addr: 0xffffffff811a06a6 Probe point found: user_path_at_empty+6 find 3 probe_trace_events. Opening /sys/kernel/debug//tracing/kprobe_events write=1 Added new events: Writing event: p:probe/getname_flags getname_flags+0 Failed to write event: No such file or directory Error: Failed to add events. (-1) Because the debuginfo knows only the original (non suffix) symbol name, it uses the original symbol for probe address but the kernel (kallsyms) knows only suffixed symbol. Then, the kernel rejects that original symbol. This patch uses dwfl_module_addrsym() to get the correct (suffixed) symbol from symtab when a probe point is found. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130925131616.31632.46658.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-25 21:16:16 +08:00
ret = convert_to_trace_point(&pf->sp_die, af->mod, pf->addr,
pp->retprobe, pp->function, &vl->point);
if (ret < 0)
return ret;
pr_debug("Probe point found: %s+%lu\n", vl->point.symbol,
vl->point.offset);
/* Find local variables */
vl->vars = strlist__new(NULL, NULL);
if (vl->vars == NULL)
return -ENOMEM;
af->child = true;
die_find_child(sc_die, collect_variables_cb, (void *)af, &die_mem);
/* Find external variables */
if (!probe_conf.show_ext_vars)
goto out;
/* Don't need to search child DIE for external vars. */
af->child = false;
perf probe: Avoid searching variables in intermediate scopes Fix variable searching logic to search one in inner than local scope or global(CU) scope. In the other words, skip searching in intermediate scopes. e.g., in the following code, int var1; void inline infunc(int i) { i++; <--- [A] } void func(void) { int var1, var2; infunc(var2); } At [A], "var1" should point the global variable "var1", however, if user mis-typed as "var2", variable search should be failed. However, current logic searches variable infunc() scope, global scope, and then func() scope. Thus, it can find "var2" variable in func() scope. This may not be what user expects. So, it would better not search outer scopes except outermost (compile unit) scope which contains only global variables, when it failed to find given variable in local scope. E.g. Without this: $ perf probe -V pre_schedule --externs > without.vars With this: $ perf probe -V pre_schedule --externs > with.vars Check the diff: $ diff without.vars with.vars 88d87 < int cpu 133d131 < long unsigned int* switch_count These vars are actually in the scope of schedule(), the caller of pre_schedule(). Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: yrl.pp-manager.tt@hitachi.com Link: http://lkml.kernel.org/r/20110811110305.19900.94374.stgit@fedora15 Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-08-11 19:03:05 +08:00
die_find_child(&pf->cu_die, collect_variables_cb, (void *)af, &die_mem);
out:
if (strlist__empty(vl->vars)) {
strlist__delete(vl->vars);
vl->vars = NULL;
}
return ret;
}
/*
* Find available variables at given probe point
* Return the number of found probe points. Return 0 if there is no
* matched probe point. Return <0 if an error occurs.
*/
int debuginfo__find_available_vars_at(struct debuginfo *dbg,
struct perf_probe_event *pev,
struct variable_list **vls)
{
struct available_var_finder af = {
.pf = {.pev = pev, .callback = add_available_vars},
.mod = dbg->mod,
.max_vls = probe_conf.max_probes};
int ret;
/* Allocate result vls array */
*vls = zalloc(sizeof(struct variable_list) * af.max_vls);
if (*vls == NULL)
return -ENOMEM;
af.vls = *vls;
af.nvls = 0;
ret = debuginfo__find_probes(dbg, &af.pf);
if (ret < 0) {
/* Free vlist for error */
while (af.nvls--) {
zfree(&af.vls[af.nvls].point.symbol);
strlist__delete(af.vls[af.nvls].vars);
}
zfree(vls);
return ret;
}
return (ret < 0) ? ret : af.nvls;
perf: Add perf probe subcommand, a kprobe-event setup helper Add perf probe subcommand that implements a kprobe-event setup helper to the perf command. This allows user to define kprobe events using C expressions (C line numbers, C function names, and C local variables). Usage ----- perf probe [<options>] -P 'PROBEDEF' [-P 'PROBEDEF' ...] -k, --vmlinux <file> vmlinux/module pathname -P, --probe <p|r:[GRP/]NAME FUNC[+OFFS][@SRC]|@SRC:LINE [ARG ...]> probe point definition, where p: kprobe probe r: kretprobe probe GRP: Group name (optional) NAME: Event name FUNC: Function name OFFS: Offset from function entry (in byte) SRC: Source code path LINE: Line number ARG: Probe argument (local variable name or kprobe-tracer argument format is supported.) Changes in v4: - Add _GNU_SOURCE macro for strndup(). Changes in v3: - Remove -r option because perf always be used for online kernel. - Check malloc/calloc results. Changes in v2: - Check synthesized string length. - Rename perf kprobe to perf probe. - Use spaces for separator and update usage comment. - Check error paths in parse_probepoint(). - Check optimized-out variables. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Christoph Hellwig <hch@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Jim Keniston <jkenisto@us.ibm.com> Cc: Frank Ch. Eigler <fche@redhat.com> LKML-Reference: <20091008211737.29299.14784.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-10-09 05:17:38 +08:00
}
perf probe: Show correct source lines of probes on kmodules Perf probe always failed to find appropriate line numbers because of failing to find .text start address offset from debuginfo. e.g. ---- # ./perf probe -m pcspkr pcspkr_event:5 Added new events: probe:pcspkr_event (on pcspkr_event:5 in pcspkr) probe:pcspkr_event_1 (on pcspkr_event:5 in pcspkr) You can now use it in all perf tools, such as: perf record -e probe:pcspkr_event_1 -aR sleep 1 # ./perf probe -l Failed to find debug information for address ffffffffa031f006 Failed to find debug information for address ffffffffa031f016 probe:pcspkr_event (on pcspkr_event+6 in pcspkr) probe:pcspkr_event_1 (on pcspkr_event+22 in pcspkr) ---- This fixes the above issue as below. 1. Get the relative address of the symbol in .text by using map->start. 2. Adjust the address by adding the offset of .text section in the kernel module binary. With this fix, perf probe -l shows lines correctly. ---- # ./perf probe -l probe:pcspkr_event (on pcspkr_event:5@drivers/input/misc/pcspkr.c in pcspkr) probe:pcspkr_event_1 (on pcspkr_event:5@drivers/input/misc/pcspkr.c in pcspkr) ---- Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/20150930164132.3733.24643.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-01 00:41:33 +08:00
/* For the kernel module, we need a special code to get a DIE */
int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
bool adjust_offset)
perf probe: Show correct source lines of probes on kmodules Perf probe always failed to find appropriate line numbers because of failing to find .text start address offset from debuginfo. e.g. ---- # ./perf probe -m pcspkr pcspkr_event:5 Added new events: probe:pcspkr_event (on pcspkr_event:5 in pcspkr) probe:pcspkr_event_1 (on pcspkr_event:5 in pcspkr) You can now use it in all perf tools, such as: perf record -e probe:pcspkr_event_1 -aR sleep 1 # ./perf probe -l Failed to find debug information for address ffffffffa031f006 Failed to find debug information for address ffffffffa031f016 probe:pcspkr_event (on pcspkr_event+6 in pcspkr) probe:pcspkr_event_1 (on pcspkr_event+22 in pcspkr) ---- This fixes the above issue as below. 1. Get the relative address of the symbol in .text by using map->start. 2. Adjust the address by adding the offset of .text section in the kernel module binary. With this fix, perf probe -l shows lines correctly. ---- # ./perf probe -l probe:pcspkr_event (on pcspkr_event:5@drivers/input/misc/pcspkr.c in pcspkr) probe:pcspkr_event_1 (on pcspkr_event:5@drivers/input/misc/pcspkr.c in pcspkr) ---- Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/20150930164132.3733.24643.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-01 00:41:33 +08:00
{
int n, i;
Elf32_Word shndx;
Elf_Scn *scn;
Elf *elf;
GElf_Shdr mem, *shdr;
const char *p;
elf = dwfl_module_getelf(dbg->mod, &dbg->bias);
if (!elf)
return -EINVAL;
/* Get the number of relocations */
n = dwfl_module_relocations(dbg->mod);
if (n < 0)
return -ENOENT;
/* Search the relocation related .text section */
for (i = 0; i < n; i++) {
p = dwfl_module_relocation_info(dbg->mod, i, &shndx);
if (strcmp(p, ".text") == 0) {
/* OK, get the section header */
scn = elf_getscn(elf, shndx);
if (!scn)
return -ENOENT;
shdr = gelf_getshdr(scn, &mem);
if (!shdr)
return -ENOENT;
*offs = shdr->sh_addr;
if (adjust_offset)
*offs -= shdr->sh_offset;
perf probe: Show correct source lines of probes on kmodules Perf probe always failed to find appropriate line numbers because of failing to find .text start address offset from debuginfo. e.g. ---- # ./perf probe -m pcspkr pcspkr_event:5 Added new events: probe:pcspkr_event (on pcspkr_event:5 in pcspkr) probe:pcspkr_event_1 (on pcspkr_event:5 in pcspkr) You can now use it in all perf tools, such as: perf record -e probe:pcspkr_event_1 -aR sleep 1 # ./perf probe -l Failed to find debug information for address ffffffffa031f006 Failed to find debug information for address ffffffffa031f016 probe:pcspkr_event (on pcspkr_event+6 in pcspkr) probe:pcspkr_event_1 (on pcspkr_event+22 in pcspkr) ---- This fixes the above issue as below. 1. Get the relative address of the symbol in .text by using map->start. 2. Adjust the address by adding the offset of .text section in the kernel module binary. With this fix, perf probe -l shows lines correctly. ---- # ./perf probe -l probe:pcspkr_event (on pcspkr_event:5@drivers/input/misc/pcspkr.c in pcspkr) probe:pcspkr_event_1 (on pcspkr_event:5@drivers/input/misc/pcspkr.c in pcspkr) ---- Reported-by: Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/20150930164132.3733.24643.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-01 00:41:33 +08:00
}
}
return 0;
}
/* Reverse search */
int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
struct perf_probe_point *ppt)
{
Dwarf_Die cudie, spdie, indie;
perf probe: Fix to find line information for probe list Fix to find the correct (as much as possible) line information for listing probes. Without this fix, perf probe --list action will show incorrect line information as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:-89@x86/include/asm/current.h) probe:getname_flags_2 (on user_path_at_empty:-2054@x86/include/asm/current.h) The minus line number is obviously wrong, and current.h is not related to the probe point. Deeper investigation discovered that there were 2 issues related to this bug, and minor typos too. The 1st issue is the rack of considering about nested inlined functions, which causes the wrong (relative) line number. The 2nd issue is that the dwarf line info is not correct at those points. It points 14th line of current.h. Since it seems that the line info includes somewhat unreliable information, this fixes perf to try to find correct line information from both of debuginfo and line info as below. 1) Probe address is the entry of a function instance In this case, the line is set as the function declared line. 2) Probe address is the entry of an expanded inline function block In this case, the line is set as the function call-site line. This means that the line number is relative from the entry line of caller function (which can be an inlined function if nested) 3) Probe address is inside a function instance or an expanded inline function block In this case, perf probe queries the line number from lineinfo and verify the function declared file is same as the file name queried from lineinfo. If the file name is different, it is a failure case. The probe address is shown as symbol+offset. 4) Probe address is not in the any function instance This is a failure case, the probe address is shown as symbol+offset. With this fix, perf probe -l shows correct probe lines as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:2@ksrc/linux-3/fs/namei.c) probe:getname_flags_2 (on user_path_at_empty:4@ksrc/linux-3/fs/namei.c) Changes at v2: - Fix typos in the function comments. (Thanks to Namhyung Kim) - Use die_find_top_inlinefunc instead of die_find_inlinefunc_next. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130930092144.1693.11058.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-30 17:21:44 +08:00
Dwarf_Addr _addr = 0, baseaddr = 0;
const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
int baseline = 0, lineno = 0, ret = 0;
perf probe: Fix to show correct locations for events on modules Fix to show correct locations for events on modules by relocating given address instead of retrying after failure. This happens when the module text size is big enough, bigger than sh_addr, because the original code retries with given address + sh_addr if it failed to find CU DIE at the given address. Any address smaller than sh_addr always fails and it retries with the correct address, but addresses bigger than sh_addr will get a CU DIE which is on the given address (not adjusted by sh_addr). In my environment(x86-64), the sh_addr of ".text" section is 0x10030. Since i915 is a huge kernel module, we can see this issue as below. $ grep "[Tt] .*\[i915\]" /proc/kallsyms | sort | head -n1 ffffffffc0270000 t i915_switcheroo_can_switch [i915] ffffffffc0270000 + 0x10030 = ffffffffc0280030, so we'll check symbols cross this boundary. $ grep "[Tt] .*\[i915\]" /proc/kallsyms | grep -B1 ^ffffffffc028\ | head -n 2 ffffffffc027ff80 t haswell_init_clock_gating [i915] ffffffffc0280110 t valleyview_init_clock_gating [i915] So setup probes on both function and see what happen. $ sudo ./perf probe -m i915 -a haswell_init_clock_gating \ -a valleyview_init_clock_gating Added new events: probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915) You can now use it in all perf tools, such as: perf record -e probe:valleyview_init_clock_gating -aR sleep 1 $ sudo ./perf probe -l probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) probe:valleyview_init_clock_gating (on i915_vga_set_decode:4@gpu/drm/i915/i915_drv.c in i915) As you can see, haswell_init_clock_gating is correctly shown, but valleyview_init_clock_gating is not. With this patch, both events are shown correctly. $ sudo ./perf probe -l probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) Committer notes: In my case: # perf probe -m i915 -a haswell_init_clock_gating -a valleyview_init_clock_gating Added new events: probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915) You can now use it in all perf tools, such as: perf record -e probe:valleyview_init_clock_gating -aR sleep 1 # perf probe -l probe:haswell_init_clock_gating (on i915_getparam+432@gpu/drm/i915/i915_drv.c in i915) probe:valleyview_init_clock_gating (on __i915_printk+240@gpu/drm/i915/i915_drv.c in i915) # # readelf -SW /lib/modules/4.9.0+/build/vmlinux | egrep -w '.text|Name' [Nr] Name Type Address Off Size ES Flg Lk Inf Al [ 1] .text PROGBITS ffffffff81000000 200000 822fd3 00 AX 0 0 4096 # So both are b0rked, now with the fix: # perf probe -m i915 -a haswell_init_clock_gating -a valleyview_init_clock_gating Added new events: probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915) You can now use it in all perf tools, such as: perf record -e probe:valleyview_init_clock_gating -aR sleep 1 # perf probe -l probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) # Both looks correct. Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/148411436777.9978.1440275861947194930.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-11 13:59:38 +08:00
/* We always need to relocate the address for aranges */
if (debuginfo__get_text_offset(dbg, &baseaddr, false) == 0)
perf probe: Fix to show correct locations for events on modules Fix to show correct locations for events on modules by relocating given address instead of retrying after failure. This happens when the module text size is big enough, bigger than sh_addr, because the original code retries with given address + sh_addr if it failed to find CU DIE at the given address. Any address smaller than sh_addr always fails and it retries with the correct address, but addresses bigger than sh_addr will get a CU DIE which is on the given address (not adjusted by sh_addr). In my environment(x86-64), the sh_addr of ".text" section is 0x10030. Since i915 is a huge kernel module, we can see this issue as below. $ grep "[Tt] .*\[i915\]" /proc/kallsyms | sort | head -n1 ffffffffc0270000 t i915_switcheroo_can_switch [i915] ffffffffc0270000 + 0x10030 = ffffffffc0280030, so we'll check symbols cross this boundary. $ grep "[Tt] .*\[i915\]" /proc/kallsyms | grep -B1 ^ffffffffc028\ | head -n 2 ffffffffc027ff80 t haswell_init_clock_gating [i915] ffffffffc0280110 t valleyview_init_clock_gating [i915] So setup probes on both function and see what happen. $ sudo ./perf probe -m i915 -a haswell_init_clock_gating \ -a valleyview_init_clock_gating Added new events: probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915) You can now use it in all perf tools, such as: perf record -e probe:valleyview_init_clock_gating -aR sleep 1 $ sudo ./perf probe -l probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) probe:valleyview_init_clock_gating (on i915_vga_set_decode:4@gpu/drm/i915/i915_drv.c in i915) As you can see, haswell_init_clock_gating is correctly shown, but valleyview_init_clock_gating is not. With this patch, both events are shown correctly. $ sudo ./perf probe -l probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) Committer notes: In my case: # perf probe -m i915 -a haswell_init_clock_gating -a valleyview_init_clock_gating Added new events: probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915) You can now use it in all perf tools, such as: perf record -e probe:valleyview_init_clock_gating -aR sleep 1 # perf probe -l probe:haswell_init_clock_gating (on i915_getparam+432@gpu/drm/i915/i915_drv.c in i915) probe:valleyview_init_clock_gating (on __i915_printk+240@gpu/drm/i915/i915_drv.c in i915) # # readelf -SW /lib/modules/4.9.0+/build/vmlinux | egrep -w '.text|Name' [Nr] Name Type Address Off Size ES Flg Lk Inf Al [ 1] .text PROGBITS ffffffff81000000 200000 822fd3 00 AX 0 0 4096 # So both are b0rked, now with the fix: # perf probe -m i915 -a haswell_init_clock_gating -a valleyview_init_clock_gating Added new events: probe:haswell_init_clock_gating (on haswell_init_clock_gating in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating in i915) You can now use it in all perf tools, such as: perf record -e probe:valleyview_init_clock_gating -aR sleep 1 # perf probe -l probe:haswell_init_clock_gating (on haswell_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) probe:valleyview_init_clock_gating (on valleyview_init_clock_gating@gpu/drm/i915/intel_pm.c in i915) # Both looks correct. Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/148411436777.9978.1440275861947194930.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-11 13:59:38 +08:00
addr += baseaddr;
/* Find cu die */
if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) {
pr_warning("Failed to find debug information for address %lx\n",
addr);
ret = -EINVAL;
goto end;
}
/* Find a corresponding line (filename and lineno) */
cu_find_lineinfo(&cudie, addr, &fname, &lineno);
/* Don't care whether it failed or not */
/* Find a corresponding function (name, baseline and baseaddr) */
if (die_find_realfunc(&cudie, (Dwarf_Addr)addr, &spdie)) {
/* Get function entry information */
perf probe: Fix to find line information for probe list Fix to find the correct (as much as possible) line information for listing probes. Without this fix, perf probe --list action will show incorrect line information as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:-89@x86/include/asm/current.h) probe:getname_flags_2 (on user_path_at_empty:-2054@x86/include/asm/current.h) The minus line number is obviously wrong, and current.h is not related to the probe point. Deeper investigation discovered that there were 2 issues related to this bug, and minor typos too. The 1st issue is the rack of considering about nested inlined functions, which causes the wrong (relative) line number. The 2nd issue is that the dwarf line info is not correct at those points. It points 14th line of current.h. Since it seems that the line info includes somewhat unreliable information, this fixes perf to try to find correct line information from both of debuginfo and line info as below. 1) Probe address is the entry of a function instance In this case, the line is set as the function declared line. 2) Probe address is the entry of an expanded inline function block In this case, the line is set as the function call-site line. This means that the line number is relative from the entry line of caller function (which can be an inlined function if nested) 3) Probe address is inside a function instance or an expanded inline function block In this case, perf probe queries the line number from lineinfo and verify the function declared file is same as the file name queried from lineinfo. If the file name is different, it is a failure case. The probe address is shown as symbol+offset. 4) Probe address is not in the any function instance This is a failure case, the probe address is shown as symbol+offset. With this fix, perf probe -l shows correct probe lines as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:2@ksrc/linux-3/fs/namei.c) probe:getname_flags_2 (on user_path_at_empty:4@ksrc/linux-3/fs/namei.c) Changes at v2: - Fix typos in the function comments. (Thanks to Namhyung Kim) - Use die_find_top_inlinefunc instead of die_find_inlinefunc_next. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130930092144.1693.11058.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-30 17:21:44 +08:00
func = basefunc = dwarf_diename(&spdie);
if (!func ||
perf probe: Fix to list probe event with correct line number Since debuginfo__find_probe_point() uses dwarf_entrypc() for finding the entry address of the function on which a probe is, it will fail when the function DIE has only ranges attribute. To fix this issue, use die_entrypc() instead of dwarf_entrypc(). Without this fix, perf probe -l shows incorrect offset: # perf probe -l probe:clear_tasks_mm_cpumask (on clear_tasks_mm_cpumask+18446744071579263632@work/linux/linux/kernel/cpu.c) probe:clear_tasks_mm_cpumask_1 (on clear_tasks_mm_cpumask+18446744071579263752@work/linux/linux/kernel/cpu.c) With this: # perf probe -l probe:clear_tasks_mm_cpumask (on clear_tasks_mm_cpumask@work/linux/linux/kernel/cpu.c) probe:clear_tasks_mm_cpumask_1 (on clear_tasks_mm_cpumask:21@work/linux/linux/kernel/cpu.c) Committer testing: Before: [root@quaco ~]# perf probe -l probe:clear_tasks_mm_cpumask (on clear_tasks_mm_cpumask+18446744071579765152@kernel/cpu.c) [root@quaco ~]# After: [root@quaco ~]# perf probe -l probe:clear_tasks_mm_cpumask (on clear_tasks_mm_cpumask@kernel/cpu.c) [root@quaco ~]# Fixes: 1d46ea2a6a40 ("perf probe: Fix listing incorrect line number with inline function") Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lore.kernel.org/lkml/157199321227.8075.14655572419136993015.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-10-25 16:46:52 +08:00
die_entrypc(&spdie, &baseaddr) != 0 ||
perf probe: Fix to find line information for probe list Fix to find the correct (as much as possible) line information for listing probes. Without this fix, perf probe --list action will show incorrect line information as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:-89@x86/include/asm/current.h) probe:getname_flags_2 (on user_path_at_empty:-2054@x86/include/asm/current.h) The minus line number is obviously wrong, and current.h is not related to the probe point. Deeper investigation discovered that there were 2 issues related to this bug, and minor typos too. The 1st issue is the rack of considering about nested inlined functions, which causes the wrong (relative) line number. The 2nd issue is that the dwarf line info is not correct at those points. It points 14th line of current.h. Since it seems that the line info includes somewhat unreliable information, this fixes perf to try to find correct line information from both of debuginfo and line info as below. 1) Probe address is the entry of a function instance In this case, the line is set as the function declared line. 2) Probe address is the entry of an expanded inline function block In this case, the line is set as the function call-site line. This means that the line number is relative from the entry line of caller function (which can be an inlined function if nested) 3) Probe address is inside a function instance or an expanded inline function block In this case, perf probe queries the line number from lineinfo and verify the function declared file is same as the file name queried from lineinfo. If the file name is different, it is a failure case. The probe address is shown as symbol+offset. 4) Probe address is not in the any function instance This is a failure case, the probe address is shown as symbol+offset. With this fix, perf probe -l shows correct probe lines as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:2@ksrc/linux-3/fs/namei.c) probe:getname_flags_2 (on user_path_at_empty:4@ksrc/linux-3/fs/namei.c) Changes at v2: - Fix typos in the function comments. (Thanks to Namhyung Kim) - Use die_find_top_inlinefunc instead of die_find_inlinefunc_next. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130930092144.1693.11058.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-30 17:21:44 +08:00
dwarf_decl_line(&spdie, &baseline) != 0) {
lineno = 0;
goto post;
perf probe: Fix to find line information for probe list Fix to find the correct (as much as possible) line information for listing probes. Without this fix, perf probe --list action will show incorrect line information as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:-89@x86/include/asm/current.h) probe:getname_flags_2 (on user_path_at_empty:-2054@x86/include/asm/current.h) The minus line number is obviously wrong, and current.h is not related to the probe point. Deeper investigation discovered that there were 2 issues related to this bug, and minor typos too. The 1st issue is the rack of considering about nested inlined functions, which causes the wrong (relative) line number. The 2nd issue is that the dwarf line info is not correct at those points. It points 14th line of current.h. Since it seems that the line info includes somewhat unreliable information, this fixes perf to try to find correct line information from both of debuginfo and line info as below. 1) Probe address is the entry of a function instance In this case, the line is set as the function declared line. 2) Probe address is the entry of an expanded inline function block In this case, the line is set as the function call-site line. This means that the line number is relative from the entry line of caller function (which can be an inlined function if nested) 3) Probe address is inside a function instance or an expanded inline function block In this case, perf probe queries the line number from lineinfo and verify the function declared file is same as the file name queried from lineinfo. If the file name is different, it is a failure case. The probe address is shown as symbol+offset. 4) Probe address is not in the any function instance This is a failure case, the probe address is shown as symbol+offset. With this fix, perf probe -l shows correct probe lines as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:2@ksrc/linux-3/fs/namei.c) probe:getname_flags_2 (on user_path_at_empty:4@ksrc/linux-3/fs/namei.c) Changes at v2: - Fix typos in the function comments. (Thanks to Namhyung Kim) - Use die_find_top_inlinefunc instead of die_find_inlinefunc_next. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130930092144.1693.11058.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-30 17:21:44 +08:00
}
fname = dwarf_decl_file(&spdie);
perf probe: Fix to find line information for probe list Fix to find the correct (as much as possible) line information for listing probes. Without this fix, perf probe --list action will show incorrect line information as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:-89@x86/include/asm/current.h) probe:getname_flags_2 (on user_path_at_empty:-2054@x86/include/asm/current.h) The minus line number is obviously wrong, and current.h is not related to the probe point. Deeper investigation discovered that there were 2 issues related to this bug, and minor typos too. The 1st issue is the rack of considering about nested inlined functions, which causes the wrong (relative) line number. The 2nd issue is that the dwarf line info is not correct at those points. It points 14th line of current.h. Since it seems that the line info includes somewhat unreliable information, this fixes perf to try to find correct line information from both of debuginfo and line info as below. 1) Probe address is the entry of a function instance In this case, the line is set as the function declared line. 2) Probe address is the entry of an expanded inline function block In this case, the line is set as the function call-site line. This means that the line number is relative from the entry line of caller function (which can be an inlined function if nested) 3) Probe address is inside a function instance or an expanded inline function block In this case, perf probe queries the line number from lineinfo and verify the function declared file is same as the file name queried from lineinfo. If the file name is different, it is a failure case. The probe address is shown as symbol+offset. 4) Probe address is not in the any function instance This is a failure case, the probe address is shown as symbol+offset. With this fix, perf probe -l shows correct probe lines as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:2@ksrc/linux-3/fs/namei.c) probe:getname_flags_2 (on user_path_at_empty:4@ksrc/linux-3/fs/namei.c) Changes at v2: - Fix typos in the function comments. (Thanks to Namhyung Kim) - Use die_find_top_inlinefunc instead of die_find_inlinefunc_next. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130930092144.1693.11058.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-30 17:21:44 +08:00
if (addr == (unsigned long)baseaddr) {
/* Function entry - Relative line number is 0 */
lineno = baseline;
perf probe: Fix to find line information for probe list Fix to find the correct (as much as possible) line information for listing probes. Without this fix, perf probe --list action will show incorrect line information as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:-89@x86/include/asm/current.h) probe:getname_flags_2 (on user_path_at_empty:-2054@x86/include/asm/current.h) The minus line number is obviously wrong, and current.h is not related to the probe point. Deeper investigation discovered that there were 2 issues related to this bug, and minor typos too. The 1st issue is the rack of considering about nested inlined functions, which causes the wrong (relative) line number. The 2nd issue is that the dwarf line info is not correct at those points. It points 14th line of current.h. Since it seems that the line info includes somewhat unreliable information, this fixes perf to try to find correct line information from both of debuginfo and line info as below. 1) Probe address is the entry of a function instance In this case, the line is set as the function declared line. 2) Probe address is the entry of an expanded inline function block In this case, the line is set as the function call-site line. This means that the line number is relative from the entry line of caller function (which can be an inlined function if nested) 3) Probe address is inside a function instance or an expanded inline function block In this case, perf probe queries the line number from lineinfo and verify the function declared file is same as the file name queried from lineinfo. If the file name is different, it is a failure case. The probe address is shown as symbol+offset. 4) Probe address is not in the any function instance This is a failure case, the probe address is shown as symbol+offset. With this fix, perf probe -l shows correct probe lines as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:2@ksrc/linux-3/fs/namei.c) probe:getname_flags_2 (on user_path_at_empty:4@ksrc/linux-3/fs/namei.c) Changes at v2: - Fix typos in the function comments. (Thanks to Namhyung Kim) - Use die_find_top_inlinefunc instead of die_find_inlinefunc_next. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130930092144.1693.11058.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-30 17:21:44 +08:00
goto post;
}
/* Track down the inline functions step by step */
while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr,
&indie)) {
/* There is an inline function */
perf probe: Fix to list probe event with correct line number Since debuginfo__find_probe_point() uses dwarf_entrypc() for finding the entry address of the function on which a probe is, it will fail when the function DIE has only ranges attribute. To fix this issue, use die_entrypc() instead of dwarf_entrypc(). Without this fix, perf probe -l shows incorrect offset: # perf probe -l probe:clear_tasks_mm_cpumask (on clear_tasks_mm_cpumask+18446744071579263632@work/linux/linux/kernel/cpu.c) probe:clear_tasks_mm_cpumask_1 (on clear_tasks_mm_cpumask+18446744071579263752@work/linux/linux/kernel/cpu.c) With this: # perf probe -l probe:clear_tasks_mm_cpumask (on clear_tasks_mm_cpumask@work/linux/linux/kernel/cpu.c) probe:clear_tasks_mm_cpumask_1 (on clear_tasks_mm_cpumask:21@work/linux/linux/kernel/cpu.c) Committer testing: Before: [root@quaco ~]# perf probe -l probe:clear_tasks_mm_cpumask (on clear_tasks_mm_cpumask+18446744071579765152@kernel/cpu.c) [root@quaco ~]# After: [root@quaco ~]# perf probe -l probe:clear_tasks_mm_cpumask (on clear_tasks_mm_cpumask@kernel/cpu.c) [root@quaco ~]# Fixes: 1d46ea2a6a40 ("perf probe: Fix listing incorrect line number with inline function") Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lore.kernel.org/lkml/157199321227.8075.14655572419136993015.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-10-25 16:46:52 +08:00
if (die_entrypc(&indie, &_addr) == 0 &&
perf probe: Fix to find line information for probe list Fix to find the correct (as much as possible) line information for listing probes. Without this fix, perf probe --list action will show incorrect line information as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:-89@x86/include/asm/current.h) probe:getname_flags_2 (on user_path_at_empty:-2054@x86/include/asm/current.h) The minus line number is obviously wrong, and current.h is not related to the probe point. Deeper investigation discovered that there were 2 issues related to this bug, and minor typos too. The 1st issue is the rack of considering about nested inlined functions, which causes the wrong (relative) line number. The 2nd issue is that the dwarf line info is not correct at those points. It points 14th line of current.h. Since it seems that the line info includes somewhat unreliable information, this fixes perf to try to find correct line information from both of debuginfo and line info as below. 1) Probe address is the entry of a function instance In this case, the line is set as the function declared line. 2) Probe address is the entry of an expanded inline function block In this case, the line is set as the function call-site line. This means that the line number is relative from the entry line of caller function (which can be an inlined function if nested) 3) Probe address is inside a function instance or an expanded inline function block In this case, perf probe queries the line number from lineinfo and verify the function declared file is same as the file name queried from lineinfo. If the file name is different, it is a failure case. The probe address is shown as symbol+offset. 4) Probe address is not in the any function instance This is a failure case, the probe address is shown as symbol+offset. With this fix, perf probe -l shows correct probe lines as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:2@ksrc/linux-3/fs/namei.c) probe:getname_flags_2 (on user_path_at_empty:4@ksrc/linux-3/fs/namei.c) Changes at v2: - Fix typos in the function comments. (Thanks to Namhyung Kim) - Use die_find_top_inlinefunc instead of die_find_inlinefunc_next. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130930092144.1693.11058.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-30 17:21:44 +08:00
_addr == addr) {
/*
* addr is at an inline function entry.
* In this case, lineno should be the call-site
perf probe: Fix to find line information for probe list Fix to find the correct (as much as possible) line information for listing probes. Without this fix, perf probe --list action will show incorrect line information as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:-89@x86/include/asm/current.h) probe:getname_flags_2 (on user_path_at_empty:-2054@x86/include/asm/current.h) The minus line number is obviously wrong, and current.h is not related to the probe point. Deeper investigation discovered that there were 2 issues related to this bug, and minor typos too. The 1st issue is the rack of considering about nested inlined functions, which causes the wrong (relative) line number. The 2nd issue is that the dwarf line info is not correct at those points. It points 14th line of current.h. Since it seems that the line info includes somewhat unreliable information, this fixes perf to try to find correct line information from both of debuginfo and line info as below. 1) Probe address is the entry of a function instance In this case, the line is set as the function declared line. 2) Probe address is the entry of an expanded inline function block In this case, the line is set as the function call-site line. This means that the line number is relative from the entry line of caller function (which can be an inlined function if nested) 3) Probe address is inside a function instance or an expanded inline function block In this case, perf probe queries the line number from lineinfo and verify the function declared file is same as the file name queried from lineinfo. If the file name is different, it is a failure case. The probe address is shown as symbol+offset. 4) Probe address is not in the any function instance This is a failure case, the probe address is shown as symbol+offset. With this fix, perf probe -l shows correct probe lines as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:2@ksrc/linux-3/fs/namei.c) probe:getname_flags_2 (on user_path_at_empty:4@ksrc/linux-3/fs/namei.c) Changes at v2: - Fix typos in the function comments. (Thanks to Namhyung Kim) - Use die_find_top_inlinefunc instead of die_find_inlinefunc_next. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130930092144.1693.11058.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-30 17:21:44 +08:00
* line number. (overwrite lineinfo)
*/
lineno = die_get_call_lineno(&indie);
perf probe: Fix to find line information for probe list Fix to find the correct (as much as possible) line information for listing probes. Without this fix, perf probe --list action will show incorrect line information as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:-89@x86/include/asm/current.h) probe:getname_flags_2 (on user_path_at_empty:-2054@x86/include/asm/current.h) The minus line number is obviously wrong, and current.h is not related to the probe point. Deeper investigation discovered that there were 2 issues related to this bug, and minor typos too. The 1st issue is the rack of considering about nested inlined functions, which causes the wrong (relative) line number. The 2nd issue is that the dwarf line info is not correct at those points. It points 14th line of current.h. Since it seems that the line info includes somewhat unreliable information, this fixes perf to try to find correct line information from both of debuginfo and line info as below. 1) Probe address is the entry of a function instance In this case, the line is set as the function declared line. 2) Probe address is the entry of an expanded inline function block In this case, the line is set as the function call-site line. This means that the line number is relative from the entry line of caller function (which can be an inlined function if nested) 3) Probe address is inside a function instance or an expanded inline function block In this case, perf probe queries the line number from lineinfo and verify the function declared file is same as the file name queried from lineinfo. If the file name is different, it is a failure case. The probe address is shown as symbol+offset. 4) Probe address is not in the any function instance This is a failure case, the probe address is shown as symbol+offset. With this fix, perf probe -l shows correct probe lines as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:2@ksrc/linux-3/fs/namei.c) probe:getname_flags_2 (on user_path_at_empty:4@ksrc/linux-3/fs/namei.c) Changes at v2: - Fix typos in the function comments. (Thanks to Namhyung Kim) - Use die_find_top_inlinefunc instead of die_find_inlinefunc_next. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130930092144.1693.11058.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-30 17:21:44 +08:00
fname = die_get_call_file(&indie);
break;
} else {
/*
* addr is in an inline function body.
* Since lineno points one of the lines
* of the inline function, baseline should
* be the entry line of the inline function.
*/
tmp = dwarf_diename(&indie);
perf probe: Fix to find line information for probe list Fix to find the correct (as much as possible) line information for listing probes. Without this fix, perf probe --list action will show incorrect line information as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:-89@x86/include/asm/current.h) probe:getname_flags_2 (on user_path_at_empty:-2054@x86/include/asm/current.h) The minus line number is obviously wrong, and current.h is not related to the probe point. Deeper investigation discovered that there were 2 issues related to this bug, and minor typos too. The 1st issue is the rack of considering about nested inlined functions, which causes the wrong (relative) line number. The 2nd issue is that the dwarf line info is not correct at those points. It points 14th line of current.h. Since it seems that the line info includes somewhat unreliable information, this fixes perf to try to find correct line information from both of debuginfo and line info as below. 1) Probe address is the entry of a function instance In this case, the line is set as the function declared line. 2) Probe address is the entry of an expanded inline function block In this case, the line is set as the function call-site line. This means that the line number is relative from the entry line of caller function (which can be an inlined function if nested) 3) Probe address is inside a function instance or an expanded inline function block In this case, perf probe queries the line number from lineinfo and verify the function declared file is same as the file name queried from lineinfo. If the file name is different, it is a failure case. The probe address is shown as symbol+offset. 4) Probe address is not in the any function instance This is a failure case, the probe address is shown as symbol+offset. With this fix, perf probe -l shows correct probe lines as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:2@ksrc/linux-3/fs/namei.c) probe:getname_flags_2 (on user_path_at_empty:4@ksrc/linux-3/fs/namei.c) Changes at v2: - Fix typos in the function comments. (Thanks to Namhyung Kim) - Use die_find_top_inlinefunc instead of die_find_inlinefunc_next. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130930092144.1693.11058.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-30 17:21:44 +08:00
if (!tmp ||
dwarf_decl_line(&indie, &baseline) != 0)
break;
func = tmp;
spdie = indie;
}
}
perf probe: Fix to find line information for probe list Fix to find the correct (as much as possible) line information for listing probes. Without this fix, perf probe --list action will show incorrect line information as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:-89@x86/include/asm/current.h) probe:getname_flags_2 (on user_path_at_empty:-2054@x86/include/asm/current.h) The minus line number is obviously wrong, and current.h is not related to the probe point. Deeper investigation discovered that there were 2 issues related to this bug, and minor typos too. The 1st issue is the rack of considering about nested inlined functions, which causes the wrong (relative) line number. The 2nd issue is that the dwarf line info is not correct at those points. It points 14th line of current.h. Since it seems that the line info includes somewhat unreliable information, this fixes perf to try to find correct line information from both of debuginfo and line info as below. 1) Probe address is the entry of a function instance In this case, the line is set as the function declared line. 2) Probe address is the entry of an expanded inline function block In this case, the line is set as the function call-site line. This means that the line number is relative from the entry line of caller function (which can be an inlined function if nested) 3) Probe address is inside a function instance or an expanded inline function block In this case, perf probe queries the line number from lineinfo and verify the function declared file is same as the file name queried from lineinfo. If the file name is different, it is a failure case. The probe address is shown as symbol+offset. 4) Probe address is not in the any function instance This is a failure case, the probe address is shown as symbol+offset. With this fix, perf probe -l shows correct probe lines as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:2@ksrc/linux-3/fs/namei.c) probe:getname_flags_2 (on user_path_at_empty:4@ksrc/linux-3/fs/namei.c) Changes at v2: - Fix typos in the function comments. (Thanks to Namhyung Kim) - Use die_find_top_inlinefunc instead of die_find_inlinefunc_next. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130930092144.1693.11058.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-30 17:21:44 +08:00
/* Verify the lineno and baseline are in a same file */
tmp = dwarf_decl_file(&spdie);
if (!tmp || strcmp(tmp, fname) != 0)
lineno = 0;
}
post:
/* Make a relative line number or an offset */
if (lineno)
ppt->line = lineno - baseline;
perf probe: Fix to find line information for probe list Fix to find the correct (as much as possible) line information for listing probes. Without this fix, perf probe --list action will show incorrect line information as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:-89@x86/include/asm/current.h) probe:getname_flags_2 (on user_path_at_empty:-2054@x86/include/asm/current.h) The minus line number is obviously wrong, and current.h is not related to the probe point. Deeper investigation discovered that there were 2 issues related to this bug, and minor typos too. The 1st issue is the rack of considering about nested inlined functions, which causes the wrong (relative) line number. The 2nd issue is that the dwarf line info is not correct at those points. It points 14th line of current.h. Since it seems that the line info includes somewhat unreliable information, this fixes perf to try to find correct line information from both of debuginfo and line info as below. 1) Probe address is the entry of a function instance In this case, the line is set as the function declared line. 2) Probe address is the entry of an expanded inline function block In this case, the line is set as the function call-site line. This means that the line number is relative from the entry line of caller function (which can be an inlined function if nested) 3) Probe address is inside a function instance or an expanded inline function block In this case, perf probe queries the line number from lineinfo and verify the function declared file is same as the file name queried from lineinfo. If the file name is different, it is a failure case. The probe address is shown as symbol+offset. 4) Probe address is not in the any function instance This is a failure case, the probe address is shown as symbol+offset. With this fix, perf probe -l shows correct probe lines as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:2@ksrc/linux-3/fs/namei.c) probe:getname_flags_2 (on user_path_at_empty:4@ksrc/linux-3/fs/namei.c) Changes at v2: - Fix typos in the function comments. (Thanks to Namhyung Kim) - Use die_find_top_inlinefunc instead of die_find_inlinefunc_next. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130930092144.1693.11058.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-30 17:21:44 +08:00
else if (basefunc) {
ppt->offset = addr - (unsigned long)baseaddr;
perf probe: Fix to find line information for probe list Fix to find the correct (as much as possible) line information for listing probes. Without this fix, perf probe --list action will show incorrect line information as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:-89@x86/include/asm/current.h) probe:getname_flags_2 (on user_path_at_empty:-2054@x86/include/asm/current.h) The minus line number is obviously wrong, and current.h is not related to the probe point. Deeper investigation discovered that there were 2 issues related to this bug, and minor typos too. The 1st issue is the rack of considering about nested inlined functions, which causes the wrong (relative) line number. The 2nd issue is that the dwarf line info is not correct at those points. It points 14th line of current.h. Since it seems that the line info includes somewhat unreliable information, this fixes perf to try to find correct line information from both of debuginfo and line info as below. 1) Probe address is the entry of a function instance In this case, the line is set as the function declared line. 2) Probe address is the entry of an expanded inline function block In this case, the line is set as the function call-site line. This means that the line number is relative from the entry line of caller function (which can be an inlined function if nested) 3) Probe address is inside a function instance or an expanded inline function block In this case, perf probe queries the line number from lineinfo and verify the function declared file is same as the file name queried from lineinfo. If the file name is different, it is a failure case. The probe address is shown as symbol+offset. 4) Probe address is not in the any function instance This is a failure case, the probe address is shown as symbol+offset. With this fix, perf probe -l shows correct probe lines as below; probe:getname_flags (on getname_flags@ksrc/linux-3/fs/namei.c) probe:getname_flags_1 (on getname:2@ksrc/linux-3/fs/namei.c) probe:getname_flags_2 (on user_path_at_empty:4@ksrc/linux-3/fs/namei.c) Changes at v2: - Fix typos in the function comments. (Thanks to Namhyung Kim) - Use die_find_top_inlinefunc instead of die_find_inlinefunc_next. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130930092144.1693.11058.stgit@udc4-manage.rcp.hitachi.co.jp Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-30 17:21:44 +08:00
func = basefunc;
}
/* Duplicate strings */
if (func) {
ppt->function = strdup(func);
if (ppt->function == NULL) {
ret = -ENOMEM;
goto end;
}
}
if (fname) {
ppt->file = strdup(fname);
if (ppt->file == NULL) {
zfree(&ppt->function);
ret = -ENOMEM;
goto end;
}
}
end:
if (ret == 0 && (fname || func))
ret = 1; /* Found a point */
return ret;
}
/* Add a line and store the src path */
static int line_range_add_line(const char *src, unsigned int lineno,
struct line_range *lr)
{
/* Copy source path */
if (!lr->path) {
lr->path = strdup(src);
if (lr->path == NULL)
return -ENOMEM;
}
return intlist__add(lr->line_list, lineno);
}
static int line_range_walk_cb(const char *fname, int lineno,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 06:15:03 +08:00
Dwarf_Addr addr __maybe_unused,
void *data)
{
struct line_finder *lf = data;
perf probe: Do not show non representive lines by perf-probe -L Since perf probe -L shows non representive lines, it can be mislead users where user can put probes. This prevents to show such non representive lines so that user can understand which lines user can probe. # perf probe -L kernel_read <kernel_read@/build/linux-pvZVvI/linux-5.0.0/fs/read_write.c:0> 0 ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { 2 mm_segment_t old_fs; ssize_t result; old_fs = get_fs(); 6 set_fs(get_ds()); /* The cast to a user pointer is valid due to the set_fs() */ 8 result = vfs_read(file, (void __user *)buf, count, pos); 9 set_fs(old_fs); 10 return result; } EXPORT_SYMBOL(kernel_read); Committer testing: Before: # perf probe -L kernel_read <kernel_read@/usr/src/debug/kernel-5.3.fc30/linux-5.3.8-200.fc30.x86_64/fs/read_write.c:0> 0 ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) 1 { 2 mm_segment_t old_fs; 3 ssize_t result; 5 old_fs = get_fs(); 6 set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ 8 result = vfs_read(file, (void __user *)buf, count, pos); 9 set_fs(old_fs); 10 return result; } EXPORT_SYMBOL(kernel_read); # See the 1, 3, 5 lines? They shouldn't be there, after this patch: # perf probe -L kernel_read <kernel_read@/usr/src/debug/kernel-5.3.fc30/linux-5.3.8-200.fc30.x86_64/fs/read_write.c:0> 0 ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { 2 mm_segment_t old_fs; ssize_t result; old_fs = get_fs(); 6 set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ 8 result = vfs_read(file, (void __user *)buf, count, pos); 9 set_fs(old_fs); 10 return result; } EXPORT_SYMBOL(kernel_read); # Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Link: http://lore.kernel.org/lkml/157406473064.24476.2913278267727587314.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-18 16:12:10 +08:00
const char *__fname;
int __lineno;
int err;
if ((strtailcmp(fname, lf->fname) != 0) ||
(lf->lno_s > lineno || lf->lno_e < lineno))
return 0;
perf probe: Do not show non representive lines by perf-probe -L Since perf probe -L shows non representive lines, it can be mislead users where user can put probes. This prevents to show such non representive lines so that user can understand which lines user can probe. # perf probe -L kernel_read <kernel_read@/build/linux-pvZVvI/linux-5.0.0/fs/read_write.c:0> 0 ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { 2 mm_segment_t old_fs; ssize_t result; old_fs = get_fs(); 6 set_fs(get_ds()); /* The cast to a user pointer is valid due to the set_fs() */ 8 result = vfs_read(file, (void __user *)buf, count, pos); 9 set_fs(old_fs); 10 return result; } EXPORT_SYMBOL(kernel_read); Committer testing: Before: # perf probe -L kernel_read <kernel_read@/usr/src/debug/kernel-5.3.fc30/linux-5.3.8-200.fc30.x86_64/fs/read_write.c:0> 0 ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) 1 { 2 mm_segment_t old_fs; 3 ssize_t result; 5 old_fs = get_fs(); 6 set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ 8 result = vfs_read(file, (void __user *)buf, count, pos); 9 set_fs(old_fs); 10 return result; } EXPORT_SYMBOL(kernel_read); # See the 1, 3, 5 lines? They shouldn't be there, after this patch: # perf probe -L kernel_read <kernel_read@/usr/src/debug/kernel-5.3.fc30/linux-5.3.8-200.fc30.x86_64/fs/read_write.c:0> 0 ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { 2 mm_segment_t old_fs; ssize_t result; old_fs = get_fs(); 6 set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ 8 result = vfs_read(file, (void __user *)buf, count, pos); 9 set_fs(old_fs); 10 return result; } EXPORT_SYMBOL(kernel_read); # Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Link: http://lore.kernel.org/lkml/157406473064.24476.2913278267727587314.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-18 16:12:10 +08:00
/* Make sure this line can be reversable */
if (cu_find_lineinfo(&lf->cu_die, addr, &__fname, &__lineno) > 0
&& (lineno != __lineno || strcmp(fname, __fname)))
return 0;
err = line_range_add_line(fname, lineno, lf->lr);
if (err < 0 && err != -EEXIST)
return err;
return 0;
}
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
/* Find line range from its line number */
static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
{
int ret;
ret = die_walk_lines(sp_die ?: &lf->cu_die, line_range_walk_cb, lf);
/* Update status */
if (ret >= 0)
if (!intlist__empty(lf->lr->line_list))
ret = lf->found = 1;
else
ret = 0; /* Lines are not found */
else {
zfree(&lf->lr->path);
}
return ret;
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
}
static int line_range_inline_cb(Dwarf_Die *in_die, void *data)
{
int ret = find_line_range_by_line(in_die, data);
/*
* We have to check all instances of inlined function, because
* some execution paths can be optimized out depends on the
* function argument of instances. However, if an error occurs,
* it should be handled by the caller.
*/
return ret < 0 ? ret : 0;
}
/* Search function definition from function name */
static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
{
struct dwarf_callback_param *param = data;
struct line_finder *lf = param->data;
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
struct line_range *lr = lf->lr;
/* Check declared file */
if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die)))
return DWARF_CB_OK;
if (die_is_func_def(sp_die) &&
die_match_name(sp_die, lr->function)) {
lf->fname = dwarf_decl_file(sp_die);
dwarf_decl_line(sp_die, &lr->offset);
pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
lf->lno_s = lr->offset + lr->start;
if (lf->lno_s < 0) /* Overflow */
lf->lno_s = INT_MAX;
lf->lno_e = lr->offset + lr->end;
if (lf->lno_e < 0) /* Overflow */
lf->lno_e = INT_MAX;
pr_debug("New line range: %d to %d\n", lf->lno_s, lf->lno_e);
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
lr->start = lf->lno_s;
lr->end = lf->lno_e;
if (!die_is_func_instance(sp_die))
param->retval = die_walk_instances(sp_die,
line_range_inline_cb, lf);
else
param->retval = find_line_range_by_line(sp_die, lf);
return DWARF_CB_ABORT;
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
}
return DWARF_CB_OK;
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
}
static int find_line_range_by_func(struct line_finder *lf)
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
{
struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0};
dwarf_getfuncs(&lf->cu_die, line_range_search_cb, &param, 0);
return param.retval;
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
}
int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr)
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
{
struct line_finder lf = {.lr = lr, .found = 0};
int ret = 0;
Dwarf_Off off = 0, noff;
size_t cuhl;
Dwarf_Die *diep;
const char *comp_dir;
perf probe: Add fastpath to do lookup by function name v3 -> v2: - Make pubname_search_cb more generic - Add fastpath to find_probes also v2 -> v1: - Don't compare file names with cu_find_realpath(...), instead, compare them with the name returned by dwarf_decl_file(sp_die) The vmlinux file may have thousands of CUs. We can lookup function name from .debug_pubnames section to avoid the slow loop on CUs. 1. Improvement data for find_line_range ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --line csum_partial_copy_to_user > tmp.log before patch applied ===================== 847,988,276 cycles 0.355075856 seconds time elapsed after patch applied ===================== 206,102,622 cycles 0.086883555 seconds time elapsed 2. Improvement data for find_probes ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --vars csum_partial_copy_to_user > tmp.log before patch applied ===================== 848,490,844 cycles 0.355307901 seconds time elapsed after patch applied ===================== 205,684,469 cycles 0.086694010 seconds time elapsed Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-kernel <linux-kernel@vger.kernel.org> LKML-Reference: <1301041668.14111.52.camel@minggr.sh.intel.com> Signed-off-by: Lin Ming <ming.m.lin@intel.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-03-25 16:27:48 +08:00
/* Fastpath: lookup by function name from .debug_pubnames section */
if (lr->function) {
struct pubname_callback_param pubname_param = {
.function = lr->function, .file = lr->file,
.cu_die = &lf.cu_die, .sp_die = &lf.sp_die, .found = 0};
struct dwarf_callback_param line_range_param = {
.data = (void *)&lf, .retval = 0};
dwarf_getpubnames(dbg->dbg, pubname_search_cb,
&pubname_param, 0);
perf probe: Add fastpath to do lookup by function name v3 -> v2: - Make pubname_search_cb more generic - Add fastpath to find_probes also v2 -> v1: - Don't compare file names with cu_find_realpath(...), instead, compare them with the name returned by dwarf_decl_file(sp_die) The vmlinux file may have thousands of CUs. We can lookup function name from .debug_pubnames section to avoid the slow loop on CUs. 1. Improvement data for find_line_range ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --line csum_partial_copy_to_user > tmp.log before patch applied ===================== 847,988,276 cycles 0.355075856 seconds time elapsed after patch applied ===================== 206,102,622 cycles 0.086883555 seconds time elapsed 2. Improvement data for find_probes ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --vars csum_partial_copy_to_user > tmp.log before patch applied ===================== 848,490,844 cycles 0.355307901 seconds time elapsed after patch applied ===================== 205,684,469 cycles 0.086694010 seconds time elapsed Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-kernel <linux-kernel@vger.kernel.org> LKML-Reference: <1301041668.14111.52.camel@minggr.sh.intel.com> Signed-off-by: Lin Ming <ming.m.lin@intel.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-03-25 16:27:48 +08:00
if (pubname_param.found) {
line_range_search_cb(&lf.sp_die, &line_range_param);
if (lf.found)
goto found;
}
}
/* Loop on CUs (Compilation Unit) */
while (!lf.found && ret >= 0) {
if (dwarf_nextcu(dbg->dbg, off, &noff, &cuhl,
NULL, NULL, NULL) != 0)
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
break;
/* Get the DIE(Debugging Information Entry) of this CU */
diep = dwarf_offdie(dbg->dbg, off + cuhl, &lf.cu_die);
if (!diep)
continue;
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
/* Check if target file is included. */
if (lr->file)
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
lf.fname = cu_find_realpath(&lf.cu_die, lr->file);
else
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
lf.fname = 0;
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
perf probe: Add lazy line matching support Add lazy line matching support for specifying new probes. This also changes the syntax of perf probe a bit. Now perf probe accepts one of below probe event definitions. 1) Define event based on function name [EVENT=]FUNC[@SRC][:RLN|+OFF|%return|;PTN] [ARG ...] 2) Define event based on source file with line number [EVENT=]SRC:ALN [ARG ...] 3) Define event based on source file with lazy pattern [EVENT=]SRC;PTN [ARG ...] - New lazy matching pattern(PTN) follows ';' (semicolon). And it must be put the end of the definition. - So, @SRC is no longer the part which must be put at the end of the definition. Note that ';' (semicolon) can be interpreted as the end of a command by the shell. This means that you need to quote it. (anyway you will need to quote the lazy pattern itself too, because it may contains other sensitive characters, like '[',']' etc.). Lazy matching ------------- The lazy line matching is similar to glob matching except ignoring spaces in both of pattern and target. e.g. 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. (for example, actual 10th line of schedule() can be changed easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist.) Changes in v3: - Cast Dwarf_Addr to uintmax_t for printf-formats. Changes in v2: - Cast Dwarf_Addr to unsigned long long for printf-formats. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: K.Prasad <prasad@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> LKML-Reference: <20100225133611.6725.45078.stgit@localhost6.localdomain6> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-25 21:36:12 +08:00
if (!lr->file || lf.fname) {
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
if (lr->function)
ret = find_line_range_by_func(&lf);
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
else {
lf.lno_s = lr->start;
lf.lno_e = lr->end;
ret = find_line_range_by_line(NULL, &lf);
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
}
}
off = noff;
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
}
perf probe: Add fastpath to do lookup by function name v3 -> v2: - Make pubname_search_cb more generic - Add fastpath to find_probes also v2 -> v1: - Don't compare file names with cu_find_realpath(...), instead, compare them with the name returned by dwarf_decl_file(sp_die) The vmlinux file may have thousands of CUs. We can lookup function name from .debug_pubnames section to avoid the slow loop on CUs. 1. Improvement data for find_line_range ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --line csum_partial_copy_to_user > tmp.log before patch applied ===================== 847,988,276 cycles 0.355075856 seconds time elapsed after patch applied ===================== 206,102,622 cycles 0.086883555 seconds time elapsed 2. Improvement data for find_probes ./perf stat -e cycles -r 10 -- ./perf probe -k /home/mlin/vmlinux \ -s /home/mlin/linux-2.6 \ --vars csum_partial_copy_to_user > tmp.log before patch applied ===================== 848,490,844 cycles 0.355307901 seconds time elapsed after patch applied ===================== 205,684,469 cycles 0.086694010 seconds time elapsed Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linux-kernel <linux-kernel@vger.kernel.org> LKML-Reference: <1301041668.14111.52.camel@minggr.sh.intel.com> Signed-off-by: Lin Ming <ming.m.lin@intel.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-03-25 16:27:48 +08:00
found:
/* Store comp_dir */
if (lf.found) {
comp_dir = cu_get_comp_dir(&lf.cu_die);
if (comp_dir) {
lr->comp_dir = strdup(comp_dir);
if (!lr->comp_dir)
ret = -ENOMEM;
}
}
pr_debug("path: %s\n", lr->path);
return (ret < 0) ? ret : lf.found;
perf probe: Support --line option to show probable source-code lines Add --line option to support showing probable source-code lines. perf probe --line SRC:LN[-LN|+NUM] or perf probe --line FUNC[:LN[-LN|+NUM]] This option shows source-code with line number if the line can be probed. Lines without line number (and blue color) means that the line can not be probed, because debuginfo doesn't have the information of those lines. The argument specifies the range of lines, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. e.g. # ./perf probe --line kernel/sched.c:1080 <kernel/sched.c:1080> * * called with rq->lock held and irqs disabled */ static void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; 1086 ktime_t time = ktime_add_ns(timer->base->get_time(), delay); hrtimer_set_expires(timer, time); 1090 if (rq == this_rq()) { 1091 hrtimer_restart(timer); 1092 } else if (!rq->hrtick_csd_pending) { 1093 __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 1094 rq->hrtick_csd_pending = 1; If you specifying function name, this shows function-relative line number. # ./perf probe --line schedule <schedule:0> asmlinkage void __sched schedule(void) 1 { struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; int cpu; need_resched: preempt_disable(); 9 cpu = smp_processor_id(); 10 rq = cpu_rq(cpu); 11 rcu_sched_qs(cpu); 12 prev = rq->curr; 13 switch_count = &prev->nivcsw; Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: systemtap <systemtap@sources.redhat.com> Cc: DLE <dle-develop@lists.sourceforge.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20100106144534.27218.77939.stgit@dhcp-100-2-132.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-01-06 22:45:34 +08:00
}
/*
* Find a src file from a DWARF tag path. Prepend optional source path prefix
* and chop off leading directories that do not exist. Result is passed back as
* a newly allocated path on success.
* Return 0 if file was found and readable, -errno otherwise.
*/
int get_real_path(const char *raw_path, const char *comp_dir,
char **new_path)
{
const char *prefix = symbol_conf.source_prefix;
if (!prefix) {
if (raw_path[0] != '/' && comp_dir)
/* If not an absolute path, try to use comp_dir */
prefix = comp_dir;
else {
if (access(raw_path, R_OK) == 0) {
*new_path = strdup(raw_path);
return *new_path ? 0 : -ENOMEM;
} else
return -errno;
}
}
*new_path = malloc((strlen(prefix) + strlen(raw_path) + 2));
if (!*new_path)
return -ENOMEM;
for (;;) {
sprintf(*new_path, "%s/%s", prefix, raw_path);
if (access(*new_path, R_OK) == 0)
return 0;
if (!symbol_conf.source_prefix) {
/* In case of searching comp_dir, don't retry */
zfree(new_path);
return -errno;
}
switch (errno) {
case ENAMETOOLONG:
case ENOENT:
case EROFS:
case EFAULT:
raw_path = strchr(++raw_path, '/');
if (!raw_path) {
zfree(new_path);
return -ENOENT;
}
continue;
default:
zfree(new_path);
return -errno;
}
}
}