linux/tools/perf/util/dwarf-aux.h

232 lines
7.4 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
#ifndef _DWARF_AUX_H
#define _DWARF_AUX_H
/*
* dwarf-aux.h : libdw auxiliary interfaces
*/
#include <dwarf.h>
#include <elfutils/libdw.h>
#include <elfutils/libdwfl.h>
#include <elfutils/version.h>
struct strbuf;
/* Find the realpath of the target file */
const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname);
/* Get DW_AT_comp_dir (should be NULL with older gcc) */
const char *cu_get_comp_dir(Dwarf_Die *cu_die);
/* Get a line number and file name for given address */
perf probe: Fix add event failure when running 32-bit perf in a 64-bit kernel The "address" member of "struct probe_trace_point" uses long data type. If kernel is 64-bit and perf program is 32-bit, size of "address" variable is 32 bits. As a result, upper 32 bits of address read from kernel are truncated, an error occurs during address comparison in kprobe_warn_out_range(). Before: # perf probe -a schedule schedule is out of .text, skip it. Error: Failed to add events. Solution: Change data type of "address" variable to u64 and change corresponding address printing and value assignment. After: # perf.new.new probe -a schedule Added new event: probe:schedule (on schedule) You can now use it in all perf tools, such as: perf record -e probe:schedule -aR sleep 1 # perf probe -l probe:schedule (on schedule@kernel/sched/core.c) # perf record -e probe:schedule -aR sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.156 MB perf.data (1366 samples) ] # perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 1K of event 'probe:schedule' # Event count (approx.): 1366 # # Overhead Command Shared Object Symbol # ........ ............... ................. ............ # 6.22% migration/0 [kernel.kallsyms] [k] schedule 6.22% migration/1 [kernel.kallsyms] [k] schedule 6.22% migration/2 [kernel.kallsyms] [k] schedule 6.22% migration/3 [kernel.kallsyms] [k] schedule 6.15% migration/10 [kernel.kallsyms] [k] schedule 6.15% migration/11 [kernel.kallsyms] [k] schedule 6.15% migration/12 [kernel.kallsyms] [k] schedule 6.15% migration/13 [kernel.kallsyms] [k] schedule 6.15% migration/14 [kernel.kallsyms] [k] schedule 6.15% migration/15 [kernel.kallsyms] [k] schedule 6.15% migration/4 [kernel.kallsyms] [k] schedule 6.15% migration/5 [kernel.kallsyms] [k] schedule 6.15% migration/6 [kernel.kallsyms] [k] schedule 6.15% migration/7 [kernel.kallsyms] [k] schedule 6.15% migration/8 [kernel.kallsyms] [k] schedule 6.15% migration/9 [kernel.kallsyms] [k] schedule 0.22% rcu_sched [kernel.kallsyms] [k] schedule ... # # (Cannot load tips.txt file, please install perf!) # Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Acked-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Ian Rogers <irogers@google.com> Cc: Jianlin Lv <jianlin.lv@arm.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Li Huafei <lihuafei1@huawei.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Link: http://lore.kernel.org/lkml/20210715063723.11926-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-07-15 14:37:23 +08:00
int cu_find_lineinfo(Dwarf_Die *cudie, Dwarf_Addr addr,
const char **fname, int *lineno);
/* Walk on functions at given address */
int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
int (*callback)(Dwarf_Die *, void *), void *data);
perf probe: Match linkage name with mangled name Match linkage name with mangled name if exists. The linkage_name is used for storing mangled name of the object. Thus, this allows 'perf probe' to find appropriate probe point from mangled symbol as below. E.g. without this fix: ---- $ perf probe -x /usr/lib64/libstdc++.so.6 \ -D _ZNKSt15basic_fstreamXXIwSt11char_traitsIwEE7is_openEv Probe point '_ZNKSt15basic_fstreamXXIwSt11char_traitsIwEE7is_openEv' not found. Error: Failed to add events. ---- With this fix, perf probe can find the correct one. ---- $ perf probe -x /usr/lib64/libstdc++.so.6 \ -D _ZNKSt15basic_fstreamXXIwSt11char_traitsIwEE7is_openEv p:probe_libstdc/_ZNKSt15basic_fstreamXXIwSt11char_traitsIwEE7is_openEv /usr/lib64/libstdc++.so.6.0.22:0x8ca60 ---- Committer notes: After the fix, setting it for real (no -D/--definition, that amounts to a --dry-run): # perf probe -x /usr/lib64/libstdc++.so.6 _ZNKSt15basic_fstreamXXIwSt11char_traitsIwEE7is_openEv Added new event: probe_libstdc:_ZNKSt15basic_fstreamXXIwSt11char_traitsIwEE7is_openEv (on _ZNKSt15basic_fstreamXXIwSt11char_traitsIwEE7is_openEv in /usr/lib64/libstdc++.so.6.0.22) You can now use it in all perf tools, such as: perf record -e probe_libstdc:_ZNKSt15basic_fstreamXXIwSt11char_traitsIwEE7is_openEv -aR sleep 1 # perf probe -l probe_libstdc:* probe_libstdc:_ZNKSt15basic_fstreamXXIwSt11char_traitsIwEE7is_openEv (on is_open@libstdc++-v3/include/fstream in /usr/lib64/libstdc++.so.6.0.22) # Reported-by: Thomas Gleixner <tglx@linutronix.de> 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> Link: http://lkml.kernel.org/r/147464493162.29804.16715053505069382443.stgit@devbox Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-24 00:35:31 +09:00
/* Get DW_AT_linkage_name (should be NULL for C binary) */
const char *die_get_linkage_name(Dwarf_Die *dw_die);
/* Get the lowest PC in DIE (including range list) */
int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr);
/* Ensure that this DIE is a subprogram and definition (not declaration) */
bool die_is_func_def(Dwarf_Die *dw_die);
/* Ensure that this DIE is an instance of a subprogram */
bool die_is_func_instance(Dwarf_Die *dw_die);
/* Compare diename and tname */
bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
/* Matching diename with glob pattern */
bool die_match_name(Dwarf_Die *dw_die, const char *glob);
/* Get callsite line number of inline-function instance */
int die_get_call_lineno(Dwarf_Die *in_die);
perf probe: Fix to search nested inlined functions in CU Fix perf probe to walk through the lines of all nested inlined function call sites and declared lines when a whole CU is passed to the line walker. The die_walk_lines() can have two different type of DIEs, subprogram (or inlined-subroutine) DIE and CU DIE. If a caller passes a subprogram DIE, this means that the walker walk on lines of given subprogram. In this case, it just needs to search on direct children of DIE tree for finding call-site information of inlined function which directly called from given subprogram. On the other hand, if a caller passes a CU DIE to the walker, this means that the walker have to walk on all lines in the source files included in given CU DIE. In this case, it has to search whole DIE trees of all subprograms to find the call-site information of all nested inlined functions. Without this patch: $ perf probe --line kernel/cpu.c:151-157 </home/mhiramat/ksrc/linux-2.6/kernel/cpu.c:151> static int cpu_notify(unsigned long val, void *v) { 154 return __cpu_notify(val, v, -1, NULL); } With this: $ perf probe --line kernel/cpu.c:151-157 </home/mhiramat/ksrc/linux-2.6/kernel/cpu.c:151> 152 static int cpu_notify(unsigned long val, void *v) { 154 return __cpu_notify(val, v, -1, NULL); } As you can see, --line option with source line range shows the declared lines as probe-able. 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/20110811110241.19900.34994.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 20:02:41 +09:00
/* Get callsite file name of inlined function instance */
const char *die_get_call_file(Dwarf_Die *in_die);
perf probe: Fix to search nested inlined functions in CU Fix perf probe to walk through the lines of all nested inlined function call sites and declared lines when a whole CU is passed to the line walker. The die_walk_lines() can have two different type of DIEs, subprogram (or inlined-subroutine) DIE and CU DIE. If a caller passes a subprogram DIE, this means that the walker walk on lines of given subprogram. In this case, it just needs to search on direct children of DIE tree for finding call-site information of inlined function which directly called from given subprogram. On the other hand, if a caller passes a CU DIE to the walker, this means that the walker have to walk on all lines in the source files included in given CU DIE. In this case, it has to search whole DIE trees of all subprograms to find the call-site information of all nested inlined functions. Without this patch: $ perf probe --line kernel/cpu.c:151-157 </home/mhiramat/ksrc/linux-2.6/kernel/cpu.c:151> static int cpu_notify(unsigned long val, void *v) { 154 return __cpu_notify(val, v, -1, NULL); } With this: $ perf probe --line kernel/cpu.c:151-157 </home/mhiramat/ksrc/linux-2.6/kernel/cpu.c:151> 152 static int cpu_notify(unsigned long val, void *v) { 154 return __cpu_notify(val, v, -1, NULL); } As you can see, --line option with source line range shows the declared lines as probe-able. 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/20110811110241.19900.34994.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 20:02:41 +09:00
2022-11-01 22:48:49 +09:00
/* Get declared file name of a DIE */
const char *die_get_decl_file(Dwarf_Die *dw_die);
/* Get type die */
Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem);
/* Get a type die, but skip qualifiers and typedef */
Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem);
/* Check whether the DIE is signed or not */
bool die_is_signed_type(Dwarf_Die *tp_die);
/* Get data_member_location offset */
int die_get_data_member_location(Dwarf_Die *mb_die, Dwarf_Word *offs);
/* Return values for die_find_child() callbacks */
enum {
DIE_FIND_CB_END = 0, /* End of Search */
DIE_FIND_CB_CHILD = 1, /* Search only children */
DIE_FIND_CB_SIBLING = 2, /* Search only siblings */
DIE_FIND_CB_CONTINUE = 3, /* Search children and siblings */
};
/* Search child DIEs */
Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
int (*callback)(Dwarf_Die *, void *),
void *data, Dwarf_Die *die_mem);
/* Search a non-inlined function including given address */
Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
Dwarf_Die *die_mem);
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 17:12:31 +05:30
/* Search a non-inlined function with tail call at given address */
Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
Dwarf_Die *die_mem);
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 18:21:44 +09:00
/* Search the top inlined function including given address */
Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
Dwarf_Die *die_mem);
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 18:21:44 +09:00
/* Search the deepest inlined function including given address */
Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
Dwarf_Die *die_mem);
/* Search a non-inlined function by name and returns its return type */
Dwarf_Die *die_find_func_rettype(Dwarf_Die *sp_die, const char *name,
Dwarf_Die *die_mem);
/* Walk on the instances of given DIE */
int die_walk_instances(Dwarf_Die *in_die,
int (*callback)(Dwarf_Die *, void *), void *data);
/* Walker on lines (Note: line number will not be sorted) */
typedef int (* line_walk_callback_t) (const char *fname, int lineno,
Dwarf_Addr addr, void *data);
/*
* Walk on lines inside given DIE. If the DIE is a subprogram, walk only on
* the lines inside the subprogram, otherwise the DIE must be a CU DIE.
*/
int die_walk_lines(Dwarf_Die *rt_die, line_walk_callback_t callback, void *data);
/* Find a variable called 'name' at given address */
Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name,
Dwarf_Addr addr, Dwarf_Die *die_mem);
/* Find a member called 'name' */
Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
Dwarf_Die *die_mem);
/* Get the name of given type DIE */
int die_get_typename_from_type(Dwarf_Die *type_die, struct strbuf *buf);
/* Get the name of given variable DIE */
int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
/* Get the name and type of given variable DIE, stored as "type\tname" */
int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
/* Check if target program is compiled with optimization */
bool die_is_optimized_target(Dwarf_Die *cu_die);
/* Use next address after prologue as probe location */
void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
Dwarf_Addr *entrypc);
/* Get the list of including scopes */
int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes);
/* Variable type information */
struct die_var_type {
struct die_var_type *next;
u64 die_off;
u64 addr;
int reg;
int offset;
};
perf dwarf-aux: Handle type transfer for memory access We want to track type states as instructions are executed. Each instruction can access compound types like struct or union and load/ store its members to a different location. The die_deref_ptr_type() is to find a type of memory access with a pointer variable. If it points to a compound type like struct, the target memory is a member in the struct. The access will happen with an offset indicating which member it refers. Let's follow the DWARF info to figure out the type of the pointer target. For example, say we have the following code. struct foo { int a; int b; }; struct foo *p = malloc(sizeof(*p)); p->b = 0; The last pointer access should produce x86 asm like below: mov 0x0, 4(%rbx) And we know %rbx register has a pointer to struct foo. Then offset 4 should return the debug info of member 'b'. Also variables of compound types can be accessed directly without a pointer. The die_get_member_type() is to handle a such case. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20240319055115.4063940-4-namhyung@kernel.org [ Check if die_get_real_type() returned NULL ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-03-18 22:50:55 -07:00
/* Return type info of a member at offset */
Dwarf_Die *die_get_member_type(Dwarf_Die *type_die, int offset, Dwarf_Die *die_mem);
/* Return type info where the pointer and offset point to */
Dwarf_Die *die_deref_ptr_type(Dwarf_Die *ptr_die, int offset, Dwarf_Die *die_mem);
#ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
/* Get byte offset range of given variable DIE */
int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
/* Find a variable saved in the 'reg' at given address */
Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg,
perf annotate-data: Support stack variables Local variables are allocated in the stack and the location list should look like base register(s) and an offset. Extend the die_find_variable_by_reg() to handle the following expressions * DW_OP_breg{0..31} * DW_OP_bregx * DW_OP_fbreg Ususally DWARF subprogram entries have frame base information and use it to locate stack variable like below: <2><43d1575>: Abbrev Number: 62 (DW_TAG_variable) <43d1576> DW_AT_location : 2 byte block: 91 7c (DW_OP_fbreg: -4) <--- here <43d1579> DW_AT_name : (indirect string, offset: 0x2c00c9): i <43d157d> DW_AT_decl_file : 1 <43d157e> DW_AT_decl_line : 78 <43d157f> DW_AT_type : <0x43d19d7> I found some differences on saving the frame base between gcc and clang. The gcc uses the CFA to get the base so it needs to check the current frame's CFI info. In this case, stack offset needs to be adjusted from the start of the CFA. <1><1bb8d>: Abbrev Number: 102 (DW_TAG_subprogram) <1bb8e> DW_AT_name : (indirect string, offset: 0x74d41): kernel_init <1bb92> DW_AT_decl_file : 2 <1bb92> DW_AT_decl_line : 1440 <1bb94> DW_AT_decl_column : 18 <1bb95> DW_AT_prototyped : 1 <1bb95> DW_AT_type : <0xcc> <1bb99> DW_AT_low_pc : 0xffffffff81bab9e0 <1bba1> DW_AT_high_pc : 0x1b2 <1bba9> DW_AT_frame_base : 1 byte block: 9c (DW_OP_call_frame_cfa) <------ here <1bbab> DW_AT_call_all_calls: 1 <1bbab> DW_AT_sibling : <0x1bf5a> While clang sets it to a register directly and it can check the register and offset in the instruction directly. <1><43d1542>: Abbrev Number: 60 (DW_TAG_subprogram) <43d1543> DW_AT_low_pc : 0xffffffff816a7c60 <43d154b> DW_AT_high_pc : 0x98 <43d154f> DW_AT_frame_base : 1 byte block: 56 (DW_OP_reg6 (rbp)) <---------- here <43d1551> DW_AT_GNU_all_call_sites: 1 <43d1551> DW_AT_name : (indirect string, offset: 0x3bce91): foo <43d1555> DW_AT_decl_file : 1 <43d1556> DW_AT_decl_line : 75 <43d1557> DW_AT_prototyped : 1 <43d1557> DW_AT_type : <0x43c7332> <43d155b> DW_AT_external : 1 Also it needs to update the offset after finding the type like global variables since the offset was from the frame base. Factor out match_var_offset() to check global and local variables in the same way. The type stats are improved too: Annotate data type stats: total 294, ok 160 (54.4%), bad 134 (45.6%) ----------------------------------------------------------- 30 : no_sym 32 : no_mem_ops 51 : no_var 14 : no_typeinfo 7 : bad_offset Reviewed-by: Ian Rogers <irogers@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Link: https://lore.kernel.org/r/20240117062657.985479-9-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-01-16 22:26:56 -08:00
int *poffset, bool is_fbreg,
Dwarf_Die *die_mem);
/* Find a (global) variable located in the 'addr' */
Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr addr,
Dwarf_Die *die_mem, int *offset);
/* Save all variables and parameters in this scope */
void die_collect_vars(Dwarf_Die *sc_die, struct die_var_type **var_types);
/* Save all global variables in this CU */
void die_collect_global_vars(Dwarf_Die *cu_die, struct die_var_type **var_types);
#else /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
static inline int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
Dwarf_Die *vr_die __maybe_unused,
struct strbuf *buf __maybe_unused)
{
return -ENOTSUP;
}
static inline Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die __maybe_unused,
Dwarf_Addr pc __maybe_unused,
int reg __maybe_unused,
perf annotate-data: Support stack variables Local variables are allocated in the stack and the location list should look like base register(s) and an offset. Extend the die_find_variable_by_reg() to handle the following expressions * DW_OP_breg{0..31} * DW_OP_bregx * DW_OP_fbreg Ususally DWARF subprogram entries have frame base information and use it to locate stack variable like below: <2><43d1575>: Abbrev Number: 62 (DW_TAG_variable) <43d1576> DW_AT_location : 2 byte block: 91 7c (DW_OP_fbreg: -4) <--- here <43d1579> DW_AT_name : (indirect string, offset: 0x2c00c9): i <43d157d> DW_AT_decl_file : 1 <43d157e> DW_AT_decl_line : 78 <43d157f> DW_AT_type : <0x43d19d7> I found some differences on saving the frame base between gcc and clang. The gcc uses the CFA to get the base so it needs to check the current frame's CFI info. In this case, stack offset needs to be adjusted from the start of the CFA. <1><1bb8d>: Abbrev Number: 102 (DW_TAG_subprogram) <1bb8e> DW_AT_name : (indirect string, offset: 0x74d41): kernel_init <1bb92> DW_AT_decl_file : 2 <1bb92> DW_AT_decl_line : 1440 <1bb94> DW_AT_decl_column : 18 <1bb95> DW_AT_prototyped : 1 <1bb95> DW_AT_type : <0xcc> <1bb99> DW_AT_low_pc : 0xffffffff81bab9e0 <1bba1> DW_AT_high_pc : 0x1b2 <1bba9> DW_AT_frame_base : 1 byte block: 9c (DW_OP_call_frame_cfa) <------ here <1bbab> DW_AT_call_all_calls: 1 <1bbab> DW_AT_sibling : <0x1bf5a> While clang sets it to a register directly and it can check the register and offset in the instruction directly. <1><43d1542>: Abbrev Number: 60 (DW_TAG_subprogram) <43d1543> DW_AT_low_pc : 0xffffffff816a7c60 <43d154b> DW_AT_high_pc : 0x98 <43d154f> DW_AT_frame_base : 1 byte block: 56 (DW_OP_reg6 (rbp)) <---------- here <43d1551> DW_AT_GNU_all_call_sites: 1 <43d1551> DW_AT_name : (indirect string, offset: 0x3bce91): foo <43d1555> DW_AT_decl_file : 1 <43d1556> DW_AT_decl_line : 75 <43d1557> DW_AT_prototyped : 1 <43d1557> DW_AT_type : <0x43c7332> <43d155b> DW_AT_external : 1 Also it needs to update the offset after finding the type like global variables since the offset was from the frame base. Factor out match_var_offset() to check global and local variables in the same way. The type stats are improved too: Annotate data type stats: total 294, ok 160 (54.4%), bad 134 (45.6%) ----------------------------------------------------------- 30 : no_sym 32 : no_mem_ops 51 : no_var 14 : no_typeinfo 7 : bad_offset Reviewed-by: Ian Rogers <irogers@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Link: https://lore.kernel.org/r/20240117062657.985479-9-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-01-16 22:26:56 -08:00
int *poffset __maybe_unused,
bool is_fbreg __maybe_unused,
Dwarf_Die *die_mem __maybe_unused)
{
return NULL;
}
static inline Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die __maybe_unused,
Dwarf_Addr addr __maybe_unused,
Dwarf_Die *die_mem __maybe_unused,
int *offset __maybe_unused)
{
return NULL;
}
static inline void die_collect_vars(Dwarf_Die *sc_die __maybe_unused,
struct die_var_type **var_types __maybe_unused)
{
}
static inline void die_collect_global_vars(Dwarf_Die *cu_die __maybe_unused,
struct die_var_type **var_types __maybe_unused)
{
}
#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
#ifdef HAVE_DWARF_CFI_SUPPORT
/* Get the frame base information from CFA */
int die_get_cfa(Dwarf *dwarf, u64 pc, int *preg, int *poffset);
#else /* HAVE_DWARF_CFI_SUPPORT */
static inline int die_get_cfa(Dwarf *dwarf __maybe_unused, u64 pc __maybe_unused,
int *preg __maybe_unused, int *poffset __maybe_unused)
{
return -1;
}
#endif /* HAVE_DWARF_CFI_SUPPORT */
#endif /* _DWARF_AUX_H */