[PATCH 0/2] perf thread-stack: Fix thread stack return from kernel for kernel-only case

[PATCH 0/2] perf thread-stack: Fix thread stack return from kernel for kernel-only case

[Adrian Hunter]

Hi

Here is one non-urgent fix and a subsequent tidy-up.


Adrian Hunter (2):
      perf thread-stack: Fix thread stack return from kernel for kernel-only case
      perf thread-stack: Eliminate code duplicating thread_stack__pop_ks()

 tools/perf/util/thread-stack.c | 48 ++++++++++++++++++++++++++++++------------
 1 file changed, 35 insertions(+), 13 deletions(-)


Regards
Adrian

[PATCH 1/2] perf thread-stack: Fix thread stack return from kernel for kernel-only case

[Adrian Hunter]

Commit f08046cb3082 ("perf thread-stack: Represent jmps to the start of a
different symbol") had the side-effect of introducing more stack entries
before return from kernel space. When user space is also traced, those
entries are popped before entry to user space, but when user space is not
traced, they get stuck at the bottom of the stack, making the stack grow
progressively larger. Fix by detecting a return-from-kernel branch type,
and popping kernel addresses from the stack then.

Note, the problem and fix affect the exported Call Graph / Tree but not
the callindent option used by "perf script --call-trace".

Example:

  perf-with-kcore record example -e intel_pt//k -- ls
  perf-with-kcore script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py example.db branches calls
  ~/libexec/perf-core/scripts/python/exported-sql-viewer.py example.db

  Menu option: Reports -> Context-Sensitive Call Graph

  Before: (showing Call Path column only)

    Call Path
    ▶ perf
    ▼ ls
      ▼ 12111:12111
        ▶ setup_new_exec
        ▶ __task_pid_nr_ns
        ▶ perf_event_pid_type
        ▶ perf_event_comm_output
        ▶ perf_iterate_ctx
        ▶ perf_iterate_sb
        ▶ perf_event_comm
        ▶ __set_task_comm
        ▶ load_elf_binary
        ▶ search_binary_handler
        ▶ __do_execve_file.isra.41
        ▶ __x64_sys_execve
        ▶ do_syscall_64
        ▼ entry_SYSCALL_64_after_hwframe
          ▼ swapgs_restore_regs_and_return_to_usermode
            ▼ native_iret
              ▶ error_entry
              ▶ do_page_fault
              ▼ error_exit
                ▼ retint_user
                  ▶ prepare_exit_to_usermode
                  ▼ native_iret
                    ▶ error_entry
                    ▶ do_page_fault
                    ▼ error_exit
                      ▼ retint_user
                        ▶ prepare_exit_to_usermode
                        ▼ native_iret
                          ▶ error_entry
                          ▶ do_page_fault
                          ▼ error_exit
                            ▼ retint_user
                              ▶ prepare_exit_to_usermode
                              ▶ native_iret

  After: (showing Call Path column only)

    Call Path
    ▶ perf
    ▼ ls
      ▼ 12111:12111
        ▶ setup_new_exec
        ▶ __task_pid_nr_ns
        ▶ perf_event_pid_type
        ▶ perf_event_comm_output
        ▶ perf_iterate_ctx
        ▶ perf_iterate_sb
        ▶ perf_event_comm
        ▶ __set_task_comm
        ▶ load_elf_binary
        ▶ search_binary_handler
        ▶ __do_execve_file.isra.41
        ▶ __x64_sys_execve
        ▶ do_syscall_64
        ▶ entry_SYSCALL_64_after_hwframe
        ▶ page_fault
        ▼ entry_SYSCALL_64
          ▼ do_syscall_64
            ▶ __x64_sys_brk
            ▶ __x64_sys_access
            ▶ __x64_sys_openat
            ▶ __x64_sys_newfstat
            ▶ __x64_sys_mmap
            ▶ __x64_sys_close
            ▶ __x64_sys_read
            ▶ __x64_sys_mprotect
            ▶ __x64_sys_arch_prctl
            ▶ __x64_sys_munmap
            ▶ exit_to_usermode_loop
            ▶ __x64_sys_set_tid_address
            ▶ __x64_sys_set_robust_list
            ▶ __x64_sys_rt_sigaction
            ▶ __x64_sys_rt_sigprocmask
            ▶ __x64_sys_prlimit64
            ▶ __x64_sys_statfs
            ▶ __x64_sys_ioctl
            ▶ __x64_sys_getdents64
            ▶ __x64_sys_write
            ▶ __x64_sys_exit_group

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Fixes: f08046cb3082 ("perf thread-stack: Represent jmps to the start of a different symbol")
Cc: stable@vger.kernel.org
---
 tools/perf/util/thread-stack.c | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 8e390f78486f..f91c00dfe23b 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -637,6 +637,23 @@ static int thread_stack__bottom(struct thread_stack *ts,
 				     true, false);
 }
 
+static int thread_stack__pop_ks(struct thread *thread, struct thread_stack *ts,
+				struct perf_sample *sample, u64 ref)
+{
+	u64 tm = sample->time;
+	int err;
+
+	/* Return to userspace, so pop all kernel addresses */
+	while (thread_stack__in_kernel(ts)) {
+		err = thread_stack__call_return(thread, ts, --ts->cnt,
+						tm, ref, true);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int thread_stack__no_call_return(struct thread *thread,
 					struct thread_stack *ts,
 					struct perf_sample *sample,
@@ -919,7 +936,18 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 			ts->rstate = X86_RETPOLINE_DETECTED;
 
 	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
-		if (!sample->ip || !sample->addr)
+		if (!sample->addr) {
+			u32 return_from_kernel = PERF_IP_FLAG_SYSCALLRET |
+						 PERF_IP_FLAG_INTERRUPT;
+
+			if (!(sample->flags & return_from_kernel))
+				return 0;
+
+			/* Pop kernel stack */
+			return thread_stack__pop_ks(thread, ts, sample, ref);
+		}
+
+		if (!sample->ip)
 			return 0;
 
 		/* x86 retpoline 'return' doesn't match the stack */
-- 
2.17.1

Re: [PATCH 1/2] perf thread-stack: Fix thread stack return from kernel for kernel-only case

[Arnaldo Carvalho de Melo]

Em Wed, Jun 19, 2019 at 09:44:28AM +0300, Adrian Hunter escreveu:
> Commit f08046cb3082 ("perf thread-stack: Represent jmps to the start of a
> different symbol") had the side-effect of introducing more stack entries
> before return from kernel space. When user space is also traced, those
> entries are popped before entry to user space, but when user space is not
> traced, they get stuck at the bottom of the stack, making the stack grow
> progressively larger. Fix by detecting a return-from-kernel branch type,
> and popping kernel addresses from the stack then.
> 
> Note, the problem and fix affect the exported Call Graph / Tree but not
> the callindent option used by "perf script --call-trace".
> 
> Example:
> 
>   perf-with-kcore record example -e intel_pt//k -- ls
>   perf-with-kcore script --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py example.db branches calls
>   ~/libexec/perf-core/scripts/python/exported-sql-viewer.py example.db

Trying with you above instructions I hit some snags, 'perf-with-kcore'
expects the first arg to be the directory where it'll find the perf.data
file, etc, right? I.e. to work I had to do:

[root@quaco tmp]# rm -rf bep
[root@quaco tmp]# rm -rf example.db 
[root@quaco tmp]# perf-with-kcore record bep -e intel_pt//k -- ls
Recording
Using /root/bin/perf
perf version 5.2.rc4.gd1d5628fa057
/root/bin/perf record -o bep/perf.data -e intel_pt//k -- ls
<SNIP>
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.123 MB bep/perf.data ]
Copying kcore
Done
[root@quaco tmp]# perf-with-kcore script bep --itrace=bep -s ~acme/libexec/perf-core/scripts/python/export-to-sqlite.py example.db branches calls
Using /root/bin/perf
perf version 5.2.rc4.gd1d5628fa057
/root/bin/perf script -i bep/perf.data --kallsyms=bep/kcore_dir/kallsyms --itrace=bep -s /home/acme/libexec/perf-core/scripts/python/export-to-sqlite.py example.db branches calls
2019-06-24 15:29:54.910209 Creating database ...
2019-06-24 15:29:54.913351 Writing records...
2019-06-24 15:29:58.009226 Adding indexes
2019-06-24 15:29:58.024644 Done
[root@quaco tmp]#

I.e. add 'bep' after 'script' and before '--itrace-bep'.

I'm fixing this up in the comment, please check.

With that in place I can reproduce your results below.


Thanks,

- Arnaldo
 
>   Menu option: Reports -> Context-Sensitive Call Graph
> 
>   Before: (showing Call Path column only)
> 
>     Call Path
>     ▶ perf
>     ▼ ls
>       ▼ 12111:12111
>         ▶ setup_new_exec
>         ▶ __task_pid_nr_ns
>         ▶ perf_event_pid_type
>         ▶ perf_event_comm_output
>         ▶ perf_iterate_ctx
>         ▶ perf_iterate_sb
>         ▶ perf_event_comm
>         ▶ __set_task_comm
>         ▶ load_elf_binary
>         ▶ search_binary_handler
>         ▶ __do_execve_file.isra.41
>         ▶ __x64_sys_execve
>         ▶ do_syscall_64
>         ▼ entry_SYSCALL_64_after_hwframe
>           ▼ swapgs_restore_regs_and_return_to_usermode
>             ▼ native_iret
>               ▶ error_entry
>               ▶ do_page_fault
>               ▼ error_exit
>                 ▼ retint_user
>                   ▶ prepare_exit_to_usermode
>                   ▼ native_iret
>                     ▶ error_entry
>                     ▶ do_page_fault
>                     ▼ error_exit
>                       ▼ retint_user
>                         ▶ prepare_exit_to_usermode
>                         ▼ native_iret
>                           ▶ error_entry
>                           ▶ do_page_fault
>                           ▼ error_exit
>                             ▼ retint_user
>                               ▶ prepare_exit_to_usermode
>                               ▶ native_iret

T

 
>   After: (showing Call Path column only)
> 
>     Call Path
>     ▶ perf
>     ▼ ls
>       ▼ 12111:12111
>         ▶ setup_new_exec
>         ▶ __task_pid_nr_ns
>         ▶ perf_event_pid_type
>         ▶ perf_event_comm_output
>         ▶ perf_iterate_ctx
>         ▶ perf_iterate_sb
>         ▶ perf_event_comm
>         ▶ __set_task_comm
>         ▶ load_elf_binary
>         ▶ search_binary_handler
>         ▶ __do_execve_file.isra.41
>         ▶ __x64_sys_execve
>         ▶ do_syscall_64
>         ▶ entry_SYSCALL_64_after_hwframe
>         ▶ page_fault
>         ▼ entry_SYSCALL_64
>           ▼ do_syscall_64
>             ▶ __x64_sys_brk
>             ▶ __x64_sys_access
>             ▶ __x64_sys_openat
>             ▶ __x64_sys_newfstat
>             ▶ __x64_sys_mmap
>             ▶ __x64_sys_close
>             ▶ __x64_sys_read
>             ▶ __x64_sys_mprotect
>             ▶ __x64_sys_arch_prctl
>             ▶ __x64_sys_munmap
>             ▶ exit_to_usermode_loop
>             ▶ __x64_sys_set_tid_address
>             ▶ __x64_sys_set_robust_list
>             ▶ __x64_sys_rt_sigaction
>             ▶ __x64_sys_rt_sigprocmask
>             ▶ __x64_sys_prlimit64
>             ▶ __x64_sys_statfs
>             ▶ __x64_sys_ioctl
>             ▶ __x64_sys_getdents64
>             ▶ __x64_sys_write
>             ▶ __x64_sys_exit_group
> 
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> Fixes: f08046cb3082 ("perf thread-stack: Represent jmps to the start of a different symbol")
> Cc: stable@vger.kernel.org
> ---
>  tools/perf/util/thread-stack.c | 30 +++++++++++++++++++++++++++++-
>  1 file changed, 29 insertions(+), 1 deletion(-)
> 
> diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
> index 8e390f78486f..f91c00dfe23b 100644
> --- a/tools/perf/util/thread-stack.c
> +++ b/tools/perf/util/thread-stack.c
> @@ -637,6 +637,23 @@ static int thread_stack__bottom(struct thread_stack *ts,
>  				     true, false);
>  }
>  
> +static int thread_stack__pop_ks(struct thread *thread, struct thread_stack *ts,
> +				struct perf_sample *sample, u64 ref)
> +{
> +	u64 tm = sample->time;
> +	int err;
> +
> +	/* Return to userspace, so pop all kernel addresses */
> +	while (thread_stack__in_kernel(ts)) {
> +		err = thread_stack__call_return(thread, ts, --ts->cnt,
> +						tm, ref, true);
> +		if (err)
> +			return err;
> +	}
> +
> +	return 0;
> +}
> +
>  static int thread_stack__no_call_return(struct thread *thread,
>  					struct thread_stack *ts,
>  					struct perf_sample *sample,
> @@ -919,7 +936,18 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
>  			ts->rstate = X86_RETPOLINE_DETECTED;
>  
>  	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
> -		if (!sample->ip || !sample->addr)
> +		if (!sample->addr) {
> +			u32 return_from_kernel = PERF_IP_FLAG_SYSCALLRET |
> +						 PERF_IP_FLAG_INTERRUPT;
> +
> +			if (!(sample->flags & return_from_kernel))
> +				return 0;
> +
> +			/* Pop kernel stack */
> +			return thread_stack__pop_ks(thread, ts, sample, ref);
> +		}
> +
> +		if (!sample->ip)
>  			return 0;
>  
>  		/* x86 retpoline 'return' doesn't match the stack */
> -- 
> 2.17.1

-- 

- Arnaldo

[tip:perf/core] perf thread-stack: Fix thread stack return from kernel for kernel-only case

[tip-bot for Adrian Hunter]

Commit-ID:  97860b483c5597663a174ff7405be957b4838391
Gitweb:     https://git.kernel.org/tip/97860b483c5597663a174ff7405be957b4838391
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Wed, 19 Jun 2019 09:44:28 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 25 Jun 2019 08:47:10 -0300

perf thread-stack: Fix thread stack return from kernel for kernel-only case

Commit f08046cb3082 ("perf thread-stack: Represent jmps to the start of a
different symbol") had the side-effect of introducing more stack entries
before return from kernel space.

When user space is also traced, those entries are popped before entry to
user space, but when user space is not traced, they get stuck at the
bottom of the stack, making the stack grow progressively larger.

Fix by detecting a return-from-kernel branch type, and popping kernel
addresses from the stack then.

Note, the problem and fix affect the exported Call Graph / Tree but not
the callindent option used by "perf script --call-trace".

Example:

  perf-with-kcore record example -e intel_pt//k -- ls
  perf-with-kcore script example --itrace=bep -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py example.db branches calls
  ~/libexec/perf-core/scripts/python/exported-sql-viewer.py example.db

  Menu option: Reports -> Context-Sensitive Call Graph

  Before: (showing Call Path column only)

    Call Path
    ▶ perf
    ▼ ls
      ▼ 12111:12111
        ▶ setup_new_exec
        ▶ __task_pid_nr_ns
        ▶ perf_event_pid_type
        ▶ perf_event_comm_output
        ▶ perf_iterate_ctx
        ▶ perf_iterate_sb
        ▶ perf_event_comm
        ▶ __set_task_comm
        ▶ load_elf_binary
        ▶ search_binary_handler
        ▶ __do_execve_file.isra.41
        ▶ __x64_sys_execve
        ▶ do_syscall_64
        ▼ entry_SYSCALL_64_after_hwframe
          ▼ swapgs_restore_regs_and_return_to_usermode
            ▼ native_iret
              ▶ error_entry
              ▶ do_page_fault
              ▼ error_exit
                ▼ retint_user
                  ▶ prepare_exit_to_usermode
                  ▼ native_iret
                    ▶ error_entry
                    ▶ do_page_fault
                    ▼ error_exit
                      ▼ retint_user
                        ▶ prepare_exit_to_usermode
                        ▼ native_iret
                          ▶ error_entry
                          ▶ do_page_fault
                          ▼ error_exit
                            ▼ retint_user
                              ▶ prepare_exit_to_usermode
                              ▶ native_iret

  After: (showing Call Path column only)

    Call Path
    ▶ perf
    ▼ ls
      ▼ 12111:12111
        ▶ setup_new_exec
        ▶ __task_pid_nr_ns
        ▶ perf_event_pid_type
        ▶ perf_event_comm_output
        ▶ perf_iterate_ctx
        ▶ perf_iterate_sb
        ▶ perf_event_comm
        ▶ __set_task_comm
        ▶ load_elf_binary
        ▶ search_binary_handler
        ▶ __do_execve_file.isra.41
        ▶ __x64_sys_execve
        ▶ do_syscall_64
        ▶ entry_SYSCALL_64_after_hwframe
        ▶ page_fault
        ▼ entry_SYSCALL_64
          ▼ do_syscall_64
            ▶ __x64_sys_brk
            ▶ __x64_sys_access
            ▶ __x64_sys_openat
            ▶ __x64_sys_newfstat
            ▶ __x64_sys_mmap
            ▶ __x64_sys_close
            ▶ __x64_sys_read
            ▶ __x64_sys_mprotect
            ▶ __x64_sys_arch_prctl
            ▶ __x64_sys_munmap
            ▶ exit_to_usermode_loop
            ▶ __x64_sys_set_tid_address
            ▶ __x64_sys_set_robust_list
            ▶ __x64_sys_rt_sigaction
            ▶ __x64_sys_rt_sigprocmask
            ▶ __x64_sys_prlimit64
            ▶ __x64_sys_statfs
            ▶ __x64_sys_ioctl
            ▶ __x64_sys_getdents64
            ▶ __x64_sys_write
            ▶ __x64_sys_exit_group

Committer notes:

The first arg to the perf-with-kcore needs to be the same for the
'record' and 'script' lines, otherwise we'll record the perf.data file
and kcore_dir/ files in one directory ('example') to then try to use it
from the 'bep' directory, fix the instructions above it so that both use
'example'.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org
Fixes: f08046cb3082 ("perf thread-stack: Represent jmps to the start of a different symbol")
Link: http://lkml.kernel.org/r/20190619064429.14940-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/thread-stack.c | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index c485186a8b6d..4c826a2e08d8 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -628,6 +628,23 @@ static int thread_stack__bottom(struct thread_stack *ts,
 				     true, false);
 }
 
+static int thread_stack__pop_ks(struct thread *thread, struct thread_stack *ts,
+				struct perf_sample *sample, u64 ref)
+{
+	u64 tm = sample->time;
+	int err;
+
+	/* Return to userspace, so pop all kernel addresses */
+	while (thread_stack__in_kernel(ts)) {
+		err = thread_stack__call_return(thread, ts, --ts->cnt,
+						tm, ref, true);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int thread_stack__no_call_return(struct thread *thread,
 					struct thread_stack *ts,
 					struct perf_sample *sample,
@@ -910,7 +927,18 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 			ts->rstate = X86_RETPOLINE_DETECTED;
 
 	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
-		if (!sample->ip || !sample->addr)
+		if (!sample->addr) {
+			u32 return_from_kernel = PERF_IP_FLAG_SYSCALLRET |
+						 PERF_IP_FLAG_INTERRUPT;
+
+			if (!(sample->flags & return_from_kernel))
+				return 0;
+
+			/* Pop kernel stack */
+			return thread_stack__pop_ks(thread, ts, sample, ref);
+		}
+
+		if (!sample->ip)
 			return 0;
 
 		/* x86 retpoline 'return' doesn't match the stack */

[PATCH 2/2] perf thread-stack: Eliminate code duplicating thread_stack__pop_ks()

[Adrian Hunter]

Use new function thread_stack__pop_ks() in place of equivalent code.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/thread-stack.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index f91c00dfe23b..b20c9b867fce 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -673,12 +673,9 @@ static int thread_stack__no_call_return(struct thread *thread,
 
 	if (ip >= ks && addr < ks) {
 		/* Return to userspace, so pop all kernel addresses */
-		while (thread_stack__in_kernel(ts)) {
-			err = thread_stack__call_return(thread, ts, --ts->cnt,
-							tm, ref, true);
-			if (err)
-				return err;
-		}
+		err = thread_stack__pop_ks(thread, ts, sample, ref);
+		if (err)
+			return err;
 
 		/* If the stack is empty, push the userspace address */
 		if (!ts->cnt) {
@@ -688,12 +685,9 @@ static int thread_stack__no_call_return(struct thread *thread,
 		}
 	} else if (thread_stack__in_kernel(ts) && ip < ks) {
 		/* Return to userspace, so pop all kernel addresses */
-		while (thread_stack__in_kernel(ts)) {
-			err = thread_stack__call_return(thread, ts, --ts->cnt,
-							tm, ref, true);
-			if (err)
-				return err;
-		}
+		err = thread_stack__pop_ks(thread, ts, sample, ref);
+		if (err)
+			return err;
 	}
 
 	if (ts->cnt)
-- 
2.17.1

[tip:perf/core] perf thread-stack: Eliminate code duplicating thread_stack__pop_ks()

[tip-bot for Adrian Hunter]

Commit-ID:  eb5d854456f5a4ccec6f9681b7196cf056df8cfa
Gitweb:     https://git.kernel.org/tip/eb5d854456f5a4ccec6f9681b7196cf056df8cfa
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Wed, 19 Jun 2019 09:44:29 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 25 Jun 2019 08:47:10 -0300

perf thread-stack: Eliminate code duplicating thread_stack__pop_ks()

Use new function thread_stack__pop_ks() in place of equivalent code.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20190619064429.14940-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/thread-stack.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 4c826a2e08d8..6ff1ff4d4ce7 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -664,12 +664,9 @@ static int thread_stack__no_call_return(struct thread *thread,
 
 	if (ip >= ks && addr < ks) {
 		/* Return to userspace, so pop all kernel addresses */
-		while (thread_stack__in_kernel(ts)) {
-			err = thread_stack__call_return(thread, ts, --ts->cnt,
-							tm, ref, true);
-			if (err)
-				return err;
-		}
+		err = thread_stack__pop_ks(thread, ts, sample, ref);
+		if (err)
+			return err;
 
 		/* If the stack is empty, push the userspace address */
 		if (!ts->cnt) {
@@ -679,12 +676,9 @@ static int thread_stack__no_call_return(struct thread *thread,
 		}
 	} else if (thread_stack__in_kernel(ts) && ip < ks) {
 		/* Return to userspace, so pop all kernel addresses */
-		while (thread_stack__in_kernel(ts)) {
-			err = thread_stack__call_return(thread, ts, --ts->cnt,
-							tm, ref, true);
-			if (err)
-				return err;
-		}
+		err = thread_stack__pop_ks(thread, ts, sample, ref);
+		if (err)
+			return err;
 	}
 
 	if (ts->cnt)

Re: [PATCH 0/2] perf thread-stack: Fix thread stack return from kernel for kernel-only case

[Arnaldo Carvalho de Melo]

Em Wed, Jun 19, 2019 at 09:44:27AM +0300, Adrian Hunter escreveu:
> Hi
> 
> Here is one non-urgent fix and a subsequent tidy-up.

Thanks, both applied.

- Arnaldo
 
> 
> Adrian Hunter (2):
>       perf thread-stack: Fix thread stack return from kernel for kernel-only case
>       perf thread-stack: Eliminate code duplicating thread_stack__pop_ks()
> 
>  tools/perf/util/thread-stack.c | 48 ++++++++++++++++++++++++++++++------------
>  1 file changed, 35 insertions(+), 13 deletions(-)
> 
> 
> Regards
> Adrian

-- 

- Arnaldo