lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20190619064429.14940-2-adrian.hunter@intel.com>
Date:   Wed, 19 Jun 2019 09:44:28 +0300
From:   Adrian Hunter <adrian.hunter@...el.com>
To:     Arnaldo Carvalho de Melo <acme@...nel.org>
Cc:     Jiri Olsa <jolsa@...hat.com>, linux-kernel@...r.kernel.org
Subject: [PATCH 1/2] 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 --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@...el.com>
Fixes: f08046cb3082 ("perf thread-stack: Represent jmps to the start of a different symbol")
Cc: stable@...r.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

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ