perf annotate: Use absolute addresses to calculate jump target offsets

These types of jumps were confusing the annotate browser:

entry_SYSCALL_64  /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux

entry_SYSCALL_64  /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
  Percent│ffffffff81a00020:   swapgs
  <SNIP>
         │ffffffff81a00128: ↓ jae    ffffffff81a00139 <syscall_return_via_sysret+0x53>
  <SNIP>
         │ffffffff81a00155: → jmpq   *0x825d2d(%rip)   # ffffffff82225e88 <pv_cpu_ops+0xe8>

I.e. the syscall_return_via_sysret function is actually "inside" the
entry_SYSCALL_64 function, and the offsets in jumps like these (+0x53)
are relative to syscall_return_via_sysret, not to syscall_return_via_sysret.

Or this may be some artifact in how the assembler marks the start and
end of a function and how this ends up in the ELF symtab for vmlinux,
i.e. syscall_return_via_sysret() isn't "inside" entry_SYSCALL_64, but
just right after it.

From readelf -sw vmlinux:

 80267: ffffffff81a00020   315 NOTYPE  GLOBAL DEFAULT    1 entry_SYSCALL_64
   316: ffffffff81a000e6     0 NOTYPE  LOCAL  DEFAULT    1 syscall_return_via_sysret

 0xffffffff81a00020 + 315 > 0xffffffff81a000e6

So instead of looking for offsets after that last '+' sign, calculate
offsets for jump target addresses that are inside the function being
disassembled from the absolute address, 0xffffffff81a00139 in this case,
subtracting from it the objdump address for the start of the function
being disassembled, entry_SYSCALL_64() in this case.

So, before this patch:

entry_SYSCALL_64  /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
Percent│       pop    %r10
       │       pop    %r9
       │       pop    %r8
       │       pop    %rax
       │       pop    %rsi
       │       pop    %rdx
       │       pop    %rsi
       │       mov    %rsp,%rdi
       │       mov    %gs:0x5004,%rsp
       │       pushq  0x28(%rdi)
       │       pushq  (%rdi)
       │       push   %rax
       │     ↑ jmp    6c
       │       mov    %cr3,%rdi
       │     ↑ jmp    62
       │       mov    %rdi,%rax
       │       and    $0x7ff,%rdi
       │       bt     %rdi,%gs:0x2219a
       │     ↑ jae    53
       │       btr    %rdi,%gs:0x2219a
       │       mov    %rax,%rdi
       │     ↑ jmp    5b

After:

entry_SYSCALL_64  /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
  0.65 │     → jne    swapgs_restore_regs_and_return_to_usermode
       │       pop    %r10
       │       pop    %r9
       │       pop    %r8
       │       pop    %rax
       │       pop    %rsi
       │       pop    %rdx
       │       pop    %rsi
       │       mov    %rsp,%rdi
       │       mov    %gs:0x5004,%rsp
       │       pushq  0x28(%rdi)
       │       pushq  (%rdi)
       │       push   %rax
       │     ↓ jmp    132
       │       mov    %cr3,%rdi
       │    ┌──jmp    128
       │    │  mov    %rdi,%rax
       │    │  and    $0x7ff,%rdi
       │    │  bt     %rdi,%gs:0x2219a
       │    │↓ jae    119
       │    │  btr    %rdi,%gs:0x2219a
       │    │  mov    %rax,%rdi
       │    │↓ jmp    121
       │119:│  mov    %rax,%rdi
       │    │  bts    $0x3f,%rdi
       │121:│  or     $0x800,%rdi
       │128:└─→or     $0x1000,%rdi
       │       mov    %rdi,%cr3
       │132:   pop    %rax
       │       pop    %rdi
       │       pop    %rsp
       │     → jmpq   *0x825d2d(%rip)        # ffffffff82225e88 <pv_cpu_ops+0xe8>

With those at least navigating to the right destination, an improvement
for these cases seems to be to be to somehow mark those inner functions,
which in this case could be:

entry_SYSCALL_64  /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
       │syscall_return_via_sysret:
       │       pop    %r15
       │       pop    %r14
       │       pop    %r13
       │       pop    %r12
       │       pop    %rbp
       │       pop    %rbx
       │       pop    %rsi
       │       pop    %r10
       │       pop    %r9
       │       pop    %r8
       │       pop    %rax
       │       pop    %rsi
       │       pop    %rdx
       │       pop    %rsi
       │       mov    %rsp,%rdi
       │       mov    %gs:0x5004,%rsp
       │       pushq  0x28(%rdi)
       │       pushq  (%rdi)
       │       push   %rax
       │     ↓ jmp    132
       │       mov    %cr3,%rdi
       │    ┌──jmp    128
       │    │  mov    %rdi,%rax
       │    │  and    $0x7ff,%rdi
       │    │  bt     %rdi,%gs:0x2219a
       │    │↓ jae    119
       │    │  btr    %rdi,%gs:0x2219a
       │    │  mov    %rax,%rdi
       │    │↓ jmp    121
       │119:│  mov    %rax,%rdi
       │    │  bts    $0x3f,%rdi
       │121:│  or     $0x800,%rdi
       │128:└─→or     $0x1000,%rdi
       │       mov    %rdi,%cr3
       │132:   pop    %rax
       │       pop    %rdi
       │       pop    %rsp
       │     → jmpq   *0x825d2d(%rip)        # ffffffff82225e88 <pv_cpu_ops+0xe8>

This all gets much better viewed if one uses 'perf report --ignore-vmlinux'
forcing the usage of /proc/kcore + /proc/kallsyms, when the above
actually gets down to:

  # perf report --ignore-vmlinux
  ## do '/64', will show the function names containing '64',
  ## navigate to /entry_SYSCALL_64_after_hwframe.annotation,
  ## press 'A' to annotate, then 'P' to print that annotation
  ## to a file
  ## From another xterm (or see on screen, this 'P' thing is for
  ## getting rid of those right side scroll bars/spaces):
  # cat /entry_SYSCALL_64_after_hwframe.annotation
  entry_SYSCALL_64_after_hwframe() /proc/kcore
  Event: cycles:ppp

  Percent
              Disassembly of section load0:

              ffffffff9aa00044 <load0>:
   11.97        push   %rax
    4.85        push   %rdi
                push   %rsi
    2.59        push   %rdx
    2.27        push   %rcx
    0.32        pushq  $0xffffffffffffffda
    1.29        push   %r8
                xor    %r8d,%r8d
    1.62        push   %r9
    0.65        xor    %r9d,%r9d
    1.62        push   %r10
                xor    %r10d,%r10d
    5.50        push   %r11
                xor    %r11d,%r11d
    3.56        push   %rbx
                xor    %ebx,%ebx
    4.21        push   %rbp
                xor    %ebp,%ebp
    2.59        push   %r12
    0.97        xor    %r12d,%r12d
    3.24        push   %r13
                xor    %r13d,%r13d
    2.27        push   %r14
                xor    %r14d,%r14d
    4.21        push   %r15
                xor    %r15d,%r15d
    0.97        mov    %rsp,%rdi
    5.50      → callq  do_syscall_64
   14.56        mov    0x58(%rsp),%rcx
    7.44        mov    0x80(%rsp),%r11
    0.32        cmp    %rcx,%r11
              → jne    swapgs_restore_regs_and_return_to_usermode
    0.32        shl    $0x10,%rcx
    0.32        sar    $0x10,%rcx
    3.24        cmp    %rcx,%r11
              → jne    swapgs_restore_regs_and_return_to_usermode
    2.27        cmpq   $0x33,0x88(%rsp)
    1.29      → jne    swapgs_restore_regs_and_return_to_usermode
                mov    0x30(%rsp),%r11
    8.74        cmp    %r11,0x90(%rsp)
              → jne    swapgs_restore_regs_and_return_to_usermode
    0.32        test   $0x10100,%r11
              → jne    swapgs_restore_regs_and_return_to_usermode
    0.32        cmpq   $0x2b,0xa0(%rsp)
    0.65      → jne    swapgs_restore_regs_and_return_to_usermode

I.e. using kallsyms makes the function start/end be done differently
than using what is in the vmlinux ELF symtab and actually the hits
goes to entry_SYSCALL_64_after_hwframe, which is a GLOBAL() after the
start of entry_SYSCALL_64:

  ENTRY(entry_SYSCALL_64)
          UNWIND_HINT_EMPTY
  <SNIP>
          pushq   $__USER_CS                      /* pt_regs->cs */
          pushq   %rcx                            /* pt_regs->ip */
  GLOBAL(entry_SYSCALL_64_after_hwframe)
          pushq   %rax                            /* pt_regs->orig_ax */

          PUSH_AND_CLEAR_REGS rax=$-ENOSYS

And it goes and ends at:

          cmpq    $__USER_DS, SS(%rsp)            /* SS must match SYSRET */
          jne     swapgs_restore_regs_and_return_to_usermode

          /*
           * We win! This label is here just for ease of understanding
           * perf profiles. Nothing jumps here.
           */
  syscall_return_via_sysret:
          /* rcx and r11 are already restored (see code above) */
          UNWIND_HINT_EMPTY
          POP_REGS pop_rdi=0 skip_r11rcx=1

So perhaps some people should really just play with '--ignore-vmlinux'
to force /proc/kcore + kallsyms.

One idea is to do both, i.e. have a vmlinux annotation and a
kcore+kallsyms one, when possible, and even show the patched location,
etc.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-r11knxv8voesav31xokjiuo6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

0 files changed, 0 insertions, 0 deletions