Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1567772

Re: perf/jit doesn't cope well with mprotect() to jit containing pages

Show all headers | View raw

On 2017-01-26 14:26:12 -0800, Stephane Eranian wrote:
> On Thu, Jan 26, 2017 at 2:19 PM, Peter Zijlstra <peterz@infradead.org> wrote:
> > On Thu, Jan 26, 2017 at 01:00:52PM -0800, Andres Freund wrote:
> >> The problem is that (quoted below) without that hack the subsequent
> >> mmaps just expand the previous VMAs which leads to perf loosing its
> >> (address,range) -> symbol mappings for previously (in the same expanded
> >> range) known symbols.
> >
> > I'm assuming this is the userspace tool doing that, right?
> >
> > Acme, is that something we can cure? Instead of throwing away eveything
> > known of the previous map, merge them when they grow?
> >
> > So I think the problem was that we don't track munmap(), so if you see
> > two overlapping mappings, we have no clue and assume an munmap() has
> > happened or something. I can't really remember, its been many many years
> > since I wrote all that :-(
> 
> But perf report takes care of overlapping mmaps normally,
> see util/map.c:map_groups__fixup_overlappings
> 
> VMA merging does not change anything at the user level.
> The kernel will see two mmaps and so will perf record and perf report.

But the kernel *didn't* report two independent mmaps.

Looking at strace shows that the mmaps were done independently in page
sized chunks:

mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7efd3866e000
mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7efd3866d000
mprotect(0x7efd3866e000, 4096, PROT_READ|PROT_EXEC) = 0
mprotect(0x7efd3866d000, 4096, PROT_READ|PROT_EXEC) = 0
write(2, "Function loaded: evalexpr0 at 139626038091776 0x7efd3866e000 len 69", 68) = 68

(first function)

mmap(0x7efd3866f000, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7efd3866c000
mmap(0x7efd3866e000, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7efd3866b000
mprotect(0x7efd3866c000, 4096, PROT_READ|PROT_EXEC) = 0
mprotect(0x7efd3866b000, 4096, PROT_READ|PROT_EXEC) = 0
write(2, "Function loaded: evalexpr1 at 139626038083584 0x7efd3866c000 len 69", 68) = 68

(second function)


But then looking at the unannotated perf script --show-mmap-events:

postgres  4107 595444.867737: PERF_RECORD_MMAP2 4107/4107: [0x7efd3866e000(0x1000) @ 0x7efd3866e000 00:00 0 0]: ---p //anon
postgres  4107 595444.867825: PERF_RECORD_MMAP2 4107/4107: [0x7efd3866d000(0x2000) @ 0x7efd3866d000 00:00 0 0]: ---p //anon
postgres  4107 595444.884090: PERF_RECORD_MMAP2 4107/4107: [0x7efd3866c000(0x3000) @ 0x7efd3866c000 00:00 0 0]: ---p //anon
postgres  4107 595444.884113: PERF_RECORD_MMAP2 4107/4107: [0x7efd3866b000(0x4000) @ 0x7efd3866b000 00:00 0 0]: ---p //anon

these four mmaps regions are:
0x7efd3866e000(0x1000): 0x7efd3866e000 - 0x7efd3866f000
0x7efd3866d000(0x2000): 0x7efd3866d000 - 0x7efd3866f000
0x7efd3866c000(0x3000): 0x7efd3866c000 - 0x7efd3866f000
0x7efd3866b000(0x4000): 0x7efd3866b000 - 0x7efd3866f000

So there's just a single mapping being reported.


> This is what you have.

I'm a bit confused - isn't the trace showing exactly that the mmaps
*are* reported with a merged VMA?


> In the case of Java, if I recall, there is a single large mmap for the
> code cache and it works fine.

That explains why it's working there...

Greetings,

Andres Freund

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

Re: perf/jit doesn't cope well with mprotect() to jit containing pages Stephane Eranian <eranian@googlemail.com> - 2017-01-26 21:50 +0100
  Re: perf/jit doesn't cope well with mprotect() to jit containing  pages Andres Freund <andres@anarazel.de> - 2017-01-26 22:10 +0100
    Re: perf/jit doesn't cope well with mprotect() to jit containing pages Stephane Eranian <eranian@google.com> - 2017-01-26 22:20 +0100
      Re: perf/jit doesn't cope well with mprotect() to jit containing  pages Andres Freund <andres@anarazel.de> - 2017-01-26 22:30 +0100
        Re: perf/jit doesn't cope well with mprotect() to jit containing pages Stephane Eranian <eranian@google.com> - 2017-01-26 22:40 +0100
          Re: perf/jit doesn't cope well with mprotect() to jit containing  pages Andres Freund <andres@anarazel.de> - 2017-01-26 23:00 +0100
    Re: perf/jit doesn't cope well with mprotect() to jit containing  pages Peter Zijlstra <peterz@infradead.org> - 2017-01-26 23:20 +0100
      Re: perf/jit doesn't cope well with mprotect() to jit containing pages Stephane Eranian <eranian@google.com> - 2017-01-26 23:30 +0100
        Re: perf/jit doesn't cope well with mprotect() to jit containing  pages Andres Freund <andres@anarazel.de> - 2017-01-26 23:40 +0100
          Re: perf/jit doesn't cope well with mprotect() to jit containing pages Stephane Eranian <eranian@google.com> - 2017-01-27 00:00 +0100
            Re: perf/jit doesn't cope well with mprotect() to jit containing  pages Andres Freund <andres@anarazel.de> - 2017-01-27 00:20 +0100
              Re: perf/jit doesn't cope well with mprotect() to jit containing pages Stephane Eranian <eranian@google.com> - 2017-01-27 00:20 +0100
                Re: perf/jit doesn't cope well with mprotect() to jit containing  pages Peter Zijlstra <peterz@infradead.org> - 2017-01-27 14:10 +0100
                Re: perf/jit doesn't cope well with mprotect() to jit containing  pages Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-01-27 16:50 +0100
                Re: perf/jit doesn't cope well with mprotect() to jit containing pages Stephane Eranian <eranian@google.com> - 2017-01-27 18:40 +0100
                [PATCH] handle munmap records in tools/perf was: Re: perf/jit  doesn't cope well with mprotect() to jit containing pages Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-01-27 18:50 +0100
                Re: [PATCH] handle munmap records in tools/perf was: Re: perf/jit  doesn't cope well with mprotect() to jit containing pages Stephane Eranian <eranian@googlemail.com> - 2017-01-27 19:00 +0100
                Re: [PATCH] handle munmap records in tools/perf was: Re: perf/jit  doesn't cope well with mprotect() to jit containing pages Stephane Eranian <eranian@googlemail.com> - 2017-01-27 19:20 +0100
                Re: [PATCH] handle munmap records in tools/perf was: Re: perf/jit  doesn't cope well with mprotect() to jit containing pages Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-01-27 20:30 +0100
                Re: [PATCH] handle munmap records in tools/perf was: Re: perf/jit  doesn't cope well with mprotect() to jit containing pages Stephane Eranian <eranian@googlemail.com> - 2017-01-27 20:40 +0100
                Re: [PATCH] handle munmap records in tools/perf was: Re: perf/jit  doesn't cope well with mprotect() to jit containing pages Arnaldo Carvalho de Melo <acme@kernel.org> - 2017-01-27 19:40 +0100

csiph-web