Commit graph

2 commits

Author SHA1 Message Date
Ryan Savitski
008465e5ec traced_perf sepolicy tweaks
* allow shell to enable/disable the daemon via a sysprop
* don't audit signals, as some denials are expected
* exclude zygote from the profileable set of targets on debug builds.
  I've not caught any crashes in practice, but believe there's a
  possibility that the zygote forks while holding a non-whitelisted fd
  due to the signal handler.

Change-Id: Ib237d4edfb40b200a3bd52e6341f13c4777de3f1
2020-02-24 12:23:13 +00:00
Ryan Savitski
67a82481f8 initial policy for traced_perf daemon (perf profiler)
The steps involved in setting up profiling and stack unwinding are
described in detail at go/perfetto-perf-android.

To summarize the interesting case: the daemon uses cpu-wide
perf_event_open, with userspace stack and register sampling on. For each
sample, it identifies whether the process is profileable, and obtains
the FDs for /proc/[pid]/{maps,mem} using a dedicated RT signal (with the
bionic signal handler handing over the FDs over a dedicated socket). It
then uses libunwindstack to unwind & symbolize the stacks, sending the
results to the central tracing daemon (traced).

This patch covers the app profiling use-cases. Splitting out the
"profile most things on debug builds" into a separate patch for easier
review.

Most of the exceptions in domain.te & coredomain.te come from the
"vendor_file_type" allow-rule. We want a subset of that (effectively all
libraries/executables), but I believe that in practice it's hard to use
just the specific subtypes, and we're better off allowing access to all
vendor_file_type files.

Bug: 137092007
Change-Id: I4aa482cfb3f9fb2fabf02e1dff92e2b5ce121a47
2020-01-22 22:04:01 +00:00