[roll] Roll fuchsia [kernel] Move per-CPU ktrace metadata record emission to boot CPU

Prior to this CL, the trace records containing the interned strings and
CPU koids were emitted on whatever CPU started tracing, not the boot
CPU. This led to situations in which strings were referenced before
the corresponding metadata record was seen. This worked in perfetto,
which can handle out of order records like this, but did not work
in the trace-reader userspace library, as that library needs to be
able to perform chunked reads. This CL fixes the issue by always
forcing the string refs to be emitted on the boot CPU.

Note that thread and process names are still emitted on whatever CPU
invokes ReportMetadata. This is fine because those records do not
need to be parsed before any other trace records.

Original-Bug: 404539312
Original-Reviewed-on: https://fuchsia-review.googlesource.com/c/fuchsia/+/1272990
Original-Revision: 83cc512916fd9ae9edb339bc1dd8ca2593476e2a
GitOrigin-RevId: 9388708405699544eb74f661b39c6ba5e8be5ce1
Change-Id: I65f11f5d2523db5ce1b1f741dd18236b5261fa2a
1 file changed
tree: 47ec16950bcafdfcaacc2e02cce2459b8769f3c9
  1. ctf/
  2. git-hooks/
  3. infra/
  4. third_party/
  5. flower
  6. jiri.lock
  7. MILESTONE
  8. minimal
  9. prebuilts
  10. README.md
  11. stem
  12. test_durations
README.md

Integration

This repository contains Fuchsia's Global Integration manifest files.

Making changes

All changes should be made to the internal version of this repository. Our infrastructure automatically updates this version when the internal one changes.

Currently all changes must be made by a Google employee. Non-Google employees wishing to make a change can ask for assistance in one of the communication channels documented at get involved.

Obtaining the source

First install Jiri.

Next run:

$ jiri init
$ jiri import minimal https://fuchsia.googlesource.com/integration
$ jiri update

Third party

Third party projects should have their own subdirectory in ./third_party.