Message-ID: <20200517195727.279322-1-andriin@fb.com>
Date:   Sun, 17 May 2020 12:57:20 -0700
From:   Andrii Nakryiko <andriin@...com>
To:     <bpf@...r.kernel.org>, <netdev@...r.kernel.org>, <ast@...com>,
        <daniel@...earbox.net>
CC:     <andrii.nakryiko@...il.com>, <kernel-team@...com>,
        Andrii Nakryiko <andriin@...com>,
        "Paul E . McKenney" <paulmck@...nel.org>,
        Jonathan Lemon <jonathan.lemon@...il.com>
Subject: [PATCH v2 bpf-next 0/7] BPF ring buffer

Implement a new BPF ring buffer, as presented at BPF virtual conference ([0]).
It presents an alternative to perf buffer, following its semantics closely,
but allowing sharing same instance of ring buffer across multiple CPUs
efficiently.

Most patches have extensive commentary explaining various aspects, so I'll
keep cover letter short. Overall structure of the patch set:
- patch #1 adds BPF ring buffer implementation to kernel and necessary
  verifier support;
- patch #2 adds litmus tests validating all the memory orderings and locking
  is correct;
- patch #3 is an optional patch that generalizes verifier's reference tracking
  machinery to capture type of reference;
- patch #4 adds libbpf consumer implementation for BPF ringbuf;
- path #5 adds selftest, both for single BPF ring buf use case, as well as
  using it with array/hash of maps;
- patch #6 adds extensive benchmarks and provide some analysis in commit
  message, it build upon selftests/bpf's bench runner.
- patch #7 adds most of patch #1 commit message as a doc under
  Documentation/bpf/ringbuf.txt.

  [0] https://docs.google.com/presentation/d/18ITdg77Bj6YDOH2LghxrnFxiPWe0fAqcmJY95t_qr0w

v1->v2:
- commit()/discard()/output() accept flags (NO_WAKEUP/FORCE_WAKEUP) (Stanislav);
- bpf_ringbuf_query() added, returning available data size, ringbuf size,
  consumer/producer positions, needed to implement smarter notification policy
  (Stanislav);
- added ringbuf UAPI constants to include/uapi/linux/bpf.h (Jonathan);
- fixed sample size check, added proper ringbuf size check (Jonathan, Alexei);
- wake_up_all() is done through irq_work (Alexei);
- consistent use of smp_load_acquire/smp_store_release, no
  READ_ONCE/WRITE_ONCE (Alexei);
- added Documentation/bpf/ringbuf.txt (Stanislav);
- updated litmus test with smp_load_acquire/smp_store_release changes;
- added ring_buffer__consume() API to libbpf for busy-polling;
- ring_buffer__poll() on success returns number of records consumed;
- fixed EPOLL notifications, don't assume available data, done similarly to
  perfbuf's implementation;
- both ringbuf and perfbuf now have --rb-sampled mode, instead of
  pb-raw/pb-custom mode, updated benchmark results;
- extended ringbuf selftests to validate epoll logic/manual notification
  logic, as well as bpf_ringbuf_query().

Cc: Paul E. McKenney <paulmck@...nel.org>
Cc: Jonathan Lemon <jonathan.lemon@...il.com>

Andrii Nakryiko (7):
  bpf: implement BPF ring buffer and verifier support for it
  tools/memory-model: add BPF ringbuf MPSC litmus tests
  bpf: track reference type in verifier
  libbpf: add BPF ring buffer support
  selftests/bpf: add BPF ringbuf selftests
  bpf: add BPF ringbuf and perf buffer benchmarks
  docs/bpf: add BPF ring buffer design notes

 Documentation/bpf/ringbuf.txt                 | 191 ++++++
 include/linux/bpf.h                           |  13 +
 include/linux/bpf_types.h                     |   1 +
 include/linux/bpf_verifier.h                  |  12 +
 include/uapi/linux/bpf.h                      |  84 ++-
 kernel/bpf/Makefile                           |   2 +-
 kernel/bpf/helpers.c                          |  10 +
 kernel/bpf/ringbuf.c                          | 487 +++++++++++++++
 kernel/bpf/syscall.c                          |  12 +
 kernel/bpf/verifier.c                         | 253 ++++++--
 kernel/trace/bpf_trace.c                      |  10 +
 tools/include/uapi/linux/bpf.h                |  90 ++-
 tools/lib/bpf/Build                           |   2 +-
 tools/lib/bpf/libbpf.h                        |  21 +
 tools/lib/bpf/libbpf.map                      |   5 +
 tools/lib/bpf/libbpf_probes.c                 |   5 +
 tools/lib/bpf/ringbuf.c                       | 285 +++++++++
 .../litmus-tests/mpsc-rb+1p1c+bounded.litmus  |  92 +++
 .../litmus-tests/mpsc-rb+1p1c+unbound.litmus  |  83 +++
 .../litmus-tests/mpsc-rb+2p1c+bounded.litmus  | 152 +++++
 .../litmus-tests/mpsc-rb+2p1c+unbound.litmus  | 137 +++++
 tools/testing/selftests/bpf/Makefile          |   5 +-
 tools/testing/selftests/bpf/bench.c           |  16 +
 .../selftests/bpf/benchs/bench_ringbufs.c     | 566 ++++++++++++++++++
 .../bpf/benchs/run_bench_ringbufs.sh          |  75 +++
 .../selftests/bpf/prog_tests/ringbuf.c        | 211 +++++++
 .../selftests/bpf/prog_tests/ringbuf_multi.c  | 102 ++++
 .../selftests/bpf/progs/perfbuf_bench.c       |  33 +
 .../selftests/bpf/progs/ringbuf_bench.c       |  60 ++
 .../selftests/bpf/progs/test_ringbuf.c        |  78 +++
 .../selftests/bpf/progs/test_ringbuf_multi.c  |  77 +++
 31 files changed, 3112 insertions(+), 58 deletions(-)
 create mode 100644 Documentation/bpf/ringbuf.txt
 create mode 100644 kernel/bpf/ringbuf.c
 create mode 100644 tools/lib/bpf/ringbuf.c
 create mode 100644 tools/memory-model/litmus-tests/mpsc-rb+1p1c+bounded.litmus
 create mode 100644 tools/memory-model/litmus-tests/mpsc-rb+1p1c+unbound.litmus
 create mode 100644 tools/memory-model/litmus-tests/mpsc-rb+2p1c+bounded.litmus
 create mode 100644 tools/memory-model/litmus-tests/mpsc-rb+2p1c+unbound.litmus
 create mode 100644 tools/testing/selftests/bpf/benchs/bench_ringbufs.c
 create mode 100755 tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
 create mode 100644 tools/testing/selftests/bpf/prog_tests/ringbuf.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
 create mode 100644 tools/testing/selftests/bpf/progs/perfbuf_bench.c
 create mode 100644 tools/testing/selftests/bpf/progs/ringbuf_bench.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_ringbuf.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_ringbuf_multi.c

-- 
2.24.1

Powered by blists - more mailing lists