Skip to content

L
linux
Switch branch/tag
  1. 17 Sep, 2021 8 commits
  3. 15 Sep, 2021 17 commits
  5. 14 Sep, 2021 6 commits
  7. 13 Sep, 2021 6 commits
    • Andrii Nakryiko's avatar
      libbpf: Make libbpf_version.h non-auto-generated · 2f383041
      Andrii Nakryiko authored 
      Turn previously auto-generated libbpf_version.h header into a normal
header file. This prevents various tricky Makefile integration issues,
simplifies the overall build process, but also allows to further extend
it with some more versioning-related APIs in the future.

To prevent accidental out-of-sync versions as defined by libbpf.map and
libbpf_version.h, Makefile checks their consistency at build time.

Simultaneously with this change bump libbpf.map to v0.6.

Also undo adding libbpf's output directory into include path for
kernel/bpf/preload, bpftool, and resolve_btfids, which is not necessary
because libbpf_version.h is just a normal header like any other.

Fixes: 0b46b755 ("libbpf: Add LIBBPF_DEPRECATED_SINCE macro for scheduling API deprecations")
Signed-off-by: default avatarAndrii Nakryiko <andrii@kernel.org>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210913222309.3220849-1-andrii@kernel.org
      2f383041
    • Daniel Borkmann's avatar
      bpf, selftests: Replicate tailcall limit test for indirect call case · dbd7eb14
      Daniel Borkmann authored 
      The tailcall_3 test program uses bpf_tail_call_static() where the JIT
would patch a direct jump. Add a new tailcall_6 test program replicating
exactly the same test just ensuring that bpf_tail_call() uses a map
index where the verifier cannot make assumptions this time.

In other words, this will now cover both on x86-64 JIT, meaning, JIT
images with emit_bpf_tail_call_direct() emission as well as JIT images
with emit_bpf_tail_call_indirect() emission.

  # echo 1 > /proc/sys/net/core/bpf_jit_enable
  # ./test_progs -t tailcalls
  #136/1 tailcalls/tailcall_1:OK
  #136/2 tailcalls/tailcall_2:OK
  #136/3 tailcalls/tailcall_3:OK
  #136/4 tailcalls/tailcall_4:OK
  #136/5 tailcalls/tailcall_5:OK
  #136/6 tailcalls/tailcall_6:OK
  #136/7 tailcalls/tailcall_bpf2bpf_1:OK
  #136/8 tailcalls/tailcall_bpf2bpf_2:OK
  #136/9 tailcalls/tailcall_bpf2bpf_3:OK
  #136/10 tailcalls/tailcall_bpf2bpf_4:OK
  #136/11 tailcalls/tailcall_bpf2bpf_5:OK
  #136 tailcalls:OK
  Summary: 1/11 PASSED, 0 SKIPPED, 0 FAILED

  # echo 0 > /proc/sys/net/core/bpf_jit_enable
  # ./test_progs -t tailcalls
  #136/1 tailcalls/tailcall_1:OK
  #136/2 tailcalls/tailcall_2:OK
  #136/3 tailcalls/tailcall_3:OK
  #136/4 tailcalls/tailcall_4:OK
  #136/5 tailcalls/tailcall_5:OK
  #136/6 tailcalls/tailcall_6:OK
  [...]

For interpreter, the tailcall_1-6 tests are passing as well. The later
tailcall_bpf2bpf_* are failing due lack of bpf2bpf + tailcall support
in interpreter, so this is expected.

Also, manual inspection shows that both loaded programs from tailcall_3
and tailcall_6 test case emit the expected opcodes:

* tailcall_3 disasm, emit_bpf_tail_call_direct():

  [...]
   b:   push   %rax
   c:   push   %rbx
   d:   push   %r13
   f:   mov    %rdi,%rbx
  12:   movabs $0xffff8d3f5afb0200,%r13
  1c:   mov    %rbx,%rdi
  1f:   mov    %r13,%rsi
  22:   xor    %edx,%edx                 _
  24:   mov    -0x4(%rbp),%eax          |  limit check
  2a:   cmp    $0x20,%eax               |
  2d:   ja     0x0000000000000046       |
  2f:   add    $0x1,%eax                |
  32:   mov    %eax,-0x4(%rbp)          |_
  38:   nopl   0x0(%rax,%rax,1)
  3d:   pop    %r13
  3f:   pop    %rbx
  40:   pop    %rax
  41:   jmpq   0xffffffffffffe377
  [...]

* tailcall_6 disasm, emit_bpf_tail_call_indirect():

  [...]
  47:   movabs $0xffff8d3f59143a00,%rsi
  51:   mov    %edx,%edx
  53:   cmp    %edx,0x24(%rsi)
  56:   jbe    0x0000000000000093        _
  58:   mov    -0x4(%rbp),%eax          |  limit check
  5e:   cmp    $0x20,%eax               |
  61:   ja     0x0000000000000093       |
  63:   add    $0x1,%eax                |
  66:   mov    %eax,-0x4(%rbp)          |_
  6c:   mov    0x110(%rsi,%rdx,8),%rcx
  74:   test   %rcx,%rcx
  77:   je     0x0000000000000093
  79:   pop    %rax
  7a:   mov    0x30(%rcx),%rcx
  7e:   add    $0xb,%rcx
  82:   callq  0x000000000000008e
  87:   pause
  89:   lfence
  8c:   jmp    0x0000000000000087
  8e:   mov    %rcx,(%rsp)
  92:   retq
  [...]
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
Tested-by: default avatarTiezhu Yang <yangtiezhu@loongson.cn>
Acked-by: default avatarYonghong Song <yhs@fb.com>
Acked-by: default avatarJohan Almbladh <johan.almbladh@anyfinetworks.com>
Acked-by: default avatarPaul Chaignon <paul@cilium.io>
Link: https://lore.kernel.org/bpf/CAM1=_QRyRVCODcXo_Y6qOm1iT163HoiSj8U2pZ8Rj3hzMTT=HQ@mail.gmail.com
Link: https://lore.kernel.org/bpf/20210910091900.16119-1-daniel@iogearbox.net
      dbd7eb14
    • Alexei Starovoitov's avatar
      Merge branch 'bpf: introduce bpf_get_branch_snapshot' · 14bef1ab
      Alexei Starovoitov authored 
      Song Liu says:

====================

Changes v6 => v7:
1. Improve/fix intel_pmu_snapshot_branch_stack() logic. (Peter).

Changes v5 => v6:
1. Add local_irq_save/restore to intel_pmu_snapshot_branch_stack. (Peter)
2. Remove buf and size check in bpf_get_branch_snapshot, move flags check
   to later fo the function. (Peter, Andrii)
3. Revise comments for bpf_get_branch_snapshot in bpf.h (Andrii)

Changes v4 => v5:
1. Modify perf_snapshot_branch_stack_t to save some memcpy. (Andrii)
2. Minor fixes in selftests. (Andrii)

Changes v3 => v4:
1. Do not reshuffle intel_pmu_disable_all(). Use some inline to save LBR
   entries. (Peter)
2. Move static_call(perf_snapshot_branch_stack) to the helper. (Alexei)
3. Add argument flags to bpf_get_branch_snapshot. (Andrii)
4. Make MAX_BRANCH_SNAPSHOT an enum (Andrii). And rename it as
   PERF_MAX_BRANCH_SNAPSHOT
5. Make bpf_get_branch_snapshot similar to bpf_read_branch_records.
   (Andrii)
6. Move the test target function to bpf_testmod. Updated kallsyms_find_next
   to work properly with modules. (Andrii)

Changes v2 => v3:
1. Fix the use of static_call. (Peter)
2. Limit the use to perfmon version >= 2. (Peter)
3. Modify intel_pmu_snapshot_branch_stack() to use intel_pmu_disable_all
   and intel_pmu_enable_all().

Changes v1 => v2:
1. Rename the helper as bpf_get_branch_snapshot;
2. Fix/simplify the use of static_call;
3. Instead of percpu variables, let intel_pmu_snapshot_branch_stack output
   branch records to an output argument of type perf_branch_snapshot.

Branch stack can be very useful in understanding software events. For
example, when a long function, e.g. sys_perf_event_open, returns an errno,
it is not obvious why the function failed. Branch stack could provide very
helpful information in this type of scenarios.

This set adds support to read branch stack with a new BPF helper
bpf_get_branch_trace(). Currently, this is only supported in Intel systems.
It is also possible to support the same feaure for PowerPC.

The hardware that records the branch stace is not stopped automatically on
software events. Therefore, it is necessary to stop it in software soon.
Otherwise, the hardware buffers/registers will be flushed. One of the key
design consideration in this set is to minimize the number of branch record
entries between the event triggers and the hardware recorder is stopped.
Based on this goal, current design is different from the discussions in
original RFC [1]:
 1) Static call is used when supported, to save function pointer
    dereference;
 2) intel_pmu_lbr_disable_all is used instead of perf_pmu_disable(),
    because the latter uses about 10 entries before stopping LBR.

With current code, on Intel CPU, LBR is stopped after 7 branch entries
after fexit triggers:

ID: 0 from bpf_get_branch_snapshot+18 to intel_pmu_snapshot_branch_stack+0
ID: 1 from __brk_limit+477143934 to bpf_get_branch_snapshot+0
ID: 2 from __brk_limit+477192263 to __brk_limit+477143880  # trampoline
ID: 3 from __bpf_prog_enter+34 to __brk_limit+477192251
ID: 4 from migrate_disable+60 to __bpf_prog_enter+9
ID: 5 from __bpf_prog_enter+4 to migrate_disable+0
ID: 6 from bpf_testmod_loop_test+20 to __bpf_prog_enter+0
ID: 7 from bpf_testmod_loop_test+20 to bpf_testmod_loop_test+13
ID: 8 from bpf_testmod_loop_test+20 to bpf_testmod_loop_test+13
...

[1] https://lore.kernel.org/bpf/20210818012937.2522409-1-songliubraving@fb.com/
====================
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
      14bef1ab
    • Song Liu's avatar
      selftests/bpf: Add test for bpf_get_branch_snapshot · 025bd7c7
      Song Liu authored 
      This test uses bpf_get_branch_snapshot from a fexit program. The test uses
a target function (bpf_testmod_loop_test) and compares the record against
kallsyms. If there isn't enough record matching kallsyms, the test fails.
Signed-off-by: default avatarSong Liu <songliubraving@fb.com>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
Acked-by: default avatarAndrii Nakryiko <andrii@kernel.org>
Acked-by: default avatarJohn Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210910183352.3151445-4-songliubraving@fb.com
      025bd7c7
    • Song Liu's avatar
      bpf: Introduce helper bpf_get_branch_snapshot · 856c02db
      Song Liu authored 
      Introduce bpf_get_branch_snapshot(), which allows tracing pogram to get
branch trace from hardware (e.g. Intel LBR). To use the feature, the
user need to create perf_event with proper branch_record filtering
on each cpu, and then calls bpf_get_branch_snapshot in the bpf function.
On Intel CPUs, VLBR event (raw event 0x1b00) can be use for this.
Signed-off-by: default avatarSong Liu <songliubraving@fb.com>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
Acked-by: default avatarJohn Fastabend <john.fastabend@gmail.com>
Acked-by: default avatarAndrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210910183352.3151445-3-songliubraving@fb.com
      856c02db
    • Song Liu's avatar
      perf: Enable branch record for software events · c22ac2a3
      Song Liu authored 
      The typical way to access branch record (e.g. Intel LBR) is via hardware
perf_event. For CPUs with FREEZE_LBRS_ON_PMI support, PMI could capture
reliable LBR. On the other hand, LBR could also be useful in non-PMI
scenario. For example, in kretprobe or bpf fexit program, LBR could
provide a lot of information on what happened with the function. Add API
to use branch record for software use.

Note that, when the software event triggers, it is necessary to stop the
branch record hardware asap. Therefore, static_call is used to remove some
branch instructions in this process.
Suggested-by: default avatarPeter Zijlstra <peterz@infradead.org>
Signed-off-by: default avatarSong Liu <songliubraving@fb.com>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
Acked-by: default avatarJohn Fastabend <john.fastabend@gmail.com>
Acked-by: default avatarAndrii Nakryiko <andrii@kernel.org>
Acked-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/bpf/20210910183352.3151445-2-songliubraving@fb.com
      c22ac2a3
  9. 10 Sep, 2021 3 commits
    • Vadim Fedorenko's avatar
      selftests/bpf: Test new __sk_buff field hwtstamp · 3384c7c7
      Vadim Fedorenko authored 
      Analogous to the gso_segs selftests introduced in commit d9ff286a
("bpf: allow BPF programs access skb_shared_info->gso_segs field").
Signed-off-by: default avatarVadim Fedorenko <vfedorenko@novek.ru>
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
Acked-by: default avatarMartin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210909220409.8804-3-vfedorenko@novek.ru
      3384c7c7
    • Vadim Fedorenko's avatar
      bpf: Add hardware timestamp field to __sk_buff · f64c4ace
      Vadim Fedorenko authored 
      BPF programs may want to know hardware timestamps if NIC supports
such timestamping.

Expose this data as hwtstamp field of __sk_buff the same way as
gso_segs/gso_size. This field could be accessed from the same
programs as tstamp field, but it's read-only field. Explicit test
to deny access to padding data is added to bpf_skb_is_valid_access.

Also update BPF_PROG_TEST_RUN tests of the feature.
Signed-off-by: default avatarVadim Fedorenko <vfedorenko@novek.ru>
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
Acked-by: default avatarMartin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210909220409.8804-2-vfedorenko@novek.ru
      f64c4ace
    • Daniel Borkmann's avatar
      Merge branch 'bpf-xsk-selftests' · e876a036
      Daniel Borkmann authored 
      Magnus Karlsson says:

====================
This patch set facilitates adding new tests as well as describing
existing ones in the xsk selftests suite and adds 3 new test suites at
the end. The idea is to isolate the run-time that executes the test
from the actual implementation of the test. Today, implementing a test
amounts to adding test specific if-statements all around the run-time,
which is not scalable or amenable for reuse. This patch set instead
introduces a test specification that is the only thing that a test
fills in. The run-time then gets this specification and acts upon it
completely unaware of what test it is executing. This way, we can get
rid of all test specific if-statements from the run-time and the
implementation of the test can be contained in a single function. This
hopefully makes it easier to add tests and for users to understand
what the test accomplishes.

As a recap of what the run-time does: each test is based on the
run-time launching two threads and connecting a veth link between the
two threads. Each thread opens an AF_XDP socket on that veth interface
and one of them sends traffic that the other one receives and
validates. Each thread has its own umem. Note that this behavior is
not changed by this patch set.

A test specification consists of several items. Most importantly:

* Two packet streams. One for Tx thread that specifies what traffic to
  send and one for the Rx thread that specifies what that thread
  should receive. If it receives exactly what is specified, the test
  passes, otherwise it fails. A packet stream can also specify what
  buffers in the umem that should be used by the Rx and Tx threads.

* What kind of AF_XDP sockets it should create and bind to what
  interfaces

* How many times it should repeat the socket creation and destruction

* The name of the test

The interface for the test spec is the following:

void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
                    struct ifobject *ifobj_rx, enum test_mode mode);

/* Reset everything but the interface specifications and the mode */
void test_spec_reset(struct test_spec *test);

void test_spec_set_name(struct test_spec *test, const char *name);

Packet streams have the following interfaces:

struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb)

struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream)

struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem,
                                       u32 nb_pkts, u32 pkt_len);

void pkt_stream_delete(struct pkt_stream *pkt_stream);

struct pkt_stream *pkt_stream_clone(struct xsk_umem_info *umem,
                                    struct pkt_stream *pkt_stream);

/* Replaces all packets in the stream*/
void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len);

/* Replaces every other packet in the stream */
void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, u32 offset);

/* For creating custom made packet streams */
void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts,
                                u32 nb_pkts);

/* Restores the default packet stream */
void pkt_stream_restore_default(struct test_spec *test);

A test can then then in the most basic case described like this
(provided the test specification has been created before calling the
function):

static bool testapp_aligned(struct test_spec *test)
{
        test_spec_set_name(test, "RUN_TO_COMPLETION");
        testapp_validate_traffic(test);
}

Running the same test in unaligned mode would then look like this:

static bool testapp_unaligned(struct test_spec *test)
{
        if (!hugepages_present(test->ifobj_tx)) {
                ksft_test_result_skip("No 2M huge pages present.\n");
                return false;
        }

        test_spec_set_name(test, "UNALIGNED_MODE");
        test->ifobj_tx->umem->unaligned_mode = true;
        test->ifobj_rx->umem->unaligned_mode = true;
        /* Let half of the packets straddle a buffer boundrary */
        pkt_stream_replace_half(test, PKT_SIZE,
                                XSK_UMEM__DEFAULT_FRAME_SIZE - 32);
	/* Populate fill ring with addresses in the packet stream */
        test->ifobj_rx->pkt_stream->use_addr_for_fill = true;
        testapp_validate_traffic(test);

        pkt_stream_restore_default(test);
	return true;
}

3 of the last 4 patches in the set add 3 new test suites, one for
unaligned mode, one for testing the rejection of tricky invalid
descriptors plus the acceptance of some valid ones in the Tx ring, and
one for testing 2K frame sizes (the default is 4K).

What is left to do for follow-up patches:

* Convert the statistics tests to the new framework.

* Implement a way of registering new tests without having the enum
  test_type. Once this has been done (together with the previous
  bullet), all the test types can be dropped from the header
  file. This means that we should be able to add tests by just writing
  a single function with a new test specification, which is one of the
  goals.

* Introduce functions for manipulating parts of the test or interface
  spec instead of direct manipulations such as
  test->ifobj_rx->pkt_stream->use_addr_for_fill = true; which is kind
  of awkward.

* Move the run-time and its interface to its own .c and .h files. Then
  we can have all the tests in a separate file.

* Better error reporting if a test fails. Today it does not state what
  test fails and might not continue execute the rest of the tests due
  to this failure. Failures are not propagated upwards through the
  functions so a failed test will also be a passed test, which messes
  up the stats counting. This needs to be changed.

* Add option to run specific test instead of all of them

* Introduce pacing of sent packets so that they are never dropped
  by the receiver even if it is stalled for some reason. If you run
  the current tests on a heavily loaded system, they might fail in SKB
  mode due to packets being dropped by the driver on Tx. Though I have
  never seen it, it might happen.

v1 -> v2:

* Fixed a number of spelling errors [Maciej]
* Fixed use after free bug in pkt_stream_replace() [Maciej]
* pkt_stream_set -> pkt_stream_generate_custom [Maciej]
* Fixed formatting problem in testapp_invalid_desc() [Maciej]
====================
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
      e876a036
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7