Fix definition of bpf_ringbuf_output() in UAPI header comments, which is used
to generate libbpf's bpf_helper_defs.h header. Return value is a number (error
code), not a pointer.
Fixes: 457f44363a88 ("bpf: Implement BPF ring buffer and verifier support for it")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200615214926.3638836-1-andriin@fb.com
Remove invalid assumption in libbpf that .bss map doesn't have to be updated
in kernel. With addition of skeleton and memory-mapped initialization image,
.bss doesn't have to be all zeroes when BPF map is created, because user-code
might have initialized those variables from user-space.
Fixes: eba9c5f498a1 ("libbpf: Refactor global data map initialization")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200612194504.557844-1-andriin@fb.com
Initial versions of sync script couldn't handle non-empty merges. But since
then, script became smarter, more interactive and thus more powerful and can
handle some complicated situations easily on its own, while falling back to
human intervention for even more complicated situations. This non-empty merge
check has outlived its purpose and is just an annoying bump in sync process.
Drop it.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Handle a GCC quirk of emitting extra volatile modifier in DWARF (and
subsequently preserved in BTF by pahole) for function pointers marked as
__attribute__((noreturn)). This was the way to mark such functions before GCC
2.5 added noreturn attribute. Drop such func_proto modifiers, similarly to how
it's done for array (also to handle GCC quirk/bug).
Such volatile attribute is emitted by GCC only, so existing selftests can't
express such test. Simple repro is like this (compiled with GCC + BTF
generated by pahole):
struct my_struct {
void __attribute__((noreturn)) (*fn)(int);
};
struct my_struct a;
Without this fix, output will be:
struct my_struct {
voidvolatile (*fn)(int);
};
With the fix:
struct my_struct {
void (*fn)(int);
};
Fixes: 351131b51c7a ("libbpf: add btf_dump API for BTF-to-C conversion")
Reported-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Link: https://lore.kernel.org/bpf/20200610052335.2862559-1-andriin@fb.com
Declaring and instantiating BPF ring buffer doesn't require any changes to
libbpf, as it's just another type of maps. So using existing BTF-defined maps
syntax with __uint(type, BPF_MAP_TYPE_RINGBUF) and __uint(max_elements,
<size-of-ring-buf>) is all that's necessary to create and use BPF ring buffer.
This patch adds BPF ring buffer consumer to libbpf. It is very similar to
perf_buffer implementation in terms of API, but also attempts to fix some
minor problems and inconveniences with existing perf_buffer API.
ring_buffer support both single ring buffer use case (with just using
ring_buffer__new()), as well as allows to add more ring buffers, each with its
own callback and context. This allows to efficiently poll and consume
multiple, potentially completely independent, ring buffers, using single
epoll instance.
The latter is actually a problem in practice for applications
that are using multiple sets of perf buffers. They have to create multiple
instances for struct perf_buffer and poll them independently or in a loop,
each approach having its own problems (e.g., inability to use a common poll
timeout). struct ring_buffer eliminates this problem by aggregating many
independent ring buffer instances under the single "ring buffer manager".
Second, perf_buffer's callback can't return error, so applications that need
to stop polling due to error in data or data signalling the end, have to use
extra mechanisms to signal that polling has to stop. ring_buffer's callback
can return error, which will be passed through back to user code and can be
acted upon appropariately.
Two APIs allow to consume ring buffer data:
- ring_buffer__poll(), which will wait for data availability notification
and will consume data only from reported ring buffer(s); this API allows
to efficiently use resources by reading data only when it becomes
available;
- ring_buffer__consume(), will attempt to read new records regardless of
data availablity notification sub-system. This API is useful for cases
when lowest latency is required, in expense of burning CPU resources.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200529075424.3139988-3-andriin@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This commit adds a new MPSC ring buffer implementation into BPF ecosystem,
which allows multiple CPUs to submit data to a single shared ring buffer. On
the consumption side, only single consumer is assumed.
Motivation
----------
There are two distinctive motivators for this work, which are not satisfied by
existing perf buffer, which prompted creation of a new ring buffer
implementation.
- more efficient memory utilization by sharing ring buffer across CPUs;
- preserving ordering of events that happen sequentially in time, even
across multiple CPUs (e.g., fork/exec/exit events for a task).
These two problems are independent, but perf buffer fails to satisfy both.
Both are a result of a choice to have per-CPU perf ring buffer. Both can be
also solved by having an MPSC implementation of ring buffer. The ordering
problem could technically be solved for perf buffer with some in-kernel
counting, but given the first one requires an MPSC buffer, the same solution
would solve the second problem automatically.
Semantics and APIs
------------------
Single ring buffer is presented to BPF programs as an instance of BPF map of
type BPF_MAP_TYPE_RINGBUF. Two other alternatives considered, but ultimately
rejected.
One way would be to, similar to BPF_MAP_TYPE_PERF_EVENT_ARRAY, make
BPF_MAP_TYPE_RINGBUF could represent an array of ring buffers, but not enforce
"same CPU only" rule. This would be more familiar interface compatible with
existing perf buffer use in BPF, but would fail if application needed more
advanced logic to lookup ring buffer by arbitrary key. HASH_OF_MAPS addresses
this with current approach. Additionally, given the performance of BPF
ringbuf, many use cases would just opt into a simple single ring buffer shared
among all CPUs, for which current approach would be an overkill.
Another approach could introduce a new concept, alongside BPF map, to
represent generic "container" object, which doesn't necessarily have key/value
interface with lookup/update/delete operations. This approach would add a lot
of extra infrastructure that has to be built for observability and verifier
support. It would also add another concept that BPF developers would have to
familiarize themselves with, new syntax in libbpf, etc. But then would really
provide no additional benefits over the approach of using a map.
BPF_MAP_TYPE_RINGBUF doesn't support lookup/update/delete operations, but so
doesn't few other map types (e.g., queue and stack; array doesn't support
delete, etc).
The approach chosen has an advantage of re-using existing BPF map
infrastructure (introspection APIs in kernel, libbpf support, etc), being
familiar concept (no need to teach users a new type of object in BPF program),
and utilizing existing tooling (bpftool). For common scenario of using
a single ring buffer for all CPUs, it's as simple and straightforward, as
would be with a dedicated "container" object. On the other hand, by being
a map, it can be combined with ARRAY_OF_MAPS and HASH_OF_MAPS map-in-maps to
implement a wide variety of topologies, from one ring buffer for each CPU
(e.g., as a replacement for perf buffer use cases), to a complicated
application hashing/sharding of ring buffers (e.g., having a small pool of
ring buffers with hashed task's tgid being a look up key to preserve order,
but reduce contention).
Key and value sizes are enforced to be zero. max_entries is used to specify
the size of ring buffer and has to be a power of 2 value.
There are a bunch of similarities between perf buffer
(BPF_MAP_TYPE_PERF_EVENT_ARRAY) and new BPF ring buffer semantics:
- variable-length records;
- if there is no more space left in ring buffer, reservation fails, no
blocking;
- memory-mappable data area for user-space applications for ease of
consumption and high performance;
- epoll notifications for new incoming data;
- but still the ability to do busy polling for new data to achieve the
lowest latency, if necessary.
BPF ringbuf provides two sets of APIs to BPF programs:
- bpf_ringbuf_output() allows to *copy* data from one place to a ring
buffer, similarly to bpf_perf_event_output();
- bpf_ringbuf_reserve()/bpf_ringbuf_commit()/bpf_ringbuf_discard() APIs
split the whole process into two steps. First, a fixed amount of space is
reserved. If successful, a pointer to a data inside ring buffer data area
is returned, which BPF programs can use similarly to a data inside
array/hash maps. Once ready, this piece of memory is either committed or
discarded. Discard is similar to commit, but makes consumer ignore the
record.
bpf_ringbuf_output() has disadvantage of incurring extra memory copy, because
record has to be prepared in some other place first. But it allows to submit
records of the length that's not known to verifier beforehand. It also closely
matches bpf_perf_event_output(), so will simplify migration significantly.
bpf_ringbuf_reserve() avoids the extra copy of memory by providing a memory
pointer directly to ring buffer memory. In a lot of cases records are larger
than BPF stack space allows, so many programs have use extra per-CPU array as
a temporary heap for preparing sample. bpf_ringbuf_reserve() avoid this needs
completely. But in exchange, it only allows a known constant size of memory to
be reserved, such that verifier can verify that BPF program can't access
memory outside its reserved record space. bpf_ringbuf_output(), while slightly
slower due to extra memory copy, covers some use cases that are not suitable
for bpf_ringbuf_reserve().
The difference between commit and discard is very small. Discard just marks
a record as discarded, and such records are supposed to be ignored by consumer
code. Discard is useful for some advanced use-cases, such as ensuring
all-or-nothing multi-record submission, or emulating temporary malloc()/free()
within single BPF program invocation.
Each reserved record is tracked by verifier through existing
reference-tracking logic, similar to socket ref-tracking. It is thus
impossible to reserve a record, but forget to submit (or discard) it.
bpf_ringbuf_query() helper allows to query various properties of ring buffer.
Currently 4 are supported:
- BPF_RB_AVAIL_DATA returns amount of unconsumed data in ring buffer;
- BPF_RB_RING_SIZE returns the size of ring buffer;
- BPF_RB_CONS_POS/BPF_RB_PROD_POS returns current logical possition of
consumer/producer, respectively.
Returned values are momentarily snapshots of ring buffer state and could be
off by the time helper returns, so this should be used only for
debugging/reporting reasons or for implementing various heuristics, that take
into account highly-changeable nature of some of those characteristics.
One such heuristic might involve more fine-grained control over poll/epoll
notifications about new data availability in ring buffer. Together with
BPF_RB_NO_WAKEUP/BPF_RB_FORCE_WAKEUP flags for output/commit/discard helpers,
it allows BPF program a high degree of control and, e.g., more efficient
batched notifications. Default self-balancing strategy, though, should be
adequate for most applications and will work reliable and efficiently already.
Design and implementation
-------------------------
This reserve/commit schema allows a natural way for multiple producers, either
on different CPUs or even on the same CPU/in the same BPF program, to reserve
independent records and work with them without blocking other producers. This
means that if BPF program was interruped by another BPF program sharing the
same ring buffer, they will both get a record reserved (provided there is
enough space left) and can work with it and submit it independently. This
applies to NMI context as well, except that due to using a spinlock during
reservation, in NMI context, bpf_ringbuf_reserve() might fail to get a lock,
in which case reservation will fail even if ring buffer is not full.
The ring buffer itself internally is implemented as a power-of-2 sized
circular buffer, with two logical and ever-increasing counters (which might
wrap around on 32-bit architectures, that's not a problem):
- consumer counter shows up to which logical position consumer consumed the
data;
- producer counter denotes amount of data reserved by all producers.
Each time a record is reserved, producer that "owns" the record will
successfully advance producer counter. At that point, data is still not yet
ready to be consumed, though. Each record has 8 byte header, which contains
the length of reserved record, as well as two extra bits: busy bit to denote
that record is still being worked on, and discard bit, which might be set at
commit time if record is discarded. In the latter case, consumer is supposed
to skip the record and move on to the next one. Record header also encodes
record's relative offset from the beginning of ring buffer data area (in
pages). This allows bpf_ringbuf_commit()/bpf_ringbuf_discard() to accept only
the pointer to the record itself, without requiring also the pointer to ring
buffer itself. Ring buffer memory location will be restored from record
metadata header. This significantly simplifies verifier, as well as improving
API usability.
Producer counter increments are serialized under spinlock, so there is
a strict ordering between reservations. Commits, on the other hand, are
completely lockless and independent. All records become available to consumer
in the order of reservations, but only after all previous records where
already committed. It is thus possible for slow producers to temporarily hold
off submitted records, that were reserved later.
Reservation/commit/consumer protocol is verified by litmus tests in
Documentation/litmus-test/bpf-rb.
One interesting implementation bit, that significantly simplifies (and thus
speeds up as well) implementation of both producers and consumers is how data
area is mapped twice contiguously back-to-back in the virtual memory. This
allows to not take any special measures for samples that have to wrap around
at the end of the circular buffer data area, because the next page after the
last data page would be first data page again, and thus the sample will still
appear completely contiguous in virtual memory. See comment and a simple ASCII
diagram showing this visually in bpf_ringbuf_area_alloc().
Another feature that distinguishes BPF ringbuf from perf ring buffer is
a self-pacing notifications of new data being availability.
bpf_ringbuf_commit() implementation will send a notification of new record
being available after commit only if consumer has already caught up right up
to the record being committed. If not, consumer still has to catch up and thus
will see new data anyways without needing an extra poll notification.
Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c) show that
this allows to achieve a very high throughput without having to resort to
tricks like "notify only every Nth sample", which are necessary with perf
buffer. For extreme cases, when BPF program wants more manual control of
notifications, commit/discard/output helpers accept BPF_RB_NO_WAKEUP and
BPF_RB_FORCE_WAKEUP flags, which give full control over notifications of data
availability, but require extra caution and diligence in using this API.
Comparison to alternatives
--------------------------
Before considering implementing BPF ring buffer from scratch existing
alternatives in kernel were evaluated, but didn't seem to meet the needs. They
largely fell into few categores:
- per-CPU buffers (perf, ftrace, etc), which don't satisfy two motivations
outlined above (ordering and memory consumption);
- linked list-based implementations; while some were multi-producer designs,
consuming these from user-space would be very complicated and most
probably not performant; memory-mapping contiguous piece of memory is
simpler and more performant for user-space consumers;
- io_uring is SPSC, but also requires fixed-sized elements. Naively turning
SPSC queue into MPSC w/ lock would have subpar performance compared to
locked reserve + lockless commit, as with BPF ring buffer. Fixed sized
elements would be too limiting for BPF programs, given existing BPF
programs heavily rely on variable-sized perf buffer already;
- specialized implementations (like a new printk ring buffer, [0]) with lots
of printk-specific limitations and implications, that didn't seem to fit
well for intended use with BPF programs.
[0] https://lwn.net/Articles/779550/
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200529075424.3139988-2-andriin@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Disable a bunch of new kernel selftests that can't succeed on 5.5 kernel.
Flatten Travis tests into a single stage to parallelize and speed them up.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
bpf_obj_id selftest added testing of bpf_link related operations, which are
not implemented in 5.5.0. Blacklist it.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Fix memory leak in hashmap_clear() not freeing hashmap_entry structs for each
of the remaining entries. Also NULL-out bucket list to prevent possible
double-free between hashmap__clear() and hashmap__free().
Running test_progs-asan flavor clearly showed this problem.
Reported-by: Alston Tang <alston64@fb.com>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200429012111.277390-5-andriin@fb.com
As discussed at LPC 2019 ([0]), this patch brings (a quite belated) support
for declarative BTF-defined map-in-map support in libbpf. It allows to define
ARRAY_OF_MAPS and HASH_OF_MAPS BPF maps without any user-space initialization
code involved.
Additionally, it allows to initialize outer map's slots with references to
respective inner maps at load time, also completely declaratively.
Despite a weak type system of C, the way BTF-defined map-in-map definition
works, it's actually quite hard to accidentally initialize outer map with
incompatible inner maps. This being C, of course, it's still possible, but
even that would be caught at load time and error returned with helpful debug
log pointing exactly to the slot that failed to be initialized.
As an example, here's a rather advanced HASH_OF_MAPS declaration and
initialization example, filling slots #0 and #4 with two inner maps:
#include <bpf/bpf_helpers.h>
struct inner_map {
__uint(type, BPF_MAP_TYPE_ARRAY);
__uint(max_entries, 1);
__type(key, int);
__type(value, int);
} inner_map1 SEC(".maps"),
inner_map2 SEC(".maps");
struct outer_hash {
__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
__uint(max_entries, 5);
__uint(key_size, sizeof(int));
__array(values, struct inner_map);
} outer_hash SEC(".maps") = {
.values = {
[0] = &inner_map2,
[4] = &inner_map1,
},
};
Here's the relevant part of libbpf debug log showing pretty clearly of what's
going on with map-in-map initialization:
libbpf: .maps relo #0: for 6 value 0 rel.r_offset 96 name 260 ('inner_map1')
libbpf: .maps relo #0: map 'outer_arr' slot [0] points to map 'inner_map1'
libbpf: .maps relo #1: for 7 value 32 rel.r_offset 112 name 249 ('inner_map2')
libbpf: .maps relo #1: map 'outer_arr' slot [2] points to map 'inner_map2'
libbpf: .maps relo #2: for 7 value 32 rel.r_offset 144 name 249 ('inner_map2')
libbpf: .maps relo #2: map 'outer_hash' slot [0] points to map 'inner_map2'
libbpf: .maps relo #3: for 6 value 0 rel.r_offset 176 name 260 ('inner_map1')
libbpf: .maps relo #3: map 'outer_hash' slot [4] points to map 'inner_map1'
libbpf: map 'inner_map1': created successfully, fd=4
libbpf: map 'inner_map2': created successfully, fd=5
libbpf: map 'outer_hash': created successfully, fd=7
libbpf: map 'outer_hash': slot [0] set to map 'inner_map2' fd=5
libbpf: map 'outer_hash': slot [4] set to map 'inner_map1' fd=4
Notice from the log above that fd=6 (not logged explicitly) is used for inner
"prototype" map, necessary for creation of outer map. It is destroyed
immediately after outer map is created.
See also included selftest with some extra comments explaining extra details
of usage. Additionally, similar initialization syntax and libbpf functionality
can be used to do initialization of BPF_PROG_ARRAY with references to BPF
sub-programs. This can be done in follow up patches, if there will be a demand
for this.
[0] https://linuxplumbersconf.org/event/4/contributions/448/
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20200429002739.48006-4-andriin@fb.com
Factor out map creation and destruction logic to simplify code and especially
error handling. Also fix map FD leak in case of partially successful map
creation during bpf_object load operation.
Fixes: 57a00f41644f ("libbpf: Add auto-pinning of maps when loading BPF objects")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20200429002739.48006-3-andriin@fb.com
Add ability to fetch bpf_link details through BPF_OBJ_GET_INFO_BY_FD command.
Also enhance show_fdinfo to potentially include bpf_link type-specific
information (similarly to obj_info).
Also introduce enum bpf_link_type stored in bpf_link itself and expose it in
UAPI. bpf_link_tracing also now will store and return bpf_attach_type.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200429001614.1544-5-andriin@fb.com
Newer git started emitting warning about dangerousness of filter-branch.
Squelch it with FILTER_BRANCH_SQUELCH_WARNING=1 envvar.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
5.5 kernel has a bug in kernel allowing to violate read-only access to
mmap()-ed map. Disable selftest that now is failing.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
For some types of BPF programs that utilize expected_attach_type, libbpf won't
set load_attr.expected_attach_type, even if expected_attach_type is known from
section definition. This was done to preserve backwards compatibility with old
kernels that didn't recognize expected_attach_type attribute yet (which was
added in 5e43f899b03a ("bpf: Check attach type at prog load time"). But this
is problematic for some BPF programs that utilize newer features that require
kernel to know specific expected_attach_type (e.g., extended set of return
codes for cgroup_skb/egress programs).
This patch makes libbpf specify expected_attach_type by default, but also
detect support for this field in kernel and not set it during program load.
This allows to have a good metadata for bpf_program
(e.g., bpf_program__get_extected_attach_type()), but still work with old
kernels (for cases where it can work at all).
Additionally, due to expected_attach_type being always set for recognized
program types, bpf_program__attach_cgroup doesn't have to do extra checks to
determine correct attach type, so remove that additional logic.
Also adjust section_names selftest to account for this change.
More detailed discussion can be found in [0].
[0] https://lore.kernel.org/bpf/20200412003604.GA15986@rdna-mbp.dhcp.thefacebook.com/
Fixes: 5cf1e9145630 ("bpf: cgroup inet skb programs can return 0 to 3")
Fixes: 5e43f899b03a ("bpf: Check attach type at prog load time")
Reported-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Andrey Ignatov <rdna@fb.com>
Link: https://lore.kernel.org/bpf/20200414182645.1368174-1-andriin@fb.com
Syncing latest libbpf commits from kernel repository.
Baseline bpf-next commit: 483d7a30f538e2f8addd32aa9a3d2e94ae55fa65
Checkpoint bpf-next commit: 1a323ea5356edbb3073dc59d51b9e6b86908857d
Baseline bpf commit: 94b18a87efdd1626a1e6aef87271af4a7c616d36
Checkpoint bpf commit: 94b18a87efdd1626a1e6aef87271af4a7c616d36
Andrii Nakryiko (2):
bpf: Implement bpf_link-based cgroup BPF program attachment
libbpf: Add support for bpf_link-based cgroup attachment
Antoine Tenart (1):
net: macsec: add support for offloading to the MAC
Daniel Borkmann (2):
bpf: Add netns cookie and enable it for bpf cgroup hooks
bpf: Enable bpf cgroup hooks to retrieve cgroup v2 and ancestor id
Fletcher Dunn (1):
libbpf, xsk: Init all ring members in xsk_umem__create and
xsk_socket__create
Joe Stringer (1):
bpf: Add socket assign support
KP Singh (2):
bpf: Introduce BPF_PROG_TYPE_LSM
tools/libbpf: Add support for BPF_PROG_TYPE_LSM
Mark Starovoytov (1):
net: macsec: add support for specifying offload upon link creation
Stanislav Fomichev (1):
libbpf: Don't allocate 16M for log buffer by default
Tobias Klauser (1):
libbpf: Remove unused parameter `def` to get_map_field_int
Toke Høiland-Jørgensen (3):
tools: Add EXPECTED_FD-related definitions in if_link.h
libbpf: Add function to set link XDP fd while specifying old program
libbpf: Add setter for initial value for internal maps
include/uapi/linux/bpf.h | 82 ++++++++++++++++++++-
include/uapi/linux/if_link.h | 6 +-
src/bpf.c | 37 +++++++++-
src/bpf.h | 19 +++++
src/btf.c | 20 ++++--
src/libbpf.c | 134 +++++++++++++++++++++++++++++------
src/libbpf.h | 22 +++++-
src/libbpf.map | 9 +++
src/libbpf_probes.c | 1 +
src/netlink.c | 34 ++++++++-
src/xsk.c | 16 ++++-
11 files changed, 345 insertions(+), 35 deletions(-)
--
2.24.1
Add bpf_program__attach_cgroup(), which uses BPF_LINK_CREATE subcommand to
create an FD-based kernel bpf_link. Also add low-level bpf_link_create() API.
If expected_attach_type is not specified explicitly with
bpf_program__set_expected_attach_type(), libbpf will try to determine proper
attach type from BPF program's section definition.
Also add support for bpf_link's underlying BPF program replacement:
- unconditional through high-level bpf_link__update_program() API;
- cmpxchg-like with specifying expected current BPF program through
low-level bpf_link_update() API.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200330030001.2312810-4-andriin@fb.com
Implement new sub-command to attach cgroup BPF programs and return FD-based
bpf_link back on success. bpf_link, once attached to cgroup, cannot be
replaced, except by owner having its FD. Cgroup bpf_link supports only
BPF_F_ALLOW_MULTI semantics. Both link-based and prog-based BPF_F_ALLOW_MULTI
attachments can be freely intermixed.
To prevent bpf_cgroup_link from keeping cgroup alive past the point when no
BPF program can be executed, implement auto-detachment of link. When
cgroup_bpf_release() is called, all attached bpf_links are forced to release
cgroup refcounts, but they leave bpf_link otherwise active and allocated, as
well as still owning underlying bpf_prog. This is because user-space might
still have FDs open and active, so bpf_link as a user-referenced object can't
be freed yet. Once last active FD is closed, bpf_link will be freed and
underlying bpf_prog refcount will be dropped. But cgroup refcount won't be
touched, because cgroup is released already.
The inherent race between bpf_cgroup_link release (from closing last FD) and
cgroup_bpf_release() is resolved by both operations taking cgroup_mutex. So
the only additional check required is when bpf_cgroup_link attempts to detach
itself from cgroup. At that time we need to check whether there is still
cgroup associated with that link. And if not, exit with success, because
bpf_cgroup_link was already successfully detached.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Roman Gushchin <guro@fb.com>
Link: https://lore.kernel.org/bpf/20200330030001.2312810-2-andriin@fb.com
Enable now-fixed sockmap_listen tests. Disabled vmlinux test on 5.5, on which
hrtimer_nanosleep() signature is incompatible. Filled out remaining
permanently disabled tests resons.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Syscall raw tracepoints have struct pt_regs pointer as tracepoint's first
argument. After that, reading any of pt_regs fields requires bpf_probe_read(),
even for tp_btf programs. Due to that, PT_REGS_PARMx macros are not usable as
is. This patch adds CO-RE variants of those macros that use BPF_CORE_READ() to
read necessary fields. This provides relocatable architecture-agnostic pt_regs
field accesses.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200313172336.1879637-4-andriin@fb.com
With fixes in selftests, these tests should now pass.
Also add ability to add comments to blacklist/whitelist to explain why certain
test is disabled.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Needs for application BTF being present differs between user-space libbpf needs and kernel
needs. Currently, BTF is mandatory only in kernel only when BPF application is
using STRUCT_OPS. While libbpf itself relies more heavily on presense of BTF:
- for BTF-defined maps;
- for Kconfig externs;
- for STRUCT_OPS as well.
Thus, checks for presence and validness of bpf_object's BPF needs to be
performed separately, which is patch does.
Fixes: 5327644614a1 ("libbpf: Relax check whether BTF is mandatory")
Reported-by: Michal Rostecki <mrostecki@opensuse.org>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/bpf/20200312185033.736911-1-andriin@fb.com
Currently, BTF_KIND_ENUM type doesn't record whether enum values should be
interpreted as signed or unsigned. In Linux, most enums are unsigned, though,
so interpreting them as unsigned matches real world better.
Change btf_dump test case to test maximum 32-bit value, instead of negative
value.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200303003233.3496043-3-andriin@fb.com
Switch BPF UAPI constants, previously defined as #define macro, to anonymous
enum values. This preserves constants values and behavior in expressions, but
has added advantaged of being captured as part of DWARF and, subsequently, BTF
type info. Which, in turn, greatly improves usefulness of generated vmlinux.h
for BPF applications, as it will not require BPF users to copy/paste various
flags and constants, which are frequently used with BPF helpers. Only those
constants that are used/useful from BPF program side are converted.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200303003233.3496043-2-andriin@fb.com
Internal functions, used by btf_dump__emit_type_decl(), assume field_name is
never going to be NULL. Ensure it's always the case.
Fixes: 9f81654eebe8 ("libbpf: Expose BTF-to-C type declaration emitting API")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200303180800.3303471-1-andriin@fb.com
With bpf_link abstraction supported by kernel explicitly, add
pinning/unpinning API for links. Also allow to create (open) bpf_link from BPF
FS file.
This API allows to have an "ephemeral" FD-based BPF links (like raw tracepoint
or fexit/freplace attachments) surviving user process exit, by pinning them in
a BPF FS, which is an important use case for long-running BPF programs.
As part of this, expose underlying FD for bpf_link. While legacy bpf_link's
might not have a FD associated with them (which will be expressed as
a bpf_link with fd=-1), kernel's abstraction is based around FD-based usage,
so match it closely. This, subsequently, allows to have a generic
pinning/unpinning API for generalized bpf_link. For some types of bpf_links
kernel might not support pinning, in which case bpf_link__pin() will return
error.
With FD being part of generic bpf_link, also get rid of bpf_link_fd in favor
of using vanialla bpf_link.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200303043159.323675-3-andriin@fb.com
Add detection of vmlinux.h to bpf_tracing.h header for PT_REGS macro.
Currently, BPF applications have to define __KERNEL__ symbol to use correct
definition of struct pt_regs on x86 arch. This is due to different field names
under internal kernel vs UAPI conditions. To make this more transparent for
users, detect vmlinux.h by checking __VMLINUX_H__ symbol.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200229231112.1240137-3-andriin@fb.com
Manually bump sync commit from kernel repo. There are no libbpf changes, but
we need latest selftest patches to try to debug more of crashing selftests.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Build latest pahole from sources and not rely on hacky Ubuntu repository
approach.
Also enable tests for latest kernel that rely on pahole 1.16.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Clean up Travis CI config, extract multi-step initializations into scripts.
Also, move kernel-building tests to happen last to not block lightweight
Debian and Ubuntu tests.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
If BPF program is using BTF-defined maps, BTF is required only for
libbpf itself to process map definitions. If after that BTF fails to
be loaded into kernel (e.g., if it doesn't support BTF at all), this
shouldn't prevent valid BPF program from loading. Existing
retry-without-BTF logic for creating maps will succeed to create such
maps without any problems. So, presence of .maps section shouldn't make
BTF required for kernel. Update the check accordingly.
Validated by ensuring simple BPF program with BTF-defined maps is still
loaded on old kernel without BTF support and map is correctly parsed and
created.
Fixes: abd29c931459 ("libbpf: allow specifying map definitions using BTF")
Reported-by: Julia Kartseva <hex@fb.com>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200220062635.1497872-1-andriin@fb.com
Update blacklists to omit some of the newest selftests. Also ensure that
blacklist is sorted alphabetically.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Commit signature, used to determine already synced commits, includes a short
stats per each file relevant. Fix this script to include only files that are
actually synced (i.e., exclude Makefile, Build file, etc).
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Fix bug requesting invalid size of reallocated array when constructing CO-RE
relocation candidate list. This can cause problems if there are many potential
candidates and a very fine-grained memory allocator bucket sizes are used.
Fixes: ddc7c3042614 ("libbpf: implement BPF CO-RE offset relocation algorithm")
Reported-by: William Smith <williampsmith@fb.com>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20200124201847.212528-1-andriin@fb.com
Previously, if libbpf failed to resolve CO-RE relocation for some
instructions, it would either return error immediately, or, if
.relaxed_core_relocs option was set, would replace relocatable offset/imm part
of an instruction with a bogus value (-1). Neither approach is good, because
there are many possible scenarios where relocation is expected to fail (e.g.,
when some field knowingly can be missing on specific kernel versions). On the
other hand, replacing offset with invalid one can hide programmer errors, if
this relocation failue wasn't anticipated.
This patch deprecates .relaxed_core_relocs option and changes the approach to
always replacing instruction, for which relocation failed, with invalid BPF
helper call instruction. For cases where this is expected, BPF program should
already ensure that that instruction is unreachable, in which case this
invalid instruction is going to be silently ignored. But if instruction wasn't
guarded, BPF program will be rejected at verification step with verifier log
pointing precisely to the place in assembly where the problem is.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200124053837.2434679-1-andriin@fb.com
Current implementation of bpf_object's BTF initialization is very convoluted
and thus prone to errors. It doesn't have to be like that. This patch
simplifies it significantly.
This code also triggered static analysis issues over logically dead code due
to redundant error checks. This simplification should fix that as well.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200117060801.1311525-3-andriin@fb.com
Revert bpf_helpers.h's change to include auto-generated bpf_helper_defs.h
through <> instead of "", which causes it to be searched in include path. This
can break existing applications that don't have their include path pointing
directly to where libbpf installs its headers.
There is ongoing work to make all (not just bpf_helper_defs.h) includes more
consistent across libbpf and its consumers, but this unbreaks user code as is
right now without any regressions. Selftests still behave sub-optimally
(taking bpf_helper_defs.h from libbpf's source directory, if it's present
there), which will be fixed in subsequent patches.
Fixes: 6910d7d3867a ("selftests/bpf: Ensure bpf_helper_defs.h are taken from selftests dir")
Reported-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200117004103.148068-1-andriin@fb.com
The LLVM patch https://reviews.llvm.org/D72197 makes LLVM emit function call
relocations within the same section. This includes a default .text section,
which contains any BPF sub-programs. This wasn't the case before and so libbpf
was able to get a way with slightly simpler handling of subprogram call
relocations.
This patch adds support for .text section relocations. It needs to ensure
correct order of relocations, so does two passes:
- first, relocate .text instructions, if there are any relocations in it;
- then process all the other programs and copy over patched .text instructions
for all sub-program calls.
v1->v2:
- break early once .text program is processed.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200115190856.2391325-1-andriin@fb.com
It's been a recurring issue with types like u32 slipping into libbpf source
code accidentally. This is not detected during builds inside kernel source
tree, but becomes a compilation error in libbpf's Github repo. Libbpf is
supposed to use only __{s,u}{8,16,32,64} typedefs, so poison {s,u}{8,16,32,64}
explicitly in every .c file. Doing that in a bit more centralized way, e.g.,
inside libbpf_internal.h breaks selftests, which are both using kernel u32 and
libbpf_internal.h.
This patch also fixes a new u32 occurence in libbpf.c, added recently.
Fixes: 590a00888250 ("bpf: libbpf: Add STRUCT_OPS support")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200110181916.271446-1-andriin@fb.com
Reorder includes search path to ensure $(OUTPUT) and $(CURDIR) go before
libbpf's directory. Also fix bpf_helpers.h to include bpf_helper_defs.h in
such a way as to leverage includes search path. This allows selftests to not
use libbpf's local and potentially stale bpf_helper_defs.h. It's important
because selftests/bpf's Makefile only re-generates bpf_helper_defs.h in
seltests' output directory, not the one in libbpf's directory.
Also force regeneration of bpf_helper_defs.h when libbpf.a is updated to
reduce staleness.
Fixes: fa633a0f8919 ("libbpf: Fix build on read-only filesystems")
Reported-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200110051716.1591485-3-andriin@fb.com
Currently, libbpf re-sorts bpf_map structs after all the maps are added and
initialized, which might change their relative order and invalidate any
bpf_map pointer or index taken before that. This is inconvenient and
error-prone. For instance, it can cause .kconfig map index to point to a wrong
map.
Furthermore, libbpf itself doesn't rely on any specific ordering of bpf_maps,
so it's just an unnecessary complication right now. This patch drops sorting
of maps and makes their relative positions fixed. If efficient index is ever
needed, it's better to have a separate array of pointers as a search index,
instead of reordering bpf_map struct in-place. This will be less error-prone
and will allow multiple independent orderings, if necessary (e.g., either by
section index or by name).
Fixes: 166750bc1dd2 ("libbpf: Support libbpf-provided extern variables")
Reported-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200110034247.1220142-1-andriin@fb.com
Clang patch [0] enables emitting relocatable generic ALU/ALU64 instructions
(i.e, shifts and arithmetic operations), as well as generic load/store
instructions. The former ones are already supported by libbpf as is. This
patch adds further support for load/store instructions. Relocatable field
offset is encoded in BPF instruction's 16-bit offset section and are adjusted
by libbpf based on target kernel BTF.
These Clang changes and corresponding libbpf changes allow for more succinct
generated BPF code by encoding relocatable field reads as a single
ST/LDX/STX instruction. It also enables relocatable access to BPF context.
Previously, if context struct (e.g., __sk_buff) was accessed with CO-RE
relocations (e.g., due to preserve_access_index attribute), it would be
rejected by BPF verifier due to modified context pointer dereference. With
Clang patch, such context accesses are both relocatable and have a fixed
offset from the point of view of BPF verifier.
[0] https://reviews.llvm.org/D71790
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20191223180305.86417-1-andriin@fb.com
zlib is now a direct dependency of libbpf (previously zlib was only dependency
of libelf, on which libbpf depends as well). For non-pkg-config case, specify
`-lz` compiler flag explicitly.
Recent sync also added another public header to libbpf. Include it in a list
of headers that are installed on target system.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Andrii Nakryiko