kprobes can be placed on most instructions in a function, not
just entry, and ftrace and bpftrace support the function+offset
notification for probe placement. Adding parsing of func_name
into func+offset to bpf_program__attach_kprobe() allows the
user to specify
SEC("kprobe/bpf_fentry_test5+0x6")
...for example, and the offset can be passed to perf_event_open_probe()
to support kprobe attachment.
Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210714094400.396467-8-jolsa@kernel.org
Adding bpf_program__attach_kprobe_opts that does the same
as bpf_program__attach_kprobe, but takes opts argument.
Currently opts struct holds just retprobe bool, but we will
add new field in following patch.
The function is not exported, so there's no need to add
size to the struct bpf_program_attach_kprobe_opts for now.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210714094400.396467-7-jolsa@kernel.org
Adding bpf_get_func_ip helper for BPF_PROG_TYPE_KPROBE programs,
so it's now possible to call bpf_get_func_ip from both kprobe and
kretprobe programs.
Taking the caller's address from 'struct kprobe::addr', which is
defined for both kprobe and kretprobe.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lore.kernel.org/bpf/20210714094400.396467-5-jolsa@kernel.org
Adding bpf_get_func_ip helper for BPF_PROG_TYPE_TRACING programs,
specifically for all trampoline attach types.
The trampoline's caller IP address is stored in (ctx - 8) address.
so there's no reason to actually call the helper, but rather fixup
the call instruction and return [ctx - 8] value directly.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210714094400.396467-4-jolsa@kernel.org
Introduce 'struct bpf_timer { __u64 :64; __u64 :64; };' that can be embedded
in hash/array/lru maps as a regular field and helpers to operate on it:
// Initialize the timer.
// First 4 bits of 'flags' specify clockid.
// Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed.
long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, int flags);
// Configure the timer to call 'callback_fn' static function.
long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn);
// Arm the timer to expire 'nsec' nanoseconds from the current time.
long bpf_timer_start(struct bpf_timer *timer, u64 nsec, u64 flags);
// Cancel the timer and wait for callback_fn to finish if it was running.
long bpf_timer_cancel(struct bpf_timer *timer);
Here is how BPF program might look like:
struct map_elem {
int counter;
struct bpf_timer timer;
};
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__uint(max_entries, 1000);
__type(key, int);
__type(value, struct map_elem);
} hmap SEC(".maps");
static int timer_cb(void *map, int *key, struct map_elem *val);
/* val points to particular map element that contains bpf_timer. */
SEC("fentry/bpf_fentry_test1")
int BPF_PROG(test1, int a)
{
struct map_elem *val;
int key = 0;
val = bpf_map_lookup_elem(&hmap, &key);
if (val) {
bpf_timer_init(&val->timer, &hmap, CLOCK_REALTIME);
bpf_timer_set_callback(&val->timer, timer_cb);
bpf_timer_start(&val->timer, 1000 /* call timer_cb2 in 1 usec */, 0);
}
}
This patch adds helper implementations that rely on hrtimers
to call bpf functions as timers expire.
The following patches add necessary safety checks.
Only programs with CAP_BPF are allowed to use bpf_timer.
The amount of timers used by the program is constrained by
the memcg recorded at map creation time.
The bpf_timer_init() helper needs explicit 'map' argument because inner maps
are dynamic and not known at load time. While the bpf_timer_set_callback() is
receiving hidden 'aux->prog' argument supplied by the verifier.
The prog pointer is needed to do refcnting of bpf program to make sure that
program doesn't get freed while the timer is armed. This approach relies on
"user refcnt" scheme used in prog_array that stores bpf programs for
bpf_tail_call. The bpf_timer_set_callback() will increment the prog refcnt which is
paired with bpf_timer_cancel() that will drop the prog refcnt. The
ops->map_release_uref is responsible for cancelling the timers and dropping
prog refcnt when user space reference to a map reaches zero.
This uref approach is done to make sure that Ctrl-C of user space process will
not leave timers running forever unless the user space explicitly pinned a map
that contained timers in bpffs.
bpf_timer_init() and bpf_timer_set_callback() will return -EPERM if map doesn't
have user references (is not held by open file descriptor from user space and
not pinned in bpffs).
The bpf_map_delete_elem() and bpf_map_update_elem() operations cancel
and free the timer if given map element had it allocated.
"bpftool map update" command can be used to cancel timers.
The 'struct bpf_timer' is explicitly __attribute__((aligned(8))) because
'__u64 :64' has 1 byte alignment of 8 byte padding.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20210715005417.78572-4-alexei.starovoitov@gmail.com
When loading a BPF program with a pinned map, the loader checks whether
the pinned map can be reused, i.e. their properties match. To derive
such of the pinned map, the loader invokes BPF_OBJ_GET_INFO_BY_FD and
then does the comparison.
Unfortunately, on < 4.12 kernels the BPF_OBJ_GET_INFO_BY_FD is not
available, so loading the program fails with the following error:
libbpf: failed to get map info for map FD 5: Invalid argument
libbpf: couldn't reuse pinned map at
'/sys/fs/bpf/tc/globals/cilium_call_policy': parameter
mismatch"
libbpf: map 'cilium_call_policy': error reusing pinned map
libbpf: map 'cilium_call_policy': failed to create:
Invalid argument(-22)
libbpf: failed to load object 'bpf_overlay.o'
To fix this, fallback to derivation of the map properties via
/proc/$PID/fdinfo/$MAP_FD if BPF_OBJ_GET_INFO_BY_FD fails with EINVAL,
which can be used as an indicator that the kernel doesn't support
the latter.
Signed-off-by: Martynas Pumputis <m@lambda.lt>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210712125552.58705-1-m@lambda.lt
The update to streamline libbpf error reporting intended to change all
functions to return the errno as a negative return value if
LIBBPF_STRICT_DIRECT_ERRS is set. However, if the flag is *not* set, the
return value changes for the two functions that were already returning a
negative errno unconditionally: bpf_link__unpin() and perf_buffer__poll().
This is a user-visible API change that breaks applications; so let's revert
these two functions back to unconditionally returning a negative errno
value.
Fixes: e9fc3ce99b34 ("libbpf: Streamline error reporting for high-level APIs")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210706122355.236082-1-toke@redhat.com
Netlink helpers I added in 8bbb77b7c7a2 ("libbpf: Add various netlink
helpers") used char * casts everywhere, and there were a few more that
existed from before.
Convert all of them to void * cast, as it is treated equivalently by
clang/gcc for the purposes of pointer arithmetic and to follow the
convention elsewhere in the kernel/libbpf.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210619041454.417577-2-memxor@gmail.com
Coverity complains about OOB writes to nlmsghdr. There is no OOB as we
write to the trailing buffer, but static analyzers and compilers may
rightfully be confused as the nlmsghdr pointer has subobject provenance
(and hence subobject bounds).
Fix this by using an explicit request structure containing the nlmsghdr,
struct tcmsg/ifinfomsg, and attribute buffer.
Also switch nh_tail (renamed to req_tail) to cast req * to char * so
that it can be understood as arithmetic on pointer to the representation
array (hence having same bound as request structure), which should
further appease analyzers.
As a bonus, callers don't have to pass sizeof(req) all the time now, as
size is implicitly obtained using the pointer. While at it, also reduce
the size of attribute buffer to 128 bytes (132 for ifinfomsg using
functions due to the padding).
Summary of problem:
Even though C standard allows interconvertibility of pointer to first
member and pointer to struct, for the purposes of alias analysis it
would still consider the first as having pointer value "pointer to T"
where T is type of first member hence having subobject bounds,
allowing analyzers within reason to complain when object is accessed
beyond the size of pointed to object.
The only exception to this rule may be when a char * is formed to a
member subobject. It is not possible for the compiler to be able to
tell the intent of the programmer that it is a pointer to member
object or the underlying representation array of the containing
object, so such diagnosis is suppressed.
Fixes: 715c5ce454a6 ("libbpf: Add low level TC-BPF management API")
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210619041454.417577-1-memxor@gmail.com
Let us sync linux/{pkt_cls.h,pkt_sched.h} to libbpf repo.
Otherwise, on ubuntu 16.04, system headers will be picked up
and this will result in compilation error like:
.../netlink.c:416:23: error: ‘TC_H_CLSACT’ undeclared (first use in this function)
*parent = TC_H_MAKE(TC_H_CLSACT,
^
.../netlink.c:418:9: error: ‘TC_H_MIN_INGRESS’ undeclared (first use in this function)
TC_H_MIN_INGRESS : TC_H_MIN_EGRESS);
^
.../netlink.c:418:28: error: ‘TC_H_MIN_EGRESS’ undeclared (first use in this function)
TC_H_MIN_INGRESS : TC_H_MIN_EGRESS);
^
.../netlink.c: In function ‘__get_tc_info’:
.../netlink.c:522:11: error: ‘TCA_BPF_ID’ undeclared (first use in this function)
if (!tbb[TCA_BPF_ID])
^
Signed-off-by: Yonghong Song <yhs@fb.com>
Make sure we run all of the tests even if some of them fail. This allows to
test all of them independently, especially kernel LATEST slow test.
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
This patch is meant to start the initiative to document libbpf.
It includes .rst files which are text documentation describing building,
API naming convention, as well as an index to generated API documentation.
In this approach the generated API documentation is enabled by the kernels
existing kernel documentation system which uses sphinx. The resulting docs
would then be synced to kernel.org/doc
You can test this by running `make htmldocs` and serving the html in
Documentation/output. Since libbpf does not yet have comments in kernel
doc format, see kernel.org/doc/html/latest/doc-guide/kernel-doc.html for
an example so you can test this.
The advantage of this approach is to use the existing sphinx
infrastructure that the kernel has, and have libbpf docs in
the same place as everything else.
The current plan is to have the libbpf mirror sync the generated docs
and version them based on the libbpf releases which are cut on github.
This patch includes the addition of libbpf_api.rst which pulls comment
documentation from header files in libbpf under tools/lib/bpf/. The comment
docs would be of the standard kernel doc format.
Signed-off-by: grantseltzer <grantseltzer@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210618140459.9887-2-grantseltzer@gmail.com
bpf2go is the Go equivalent of libbpf skeleton. The convention is that
the compiled BPF is checked into the repository to facilitate distributing
BPF as part of Go packages. To make this portable, bpf2go by default
generates both bpfel and bpfeb variants of the C.
Using bpf_tracing.h is inherently non-portable since the fields of
struct pt_regs differ between platforms, so CO-RE can't help us here.
The only way of working around this is to compile for each target
platform independently. bpf2go can't do this by default since there
are too many platforms.
Define the various PT_... macros when no target can be determined and
turn them into compilation failures. This works because bpf2go always
compiles for bpf targets, so the compiler fallback doesn't kick in.
Conditionally define __BPF_MISSING_TARGET so that we can inject a
more appropriate error message at build time. The user can then
choose which platform to target explicitly.
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210616083635.11434-1-lmb@cloudflare.com
This patch introduces a new bpf_attach_type for BPF_PROG_TYPE_SK_REUSEPORT
to check if the attached eBPF program is capable of migrating sockets. When
the eBPF program is attached, we run it for socket migration if the
expected_attach_type is BPF_SK_REUSEPORT_SELECT_OR_MIGRATE or
net.ipv4.tcp_migrate_req is enabled.
Currently, the expected_attach_type is not enforced for the
BPF_PROG_TYPE_SK_REUSEPORT type of program. Thus, this commit follows the
earlier idea in the commit aac3fc320d94 ("bpf: Post-hooks for sys_bind") to
fix up the zero expected_attach_type in bpf_prog_load_fixup_attach_type().
Moreover, this patch adds a new field (migrating_sk) to sk_reuseport_md to
select a new listener based on the child socket. migrating_sk varies
depending on if it is migrating a request in the accept queue or during
3WHS.
- accept_queue : sock (ESTABLISHED/SYN_RECV)
- 3WHS : request_sock (NEW_SYN_RECV)
In the eBPF program, we can select a new listener by
BPF_FUNC_sk_select_reuseport(). Also, we can cancel migration by returning
SK_DROP. This feature is useful when listeners have different settings at
the socket API level or when we want to free resources as soon as possible.
- SK_PASS with selected_sk, select it as a new listener
- SK_PASS with selected_sk NULL, fallbacks to the random selection
- SK_DROP, cancel the migration.
There is a noteworthy point. We select a listening socket in three places,
but we do not have struct skb at closing a listener or retransmitting a
SYN+ACK. On the other hand, some helper functions do not expect skb is NULL
(e.g. skb_header_pointer() in BPF_FUNC_skb_load_bytes(), skb_tail_pointer()
in BPF_FUNC_skb_load_bytes_relative()). So we allocate an empty skb
temporarily before running the eBPF program.
Suggested-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/netdev/20201123003828.xjpjdtk4ygl6tg6h@kafai-mbp.dhcp.thefacebook.com/
Link: https://lore.kernel.org/netdev/20201203042402.6cskdlit5f3mw4ru@kafai-mbp.dhcp.thefacebook.com/
Link: https://lore.kernel.org/netdev/20201209030903.hhow5r53l6fmozjn@kafai-mbp.dhcp.thefacebook.com/
Link: https://lore.kernel.org/bpf/20210612123224.12525-10-kuniyu@amazon.co.jp
When calling xsk_socket__create_shared(), the logic at line 1097 marks a
boolean flag true within the xsk_umem structure to track setup progress
in order to support multiple calls to the function. However, instead of
marking umem->tx_ring_setup_done, the code incorrectly sets
umem->rx_ring_setup_done. This leads to improper behaviour when
creating and destroying xsk and umem structures.
Multiple calls to this function is documented as supported.
Fixes: ca7a83e2487a ("libbpf: Only create rx and tx XDP rings when necessary")
Signed-off-by: Kev Jackson <foamdino@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/YL4aU4f3Aaik7CN0@linux-dev
These macros are convenient wrappers around the bpf_seq_printf and
bpf_snprintf helpers. They are currently provided by bpf_tracing.h which
targets low level tracing primitives. bpf_helpers.h is a better fit.
The __bpf_narg and __bpf_apply are needed in both files and provided
twice. __bpf_empty isn't used anywhere and is removed from bpf_tracing.h
Reported-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Florent Revest <revest@chromium.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210526164643.2881368-1-revest@chromium.org
This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to
extend xdp_redirect_map for broadcast support.
With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces
in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be
excluded when do broadcasting.
When getting the devices in dev hash map via dev_map_hash_get_next_key(),
there is a possibility that we fall back to the first key when a device
was removed. This will duplicate packets on some interfaces. So just walk
the whole buckets to avoid this issue. For dev array map, we also walk the
whole map to find valid interfaces.
Function bpf_clear_redirect_map() was removed in
commit ee75aef23afe ("bpf, xdp: Restructure redirect actions").
Add it back as we need to use ri->map again.
With test topology:
+-------------------+ +-------------------+
| Host A (i40e 10G) | ---------- | eno1(i40e 10G) |
+-------------------+ | |
| Host B |
+-------------------+ | |
| Host C (i40e 10G) | ---------- | eno2(i40e 10G) |
+-------------------+ | |
| +------+ |
| veth0 -- | Peer | |
| veth1 -- | | |
| veth2 -- | NS | |
| +------+ |
+-------------------+
On Host A:
# pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64
On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory):
Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing.
All the veth peers in the NS have a XDP_DROP program loaded. The
forward_map max_entries in xdp_redirect_map_multi is modify to 4.
Testing the performance impact on the regular xdp_redirect path with and
without patch (to check impact of additional check for broadcast mode):
5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M
5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M
5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M
5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M
Testing the performance when cloning packets with the redirect_map_multi
test, using a redirect map size of 4, filled with 1-3 devices:
5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M
5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M
5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
Implement changes to error reporting for high-level libbpf APIs to make them
less surprising and less error-prone to users:
- in all the cases when error happens, errno is set to an appropriate error
value;
- in libbpf 1.0 mode, all pointer-returning APIs return NULL on error and
error code is communicated through errno; this applies both to APIs that
already returned NULL before (so now they communicate more detailed error
codes), as well as for many APIs that used ERR_PTR() macro and encoded
error numbers as fake pointers.
- in legacy (default) mode, those APIs that were returning ERR_PTR(err),
continue doing so, but still set errno.
With these changes, errno can be always used to extract actual error,
regardless of legacy or libbpf 1.0 modes. This is utilized internally in
libbpf in places where libbpf uses it's own high-level APIs.
libbpf_get_error() is adapted to handle both cases completely transparently to
end-users (and is used by libbpf consistently as well).
More context, justification, and discussion can be found in "Libbpf: the road
to v1.0" document ([0]).
[0] https://docs.google.com/document/d/1UyjTZuPFWiPFyKk1tV5an11_iaRuec6U-ZESZ54nNTY
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20210525035935.1461796-5-andrii@kernel.org
Add libbpf_set_strict_mode() API that allows application to simulate libbpf
1.0 breaking changes before libbpf 1.0 is released. This will help users
migrate gradually and with confidence.
For now only ALL or NONE options are available, subsequent patches will add
more flags. This patch is preliminary for selftests/bpf changes.
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20210525035935.1461796-2-andrii@kernel.org
I'm getting the following error when running 'gen skeleton -L' as
regular user:
libbpf: Error in bpf_object__probe_loading():Operation not permitted(1).
Couldn't load trivial BPF program. Make sure your kernel supports BPF
(CONFIG_BPF_SYSCALL=y) and/or that RLIMIT_MEMLOCK is set to big enough
value.
Fixes: 67234743736a ("libbpf: Generate loader program out of BPF ELF file.")
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210521030653.2626513-1-sdf@google.com
