[ Upstream commit 36d5b2913219ac853908b0f1c664345e04313856 ]
When doing lookups for rules on the same batch by using its ID, a rule from
a different chain can be used. If a rule is added to a chain but tries to
be positioned next to a rule from a different chain, it will be linked to
chain2, but the use counter on chain1 would be the one to be incremented.
When looking for rules by ID, use the chain that was used for the lookup by
name. The chain used in the context copied to the transaction needs to
match that same chain. That way, struct nft_rule does not need to get
enlarged with another member.
Fixes: 1a94e38d254b ("netfilter: nf_tables: add NFTA_RULE_ID attribute")
Fixes: 75dd48e2e420 ("netfilter: nf_tables: Support RULE_ID reference in new rule")
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Tao Wu <tallwu@tencent.com>
[ Upstream commit 470ee20e069a6d05ae549f7d0ef2bdbcee6a81b2 ]
When doing lookups for sets on the same batch by using its ID, a set from a
different table can be used.
Then, when the table is removed, a reference to the set may be kept after
the set is freed, leading to a potential use-after-free.
When looking for sets by ID, use the table that was used for the lookup by
name, and only return sets belonging to that same table.
This fixes CVE-2022-2586, also reported as ZDI-CAN-17470.
Reported-by: Team Orca of Sea Security (@seasecresponse)
Fixes: 958bee14d071 ("netfilter: nf_tables: use new transaction infrastructure to handle sets")
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Tao Wu <tallwu@tencent.com>
upstream: 9ad36309e2719a884f946678e0296be10f0bb4c1
When a route filter is replaced and the old filter has a 0 handle, the old
one won't be removed from the hashtable, while it will still be freed.
The test was there since before commit 1109c00547fc ("net: sched: RCU
cls_route"), when a new filter was not allocated when there was an old one.
The old filter was reused and the reinserting would only be necessary if an
old filter was replaced. That was still wrong for the same case where the
old handle was 0.
Remove the old filter from the list independently from its handle value.
This fixes CVE-2022-2588, also reported as ZDI-CAN-17440.
Reported-by: Zhenpeng Lin <zplin@u.northwestern.edu>
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Reviewed-by: Kamal Mostafa <kamal@canonical.com>
Cc: <stable@vger.kernel.org>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://lore.kernel.org/r/20220809170518.164662-1-cascardo@canonical.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Bin Lai <robinlai@tencent.com>
[upstream commit c205cc7534a97f2d6fbd2a23a94ed7c036c6e2aa]
Sometimes, gcc will optimize the function by spliting it to two or
more functions. In this case, kfree_skb_reason() is splited to
kfree_skb_reason and kfree_skb_reason.part.0. However, the
function/tracepoint trace_kfree_skb() in it needs the return address
of kfree_skb_reason().
This split makes the call chains becomes:
kfree_skb_reason() -> kfree_skb_reason.part.0 -> trace_kfree_skb()
which makes the return address that passed to trace_kfree_skb() be
kfree_skb().
Therefore, introduce '__fix_address', which is the combination of
'__noclone' and 'noinline', and apply it to kfree_skb_reason() to
prevent to from being splited or made inline.
(Is it better to simply apply '__noclone oninline' to kfree_skb_reason?
I'm thinking maybe other functions have the same problems)
Meanwhile, wrap 'skb_unref()' with 'unlikely()', as the compiler thinks
it is likely return true and splits kfree_skb_reason().
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The usage of bpf_dispatcher for XDP caused kernel panic, and the reason
has not found. Therefore, disable it for now.
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Reviewed-by: robinlai <robinlai@tencent.com>
The usage of bpf_dispatcher for XDP caused kernel panic, and the reason
has not found. Therefore, disable it for now.
Signed-off-by: Menglong Dong <imagedong@tencent.com>
[ Upstream commit 29e8e659f984be00d75ec5fef4e37c88def72712 ]
packet_sock xmit could be dev_queue_xmit, which also returns negative
errors. So only checking positive errors is not enough, or userspace
sendmsg may return success while packet is not send out.
Move the net_xmit_errno() assignment in the braces as checkpatch.pl said
do not use assignment in if condition.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Flavio Leitner <fbl@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Jianping Liu <frankjpliu@tencent.com>
commit e42e70ad6ae2ae511a6143d2e8da929366e58bd9 upstream.
When packet_setsockopt( PACKET_FANOUT_DATA ) reads po->fanout,
no lock is held, meaning that another thread can change po->fanout.
Given that po->fanout can only be set once during the socket lifetime
(it is only cleared from fanout_release()), we can use
READ_ONCE()/WRITE_ONCE() to document the race.
BUG: KCSAN: data-race in packet_setsockopt / packet_setsockopt
write to 0xffff88813ae8e300 of 8 bytes by task 14653 on cpu 0:
fanout_add net/packet/af_packet.c:1791 [inline]
packet_setsockopt+0x22fe/0x24a0 net/packet/af_packet.c:3931
__sys_setsockopt+0x209/0x2a0 net/socket.c:2180
__do_sys_setsockopt net/socket.c:2191 [inline]
__se_sys_setsockopt net/socket.c:2188 [inline]
__x64_sys_setsockopt+0x62/0x70 net/socket.c:2188
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
read to 0xffff88813ae8e300 of 8 bytes by task 14654 on cpu 1:
packet_setsockopt+0x691/0x24a0 net/packet/af_packet.c:3935
__sys_setsockopt+0x209/0x2a0 net/socket.c:2180
__do_sys_setsockopt net/socket.c:2191 [inline]
__se_sys_setsockopt net/socket.c:2188 [inline]
__x64_sys_setsockopt+0x62/0x70 net/socket.c:2188
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
value changed: 0x0000000000000000 -> 0xffff888106f8c000
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 14654 Comm: syz-executor.3 Not tainted 5.16.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Fixes: 47dceb8ecdc1 ("packet: add classic BPF fanout mode")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Link: https://lore.kernel.org/r/20220201022358.330621-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jianping Liu <frankjpliu@tencent.com>
[ Upstream commit ec6af094ea28f0f2dda1a6a33b14cd57e36a9755 ]
Packet sockets may switch ring versions. Avoid misinterpreting state
between versions, whose fields share a union. rx_owner_map is only
allocated with a packet ring (pg_vec) and both are swapped together.
If pg_vec is NULL, meaning no packet ring was allocated, then neither
was rx_owner_map. And the field may be old state from a tpacket_v3.
Fixes: 61fad6816fc1 ("net/packet: tpacket_rcv: avoid a producer race condition")
Reported-by: Syzbot <syzbot+1ac0994a0a0c55151121@syzkaller.appspotmail.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20211215143937.106178-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Jianping Liu <frankjpliu@tencent.com>
[ Upstream commit e032f7c9c7cefffcfb79b9fc16c53011d2d9d11f ]
Like prior patch, we need to annotate lockless accesses to po->ifindex
For instance, packet_getname() is reading po->ifindex (twice) while
another thread is able to change po->ifindex.
KCSAN reported:
BUG: KCSAN: data-race in packet_do_bind / packet_getname
write to 0xffff888143ce3cbc of 4 bytes by task 25573 on cpu 1:
packet_do_bind+0x420/0x7e0 net/packet/af_packet.c:3191
packet_bind+0xc3/0xd0 net/packet/af_packet.c:3255
__sys_bind+0x200/0x290 net/socket.c:1637
__do_sys_bind net/socket.c:1648 [inline]
__se_sys_bind net/socket.c:1646 [inline]
__x64_sys_bind+0x3d/0x50 net/socket.c:1646
do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47
entry_SYSCALL_64_after_hwframe+0x44/0xae
read to 0xffff888143ce3cbc of 4 bytes by task 25578 on cpu 0:
packet_getname+0x5b/0x1a0 net/packet/af_packet.c:3525
__sys_getsockname+0x10e/0x1a0 net/socket.c:1887
__do_sys_getsockname net/socket.c:1902 [inline]
__se_sys_getsockname net/socket.c:1899 [inline]
__x64_sys_getsockname+0x3e/0x50 net/socket.c:1899
do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47
entry_SYSCALL_64_after_hwframe+0x44/0xae
value changed: 0x00000000 -> 0x00000001
Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 25578 Comm: syz-executor.5 Not tainted 5.13.0-rc6-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Jianping Liu <frankjpliu@tencent.com>
[ Upstream commit c7d2ef5dd4b03ed0ee1d13bc0c55f9cf62d49bd6 ]
tpacket_snd(), packet_snd(), packet_getname() and packet_seq_show()
can read po->num without holding a lock. This means other threads
can change po->num at the same time.
KCSAN complained about this known fact [1]
Add READ_ONCE()/WRITE_ONCE() to address the issue.
[1] BUG: KCSAN: data-race in packet_do_bind / packet_sendmsg
write to 0xffff888131a0dcc0 of 2 bytes by task 24714 on cpu 0:
packet_do_bind+0x3ab/0x7e0 net/packet/af_packet.c:3181
packet_bind+0xc3/0xd0 net/packet/af_packet.c:3255
__sys_bind+0x200/0x290 net/socket.c:1637
__do_sys_bind net/socket.c:1648 [inline]
__se_sys_bind net/socket.c:1646 [inline]
__x64_sys_bind+0x3d/0x50 net/socket.c:1646
do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47
entry_SYSCALL_64_after_hwframe+0x44/0xae
read to 0xffff888131a0dcc0 of 2 bytes by task 24719 on cpu 1:
packet_snd net/packet/af_packet.c:2899 [inline]
packet_sendmsg+0x317/0x3570 net/packet/af_packet.c:3040
sock_sendmsg_nosec net/socket.c:654 [inline]
sock_sendmsg net/socket.c:674 [inline]
____sys_sendmsg+0x360/0x4d0 net/socket.c:2350
___sys_sendmsg net/socket.c:2404 [inline]
__sys_sendmsg+0x1ed/0x270 net/socket.c:2433
__do_sys_sendmsg net/socket.c:2442 [inline]
__se_sys_sendmsg net/socket.c:2440 [inline]
__x64_sys_sendmsg+0x42/0x50 net/socket.c:2440
do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47
entry_SYSCALL_64_after_hwframe+0x44/0xae
value changed: 0x0000 -> 0x1200
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 24719 Comm: syz-executor.5 Not tainted 5.13.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Jianping Liu <frankjpliu@tencent.com>
Add an efficient ingress to ingress netns switch that can be used out of tc BPF
programs in order to redirect traffic from host ns ingress into a container
veth device ingress without having to go via CPU backlog queue [0]. For local
containers this can also be utilized and path via CPU backlog queue only needs
to be taken once, not twice. On a high level this borrows from ipvlan which does
similar switch in __netif_receive_skb_core() and then iterates via another_round.
This helps to reduce latency for mentioned use cases.
Pod to remote pod with redirect(), TCP_RR [1]:
# percpu_netperf 10.217.1.33
RT_LATENCY: 122.450 (per CPU: 122.666 122.401 122.333 122.401 )
MEAN_LATENCY: 121.210 (per CPU: 121.100 121.260 121.320 121.160 )
STDDEV_LATENCY: 120.040 (per CPU: 119.420 119.910 125.460 115.370 )
MIN_LATENCY: 46.500 (per CPU: 47.000 47.000 47.000 45.000 )
P50_LATENCY: 118.500 (per CPU: 118.000 119.000 118.000 119.000 )
P90_LATENCY: 127.500 (per CPU: 127.000 128.000 127.000 128.000 )
P99_LATENCY: 130.750 (per CPU: 131.000 131.000 129.000 132.000 )
TRANSACTION_RATE: 32666.400 (per CPU: 8152.200 8169.842 8174.439 8169.897 )
Pod to remote pod with redirect_peer(), TCP_RR:
# percpu_netperf 10.217.1.33
RT_LATENCY: 44.449 (per CPU: 43.767 43.127 45.279 45.622 )
MEAN_LATENCY: 45.065 (per CPU: 44.030 45.530 45.190 45.510 )
STDDEV_LATENCY: 84.823 (per CPU: 66.770 97.290 84.380 90.850 )
MIN_LATENCY: 33.500 (per CPU: 33.000 33.000 34.000 34.000 )
P50_LATENCY: 43.250 (per CPU: 43.000 43.000 43.000 44.000 )
P90_LATENCY: 46.750 (per CPU: 46.000 47.000 47.000 47.000 )
P99_LATENCY: 52.750 (per CPU: 51.000 54.000 53.000 53.000 )
TRANSACTION_RATE: 90039.500 (per CPU: 22848.186 23187.089 22085.077 21919.130 )
[0] https://linuxplumbersconf.org/event/7/contributions/674/attachments/568/1002/plumbers_2020_cilium_load_balancer.pdf
[1] https://github.com/borkmann/netperf_scripts/blob/master/percpu_netperf
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201010234006.7075-3-daniel@iogearbox.net
Some error happens while compiling bpf_redirect_peer helper, which
may be caused during code backport.
Fix it by add the missing BPF_F_PEER.
Signed-off-by: Menglong Dong <imagedong@tencent.com>
[upstream commit ba452c9e996d8a4c347b32805f91abb70de5de7e]
Based on the discussion in [0], update the bpf_redirect_neigh() helper to
accept an optional parameter specifying the nexthop information. This makes
it possible to combine bpf_fib_lookup() and bpf_redirect_neigh() without
incurring a duplicate FIB lookup - since the FIB lookup helper will return
the nexthop information even if no neighbour is present, this can simply
be passed on to bpf_redirect_neigh() if bpf_fib_lookup() returns
BPF_FIB_LKUP_RET_NO_NEIGH. Thus fix & extend it before helper API is frozen.
[0] https://lore.kernel.org/bpf/393e17fc-d187-3a8d-2f0d-a627c7c63fca@iogearbox.net/
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/bpf/160322915615.32199.1187570224032024535.stgit@toke.dk
[upstream commit 8086fbaf49345f988deec539ec8e182b02914401]
We want to have a tighter control on what ports we bind to in
the BPF_CGROUP_INET{4,6}_CONNECT hooks even if it means
connect() becomes slightly more expensive. The expensive part
comes from the fact that we now need to call inet_csk_get_port()
that verifies that the port is not used and allocates an entry
in the hash table for it.
Since we can't rely on "snum || !bind_address_no_port" to prevent
us from calling POST_BIND hook anymore, let's add another bind flag
to indicate that the call site is BPF program.
v5:
* fix wrong AF_INET (should be AF_INET6) in the bpf program for v6
v3:
* More bpf_bind documentation refinements (Martin KaFai Lau)
* Add UDP tests as well (Martin KaFai Lau)
* Don't start the thread, just do socket+bind+listen (Martin KaFai Lau)
v2:
* Update documentation (Andrey Ignatov)
* Pass BIND_FORCE_ADDRESS_NO_PORT conditionally (Andrey Ignatov)
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200508174611.228805-5-sdf@google.com
[upstream commit cb0721c7e200750907bb8ef59b12646a5cb2dadf]
The intent is to add an additional bind parameter in the next commit.
Instead of adding another argument, let's convert all existing
flag arguments into an extendable bit field.
No functional changes.
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200508174611.228805-4-sdf@google.com
[upstream commit b4ab31414970a7a03a5d55d75083f2c101a30592]
Add a redirect_neigh() helper as redirect() drop-in replacement
for the xmit side. Main idea for the helper is to be very similar
in semantics to the latter just that the skb gets injected into
the neighboring subsystem in order to let the stack do the work
it knows best anyway to populate the L2 addresses of the packet
and then hand over to dev_queue_xmit() as redirect() does.
This solves two bigger items: i) skbs don't need to go up to the
stack on the host facing veth ingress side for traffic egressing
the container to achieve the same for populating L2 which also
has the huge advantage that ii) the skb->sk won't get orphaned in
ip_rcv_core() when entering the IP routing layer on the host stack.
Given that skb->sk neither gets orphaned when crossing the netns
as per 9c4c325252c5 ("skbuff: preserve sock reference when scrubbing
the skb.") the helper can then push the skbs directly to the phys
device where FQ scheduler can do its work and TCP stack gets proper
backpressure given we hold on to skb->sk as long as skb is still
residing in queues.
With the helper used in BPF data path to then push the skb to the
phys device, I observed a stable/consistent TCP_STREAM improvement
on veth devices for traffic going container -> host -> host ->
container from ~10Gbps to ~15Gbps for a single stream in my test
environment.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/bpf/f207de81629e1724899b73b8112e0013be782d35.1601477936.git.daniel@iogearbox.net
[upstream commit b426ce83baa7dff947fb354118d3133f2953aac8]
Similarly to 5a52ae4e32a6 ("bpf: Allow to retrieve cgroup v1 classid
from v2 hooks"), add a helper to retrieve cgroup v1 classid solely
based on the skb->sk, so it can be used as key as part of BPF map
lookups out of tc from host ns, in particular given the skb->sk is
retained these days when crossing net ns thanks to 9c4c325252c5
("skbuff: preserve sock reference when scrubbing the skb."). This
is similar to bpf_skb_cgroup_id() which implements the same for v2.
Kubernetes ecosystem is still operating on v1 however, hence net_cls
needs to be used there until this can be dropped in with the v2
helper of bpf_skb_cgroup_id().
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/ed633cf27a1c620e901c5aa99ebdefb028dce600.1601477936.git.daniel@iogearbox.net
[upstream commit 1b66d253610c7f8f257103808a9460223a087469]
As stated in 983695fa6765 ("bpf: fix unconnected udp hooks"), the objective
for the existing cgroup connect/sendmsg/recvmsg/bind BPF hooks is to be
transparent to applications. In Cilium we make use of these hooks [0] in
order to enable E-W load balancing for existing Kubernetes service types
for all Cilium managed nodes in the cluster. Those backends can be local
or remote. The main advantage of this approach is that it operates as close
as possible to the socket, and therefore allows to avoid packet-based NAT
given in connect/sendmsg/recvmsg hooks we only need to xlate sock addresses.
This also allows to expose NodePort services on loopback addresses in the
host namespace, for example. As another advantage, this also efficiently
blocks bind requests for applications in the host namespace for exposed
ports. However, one missing item is that we also need to perform reverse
xlation for inet{,6}_getname() hooks such that we can return the service
IP/port tuple back to the application instead of the remote peer address.
The vast majority of applications does not bother about getpeername(), but
in a few occasions we've seen breakage when validating the peer's address
since it returns unexpectedly the backend tuple instead of the service one.
Therefore, this trivial patch allows to customise and adds a getpeername()
as well as getsockname() BPF cgroup hook for both IPv4 and IPv6 in order
to address this situation.
Simple example:
# ./cilium/cilium service list
ID Frontend Service Type Backend
1 1.2.3.4:80 ClusterIP 1 => 10.0.0.10:80
Before; curl's verbose output example, no getpeername() reverse xlation:
# curl --verbose 1.2.3.4
* Rebuilt URL to: 1.2.3.4/
* Trying 1.2.3.4...
* TCP_NODELAY set
* Connected to 1.2.3.4 (10.0.0.10) port 80 (#0)
> GET / HTTP/1.1
> Host: 1.2.3.4
> User-Agent: curl/7.58.0
> Accept: */*
[...]
After; with getpeername() reverse xlation:
# curl --verbose 1.2.3.4
* Rebuilt URL to: 1.2.3.4/
* Trying 1.2.3.4...
* TCP_NODELAY set
* Connected to 1.2.3.4 (1.2.3.4) port 80 (#0)
> GET / HTTP/1.1
> Host: 1.2.3.4
> User-Agent: curl/7.58.0
> Accept: */*
[...]
Originally, I had both under a BPF_CGROUP_INET{4,6}_GETNAME type and exposed
peer to the context similar as in inet{,6}_getname() fashion, but API-wise
this is suboptimal as it always enforces programs having to test for ctx->peer
which can easily be missed, hence BPF_CGROUP_INET{4,6}_GET{PEER,SOCK}NAME split.
Similarly, the checked return code is on tnum_range(1, 1), but if a use case
comes up in future, it can easily be changed to return an error code instead.
Helper and ctx member access is the same as with connect/sendmsg/etc hooks.
[0] https://github.com/cilium/cilium/blob/master/bpf/bpf_sock.c
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Andrey Ignatov <rdna@fb.com>
Link: https://lore.kernel.org/bpf/61a479d759b2482ae3efb45546490bacd796a220.1589841594.git.daniel@iogearbox.net
Looks like the IPv6 version of the patch under Fixes was
a copy/paste of the IPv4 but hit the wrong spot.
It is tcp_v6_rcv() which uses drop_reason as a boolean, and
needs to be protected against reason == 0 before calling free.
tcp_v6_do_rcv() has a pretty straightforward flow.
The resulting warning looks like this:
WARNING: CPU: 1 PID: 0 at net/core/skbuff.c:775
Call Trace:
tcp_v6_rcv (net/ipv6/tcp_ipv6.c:1767)
ip6_protocol_deliver_rcu (net/ipv6/ip6_input.c:438)
ip6_input_finish (include/linux/rcupdate.h:726)
ip6_input (include/linux/netfilter.h:307)
Fixes: f8319dfd1b3b ("net: tcp: reset 'drop_reason' to NOT_SPCIFIED in tcp_v{4,6}_rcv()")
Tested-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Link: https://lore.kernel.org/r/20220520021347.2270207-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
commit 164051a6ab5445bd97f719f50b16db8b32174269 upstream.
The TP.CM_BAM message must be sent to the global address [1], so add a
check to drop TP.CM_BAM sent to a non-global address.
Without this patch, the receiver will treat the following packets as
normal RTS/CTS transport:
18EC0102#20090002FF002301
18EB0102#0100000000000000
18EB0102#020000FFFFFFFFFF
[1] SAE-J1939-82 2015 A.3.3 Row 1.
Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Link: https://lore.kernel.org/all/1635431907-15617-4-git-send-email-zhangchangzhong@huawei.com
Cc: stable@vger.kernel.org
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit a79305e156db3d24fcd8eb649cdb3c3b2350e5c2 upstream.
According to SAE-J1939-82 2015 (A.3.6 Row 2), a receiver should never
send TP.CM_CTS to the global address, so we can add a check in
j1939_can_recv() to drop messages with invalid source address.
Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Link: https://lore.kernel.org/all/1635431907-15617-3-git-send-email-zhangchangzhong@huawei.com
Cc: stable@vger.kernel.org
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit a4fbe70c5cb746441d56b28cf88161d9e0e25378 upstream.
The receiver should abort TP if 'total message size' in TP.CM_RTS and
TP.CM_BAM is less than 9 or greater than 1785 [1], but currently the
j1939 stack only checks the upper bound and the receiver will accept
the following broadcast message:
vcan1 18ECFF00 [8] 20 08 00 02 FF 00 23 01
vcan1 18EBFF00 [8] 01 00 00 00 00 00 00 00
vcan1 18EBFF00 [8] 02 00 FF FF FF FF FF FF
This patch adds check for the lower bound and abort illegal TP.
[1] SAE-J1939-82 A.3.4 Row 2 and A.3.6 Row 6.
Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Link: https://lore.kernel.org/all/1634203601-3460-1-git-send-email-zhangchangzhong@huawei.com
Cc: stable@vger.kernel.org
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 379743985ab6cfe2cbd32067cf4ed497baca6d06 upstream.
According to SAE-J1939-21, the data length of TP.DT must be 8 bytes, so
cancel session when receive unexpected TP.DT message.
Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Link: https://lore.kernel.org/all/1632972800-45091-1-git-send-email-zhangchangzhong@huawei.com
Cc: stable@vger.kernel.org
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit b504a884f6b5a77dac7d580ffa08e482f70d1a30 upstream.
When the session state is J1939_SESSION_DONE, j1939_tp_rxtimer() will
give an alert "rx timeout, send abort", but do nothing actually. Move
the alert into session active judgment condition, it is more
reasonable.
One of the scenarios is that j1939_tp_rxtimer() execute followed by
j1939_xtp_rx_abort_one(). After j1939_xtp_rx_abort_one(), the session
state is J1939_SESSION_DONE, then j1939_tp_rxtimer() give an alert.
Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Link: https://lore.kernel.org/all/20210906094219.95924-1-william.xuanziyang@huawei.com
Cc: stable@vger.kernel.org
Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 0c71437dd50dd687c15d8ca80b3b68f10bb21d63 upstream.
The j1939_session_deactivate() is decrementing the session ref-count and
potentially can free() the session. This would cause use-after-free
situation.
However, the code calling j1939_session_deactivate() does always hold
another reference to the session, so that it would not be free()ed in
this code path.
This patch adds a comment to make this clear and a WARN_ON, to ensure
that future changes will not violate this requirement. Further this
patch avoids dereferencing the session pointer as a precaution to avoid
use-after-free if the session is actually free()ed.
Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Link: https://lore.kernel.org/r/20210714111602.24021-1-o.rempel@pengutronix.de
Reported-by: Xiaochen Zou <xzou017@ucr.edu>
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit c6eea1c8bda56737752465a298dc6ce07d6b8ce3 upstream.
For receive side, the max time interval between two consecutive TP.DT
should be 750ms.
Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Link: https://lore.kernel.org/r/1625569210-47506-1-git-send-email-zhangchangzhong@huawei.com
Cc: linux-stable <stable@vger.kernel.org>
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 22c696fed25c63c7f67508309820358b94a96b6d upstream.
Set SOCK_RCU_FREE to let RCU to call sk_destruct() on completion.
Without this patch, we will run in to j1939_can_recv() after priv was
freed by j1939_sk_release()->j1939_sk_sock_destruct()
Fixes: 25fe97cb7620 ("can: j1939: move j1939_priv_put() into sk_destruct callback")
Link: https://lore.kernel.org/r/20210617130623.12705-1-o.rempel@pengutronix.de
Cc: linux-stable <stable@vger.kernel.org>
Reported-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Reported-by: syzbot+bdf710cfc41c186fdff3@syzkaller.appspotmail.com
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit fb8696ab14adadb2e3f6c17c18ed26b3ecd96691 upstream.
can_can_gw_rcv() is called under RCU protection, so after calling
can_rx_unregister(), we have to call synchronize_rcu in order to wait
for any RCU read-side critical sections to finish before removing the
kmem_cache entry with the referenced gw job entry.
Link: https://lore.kernel.org/r/20210618173645.2238-1-socketcan@hartkopp.net
Fixes: c1aabdf379bc ("can-gw: add netlink based CAN routing")
Cc: linux-stable <stable@vger.kernel.org>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit d5f9023fa61ee8b94f37a93f08e94b136cf1e463 upstream.
can_rx_register() callbacks may be called concurrently to the call to
can_rx_unregister(). The callbacks and callback data, though, are
protected by RCU and the struct sock reference count.
So the callback data is really attached to the life of sk, meaning
that it should be released on sk_destruct. However, bcm_remove_op()
calls tasklet_kill(), and RCU callbacks may be called under RCU
softirq, so that cannot be used on kernels before the introduction of
HRTIMER_MODE_SOFT.
However, bcm_rx_handler() is called under RCU protection, so after
calling can_rx_unregister(), we may call synchronize_rcu() in order to
wait for any RCU read-side critical sections to finish. That is,
bcm_rx_handler() won't be called anymore for those ops. So, we only
free them, after we do that synchronize_rcu().
Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol")
Link: https://lore.kernel.org/r/20210619161813.2098382-1-cascardo@canonical.com
Cc: linux-stable <stable@vger.kernel.org>
Reported-by: syzbot+0f7e7e5e2f4f40fa89c0@syzkaller.appspotmail.com
Reported-by: Norbert Slusarek <nslusarek@gmx.net>
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 2030043e616cab40f510299f09b636285e0a3678 upstream.
This patch fixes a Use-after-Free found by the syzbot.
The problem is that a skb is taken from the per-session skb queue,
without incrementing the ref count. This leads to a Use-after-Free if
the skb is taken concurrently from the session queue due to a CTS.
Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Link: https://lore.kernel.org/r/20210521115720.7533-1-o.rempel@pengutronix.de
Cc: Hillf Danton <hdanton@sina.com>
Cc: linux-stable <stable@vger.kernel.org>
Reported-by: syzbot+220c1a29987a9a490903@syzkaller.appspotmail.com
Reported-by: syzbot+45199c1b73b4013525cf@syzkaller.appspotmail.com
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 8d0caedb759683041d9db82069937525999ada53 upstream.
syzbot is reporting hung task at register_netdevice_notifier() [1] and
unregister_netdevice_notifier() [2], for cleanup_net() might perform
time consuming operations while CAN driver's raw/bcm/isotp modules are
calling {register,unregister}_netdevice_notifier() on each socket.
Change raw/bcm/isotp modules to call register_netdevice_notifier() from
module's __init function and call unregister_netdevice_notifier() from
module's __exit function, as with gw/j1939 modules are doing.
Link: https://syzkaller.appspot.com/bug?id=391b9498827788b3cc6830226d4ff5be87107c30 [1]
Link: https://syzkaller.appspot.com/bug?id=1724d278c83ca6e6df100a2e320c10d991cf2bce [2]
Link: https://lore.kernel.org/r/54a5f451-05ed-f977-8534-79e7aa2bcc8f@i-love.sakura.ne.jp
Cc: linux-stable <stable@vger.kernel.org>
Reported-by: syzbot <syzbot+355f8edb2ff45d5f95fa@syzkaller.appspotmail.com>
Reported-by: syzbot <syzbot+0f1827363a305f74996f@syzkaller.appspotmail.com>
Reviewed-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Tested-by: syzbot <syzbot+355f8edb2ff45d5f95fa@syzkaller.appspotmail.com>
Tested-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 5e87ddbe3942e27e939bdc02deb8579b0cbd8ecc upstream.
On 64-bit systems, struct bcm_msg_head has an added padding of 4 bytes between
struct members count and ival1. Even though all struct members are initialized,
the 4-byte hole will contain data from the kernel stack. This patch zeroes out
struct bcm_msg_head before usage, preventing infoleaks to userspace.
Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol")
Link: https://lore.kernel.org/r/trinity-7c1b2e82-e34f-4885-8060-2cd7a13769ce-1623532166177@3c-app-gmx-bs52
Cc: linux-stable <stable@vger.kernel.org>
Signed-off-by: Norbert Slusarek <nslusarek@gmx.net>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Test for two scenarios:
* When the fmod_ret program returns 0, the original function should
be called along with fentry and fexit programs.
* When the fmod_ret program returns a non-zero value, the original
function should not be called, no side effect should be observed and
fentry and fexit programs should be called.
The result from the kernel function call and whether a side-effect is
observed is returned via the retval attr of the BPF_PROG_TEST_RUN (bpf)
syscall.
Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200304191853.1529-8-kpsingh@chromium.org
Signed-off-by: Menglong Dong <imagedong@tencent.com>
[upstream commit faeb2dce084aff92d466c6ce68481989b815435b]
Add few kernel functions with various number of arguments,
their types and sizes for BPF trampoline testing to cover
different calling conventions.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191114185720.1641606-9-ast@kernel.org
[upstream commit b00628b1c7d595ae5b544e059c27b1f5828314b4]
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
[upstream commit 69c087ba6225b574afb6e505b72cb75242a3d844]
The bpf_for_each_map_elem() helper is introduced which
iterates all map elements with a callback function. The
helper signature looks like
long bpf_for_each_map_elem(map, callback_fn, callback_ctx, flags)
and for each map element, the callback_fn will be called. For example,
like hashmap, the callback signature may look like
long callback_fn(map, key, val, callback_ctx)
There are two known use cases for this. One is from upstream ([1]) where
a for_each_map_elem helper may help implement a timeout mechanism
in a more generic way. Another is from our internal discussion
for a firewall use case where a map contains all the rules. The packet
data can be compared to all these rules to decide allow or deny
the packet.
For array maps, users can already use a bounded loop to traverse
elements. Using this helper can avoid using bounded loop. For other
type of maps (e.g., hash maps) where bounded loop is hard or
impossible to use, this helper provides a convenient way to
operate on all elements.
For callback_fn, besides map and map element, a callback_ctx,
allocated on caller stack, is also passed to the callback
function. This callback_ctx argument can provide additional
input and allow to write to caller stack for output.
If the callback_fn returns 0, the helper will iterate through next
element if available. If the callback_fn returns 1, the helper
will stop iterating and returns to the bpf program. Other return
values are not used for now.
Currently, this helper is only available with jit. It is possible
to make it work with interpreter with so effort but I leave it
as the future work.
[1]: https://lore.kernel.org/bpf/20210122205415.113822-1-xiyou.wangcong@gmail.com/
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210226204925.3884923-1-yhs@fb.com
[upstream commit 457f44363a8894135c85b7a9afd2bd8196db24ab]
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>
[upstream commit 30897832d8b97e93833fb52c0a02951db3692ed2]
Adds support for both bpf_{sk, inode}_storage_{get, delete} to be used
in LSM programs. These helpers are not used for tracing programs
(currently) as their usage is tied to the life-cycle of the object and
should only be used where the owning object won't be freed (when the
owning object is passed as an argument to the LSM hook). Thus, they
are safer to use in LSM hooks than tracing. Usage of local storage in
tracing programs will probably follow a per function based whitelist
approach.
Since the UAPI helper signature for bpf_sk_storage expect a bpf_sock,
it, leads to a compilation warning for LSM programs, it's also updated
to accept a void * pointer instead.
Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200825182919.1118197-7-kpsingh@chromium.org
sclaibin