| Age | Commit message (Collapse) | Author |
|---|
|
If backlog handler is running during a tear down operation we may enqueue
data on the ingress msg queue while tear down is trying to free it.
sk_psock_backlog()
sk_psock_handle_skb()
skb_psock_skb_ingress()
sk_psock_skb_ingress_enqueue()
sk_psock_queue_msg(psock,msg)
spin_lock(ingress_lock)
sk_psock_zap_ingress()
_sk_psock_purge_ingerss_msg()
_sk_psock_purge_ingress_msg()
-- free ingress_msg list --
spin_unlock(ingress_lock)
spin_lock(ingress_lock)
list_add_tail(msg,ingress_msg) <- entry on list with no one
left to free it.
spin_unlock(ingress_lock)
To fix we only enqueue from backlog if the ENABLED bit is set. The tear
down logic clears the bit with ingress_lock set so we wont enqueue the
msg in the last step.
Fixes: 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210727160500.1713554-4-john.fastabend@gmail.com
|
|
Its possible if a socket is closed and the receive thread is under memory
pressure it may have cached a skb. We need to ensure these skbs are
free'd along with the normal ingress_skb queue.
Before 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()") tear
down and backlog processing both had sock_lock for the common case of
socket close or unhash. So it was not possible to have both running in
parrallel so all we would need is the kfree in those kernels.
But, latest kernels include the commit 799aa7f98d5e and this requires a
bit more work. Without the ingress_lock guarding reading/writing the
state->skb case its possible the tear down could run before the state
update causing it to leak memory or worse when the backlog reads the state
it could potentially run interleaved with the tear down and we might end up
free'ing the state->skb from tear down side but already have the reference
from backlog side. To resolve such races we wrap accesses in ingress_lock
on both sides serializing tear down and backlog case. In both cases this
only happens after an EAGAIN error case so having an extra lock in place
is likely fine. The normal path will skip the locks.
Note, we check state->skb before grabbing lock. This works because
we can only enqueue with the mutex we hold already. Avoiding a race
on adding state->skb after the check. And if tear down path is running
that is also fine if the tear down path then removes state->skb we
will simply set skb=NULL and the subsequent goto is skipped. This
slight complication avoids locking in normal case.
With this fix we no longer see this warning splat from tcp side on
socket close when we hit the above case with redirect to ingress self.
[224913.935822] WARNING: CPU: 3 PID: 32100 at net/core/stream.c:208 sk_stream_kill_queues+0x212/0x220
[224913.935841] Modules linked in: fuse overlay bpf_preload x86_pkg_temp_thermal intel_uncore wmi_bmof squashfs sch_fq_codel efivarfs ip_tables x_tables uas xhci_pci ixgbe mdio xfrm_algo xhci_hcd wmi
[224913.935897] CPU: 3 PID: 32100 Comm: fgs-bench Tainted: G I 5.14.0-rc1alu+ #181
[224913.935908] Hardware name: Dell Inc. Precision 5820 Tower/002KVM, BIOS 1.9.2 01/24/2019
[224913.935914] RIP: 0010:sk_stream_kill_queues+0x212/0x220
[224913.935923] Code: 8b 83 20 02 00 00 85 c0 75 20 5b 5d 41 5c 41 5d 41 5e 41 5f c3 48 89 df e8 2b 11 fe ff eb c3 0f 0b e9 7c ff ff ff 0f 0b eb ce <0f> 0b 5b 5d 41 5c 41 5d 41 5e 41 5f c3 90 0f 1f 44 00 00 41 57 41
[224913.935932] RSP: 0018:ffff88816271fd38 EFLAGS: 00010206
[224913.935941] RAX: 0000000000000ae8 RBX: ffff88815acd5240 RCX: dffffc0000000000
[224913.935948] RDX: 0000000000000003 RSI: 0000000000000ae8 RDI: ffff88815acd5460
[224913.935954] RBP: ffff88815acd5460 R08: ffffffff955c0ae8 R09: fffffbfff2e6f543
[224913.935961] R10: ffffffff9737aa17 R11: fffffbfff2e6f542 R12: ffff88815acd5390
[224913.935967] R13: ffff88815acd5480 R14: ffffffff98d0c080 R15: ffffffff96267500
[224913.935974] FS: 00007f86e6bd1700(0000) GS:ffff888451cc0000(0000) knlGS:0000000000000000
[224913.935981] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[224913.935988] CR2: 000000c0008eb000 CR3: 00000001020e0005 CR4: 00000000003706e0
[224913.935994] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[224913.936000] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[224913.936007] Call Trace:
[224913.936016] inet_csk_destroy_sock+0xba/0x1f0
[224913.936033] __tcp_close+0x620/0x790
[224913.936047] tcp_close+0x20/0x80
[224913.936056] inet_release+0x8f/0xf0
[224913.936070] __sock_release+0x72/0x120
[224913.936083] sock_close+0x14/0x20
Fixes: a136678c0bdbb ("bpf: sk_msg, zap ingress queue on psock down")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210727160500.1713554-3-john.fastabend@gmail.com
|
|
We don't want strparser to run and pass skbs into skmsg handlers when
the psock is null. We just sk_drop them in this case. When removing
a live socket from map it means extra drops that we do not need to
incur. Move the zap below strparser close to avoid this condition.
This way we stop the stream parser first stopping it from processing
packets and then delete the psock.
Fixes: a136678c0bdbb ("bpf: sk_msg, zap ingress queue on psock down")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210727160500.1713554-2-john.fastabend@gmail.com
|
|
If skb_linearize is needed and fails we could leak a msg on the error
handling. To fix ensure we kfree the msg block before returning error.
Found during code review.
Fixes: 4363023d2668e ("bpf, sockmap: Avoid failures from skb_to_sgvec when skb has frag_list")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Cong Wang <cong.wang@bytedance.com>
Link: https://lore.kernel.org/bpf/20210712195546.423990-2-john.fastabend@gmail.com
|
|
It is hard to observe packet drops without increasing relevant
drop counters, here we should increase sk->sk_drops which is
a protocol-independent counter. Fortunately psock is always
associated with a struct sock, we can just use psock->sk.
Suggested-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210615021342.7416-9-xiyou.wangcong@gmail.com
|
|
sk_psock_skb_redirect() only takes skb as a parameter, we
will need to know where this skb is from, so just pass
the source psock to this function as a new parameter.
This patch prepares for the next one.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210615021342.7416-8-xiyou.wangcong@gmail.com
|
|
Currently sk_psock_verdict_apply() is void, but it handles some
error conditions too. Its caller is impossible to learn whether
it succeeds or fails, especially sk_psock_verdict_recv().
Make it return int to indicate error cases and propagate errors
to callers properly.
Fixes: ef5659280eb1 ("bpf, sockmap: Allow skipping sk_skb parser program")
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210615021342.7416-7-xiyou.wangcong@gmail.com
|
|
If the dest psock does not set SK_PSOCK_TX_ENABLED,
the skb can't be queued anywhere so must be dropped.
This one is found during code review.
Fixes: 799aa7f98d53 ("skmsg: Avoid lock_sock() in sk_psock_backlog()")
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210615021342.7416-6-xiyou.wangcong@gmail.com
|
|
When we drop skb inside sk_psock_skb_redirect(), we have to clear
its skb->_sk_redir pointer too, otherwise kfree_skb() would
misinterpret it as a valid skb->_skb_refdst and dst_release()
would eventually complain.
Fixes: e3526bb92a20 ("skmsg: Move sk_redir from TCP_SKB_CB to skb")
Reported-by: Jiang Wang <jiang.wang@bytedance.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210615021342.7416-5-xiyou.wangcong@gmail.com
|
|
I tried to reuse sk_msg_wait_data() for different protocols,
but it turns out it can not be simply reused. For example,
UDP actually uses two queues to receive skb:
udp_sk(sk)->reader_queue and sk->sk_receive_queue. So we have
to check both of them to know whether we have received any
packet.
Also, UDP does not lock the sock during BH Rx path, it makes
no sense for its ->recvmsg() to lock the sock. It is always
possible for ->recvmsg() to be called before packets actually
arrive in the receive queue, we just use best effort to make
it accurate here.
Fixes: 1f5be6b3b063 ("udp: Implement udp_bpf_recvmsg() for sockmap")
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210615021342.7416-2-xiyou.wangcong@gmail.com
|
|
Conflicts:
MAINTAINERS
- keep Chandrasekar
drivers/net/ethernet/mellanox/mlx5/core/en_main.c
- simple fix + trust the code re-added to param.c in -next is fine
include/linux/bpf.h
- trivial
include/linux/ethtool.h
- trivial, fix kdoc while at it
include/linux/skmsg.h
- move to relevant place in tcp.c, comment re-wrapped
net/core/skmsg.c
- add the sk = sk // sk = NULL around calls
net/tipc/crypto.c
- trivial
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Incorrect accounting fwd_alloc can result in a warning when the socket
is torn down,
[18455.319240] WARNING: CPU: 0 PID: 24075 at net/core/stream.c:208 sk_stream_kill_queues+0x21f/0x230
[...]
[18455.319543] Call Trace:
[18455.319556] inet_csk_destroy_sock+0xba/0x1f0
[18455.319577] tcp_rcv_state_process+0x1b4e/0x2380
[18455.319593] ? lock_downgrade+0x3a0/0x3a0
[18455.319617] ? tcp_finish_connect+0x1e0/0x1e0
[18455.319631] ? sk_reset_timer+0x15/0x70
[18455.319646] ? tcp_schedule_loss_probe+0x1b2/0x240
[18455.319663] ? lock_release+0xb2/0x3f0
[18455.319676] ? __release_sock+0x8a/0x1b0
[18455.319690] ? lock_downgrade+0x3a0/0x3a0
[18455.319704] ? lock_release+0x3f0/0x3f0
[18455.319717] ? __tcp_close+0x2c6/0x790
[18455.319736] ? tcp_v4_do_rcv+0x168/0x370
[18455.319750] tcp_v4_do_rcv+0x168/0x370
[18455.319767] __release_sock+0xbc/0x1b0
[18455.319785] __tcp_close+0x2ee/0x790
[18455.319805] tcp_close+0x20/0x80
This currently happens because on redirect case we do skb_set_owner_r()
with the original sock. This increments the fwd_alloc memory accounting
on the original sock. Then on redirect we may push this into the queue
of the psock we are redirecting to. When the skb is flushed from the
queue we give the memory back to the original sock. The problem is if
the original sock is destroyed/closed with skbs on another psocks queue
then the original sock will not have a way to reclaim the memory before
being destroyed. Then above warning will be thrown
sockA sockB
sk_psock_strp_read()
sk_psock_verdict_apply()
-- SK_REDIRECT --
sk_psock_skb_redirect()
skb_queue_tail(psock_other->ingress_skb..)
sk_close()
sock_map_unref()
sk_psock_put()
sk_psock_drop()
sk_psock_zap_ingress()
At this point we have torn down our own psock, but have the outstanding
skb in psock_other. Note that SK_PASS doesn't have this problem because
the sk_psock_drop() logic releases the skb, its still associated with
our psock.
To resolve lets only account for sockets on the ingress queue that are
still associated with the current socket. On the redirect case we will
check memory limits per 6fa9201a89898, but will omit fwd_alloc accounting
until skb is actually enqueued. When the skb is sent via skb_send_sock_locked
or received with sk_psock_skb_ingress memory will be claimed on psock_other.
Fixes: 6fa9201a89898 ("bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self")
Reported-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/161731444013.68884.4021114312848535993.stgit@john-XPS-13-9370
|
|
Although these two functions are only used by TCP, they are not
specific to TCP at all, both operate on skmsg and ingress_msg,
so fit in net/core/skmsg.c very well.
And we will need them for non-TCP, so rename and move them to
skmsg.c and export them to modules.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331023237.41094-13-xiyou.wangcong@gmail.com
|
|
Currently sockmap calls into each protocol to update the struct
proto and replace it. This certainly won't work when the protocol
is implemented as a module, for example, AF_UNIX.
Introduce a new ops sk->sk_prot->psock_update_sk_prot(), so each
protocol can implement its own way to replace the struct proto.
This also helps get rid of symbol dependencies on CONFIG_INET.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331023237.41094-11-xiyou.wangcong@gmail.com
|
|
Reusing BPF_SK_SKB_STREAM_VERDICT is possible but its name is
confusing and more importantly we still want to distinguish them
from user-space. So we can just reuse the stream verdict code but
introduce a new type of eBPF program, skb_verdict. Users are not
allowed to attach stream_verdict and skb_verdict programs to the
same map.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-10-xiyou.wangcong@gmail.com
|
|
This function is only called in process context.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-7-xiyou.wangcong@gmail.com
|
|
The RCU callback sk_psock_destroy() only queues work psock->gc,
so we can just switch to rcu work to simplify the code.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-6-xiyou.wangcong@gmail.com
|
|
We do not have to lock the sock to avoid losing sk_socket,
instead we can purge all the ingress queues when we close
the socket. Sending or receiving packets after orphaning
socket makes no sense.
We do purge these queues when psock refcnt reaches zero but
here we want to purge them explicitly in sock_map_close().
There are also some nasty race conditions on testing bit
SK_PSOCK_TX_ENABLED and queuing/canceling the psock work,
we can expand psock->ingress_lock a bit to protect them too.
As noticed by John, we still have to lock the psock->work,
because the same work item could be running concurrently on
different CPU's.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
|
|
Currently we rely on lock_sock to protect ingress_msg,
it is too big for this, we can actually just use a spinlock
to protect this list like protecting other skb queues.
__tcp_bpf_recvmsg() is still special because of peeking,
it still has to use lock_sock.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-3-xiyou.wangcong@gmail.com
|
|
Currently we purge the ingress_skb queue only when psock
refcnt goes down to 0, so locking the queue is not necessary,
but in order to be called during ->close, we have to lock it
here.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-2-xiyou.wangcong@gmail.com
|
|
It is now nearly identical to bpf_prog_run_pin_on_cpu() and
it has an unused parameter 'psock', so we can just get rid
of it and call bpf_prog_run_pin_on_cpu() directly.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210223184934.6054-9-xiyou.wangcong@gmail.com
|
|
It is only used within skmsg.c so can become static.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210223184934.6054-8-xiyou.wangcong@gmail.com
|
|
These two eBPF programs are tied to BPF_SK_SKB_STREAM_PARSER
and BPF_SK_SKB_STREAM_VERDICT, rename them to reflect the fact
they are only used for TCP. And save the name 'skb_verdict' for
general use later.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Lorenz Bauer <lmb@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210223184934.6054-6-xiyou.wangcong@gmail.com
|
|
Currently TCP_SKB_CB() is hard-coded in skmsg code, it certainly
does not work for any other non-TCP protocols. We can move them to
skb ext, but it introduces a memory allocation on fast path.
Fortunately, we only need to a word-size to store all the information,
because the flags actually only contains 1 bit so can be just packed
into the lowest bit of the "pointer", which is stored as unsigned
long.
Inside struct sk_buff, '_skb_refdst' can be reused because skb dst is
no longer needed after ->sk_data_ready() so we can just drop it.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210223184934.6054-5-xiyou.wangcong@gmail.com
|
|
Currently, we compute ->data_end with a compile-time constant
offset of skb. But as Jakub pointed out, we can actually compute
it in eBPF JIT code at run-time, so that we can competely get
rid of ->data_end. This is similar to skb_shinfo(skb) computation
in bpf_convert_shinfo_access().
Suggested-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210223184934.6054-4-xiyou.wangcong@gmail.com
|
|
struct sk_psock_parser is embedded in sk_psock, it is
unnecessary as skb verdict also uses ->saved_data_ready.
We can simply fold these fields into sk_psock, and get rid
of ->enabled.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210223184934.6054-3-xiyou.wangcong@gmail.com
|
|
As suggested by John, clean up sockmap related Kconfigs:
Reduce the scope of CONFIG_BPF_STREAM_PARSER down to TCP stream
parser, to reflect its name.
Make the rest sockmap code simply depend on CONFIG_BPF_SYSCALL
and CONFIG_INET, the latter is still needed at this point because
of TCP/UDP proto update. And leave CONFIG_NET_SOCK_MSG untouched,
as it is used by non-sockmap cases.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Lorenz Bauer <lmb@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210223184934.6054-2-xiyou.wangcong@gmail.com
|
|
sk_psock_destroy() is a RCU callback, I can't see any reason why
it could be used outside.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Cc: Lorenz Bauer <lmb@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210127221501.46866-1-xiyou.wangcong@gmail.com
|
|
When skb has a frag_list its possible for skb_to_sgvec() to fail. This
happens when the scatterlist has fewer elements to store pages than would
be needed for the initial skb plus any of its frags.
This case appears rare, but is possible when running an RX parser/verdict
programs exposed to the internet. Currently, when this happens we throw
an error, break the pipe, and kfree the msg. This effectively breaks the
application or forces it to do a retry.
Lets catch this case and handle it by doing an skb_linearize() on any
skb we receive with frags. At this point skb_to_sgvec should not fail
because the failing conditions would require frags to be in place.
Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/160556576837.73229.14800682790808797635.stgit@john-XPS-13-9370
|
|
If the skb_verdict_prog redirects an skb knowingly to itself, fix your
BPF program this is not optimal and an abuse of the API please use
SK_PASS. That said there may be cases, such as socket load balancing,
where picking the socket is hashed based or otherwise picks the same
socket it was received on in some rare cases. If this happens we don't
want to confuse userspace giving them an EAGAIN error if we can avoid
it.
To avoid double accounting in these cases. At the moment even if the
skb has already been charged against the sockets rcvbuf and forward
alloc we check it again and do set_owner_r() causing it to be orphaned
and recharged. For one this is useless work, but more importantly we
can have a case where the skb could be put on the ingress queue, but
because we are under memory pressure we return EAGAIN. The trouble
here is the skb has already been accounted for so any rcvbuf checks
include the memory associated with the packet already. This rolls
up and can result in unnecessary EAGAIN errors in userspace read()
calls.
Fix by doing an unlikely check and skipping checks if skb->sk == sk.
Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/160556574804.73229.11328201020039674147.stgit@john-XPS-13-9370
|
|
If a socket redirects to itself and it is under memory pressure it is
possible to get a socket stuck so that recv() returns EAGAIN and the
socket can not advance for some time. This happens because when
redirecting a skb to the same socket we received the skb on we first
check if it is OK to enqueue the skb on the receiving socket by checking
memory limits. But, if the skb is itself the object holding the memory
needed to enqueue the skb we will keep retrying from kernel side
and always fail with EAGAIN. Then userspace will get a recv() EAGAIN
error if there are no skbs in the psock ingress queue. This will continue
until either some skbs get kfree'd causing the memory pressure to
reduce far enough that we can enqueue the pending packet or the
socket is destroyed. In some cases its possible to get a socket
stuck for a noticeable amount of time if the socket is only receiving
skbs from sk_skb verdict programs. To reproduce I make the socket
memory limits ridiculously low so sockets are always under memory
pressure. More often though if under memory pressure it looks like
a spurious EAGAIN error on user space side causing userspace to retry
and typically enough has moved on the memory side that it works.
To fix skip memory checks and skb_orphan if receiving on the same
sock as already assigned.
For SK_PASS cases this is easy, its always the same socket so we
can just omit the orphan/set_owner pair.
For backlog cases we need to check skb->sk and decide if the orphan
and set_owner pair are needed.
Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/160556572660.73229.12566203819812939627.stgit@john-XPS-13-9370
|
|
We use skb->size with sk_rmem_scheduled() which is not correct. Instead
use truesize to align with socket and tcp stack usage of sk_rmem_schedule.
Suggested-by: Daniel Borkman <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/160556570616.73229.17003722112077507863.stgit@john-XPS-13-9370
|
|
Fix sockmap sk_skb programs so that they observe sk_rcvbuf limits. This
allows users to tune SO_RCVBUF and sockmap will honor them.
We can refactor the if(charge) case out in later patches. But, keep this
fix to the point.
Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path")
Suggested-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/160556568657.73229.8404601585878439060.stgit@john-XPS-13-9370
|
|
Currently, we often run with a nop parser namely one that just does
this, 'return skb->len'. This happens when either our verdict program
can handle streaming data or it is only looking at socket data such
as IP addresses and other metadata associated with the flow. The second
case is common for a L3/L4 proxy for instance.
So lets allow loading programs without the parser then we can skip
the stream parser logic and avoid having to add a BPF program that
is effectively a nop.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
|
|
Move skb->sk assignment out of sk_psock_bpf_run() and into individual
callers. Then we can use proper skb_set_owner_r() call to assign a
sk to a skb. This improves things by also charging the truesize against
the sockets sk_rmem_alloc counter. With this done we get some accounting
in place to ensure the memory associated with skbs on the workqueue are
still being accounted for somewhere. Finally, by using skb_set_owner_r
the destructor is setup so we can just let the normal skb_kfree logic
recover the memory. Combined with previous patch dropping skb_orphan()
we now can recover from memory pressure and maintain accounting.
Note, we will charge the skbs against their originating socket even
if being redirected into another socket. Once the skb completes the
redirect op the kfree_skb will give the memory back. This is important
because if we charged the socket we are redirecting to (like it was
done before this series) the sock_writeable() test could fail because
of the skb trying to be sent is already charged against the socket.
Also TLS case is special. Here we wait until we have decided not to
simply PASS the packet up the stack. In the case where we PASS the
packet up the stack we already have an skb which is accounted for on
the TLS socket context.
For the parser case we continue to just set/clear skb->sk this is
because the skb being used here may be combined with other skbs or
turned into multiple skbs depending on the parser logic. For example
the parser could request a payload length greater than skb->len so
that the strparser needs to collect multiple skbs. At any rate
the final result will be handled in the strparser recv callback.
Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/160226867513.5692.10579573214635925960.stgit@john-Precision-5820-Tower
|
|
Calling skb_orphan() is unnecessary in the strp rcv handler because the skb
is from a skb_clone() in __strp_recv. So it never has a destructor or a
sk assigned. Plus its confusing to read because it might hint to the reader
that the skb could have an sk assigned which is not true. Even if we did
have an sk assigned it would be cleaner to simply wait for the upcoming
kfree_skb().
Additionally, move the comment about strparser clone up so its closer to
the logic it is describing and add to it so that it is more complete.
Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/160226865548.5692.9098315689984599579.stgit@john-Precision-5820-Tower
|
|
In the sk_skb redirect case we didn't handle the case where we overrun
the sk_rmem_alloc entry on ingress redirect or sk_wmem_alloc on egress.
Because we didn't have anything implemented we simply dropped the skb.
This meant data could be dropped if socket memory accounting was in
place.
This fixes the above dropped data case by moving the memory checks
later in the code where we actually do the send or recv. This pushes
those checks into the workqueue and allows us to return an EAGAIN error
which in turn allows us to try again later from the workqueue.
Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/160226863689.5692.13861422742592309285.stgit@john-Precision-5820-Tower
|
|
The skb_set_owner_w is unnecessary here. The sendpage call will create a
fresh skb and set the owner correctly from workqueue. Its also not entirely
harmless because it consumes cycles, but also impacts resource accounting
by increasing sk_wmem_alloc. This is charging the socket we are going to
send to for the skb, but we will put it on the workqueue for some time
before this happens so we are artifically inflating sk_wmem_alloc for
this period. Further, we don't know how many skbs will be used to send the
packet or how it will be broken up when sent over the new socket so
charging it with one big sum is also not correct when the workqueue may
break it up if facing memory pressure. Seeing we don't know how/when
this is going to be sent drop the early accounting.
A later patch will do proper accounting charged on receive socket for
the case where skbs get enqueued on the workqueue.
Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/160226861708.5692.17964237936462425136.stgit@john-Precision-5820-Tower
|
|
When we receive an skb and the ingress skb verdict program returns
SK_PASS we currently set the ingress flag and put it on the workqueue
so it can be turned into a sk_msg and put on the sk_msg ingress queue.
Then finally telling userspace with data_ready hook.
Here we observe that if the workqueue is empty then we can try to
convert into a sk_msg type and call data_ready directly without
bouncing through a workqueue. Its a common pattern to have a recv
verdict program for visibility that always returns SK_PASS. In this
case unless there is an ENOMEM error or we overrun the socket we
can avoid the workqueue completely only using it when we fall back
to error cases caused by memory pressure.
By doing this we eliminate another case where data may be dropped
if errors occur on memory limits in workqueue.
Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/160226859704.5692.12929678876744977669.stgit@john-Precision-5820-Tower
|
|
For sk_skb case where skb_verdict program returns SK_PASS to continue to
pass packet up the stack, the memory limits were already checked before
enqueuing in skb_queue_tail from TCP side. So, lets remove the extra checks
here. The theory is if the TCP stack believes we have memory to receive
the packet then lets trust the stack and not double check the limits.
In fact the accounting here can cause a drop if sk_rmem_alloc has increased
after the stack accepted this packet, but before the duplicate check here.
And worse if this happens because TCP stack already believes the data has
been received there is no retransmit.
Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/160226857664.5692.668205469388498375.stgit@john-Precision-5820-Tower
|
|
We got slightly different patches removing a double word
in a comment in net/ipv4/raw.c - picked the version from net.
Simple conflict in drivers/net/ethernet/ibm/ibmvnic.c. Use cached
values instead of VNIC login response buffer (following what
commit 507ebe6444a4 ("ibmvnic: Fix use-after-free of VNIC login
response buffer") did).
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Replace the existing /* fall through */ comments and its variants with
the new pseudo-keyword macro fallthrough[1]. Also, remove unnecessary
fall-through markings when it is the case.
[1] https://www.kernel.org/doc/html/v5.7/process/deprecated.html?highlight=fallthrough#implicit-switch-case-fall-through
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
|
|
Initializing psock->sk_proto and other saved callbacks is only
done in sk_psock_update_proto, after sk_psock_init has returned.
The logic for this is difficult to follow, and needlessly complex.
Instead, initialize psock->sk_proto whenever we allocate a new
psock. Additionally, assert the following invariants:
* The SK has no ULP: ULP does it's own finagling of sk->sk_prot
* sk_user_data is unused: we need it to store sk_psock
Protect our access to sk_user_data with sk_callback_lock, which
is what other users like reuseport arrays, etc. do.
The result is that an sk_psock is always fully initialized, and
that psock->sk_proto is always the "original" struct proto.
The latter allows us to use psock->sk_proto when initializing
IPv6 TCP / UDP callbacks for sockmap.
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200821102948.21918-2-lmb@cloudflare.com
|
|
If an ingress verdict program specifies message sizes greater than
skb->len and there is an ENOMEM error due to memory pressure we
may call the rcv_msg handler outside the strp_data_ready() caller
context. This is because on an ENOMEM error the strparser will
retry from a workqueue. The caller currently protects the use of
psock by calling the strp_data_ready() inside a rcu_read_lock/unlock
block.
But, in above workqueue error case the psock is accessed outside
the read_lock/unlock block of the caller. So instead of using
psock directly we must do a look up against the sk again to
ensure the psock is available.
There is an an ugly piece here where we must handle
the case where we paused the strp and removed the psock. On
psock removal we first pause the strparser and then remove
the psock. If the strparser is paused while an skb is
scheduled on the workqueue the skb will be dropped on the
flow and kfree_skb() is called. If the workqueue manages
to get called before we pause the strparser but runs the rcvmsg
callback after the psock is removed we will hit the unlikely
case where we run the sockmap rcvmsg handler but do not have
a psock. For now we will follow strparser logic and drop the
skb on the floor with skb_kfree(). This is ugly because the
data is dropped. To date this has not caused problems in practice
because either the application controlling the sockmap is
coordinating with the datapath so that skbs are "flushed"
before removal or we simply wait for the sock to be closed before
removing it.
This patch fixes the describe RCU bug and dropping the skb doesn't
make things worse. Future patches will improve this by allowing
the normal case where skbs are not merged to skip the strparser
altogether. In practice many (most?) use cases have no need to
merge skbs so its both a code complexity hit as seen above and
a performance issue. For example, in the Cilium case we always
set the strparser up to return sbks 1:1 without any merging and
have avoided above issues.
Fixes: e91de6afa81c1 ("bpf: Fix running sk_skb program types with ktls")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/159312679888.18340.15248924071966273998.stgit@john-XPS-13-9370
|
|
There are two paths to generate the below RCU splat the first and
most obvious is the result of the BPF verdict program issuing a
redirect on a TLS socket (This is the splat shown below). Unlike
the non-TLS case the caller of the *strp_read() hooks does not
wrap the call in a rcu_read_lock/unlock. Then if the BPF program
issues a redirect action we hit the RCU splat.
However, in the non-TLS socket case the splat appears to be
relatively rare, because the skmsg caller into the strp_data_ready()
is wrapped in a rcu_read_lock/unlock. Shown here,
static void sk_psock_strp_data_ready(struct sock *sk)
{
struct sk_psock *psock;
rcu_read_lock();
psock = sk_psock(sk);
if (likely(psock)) {
if (tls_sw_has_ctx_rx(sk)) {
psock->parser.saved_data_ready(sk);
} else {
write_lock_bh(&sk->sk_callback_lock);
strp_data_ready(&psock->parser.strp);
write_unlock_bh(&sk->sk_callback_lock);
}
}
rcu_read_unlock();
}
If the above was the only way to run the verdict program we
would be safe. But, there is a case where the strparser may throw an
ENOMEM error while parsing the skb. This is a result of a failed
skb_clone, or alloc_skb_for_msg while building a new merged skb when
the msg length needed spans multiple skbs. This will in turn put the
skb on the strp_wrk workqueue in the strparser code. The skb will
later be dequeued and verdict programs run, but now from a
different context without the rcu_read_lock()/unlock() critical
section in sk_psock_strp_data_ready() shown above. In practice
I have not seen this yet, because as far as I know most users of the
verdict programs are also only working on single skbs. In this case no
merge happens which could trigger the above ENOMEM errors. In addition
the system would need to be under memory pressure. For example, we
can't hit the above case in selftests because we missed having tests
to merge skbs. (Added in later patch)
To fix the below splat extend the rcu_read_lock/unnlock block to
include the call to sk_psock_tls_verdict_apply(). This will fix both
TLS redirect case and non-TLS redirect+error case. Also remove
psock from the sk_psock_tls_verdict_apply() function signature its
not used there.
[ 1095.937597] WARNING: suspicious RCU usage
[ 1095.940964] 5.7.0-rc7-02911-g463bac5f1ca79 #1 Tainted: G W
[ 1095.944363] -----------------------------
[ 1095.947384] include/linux/skmsg.h:284 suspicious rcu_dereference_check() usage!
[ 1095.950866]
[ 1095.950866] other info that might help us debug this:
[ 1095.950866]
[ 1095.957146]
[ 1095.957146] rcu_scheduler_active = 2, debug_locks = 1
[ 1095.961482] 1 lock held by test_sockmap/15970:
[ 1095.964501] #0: ffff9ea6b25de660 (sk_lock-AF_INET){+.+.}-{0:0}, at: tls_sw_recvmsg+0x13a/0x840 [tls]
[ 1095.968568]
[ 1095.968568] stack backtrace:
[ 1095.975001] CPU: 1 PID: 15970 Comm: test_sockmap Tainted: G W 5.7.0-rc7-02911-g463bac5f1ca79 #1
[ 1095.977883] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
[ 1095.980519] Call Trace:
[ 1095.982191] dump_stack+0x8f/0xd0
[ 1095.984040] sk_psock_skb_redirect+0xa6/0xf0
[ 1095.986073] sk_psock_tls_strp_read+0x1d8/0x250
[ 1095.988095] tls_sw_recvmsg+0x714/0x840 [tls]
v2: Improve commit message to identify non-TLS redirect plus error case
condition as well as more common TLS case. In the process I decided
doing the rcu_read_unlock followed by the lock/unlock inside branches
was unnecessarily complex. We can just extend the current rcu block
and get the same effeective without the shuffling and branching.
Thanks Martin!
Fixes: e91de6afa81c1 ("bpf: Fix running sk_skb program types with ktls")
Reported-by: Jakub Sitnicki <jakub@cloudflare.com>
Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/159312677907.18340.11064813152758406626.stgit@john-XPS-13-9370
|
|
KTLS uses a stream parser to collect TLS messages and send them to
the upper layer tls receive handler. This ensures the tls receiver
has a full TLS header to parse when it is run. However, when a
socket has BPF_SK_SKB_STREAM_VERDICT program attached before KTLS
is enabled we end up with two stream parsers running on the same
socket.
The result is both try to run on the same socket. First the KTLS
stream parser runs and calls read_sock() which will tcp_read_sock
which in turn calls tcp_rcv_skb(). This dequeues the skb from the
sk_receive_queue. When this is done KTLS code then data_ready()
callback which because we stacked KTLS on top of the bpf stream
verdict program has been replaced with sk_psock_start_strp(). This
will in turn kick the stream parser again and eventually do the
same thing KTLS did above calling into tcp_rcv_skb() and dequeuing
a skb from the sk_receive_queue.
At this point the data stream is broke. Part of the stream was
handled by the KTLS side some other bytes may have been handled
by the BPF side. Generally this results in either missing data
or more likely a "Bad Message" complaint from the kTLS receive
handler as the BPF program steals some bytes meant to be in a
TLS header and/or the TLS header length is no longer correct.
We've already broke the idealized model where we can stack ULPs
in any order with generic callbacks on the TX side to handle this.
So in this patch we do the same thing but for RX side. We add
a sk_psock_strp_enabled() helper so TLS can learn a BPF verdict
program is running and add a tls_sw_has_ctx_rx() helper so BPF
side can learn there is a TLS ULP on the socket.
Then on BPF side we omit calling our stream parser to avoid
breaking the data stream for the KTLS receiver. Then on the
KTLS side we call BPF_SK_SKB_STREAM_VERDICT once the KTLS
receiver is done with the packet but before it posts the
msg to userspace. This gives us symmetry between the TX and
RX halfs and IMO makes it usable again. On the TX side we
process packets in this order BPF -> TLS -> TCP and on
the receive side in the reverse order TCP -> TLS -> BPF.
Discovered while testing OpenSSL 3.0 Alpha2.0 release.
Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/159079361946.5745.605854335665044485.stgit@john-Precision-5820-Tower
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
We will need this block of code called from tls context shortly
lets refactor the redirect logic so its easy to use. This also
cleans up the switch stmt so we have fewer fallthrough cases.
No logic changes are intended.
Fixes: d829e9c4112b5 ("tls: convert to generic sk_msg interface")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/159079360110.5745.7024009076049029819.stgit@john-Precision-5820-Tower
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
All of these cases are strictly of the form:
preempt_disable();
BPF_PROG_RUN(...);
preempt_enable();
Replace this with bpf_prog_run_pin_on_cpu() which wraps BPF_PROG_RUN()
with:
migrate_disable();
BPF_PROG_RUN(...);
migrate_enable();
On non RT enabled kernels this maps to preempt_disable/enable() and on RT
enabled kernels this solely prevents migration, which is sufficient as
there is no requirement to prevent reentrancy to any BPF program from a
preempting task. The only requirement is that the program stays on the same
CPU.
Therefore, this is a trivially correct transformation.
The seccomp loop does not need protection over the loop. It only needs
protection per BPF filter program
[ tglx: Converted to bpf_prog_run_pin_on_cpu() ]
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200224145643.691493094@linutronix.de
|
|
sk_user_data can hold a pointer to an object that is not intended to be
shared between the parent socket and the child that gets a pointer copy on
clone. This is the case when sk_user_data points at reference-counted
object, like struct sk_psock.
One way to resolve it is to tag the pointer with a no-copy flag by
repurposing its lowest bit. Based on the bit-flag value we clear the child
sk_user_data pointer after cloning the parent socket.
The no-copy flag is stored in the pointer itself as opposed to externally,
say in socket flags, to guarantee that the pointer and the flag are copied
from parent to child socket in an atomic fashion. Parent socket state is
subject to change while copying, we don't hold any locks at that time.
This approach relies on an assumption that sk_user_data holds a pointer to
an object aligned at least 2 bytes. A manual audit of existing users of
rcu_dereference_sk_user_data helper confirms our assumption.
Also, an RCU-protected sk_user_data is not likely to hold a pointer to a
char value or a pathological case of "struct { char c; }". To be safe, warn
when the flag-bit is set when setting sk_user_data to catch any future
misuses.
It is worth considering why clearing sk_user_data unconditionally is not an
option. There exist users, DRBD, NVMe, and Xen drivers being among them,
that rely on the pointer being copied when cloning the listening socket.
Potentially we could distinguish these users by checking if the listening
socket has been created in kernel-space via sock_create_kern, and hence has
sk_kern_sock flag set. However, this is not the case for NVMe and Xen
drivers, which create sockets without marking them as belonging to the
kernel.
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200218171023.844439-3-jakub@cloudflare.com
|
|
As John Fastabend reports [0], psock state tear-down can happen on receive
path *after* unlocking the socket, if the only other psock user, that is
sockmap or sockhash, releases its psock reference before tcp_bpf_recvmsg
does so:
tcp_bpf_recvmsg()
psock = sk_psock_get(sk) <- refcnt 2
lock_sock(sk);
...
sock_map_free() <- refcnt 1
release_sock(sk)
sk_psock_put() <- refcnt 0
Remove the lockdep check for socket lock in psock tear-down that got
introduced in 7e81a3530206 ("bpf: Sockmap, ensure sock lock held during
tear down").
[0] https://lore.kernel.org/netdev/5e25dc995d7d_74082aaee6e465b441@john-XPS-13-9370.notmuch/
Fixes: 7e81a3530206 ("bpf: Sockmap, ensure sock lock held during tear down")
Reported-by: syzbot+d73682fcf7fee6982fe3@syzkaller.appspotmail.com
Suggested-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
