diff options
author | Jakub Kicinski <kuba@kernel.org> | 2020-11-19 12:26:09 -0800 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2020-11-19 12:26:10 -0800 |
commit | e6ea60bac1ee28bb46232f8c2ecd3a3fbb9011e0 (patch) | |
tree | f119a3b701852f184b6131405470de0f3969c783 /net/core | |
parent | 90b49784814c10c0f028646f95cc2c2848696712 (diff) | |
parent | 2801a5da5b25b7af9dd2addd19b2315c02d17b64 (diff) | |
download | linux-e6ea60bac1ee28bb46232f8c2ecd3a3fbb9011e0.tar.bz2 |
Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf
Alexei Starovoitov says:
====================
1) libbpf should not attempt to load unused subprogs, from Andrii.
2) Make strncpy_from_user() mask out bytes after NUL terminator, from Daniel.
3) Relax return code check for subprograms in the BPF verifier, from Dmitrii.
4) Fix several sockmap issues, from John.
* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
fail_function: Remove a redundant mutex unlock
selftest/bpf: Test bpf_probe_read_user_str() strips trailing bytes after NUL
lib/strncpy_from_user.c: Mask out bytes after NUL terminator.
libbpf: Fix VERSIONED_SYM_COUNT number parsing
bpf, sockmap: Avoid failures from skb_to_sgvec when skb has frag_list
bpf, sockmap: Handle memory acct if skb_verdict prog redirects to self
bpf, sockmap: Avoid returning unneeded EAGAIN when redirecting to self
bpf, sockmap: Use truesize with sk_rmem_schedule()
bpf, sockmap: Ensure SO_RCVBUF memory is observed on ingress redirect
bpf, sockmap: Fix partial copy_page_to_iter so progress can still be made
selftests/bpf: Fix error return code in run_getsockopt_test()
bpf: Relax return code check for subprograms
tools, bpftool: Add missing close before bpftool net attach exit
MAINTAINERS/bpf: Update Andrii's entry.
selftests/bpf: Fix unused attribute usage in subprogs_unused test
bpf: Fix unsigned 'datasec_id' compared with zero in check_pseudo_btf_id
bpf: Fix passing zero to PTR_ERR() in bpf_btf_printf_prepare
libbpf: Don't attempt to load unused subprog as an entry-point BPF program
====================
Link: https://lore.kernel.org/r/20201119200721.288-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/skmsg.c | 87 |
1 files changed, 74 insertions, 13 deletions
diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 654182ecf87b..25cdbb20f3a0 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -170,10 +170,12 @@ static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i, struct scatterlist *sge = sk_msg_elem(msg, i); u32 len = sge->length; - if (charge) - sk_mem_uncharge(sk, len); - if (!msg->skb) + /* When the skb owns the memory we free it from consume_skb path. */ + if (!msg->skb) { + if (charge) + sk_mem_uncharge(sk, len); put_page(sg_page(sge)); + } memset(sge, 0, sizeof(*sge)); return len; } @@ -397,28 +399,45 @@ out: } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); -static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, + struct sk_buff *skb) { - struct sock *sk = psock->sk; - int copied = 0, num_sge; struct sk_msg *msg; + if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) + return NULL; + + if (!sk_rmem_schedule(sk, skb, skb->truesize)) + return NULL; + msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); if (unlikely(!msg)) - return -EAGAIN; - if (!sk_rmem_schedule(sk, skb, skb->len)) { - kfree(msg); - return -EAGAIN; - } + return NULL; sk_msg_init(msg); + return msg; +} + +static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, + struct sk_psock *psock, + struct sock *sk, + struct sk_msg *msg) +{ + int num_sge, copied; + + /* skb linearize may fail with ENOMEM, but lets simply try again + * later if this happens. Under memory pressure we don't want to + * drop the skb. We need to linearize the skb so that the mapping + * in skb_to_sgvec can not error. + */ + if (skb_linearize(skb)) + return -EAGAIN; num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); if (unlikely(num_sge < 0)) { kfree(msg); return num_sge; } - sk_mem_charge(sk, skb->len); copied = skb->len; msg->sg.start = 0; msg->sg.size = copied; @@ -430,6 +449,48 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) return copied; } +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb); + +static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +{ + struct sock *sk = psock->sk; + struct sk_msg *msg; + + /* If we are receiving on the same sock skb->sk is already assigned, + * skip memory accounting and owner transition seeing it already set + * correctly. + */ + if (unlikely(skb->sk == sk)) + return sk_psock_skb_ingress_self(psock, skb); + msg = sk_psock_create_ingress_msg(sk, skb); + if (!msg) + return -EAGAIN; + + /* This will transition ownership of the data from the socket where + * the BPF program was run initiating the redirect to the socket + * we will eventually receive this data on. The data will be released + * from skb_consume found in __tcp_bpf_recvmsg() after its been copied + * into user buffers. + */ + skb_set_owner_r(skb, sk); + return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); +} + +/* Puts an skb on the ingress queue of the socket already assigned to the + * skb. In this case we do not need to check memory limits or skb_set_owner_r + * because the skb is already accounted for here. + */ +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb) +{ + struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); + struct sock *sk = psock->sk; + + if (unlikely(!msg)) + return -EAGAIN; + sk_msg_init(msg); + return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); +} + static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len, bool ingress) { @@ -789,7 +850,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, * retrying later from workqueue. */ if (skb_queue_empty(&psock->ingress_skb)) { - err = sk_psock_skb_ingress(psock, skb); + err = sk_psock_skb_ingress_self(psock, skb); } if (err < 0) { skb_queue_tail(&psock->ingress_skb, skb); |