diff options
author | Daniel Borkmann <daniel@iogearbox.net> | 2018-10-13 02:45:58 +0200 |
---|---|---|
committer | Alexei Starovoitov <ast@kernel.org> | 2018-10-15 12:23:19 -0700 |
commit | 604326b41a6fb9b4a78b6179335decee0365cd8c (patch) | |
tree | 95d439c3739f0b3ed5022780cd3f6925f1a4f94d /kernel/bpf/sockmap.c | |
parent | 1243a51f6c05ecbb2c5c9e02fdcc1e7a06f76f26 (diff) |
bpf, sockmap: convert to generic sk_msg interface
Add a generic sk_msg layer, and convert current sockmap and later
kTLS over to make use of it. While sk_buff handles network packet
representation from netdevice up to socket, sk_msg handles data
representation from application to socket layer.
This means that sk_msg framework spans across ULP users in the
kernel, and enables features such as introspection or filtering
of data with the help of BPF programs that operate on this data
structure.
Latter becomes in particular useful for kTLS where data encryption
is deferred into the kernel, and as such enabling the kernel to
perform L7 introspection and policy based on BPF for TLS connections
where the record is being encrypted after BPF has run and came to
a verdict. In order to get there, first step is to transform open
coding of scatter-gather list handling into a common core framework
that subsystems can use.
The code itself has been split and refactored into three bigger
pieces: i) the generic sk_msg API which deals with managing the
scatter gather ring, providing helpers for walking and mangling,
transferring application data from user space into it, and preparing
it for BPF pre/post-processing, ii) the plain sock map itself
where sockets can be attached to or detached from; these bits
are independent of i) which can now be used also without sock
map, and iii) the integration with plain TCP as one protocol
to be used for processing L7 application data (later this could
e.g. also be extended to other protocols like UDP). The semantics
are the same with the old sock map code and therefore no change
of user facing behavior or APIs. While pursuing this work it
also helped finding a number of bugs in the old sockmap code
that we've fixed already in earlier commits. The test_sockmap
kselftest suite passes through fine as well.
Joint work with John.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'kernel/bpf/sockmap.c')
-rw-r--r-- | kernel/bpf/sockmap.c | 2610 |
1 files changed, 0 insertions, 2610 deletions
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c deleted file mode 100644 index de6f7a65c72b..000000000000 --- a/kernel/bpf/sockmap.c +++ /dev/null @@ -1,2610 +0,0 @@ -/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ - -/* A BPF sock_map is used to store sock objects. This is primarly used - * for doing socket redirect with BPF helper routines. - * - * A sock map may have BPF programs attached to it, currently a program - * used to parse packets and a program to provide a verdict and redirect - * decision on the packet are supported. Any programs attached to a sock - * map are inherited by sock objects when they are added to the map. If - * no BPF programs are attached the sock object may only be used for sock - * redirect. - * - * A sock object may be in multiple maps, but can only inherit a single - * parse or verdict program. If adding a sock object to a map would result - * in having multiple parsing programs the update will return an EBUSY error. - * - * For reference this program is similar to devmap used in XDP context - * reviewing these together may be useful. For an example please review - * ./samples/bpf/sockmap/. - */ -#include <linux/bpf.h> -#include <net/sock.h> -#include <linux/filter.h> -#include <linux/errno.h> -#include <linux/file.h> -#include <linux/kernel.h> -#include <linux/net.h> -#include <linux/skbuff.h> -#include <linux/workqueue.h> -#include <linux/list.h> -#include <linux/mm.h> -#include <net/strparser.h> -#include <net/tcp.h> -#include <linux/ptr_ring.h> -#include <net/inet_common.h> -#include <linux/sched/signal.h> - -#define SOCK_CREATE_FLAG_MASK \ - (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) - -struct bpf_sock_progs { - struct bpf_prog *bpf_tx_msg; - struct bpf_prog *bpf_parse; - struct bpf_prog *bpf_verdict; -}; - -struct bpf_stab { - struct bpf_map map; - struct sock **sock_map; - struct bpf_sock_progs progs; - raw_spinlock_t lock; -}; - -struct bucket { - struct hlist_head head; - raw_spinlock_t lock; -}; - -struct bpf_htab { - struct bpf_map map; - struct bucket *buckets; - atomic_t count; - u32 n_buckets; - u32 elem_size; - struct bpf_sock_progs progs; - struct rcu_head rcu; -}; - -struct htab_elem { - struct rcu_head rcu; - struct hlist_node hash_node; - u32 hash; - struct sock *sk; - char key[0]; -}; - -enum smap_psock_state { - SMAP_TX_RUNNING, -}; - -struct smap_psock_map_entry { - struct list_head list; - struct bpf_map *map; - struct sock **entry; - struct htab_elem __rcu *hash_link; -}; - -struct smap_psock { - struct rcu_head rcu; - refcount_t refcnt; - - /* datapath variables */ - struct sk_buff_head rxqueue; - bool strp_enabled; - - /* datapath error path cache across tx work invocations */ - int save_rem; - int save_off; - struct sk_buff *save_skb; - - /* datapath variables for tx_msg ULP */ - struct sock *sk_redir; - int apply_bytes; - int cork_bytes; - int sg_size; - int eval; - struct sk_msg_buff *cork; - struct list_head ingress; - - struct strparser strp; - struct bpf_prog *bpf_tx_msg; - struct bpf_prog *bpf_parse; - struct bpf_prog *bpf_verdict; - struct list_head maps; - spinlock_t maps_lock; - - /* Back reference used when sock callback trigger sockmap operations */ - struct sock *sock; - unsigned long state; - - struct work_struct tx_work; - struct work_struct gc_work; - - struct proto *sk_proto; - void (*save_unhash)(struct sock *sk); - void (*save_close)(struct sock *sk, long timeout); - void (*save_data_ready)(struct sock *sk); - void (*save_write_space)(struct sock *sk); -}; - -static void smap_release_sock(struct smap_psock *psock, struct sock *sock); -static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int nonblock, int flags, int *addr_len); -static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); -static int bpf_tcp_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags); -static void bpf_tcp_unhash(struct sock *sk); -static void bpf_tcp_close(struct sock *sk, long timeout); - -static inline struct smap_psock *smap_psock_sk(const struct sock *sk) -{ - return rcu_dereference_sk_user_data(sk); -} - -static bool bpf_tcp_stream_read(const struct sock *sk) -{ - struct smap_psock *psock; - bool empty = true; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto out; - empty = list_empty(&psock->ingress); -out: - rcu_read_unlock(); - return !empty; -} - -enum { - SOCKMAP_IPV4, - SOCKMAP_IPV6, - SOCKMAP_NUM_PROTS, -}; - -enum { - SOCKMAP_BASE, - SOCKMAP_TX, - SOCKMAP_NUM_CONFIGS, -}; - -static struct proto *saved_tcpv6_prot __read_mostly; -static DEFINE_SPINLOCK(tcpv6_prot_lock); -static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS]; - -static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS], - struct proto *base) -{ - prot[SOCKMAP_BASE] = *base; - prot[SOCKMAP_BASE].unhash = bpf_tcp_unhash; - prot[SOCKMAP_BASE].close = bpf_tcp_close; - prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg; - prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read; - - prot[SOCKMAP_TX] = prot[SOCKMAP_BASE]; - prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg; - prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage; -} - -static void update_sk_prot(struct sock *sk, struct smap_psock *psock) -{ - int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4; - int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE; - - sk->sk_prot = &bpf_tcp_prots[family][conf]; -} - -static int bpf_tcp_init(struct sock *sk) -{ - struct smap_psock *psock; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - return -EINVAL; - } - - if (unlikely(psock->sk_proto)) { - rcu_read_unlock(); - return -EBUSY; - } - - psock->save_unhash = sk->sk_prot->unhash; - psock->save_close = sk->sk_prot->close; - psock->sk_proto = sk->sk_prot; - - /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */ - if (sk->sk_family == AF_INET6 && - unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { - spin_lock_bh(&tcpv6_prot_lock); - if (likely(sk->sk_prot != saved_tcpv6_prot)) { - build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot); - smp_store_release(&saved_tcpv6_prot, sk->sk_prot); - } - spin_unlock_bh(&tcpv6_prot_lock); - } - update_sk_prot(sk, psock); - rcu_read_unlock(); - return 0; -} - -static int __init bpf_sock_init(void) -{ - build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot); - return 0; -} -core_initcall(bpf_sock_init); - -static void smap_release_sock(struct smap_psock *psock, struct sock *sock); -static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge); - -static void bpf_tcp_release(struct sock *sk) -{ - struct smap_psock *psock; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto out; - - if (psock->cork) { - free_start_sg(psock->sock, psock->cork, true); - kfree(psock->cork); - psock->cork = NULL; - } - - if (psock->sk_proto) { - sk->sk_prot = psock->sk_proto; - psock->sk_proto = NULL; - } -out: - rcu_read_unlock(); -} - -static struct htab_elem *lookup_elem_raw(struct hlist_head *head, - u32 hash, void *key, u32 key_size) -{ - struct htab_elem *l; - - hlist_for_each_entry_rcu(l, head, hash_node) { - if (l->hash == hash && !memcmp(&l->key, key, key_size)) - return l; - } - - return NULL; -} - -static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) -{ - return &htab->buckets[hash & (htab->n_buckets - 1)]; -} - -static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) -{ - return &__select_bucket(htab, hash)->head; -} - -static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) -{ - atomic_dec(&htab->count); - kfree_rcu(l, rcu); -} - -static struct smap_psock_map_entry *psock_map_pop(struct sock *sk, - struct smap_psock *psock) -{ - struct smap_psock_map_entry *e; - - spin_lock_bh(&psock->maps_lock); - e = list_first_entry_or_null(&psock->maps, - struct smap_psock_map_entry, - list); - if (e) - list_del(&e->list); - spin_unlock_bh(&psock->maps_lock); - return e; -} - -static void bpf_tcp_remove(struct sock *sk, struct smap_psock *psock) -{ - struct smap_psock_map_entry *e; - struct sk_msg_buff *md, *mtmp; - struct sock *osk; - - if (psock->cork) { - free_start_sg(psock->sock, psock->cork, true); - kfree(psock->cork); - psock->cork = NULL; - } - - list_for_each_entry_safe(md, mtmp, &psock->ingress, list) { - list_del(&md->list); - free_start_sg(psock->sock, md, true); - kfree(md); - } - - e = psock_map_pop(sk, psock); - while (e) { - if (e->entry) { - struct bpf_stab *stab = container_of(e->map, struct bpf_stab, map); - - raw_spin_lock_bh(&stab->lock); - osk = *e->entry; - if (osk == sk) { - *e->entry = NULL; - smap_release_sock(psock, sk); - } - raw_spin_unlock_bh(&stab->lock); - } else { - struct htab_elem *link = rcu_dereference(e->hash_link); - struct bpf_htab *htab = container_of(e->map, struct bpf_htab, map); - struct hlist_head *head; - struct htab_elem *l; - struct bucket *b; - - b = __select_bucket(htab, link->hash); - head = &b->head; - raw_spin_lock_bh(&b->lock); - l = lookup_elem_raw(head, - link->hash, link->key, - htab->map.key_size); - /* If another thread deleted this object skip deletion. - * The refcnt on psock may or may not be zero. - */ - if (l && l == link) { - hlist_del_rcu(&link->hash_node); - smap_release_sock(psock, link->sk); - free_htab_elem(htab, link); - } - raw_spin_unlock_bh(&b->lock); - } - kfree(e); - e = psock_map_pop(sk, psock); - } -} - -static void bpf_tcp_unhash(struct sock *sk) -{ - void (*unhash_fun)(struct sock *sk); - struct smap_psock *psock; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - if (sk->sk_prot->unhash) - sk->sk_prot->unhash(sk); - return; - } - unhash_fun = psock->save_unhash; - bpf_tcp_remove(sk, psock); - rcu_read_unlock(); - unhash_fun(sk); -} - -static void bpf_tcp_close(struct sock *sk, long timeout) -{ - void (*close_fun)(struct sock *sk, long timeout); - struct smap_psock *psock; - - lock_sock(sk); - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - release_sock(sk); - return sk->sk_prot->close(sk, timeout); - } - close_fun = psock->save_close; - bpf_tcp_remove(sk, psock); - rcu_read_unlock(); - release_sock(sk); - close_fun(sk, timeout); -} - -enum __sk_action { - __SK_DROP = 0, - __SK_PASS, - __SK_REDIRECT, - __SK_NONE, -}; - -static int memcopy_from_iter(struct sock *sk, - struct sk_msg_buff *md, - struct iov_iter *from, int bytes) -{ - struct scatterlist *sg = md->sg_data; - int i = md->sg_curr, rc = -ENOSPC; - - do { - int copy; - char *to; - - if (md->sg_copybreak >= sg[i].length) { - md->sg_copybreak = 0; - - if (++i == MAX_SKB_FRAGS) - i = 0; - - if (i == md->sg_end) - break; - } - - copy = sg[i].length - md->sg_copybreak; - to = sg_virt(&sg[i]) + md->sg_copybreak; - md->sg_copybreak += copy; - - if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) - rc = copy_from_iter_nocache(to, copy, from); - else - rc = copy_from_iter(to, copy, from); - - if (rc != copy) { - rc = -EFAULT; - goto out; - } - - bytes -= copy; - if (!bytes) - break; - - md->sg_copybreak = 0; - if (++i == MAX_SKB_FRAGS) - i = 0; - } while (i != md->sg_end); -out: - md->sg_curr = i; - return rc; -} - -static int bpf_tcp_push(struct sock *sk, int apply_bytes, - struct sk_msg_buff *md, - int flags, bool uncharge) -{ - bool apply = apply_bytes; - struct scatterlist *sg; - int offset, ret = 0; - struct page *p; - size_t size; - - while (1) { - sg = md->sg_data + md->sg_start; - size = (apply && apply_bytes < sg->length) ? - apply_bytes : sg->length; - offset = sg->offset; - - tcp_rate_check_app_limited(sk); - p = sg_page(sg); -retry: - ret = do_tcp_sendpages(sk, p, offset, size, flags); - if (ret != size) { - if (ret > 0) { - if (apply) - apply_bytes -= ret; - - sg->offset += ret; - sg->length -= ret; - size -= ret; - offset += ret; - if (uncharge) - sk_mem_uncharge(sk, ret); - goto retry; - } - - return ret; - } - - if (apply) - apply_bytes -= ret; - sg->offset += ret; - sg->length -= ret; - if (uncharge) - sk_mem_uncharge(sk, ret); - - if (!sg->length) { - put_page(p); - md->sg_start++; - if (md->sg_start == MAX_SKB_FRAGS) - md->sg_start = 0; - sg_init_table(sg, 1); - - if (md->sg_start == md->sg_end) - break; - } - - if (apply && !apply_bytes) - break; - } - return 0; -} - -static inline void bpf_compute_data_pointers_sg(struct sk_msg_buff *md) -{ - struct scatterlist *sg = md->sg_data + md->sg_start; - - if (md->sg_copy[md->sg_start]) { - md->data = md->data_end = 0; - } else { - md->data = sg_virt(sg); - md->data_end = md->data + sg->length; - } -} - -static void return_mem_sg(struct sock *sk, int bytes, struct sk_msg_buff *md) -{ - struct scatterlist *sg = md->sg_data; - int i = md->sg_start; - - do { - int uncharge = (bytes < sg[i].length) ? bytes : sg[i].length; - - sk_mem_uncharge(sk, uncharge); - bytes -= uncharge; - if (!bytes) - break; - i++; - if (i == MAX_SKB_FRAGS) - i = 0; - } while (i != md->sg_end); -} - -static void free_bytes_sg(struct sock *sk, int bytes, - struct sk_msg_buff *md, bool charge) -{ - struct scatterlist *sg = md->sg_data; - int i = md->sg_start, free; - - while (bytes && sg[i].length) { - free = sg[i].length; - if (bytes < free) { - sg[i].length -= bytes; - sg[i].offset += bytes; - if (charge) - sk_mem_uncharge(sk, bytes); - break; - } - - if (charge) - sk_mem_uncharge(sk, sg[i].length); - put_page(sg_page(&sg[i])); - bytes -= sg[i].length; - sg[i].length = 0; - sg[i].page_link = 0; - sg[i].offset = 0; - i++; - - if (i == MAX_SKB_FRAGS) - i = 0; - } - md->sg_start = i; -} - -static int free_sg(struct sock *sk, int start, - struct sk_msg_buff *md, bool charge) -{ - struct scatterlist *sg = md->sg_data; - int i = start, free = 0; - - while (sg[i].length) { - free += sg[i].length; - if (charge) - sk_mem_uncharge(sk, sg[i].length); - if (!md->skb) - put_page(sg_page(&sg[i])); - sg[i].length = 0; - sg[i].page_link = 0; - sg[i].offset = 0; - i++; - - if (i == MAX_SKB_FRAGS) - i = 0; - } - consume_skb(md->skb); - - return free; -} - -static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge) -{ - int free = free_sg(sk, md->sg_start, md, charge); - - md->sg_start = md->sg_end; - return free; -} - -static int free_curr_sg(struct sock *sk, struct sk_msg_buff *md) -{ - return free_sg(sk, md->sg_curr, md, true); -} - -static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md) -{ - return ((_rc == SK_PASS) ? - (md->sk_redir ? __SK_REDIRECT : __SK_PASS) : - __SK_DROP); -} - -static unsigned int smap_do_tx_msg(struct sock *sk, - struct smap_psock *psock, - struct sk_msg_buff *md) -{ - struct bpf_prog *prog; - unsigned int rc, _rc; - - preempt_disable(); - rcu_read_lock(); - - /* If the policy was removed mid-send then default to 'accept' */ - prog = READ_ONCE(psock->bpf_tx_msg); - if (unlikely(!prog)) { - _rc = SK_PASS; - goto verdict; - } - - bpf_compute_data_pointers_sg(md); - md->sk = sk; - rc = (*prog->bpf_func)(md, prog->insnsi); - psock->apply_bytes = md->apply_bytes; - - /* Moving return codes from UAPI namespace into internal namespace */ - _rc = bpf_map_msg_verdict(rc, md); - - /* The psock has a refcount on the sock but not on the map and because - * we need to drop rcu read lock here its possible the map could be - * removed between here and when we need it to execute the sock - * redirect. So do the map lookup now for future use. - */ - if (_rc == __SK_REDIRECT) { - if (psock->sk_redir) - sock_put(psock->sk_redir); - psock->sk_redir = do_msg_redirect_map(md); - if (!psock->sk_redir) { - _rc = __SK_DROP; - goto verdict; - } - sock_hold(psock->sk_redir); - } -verdict: - rcu_read_unlock(); - preempt_enable(); - - return _rc; -} - -static int bpf_tcp_ingress(struct sock *sk, int apply_bytes, - struct smap_psock *psock, - struct sk_msg_buff *md, int flags) -{ - bool apply = apply_bytes; - size_t size, copied = 0; - struct sk_msg_buff *r; - int err = 0, i; - - r = kzalloc(sizeof(struct sk_msg_buff), __GFP_NOWARN | GFP_KERNEL); - if (unlikely(!r)) - return -ENOMEM; - - lock_sock(sk); - r->sg_start = md->sg_start; - i = md->sg_start; - - do { - size = (apply && apply_bytes < md->sg_data[i].length) ? - apply_bytes : md->sg_data[i].length; - - if (!sk_wmem_schedule(sk, size)) { - if (!copied) - err = -ENOMEM; - break; - } - - sk_mem_charge(sk, size); - r->sg_data[i] = md->sg_data[i]; - r->sg_data[i].length = size; - md->sg_data[i].length -= size; - md->sg_data[i].offset += size; - copied += size; - - if (md->sg_data[i].length) { - get_page(sg_page(&r->sg_data[i])); - r->sg_end = (i + 1) == MAX_SKB_FRAGS ? 0 : i + 1; - } else { - i++; - if (i == MAX_SKB_FRAGS) - i = 0; - r->sg_end = i; - } - - if (apply) { - apply_bytes -= size; - if (!apply_bytes) - break; - } - } while (i != md->sg_end); - - md->sg_start = i; - - if (!err) { - list_add_tail(&r->list, &psock->ingress); - sk->sk_data_ready(sk); - } else { - free_start_sg(sk, r, true); - kfree(r); - } - - release_sock(sk); - return err; -} - -static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send, - struct sk_msg_buff *md, - int flags) -{ - bool ingress = !!(md->flags & BPF_F_INGRESS); - struct smap_psock *psock; - int err = 0; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto out_rcu; - - if (!refcount_inc_not_zero(&psock->refcnt)) - goto out_rcu; - - rcu_read_unlock(); - - if (ingress) { - err = bpf_tcp_ingress(sk, send, psock, md, flags); - } else { - lock_sock(sk); - err = bpf_tcp_push(sk, send, md, flags, false); - release_sock(sk); - } - smap_release_sock(psock, sk); - return err; -out_rcu: - rcu_read_unlock(); - return 0; -} - -static inline void bpf_md_init(struct smap_psock *psock) -{ - if (!psock->apply_bytes) { - psock->eval = __SK_NONE; - if (psock->sk_redir) { - sock_put(psock->sk_redir); - psock->sk_redir = NULL; - } - } -} - -static void apply_bytes_dec(struct smap_psock *psock, int i) -{ - if (psock->apply_bytes) { - if (psock->apply_bytes < i) - psock->apply_bytes = 0; - else - psock->apply_bytes -= i; - } -} - -static int bpf_exec_tx_verdict(struct smap_psock *psock, - struct sk_msg_buff *m, - struct sock *sk, - int *copied, int flags) -{ - bool cork = false, enospc = (m->sg_start == m->sg_end); - struct sock *redir; - int err = 0; - int send; - -more_data: - if (psock->eval == __SK_NONE) - psock->eval = smap_do_tx_msg(sk, psock, m); - - if (m->cork_bytes && - m->cork_bytes > psock->sg_size && !enospc) { - psock->cork_bytes = m->cork_bytes - psock->sg_size; - if (!psock->cork) { - psock->cork = kcalloc(1, - sizeof(struct sk_msg_buff), - GFP_ATOMIC | __GFP_NOWARN); - - if (!psock->cork) { - err = -ENOMEM; - goto out_err; - } - } - memcpy(psock->cork, m, sizeof(*m)); - goto out_err; - } - - send = psock->sg_size; - if (psock->apply_bytes && psock->apply_bytes < send) - send = psock->apply_bytes; - - switch (psock->eval) { - case __SK_PASS: - err = bpf_tcp_push(sk, send, m, flags, true); - if (unlikely(err)) { - *copied -= free_start_sg(sk, m, true); - break; - } - - apply_bytes_dec(psock, send); - psock->sg_size -= send; - break; - case __SK_REDIRECT: - redir = psock->sk_redir; - apply_bytes_dec(psock, send); - - if (psock->cork) { - cork = true; - psock->cork = NULL; - } - - return_mem_sg(sk, send, m); - release_sock(sk); - - err = bpf_tcp_sendmsg_do_redirect(redir, send, m, flags); - lock_sock(sk); - - if (unlikely(err < 0)) { - int free = free_start_sg(sk, m, false); - - psock->sg_size = 0; - if (!cork) - *copied -= free; - } else { - psock->sg_size -= send; - } - - if (cork) { - free_start_sg(sk, m, true); - psock->sg_size = 0; - kfree(m); - m = NULL; - err = 0; - } - break; - case __SK_DROP: - default: - free_bytes_sg(sk, send, m, true); - apply_bytes_dec(psock, send); - *copied -= send; - psock->sg_size -= send; - err = -EACCES; - break; - } - - if (likely(!err)) { - bpf_md_init(psock); - if (m && - m->sg_data[m->sg_start].page_link && - m->sg_data[m->sg_start].length) - goto more_data; - } - -out_err: - return err; -} - -static int bpf_wait_data(struct sock *sk, - struct smap_psock *psk, int flags, - long timeo, int *err) -{ - int rc; - - DEFINE_WAIT_FUNC(wait, woken_wake_function); - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - rc = sk_wait_event(sk, &timeo, - !list_empty(&psk->ingress) || - !skb_queue_empty(&sk->sk_receive_queue), - &wait); - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); - - return rc; -} - -static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int nonblock, int flags, int *addr_len) -{ - struct iov_iter *iter = &msg->msg_iter; - struct smap_psock *psock; - int copied = 0; - - if (unlikely(flags & MSG_ERRQUEUE)) - return inet_recv_error(sk, msg, len, addr_len); - if (!skb_queue_empty(&sk->sk_receive_queue)) - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto out; - - if (unlikely(!refcount_inc_not_zero(&psock->refcnt))) - goto out; - rcu_read_unlock(); - - lock_sock(sk); -bytes_ready: - while (copied != len) { - struct scatterlist *sg; - struct sk_msg_buff *md; - int i; - - md = list_first_entry_or_null(&psock->ingress, - struct sk_msg_buff, list); - if (unlikely(!md)) - break; - i = md->sg_start; - do { - struct page *page; - int n, copy; - - sg = &md->sg_data[i]; - copy = sg->length; - page = sg_page(sg); - - if (copied + copy > len) - copy = len - copied; - - n = copy_page_to_iter(page, sg->offset, copy, iter); - if (n != copy) { - md->sg_start = i; - release_sock(sk); - smap_release_sock(psock, sk); - return -EFAULT; - } - - copied += copy; - sg->offset += copy; - sg->length -= copy; - sk_mem_uncharge(sk, copy); - - if (!sg->length) { - i++; - if (i == MAX_SKB_FRAGS) - i = 0; - if (!md->skb) - put_page(page); - } - if (copied == len) - break; - } while (i != md->sg_end); - md->sg_start = i; - - if (!sg->length && md->sg_start == md->sg_end) { - list_del(&md->list); - consume_skb(md->skb); - kfree(md); - } - } - - if (!copied) { - long timeo; - int data; - int err = 0; - - timeo = sock_rcvtimeo(sk, nonblock); - data = bpf_wait_data(sk, psock, flags, timeo, &err); - - if (data) { - if (!skb_queue_empty(&sk->sk_receive_queue)) { - release_sock(sk); - smap_release_sock(psock, sk); - copied = tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - return copied; - } - goto bytes_ready; - } - - if (err) - copied = err; - } - - release_sock(sk); - smap_release_sock(psock, sk); - return copied; -out: - rcu_read_unlock(); - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); -} - - -static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) -{ - int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS; - struct sk_msg_buff md = {0}; - unsigned int sg_copy = 0; - struct smap_psock *psock; - int copied = 0, err = 0; - struct scatterlist *sg; - long timeo; - - /* Its possible a sock event or user removed the psock _but_ the ops - * have not been reprogrammed yet so we get here. In this case fallback - * to tcp_sendmsg. Note this only works because we _only_ ever allow - * a single ULP there is no hierarchy here. - */ - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - return tcp_sendmsg(sk, msg, size); - } - - /* Increment the psock refcnt to ensure its not released while sending a - * message. Required because sk lookup and bpf programs are used in - * separate rcu critical sections. Its OK if we lose the map entry - * but we can't lose the sock reference. - */ - if (!refcount_inc_not_zero(&psock->refcnt)) { - rcu_read_unlock(); - return tcp_sendmsg(sk, msg, size); - } - - sg = md.sg_data; - sg_init_marker(sg, MAX_SKB_FRAGS); - rcu_read_unlock(); - - lock_sock(sk); - timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); - - while (msg_data_left(msg)) { - struct sk_msg_buff *m = NULL; - bool enospc = false; - int copy; - - if (sk->sk_err) { - err = -sk->sk_err; - goto out_err; - } - - copy = msg_data_left(msg); - if (!sk_stream_memory_free(sk)) - goto wait_for_sndbuf; - - m = psock->cork_bytes ? psock->cork : &md; - m->sg_curr = m->sg_copybreak ? m->sg_curr : m->sg_end; - err = sk_alloc_sg(sk, copy, m->sg_data, - m->sg_start, &m->sg_end, &sg_copy, - m->sg_end - 1); - if (err) { - if (err != -ENOSPC) - goto wait_for_memory; - enospc = true; - copy = sg_copy; - } - - err = memcopy_from_iter(sk, m, &msg->msg_iter, copy); - if (err < 0) { - free_curr_sg(sk, m); - goto out_err; - } - - psock->sg_size += copy; - copied += copy; - sg_copy = 0; - - /* When bytes are being corked skip running BPF program and - * applying verdict unless there is no more buffer space. In - * the ENOSPC case simply run BPF prorgram with currently - * accumulated data. We don't have much choice at this point - * we could try extending the page frags or chaining complex - * frags but even in these cases _eventually_ we will hit an - * OOM scenario. More complex recovery schemes may be - * implemented in the future, but BPF programs must handle - * the case where apply_cork requests are not honored. The - * canonical method to verify this is to check data length. - */ - if (psock->cork_bytes) { - if (copy > psock->cork_bytes) - psock->cork_bytes = 0; - else - psock->cork_bytes -= copy; - - if (psock->cork_bytes && !enospc) - goto out_cork; - - /* All cork bytes accounted for re-run filter */ - psock->eval = __SK_NONE; - psock->cork_bytes = 0; - } - - err = bpf_exec_tx_verdict(psock, m, sk, &copied, flags); - if (unlikely(err < 0)) - goto out_err; - continue; -wait_for_sndbuf: - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); -wait_for_memory: - err = sk_stream_wait_memory(sk, &timeo); - if (err) { - if (m && m != psock->cork) - free_start_sg(sk, m, true); - goto out_err; - } - } -out_err: - if (err < 0) - err = sk_stream_error(sk, msg->msg_flags, err); -out_cork: - release_sock(sk); - smap_release_sock(psock, sk); - return copied ? copied : err; -} - -static int bpf_tcp_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags) -{ - struct sk_msg_buff md = {0}, *m = NULL; - int err = 0, copied = 0; - struct smap_psock *psock; - struct scatterlist *sg; - bool enospc = false; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto accept; - - if (!refcount_inc_not_zero(&psock->refcnt)) - goto accept; - rcu_read_unlock(); - - lock_sock(sk); - - if (psock->cork_bytes) { - m = psock->cork; - sg = &m->sg_data[m->sg_end]; - } else { - m = &md; - sg = m->sg_data; - sg_init_marker(sg, MAX_SKB_FRAGS); - } - - /* Catch case where ring is full and sendpage is stalled. */ - if (unlikely(m->sg_end == m->sg_start && - m->sg_data[m->sg_end].length)) - goto out_err; - - psock->sg_size += size; - sg_set_page(sg, page, size, offset); - get_page(page); - m->sg_copy[m->sg_end] = true; - sk_mem_charge(sk, size); - m->sg_end++; - copied = size; - - if (m->sg_end == MAX_SKB_FRAGS) - m->sg_end = 0; - - if (m->sg_end == m->sg_start) - enospc = true; - - if (psock->cork_bytes) { - if (size > psock->cork_bytes) - psock->cork_bytes = 0; - else - psock->cork_bytes -= size; - - if (psock->cork_bytes && !enospc) - goto out_err; - - /* All cork bytes accounted for re-run filter */ - psock->eval = __SK_NONE; - psock->cork_bytes = 0; - } - - err = bpf_exec_tx_verdict(psock, m, sk, &copied, |