From ed2b82c03dc187018307c7c6bf9299705f3db383 Mon Sep 17 00:00:00 2001 From: Mauricio Vasquez B Date: Fri, 29 Jun 2018 14:48:20 +0200 Subject: bpf: hash map: decrement counter on error Decrement the number of elements in the map in case the allocation of a new node fails. Fixes: 6c9059817432 ("bpf: pre-allocate hash map elements") Signed-off-by: Mauricio Vasquez B Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/hashtab.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3ca2198a6d22..513d9dfcf4ee 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -747,13 +747,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, * old element will be freed immediately. * Otherwise return an error */ - atomic_dec(&htab->count); - return ERR_PTR(-E2BIG); + l_new = ERR_PTR(-E2BIG); + goto dec_count; } l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, htab->map.numa_node); - if (!l_new) - return ERR_PTR(-ENOMEM); + if (!l_new) { + l_new = ERR_PTR(-ENOMEM); + goto dec_count; + } } memcpy(l_new->key, key, key_size); @@ -766,7 +768,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, GFP_ATOMIC | __GFP_NOWARN); if (!pptr) { kfree(l_new); - return ERR_PTR(-ENOMEM); + l_new = ERR_PTR(-ENOMEM); + goto dec_count; } } @@ -780,6 +783,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new->hash = hash; return l_new; +dec_count: + atomic_dec(&htab->count); + return l_new; } static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, -- cgit v1.2.3 From 547b3aa451ae2739585547db9fbdee11a43ff999 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 5 Jul 2018 08:05:56 -0700 Subject: bpf: sockmap, error path can not release psock in multi-map case The current code, in the error path of sock_hash_ctx_update_elem, checks if the sock has a psock in the user data and if so decrements the reference count of the psock. However, if the error happens early in the error path we may have never incremented the psock reference count and if the psock exists because the sock is in another map then we may inadvertently decrement the reference count. Fix this by making the error path only call smap_release_sock if the error happens after the increment. Reported-by: syzbot+d464d2c20c717ef5a6a8@syzkaller.appspotmail.com Fixes: 81110384441a ("bpf: sockmap, add hash map support") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- kernel/bpf/sockmap.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index cf7b6a6dbd1f..3847a7ce7dae 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -1896,7 +1896,7 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); if (!e) { err = -ENOMEM; - goto out_progs; + goto out_free; } } @@ -2342,7 +2342,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, if (err) goto err; - /* bpf_map_update_elem() can be called in_irq() */ + /* psock is valid here because otherwise above *ctx_update_elem would + * have thrown an error. It is safe to skip error check. + */ + psock = smap_psock_sk(sock); raw_spin_lock_bh(&b->lock); l_old = lookup_elem_raw(head, hash, key, key_size); if (l_old && map_flags == BPF_NOEXIST) { @@ -2360,12 +2363,6 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, goto bucket_err; } - psock = smap_psock_sk(sock); - if (unlikely(!psock)) { - err = -EINVAL; - goto bucket_err; - } - rcu_assign_pointer(e->hash_link, l_new); rcu_assign_pointer(e->htab, container_of(map, struct bpf_htab, map)); @@ -2388,12 +2385,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, raw_spin_unlock_bh(&b->lock); return 0; bucket_err: + smap_release_sock(psock, sock); raw_spin_unlock_bh(&b->lock); err: kfree(e); - psock = smap_psock_sk(sock); - if (psock) - smap_release_sock(psock, sock); return err; } -- cgit v1.2.3 From 1d1ef005dbc6de673c62cbd2562290ada3090463 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 5 Jul 2018 08:06:01 -0700 Subject: bpf: sockmap, hash table is RCU so readers do not need locks This removes locking from readers of RCU hash table. Its not necessary. Fixes: 81110384441a ("bpf: sockmap, add hash map support") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- kernel/bpf/sockmap.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 3847a7ce7dae..00fb2e328d1b 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -2467,10 +2467,8 @@ struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - raw_spin_lock_bh(&b->lock); l = lookup_elem_raw(head, hash, key, key_size); sk = l ? l->sk : NULL; - raw_spin_unlock_bh(&b->lock); return sk; } -- cgit v1.2.3 From 99ba2b5aba24e022683a7db63204f9e306fe7ab9 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 5 Jul 2018 08:50:04 -0700 Subject: bpf: sockhash, disallow bpf_tcp_close and update in parallel After latest lock updates there is no longer anything preventing a close and recvmsg call running in parallel. Additionally, we can race update with close if we close a socket and simultaneously update if via the BPF userspace API (note the cgroup ops are already run with sock_lock held). To resolve this take sock_lock in close and update paths. Reported-by: syzbot+b680e42077a0d7c9a0c4@syzkaller.appspotmail.com Fixes: e9db4ef6bf4c ("bpf: sockhash fix omitted bucket lock in sock_close") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- kernel/bpf/sockmap.c | 15 +++++++++++++++ kernel/bpf/syscall.c | 4 +++- 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 00fb2e328d1b..9c67e96fe336 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -312,10 +312,12 @@ static void bpf_tcp_close(struct sock *sk, long timeout) struct smap_psock *psock; struct sock *osk; + 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); } @@ -371,6 +373,7 @@ static void bpf_tcp_close(struct sock *sk, long timeout) e = psock_map_pop(sk, psock); } rcu_read_unlock(); + release_sock(sk); close_fun(sk, timeout); } @@ -2069,7 +2072,13 @@ static int sock_map_update_elem(struct bpf_map *map, return -EOPNOTSUPP; } + lock_sock(skops.sk); + preempt_disable(); + rcu_read_lock(); err = sock_map_ctx_update_elem(&skops, map, key, flags); + rcu_read_unlock(); + preempt_enable(); + release_sock(skops.sk); fput(socket->file); return err; } @@ -2410,7 +2419,13 @@ static int sock_hash_update_elem(struct bpf_map *map, return -EINVAL; } + lock_sock(skops.sk); + preempt_disable(); + rcu_read_lock(); err = sock_hash_ctx_update_elem(&skops, map, key, flags); + rcu_read_unlock(); + preempt_enable(); + release_sock(skops.sk); fput(socket->file); return err; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d10ecd78105f..a31a1ba0f8ea 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -735,7 +735,9 @@ static int map_update_elem(union bpf_attr *attr) if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_update_elem(map, key, value, attr->flags); goto out; - } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || + map->map_type == BPF_MAP_TYPE_SOCKHASH || + map->map_type == BPF_MAP_TYPE_SOCKMAP) { err = map->ops->map_update_elem(map, key, value, attr->flags); goto out; } -- cgit v1.2.3 From 7ebc14d507b4b55105da8d1a1eda323381529cc7 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 5 Jul 2018 08:50:10 -0700 Subject: bpf: sockmap, consume_skb in close path Currently, when a sock is closed and the bpf_tcp_close() callback is used we remove memory but do not free the skb. Call consume_skb() if the skb is attached to the buffer. Reported-by: syzbot+d464d2c20c717ef5a6a8@syzkaller.appspotmail.com Fixes: 1aa12bdf1bfb ("bpf: sockmap, add sock close() hook to remove socks") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- kernel/bpf/sockmap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 9c67e96fe336..dfc8a8a07c1f 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -571,7 +571,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) while (sg[i].length) { free += sg[i].length; sk_mem_uncharge(sk, sg[i].length); - put_page(sg_page(&sg[i])); + if (!md->skb) + put_page(sg_page(&sg[i])); sg[i].length = 0; sg[i].page_link = 0; sg[i].offset = 0; @@ -580,6 +581,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) if (i == MAX_SKB_FRAGS) i = 0; } + if (md->skb) + consume_skb(md->skb); return free; } -- cgit v1.2.3 From 0ea488ff8d23c93da383fcf424825c298b13b1fb Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 5 Jul 2018 08:50:15 -0700 Subject: bpf: sockmap, convert bpf_compute_data_pointers to bpf_*_sk_skb In commit 'bpf: bpf_compute_data uses incorrect cb structure' (8108a7751512) we added the routine bpf_compute_data_end_sk_skb() to compute the correct data_end values, but this has since been lost. In kernel v4.14 this was correct and the above patch was applied in it entirety. Then when v4.14 was merged into v4.15-rc1 net-next tree we lost the piece that renamed bpf_compute_data_pointers to the new function bpf_compute_data_end_sk_skb. This was done here, e1ea2f9856b7 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net") When it conflicted with the following rename patch, 6aaae2b6c433 ("bpf: rename bpf_compute_data_end into bpf_compute_data_pointers") Finally, after a refactor I thought even the function bpf_compute_data_end_sk_skb() was no longer needed and it was erroneously removed. However, we never reverted the sk_skb_convert_ctx_access() usage of tcp_skb_cb which had been committed and survived the merge conflict. Here we fix this by adding back the helper and *_data_end_sk_skb() usage. Using the bpf_skc_data_end mapping is not correct because it expects a qdisc_skb_cb object but at the sock layer this is not the case. Even though it happens to work here because we don't overwrite any data in-use at the socket layer and the cb structure is cleared later this has potential to create some subtle issues. But, even more concretely the filter.c access check uses tcp_skb_cb. And by some act of chance though, struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; /* 0 28 */ /* XXX 4 bytes hole, try to pack */ void * data_meta; /* 32 8 */ void * data_end; /* 40 8 */ /* size: 48, cachelines: 1, members: 3 */ /* sum members: 44, holes: 1, sum holes: 4 */ /* last cacheline: 48 bytes */ }; and then tcp_skb_cb, struct tcp_skb_cb { [...] struct { __u32 flags; /* 24 4 */ struct sock * sk_redir; /* 32 8 */ void * data_end; /* 40 8 */ } bpf; /* 24 */ }; So when we use offset_of() to track down the byte offset we get 40 in either case and everything continues to work. Fix this mess and use correct structures its unclear how long this might actually work for until someone moves the structs around. Reported-by: Martin KaFai Lau Fixes: e1ea2f9856b7 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net") Fixes: 6aaae2b6c433 ("bpf: rename bpf_compute_data_end into bpf_compute_data_pointers") Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- include/net/tcp.h | 4 +++ kernel/bpf/sockmap.c | 4 +-- net/core/filter.c | 98 ++++++++++++++++++++++++++++++++++++++++++++++++---- 3 files changed, 97 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/include/net/tcp.h b/include/net/tcp.h index 800582b5dd54..af3ec72d5d41 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -828,6 +828,10 @@ struct tcp_skb_cb { #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) +static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) +{ + TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); +} #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index dfc8a8a07c1f..98fb7938beea 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -1236,7 +1236,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) */ TCP_SKB_CB(skb)->bpf.sk_redir = NULL; skb->sk = psock->sock; - bpf_compute_data_pointers(skb); + bpf_compute_data_end_sk_skb(skb); preempt_disable(); rc = (*prog->bpf_func)(skb, prog->insnsi); preempt_enable(); @@ -1491,7 +1491,7 @@ static int smap_parse_func_strparser(struct strparser *strp, * any socket yet. */ skb->sk = psock->sock; - bpf_compute_data_pointers(skb); + bpf_compute_data_end_sk_skb(skb); rc = (*prog->bpf_func)(skb, prog->insnsi); skb->sk = NULL; rcu_read_unlock(); diff --git a/net/core/filter.c b/net/core/filter.c index 3095f1ba7015..470268024a40 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1762,6 +1762,37 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = { .arg2_type = ARG_ANYTHING, }; +static inline int sk_skb_try_make_writable(struct sk_buff *skb, + unsigned int write_len) +{ + int err = __bpf_try_make_writable(skb, write_len); + + bpf_compute_data_end_sk_skb(skb); + return err; +} + +BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len) +{ + /* Idea is the following: should the needed direct read/write + * test fail during runtime, we can pull in more data and redo + * again, since implicitly, we invalidate previous checks here. + * + * Or, since we know how much we need to make read/writeable, + * this can be done once at the program beginning for direct + * access case. By this we overcome limitations of only current + * headroom being accessible. + */ + return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb)); +} + +static const struct bpf_func_proto sk_skb_pull_data_proto = { + .func = sk_skb_pull_data, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { @@ -2864,8 +2895,8 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) return __skb_trim_rcsum(skb, new_len); } -BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, - u64, flags) +static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, + u64 flags) { u32 max_len = __bpf_skb_max_len(skb); u32 min_len = __bpf_skb_min_len(skb); @@ -2901,6 +2932,13 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, if (!ret && skb_is_gso(skb)) skb_gso_reset(skb); } + return ret; +} + +BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, + u64, flags) +{ + int ret = __bpf_skb_change_tail(skb, new_len, flags); bpf_compute_data_pointers(skb); return ret; @@ -2915,8 +2953,26 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = { .arg3_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, +BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) +{ + int ret = __bpf_skb_change_tail(skb, new_len, flags); + + bpf_compute_data_end_sk_skb(skb); + return ret; +} + +static const struct bpf_func_proto sk_skb_change_tail_proto = { + .func = sk_skb_change_tail, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + +static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, + u64 flags) { u32 max_len = __bpf_skb_max_len(skb); u32 new_len = skb->len + head_room; @@ -2942,8 +2998,16 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, skb_reset_mac_header(skb); } + return ret; +} + +BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, + u64, flags) +{ + int ret = __bpf_skb_change_head(skb, head_room, flags); + bpf_compute_data_pointers(skb); - return 0; + return ret; } static const struct bpf_func_proto bpf_skb_change_head_proto = { @@ -2955,6 +3019,23 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room, + u64, flags) +{ + int ret = __bpf_skb_change_head(skb, head_room, flags); + + bpf_compute_data_end_sk_skb(skb); + return ret; +} + +static const struct bpf_func_proto sk_skb_change_head_proto = { + .func = sk_skb_change_head, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : @@ -4618,9 +4699,12 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_skb_store_bytes || func == bpf_skb_change_proto || func == bpf_skb_change_head || + func == sk_skb_change_head || func == bpf_skb_change_tail || + func == sk_skb_change_tail || func == bpf_skb_adjust_room || func == bpf_skb_pull_data || + func == sk_skb_pull_data || func == bpf_clone_redirect || func == bpf_l3_csum_replace || func == bpf_l4_csum_replace || @@ -4872,11 +4956,11 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: - return &bpf_skb_pull_data_proto; + return &sk_skb_pull_data_proto; case BPF_FUNC_skb_change_tail: - return &bpf_skb_change_tail_proto; + return &sk_skb_change_tail_proto; case BPF_FUNC_skb_change_head: - return &bpf_skb_change_head_proto; + return &sk_skb_change_head_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: -- cgit v1.2.3 From d8d7218ad842e18fc6976b87c08ed749e8d56313 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Fri, 6 Jul 2018 11:49:00 +0900 Subject: xdp: XDP_REDIRECT should check IFF_UP and MTU Otherwise we end up with attempting to send packets from down devices or to send oversized packets, which may cause unexpected driver/device behaviour. Generic XDP has already done this check, so reuse the logic in native XDP. Fixes: 814abfabef3c ("xdp: add bpf_redirect helper function") Signed-off-by: Toshiaki Makita Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 6 +++--- kernel/bpf/devmap.c | 7 ++++++- net/core/filter.c | 9 +++++++-- 3 files changed, 16 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/include/linux/filter.h b/include/linux/filter.h index 300baad62c88..c73dd7396886 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -765,8 +765,8 @@ static inline bool bpf_dump_raw_ok(void) struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); -static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, - struct net_device *fwd) +static inline int xdp_ok_fwd_dev(const struct net_device *fwd, + unsigned int pktlen) { unsigned int len; @@ -774,7 +774,7 @@ static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, return -ENETDOWN; len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; - if (skb->len > len) + if (pktlen > len) return -EMSGSIZE; return 0; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 642c97f6d1b8..d361fc1e3bf3 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -334,10 +334,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, { struct net_device *dev = dst->dev; struct xdp_frame *xdpf; + int err; if (!dev->netdev_ops->ndo_xdp_xmit) return -EOPNOTSUPP; + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + if (unlikely(err)) + return err; + xdpf = convert_to_xdp_frame(xdp); if (unlikely(!xdpf)) return -EOVERFLOW; @@ -350,7 +355,7 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, { int err; - err = __xdp_generic_ok_fwd_dev(skb, dst->dev); + err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; skb->dev = dst->dev; diff --git a/net/core/filter.c b/net/core/filter.c index 470268024a40..5fa66a33927f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3128,12 +3128,16 @@ static int __bpf_tx_xdp(struct net_device *dev, u32 index) { struct xdp_frame *xdpf; - int sent; + int err, sent; if (!dev->netdev_ops->ndo_xdp_xmit) { return -EOPNOTSUPP; } + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + if (unlikely(err)) + return err; + xdpf = convert_to_xdp_frame(xdp); if (unlikely(!xdpf)) return -EOVERFLOW; @@ -3367,7 +3371,8 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, goto err; } - if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) + err = xdp_ok_fwd_dev(fwd, skb->len); + if (unlikely(err)) goto err; skb->dev = fwd; -- cgit v1.2.3 From b65f370d0671c4980ffe866c41e327b88893245c Mon Sep 17 00:00:00 2001 From: Okash Khawaja Date: Tue, 10 Jul 2018 14:33:07 -0700 Subject: bpf: btf: Fix bitfield extraction for big endian When extracting bitfield from a number, btf_int_bits_seq_show() builds a mask and accesses least significant byte of the number in a way specific to little-endian. This patch fixes that by checking endianness of the machine and then shifting left and right the unneeded bits. Thanks to Martin Lau for the help in navigating potential pitfalls when dealing with endianess and for the final solution. Fixes: b00b8daec828 ("bpf: btf: Add pretty print capability for data with BTF type info") Signed-off-by: Okash Khawaja Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- kernel/bpf/btf.c | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2d49d18b793a..e016ac3afa24 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -991,16 +991,13 @@ static void btf_int_bits_seq_show(const struct btf *btf, void *data, u8 bits_offset, struct seq_file *m) { + u16 left_shift_bits, right_shift_bits; u32 int_data = btf_type_int(t); u16 nr_bits = BTF_INT_BITS(int_data); u16 total_bits_offset; u16 nr_copy_bytes; u16 nr_copy_bits; - u8 nr_upper_bits; - union { - u64 u64_num; - u8 u8_nums[8]; - } print_num; + u64 print_num; total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); data += BITS_ROUNDDOWN_BYTES(total_bits_offset); @@ -1008,21 +1005,20 @@ static void btf_int_bits_seq_show(const struct btf *btf, nr_copy_bits = nr_bits + bits_offset; nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits); - print_num.u64_num = 0; - memcpy(&print_num.u64_num, data, nr_copy_bytes); + print_num = 0; + memcpy(&print_num, data, nr_copy_bytes); - /* Ditch the higher order bits */ - nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits); - if (nr_upper_bits) { - /* We need to mask out some bits of the upper byte. */ - u8 mask = (1 << nr_upper_bits) - 1; +#ifdef __BIG_ENDIAN_BITFIELD + left_shift_bits = bits_offset; +#else + left_shift_bits = BITS_PER_U64 - nr_copy_bits; +#endif + right_shift_bits = BITS_PER_U64 - nr_bits; - print_num.u8_nums[nr_copy_bytes - 1] &= mask; - } - - print_num.u64_num >>= bits_offset; + print_num <<= left_shift_bits; + print_num >>= right_shift_bits; - seq_printf(m, "0x%llx", print_num.u64_num); + seq_printf(m, "0x%llx", print_num); } static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, -- cgit v1.2.3 From c7a897843224a92209f306c984975b704969b89d Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 12 Jul 2018 21:44:28 +0200 Subject: bpf: don't leave partial mangled prog in jit_subprogs error path syzkaller managed to trigger the following bug through fault injection: [...] [ 141.043668] verifier bug. No program starts at insn 3 [ 141.044648] WARNING: CPU: 3 PID: 4072 at kernel/bpf/verifier.c:1613 get_callee_stack_depth kernel/bpf/verifier.c:1612 [inline] [ 141.044648] WARNING: CPU: 3 PID: 4072 at kernel/bpf/verifier.c:1613 fixup_call_args kernel/bpf/verifier.c:5587 [inline] [ 141.044648] WARNING: CPU: 3 PID: 4072 at kernel/bpf/verifier.c:1613 bpf_check+0x525e/0x5e60 kernel/bpf/verifier.c:5952 [ 141.047355] CPU: 3 PID: 4072 Comm: a.out Not tainted 4.18.0-rc4+ #51 [ 141.048446] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),BIOS 1.10.2-1 04/01/2014 [ 141.049877] Call Trace: [ 141.050324] __dump_stack lib/dump_stack.c:77 [inline] [ 141.050324] dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113 [ 141.050950] ? dump_stack_print_info.cold.2+0x52/0x52 lib/dump_stack.c:60 [ 141.051837] panic+0x238/0x4e7 kernel/panic.c:184 [ 141.052386] ? add_taint.cold.5+0x16/0x16 kernel/panic.c:385 [ 141.053101] ? __warn.cold.8+0x148/0x1ba kernel/panic.c:537 [ 141.053814] ? __warn.cold.8+0x117/0x1ba kernel/panic.c:530 [ 141.054506] ? get_callee_stack_depth kernel/bpf/verifier.c:1612 [inline] [ 141.054506] ? fixup_call_args kernel/bpf/verifier.c:5587 [inline] [ 141.054506] ? bpf_check+0x525e/0x5e60 kernel/bpf/verifier.c:5952 [ 141.055163] __warn.cold.8+0x163/0x1ba kernel/panic.c:538 [ 141.055820] ? get_callee_stack_depth kernel/bpf/verifier.c:1612 [inline] [ 141.055820] ? fixup_call_args kernel/bpf/verifier.c:5587 [inline] [ 141.055820] ? bpf_check+0x525e/0x5e60 kernel/bpf/verifier.c:5952 [...] What happens in jit_subprogs() is that kcalloc() for the subprog func buffer is failing with NULL where we then bail out. Latter is a plain return -ENOMEM, and this is definitely not okay since earlier in the loop we are walking all subprogs and temporarily rewrite insn->off to remember the subprog id as well as insn->imm to temporarily point the call to __bpf_call_base + 1 for the initial JIT pass. Thus, bailing out in such state and handing this over to the interpreter is troublesome since later/subsequent e.g. find_subprog() lookups are based on wrong insn->imm. Therefore, once we hit this point, we need to jump to out_free path where we undo all changes from earlier loop, so that interpreter can work on unmodified insn->{off,imm}. Another point is that should find_subprog() fail in jit_subprogs() due to a verifier bug, then we also should not simply defer the program to the interpreter since also here we did partial modifications. Instead we should just bail out entirely and return an error to the user who is trying to load the program. Fixes: 1c2a088a6626 ("bpf: x64: add JIT support for multi-function programs") Reported-by: syzbot+7d427828b2ea6e592804@syzkaller.appspotmail.com Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9e2bf834f13a..63aaac52a265 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5430,6 +5430,10 @@ static int jit_subprogs(struct bpf_verifier_env *env) if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; + /* Upon error here we cannot fall back to interpreter but + * need a hard reject of the program. Thus -EFAULT is + * propagated in any case. + */ subprog = find_subprog(env, i + insn->imm + 1); if (subprog < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", @@ -5450,7 +5454,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL); if (!func) - return -ENOMEM; + goto out_undo_insn; for (i = 0; i < env->subprog_cnt; i++) { subprog_start = subprog_end; @@ -5515,7 +5519,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) tmp = bpf_int_jit_compile(func[i]); if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) { verbose(env, "JIT doesn't support bpf-to-bpf calls\n"); - err = -EFAULT; + err = -ENOTSUPP; goto out_free; } cond_resched(); @@ -5552,6 +5556,7 @@ out_free: if (func[i]) bpf_jit_free(func[i]); kfree(func); +out_undo_insn: /* cleanup main prog to be interpreted */ prog->jit_requested = 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { @@ -5578,6 +5583,8 @@ static int fixup_call_args(struct bpf_verifier_env *env) err = jit_subprogs(env); if (err == 0) return 0; + if (err == -EFAULT) + return err; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON for (i = 0; i < prog->len; i++, insn++) { -- cgit v1.2.3