diff --git a/Documentation/networking/strparser.rst b/Documentation/networking/strparser.rst
index 6cab1f74ae05a39e54cdba498928d7ef1d6953da..7f623d1db72aae7b50ee0bc529dc7be67b8c82fd 100644
--- a/Documentation/networking/strparser.rst
+++ b/Documentation/networking/strparser.rst
@@ -112,7 +112,7 @@ Functions
Callbacks
=========
-There are six callbacks:
+There are seven callbacks:
::
@@ -182,6 +182,13 @@ There are six callbacks:
the length of the message. skb->len - offset may be greater
then full_len since strparser does not trim the skb.
+ ::
+
+ int (*read_sock)(struct strparser *strp, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor);
+
+ The read_sock callback is used by strparser instead of
+ sock->ops->read_sock, if provided.
::
int (*read_sock_done)(struct strparser *strp, int err);
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 2cbe0c22a32f3cd3040e6994b1d442097be9259c..0b9095a281b8988dfd06c69254d2bcbedcfaf6b4 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -91,6 +91,8 @@ struct sk_psock {
struct sk_psock_progs progs;
#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
struct strparser strp;
+ u32 copied_seq;
+ u32 ingress_bytes;
#endif
struct sk_buff_head ingress_skb;
struct list_head ingress_msg;
diff --git a/include/net/strparser.h b/include/net/strparser.h
index 41e2ce9e9e10ff5018a76b142e9372aa4276bc5b..0a83010b3a64a9d87803e50f51feac1cdbc92794 100644
--- a/include/net/strparser.h
+++ b/include/net/strparser.h
@@ -43,6 +43,8 @@ struct strparser;
struct strp_callbacks {
int (*parse_msg)(struct strparser *strp, struct sk_buff *skb);
void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb);
+ int (*read_sock)(struct strparser *strp, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor);
int (*read_sock_done)(struct strparser *strp, int err);
void (*abort_parser)(struct strparser *strp, int err);
void (*lock)(struct strparser *strp);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 930cda5b5eb98dc6d83418d6ffadc0cb5f0b4ca1..2d08473a6dc0039c46893fbd0e538abdfd4fc993 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -743,6 +743,9 @@ void tcp_get_info(struct sock *, struct tcp_info *);
/* Read 'sendfile()'-style from a TCP socket */
int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
sk_read_actor_t recv_actor);
+int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor, bool noack,
+ u32 *copied_seq);
int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor);
struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off);
void tcp_read_done(struct sock *sk, size_t len);
@@ -2613,6 +2616,11 @@ struct sk_psock;
#ifdef CONFIG_BPF_SYSCALL
int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
void tcp_bpf_clone(const struct sock *sk, struct sock *newsk);
+#ifdef CONFIG_BPF_STREAM_PARSER
+struct strparser;
+int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor);
+#endif /* CONFIG_BPF_STREAM_PARSER */
#endif /* CONFIG_BPF_SYSCALL */
#ifdef CONFIG_INET
diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index 870aeb51d70add0b1fb238a0d91acd7baea171af..095a9554e1def67b04d92dc4560b50edf531e324 100644
--- a/kernel/bpf/arena.c
+++ b/kernel/bpf/arena.c
@@ -39,7 +39,7 @@
*/
/* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */
-#define GUARD_SZ (1ull << sizeof_field(struct bpf_insn, off) * 8)
+#define GUARD_SZ round_up(1ull << sizeof_field(struct bpf_insn, off) * 8, PAGE_SIZE << 1)
#define KERN_VM_SZ (SZ_4G + GUARD_SZ)
struct bpf_arena {
diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c
index d5dc65bb175509d2bf83cb529fa9a8201a7c5c5c..54ff2a85d4c0220b2c84486642f1ea544873736e 100644
--- a/kernel/bpf/bpf_cgrp_storage.c
+++ b/kernel/bpf/bpf_cgrp_storage.c
@@ -153,7 +153,7 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
static void cgroup_storage_map_free(struct bpf_map *map)
{
- bpf_local_storage_map_free(map, &cgroup_cache, NULL);
+ bpf_local_storage_map_free(map, &cgroup_cache, &bpf_cgrp_storage_busy);
}
/* *gfp_flags* is a hidden argument provided by the verifier */
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 9de6acddd479b4f5e32a5e6ba43cf369de4cee29..c3223e0db2f51834caf31a420d51f6ea3da71c63 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6507,6 +6507,8 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = {
/* rxrpc */
{ "rxrpc_recvdata", 0x1 },
{ "rxrpc_resend", 0x10 },
+ /* skb */
+ {"kfree_skb", 0x1000},
/* sunrpc */
{ "xs_stream_read_data", 0x1 },
/* ... from xprt_cong_event event class */
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index e1cfe890e0be6486385c4e81816919f4d9170413..1499d8caa9a35152a27fde8d5b34639145906392 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -268,8 +268,6 @@ static int ringbuf_map_mmap_kern(struct bpf_map *map, struct vm_area_struct *vma
/* allow writable mapping for the consumer_pos only */
if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE)
return -EPERM;
- } else {
- vm_flags_clear(vma, VM_MAYWRITE);
}
/* remap_vmalloc_range() checks size and offset constraints */
return remap_vmalloc_range(vma, rb_map->rb,
@@ -289,8 +287,6 @@ static int ringbuf_map_mmap_user(struct bpf_map *map, struct vm_area_struct *vma
* position, and the ring buffer data itself.
*/
return -EPERM;
- } else {
- vm_flags_clear(vma, VM_MAYWRITE);
}
/* remap_vmalloc_range() checks size and offset constraints */
return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index c420edbfb7c874ddc5f0ba97d120b16c4ee81c02..e1e42e918ba7f682223e9a78028bb0cc360c01ce 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1035,7 +1035,7 @@ static const struct vm_operations_struct bpf_map_default_vmops = {
static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
{
struct bpf_map *map = filp->private_data;
- int err;
+ int err = 0;
if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record))
return -ENOTSUPP;
@@ -1059,24 +1059,33 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
err = -EACCES;
goto out;
}
+ bpf_map_write_active_inc(map);
}
+out:
+ mutex_unlock(&map->freeze_mutex);
+ if (err)
+ return err;
/* set default open/close callbacks */
vma->vm_ops = &bpf_map_default_vmops;
vma->vm_private_data = map;
vm_flags_clear(vma, VM_MAYEXEC);
+ /* If mapping is read-only, then disallow potentially re-mapping with
+ * PROT_WRITE by dropping VM_MAYWRITE flag. This VM_MAYWRITE clearing
+ * means that as far as BPF map's memory-mapped VMAs are concerned,
+ * VM_WRITE and VM_MAYWRITE and equivalent, if one of them is set,
+ * both should be set, so we can forget about VM_MAYWRITE and always
+ * check just VM_WRITE
+ */
if (!(vma->vm_flags & VM_WRITE))
- /* disallow re-mapping with PROT_WRITE */
vm_flags_clear(vma, VM_MAYWRITE);
err = map->ops->map_mmap(map, vma);
- if (err)
- goto out;
+ if (err) {
+ if (vma->vm_flags & VM_WRITE)
+ bpf_map_write_active_dec(map);
+ }
- if (vma->vm_flags & VM_MAYWRITE)
- bpf_map_write_active_inc(map);
-out:
- mutex_unlock(&map->freeze_mutex);
return err;
}
@@ -1968,8 +1977,6 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
return err;
}
-#define MAP_LOOKUP_RETRIES 3
-
int generic_map_lookup_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
@@ -1979,8 +1986,8 @@ int generic_map_lookup_batch(struct bpf_map *map,
void __user *values = u64_to_user_ptr(attr->batch.values);
void __user *keys = u64_to_user_ptr(attr->batch.keys);
void *buf, *buf_prevkey, *prev_key, *key, *value;
- int err, retry = MAP_LOOKUP_RETRIES;
u32 value_size, cp, max_count;
+ int err;
if (attr->batch.elem_flags & ~BPF_F_LOCK)
return -EINVAL;
@@ -2026,14 +2033,8 @@ int generic_map_lookup_batch(struct bpf_map *map,
err = bpf_map_copy_value(map, key, value,
attr->batch.elem_flags);
- if (err == -ENOENT) {
- if (retry) {
- retry--;
- continue;
- }
- err = -EINTR;
- break;
- }
+ if (err == -ENOENT)
+ goto next_key;
if (err)
goto free_buf;
@@ -2048,12 +2049,12 @@ int generic_map_lookup_batch(struct bpf_map *map,
goto free_buf;
}
+ cp++;
+next_key:
if (!prev_key)
prev_key = buf_prevkey;
swap(prev_key, key);
- retry = MAP_LOOKUP_RETRIES;
- cp++;
cond_resched();
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9971c03adfd5d69645e057dc9f8f55ecdd45f908..60611df77957a5eb807eebd86bab8efe2943d2c7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1501,6 +1501,8 @@ static int acquire_lock_state(struct bpf_verifier_env *env, int insn_idx, enum r
struct bpf_reference_state *s;
s = acquire_reference_state(env, insn_idx);
+ if (!s)
+ return -ENOMEM;
s->type = type;
s->id = id;
s->ptr = ptr;
@@ -9149,10 +9151,11 @@ static int check_reg_const_str(struct bpf_verifier_env *env,
return 0;
}
-/* Returns constant key value if possible, else negative error */
-static s64 get_constant_map_key(struct bpf_verifier_env *env,
+/* Returns constant key value in `value` if possible, else negative error */
+static int get_constant_map_key(struct bpf_verifier_env *env,
struct bpf_reg_state *key,
- u32 key_size)
+ u32 key_size,
+ s64 *value)
{
struct bpf_func_state *state = func(env, key);
struct bpf_reg_state *reg;
@@ -9179,8 +9182,10 @@ static s64 get_constant_map_key(struct bpf_verifier_env *env,
/* First handle precisely tracked STACK_ZERO */
for (i = off; i >= 0 && stype[i] == STACK_ZERO; i--)
zero_size++;
- if (zero_size >= key_size)
+ if (zero_size >= key_size) {
+ *value = 0;
return 0;
+ }
/* Check that stack contains a scalar spill of expected size */
if (!is_spilled_scalar_reg(&state->stack[spi]))
@@ -9203,9 +9208,12 @@ static s64 get_constant_map_key(struct bpf_verifier_env *env,
if (err < 0)
return err;
- return reg->var_off.value;
+ *value = reg->var_off.value;
+ return 0;
}
+static bool can_elide_value_nullness(enum bpf_map_type type);
+
static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
struct bpf_call_arg_meta *meta,
const struct bpf_func_proto *fn,
@@ -9354,9 +9362,16 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
err = check_helper_mem_access(env, regno, key_size, BPF_READ, false, NULL);
if (err)
return err;
- meta->const_map_key = get_constant_map_key(env, reg, key_size);
- if (meta->const_map_key < 0 && meta->const_map_key != -EOPNOTSUPP)
- return meta->const_map_key;
+ if (can_elide_value_nullness(meta->map_ptr->map_type)) {
+ err = get_constant_map_key(env, reg, key_size, &meta->const_map_key);
+ if (err < 0) {
+ meta->const_map_key = -1;
+ if (err == -EOPNOTSUPP)
+ err = 0;
+ else
+ return err;
+ }
+ }
break;
case ARG_PTR_TO_MAP_VALUE:
if (type_may_be_null(arg_type) && register_is_null(reg))
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 8f6f7db48d4e40ef0a3e0c9debe5b6ae357121e3..7cb192cbd65f322baf11882adaee27adaacb4820 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -660,12 +660,9 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size,
void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
void *data;
- if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom)
+ if (user_size < ETH_HLEN || user_size > PAGE_SIZE - headroom - tailroom)
return ERR_PTR(-EINVAL);
- if (user_size > size)
- return ERR_PTR(-EMSGSIZE);
-
size = SKB_DATA_ALIGN(size);
data = kzalloc(size + headroom + tailroom, GFP_USER);
if (!data)
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 7d41cde1bcca625ac7d49b7923833f70c4aa2cd6..2e538399757fea25720a9ead6301234103133e3d 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -355,11 +355,6 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = {
static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog)
{
- const struct btf *btf_vmlinux;
- const struct btf_type *t;
- const char *tname;
- u32 btf_id;
-
if (prog->aux->dst_prog)
return false;
@@ -374,13 +369,7 @@ static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog)
return true;
case BPF_TRACE_FENTRY:
case BPF_TRACE_FEXIT:
- btf_vmlinux = bpf_get_btf_vmlinux();
- if (IS_ERR_OR_NULL(btf_vmlinux))
- return false;
- btf_id = prog->aux->attach_btf_id;
- t = btf_type_by_id(btf_vmlinux, btf_id);
- tname = btf_name_by_offset(btf_vmlinux, t->name_off);
- return !!strncmp(tname, "bpf_sk_storage",
+ return !!strncmp(prog->aux->attach_func_name, "bpf_sk_storage",
strlen("bpf_sk_storage"));
default:
return false;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 61f3f3d4e52856c5c1355c3b419adec82f97c571..0ddc4c7188332a60f2875b11276e3f9487b36728 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -549,6 +549,9 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
return num_sge;
}
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
+ psock->ingress_bytes += len;
+#endif
copied = len;
msg->sg.start = 0;
msg->sg.size = copied;
@@ -1144,6 +1147,10 @@ int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
if (!ret)
sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED);
+ if (sk_is_tcp(sk)) {
+ psock->strp.cb.read_sock = tcp_bpf_strp_read_sock;
+ psock->copied_seq = tcp_sk(sk)->copied_seq;
+ }
return ret;
}
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 2f1be9baad0578e2202b5cf79616b6e814c1ed54..82a14f131d00c604f1dfa51e51563aeacda44198 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -303,7 +303,10 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk)
write_lock_bh(&sk->sk_callback_lock);
if (stream_parser && stream_verdict && !psock->saved_data_ready) {
- ret = sk_psock_init_strp(sk, psock);
+ if (sk_is_tcp(sk))
+ ret = sk_psock_init_strp(sk, psock);
+ else
+ ret = -EOPNOTSUPP;
if (ret) {
write_unlock_bh(&sk->sk_callback_lock);
sk_psock_put(sk, psock);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0d704bda6c416bd722223eb19bec5667df4e7bb7..285678d8ce07771600d381734beb5e32fb2926af 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1565,12 +1565,13 @@ EXPORT_SYMBOL(tcp_recv_skb);
* or for 'peeking' the socket using this routine
* (although both would be easy to implement).
*/
-int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
- sk_read_actor_t recv_actor)
+static int __tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor, bool noack,
+ u32 *copied_seq)
{
struct sk_buff *skb;
struct tcp_sock *tp = tcp_sk(sk);
- u32 seq = tp->copied_seq;
+ u32 seq = *copied_seq;
u32 offset;
int copied = 0;
@@ -1624,9 +1625,12 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
tcp_eat_recv_skb(sk, skb);
if (!desc->count)
break;
- WRITE_ONCE(tp->copied_seq, seq);
+ WRITE_ONCE(*copied_seq, seq);
}
- WRITE_ONCE(tp->copied_seq, seq);
+ WRITE_ONCE(*copied_seq, seq);
+
+ if (noack)
+ goto out;
tcp_rcv_space_adjust(sk);
@@ -1635,10 +1639,25 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
tcp_recv_skb(sk, seq, &offset);
tcp_cleanup_rbuf(sk, copied);
}
+out:
return copied;
}
+
+int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor)
+{
+ return __tcp_read_sock(sk, desc, recv_actor, false,
+ &tcp_sk(sk)->copied_seq);
+}
EXPORT_SYMBOL(tcp_read_sock);
+int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor, bool noack,
+ u32 *copied_seq)
+{
+ return __tcp_read_sock(sk, desc, recv_actor, noack, copied_seq);
+}
+
int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
{
struct sk_buff *skb;
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 47f65b1b70ca2e4bc7db049a22d0f70bc02a3daf..ba581785adb4b37e6d06da40728cfb7fdf74db61 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -646,6 +646,42 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops)
ops->sendmsg == tcp_sendmsg ? 0 : -ENOTSUPP;
}
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
+int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc,
+ sk_read_actor_t recv_actor)
+{
+ struct sock *sk = strp->sk;
+ struct sk_psock *psock;
+ struct tcp_sock *tp;
+ int copied = 0;
+
+ tp = tcp_sk(sk);
+ rcu_read_lock();
+ psock = sk_psock(sk);
+ if (WARN_ON_ONCE(!psock)) {
+ desc->error = -EINVAL;
+ goto out;
+ }
+
+ psock->ingress_bytes = 0;
+ copied = tcp_read_sock_noack(sk, desc, recv_actor, true,
+ &psock->copied_seq);
+ if (copied < 0)
+ goto out;
+ /* recv_actor may redirect skb to another socket (SK_REDIRECT) or
+ * just put skb into ingress queue of current socket (SK_PASS).
+ * For SK_REDIRECT, we need to ack the frame immediately but for
+ * SK_PASS, we want to delay the ack until tcp_bpf_recvmsg_parser().
+ */
+ tp->copied_seq = psock->copied_seq - psock->ingress_bytes;
+ tcp_rcv_space_adjust(sk);
+ __tcp_cleanup_rbuf(sk, copied - psock->ingress_bytes);
+out:
+ rcu_read_unlock();
+ return copied;
+}
+#endif /* CONFIG_BPF_STREAM_PARSER */
+
int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
{
int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 8299ceb3e3739dca9ccda67f91c81b806f482d05..95696f42647ec1f5510ea02cd663d421a0ed44d2 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -347,7 +347,10 @@ static int strp_read_sock(struct strparser *strp)
struct socket *sock = strp->sk->sk_socket;
read_descriptor_t desc;
- if (unlikely(!sock || !sock->ops || !sock->ops->read_sock))
+ if (unlikely(!sock || !sock->ops))
+ return -EBUSY;
+
+ if (unlikely(!strp->cb.read_sock && !sock->ops->read_sock))
return -EBUSY;
desc.arg.data = strp;
@@ -355,7 +358,10 @@ static int strp_read_sock(struct strparser *strp)
desc.count = 1; /* give more than one skb per call */
/* sk should be locked here, so okay to do read_sock */
- sock->ops->read_sock(strp->sk, &desc, strp_recv);
+ if (strp->cb.read_sock)
+ strp->cb.read_sock(strp, &desc, strp_recv);
+ else
+ sock->ops->read_sock(strp->sk, &desc, strp_recv);
desc.error = strp->cb.read_sock_done(strp, desc.error);
@@ -468,6 +474,7 @@ int strp_init(struct strparser *strp, struct sock *sk,
strp->cb.unlock = cb->unlock ? : strp_sock_unlock;
strp->cb.rcv_msg = cb->rcv_msg;
strp->cb.parse_msg = cb->parse_msg;
+ strp->cb.read_sock = cb->read_sock;
strp->cb.read_sock_done = cb->read_sock_done ? : default_read_sock_done;
strp->cb.abort_parser = cb->abort_parser ? : strp_abort_strp;
diff --git a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c
index 66191ae9863c1d4589ecf367cc9bfa4eac54399d..79c3ccadb962289fa9a38ad04dd40f2c2e0f294f 100644
--- a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c
@@ -120,11 +120,12 @@ static void validate_fetch_results(int outer_map_fd,
static void fetch_and_validate(int outer_map_fd,
struct bpf_map_batch_opts *opts,
- __u32 batch_size, bool delete_entries)
+ __u32 batch_size, bool delete_entries,
+ bool has_holes)
{
- __u32 *fetched_keys, *fetched_values, total_fetched = 0;
- __u32 batch_key = 0, fetch_count, step_size;
- int err, max_entries = OUTER_MAP_ENTRIES;
+ int err, max_entries = OUTER_MAP_ENTRIES - !!has_holes;
+ __u32 *fetched_keys, *fetched_values, total_fetched = 0, i;
+ __u32 batch_key = 0, fetch_count, step_size = batch_size;
__u32 value_size = sizeof(__u32);
/* Total entries needs to be fetched */
@@ -134,9 +135,8 @@ static void fetch_and_validate(int outer_map_fd,
"Memory allocation failed for fetched_keys or fetched_values",
"error=%s\n", strerror(errno));
- for (step_size = batch_size;
- step_size <= max_entries;
- step_size += batch_size) {
+ /* hash map may not always return full batch */
+ for (i = 0; i < OUTER_MAP_ENTRIES; i++) {
fetch_count = step_size;
err = delete_entries
? bpf_map_lookup_and_delete_batch(outer_map_fd,
@@ -155,6 +155,7 @@ static void fetch_and_validate(int outer_map_fd,
if (err && errno == ENOSPC) {
/* Fetch again with higher batch size */
total_fetched = 0;
+ step_size += batch_size;
continue;
}
@@ -184,18 +185,19 @@ static void fetch_and_validate(int outer_map_fd,
}
static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type,
- enum bpf_map_type inner_map_type)
+ enum bpf_map_type inner_map_type,
+ bool has_holes)
{
+ __u32 max_entries = OUTER_MAP_ENTRIES - !!has_holes;
__u32 *outer_map_keys, *inner_map_fds;
- __u32 max_entries = OUTER_MAP_ENTRIES;
LIBBPF_OPTS(bpf_map_batch_opts, opts);
__u32 value_size = sizeof(__u32);
int batch_size[2] = {5, 10};
__u32 map_index, op_index;
int outer_map_fd, ret;
- outer_map_keys = calloc(max_entries, value_size);
- inner_map_fds = calloc(max_entries, value_size);
+ outer_map_keys = calloc(OUTER_MAP_ENTRIES, value_size);
+ inner_map_fds = calloc(OUTER_MAP_ENTRIES, value_size);
CHECK((!outer_map_keys || !inner_map_fds),
"Memory allocation failed for outer_map_keys or inner_map_fds",
"error=%s\n", strerror(errno));
@@ -209,6 +211,24 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type,
((outer_map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
? 9 : 1000) - map_index;
+ /* This condition is only meaningful for array of maps.
+ *
+ * max_entries == OUTER_MAP_ENTRIES - 1 if it is true. Say
+ * max_entries is short for n, then outer_map_keys looks like:
+ *
+ * [n, n-1, ... 2, 1]
+ *
+ * We change it to
+ *
+ * [n, n-1, ... 2, 0]
+ *
+ * So it will leave key 1 as a hole. It will serve to test the
+ * correctness when batch on an array: a "non-exist" key might be
+ * actually allocated and returned from key iteration.
+ */
+ if (has_holes)
+ outer_map_keys[max_entries - 1]--;
+
/* batch operation - map_update */
ret = bpf_map_update_batch(outer_map_fd, outer_map_keys,
inner_map_fds, &max_entries, &opts);
@@ -219,15 +239,17 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type,
/* batch operation - map_lookup */
for (op_index = 0; op_index < 2; ++op_index)
fetch_and_validate(outer_map_fd, &opts,
- batch_size[op_index], false);
+ batch_size[op_index], false,
+ has_holes);
/* batch operation - map_lookup_delete */
if (outer_map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
fetch_and_validate(outer_map_fd, &opts,
- max_entries, true /*delete*/);
+ max_entries, true /*delete*/,
+ has_holes);
/* close all map fds */
- for (map_index = 0; map_index < max_entries; map_index++)
+ for (map_index = 0; map_index < OUTER_MAP_ENTRIES; map_index++)
close(inner_map_fds[map_index]);
close(outer_map_fd);
@@ -237,16 +259,20 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type,
void test_map_in_map_batch_ops_array(void)
{
- _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY);
+ _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY, false);
printf("%s:PASS with inner ARRAY map\n", __func__);
- _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH);
+ _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH, false);
printf("%s:PASS with inner HASH map\n", __func__);
+ _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY, true);
+ printf("%s:PASS with inner ARRAY map with holes\n", __func__);
+ _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH, true);
+ printf("%s:PASS with inner HASH map with holes\n", __func__);
}
void test_map_in_map_batch_ops_hash(void)
{
- _map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_ARRAY);
+ _map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_ARRAY, false);
printf("%s:PASS with inner ARRAY map\n", __func__);
- _map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_HASH);
+ _map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_HASH, false);
printf("%s:PASS with inner HASH map\n", __func__);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 05eb37935c3e290ee52b8d8c7c3e3a8db026cba2..1e3e4392dcca0e1722c1982ecc649a80c27443b2 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -526,8 +526,8 @@ static void test_sockmap_skb_verdict_shutdown(void)
if (!ASSERT_EQ(err, 1, "epoll_wait(fd)"))
goto out_close;
- n = recv(c1, &b, 1, SOCK_NONBLOCK);
- ASSERT_EQ(n, 0, "recv_timeout(fin)");
+ n = recv(c1, &b, 1, MSG_DONTWAIT);
+ ASSERT_EQ(n, 0, "recv(fin)");
out_close:
close(c1);
close(p1);
@@ -535,57 +535,6 @@ static void test_sockmap_skb_verdict_shutdown(void)
test_sockmap_pass_prog__destroy(skel);
}
-static void test_sockmap_stream_pass(void)
-{
- int zero = 0, sent, recvd;
- int verdict, parser;
- int err, map;
- int c = -1, p = -1;
- struct test_sockmap_pass_prog *pass = NULL;
- char snd[256] = "0123456789";
- char rcv[256] = "0";
-
- pass = test_sockmap_pass_prog__open_and_load();
- verdict = bpf_program__fd(pass->progs.prog_skb_verdict);
- parser = bpf_program__fd(pass->progs.prog_skb_parser);
- map = bpf_map__fd(pass->maps.sock_map_rx);
-
- err = bpf_prog_attach(parser, map, BPF_SK_SKB_STREAM_PARSER, 0);
- if (!ASSERT_OK(err, "bpf_prog_attach stream parser"))
- goto out;
-
- err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
- if (!ASSERT_OK(err, "bpf_prog_attach stream verdict"))
- goto out;
-
- err = create_pair(AF_INET, SOCK_STREAM, &c, &p);
- if (err)
- goto out;
-
- /* sk_data_ready of 'p' will be replaced by strparser handler */
- err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
- if (!ASSERT_OK(err, "bpf_map_update_elem(p)"))
- goto out_close;
-
- /*
- * as 'prog_skb_parser' return the original skb len and
- * 'prog_skb_verdict' return SK_PASS, the kernel will just
- * pass it through to original socket 'p'
- */
- sent = xsend(c, snd, sizeof(snd), 0);
- ASSERT_EQ(sent, sizeof(snd), "xsend(c)");
-
- recvd = recv_timeout(p, rcv, sizeof(rcv), SOCK_NONBLOCK,
- IO_TIMEOUT_SEC);
- ASSERT_EQ(recvd, sizeof(rcv), "recv_timeout(p)");
-
-out_close:
- close(c);
- close(p);
-
-out:
- test_sockmap_pass_prog__destroy(pass);
-}
static void test_sockmap_skb_verdict_fionread(bool pass_prog)
{
@@ -632,7 +581,7 @@ static void test_sockmap_skb_verdict_fionread(bool pass_prog)
ASSERT_EQ(avail, expected, "ioctl(FIONREAD)");
/* On DROP test there will be no data to read */
if (pass_prog) {
- recvd = recv_timeout(c1, &buf, sizeof(buf), SOCK_NONBLOCK, IO_TIMEOUT_SEC);
+ recvd = recv_timeout(c1, &buf, sizeof(buf), MSG_DONTWAIT, IO_TIMEOUT_SEC);
ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)");
}
@@ -1133,8 +1082,6 @@ void test_sockmap_basic(void)
test_sockmap_progs_query(BPF_SK_SKB_VERDICT);
if (test__start_subtest("sockmap skb_verdict shutdown"))
test_sockmap_skb_verdict_shutdown();
- if (test__start_subtest("sockmap stream parser and verdict pass"))
- test_sockmap_stream_pass();
if (test__start_subtest("sockmap skb_verdict fionread"))
test_sockmap_skb_verdict_fionread(true);
if (test__start_subtest("sockmap skb_verdict fionread on drop"))
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c b/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c
new file mode 100644
index 0000000000000000000000000000000000000000..621b3b71888efe1a0ae2f4e05fe8cbe03acf8d44
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c
@@ -0,0 +1,454 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <netinet/tcp.h>
+#include <test_progs.h>
+#include "sockmap_helpers.h"
+#include "test_skmsg_load_helpers.skel.h"
+#include "test_sockmap_strp.skel.h"
+
+#define STRP_PKT_HEAD_LEN 4
+#define STRP_PKT_BODY_LEN 6
+#define STRP_PKT_FULL_LEN (STRP_PKT_HEAD_LEN + STRP_PKT_BODY_LEN)
+
+static const char packet[STRP_PKT_FULL_LEN] = "head+body\0";
+static const int test_packet_num = 100;
+
+/* Current implementation of tcp_bpf_recvmsg_parser() invokes data_ready
+ * with sk held if an skb exists in sk_receive_queue. Then for the
+ * data_ready implementation of strparser, it will delay the read
+ * operation if sk is held and EAGAIN is returned.
+ */
+static int sockmap_strp_consume_pre_data(int p)
+{
+ int recvd;
+ bool retried = false;
+ char rcv[10];
+
+retry:
+ errno = 0;
+ recvd = recv_timeout(p, rcv, sizeof(rcv), 0, 1);
+ if (recvd < 0 && errno == EAGAIN && retried == false) {
+ /* On the first call, EAGAIN will certainly be returned.
+ * A 1-second wait is enough for the workqueue to finish.
+ */
+ sleep(1);
+ retried = true;
+ goto retry;
+ }
+
+ if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "recv error or truncated data") ||
+ !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN),
+ "data mismatch"))
+ return -1;
+ return 0;
+}
+
+static struct test_sockmap_strp *sockmap_strp_init(int *out_map, bool pass,
+ bool need_parser)
+{
+ struct test_sockmap_strp *strp = NULL;
+ int verdict, parser;
+ int err;
+
+ strp = test_sockmap_strp__open_and_load();
+ *out_map = bpf_map__fd(strp->maps.sock_map);
+
+ if (need_parser)
+ parser = bpf_program__fd(strp->progs.prog_skb_parser_partial);
+ else
+ parser = bpf_program__fd(strp->progs.prog_skb_parser);
+
+ if (pass)
+ verdict = bpf_program__fd(strp->progs.prog_skb_verdict_pass);
+ else
+ verdict = bpf_program__fd(strp->progs.prog_skb_verdict);
+
+ err = bpf_prog_attach(parser, *out_map, BPF_SK_SKB_STREAM_PARSER, 0);
+ if (!ASSERT_OK(err, "bpf_prog_attach stream parser"))
+ goto err;
+
+ err = bpf_prog_attach(verdict, *out_map, BPF_SK_SKB_STREAM_VERDICT, 0);
+ if (!ASSERT_OK(err, "bpf_prog_attach stream verdict"))
+ goto err;
+
+ return strp;
+err:
+ test_sockmap_strp__destroy(strp);
+ return NULL;
+}
+
+/* Dispatch packets to different socket by packet size:
+ *
+ * ------ ------
+ * | pkt4 || pkt1 |... > remote socket
+ * ------ ------ / ------ ------
+ * | pkt8 | pkt7 |...
+ * ------ ------ \ ------ ------
+ * | pkt3 || pkt2 |... > local socket
+ * ------ ------
+ */
+static void test_sockmap_strp_dispatch_pkt(int family, int sotype)
+{
+ int i, j, zero = 0, one = 1, recvd;
+ int err, map;
+ int c0 = -1, p0 = -1, c1 = -1, p1 = -1;
+ struct test_sockmap_strp *strp = NULL;
+ int test_cnt = 6;
+ char rcv[10];
+ struct {
+ char data[7];
+ int data_len;
+ int send_cnt;
+ int *receiver;
+ } send_dir[2] = {
+ /* data expected to deliver to local */
+ {"llllll", 6, 0, &p0},
+ /* data expected to deliver to remote */
+ {"rrrrr", 5, 0, &c1}
+ };
+
+ strp = sockmap_strp_init(&map, false, false);
+ if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+ return;
+
+ err = create_socket_pairs(family, sotype, &c0, &c1, &p0, &p1);
+ if (!ASSERT_OK(err, "create_socket_pairs()"))
+ goto out;
+
+ err = bpf_map_update_elem(map, &zero, &p0, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem(p0)"))
+ goto out_close;
+
+ err = bpf_map_update_elem(map, &one, &p1, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem(p1)"))
+ goto out_close;
+
+ err = setsockopt(c1, IPPROTO_TCP, TCP_NODELAY, &zero, sizeof(zero));
+ if (!ASSERT_OK(err, "setsockopt(TCP_NODELAY)"))
+ goto out_close;
+
+ /* deliver data with data size greater than 5 to local */
+ strp->data->verdict_max_size = 5;
+
+ for (i = 0; i < test_cnt; i++) {
+ int d = i % 2;
+
+ xsend(c0, send_dir[d].data, send_dir[d].data_len, 0);
+ send_dir[d].send_cnt++;
+ }
+
+ for (i = 0; i < 2; i++) {
+ for (j = 0; j < send_dir[i].send_cnt; j++) {
+ int expected = send_dir[i].data_len;
+
+ recvd = recv_timeout(*send_dir[i].receiver, rcv,
+ expected, MSG_DONTWAIT,
+ IO_TIMEOUT_SEC);
+ if (!ASSERT_EQ(recvd, expected, "recv_timeout()"))
+ goto out_close;
+ if (!ASSERT_OK(memcmp(send_dir[i].data, rcv, recvd),
+ "data mismatch"))
+ goto out_close;
+ }
+ }
+out_close:
+ close(c0);
+ close(c1);
+ close(p0);
+ close(p1);
+out:
+ test_sockmap_strp__destroy(strp);
+}
+
+/* We have multiple packets in one skb
+ * ------------ ------------ ------------
+ * | packet1 | packet2 | ...
+ * ------------ ------------ ------------
+ */
+static void test_sockmap_strp_multiple_pkt(int family, int sotype)
+{
+ int i, zero = 0;
+ int sent, recvd, total;
+ int err, map;
+ int c = -1, p = -1;
+ struct test_sockmap_strp *strp = NULL;
+ char *snd = NULL, *rcv = NULL;
+
+ strp = sockmap_strp_init(&map, true, true);
+ if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+ return;
+
+ err = create_pair(family, sotype, &c, &p);
+ if (err)
+ goto out;
+
+ err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem(zero, p)"))
+ goto out_close;
+
+ /* construct multiple packets in one buffer */
+ total = test_packet_num * STRP_PKT_FULL_LEN;
+ snd = malloc(total);
+ rcv = malloc(total + 1);
+ if (!ASSERT_TRUE(snd, "malloc(snd)") ||
+ !ASSERT_TRUE(rcv, "malloc(rcv)"))
+ goto out_close;
+
+ for (i = 0; i < test_packet_num; i++) {
+ memcpy(snd + i * STRP_PKT_FULL_LEN,
+ packet, STRP_PKT_FULL_LEN);
+ }
+
+ sent = xsend(c, snd, total, 0);
+ if (!ASSERT_EQ(sent, total, "xsend(c)"))
+ goto out_close;
+
+ /* try to recv one more byte to avoid truncation check */
+ recvd = recv_timeout(p, rcv, total + 1, MSG_DONTWAIT, IO_TIMEOUT_SEC);
+ if (!ASSERT_EQ(recvd, total, "recv(rcv)"))
+ goto out_close;
+
+ /* we sent TCP segment with multiple encapsulation
+ * then check whether packets are handled correctly
+ */
+ if (!ASSERT_OK(memcmp(snd, rcv, total), "data mismatch"))
+ goto out_close;
+
+out_close:
+ close(c);
+ close(p);
+ if (snd)
+ free(snd);
+ if (rcv)
+ free(rcv);
+out:
+ test_sockmap_strp__destroy(strp);
+}
+
+/* Test strparser with partial read */
+static void test_sockmap_strp_partial_read(int family, int sotype)
+{
+ int zero = 0, recvd, off;
+ int err, map;
+ int c = -1, p = -1;
+ struct test_sockmap_strp *strp = NULL;
+ char rcv[STRP_PKT_FULL_LEN + 1] = "0";
+
+ strp = sockmap_strp_init(&map, true, true);
+ if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+ return;
+
+ err = create_pair(family, sotype, &c, &p);
+ if (err)
+ goto out;
+
+ /* sk_data_ready of 'p' will be replaced by strparser handler */
+ err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem(zero, p)"))
+ goto out_close;
+
+ /* 1.1 send partial head, 1 byte header left */
+ off = STRP_PKT_HEAD_LEN - 1;
+ xsend(c, packet, off, 0);
+ recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+ if (!ASSERT_EQ(-1, recvd, "partial head sent, expected no data"))
+ goto out_close;
+
+ /* 1.2 send remaining head and body */
+ xsend(c, packet + off, STRP_PKT_FULL_LEN - off, 0);
+ recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, IO_TIMEOUT_SEC);
+ if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "expected full data"))
+ goto out_close;
+
+ /* 2.1 send partial head, 1 byte header left */
+ off = STRP_PKT_HEAD_LEN - 1;
+ xsend(c, packet, off, 0);
+
+ /* 2.2 send remaining head and partial body, 1 byte body left */
+ xsend(c, packet + off, STRP_PKT_FULL_LEN - off - 1, 0);
+ off = STRP_PKT_FULL_LEN - 1;
+ recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+ if (!ASSERT_EQ(-1, recvd, "partial body sent, expected no data"))
+ goto out_close;
+
+ /* 2.3 send remaining body */
+ xsend(c, packet + off, STRP_PKT_FULL_LEN - off, 0);
+ recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, IO_TIMEOUT_SEC);
+ if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "expected full data"))
+ goto out_close;
+
+out_close:
+ close(c);
+ close(p);
+
+out:
+ test_sockmap_strp__destroy(strp);
+}
+
+/* Test simple socket read/write with strparser + FIONREAD */
+static void test_sockmap_strp_pass(int family, int sotype, bool fionread)
+{
+ int zero = 0, pkt_size = STRP_PKT_FULL_LEN, sent, recvd, avail;
+ int err, map;
+ int c = -1, p = -1;
+ int test_cnt = 10, i;
+ struct test_sockmap_strp *strp = NULL;
+ char rcv[STRP_PKT_FULL_LEN + 1] = "0";
+
+ strp = sockmap_strp_init(&map, true, true);
+ if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+ return;
+
+ err = create_pair(family, sotype, &c, &p);
+ if (err)
+ goto out;
+
+ /* inject some data before bpf process, it should be read
+ * correctly because we check sk_receive_queue in
+ * tcp_bpf_recvmsg_parser().
+ */
+ sent = xsend(c, packet, pkt_size, 0);
+ if (!ASSERT_EQ(sent, pkt_size, "xsend(pre-data)"))
+ goto out_close;
+
+ /* sk_data_ready of 'p' will be replaced by strparser handler */
+ err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem(p)"))
+ goto out_close;
+
+ /* consume previous data we injected */
+ if (sockmap_strp_consume_pre_data(p))
+ goto out_close;
+
+ /* Previously, we encountered issues such as deadlocks and
+ * sequence errors that resulted in the inability to read
+ * continuously. Therefore, we perform multiple iterations
+ * of testing here.
+ */
+ for (i = 0; i < test_cnt; i++) {
+ sent = xsend(c, packet, pkt_size, 0);
+ if (!ASSERT_EQ(sent, pkt_size, "xsend(c)"))
+ goto out_close;
+
+ recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT,
+ IO_TIMEOUT_SEC);
+ if (!ASSERT_EQ(recvd, pkt_size, "recv_timeout(p)") ||
+ !ASSERT_OK(memcmp(packet, rcv, pkt_size),
+ "memcmp, data mismatch"))
+ goto out_close;
+ }
+
+ if (fionread) {
+ sent = xsend(c, packet, pkt_size, 0);
+ if (!ASSERT_EQ(sent, pkt_size, "second xsend(c)"))
+ goto out_close;
+
+ err = ioctl(p, FIONREAD, &avail);
+ if (!ASSERT_OK(err, "ioctl(FIONREAD) error") ||
+ !ASSERT_EQ(avail, pkt_size, "ioctl(FIONREAD)"))
+ goto out_close;
+
+ recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT,
+ IO_TIMEOUT_SEC);
+ if (!ASSERT_EQ(recvd, pkt_size, "second recv_timeout(p)") ||
+ !ASSERT_OK(memcmp(packet, rcv, pkt_size),
+ "second memcmp, data mismatch"))
+ goto out_close;
+ }
+
+out_close:
+ close(c);
+ close(p);
+
+out:
+ test_sockmap_strp__destroy(strp);
+}
+
+/* Test strparser with verdict mode */
+static void test_sockmap_strp_verdict(int family, int sotype)
+{
+ int zero = 0, one = 1, sent, recvd, off;
+ int err, map;
+ int c0 = -1, p0 = -1, c1 = -1, p1 = -1;
+ struct test_sockmap_strp *strp = NULL;
+ char rcv[STRP_PKT_FULL_LEN + 1] = "0";
+
+ strp = sockmap_strp_init(&map, false, true);
+ if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+ return;
+
+ /* We simulate a reverse proxy server.
+ * When p0 receives data from c0, we forward it to c1.
+ * From c1's perspective, it will consider this data
+ * as being sent by p1.
+ */
+ err = create_socket_pairs(family, sotype, &c0, &c1, &p0, &p1);
+ if (!ASSERT_OK(err, "create_socket_pairs()"))
+ goto out;
+
+ err = bpf_map_update_elem(map, &zero, &p0, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem(p0)"))
+ goto out_close;
+
+ err = bpf_map_update_elem(map, &one, &p1, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem(p1)"))
+ goto out_close;
+
+ sent = xsend(c0, packet, STRP_PKT_FULL_LEN, 0);
+ if (!ASSERT_EQ(sent, STRP_PKT_FULL_LEN, "xsend(c0)"))
+ goto out_close;
+
+ recvd = recv_timeout(c1, rcv, sizeof(rcv), MSG_DONTWAIT,
+ IO_TIMEOUT_SEC);
+ if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "recv_timeout(c1)") ||
+ !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN),
+ "received data does not match the sent data"))
+ goto out_close;
+
+ /* send again to ensure the stream is functioning correctly. */
+ sent = xsend(c0, packet, STRP_PKT_FULL_LEN, 0);
+ if (!ASSERT_EQ(sent, STRP_PKT_FULL_LEN, "second xsend(c0)"))
+ goto out_close;
+
+ /* partial read */
+ off = STRP_PKT_FULL_LEN / 2;
+ recvd = recv_timeout(c1, rcv, off, MSG_DONTWAIT,
+ IO_TIMEOUT_SEC);
+ recvd += recv_timeout(c1, rcv + off, sizeof(rcv) - off, MSG_DONTWAIT,
+ IO_TIMEOUT_SEC);
+
+ if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "partial recv_timeout(c1)") ||
+ !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN),
+ "partial received data does not match the sent data"))
+ goto out_close;
+
+out_close:
+ close(c0);
+ close(c1);
+ close(p0);
+ close(p1);
+out:
+ test_sockmap_strp__destroy(strp);
+}
+
+void test_sockmap_strp(void)
+{
+ if (test__start_subtest("sockmap strp tcp pass"))
+ test_sockmap_strp_pass(AF_INET, SOCK_STREAM, false);
+ if (test__start_subtest("sockmap strp tcp v6 pass"))
+ test_sockmap_strp_pass(AF_INET6, SOCK_STREAM, false);
+ if (test__start_subtest("sockmap strp tcp pass fionread"))
+ test_sockmap_strp_pass(AF_INET, SOCK_STREAM, true);
+ if (test__start_subtest("sockmap strp tcp v6 pass fionread"))
+ test_sockmap_strp_pass(AF_INET6, SOCK_STREAM, true);
+ if (test__start_subtest("sockmap strp tcp verdict"))
+ test_sockmap_strp_verdict(AF_INET, SOCK_STREAM);
+ if (test__start_subtest("sockmap strp tcp v6 verdict"))
+ test_sockmap_strp_verdict(AF_INET6, SOCK_STREAM);
+ if (test__start_subtest("sockmap strp tcp partial read"))
+ test_sockmap_strp_partial_read(AF_INET, SOCK_STREAM);
+ if (test__start_subtest("sockmap strp tcp multiple packets"))
+ test_sockmap_strp_multiple_pkt(AF_INET, SOCK_STREAM);
+ if (test__start_subtest("sockmap strp tcp dispatch"))
+ test_sockmap_strp_dispatch_pkt(AF_INET, SOCK_STREAM);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
index c7f74f068e78835329f0b1e35c2dffb54adfe3ae..df27535995af8d5fb9823f114b6ed5ac3847d826 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
@@ -52,10 +52,10 @@ static void test_xdp_with_cpumap_helpers(void)
ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to cpumap entry prog_id");
/* send a packet to trigger any potential bugs in there */
- char data[10] = {};
+ char data[ETH_HLEN] = {};
DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
.data_in = &data,
- .data_size_in = 10,
+ .data_size_in = sizeof(data),
.flags = BPF_F_TEST_XDP_LIVE_FRAMES,
.repeat = 1,
);
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
index 27ffed17d4be33fab8776baa1dd1a6055e7194bf..461ab18705d5c0f15ad0b0f4e8869d1e92de2854 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
@@ -23,7 +23,7 @@ static void test_xdp_with_devmap_helpers(void)
__u32 len = sizeof(info);
int err, dm_fd, dm_fd_redir, map_fd;
struct nstoken *nstoken = NULL;
- char data[10] = {};
+ char data[ETH_HLEN] = {};
__u32 idx = 0;
SYS(out_close, "ip netns add %s", TEST_NS);
@@ -58,7 +58,7 @@ static void test_xdp_with_devmap_helpers(void)
/* send a packet to trigger any potential bugs in there */
DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
.data_in = &data,
- .data_size_in = 10,
+ .data_size_in = sizeof(data),
.flags = BPF_F_TEST_XDP_LIVE_FRAMES,
.repeat = 1,
);
@@ -158,7 +158,7 @@ static void test_xdp_with_devmap_helpers_veth(void)
struct nstoken *nstoken = NULL;
__u32 len = sizeof(info);
int err, dm_fd, dm_fd_redir, map_fd, ifindex_dst;
- char data[10] = {};
+ char data[ETH_HLEN] = {};
__u32 idx = 0;
SYS(out_close, "ip netns add %s", TEST_NS);
@@ -208,7 +208,7 @@ static void test_xdp_with_devmap_helpers_veth(void)
/* send a packet to trigger any potential bugs in there */
DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
.data_in = &data,
- .data_size_in = 10,
+ .data_size_in = sizeof(data),
.flags = BPF_F_TEST_XDP_LIVE_FRAMES,
.repeat = 1,
);
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_strp.c b/tools/testing/selftests/bpf/progs/test_sockmap_strp.c
new file mode 100644
index 0000000000000000000000000000000000000000..dde3d5bec5154a649fb2266bf9ca7b6d006ab6df
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_strp.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+int verdict_max_size = 10000;
+struct {
+ __uint(type, BPF_MAP_TYPE_SOCKMAP);
+ __uint(max_entries, 20);
+ __type(key, int);
+ __type(value, int);
+} sock_map SEC(".maps");
+
+SEC("sk_skb/stream_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+ __u32 one = 1;
+
+ if (skb->len > verdict_max_size)
+ return SK_PASS;
+
+ return bpf_sk_redirect_map(skb, &sock_map, one, 0);
+}
+
+SEC("sk_skb/stream_verdict")
+int prog_skb_verdict_pass(struct __sk_buff *skb)
+{
+ return SK_PASS;
+}
+
+SEC("sk_skb/stream_parser")
+int prog_skb_parser(struct __sk_buff *skb)
+{
+ return skb->len;
+}
+
+SEC("sk_skb/stream_parser")
+int prog_skb_parser_partial(struct __sk_buff *skb)
+{
+ /* agreement with the test program on a 4-byte size header
+ * and 6-byte body.
+ */
+ if (skb->len < 4) {
+ /* need more header to determine full length */
+ return 0;
+ }
+ /* return full length decoded from header.
+ * the return value may be larger than skb->len which
+ * means framework must wait body coming.
+ */
+ return 10;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_array_access.c b/tools/testing/selftests/bpf/progs/verifier_array_access.c
index 29eb9568633ffae20f3bf6b7fd24ceef6789f462..0a187ff725cc478c374841e7c990ac2f9ef0f6a9 100644
--- a/tools/testing/selftests/bpf/progs/verifier_array_access.c
+++ b/tools/testing/selftests/bpf/progs/verifier_array_access.c
@@ -713,4 +713,19 @@ unsigned int non_stack_key_lookup(void)
return val->index;
}
+SEC("socket")
+__description("doesn't reject UINT64_MAX as s64 for irrelevant maps")
+__success __retval(42)
+unsigned int doesnt_reject_irrelevant_maps(void)
+{
+ __u64 key = 0xFFFFFFFFFFFFFFFF;
+ struct test_val *val;
+
+ val = bpf_map_lookup_elem(&map_hash_48b, &key);
+ if (val)
+ return val->index;
+
+ return 42;
+}
+
char _license[] SEC("license") = "GPL";