Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Alexei Starovoitov says:

====================
pull-request: bpf 2021-11-09

We've added 7 non-merge commits during the last 3 day(s) which contain
a total of 10 files changed, 174 insertions(+), 48 deletions(-).

The main changes are:

1) Various sockmap fixes, from John and Jussi.

2) Fix out-of-bound issue with bpf_pseudo_func, from Martin.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf, sockmap: sk_skb data_end access incorrect when src_reg = dst_reg
  bpf: sockmap, strparser, and tls are reusing qdisc_skb_cb and colliding
  bpf, sockmap: Fix race in ingress receive verdict with redirect to self
  bpf, sockmap: Remove unhash handler for BPF sockmap usage
  bpf, sockmap: Use stricter sk state checks in sk_lookup_assign
  bpf: selftest: Trigger a DCE on the whole subprog
  bpf: Stop caching subprog index in the bpf_pseudo_func insn
====================

Link: https://lore.kernel.org/r/20211109215702.38350-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 104 insertions, 24 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 8e8d3b49c297..e471c9b09670 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -9756,22 +9756,46 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 static struct bpf_insn *bpf_convert_data_end_access(const struct bpf_insn *si,
 						    struct bpf_insn *insn)
 {
-	/* si->dst_reg = skb->data */
+	int reg;
+	int temp_reg_off = offsetof(struct sk_buff, cb) +
+			   offsetof(struct sk_skb_cb, temp_reg);
+
+	if (si->src_reg == si->dst_reg) {
+		/* We need an extra register, choose and save a register. */
+		reg = BPF_REG_9;
+		if (si->src_reg == reg || si->dst_reg == reg)
+			reg--;
+		if (si->src_reg == reg || si->dst_reg == reg)
+			reg--;
+		*insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, temp_reg_off);
+	} else {
+		reg = si->dst_reg;
+	}
+
+	/* reg = skb->data */
 	*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data),
-			      si->dst_reg, si->src_reg,
+			      reg, si->src_reg,
 			      offsetof(struct sk_buff, data));
 	/* AX = skb->len */
 	*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len),
 			      BPF_REG_AX, si->src_reg,
 			      offsetof(struct sk_buff, len));
-	/* si->dst_reg = skb->data + skb->len */
-	*insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX);
+	/* reg = skb->data + skb->len */
+	*insn++ = BPF_ALU64_REG(BPF_ADD, reg, BPF_REG_AX);
 	/* AX = skb->data_len */
 	*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data_len),
 			      BPF_REG_AX, si->src_reg,
 			      offsetof(struct sk_buff, data_len));
-	/* si->dst_reg = skb->data + skb->len - skb->data_len */
-	*insn++ = BPF_ALU64_REG(BPF_SUB, si->dst_reg, BPF_REG_AX);
+
+	/* reg = skb->data + skb->len - skb->data_len */
+	*insn++ = BPF_ALU64_REG(BPF_SUB, reg, BPF_REG_AX);
+
+	if (si->src_reg == si->dst_reg) {
+		/* Restore the saved register */
+		*insn++ = BPF_MOV64_REG(BPF_REG_AX, si->src_reg);
+		*insn++ = BPF_MOV64_REG(si->dst_reg, reg);
+		*insn++ = BPF_LDX_MEM(BPF_DW, reg, BPF_REG_AX, temp_reg_off);
+	}
 
 	return insn;
 }
@@ -9782,11 +9806,33 @@ static u32 sk_skb_convert_ctx_access(enum bpf_access_type type,
 				     struct bpf_prog *prog, u32 *target_size)
 {
 	struct bpf_insn *insn = insn_buf;
+	int off;
 
 	switch (si->off) {
 	case offsetof(struct __sk_buff, data_end):
 		insn = bpf_convert_data_end_access(si, insn);
 		break;
+	case offsetof(struct __sk_buff, cb[0]) ...
+	     offsetofend(struct __sk_buff, cb[4]) - 1:
+		BUILD_BUG_ON(sizeof_field(struct sk_skb_cb, data) < 20);
+		BUILD_BUG_ON((offsetof(struct sk_buff, cb) +
+			      offsetof(struct sk_skb_cb, data)) %
+			     sizeof(__u64));
+
+		prog->cb_access = 1;
+		off  = si->off;
+		off -= offsetof(struct __sk_buff, cb[0]);
+		off += offsetof(struct sk_buff, cb);
+		off += offsetof(struct sk_skb_cb, data);
+		if (type == BPF_WRITE)
+			*insn++ = BPF_STX_MEM(BPF_SIZE(si->code), si->dst_reg,
+					      si->src_reg, off);
+		else
+			*insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg,
+					      si->src_reg, off);
+		break;
+
+
 	default:
 		return bpf_convert_ctx_access(type, si, insn_buf, prog,
 					      target_size);
@@ -10423,8 +10469,10 @@ BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx,
 		return -EINVAL;
 	if (unlikely(sk && sk_is_refcounted(sk)))
 		return -ESOCKTNOSUPPORT; /* reject non-RCU freed sockets */
-	if (unlikely(sk && sk->sk_state == TCP_ESTABLISHED))
-		return -ESOCKTNOSUPPORT; /* reject connected sockets */
+	if (unlikely(sk && sk_is_tcp(sk) && sk->sk_state != TCP_LISTEN))
+		return -ESOCKTNOSUPPORT; /* only accept TCP socket in LISTEN */
+	if (unlikely(sk && sk_is_udp(sk) && sk->sk_state != TCP_CLOSE))
+		return -ESOCKTNOSUPPORT; /* only accept UDP socket in CLOSE */
 
 	/* Check if socket is suitable for packet L3/L4 protocol */
 	if (sk && sk->sk_protocol != ctx->protocol)
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index e252b8ec2b85..f39ef79ced67 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -511,12 +511,6 @@ static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops)
 	       ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB;
 }
 
-static bool sk_is_tcp(const struct sock *sk)
-{
-	return sk->sk_type == SOCK_STREAM &&
-	       sk->sk_protocol == IPPROTO_TCP;
-}
-
 static bool sock_map_redirect_allowed(const struct sock *sk)
 {
 	if (sk_is_tcp(sk))
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 5f4d6f45d87f..f70aa0932bd6 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -172,6 +172,41 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
 	return ret;
 }
 
+static int tcp_bpf_recvmsg_parser(struct sock *sk,
+				  struct msghdr *msg,
+				  size_t len,
+				  int nonblock,
+				  int flags,
+				  int *addr_len)
+{
+	struct sk_psock *psock;
+	int copied;
+
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return inet_recv_error(sk, msg, len, addr_len);
+
+	psock = sk_psock_get(sk);
+	if (unlikely(!psock))
+		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+
+	lock_sock(sk);
+msg_bytes_ready:
+	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
+	if (!copied) {
+		long timeo;
+		int data;
+
+		timeo = sock_rcvtimeo(sk, nonblock);
+		data = tcp_msg_wait_data(sk, psock, timeo);
+		if (data && !sk_psock_queue_empty(psock))
+			goto msg_bytes_ready;
+		copied = -EAGAIN;
+	}
+	release_sock(sk);
+	sk_psock_put(sk, psock);
+	return copied;
+}
+
 static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		    int nonblock, int flags, int *addr_len)
 {
@@ -464,6 +499,8 @@ enum {
 enum {
 	TCP_BPF_BASE,
 	TCP_BPF_TX,
+	TCP_BPF_RX,
+	TCP_BPF_TXRX,
 	TCP_BPF_NUM_CFGS,
 };
 
@@ -475,7 +512,6 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
 				   struct proto *base)
 {
 	prot[TCP_BPF_BASE]			= *base;
-	prot[TCP_BPF_BASE].unhash		= sock_map_unhash;
 	prot[TCP_BPF_BASE].close		= sock_map_close;
 	prot[TCP_BPF_BASE].recvmsg		= tcp_bpf_recvmsg;
 	prot[TCP_BPF_BASE].sock_is_readable	= sk_msg_is_readable;
@@ -483,6 +519,12 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
 	prot[TCP_BPF_TX]			= prot[TCP_BPF_BASE];
 	prot[TCP_BPF_TX].sendmsg		= tcp_bpf_sendmsg;
 	prot[TCP_BPF_TX].sendpage		= tcp_bpf_sendpage;
+
+	prot[TCP_BPF_RX]			= prot[TCP_BPF_BASE];
+	prot[TCP_BPF_RX].recvmsg		= tcp_bpf_recvmsg_parser;
+
+	prot[TCP_BPF_TXRX]			= prot[TCP_BPF_TX];
+	prot[TCP_BPF_TXRX].recvmsg		= tcp_bpf_recvmsg_parser;
 }
 
 static void tcp_bpf_check_v6_needs_rebuild(struct proto *ops)
@@ -520,6 +562,10 @@ 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;
 	int config = psock->progs.msg_parser   ? TCP_BPF_TX   : TCP_BPF_BASE;
 
+	if (psock->progs.stream_verdict || psock->progs.skb_verdict) {
+		config = (config == TCP_BPF_TX) ? TCP_BPF_TXRX : TCP_BPF_RX;
+	}
+
 	if (restore) {
 		if (inet_csk_has_ulp(sk)) {
 			/* TLS does not have an unhash proto in SW cases,
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 9c0343568d2a..1a72c67afed5 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -27,18 +27,10 @@
 
 static struct workqueue_struct *strp_wq;
 
-struct _strp_msg {
-	/* Internal cb structure. struct strp_msg must be first for passing
-	 * to upper layer.
-	 */
-	struct strp_msg strp;
-	int accum_len;
-};
-
 static inline struct _strp_msg *_strp_msg(struct sk_buff *skb)
 {
 	return (struct _strp_msg *)((void *)skb->cb +
-		offsetof(struct qdisc_skb_cb, data));
+		offsetof(struct sk_skb_cb, strp));
 }
 
 /* Lower lock held */