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.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/bpf.h

@@ -484,6 +484,12 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size)
 	aux->ctx_field_size = size;
 }
 
+static inline bool bpf_pseudo_func(const struct bpf_insn *insn)
+{
+	return insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
+	       insn->src_reg == BPF_PSEUDO_FUNC;
+}
+
 struct bpf_prog_ops {
 	int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
 			union bpf_attr __user *uattr);

include/linux/skmsg.h

@@ -507,6 +507,18 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock)
 	return !!psock->saved_data_ready;
 }
 
+static inline bool sk_is_tcp(const struct sock *sk)
+{
+	return sk->sk_type == SOCK_STREAM &&
+	       sk->sk_protocol == IPPROTO_TCP;
+}
+
+static inline bool sk_is_udp(const struct sock *sk)
+{
+	return sk->sk_type == SOCK_DGRAM &&
+	       sk->sk_protocol == IPPROTO_UDP;
+}
+
 #if IS_ENABLED(CONFIG_NET_SOCK_MSG)
 
 #define BPF_F_STRPARSER	(1UL << 1)

include/net/strparser.h

@@ -54,10 +54,28 @@ struct strp_msg {
 	int offset;
 };
 
+struct _strp_msg {
+	/* Internal cb structure. struct strp_msg must be first for passing
+	 * to upper layer.
+	 */
+	struct strp_msg strp;
+	int accum_len;
+};
+
+struct sk_skb_cb {
+#define SK_SKB_CB_PRIV_LEN 20
+	unsigned char data[SK_SKB_CB_PRIV_LEN];
+	struct _strp_msg strp;
+	/* temp_reg is a temporary register used for bpf_convert_data_end_access
+	 * when dst_reg == src_reg.
+	 */
+	u64 temp_reg;
+};
+
 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));
 }
 
 /* Structure for an attached lower socket */

kernel/bpf/core.c

@@ -390,6 +390,13 @@ static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old,
 			i = end_new;
 			insn = prog->insnsi + end_old;
 		}
+		if (bpf_pseudo_func(insn)) {
+			ret = bpf_adj_delta_to_imm(insn, pos, end_old,
+						   end_new, i, probe_pass);
+			if (ret)
+				return ret;
+			continue;
+		}
 		code = insn->code;
 		if ((BPF_CLASS(code) != BPF_JMP &&
 		     BPF_CLASS(code) != BPF_JMP32) ||

kernel/bpf/verifier.c

@@ -240,12 +240,6 @@ static bool bpf_pseudo_kfunc_call(const struct bpf_insn *insn)
 	       insn->src_reg == BPF_PSEUDO_KFUNC_CALL;
 }
 
-static bool bpf_pseudo_func(const struct bpf_insn *insn)
-{
-	return insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
-	       insn->src_reg == BPF_PSEUDO_FUNC;
-}
-
 struct bpf_call_arg_meta {
 	struct bpf_map *map_ptr;
 	bool raw_mode;
@@ -1960,16 +1954,10 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
 			return -EPERM;
 		}
 
-		if (bpf_pseudo_func(insn)) {
+		if (bpf_pseudo_func(insn) || bpf_pseudo_call(insn))
 			ret = add_subprog(env, i + insn->imm + 1);
-			if (ret >= 0)
-				/* remember subprog */
-				insn[1].imm = ret;
-		} else if (bpf_pseudo_call(insn)) {
-			ret = add_subprog(env, i + insn->imm + 1);
-		} else {
+		else
 			ret = add_kfunc_call(env, insn->imm, insn->off);
-		}
 
 		if (ret < 0)
 			return ret;
@@ -9387,7 +9375,8 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 	if (insn->src_reg == BPF_PSEUDO_FUNC) {
 		struct bpf_prog_aux *aux = env->prog->aux;
-		u32 subprogno = insn[1].imm;
+		u32 subprogno = find_subprog(env,
+					     env->insn_idx + insn->imm + 1);
 
 		if (!aux->func_info) {
 			verbose(env, "missing btf func_info\n");
@@ -12557,14 +12546,9 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		return 0;
 
 	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
-		if (bpf_pseudo_func(insn)) {
-			env->insn_aux_data[i].call_imm = insn->imm;
-			/* subprog is encoded in insn[1].imm */
+		if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn))
 			continue;
-		}
 
-		if (!bpf_pseudo_call(insn))
-			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.
@@ -12585,6 +12569,12 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		env->insn_aux_data[i].call_imm = insn->imm;
 		/* point imm to __bpf_call_base+1 from JITs point of view */
 		insn->imm = 1;
+		if (bpf_pseudo_func(insn))
+			/* jit (e.g. x86_64) may emit fewer instructions
+			 * if it learns a u32 imm is the same as a u64 imm.
+			 * Force a non zero here.
+			 */
+			insn[1].imm = 1;
 	}
 
 	err = bpf_prog_alloc_jited_linfo(prog);
@@ -12669,7 +12659,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		insn = func[i]->insnsi;
 		for (j = 0; j < func[i]->len; j++, insn++) {
 			if (bpf_pseudo_func(insn)) {
-				subprog = insn[1].imm;
+				subprog = insn->off;
 				insn[0].imm = (u32)(long)func[subprog]->bpf_func;
 				insn[1].imm = ((u64)(long)func[subprog]->bpf_func) >> 32;
 				continue;
@@ -12720,7 +12710,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
 		if (bpf_pseudo_func(insn)) {
 			insn[0].imm = env->insn_aux_data[i].call_imm;
-			insn[1].imm = find_subprog(env, i + insn[0].imm + 1);
+			insn[1].imm = insn->off;
+			insn->off = 0;
 			continue;
 		}
 		if (!bpf_pseudo_call(insn))

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)

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))

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,

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 */

tools/testing/selftests/bpf/progs/for_each_array_map_elem.c

@@ -23,6 +23,16 @@ struct callback_ctx {
 	int output;
 };
 
+const volatile int bypass_unused = 1;
+
+static __u64
+unused_subprog(struct bpf_map *map, __u32 *key, __u64 *val,
+	       struct callback_ctx *data)
+{
+	data->output = 0;
+	return 1;
+}
+
 static __u64
 check_array_elem(struct bpf_map *map, __u32 *key, __u64 *val,
 		 struct callback_ctx *data)
@@ -54,6 +64,8 @@ int test_pkt_access(struct __sk_buff *skb)
 
 	data.output = 0;
 	bpf_for_each_map_elem(&arraymap, check_array_elem, &data, 0);
+	if (!bypass_unused)
+		bpf_for_each_map_elem(&arraymap, unused_subprog, &data, 0);
 	arraymap_output = data.output;
 
 	bpf_for_each_map_elem(&percpu_map, check_percpu_elem, (void *)0, 0);