Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
bpf-next 2023-01-28

We've added 124 non-merge commits during the last 22 day(s) which contain
a total of 124 files changed, 6386 insertions(+), 1827 deletions(-).

The main changes are:

1) Implement XDP hints via kfuncs with initial support for RX hash and
   timestamp metadata kfuncs, from Stanislav Fomichev and
   Toke Høiland-Jørgensen.
   Measurements on overhead: https://lore.kernel.org/bpf/875yellcx6.fsf@toke.dk

2) Extend libbpf's bpf_tracing.h support for tracing arguments of
   kprobes/uprobes and syscall as a special case, from Andrii Nakryiko.

3) Significantly reduce the search time for module symbols by livepatch
   and BPF, from Jiri Olsa and Zhen Lei.

4) Enable cpumasks to be used as kptrs, which is useful for tracing
   programs tracking which tasks end up running on which CPUs
   in different time intervals, from David Vernet.

5) Fix several issues in the dynptr processing such as stack slot liveness
   propagation, missing checks for PTR_TO_STACK variable offset, etc,
   from Kumar Kartikeya Dwivedi.

6) Various performance improvements, fixes, and introduction of more
   than just one XDP program to XSK selftests, from Magnus Karlsson.

7) Big batch to BPF samples to reduce deprecated functionality,
   from Daniel T. Lee.

8) Enable struct_ops programs to be sleepable in verifier,
   from David Vernet.

9) Reduce pr_warn() noise on BTF mismatches when they are expected under
   the CONFIG_MODULE_ALLOW_BTF_MISMATCH config anyway, from Connor O'Brien.

10) Describe modulo and division by zero behavior of the BPF runtime
    in BPF's instruction specification document, from Dave Thaler.

11) Several improvements to libbpf API documentation in libbpf.h,
    from Grant Seltzer.

12) Improve resolve_btfids header dependencies related to subcmd and add
    proper support for HOSTCC, from Ian Rogers.

13) Add ipip6 and ip6ip decapsulation support for bpf_skb_adjust_room()
    helper along with BPF selftests, from Ziyang Xuan.

14) Simplify the parsing logic of structure parameters for BPF trampoline
    in the x86-64 JIT compiler, from Pu Lehui.

15) Get BTF working for kernels with CONFIG_RUST enabled by excluding
    Rust compilation units with pahole, from Martin Rodriguez Reboredo.

16) Get bpf_setsockopt() working for kTLS on top of TCP sockets,
    from Kui-Feng Lee.

17) Disable stack protection for BPF objects in bpftool given BPF backends
    don't support it, from Holger Hoffstätte.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (124 commits)
  selftest/bpf: Make crashes more debuggable in test_progs
  libbpf: Add documentation to map pinning API functions
  libbpf: Fix malformed documentation formatting
  selftests/bpf: Properly enable hwtstamp in xdp_hw_metadata
  selftests/bpf: Calls bpf_setsockopt() on a ktls enabled socket.
  bpf: Check the protocol of a sock to agree the calls to bpf_setsockopt().
  bpf/selftests: Verify struct_ops prog sleepable behavior
  bpf: Pass const struct bpf_prog * to .check_member
  libbpf: Support sleepable struct_ops.s section
  bpf: Allow BPF_PROG_TYPE_STRUCT_OPS programs to be sleepable
  selftests/bpf: Fix vmtest static compilation error
  tools/resolve_btfids: Alter how HOSTCC is forced
  tools/resolve_btfids: Install subcmd headers
  bpf/docs: Document the nocast aliasing behavior of ___init
  bpf/docs: Document how nested trusted fields may be defined
  bpf/docs: Document cpumask kfuncs in a new file
  selftests/bpf: Add selftest suite for cpumask kfuncs
  selftests/bpf: Add nested trust selftests suite
  bpf: Enable cpumasks to be queried and used as kptrs
  bpf: Disallow NULLable pointers for trusted kfuncs
  ...
====================

Link: https://lore.kernel.org/r/20230128004827.21371-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 126 insertions, 12 deletions

diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index 1ac4467928a9..ff4f89a2b02a 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -154,6 +154,23 @@ static bool bpf_dummy_ops_is_valid_access(int off, int size,
 	return bpf_tracing_btf_ctx_access(off, size, type, prog, info);
 }
 
+static int bpf_dummy_ops_check_member(const struct btf_type *t,
+				      const struct btf_member *member,
+				      const struct bpf_prog *prog)
+{
+	u32 moff = __btf_member_bit_offset(t, member) / 8;
+
+	switch (moff) {
+	case offsetof(struct bpf_dummy_ops, test_sleepable):
+		break;
+	default:
+		if (prog->aux->sleepable)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int bpf_dummy_ops_btf_struct_access(struct bpf_verifier_log *log,
 					   const struct bpf_reg_state *reg,
 					   int off, int size, enum bpf_access_type atype,
@@ -208,6 +225,7 @@ static void bpf_dummy_unreg(void *kdata)
 struct bpf_struct_ops bpf_bpf_dummy_ops = {
 	.verifier_ops = &bpf_dummy_verifier_ops,
 	.init = bpf_dummy_init,
+	.check_member = bpf_dummy_ops_check_member,
 	.init_member = bpf_dummy_init_member,
 	.reg = bpf_dummy_reg,
 	.unreg = bpf_dummy_unreg,
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 2723623429ac..8da0d73b368e 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -1300,6 +1300,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	if (kattr->test.flags & ~BPF_F_TEST_XDP_LIVE_FRAMES)
 		return -EINVAL;
 
+	if (bpf_prog_is_dev_bound(prog->aux))
+		return -EINVAL;
+
 	if (do_live) {
 		if (!batch_size)
 			batch_size = NAPI_POLL_WEIGHT;
diff --git a/net/core/dev.c b/net/core/dev.c
index 9c60190fe352..f72f5c4ee7e2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9223,8 +9223,12 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 			NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time");
 			return -EEXIST;
 		}
-		if (!offload && bpf_prog_is_dev_bound(new_prog->aux)) {
-			NL_SET_ERR_MSG(extack, "Using device-bound program without HW_MODE flag is not supported");
+		if (!offload && bpf_prog_is_offloaded(new_prog->aux)) {
+			NL_SET_ERR_MSG(extack, "Using offloaded program without HW_MODE flag is not supported");
+			return -EINVAL;
+		}
+		if (bpf_prog_is_dev_bound(new_prog->aux) && !bpf_offload_dev_match(new_prog, dev)) {
+			NL_SET_ERR_MSG(extack, "Program bound to different device");
 			return -EINVAL;
 		}
 		if (new_prog->expected_attach_type == BPF_XDP_DEVMAP) {
@@ -10829,6 +10833,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		dev_shutdown(dev);
 
 		dev_xdp_uninstall(dev);
+		bpf_dev_bound_netdev_unregister(dev);
 
 		netdev_offload_xstats_disable_all(dev);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 7a2b67893afd..d8f9b53f3db6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3381,13 +3381,17 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
 #define BPF_F_ADJ_ROOM_ENCAP_L3_MASK	(BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 | \
 					 BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
 
+#define BPF_F_ADJ_ROOM_DECAP_L3_MASK	(BPF_F_ADJ_ROOM_DECAP_L3_IPV4 | \
+					 BPF_F_ADJ_ROOM_DECAP_L3_IPV6)
+
 #define BPF_F_ADJ_ROOM_MASK		(BPF_F_ADJ_ROOM_FIXED_GSO | \
 					 BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \
 					 BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \
 					 BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \
 					 BPF_F_ADJ_ROOM_ENCAP_L2_ETH | \
 					 BPF_F_ADJ_ROOM_ENCAP_L2( \
-					  BPF_ADJ_ROOM_ENCAP_L2_MASK))
+					  BPF_ADJ_ROOM_ENCAP_L2_MASK) | \
+					 BPF_F_ADJ_ROOM_DECAP_L3_MASK)
 
 static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			    u64 flags)
@@ -3501,6 +3505,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
 	int ret;
 
 	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO |
+			       BPF_F_ADJ_ROOM_DECAP_L3_MASK |
 			       BPF_F_ADJ_ROOM_NO_CSUM_RESET)))
 		return -EINVAL;
 
@@ -3519,6 +3524,14 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
 	if (unlikely(ret < 0))
 		return ret;
 
+	/* Match skb->protocol to new outer l3 protocol */
+	if (skb->protocol == htons(ETH_P_IP) &&
+	    flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6)
+		skb->protocol = htons(ETH_P_IPV6);
+	else if (skb->protocol == htons(ETH_P_IPV6) &&
+		 flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4)
+		skb->protocol = htons(ETH_P_IP);
+
 	if (skb_is_gso(skb)) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
@@ -3608,6 +3621,22 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 		return -ENOTSUPP;
 	}
 
+	if (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) {
+		if (!shrink)
+			return -EINVAL;
+
+		switch (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) {
+		case BPF_F_ADJ_ROOM_DECAP_L3_IPV4:
+			len_min = sizeof(struct iphdr);
+			break;
+		case BPF_F_ADJ_ROOM_DECAP_L3_IPV6:
+			len_min = sizeof(struct ipv6hdr);
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
 	len_cur = skb->len - skb_network_offset(skb);
 	if ((shrink && (len_diff_abs >= len_cur ||
 			len_cur - len_diff_abs < len_min)) ||
@@ -5179,7 +5208,7 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
 			   char *optval, int *optlen,
 			   bool getopt)
 {
-	if (sk->sk_prot->setsockopt != tcp_setsockopt)
+	if (sk->sk_protocol != IPPROTO_TCP)
 		return -EINVAL;
 
 	switch (optname) {
@@ -6851,9 +6880,6 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
 					FIELD));			\
 	} while (0)
 
-	if (insn > insn_buf)
-		return insn - insn_buf;
-
 	switch (si->off) {
 	case offsetof(struct bpf_tcp_sock, rtt_min):
 		BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) !=
@@ -8738,7 +8764,7 @@ static bool xdp_is_valid_access(int off, int size,
 	}
 
 	if (type == BPF_WRITE) {
-		if (bpf_prog_is_dev_bound(prog->aux)) {
+		if (bpf_prog_is_offloaded(prog->aux)) {
 			switch (off) {
 			case offsetof(struct xdp_md, rx_queue_index):
 				return __is_valid_xdp_access(off, size);
@@ -10151,9 +10177,6 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 			SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ);	      \
 	} while (0)
 
-	if (insn > insn_buf)
-		return insn - insn_buf;
-
 	switch (si->off) {
 	case offsetof(struct bpf_sock_ops, op):
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 844c9d99dc0e..a5a7ecf6391c 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -4,6 +4,7 @@
  * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
  */
 #include <linux/bpf.h>
+#include <linux/btf_ids.h>
 #include <linux/filter.h>
 #include <linux/types.h>
 #include <linux/mm.h>
@@ -709,3 +710,66 @@ struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf)
 
 	return nxdpf;
 }
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "Global functions as their definitions will be in vmlinux BTF");
+
+/**
+ * bpf_xdp_metadata_rx_timestamp - Read XDP frame RX timestamp.
+ * @ctx: XDP context pointer.
+ * @timestamp: Return value pointer.
+ *
+ * Returns 0 on success or ``-errno`` on error.
+ */
+int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * bpf_xdp_metadata_rx_hash - Read XDP frame RX hash.
+ * @ctx: XDP context pointer.
+ * @hash: Return value pointer.
+ *
+ * Returns 0 on success or ``-errno`` on error.
+ */
+int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash)
+{
+	return -EOPNOTSUPP;
+}
+
+__diag_pop();
+
+BTF_SET8_START(xdp_metadata_kfunc_ids)
+#define XDP_METADATA_KFUNC(_, name) BTF_ID_FLAGS(func, name, 0)
+XDP_METADATA_KFUNC_xxx
+#undef XDP_METADATA_KFUNC
+BTF_SET8_END(xdp_metadata_kfunc_ids)
+
+static const struct btf_kfunc_id_set xdp_metadata_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &xdp_metadata_kfunc_ids,
+};
+
+BTF_ID_LIST(xdp_metadata_kfunc_ids_unsorted)
+#define XDP_METADATA_KFUNC(name, str) BTF_ID(func, str)
+XDP_METADATA_KFUNC_xxx
+#undef XDP_METADATA_KFUNC
+
+u32 bpf_xdp_metadata_kfunc_id(int id)
+{
+	/* xdp_metadata_kfunc_ids is sorted and can't be used */
+	return xdp_metadata_kfunc_ids_unsorted[id];
+}
+
+bool bpf_dev_bound_kfunc_id(u32 btf_id)
+{
+	return btf_id_set8_contains(&xdp_metadata_kfunc_ids, btf_id);
+}
+
+static int __init xdp_metadata_init(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &xdp_metadata_kfunc_set);
+}
+late_initcall(xdp_metadata_init);
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 4517d2bd186a..13fc0c185cd9 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -248,7 +248,8 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t,
 }
 
 static int bpf_tcp_ca_check_member(const struct btf_type *t,
-				   const struct btf_member *member)
+				   const struct btf_member *member,
+				   const struct bpf_prog *prog)
 {
 	if (is_unsupported(__btf_member_bit_offset(t, member) / 8))
 		return -ENOTSUPP;