Merge tag 'bpf-next-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Pull bpf updates from Alexei Starovoitov:

 - Introduce '__attribute__((bpf_fastcall))' for helpers and kfuncs with
   corresponding support in LLVM.

   It is similar to existing 'no_caller_saved_registers' attribute in
   GCC/LLVM with a provision for backward compatibility. It allows
   compilers generate more efficient BPF code assuming the verifier or
   JITs will inline or partially inline a helper/kfunc with such
   attribute. bpf_cast_to_kern_ctx, bpf_rdonly_cast,
   bpf_get_smp_processor_id are the first set of such helpers.

 - Harden and extend ELF build ID parsing logic.

   When called from sleepable context the relevants parts of ELF file
   will be read to find and fetch .note.gnu.build-id information. Also
   harden the logic to avoid TOCTOU, overflow, out-of-bounds problems.

 - Improvements and fixes for sched-ext:
    - Allow passing BPF iterators as kfunc arguments
    - Make the pointer returned from iter_next method trusted
    - Fix x86 JIT convergence issue due to growing/shrinking conditional
      jumps in variable length encoding

 - BPF_LSM related:
    - Introduce few VFS kfuncs and consolidate them in
      fs/bpf_fs_kfuncs.c
    - Enforce correct range of return values from certain LSM hooks
    - Disallow attaching to other LSM hooks

 - Prerequisite work for upcoming Qdisc in BPF:
    - Allow kptrs in program provided structs
    - Support for gen_epilogue in verifier_ops

 - Important fixes:
    - Fix uprobe multi pid filter check
    - Fix bpf_strtol and bpf_strtoul helpers
    - Track equal scalars history on per-instruction level
    - Fix tailcall hierarchy on x86 and arm64
    - Fix signed division overflow to prevent INT_MIN/-1 trap on x86
    - Fix get kernel stack in BPF progs attached to tracepoint:syscall

 - Selftests:
    - Add uprobe bench/stress tool
    - Generate file dependencies to drastically improve re-build time
    - Match JIT-ed and BPF asm with __xlated/__jited keywords
    - Convert older tests to test_progs framework
    - Add support for RISC-V
    - Few fixes when BPF programs are compiled with GCC-BPF backend
      (support for GCC-BPF in BPF CI is ongoing in parallel)
    - Add traffic monitor
    - Enable cross compile and musl libc

* tag 'bpf-next-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (260 commits)
  btf: require pahole 1.21+ for DEBUG_INFO_BTF with default DWARF version
  btf: move pahole check in scripts/link-vmlinux.sh to lib/Kconfig.debug
  btf: remove redundant CONFIG_BPF test in scripts/link-vmlinux.sh
  bpf: Call the missed kfree() when there is no special field in btf
  bpf: Call the missed btf_record_free() when map creation fails
  selftests/bpf: Add a test case to write mtu result into .rodata
  selftests/bpf: Add a test case to write strtol result into .rodata
  selftests/bpf: Rename ARG_PTR_TO_LONG test description
  selftests/bpf: Fix ARG_PTR_TO_LONG {half-,}uninitialized test
  bpf: Zero former ARG_PTR_TO_{LONG,INT} args in case of error
  bpf: Improve check_raw_mode_ok test for MEM_UNINIT-tagged types
  bpf: Fix helper writes to read-only maps
  bpf: Remove truncation test in bpf_strtol and bpf_strtoul helpers
  bpf: Fix bpf_strtol and bpf_strtoul helpers for 32bit
  selftests/bpf: Add tests for sdiv/smod overflow cases
  bpf: Fix a sdiv overflow issue
  libbpf: Add bpf_object__token_fd accessor
  docs/bpf: Add missing BPF program types to docs
  docs/bpf: Add constant values for linkages
  bpf: Use fake pt_regs when doing bpf syscall tracepoint tracing
  ...

4 files changed, 58 insertions, 68 deletions

diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index 3ea52b05adfb..f71f67c6896b 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -115,7 +115,7 @@ static int check_test_run_args(struct bpf_prog *prog, struct bpf_dummy_ops_test_
 
 		offset = btf_ctx_arg_offset(bpf_dummy_ops_btf, func_proto, arg_no);
 		info = find_ctx_arg_info(prog->aux, offset);
-		if (info && (info->reg_type & PTR_MAYBE_NULL))
+		if (info && type_may_be_null(info->reg_type))
 			continue;
 
 		return -EINVAL;
diff --git a/net/core/filter.c b/net/core/filter.c
index 0f4d9f3b206e..cd3524cb326b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1266,8 +1266,8 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
 	 * so we need to keep the user BPF around until the 2nd
 	 * pass. At this time, the user BPF is stored in fp->insns.
 	 */
-	old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter),
-			   GFP_KERNEL | __GFP_NOWARN);
+	old_prog = kmemdup_array(fp->insns, old_len, sizeof(struct sock_filter),
+				 GFP_KERNEL | __GFP_NOWARN);
 	if (!old_prog) {
 		err = -ENOMEM;
 		goto out_err;
@@ -6280,20 +6280,25 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
 	int ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
 	struct net_device *dev = skb->dev;
 	int skb_len, dev_len;
-	int mtu;
+	int mtu = 0;
 
-	if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
-		return -EINVAL;
+	if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) {
+		ret = -EINVAL;
+		goto out;
+	}
 
-	if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len)))
-		return -EINVAL;
+	if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	dev = __dev_via_ifindex(dev, ifindex);
-	if (unlikely(!dev))
-		return -ENODEV;
+	if (unlikely(!dev)) {
+		ret = -ENODEV;
+		goto out;
+	}
 
 	mtu = READ_ONCE(dev->mtu);
-
 	dev_len = mtu + dev->hard_header_len;
 
 	/* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
@@ -6311,15 +6316,12 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
 	 */
 	if (skb_is_gso(skb)) {
 		ret = BPF_MTU_CHK_RET_SUCCESS;
-
 		if (flags & BPF_MTU_CHK_SEGS &&
 		    !skb_gso_validate_network_len(skb, mtu))
 			ret = BPF_MTU_CHK_RET_SEGS_TOOBIG;
 	}
 out:
-	/* BPF verifier guarantees valid pointer */
 	*mtu_len = mtu;
-
 	return ret;
 }
 
@@ -6329,19 +6331,21 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
 	struct net_device *dev = xdp->rxq->dev;
 	int xdp_len = xdp->data_end - xdp->data;
 	int ret = BPF_MTU_CHK_RET_SUCCESS;
-	int mtu, dev_len;
+	int mtu = 0, dev_len;
 
 	/* XDP variant doesn't support multi-buffer segment check (yet) */
-	if (unlikely(flags))
-		return -EINVAL;
+	if (unlikely(flags)) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	dev = __dev_via_ifindex(dev, ifindex);
-	if (unlikely(!dev))
-		return -ENODEV;
+	if (unlikely(!dev)) {
+		ret = -ENODEV;
+		goto out;
+	}
 
 	mtu = READ_ONCE(dev->mtu);
-
-	/* Add L2-header as dev MTU is L3 size */
 	dev_len = mtu + dev->hard_header_len;
 
 	/* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
@@ -6351,10 +6355,8 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
 	xdp_len += len_diff; /* minus result pass check */
 	if (xdp_len > dev_len)
 		ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
-
-	/* BPF verifier guarantees valid pointer */
+out:
 	*mtu_len = mtu;
-
 	return ret;
 }
 
@@ -6364,7 +6366,8 @@ static const struct bpf_func_proto bpf_skb_check_mtu_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type      = ARG_PTR_TO_CTX,
 	.arg2_type      = ARG_ANYTHING,
-	.arg3_type      = ARG_PTR_TO_INT,
+	.arg3_type      = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+	.arg3_size	= sizeof(u32),
 	.arg4_type      = ARG_ANYTHING,
 	.arg5_type      = ARG_ANYTHING,
 };
@@ -6375,7 +6378,8 @@ static const struct bpf_func_proto bpf_xdp_check_mtu_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type      = ARG_PTR_TO_CTX,
 	.arg2_type      = ARG_ANYTHING,
-	.arg3_type      = ARG_PTR_TO_INT,
+	.arg3_type      = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+	.arg3_size	= sizeof(u32),
 	.arg4_type      = ARG_ANYTHING,
 	.arg5_type      = ARG_ANYTHING,
 };
@@ -8597,13 +8601,16 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
 		if (off + size > offsetofend(struct __sk_buff, cb[4]))
 			return false;
 		break;
+	case bpf_ctx_range(struct __sk_buff, data):
+	case bpf_ctx_range(struct __sk_buff, data_meta):
+	case bpf_ctx_range(struct __sk_buff, data_end):
+		if (info->is_ldsx || size != size_default)
+			return false;
+		break;
 	case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]):
 	case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]):
 	case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4):
 	case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4):
-	case bpf_ctx_range(struct __sk_buff, data):
-	case bpf_ctx_range(struct __sk_buff, data_meta):
-	case bpf_ctx_range(struct __sk_buff, data_end):
 		if (size != size_default)
 			return false;
 		break;
@@ -9047,6 +9054,14 @@ static bool xdp_is_valid_access(int off, int size,
 			}
 		}
 		return false;
+	} else {
+		switch (off) {
+		case offsetof(struct xdp_md, data_meta):
+		case offsetof(struct xdp_md, data):
+		case offsetof(struct xdp_md, data_end):
+			if (info->is_ldsx)
+				return false;
+		}
 	}
 
 	switch (off) {
@@ -9372,12 +9387,12 @@ static bool flow_dissector_is_valid_access(int off, int size,
 
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, data):
-		if (size != size_default)
+		if (info->is_ldsx || size != size_default)
 			return false;
 		info->reg_type = PTR_TO_PACKET;
 		return true;
 	case bpf_ctx_range(struct __sk_buff, data_end):
-		if (size != size_default)
+		if (info->is_ldsx || size != size_default)
 			return false;
 		info->reg_type = PTR_TO_PACKET_END;
 		return true;
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 3f88d0961e5b..554804774628 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -14,10 +14,6 @@
 /* "extern" is to avoid sparse warning.  It is only used in bpf_struct_ops.c. */
 static struct bpf_struct_ops bpf_tcp_congestion_ops;
 
-static u32 unsupported_ops[] = {
-	offsetof(struct tcp_congestion_ops, get_info),
-};
-
 static const struct btf_type *tcp_sock_type;
 static u32 tcp_sock_id, sock_id;
 static const struct btf_type *tcp_congestion_ops_type;
@@ -45,18 +41,6 @@ static int bpf_tcp_ca_init(struct btf *btf)
 	return 0;
 }
 
-static bool is_unsupported(u32 member_offset)
-{
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(unsupported_ops); i++) {
-		if (member_offset == unsupported_ops[i])
-			return true;
-	}
-
-	return false;
-}
-
 static bool bpf_tcp_ca_is_valid_access(int off, int size,
 				       enum bpf_access_type type,
 				       const struct bpf_prog *prog,
@@ -251,15 +235,6 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t,
 	return 0;
 }
 
-static int bpf_tcp_ca_check_member(const struct btf_type *t,
-				   const struct btf_member *member,
-				   const struct bpf_prog *prog)
-{
-	if (is_unsupported(__btf_member_bit_offset(t, member) / 8))
-		return -ENOTSUPP;
-	return 0;
-}
-
 static int bpf_tcp_ca_reg(void *kdata, struct bpf_link *link)
 {
 	return tcp_register_congestion_control(kdata);
@@ -354,7 +329,6 @@ static struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.reg = bpf_tcp_ca_reg,
 	.unreg = bpf_tcp_ca_unreg,
 	.update = bpf_tcp_ca_update,
-	.check_member = bpf_tcp_ca_check_member,
 	.init_member = bpf_tcp_ca_init_member,
 	.init = bpf_tcp_ca_init,
 	.validate = bpf_tcp_ca_validate,
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 7e16336044b2..1140b2a120ca 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -1320,14 +1320,6 @@ struct xdp_umem_reg_v1 {
 	__u32 headroom;
 };
 
-struct xdp_umem_reg_v2 {
-	__u64 addr; /* Start of packet data area */
-	__u64 len; /* Length of packet data area */
-	__u32 chunk_size;
-	__u32 headroom;
-	__u32 flags;
-};
-
 static int xsk_setsockopt(struct socket *sock, int level, int optname,
 			  sockptr_t optval, unsigned int optlen)
 {
@@ -1371,10 +1363,19 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 
 		if (optlen < sizeof(struct xdp_umem_reg_v1))
 			return -EINVAL;
-		else if (optlen < sizeof(struct xdp_umem_reg_v2))
-			mr_size = sizeof(struct xdp_umem_reg_v1);
 		else if (optlen < sizeof(mr))
-			mr_size = sizeof(struct xdp_umem_reg_v2);
+			mr_size = sizeof(struct xdp_umem_reg_v1);
+
+		BUILD_BUG_ON(sizeof(struct xdp_umem_reg_v1) >= sizeof(struct xdp_umem_reg));
+
+		/* Make sure the last field of the struct doesn't have
+		 * uninitialized padding. All padding has to be explicit
+		 * and has to be set to zero by the userspace to make
+		 * struct xdp_umem_reg extensible in the future.
+		 */
+		BUILD_BUG_ON(offsetof(struct xdp_umem_reg, tx_metadata_len) +
+			     sizeof_field(struct xdp_umem_reg, tx_metadata_len) !=
+			     sizeof(struct xdp_umem_reg));
 
 		if (copy_from_sockptr(&mr, optval, mr_size))
 			return -EFAULT;