Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

1 files changed, 195 insertions, 46 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ea04b0deb5ce..e343f158e556 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -73,11 +73,10 @@ static const struct bpf_map_ops * const bpf_map_types[] = {
  * copy_from_user() call. However, this is not a concern since this function is
  * meant to be a future-proofing of bits.
  */
-int bpf_check_uarg_tail_zero(void __user *uaddr,
+int bpf_check_uarg_tail_zero(bpfptr_t uaddr,
 			     size_t expected_size,
 			     size_t actual_size)
 {
-	unsigned char __user *addr = uaddr + expected_size;
 	int res;
 
 	if (unlikely(actual_size > PAGE_SIZE))	/* silly large */
@@ -86,7 +85,12 @@ int bpf_check_uarg_tail_zero(void __user *uaddr,
 	if (actual_size <= expected_size)
 		return 0;
 
-	res = check_zeroed_user(addr, actual_size - expected_size);
+	if (uaddr.is_kernel)
+		res = memchr_inv(uaddr.kernel + expected_size, 0,
+				 actual_size - expected_size) == NULL;
+	else
+		res = check_zeroed_user(uaddr.user + expected_size,
+					actual_size - expected_size);
 	if (res < 0)
 		return res;
 	return res ? 0 : -E2BIG;
@@ -1005,6 +1009,17 @@ static void *__bpf_copy_key(void __user *ukey, u64 key_size)
 	return NULL;
 }
 
+static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size)
+{
+	if (key_size)
+		return memdup_bpfptr(ukey, key_size);
+
+	if (!bpfptr_is_null(ukey))
+		return ERR_PTR(-EINVAL);
+
+	return NULL;
+}
+
 /* last field in 'union bpf_attr' used by this command */
 #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags
 
@@ -1075,10 +1090,10 @@ err_put:
 
 #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
 
-static int map_update_elem(union bpf_attr *attr)
+static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
 {
-	void __user *ukey = u64_to_user_ptr(attr->key);
-	void __user *uvalue = u64_to_user_ptr(attr->value);
+	bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel);
+	bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel);
 	int ufd = attr->map_fd;
 	struct bpf_map *map;
 	void *key, *value;
@@ -1104,7 +1119,7 @@ static int map_update_elem(union bpf_attr *attr)
 		goto err_put;
 	}
 
-	key = __bpf_copy_key(ukey, map->key_size);
+	key = ___bpf_copy_key(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
 		goto err_put;
@@ -1124,7 +1139,7 @@ static int map_update_elem(union bpf_attr *attr)
 		goto free_key;
 
 	err = -EFAULT;
-	if (copy_from_user(value, uvalue, value_size) != 0)
+	if (copy_from_bpfptr(value, uvalue, value_size) != 0)
 		goto free_value;
 
 	err = bpf_map_update_value(map, f, key, value, attr->flags);
@@ -1469,7 +1484,7 @@ free_buf:
 	return err;
 }
 
-#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value
+#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags
 
 static int map_lookup_and_delete_elem(union bpf_attr *attr)
 {
@@ -1485,6 +1500,9 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM))
 		return -EINVAL;
 
+	if (attr->flags & ~BPF_F_LOCK)
+		return -EINVAL;
+
 	f = fdget(ufd);
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
@@ -1495,24 +1513,47 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 		goto err_put;
 	}
 
+	if (attr->flags &&
+	    (map->map_type == BPF_MAP_TYPE_QUEUE ||
+	     map->map_type == BPF_MAP_TYPE_STACK)) {
+		err = -EINVAL;
+		goto err_put;
+	}
+
+	if ((attr->flags & BPF_F_LOCK) &&
+	    !map_value_has_spin_lock(map)) {
+		err = -EINVAL;
+		goto err_put;
+	}
+
 	key = __bpf_copy_key(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
 		goto err_put;
 	}
 
-	value_size = map->value_size;
+	value_size = bpf_map_value_size(map);
 
 	err = -ENOMEM;
 	value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
 	if (!value)
 		goto free_key;
 
+	err = -ENOTSUPP;
 	if (map->map_type == BPF_MAP_TYPE_QUEUE ||
 	    map->map_type == BPF_MAP_TYPE_STACK) {
 		err = map->ops->map_pop_elem(map, value);
-	} else {
-		err = -ENOTSUPP;
+	} else if (map->map_type == BPF_MAP_TYPE_HASH ||
+		   map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+		   map->map_type == BPF_MAP_TYPE_LRU_HASH ||
+		   map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+		if (!bpf_map_is_dev_bound(map)) {
+			bpf_disable_instrumentation();
+			rcu_read_lock();
+			err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags);
+			rcu_read_unlock();
+			bpf_enable_instrumentation();
+		}
 	}
 
 	if (err)
@@ -1932,6 +1973,11 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr)
 			attr->expected_attach_type =
 				BPF_CGROUP_INET_SOCK_CREATE;
 		break;
+	case BPF_PROG_TYPE_SK_REUSEPORT:
+		if (!attr->expected_attach_type)
+			attr->expected_attach_type =
+				BPF_SK_REUSEPORT_SELECT;
+		break;
 	}
 }
 
@@ -2015,6 +2061,15 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 		if (expected_attach_type == BPF_SK_LOOKUP)
 			return 0;
 		return -EINVAL;
+	case BPF_PROG_TYPE_SK_REUSEPORT:
+		switch (expected_attach_type) {
+		case BPF_SK_REUSEPORT_SELECT:
+		case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE:
+			return 0;
+		default:
+			return -EINVAL;
+		}
+	case BPF_PROG_TYPE_SYSCALL:
 	case BPF_PROG_TYPE_EXT:
 		if (expected_attach_type)
 			return -EINVAL;
@@ -2074,9 +2129,9 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD attach_prog_fd
+#define	BPF_PROG_LOAD_LAST_FIELD fd_array
 
-static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
+static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 {
 	enum bpf_prog_type type = attr->prog_type;
 	struct bpf_prog *prog, *dst_prog = NULL;
@@ -2101,8 +2156,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 		return -EPERM;
 
 	/* copy eBPF program license from user space */
-	if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
-			      sizeof(license) - 1) < 0)
+	if (strncpy_from_bpfptr(license,
+				make_bpfptr(attr->license, uattr.is_kernel),
+				sizeof(license) - 1) < 0)
 		return -EFAULT;
 	license[sizeof(license) - 1] = 0;
 
@@ -2186,8 +2242,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	prog->len = attr->insn_cnt;
 
 	err = -EFAULT;
-	if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns),
-			   bpf_prog_insn_size(prog)) != 0)
+	if (copy_from_bpfptr(prog->insns,
+			     make_bpfptr(attr->insns, uattr.is_kernel),
+			     bpf_prog_insn_size(prog)) != 0)
 		goto free_prog_sec;
 
 	prog->orig_prog = NULL;
@@ -3423,7 +3480,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 	u32 ulen;
 	int err;
 
-	err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+	err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len);
 	if (err)
 		return err;
 	info_len = min_t(u32, sizeof(info), info_len);
@@ -3702,7 +3759,7 @@ static int bpf_map_get_info_by_fd(struct file *file,
 	u32 info_len = attr->info.info_len;
 	int err;
 
-	err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+	err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len);
 	if (err)
 		return err;
 	info_len = min_t(u32, sizeof(info), info_len);
@@ -3745,7 +3802,7 @@ static int bpf_btf_get_info_by_fd(struct file *file,
 	u32 info_len = attr->info.info_len;
 	int err;
 
-	err = bpf_check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len);
+	err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len);
 	if (err)
 		return err;
 
@@ -3762,7 +3819,7 @@ static int bpf_link_get_info_by_fd(struct file *file,
 	u32 info_len = attr->info.info_len;
 	int err;
 
-	err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+	err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len);
 	if (err)
 		return err;
 	info_len = min_t(u32, sizeof(info), info_len);
@@ -3825,7 +3882,7 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 
 #define BPF_BTF_LOAD_LAST_FIELD btf_log_level
 
-static int bpf_btf_load(const union bpf_attr *attr)
+static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr)
 {
 	if (CHECK_ATTR(BPF_BTF_LOAD))
 		return -EINVAL;
@@ -3833,7 +3890,7 @@ static int bpf_btf_load(const union bpf_attr *attr)
 	if (!bpf_capable())
 		return -EPERM;
 
-	return btf_new_fd(attr);
+	return btf_new_fd(attr, uattr);
 }
 
 #define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id
@@ -4023,13 +4080,14 @@ err_put:
 	return err;
 }
 
-static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+static int tracing_bpf_link_attach(const union bpf_attr *attr, bpfptr_t uattr,
+				   struct bpf_prog *prog)
 {
 	if (attr->link_create.attach_type != prog->expected_attach_type)
 		return -EINVAL;
 
 	if (prog->expected_attach_type == BPF_TRACE_ITER)
-		return bpf_iter_link_attach(attr, prog);
+		return bpf_iter_link_attach(attr, uattr, prog);
 	else if (prog->type == BPF_PROG_TYPE_EXT)
 		return bpf_tracing_prog_attach(prog,
 					       attr->link_create.target_fd,
@@ -4038,7 +4096,7 @@ static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *
 }
 
 #define BPF_LINK_CREATE_LAST_FIELD link_create.iter_info_len
-static int link_create(union bpf_attr *attr)
+static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 {
 	enum bpf_prog_type ptype;
 	struct bpf_prog *prog;
@@ -4057,7 +4115,7 @@ static int link_create(union bpf_attr *attr)
 		goto out;
 
 	if (prog->type == BPF_PROG_TYPE_EXT) {
-		ret = tracing_bpf_link_attach(attr, prog);
+		ret = tracing_bpf_link_attach(attr, uattr, prog);
 		goto out;
 	}
 
@@ -4078,7 +4136,7 @@ static int link_create(union bpf_attr *attr)
 		ret = cgroup_bpf_link_attach(attr, prog);
 		break;
 	case BPF_PROG_TYPE_TRACING:
-		ret = tracing_bpf_link_attach(attr, prog);
+		ret = tracing_bpf_link_attach(attr, uattr, prog);
 		break;
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_SK_LOOKUP:
@@ -4366,7 +4424,7 @@ out_prog_put:
 	return ret;
 }
 
-SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
+static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
 {
 	union bpf_attr attr;
 	int err;
@@ -4381,7 +4439,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 
 	/* copy attributes from user space, may be less than sizeof(bpf_attr) */
 	memset(&attr, 0, sizeof(attr));
-	if (copy_from_user(&attr, uattr, size) != 0)
+	if (copy_from_bpfptr(&attr, uattr, size) != 0)
 		return -EFAULT;
 
 	err = security_bpf(cmd, &attr, size);
@@ -4396,7 +4454,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 		err = map_lookup_elem(&attr);
 		break;
 	case BPF_MAP_UPDATE_ELEM:
-		err = map_update_elem(&attr);
+		err = map_update_elem(&attr, uattr);
 		break;
 	case BPF_MAP_DELETE_ELEM:
 		err = map_delete_elem(&attr);
@@ -4423,21 +4481,21 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 		err = bpf_prog_detach(&attr);
 		break;
 	case BPF_PROG_QUERY:
-		err = bpf_prog_query(&attr, uattr);
+		err = bpf_prog_query(&attr, uattr.user);
 		break;
 	case BPF_PROG_TEST_RUN:
-		err = bpf_prog_test_run(&attr, uattr);
+		err = bpf_prog_test_run(&attr, uattr.user);
 		break;
 	case BPF_PROG_GET_NEXT_ID:
-		err = bpf_obj_get_next_id(&attr, uattr,
+		err = bpf_obj_get_next_id(&attr, uattr.user,
 					  &prog_idr, &prog_idr_lock);
 		break;
 	case BPF_MAP_GET_NEXT_ID:
-		err = bpf_obj_get_next_id(&attr, uattr,
+		err = bpf_obj_get_next_id(&attr, uattr.user,
 					  &map_idr, &map_idr_lock);
 		break;
 	case BPF_BTF_GET_NEXT_ID:
-		err = bpf_obj_get_next_id(&attr, uattr,
+		err = bpf_obj_get_next_id(&attr, uattr.user,
 					  &btf_idr, &btf_idr_lock);
 		break;
 	case BPF_PROG_GET_FD_BY_ID:
@@ -4447,38 +4505,38 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 		err = bpf_map_get_fd_by_id(&attr);
 		break;
 	case BPF_OBJ_GET_INFO_BY_FD:
-		err = bpf_obj_get_info_by_fd(&attr, uattr);
+		err = bpf_obj_get_info_by_fd(&attr, uattr.user);
 		break;
 	case BPF_RAW_TRACEPOINT_OPEN:
 		err = bpf_raw_tracepoint_open(&attr);
 		break;
 	case BPF_BTF_LOAD:
-		err = bpf_btf_load(&attr);
+		err = bpf_btf_load(&attr, uattr);
 		break;
 	case BPF_BTF_GET_FD_BY_ID:
 		err = bpf_btf_get_fd_by_id(&attr);
 		break;
 	case BPF_TASK_FD_QUERY:
-		err = bpf_task_fd_query(&attr, uattr);
+		err = bpf_task_fd_query(&attr, uattr.user);
 		break;
 	case BPF_MAP_LOOKUP_AND_DELETE_ELEM:
 		err = map_lookup_and_delete_elem(&attr);
 		break;
 	case BPF_MAP_LOOKUP_BATCH:
-		err = bpf_map_do_batch(&attr, uattr, BPF_MAP_LOOKUP_BATCH);
+		err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_BATCH);
 		break;
 	case BPF_MAP_LOOKUP_AND_DELETE_BATCH:
-		err = bpf_map_do_batch(&attr, uattr,
+		err = bpf_map_do_batch(&attr, uattr.user,
 				       BPF_MAP_LOOKUP_AND_DELETE_BATCH);
 		break;
 	case BPF_MAP_UPDATE_BATCH:
-		err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH);
+		err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_UPDATE_BATCH);
 		break;
 	case BPF_MAP_DELETE_BATCH:
-		err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH);
+		err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_DELETE_BATCH);
 		break;
 	case BPF_LINK_CREATE:
-		err = link_create(&attr);
+		err = link_create(&attr, uattr);
 		break;
 	case BPF_LINK_UPDATE:
 		err = link_update(&attr);
@@ -4487,7 +4545,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 		err = bpf_link_get_fd_by_id(&attr);
 		break;
 	case BPF_LINK_GET_NEXT_ID:
-		err = bpf_obj_get_next_id(&attr, uattr,
+		err = bpf_obj_get_next_id(&attr, uattr.user,
 					  &link_idr, &link_idr_lock);
 		break;
 	case BPF_ENABLE_STATS:
@@ -4509,3 +4567,94 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 
 	return err;
 }
+
+SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
+{
+	return __sys_bpf(cmd, USER_BPFPTR(uattr), size);
+}
+
+static bool syscall_prog_is_valid_access(int off, int size,
+					 enum bpf_access_type type,
+					 const struct bpf_prog *prog,
+					 struct bpf_insn_access_aux *info)
+{
+	if (off < 0 || off >= U16_MAX)
+		return false;
+	if (off % size != 0)
+		return false;
+	return true;
+}
+
+BPF_CALL_3(bpf_sys_bpf, int, cmd, void *, attr, u32, attr_size)
+{
+	switch (cmd) {
+	case BPF_MAP_CREATE:
+	case BPF_MAP_UPDATE_ELEM:
+	case BPF_MAP_FREEZE:
+	case BPF_PROG_LOAD:
+	case BPF_BTF_LOAD:
+		break;
+	/* case BPF_PROG_TEST_RUN:
+	 * is not part of this list to prevent recursive test_run
+	 */
+	default:
+		return -EINVAL;
+	}
+	return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size);
+}
+
+static const struct bpf_func_proto bpf_sys_bpf_proto = {
+	.func		= bpf_sys_bpf,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+};
+
+const struct bpf_func_proto * __weak
+tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	return bpf_base_func_proto(func_id);
+}
+
+BPF_CALL_1(bpf_sys_close, u32, fd)
+{
+	/* When bpf program calls this helper there should not be
+	 * an fdget() without matching completed fdput().
+	 * This helper is allowed in the following callchain only:
+	 * sys_bpf->prog_test_run->bpf_prog->bpf_sys_close
+	 */
+	return close_fd(fd);
+}
+
+static const struct bpf_func_proto bpf_sys_close_proto = {
+	.func		= bpf_sys_close,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *
+syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_sys_bpf:
+		return &bpf_sys_bpf_proto;
+	case BPF_FUNC_btf_find_by_name_kind:
+		return &bpf_btf_find_by_name_kind_proto;
+	case BPF_FUNC_sys_close:
+		return &bpf_sys_close_proto;
+	default:
+		return tracing_prog_func_proto(func_id, prog);
+	}
+}
+
+const struct bpf_verifier_ops bpf_syscall_verifier_ops = {
+	.get_func_proto  = syscall_prog_func_proto,
+	.is_valid_access = syscall_prog_is_valid_access,
+};
+
+const struct bpf_prog_ops bpf_syscall_prog_ops = {
+	.test_run = bpf_prog_test_run_syscall,
+};