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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2023-12-18

This PR is larger than usual and contains changes in various parts
of the kernel.

The main changes are:

1) Fix kCFI bugs in BPF, from Peter Zijlstra.

End result: all forms of indirect calls from BPF into kernel
and from kernel into BPF work with CFI enabled. This allows BPF
to work with CONFIG_FINEIBT=y.

2) Introduce BPF token object, from Andrii Nakryiko.

It adds an ability to delegate a subset of BPF features from privileged
daemon (e.g., systemd) through special mount options for userns-bound
BPF FS to a trusted unprivileged application. The design accommodates
suggestions from Christian Brauner and Paul Moore.

Example:
$ sudo mkdir -p /sys/fs/bpf/token
$ sudo mount -t bpf bpffs /sys/fs/bpf/token \
             -o delegate_cmds=prog_load:MAP_CREATE \
             -o delegate_progs=kprobe \
             -o delegate_attachs=xdp

3) Various verifier improvements and fixes, from Andrii Nakryiko, Andrei Matei.

 - Complete precision tracking support for register spills
 - Fix verification of possibly-zero-sized stack accesses
 - Fix access to uninit stack slots
 - Track aligned STACK_ZERO cases as imprecise spilled registers.
   It improves the verifier "instructions processed" metric from single
   digit to 50-60% for some programs.
 - Fix verifier retval logic

4) Support for VLAN tag in XDP hints, from Larysa Zaremba.

5) Allocate BPF trampoline via bpf_prog_pack mechanism, from Song Liu.

End result: better memory utilization and lower I$ miss for calls to BPF
via BPF trampoline.

6) Fix race between BPF prog accessing inner map and parallel delete,
from Hou Tao.

7) Add bpf_xdp_get_xfrm_state() kfunc, from Daniel Xu.

It allows BPF interact with IPSEC infra. The intent is to support
software RSS (via XDP) for the upcoming ipsec pcpu work.
Experiments on AWS demonstrate single tunnel pcpu ipsec reaching
line rate on 100G ENA nics.

8) Expand bpf_cgrp_storage to support cgroup1 non-attach, from Yafang Shao.

9) BPF file verification via fsverity, from Song Liu.

It allows BPF progs get fsverity digest.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (164 commits)
  bpf: Ensure precise is reset to false in __mark_reg_const_zero()
  selftests/bpf: Add more uprobe multi fail tests
  bpf: Fail uprobe multi link with negative offset
  selftests/bpf: Test the release of map btf
  s390/bpf: Fix indirect trampoline generation
  selftests/bpf: Temporarily disable dummy_struct_ops test on s390
  x86/cfi,bpf: Fix bpf_exception_cb() signature
  bpf: Fix dtor CFI
  cfi: Add CFI_NOSEAL()
  x86/cfi,bpf: Fix bpf_struct_ops CFI
  x86/cfi,bpf: Fix bpf_callback_t CFI
  x86/cfi,bpf: Fix BPF JIT call
  cfi: Flip headers
  selftests/bpf: Add test for abnormal cnt during multi-kprobe attachment
  selftests/bpf: Don't use libbpf_get_error() in kprobe_multi_test
  selftests/bpf: Add test for abnormal cnt during multi-uprobe attachment
  bpf: Limit the number of kprobes when attaching program to multiple kprobes
  bpf: Limit the number of uprobes when attaching program to multiple uprobes
  bpf: xdp: Register generic_kfunc_set with XDP programs
  selftests/bpf: utilize string values for delegate_xxx mount options
  ...
====================

Link: https://lore.kernel.org/r/20231219000520.34178-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 220 insertions, 74 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 5e43ddd1b83f..8faa1a20edf8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -142,9 +142,13 @@ static u32 bpf_map_value_size(const struct bpf_map *map)
 
 static void maybe_wait_bpf_programs(struct bpf_map *map)
 {
-	/* Wait for any running BPF programs to complete so that
-	 * userspace, when we return to it, knows that all programs
-	 * that could be running use the new map value.
+	/* Wait for any running non-sleepable BPF programs to complete so that
+	 * userspace, when we return to it, knows that all non-sleepable
+	 * programs that could be running use the new map value. For sleepable
+	 * BPF programs, synchronize_rcu_tasks_trace() should be used to wait
+	 * for the completions of these programs, but considering the waiting
+	 * time can be very long and userspace may think it will hang forever,
+	 * so don't handle sleepable BPF programs now.
 	 */
 	if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS ||
 	    map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
@@ -180,15 +184,11 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file,
 		err = bpf_percpu_cgroup_storage_update(map, key, value,
 						       flags);
 	} else if (IS_FD_ARRAY(map)) {
-		rcu_read_lock();
 		err = bpf_fd_array_map_update_elem(map, map_file, key, value,
 						   flags);
-		rcu_read_unlock();
 	} else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
-		rcu_read_lock();
 		err = bpf_fd_htab_map_update_elem(map, map_file, key, value,
 						  flags);
-		rcu_read_unlock();
 	} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
 		/* rcu_read_lock() is not needed */
 		err = bpf_fd_reuseport_array_update_elem(map, key, value,
@@ -203,7 +203,6 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file,
 		rcu_read_unlock();
 	}
 	bpf_enable_instrumentation();
-	maybe_wait_bpf_programs(map);
 
 	return err;
 }
@@ -264,7 +263,6 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
 	}
 
 	bpf_enable_instrumentation();
-	maybe_wait_bpf_programs(map);
 
 	return err;
 }
@@ -694,6 +692,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
 {
 	struct bpf_map *map = container_of(work, struct bpf_map, work);
 	struct btf_record *rec = map->record;
+	struct btf *btf = map->btf;
 
 	security_bpf_map_free(map);
 	bpf_map_release_memcg(map);
@@ -709,6 +708,10 @@ static void bpf_map_free_deferred(struct work_struct *work)
 	 * template bpf_map struct used during verification.
 	 */
 	btf_record_free(rec);
+	/* Delay freeing of btf for maps, as map_free callback may need
+	 * struct_meta info which will be freed with btf_put().
+	 */
+	btf_put(btf);
 }
 
 static void bpf_map_put_uref(struct bpf_map *map)
@@ -719,6 +722,28 @@ static void bpf_map_put_uref(struct bpf_map *map)
 	}
 }
 
+static void bpf_map_free_in_work(struct bpf_map *map)
+{
+	INIT_WORK(&map->work, bpf_map_free_deferred);
+	/* Avoid spawning kworkers, since they all might contend
+	 * for the same mutex like slab_mutex.
+	 */
+	queue_work(system_unbound_wq, &map->work);
+}
+
+static void bpf_map_free_rcu_gp(struct rcu_head *rcu)
+{
+	bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu));
+}
+
+static void bpf_map_free_mult_rcu_gp(struct rcu_head *rcu)
+{
+	if (rcu_trace_implies_rcu_gp())
+		bpf_map_free_rcu_gp(rcu);
+	else
+		call_rcu(rcu, bpf_map_free_rcu_gp);
+}
+
 /* decrement map refcnt and schedule it for freeing via workqueue
  * (underlying map implementation ops->map_free() might sleep)
  */
@@ -727,12 +752,14 @@ void bpf_map_put(struct bpf_map *map)
 	if (atomic64_dec_and_test(&map->refcnt)) {
 		/* bpf_map_free_id() must be called first */
 		bpf_map_free_id(map);
-		btf_put(map->btf);
-		INIT_WORK(&map->work, bpf_map_free_deferred);
-		/* Avoid spawning kworkers, since they all might contend
-		 * for the same mutex like slab_mutex.
-		 */
-		queue_work(system_unbound_wq, &map->work);
+
+		WARN_ON_ONCE(atomic64_read(&map->sleepable_refcnt));
+		if (READ_ONCE(map->free_after_mult_rcu_gp))
+			call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp);
+		else if (READ_ONCE(map->free_after_rcu_gp))
+			call_rcu(&map->rcu, bpf_map_free_rcu_gp);
+		else
+			bpf_map_free_in_work(map);
 	}
 }
 EXPORT_SYMBOL_GPL(bpf_map_put);
@@ -984,8 +1011,8 @@ int map_check_no_btf(const struct bpf_map *map,
 	return -ENOTSUPP;
 }
 
-static int map_check_btf(struct bpf_map *map, const struct btf *btf,
-			 u32 btf_key_id, u32 btf_value_id)
+static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
+			 const struct btf *btf, u32 btf_key_id, u32 btf_value_id)
 {
 	const struct btf_type *key_type, *value_type;
 	u32 key_size, value_size;
@@ -1013,7 +1040,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 	if (!IS_ERR_OR_NULL(map->record)) {
 		int i;
 
-		if (!bpf_capable()) {
+		if (!bpf_token_capable(token, CAP_BPF)) {
 			ret = -EPERM;
 			goto free_map_tab;
 		}
@@ -1096,11 +1123,17 @@ free_map_tab:
 	return ret;
 }
 
-#define BPF_MAP_CREATE_LAST_FIELD map_extra
+static bool bpf_net_capable(void)
+{
+	return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN);
+}
+
+#define BPF_MAP_CREATE_LAST_FIELD map_token_fd
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
 	const struct bpf_map_ops *ops;
+	struct bpf_token *token = NULL;
 	int numa_node = bpf_map_attr_numa_node(attr);
 	u32 map_type = attr->map_type;
 	struct bpf_map *map;
@@ -1151,14 +1184,32 @@ static int map_create(union bpf_attr *attr)
 	if (!ops->map_mem_usage)
 		return -EINVAL;
 
+	if (attr->map_token_fd) {
+		token = bpf_token_get_from_fd(attr->map_token_fd);
+		if (IS_ERR(token))
+			return PTR_ERR(token);
+
+		/* if current token doesn't grant map creation permissions,
+		 * then we can't use this token, so ignore it and rely on
+		 * system-wide capabilities checks
+		 */
+		if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) ||
+		    !bpf_token_allow_map_type(token, attr->map_type)) {
+			bpf_token_put(token);
+			token = NULL;
+		}
+	}
+
+	err = -EPERM;
+
 	/* Intent here is for unprivileged_bpf_disabled to block BPF map
 	 * creation for unprivileged users; other actions depend
 	 * on fd availability and access to bpffs, so are dependent on
 	 * object creation success. Even with unprivileged BPF disabled,
 	 * capability checks are still carried out.
 	 */
-	if (sysctl_unprivileged_bpf_disabled && !bpf_capable())
-		return -EPERM;
+	if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF))
+		goto put_token;
 
 	/* check privileged map type permissions */
 	switch (map_type) {
@@ -1191,25 +1242,27 @@ static int map_create(union bpf_attr *attr)
 	case BPF_MAP_TYPE_LRU_PERCPU_HASH:
 	case BPF_MAP_TYPE_STRUCT_OPS:
 	case BPF_MAP_TYPE_CPUMAP:
-		if (!bpf_capable())
-			return -EPERM;
+		if (!bpf_token_capable(token, CAP_BPF))
+			goto put_token;
 		break;
 	case BPF_MAP_TYPE_SOCKMAP:
 	case BPF_MAP_TYPE_SOCKHASH:
 	case BPF_MAP_TYPE_DEVMAP:
 	case BPF_MAP_TYPE_DEVMAP_HASH:
 	case BPF_MAP_TYPE_XSKMAP:
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
+		if (!bpf_token_capable(token, CAP_NET_ADMIN))
+			goto put_token;
 		break;
 	default:
 		WARN(1, "unsupported map type %d", map_type);
-		return -EPERM;
+		goto put_token;
 	}
 
 	map = ops->map_alloc(attr);
-	if (IS_ERR(map))
-		return PTR_ERR(map);
+	if (IS_ERR(map)) {
+		err = PTR_ERR(map);
+		goto put_token;
+	}
 	map->ops = ops;
 	map->map_type = map_type;
 
@@ -1246,7 +1299,7 @@ static int map_create(union bpf_attr *attr)
 		map->btf = btf;
 
 		if (attr->btf_value_type_id) {
-			err = map_check_btf(map, btf, attr->btf_key_type_id,
+			err = map_check_btf(map, token, btf, attr->btf_key_type_id,
 					    attr->btf_value_type_id);
 			if (err)
 				goto free_map;
@@ -1258,15 +1311,16 @@ static int map_create(union bpf_attr *attr)
 			attr->btf_vmlinux_value_type_id;
 	}
 
-	err = security_bpf_map_alloc(map);
+	err = security_bpf_map_create(map, attr, token);
 	if (err)
-		goto free_map;
+		goto free_map_sec;
 
 	err = bpf_map_alloc_id(map);
 	if (err)
 		goto free_map_sec;
 
 	bpf_map_save_memcg(map);
+	bpf_token_put(token);
 
 	err = bpf_map_new_fd(map, f_flags);
 	if (err < 0) {
@@ -1287,6 +1341,8 @@ free_map_sec:
 free_map:
 	btf_put(map->btf);
 	map->ops->map_free(map);
+put_token:
+	bpf_token_put(token);
 	return err;
 }
 
@@ -1524,6 +1580,8 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
 	}
 
 	err = bpf_map_update_value(map, f.file, key, value, attr->flags);
+	if (!err)
+		maybe_wait_bpf_programs(map);
 
 	kvfree(value);
 free_key:
@@ -1579,7 +1637,8 @@ static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr)
 	err = map->ops->map_delete_elem(map, key);
 	rcu_read_unlock();
 	bpf_enable_instrumentation();
-	maybe_wait_bpf_programs(map);
+	if (!err)
+		maybe_wait_bpf_programs(map);
 out:
 	kvfree(key);
 err_put:
@@ -1676,6 +1735,9 @@ int generic_map_delete_batch(struct bpf_map *map,
 	if (!max_count)
 		return 0;
 
+	if (put_user(0, &uattr->batch.count))
+		return -EFAULT;
+
 	key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
 	if (!key)
 		return -ENOMEM;
@@ -1705,7 +1767,6 @@ int generic_map_delete_batch(struct bpf_map *map,
 
 	kvfree(key);
 
-	maybe_wait_bpf_programs(map);
 	return err;
 }
 
@@ -1733,6 +1794,9 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
 	if (!max_count)
 		return 0;
 
+	if (put_user(0, &uattr->batch.count))
+		return -EFAULT;
+
 	key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
 	if (!key)
 		return -ENOMEM;
@@ -1763,6 +1827,7 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
 
 	kvfree(value);
 	kvfree(key);
+
 	return err;
 }
 
@@ -2108,7 +2173,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 	kvfree(aux->func_info);
 	kfree(aux->func_info_aux);
 	free_uid(aux->user);
-	security_bpf_prog_free(aux);
+	security_bpf_prog_free(aux->prog);
 	bpf_prog_free(aux->prog);
 }
 
@@ -2554,13 +2619,15 @@ 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 log_true_size
+#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd
 
 static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 {
 	enum bpf_prog_type type = attr->prog_type;
 	struct bpf_prog *prog, *dst_prog = NULL;
 	struct btf *attach_btf = NULL;
+	struct bpf_token *token = NULL;
+	bool bpf_cap;
 	int err;
 	char license[128];
 
@@ -2577,10 +2644,31 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 				 BPF_F_TEST_REG_INVARIANTS))
 		return -EINVAL;
 
+	bpf_prog_load_fixup_attach_type(attr);
+
+	if (attr->prog_token_fd) {
+		token = bpf_token_get_from_fd(attr->prog_token_fd);
+		if (IS_ERR(token))
+			return PTR_ERR(token);
+		/* if current token doesn't grant prog loading permissions,
+		 * then we can't use this token, so ignore it and rely on
+		 * system-wide capabilities checks
+		 */
+		if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) ||
+		    !bpf_token_allow_prog_type(token, attr->prog_type,
+					       attr->expected_attach_type)) {
+			bpf_token_put(token);
+			token = NULL;
+		}
+	}
+
+	bpf_cap = bpf_token_capable(token, CAP_BPF);
+	err = -EPERM;
+
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
 	    (attr->prog_flags & BPF_F_ANY_ALIGNMENT) &&
-	    !bpf_capable())
-		return -EPERM;
+	    !bpf_cap)
+		goto put_token;
 
 	/* Intent here is for unprivileged_bpf_disabled to block BPF program
 	 * creation for unprivileged users; other actions depend
@@ -2589,21 +2677,23 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 	 * capability checks are still carried out for these
 	 * and other operations.
 	 */
-	if (sysctl_unprivileged_bpf_disabled && !bpf_capable())
-		return -EPERM;
+	if (sysctl_unprivileged_bpf_disabled && !bpf_cap)
+		goto put_token;
 
 	if (attr->insn_cnt == 0 ||
-	    attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
-		return -E2BIG;
+	    attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) {
+		err = -E2BIG;
+		goto put_token;
+	}
 	if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
 	    type != BPF_PROG_TYPE_CGROUP_SKB &&
-	    !bpf_capable())
-		return -EPERM;
+	    !bpf_cap)
+		goto put_token;
 
-	if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN))
-		return -EPERM;
-	if (is_perfmon_prog_type(type) && !perfmon_capable())
-		return -EPERM;
+	if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN))
+		goto put_token;
+	if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON))
+		goto put_token;
 
 	/* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog
 	 * or btf, we need to check which one it is
@@ -2613,27 +2703,33 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 		if (IS_ERR(dst_prog)) {
 			dst_prog = NULL;
 			attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd);
-			if (IS_ERR(attach_btf))
-				return -EINVAL;
+			if (IS_ERR(attach_btf)) {
+				err = -EINVAL;
+				goto put_token;
+			}
 			if (!btf_is_kernel(attach_btf)) {
 				/* attaching through specifying bpf_prog's BTF
 				 * objects directly might be supported eventually
 				 */
 				btf_put(attach_btf);
-				return -ENOTSUPP;
+				err = -ENOTSUPP;
+				goto put_token;
 			}
 		}
 	} else if (attr->attach_btf_id) {
 		/* fall back to vmlinux BTF, if BTF type ID is specified */
 		attach_btf = bpf_get_btf_vmlinux();
-		if (IS_ERR(attach_btf))
-			return PTR_ERR(attach_btf);
-		if (!attach_btf)
-			return -EINVAL;
+		if (IS_ERR(attach_btf)) {
+			err = PTR_ERR(attach_btf);
+			goto put_token;
+		}
+		if (!attach_btf) {
+			err = -EINVAL;
+			goto put_token;
+		}
 		btf_get(attach_btf);
 	}
 
-	bpf_prog_load_fixup_attach_type(attr);
 	if (bpf_prog_load_check_attach(type, attr->expected_attach_type,
 				       attach_btf, attr->attach_btf_id,
 				       dst_prog)) {
@@ -2641,7 +2737,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 			bpf_prog_put(dst_prog);
 		if (attach_btf)
 			btf_put(attach_btf);
-		return -EINVAL;
+		err = -EINVAL;
+		goto put_token;
 	}
 
 	/* plain bpf_prog allocation */
@@ -2651,7 +2748,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 			bpf_prog_put(dst_prog);
 		if (attach_btf)
 			btf_put(attach_btf);
-		return -ENOMEM;
+		err = -EINVAL;
+		goto put_token;
 	}
 
 	prog->expected_attach_type = attr->expected_attach_type;
@@ -2662,9 +2760,9 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 	prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
 	prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS;
 
-	err = security_bpf_prog_alloc(prog->aux);
-	if (err)
-		goto free_prog;
+	/* move token into prog->aux, reuse taken refcnt */
+	prog->aux->token = token;
+	token = NULL;
 
 	prog->aux->user = get_current_user();
 	prog->len = attr->insn_cnt;
@@ -2673,12 +2771,12 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 	if (copy_from_bpfptr(prog->insns,
 			     make_bpfptr(attr->insns, uattr.is_kernel),
 			     bpf_prog_insn_size(prog)) != 0)
-		goto free_prog_sec;
+		goto free_prog;
 	/* copy eBPF program license from user space */
 	if (strncpy_from_bpfptr(license,
 				make_bpfptr(attr->license, uattr.is_kernel),
 				sizeof(license) - 1) < 0)
-		goto free_prog_sec;
+		goto free_prog;
 	license[sizeof(license) - 1] = 0;
 
 	/* eBPF programs must be GPL compatible to use GPL-ed functions */
@@ -2692,25 +2790,29 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 	if (bpf_prog_is_dev_bound(prog->aux)) {
 		err = bpf_prog_dev_bound_init(prog, attr);
 		if (err)
-			goto free_prog_sec;
+			goto free_prog;
 	}
 
 	if (type == BPF_PROG_TYPE_EXT && dst_prog &&
 	    bpf_prog_is_dev_bound(dst_prog->aux)) {
 		err = bpf_prog_dev_bound_inherit(prog, dst_prog);
 		if (err)
-			goto free_prog_sec;
+			goto free_prog;
 	}
 
 	/* find program type: socket_filter vs tracing_filter */
 	err = find_prog_type(type, prog);
 	if (err < 0)
-		goto free_prog_sec;
+		goto free_prog;
 
 	prog->aux->load_time = ktime_get_boottime_ns();
 	err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name,
 			       sizeof(attr->prog_name));
 	if (err < 0)
+		goto free_prog;
+
+	err = security_bpf_prog_load(prog, attr, token);
+	if (err)
 		goto free_prog_sec;
 
 	/* run eBPF verifier */
@@ -2756,13 +2858,16 @@ free_used_maps:
 	 */
 	__bpf_prog_put_noref(prog, prog->aux->real_func_cnt);
 	return err;
+
 free_prog_sec:
-	free_uid(prog->aux->user);
-	security_bpf_prog_free(prog->aux);
+	security_bpf_prog_free(prog);
 free_prog:
+	free_uid(prog->aux->user);
 	if (prog->aux->attach_btf)
 		btf_put(prog->aux->attach_btf);
 	bpf_prog_free(prog);
+put_token:
+	bpf_token_put(token);
 	return err;
 }
 
@@ -3752,7 +3857,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 	case BPF_PROG_TYPE_SK_LOOKUP:
 		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
 	case BPF_PROG_TYPE_CGROUP_SKB:
-		if (!capable(CAP_NET_ADMIN))
+		if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN))
 			/* cg-skb progs can be loaded by unpriv user.
 			 * check permissions at attach time.
 			 */
@@ -3955,7 +4060,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 static int bpf_prog_query(const union bpf_attr *attr,
 			  union bpf_attr __user *uattr)
 {
-	if (!capable(CAP_NET_ADMIN))
+	if (!bpf_net_capable())
 		return -EPERM;
 	if (CHECK_ATTR(BPF_PROG_QUERY))
 		return -EINVAL;
@@ -4723,15 +4828,31 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 	return err;
 }
 
-#define BPF_BTF_LOAD_LAST_FIELD btf_log_true_size
+#define BPF_BTF_LOAD_LAST_FIELD btf_token_fd
 
 static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size)
 {
+	struct bpf_token *token = NULL;
+
 	if (CHECK_ATTR(BPF_BTF_LOAD))
 		return -EINVAL;
 
-	if (!bpf_capable())
+	if (attr->btf_token_fd) {
+		token = bpf_token_get_from_fd(attr->btf_token_fd);
+		if (IS_ERR(token))
+			return PTR_ERR(token);
+		if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) {
+			bpf_token_put(token);
+			token = NULL;
+		}
+	}
+
+	if (!bpf_token_capable(token, CAP_BPF)) {
+		bpf_token_put(token);
 		return -EPERM;
+	}
+
+	bpf_token_put(token);
 
 	return btf_new_fd(attr, uattr, uattr_size);
 }
@@ -4920,8 +5041,10 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 	else
 		BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr);
 err_put:
-	if (has_write)
+	if (has_write) {
+		maybe_wait_bpf_programs(map);
 		bpf_map_write_active_dec(map);
+	}
 	fdput(f);
 	return err;
 }
@@ -5323,6 +5446,11 @@ static int bpf_prog_bind_map(union bpf_attr *attr)
 		goto out_unlock;
 	}
 
+	/* The bpf program will not access the bpf map, but for the sake of
+	 * simplicity, increase sleepable_refcnt for sleepable program as well.
+	 */
+	if (prog->aux->sleepable)
+		atomic64_inc(&map->sleepable_refcnt);
 	memcpy(used_maps_new, used_maps_old,
 	       sizeof(used_maps_old[0]) * prog->aux->used_map_cnt);
 	used_maps_new[prog->aux->used_map_cnt] = map;
@@ -5342,6 +5470,20 @@ out_prog_put:
 	return ret;
 }
 
+#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd
+
+static int token_create(union bpf_attr *attr)
+{
+	if (CHECK_ATTR(BPF_TOKEN_CREATE))
+		return -EINVAL;
+
+	/* no flags are supported yet */
+	if (attr->token_create.flags)
+		return -EINVAL;
+
+	return bpf_token_create(attr);
+}
+
 static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
 {
 	union bpf_attr attr;
@@ -5475,6 +5617,9 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
 	case BPF_PROG_BIND_MAP:
 		err = bpf_prog_bind_map(&attr);
 		break;
+	case BPF_TOKEN_CREATE:
+		err = token_create(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
@@ -5581,7 +5726,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = {
 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);
+	return bpf_base_func_proto(func_id, prog);
 }
 
 BPF_CALL_1(bpf_sys_close, u32, fd)
@@ -5631,7 +5776,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_sys_bpf:
-		return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto;
+		return !bpf_token_capable(prog->aux->token, CAP_PERFMON)
+		       ? NULL : &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: