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>

22 files changed, 1497 insertions, 458 deletions

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index f526b7573e97..4ce95acfcaa7 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
 endif
 CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
 
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o
 obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index c85ff9162a5c..13358675ff2e 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -82,7 +82,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
 	int numa_node = bpf_map_attr_numa_node(attr);
 	u32 elem_size, index_mask, max_entries;
-	bool bypass_spec_v1 = bpf_bypass_spec_v1();
+	bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL);
 	u64 array_size, mask64;
 	struct bpf_array *array;
 
@@ -867,11 +867,11 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
 	}
 
 	if (old_ptr)
-		map->ops->map_fd_put_ptr(old_ptr);
+		map->ops->map_fd_put_ptr(map, old_ptr, true);
 	return 0;
 }
 
-static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
+static long __fd_array_map_delete_elem(struct bpf_map *map, void *key, bool need_defer)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	void *old_ptr;
@@ -890,13 +890,18 @@ static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
 	}
 
 	if (old_ptr) {
-		map->ops->map_fd_put_ptr(old_ptr);
+		map->ops->map_fd_put_ptr(map, old_ptr, need_defer);
 		return 0;
 	} else {
 		return -ENOENT;
 	}
 }
 
+static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
+{
+	return __fd_array_map_delete_elem(map, key, true);
+}
+
 static void *prog_fd_array_get_ptr(struct bpf_map *map,
 				   struct file *map_file, int fd)
 {
@@ -913,8 +918,9 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map,
 	return prog;
 }
 
-static void prog_fd_array_put_ptr(void *ptr)
+static void prog_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
+	/* bpf_prog is freed after one RCU or tasks trace grace period */
 	bpf_prog_put(ptr);
 }
 
@@ -924,13 +930,13 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr)
 }
 
 /* decrement refcnt of all bpf_progs that are stored in this map */
-static void bpf_fd_array_map_clear(struct bpf_map *map)
+static void bpf_fd_array_map_clear(struct bpf_map *map, bool need_defer)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
 
 	for (i = 0; i < array->map.max_entries; i++)
-		fd_array_map_delete_elem(map, &i);
+		__fd_array_map_delete_elem(map, &i, need_defer);
 }
 
 static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key,
@@ -1071,7 +1077,7 @@ static void prog_array_map_clear_deferred(struct work_struct *work)
 {
 	struct bpf_map *map = container_of(work, struct bpf_array_aux,
 					   work)->map;
-	bpf_fd_array_map_clear(map);
+	bpf_fd_array_map_clear(map, true);
 	bpf_map_put(map);
 }
 
@@ -1151,7 +1157,7 @@ static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
 {
 	struct bpf_event_entry *ee;
 
-	ee = kzalloc(sizeof(*ee), GFP_ATOMIC);
+	ee = kzalloc(sizeof(*ee), GFP_KERNEL);
 	if (ee) {
 		ee->event = perf_file->private_data;
 		ee->perf_file = perf_file;
@@ -1201,8 +1207,9 @@ err_out:
 	return ee;
 }
 
-static void perf_event_fd_array_put_ptr(void *ptr)
+static void perf_event_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
+	/* bpf_perf_event is freed after one RCU grace period */
 	bpf_event_entry_free_rcu(ptr);
 }
 
@@ -1220,7 +1227,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 	for (i = 0; i < array->map.max_entries; i++) {
 		ee = READ_ONCE(array->ptrs[i]);
 		if (ee && ee->map_file == map_file)
-			fd_array_map_delete_elem(map, &i);
+			__fd_array_map_delete_elem(map, &i, true);
 	}
 	rcu_read_unlock();
 }
@@ -1228,7 +1235,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 static void perf_event_fd_array_map_free(struct bpf_map *map)
 {
 	if (map->map_flags & BPF_F_PRESERVE_ELEMS)
-		bpf_fd_array_map_clear(map);
+		bpf_fd_array_map_clear(map, false);
 	fd_array_map_free(map);
 }
 
@@ -1256,7 +1263,7 @@ static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
 	return cgroup_get_from_fd(fd);
 }
 
-static void cgroup_fd_array_put_ptr(void *ptr)
+static void cgroup_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
 	/* cgroup_put free cgrp after a rcu grace period */
 	cgroup_put(ptr);
@@ -1264,7 +1271,7 @@ static void cgroup_fd_array_put_ptr(void *ptr)
 
 static void cgroup_fd_array_free(struct bpf_map *map)
 {
-	bpf_fd_array_map_clear(map);
+	bpf_fd_array_map_clear(map, false);
 	fd_array_map_free(map);
 }
 
@@ -1309,7 +1316,7 @@ static void array_of_map_free(struct bpf_map *map)
 	 * is protected by fdget/fdput.
 	 */
 	bpf_map_meta_free(map->inner_map_meta);
-	bpf_fd_array_map_clear(map);
+	bpf_fd_array_map_clear(map, false);
 	fd_array_map_free(map);
 }
 
diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c
index d44fe8dd9732..28efd0a3f220 100644
--- a/kernel/bpf/bpf_cgrp_storage.c
+++ b/kernel/bpf/bpf_cgrp_storage.c
@@ -82,7 +82,7 @@ static void *bpf_cgrp_storage_lookup_elem(struct bpf_map *map, void *key)
 	int fd;
 
 	fd = *(int *)key;
-	cgroup = cgroup_get_from_fd(fd);
+	cgroup = cgroup_v1v2_get_from_fd(fd);
 	if (IS_ERR(cgroup))
 		return ERR_CAST(cgroup);
 
@@ -101,7 +101,7 @@ static long bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key,
 	int fd;
 
 	fd = *(int *)key;
-	cgroup = cgroup_get_from_fd(fd);
+	cgroup = cgroup_v1v2_get_from_fd(fd);
 	if (IS_ERR(cgroup))
 		return PTR_ERR(cgroup);
 
@@ -131,7 +131,7 @@ static long bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key)
 	int err, fd;
 
 	fd = *(int *)key;
-	cgroup = cgroup_get_from_fd(fd);
+	cgroup = cgroup_v1v2_get_from_fd(fd);
 	if (IS_ERR(cgroup))
 		return PTR_ERR(cgroup);
 
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index e14c822f8911..63b4dc495125 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -260,9 +260,15 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 BTF_SET_START(sleepable_lsm_hooks)
 BTF_ID(func, bpf_lsm_bpf)
 BTF_ID(func, bpf_lsm_bpf_map)
-BTF_ID(func, bpf_lsm_bpf_map_alloc_security)
-BTF_ID(func, bpf_lsm_bpf_map_free_security)
+BTF_ID(func, bpf_lsm_bpf_map_create)
+BTF_ID(func, bpf_lsm_bpf_map_free)
 BTF_ID(func, bpf_lsm_bpf_prog)
+BTF_ID(func, bpf_lsm_bpf_prog_load)
+BTF_ID(func, bpf_lsm_bpf_prog_free)
+BTF_ID(func, bpf_lsm_bpf_token_create)
+BTF_ID(func, bpf_lsm_bpf_token_free)
+BTF_ID(func, bpf_lsm_bpf_token_cmd)
+BTF_ID(func, bpf_lsm_bpf_token_capable)
 BTF_ID(func, bpf_lsm_bprm_check_security)
 BTF_ID(func, bpf_lsm_bprm_committed_creds)
 BTF_ID(func, bpf_lsm_bprm_committing_creds)
@@ -298,6 +304,18 @@ BTF_ID(func, bpf_lsm_kernel_module_request)
 BTF_ID(func, bpf_lsm_kernel_read_file)
 BTF_ID(func, bpf_lsm_kernfs_init_security)
 
+#ifdef CONFIG_SECURITY_PATH
+BTF_ID(func, bpf_lsm_path_unlink)
+BTF_ID(func, bpf_lsm_path_mkdir)
+BTF_ID(func, bpf_lsm_path_rmdir)
+BTF_ID(func, bpf_lsm_path_truncate)
+BTF_ID(func, bpf_lsm_path_symlink)
+BTF_ID(func, bpf_lsm_path_link)
+BTF_ID(func, bpf_lsm_path_rename)
+BTF_ID(func, bpf_lsm_path_chmod)
+BTF_ID(func, bpf_lsm_path_chown)
+#endif /* CONFIG_SECURITY_PATH */
+
 #ifdef CONFIG_KEYS
 BTF_ID(func, bpf_lsm_key_free)
 #endif /* CONFIG_KEYS */
@@ -345,9 +363,8 @@ BTF_ID(func, bpf_lsm_userns_create)
 BTF_SET_END(sleepable_lsm_hooks)
 
 BTF_SET_START(untrusted_lsm_hooks)
-BTF_ID(func, bpf_lsm_bpf_map_free_security)
-BTF_ID(func, bpf_lsm_bpf_prog_alloc_security)
-BTF_ID(func, bpf_lsm_bpf_prog_free_security)
+BTF_ID(func, bpf_lsm_bpf_map_free)
+BTF_ID(func, bpf_lsm_bpf_prog_free)
 BTF_ID(func, bpf_lsm_file_alloc_security)
 BTF_ID(func, bpf_lsm_file_free_security)
 #ifdef CONFIG_SECURITY_NETWORK
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index db6176fb64dc..02068bd0e4d9 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -352,18 +352,24 @@ const struct bpf_link_ops bpf_struct_ops_link_lops = {
 int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 				      struct bpf_tramp_link *link,
 				      const struct btf_func_model *model,
-				      void *image, void *image_end)
+				      void *stub_func, void *image, void *image_end)
 {
-	u32 flags;
+	u32 flags = BPF_TRAMP_F_INDIRECT;
+	int size;
 
 	tlinks[BPF_TRAMP_FENTRY].links[0] = link;
 	tlinks[BPF_TRAMP_FENTRY].nr_links = 1;
-	/* BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops,
-	 * and it must be used alone.
-	 */
-	flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0;
+
+	if (model->ret_size > 0)
+		flags |= BPF_TRAMP_F_RET_FENTRY_RET;
+
+	size = arch_bpf_trampoline_size(model, flags, tlinks, NULL);
+	if (size < 0)
+		return size;
+	if (size > (unsigned long)image_end - (unsigned long)image)
+		return -E2BIG;
 	return arch_prepare_bpf_trampoline(NULL, image, image_end,
-					   model, flags, tlinks, NULL);
+					   model, flags, tlinks, stub_func);
 }
 
 static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
@@ -497,11 +503,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 
 		err = bpf_struct_ops_prepare_trampoline(tlinks, link,
 							&st_ops->func_models[i],
+							*(void **)(st_ops->cfi_stubs + moff),
 							image, image_end);
 		if (err < 0)
 			goto reset_unlock;
 
-		*(void **)(kdata + moff) = image;
+		*(void **)(kdata + moff) = image + cfi_get_offset();
 		image += err;
 
 		/* put prog_id to udata */
@@ -515,7 +522,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 			if (err)
 				goto reset_unlock;
 		}
-		set_memory_rox((long)st_map->image, 1);
+		arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE);
 		/* Let bpf_link handle registration & unregistration.
 		 *
 		 * Pair with smp_load_acquire() during lookup_elem().
@@ -524,7 +531,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 		goto unlock;
 	}
 
-	set_memory_rox((long)st_map->image, 1);
+	arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE);
 	err = st_ops->reg(kdata);
 	if (likely(!err)) {
 		/* This refcnt increment on the map here after
@@ -547,8 +554,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	 * there was a race in registering the struct_ops (under the same name) to
 	 * a sub-system through different struct_ops's maps.
 	 */
-	set_memory_nx((long)st_map->image, 1);
-	set_memory_rw((long)st_map->image, 1);
+	arch_unprotect_bpf_trampoline(st_map->image, PAGE_SIZE);
 
 reset_unlock:
 	bpf_struct_ops_map_put_progs(st_map);
@@ -616,7 +622,7 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map)
 		bpf_struct_ops_map_put_progs(st_map);
 	bpf_map_area_free(st_map->links);
 	if (st_map->image) {
-		bpf_jit_free_exec(st_map->image);
+		arch_free_bpf_trampoline(st_map->image, PAGE_SIZE);
 		bpf_jit_uncharge_modmem(PAGE_SIZE);
 	}
 	bpf_map_area_free(st_map->uvalue);
@@ -691,7 +697,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(ret);
 	}
 
-	st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
+	st_map->image = arch_alloc_bpf_trampoline(PAGE_SIZE);
 	if (!st_map->image) {
 		/* __bpf_struct_ops_map_free() uses st_map->image as flag
 		 * for "charged or not". In this case, we need to unchange
@@ -711,7 +717,6 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	}
 
 	mutex_init(&st_map->lock);
-	set_vm_flush_reset_perms(st_map->image);
 	bpf_map_init_from_attr(map, attr);
 
 	return map;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 63cf4128fc05..d56433bf8aba 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6956,7 +6956,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
  * (either PTR_TO_CTX or SCALAR_VALUE).
  */
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
-			  struct bpf_reg_state *regs, bool is_ex_cb)
+			  struct bpf_reg_state *regs, u32 *arg_cnt)
 {
 	struct bpf_verifier_log *log = &env->log;
 	struct bpf_prog *prog = env->prog;
@@ -7013,6 +7013,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 			tname, nargs, MAX_BPF_FUNC_REG_ARGS);
 		return -EINVAL;
 	}
+	*arg_cnt = nargs;
 	/* check that function returns int, exception cb also requires this */
 	t = btf_type_by_id(btf, t->type);
 	while (btf_type_is_modifier(t))
@@ -7062,14 +7063,6 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 			i, btf_type_str(t), tname);
 		return -EINVAL;
 	}
-	/* We have already ensured that the callback returns an integer, just
-	 * like all global subprogs. We need to determine it only has a single
-	 * scalar argument.
-	 */
-	if (is_ex_cb && (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE)) {
-		bpf_log(log, "exception cb only supports single integer argument\n");
-		return -EINVAL;
-	}
 	return 0;
 }
 
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 491d20038cbe..98e0e3835b28 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1630,7 +1630,7 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
@@ -2191,7 +2191,7 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
@@ -2348,7 +2348,7 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index fe254ae035fe..14ace23d517b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -121,6 +121,9 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 #endif
 
 	INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
+#ifdef CONFIG_FINEIBT
+	INIT_LIST_HEAD_RCU(&fp->aux->ksym_prefix.lnode);
+#endif
 	mutex_init(&fp->aux->used_maps_mutex);
 	mutex_init(&fp->aux->dst_mutex);
 
@@ -679,7 +682,7 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp)
 void bpf_prog_kallsyms_add(struct bpf_prog *fp)
 {
 	if (!bpf_prog_kallsyms_candidate(fp) ||
-	    !bpf_capable())
+	    !bpf_token_capable(fp->aux->token, CAP_BPF))
 		return;
 
 	bpf_prog_ksym_set_addr(fp);
@@ -687,6 +690,23 @@ void bpf_prog_kallsyms_add(struct bpf_prog *fp)
 	fp->aux->ksym.prog = true;
 
 	bpf_ksym_add(&fp->aux->ksym);
+
+#ifdef CONFIG_FINEIBT
+	/*
+	 * When FineIBT, code in the __cfi_foo() symbols can get executed
+	 * and hence unwinder needs help.
+	 */
+	if (cfi_mode != CFI_FINEIBT)
+		return;
+
+	snprintf(fp->aux->ksym_prefix.name, KSYM_NAME_LEN,
+		 "__cfi_%s", fp->aux->ksym.name);
+
+	fp->aux->ksym_prefix.start = (unsigned long) fp->bpf_func - 16;
+	fp->aux->ksym_prefix.end   = (unsigned long) fp->bpf_func;
+
+	bpf_ksym_add(&fp->aux->ksym_prefix);
+#endif
 }
 
 void bpf_prog_kallsyms_del(struct bpf_prog *fp)
@@ -695,6 +715,11 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp)
 		return;
 
 	bpf_ksym_del(&fp->aux->ksym);
+#ifdef CONFIG_FINEIBT
+	if (cfi_mode != CFI_FINEIBT)
+		return;
+	bpf_ksym_del(&fp->aux->ksym_prefix);
+#endif
 }
 
 static struct bpf_ksym *bpf_ksym_find(unsigned long addr)
@@ -932,20 +957,20 @@ out:
 	return ptr;
 }
 
-void bpf_prog_pack_free(struct bpf_binary_header *hdr)
+void bpf_prog_pack_free(void *ptr, u32 size)
 {
 	struct bpf_prog_pack *pack = NULL, *tmp;
 	unsigned int nbits;
 	unsigned long pos;
 
 	mutex_lock(&pack_mutex);
-	if (hdr->size > BPF_PROG_PACK_SIZE) {
-		bpf_jit_free_exec(hdr);
+	if (size > BPF_PROG_PACK_SIZE) {
+		bpf_jit_free_exec(ptr);
 		goto out;
 	}
 
 	list_for_each_entry(tmp, &pack_list, list) {
-		if ((void *)hdr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > (void *)hdr) {
+		if (ptr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > ptr) {
 			pack = tmp;
 			break;
 		}
@@ -954,10 +979,10 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr)
 	if (WARN_ONCE(!pack, "bpf_prog_pack bug\n"))
 		goto out;
 
-	nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size);
-	pos = ((unsigned long)hdr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT;
+	nbits = BPF_PROG_SIZE_TO_NBITS(size);
+	pos = ((unsigned long)ptr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT;
 
-	WARN_ONCE(bpf_arch_text_invalidate(hdr, hdr->size),
+	WARN_ONCE(bpf_arch_text_invalidate(ptr, size),
 		  "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n");
 
 	bitmap_clear(pack->bitmap, pos, nbits);
@@ -1104,8 +1129,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr,
 
 	*rw_header = kvmalloc(size, GFP_KERNEL);
 	if (!*rw_header) {
-		bpf_arch_text_copy(&ro_header->size, &size, sizeof(size));
-		bpf_prog_pack_free(ro_header);
+		bpf_prog_pack_free(ro_header, size);
 		bpf_jit_uncharge_modmem(size);
 		return NULL;
 	}
@@ -1136,7 +1160,7 @@ int bpf_jit_binary_pack_finalize(struct bpf_prog *prog,
 	kvfree(rw_header);
 
 	if (IS_ERR(ptr)) {
-		bpf_prog_pack_free(ro_header);
+		bpf_prog_pack_free(ro_header, ro_header->size);
 		return PTR_ERR(ptr);
 	}
 	return 0;
@@ -1157,7 +1181,7 @@ void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header,
 {
 	u32 size = ro_header->size;
 
-	bpf_prog_pack_free(ro_header);
+	bpf_prog_pack_free(ro_header, size);
 	kvfree(rw_header);
 	bpf_jit_uncharge_modmem(size);
 }
@@ -2668,12 +2692,16 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux,
 			  struct bpf_map **used_maps, u32 len)
 {
 	struct bpf_map *map;
+	bool sleepable;
 	u32 i;
 
+	sleepable = aux->sleepable;
 	for (i = 0; i < len; i++) {
 		map = used_maps[i];
 		if (map->ops->map_poke_untrack)
 			map->ops->map_poke_untrack(map, aux);
+		if (sleepable)
+			atomic64_dec(&map->sleepable_refcnt);
 		bpf_map_put(map);
 	}
 }
@@ -2751,6 +2779,7 @@ void bpf_prog_free(struct bpf_prog *fp)
 
 	if (aux->dst_prog)
 		bpf_prog_put(aux->dst_prog);
+	bpf_token_put(aux->token);
 	INIT_WORK(&aux->work, bpf_prog_free_deferred);
 	schedule_work(&aux->work);
 }
diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c
index e01c741e54e7..2e73533a3811 100644
--- a/kernel/bpf/cpumask.c
+++ b/kernel/bpf/cpumask.c
@@ -96,6 +96,12 @@ __bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask)
 	migrate_enable();
 }
 
+__bpf_kfunc void bpf_cpumask_release_dtor(void *cpumask)
+{
+	bpf_cpumask_release(cpumask);
+}
+CFI_NOSEAL(bpf_cpumask_release_dtor);
+
 /**
  * bpf_cpumask_first() - Get the index of the first nonzero bit in the cpumask.
  * @cpumask: The cpumask being queried.
@@ -405,6 +411,17 @@ __bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
 	return cpumask_any_and_distribute(src1, src2);
 }
 
+/**
+ * bpf_cpumask_weight() - Return the number of bits in @cpumask.
+ * @cpumask: The cpumask being queried.
+ *
+ * Count the number of set bits in the given cpumask.
+ */
+__bpf_kfunc u32 bpf_cpumask_weight(const struct cpumask *cpumask)
+{
+	return cpumask_weight(cpumask);
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_SET8_START(cpumask_kfunc_btf_ids)
@@ -432,6 +449,7 @@ BTF_ID_FLAGS(func, bpf_cpumask_full, KF_RCU)
 BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_RCU)
 BTF_ID_FLAGS(func, bpf_cpumask_any_distribute, KF_RCU)
 BTF_ID_FLAGS(func, bpf_cpumask_any_and_distribute, KF_RCU)
+BTF_ID_FLAGS(func, bpf_cpumask_weight, KF_RCU)
 BTF_SET8_END(cpumask_kfunc_btf_ids)
 
 static const struct btf_kfunc_id_set cpumask_kfunc_set = {
@@ -441,7 +459,7 @@ static const struct btf_kfunc_id_set cpumask_kfunc_set = {
 
 BTF_ID_LIST(cpumask_dtor_ids)
 BTF_ID(struct, bpf_cpumask)
-BTF_ID(func, bpf_cpumask_release)
+BTF_ID(func, bpf_cpumask_release_dtor)
 
 static int __init cpumask_kfunc_init(void)
 {
diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c
index fa3e9225aedc..70fb82bf1637 100644
--- a/kernel/bpf/dispatcher.c
+++ b/kernel/bpf/dispatcher.c
@@ -150,14 +150,11 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
 			goto out;
 		d->rw_image = bpf_jit_alloc_exec(PAGE_SIZE);
 		if (!d->rw_image) {
-			u32 size = PAGE_SIZE;
-
-			bpf_arch_text_copy(d->image, &size, sizeof(size));
-			bpf_prog_pack_free((struct bpf_binary_header *)d->image);
+			bpf_prog_pack_free(d->image, PAGE_SIZE);
 			d->image = NULL;
 			goto out;
 		}
-		bpf_image_ksym_add(d->image, &d->ksym);
+		bpf_image_ksym_add(d->image, PAGE_SIZE, &d->ksym);
 	}
 
 	prev_num_progs = d->num_progs;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index fd8d4b0addfc..ec3bdcc6a3cf 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -897,7 +897,7 @@ static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)
 
 	if (map->ops->map_fd_put_ptr) {
 		ptr = fd_htab_map_get_ptr(map, l);
-		map->ops->map_fd_put_ptr(ptr);
+		map->ops->map_fd_put_ptr(map, ptr, true);
 	}
 }
 
@@ -2484,7 +2484,7 @@ static void fd_htab_map_free(struct bpf_map *map)
 		hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
 			void *ptr = fd_htab_map_get_ptr(map, l);
 
-			map->ops->map_fd_put_ptr(ptr);
+			map->ops->map_fd_put_ptr(map, ptr, false);
 		}
 	}
 
@@ -2523,9 +2523,15 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
 	if (IS_ERR(ptr))
 		return PTR_ERR(ptr);
 
+	/* The htab bucket lock is always held during update operations in fd
+	 * htab map, and the following rcu_read_lock() is only used to avoid
+	 * the WARN_ON_ONCE in htab_map_update_elem().
+	 */
+	rcu_read_lock();
 	ret = htab_map_update_elem(map, key, &ptr, map_flags);
+	rcu_read_unlock();
 	if (ret)
-		map->ops->map_fd_put_ptr(ptr);
+		map->ops->map_fd_put_ptr(map, ptr, false);
 
 	return ret;
 }
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index b45a8381f9bd..07fd4b5704f3 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -32,12 +32,13 @@
  *
  * Different map implementations will rely on rcu in map methods
  * lookup/update/delete, therefore eBPF programs must run under rcu lock
- * if program is allowed to access maps, so check rcu_read_lock_held in
- * all three functions.
+ * if program is allowed to access maps, so check rcu_read_lock_held() or
+ * rcu_read_lock_trace_held() in all three functions.
  */
 BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 	return (unsigned long) map->ops->map_lookup_elem(map, key);
 }
 
@@ -53,7 +54,8 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto = {
 BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key,
 	   void *, value, u64, flags)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 	return map->ops->map_update_elem(map, key, value, flags);
 }
 
@@ -70,7 +72,8 @@ const struct bpf_func_proto bpf_map_update_elem_proto = {
 
 BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 	return map->ops->map_delete_elem(map, key);
 }
 
@@ -1676,7 +1679,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak;
 const struct bpf_func_proto bpf_task_pt_regs_proto __weak;
 
 const struct bpf_func_proto *
-bpf_base_func_proto(enum bpf_func_id func_id)
+bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_map_lookup_elem:
@@ -1727,7 +1730,7 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		break;
 	}
 
-	if (!bpf_capable())
+	if (!bpf_token_capable(prog->aux->token, CAP_BPF))
 		return NULL;
 
 	switch (func_id) {
@@ -1785,7 +1788,7 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		break;
 	}
 
-	if (!perfmon_capable())
+	if (!bpf_token_capable(prog->aux->token, CAP_PERFMON))
 		return NULL;
 
 	switch (func_id) {
@@ -2147,6 +2150,12 @@ __bpf_kfunc void bpf_task_release(struct task_struct *p)
 	put_task_struct_rcu_user(p);
 }
 
+__bpf_kfunc void bpf_task_release_dtor(void *p)
+{
+	put_task_struct_rcu_user(p);
+}
+CFI_NOSEAL(bpf_task_release_dtor);
+
 #ifdef CONFIG_CGROUPS
 /**
  * bpf_cgroup_acquire - Acquire a reference to a cgroup. A cgroup acquired by
@@ -2171,6 +2180,12 @@ __bpf_kfunc void bpf_cgroup_release(struct cgroup *cgrp)
 	cgroup_put(cgrp);
 }
 
+__bpf_kfunc void bpf_cgroup_release_dtor(void *cgrp)
+{
+	cgroup_put(cgrp);
+}
+CFI_NOSEAL(bpf_cgroup_release_dtor);
+
 /**
  * bpf_cgroup_ancestor - Perform a lookup on an entry in a cgroup's ancestor
  * array. A cgroup returned by this kfunc which is not subsequently stored in a
@@ -2522,7 +2537,7 @@ __bpf_kfunc void bpf_throw(u64 cookie)
 	 * which skips compiler generated instrumentation to do the same.
 	 */
 	kasan_unpoison_task_stack_below((void *)(long)ctx.sp);
-	ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp);
+	ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp, 0, 0);
 	WARN(1, "A call to BPF exception callback should never return\n");
 }
 
@@ -2567,10 +2582,10 @@ static const struct btf_kfunc_id_set generic_kfunc_set = {
 
 BTF_ID_LIST(generic_dtor_ids)