From 4cbb270e115bc197ff2046aeb54cc951666b16ec Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:19 -0800
Subject: bpf: take into account BPF token when fetching helper protos

Instead of performing unconditional system-wide bpf_capable() and
perfmon_capable() calls inside bpf_base_func_proto() function (and other
similar ones) to determine eligibility of a given BPF helper for a given
program, use previously recorded BPF token during BPF_PROG_LOAD command
handling to inform the decision.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-8-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/core/filter.c           | 32 ++++++++++++++++----------------
 net/ipv4/bpf_tcp_ca.c       |  2 +-
 net/netfilter/nf_bpf_link.c |  2 +-
 3 files changed, 18 insertions(+), 18 deletions(-)

(limited to 'net')

diff --git a/net/core/filter.c b/net/core/filter.c
index 0adaa4afa35f..0bf2a03d8203 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -87,7 +87,7 @@
 #include "dev.h"
 
 static const struct bpf_func_proto *
-bpf_sk_base_func_proto(enum bpf_func_id func_id);
+bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
 
 int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len)
 {
@@ -7841,7 +7841,7 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
@@ -7934,7 +7934,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 			return NULL;
 		}
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -7953,7 +7953,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_skb_event_output_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8140,7 +8140,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #endif
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8199,7 +8199,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #endif
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 
 #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)
@@ -8260,7 +8260,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_sock_proto;
 #endif /* CONFIG_INET */
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8302,7 +8302,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_cgroup_classid_curr_proto;
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8346,7 +8346,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_lookup_tcp_proto;
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8357,7 +8357,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_flow_dissector_load_bytes_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8384,7 +8384,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -11215,7 +11215,7 @@ sk_reuseport_func_proto(enum bpf_func_id func_id,
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
@@ -11397,7 +11397,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -11731,7 +11731,7 @@ const struct bpf_func_proto bpf_sock_from_file_proto = {
 };
 
 static const struct bpf_func_proto *
-bpf_sk_base_func_proto(enum bpf_func_id func_id)
+bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	const struct bpf_func_proto *func;
 
@@ -11760,10 +11760,10 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 
-	if (!perfmon_capable())
+	if (!bpf_token_capable(prog->aux->token, CAP_PERFMON))
 		return NULL;
 
 	return func;
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 39dcccf0f174..c7bbd8f3c708 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -191,7 +191,7 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
index e502ec00b2fe..1969facac91c 100644
--- a/net/netfilter/nf_bpf_link.c
+++ b/net/netfilter/nf_bpf_link.c
@@ -314,7 +314,7 @@ static bool nf_is_valid_access(int off, int size, enum bpf_access_type type,
 static const struct bpf_func_proto *
 bpf_nf_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);
 }
 
 const struct bpf_verifier_ops netfilter_verifier_ops = {
-- 
cgit v1.2.3


From 8062fb12de99b2da33754c6a3be1bfc30d9a35f4 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:20 -0800
Subject: bpf: consistently use BPF token throughout BPF verifier logic

Remove remaining direct queries to perfmon_capable() and bpf_capable()
in BPF verifier logic and instead use BPF token (if available) to make
decisions about privileges.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-9-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h    | 16 ++++++++--------
 include/linux/filter.h |  2 +-
 kernel/bpf/arraymap.c  |  2 +-
 kernel/bpf/core.c      |  2 +-
 kernel/bpf/verifier.c  | 13 ++++++-------
 net/core/filter.c      |  4 ++--
 6 files changed, 19 insertions(+), 20 deletions(-)

(limited to 'net')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2a3ab4f3dd8c..435abad3cc61 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2200,24 +2200,24 @@ extern int sysctl_unprivileged_bpf_disabled;
 
 bool bpf_token_capable(const struct bpf_token *token, int cap);
 
-static inline bool bpf_allow_ptr_leaks(void)
+static inline bool bpf_allow_ptr_leaks(const struct bpf_token *token)
 {
-	return perfmon_capable();
+	return bpf_token_capable(token, CAP_PERFMON);
 }
 
-static inline bool bpf_allow_uninit_stack(void)
+static inline bool bpf_allow_uninit_stack(const struct bpf_token *token)
 {
-	return perfmon_capable();
+	return bpf_token_capable(token, CAP_PERFMON);
 }
 
-static inline bool bpf_bypass_spec_v1(void)
+static inline bool bpf_bypass_spec_v1(const struct bpf_token *token)
 {
-	return cpu_mitigations_off() || perfmon_capable();
+	return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON);
 }
 
-static inline bool bpf_bypass_spec_v4(void)
+static inline bool bpf_bypass_spec_v4(const struct bpf_token *token)
 {
-	return cpu_mitigations_off() || perfmon_capable();
+	return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON);
 }
 
 int bpf_map_new_fd(struct bpf_map *map, int flags);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index a4953fafc8cb..14354605ad26 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1139,7 +1139,7 @@ static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog)
 		return false;
 	if (!bpf_jit_harden)
 		return false;
-	if (bpf_jit_harden == 1 && bpf_capable())
+	if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF))
 		return false;
 
 	return true;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 4a4a67956e21..8d365bda9a8b 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;
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 47085839af8d..ced511f44174 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -675,7 +675,7 @@ 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);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e5ce530641ba..45e85fb76d82 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -20597,7 +20597,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	env->prog = *prog;
 	env->ops = bpf_verifier_ops[env->prog->type];
 	env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel);
-	is_priv = bpf_capable();
+
+	env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token);
+	env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token);
+	env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token);
+	env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token);
+	env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF);
 
 	bpf_get_btf_vmlinux();
 
@@ -20629,12 +20634,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
 		env->strict_alignment = false;
 
-	env->allow_ptr_leaks = bpf_allow_ptr_leaks();
-	env->allow_uninit_stack = bpf_allow_uninit_stack();
-	env->bypass_spec_v1 = bpf_bypass_spec_v1();
-	env->bypass_spec_v4 = bpf_bypass_spec_v4();
-	env->bpf_capable = bpf_capable();
-
 	if (is_priv)
 		env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
 	env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS;
diff --git a/net/core/filter.c b/net/core/filter.c
index 0bf2a03d8203..adcfc2c25754 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -8559,7 +8559,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 		return false;
 	case bpf_ctx_range(struct __sk_buff, data):
 	case bpf_ctx_range(struct __sk_buff, data_end):
-		if (!bpf_capable())
+		if (!bpf_token_capable(prog->aux->token, CAP_BPF))
 			return false;
 		break;
 	}
@@ -8571,7 +8571,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
 			break;
 		case bpf_ctx_range(struct __sk_buff, tstamp):
-			if (!bpf_capable())
+			if (!bpf_token_capable(prog->aux->token, CAP_BPF))
 				return false;
 			break;
 		default:
-- 
cgit v1.2.3


From 82583daa2efc2e336962b231a46bad03a280b3e0 Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Wed, 6 Dec 2023 14:40:50 -0800
Subject: bpf: Add helpers for trampoline image management

As BPF trampoline of different archs moves from bpf_jit_[alloc|free]_exec()
to bpf_prog_pack_[alloc|free](), we need to use different _alloc, _free for
different archs during the transition. Add the following helpers for this
transition:

void *arch_alloc_bpf_trampoline(unsigned int size);
void arch_free_bpf_trampoline(void *image, unsigned int size);
void arch_protect_bpf_trampoline(void *image, unsigned int size);
void arch_unprotect_bpf_trampoline(void *image, unsigned int size);

The fallback version of these helpers require size <= PAGE_SIZE, but they
are only called with size == PAGE_SIZE. They will be called with size <
PAGE_SIZE when arch_bpf_trampoline_size() helper is introduced later.

Signed-off-by: Song Liu <song@kernel.org>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com>  # on s390x
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20231206224054.492250-4-song@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h            |  5 +++++
 kernel/bpf/bpf_struct_ops.c    | 12 +++++------
 kernel/bpf/trampoline.c        | 46 +++++++++++++++++++++++++++++++++++-------
 net/bpf/bpf_dummy_struct_ops.c |  7 +++----
 4 files changed, 52 insertions(+), 18 deletions(-)

(limited to 'net')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 17eb6d905204..b7fca151cf1b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1102,6 +1102,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 				const struct btf_func_model *m, u32 flags,
 				struct bpf_tramp_links *tlinks,
 				void *func_addr);
+void *arch_alloc_bpf_trampoline(unsigned int size);
+void arch_free_bpf_trampoline(void *image, unsigned int size);
+void arch_protect_bpf_trampoline(void *image, unsigned int size);
+void arch_unprotect_bpf_trampoline(void *image, unsigned int size);
+
 u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
 					     struct bpf_tramp_run_ctx *run_ctx);
 void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start,
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index db6176fb64dc..e9e95879bce2 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -515,7 +515,7 @@ 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 +524,7 @@ 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 +547,7 @@ 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 +615,7 @@ 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 +690,7 @@ 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 +710,6 @@ 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/trampoline.c b/kernel/bpf/trampoline.c
index e114a1c7961e..affbcbf7e76e 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -254,7 +254,7 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_a
 static void bpf_tramp_image_free(struct bpf_tramp_image *im)
 {
 	bpf_image_ksym_del(&im->ksym);
-	bpf_jit_free_exec(im->image);
+	arch_free_bpf_trampoline(im->image, PAGE_SIZE);
 	bpf_jit_uncharge_modmem(PAGE_SIZE);
 	percpu_ref_exit(&im->pcref);
 	kfree_rcu(im, rcu);
@@ -365,10 +365,9 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
 		goto out_free_im;
 
 	err = -ENOMEM;
-	im->image = image = bpf_jit_alloc_exec(PAGE_SIZE);
+	im->image = image = arch_alloc_bpf_trampoline(PAGE_SIZE);
 	if (!image)
 		goto out_uncharge;
-	set_vm_flush_reset_perms(image);
 
 	err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL);
 	if (err)
@@ -381,7 +380,7 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
 	return im;
 
 out_free_image:
-	bpf_jit_free_exec(im->image);
+	arch_free_bpf_trampoline(im->image, PAGE_SIZE);
 out_uncharge:
 	bpf_jit_uncharge_modmem(PAGE_SIZE);
 out_free_im:
@@ -444,7 +443,7 @@ again:
 	if (err < 0)
 		goto out_free;
 
-	set_memory_rox((long)im->image, 1);
+	arch_protect_bpf_trampoline(im->image, PAGE_SIZE);
 
 	WARN_ON(tr->cur_image && total == 0);
 	if (tr->cur_image)
@@ -465,8 +464,7 @@ again:
 		tr->fops->trampoline = 0;
 
 		/* reset im->image memory attr for arch_prepare_bpf_trampoline */
-		set_memory_nx((long)im->image, 1);
-		set_memory_rw((long)im->image, 1);
+		arch_unprotect_bpf_trampoline(im->image, PAGE_SIZE);
 		goto again;
 	}
 #endif
@@ -1040,6 +1038,40 @@ arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image
 	return -ENOTSUPP;
 }
 
+void * __weak arch_alloc_bpf_trampoline(unsigned int size)
+{
+	void *image;
+
+	if (WARN_ON_ONCE(size > PAGE_SIZE))
+		return NULL;
+	image = bpf_jit_alloc_exec(PAGE_SIZE);
+	if (image)
+		set_vm_flush_reset_perms(image);
+	return image;
+}
+
+void __weak arch_free_bpf_trampoline(void *image, unsigned int size)
+{
+	WARN_ON_ONCE(size > PAGE_SIZE);
+	/* bpf_jit_free_exec doesn't need "size", but
+	 * bpf_prog_pack_free() needs it.
+	 */
+	bpf_jit_free_exec(image);
+}
+
+void __weak arch_protect_bpf_trampoline(void *image, unsigned int size)
+{
+	WARN_ON_ONCE(size > PAGE_SIZE);
+	set_memory_rox((long)image, 1);
+}
+
+void __weak arch_unprotect_bpf_trampoline(void *image, unsigned int size)
+{
+	WARN_ON_ONCE(size > PAGE_SIZE);
+	set_memory_nx((long)image, 1);
+	set_memory_rw((long)image, 1);
+}
+
 static int __init init_trampolines(void)
 {
 	int i;
diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index 5918d1b32e19..2748f9d77b18 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -101,12 +101,11 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 		goto out;
 	}
 
-	image = bpf_jit_alloc_exec(PAGE_SIZE);
+	image = arch_alloc_bpf_trampoline(PAGE_SIZE);
 	if (!image) {
 		err = -ENOMEM;
 		goto out;
 	}
-	set_vm_flush_reset_perms(image);
 
 	link = kzalloc(sizeof(*link), GFP_USER);
 	if (!link) {
@@ -124,7 +123,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 	if (err < 0)
 		goto out;
 
-	set_memory_rox((long)image, 1);
+	arch_protect_bpf_trampoline(image, PAGE_SIZE);
 	prog_ret = dummy_ops_call_op(image, args);
 
 	err = dummy_ops_copy_args(args);
@@ -134,7 +133,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 		err = -EFAULT;
 out:
 	kfree(args);
-	bpf_jit_free_exec(image);
+	arch_free_bpf_trampoline(image, PAGE_SIZE);
 	if (link)
 		bpf_link_put(&link->link);
 	kfree(tlinks);
-- 
cgit v1.2.3


From b4e352ff1169ebce930c734630f9587b1677d163 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 5 Dec 2023 22:08:36 +0100
Subject: xsk: add functions to fill control buffer

Commit 94ecc5ca4dbf ("xsk: Add cb area to struct xdp_buff_xsk") has added
a buffer for custom data to xdp_buff_xsk. Particularly, this memory is used
for data, consumed by XDP hints kfuncs. It does not always change on
a per-packet basis and some parts can be set for example, at the same time
as RX queue info.

Add functions to fill all cbs in xsk_buff_pool with the same metadata.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20231205210847.28460-8-larysa.zaremba@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/xdp_sock_drv.h  | 17 +++++++++++++++++
 include/net/xsk_buff_pool.h |  2 ++
 net/xdp/xsk_buff_pool.c     | 12 ++++++++++++
 3 files changed, 31 insertions(+)

(limited to 'net')

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 81e02de3f453..b62bb8525a5f 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -14,6 +14,12 @@
 
 #ifdef CONFIG_XDP_SOCKETS
 
+struct xsk_cb_desc {
+	void *src;
+	u8 off;
+	u8 bytes;
+};
+
 void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries);
 bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc);
 u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max);
@@ -47,6 +53,12 @@ static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 	xp_set_rxq_info(pool, rxq);
 }
 
+static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
+				    struct xsk_cb_desc *desc)
+{
+	xp_fill_cb(pool, desc);
+}
+
 static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
@@ -274,6 +286,11 @@ static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 {
 }
 
+static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
+				    struct xsk_cb_desc *desc)
+{
+}
+
 static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
 {
 	return 0;
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 8d48d37ab7c0..99dd7376df6a 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -12,6 +12,7 @@
 
 struct xsk_buff_pool;
 struct xdp_rxq_info;
+struct xsk_cb_desc;
 struct xsk_queue;
 struct xdp_desc;
 struct xdp_umem;
@@ -135,6 +136,7 @@ static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_p
 
 /* AF_XDP ZC drivers, via xdp_sock_buff.h */
 void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq);
+void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc);
 int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 	       unsigned long attrs, struct page **pages, u32 nr_pages);
 void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs);
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 4f6f538a5462..28711cc44ced 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -125,6 +125,18 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
 }
 EXPORT_SYMBOL(xp_set_rxq_info);
 
+void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc)
+{
+	u32 i;
+
+	for (i = 0; i < pool->heads_cnt; i++) {
+		struct xdp_buff_xsk *xskb = &pool->heads[i];
+
+		memcpy(xskb->cb + desc->off, desc->src, desc->bytes);
+	}
+}
+EXPORT_SYMBOL(xp_fill_cb);
+
 static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
 {
 	struct netdev_bpf bpf;
-- 
cgit v1.2.3


From e6795330f88b4f643c649a02662d47b779340535 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Tue, 5 Dec 2023 22:08:38 +0100
Subject: xdp: Add VLAN tag hint

Implement functionality that enables drivers to expose VLAN tag
to XDP code.

VLAN tag is represented by 2 variables:
- protocol ID, which is passed to bpf code in BE
- VLAN TCI, in host byte order

Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/20231205210847.28460-10-larysa.zaremba@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml      |  4 ++++
 Documentation/networking/xdp-rx-metadata.rst |  8 ++++++-
 include/net/xdp.h                            |  6 +++++
 include/uapi/linux/netdev.h                  |  3 +++
 net/core/xdp.c                               | 33 ++++++++++++++++++++++++++++
 tools/include/uapi/linux/netdev.h            |  3 +++
 tools/net/ynl/generated/netdev-user.c        |  1 +
 7 files changed, 57 insertions(+), 1 deletion(-)

(limited to 'net')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index eef6358ec587..aeec090e1387 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -54,6 +54,10 @@ definitions:
         name: hash
         doc:
           Device is capable of exposing receive packet hash via bpf_xdp_metadata_rx_hash().
+      -
+        name: vlan-tag
+        doc:
+          Device is capable of exposing receive packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
   -
     type: flags
     name: xsk-flags
diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst
index e3e9420fd817..a6e0ece18be5 100644
--- a/Documentation/networking/xdp-rx-metadata.rst
+++ b/Documentation/networking/xdp-rx-metadata.rst
@@ -20,7 +20,13 @@ Currently, the following kfuncs are supported. In the future, as more
 metadata is supported, this set will grow:
 
 .. kernel-doc:: net/core/xdp.c
-   :identifiers: bpf_xdp_metadata_rx_timestamp bpf_xdp_metadata_rx_hash
+   :identifiers: bpf_xdp_metadata_rx_timestamp
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_hash
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_vlan_tag
 
 An XDP program can use these kfuncs to read the metadata into stack
 variables for its own consumption. Or, to pass the metadata on to other
diff --git a/include/net/xdp.h b/include/net/xdp.h
index b7d6fe61381f..8cd04a74dba5 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -404,6 +404,10 @@ void xdp_attachment_setup(struct xdp_attachment_info *info,
 			   NETDEV_XDP_RX_METADATA_HASH, \
 			   bpf_xdp_metadata_rx_hash, \
 			   xmo_rx_hash) \
+	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_VLAN_TAG, \
+			   NETDEV_XDP_RX_METADATA_VLAN_TAG, \
+			   bpf_xdp_metadata_rx_vlan_tag, \
+			   xmo_rx_vlan_tag) \
 
 enum xdp_rx_metadata {
 #define XDP_METADATA_KFUNC(name, _, __, ___) name,
@@ -465,6 +469,8 @@ struct xdp_metadata_ops {
 	int	(*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp);
 	int	(*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash,
 			       enum xdp_rss_hash_type *rss_type);
+	int	(*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto,
+				   u16 *vlan_tci);
 };
 
 #ifdef CONFIG_NET
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 6244c0164976..966638b08ccf 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -44,10 +44,13 @@ enum netdev_xdp_act {
  *   timestamp via bpf_xdp_metadata_rx_timestamp().
  * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
  *   hash via bpf_xdp_metadata_rx_hash().
+ * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
+ *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
  */
 enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
 	NETDEV_XDP_RX_METADATA_HASH = 2,
+	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
 };
 
 /**
diff --git a/net/core/xdp.c b/net/core/xdp.c
index b6f1d6dab3f2..4869c1c2d8f3 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -736,6 +736,39 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return -EOPNOTSUPP;
 }
 
+/**
+ * bpf_xdp_metadata_rx_vlan_tag - Get XDP packet outermost VLAN tag
+ * @ctx: XDP context pointer.
+ * @vlan_proto: Destination pointer for VLAN Tag protocol identifier (TPID).
+ * @vlan_tci: Destination pointer for VLAN TCI (VID + DEI + PCP)
+ *
+ * In case of success, ``vlan_proto`` contains *Tag protocol identifier (TPID)*,
+ * usually ``ETH_P_8021Q`` or ``ETH_P_8021AD``, but some networks can use
+ * custom TPIDs. ``vlan_proto`` is stored in **network byte order (BE)**
+ * and should be used as follows:
+ * ``if (vlan_proto == bpf_htons(ETH_P_8021Q)) do_something();``
+ *
+ * ``vlan_tci`` contains the remaining 16 bits of a VLAN tag.
+ * Driver is expected to provide those in **host byte order (usually LE)**,
+ * so the bpf program should not perform byte conversion.
+ * According to 802.1Q standard, *VLAN TCI (Tag control information)*
+ * is a bit field that contains:
+ * *VLAN identifier (VID)* that can be read with ``vlan_tci & 0xfff``,
+ * *Drop eligible indicator (DEI)* - 1 bit,
+ * *Priority code point (PCP)* - 3 bits.
+ * For detailed meaning of DEI and PCP, please refer to other sources.
+ *
+ * Return:
+ * * Returns 0 on success or ``-errno`` on error.
+ * * ``-EOPNOTSUPP`` : device driver doesn't implement kfunc
+ * * ``-ENODATA``    : VLAN tag was not stripped or is not available
+ */
+__bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
+					     __be16 *vlan_proto, u16 *vlan_tci)
+{
+	return -EOPNOTSUPP;
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_SET8_START(xdp_metadata_kfunc_ids)
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 6244c0164976..966638b08ccf 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -44,10 +44,13 @@ enum netdev_xdp_act {
  *   timestamp via bpf_xdp_metadata_rx_timestamp().
  * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
  *   hash via bpf_xdp_metadata_rx_hash().
+ * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
+ *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
  */
 enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
 	NETDEV_XDP_RX_METADATA_HASH = 2,
+	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
 };
 
 /**
diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c
index 3b9dee94d4ce..e3fe748086bd 100644
--- a/tools/net/ynl/generated/netdev-user.c
+++ b/tools/net/ynl/generated/netdev-user.c
@@ -53,6 +53,7 @@ const char *netdev_xdp_act_str(enum netdev_xdp_act value)
 static const char * const netdev_xdp_rx_metadata_strmap[] = {
 	[0] = "timestamp",
 	[1] = "hash",
+	[2] = "vlan-tag",
 };
 
 const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value)
-- 
cgit v1.2.3


From 8f0ec8c681755f523cf842bfe350ea40609b83a9 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Thu, 14 Dec 2023 15:49:02 -0700
Subject: bpf: xfrm: Add bpf_xdp_get_xfrm_state() kfunc

This commit adds an unstable kfunc helper to access internal xfrm_state
associated with an SA. This is intended to be used for the upcoming
IPsec pcpu work to assign special pcpu SAs to a particular CPU. In other
words: for custom software RSS.

That being said, the function that this kfunc wraps is fairly generic
and used for a lot of xfrm tasks. I'm sure people will find uses
elsewhere over time.

This commit also adds a corresponding bpf_xdp_xfrm_state_release() kfunc
to release the refcnt acquired by bpf_xdp_get_xfrm_state(). The verifier
will require that all acquired xfrm_state's are released.

Co-developed-by: Antony Antony <antony.antony@secunet.com>
Signed-off-by: Antony Antony <antony.antony@secunet.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/a29699c42f5fad456b875c98dd11c6afc3ffb707.1702593901.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/xfrm.h        |   9 ++++
 net/xfrm/Makefile         |   1 +
 net/xfrm/xfrm_policy.c    |   2 +
 net/xfrm/xfrm_state_bpf.c | 134 ++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 146 insertions(+)
 create mode 100644 net/xfrm/xfrm_state_bpf.c

(limited to 'net')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index c9bb0f892f55..1d107241b901 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -2190,4 +2190,13 @@ static inline int register_xfrm_interface_bpf(void)
 
 #endif
 
+#if IS_ENABLED(CONFIG_DEBUG_INFO_BTF)
+int register_xfrm_state_bpf(void);
+#else
+static inline int register_xfrm_state_bpf(void)
+{
+	return 0;
+}
+#endif
+
 #endif	/* _NET_XFRM_H */
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index cd47f88921f5..547cec77ba03 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -21,3 +21,4 @@ obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o
 obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
 obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
 obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o
+obj-$(CONFIG_DEBUG_INFO_BTF) += xfrm_state_bpf.o
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index c13dc3ef7910..1b7e75159727 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4218,6 +4218,8 @@ void __init xfrm_init(void)
 #ifdef CONFIG_XFRM_ESPINTCP
 	espintcp_init();
 #endif
+
+	register_xfrm_state_bpf();
 }
 
 #ifdef CONFIG_AUDITSYSCALL
diff --git a/net/xfrm/xfrm_state_bpf.c b/net/xfrm/xfrm_state_bpf.c
new file mode 100644
index 000000000000..9e20d4a377f7
--- /dev/null
+++ b/net/xfrm/xfrm_state_bpf.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Unstable XFRM state BPF helpers.
+ *
+ * Note that it is allowed to break compatibility for these functions since the
+ * interface they are exposed through to BPF programs is explicitly unstable.
+ */
+
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
+#include <net/xdp.h>
+#include <net/xfrm.h>
+
+/* bpf_xfrm_state_opts - Options for XFRM state lookup helpers
+ *
+ * Members:
+ * @error      - Out parameter, set for any errors encountered
+ *		 Values:
+ *		   -EINVAL - netns_id is less than -1
+ *		   -EINVAL - opts__sz isn't BPF_XFRM_STATE_OPTS_SZ
+ *		   -ENONET - No network namespace found for netns_id
+ *		   -ENOENT - No xfrm_state found
+ * @netns_id	- Specify the network namespace for lookup
+ *		 Values:
+ *		   BPF_F_CURRENT_NETNS (-1)
+ *		     Use namespace associated with ctx
+ *		   [0, S32_MAX]
+ *		     Network Namespace ID
+ * @mark	- XFRM mark to match on
+ * @daddr	- Destination address to match on
+ * @spi		- Security parameter index to match on
+ * @proto	- IP protocol to match on (eg. IPPROTO_ESP)
+ * @family	- Protocol family to match on (AF_INET/AF_INET6)
+ */
+struct bpf_xfrm_state_opts {
+	s32 error;
+	s32 netns_id;
+	u32 mark;
+	xfrm_address_t daddr;
+	__be32 spi;
+	u8 proto;
+	u16 family;
+};
+
+enum {
+	BPF_XFRM_STATE_OPTS_SZ = sizeof(struct bpf_xfrm_state_opts),
+};
+
+__bpf_kfunc_start_defs();
+
+/* bpf_xdp_get_xfrm_state - Get XFRM state
+ *
+ * A `struct xfrm_state *`, if found, must be released with a corresponding
+ * bpf_xdp_xfrm_state_release.
+ *
+ * Parameters:
+ * @ctx	- Pointer to ctx (xdp_md) in XDP program
+ *		    Cannot be NULL
+ * @opts	- Options for lookup (documented above)
+ *		    Cannot be NULL
+ * @opts__sz	- Length of the bpf_xfrm_state_opts structure
+ *		    Must be BPF_XFRM_STATE_OPTS_SZ
+ */
+__bpf_kfunc struct xfrm_state *
+bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts, u32 opts__sz)
+{
+	struct xdp_buff *xdp = (struct xdp_buff *)ctx;
+	struct net *net = dev_net(xdp->rxq->dev);
+	struct xfrm_state *x;
+
+	if (!opts || opts__sz < sizeof(opts->error))
+		return NULL;
+
+	if (opts__sz != BPF_XFRM_STATE_OPTS_SZ) {
+		opts->error = -EINVAL;
+		return NULL;
+	}
+
+	if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) {
+		opts->error = -EINVAL;
+		return NULL;
+	}
+
+	if (opts->netns_id >= 0) {
+		net = get_net_ns_by_id(net, opts->netns_id);
+		if (unlikely(!net)) {
+			opts->error = -ENONET;
+			return NULL;
+		}
+	}
+
+	x = xfrm_state_lookup(net, opts->mark, &opts->daddr, opts->spi,
+			      opts->proto, opts->family);
+
+	if (opts->netns_id >= 0)
+		put_net(net);
+	if (!x)
+		opts->error = -ENOENT;
+
+	return x;
+}
+
+/* bpf_xdp_xfrm_state_release - Release acquired xfrm_state object
+ *
+ * This must be invoked for referenced PTR_TO_BTF_ID, and the verifier rejects
+ * the program if any references remain in the program in all of the explored
+ * states.
+ *
+ * Parameters:
+ * @x		- Pointer to referenced xfrm_state object, obtained using
+ *		  bpf_xdp_get_xfrm_state.
+ */
+__bpf_kfunc void bpf_xdp_xfrm_state_release(struct xfrm_state *x)
+{
+	xfrm_state_put(x);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_SET8_START(xfrm_state_kfunc_set)
+BTF_ID_FLAGS(func, bpf_xdp_get_xfrm_state, KF_RET_NULL | KF_ACQUIRE)
+BTF_ID_FLAGS(func, bpf_xdp_xfrm_state_release, KF_RELEASE)
+BTF_SET8_END(xfrm_state_kfunc_set)
+
+static const struct btf_kfunc_id_set xfrm_state_xdp_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &xfrm_state_kfunc_set,
+};
+
+int __init register_xfrm_state_bpf(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP,
+					 &xfrm_state_xdp_kfunc_set);
+}
-- 
cgit v1.2.3


From 2cd3e3772e41377f32d6eea643e0590774e9187c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 15 Dec 2023 10:12:20 +0100
Subject: x86/cfi,bpf: Fix bpf_struct_ops CFI

BPF struct_ops uses __arch_prepare_bpf_trampoline() to write
trampolines for indirect function calls. These tramplines much have
matching CFI.

In order to obtain the correct CFI hash for the various methods, add a
matching structure that contains stub functions, the compiler will
generate correct CFI which we can pilfer for the trampolines.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231215092707.566977112@infradead.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/include/asm/cfi.h     |  6 ++++
 arch/x86/kernel/alternative.c  | 22 ++++++++++++++
 arch/x86/net/bpf_jit_comp.c    | 66 ++++++++++++++++++++++++++--------------
 include/linux/bpf.h            | 13 ++++++++
 kernel/bpf/bpf_struct_ops.c    | 16 +++++-----
 net/bpf/bpf_dummy_struct_ops.c | 31 ++++++++++++++++++-
 net/ipv4/bpf_tcp_ca.c          | 69 ++++++++++++++++++++++++++++++++++++++++++
 7 files changed, 191 insertions(+), 32 deletions(-)

(limited to 'net')

diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 8779abd217b7..1a50b2cd4713 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -123,6 +123,8 @@ static inline int cfi_get_offset(void)
 }
 #define cfi_get_offset cfi_get_offset
 
+extern u32 cfi_get_func_hash(void *func);
+
 #else
 static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 {
@@ -130,6 +132,10 @@ static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 }
 #define cfi_bpf_hash 0U
 #define cfi_bpf_subprog_hash 0U
+static inline u32 cfi_get_func_hash(void *func)
+{
+	return 0;
+}
 #endif /* CONFIG_CFI_CLANG */
 
 #endif /* _ASM_X86_CFI_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index cb393efd5ccd..49c2a62ba5e4 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -883,6 +883,28 @@ asm (
 "	.size	cfi_bpf_subprog_hash, 4				\n"
 "	.popsection						\n"
 );
+
+u32 cfi_get_func_hash(void *func)
+{
+	u32 hash;
+
+	func -= cfi_get_offset();
+	switch (cfi_mode) {
+	case CFI_FINEIBT:
+		func += 7;
+		break;
+	case CFI_KCFI:
+		func += 1;
+		break;
+	default:
+		return 0;
+	}
+
+	if (get_kernel_nofault(hash, func))
+		return 0;
+
+	return hash;
+}
 #endif
 
 #ifdef CONFIG_FINEIBT
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 43b8c08fdf8d..c89a4abdd726 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -312,9 +312,8 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
  * in arch/x86/kernel/alternative.c
  */
 
-static void emit_fineibt(u8 **pprog, bool is_subprog)
+static void emit_fineibt(u8 **pprog, u32 hash)
 {
-	u32 hash = is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash;
 	u8 *prog = *pprog;
 
 	EMIT_ENDBR();
@@ -327,9 +326,8 @@ static void emit_fineibt(u8 **pprog, bool is_subprog)
 	*pprog = prog;
 }
 
-static void emit_kcfi(u8 **pprog, bool is_subprog)
+static void emit_kcfi(u8 **pprog, u32 hash)
 {
-	u32 hash = is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash;
 	u8 *prog = *pprog;
 
 	EMIT1_off32(0xb8, hash);			/* movl $hash, %eax	*/
@@ -351,17 +349,17 @@ static void emit_kcfi(u8 **pprog, bool is_subprog)
 	*pprog = prog;
 }
 
-static void emit_cfi(u8 **pprog, bool is_subprog)
+static void emit_cfi(u8 **pprog, u32 hash)
 {
 	u8 *prog = *pprog;
 
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
-		emit_fineibt(&prog, is_subprog);
+		emit_fineibt(&prog, hash);
 		break;
 
 	case CFI_KCFI:
-		emit_kcfi(&prog, is_subprog);
+		emit_kcfi(&prog, hash);
 		break;
 
 	default:
@@ -383,7 +381,7 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
 {
 	u8 *prog = *pprog;
 
-	emit_cfi(&prog, is_subprog);
+	emit_cfi(&prog, is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash);
 	/* BPF trampoline can be made to work without these nops,
 	 * but let's waste 5 bytes for now and optimize later
 	 */
@@ -2510,10 +2508,19 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	u8 *prog;
 	bool save_ret;
 
+	/*
+	 * F_INDIRECT is only compatible with F_RET_FENTRY_RET, it is
+	 * explicitly incompatible with F_CALL_ORIG | F_SKIP_FRAME | F_IP_ARG
+	 * because @func_addr.
+	 */
+	WARN_ON_ONCE((flags & BPF_TRAMP_F_INDIRECT) &&
+		     (flags & ~(BPF_TRAMP_F_INDIRECT | BPF_TRAMP_F_RET_FENTRY_RET)));
+
 	/* extra registers for struct arguments */
-	for (i = 0; i < m->nr_args; i++)
+	for (i = 0; i < m->nr_args; i++) {
 		if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG)
 			nr_regs += (m->arg_size[i] + 7) / 8 - 1;
+	}
 
 	/* x86-64 supports up to MAX_BPF_FUNC_ARGS arguments. 1-6
 	 * are passed through regs, the remains are through stack.
@@ -2596,20 +2603,27 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 
 	prog = rw_image;
 
-	EMIT_ENDBR();
-	/*
-	 * This is the direct-call trampoline, as such it needs accounting
-	 * for the __fentry__ call.
-	 */
-	x86_call_depth_emit_accounting(&prog, NULL);
+	if (flags & BPF_TRAMP_F_INDIRECT) {
+		/*
+		 * Indirect call for bpf_struct_ops
+		 */
+		emit_cfi(&prog, cfi_get_func_hash(func_addr));
+	} else {
+		/*
+		 * Direct-call fentry stub, as such it needs accounting for the
+		 * __fentry__ call.
+		 */
+		x86_call_depth_emit_accounting(&prog, NULL);
+	}
 	EMIT1(0x55);		 /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
-	if (!is_imm8(stack_size))
+	if (!is_imm8(stack_size)) {
 		/* sub rsp, stack_size */
 		EMIT3_off32(0x48, 0x81, 0xEC, stack_size);
-	else
+	} else {
 		/* sub rsp, stack_size */
 		EMIT4(0x48, 0x83, 0xEC, stack_size);
+	}
 	if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
 		EMIT1(0x50);		/* push rax */
 	/* mov QWORD PTR [rbp - rbx_off], rbx */
@@ -2643,10 +2657,11 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		}
 	}
 
-	if (fentry->nr_links)
+	if (fentry->nr_links) {
 		if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off,
 			       flags & BPF_TRAMP_F_RET_FENTRY_RET, image, rw_image))
 			return -EINVAL;
+	}
 
 	if (fmod_ret->nr_links) {
 		branches = kcalloc(fmod_ret->nr_links, sizeof(u8 *),
@@ -2665,11 +2680,12 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		restore_regs(m, &prog, regs_off);
 		save_args(m, &prog, arg_stack_off, true);
 
-		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) {
 			/* Before calling the original function, restore the
 			 * tail_call_cnt from stack to rax.
 			 */
 			RESTORE_TAIL_CALL_CNT(stack_size);
+		}
 
 		if (flags & BPF_TRAMP_F_ORIG_STACK) {
 			emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, 8);
@@ -2698,17 +2714,19 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		/* Update the branches saved in invoke_bpf_mod_ret with the
 		 * aligned address of do_fexit.
 		 */
-		for (i = 0; i < fmod_ret->nr_links; i++)
+		for (i = 0; i < fmod_ret->nr_links; i++) {
 			emit_cond_near_jump(&branches[i], image + (prog - (u8 *)rw_image),
 					    image + (branches[i] - (u8 *)rw_image), X86_JNE);
+		}
 	}
 
-	if (fexit->nr_links)
+	if (fexit->nr_links) {
 		if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off,
 			       false, image, rw_image)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
+	}
 
 	if (flags & BPF_TRAMP_F_RESTORE_REGS)
 		restore_regs(m, &prog, regs_off);
@@ -2725,11 +2743,12 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 			ret = -EINVAL;
 			goto cleanup;
 		}
-	} else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+	} else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) {
 		/* Before running the original function, restore the
 		 * tail_call_cnt from stack to rax.
 		 */
 		RESTORE_TAIL_CALL_CNT(stack_size);
+	}
 
 	/* restore return value of orig_call or fentry prog back into RAX */
 	if (save_ret)
@@ -2737,9 +2756,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 
 	emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, -rbx_off);
 	EMIT1(0xC9); /* leave */
-	if (flags & BPF_TRAMP_F_SKIP_FRAME)
+	if (flags & BPF_TRAMP_F_SKIP_FRAME) {
 		/* skip our return address and return to parent */
 		EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */
+	}
 	emit_return(&prog, image + (prog - (u8 *)rw_image));
 	/* Make sure the trampoline generation logic doesn't overflow */
 	if (WARN_ON_ONCE(prog > (u8 *)rw_image_end - BPF_INSN_SAFETY)) {
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 9d84c376851a..db46b3359bf5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1060,6 +1060,17 @@ struct btf_func_model {
  */
 #define BPF_TRAMP_F_TAIL_CALL_CTX	BIT(7)
 
+/*
+ * Indicate the trampoline should be suitable to receive indirect calls;
+ * without this indirectly calling the generated code can result in #UD/#CP,
+ * depending on the CFI options.
+ *
+ * Used by bpf_struct_ops.
+ *
+ * Incompatible with FENTRY usage, overloads @func_addr argument.
+ */
+#define BPF_TRAMP_F_INDIRECT		BIT(8)
+
 /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
  * bytes on x86.
  */
@@ -1697,6 +1708,7 @@ struct bpf_struct_ops {
 	struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS];
 	u32 type_id;
 	u32 value_id;
+	void *cfi_stubs;
 };
 
 #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
@@ -1710,6 +1722,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
 int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 				      struct bpf_tramp_link *link,
 				      const struct btf_func_model *model,
+				      void *stub_func,
 				      void *image, void *image_end);
 static inline bool bpf_try_module_get(const void *data, struct module *owner)
 {
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 4d53c53fc5aa..02068bd0e4d9 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -352,17 +352,16 @@ 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)
@@ -370,7 +369,7 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 	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,
@@ -504,11 +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 */
diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index 2748f9d77b18..8906f7bdf4a9 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -12,6 +12,11 @@ extern struct bpf_struct_ops bpf_bpf_dummy_ops;
 /* A common type for test_N with return value in bpf_dummy_ops */
 typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...);
 
+static int dummy_ops_test_ret_function(struct bpf_dummy_ops_state *state, ...)
+{
+	return 0;
+}
+
 struct bpf_dummy_ops_test_args {
 	u64 args[MAX_BPF_FUNC_ARGS];
 	struct bpf_dummy_ops_state state;
@@ -62,7 +67,7 @@ static int dummy_ops_copy_args(struct bpf_dummy_ops_test_args *args)
 
 static int dummy_ops_call_op(void *image, struct bpf_dummy_ops_test_args *args)
 {
-	dummy_ops_test_ret_fn test = (void *)image;
+	dummy_ops_test_ret_fn test = (void *)image + cfi_get_offset();
 	struct bpf_dummy_ops_state *state = NULL;
 
 	/* state needs to be NULL if args[0] is 0 */
@@ -119,6 +124,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 	op_idx = prog->expected_attach_type;
 	err = bpf_struct_ops_prepare_trampoline(tlinks, link,
 						&st_ops->func_models[op_idx],
+						&dummy_ops_test_ret_function,
 						image, image + PAGE_SIZE);
 	if (err < 0)
 		goto out;
@@ -219,6 +225,28 @@ static void bpf_dummy_unreg(void *kdata)
 {
 }
 
+static int bpf_dummy_test_1(struct bpf_dummy_ops_state *cb)
+{
+	return 0;
+}
+
+static int bpf_dummy_test_2(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2,
+			    char a3, unsigned long a4)
+{
+	return 0;
+}
+
+static int bpf_dummy_test_sleepable(struct bpf_dummy_ops_state *cb)
+{
+	return 0;
+}
+
+static struct bpf_dummy_ops __bpf_bpf_dummy_ops = {
+	.test_1 = bpf_dummy_test_1,
+	.test_2 = bpf_dummy_test_2,
+	.test_sleepable = bpf_dummy_test_sleepable,
+};
+
 struct bpf_struct_ops bpf_bpf_dummy_ops = {
 	.verifier_ops = &bpf_dummy_verifier_ops,
 	.init = bpf_dummy_init,
@@ -227,4 +255,5 @@ struct bpf_struct_ops bpf_bpf_dummy_ops = {
 	.reg = bpf_dummy_reg,
 	.unreg = bpf_dummy_unreg,
 	.name = "bpf_dummy_ops",
+	.cfi_stubs = &__bpf_bpf_dummy_ops,
 };
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index c7bbd8f3c708..634cfafa583d 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -271,6 +271,74 @@ static int bpf_tcp_ca_validate(void *kdata)
 	return tcp_validate_congestion_control(kdata);
 }
 
+static u32 bpf_tcp_ca_ssthresh(struct sock *sk)
+{
+	return 0;
+}
+
+static void bpf_tcp_ca_cong_avoid(struct sock *sk, u32 ack, u32 acked)
+{
+}
+
+static void bpf_tcp_ca_set_state(struct sock *sk, u8 new_state)
+{
+}
+
+static void bpf_tcp_ca_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
+{
+}
+
+static void bpf_tcp_ca_in_ack_event(struct sock *sk, u32 flags)
+{
+}
+
+static void bpf_tcp_ca_pkts_acked(struct sock *sk, const struct ack_sample *sample)
+{
+}
+
+static u32 bpf_tcp_ca_min_tso_segs(struct sock *sk)
+{
+	return 0;
+}
+
+static void bpf_tcp_ca_cong_control(struct sock *sk, const struct rate_sample *rs)
+{
+}
+
+static u32 bpf_tcp_ca_undo_cwnd(struct sock *sk)
+{
+	return 0;
+}
+
+static u32 bpf_tcp_ca_sndbuf_expand(struct sock *sk)
+{
+	return 0;
+}
+
+static void __bpf_tcp_ca_init(struct sock *sk)
+{
+}
+
+static void __bpf_tcp_ca_release(struct sock *sk)
+{
+}
+
+static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = {
+	.ssthresh = bpf_tcp_ca_ssthresh,
+	.cong_avoid = bpf_tcp_ca_cong_avoid,
+	.set_state = bpf_tcp_ca_set_state,
+	.cwnd_event = bpf_tcp_ca_cwnd_event,
+	.in_ack_event = bpf_tcp_ca_in_ack_event,
+	.pkts_acked = bpf_tcp_ca_pkts_acked,
+	.min_tso_segs = bpf_tcp_ca_min_tso_segs,
+	.cong_control = bpf_tcp_ca_cong_control,
+	.undo_cwnd = bpf_tcp_ca_undo_cwnd,
+	.sndbuf_expand = bpf_tcp_ca_sndbuf_expand,
+
+	.init = __bpf_tcp_ca_init,
+	.release = __bpf_tcp_ca_release,
+};
+
 struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.verifier_ops = &bpf_tcp_ca_verifier_ops,
 	.reg = bpf_tcp_ca_reg,
@@ -281,6 +349,7 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.init = bpf_tcp_ca_init,
 	.validate = bpf_tcp_ca_validate,
 	.name = "tcp_congestion_ops",
+	.cfi_stubs = &__bpf_ops_tcp_congestion_ops,
 };
 
 static int __init bpf_tcp_ca_kfunc_init(void)
-- 
cgit v1.2.3


From e4c00339891c074c76f626ac82981963cbba5332 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 15 Dec 2023 10:12:22 +0100
Subject: bpf: Fix dtor CFI

Ensure the various dtor functions match their prototype and retain
their CFI signatures, since they don't have their address taken, they
are prone to not getting CFI, making them impossible to call
indirectly.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231215092707.799451071@infradead.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/cpumask.c |  8 +++++++-
 kernel/bpf/helpers.c | 16 ++++++++++++++--
 net/bpf/test_run.c   | 15 +++++++++++++--
 3 files changed, 34 insertions(+), 5 deletions(-)

(limited to 'net')

diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c
index 7499b7d8c06f..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.
@@ -453,7 +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/helpers.c b/kernel/bpf/helpers.c
index b0b485126a76..e0c0e3676df8 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2150,6 +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
@@ -2174,6 +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
@@ -2570,10 +2582,10 @@ static const struct btf_kfunc_id_set generic_kfunc_set = {
 
 BTF_ID_LIST(generic_dtor_ids)
 BTF_ID(struct, task_struct)
-BTF_ID(func, bpf_task_release)
+BTF_ID(func, bpf_task_release_dtor)
 #ifdef CONFIG_CGROUPS
 BTF_ID(struct, cgroup)
-BTF_ID(func, bpf_cgroup_release)
+BTF_ID(func, bpf_cgroup_release_dtor)
 #endif
 
 BTF_SET8_START(common_btf_ids)
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 711cf5d59816..dfd919374017 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -600,10 +600,21 @@ __bpf_kfunc void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p)
 	refcount_dec(&p->cnt);
 }
 
+__bpf_kfunc void bpf_kfunc_call_test_release_dtor(void *p)
+{
+	bpf_kfunc_call_test_release(p);
+}
+CFI_NOSEAL(bpf_kfunc_call_test_release_dtor);
+
 __bpf_kfunc void bpf_kfunc_call_memb_release(struct prog_test_member *p)
 {
 }
 
+__bpf_kfunc void bpf_kfunc_call_memb_release_dtor(void *p)
+{
+}
+CFI_NOSEAL(bpf_kfunc_call_memb_release_dtor);
+
 __bpf_kfunc_end_defs();
 
 BTF_SET8_START(bpf_test_modify_return_ids)
@@ -1671,9 +1682,9 @@ static const struct btf_kfunc_id_set bpf_prog_test_kfunc_set = {
 
 BTF_ID_LIST(bpf_prog_test_dtor_kfunc_ids)
 BTF_ID(struct, prog_test_ref_kfunc)
-BTF_ID(func, bpf_kfunc_call_test_release)
+BTF_ID(func, bpf_kfunc_call_test_release_dtor)
 BTF_ID(struct, prog_test_member)
-BTF_ID(func, bpf_kfunc_call_memb_release)
+BTF_ID(func, bpf_kfunc_call_memb_release_dtor)
 
 static int __init bpf_prog_test_run_init(void)
 {
-- 
cgit v1.2.3