BPF program signatures can currently be verified against one of the
system keyrings (builtin, secondary, platform) or against an arbitrary
user/session caller-supplied keyring named through keyring_id. There
is nothing in between: the system keyrings need a kernel rebuild or a
vouched-for enrollment to rotate a key, while a caller-supplied keyring
is fully controlled by the loader and therefore carries no trust on
its own (unless explicitly combined with BPF LSM to protect against
key tampering).

Add a dedicated bpf keyring to fill that gap, modelled after the
dm-verity keyring which was added in commit 033724b1c627 ("dm-verity:
add dm-verity keyring") and which can eventually be used also via
systemd through the same enrollment method as in dm-verity's case. It
is selected with the new well-known keyring_id VERIFY_USE_BPF_KEYRING
and gives an operator a place to enroll a BPF-only signing key at boot,
specifically scoped to BPF program loading and nothing else in the
kernel's trust hierarchy.

By default the keyring is sealed empty at init. Systems that want to
provision keys pass bpf.keyring_unsealed=1, which leaves the keyring
open for the initrd to add keys to. The keyring is only ever consulted
once it is both non-empty and restricted. An unrestricted keyring is
ignored.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 .../admin-guide/kernel-parameters.txt         |  8 +++
 include/linux/bpf.h                           |  7 ++
 include/linux/verification.h                  | 10 +++
 kernel/bpf/Makefile                           |  3 +
 kernel/bpf/keys.c                             | 67 +++++++++++++++++++
 kernel/bpf/verifier.c                         | 13 +++-
 6 files changed, 106 insertions(+), 2 deletions(-)
 create mode 100644 kernel/bpf/keys.c

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index e4643634a9b1..2beb61092bb3 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -667,6 +667,14 @@ Kernel parameters
 
 			See Documentation/admin-guide/bootconfig.rst
 
+	bpf.keyring_unsealed=
+			[BPF] When set to 1, leave the bpf keyring unsealed
+			after initialization so that userspace can provision
+			keys. Once the keyring is restricted it becomes active
+			and can be used for BPF program signature verification.
+
+			See Documentation/bpf/signing.rst
+
 	bttv.card=	[HW,V4L] bttv (bt848 + bt878 based grabber cards)
 	bttv.radio=	Most important insmod options are available as
 			kernel args too.
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ffa5626411ac..240e527c864b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1735,6 +1735,7 @@ enum bpf_sig_keyring {
 	BPF_SIG_KEYRING_SECONDARY,
 	BPF_SIG_KEYRING_PLATFORM,
 	BPF_SIG_KEYRING_USER,
+	BPF_SIG_KEYRING_BPF,
 };
 
 struct bpf_prog_aux {
@@ -3819,6 +3820,7 @@ struct bpf_key {
 #if defined(CONFIG_KEYS) && defined(CONFIG_BPF_SYSCALL)
 struct bpf_key *bpf_lookup_user_key(s32 serial, u64 flags);
 struct bpf_key *bpf_lookup_system_key(u64 id);
+struct bpf_key *bpf_lookup_keyring(void);
 void bpf_key_put(struct bpf_key *bkey);
 int bpf_verify_pkcs7_signature(const struct bpf_dynptr *data_p,
 			       const struct bpf_dynptr *sig_p,
@@ -3839,6 +3841,11 @@ static inline struct bpf_key *bpf_lookup_system_key(u64 id)
 	return NULL;
 }
 
+static inline struct bpf_key *bpf_lookup_keyring(void)
+{
+	return NULL;
+}
+
 static inline void bpf_key_put(struct bpf_key *bkey)
 {
 }
diff --git a/include/linux/verification.h b/include/linux/verification.h
index dec7f2beabfd..1cb59ddda250 100644
--- a/include/linux/verification.h
+++ b/include/linux/verification.h
@@ -18,6 +18,16 @@
 #define VERIFY_USE_SECONDARY_KEYRING ((struct key *)1UL)
 #define VERIFY_USE_PLATFORM_KEYRING  ((struct key *)2UL)
 
+/*
+ * The id of BPF's ".bpf" keyring, reserved from the same space. It is
+ * explicitly not a sentinel like the two above as BPF resolves it to
+ * the keyring itself and passes that, so verify_pkcs7_signature() never
+ * sees this value, and system_keyring_id_check() must keep rejecting it.
+ * Left as a plain integer so that handing it over as @trusted_keys does
+ * not compile.
+ */
+#define VERIFY_USE_BPF_KEYRING	3
+
 static inline int system_keyring_id_check(u64 id)
 {
 	if (id > (unsigned long)VERIFY_USE_PLATFORM_KEYRING)
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 90255d80e5be..9a92c348bbda 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -27,6 +27,9 @@ obj-$(CONFIG_BPF_SYSCALL) += offload.o
 obj-$(CONFIG_BPF_SYSCALL) += net_namespace.o
 obj-$(CONFIG_BPF_SYSCALL) += tcx.o
 endif
+ifeq ($(CONFIG_KEYS),y)
+obj-$(CONFIG_BPF_SYSCALL) += keys.o
+endif
 ifeq ($(CONFIG_PERF_EVENTS),y)
 obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
 endif
diff --git a/kernel/bpf/keys.c b/kernel/bpf/keys.c
new file mode 100644
index 000000000000..dc4d3a33158a
--- /dev/null
+++ b/kernel/bpf/keys.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2026 Isovalent */
+
+#include <linux/bpf.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/key.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+
+#undef MODULE_PARAM_PREFIX
+#define MODULE_PARAM_PREFIX "bpf."
+
+static struct key *bpf_keyring;
+
+static bool bpf_keyring_unsealed __ro_after_init;
+module_param_named(keyring_unsealed, bpf_keyring_unsealed, bool, 0444);
+MODULE_PARM_DESC(keyring_unsealed, "Leave the bpf keyring unsealed");
+
+struct bpf_key *bpf_lookup_keyring(void)
+{
+	struct bpf_key *bkey;
+
+	if (!bpf_keyring)
+		return NULL;
+	if (!READ_ONCE(bpf_keyring->keys.nr_leaves_on_tree) ||
+	    !READ_ONCE(bpf_keyring->restrict_link))
+		return NULL;
+
+	bkey = kmalloc_obj(*bkey);
+	if (!bkey)
+		return NULL;
+
+	bkey->key = bpf_keyring;
+	bkey->has_ref = false;
+	return bkey;
+}
+
+static int __init bpf_keyring_init(void)
+{
+	struct key *keyring;
+
+	keyring = keyring_alloc(".bpf",
+				GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+				current_cred(), KEY_POS_SEARCH |
+				KEY_USR_VIEW | KEY_USR_READ |
+				KEY_USR_WRITE | KEY_USR_SEARCH |
+				KEY_USR_SETATTR, KEY_ALLOC_NOT_IN_QUOTA,
+				NULL, NULL);
+	if (IS_ERR(keyring)) {
+		pr_err("bpf: cannot allocate bpf keyring: %ld\n",
+		       PTR_ERR(keyring));
+		return 0;
+	}
+	if (!bpf_keyring_unsealed &&
+	    keyring_restrict(make_key_ref(keyring, true), NULL, NULL)) {
+		pr_err("bpf: cannot seal bpf keyring\n");
+		key_revoke(keyring);
+		key_put(keyring);
+		return 0;
+	}
+
+	bpf_keyring = keyring;
+	return 0;
+}
+late_initcall(bpf_keyring_init);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e036ae20bf6b..3be8d51d35ac 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -20981,6 +20981,8 @@ static enum bpf_sig_keyring bpf_classify_keyring(s32 keyring_id)
 		return BPF_SIG_KEYRING_SECONDARY;
 	case (s32)(unsigned long)VERIFY_USE_PLATFORM_KEYRING:
 		return BPF_SIG_KEYRING_PLATFORM;
+	case VERIFY_USE_BPF_KEYRING:
+		return BPF_SIG_KEYRING_BPF;
 	default:
 		return BPF_SIG_KEYRING_USER;
 	}
@@ -21016,10 +21018,17 @@ static int bpf_prog_verify_signature(struct bpf_verifier_env *env,
 	if (!attr->signature_size ||
 	    attr->signature_size > KMALLOC_MAX_CACHE_SIZE)
 		return -EINVAL;
-	if (system_keyring_id_check(attr->keyring_id) == 0)
+	if (attr->keyring_id == VERIFY_USE_BPF_KEYRING) {
+		key = bpf_lookup_keyring();
+		if (!key) {
+			verbose(env, "the bpf keyring is empty or has not been restricted\n");
+			return -ENOKEY;
+		}
+	} else if (system_keyring_id_check(attr->keyring_id) == 0) {
 		key = bpf_lookup_system_key(attr->keyring_id);
-	else
+	} else {
 		key = bpf_lookup_user_key(attr->keyring_id, 0);
+	}
 	if (!key) {
 		verbose(env, "cannot resolve signing keyring with keyring_id %d\n",
 			attr->keyring_id);
-- 
2.43.0

Nothing changes for systems that do not use the bpf keyring. Without
bpf.keyring_unsealed=1 a caller-supplied keyring behaves exactly as
before, which also lets it serve as the staging step for software
installed onto a running system whose signing key is not enrolled
anywhere yet.

Passing bpf.keyring_unsealed=1 states that the bpf keyring is the trust
anchor for this boot, so from the first program load onwards a caller-
supplied keyring is refused with -EPERM. Deriving this from the boot
flag rather than from the keyring's runtime state keeps the decision
immutable from userspace.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 .../admin-guide/kernel-parameters.txt         |  7 +++++
 include/linux/bpf.h                           |  6 ++++
 kernel/bpf/keys.c                             |  5 ++++
 kernel/bpf/verifier.c                         | 29 ++++++++++++-------
 4 files changed, 36 insertions(+), 11 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 2beb61092bb3..543f245cc255 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -673,6 +673,13 @@ Kernel parameters
 			keys. Once the keyring is restricted it becomes active
 			and can be used for BPF program signature verification.
 
+			Setting this also means that the bpf keyring is the
+			only keyring a loader may select for the rest of the
+			boot: caller-supplied user/session keyrings are
+			refused with -EPERM, whether or not provisioning
+			actually completed. Leaving it unset keeps the prior
+			behaviour, where a caller-supplied keyring is allowed.
+
 			See Documentation/bpf/signing.rst
 
 	bttv.card=	[HW,V4L] bttv (bt848 + bt878 based grabber cards)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 240e527c864b..f6ef16c938cb 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3821,6 +3821,7 @@ struct bpf_key {
 struct bpf_key *bpf_lookup_user_key(s32 serial, u64 flags);
 struct bpf_key *bpf_lookup_system_key(u64 id);
 struct bpf_key *bpf_lookup_keyring(void);
+bool bpf_keyring_enforced(void);
 void bpf_key_put(struct bpf_key *bkey);
 int bpf_verify_pkcs7_signature(const struct bpf_dynptr *data_p,
 			       const struct bpf_dynptr *sig_p,
@@ -3846,6 +3847,11 @@ static inline struct bpf_key *bpf_lookup_keyring(void)
 	return NULL;
 }
 
+static inline bool bpf_keyring_enforced(void)
+{
+	return false;
+}
+
 static inline void bpf_key_put(struct bpf_key *bkey)
 {
 }
diff --git a/kernel/bpf/keys.c b/kernel/bpf/keys.c
index dc4d3a33158a..60cb85295c89 100644
--- a/kernel/bpf/keys.c
+++ b/kernel/bpf/keys.c
@@ -18,6 +18,11 @@ static bool bpf_keyring_unsealed __ro_after_init;
 module_param_named(keyring_unsealed, bpf_keyring_unsealed, bool, 0444);
 MODULE_PARM_DESC(keyring_unsealed, "Leave the bpf keyring unsealed");
 
+bool bpf_keyring_enforced(void)
+{
+	return bpf_keyring_unsealed;
+}
+
 struct bpf_key *bpf_lookup_keyring(void)
 {
 	struct bpf_key *bkey;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3be8d51d35ac..a93a8dc427d8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -21018,21 +21018,28 @@ static int bpf_prog_verify_signature(struct bpf_verifier_env *env,
 	if (!attr->signature_size ||
 	    attr->signature_size > KMALLOC_MAX_CACHE_SIZE)
 		return -EINVAL;
-	if (attr->keyring_id == VERIFY_USE_BPF_KEYRING) {
-		key = bpf_lookup_keyring();
-		if (!key) {
-			verbose(env, "the bpf keyring is empty or has not been restricted\n");
-			return -ENOKEY;
-		}
-	} else if (system_keyring_id_check(attr->keyring_id) == 0) {
+	if (!system_keyring_id_check(attr->keyring_id)) {
 		key = bpf_lookup_system_key(attr->keyring_id);
 	} else {
-		key = bpf_lookup_user_key(attr->keyring_id, 0);
+		if (attr->keyring_id != VERIFY_USE_BPF_KEYRING) {
+			if (bpf_keyring_enforced()) {
+				verbose(env, "caller-supplied keyring refused, use bpf keyring\n");
+				return -EPERM;
+			}
+			key = bpf_lookup_user_key(attr->keyring_id, 0);
+		} else {
+			key = bpf_lookup_keyring();
+		}
 	}
 	if (!key) {
-		verbose(env, "cannot resolve signing keyring with keyring_id %d\n",
-			attr->keyring_id);
-		return -EINVAL;
+		if (attr->keyring_id == VERIFY_USE_BPF_KEYRING) {
+			verbose(env, "the bpf keyring is empty or has not been restricted\n");
+			return -ENOKEY;
+		} else {
+			verbose(env, "cannot resolve signing keyring with keyring_id %d\n",
+				attr->keyring_id);
+			return -EINVAL;
+		}
 	}
 
 	sig = kvmemdup_bpfptr(usig, attr->signature_size);
-- 
2.43.0

signature_size is bounded by KMALLOC_MAX_CACHE_SIZE, which is 8 KiB on a
4 KiB page system. Back then we chose it somewhat arbitrarily and was
picked when a BPF program signature was RSA or ECDSA. ML-DSA (FIPS-204)
verification is wired through the X.509 and PKCS#7 parsers, and BPF
reaches them too via verify_pkcs7_signature() without having to know the
concrete algorithm. The bound becomes a bit too small, thus add an
explicit BPF_PROG_MAX_SIGNATURE_SIZE of 64 KiB and use that instead
to cover all options.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c                              | 14 +++++++++-----
 .../selftests/bpf/prog_tests/signed_loader.c       |  5 +++--
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a93a8dc427d8..575c4e5e4443 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -20972,6 +20972,13 @@ int bpf_fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	return 0;
 }
 
+/*
+ * Upper bound on the PKCS#7 signature blob passed with a program. Comfortably
+ * above the largest signature the kernel can verify, and far below anything
+ * that would make rejecting a load expensive.
+ */
+#define BPF_PROG_MAX_SIGNATURE_SIZE	(64 * 1024)
+
 static enum bpf_sig_keyring bpf_classify_keyring(s32 keyring_id)
 {
 	switch (keyring_id) {
@@ -21011,13 +21018,10 @@ static int bpf_prog_verify_signature(struct bpf_verifier_env *env,
 	u64 data_sz;
 	int err = 0;
 
-	/*
-	 * Don't attempt to use kmalloc_large or vmalloc for signatures.
-	 * Practical signature for BPF program should be below this limit.
-	 */
 	if (!attr->signature_size ||
-	    attr->signature_size > KMALLOC_MAX_CACHE_SIZE)
+	    attr->signature_size > BPF_PROG_MAX_SIGNATURE_SIZE)
 		return -EINVAL;
+
 	if (!system_keyring_id_check(attr->keyring_id)) {
 		key = bpf_lookup_system_key(attr->keyring_id);
 	} else {
diff --git a/tools/testing/selftests/bpf/prog_tests/signed_loader.c b/tools/testing/selftests/bpf/prog_tests/signed_loader.c
index 77381d345435..0c5294738d6c 100644
--- a/tools/testing/selftests/bpf/prog_tests/signed_loader.c
+++ b/tools/testing/selftests/bpf/prog_tests/signed_loader.c
@@ -571,8 +571,9 @@ static void signature_too_large(void)
 
 	if (gen_loader_fixture_init(&f) == 0) {
 		/*
-		 * signature_size beyond the kernel's bound (KMALLOC_MAX_CACHE_SIZE)
-		 * is rejected before the buffer is read.
+		 * signature_size beyond the kernel's bound
+		 * (BPF_PROG_MAX_SIGNATURE_SIZE) is rejected before the buffer
+		 * is read.
 		 */
 		fd = load_loader(f.gopts.insns, f.gopts.insns_sz, -1, junk,
 				 64 << 20, KEY_SPEC_SESSION_KEYRING, 0);
-- 
2.43.0

Add bpftool support for ML-DSA program signing and drop the flag for
ML-DSA keys on affected OpenSSL versions, the same way as commit
0ad9a71933e7 ("modsign: Enable ML-DSA module signing").

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/main.h |  2 +-
 tools/bpf/bpftool/sign.c | 22 +++++++++++++++++++---
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 78b6e0ebb85d..9315a1db1f7c 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -57,7 +57,7 @@ static inline void *u64_to_ptr(__u64 ptr)
 	})
 
 #define ERR_MAX_LEN	1024
-#define MAX_SIG_SIZE	4096
+#define MAX_SIG_SIZE	16384
 
 #define BPF_TAG_FMT	"%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx"
 
diff --git a/tools/bpf/bpftool/sign.c b/tools/bpf/bpftool/sign.c
index 88726a6db6d0..818a4f900bbb 100644
--- a/tools/bpf/bpftool/sign.c
+++ b/tools/bpf/bpftool/sign.c
@@ -130,6 +130,9 @@ __u32 register_session_key(const char *key_der_path)
 
 int bpftool_prog_sign(struct bpf_load_and_run_opts *opts)
 {
+	unsigned int signer_flags = CMS_NOCERTS | CMS_BINARY | CMS_NOSMIMECAP |
+				    CMS_USE_KEYID | CMS_NOATTR;
+	const EVP_MD *cms_digest = EVP_sha256();
 	BIO *bd_in = NULL, *bd_out = NULL;
 	EVP_PKEY *private_key = NULL;
 	CMS_ContentInfo *cms = NULL;
@@ -167,6 +170,21 @@ int bpftool_prog_sign(struct bpf_load_and_run_opts *opts)
 		goto cleanup;
 	}
 
+#if OPENSSL_VERSION_NUMBER >= 0x30000000L && OPENSSL_VERSION_NUMBER < 0x40000000L
+	if (EVP_PKEY_is_a(private_key, "ML-DSA-44") ||
+	    EVP_PKEY_is_a(private_key, "ML-DSA-65") ||
+	    EVP_PKEY_is_a(private_key, "ML-DSA-87")) {
+		/*
+		 * ML-DSA + CMS_NOATTR is not supported in openssl-3.5 and
+		 * before, so fall back to signedAttrs. ML-DSA does its own
+		 * hashing and ignores the CMS digest, except when signedAttrs
+		 * are used, where only SHA-512 is permitted.
+		 */
+		signer_flags &= ~CMS_NOATTR;
+		cms_digest = EVP_sha512();
+	}
+#endif
+
 	cms = CMS_sign(NULL, NULL, NULL, NULL,
 		       CMS_NOCERTS | CMS_PARTIAL | CMS_BINARY | CMS_DETACHED |
 			       CMS_STREAM);
@@ -175,9 +193,7 @@ int bpftool_prog_sign(struct bpf_load_and_run_opts *opts)
 		goto cleanup;
 	}
 
-	if (!CMS_add1_signer(cms, x509, private_key, EVP_sha256(),
-			     CMS_NOCERTS | CMS_BINARY | CMS_NOSMIMECAP |
-			     CMS_USE_KEYID | CMS_NOATTR)) {
+	if (!CMS_add1_signer(cms, x509, private_key, cms_digest, signer_flags)) {
 		err = -EINVAL;
 		goto cleanup;
 	}
-- 
2.43.0

bpf_keyring_sealed checks that a load naming the bpf keyring fails with
-ENOKEY while the keyring has not been provisioned. It uses a junk signature
as the size check and the keyring lookup both happen before any crypto, so
the error under test is reached without a real signature and the ordering
is what gets verified:

  # LDLIBS=-static PKG_CONFIG='pkg-config --static' ./vmtest.sh -- ./test_progs -t signed_loader
  [...]
  #424/9   signed_loader/signed_module_kfunc_rejected:OK
  #424/10  signed_loader/signature_failure_logs:OK
  #424/11  signed_loader/signature_too_large:OK
  #424/12  signed_loader/signature_zero_size:OK
  #424/13  signed_loader/signature_bad_keyring:OK
  #424/14  signed_loader/bpf_keyring_sealed:OK
  #424/15  signed_loader/metadata_ctx_max_entries_ignored:OK
  #424/16  signed_loader/metadata_ctx_initial_value_ignored:OK
  #424/17  signed_loader/signature_authenticates_insns:OK
  #424/18  signed_loader/signature_authenticates_metadata:OK
  #424/19  signed_loader/hash_requires_frozen:OK
  [...]
  #424     signed_loader:OK
  Summary: 1/30 PASSED, 0 SKIPPED, 0/0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 .../selftests/bpf/prog_tests/signed_loader.c  | 27 +++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/signed_loader.c b/tools/testing/selftests/bpf/prog_tests/signed_loader.c
index 0c5294738d6c..94b57e7cdab3 100644
--- a/tools/testing/selftests/bpf/prog_tests/signed_loader.c
+++ b/tools/testing/selftests/bpf/prog_tests/signed_loader.c
@@ -32,8 +32,11 @@ enum {
 	BPF_SIG_KEYRING_SECONDARY,
 	BPF_SIG_KEYRING_PLATFORM,
 	BPF_SIG_KEYRING_USER,
+	BPF_SIG_KEYRING_BPF,
 };
 
+#define BPF_KEYRING_BPF		3
+
 static int load_loader(const void *insns, __u32 insns_sz, int map_fd,
 		       const void *sig, __u32 sig_sz, __s32 keyring_id,
 		       __u32 fd_array_cnt)
@@ -627,6 +630,28 @@ static void signature_bad_keyring(void)
 	gen_loader_fixture_fini(&f);
 }
 
+static void bpf_keyring_sealed(void)
+{
+	static const __u8 junk[64] = {};
+	struct gen_loader_fixture f;
+	int fd;
+
+	if (gen_loader_fixture_init(&f) == 0) {
+		/*
+		 * Without bpf.keyring_unsealed=1 on the command line the bpf
+		 * keyring is sealed empty during boot, so it is never handed
+		 * out and a load naming it fails with -ENOKEY before the
+		 * signature bytes are examined.
+		 */
+		fd = load_loader(f.gopts.insns, f.gopts.insns_sz, -1, junk,
+				 sizeof(junk), BPF_KEYRING_BPF, 0);
+		ASSERT_EQ(fd, -ENOKEY, "sealed bpf keyring rejected");
+		if (fd >= 0)
+			close(fd);
+	}
+	gen_loader_fixture_fini(&f);
+}
+
 /*
  * A signed loader must ignore ctx-supplied map dimensions: the host cannot
  * resize a signed program's maps via the loader ctx. Drive a one-map program
@@ -1806,6 +1831,8 @@ void test_signed_loader(void)
 		signature_zero_size();
 	if (test__start_subtest("signature_bad_keyring"))
 		signature_bad_keyring();
+	if (test__start_subtest("bpf_keyring_sealed"))
+		bpf_keyring_sealed();
 	if (test__start_subtest("metadata_ctx_max_entries_ignored"))
 		metadata_ctx_max_entries_ignored();
 	if (test__start_subtest("metadata_ctx_initial_value_ignored"))
-- 
2.43.0

The signing key is regenerated whenever verify_sig_setup.sh changes,
but the signed light skeletons only depend on the BPF object and on
bpftool, not on the key they are signed with. Thus, add the certificate
as a prereq so a new key forces the skeletons to be signed again.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 5f1a3bfc0569..05b3ee64290f 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -663,7 +663,7 @@ $(TRUNNER_BPF_LSKELS): %.lskel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	}) && \
 	rm -f $$(<:.o=.llinked1.o) $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o)
 
-$(TRUNNER_BPF_LSKELS_SIGNED): %.lskel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
+$(TRUNNER_BPF_LSKELS_SIGNED): %.lskel.h: %.bpf.o $(BPFTOOL) $(VERIFICATION_CERT) | $(TRUNNER_OUTPUT)
 	$(Q)$(if $(PERMISSIVE),if [ ! -f $$< ]; then			\
 		$$(RM) $$@;						\
 		printf '  %-12s %s\n' 'SKIP-SKEL' '$$(notdir $$@)' 1>&2; \
-- 
2.43.0

The script's "setup" action generates an RSA key, enrolls it and builds
a keyring around it. The name says nothing about the algorithm, which is
fine while there is only one, but we'll add "setup-mldsa" soon, therefore
rename the existing one into "setup-rsa". No functional change.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 .../selftests/bpf/prog_tests/signed_loader.c   | 18 +++++++++---------
 .../bpf/prog_tests/verify_pkcs7_sig.c          |  4 ++--
 .../testing/selftests/bpf/verify_sig_setup.sh  |  8 ++++----
 3 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/signed_loader.c b/tools/testing/selftests/bpf/prog_tests/signed_loader.c
index 94b57e7cdab3..4b2416903d90 100644
--- a/tools/testing/selftests/bpf/prog_tests/signed_loader.c
+++ b/tools/testing/selftests/bpf/prog_tests/signed_loader.c
@@ -460,7 +460,7 @@ static void signed_btf_fd_array_rejected(void)
 	dir = mkdtemp(dir_tmpl);
 	if (!ASSERT_OK_PTR(dir, "mkdtemp"))
 		return;
-	if (!ASSERT_OK(run_setup("setup", dir), "verify_sig_setup")) {
+	if (!ASSERT_OK(run_setup("setup-rsa", dir), "verify_sig_setup")) {
 		rmdir(dir);
 		return;
 	}
@@ -857,7 +857,7 @@ static void signature_authenticates_insns(void)
 	dir = mkdtemp(dir_tmpl);
 	if (!ASSERT_OK_PTR(dir, "mkdtemp"))
 		return;
-	if (!ASSERT_OK(run_setup("setup", dir), "verify_sig_setup")) {
+	if (!ASSERT_OK(run_setup("setup-rsa", dir), "verify_sig_setup")) {
 		rmdir(dir);
 		return;
 	}
@@ -957,7 +957,7 @@ static void signature_authenticates_metadata(void)
 	dir = mkdtemp(dir_tmpl);
 	if (!ASSERT_OK_PTR(dir, "mkdtemp"))
 		return;
-	if (!ASSERT_OK(run_setup("setup", dir), "verify_sig_setup")) {
+	if (!ASSERT_OK(run_setup("setup-rsa", dir), "verify_sig_setup")) {
 		rmdir(dir);
 		return;
 	}
@@ -1293,7 +1293,7 @@ static void lsm_signature_verdict(void)
 	dir = mkdtemp(dir_tmpl);
 	if (!ASSERT_OK_PTR(dir, "mkdtemp"))
 		goto out;
-	if (!ASSERT_OK(run_setup("setup", dir), "verify_sig_setup")) {
+	if (!ASSERT_OK(run_setup("setup-rsa", dir), "verify_sig_setup")) {
 		rmdir(dir);
 		dir = NULL;
 		goto out;
@@ -1476,7 +1476,7 @@ static void loadtime_verify(struct bpf_object *obj, int expect_maps)
 	dir = mkdtemp(dir_tmpl);
 	if (!ASSERT_OK_PTR(dir, "mkdtemp"))
 		return;
-	if (!ASSERT_OK(run_setup("setup", dir), "verify_sig_setup")) {
+	if (!ASSERT_OK(run_setup("setup-rsa", dir), "verify_sig_setup")) {
 		rmdir(dir);
 		return;
 	}
@@ -1574,7 +1574,7 @@ static void signed_no_fd_array(void)
 	dir = mkdtemp(dir_tmpl);
 	if (!ASSERT_OK_PTR(dir, "mkdtemp"))
 		return;
-	if (!ASSERT_OK(run_setup("setup", dir), "verify_sig_setup")) {
+	if (!ASSERT_OK(run_setup("setup-rsa", dir), "verify_sig_setup")) {
 		rmdir(dir);
 		return;
 	}
@@ -1645,7 +1645,7 @@ static void signed_map_by_fd_rejected(void)
 	dir = mkdtemp(dir_tmpl);
 	if (!ASSERT_OK_PTR(dir, "mkdtemp"))
 		goto out_map;
-	if (!ASSERT_OK(run_setup("setup", dir), "verify_sig_setup")) {
+	if (!ASSERT_OK(run_setup("setup-rsa", dir), "verify_sig_setup")) {
 		rmdir(dir);
 		goto out_map;
 	}
@@ -1707,7 +1707,7 @@ static void signed_sparse_fd_array_rejected(void)
 	dir = mkdtemp(dir_tmpl);
 	if (!ASSERT_OK_PTR(dir, "mkdtemp"))
 		goto out_map;
-	if (!ASSERT_OK(run_setup("setup", dir), "verify_sig_setup")) {
+	if (!ASSERT_OK(run_setup("setup-rsa", dir), "verify_sig_setup")) {
 		rmdir(dir);
 		goto out_map;
 	}
@@ -1761,7 +1761,7 @@ static void signed_module_kfunc_rejected(void)
 	dir = mkdtemp(dir_tmpl);
 	if (!ASSERT_OK_PTR(dir, "mkdtemp"))
 		return;
-	if (!ASSERT_OK(run_setup("setup", dir), "verify_sig_setup")) {
+	if (!ASSERT_OK(run_setup("setup-rsa", dir), "verify_sig_setup")) {
 		rmdir(dir);
 		return;
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
index f327feb8e38c..12b146d205d7 100644
--- a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
+++ b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
@@ -257,7 +257,7 @@ static void test_verify_pkcs7_sig_from_map(void)
 	if (!ASSERT_OK_PTR(tmp_dir, "mkdtemp"))
 		return;
 
-	ret = _run_setup_process(tmp_dir, "setup");
+	ret = _run_setup_process(tmp_dir, "setup-rsa");
 	if (!ASSERT_OK(ret, "_run_setup_process"))
 		goto close_prog;
 
@@ -458,7 +458,7 @@ static void test_pkcs7_sig_fsverity(void)
 	snprintf(data_path, PATH_MAX, "%s/data-file", tmp_dir);
 	snprintf(sig_path, PATH_MAX, "%s/sig-file", tmp_dir);
 
-	ret = _run_setup_process(tmp_dir, "setup");
+	ret = _run_setup_process(tmp_dir, "setup-rsa");
 	if (!ASSERT_OK(ret, "_run_setup_process"))
 		goto out;
 
diff --git a/tools/testing/selftests/bpf/verify_sig_setup.sh b/tools/testing/selftests/bpf/verify_sig_setup.sh
index 09179fb551f0..202e6e6418fe 100755
--- a/tools/testing/selftests/bpf/verify_sig_setup.sh
+++ b/tools/testing/selftests/bpf/verify_sig_setup.sh
@@ -28,7 +28,7 @@ authorityKeyIdentifier=keyid
 
 usage()
 {
-	echo "Usage: $0 <setup|cleanup <existing_tmp_dir>"
+	echo "Usage: $0 <setup-rsa|cleanup <existing_tmp_dir>"
 	exit 1
 }
 
@@ -47,7 +47,7 @@ genkey()
 		${tmp_dir}/signing_key.der -outform der
 }
 
-setup()
+setup_rsa()
 {
 	local tmp_dir="$1"
 
@@ -108,8 +108,8 @@ main()
 
 	[[ ! -d "${tmp_dir}" ]] && echo "Directory ${tmp_dir} doesn't exist" && exit 1
 
-	if [[ "${action}" == "setup" ]]; then
-		setup "${tmp_dir}"
+	if [[ "${action}" == "setup-rsa" ]]; then
+		setup_rsa "${tmp_dir}"
 	elif [[ "${action}" == "genkey" ]]; then
 		genkey "${tmp_dir}"
 	elif [[ "${action}" == "cleanup" ]]; then
-- 
2.43.0

The BPF signing is algorithm agnostic, but so far the BPF CI only
has tested a single one. BPF hands verify_pkcs7_signature() a keyring
and byte ranges, and everything below it already understands ML-DSA,
so add a test for ML-DSA signed program to validate it works as well.

  # LDLIBS=-static PKG_CONFIG='pkg-config --static' ./vmtest.sh -- ./test_progs -t signed_loader
  [...]
  #424/10  signed_loader/signature_failure_logs:OK
  #424/11  signed_loader/signature_too_large:OK
  #424/12  signed_loader/signature_zero_size:OK
  #424/13  signed_loader/signature_bad_keyring:OK
  #424/14  signed_loader/bpf_keyring_sealed:OK
  #424/15  signed_loader/mldsa_signed_load:OK
  #424/16  signed_loader/metadata_ctx_max_entries_ignored:OK
  #424/17  signed_loader/metadata_ctx_initial_value_ignored:OK
  #424/18  signed_loader/signature_authenticates_insns:OK
  #424/19  signed_loader/signature_authenticates_metadata:OK
  #424/20  signed_loader/hash_requires_frozen:OK
  [...]
  #424     signed_loader:OK
  Summary: 1/31 PASSED, 0 SKIPPED, 0/0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/config            |   1 +
 .../selftests/bpf/prog_tests/signed_loader.c  | 106 +++++++++++++++++-
 .../testing/selftests/bpf/verify_sig_setup.sh |  57 +++++++++-
 3 files changed, 157 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index ea7044f30adc..4e6d13dbf266 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -51,6 +51,7 @@ CONFIG_IPV6_SEG6_LWTUNNEL=y
 CONFIG_IPV6_SIT=y
 CONFIG_IPV6_TUNNEL=y
 CONFIG_KEYS=y
+CONFIG_CRYPTO_MLDSA=y
 CONFIG_LIRC=y
 CONFIG_LIVEPATCH=y
 CONFIG_LWTUNNEL=y
diff --git a/tools/testing/selftests/bpf/prog_tests/signed_loader.c b/tools/testing/selftests/bpf/prog_tests/signed_loader.c
index 4b2416903d90..a1fa1c37815b 100644
--- a/tools/testing/selftests/bpf/prog_tests/signed_loader.c
+++ b/tools/testing/selftests/bpf/prog_tests/signed_loader.c
@@ -37,6 +37,12 @@ enum {
 
 #define BPF_KEYRING_BPF		3
 
+/* verify_sig_setup.sh exits with this when openssl cannot do ML-DSA. */
+#define SETUP_SKIP		(-77)
+
+/* FIPS-204 ML-DSA-87 signature size, see include/crypto/mldsa.h. */
+#define MLDSA87_SIGNATURE_SIZE	4627
+
 static int load_loader(const void *insns, __u32 insns_sz, int map_fd,
 		       const void *sig, __u32 sig_sz, __s32 keyring_id,
 		       __u32 fd_array_cnt)
@@ -159,12 +165,13 @@ static int run_setup(const char *cmd, const char *dir)
 	}
 	if (waitpid(pid, &status, 0) < 0)
 		return -errno;
-	return (WIFEXITED(status) &&
-		WEXITSTATUS(status) == 0) ? 0 : -EINVAL;
+	if (!WIFEXITED(status))
+		return -EINVAL;
+	return -WEXITSTATUS(status);
 }
 
-static int sign_buf(const char *dir, const void *buf, __u32 len,
-		    void *sig, __u32 *sig_sz)
+static int sign_buf_digest(const char *dir, const void *buf, __u32 len,
+			   void *sig, __u32 *sig_sz, const char *digest)
 {
 	char data_tmpl[PATH_MAX], key[PATH_MAX];
 	char sigpath[PATH_MAX + sizeof(".p7s")];
@@ -193,7 +200,7 @@ static int sign_buf(const char *dir, const void *buf, __u32 len,
 	}
 	if (pid == 0) {
 		snprintf(key, sizeof(key), "%s/signing_key.pem", dir);
-		execlp("./sign-file", "./sign-file", "-d", "sha256",
+		execlp("./sign-file", "./sign-file", "-d", digest,
 		       key, key, data_tmpl, NULL);
 		exit(1);
 	}
@@ -231,6 +238,12 @@ static int sign_buf(const char *dir, const void *buf, __u32 len,
 	return ret;
 }
 
+static int sign_buf(const char *dir, const void *buf, __u32 len,
+		    void *sig, __u32 *sig_sz)
+{
+	return sign_buf_digest(dir, buf, len, sig, sig_sz, "sha256");
+}
+
 struct gen_loader_fixture {
 	struct test_signed_loader *skel;
 	struct gen_loader_opts gopts;
@@ -1550,6 +1563,87 @@ static void loadtime_with_map(void)
 	test_signed_loader_map__destroy(skel);
 }
 
+/*
+ * End-to-end signed load with a post-quantum key. ML-DSA (FIPS-204) is wired
+ * through the X.509 and PKCS#7 parsers, and BPF reaches them via
+ * verify_pkcs7_signature() without knowing the algorithm, so an ML-DSA key in
+ * the keyring should verify an ML-DSA signed program with no BPF-side work.
+ */
+static void mldsa_signed_load(void)
+{
+	char dir_tmpl[] = "/tmp/bpfmldsaXXXXXX";
+	int map_fd = -1, prog_fd = -1, err;
+	__u8 *sig = NULL, *buf = NULL;
+	struct gen_loader_fixture f;
+	bool have_fixture = false;
+	__u32 sig_sz = 16384;
+	char *dir;
+
+	dir = mkdtemp(dir_tmpl);
+	if (!ASSERT_OK_PTR(dir, "mkdtemp"))
+		return;
+
+	err = run_setup("setup-mldsa", dir);
+	if (err == SETUP_SKIP) {
+		printf("%s:SKIP:openssl has no ML-DSA support (needs 3.5+)\n",
+		       __func__);
+		test__skip();
+		rmdir(dir);
+		return;
+	}
+	if (!ASSERT_OK(err, "verify_sig_setup setup-mldsa")) {
+		rmdir(dir);
+		return;
+	}
+
+	sig = malloc(sig_sz);
+	if (!ASSERT_OK_PTR(sig, "sig buf"))
+		goto out;
+	have_fixture = true;
+	if (gen_loader_fixture_init(&f) != 0)
+		goto out;
+
+	buf = malloc((size_t)f.gopts.insns_sz + f.data_sz);
+	if (!ASSERT_OK_PTR(buf, "signbuf"))
+		goto out;
+	memcpy(buf, f.gopts.insns, f.gopts.insns_sz);
+	memcpy(buf + f.gopts.insns_sz, f.blob, f.data_sz);
+
+	/*
+	 * ML-DSA hashes the message itself, but openssl before 4.0 cannot
+	 * produce a CMS message without signedAttrs for it, and with those in
+	 * play only SHA-512 is permitted for the messageDigest attribute.
+	 */
+	if (!ASSERT_OK(sign_buf_digest(dir, buf, f.gopts.insns_sz + f.data_sz,
+				       sig, &sig_sz, "sha512"),
+		       "sign insns||metadata with ML-DSA"))
+		goto out;
+
+	/*
+	 * Guard against the setup silently handing back some other key type:
+	 * an RSA or ECDSA signature is a few hundred bytes, where an ML-DSA-87
+	 * one cannot be smaller than the raw signature it carries.
+	 */
+	ASSERT_GT(sig_sz, MLDSA87_SIGNATURE_SIZE, "ML-DSA-87 signature size");
+
+	map_fd = setup_meta_map(&f);
+	if (!ASSERT_OK_FD(map_fd, "meta_map"))
+		goto out;
+	prog_fd = load_loader(f.gopts.insns, f.gopts.insns_sz, map_fd, sig,
+			      sig_sz, KEY_SPEC_SESSION_KEYRING, 1);
+	ASSERT_OK_FD(prog_fd, "ML-DSA signed loader load");
+out:
+	if (prog_fd >= 0)
+		close(prog_fd);
+	if (map_fd >= 0)
+		close(map_fd);
+	if (have_fixture)
+		gen_loader_fixture_fini(&f);
+	free(buf);
+	free(sig);
+	run_setup("cleanup", dir);
+}
+
 /*
  * A signed program need not bind any map. A plain BPF_PROG_TYPE_SYSCALL
  * program with no fd_array is signed over its instructions alone: the kernel
@@ -1833,6 +1927,8 @@ void test_signed_loader(void)
 		signature_bad_keyring();
 	if (test__start_subtest("bpf_keyring_sealed"))
 		bpf_keyring_sealed();
+	if (test__start_subtest("mldsa_signed_load"))
+		mldsa_signed_load();
 	if (test__start_subtest("metadata_ctx_max_entries_ignored"))
 		metadata_ctx_max_entries_ignored();
 	if (test__start_subtest("metadata_ctx_initial_value_ignored"))
diff --git a/tools/testing/selftests/bpf/verify_sig_setup.sh b/tools/testing/selftests/bpf/verify_sig_setup.sh
index 202e6e6418fe..2737c1a2bcfd 100755
--- a/tools/testing/selftests/bpf/verify_sig_setup.sh
+++ b/tools/testing/selftests/bpf/verify_sig_setup.sh
@@ -28,7 +28,7 @@ authorityKeyIdentifier=keyid
 
 usage()
 {
-	echo "Usage: $0 <setup-rsa|cleanup <existing_tmp_dir>"
+	echo "Usage: $0 <setup-rsa|setup-mldsa|cleanup <existing_tmp_dir>"
 	exit 1
 }
 
@@ -57,6 +57,57 @@ setup_rsa()
 	keyctl link $key_id $keyring_id
 }
 
+mldsa_supported()
+{
+	local tmp_dir="$1"
+
+	genkey_mldsa "${tmp_dir}" || return 1
+	: > ${tmp_dir}/probe
+	# Same digest as the caller signs with, see sign_buf_digest().
+	./sign-file -d sha512 ${tmp_dir}/signing_key.pem \
+		${tmp_dir}/signing_key.pem ${tmp_dir}/probe || return 1
+	rm -f ${tmp_dir}/probe ${tmp_dir}/probe.p7s
+}
+
+genkey_mldsa()
+{
+	local tmp_dir="$1"
+
+	echo "${x509_genkey_content}" > ${tmp_dir}/x509.genkey
+
+	# No -<digest> here: ML-DSA hashes the message itself, and openssl
+	# rejects an explicit digest for it.
+	openssl req -new -nodes -utf8 -days 36500 \
+			-batch -x509 -newkey ML-DSA-87 \
+			-config ${tmp_dir}/x509.genkey \
+			-outform PEM -out ${tmp_dir}/signing_key.pem \
+			-keyout ${tmp_dir}/signing_key.pem 2>&1
+
+	openssl x509 -in ${tmp_dir}/signing_key.pem -out \
+		${tmp_dir}/signing_key.der -outform der
+}
+
+mldsa_skip()
+{
+	local tmp_dir="$1"
+
+	rm -f ${tmp_dir}/x509.genkey ${tmp_dir}/signing_key.pem \
+		${tmp_dir}/signing_key.der ${tmp_dir}/probe \
+		${tmp_dir}/probe.p7s
+	exit 77
+}
+
+setup_mldsa()
+{
+	local tmp_dir="$1"
+
+	mldsa_supported "${tmp_dir}" || mldsa_skip "${tmp_dir}"
+	key_id=$(cat ${tmp_dir}/signing_key.der |
+		 keyctl padd asymmetric ebpf_testing_key @s)
+	keyring_id=$(keyctl newring ebpf_testing_keyring @s)
+	keyctl link $key_id $keyring_id
+}
+
 cleanup() {
 	local tmp_dir="$1"
 
@@ -91,7 +142,7 @@ catch()
 	local exit_code="$1"
 	local log_file="$2"
 
-	if [[ "${exit_code}" -ne 0 ]]; then
+	if [[ "${exit_code}" -ne 0 && "${exit_code}" -ne 77 ]]; then
 		cat "${log_file}" >&3
 	fi
 
@@ -110,6 +161,8 @@ main()
 
 	if [[ "${action}" == "setup-rsa" ]]; then
 		setup_rsa "${tmp_dir}"
+	elif [[ "${action}" == "setup-mldsa" ]]; then
+		setup_mldsa "${tmp_dir}"
 	elif [[ "${action}" == "genkey" ]]; then
 		genkey "${tmp_dir}"
 	elif [[ "${action}" == "cleanup" ]]; then
-- 
2.43.0

vmtest.sh currently hardcodes the guest command line, so there is no
way to ask for such a setting without editing the script. Append
$KERNEL_CMDLINE_EXTRA to it when set to it can be used for testing
BPF keyring:

   # KERNEL_CMDLINE_EXTRA="bpf.keyring_unsealed=1" \
	./vmtest.sh -- ./test_progs -t signed_loader

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/vmtest.sh | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 6a3d026d76bd..e7e0b419a0b8 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -107,6 +107,14 @@ Options:
 	-s)		Instead of powering off the VM, start an interactive
 			shell. If <command> is specified, the shell runs after
 			the command finishes executing
+
+Environment variables:
+
+	KERNEL_CMDLINE_EXTRA
+			Extra arguments to append to the guest kernel command
+			line, for tests that need a boot-time setting. e.g:
+
+	  KERNEL_CMDLINE_EXTRA="bpf.keyring_unsealed=1" $0 -- ./test_progs -t signed_loader
 EOF
 }
 
@@ -286,6 +294,12 @@ EOF
 		QEMU_FLAGS=("${HOST_FLAGS[@]}")
 	fi
 
+	local kernel_cmdline="root=/dev/vda rw console=${QEMU_CONSOLE}"
+
+	if [[ -n "${KERNEL_CMDLINE_EXTRA:-}" ]]; then
+		kernel_cmdline+=" ${KERNEL_CMDLINE_EXTRA}"
+	fi
+
 	${QEMU_BINARY} \
 		-nodefaults \
 		-display none \
@@ -294,7 +308,7 @@ EOF
 		-m 4G \
 		-drive file="${rootfs_img}",format=raw,index=1,media=disk,if=virtio,cache=none \
 		-kernel "${kernel_bzimage}" \
-		-append "root=/dev/vda rw console=${QEMU_CONSOLE}"
+		-append "${kernel_cmdline}"
 }
 
 copy_logs()
-- 
2.43.0

bpf_keyring_provisioned walks the keyring through its whole lifecycle in
one boot for ease of testing. It enrolls a freshly generated key into the
bpf keyring, confirms a load is still refused with -ENOKEY while the keyring
carries no restriction, then restricts it, and only then does the same
signed BPF program load with the bpf keyring. A caller-supplied keyring is
asserted to be refused both before and after the restriction, since what
refuses it is bpf.keyring_unsealed=1 rather than the state of the keyring.

Unsealing is a boot-time decision which also refuses the session keyring
that every other subtest here signs against, so such a boot goes straight
to this test and a regular run covers the rest. Without bpf.keyring_unsealed=1
on the vmtest guest command line the subtest is not registered at all, since
a sealed keyring can never be provisioned.

Regular run:

  # LDLIBS=-static PKG_CONFIG='pkg-config --static' ./vmtest.sh -- ./test_progs -t signed_loader
  [...]
  #424/12  signed_loader/signature_zero_size:OK
  #424/13  signed_loader/signature_bad_keyring:OK
  #424/14  signed_loader/bpf_keyring_sealed:OK
  [...]
  #424/30  signed_loader/signed_map_by_fd_rejected:OK
  #424/31  signed_loader/signed_sparse_fd_array_rejected:OK
  #424     signed_loader:OK
  Summary: 1/31 PASSED, 0 SKIPPED, 0/0 FAILED

Unsealed run:

  # KERNEL_CMDLINE_EXTRA="bpf.keyring_unsealed=1" \
    LDLIBS=-static PKG_CONFIG='pkg-config --static' ./vmtest.sh -- ./test_progs -t signed_loader
  #424/1   signed_loader/bpf_keyring_provisioned:OK
  #424     signed_loader:OK
  Summary: 1/1 PASSED, 0 SKIPPED, 0/0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 .../selftests/bpf/prog_tests/signed_loader.c  | 362 +++++++++++++++++-
 1 file changed, 356 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/signed_loader.c b/tools/testing/selftests/bpf/prog_tests/signed_loader.c
index a1fa1c37815b..9d2384071a42 100644
--- a/tools/testing/selftests/bpf/prog_tests/signed_loader.c
+++ b/tools/testing/selftests/bpf/prog_tests/signed_loader.c
@@ -69,6 +69,33 @@ static int load_loader(const void *insns, __u32 insns_sz, int map_fd,
 	return fd < 0 ? -errno : fd;
 }
 
+static int load_loader_log(const void *insns, __u32 insns_sz, int map_fd,
+			   const void *sig, __u32 sig_sz, __s32 keyring_id,
+			   __u32 fd_array_cnt, char *log_buf, __u32 log_sz)
+{
+	union bpf_attr attr;
+	int fd;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_type = BPF_PROG_TYPE_SYSCALL;
+	attr.insns = ptr_to_u64(insns);
+	attr.insn_cnt = insns_sz / sizeof(struct bpf_insn);
+	attr.license = ptr_to_u64("Dual BSD/GPL");
+	attr.prog_flags = BPF_F_SLEEPABLE;
+	attr.fd_array = ptr_to_u64(&map_fd);
+	attr.fd_array_cnt = fd_array_cnt;
+	attr.signature = ptr_to_u64(sig);
+	attr.signature_size = sig_sz;
+	attr.keyring_id = keyring_id;
+	attr.log_level = 1;
+	attr.log_buf = ptr_to_u64(log_buf);
+	attr.log_size = log_sz;
+	memcpy(attr.prog_name, "__loader.prog", sizeof("__loader.prog"));
+	fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr,
+		     offsetofend(union bpf_attr, keyring_id));
+	return fd < 0 ? -errno : fd;
+}
+
 static int run_gen_loader(const void *insns, __u32 insns_sz,
 			  const void *data, __u32 data_sz,
 			  const void *excl, __u32 excl_sz,
@@ -170,6 +197,23 @@ static int run_setup(const char *cmd, const char *dir)
 	return -WEXITSTATUS(status);
 }
 
+static void genkey_dir_fini(const char *dir)
+{
+	static const char * const files[] = {
+		"signing_key.der", "signing_key.pem", "x509.genkey",
+	};
+	char path[PATH_MAX];
+	size_t i;
+
+	if (!dir)
+		return;
+	for (i = 0; i < ARRAY_SIZE(files); i++) {
+		snprintf(path, sizeof(path), "%s/%s", dir, files[i]);
+		unlink(path);
+	}
+	rmdir(dir);
+}
+
 static int sign_buf_digest(const char *dir, const void *buf, __u32 len,
 			   void *sig, __u32 *sig_sz, const char *digest)
 {
@@ -186,6 +230,7 @@ static int sign_buf_digest(const char *dir, const void *buf, __u32 len,
 	fd = mkstemp(data_tmpl);
 	if (fd < 0)
 		return -errno;
+	snprintf(sigpath, sizeof(sigpath), "%s.p7s", data_tmpl);
 	if (write(fd, buf, len) != (ssize_t)len) {
 		close(fd);
 		ret = -EIO;
@@ -210,30 +255,28 @@ static int sign_buf_digest(const char *dir, const void *buf, __u32 len,
 		goto out;
 	}
 
-	snprintf(sigpath, sizeof(sigpath), "%s.p7s", data_tmpl);
 	if (stat(sigpath, &st) < 0) {
 		ret = -errno;
 		goto out;
 	}
 	if (st.st_size > (off_t)*sig_sz) {
 		ret = -E2BIG;
-		goto out_sig;
+		goto out;
 	}
 	fd = open(sigpath, O_RDONLY);
 	if (fd < 0) {
 		ret = -errno;
-		goto out_sig;
+		goto out;
 	}
 	if (read(fd, sig, st.st_size) != st.st_size) {
 		close(fd);
 		ret = -EIO;
-		goto out_sig;
+		goto out;
 	}
 	close(fd);
 	*sig_sz = st.st_size;
-out_sig:
-	unlink(sigpath);
 out:
+	unlink(sigpath);
 	unlink(data_tmpl);
 	return ret;
 }
@@ -643,6 +686,68 @@ static void signature_bad_keyring(void)
 	gen_loader_fixture_fini(&f);
 }
 
+static bool keyring_unsealed_boot(void)
+{
+	char val = 0;
+	int fd;
+
+	fd = open("/sys/module/bpf/parameters/keyring_unsealed", O_RDONLY);
+	if (fd < 0)
+		return false;
+	if (read(fd, &val, 1) != 1)
+		val = 0;
+	close(fd);
+	return val == 'Y' || val == '1';
+}
+
+static int bpf_keyring_lookup(int *nr_keys)
+{
+	char line[512], type[32], desc[64];
+	int serial = -ENOENT;
+	FILE *f;
+
+	f = fopen("/proc/keys", "r");
+	if (!f)
+		return -errno;
+
+	while (fgets(line, sizeof(line), f)) {
+		unsigned int hex;
+		char *sum;
+
+		if (sscanf(line, "%x %*s %*s %*s %*s %*s %*s %31s %63s",
+			   &hex, type, desc) != 3)
+			continue;
+		if (strcmp(type, "keyring") || strcmp(desc, ".bpf:"))
+			continue;
+
+		serial = (int)hex;
+		if (nr_keys) {
+			sum = strstr(line, ".bpf: ");
+			*nr_keys = (sum && !strncmp(sum + 6, "empty", 5)) ?
+				   0 : atoi(sum + 6);
+		}
+		break;
+	}
+	fclose(f);
+	return serial;
+}
+
+static long keyctl_ret(int cmd, unsigned long arg2, unsigned long arg3)
+{
+	long ret = syscall(__NR_keyctl, cmd, arg2, arg3);
+
+	return ret < 0 ? -errno : ret;
+}
+
+/*
+ * What the bpf keyring still needs once it is provisioned: KEY_POS_SEARCH for
+ * the in-kernel search during verification, and the user view/read bits so it
+ * stays visible in /proc/keys. Write, search and setattr are what every path
+ * that removes a key goes through, so dropping them is what makes the enrolled
+ * set final.
+ */
+#define BPF_KEYRING_PERM_LOCKED	0x08030000
+
 static void bpf_keyring_sealed(void)
 {
 	static const __u8 junk[64] = {};
@@ -665,6 +770,246 @@ static void bpf_keyring_sealed(void)
 	gen_loader_fixture_fini(&f);
 }
 
+/*
+ * This needs bpf.keyring_unsealed=1 on the guest kernel command line, which
+ * vmtest.sh can pass via KERNEL_CMDLINE_EXTRA. There is no way to unseal the
+ * keyring from here, so without it the test skips. It also only works once
+ * per boot, as restricting a keyring cannot be undone.
+ */
+static void bpf_keyring_provisioned(void)
+{
+	char dir_tmpl[] = "/tmp/bpfkeyringXXXXXX";
+	char bad_tmpl[] = "/tmp/bpfkeyringbadXXXXXX";
+	int map_fd = -1, prog_fd = -1, serial, err;
+	__u8 *sig = NULL, *bad = NULL, *buf = NULL;
+	int nr_keys = 0, der_fd = -1;
+	struct gen_loader_fixture f;
+	__u32 sig_sz = 8192, bad_sz;
+	bool have_fixture = false;
+	char *dir, *bad_dir = NULL;
+	char log_buf[1024] = {};
+	char path[PATH_MAX];
+	__u8 der[4096];
+	ssize_t der_sz;
+
+	serial = bpf_keyring_lookup(&nr_keys);
+	if (serial < 0) {
+		printf("%s:SKIP:no bpf keyring (needs CONFIG_KEYS)\n", __func__);
+		test__skip();
+		return;
+	}
+	if (nr_keys != 0) {
+		printf("%s:SKIP:the bpf keyring has already been provisioned\n",
+		       __func__);
+		test__skip();
+		return;
+	}
+
+	dir = mkdtemp(dir_tmpl);
+	if (!ASSERT_OK_PTR(dir, "mkdtemp"))
+		return;
+	if (!ASSERT_OK(run_setup("genkey", dir), "verify_sig_setup genkey"))
+		goto rmdir;
+
+	snprintf(path, sizeof(path), "%s/signing_key.der", dir);
+	der_fd = open(path, O_RDONLY);
+	if (!ASSERT_OK_FD(der_fd, "open signing_key.der"))
+		goto rmdir;
+	der_sz = read(der_fd, der, sizeof(der));
+	close(der_fd);
+	if (!ASSERT_GT(der_sz, 0, "read signing_key.der"))
+		goto rmdir;
+
+	err = syscall(__NR_add_key, "asymmetric", "", der, (size_t)der_sz,
+		      serial);
+	if (err < 0 && errno == EPERM) {
+		printf("%s:SKIP:the bpf keyring is sealed, need bpf.keyring_unsealed=1\n",
+		       __func__);
+		test__skip();
+		goto rmdir;
+	}
+	if (!ASSERT_GE(err, 0, "add the signing key to the bpf keyring"))
+		goto rmdir;
+
+	/*
+	 * Still inert at this point: the keyring is non-empty but carries no
+	 * restriction, so it is not handed out yet.
+	 */
+	sig = malloc(sig_sz);
+	if (!ASSERT_OK_PTR(sig, "sig buf"))
+		goto out;
+	have_fixture = true;
+	if (gen_loader_fixture_init(&f) != 0)
+		goto out;
+
+	buf = malloc((size_t)f.gopts.insns_sz + f.data_sz);
+	if (!ASSERT_OK_PTR(buf, "signbuf"))
+		goto out;
+	memcpy(buf, f.gopts.insns, f.gopts.insns_sz);
+	memcpy(buf + f.gopts.insns_sz, f.blob, f.data_sz);
+	if (!ASSERT_OK(sign_buf(dir, buf, f.gopts.insns_sz + f.data_sz, sig,
+				&sig_sz), "sign insns||metadata"))
+		goto out;
+
+	map_fd = setup_meta_map(&f);
+	if (!ASSERT_OK_FD(map_fd, "meta_map_unrestricted"))
+		goto out;
+	prog_fd = load_loader(f.gopts.insns, f.gopts.insns_sz, map_fd, sig,
+			      sig_sz, BPF_KEYRING_BPF, 1);
+	close(map_fd);
+	map_fd = -1;
+	ASSERT_EQ(prog_fd, -ENOKEY, "unrestricted keyring still not consulted");
+	if (prog_fd >= 0)
+		close(prog_fd);
+	prog_fd = -1;
+
+	/*
+	 * Enforcement follows the boot flag rather than the keyring's state, so
+	 * a caller-supplied keyring is already refused here, while nothing has
+	 * been provisioned yet.
+	 */
+	map_fd = setup_meta_map(&f);
+	if (!ASSERT_OK_FD(map_fd, "meta_map_session_unprovisioned"))
+		goto out;
+	prog_fd = load_loader(f.gopts.insns, f.gopts.insns_sz, map_fd, sig,
+			      sig_sz, KEY_SPEC_SESSION_KEYRING, 1);
+	close(map_fd);
+	map_fd = -1;
+	ASSERT_EQ(prog_fd, -EPERM, "caller-supplied keyring refused before provisioning");
+	if (prog_fd >= 0)
+		close(prog_fd);
+	prog_fd = -1;
+
+	/* Restricting it is what turns it on. */
+	if (!ASSERT_OK(syscall(__NR_keyctl, KEYCTL_RESTRICT_KEYRING, serial,
+			       NULL, NULL), "restrict bpf keyring"))
+		goto out;
+
+	map_fd = setup_meta_map(&f);
+	if (!ASSERT_OK_FD(map_fd, "meta_map_restricted"))
+		goto out;
+	prog_fd = load_loader(f.gopts.insns, f.gopts.insns_sz, map_fd, sig,
+			      sig_sz, BPF_KEYRING_BPF, 1);
+	close(map_fd);
+	map_fd = -1;
+	if (!ASSERT_OK_FD(prog_fd, "load signed by a key in the .bpf keyring"))
+		goto out;
+	close(prog_fd);
+	prog_fd = -1;
+
+	bad_dir = mkdtemp(bad_tmpl);
+	if (!ASSERT_OK_PTR(bad_dir, "mkdtemp unenrolled"))
+		goto out;
+	if (!ASSERT_OK(run_setup("genkey", bad_dir), "verify_sig_setup genkey unenrolled"))
+		goto out;
+	bad_sz = 8192;
+	bad = malloc(bad_sz);
+	if (!ASSERT_OK_PTR(bad, "bad sig buf"))
+		goto out;
+	if (!ASSERT_OK(sign_buf(bad_dir, buf, f.gopts.insns_sz + f.data_sz, bad,
+				&bad_sz), "sign with an unenrolled key"))
+		goto out;
+
+	map_fd = setup_meta_map(&f);
+	if (!ASSERT_OK_FD(map_fd, "meta_map_unenrolled"))
+		goto out;
+	prog_fd = load_loader_log(f.gopts.insns, f.gopts.insns_sz, map_fd, bad,
+				  bad_sz, BPF_KEYRING_BPF, 1, log_buf,
+				  sizeof(log_buf));
+	close(map_fd);
+	map_fd = -1;
+	ASSERT_EQ(prog_fd, -ENOKEY, "key outside the bpf keyring refused");
+	ASSERT_HAS_SUBSTR(log_buf, "signature verification failed",
+			  "the bpf keyring was consulted");
+	if (prog_fd >= 0)
+		close(prog_fd);
+	prog_fd = -1;
+
+	f.blob[0] ^= 0xff;
+	map_fd = setup_meta_map(&f);
+	f.blob[0] ^= 0xff;
+	if (!ASSERT_OK_FD(map_fd, "meta_map_tampered"))
+		goto out;
+	prog_fd = load_loader(f.gopts.insns, f.gopts.insns_sz, map_fd, sig,
+			      sig_sz, BPF_KEYRING_BPF, 1);
+	close(map_fd);
+	map_fd = -1;
+	ASSERT_EQ(prog_fd, -EKEYREJECTED, "tampered metadata refused");
+	if (prog_fd >= 0)
+		close(prog_fd);
+	prog_fd = -1;
+
+	map_fd = setup_meta_map(&f);
+	if (!ASSERT_OK_FD(map_fd, "meta_map_session"))
+		goto out;
+	prog_fd = load_loader(f.gopts.insns, f.gopts.insns_sz, map_fd, sig,
+			      sig_sz, KEY_SPEC_SESSION_KEYRING, 1);
+	close(map_fd);
+	map_fd = -1;
+	ASSERT_EQ(prog_fd, -EPERM, "caller-supplied keyring refused once .bpf is in use");
+	if (prog_fd >= 0)
+		close(prog_fd);
+	prog_fd = -1;
+
+	/*
+	 * The restriction bounds what can be added and not what can be taken
+	 * away, so the keyring is still writable here. Probe it with a key that
+	 * is not a member: the permission check on the keyring is what is under
+	 * test, and -ENOENT means it passed and only the removal itself did not
+	 * find anything.
+	 */
+	err = keyctl_ret(KEYCTL_UNLINK, KEY_SPEC_SESSION_KEYRING, serial);
+	ASSERT_EQ(err, -ENOENT, "keyring writable while the user bits are there");
+
+	/* Dropping the bits it no longer needs is what makes the set final. */
+	err = keyctl_ret(KEYCTL_SETPERM, serial, BPF_KEYRING_PERM_LOCKED);
+	if (!ASSERT_OK(err, "drop the user bits on the bpf keyring"))
+		goto out;
+
+	/* Verification runs on KEY_POS_SEARCH, so a load is unaffected. */
+	map_fd = setup_meta_map(&f);
+	if (!ASSERT_OK_FD(map_fd, "meta_map_locked"))
+		goto out;
+	prog_fd = load_loader(f.gopts.insns, f.gopts.insns_sz, map_fd, sig,
+			      sig_sz, BPF_KEYRING_BPF, 1);
+	close(map_fd);
+	map_fd = -1;
+	ASSERT_OK_FD(prog_fd, "load still verified against the locked keyring");
+	if (prog_fd >= 0)
+		close(prog_fd);
+	prog_fd = -1;
+
+	err = keyctl_ret(KEYCTL_UNLINK, KEY_SPEC_SESSION_KEYRING, serial);
+	ASSERT_EQ(err, -EACCES, "unlink refused");
+	err = keyctl_ret(KEYCTL_CLEAR, serial, 0);
+	ASSERT_EQ(err, -EACCES, "clear refused");
+	err = keyctl_ret(KEYCTL_REVOKE, serial, 0);
+	ASSERT_EQ(err, -EACCES, "revoke refused");
+	err = keyctl_ret(KEYCTL_INVALIDATE, serial, 0);
+	ASSERT_EQ(err, -EACCES, "invalidate refused");
+	err = keyctl_ret(KEYCTL_SET_TIMEOUT, serial, 1);
+	ASSERT_EQ(err, -EACCES, "timeout refused");
+	err = keyctl_ret(KEYCTL_SETPERM, serial, 0x082f0000);
+	ASSERT_EQ(err, -EACCES, "the bits cannot be granted back");
+
+	/* Nothing above got through: the keyring still holds its one key. */
+	ASSERT_EQ(bpf_keyring_lookup(&nr_keys), serial, "keyring still there");
+	ASSERT_EQ(nr_keys, 1, "the enrolled key survived");
+out:
+	if (prog_fd >= 0)
+		close(prog_fd);
+	if (map_fd >= 0)
+		close(map_fd);
+	if (have_fixture)
+		gen_loader_fixture_fini(&f);
+	genkey_dir_fini(bad_dir);
+	free(buf);
+	free(bad);
+	free(sig);
+rmdir:
+	genkey_dir_fini(dir);
+}
+
 /*
  * A signed loader must ignore ctx-supplied map dimensions: the host cannot
  * resize a signed program's maps via the loader ctx. Drive a one-map program
@@ -1899,6 +2244,11 @@ static void signed_module_kfunc_rejected(void)
 
 void test_signed_loader(void)
 {
+	if (keyring_unsealed_boot()) {
+		if (test__start_subtest("bpf_keyring_provisioned"))
+			bpf_keyring_provisioned();
+		return;
+	}
 	if (test__start_subtest("loadtime_no_map"))
 		loadtime_no_map();
 	if (test__start_subtest("loadtime_with_map"))
-- 
2.43.0

Key generation is detailled for RSA and ML-DSA, the load example sets
keyring_id to the bpf keyring with the session keyring shown only as
the staging variant, and the LSM admission example anchors on the bpf
keyring while allowlisting staged serials rather than treating a user
keyring as ordinary trust.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 Documentation/bpf/signing.rst | 274 +++++++++++++++++++++++++++++-----
 1 file changed, 237 insertions(+), 37 deletions(-)

diff --git a/Documentation/bpf/signing.rst b/Documentation/bpf/signing.rst
index e73eaaebd8b1..e35997746267 100644
--- a/Documentation/bpf/signing.rst
+++ b/Documentation/bpf/signing.rst
@@ -254,21 +254,25 @@ returned. Only after the program has fully loaded, at the next hook
 (``security_bpf_prog()``), does ``BPF_SIG_VERIFIED`` carry its full meaning:
 validly signed *and* fully verified.
 
-A more realistic admission policy than "is it signed at all": accept programs
-signed by a system keyring, accept a user-keyring signature only if the
-key/keyring it was verified against is on an explicit allowlist, and emit a
-tamper-evident record of every decision so that even denied attempts are
-auditable. (Illustrative - error checking elided.)
+A more realistic admission policy than "is it signed at all": base trust in
+the bpf keyring, accept a staging signature only while the key/keyring the
+program was verified against is on an explicit allowlist, and emit a tamper-
+evident record of every decision so that even denied attempts are auditable.
+(illustrative - error checking elided.)
 
 .. code-block:: c
 
-    /* Serials of user keys/keyrings we additionally trust. */
+    /*
+     * Serials of caller-supplied keyrings we are willing to stage. Empty
+     * on a system that has committed to the bpf keyring, where the kernel
+     * refuses them anyway.
+     */
     struct {
             __uint(type, BPF_MAP_TYPE_HASH);
             __type(key, __s32);             /* keyring_serial */
             __type(value, __u8);
             __uint(max_entries, 64);
-    } trusted_user_keys SEC(".maps");
+    } staging_keys SEC(".maps");
 
     /* Audit stream consumed by a userspace logger. */
     struct {
@@ -291,11 +295,19 @@ auditable. (Illustrative - error checking elided.)
             if (kernel)
                     return 0;                       /* trust in-kernel loads */
 
-            if (verdict != BPF_SIG_VERIFIED)
+            if (verdict != BPF_SIG_VERIFIED) {
                     ret = -EPERM;                   /* must be validly signed */
-            else if (ktype == BPF_SIG_KEYRING_USER &&
-                     !bpf_map_lookup_elem(&trusted_user_keys, &serial))
-                    ret = -EPERM;                   /* key/keyring not allowlisted */
+            } else switch (ktype) {
+            case BPF_SIG_KEYRING_BUILTIN:
+            case BPF_SIG_KEYRING_BPF:
+                    break;
+            case BPF_SIG_KEYRING_USER:
+                    if (!bpf_map_lookup_elem(&staging_keys, &serial))
+                            ret = -EPERM;
+                    break;
+            default:
+                    ret = -EPERM;                   /* keyring not in policy */
+            }
 
             d = bpf_ringbuf_reserve(&audit, sizeof(*d), 0);
             if (d) {
@@ -309,6 +321,10 @@ auditable. (Illustrative - error checking elided.)
             return ret;
     }
 
+Such a policy is what makes a caller-supplied keyring usable at all before
+``bpf.keyring_unsealed=1`` is set: the allowlist bounds which staged keys
+count, and the LSM itself has to protect them from being tampered with.
+
 Observing a verified load: ``security_bpf_prog()``
 --------------------------------------------------
 
@@ -381,8 +397,9 @@ that verdict covered all of its exclusive maps, rejecting any that did not - so
 a deny-by-default admission policy needs no second enforcement point. Use
 ``security_bpf_prog()`` to record or finally gate the verified programs once
 they carry an id. The ``verdict``, ``keyring_type`` and ``keyring_serial`` fields
-let a policy distinguish, for example, "verified and signed by a builtin key"
-from "verified by a user key". A policy LSM such as IPE could consume the same
+let a policy distinguish "verified against the operator's bpf keyring" from
+"verified against a keyring the loader supplied itself", which is the
+distinction that matters most. A policy LSM such as IPE could consume the same
 hooks to enforce system policy without writing any BPF, though none implements
 this today.
 
@@ -390,33 +407,152 @@ Keyrings
 ========
 
 ``keyring_id`` selects the trusted keyring the PKCS#7 signature is verified
-against. The well-known ids ``0`` (builtin), ``VERIFY_USE_SECONDARY_KEYRING``
-and ``VERIFY_USE_PLATFORM_KEYRING`` select the corresponding system keyrings;
-any other value is treated as the serial of a user/session key or keyring.
-The keyring is looked up first, before the signature bytes are examined, so a
-signature naming a non-existent keyring is rejected up front, and a failed
-verification aborts the load - so a program that loads successfully with a
-signature always has consistent keyring fields recorded.
+against. Four values are well-known; anything else is taken as the serial of a
+caller-supplied user or session key or keyring:
+
+.. list-table::
+   :header-rows: 1
+
+   * - ``keyring_id``
+     - Keyring
+   * - ``0``
+     - builtin trusted keyring
+   * - ``VERIFY_USE_SECONDARY_KEYRING`` (``1``)
+     - secondary trusted keyring
+   * - ``VERIFY_USE_PLATFORM_KEYRING`` (``2``)
+     - platform keyring
+   * - ``VERIFY_USE_BPF_KEYRING`` (``3``)
+     - the bpf keyring
+   * - anything else
+     - serial of a caller-supplied user/session key or keyring
+
+The keyring is resolved first, before the signature bytes are examined, so a
+signature naming a keyring that cannot be used is rejected up front, and a
+failed verification aborts the load - a program that loads successfully with
+a signature therefore always has consistent keyring fields recorded.
+
+The bpf keyring
+---------------
+
+A system keyring needs a kernel rebuild or a vouched-for enrollment to rotate a
+key, and grants BPF-signing trust to keys trusted for everything else in the
+kernel too. A caller-supplied keyring, at the other extreme, is filled by the
+very process that loads the program and so carries no trust of its own.
+
+The bpf keyring fills that gap and is the trust anchor which a signed BPF
+deployment should be built on top of: a keyring named ``.bpf``, selected with
+``VERIFY_USE_BPF_KEYRING``, that an operator provisions at boot with a key
+scoped to BPF program loading and nothing else in the kernel's trust hierarchy.
+It is owned by the operator rather than by the loader, and rotatable across a
+reboot without touching the kernel image. It is modelled after the dm-verity
+keyring (see ``dm_verity.keyring_unsealed=``) and provisioned the same way: an
+initrd runs the ``keyctl`` steps below before handing off to the rootfs.
+
+Provisioning
+~~~~~~~~~~~~
+
+The keyring is created during ``late_initcall`` and is **sealed empty** by
+default: it carries a reject-all restriction, so no key can ever be added and
+``VERIFY_USE_BPF_KEYRING`` fails with ``-ENOKEY`` for the whole boot.
+
+``bpf.keyring_unsealed=1`` leaves it unrestricted at init so the initrd can
+provision it. The keyring is not linked into any process keyring, so it is
+addressed by the serial ``/proc/keys`` reports. Steps would be as follows::
+
+    serial=$(awk '$8 == "keyring" && $9 == ".bpf:" { print strtonum("0x" $1) }' \
+             /proc/keys)
+
+    keyctl padd asymmetric "" $serial < signing_key.der
+    keyctl restrict_keyring $serial
+
+Both steps are required: the keyring is consulted only once it is **non-empty
+and restricted**. An unrestricted keyring is ignored even when it holds keys,
+so a half-provisioned keyring is inert rather than a weaker trust anchor, and a
+load naming it fails with ``-ENOKEY`` and a verifier log. Restricting cannot
+be undone.
+
+More than one key is enrolled by repeating the ``keyctl padd`` step; the
+restriction is applied once, after the last of them::
+
+    for key in /etc/bpf/keys/*.der; do
+        keyctl padd asymmetric "" $serial < $key
+    done
+
+    keyctl restrict_keyring $serial
+    keyctl show $serial
+
+The restriction bounds what can be added, never what can be taken away. A key
+that is already enrolled can still be unlinked, and the keyring cleared or
+revoked, by anything running as root. That does not weaken the anchor, since
+a keyring left empty is no longer consulted and a load naming it fails with
+``-ENOKEY``, but it does take signed loading out until the next boot. Dropping
+the user permissions the keyring no longer needs would close that; as a third
+step in the initrd::
+
+    keyctl setperm $serial 0x08030000
+
+What remains is ``KEY_POS_SEARCH`` for the in-kernel search during verification,
+plus ``KEY_USR_VIEW`` and ``KEY_USR_READ`` so the keyring stays visible in
+``/proc/keys`` and ``keyctl show``.
+
+Provisioning has to complete before control passes to the rootfs. The keyring
+is unrestricted for as long as it is unsealed, so the first writer wins: an
+initrd that hands off before restricting leaves that window open to whatever
+runs next.
+
+Enforcement
+~~~~~~~~~~~
+
+``bpf.keyring_unsealed=1`` states that the bpf keyring is *the* trust anchor for
+this boot, so it does more than unseal. From the first program load onwards a
+caller-supplied user/session keyring is refused with ``-EPERM`` and a verifier
+log message, whether or not provisioning ever completed. The system keyrings
+stay selectable.
+
+Enforcement is readable at ``/sys/module/bpf/parameters/keyring_unsealed``. It
+is therefore immutable from userspace, and there is no window early in boot
+during which a caller-supplied keyring is still accepted.
+
+Caller-supplied keyrings are for staging
+----------------------------------------
+
+A ``keyring_id`` naming a user or session key or keyring is a *staging*
+mechanism, not a trust anchor: it is filled by the same userspace that loads the
+program, so verifying against it establishes only that the loader signed what it
+loaded. Its purpose is to let software installed onto a running system - whose
+signing key is not enrolled anywhere yet - run signed until that key reaches the
+bpf keyring on the next boot.
+
+A system that has committed to the bpf keyring refuses this path outright (see
+`Enforcement`_). A system that has not can still allow it, but a policy must
+never treat ``BPF_SIG_KEYRING_USER`` as equivalent to the bpf or system
+keyrings; it should allowlist the specific serials it is willing to stage and
+pair that with a BPF LSM policy protecting those keys from tampering, as in
+`Enforcement via LSMs`_.
+
+Recorded fields
+---------------
 
 Two fields are recorded in ``prog->aux->sig`` for an LSM to inspect:
 
 ``keyring_type`` (``enum bpf_sig_keyring``)
     Classified purely from ``keyring_id`` whenever the program is signed:
     ``BPF_SIG_KEYRING_BUILTIN``, ``_SECONDARY``, ``_PLATFORM`` for the system
-    keyrings, or ``_USER`` for a user/session keyring. It is
-    ``BPF_SIG_KEYRING_NONE`` for an unsigned program.
+    keyrings, ``_BPF`` for the bpf keyring, or ``_USER`` for a caller-supplied
+    user/session keyring. It is ``BPF_SIG_KEYRING_NONE`` for an unsigned
+    program.
 
 ``keyring_serial`` (``s32``)
     Set **only** on a successful verification, to the serial of the
-    **user/session key or keyring** that ``keyring_id`` resolved to - the
+    **caller-supplied key or keyring** that ``keyring_id`` resolved to - the
     object the signature was verified against, not the individual asymmetric
     key inside it that matched the signer. Passing
     ``KEY_SPEC_SESSION_KEYRING``, for example, records the session keyring's
-    serial. The system keyrings are trusted as a whole and expose no serial
-    here, so the serial is ``0`` for builtin, secondary and platform
-    signatures, and ``0`` for unsigned programs. In other words, a non-zero
-    ``keyring_serial`` is exactly "verified against the user key/keyring with
-    this serial".
+    serial. The system keyrings and the bpf keyring are trusted as a whole and
+    expose no serial here, so the serial is ``0`` for them, and ``0`` for
+    unsigned programs. A non-zero ``keyring_serial`` is therefore exactly
+    "verified against the caller-supplied key/keyring with this serial", which
+    is exactly the case a policy has to scrutinise.
 
 .. list-table::
    :header-rows: 1
@@ -436,16 +572,47 @@ Two fields are recorded in ``prog->aux->sig`` for an LSM to inspect:
    * - ``VERIFY_USE_PLATFORM_KEYRING``
      - ``BPF_SIG_KEYRING_PLATFORM``
      - ``0``
-   * - other (a user/session key serial)
+   * - ``VERIFY_USE_BPF_KEYRING``
+     - ``BPF_SIG_KEYRING_BPF``
+     - ``0``
+   * - other (a caller-supplied key serial)
      - ``BPF_SIG_KEYRING_USER``
      - serial of the resolved key/keyring
 
-Producing a signed object
-==========================
+Producing and loading a signed object
+=====================================
+
+Generating a signing key
+------------------------
+
+Signing is algorithm agnostic: the algorithm comes from the X.509 certificate
+and the PKCS#7 ``SignerInfo``. Anything the X.509 and PKCS#7 parsers understand
+works with no BPF-side change. RSA::
+
+    openssl req -new -nodes -utf8 -sha256 -days 36500 -batch -x509 \
+            -config x509.genkey -outform PEM \
+            -out signing_key.pem -keyout signing_key.pem
+    openssl x509 -in signing_key.pem -outform der -out signing_key.der
+
+ML-DSA-87 (FIPS-204), which needs openssl 3.5 or later and ``CONFIG_CRYPTO_MLDSA``
+in the kernel. Note the absence of a digest option: ML-DSA hashes the message
+itself and openssl rejects an explicit digest for it::
+
+    openssl req -new -nodes -utf8 -days 36500 -batch -x509 \
+            -newkey ML-DSA-87 -config x509.genkey -outform PEM \
+            -out signing_key.pem -keyout signing_key.pem
+    openssl x509 -in signing_key.pem -outform der -out signing_key.der
+
+``bpftool`` handles the following internally: openssl 3.5 and earlier cannot
+combine ML-DSA with ``CMS_NOATTR``, so it falls back to signedAttrs, where
+only SHA-512 is permitted. This mirrors what module signing does as well.
+
+Signing
+-------
 
 ``bpftool`` generates and signs a light skeleton in one step::
 
-    bpftool gen skeleton -L -S -k <private_key.pem> -i <certificate.x509> \
+    bpftool gen skeleton -L -S -k signing_key.pem -i signing_key.der \
             obj.bpf.o > obj.lskel.h
 
 ``-L`` selects the light-skeleton (``gen_loader``) backend and ``-S`` enables
@@ -454,12 +621,36 @@ signing; ``-k`` and ``-i`` supply the signing key and its X.509 certificate.
 reconstructs - and also computes ``excl_prog_hash`` as the digest of the loader
 instructions so the metadata map can be bound to the loader. The signature and
 hash are embedded in the generated header; the certificate is used only for
-signing and is not included. Loading the skeleton performs the
-create/populate/freeze/load sequence described above.
+signing and is not included.
+
+Loading
+-------
+
+The generated skeleton exposes ``keyring_id``, which selects the keyring the
+kernel verifies against. Set it between open and load; loading then performs
+the create/populate/freeze/load sequence described above::
 
-At runtime the trusted public key must be present in the chosen keyring (for
-example added to the session keyring, or built into the kernel's builtin trusted
-keyring) for verification to succeed.
+    struct obj *skel = obj__open();
+
+    skel->keyring_id = 3;           /* VERIFY_USE_BPF_KEYRING */
+    err = obj__load(skel);
+
+For the staging case the same object is loaded against a keyring the caller
+populated itself, which only works on a system that has not set
+``bpf.keyring_unsealed=1``::
+
+    /*
+     * Staging only: this keyring is under the loader's own control and
+     * carries no trust of its own. See "Caller-supplied keyrings are for
+     * staging".
+     */
+    key_id = add_key("asymmetric", "", der, der_sz, KEY_SPEC_SESSION_KEYRING);
+    skel->keyring_id = KEY_SPEC_SESSION_KEYRING;
+    err = obj__load(skel);
+
+Either way the trusted public key must already be in the chosen keyring for
+verification to succeed. For the bpf keyring that enrollment happens once at
+boot, see `Provisioning`_.
 
 UAPI reference
 ==============
@@ -487,6 +678,13 @@ UAPI reference
     The map content is not hashed separately at all - it is covered, as bytes,
     by the program signature.
 
+Kernel command line:
+
+``bpf.keyring_unsealed=``
+    Set to ``1`` to leave the bpf keyring unsealed for provisioning, and to make
+    it the only non-system keyring a loader may select for the rest of the boot
+    (see `The bpf keyring`_).
+
 Notes and limitations
 ======================
 
@@ -495,3 +693,5 @@ Notes and limitations
   exceed it.
 - The metadata container is a single-element array map, accessed through
   ``map_direct_value_addr``.
+- The bpf keyring needs ``CONFIG_KEYS``; without it there is no bpf keyring
+  and ``VERIFY_USE_BPF_KEYRING`` never resolves.
-- 
2.43.0