Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Kees Cook <keescook@chromium.org>
To:     YiFei Zhu <yifeifz2@illinois.edu>
Cc:     Kees Cook <keescook@chromium.org>, Jann Horn <jannh@google.com>,
        Christian Brauner <christian.brauner@ubuntu.com>,
        Tycho Andersen <tycho@tycho.pizza>,
        Andy Lutomirski <luto@amacapital.net>,
        Will Drewry <wad@chromium.org>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Giuseppe Scrivano <gscrivan@redhat.com>,
        Tobin Feldman-Fitzthum <tobin@ibm.com>,
        Dimitrios Skarlatos <dskarlat@cs.cmu.edu>,
        Valentin Rothberg <vrothber@redhat.com>,
        Hubertus Franke <frankeh@us.ibm.com>,
        Jack Chen <jianyan2@illinois.edu>,
        Josep Torrellas <torrella@illinois.edu>,
        Tianyin Xu <tyxu@illinois.edu>, bpf@vger.kernel.org,
        containers@lists.linux-foundation.org, linux-api@vger.kernel.org,
        linux-kernel@vger.kernel.org
Subject: [PATCH 4/6] seccomp: Emulate basic filters for constant action results
Date:   Wed, 23 Sep 2020 16:29:21 -0700
Message-Id: <20200923232923.3142503-5-keescook@chromium.org>
In-Reply-To: <20200923232923.3142503-1-keescook@chromium.org>
References: <20200923232923.3142503-1-keescook@chromium.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

This emulates absolutely the most basic seccomp filters to figure out
if they will always give the same results for a given arch/nr combo.

Nearly all seccomp filters are built from the following ops:

BPF_LD  | BPF_W    | BPF_ABS
BPF_JMP | BPF_JEQ  | BPF_K
BPF_JMP | BPF_JGE  | BPF_K
BPF_JMP | BPF_JGT  | BPF_K
BPF_JMP | BPF_JSET | BPF_K
BPF_JMP | BPF_JA
BPF_RET | BPF_K

These are now emulated to check for accesses beyond seccomp_data::arch
or unknown instructions.

Not yet implemented are:

BPF_ALU | BPF_AND (generated by libseccomp and Chrome)

Suggested-by: Jann Horn <jannh@google.com>
Link: https://lore.kernel.org/lkml/CAG48ez1p=dR_2ikKq=xVxkoGg0fYpTBpkhJSv1w-6BG=76PAvw@mail.gmail.com/
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 kernel/seccomp.c  | 82 ++++++++++++++++++++++++++++++++++++++++++++---
 net/core/filter.c |  3 +-
 2 files changed, 79 insertions(+), 6 deletions(-)

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 111a238bc532..9921f6f39d12 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -610,7 +610,12 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
 {
 	struct seccomp_filter *sfilter;
 	int ret;
-	const bool save_orig = IS_ENABLED(CONFIG_CHECKPOINT_RESTORE);
+	const bool save_orig =
+#if defined(CONFIG_CHECKPOINT_RESTORE) || defined(SECCOMP_ARCH)
+		true;
+#else
+		false;
+#endif
 
 	if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
 		return ERR_PTR(-EINVAL);
@@ -690,11 +695,78 @@ static inline bool sd_touched(pte_t *ptep)
  * This approach could also be used to test for access to sd->arch too,
  * if we wanted to warn about compat-unsafe filters.
  */
-static inline bool seccomp_filter_action_is_constant(struct bpf_prog *prog,
-						     struct seccomp_data *sd,
-						     u32 *action)
+static bool seccomp_filter_action_is_constant(struct bpf_prog *prog,
+					      struct seccomp_data *sd,
+					      u32 *action)
 {
-	/* No evaluation implementation yet. */
+	struct sock_fprog_kern *fprog = prog->orig_prog;
+	unsigned int insns;
+	unsigned int reg_value = 0;
+	unsigned int pc;
+	bool op_res;
+
+	if (WARN_ON_ONCE(!fprog))
+		return false;
+
+	insns = bpf_classic_proglen(fprog);
+	for (pc = 0; pc < insns; pc++) {
+		struct sock_filter *insn = &fprog->filter[pc];
+		u16 code = insn->code;
+		u32 k = insn->k;
+
+		switch (code) {
+		case BPF_LD | BPF_W | BPF_ABS:
+			switch (k) {
+			case offsetof(struct seccomp_data, nr):
+				reg_value = sd->nr;
+				break;
+			case offsetof(struct seccomp_data, arch):
+				reg_value = sd->arch;
+				break;
+			default:
+				/* can't optimize (non-constant value load) */
+				return false;
+			}
+			break;
+		case BPF_RET | BPF_K:
+			*action = insn->k;
+			/* success: reached return with constant values only */
+			return true;
+		case BPF_JMP | BPF_JA:
+			pc += insn->k;
+			break;
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JSET | BPF_K:
+			switch (BPF_OP(code)) {
+			case BPF_JEQ:
+				op_res = reg_value == k;
+				break;
+			case BPF_JGE:
+				op_res = reg_value >= k;
+				break;
+			case BPF_JGT:
+				op_res = reg_value > k;
+				break;
+			case BPF_JSET:
+				op_res = !!(reg_value & k);
+				break;
+			default:
+				/* can't optimize (unknown jump) */
+				return false;
+			}
+
+			pc += op_res ? insn->jt : insn->jf;
+			break;
+		default:
+			/* can't optimize (unknown insn) */
+			return false;
+		}
+	}
+
+	/* ran off the end of the filter?! */
+	WARN_ON(1);
 	return false;
 }
 
diff --git a/net/core/filter.c b/net/core/filter.c
index b2df52086445..cb1bdb0bfe87 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1145,7 +1145,7 @@ static int bpf_prog_store_orig_filter(struct bpf_prog *fp,
 	return 0;
 }
 
-static void bpf_release_orig_filter(struct bpf_prog *fp)
+void bpf_release_orig_filter(struct bpf_prog *fp)
 {
 	struct sock_fprog_kern *fprog = fp->orig_prog;
 
@@ -1154,6 +1154,7 @@ static void bpf_release_orig_filter(struct bpf_prog *fp)
 		kfree(fprog);
 	}
 }
+EXPORT_SYMBOL_GPL(bpf_release_orig_filter);
 
 static void __bpf_prog_release(struct bpf_prog *prog)
 {
-- 
2.25.1