[PATCH v3 seccomp 3/5] seccomp/cache: Lookup syscall allowlist for fast path

From: YiFei Zhu <zhuyifei1999@gmail.com>
To: containers@lists.linux-foundation.org
Cc: Andrea Arcangeli <aarcange@redhat.com>,
	Giuseppe Scrivano <gscrivan@redhat.com>,
	Valentin Rothberg <vrothber@redhat.com>,
	Kees Cook <keescook@chromium.org>, Jann Horn <jannh@google.com>,
	YiFei Zhu <yifeifz2@illinois.edu>,
	Tobin Feldman-Fitzthum <tobin@ibm.com>,
	linux-kernel@vger.kernel.org,
	Andy Lutomirski <luto@amacapital.net>,
	Hubertus Franke <frankeh@us.ibm.com>,
	David Laight <David.Laight@aculab.com>,
	Jack Chen <jianyan2@illinois.edu>,
	Dimitrios Skarlatos <dskarlat@cs.cmu.edu>,
	Josep Torrellas <torrella@illinois.edu>,
	Will Drewry <wad@chromium.org>,
	bpf@vger.kernel.org, Tianyin Xu <tyxu@illinois.edu>
Subject: [PATCH v3 seccomp 3/5] seccomp/cache: Lookup syscall allowlist for fast path
Date: Wed, 30 Sep 2020 10:19:14 -0500	[thread overview]
Message-ID: <83c72471f9f79fa982508bd4db472686a67b8320.1601478774.git.yifeifz2@illinois.edu> (raw)
In-Reply-To: <cover.1601478774.git.yifeifz2@illinois.edu>

From: YiFei Zhu <yifeifz2@illinois.edu>

The fast (common) path for seccomp should be that the filter permits
the syscall to pass through, and failing seccomp is expected to be
an exceptional case; it is not expected for userspace to call a
denylisted syscall over and over.

This first finds the current allow bitmask by iterating through
syscall_arches[] array and comparing it to the one in struct
seccomp_data; this loop is expected to be unrolled. It then
does a test_bit against the bitmask. If the bit is set, then
there is no need to run the full filter; it returns
SECCOMP_RET_ALLOW immediately.

Co-developed-by: Dimitrios Skarlatos <dskarlat@cs.cmu.edu>
Signed-off-by: Dimitrios Skarlatos <dskarlat@cs.cmu.edu>
Signed-off-by: YiFei Zhu <yifeifz2@illinois.edu>
---
 kernel/seccomp.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index f09c9e74ae05..bed3b2a7f6c8 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -172,6 +172,12 @@ struct seccomp_cache_filter_data { };
 static inline void seccomp_cache_prepare(struct seccomp_filter *sfilter)
 {
 }
+
+static inline bool seccomp_cache_check(const struct seccomp_filter *sfilter,
+				       const struct seccomp_data *sd)
+{
+	return false;
+}
 #endif /* CONFIG_SECCOMP_CACHE_NR_ONLY */
 
 /**
@@ -331,6 +337,49 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
 	return 0;
 }
 
+#ifdef CONFIG_SECCOMP_CACHE_NR_ONLY
+static bool seccomp_cache_check_bitmap(const void *bitmap, size_t bitmap_size,
+				       int syscall_nr)
+{
+	if (unlikely(syscall_nr < 0 || syscall_nr >= bitmap_size))
+		return false;
+	syscall_nr = array_index_nospec(syscall_nr, bitmap_size);
+
+	return test_bit(syscall_nr, bitmap);
+}
+
+/**
+ * seccomp_cache_check - lookup seccomp cache
+ * @sfilter: The seccomp filter
+ * @sd: The seccomp data to lookup the cache with
+ *
+ * Returns true if the seccomp_data is cached and allowed.
+ */
+static bool seccomp_cache_check(const struct seccomp_filter *sfilter,
+				const struct seccomp_data *sd)
+{
+	int syscall_nr = sd->nr;
+	const struct seccomp_cache_filter_data *cache = &sfilter->cache;
+
+#ifdef SECCOMP_ARCH_DEFAULT
+	if (likely(sd->arch == SECCOMP_ARCH_DEFAULT))
+		return seccomp_cache_check_bitmap(cache->syscall_allow_default,
+						  SECCOMP_ARCH_DEFAULT_NR,
+						  syscall_nr);
+#endif /* SECCOMP_ARCH_DEFAULT */
+
+#ifdef SECCOMP_ARCH_COMPAT
+	if (likely(sd->arch == SECCOMP_ARCH_COMPAT))
+		return seccomp_cache_check_bitmap(cache->syscall_allow_compat,
+						  SECCOMP_ARCH_COMPAT_NR,
+						  syscall_nr);
+#endif /* SECCOMP_ARCH_COMPAT */
+
+	WARN_ON_ONCE(true);
+	return false;
+}
+#endif /* CONFIG_SECCOMP_CACHE_NR_ONLY */
+
 /**
  * seccomp_run_filters - evaluates all seccomp filters against @sd
  * @sd: optional seccomp data to be passed to filters
@@ -353,6 +402,9 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd,
 	if (WARN_ON(f == NULL))
 		return SECCOMP_RET_KILL_PROCESS;
 
+	if (seccomp_cache_check(f, sd))
+		return SECCOMP_RET_ALLOW;
+
 	/*
 	 * All filters in the list are evaluated and the lowest BPF return
 	 * value always takes priority (ignoring the DATA).
-- 
2.28.0

_______________________________________________
Containers mailing list
Containers@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/containers
