| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1329845435-2313-6-git-send-email-wad@chromium.org>
Date: Tue, 21 Feb 2012 11:30:30 -0600
From: Will Drewry <wad@...omium.org>
To: linux-kernel@...r.kernel.org
Cc: linux-arch@...r.kernel.org, linux-doc@...r.kernel.org,
kernel-hardening@...ts.openwall.com, netdev@...r.kernel.org,
x86@...nel.org, arnd@...db.de, davem@...emloft.net, hpa@...or.com,
mingo@...hat.com, oleg@...hat.com, peterz@...radead.org,
rdunlap@...otime.net, mcgrathr@...omium.org, tglx@...utronix.de,
luto@....edu, eparis@...hat.com, serge.hallyn@...onical.com,
djm@...drot.org, scarybeasts@...il.com, indan@....nu,
pmoore@...hat.com, akpm@...ux-foundation.org, corbet@....net,
eric.dumazet@...il.com, markus@...omium.org, keescook@...omium.org,
Will Drewry <wad@...omium.org>
Subject: [PATCH v10 06/11] seccomp: add SECCOMP_RET_ERRNO
This change adds the SECCOMP_RET_ERRNO as a valid return value from a
seccomp filter. Additionally, it makes the first use of the lower
16-bits for storing a filter-supplied errno. 16-bits is more than
enough for the errno-base.h calls.
Returning errors instead of immediately terminating processes that
violate seccomp policy allow for broader use of this functionality
for kernel attack surface reduction. For example, a linux container
could maintain a whitelist of pre-existing system calls but drop
all new ones with errnos. This would keep a logically static attack
surface while providing errnos that may allow for graceful failure
without the downside of do_exit() on a bad call.
v10: - change loaders to fn
v9: - n/a
v8: - update Kconfig to note new need for syscall_set_return_value.
- reordered such that TRAP behavior follows on later.
- made the for loop a little less indent-y
v7: - introduced
Signed-off-by: Will Drewry <wad@...omium.org>
---
arch/Kconfig | 6 ++++--
include/linux/seccomp.h | 15 +++++++++++----
kernel/seccomp.c | 39 ++++++++++++++++++++++++++++-----------
3 files changed, 43 insertions(+), 17 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 8150fa2..aa00571 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -203,8 +203,10 @@ config HAVE_ARCH_SECCOMP_FILTER
bool
help
This symbol should be selected by an architecure if it provides
- asm/syscall.h, specifically syscall_get_arguments() and
- syscall_get_arch().
+ asm/syscall.h, specifically syscall_get_arguments(),
+ syscall_get_arch(), and syscall_set_return_value(). Additionally,
+ its system call entry path must respect a return value of -1 from
+ __secure_computing_int() and/or secure_computing().
config SECCOMP_FILTER
def_bool y
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 001f883..54ecb61 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -12,13 +12,14 @@
/*
* BPF programs may return a 32-bit value.
- * The bottom 16-bits are reserved for future use.
+ * The bottom 16-bits are for optional related return data.
* The upper 16-bits are ordered from least permissive values to most.
*
* The ordering ensures that a min_t() over composed return values always
* selects the least permissive choice.
*/
#define SECCOMP_RET_KILL 0x00000000U /* kill the task immediately */
+#define SECCOMP_RET_ERRNO 0x00030000U /* returns an errno */
#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */
/* Masks for the return value sections. */
@@ -64,11 +65,17 @@ struct seccomp {
struct seccomp_filter *filter;
};
-extern void __secure_computing(int);
-static inline void secure_computing(int this_syscall)
+/*
+ * Direct callers to __secure_computing should be updated as
+ * CONFIG_HAVE_ARCH_SECCOMP_FILTER propagates.
+ */
+extern void __secure_computing(int) __deprecated;
+extern int __secure_computing_int(int);
+static inline int secure_computing(int this_syscall)
{
if (unlikely(test_thread_flag(TIF_SECCOMP)))
- __secure_computing(this_syscall);
+ return __secure_computing_int(this_syscall);
+ return 0;
}
extern long prctl_get_seccomp(void);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 0043b7e..23f1844 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -136,22 +136,18 @@ static void *bpf_load(const void *nr, int off, unsigned int size, void *buf)
static u32 seccomp_run_filters(int syscall)
{
struct seccomp_filter *f;
- u32 ret = SECCOMP_RET_KILL;
static const struct bpf_load_fn fns = {
bpf_load,
sizeof(struct seccomp_data),
};
+ u32 ret = SECCOMP_RET_ALLOW;
const void *sc_ptr = (const void *)(uintptr_t)syscall;
-
/*
* All filters are evaluated in order of youngest to oldest. The lowest
* BPF return value always takes priority.
*/
- for (f = current->seccomp.filter; f; f = f->prev) {
- ret = bpf_run_filter(sc_ptr, f->insns, &fns);
- if (ret != SECCOMP_RET_ALLOW)
- break;
- }
+ for (f = current->seccomp.filter; f; f = f->prev)
+ ret = min_t(u32, ret, bpf_run_filter(sc_ptr, f->insns, &fns));
return ret;
}
@@ -304,6 +300,13 @@ static int mode1_syscalls_32[] = {
void __secure_computing(int this_syscall)
{
+ /* Filter calls should never use this function. */
+ BUG_ON(current->seccomp.mode == SECCOMP_MODE_FILTER);
+ __secure_computing_int(this_syscall);
+}
+
+int __secure_computing_int(int this_syscall)
+{
int mode = current->seccomp.mode;
int *syscall;
@@ -316,15 +319,28 @@ void __secure_computing(int this_syscall)
#endif
do {
if (*syscall == this_syscall)
- return;
+ return 0;
} while (*++syscall);
break;
#ifdef CONFIG_SECCOMP_FILTER
- case SECCOMP_MODE_FILTER:
- if (seccomp_run_filters(this_syscall) == SECCOMP_RET_ALLOW)
- return;
+ case SECCOMP_MODE_FILTER: {
+ u32 action = seccomp_run_filters(this_syscall);
+ switch (action & SECCOMP_RET_ACTION) {
+ case SECCOMP_RET_ERRNO:
+ /* Set the low-order 16-bits as a errno. */
+ syscall_set_return_value(current, task_pt_regs(current),
+ -(action & SECCOMP_RET_DATA),
+ 0);
+ return -1;
+ case SECCOMP_RET_ALLOW:
+ return 0;
+ case SECCOMP_RET_KILL:
+ default:
+ break;
+ }
seccomp_filter_log_failure(this_syscall);
break;
+ }
#endif
default:
BUG();
@@ -335,6 +351,7 @@ void __secure_computing(int this_syscall)
#endif
audit_seccomp(this_syscall);
do_exit(SIGKILL);
+ return -1; /* never reached */
}
long prctl_get_seccomp(void)
--
1.7.5.4
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists