[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Thu, 29 Mar 2012 15:01:55 -0500
From: Will Drewry <wad@...omium.org>
To: linux-kernel@...r.kernel.org
Cc: linux-security-module@...r.kernel.org,
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,
coreyb@...ux.vnet.ibm.com,
keescook@...omium.org,
jmorris@...ei.org,
Will Drewry <wad@...omium.org>
Subject: [PATCH v17 10/15] 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.
v17: rebase
v16: -
v15: - use audit_seccomp and add a skip label. (eparis@...hat.com)
- clean up and pad out return codes (indan@....nu)
v14: - no change/rebase
v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc
v12: - move to WARN_ON if filter is NULL
(oleg@...hat.com, luto@....edu, keescook@...omium.org)
- return immediately for filter==NULL (keescook@...omium.org)
- change evaluation to only compare the ACTION so that layered
errnos don't result in the lowest one being returned.
(keeschook@...omium.org)
v11: - check for NULL filter (keescook@...omium.org)
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
Reviewed-by: Kees Cook <keescook@...omium.org>
Acked-by: Serge Hallyn <serge.hallyn@...onical.com>
Signed-off-by: Will Drewry <wad@...omium.org>
---
arch/Kconfig | 6 ++++--
include/linux/seccomp.h | 15 +++++++++++----
kernel/seccomp.c | 47 ++++++++++++++++++++++++++++++++++++++---------
3 files changed, 53 insertions(+), 15 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 697304d..9ba3003 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -217,8 +217,10 @@ 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 86bb68f..44004df 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -12,13 +12,14 @@
/*
* All BPF programs must return a 32-bit value.
- * The bottom 16-bits are reserved for future use.
+ * The bottom 16-bits are for optional 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 0x00050000U /* 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 85cbe37..06b97aa 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -195,15 +195,20 @@ static int seccomp_chk_filter(struct sock_filter *filter, unsigned int flen)
static u32 seccomp_run_filters(int syscall)
{
struct seccomp_filter *f;
- u32 ret = SECCOMP_RET_KILL;
+ u32 ret = SECCOMP_RET_ALLOW;
+
+ /* Ensure unexpected behavior doesn't result in failing open. */
+ if (WARN_ON(current->seccomp.filter == NULL))
+ return SECCOMP_RET_KILL;
+
/*
* All filters are evaluated in order of youngest to oldest. The lowest
- * BPF return value always takes priority.
+ * BPF return value (ignoring the DATA) always takes priority.
*/
for (f = current->seccomp.filter; f; f = f->prev) {
- ret = sk_run_filter(NULL, f->insns);
- if (ret != SECCOMP_RET_ALLOW)
- break;
+ u32 cur_ret = sk_run_filter(NULL, f->insns);
+ if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
+ ret = cur_ret;
}
return ret;
}
@@ -343,9 +348,18 @@ 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 exit_sig = 0;
int *syscall;
+ u32 ret = SECCOMP_RET_KILL;
+ int data;
switch (mode) {
case SECCOMP_MODE_STRICT:
@@ -356,14 +370,26 @@ void __secure_computing(int this_syscall)
#endif
do {
if (*syscall == this_syscall)
- return;
+ return 0;
} while (*++syscall);
exit_sig = SIGKILL;
break;
#ifdef CONFIG_SECCOMP_FILTER
case SECCOMP_MODE_FILTER:
- if (seccomp_run_filters(this_syscall) == SECCOMP_RET_ALLOW)
- return;
+ ret = seccomp_run_filters(this_syscall);
+ data = ret & SECCOMP_RET_DATA;
+ switch (code & 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),
+ -data, 0);
+ goto skip;
+ case SECCOMP_RET_ALLOW:
+ return 0;
+ case SECCOMP_RET_KILL:
+ default:
+ break;
+ }
exit_sig = SIGSYS;
break;
#endif
@@ -374,8 +400,11 @@ void __secure_computing(int this_syscall)
#ifdef SECCOMP_DEBUG
dump_stack();
#endif
- audit_seccomp(this_syscall, exit_code, SECCOMP_RET_KILL);
+ audit_seccomp(this_syscall, exit_sig, ret);
do_exit(exit_sig);
+skip:
+ audit_seccomp(this_syscall, exit_sig, ret);
+ return -1;
}
long prctl_get_seccomp(void)
--
1.7.5.4
Powered by blists - more mailing lists
Confused about mailing lists and their use?
Read about mailing lists on Wikipedia
and check out these
guidelines on proper formatting of your messages.
