This patch creates a read-only sysctl containing an ordered list of seccomp actions that the kernel supports. The ordering, from left to right, is the lowest action value (kill) to the highest action value (allow). Currently, a read of the sysctl file would return "kill trap errno trace allow". The contents of this sysctl file can be useful for userspace code as well as the system administrator. The path to the sysctl is: /proc/sys/kernel/seccomp/actions_avail libseccomp and other userspace code can easily determine which actions the current kernel supports. The set of actions supported by the current kernel may be different than the set of action macros found in kernel headers that were installed where the userspace code was built. In addition, this sysctl will allow system administrators to know which actions are supported by the kernel and make it easier to configure exactly what seccomp logs through the audit subsystem. Support for this level of logging configuration will come in a future patch. Signed-off-by: Tyler Hicks <tyhicks(a)canonical.com&gt; --- Documentation/sysctl/kernel.txt | 1 + Documentation/userspace-api/seccomp_filter.rst | 16 ++++++++ kernel/seccomp.c | 51 ++++++++++++++++++++++++++ 3 files changed, 68 insertions(+) diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index bac23c1..995c42c 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -74,6 +74,7 @@ show up in /proc/sys/kernel: - reboot-cmd [ SPARC only ] - rtsig-max - rtsig-nr +- seccomp/ ==> Documentation/userspace-api/seccomp_filter.rst - sem - sem_next_id [ sysv ipc ] - sg-big-buff [ generic SCSI device (sg) ] diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index f71eb5e..35fc7cb 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -169,7 +169,23 @@ The ``samples/seccomp/`` directory contains both an x86-specific example and a more generic example of a higher level macro interface for BPF program generation. +Sysctls +======= + +Seccomp's sysctl files can be found in the ``/proc/sys/kernel/seccomp/`` +directory. Here's a description of each file in that directory: + +``actions_avail``: + A read-only ordered list of seccomp return values (refer to the + ``SECCOMP_RET_*`` macros above) in string form. The ordering, from + left-to-right, is the least permissive return value to the most + permissive return value. + The list represents the set of seccomp return values supported + by the kernel. A userspace program may use this list to + determine if the actions found in the ``seccomp.h``, when the + program was built, differs from the set of actions actually + supported in the current running kernel. Adding architecture support =========================== diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 6a196d1..ee77eb3 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -17,11 +17,13 @@ #include <linux/audit.h> #include <linux/compat.h> #include <linux/coredump.h> +#include <linux/kmemleak.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/seccomp.h> #include <linux/slab.h> #include <linux/syscalls.h> +#include <linux/sysctl.h> #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER #include <asm/syscall.h> @@ -980,3 +982,52 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off, return ret; } #endif + +#ifdef CONFIG_SYSCTL + +/* Human readable action names for friendly sysctl interaction */ +#define SECCOMP_RET_KILL_NAME "kill" +#define SECCOMP_RET_TRAP_NAME "trap" +#define SECCOMP_RET_ERRNO_NAME "errno" +#define SECCOMP_RET_TRACE_NAME "trace" +#define SECCOMP_RET_ALLOW_NAME "allow" + +static const char seccomp_actions_avail[] = SECCOMP_RET_KILL_NAME " " + SECCOMP_RET_TRAP_NAME " " + SECCOMP_RET_ERRNO_NAME " " + SECCOMP_RET_TRACE_NAME " " + SECCOMP_RET_ALLOW_NAME; + +static struct ctl_path seccomp_sysctl_path[] = { + { .procname = "kernel", }, + { .procname = "seccomp", }, + { } +}; + +static struct ctl_table seccomp_sysctl_table[] = { + { + .procname = "actions_avail", + .data = (void *) &seccomp_actions_avail, + .maxlen = sizeof(seccomp_actions_avail), + .mode = 0444, + .proc_handler = proc_dostring, + }, + { } +}; + +static int __init seccomp_sysctl_init(void) +{ + struct ctl_table_header *hdr; + + hdr = register_sysctl_paths(seccomp_sysctl_path, seccomp_sysctl_table); + if (!hdr) + pr_warn("seccomp: sysctl registration failed\n"); + else + kmemleak_not_leak(hdr); + + return 0; +} + +device_initcall(seccomp_sysctl_init) + +#endif /* CONFIG_SYSCTL */ -- 2.7.4

Adminstrators can write to this sysctl to set the seccomp actions that are allowed to be logged. Any actions not found in this sysctl will not be logged. For example, all SECCOMP_RET_KILL, SECCOMP_RET_TRAP, and SECCOMP_RET_ERRNO actions would be loggable if "kill trap errno" were written to the sysctl. SECCOMP_RET_TRACE actions would not be logged since its string representation ("trace") wasn't present in the sysctl value. The path to the sysctl is: /proc/sys/kernel/seccomp/actions_logged The actions_avail sysctl can be read to discover the valid action names that can be written to the actions_logged sysctl with the exception of "allow". SECCOMP_RET_ALLOW actions cannot be configured for logging. The default setting for the sysctl is to allow all actions to be logged except SECCOMP_RET_ALLOW. While only SECCOMP_RET_KILL actions are currently logged, an upcoming patch will allow applications to request additional actions to be logged. There's one important exception to this sysctl. If a task is specifically being audited, meaning that an audit context has been allocated for the task, seccomp will log all actions other than SECCOMP_RET_ALLOW despite the value of actions_logged. This exception preserves the existing auditing behavior of tasks with an allocated audit context. With this patch, the logic for deciding if an action will be logged is: if action == RET_ALLOW: do not log else if action == RET_KILL && RET_KILL in actions_logged: log else if audit_enabled && task-is-being-audited: log else: do not log Signed-off-by: Tyler Hicks <tyhicks(a)canonical.com&gt; --- Documentation/userspace-api/seccomp_filter.rst | 18 +++ include/linux/audit.h | 6 +- kernel/seccomp.c | 171 ++++++++++++++++++++++++- 3 files changed, 187 insertions(+), 8 deletions(-) diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index 35fc7cb..2d1d8ab 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -187,6 +187,24 @@ directory. Here's a description of each file in that directory: program was built, differs from the set of actions actually supported in the current running kernel. +``actions_logged``: + A read-write ordered list of seccomp return values (refer to the + ``SECCOMP_RET_*`` macros above) that are allowed to be logged. Writes + to the file do not need to be in ordered form but reads from the file + will be ordered in the same way as the actions_avail sysctl. + + It is important to note that the value of ``actions_logged`` does not + prevent certain actions from being logged when the audit subsystem is + configured to audit a task. If the action is not found in + ``actions_logged`` list, the final decision on whether to audit the + action for that task is ultimately left up to the audit subsystem to + decide for all seccomp return values other than ``SECCOMP_RET_ALLOW``. + + The ``allow`` string is not accepted in the ``actions_logged`` sysctl + as it is not possible to log ``SECCOMP_RET_ALLOW`` actions. Attempting + to write ``allow`` to the sysctl will result in an EINVAL being + returned. + Adding architecture support =========================== diff --git a/include/linux/audit.h b/include/linux/audit.h index 2150bdc..8c30f06 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -314,11 +314,7 @@ void audit_core_dumps(long signr); static inline void audit_seccomp(unsigned long syscall, long signr, int code) { - if (!audit_enabled) - return; - - /* Force a record to be reported if a signal was delivered. */ - if (signr || unlikely(!audit_dummy_context())) + if (audit_enabled && unlikely(!audit_dummy_context())) __audit_seccomp(syscall, signr, code); } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 1e57eff..2cb362a 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -545,6 +545,45 @@ static void seccomp_send_sigsys(int syscall, int reason) } #endif /* CONFIG_SECCOMP_FILTER */ +/* For use with seccomp_actions_logged */ +#define SECCOMP_LOG_KILL (1 << 0) +#define SECCOMP_LOG_TRAP (1 << 2) +#define SECCOMP_LOG_ERRNO (1 << 3) +#define SECCOMP_LOG_TRACE (1 << 4) +#define SECCOMP_LOG_ALLOW (1 << 5) + +static u32 seccomp_actions_logged = SECCOMP_LOG_KILL | SECCOMP_LOG_TRAP | + SECCOMP_LOG_ERRNO | SECCOMP_LOG_TRACE; + +static inline void seccomp_log(unsigned long syscall, long signr, u32 action) +{ + bool log = false; + + switch (action) { + case SECCOMP_RET_ALLOW: + case SECCOMP_RET_TRAP: + case SECCOMP_RET_ERRNO: + case SECCOMP_RET_TRACE: + break; + case SECCOMP_RET_KILL: + default: + log = seccomp_actions_logged & SECCOMP_LOG_KILL; + } + + /* + * Force an audit message to be emitted when the action is RET_KILL and + * the action is allowed to be logged by the admin. + */ + if (log) + return __audit_seccomp(syscall, signr, action); + + /* + * Let the audit subsystem decide if the action should be audited based + * on whether the current task itself is being audited. + */ + return audit_seccomp(syscall, signr, action); +} + /* * Secure computing mode 1 allows only read/write/exit/sigreturn. * To be fully secure this must be combined with rlimit @@ -570,7 +609,7 @@ static void __secure_computing_strict(int this_syscall) #ifdef SECCOMP_DEBUG dump_stack(); #endif - audit_seccomp(this_syscall, SIGKILL, SECCOMP_RET_KILL); + seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL); do_exit(SIGKILL); } @@ -680,7 +719,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, case SECCOMP_RET_KILL: default: - audit_seccomp(this_syscall, SIGSYS, action); + seccomp_log(this_syscall, SIGSYS, action); /* * The only way match can be NULL here is if something @@ -719,7 +758,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, unreachable(); skip: - audit_seccomp(this_syscall, 0, action); + seccomp_log(this_syscall, 0, action); return -1; } #else @@ -1024,6 +1063,127 @@ static const char seccomp_actions_avail[] = SECCOMP_RET_KILL_NAME " " SECCOMP_RET_TRACE_NAME " " SECCOMP_RET_ALLOW_NAME; +struct seccomp_log_name { + u32 log; + const char *name; +}; + +static const struct seccomp_log_name seccomp_log_names[] = { + { SECCOMP_LOG_KILL, SECCOMP_RET_KILL_NAME }, + { SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME }, + { SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME }, + { SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME }, + { SECCOMP_LOG_ALLOW, SECCOMP_RET_ALLOW_NAME }, + { } +}; + +static bool seccomp_names_from_actions_logged(char *names, size_t size, + u32 actions_logged) +{ + const struct seccomp_log_name *cur; + bool append_space = false; + + for (cur = seccomp_log_names; cur->name && size; cur++) { + ssize_t ret; + + if (!(actions_logged & cur->log)) + continue; + + if (append_space) { + ret = strscpy(names, " ", size); + if (ret < 0) + return false; + + names += ret; + size -= ret; + } else + append_space = true; + + ret = strscpy(names, cur->name, size); + if (ret < 0) + return false; + + names += ret; + size -= ret; + } + + return true; +} + +static bool seccomp_action_logged_from_name(u32 *action_logged, + const char *name) +{ + const struct seccomp_log_name *cur; + + for (cur = seccomp_log_names; cur->name; cur++) { + if (!strcmp(cur->name, name)) { + *action_logged = cur->log; + return true; + } + } + + return false; +} + +static bool seccomp_actions_logged_from_names(u32 *actions_logged, char *names) +{ + char *name; + + *actions_logged = 0; + while ((name = strsep(&names, " ")) && *name) { + u32 action_logged = 0; + + if (!seccomp_action_logged_from_name(&action_logged, name)) + return false; + + *actions_logged |= action_logged; + } + + return true; +} + +static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + char names[sizeof(seccomp_actions_avail)]; + struct ctl_table table; + int ret; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + memset(names, 0, sizeof(names)); + + if (!write) { + if (!seccomp_names_from_actions_logged(names, sizeof(names), + seccomp_actions_logged)) + return -EINVAL; + } + + table = *ro_table; + table.data = names; + table.maxlen = sizeof(names); + ret = proc_dostring(&table, write, buffer, lenp, ppos); + if (ret) + return ret; + + if (write) { + u32 actions_logged; + + if (!seccomp_actions_logged_from_names(&actions_logged, + table.data)) + return -EINVAL; + + if (actions_logged & SECCOMP_LOG_ALLOW) + return -EINVAL; + + seccomp_actions_logged = actions_logged; + } + + return 0; +} + static struct ctl_path seccomp_sysctl_path[] = { { .procname = "kernel", }, { .procname = "seccomp", }, @@ -1038,6 +1198,11 @@ static struct ctl_table seccomp_sysctl_table[] = { .mode = 0444, .proc_handler = proc_dostring, }, + { + .procname = "actions_logged", + .mode = 0644, + .proc_handler = seccomp_actions_logged_handler, + }, { } }; -- 2.7.4

Userspace needs to be able to reliably detect the support of a filter flag. A good way of doing that is by attempting to enter filter mode, with the flag bit(s) in question set, and a NULL pointer for the args parameter of seccomp(2). EFAULT indicates that the flag is valid and EINVAL indicates that the flag is invalid. This patch adds a selftest that can be used to test this method of detection in userspace. Signed-off-by: Tyler Hicks <tyhicks(a)canonical.com&gt; --- tools/testing/selftests/seccomp/seccomp_bpf.c | 59 +++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index d3a78ec..ed4528c 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1918,6 +1918,65 @@ TEST(seccomp_syscall_mode_lock) } } +/* Test detection of known and unknown filter flags. Userspace needs to be able + * to check if a filter flag is supported by the current kernel and a good way + * of doing that is by attempting to enter filter mode, with the flag bit in + * question set, and a NULL pointer for the _args_ parameter. EFAULT indicates + * that the flag is valid and EINVAL indicates that the flag is invalid. + */ +TEST(detect_seccomp_filter_flags) +{ + unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC, + SECCOMP_FILTER_FLAG_KILL_PROCESS }; + unsigned int flag, all_flags; + int i; + long ret; + + /* Test detection of known-good filter flags */ + for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) { + flag = flags[i]; + ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } + EXPECT_EQ(-1, ret); + EXPECT_EQ(EFAULT, errno) { + TH_LOG("Failed to detect that a known-good filter flag (0x%X) is supported!", + flag); + } + + all_flags |= flag; + } + + /* Test detection of all known-good filter flags */ + ret = seccomp(SECCOMP_SET_MODE_FILTER, all_flags, NULL); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EFAULT, errno) { + TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!", + all_flags); + } + + /* Test detection of an unknown filter flag */ + flag = -1; + ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno) { + TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported!", + flag); + } + + /* Test detection of an unknown filter flag that may simply need to be + * added to this test + */ + flag = flags[ARRAY_SIZE(flags) - 1] << 1; + ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno) { + TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported! Does a new flag need to be added to this test?", + flag); + } +} + TEST(TSYNC_first) { struct sock_filter filter[] = { -- 2.7.4

Add a new action, SECCOMP_RET_LOG, that logs a syscall before allowing the syscall. At the implementation level, this action is identical to the existing SECCOMP_RET_ALLOW action. However, it can be very useful when initially developing a seccomp filter for an application. The developer can set the default action to be SECCOMP_RET_LOG, maybe mark any obviously needed syscalls with SECCOMP_RET_ALLOW, and then put the application through its paces. A list of syscalls that triggered the default action (SECCOMP_RET_LOG) can be easily gleaned from the logs and that list can be used to build the syscall whitelist. Finally, the developer can change the default action to the desired value. This provides a more friendly experience than seeing the application get killed, then updating the filter and rebuilding the app, seeing the application get killed due to a different syscall, then updating the filter and rebuilding the app, etc. The functionality is similar to what's supported by the various LSMs. SELinux has permissive mode, AppArmor has complain mode, SMACK has bring-up mode, etc. SECCOMP_RET_LOG is given a lower value than SECCOMP_RET_ALLOW as allow while logging is slightly more restrictive than quietly allowing. Unfortunately, the tests added for SECCOMP_RET_LOG are not capable of inspecting the audit log to verify that the syscall was logged. With this patch, the logic for deciding if an action will be logged is: if action == RET_ALLOW: do not log else if action == RET_KILL && RET_KILL in actions_logged: log else if action == RET_LOG && RET_LOG in actions_logged: log else if filter-requests-logging && action in actions_logged: log else if audit_enabled && process-is-being-audited: log else: do not log Signed-off-by: Tyler Hicks <tyhicks(a)canonical.com&gt; --- Documentation/userspace-api/seccomp_filter.rst | 9 +++ include/uapi/linux/seccomp.h | 1 + kernel/seccomp.c | 23 ++++-- tools/testing/selftests/seccomp/seccomp_bpf.c | 97 +++++++++++++++++++++++++- 4 files changed, 124 insertions(+), 6 deletions(-) diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index 2d1d8ab..f497735 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -141,6 +141,15 @@ In precedence order, they are: allow use of ptrace, even of other sandboxed processes, without extreme care; ptracers can use this mechanism to escape.) +``SECCOMP_RET_LOG``: + Results in the system call being executed after it is logged. This + should be used by application developers to learn which syscalls their + application needs without having to iterate through multiple test and + development cycles to build the list. + + This action will only be logged if "log" is present in the + actions_logged sysctl string. + ``SECCOMP_RET_ALLOW``: Results in the system call being executed. diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 144a101..58a07f4 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -32,6 +32,7 @@ #define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ #define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ #define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ +#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */ #define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ /* Masks for the return value sections. */ diff --git a/kernel/seccomp.c b/kernel/seccomp.c index e9ebaa5..cf841d7 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -556,10 +556,12 @@ static void seccomp_send_sigsys(int syscall, int reason) #define SECCOMP_LOG_TRAP (1 << 2) #define SECCOMP_LOG_ERRNO (1 << 3) #define SECCOMP_LOG_TRACE (1 << 4) -#define SECCOMP_LOG_ALLOW (1 << 5) +#define SECCOMP_LOG_LOG (1 << 5) +#define SECCOMP_LOG_ALLOW (1 << 6) static u32 seccomp_actions_logged = SECCOMP_LOG_KILL | SECCOMP_LOG_TRAP | - SECCOMP_LOG_ERRNO | SECCOMP_LOG_TRACE; + SECCOMP_LOG_ERRNO | SECCOMP_LOG_TRACE | + SECCOMP_LOG_LOG; static inline void seccomp_log(unsigned long syscall, long signr, u32 action, bool requested) @@ -578,15 +580,18 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action, case SECCOMP_RET_TRACE: log = requested && seccomp_actions_logged & SECCOMP_LOG_TRACE; break; + case SECCOMP_RET_LOG: + log = seccomp_actions_logged & SECCOMP_LOG_LOG; + break; case SECCOMP_RET_KILL: default: log = seccomp_actions_logged & SECCOMP_LOG_KILL; } /* - * Force an audit message to be emitted when the action is RET_KILL or - * the FILTER_FLAG_LOG bit was set and the action is allowed to be - * logged by the admin. + * Force an audit message to be emitted when the action is RET_KILL, + * RET_LOG, or the FILTER_FLAG_LOG bit was set and the action is + * allowed to be logged by the admin. */ if (log) return __audit_seccomp(syscall, signr, action); @@ -723,6 +728,10 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, return 0; + case SECCOMP_RET_LOG: + seccomp_log(this_syscall, 0, action, true); + return 0; + case SECCOMP_RET_ALLOW: /* * Note that the "match" filter will always be NULL for @@ -919,6 +928,7 @@ static long seccomp_get_action_avail(const char __user *uaction) case SECCOMP_RET_TRAP: case SECCOMP_RET_ERRNO: case SECCOMP_RET_TRACE: + case SECCOMP_RET_LOG: case SECCOMP_RET_ALLOW: break; default: @@ -1069,12 +1079,14 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off, #define SECCOMP_RET_TRAP_NAME "trap" #define SECCOMP_RET_ERRNO_NAME "errno" #define SECCOMP_RET_TRACE_NAME "trace" +#define SECCOMP_RET_LOG_NAME "log" #define SECCOMP_RET_ALLOW_NAME "allow" static const char seccomp_actions_avail[] = SECCOMP_RET_KILL_NAME " " SECCOMP_RET_TRAP_NAME " " SECCOMP_RET_ERRNO_NAME " " SECCOMP_RET_TRACE_NAME " " + SECCOMP_RET_LOG_NAME " " SECCOMP_RET_ALLOW_NAME; struct seccomp_log_name { @@ -1087,6 +1099,7 @@ static const struct seccomp_log_name seccomp_log_names[] = { { SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME }, { SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME }, { SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME }, + { SECCOMP_LOG_LOG, SECCOMP_RET_LOG_NAME }, { SECCOMP_LOG_ALLOW, SECCOMP_RET_ALLOW_NAME }, { } }; diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index fd0fb32..f64c81d2 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -140,6 +140,10 @@ int seccomp(unsigned int op, unsigned int flags, void *args) } #endif +#ifndef SECCOMP_RET_LOG +#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */ +#endif + #if __BYTE_ORDER == __LITTLE_ENDIAN #define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n])) #elif __BYTE_ORDER == __BIG_ENDIAN @@ -395,6 +399,28 @@ TEST(empty_prog) EXPECT_EQ(EINVAL, errno); } +TEST(log_all) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; + pid_t parent = getppid(); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); + ASSERT_EQ(0, ret); + + /* getppid() should succeed and be logged (no check for logging) */ + EXPECT_EQ(parent, syscall(__NR_getppid)); +} + TEST_SIGNAL(unknown_ret_is_kill_inside, SIGSYS) { struct sock_filter filter[] = { @@ -915,6 +941,7 @@ TEST_F(TRAP, handler) FIXTURE_DATA(precedence) { struct sock_fprog allow; + struct sock_fprog log; struct sock_fprog trace; struct sock_fprog error; struct sock_fprog trap; @@ -926,6 +953,13 @@ FIXTURE_SETUP(precedence) struct sock_filter allow_insns[] = { BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), }; + struct sock_filter log_insns[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG), + }; struct sock_filter trace_insns[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, offsetof(struct seccomp_data, nr)), @@ -962,6 +996,7 @@ FIXTURE_SETUP(precedence) memcpy(self->_x.filter, &_x##_insns, sizeof(_x##_insns)); \ self->_x.len = (unsigned short)ARRAY_SIZE(_x##_insns) FILTER_ALLOC(allow); + FILTER_ALLOC(log); FILTER_ALLOC(trace); FILTER_ALLOC(error); FILTER_ALLOC(trap); @@ -972,6 +1007,7 @@ FIXTURE_TEARDOWN(precedence) { #define FILTER_FREE(_x) if (self->_x.filter) free(self->_x.filter) FILTER_FREE(allow); + FILTER_FREE(log); FILTER_FREE(trace); FILTER_FREE(error); FILTER_FREE(trap); @@ -989,6 +1025,8 @@ TEST_F(precedence, allow_ok) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -1013,6 +1051,8 @@ TEST_F_SIGNAL(precedence, kill_is_highest, SIGSYS) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -1044,6 +1084,8 @@ TEST_F_SIGNAL(precedence, kill_is_highest_in_any_order, SIGSYS) ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap); @@ -1065,6 +1107,8 @@ TEST_F_SIGNAL(precedence, trap_is_second, SIGSYS) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -1090,6 +1134,8 @@ TEST_F_SIGNAL(precedence, trap_is_second_in_any_order, SIGSYS) ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -1111,6 +1157,8 @@ TEST_F(precedence, errno_is_third) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -1129,6 +1177,8 @@ TEST_F(precedence, errno_is_third_in_any_order) ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); @@ -1151,6 +1201,8 @@ TEST_F(precedence, trace_is_fourth) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); /* Should work just fine. */ @@ -1172,12 +1224,54 @@ TEST_F(precedence, trace_is_fourth_in_any_order) ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); /* Should work just fine. */ EXPECT_EQ(parent, syscall(__NR_getppid)); /* No ptracer */ EXPECT_EQ(-1, syscall(__NR_getpid)); } +TEST_F(precedence, log_is_fifth) +{ + pid_t mypid, parent; + long ret; + + mypid = getpid(); + parent = getppid(); + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); + ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); + /* Should work just fine. */ + EXPECT_EQ(parent, syscall(__NR_getppid)); + /* Should also work just fine */ + EXPECT_EQ(mypid, syscall(__NR_getpid)); +} + +TEST_F(precedence, log_is_fifth_in_any_order) +{ + pid_t mypid, parent; + long ret; + + mypid = getpid(); + parent = getppid(); + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); + ASSERT_EQ(0, ret); + /* Should work just fine. */ + EXPECT_EQ(parent, syscall(__NR_getppid)); + /* Should also work just fine */ + EXPECT_EQ(mypid, syscall(__NR_getpid)); +} + #ifndef PTRACE_O_TRACESECCOMP #define PTRACE_O_TRACESECCOMP 0x00000080 #endif @@ -2685,7 +2779,7 @@ TEST(get_action_avail) { __u32 actions[] = { SECCOMP_RET_KILL, SECCOMP_RET_TRAP, SECCOMP_RET_ERRNO, SECCOMP_RET_TRACE, - SECCOMP_RET_ALLOW }; + SECCOMP_RET_LOG, SECCOMP_RET_ALLOW }; __u32 unknown_action = 0x10000000U; int i; long ret; @@ -2722,6 +2816,7 @@ TEST(get_action_avail) * - 64-bit arg prodding * - arch value testing (x86 modes especially) * - verify that FILTER_FLAG_LOG filters generate log messages + * - verify that RET_LOG generates log messages * - ... */ -- 2.7.4