From 8225d3853f34f6cf9caff15d8c385a528e0d7cb1 Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Fri, 21 Nov 2014 10:06:01 -0500 Subject: [PATCH 1/3] seccomp: Replace smp_read_barrier_depends() with lockless_dereference() Recently lockless_dereference() was added which can be used in place of hard-coding smp_read_barrier_depends(). The following PATCH makes the change. Signed-off-by: Pranith Kumar Signed-off-by: Kees Cook --- kernel/seccomp.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 4f44028943e6..980fd26da22e 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -175,17 +175,16 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) */ static u32 seccomp_run_filters(struct seccomp_data *sd) { - struct seccomp_filter *f = ACCESS_ONCE(current->seccomp.filter); struct seccomp_data sd_local; u32 ret = SECCOMP_RET_ALLOW; + /* Make sure cross-thread synced filter points somewhere sane. */ + struct seccomp_filter *f = + lockless_dereference(current->seccomp.filter); /* Ensure unexpected behavior doesn't result in failing open. */ if (unlikely(WARN_ON(f == NULL))) return SECCOMP_RET_KILL; - /* Make sure cross-thread synced filter points somewhere sane. */ - smp_read_barrier_depends(); - if (!sd) { populate_seccomp_data(&sd_local); sd = &sd_local; From 13c4a90119d28cfcb6b5bdd820c233b86c2b0237 Mon Sep 17 00:00:00 2001 From: Tycho Andersen Date: Sat, 13 Jun 2015 09:02:48 -0600 Subject: [PATCH 2/3] seccomp: add ptrace options for suspend/resume This patch is the first step in enabling checkpoint/restore of processes with seccomp enabled. One of the things CRIU does while dumping tasks is inject code into them via ptrace to collect information that is only available to the process itself. However, if we are in a seccomp mode where these processes are prohibited from making these syscalls, then what CRIU does kills the task. This patch adds a new ptrace option, PTRACE_O_SUSPEND_SECCOMP, that enables a task from the init user namespace which has CAP_SYS_ADMIN and no seccomp filters to disable (and re-enable) seccomp filters for another task so that they can be successfully dumped (and restored). We restrict the set of processes that can disable seccomp through ptrace because although today ptrace can be used to bypass seccomp, there is some discussion of closing this loophole in the future and we would like this patch to not depend on that behavior and be future proofed for when it is removed. Note that seccomp can be suspended before any filters are actually installed; this behavior is useful on criu restore, so that we can suspend seccomp, restore the filters, unmap our restore code from the restored process' address space, and then resume the task by detaching and have the filters resumed as well. v2 changes: * require that the tracer have no seccomp filters installed * drop TIF_NOTSC manipulation from the patch * change from ptrace command to a ptrace option and use this ptrace option as the flag to check. This means that as soon as the tracer detaches/dies, seccomp is re-enabled and as a corrollary that one can not disable seccomp across PTRACE_ATTACHs. v3 changes: * get rid of various #ifdefs everywhere * report more sensible errors when PTRACE_O_SUSPEND_SECCOMP is incorrectly used v4 changes: * get rid of may_suspend_seccomp() in favor of a capable() check in ptrace directly v5 changes: * check that seccomp is not enabled (or suspended) on the tracer Signed-off-by: Tycho Andersen CC: Will Drewry CC: Roland McGrath CC: Pavel Emelyanov CC: Serge E. Hallyn Acked-by: Oleg Nesterov Acked-by: Andy Lutomirski [kees: access seccomp.mode through seccomp_mode() instead] Signed-off-by: Kees Cook --- include/linux/ptrace.h | 1 + include/uapi/linux/ptrace.h | 6 ++++-- kernel/ptrace.c | 13 +++++++++++++ kernel/seccomp.c | 8 ++++++++ 4 files changed, 26 insertions(+), 2 deletions(-) diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 987a73a40ef8..061265f92876 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -34,6 +34,7 @@ #define PT_TRACE_SECCOMP PT_EVENT_FLAG(PTRACE_EVENT_SECCOMP) #define PT_EXITKILL (PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT) +#define PT_SUSPEND_SECCOMP (PTRACE_O_SUSPEND_SECCOMP << PT_OPT_FLAG_SHIFT) /* single stepping state bits (used on ARM and PA-RISC) */ #define PT_SINGLESTEP_BIT 31 diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h index cf1019e15f5b..a7a697986614 100644 --- a/include/uapi/linux/ptrace.h +++ b/include/uapi/linux/ptrace.h @@ -89,9 +89,11 @@ struct ptrace_peeksiginfo_args { #define PTRACE_O_TRACESECCOMP (1 << PTRACE_EVENT_SECCOMP) /* eventless options */ -#define PTRACE_O_EXITKILL (1 << 20) +#define PTRACE_O_EXITKILL (1 << 20) +#define PTRACE_O_SUSPEND_SECCOMP (1 << 21) -#define PTRACE_O_MASK (0x000000ff | PTRACE_O_EXITKILL) +#define PTRACE_O_MASK (\ + 0x000000ff | PTRACE_O_EXITKILL | PTRACE_O_SUSPEND_SECCOMP) #include diff --git a/kernel/ptrace.c b/kernel/ptrace.c index c8e0e050a36a..787320de68e0 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -556,6 +556,19 @@ static int ptrace_setoptions(struct task_struct *child, unsigned long data) if (data & ~(unsigned long)PTRACE_O_MASK) return -EINVAL; + if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { + if (!config_enabled(CONFIG_CHECKPOINT_RESTORE) || + !config_enabled(CONFIG_SECCOMP)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (seccomp_mode(¤t->seccomp) != SECCOMP_MODE_DISABLED || + current->ptrace & PT_SUSPEND_SECCOMP) + return -EPERM; + } + /* Avoid intermediate state when all opts are cleared */ flags = child->ptrace; flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 980fd26da22e..645e42d6fa4d 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -590,6 +590,10 @@ void secure_computing_strict(int this_syscall) { int mode = current->seccomp.mode; + if (config_enabled(CONFIG_CHECKPOINT_RESTORE) && + unlikely(current->ptrace & PT_SUSPEND_SECCOMP)) + return; + if (mode == 0) return; else if (mode == SECCOMP_MODE_STRICT) @@ -691,6 +695,10 @@ u32 seccomp_phase1(struct seccomp_data *sd) int this_syscall = sd ? sd->nr : syscall_get_nr(current, task_pt_regs(current)); + if (config_enabled(CONFIG_CHECKPOINT_RESTORE) && + unlikely(current->ptrace & PT_SUSPEND_SECCOMP)) + return SECCOMP_PHASE1_OK; + switch (mode) { case SECCOMP_MODE_STRICT: __secure_computing_strict(this_syscall); /* may call do_exit */ From 221272f97ca528048a577a3ff23d7774286ca5fd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 15 Jun 2015 15:29:16 -0700 Subject: [PATCH 3/3] seccomp: swap hard-coded zeros to defined name For clarity, if CONFIG_SECCOMP isn't defined, seccomp_mode() is returning "disabled". This makes that more clear, along with another 0-use, and results in no operational change. Signed-off-by: Kees Cook --- include/linux/seccomp.h | 2 +- kernel/seccomp.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index a19ddacdac30..f4265039a94c 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -78,7 +78,7 @@ static inline long prctl_set_seccomp(unsigned long arg2, char __user *arg3) static inline int seccomp_mode(struct seccomp *s) { - return 0; + return SECCOMP_MODE_DISABLED; } #endif /* CONFIG_SECCOMP */ diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 645e42d6fa4d..383bd6caca81 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -594,7 +594,7 @@ void secure_computing_strict(int this_syscall) unlikely(current->ptrace & PT_SUSPEND_SECCOMP)) return; - if (mode == 0) + if (mode == SECCOMP_MODE_DISABLED) return; else if (mode == SECCOMP_MODE_STRICT) __secure_computing_strict(this_syscall);