From 23d67a54857a768acdb0804cdd6037c324a50ecd Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 16 Nov 2020 12:42:00 -0500 Subject: seccomp: Migrate to use SYSCALL_WORK flag On architectures using the generic syscall entry code the architecture independent syscall work is moved to flags in thread_info::syscall_work. This removes architecture dependencies and frees up TIF bits. Define SYSCALL_WORK_SECCOMP, use it in the generic entry code and convert the code which uses the TIF specific helper functions to use the new *_syscall_work() helpers which either resolve to the new mode for users of the generic entry code or to the TIF based functions for the other architectures. Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Thomas Gleixner Reviewed-by: Andy Lutomirski Link: https://lore.kernel.org/r/20201116174206.2639648-5-krisman@collabora.com --- include/linux/seccomp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/seccomp.h') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 02aef2844c38..47763f3999f7 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -42,7 +42,7 @@ struct seccomp { extern int __secure_computing(const struct seccomp_data *sd); static inline int secure_computing(void) { - if (unlikely(test_thread_flag(TIF_SECCOMP))) + if (unlikely(test_syscall_work(SECCOMP))) return __secure_computing(NULL); return 0; } -- cgit v1.3-14-g43fede From 0d8315dddd2899f519fe1ca3d4d5cdaf44ea421e Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Wed, 11 Nov 2020 07:33:54 -0600 Subject: seccomp/cache: Report cache data through /proc/pid/seccomp_cache Currently the kernel does not provide an infrastructure to translate architecture numbers to a human-readable name. Translating syscall numbers to syscall names is possible through FTRACE_SYSCALL infrastructure but it does not provide support for compat syscalls. This will create a file for each PID as /proc/pid/seccomp_cache. The file will be empty when no seccomp filters are loaded, or be in the format of: where ALLOW means the cache is guaranteed to allow the syscall, and filter means the cache will pass the syscall to the BPF filter. For the docker default profile on x86_64 it looks like: x86_64 0 ALLOW x86_64 1 ALLOW x86_64 2 ALLOW x86_64 3 ALLOW [...] x86_64 132 ALLOW x86_64 133 ALLOW x86_64 134 FILTER x86_64 135 FILTER x86_64 136 FILTER x86_64 137 ALLOW x86_64 138 ALLOW x86_64 139 FILTER x86_64 140 ALLOW x86_64 141 ALLOW [...] This file is guarded by CONFIG_SECCOMP_CACHE_DEBUG with a default of N because I think certain users of seccomp might not want the application to know which syscalls are definitely usable. For the same reason, it is also guarded by CAP_SYS_ADMIN. Suggested-by: Jann Horn Link: https://lore.kernel.org/lkml/CAG48ez3Ofqp4crXGksLmZY6=fGrF_tWyUCg7PBkAetvbbOPeOA@mail.gmail.com/ Signed-off-by: YiFei Zhu Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/94e663fa53136f5a11f432c661794d1ee7060779.1605101222.git.yifeifz2@illinois.edu --- arch/Kconfig | 17 ++++++++++++++ fs/proc/base.c | 6 +++++ include/linux/seccomp.h | 7 ++++++ kernel/seccomp.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 89 insertions(+) (limited to 'include/linux/seccomp.h') diff --git a/arch/Kconfig b/arch/Kconfig index 56b6ccc0e32d..35c9463b7d10 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -486,6 +486,9 @@ config HAVE_ARCH_SECCOMP_FILTER - secure_computing return value is checked and a return value of -1 results in the system call being skipped immediately. - seccomp syscall wired up + - if !HAVE_SPARSE_SYSCALL_NR, have SECCOMP_ARCH_NATIVE, + SECCOMP_ARCH_NATIVE_NR, SECCOMP_ARCH_NATIVE_NAME defined. If + COMPAT is supported, have the SECCOMP_ARCH_COMPAT* defines too. config SECCOMP prompt "Enable seccomp to safely execute untrusted bytecode" @@ -514,6 +517,20 @@ config SECCOMP_FILTER See Documentation/userspace-api/seccomp_filter.rst for details. +config SECCOMP_CACHE_DEBUG + bool "Show seccomp filter cache status in /proc/pid/seccomp_cache" + depends on SECCOMP_FILTER && !HAVE_SPARSE_SYSCALL_NR + depends on PROC_FS + help + This enables the /proc/pid/seccomp_cache interface to monitor + seccomp cache data. The file format is subject to change. Reading + the file requires CAP_SYS_ADMIN. + + This option is for debugging only. Enabling presents the risk that + an adversary may be able to infer the seccomp filter logic. + + If unsure, say N. + config HAVE_ARCH_STACKLEAK bool help diff --git a/fs/proc/base.c b/fs/proc/base.c index b362523a9829..8a7d682ba881 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3263,6 +3263,9 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_PROC_PID_ARCH_STATUS ONE("arch_status", S_IRUGO, proc_pid_arch_status), #endif +#ifdef CONFIG_SECCOMP_CACHE_DEBUG + ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), +#endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) @@ -3592,6 +3595,9 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_PROC_PID_ARCH_STATUS ONE("arch_status", S_IRUGO, proc_pid_arch_status), #endif +#ifdef CONFIG_SECCOMP_CACHE_DEBUG + ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), +#endif }; static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx) diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 02aef2844c38..76963ec4641a 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -121,4 +121,11 @@ static inline long seccomp_get_metadata(struct task_struct *task, return -EINVAL; } #endif /* CONFIG_SECCOMP_FILTER && CONFIG_CHECKPOINT_RESTORE */ + +#ifdef CONFIG_SECCOMP_CACHE_DEBUG +struct seq_file; + +int proc_pid_seccomp_cache(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task); +#endif #endif /* _LINUX_SECCOMP_H */ diff --git a/kernel/seccomp.c b/kernel/seccomp.c index d8cf468dbe1e..76f524e320b1 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -553,6 +553,9 @@ void seccomp_filter_release(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; + /* We are effectively holding the siglock by not having any sighand. */ + WARN_ON(tsk->sighand != NULL); + /* Detach task from its filter tree. */ tsk->seccomp.filter = NULL; __seccomp_filter_release(orig); @@ -2335,3 +2338,59 @@ static int __init seccomp_sysctl_init(void) device_initcall(seccomp_sysctl_init) #endif /* CONFIG_SYSCTL */ + +#ifdef CONFIG_SECCOMP_CACHE_DEBUG +/* Currently CONFIG_SECCOMP_CACHE_DEBUG implies SECCOMP_ARCH_NATIVE */ +static void proc_pid_seccomp_cache_arch(struct seq_file *m, const char *name, + const void *bitmap, size_t bitmap_size) +{ + int nr; + + for (nr = 0; nr < bitmap_size; nr++) { + bool cached = test_bit(nr, bitmap); + char *status = cached ? "ALLOW" : "FILTER"; + + seq_printf(m, "%s %d %s\n", name, nr, status); + } +} + +int proc_pid_seccomp_cache(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) +{ + struct seccomp_filter *f; + unsigned long flags; + + /* + * We don't want some sandboxed process to know what their seccomp + * filters consist of. + */ + if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) + return -EACCES; + + if (!lock_task_sighand(task, &flags)) + return -ESRCH; + + f = READ_ONCE(task->seccomp.filter); + if (!f) { + unlock_task_sighand(task, &flags); + return 0; + } + + /* prevent filter from being freed while we are printing it */ + __get_seccomp_filter(f); + unlock_task_sighand(task, &flags); + + proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_NATIVE_NAME, + f->cache.allow_native, + SECCOMP_ARCH_NATIVE_NR); + +#ifdef SECCOMP_ARCH_COMPAT + proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_COMPAT_NAME, + f->cache.allow_compat, + SECCOMP_ARCH_COMPAT_NR); +#endif /* SECCOMP_ARCH_COMPAT */ + + __put_seccomp_filter(f); + return 0; +} +#endif /* CONFIG_SECCOMP_CACHE_DEBUG */ -- cgit v1.3-14-g43fede