From: YiFei Zhu <yifei...@illinois.edu> 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: <arch name> <decimal syscall number> <ALLOW | FILTER> 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_DEBUG_SECCOMP_CACHE 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 <ja...@google.com> Link: https://lore.kernel.org/lkml/CAG48ez3Ofqp4crXGksLmZY6=fgrf_twyucg7pbkaetvbbop...@mail.gmail.com/ Signed-off-by: YiFei Zhu <yifei...@illinois.edu> --- arch/Kconfig | 15 +++++++++++ arch/x86/include/asm/seccomp.h | 3 +++ fs/proc/base.c | 3 +++ include/linux/seccomp.h | 5 ++++ kernel/seccomp.c | 46 ++++++++++++++++++++++++++++++++++ 5 files changed, 72 insertions(+) diff --git a/arch/Kconfig b/arch/Kconfig index ca867b2a5d71..b840cadcc882 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -478,6 +478,7 @@ config HAVE_ARCH_SECCOMP_CACHE_NR_ONLY - all the requirements for HAVE_ARCH_SECCOMP_FILTER - SECCOMP_ARCH_DEFAULT - SECCOMP_ARCH_DEFAULT_NR + - SECCOMP_ARCH_DEFAULT_NAME config SECCOMP prompt "Enable seccomp to safely execute untrusted bytecode" @@ -532,6 +533,20 @@ config SECCOMP_CACHE_NR_ONLY endchoice +config DEBUG_SECCOMP_CACHE + bool "Show seccomp filter cache status in /proc/pid/seccomp_cache" + depends on SECCOMP_CACHE_NR_ONLY + depends on PROC_FS + help + This is enables /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 present 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/arch/x86/include/asm/seccomp.h b/arch/x86/include/asm/seccomp.h index 7b3a58271656..33ccc074be7a 100644 --- a/arch/x86/include/asm/seccomp.h +++ b/arch/x86/include/asm/seccomp.h @@ -19,13 +19,16 @@ #ifdef CONFIG_X86_64 # define SECCOMP_ARCH_DEFAULT AUDIT_ARCH_X86_64 # define SECCOMP_ARCH_DEFAULT_NR NR_syscalls +# define SECCOMP_ARCH_DEFAULT_NAME "x86_64" # ifdef CONFIG_COMPAT # define SECCOMP_ARCH_COMPAT AUDIT_ARCH_I386 # define SECCOMP_ARCH_COMPAT_NR IA32_NR_syscalls +# define SECCOMP_ARCH_COMPAT_NAME "x86_32" # endif #else /* !CONFIG_X86_64 */ # define SECCOMP_ARCH_DEFAULT AUDIT_ARCH_I386 # define SECCOMP_ARCH_DEFAULT_NR NR_syscalls +# define SECCOMP_ARCH_COMPAT_NAME "x86_32" #endif #include <asm-generic/seccomp.h> diff --git a/fs/proc/base.c b/fs/proc/base.c index 617db4e0faa0..c60c5fce70fa 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3258,6 +3258,9 @@ 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_DEBUG_SECCOMP_CACHE + ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), +#endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 02aef2844c38..c35430f5f553 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -121,4 +121,9 @@ static inline long seccomp_get_metadata(struct task_struct *task, return -EINVAL; } #endif /* CONFIG_SECCOMP_FILTER && CONFIG_CHECKPOINT_RESTORE */ + +#ifdef CONFIG_DEBUG_SECCOMP_CACHE +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 bed3b2a7f6c8..c5ca5e30281b 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -2297,3 +2297,49 @@ static int __init seccomp_sysctl_init(void) device_initcall(seccomp_sysctl_init) #endif /* CONFIG_SYSCTL */ + +#ifdef CONFIG_DEBUG_SECCOMP_CACHE +/* Currently CONFIG_DEBUG_SECCOMP_CACHE implies CONFIG_SECCOMP_CACHE_NR_ONLY */ +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; + + /* + * We don't want some sandboxed process know what their seccomp + * filters consist of. + */ + if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) + return -EACCES; + + f = READ_ONCE(task->seccomp.filter); + if (!f) + return 0; + +#ifdef SECCOMP_ARCH_DEFAULT + proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_DEFAULT_NAME, + f->cache.syscall_allow_default, + SECCOMP_ARCH_DEFAULT_NR); +#endif /* SECCOMP_ARCH_DEFAULT */ + +#ifdef SECCOMP_ARCH_COMPAT + proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_COMPAT_NAME, + f->cache.syscall_allow_compat, + SECCOMP_ARCH_COMPAT_NR); +#endif /* SECCOMP_ARCH_COMPAT */ + return 0; +} +#endif /* CONFIG_DEBUG_SECCOMP_CACHE */ -- 2.28.0
