// SPDX-License-Identifier: GPL-2.0/* * linux/kernel/seccomp.c * * Copyright 2004-2005 Andrea Arcangeli <andrea@cpushare.com> * * Copyright (C) 2012 Google, Inc. * Will Drewry <wad@chromium.org> * * This defines a simple but solid secure-computing facility. * * Mode 1 uses a fixed list of allowed system calls. * Mode 2 allows user-defined system call filters in the form * of Berkeley Packet Filters/Linux Socket Filters. */#define pr_fmt(fmt) "seccomp: " fmt #include <linux/refcount.h>#include <linux/audit.h>#include <linux/compat.h>#include <linux/coredump.h>#include <linux/kmemleak.h>#include <linux/nospec.h>#include <linux/prctl.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>#endif #ifdef CONFIG_SECCOMP_FILTER#include <linux/file.h>#include <linux/filter.h>#include <linux/pid.h>#include <linux/ptrace.h>#include <linux/capability.h>#include <linux/tracehook.h>#include <linux/uaccess.h>#include <linux/anon_inodes.h>#include <linux/lockdep.h> /* * When SECCOMP_IOCTL_NOTIF_ID_VALID was first introduced, it had the * wrong direction flag in the ioctl number. This is the broken one, * which the kernel needs to keep supporting until all userspaces stop * using the wrong command number. */#define SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR SECCOMP_IOR(2, __u64) enum notify_state { SECCOMP_NOTIFY_INIT, SECCOMP_NOTIFY_SENT, SECCOMP_NOTIFY_REPLIED,}; struct seccomp_knotif { /* The struct pid of the task whose filter triggered the notification */ struct task_struct *task; /* The "cookie" for this request; this is unique for this filter. */ u64 id; /* * The seccomp data. This pointer is valid the entire time this * notification is active, since it comes from __seccomp_filter which * eclipses the entire lifecycle here. */ const struct seccomp_data *data; /* * Notification states. When SECCOMP_RET_USER_NOTIF is returned, a * struct seccomp_knotif is created and starts out in INIT. Once the * handler reads the notification off of an FD, it transitions to SENT. * If a signal is received the state transitions back to INIT and * another message is sent. When the userspace handler replies, state * transitions to REPLIED. */ enum notify_state state; /* The return values, only valid when in SECCOMP_NOTIFY_REPLIED */ int error; long val; u32 flags; /* * Signals when this has changed states, such as the listener * dying, a new seccomp addfd message, or changing to REPLIED */ struct completion ready; struct list_head list; /* outstanding addfd requests */ struct list_head addfd;}; /** * struct seccomp_kaddfd - container for seccomp_addfd ioctl messages * * @file: A reference to the file to install in the other task * @fd: The fd number to install it at. If the fd number is -1, it means the * installing process should allocate the fd as normal. * @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC * is allowed. * @ret: The return value of the installing process. It is set to the fd num * upon success (>= 0). * @completion: Indicates that the installing process has completed fd * installation, or gone away (either due to successful * reply, or signal) * */struct seccomp_kaddfd { struct file *file; int fd; unsigned int flags; /* To only be set on reply */ int ret; struct completion completion; struct list_head list;}; /** * struct notification - container for seccomp userspace notifications. Since * most seccomp filters will not have notification listeners attached and this * structure is fairly large, we store the notification-specific stuff in a * separate structure. * * @request: A semaphore that users of this notification can wait on for * changes. Actual reads and writes are still controlled with * filter->notify_lock. * @next_id: The id of the next request. * @notifications: A list of struct seccomp_knotif elements. */struct notification { struct semaphore request; u64 next_id; struct list_head notifications;}; /** * struct seccomp_filter - container for seccomp BPF programs * * @refs: Reference count to manage the object lifetime. * A filter's reference count is incremented for each directly * attached task, once for the dependent filter, and if * requested for the user notifier. When @refs reaches zero, * the filter can be freed. * @users: A filter's @users count is incremented for each directly * attached task (filter installation, fork(), thread_sync), * and once for the dependent filter (tracked in filter->prev). * When it reaches zero it indicates that no direct or indirect * users of that filter exist. No new tasks can get associated with * this filter after reaching 0. The @users count is always smaller * or equal to @refs. Hence, reaching 0 for @users does not mean * the filter can be freed. * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged * @prev: points to a previously installed, or inherited, filter * @prog: the BPF program to evaluate * @notif: the struct that holds all notification related information * @notify_lock: A lock for all notification-related accesses. * @wqh: A wait queue for poll if a notifier is in use. * * seccomp_filter objects are organized in a tree linked via the @prev * pointer. For any task, it appears to be a singly-linked list starting * with current->seccomp.filter, the most recently attached or inherited filter. * However, multiple filters may share a @prev node, by way of fork(), which * results in a unidirectional tree existing in memory. This is similar to * how namespaces work. * * seccomp_filter objects should never be modified after being attached * to a task_struct (other than @refs). */struct seccomp_filter { refcount_t refs; refcount_t users; bool log; struct seccomp_filter *prev; struct bpf_prog *prog; struct notification *notif; struct mutex notify_lock; wait_queue_head_t wqh;}; /* Limit any path through the tree to 256KB worth of instructions. */#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter)) /* * Endianness is explicitly ignored and left for BPF program authors to manage * as per the specific architecture. */static void populate_seccomp_data(struct seccomp_data *sd){ /* * Instead of using current_pt_reg(), we're already doing the work * to safely fetch "current", so just use "task" everywhere below. */ struct task_struct *task = current; struct pt_regs *regs = task_pt_regs(task); unsigned long args[6]; sd->nr = syscall_get_nr(task, regs); sd->arch = syscall_get_arch(task); syscall_get_arguments(task, regs, args); sd->args[0] = args[0]; sd->args[1] = args[1]; sd->args[2] = args[2]; sd->args[3] = args[3]; sd->args[4] = args[4]; sd->args[5] = args[5]; sd->instruction_pointer = KSTK_EIP(task);} /** * seccomp_check_filter - verify seccomp filter code * @filter: filter to verify * @flen: length of filter * * Takes a previously checked filter (by bpf_check_classic) and * redirects all filter code that loads struct sk_buff data * and related data through seccomp_bpf_load. It also * enforces length and alignment checking of those loads. * * Returns 0 if the rule set is legal or -EINVAL if not. */static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen){ int pc; for (pc = 0; pc < flen; pc++) { struct sock_filter *ftest = &filter[pc]; u16 code = ftest->code; u32 k = ftest->k; switch (code) { case BPF_LD | BPF_W | BPF_ABS: ftest->code = BPF_LDX | BPF_W | BPF_ABS; /* 32-bit aligned and not out of bounds. */ if (k >= sizeof(struct seccomp_data) || k & 3) return -EINVAL; continue; case BPF_LD | BPF_W | BPF_LEN: ftest->code = BPF_LD | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; case BPF_LDX | BPF_W | BPF_LEN: ftest->code = BPF_LDX | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; /* Explicitly include allowed calls. */ case BPF_RET | BPF_K: case BPF_RET | BPF_A: case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_SUB | BPF_X: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_AND | BPF_X: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_OR | BPF_X: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_XOR | BPF_X: case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_X: case BPF_ALU | BPF_NEG: case BPF_LD | BPF_IMM: case BPF_LDX | BPF_IMM: case BPF_MISC | BPF_TAX: case BPF_MISC | BPF_TXA: case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: case BPF_STX: case BPF_JMP | BPF_JA: case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: continue; default: return -EINVAL; } } return 0;} /** * seccomp_run_filters - evaluates all seccomp filters against @sd * @sd: optional seccomp data to be passed to filters * @match: stores struct seccomp_filter that resulted in the return value, * unless filter returned SECCOMP_RET_ALLOW, in which case it will * be unchanged. * * Returns valid seccomp BPF response codes. */#define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL)))static u32 seccomp_run_filters(const struct seccomp_data *sd, struct seccomp_filter **match){ u32 ret = SECCOMP_RET_ALLOW; /* Make sure cross-thread synced filter points somewhere sane. */ struct seccomp_filter *f = READ_ONCE(current->seccomp.filter); /* Ensure unexpected behavior doesn't result in failing open. */ if (WARN_ON(f == NULL)) return SECCOMP_RET_KILL_PROCESS; /* * All filters in the list are evaluated and the lowest BPF return * value always takes priority (ignoring the DATA). */ for (; f; f = f->prev) { u32 cur_ret = bpf_prog_run_pin_on_cpu(f->prog, sd); if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) { ret = cur_ret; *match = f; } } return ret;}#endif /* CONFIG_SECCOMP_FILTER */ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode){ assert_spin_locked(¤t->sighand->siglock); if (current->seccomp.mode && current->seccomp.mode != seccomp_mode) return false; return true;} void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { } static inline void seccomp_assign_mode(struct task_struct *task, unsigned long seccomp_mode, unsigned long flags){ assert_spin_locked(&task->sighand->siglock); task->seccomp.mode = seccomp_mode; /* * Make sure TIF_SECCOMP cannot be set before the mode (and * filter) is set. */ smp_mb__before_atomic(); /* Assume default seccomp processes want spec flaw mitigation. */ if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0) arch_seccomp_spec_mitigate(task); set_tsk_thread_flag(task, TIF_SECCOMP);} #ifdef CONFIG_SECCOMP_FILTER/* Returns 1 if the parent is an ancestor of the child. */static int is_ancestor(struct seccomp_filter *parent, struct seccomp_filter *child){ /* NULL is the root ancestor. */ if (parent == NULL) return 1; for (; child; child = child->prev) if (child == parent) return 1; return 0;} /** * seccomp_can_sync_threads: checks if all threads can be synchronized * * Expects sighand and cred_guard_mutex locks to be held. * * Returns 0 on success, -ve on error, or the pid of a thread which was * either not in the correct seccomp mode or did not have an ancestral * seccomp filter. */static inline pid_t seccomp_can_sync_threads(void){ struct task_struct *thread, *caller; BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex)); assert_spin_locked(¤t->sighand->siglock); /* Validate all threads being eligible for synchronization. */ caller = current; for_each_thread(caller, thread) { pid_t failed; /* Skip current, since it is initiating the sync. */ if (thread == caller) continue; if (thread->seccomp.mode == SECCOMP_MODE_DISABLED || (thread->seccomp.mode == SECCOMP_MODE_FILTER && is_ancestor(thread->seccomp.filter, caller->seccomp.filter))) continue; /* Return the first thread that cannot be synchronized. */ failed = task_pid_vnr(thread); /* If the pid cannot be resolved, then return -ESRCH */ if (WARN_ON(failed == 0)) failed = -ESRCH; return failed; } return 0;} static inline void seccomp_filter_free(struct seccomp_filter *filter){ if (filter) { bpf_prog_destroy(filter->prog); kfree(filter); }} static void __seccomp_filter_orphan(struct seccomp_filter *orig){ while (orig && refcount_dec_and_test(&orig->users)) { if (waitqueue_active(&orig->wqh)) wake_up_poll(&orig->wqh, EPOLLHUP); orig = orig->prev; }} static void __put_seccomp_filter(struct seccomp_filter *orig){ /* Clean up single-reference branches iteratively. */ while (orig && refcount_dec_and_test(&orig->refs)) { struct seccomp_filter *freeme = orig; orig = orig->prev; seccomp_filter_free(freeme); }} static void __seccomp_filter_release(struct seccomp_filter *orig){ /* Notify about any unused filters in the task's former filter tree. */ __seccomp_filter_orphan(orig); /* Finally drop all references to the task's former tree. */ __put_seccomp_filter(orig);} /** * seccomp_filter_release - Detach the task from its filter tree, * drop its reference count, and notify * about unused filters * * This function should only be called when the task is exiting as * it detaches it from its filter tree. As such, READ_ONCE() and * barriers are not needed here, as would normally be needed. */void seccomp_filter_release(struct task_struct *tsk){ struct seccomp_filter *orig = tsk->seccomp.filter; /* Detach task from its filter tree. */ tsk->seccomp.filter = NULL; __seccomp_filter_release(orig);} /** * seccomp_sync_threads: sets all threads to use current's filter * * Expects sighand and cred_guard_mutex locks to be held, and for * seccomp_can_sync_threads() to have returned success already * without dropping the locks. * */static inline void seccomp_sync_threads(unsigned long flags){ struct task_struct *thread, *caller; BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex)); assert_spin_locked(¤t->sighand->siglock); /* Synchronize all threads. */ caller = current; for_each_thread(caller, thread) { /* Skip current, since it needs no changes. */ if (thread == caller) continue; /* Get a task reference for the new leaf node. */Lines 1–500 of 2105. Load more
// SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/seccomp.c * * Copyright 2004-2005 Andrea Arcangeli <andrea@cpushare.com> * * Copyright (C) 2012 Google, Inc. * Will Drewry <wad@chromium.org> * * This defines a simple but solid secure-computing facility. * * Mode 1 uses a fixed list of allowed system calls. * Mode 2 allows user-defined system call filters in the form * of Berkeley Packet Filters/Linux Socket Filters. */ #define pr_fmt(fmt) "seccomp: " fmt #include <linux/refcount.h> #include <linux/audit.h> #include <linux/compat.h> #include <linux/coredump.h> #include <linux/kmemleak.h> #include <linux/nospec.h> #include <linux/prctl.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> #endif #ifdef CONFIG_SECCOMP_FILTER #include <linux/file.h> #include <linux/filter.h> #include <linux/pid.h> #include <linux/ptrace.h> #include <linux/capability.h> #include <linux/tracehook.h> #include <linux/uaccess.h> #include <linux/anon_inodes.h> #include <linux/lockdep.h> /* * When SECCOMP_IOCTL_NOTIF_ID_VALID was first introduced, it had the * wrong direction flag in the ioctl number. This is the broken one, * which the kernel needs to keep supporting until all userspaces stop * using the wrong command number. */ #define SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR SECCOMP_IOR(2, __u64) enum notify_state { SECCOMP_NOTIFY_INIT, SECCOMP_NOTIFY_SENT, SECCOMP_NOTIFY_REPLIED, }; struct seccomp_knotif { /* The struct pid of the task whose filter triggered the notification */ struct task_struct *task; /* The "cookie" for this request; this is unique for this filter. */ u64 id; /* * The seccomp data. This pointer is valid the entire time this * notification is active, since it comes from __seccomp_filter which * eclipses the entire lifecycle here. */ const struct seccomp_data *data; /* * Notification states. When SECCOMP_RET_USER_NOTIF is returned, a * struct seccomp_knotif is created and starts out in INIT. Once the * handler reads the notification off of an FD, it transitions to SENT. * If a signal is received the state transitions back to INIT and * another message is sent. When the userspace handler replies, state * transitions to REPLIED. */ enum notify_state state; /* The return values, only valid when in SECCOMP_NOTIFY_REPLIED */ int error; long val; u32 flags; /* * Signals when this has changed states, such as the listener * dying, a new seccomp addfd message, or changing to REPLIED */ struct completion ready; struct list_head list; /* outstanding addfd requests */ struct list_head addfd; }; /** * struct seccomp_kaddfd - container for seccomp_addfd ioctl messages * * @file: A reference to the file to install in the other task * @fd: The fd number to install it at. If the fd number is -1, it means the * installing process should allocate the fd as normal. * @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC * is allowed. * @ret: The return value of the installing process. It is set to the fd num * upon success (>= 0). * @completion: Indicates that the installing process has completed fd * installation, or gone away (either due to successful * reply, or signal) * */ struct seccomp_kaddfd { struct file *file; int fd; unsigned int flags; /* To only be set on reply */ int ret; struct completion completion; struct list_head list; }; /** * struct notification - container for seccomp userspace notifications. Since * most seccomp filters will not have notification listeners attached and this * structure is fairly large, we store the notification-specific stuff in a * separate structure. * * @request: A semaphore that users of this notification can wait on for * changes. Actual reads and writes are still controlled with * filter->notify_lock. * @next_id: The id of the next request. * @notifications: A list of struct seccomp_knotif elements. */ struct notification { struct semaphore request; u64 next_id; struct list_head notifications; }; /** * struct seccomp_filter - container for seccomp BPF programs * * @refs: Reference count to manage the object lifetime. * A filter's reference count is incremented for each directly * attached task, once for the dependent filter, and if * requested for the user notifier. When @refs reaches zero, * the filter can be freed. * @users: A filter's @users count is incremented for each directly * attached task (filter installation, fork(), thread_sync), * and once for the dependent filter (tracked in filter->prev). * When it reaches zero it indicates that no direct or indirect * users of that filter exist. No new tasks can get associated with * this filter after reaching 0. The @users count is always smaller * or equal to @refs. Hence, reaching 0 for @users does not mean * the filter can be freed. * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged * @prev: points to a previously installed, or inherited, filter * @prog: the BPF program to evaluate * @notif: the struct that holds all notification related information * @notify_lock: A lock for all notification-related accesses. * @wqh: A wait queue for poll if a notifier is in use. * * seccomp_filter objects are organized in a tree linked via the @prev * pointer. For any task, it appears to be a singly-linked list starting * with current->seccomp.filter, the most recently attached or inherited filter. * However, multiple filters may share a @prev node, by way of fork(), which * results in a unidirectional tree existing in memory. This is similar to * how namespaces work. * * seccomp_filter objects should never be modified after being attached * to a task_struct (other than @refs). */ struct seccomp_filter { refcount_t refs; refcount_t users; bool log; struct seccomp_filter *prev; struct bpf_prog *prog; struct notification *notif; struct mutex notify_lock; wait_queue_head_t wqh; }; /* Limit any path through the tree to 256KB worth of instructions. */ #define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter)) /* * Endianness is explicitly ignored and left for BPF program authors to manage * as per the specific architecture. */ static void populate_seccomp_data(struct seccomp_data *sd) { /* * Instead of using current_pt_reg(), we're already doing the work * to safely fetch "current", so just use "task" everywhere below. */ struct task_struct *task = current; struct pt_regs *regs = task_pt_regs(task); unsigned long args[6]; sd->nr = syscall_get_nr(task, regs); sd->arch = syscall_get_arch(task); syscall_get_arguments(task, regs, args); sd->args[0] = args[0]; sd->args[1] = args[1]; sd->args[2] = args[2]; sd->args[3] = args[3]; sd->args[4] = args[4]; sd->args[5] = args[5]; sd->instruction_pointer = KSTK_EIP(task); } /** * seccomp_check_filter - verify seccomp filter code * @filter: filter to verify * @flen: length of filter * * Takes a previously checked filter (by bpf_check_classic) and * redirects all filter code that loads struct sk_buff data * and related data through seccomp_bpf_load. It also * enforces length and alignment checking of those loads. * * Returns 0 if the rule set is legal or -EINVAL if not. */ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) { int pc; for (pc = 0; pc < flen; pc++) { struct sock_filter *ftest = &filter[pc]; u16 code = ftest->code; u32 k = ftest->k; switch (code) { case BPF_LD | BPF_W | BPF_ABS: ftest->code = BPF_LDX | BPF_W | BPF_ABS; /* 32-bit aligned and not out of bounds. */ if (k >= sizeof(struct seccomp_data) || k & 3) return -EINVAL; continue; case BPF_LD | BPF_W | BPF_LEN: ftest->code = BPF_LD | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; case BPF_LDX | BPF_W | BPF_LEN: ftest->code = BPF_LDX | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; /* Explicitly include allowed calls. */ case BPF_RET | BPF_K: case BPF_RET | BPF_A: case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_SUB | BPF_X: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_AND | BPF_X: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_OR | BPF_X: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_XOR | BPF_X: case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_X: case BPF_ALU | BPF_NEG: case BPF_LD | BPF_IMM: case BPF_LDX | BPF_IMM: case BPF_MISC | BPF_TAX: case BPF_MISC | BPF_TXA: case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: case BPF_STX: case BPF_JMP | BPF_JA: case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: continue; default: return -EINVAL; } } return 0; } /** * seccomp_run_filters - evaluates all seccomp filters against @sd * @sd: optional seccomp data to be passed to filters * @match: stores struct seccomp_filter that resulted in the return value, * unless filter returned SECCOMP_RET_ALLOW, in which case it will * be unchanged. * * Returns valid seccomp BPF response codes. */ #define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL))) static u32 seccomp_run_filters(const struct seccomp_data *sd, struct seccomp_filter **match) { u32 ret = SECCOMP_RET_ALLOW; /* Make sure cross-thread synced filter points somewhere sane. */ struct seccomp_filter *f = READ_ONCE(current->seccomp.filter); /* Ensure unexpected behavior doesn't result in failing open. */ if (WARN_ON(f == NULL)) return SECCOMP_RET_KILL_PROCESS; /* * All filters in the list are evaluated and the lowest BPF return * value always takes priority (ignoring the DATA). */ for (; f; f = f->prev) { u32 cur_ret = bpf_prog_run_pin_on_cpu(f->prog, sd); if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) { ret = cur_ret; *match = f; } } return ret; } #endif /* CONFIG_SECCOMP_FILTER */ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode) { assert_spin_locked(¤t->sighand->siglock); if (current->seccomp.mode && current->seccomp.mode != seccomp_mode) return false; return true; } void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { } static inline void seccomp_assign_mode(struct task_struct *task, unsigned long seccomp_mode, unsigned long flags) { assert_spin_locked(&task->sighand->siglock); task->seccomp.mode = seccomp_mode; /* * Make sure TIF_SECCOMP cannot be set before the mode (and * filter) is set. */ smp_mb__before_atomic(); /* Assume default seccomp processes want spec flaw mitigation. */ if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0) arch_seccomp_spec_mitigate(task); set_tsk_thread_flag(task, TIF_SECCOMP); } #ifdef CONFIG_SECCOMP_FILTER /* Returns 1 if the parent is an ancestor of the child. */ static int is_ancestor(struct seccomp_filter *parent, struct seccomp_filter *child) { /* NULL is the root ancestor. */ if (parent == NULL) return 1; for (; child; child = child->prev) if (child == parent) return 1; return 0; } /** * seccomp_can_sync_threads: checks if all threads can be synchronized * * Expects sighand and cred_guard_mutex locks to be held. * * Returns 0 on success, -ve on error, or the pid of a thread which was * either not in the correct seccomp mode or did not have an ancestral * seccomp filter. */ static inline pid_t seccomp_can_sync_threads(void) { struct task_struct *thread, *caller; BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex)); assert_spin_locked(¤t->sighand->siglock); /* Validate all threads being eligible for synchronization. */ caller = current; for_each_thread(caller, thread) { pid_t failed; /* Skip current, since it is initiating the sync. */ if (thread == caller) continue; if (thread->seccomp.mode == SECCOMP_MODE_DISABLED || (thread->seccomp.mode == SECCOMP_MODE_FILTER && is_ancestor(thread->seccomp.filter, caller->seccomp.filter))) continue; /* Return the first thread that cannot be synchronized. */ failed = task_pid_vnr(thread); /* If the pid cannot be resolved, then return -ESRCH */ if (WARN_ON(failed == 0)) failed = -ESRCH; return failed; } return 0; } static inline void seccomp_filter_free(struct seccomp_filter *filter) { if (filter) { bpf_prog_destroy(filter->prog); kfree(filter); } } static void __seccomp_filter_orphan(struct seccomp_filter *orig) { while (orig && refcount_dec_and_test(&orig->users)) { if (waitqueue_active(&orig->wqh)) wake_up_poll(&orig->wqh, EPOLLHUP); orig = orig->prev; } } static void __put_seccomp_filter(struct seccomp_filter *orig) { /* Clean up single-reference branches iteratively. */ while (orig && refcount_dec_and_test(&orig->refs)) { struct seccomp_filter *freeme = orig; orig = orig->prev; seccomp_filter_free(freeme); } } static void __seccomp_filter_release(struct seccomp_filter *orig) { /* Notify about any unused filters in the task's former filter tree. */ __seccomp_filter_orphan(orig); /* Finally drop all references to the task's former tree. */ __put_seccomp_filter(orig); } /** * seccomp_filter_release - Detach the task from its filter tree, * drop its reference count, and notify * about unused filters * * This function should only be called when the task is exiting as * it detaches it from its filter tree. As such, READ_ONCE() and * barriers are not needed here, as would normally be needed. */ void seccomp_filter_release(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; /* Detach task from its filter tree. */ tsk->seccomp.filter = NULL; __seccomp_filter_release(orig); } /** * seccomp_sync_threads: sets all threads to use current's filter * * Expects sighand and cred_guard_mutex locks to be held, and for * seccomp_can_sync_threads() to have returned success already * without dropping the locks. * */ static inline void seccomp_sync_threads(unsigned long flags) { struct task_struct *thread, *caller; BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex)); assert_spin_locked(¤t->sighand->siglock); /* Synchronize all threads. */ caller = current; for_each_thread(caller, thread) { /* Skip current, since it needs no changes. */ if (thread == caller) continue; /* Get a task reference for the new leaf node. */