// SPDX-License-Identifier: GPL-2.0-only/* * linux/kernel/ptrace.c * * (C) Copyright 1999 Linus Torvalds * * Common interfaces for "ptrace()" which we do not want * to continually duplicate across every architecture. */ #include <linux/capability.h>#include <linux/export.h>#include <linux/sched.h>#include <linux/sched/mm.h>#include <linux/sched/coredump.h>#include <linux/sched/exec_state.h>#include <linux/sched/task.h>#include <linux/errno.h>#include <linux/mm.h>#include <linux/highmem.h>#include <linux/pagemap.h>#include <linux/ptrace.h>#include <linux/security.h>#include <linux/signal.h>#include <linux/uio.h>#include <linux/audit.h>#include <linux/pid_namespace.h>#include <linux/syscalls.h>#include <linux/uaccess.h>#include <linux/regset.h>#include <linux/hw_breakpoint.h>#include <linux/cn_proc.h>#include <linux/compat.h>#include <linux/sched/signal.h>#include <linux/minmax.h>#include <linux/syscall_user_dispatch.h> #include <asm/syscall.h> /* for syscall_get_* */ /** * ptracer_access_allowed - may current peek/poke @tsk's address space? * @tsk: tracee * * Per-access check used by ptrace_access_vm() and architecture-specific * tag/register accessors. Returns true iff current is the registered * ptracer of @tsk and either @tsk is owner-dumpable or current holds * CAP_SYS_PTRACE in @tsk's exec namespace. Lighter than * __ptrace_may_access(): it re-validates only dumpability and * capability on every access, without re-running LSM hooks or * cred_cap_issubset() checks performed at attach time. */bool ptracer_access_allowed(struct task_struct *tsk){ const struct task_exec_state *es; guard(rcu)(); if (ptrace_parent(tsk) != current) return false; es = task_exec_state_rcu(tsk); return READ_ONCE(es->dumpable) == TASK_DUMPABLE_OWNER || ptracer_capable(tsk, es->user_ns);} /* * Access another process' address space via ptrace. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags){ struct mm_struct *mm; int ret = 0; mm = get_task_mm(tsk); if (!mm) return 0; if (ptracer_access_allowed(tsk)) ret = access_remote_vm(mm, addr, buf, len, gup_flags); mmput(mm); return ret;} void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred){ BUG_ON(!list_empty(&child->ptrace_entry)); list_add(&child->ptrace_entry, &new_parent->ptraced); child->parent = new_parent; child->ptracer_cred = get_cred(ptracer_cred);} /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. * * Must be called with the tasklist lock write-held. */static void ptrace_link(struct task_struct *child, struct task_struct *new_parent){ __ptrace_link(child, new_parent, current_cred());} /** * __ptrace_unlink - unlink ptracee and restore its execution state * @child: ptracee to be unlinked * * Remove @child from the ptrace list, move it back to the original parent, * and restore the execution state so that it conforms to the group stop * state. * * Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer * exiting. For PTRACE_DETACH, unless the ptracee has been killed between * ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED. * If the ptracer is exiting, the ptracee can be in any state. * * After detach, the ptracee should be in a state which conforms to the * group stop. If the group is stopped or in the process of stopping, the * ptracee should be put into TASK_STOPPED; otherwise, it should be woken * up from TASK_TRACED. * * If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED, * it goes through TRACED -> RUNNING -> STOPPED transition which is similar * to but in the opposite direction of what happens while attaching to a * stopped task. However, in this direction, the intermediate RUNNING * state is not hidden even from the current ptracer and if it immediately * re-attaches and performs a WNOHANG wait(2), it may fail. * * CONTEXT: * write_lock_irq(tasklist_lock) */void __ptrace_unlink(struct task_struct *child){ const struct cred *old_cred; BUG_ON(!child->ptrace); clear_task_syscall_work(child, SYSCALL_TRACE);#if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(child, SYSCALL_EMU);#endif child->parent = child->real_parent; list_del_init(&child->ptrace_entry); old_cred = child->ptracer_cred; child->ptracer_cred = NULL; put_cred(old_cred); spin_lock(&child->sighand->siglock); child->ptrace = 0; /* * Clear all pending traps and TRAPPING. TRAPPING should be * cleared regardless of JOBCTL_STOP_PENDING. Do it explicitly. */ task_clear_jobctl_pending(child, JOBCTL_TRAP_MASK); task_clear_jobctl_trapping(child); /* * Reinstate JOBCTL_STOP_PENDING if group stop is in effect and * @child isn't dead. */ if (!(child->flags & PF_EXITING) && (child->signal->flags & SIGNAL_STOP_STOPPED || child->signal->group_stop_count)) child->jobctl |= JOBCTL_STOP_PENDING; /* * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick * @child in the butt. Note that @resume should be used iff @child * is in TASK_TRACED; otherwise, we might unduly disrupt * TASK_KILLABLE sleeps. */ if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child)) ptrace_signal_wake_up(child, true); spin_unlock(&child->sighand->siglock);} static bool looks_like_a_spurious_pid(struct task_struct *task){ if (task->exit_code != ((PTRACE_EVENT_EXEC << 8) | SIGTRAP)) return false; if (task_pid_vnr(task) == task->ptrace_message) return false; /* * The tracee changed its pid but the PTRACE_EVENT_EXEC event * was not wait()'ed, most probably debugger targets the old * leader which was destroyed in de_thread(). */ return true;} /* * Ensure that nothing can wake it up, even SIGKILL * * A task is switched to this state while a ptrace operation is in progress; * such that the ptrace operation is uninterruptible. */static bool ptrace_freeze_traced(struct task_struct *task){ bool ret = false; /* Lockless, nobody but us can set this flag */ if (task->jobctl & JOBCTL_LISTENING) return ret; spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && !__fatal_signal_pending(task)) { task->jobctl |= JOBCTL_PTRACE_FROZEN; ret = true; } spin_unlock_irq(&task->sighand->siglock); return ret;} static void ptrace_unfreeze_traced(struct task_struct *task){ unsigned long flags; /* * The child may be awake and may have cleared * JOBCTL_PTRACE_FROZEN (see ptrace_resume). The child will * not set JOBCTL_PTRACE_FROZEN or enter __TASK_TRACED anew. */ if (lock_task_sighand(task, &flags)) { task->jobctl &= ~JOBCTL_PTRACE_FROZEN; if (__fatal_signal_pending(task)) { task->jobctl &= ~JOBCTL_TRACED; wake_up_state(task, __TASK_TRACED); } unlock_task_sighand(task, &flags); }} /** * ptrace_check_attach - check whether ptracee is ready for ptrace operation * @child: ptracee to check for * @ignore_state: don't check whether @child is currently %TASK_TRACED * * Check whether @child is being ptraced by %current and ready for further * ptrace operations. If @ignore_state is %false, @child also should be in * %TASK_TRACED state and on return the child is guaranteed to be traced * and not executing. If @ignore_state is %true, @child can be in any * state. * * CONTEXT: * Grabs and releases tasklist_lock and @child->sighand->siglock. * * RETURNS: * 0 on success, -ESRCH if %child is not ready. */static int ptrace_check_attach(struct task_struct *child, bool ignore_state){ int ret = -ESRCH; /* * We take the read lock around doing both checks to close a * possible race where someone else was tracing our child and * detached between these two checks. After this locked check, * we are sure that this is our traced child and that can only * be changed by us so it's not changing right after this. */ read_lock(&tasklist_lock); if (child->ptrace && child->parent == current) { /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). */ if (ignore_state || ptrace_freeze_traced(child)) ret = 0; } read_unlock(&tasklist_lock); if (!ret && !ignore_state && WARN_ON_ONCE(!wait_task_inactive(child, __TASK_TRACED|TASK_FROZEN))) ret = -ESRCH; return ret;} static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode){ if (mode & PTRACE_MODE_NOAUDIT) return ns_capable_noaudit(ns, CAP_SYS_PTRACE); return ns_capable(ns, CAP_SYS_PTRACE);} static bool task_still_dumpable(struct task_struct *task, unsigned int mode){ const struct task_exec_state *exec_state; guard(rcu)(); exec_state = task_exec_state_rcu(task); if (READ_ONCE(exec_state->dumpable) == TASK_DUMPABLE_OWNER) return true; return ptrace_has_cap(exec_state->user_ns, mode);} /* Returns 0 on success, -errno on denial. */static int __ptrace_may_access(struct task_struct *task, unsigned int mode){ const struct cred *cred = current_cred(), *tcred; kuid_t caller_uid; kgid_t caller_gid; if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) { WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n"); return -EPERM; } /* May we inspect the given task? * This check is used both for attaching with ptrace * and for allowing access to sensitive information in /proc. * * ptrace_attach denies several cases that /proc allows * because setting up the necessary parent/child relationship * or halting the specified task is impossible. */ /* Don't let security modules deny introspection */ if (same_thread_group(task, current)) return 0; rcu_read_lock(); if (mode & PTRACE_MODE_FSCREDS) { caller_uid = cred->fsuid; caller_gid = cred->fsgid; } else { /* * Using the euid would make more sense here, but something * in userland might rely on the old behavior, and this * shouldn't be a security problem since * PTRACE_MODE_REALCREDS implies that the caller explicitly * used a syscall that requests access to another process * (and not a filesystem syscall to procfs). */ caller_uid = cred->uid; caller_gid = cred->gid; } tcred = __task_cred(task); if (uid_eq(caller_uid, tcred->euid) && uid_eq(caller_uid, tcred->suid) && uid_eq(caller_uid, tcred->uid) && gid_eq(caller_gid, tcred->egid) && gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM;ok: rcu_read_unlock(); /* * If a task drops privileges and becomes nondumpable (through a syscall * like setresuid()) while we are trying to access it, we must ensure * that the dumpability is read after the credentials; otherwise, * we may be able to attach to a task that we shouldn't be able to * attach to (as if the task had dropped privileges without becoming * nondumpable). * Pairs with a write barrier in commit_creds(). */ smp_rmb(); if (!task_still_dumpable(task, mode)) return -EPERM; return security_ptrace_access_check(task, mode);} bool ptrace_may_access(struct task_struct *task, unsigned int mode){ int err; task_lock(task); err = __ptrace_may_access(task, mode); task_unlock(task); return !err;} static int check_ptrace_options(unsigned long data){ if (data & ~(unsigned long)PTRACE_O_MASK) return -EINVAL; if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || !IS_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; } return 0;} static inline void ptrace_set_stopped(struct task_struct *task, bool seize){ guard(spinlock)(&task->sighand->siglock); /* SEIZE doesn't trap tracee on attach */ if (!seize) send_signal_locked(SIGSTOP, SEND_SIG_PRIV, task, PIDTYPE_PID); /* * If the task is already STOPPED, set JOBCTL_TRAP_STOP and * TRAPPING, and kick it so that it transits to TRACED. TRAPPING * will be cleared if the child completes the transition or any * event which clears the group stop states happens. We'll wait * for the transition to complete before returning from this * function. * * This hides STOPPED -> RUNNING -> TRACED transition from the * attaching thread but a different thread in the same group can * still observe the transient RUNNING state. IOW, if another * thread's WNOHANG wait(2) on the stopped tracee races against * ATTACH, the wait(2) may fail due to the transient RUNNING. * * The following task_is_stopped() test is safe as both transitions * in and out of STOPPED are protected by siglock. */ if (task_is_stopped(task) && task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) { task->jobctl &= ~JOBCTL_STOPPED; signal_wake_up_state(task, __TASK_STOPPED); }} static int ptrace_attach(struct task_struct *task, long request, unsigned long addr, unsigned long flags){ bool seize = (request == PTRACE_SEIZE); int retval; if (seize) { if (addr != 0) return -EIO; /* * This duplicates the check in check_ptrace_options() because * ptrace_attach() and ptrace_setoptions() have historically * used different error codes for unknown ptrace options. */ if (flags & ~(unsigned long)PTRACE_O_MASK) return -EIO; retval = check_ptrace_options(flags); if (retval) return retval; flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT); } else { flags = PT_PTRACED; } audit_ptrace(task); if (unlikely(task->flags & PF_KTHREAD)) return -EPERM; if (same_thread_group(task, current)) return -EPERM; /* * Protect exec's credential calculations against our interference; * SUID, SGID and LSM creds get determined differently * under ptrace. */ scoped_cond_guard (mutex_intr, return -ERESTARTNOINTR, &task->signal->cred_guard_mutex) { scoped_guard (task_lock, task) { retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); if (retval) return retval; } scoped_guard (write_lock_irq, &tasklist_lock) { if (unlikely(task->exit_state)) return -EPERM; if (task->ptrace) return -EPERM; task->ptrace = flags; ptrace_link(task, current); ptrace_set_stopped(task, seize); } } /* * We do not bother to change retval or clear JOBCTL_TRAPPING * if wait_on_bit() was interrupted by SIGKILL. The tracer will * not return to user-mode, it will exit and clear this bit in * __ptrace_unlink() if it wasn't already cleared by the tracee; * and until then nobody can ptrace this task. */ wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE);Lines 1–500 of 1587. Load more
// SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/ptrace.c * * (C) Copyright 1999 Linus Torvalds * * Common interfaces for "ptrace()" which we do not want * to continually duplicate across every architecture. */ #include <linux/capability.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/exec_state.h> #include <linux/sched/task.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/signal.h> #include <linux/uio.h> #include <linux/audit.h> #include <linux/pid_namespace.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/regset.h> #include <linux/hw_breakpoint.h> #include <linux/cn_proc.h> #include <linux/compat.h> #include <linux/sched/signal.h> #include <linux/minmax.h> #include <linux/syscall_user_dispatch.h> #include <asm/syscall.h> /* for syscall_get_* */ /** * ptracer_access_allowed - may current peek/poke @tsk's address space? * @tsk: tracee * * Per-access check used by ptrace_access_vm() and architecture-specific * tag/register accessors. Returns true iff current is the registered * ptracer of @tsk and either @tsk is owner-dumpable or current holds * CAP_SYS_PTRACE in @tsk's exec namespace. Lighter than * __ptrace_may_access(): it re-validates only dumpability and * capability on every access, without re-running LSM hooks or * cred_cap_issubset() checks performed at attach time. */ bool ptracer_access_allowed(struct task_struct *tsk) { const struct task_exec_state *es; guard(rcu)(); if (ptrace_parent(tsk) != current) return false; es = task_exec_state_rcu(tsk); return READ_ONCE(es->dumpable) == TASK_DUMPABLE_OWNER || ptracer_capable(tsk, es->user_ns); } /* * Access another process' address space via ptrace. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret = 0; mm = get_task_mm(tsk); if (!mm) return 0; if (ptracer_access_allowed(tsk)) ret = access_remote_vm(mm, addr, buf, len, gup_flags); mmput(mm); return ret; } void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred) { BUG_ON(!list_empty(&child->ptrace_entry)); list_add(&child->ptrace_entry, &new_parent->ptraced); child->parent = new_parent; child->ptracer_cred = get_cred(ptracer_cred); } /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. * * Must be called with the tasklist lock write-held. */ static void ptrace_link(struct task_struct *child, struct task_struct *new_parent) { __ptrace_link(child, new_parent, current_cred()); } /** * __ptrace_unlink - unlink ptracee and restore its execution state * @child: ptracee to be unlinked * * Remove @child from the ptrace list, move it back to the original parent, * and restore the execution state so that it conforms to the group stop * state. * * Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer * exiting. For PTRACE_DETACH, unless the ptracee has been killed between * ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED. * If the ptracer is exiting, the ptracee can be in any state. * * After detach, the ptracee should be in a state which conforms to the * group stop. If the group is stopped or in the process of stopping, the * ptracee should be put into TASK_STOPPED; otherwise, it should be woken * up from TASK_TRACED. * * If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED, * it goes through TRACED -> RUNNING -> STOPPED transition which is similar * to but in the opposite direction of what happens while attaching to a * stopped task. However, in this direction, the intermediate RUNNING * state is not hidden even from the current ptracer and if it immediately * re-attaches and performs a WNOHANG wait(2), it may fail. * * CONTEXT: * write_lock_irq(tasklist_lock) */ void __ptrace_unlink(struct task_struct *child) { const struct cred *old_cred; BUG_ON(!child->ptrace); clear_task_syscall_work(child, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(child, SYSCALL_EMU); #endif child->parent = child->real_parent; list_del_init(&child->ptrace_entry); old_cred = child->ptracer_cred; child->ptracer_cred = NULL; put_cred(old_cred); spin_lock(&child->sighand->siglock); child->ptrace = 0; /* * Clear all pending traps and TRAPPING. TRAPPING should be * cleared regardless of JOBCTL_STOP_PENDING. Do it explicitly. */ task_clear_jobctl_pending(child, JOBCTL_TRAP_MASK); task_clear_jobctl_trapping(child); /* * Reinstate JOBCTL_STOP_PENDING if group stop is in effect and * @child isn't dead. */ if (!(child->flags & PF_EXITING) && (child->signal->flags & SIGNAL_STOP_STOPPED || child->signal->group_stop_count)) child->jobctl |= JOBCTL_STOP_PENDING; /* * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick * @child in the butt. Note that @resume should be used iff @child * is in TASK_TRACED; otherwise, we might unduly disrupt * TASK_KILLABLE sleeps. */ if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child)) ptrace_signal_wake_up(child, true); spin_unlock(&child->sighand->siglock); } static bool looks_like_a_spurious_pid(struct task_struct *task) { if (task->exit_code != ((PTRACE_EVENT_EXEC << 8) | SIGTRAP)) return false; if (task_pid_vnr(task) == task->ptrace_message) return false; /* * The tracee changed its pid but the PTRACE_EVENT_EXEC event * was not wait()'ed, most probably debugger targets the old * leader which was destroyed in de_thread(). */ return true; } /* * Ensure that nothing can wake it up, even SIGKILL * * A task is switched to this state while a ptrace operation is in progress; * such that the ptrace operation is uninterruptible. */ static bool ptrace_freeze_traced(struct task_struct *task) { bool ret = false; /* Lockless, nobody but us can set this flag */ if (task->jobctl & JOBCTL_LISTENING) return ret; spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && !__fatal_signal_pending(task)) { task->jobctl |= JOBCTL_PTRACE_FROZEN; ret = true; } spin_unlock_irq(&task->sighand->siglock); return ret; } static void ptrace_unfreeze_traced(struct task_struct *task) { unsigned long flags; /* * The child may be awake and may have cleared * JOBCTL_PTRACE_FROZEN (see ptrace_resume). The child will * not set JOBCTL_PTRACE_FROZEN or enter __TASK_TRACED anew. */ if (lock_task_sighand(task, &flags)) { task->jobctl &= ~JOBCTL_PTRACE_FROZEN; if (__fatal_signal_pending(task)) { task->jobctl &= ~JOBCTL_TRACED; wake_up_state(task, __TASK_TRACED); } unlock_task_sighand(task, &flags); } } /** * ptrace_check_attach - check whether ptracee is ready for ptrace operation * @child: ptracee to check for * @ignore_state: don't check whether @child is currently %TASK_TRACED * * Check whether @child is being ptraced by %current and ready for further * ptrace operations. If @ignore_state is %false, @child also should be in * %TASK_TRACED state and on return the child is guaranteed to be traced * and not executing. If @ignore_state is %true, @child can be in any * state. * * CONTEXT: * Grabs and releases tasklist_lock and @child->sighand->siglock. * * RETURNS: * 0 on success, -ESRCH if %child is not ready. */ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) { int ret = -ESRCH; /* * We take the read lock around doing both checks to close a * possible race where someone else was tracing our child and * detached between these two checks. After this locked check, * we are sure that this is our traced child and that can only * be changed by us so it's not changing right after this. */ read_lock(&tasklist_lock); if (child->ptrace && child->parent == current) { /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). */ if (ignore_state || ptrace_freeze_traced(child)) ret = 0; } read_unlock(&tasklist_lock); if (!ret && !ignore_state && WARN_ON_ONCE(!wait_task_inactive(child, __TASK_TRACED|TASK_FROZEN))) ret = -ESRCH; return ret; } static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { if (mode & PTRACE_MODE_NOAUDIT) return ns_capable_noaudit(ns, CAP_SYS_PTRACE); return ns_capable(ns, CAP_SYS_PTRACE); } static bool task_still_dumpable(struct task_struct *task, unsigned int mode) { const struct task_exec_state *exec_state; guard(rcu)(); exec_state = task_exec_state_rcu(task); if (READ_ONCE(exec_state->dumpable) == TASK_DUMPABLE_OWNER) return true; return ptrace_has_cap(exec_state->user_ns, mode); } /* Returns 0 on success, -errno on denial. */ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; kuid_t caller_uid; kgid_t caller_gid; if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) { WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n"); return -EPERM; } /* May we inspect the given task? * This check is used both for attaching with ptrace * and for allowing access to sensitive information in /proc. * * ptrace_attach denies several cases that /proc allows * because setting up the necessary parent/child relationship * or halting the specified task is impossible. */ /* Don't let security modules deny introspection */ if (same_thread_group(task, current)) return 0; rcu_read_lock(); if (mode & PTRACE_MODE_FSCREDS) { caller_uid = cred->fsuid; caller_gid = cred->fsgid; } else { /* * Using the euid would make more sense here, but something * in userland might rely on the old behavior, and this * shouldn't be a security problem since * PTRACE_MODE_REALCREDS implies that the caller explicitly * used a syscall that requests access to another process * (and not a filesystem syscall to procfs). */ caller_uid = cred->uid; caller_gid = cred->gid; } tcred = __task_cred(task); if (uid_eq(caller_uid, tcred->euid) && uid_eq(caller_uid, tcred->suid) && uid_eq(caller_uid, tcred->uid) && gid_eq(caller_gid, tcred->egid) && gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; ok: rcu_read_unlock(); /* * If a task drops privileges and becomes nondumpable (through a syscall * like setresuid()) while we are trying to access it, we must ensure * that the dumpability is read after the credentials; otherwise, * we may be able to attach to a task that we shouldn't be able to * attach to (as if the task had dropped privileges without becoming * nondumpable). * Pairs with a write barrier in commit_creds(). */ smp_rmb(); if (!task_still_dumpable(task, mode)) return -EPERM; return security_ptrace_access_check(task, mode); } bool ptrace_may_access(struct task_struct *task, unsigned int mode) { int err; task_lock(task); err = __ptrace_may_access(task, mode); task_unlock(task); return !err; } static int check_ptrace_options(unsigned long data) { if (data & ~(unsigned long)PTRACE_O_MASK) return -EINVAL; if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || !IS_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; } return 0; } static inline void ptrace_set_stopped(struct task_struct *task, bool seize) { guard(spinlock)(&task->sighand->siglock); /* SEIZE doesn't trap tracee on attach */ if (!seize) send_signal_locked(SIGSTOP, SEND_SIG_PRIV, task, PIDTYPE_PID); /* * If the task is already STOPPED, set JOBCTL_TRAP_STOP and * TRAPPING, and kick it so that it transits to TRACED. TRAPPING * will be cleared if the child completes the transition or any * event which clears the group stop states happens. We'll wait * for the transition to complete before returning from this * function. * * This hides STOPPED -> RUNNING -> TRACED transition from the * attaching thread but a different thread in the same group can * still observe the transient RUNNING state. IOW, if another * thread's WNOHANG wait(2) on the stopped tracee races against * ATTACH, the wait(2) may fail due to the transient RUNNING. * * The following task_is_stopped() test is safe as both transitions * in and out of STOPPED are protected by siglock. */ if (task_is_stopped(task) && task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) { task->jobctl &= ~JOBCTL_STOPPED; signal_wake_up_state(task, __TASK_STOPPED); } } static int ptrace_attach(struct task_struct *task, long request, unsigned long addr, unsigned long flags) { bool seize = (request == PTRACE_SEIZE); int retval; if (seize) { if (addr != 0) return -EIO; /* * This duplicates the check in check_ptrace_options() because * ptrace_attach() and ptrace_setoptions() have historically * used different error codes for unknown ptrace options. */ if (flags & ~(unsigned long)PTRACE_O_MASK) return -EIO; retval = check_ptrace_options(flags); if (retval) return retval; flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT); } else { flags = PT_PTRACED; } audit_ptrace(task); if (unlikely(task->flags & PF_KTHREAD)) return -EPERM; if (same_thread_group(task, current)) return -EPERM; /* * Protect exec's credential calculations against our interference; * SUID, SGID and LSM creds get determined differently * under ptrace. */ scoped_cond_guard (mutex_intr, return -ERESTARTNOINTR, &task->signal->cred_guard_mutex) { scoped_guard (task_lock, task) { retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); if (retval) return retval; } scoped_guard (write_lock_irq, &tasklist_lock) { if (unlikely(task->exit_state)) return -EPERM; if (task->ptrace) return -EPERM; task->ptrace = flags; ptrace_link(task, current); ptrace_set_stopped(task, seize); } } /* * We do not bother to change retval or clear JOBCTL_TRAPPING * if wait_on_bit() was interrupted by SIGKILL. The tracer will * not return to user-mode, it will exit and clear this bit in * __ptrace_unlink() if it wasn't already cleared by the tracee; * and until then nobody can ptrace this task. */ wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE);