path: root/kernel/ptrace.c

// 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