Merge tag 'ptrace-cleanups-for-v5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull ptrace cleanups from Eric Biederman:
 "This set of changes removes tracehook.h, moves modification of all of
  the ptrace fields inside of siglock to remove races, adds a missing
  permission check to ptrace.c

  The removal of tracehook.h is quite significant as it has been a major
  source of confusion in recent years. Much of that confusion was around
  task_work and TIF_NOTIFY_SIGNAL (which I have now decoupled making the
  semantics clearer).

  For people who don't know tracehook.h is a vestiage of an attempt to
  implement uprobes like functionality that was never fully merged, and
  was later superseeded by uprobes when uprobes was merged. For many
  years now we have been removing what tracehook functionaly a little
  bit at a time. To the point where anything left in tracehook.h was
  some weird strange thing that was difficult to understand"

* tag 'ptrace-cleanups-for-v5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  ptrace: Remove duplicated include in ptrace.c
  ptrace: Check PTRACE_O_SUSPEND_SECCOMP permission on PTRACE_SEIZE
  ptrace: Return the signal to continue with from ptrace_stop
  ptrace: Move setting/clearing ptrace_message into ptrace_stop
  tracehook: Remove tracehook.h
  resume_user_mode: Move to resume_user_mode.h
  resume_user_mode: Remove #ifdef TIF_NOTIFY_RESUME in set_notify_resume
  signal: Move set_notify_signal and clear_notify_signal into sched/signal.h
  task_work: Decouple TIF_NOTIFY_SIGNAL and task_work
  task_work: Call tracehook_notify_signal from get_signal on all architectures
  task_work: Introduce task_work_pending
  task_work: Remove unnecessary include from posix_timers.h
  ptrace: Remove tracehook_signal_handler
  ptrace: Remove arch_syscall_{enter,exit}_tracehook
  ptrace: Create ptrace_report_syscall_{entry,exit} in ptrace.h
  ptrace/arm: Rename tracehook_report_syscall report_syscall
  ptrace: Move ptrace_report_syscall into ptrace.h

10 files changed, 82 insertions, 66 deletions

diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index ed10a95a6b1d..ef8d94a98b7e 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -2,6 +2,7 @@
 
 #include <linux/context_tracking.h>
 #include <linux/entry-common.h>
+#include <linux/resume_user_mode.h>
 #include <linux/highmem.h>
 #include <linux/jump_label.h>
 #include <linux/livepatch.h>
@@ -59,7 +60,7 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 
 	/* Handle ptrace */
 	if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
-		ret = arch_syscall_enter_tracehook(regs);
+		ret = ptrace_report_syscall_entry(regs);
 		if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
 			return -1L;
 	}
@@ -139,15 +140,7 @@ void noinstr exit_to_user_mode(void)
 }
 
 /* Workaround to allow gradual conversion of architecture code */
-void __weak arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) { }
-
-static void handle_signal_work(struct pt_regs *regs, unsigned long ti_work)
-{
-	if (ti_work & _TIF_NOTIFY_SIGNAL)
-		tracehook_notify_signal();
-
-	arch_do_signal_or_restart(regs, ti_work & _TIF_SIGPENDING);
-}
+void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
 
 #ifdef CONFIG_RT_DELAYED_SIGNALS
 static inline void raise_delayed_signal(void)
@@ -184,10 +177,10 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 			klp_update_patch_state(current);
 
 		if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
-			handle_signal_work(regs, ti_work);
+			arch_do_signal_or_restart(regs);
 
 		if (ti_work & _TIF_NOTIFY_RESUME)
-			tracehook_notify_resume(regs);
+			resume_user_mode_work(regs);
 
 		/* Architecture specific TIF work */
 		arch_exit_to_user_mode_work(regs, ti_work);
@@ -267,7 +260,7 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
 
 	step = report_single_step(work);
 	if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
-		arch_syscall_exit_tracehook(regs, step);
+		ptrace_report_syscall_exit(regs, step);
 }
 
 /*
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
index 96d476e06c77..9d09f489b60e 100644
--- a/kernel/entry/kvm.c
+++ b/kernel/entry/kvm.c
@@ -8,8 +8,11 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
 	do {
 		int ret;
 
-		if (ti_work & _TIF_NOTIFY_SIGNAL)
-			tracehook_notify_signal();
+		if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) {
+			clear_notify_signal();
+			if (task_work_pending(current))
+				task_work_run();
+		}
 
 		if (ti_work & _TIF_SIGPENDING) {
 			kvm_handle_signal_exit(vcpu);
@@ -20,7 +23,7 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
 			schedule();
 
 		if (ti_work & _TIF_NOTIFY_RESUME)
-			tracehook_notify_resume(NULL);
+			resume_user_mode_work(NULL);
 
 		ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work);
 		if (ret)
diff --git a/kernel/exit.c b/kernel/exit.c
index c8ce55541a25..f072959fcab7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -49,7 +49,8 @@
 #include <linux/audit.h> /* for audit_free() */
 #include <linux/resource.h>
 #include <linux/task_io_accounting_ops.h>
-#include <linux/tracehook.h>
+#include <linux/blkdev.h>
+#include <linux/task_work.h>
 #include <linux/fs_struct.h>
 #include <linux/init_task.h>
 #include <linux/perf_event.h>
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index 77ef45a1e0a3..5d03a2ad1066 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -9,7 +9,6 @@
 
 #include <linux/cpu.h>
 #include <linux/stacktrace.h>
-#include <linux/tracehook.h>
 #include "core.h"
 #include "patch.h"
 #include "transition.h"
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index eea265082e97..ccc4b465775b 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -371,6 +371,26 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode)
 	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(&current->seccomp) != SECCOMP_MODE_DISABLED ||
+		    current->ptrace & PT_SUSPEND_SECCOMP)
+			return -EPERM;
+	}
+	return 0;
+}
+
 static int ptrace_attach(struct task_struct *task, long request,
 			 unsigned long addr,
 			 unsigned long flags)
@@ -382,8 +402,16 @@ static int ptrace_attach(struct task_struct *task, long request,
 	if (seize) {
 		if (addr != 0)
 			goto out;
+		/*
+		 * 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)
 			goto out;
+		retval = check_ptrace_options(flags);
+		if (retval)
+			return retval;
 		flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT);
 	} else {
 		flags = PT_PTRACED;
@@ -654,22 +682,11 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds
 static int ptrace_setoptions(struct task_struct *child, unsigned long data)
 {
 	unsigned flags;
+	int ret;
 
-	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(&current->seccomp) != SECCOMP_MODE_DISABLED ||
-		    current->ptrace & PT_SUSPEND_SECCOMP)
-			return -EPERM;
-	}
+	ret = check_ptrace_options(data);
+	if (ret)
+		return ret;
 
 	/* Avoid intermediate state when all opts are cleared */
 	flags = child->ptrace;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ee0664c9d291..d4bd299d67ab 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -44,6 +44,7 @@
 #include <linux/profile.h>
 #include <linux/psi.h>
 #include <linux/ratelimit.h>
+#include <linux/task_work.h>
 
 #include <asm/switch_to.h>
 
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index db10e73d06e0..b5ac87f6dbd4 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -42,7 +42,6 @@
 #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>
diff --git a/kernel/signal.c b/kernel/signal.c
index e93de6daa188..368a34c25bbf 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -32,7 +32,7 @@
 #include <linux/signal.h>
 #include <linux/signalfd.h>
 #include <linux/ratelimit.h>
-#include <linux/tracehook.h>
+#include <linux/task_work.h>
 #include <linux/capability.h>
 #include <linux/freezer.h>
 #include <linux/pid_namespace.h>
@@ -2229,14 +2229,17 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
  * That makes it a way to test a stopped process for
  * being ptrace-stopped vs being job-control-stopped.
  *
- * If we actually decide not to stop at all because the tracer
- * is gone, we keep current->exit_code unless clear_code.
+ * Returns the signal the ptracer requested the code resume
+ * with.  If the code did not stop because the tracer is gone,
+ * the stop signal remains unchanged unless clear_code.
  */
-static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t *info)
+static int ptrace_stop(int exit_code, int why, int clear_code,
+			unsigned long message, kernel_siginfo_t *info)
 	__releases(&current->sighand->siglock)
 	__acquires(&current->sighand->siglock)
 {
 	bool gstop_done = false;
+	bool read_code = true;
 
 	if (arch_ptrace_stop_needed()) {
 		/*
@@ -2278,6 +2281,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t
 	 */
 	smp_wmb();
 
+	current->ptrace_message = message;
 	current->last_siginfo = info;
 	current->exit_code = exit_code;
 
@@ -2344,8 +2348,9 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t
 
 		/* tasklist protects us from ptrace_freeze_traced() */
 		__set_current_state(TASK_RUNNING);
+		read_code = false;
 		if (clear_code)
-			current->exit_code = 0;
+			exit_code = 0;
 		read_unlock(&tasklist_lock);
 	}
 
@@ -2355,7 +2360,11 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t
 	 * any signal-sending on another CPU that wants to examine it.
 	 */
 	spin_lock_irq(&current->sighand->siglock);
+	if (read_code)
+		exit_code = current->exit_code;
 	current->last_siginfo = NULL;
+	current->ptrace_message = 0;
+	current->exit_code = 0;
 
 	/* LISTENING can be set only during STOP traps, clear it */
 	current->jobctl &= ~JOBCTL_LISTENING;
@@ -2366,9 +2375,10 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t
 	 * This sets TIF_SIGPENDING, but never clears it.
 	 */
 	recalc_sigpending_tsk(current);
+	return exit_code;
 }
 
-static void ptrace_do_notify(int signr, int exit_code, int why)
+static int ptrace_do_notify(int signr, int exit_code, int why, unsigned long message)
 {
 	kernel_siginfo_t info;
 
@@ -2379,18 +2389,21 @@ static void ptrace_do_notify(int signr, int exit_code, int why)
 	info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
 
 	/* Let the debugger run.  */
-	ptrace_stop(exit_code, why, 1, &info);
+	return ptrace_stop(exit_code, why, 1, message, &info);
 }
 
-void ptrace_notify(int exit_code)
+int ptrace_notify(int exit_code, unsigned long message)
 {
+	int signr;
+
 	BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP);
-	if (unlikely(current->task_works))
+	if (unlikely(task_work_pending(current)))
 		task_work_run();
 
 	spin_lock_irq(&current->sighand->siglock);
-	ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED);
+	signr = ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED, message);
 	spin_unlock_irq(&current->sighand->siglock);
+	return signr;
 }
 
 /**
@@ -2545,11 +2558,10 @@ static void do_jobctl_trap(void)
 			signr = SIGTRAP;
 		WARN_ON_ONCE(!signr);
 		ptrace_do_notify(signr, signr | (PTRACE_EVENT_STOP << 8),
-				 CLD_STOPPED);
+				 CLD_STOPPED, 0);
 	} else {
 		WARN_ON_ONCE(!signr);
-		ptrace_stop(signr, CLD_STOPPED, 0, NULL);
-		current->exit_code = 0;
+		ptrace_stop(signr, CLD_STOPPED, 0, 0, NULL);
 	}
 }
 
@@ -2602,15 +2614,12 @@ static int ptrace_signal(int signr, kernel_siginfo_t *info, enum pid_type type)
 	 * comment in dequeue_signal().
 	 */
 	current->jobctl |= JOBCTL_STOP_DEQUEUED;
-	ptrace_stop(signr, CLD_TRAPPED, 0, info);
+	signr = ptrace_stop(signr, CLD_TRAPPED, 0, 0, info);
 
 	/* We're back.  Did the debugger cancel the sig?  */
-	signr = current->exit_code;
 	if (signr == 0)
 		return signr;
 
-	current->exit_code = 0;
-
 	/*
 	 * Update the siginfo structure if the signal has
 	 * changed.  If the debugger wanted something
@@ -2667,20 +2676,12 @@ bool get_signal(struct ksignal *ksig)
 	struct signal_struct *signal = current->signal;
 	int signr;
 
-	if (unlikely(current->task_works))
+	clear_notify_signal();
+	if (unlikely(task_work_pending(current)))
 		task_work_run();
 
-	/*
-	 * For non-generic architectures, check for TIF_NOTIFY_SIGNAL so
-	 * that the arch handlers don't all have to do it. If we get here
-	 * without TIF_SIGPENDING, just exit after running signal work.
-	 */
-	if (!IS_ENABLED(CONFIG_GENERIC_ENTRY)) {
-		if (test_thread_flag(TIF_NOTIFY_SIGNAL))
-			tracehook_notify_signal();
-		if (!task_sigpending(current))
-			return false;
-	}
+	if (!task_sigpending(current))
+		return false;
 
 	if (unlikely(uprobe_deny_signal()))
 		return false;
@@ -2939,7 +2940,8 @@ static void signal_delivered(struct ksignal *ksig, int stepping)
 	set_current_blocked(&blocked);
 	if (current->sas_ss_flags & SS_AUTODISARM)
 		sas_ss_reset(current);
-	tracehook_signal_handler(stepping);
+	if (stepping)
+		ptrace_notify(SIGTRAP, 0);
 }
 
 void signal_setup_done(int failed, struct ksignal *ksig, int stepping)
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 1698fbe6f0e1..c59e1a49bc40 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/spinlock.h>
 #include <linux/task_work.h>
-#include <linux/tracehook.h>
+#include <linux/resume_user_mode.h>
 
 static struct callback_head work_exited; /* all we need is ->next == NULL */
 
@@ -78,7 +78,7 @@ task_work_cancel_match(struct task_struct *task,
 	struct callback_head *work;
 	unsigned long flags;
 
-	if (likely(!task->task_works))
+	if (likely(!task_work_pending(task)))
 		return NULL;
 	/*
 	 * If cmpxchg() fails we continue without updating pprev.
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index e13e628509fb..0a97193984db 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -15,6 +15,7 @@
 #include <linux/workqueue.h>
 #include <linux/compat.h>
 #include <linux/sched/deadline.h>
+#include <linux/task_work.h>
 
 #include "posix-timers.h"