3 files changed, 140 insertions, 142 deletions

diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index f9d491b17b78..90843cc38588 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -2,34 +2,19 @@
 
 #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/kmsan.h>
 #include <linux/livepatch.h>
 #include <linux/audit.h>
+#include <linux/tick.h>
 
 #include "common.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
-/* See comment for enter_from_user_mode() in entry-common.h */
-static __always_inline void __enter_from_user_mode(struct pt_regs *regs)
-{
-	arch_check_user_regs(regs);
-	lockdep_hardirqs_off(CALLER_ADDR0);
-
-	CT_WARN_ON(ct_state() != CONTEXT_USER);
-	user_exit_irqoff();
-
-	instrumentation_begin();
-	trace_hardirqs_off_finish();
-	instrumentation_end();
-}
-
-void noinstr enter_from_user_mode(struct pt_regs *regs)
-{
-	__enter_from_user_mode(regs);
-}
-
 static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
 {
 	if (unlikely(audit_context())) {
@@ -40,7 +25,7 @@ static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
 	}
 }
 
-static long syscall_trace_enter(struct pt_regs *regs, long syscall,
+long syscall_trace_enter(struct pt_regs *regs, long syscall,
 				unsigned long work)
 {
 	long ret = 0;
@@ -57,7 +42,7 @@ 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;
 	}
@@ -72,83 +57,38 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 	/* Either of the above might have changed the syscall number */
 	syscall = syscall_get_nr(current, regs);
 
-	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT))
+	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) {
 		trace_sys_enter(regs, syscall);
+		/*
+		 * Probes or BPF hooks in the tracepoint may have changed the
+		 * system call number as well.
+		 */
+		syscall = syscall_get_nr(current, regs);
+	}
 
 	syscall_enter_audit(regs, syscall);
 
 	return ret ? : syscall;
 }
 
-static __always_inline long
-__syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
-{
-	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
-
-	if (work & SYSCALL_WORK_ENTER)
-		syscall = syscall_trace_enter(regs, syscall, work);
-
-	return syscall;
-}
-
-long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
-{
-	return __syscall_enter_from_user_work(regs, syscall);
-}
-
-noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
-{
-	long ret;
-
-	__enter_from_user_mode(regs);
-
-	instrumentation_begin();
-	local_irq_enable();
-	ret = __syscall_enter_from_user_work(regs, syscall);
-	instrumentation_end();
-
-	return ret;
-}
-
 noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
 {
-	__enter_from_user_mode(regs);
+	enter_from_user_mode(regs);
 	instrumentation_begin();
 	local_irq_enable();
 	instrumentation_end();
 }
 
-/* See comment for exit_to_user_mode() in entry-common.h */
-static __always_inline void __exit_to_user_mode(void)
-{
-	instrumentation_begin();
-	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
-	instrumentation_end();
-
-	user_enter_irqoff();
-	arch_exit_to_user_mode();
-	lockdep_hardirqs_on(CALLER_ADDR0);
-}
-
-void noinstr exit_to_user_mode(void)
-{
-	__exit_to_user_mode();
-}
-
 /* 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) { }
 
-static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
-					    unsigned long ti_work)
+/**
+ * exit_to_user_mode_loop - do any pending work before leaving to user space
+ * @regs:	Pointer to pt_regs on entry stack
+ * @ti_work:	TIF work flags as read by the caller
+ */
+__always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
+						     unsigned long ti_work)
 {
 	/*
 	 * Before returning to user space ensure that all pending work
@@ -168,12 +108,10 @@ 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);
-			rseq_handle_notify_resume(NULL, regs);
-		}
+		if (ti_work & _TIF_NOTIFY_RESUME)
+			resume_user_mode_work(regs);
 
 		/* Architecture specific TIF work */
 		arch_exit_to_user_mode_work(regs, ti_work);
@@ -184,31 +122,17 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 		 * enabled above.
 		 */
 		local_irq_disable_exit_to_user();
-		ti_work = READ_ONCE(current_thread_info()->flags);
+
+		/* Check if any of the above work has queued a deferred wakeup */
+		tick_nohz_user_enter_prepare();
+
+		ti_work = read_thread_flags();
 	}
 
 	/* Return the latest work state for arch_exit_to_user_mode() */
 	return ti_work;
 }
 
-static void exit_to_user_mode_prepare(struct pt_regs *regs)
-{
-	unsigned long ti_work = READ_ONCE(current_thread_info()->flags);
-
-	lockdep_assert_irqs_disabled();
-
-	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
-		ti_work = exit_to_user_mode_loop(regs, ti_work);
-
-	arch_exit_to_user_mode_prepare(regs, ti_work);
-
-	/* Ensure that the address limit is intact and no locks are held */
-	addr_limit_user_check();
-	kmap_assert_nomap();
-	lockdep_assert_irqs_disabled();
-	lockdep_sys_exit();
-}
-
 /*
  * If SYSCALL_EMU is set, then the only reason to report is when
  * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
@@ -246,7 +170,7 @@ 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);
 }
 
 /*
@@ -293,12 +217,12 @@ __visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
 	instrumentation_begin();
 	__syscall_exit_to_user_mode_work(regs);
 	instrumentation_end();
-	__exit_to_user_mode();
+	exit_to_user_mode();
 }
 
 noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
 {
-	__enter_from_user_mode(regs);
+	enter_from_user_mode(regs);
 }
 
 noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
@@ -306,7 +230,7 @@ noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
 	instrumentation_begin();
 	exit_to_user_mode_prepare(regs);
 	instrumentation_end();
-	__exit_to_user_mode();
+	exit_to_user_mode();
 }
 
 noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
@@ -321,7 +245,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 	}
 
 	/*
-	 * If this entry hit the idle task invoke rcu_irq_enter() whether
+	 * If this entry hit the idle task invoke ct_irq_enter() whether
 	 * RCU is watching or not.
 	 *
 	 * Interrupts can nest when the first interrupt invokes softirq
@@ -332,12 +256,12 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 	 * not nested into another interrupt.
 	 *
 	 * Checking for rcu_is_watching() here would prevent the nesting
-	 * interrupt to invoke rcu_irq_enter(). If that nested interrupt is
+	 * interrupt to invoke ct_irq_enter(). If that nested interrupt is
 	 * the tick then rcu_flavor_sched_clock_irq() would wrongfully
-	 * assume that it is the first interupt and eventually claim
+	 * assume that it is the first interrupt and eventually claim
 	 * quiescent state and end grace periods prematurely.
 	 *
-	 * Unconditionally invoke rcu_irq_enter() so RCU state stays
+	 * Unconditionally invoke ct_irq_enter() so RCU state stays
 	 * consistent.
 	 *
 	 * TINY_RCU does not support EQS, so let the compiler eliminate
@@ -350,8 +274,9 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 		 * as in irqentry_enter_from_user_mode().
 		 */
 		lockdep_hardirqs_off(CALLER_ADDR0);
-		rcu_irq_enter();
+		ct_irq_enter();
 		instrumentation_begin();
+		kmsan_unpoison_entry_regs(regs);
 		trace_hardirqs_off_finish();
 		instrumentation_end();
 
@@ -367,6 +292,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 	 */
 	lockdep_hardirqs_off(CALLER_ADDR0);
 	instrumentation_begin();
+	kmsan_unpoison_entry_regs(regs);
 	rcu_irq_enter_check_tick();
 	trace_hardirqs_off_finish();
 	instrumentation_end();
@@ -374,7 +300,7 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 	return ret;
 }
 
-void irqentry_exit_cond_resched(void)
+void raw_irqentry_exit_cond_resched(void)
 {
 	if (!preempt_count()) {
 		/* Sanity check RCU and thread stack */
@@ -385,6 +311,19 @@ void irqentry_exit_cond_resched(void)
 			preempt_schedule_irq();
 	}
 }
+#ifdef CONFIG_PREEMPT_DYNAMIC
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+void dynamic_irqentry_exit_cond_resched(void)
+{
+	if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
+		return;
+	raw_irqentry_exit_cond_resched();
+}
+#endif
+#endif
 
 noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 {
@@ -403,9 +342,9 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 			instrumentation_begin();
 			/* Tell the tracer that IRET will enable interrupts */
 			trace_hardirqs_on_prepare();
-			lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+			lockdep_hardirqs_on_prepare();
 			instrumentation_end();
-			rcu_irq_exit();
+			ct_irq_exit();
 			lockdep_hardirqs_on(CALLER_ADDR0);
 			return;
 		}
@@ -413,6 +352,7 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 		instrumentation_begin();
 		if (IS_ENABLED(CONFIG_PREEMPTION))
 			irqentry_exit_cond_resched();
+
 		/* Covers both tracing and lockdep */
 		trace_hardirqs_on();
 		instrumentation_end();
@@ -422,7 +362,7 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
 		 * was not watching on entry.
 		 */
 		if (state.exit_rcu)
-			rcu_irq_exit();
+			ct_irq_exit();
 	}
 }
 
@@ -435,9 +375,10 @@ irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs)
 	__nmi_enter();
 	lockdep_hardirqs_off(CALLER_ADDR0);
 	lockdep_hardirq_enter();
-	rcu_nmi_enter();
+	ct_nmi_enter();
 
 	instrumentation_begin();
+	kmsan_unpoison_entry_regs(regs);
 	trace_hardirqs_off_finish();
 	ftrace_nmi_enter();
 	instrumentation_end();
@@ -451,11 +392,11 @@ void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state)
 	ftrace_nmi_exit();
 	if (irq_state.lockdep) {
 		trace_hardirqs_on_prepare();
-		lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+		lockdep_hardirqs_on_prepare();
 	}
 	instrumentation_end();
 
-	rcu_nmi_exit();
+	ct_nmi_exit();
 	lockdep_hardirq_exit();
 	if (irq_state.lockdep)
 		lockdep_hardirqs_on(CALLER_ADDR0);
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
index 49972ee99aff..2e0f75bcb7fd 100644
--- a/kernel/entry/kvm.c
+++ b/kernel/entry/kvm.c
@@ -8,10 +8,7 @@ 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) {
+		if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) {
 			kvm_handle_signal_exit(vcpu);
 			return -EINTR;
 		}
@@ -20,13 +17,13 @@ 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)
 			return ret;
 
-		ti_work = READ_ONCE(current_thread_info()->flags);
+		ti_work = read_thread_flags();
 	} while (ti_work & XFER_TO_GUEST_MODE_WORK || need_resched());
 	return 0;
 }
@@ -43,7 +40,7 @@ int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu)
 	 * disabled in the inner loop before going into guest mode. No need
 	 * to disable interrupts here.
 	 */
-	ti_work = READ_ONCE(current_thread_info()->flags);
+	ti_work = read_thread_flags();
 	if (!(ti_work & XFER_TO_GUEST_MODE_WORK))
 		return 0;
 
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
index c240302f56e2..5340c5aa89e7 100644
--- a/kernel/entry/syscall_user_dispatch.c
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -4,6 +4,7 @@
  */
 #include <linux/sched.h>
 #include <linux/prctl.h>
+#include <linux/ptrace.h>
 #include <linux/syscall_user_dispatch.h>
 #include <linux/uaccess.h>
 #include <linux/signal.h>
@@ -47,14 +48,18 @@ bool syscall_user_dispatch(struct pt_regs *regs)
 		 * access_ok() is performed once, at prctl time, when
 		 * the selector is loaded by userspace.
 		 */
-		if (unlikely(__get_user(state, sd->selector)))
-			do_exit(SIGSEGV);
+		if (unlikely(__get_user(state, sd->selector))) {
+			force_exit_sig(SIGSEGV);
+			return true;
+		}
 
 		if (likely(state == SYSCALL_DISPATCH_FILTER_ALLOW))
 			return false;
 
-		if (state != SYSCALL_DISPATCH_FILTER_BLOCK)
-			do_exit(SIGSYS);
+		if (state != SYSCALL_DISPATCH_FILTER_BLOCK) {
+			force_exit_sig(SIGSYS);
+			return true;
+		}
 	}
 
 	sd->on_dispatch = true;
@@ -64,8 +69,9 @@ bool syscall_user_dispatch(struct pt_regs *regs)
 	return true;
 }
 
-int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
-			      unsigned long len, char __user *selector)
+static int task_set_syscall_user_dispatch(struct task_struct *task, unsigned long mode,
+					  unsigned long offset, unsigned long len,
+					  char __user *selector)
 {
 	switch (mode) {
 	case PR_SYS_DISPATCH_OFF:
@@ -82,7 +88,16 @@ int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
 		if (offset && offset + len <= offset)
 			return -EINVAL;
 
-		if (selector && !access_ok(selector, sizeof(*selector)))
+		/*
+		 * access_ok() will clear memory tags for tagged addresses
+		 * if current has memory tagging enabled.
+
+		 * To enable a tracer to set a tracees selector the
+		 * selector address must be untagged for access_ok(),
+		 * otherwise an untagged tracer will always fail to set a
+		 * tagged tracees selector.
+		 */
+		if (selector && !access_ok(untagged_addr(selector), sizeof(*selector)))
 			return -EFAULT;
 
 		break;
@@ -90,15 +105,60 @@ int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
 		return -EINVAL;
 	}
 
-	current->syscall_dispatch.selector = selector;
-	current->syscall_dispatch.offset = offset;
-	current->syscall_dispatch.len = len;
-	current->syscall_dispatch.on_dispatch = false;
+	task->syscall_dispatch.selector = selector;
+	task->syscall_dispatch.offset = offset;
+	task->syscall_dispatch.len = len;
+	task->syscall_dispatch.on_dispatch = false;
 
 	if (mode == PR_SYS_DISPATCH_ON)
-		set_syscall_work(SYSCALL_USER_DISPATCH);
+		set_task_syscall_work(task, SYSCALL_USER_DISPATCH);
+	else
+		clear_task_syscall_work(task, SYSCALL_USER_DISPATCH);
+
+	return 0;
+}
+
+int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
+			      unsigned long len, char __user *selector)
+{
+	return task_set_syscall_user_dispatch(current, mode, offset, len, selector);
+}
+
+int syscall_user_dispatch_get_config(struct task_struct *task, unsigned long size,
+				     void __user *data)
+{
+	struct syscall_user_dispatch *sd = &task->syscall_dispatch;
+	struct ptrace_sud_config cfg;
+
+	if (size != sizeof(cfg))
+		return -EINVAL;
+
+	if (test_task_syscall_work(task, SYSCALL_USER_DISPATCH))
+		cfg.mode = PR_SYS_DISPATCH_ON;
 	else
-		clear_syscall_work(SYSCALL_USER_DISPATCH);
+		cfg.mode = PR_SYS_DISPATCH_OFF;
+
+	cfg.offset = sd->offset;
+	cfg.len = sd->len;
+	cfg.selector = (__u64)(uintptr_t)sd->selector;
+
+	if (copy_to_user(data, &cfg, sizeof(cfg)))
+		return -EFAULT;
 
 	return 0;
 }
+
+int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long size,
+				     void __user *data)
+{
+	struct ptrace_sud_config cfg;
+
+	if (size != sizeof(cfg))
+		return -EINVAL;
+
+	if (copy_from_user(&cfg, data, sizeof(cfg)))
+		return -EFAULT;
+
+	return task_set_syscall_user_dispatch(task, cfg.mode, cfg.offset, cfg.len,
+					      (char __user *)(uintptr_t)cfg.selector);
+}