entry: Provide generic syscall exit function

Like syscall entry all architectures have similar and pointlessly different
code to handle pending work before returning from a syscall to user space.

  1) One-time syscall exit work:
      - rseq syscall exit
      - audit
      - syscall tracing
      - tracehook (single stepping)

  2) Preparatory work
      - Exit to user mode loop (common TIF handling).
      - Architecture specific one time work arch_exit_to_user_mode_prepare()
      - Address limit and lockdep checks
     
  3) Final transition (lockdep, tracing, context tracking, RCU). Invokes
     arch_exit_to_user_mode() to handle e.g. speculation mitigations

Provide a generic version based on the x86 code which has all the RCU and
instrumentation protections right.

Provide a variant for interrupt return to user mode as well which shares
the above #2 and #3 work items.

After syscall_exit_to_user_mode() and irqentry_exit_to_user_mode() the
architecture code just has to return to user space. The code after
returning from these functions must not be instrumented.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200722220519.613977173@linutronix.de

1 files changed, 169 insertions, 0 deletions

diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 1d636dee2fec..0a051bb91a56 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -2,6 +2,8 @@
 
 #include <linux/context_tracking.h>
 #include <linux/entry-common.h>
+#include <linux/livepatch.h>
+#include <linux/audit.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -82,7 +84,174 @@ noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
 	return syscall;
 }
 
+/**
+ * exit_to_user_mode - Fixup state when exiting to user mode
+ *
+ * Syscall/interupt exit enables interrupts, but the kernel state is
+ * interrupts disabled when this is invoked. Also tell RCU about it.
+ *
+ * 1) Trace interrupts on state
+ * 2) Invoke context tracking if enabled to adjust RCU state
+ * 3) Invoke architecture specific last minute exit code, e.g. speculation
+ *    mitigations, etc.
+ * 4) Tell lockdep that interrupts are enabled
+ */
+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);
+}
+
+/* Workaround to allow gradual conversion of architecture code */
+void __weak arch_do_signal(struct pt_regs *regs) { }
+
+static 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
+	 * items have been completed.
+	 */
+	while (ti_work & EXIT_TO_USER_MODE_WORK) {
+
+		local_irq_enable_exit_to_user(ti_work);
+
+		if (ti_work & _TIF_NEED_RESCHED)
+			schedule();
+
+		if (ti_work & _TIF_UPROBE)
+			uprobe_notify_resume(regs);
+
+		if (ti_work & _TIF_PATCH_PENDING)
+			klp_update_patch_state(current);
+
+		if (ti_work & _TIF_SIGPENDING)
+			arch_do_signal(regs);
+
+		if (ti_work & _TIF_NOTIFY_RESUME) {
+			clear_thread_flag(TIF_NOTIFY_RESUME);
+			tracehook_notify_resume(regs);
+			rseq_handle_notify_resume(NULL, regs);
+		}
+
+		/* Architecture specific TIF work */
+		arch_exit_to_user_mode_work(regs, ti_work);
+
+		/*
+		 * Disable interrupts and reevaluate the work flags as they
+		 * might have changed while interrupts and preemption was
+		 * enabled above.
+		 */
+		local_irq_disable_exit_to_user();
+		ti_work = READ_ONCE(current_thread_info()->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();
+	lockdep_assert_irqs_disabled();
+	lockdep_sys_exit();
+}
+
+#ifndef _TIF_SINGLESTEP
+static inline bool report_single_step(unsigned long ti_work)
+{
+	return false;
+}
+#else
+/*
+ * If TIF_SYSCALL_EMU is set, then the only reason to report is when
+ * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
+ * instruction has been already reported in syscall_enter_from_usermode().
+ */
+#define SYSEMU_STEP	(_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)
+
+static inline bool report_single_step(unsigned long ti_work)
+{
+	return (ti_work & SYSEMU_STEP) == _TIF_SINGLESTEP;
+}
+#endif
+
+static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work)
+{
+	bool step;
+
+	audit_syscall_exit(regs);
+
+	if (ti_work & _TIF_SYSCALL_TRACEPOINT)
+		trace_sys_exit(regs, syscall_get_return_value(current, regs));
+
+	step = report_single_step(ti_work);
+	if (step || ti_work & _TIF_SYSCALL_TRACE)
+		arch_syscall_exit_tracehook(regs, step);
+}
+
+/*
+ * Syscall specific exit to user mode preparation. Runs with interrupts
+ * enabled.
+ */
+static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+	u32 cached_flags = READ_ONCE(current_thread_info()->flags);
+	unsigned long nr = syscall_get_nr(current, regs);
+
+	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
+
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
+		if (WARN(irqs_disabled(), "syscall %lu left IRQs disabled", nr))
+			local_irq_enable();
+	}
+
+	rseq_syscall(regs);
+
+	/*
+	 * Do one-time syscall specific work. If these work items are
+	 * enabled, we want to run them exactly once per syscall exit with
+	 * interrupts enabled.
+	 */
+	if (unlikely(cached_flags & SYSCALL_EXIT_WORK))
+		syscall_exit_work(regs, cached_flags);
+}
+
+__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	syscall_exit_to_user_mode_prepare(regs);
+	local_irq_disable_exit_to_user();
+	exit_to_user_mode_prepare(regs);
+	instrumentation_end();
+	exit_to_user_mode();
+}
+
 noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
 {
 	enter_from_user_mode(regs);
 }
+
+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();
+}