entry: Add syscall_exit_to_user_mode_work()

This is the same as syscall_exit_to_user_mode() but without calling
exit_to_user_mode(). This can be used if there is an architectural reason
to avoid the combo function, e.g. restarting a syscall without returning to
userspace. Before returning to user space the caller has to invoke
exit_to_user_mode().

[ tglx: Amended comments ]

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201201142755.31931-6-svens@linux.ibm.com

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index e370be8..7c581a4 100644 (file)
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -316,10 +316,26 @@ static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step)
  * is not suitable as the last step before returning to userspace. Must be
  * invoked with interrupts disabled and the caller must be
  * non-instrumentable.
+ * The caller has to invoke syscall_exit_to_user_mode_work() before this.
  */
 void exit_to_user_mode(void);
 
 /**
+ * syscall_exit_to_user_mode_work - Handle work before returning to user mode
+ * @regs:      Pointer to currents pt_regs
+ *
+ * Same as step 1 and 2 of syscall_exit_to_user_mode() but without calling
+ * exit_to_user_mode() to perform the final transition to user mode.
+ *
+ * Calling convention is the same as for syscall_exit_to_user_mode() and it
+ * returns with all work handled and interrupts disabled. The caller must
+ * invoke exit_to_user_mode() before actually switching to user mode to
+ * make the final state transitions. Interrupts must stay disabled between
+ * return from this function and the invocation of exit_to_user_mode().
+ */
+void syscall_exit_to_user_mode_work(struct pt_regs *regs);
+
+/**
  * syscall_exit_to_user_mode - Handle work before returning to user mode
  * @regs:      Pointer to currents pt_regs
  *
@@ -343,6 +359,10 @@ void exit_to_user_mode(void);
  *
  *  3) Final transition (lockdep, tracing, context tracking, RCU), i.e. the
  *     functionality in exit_to_user_mode().
+ *
+ * This is a combination of syscall_exit_to_user_mode_work() (1,2) and
+ * exit_to_user_mode(). This function is preferred unless there is a
+ * compelling architectural reason to use the seperate functions.
  */
 void syscall_exit_to_user_mode(struct pt_regs *regs);
 

diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 48d30ce..d6b7393 100644 (file)
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -282,12 +282,22 @@ static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
                syscall_exit_work(regs, work);
 }
 
-__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
+static __always_inline void __syscall_exit_to_user_mode_work(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);
+}
+
+void syscall_exit_to_user_mode_work(struct pt_regs *regs)
+{
+       __syscall_exit_to_user_mode_work(regs);
+}
+
+__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();
 }