entry: Ensure trap after single-step on system call return

Commit 29915524 ("entry: Drop usage of TIF flags in the generic syscall
code") introduced a bug on architectures using the generic syscall entry
code, in which processes stopped by PTRACE_SYSCALL do not trap on syscall
return after receiving a TIF_SINGLESTEP.

The reason is that the meaning of TIF_SINGLESTEP flag is overloaded to
cause the trap after a system call is executed, but since the above commit,
the syscall call handler only checks for the SYSCALL_WORK flags on the exit
work.

Split the meaning of TIF_SINGLESTEP such that it only means single-step
mode, and create a new type of SYSCALL_WORK to request a trap immediately
after a syscall in single-step mode.  In the current implementation, the
SYSCALL_WORK flag shadows the TIF_SINGLESTEP flag for simplicity.

Update x86 to flip this bit when a tracer enables single stepping.

Fixes: 29915524 ("entry: Drop usage of TIF flags in the generic syscall code")
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Kyle Huey <me@kylehuey.com>
Link: https://lore.kernel.org/r/87h7mtc9pr.fsf_-_@collabora.com

arch/x86/include/asm/entry-common.h

@@ -43,8 +43,6 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs)
 }
 #define arch_check_user_regs arch_check_user_regs
 
-#define ARCH_SYSCALL_EXIT_WORK		(_TIF_SINGLESTEP)
-
 static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 						  unsigned long ti_work)
 {

arch/x86/kernel/step.c

@@ -127,12 +127,17 @@ static int enable_single_step(struct task_struct *child)
 		regs->flags |= X86_EFLAGS_TF;
 
 	/*
-	 * Always set TIF_SINGLESTEP - this guarantees that
-	 * we single-step system calls etc..  This will also
+	 * Always set TIF_SINGLESTEP.  This will also
 	 * cause us to set TF when returning to user mode.
 	 */
 	set_tsk_thread_flag(child, TIF_SINGLESTEP);
 
+	/*
+	 * Ensure that a trap is triggered once stepping out of a system
+	 * call prior to executing any user instruction.
+	 */
+	set_task_syscall_work(child, SYSCALL_EXIT_TRAP);
+
 	oflags = regs->flags;
 
 	/* Set TF on the kernel stack.. */
@@ -230,6 +235,7 @@ void user_disable_single_step(struct task_struct *child)
 
 	/* Always clear TIF_SINGLESTEP... */
 	clear_tsk_thread_flag(child, TIF_SINGLESTEP);
+	clear_task_syscall_work(child, SYSCALL_EXIT_TRAP);
 
 	/* But touch TF only if it was set by us.. */
 	if (test_and_clear_tsk_thread_flag(child, TIF_FORCED_TF))

include/linux/entry-common.h

@@ -46,6 +46,7 @@
 				 SYSCALL_WORK_SYSCALL_TRACE |		\
 				 SYSCALL_WORK_SYSCALL_AUDIT |		\
 				 SYSCALL_WORK_SYSCALL_USER_DISPATCH |	\
+				 SYSCALL_WORK_SYSCALL_EXIT_TRAP	|	\
 				 ARCH_SYSCALL_WORK_EXIT)
 
 /*

include/linux/thread_info.h

@@ -43,6 +43,7 @@ enum syscall_work_bit {
 	SYSCALL_WORK_BIT_SYSCALL_EMU,
 	SYSCALL_WORK_BIT_SYSCALL_AUDIT,
 	SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH,
+	SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP,
 };
 
 #define SYSCALL_WORK_SECCOMP		BIT(SYSCALL_WORK_BIT_SECCOMP)
@@ -51,6 +52,7 @@ enum syscall_work_bit {
 #define SYSCALL_WORK_SYSCALL_EMU	BIT(SYSCALL_WORK_BIT_SYSCALL_EMU)
 #define SYSCALL_WORK_SYSCALL_AUDIT	BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT)
 #define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH)
+#define SYSCALL_WORK_SYSCALL_EXIT_TRAP	BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP)
 #endif
 
 #include <asm/thread_info.h>

kernel/entry/common.c

@@ -209,15 +209,9 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
 	lockdep_sys_exit();
 }
 
-#ifndef _TIF_SINGLESTEP
-static inline bool report_single_step(unsigned long work)
-{
-	return false;
-}
-#else
 /*
  * If SYSCALL_EMU is set, then the only reason to report is when
- * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
+ * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
  * instruction has been already reported in syscall_enter_from_user_mode().
  */
 static inline bool report_single_step(unsigned long work)
@@ -225,10 +219,8 @@ static inline bool report_single_step(unsigned long work)
 	if (work & SYSCALL_WORK_SYSCALL_EMU)
 		return false;
 
-	return !!(current_thread_info()->flags & _TIF_SINGLESTEP);
+	return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
 }
-#endif
-
 
 static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
 {