[S390] signal race with restarting system calls

For a ERESTARTNOHAND/ERESTARTSYS/ERESTARTNOINTR restarting system call
do_signal will prepare the restart of the system call with a rewind of
the PSW before calling get_signal_to_deliver (where the debugger might
take control). For A ERESTART_RESTARTBLOCK restarting system call
do_signal will set -EINTR as return code.
There are two issues with this approach:
1) strace never sees ERESTARTNOHAND, ERESTARTSYS, ERESTARTNOINTR or
   ERESTART_RESTARTBLOCK as the rewinding already took place or the
   return code has been changed to -EINTR
2) if get_signal_to_deliver does not return with a signal to deliver
   the restart via the repeat of the svc instruction is left in place.
   This opens a race if another signal is made pending before the
   system call instruction can be reexecuted. The original system call
   will be restarted even if the second signal would have ended the
   system call with -EINTR.

These two issues can be solved by dropping the early rewind of the
system call before get_signal_to_deliver has been called and by using
the TIF_RESTART_SVC magic to do the restart if no signal has to be
delivered. The only situation where the system call restart via the
repeat of the svc instruction is appropriate is when a SA_RESTART
signal is delivered to user space.

Unfortunately this breaks inferior calls by the debugger again. The
system call number and the length of the system call instruction is
lost over the inferior call and user space will see ERESTARTNOHAND/
ERESTARTSYS/ERESTARTNOINTR/ERESTART_RESTARTBLOCK. To correct this a
new ptrace interface is added to save/restore the system call number
and system call instruction length.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

1 files changed, 50 insertions, 1 deletions

diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index ae0e14b..bae1cc4 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -42,6 +42,7 @@ enum s390_regset {
 	REGSET_GENERAL,
 	REGSET_FP,
 	REGSET_LAST_BREAK,
+	REGSET_SYSTEM_CALL,
 	REGSET_GENERAL_EXTENDED,
 };
 
@@ -303,6 +304,13 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 			   high order bit but older gdb's rely on it */
 			data |= PSW_ADDR_AMODE;
 #endif
+		if (addr == (addr_t) &dummy->regs.psw.addr)
+			/*
+			 * The debugger changed the instruction address,
+			 * reset system call restart, see signal.c:do_signal
+			 */
+			task_thread_info(child)->system_call = 0;
+
 		*(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
 
 	} else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {
@@ -610,6 +618,11 @@ static int __poke_user_compat(struct task_struct *child,
 			/* Build a 64 bit psw address from 31 bit address. */
 			task_pt_regs(child)->psw.addr =
 				(__u64) tmp & PSW32_ADDR_INSN;
+			/*
+			 * The debugger changed the instruction address,
+			 * reset system call restart, see signal.c:do_signal
+			 */
+			task_thread_info(child)->system_call = 0;
 		} else {
 			/* gpr 0-15 */
 			*(__u32*)((addr_t) &task_pt_regs(child)->psw
@@ -737,7 +750,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 		 * debugger stored an invalid system call number. Skip
 		 * the system call and the system call restart handling.
 		 */
-		regs->svcnr = 0;
+		regs->svc_code = 0;
 		ret = -1;
 	}
 
@@ -899,6 +912,26 @@ static int s390_last_break_get(struct task_struct *target,
 
 #endif
 
+static int s390_system_call_get(struct task_struct *target,
+				const struct user_regset *regset,
+				unsigned int pos, unsigned int count,
+				void *kbuf, void __user *ubuf)
+{
+	unsigned int *data = &task_thread_info(target)->system_call;
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   data, 0, sizeof(unsigned int));
+}
+
+static int s390_system_call_set(struct task_struct *target,
+				const struct user_regset *regset,
+				unsigned int pos, unsigned int count,
+				const void *kbuf, const void __user *ubuf)
+{
+	unsigned int *data = &task_thread_info(target)->system_call;
+	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  data, 0, sizeof(unsigned int));
+}
+
 static const struct user_regset s390_regsets[] = {
 	[REGSET_GENERAL] = {
 		.core_note_type = NT_PRSTATUS,
@@ -925,6 +958,14 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_last_break_get,
 	},
 #endif
+	[REGSET_SYSTEM_CALL] = {
+		.core_note_type = NT_S390_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(unsigned int),
+		.align = sizeof(unsigned int),
+		.get = s390_system_call_get,
+		.set = s390_system_call_set,
+	},
 };
 
 static const struct user_regset_view user_s390_view = {
@@ -1104,6 +1145,14 @@ static const struct user_regset s390_compat_regsets[] = {
 		.align = sizeof(long),
 		.get = s390_compat_last_break_get,
 	},
+	[REGSET_SYSTEM_CALL] = {
+		.core_note_type = NT_S390_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(compat_uint_t),
+		.align = sizeof(compat_uint_t),
+		.get = s390_system_call_get,
+		.set = s390_system_call_set,
+	},
 	[REGSET_GENERAL_EXTENDED] = {
 		.core_note_type = NT_S390_HIGH_GPRS,
 		.n = sizeof(s390_compat_regs_high) / sizeof(compat_long_t),