[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, 15 insertions, 15 deletions

diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 3257f7f..7ff07d3 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -43,8 +43,7 @@ SP_R13	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 104
 SP_R14	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 112
 SP_R15	     =	STACK_FRAME_OVERHEAD + __PT_GPRS + 120
 SP_ORIG_R2   =	STACK_FRAME_OVERHEAD + __PT_ORIG_GPR2
-SP_ILC	     =	STACK_FRAME_OVERHEAD + __PT_ILC
-SP_SVCNR      =	STACK_FRAME_OVERHEAD + __PT_SVCNR
+SP_SVC_CODE  =	STACK_FRAME_OVERHEAD + __PT_SVC_CODE
 SP_SIZE      =	STACK_FRAME_OVERHEAD + __PT_SIZE
 
 STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER
@@ -250,7 +249,7 @@ sysc_saveall:
 	SAVE_ALL_SVC __LC_SVC_OLD_PSW,__LC_SAVE_AREA
 	CREATE_STACK_FRAME __LC_SAVE_AREA
 	mvc	SP_PSW(16,%r15),__LC_SVC_OLD_PSW
-	mvc	SP_ILC(4,%r15),__LC_SVC_ILC
+	mvc	SP_SVC_CODE(4,%r15),__LC_SVC_ILC
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
 sysc_vtime:
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
@@ -260,14 +259,14 @@ sysc_update:
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
 	LAST_BREAK
 sysc_do_svc:
-	llgh	%r7,SP_SVCNR(%r15)
+	llgh	%r7,SP_SVC_CODE+2(%r15)
 	slag	%r7,%r7,2	# shift and test for svc 0
 	jnz	sysc_nr_ok
 	# svc 0: system call number in %r1
 	llgfr	%r1,%r1		# clear high word in r1
 	cghi	%r1,NR_syscalls
 	jnl	sysc_nr_ok
-	sth	%r1,SP_SVCNR(%r15)
+	sth	%r1,SP_SVC_CODE+2(%r15)
 	slag	%r7,%r1,2	# shift and test for svc 0
 sysc_nr_ok:
 	larl	%r10,sys_call_table
@@ -358,11 +357,12 @@ sysc_notify_resume:
 #
 sysc_restart:
 	ni	__TI_flags+7(%r12),255-_TIF_RESTART_SVC # clear TIF_RESTART_SVC
-	lg	%r7,SP_R2(%r15)		# load new svc number
-	mvc	SP_R2(8,%r15),SP_ORIG_R2(%r15) # restore first argument
 	lmg	%r2,%r6,SP_R2(%r15)	# load svc arguments
-	sth	%r7,SP_SVCNR(%r15)
-	slag	%r7,%r7,2
+	lghi	%r7,0			# svc 0 returns -ENOSYS
+	lh	%r1,SP_SVC_CODE+2(%r15)	# load new svc number
+	cghi	%r1,NR_syscalls
+	jnl	sysc_nr_ok		# invalid svc number -> do svc 0
+	slag	%r7,%r1,2
 	j	sysc_nr_ok		# restart svc
 
 #
@@ -370,7 +370,7 @@ sysc_restart:
 #
 sysc_singlestep:
 	ni	__TI_flags+7(%r12),255-_TIF_PER_TRAP	# clear TIF_PER_TRAP
-	xc	SP_SVCNR(2,%r15),SP_SVCNR(%r15)		# clear svc number
+	xc	SP_SVC_CODE(4,%r15),SP_SVC_CODE(%r15)	# clear svc code
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
 	larl	%r14,sysc_return	# load adr. of system return
 	jg	do_per_trap
@@ -382,7 +382,7 @@ sysc_singlestep:
 sysc_tracesys:
 	la	%r2,SP_PTREGS(%r15)	# load pt_regs
 	la	%r3,0
-	llgh	%r0,SP_SVCNR(%r15)
+	llgh	%r0,SP_SVC_CODE+2(%r15)
 	stg	%r0,SP_R2(%r15)
 	brasl	%r14,do_syscall_trace_enter
 	lghi	%r0,NR_syscalls
@@ -470,7 +470,7 @@ ENTRY(pgm_check_handler)
 	jnz	pgm_per 		 # got per exception -> special case
 	SAVE_ALL_PGM __LC_PGM_OLD_PSW,__LC_SAVE_AREA
 	CREATE_STACK_FRAME __LC_SAVE_AREA
-	xc	SP_ILC(4,%r15),SP_ILC(%r15)
+	xc	SP_SVC_CODE(4,%r15),SP_SVC_CODE(%r15)
 	mvc	SP_PSW(16,%r15),__LC_PGM_OLD_PSW
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
 	HANDLE_SIE_INTERCEPT
@@ -551,7 +551,7 @@ pgm_svcper:
 	SAVE_ALL_PGM __LC_SVC_OLD_PSW,__LC_SAVE_AREA
 	CREATE_STACK_FRAME __LC_SAVE_AREA
 	mvc	SP_PSW(16,%r15),__LC_SVC_OLD_PSW
-	mvc	SP_ILC(4,%r15),__LC_SVC_ILC
+	mvc	SP_SVC_CODE(4,%r15),__LC_SVC_ILC
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
 	UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER
@@ -571,7 +571,7 @@ pgm_svcper:
 #
 kernel_per:
 	REENABLE_IRQS
-	xc	SP_SVCNR(2,%r15),SP_SVCNR(%r15)	# clear svc number
+	xc	SP_SVC_CODE(4,%r15),SP_SVC_CODE(%r15)	# clear svc number
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
 	brasl	%r14,do_per_trap
 	j	pgm_exit
@@ -973,7 +973,7 @@ cleanup_system_call:
 	stg	%r11,0(%r12)
 	CREATE_STACK_FRAME __LC_SAVE_AREA
 	mvc	SP_PSW(16,%r15),__LC_SVC_OLD_PSW
-	mvc	SP_ILC(4,%r15),__LC_SVC_ILC
+	mvc	SP_SVC_CODE(4,%r15),__LC_SVC_ILC
 	mvc	8(8,%r12),__LC_THREAD_INFO
 cleanup_vtime:
 	clc	__LC_RETURN_PSW+8(8),BASED(cleanup_system_call_insn+24)