s390: fix fpu restore in entry.S

We need to disable interrupts in load_fpu_regs(). Otherwise an
interrupt might come in after the registers are loaded, but before
CIF_FPU is cleared in load_fpu_regs(). When the interrupt returns,
CIF_FPU will be cleared and the registers will never be restored.

The entry.S code usually saves the interrupt state in __SF_EMPTY on the
stack when disabling/restoring interrupts. sie64a however saves the pointer
to the sie control block in __SF_SIE_CONTROL, which references the same
location.  This is non-obvious to the reader. To avoid thrashing the sie
control block pointer in load_fpu_regs(), move the __SIE_* offsets eight
bytes after __SF_EMPTY on the stack.

Cc: <stable@vger.kernel.org> # 5.8
Fixes: 0b0ed65 ("s390: remove critical section cleanup from entry.S")
Reported-by: Pierre Morel <pmorel@linux.ibm.com>
Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>

Author: svens-s390

arch/s390/kernel/asm-offsets.c

@@ -53,11 +53,11 @@ int main(void)
 	/* stack_frame offsets */
 	OFFSET(__SF_BACKCHAIN, stack_frame, back_chain);
 	OFFSET(__SF_GPRS, stack_frame, gprs);
-	OFFSET(__SF_EMPTY, stack_frame, empty1);
-	OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[0]);
-	OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[1]);
-	OFFSET(__SF_SIE_REASON, stack_frame, empty1[2]);
-	OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[3]);
+	OFFSET(__SF_EMPTY, stack_frame, empty1[0]);
+	OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[1]);
+	OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[2]);
+	OFFSET(__SF_SIE_REASON, stack_frame, empty1[3]);
+	OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[4]);
 	BLANK();
 	OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val);
 	BLANK();

arch/s390/kernel/entry.S

@@ -1068,6 +1068,7 @@ EXPORT_SYMBOL(save_fpu_regs)
  *	%r4
  */
 load_fpu_regs:
+	stnsm	__SF_EMPTY(%r15),0xfc
 	lg	%r4,__LC_CURRENT
 	aghi	%r4,__TASK_thread
 	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
@@ -1099,6 +1100,7 @@ load_fpu_regs:
 .Lload_fpu_regs_done:
 	ni	__LC_CPU_FLAGS+7,255-_CIF_FPU
 .Lload_fpu_regs_exit:
+	ssm	__SF_EMPTY(%r15)
 	BR_EX	%r14
 .Lload_fpu_regs_end:
 ENDPROC(load_fpu_regs)