s390/kdump: remove nodat stack restriction for calling nodat functions

To allow calling of DAT-off code from kernel the stack needs
to be switched to nodat_stack (or other stack mapped as 1:1).

Before call_nodat() macro was introduced that was necessary
to provide the very same memory address for STNSM and STOSM
instructions. If the kernel would stay on a random stack
(e.g. a virtually mapped one) then a virtual address provided
for STNSM instruction could differ from the physical address
needed for the corresponding STOSM instruction.

After call_nodat() macro is introduced the kernel stack does
not need to be mapped 1:1 anymore, since the macro stores the
physical memory address of return PSW in a register before
entering DAT-off mode. This way the return LPSWE instruction
is able to pick the correct memory location and restore the
DAT-on mode. That however might fail in case the 16-byte return
PSW happened to cross page boundary: PSW mask and PSW address
could end up in two separate non-contiguous physical pages.

Align the return PSW on 16-byte boundary so it always fits
into a single physical page. As result any stack (including
the virtually mapped one) could be used for calling DAT-off
code and prior switching to nodat_stack becomes unnecessary.
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>

arch/s390/include/asm/stacktrace.h

@@ -210,7 +210,9 @@ static __always_inline unsigned long get_stack_pointer(struct task_struct *task,
 #define call_nodat(nr, rettype, fn, ...)				\
 ({									\
 	rettype (*__fn)(CALL_PARM_##nr(__VA_ARGS__)) = (fn);		\
-	psw_t psw_enter, psw_leave;					\
+	/* aligned since psw_leave must not cross page boundary */	\
+	psw_t __aligned(16) psw_leave;					\
+	psw_t psw_enter;						\
 	CALL_LARGS_##nr(__VA_ARGS__);					\
 	CALL_REGS_##nr;							\
 									\

arch/s390/kernel/machine_kexec.c

@@ -112,13 +112,6 @@ static noinline void __machine_kdump(void *image)
 	store_status(__do_machine_kdump, image);
 }
 
-static int do_start_kdump(struct kimage *image)
-{
-	purgatory_t purgatory = (purgatory_t)image->start;
-
-	return call_nodat(1, int, purgatory, int, 0);
-}
-
 #endif /* CONFIG_CRASH_DUMP */
 
 /*
@@ -127,12 +120,10 @@ static int do_start_kdump(struct kimage *image)
 static bool kdump_csum_valid(struct kimage *image)
 {
 #ifdef CONFIG_CRASH_DUMP
+	purgatory_t purgatory = (purgatory_t)image->start;
 	int rc;
 
-	preempt_disable();
-	rc = call_on_stack(1, S390_lowcore.nodat_stack, int, do_start_kdump,
-			   struct kimage *, image);
-	preempt_enable();
+	rc = call_nodat(1, int, purgatory, int, 0);
 	return rc == 0;
 #else
 	return false;