s390/mm: remove set_fs / rework address space handling

Remove set_fs support from s390. With doing this rework address space
handling and simplify it. As a result address spaces are now setup
like this:

CPU running in              | %cr1 ASCE | %cr7 ASCE | %cr13 ASCE
----------------------------|-----------|-----------|-----------
user space                  |  user     |  user     |  kernel
kernel, normal execution    |  kernel   |  user     |  kernel
kernel, kvm guest execution |  gmap     |  user     |  kernel

To achieve this the getcpu vdso syscall is removed in order to avoid
secondary address mode and a separate vdso address space in for user
space. The getcpu vdso syscall will be implemented differently with a
subsequent patch.

The kernel accesses user space always via secondary address space.
This happens in different ways:
- with mvcos in home space mode and directly read/write to secondary
  address space
- with mvcs/mvcp in primary space mode and copy from primary space to
  secondary space or vice versa
- with e.g. cs in secondary space mode and access secondary space

Switching translation modes happens with sacf before and after
instructions which access user space, like before.

Lazy handling of control register reloading is removed in the hope to
make everything simpler, but at the cost of making kernel entry and
exit a bit slower. That is: on kernel entry the primary asce is always
changed to contain the kernel asce, and on kernel exit the primary
asce is changed again so it contains the user asce.

In kernel mode there is only one exception to the primary asce: when
kvm guests are executed the primary asce contains the gmap asce (which
describes the guest address space). The primary asce is reset to
kernel asce whenever kvm guest execution is interrupted, so that this
doesn't has to be taken into account for any user space accesses.

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>

2 files changed, 9 insertions, 33 deletions

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 996884dcc9fd..b8210103de14 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -53,7 +53,6 @@
 enum fault_type {
 	KERNEL_FAULT,
 	USER_FAULT,
-	VDSO_FAULT,
 	GMAP_FAULT,
 };
 
@@ -77,22 +76,16 @@ static enum fault_type get_fault_type(struct pt_regs *regs)
 	trans_exc_code = regs->int_parm_long & 3;
 	if (likely(trans_exc_code == 0)) {
 		/* primary space exception */
-		if (IS_ENABLED(CONFIG_PGSTE) &&
-		    test_pt_regs_flag(regs, PIF_GUEST_FAULT))
-			return GMAP_FAULT;
-		if (current->thread.mm_segment == USER_DS)
+		if (user_mode(regs))
 			return USER_FAULT;
-		return KERNEL_FAULT;
-	}
-	if (trans_exc_code == 2) {
-		/* secondary space exception */
-		if (current->thread.mm_segment & 1) {
-			if (current->thread.mm_segment == USER_DS_SACF)
-				return USER_FAULT;
+		if (!IS_ENABLED(CONFIG_PGSTE))
 			return KERNEL_FAULT;
-		}
-		return VDSO_FAULT;
+		if (test_pt_regs_flag(regs, PIF_GUEST_FAULT))
+			return GMAP_FAULT;
+		return KERNEL_FAULT;
 	}
+	if (trans_exc_code == 2)
+		return USER_FAULT;
 	if (trans_exc_code == 1) {
 		/* access register mode, not used in the kernel */
 		return USER_FAULT;
@@ -188,10 +181,6 @@ static void dump_fault_info(struct pt_regs *regs)
 		asce = S390_lowcore.user_asce;
 		pr_cont("user ");
 		break;
-	case VDSO_FAULT:
-		asce = S390_lowcore.vdso_asce;
-		pr_cont("vdso ");
-		break;
 	case GMAP_FAULT:
 		asce = ((struct gmap *) S390_lowcore.gmap)->asce;
 		pr_cont("gmap ");
@@ -414,9 +403,6 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
 	switch (type) {
 	case KERNEL_FAULT:
 		goto out;
-	case VDSO_FAULT:
-		fault = VM_FAULT_BADMAP;
-		goto out;
 	case USER_FAULT:
 	case GMAP_FAULT:
 		if (faulthandler_disabled() || !mm)
@@ -834,7 +820,6 @@ void do_secure_storage_access(struct pt_regs *regs)
 		if (rc)
 			BUG();
 		break;
-	case VDSO_FAULT:
 	case GMAP_FAULT:
 	default:
 		do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP);
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 11d2c8395e2a..4e87c819ddea 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -70,19 +70,10 @@ static void __crst_table_upgrade(void *arg)
 {
 	struct mm_struct *mm = arg;
 
-	/* we must change all active ASCEs to avoid the creation of new TLBs */
+	/* change all active ASCEs to avoid the creation of new TLBs */
 	if (current->active_mm == mm) {
 		S390_lowcore.user_asce = mm->context.asce;
-		if (current->thread.mm_segment == USER_DS) {
-			__ctl_load(S390_lowcore.user_asce, 1, 1);
-			/* Mark user-ASCE present in CR1 */
-			clear_cpu_flag(CIF_ASCE_PRIMARY);
-		}
-		if (current->thread.mm_segment == USER_DS_SACF) {
-			__ctl_load(S390_lowcore.user_asce, 7, 7);
-			/* enable_sacf_uaccess does all or nothing */
-			WARN_ON(!test_cpu_flag(CIF_ASCE_SECONDARY));
-		}
+		__ctl_load(S390_lowcore.user_asce, 7, 7);
 	}
 	__tlb_flush_local();
 }