[S390] kvm: fix address mode switching

598841ca9919d008b520114d8a4378c4ce4e40a1 ([S390] use gmap address
spaces for kvm guest images) changed kvm to use a separate address
space for kvm guests. This address space was switched in __vcpu_run
In some cases (preemption, page fault) there is the possibility that
this address space switch is lost.
The typical symptom was a huge amount of validity intercepts or
random guest addressing exceptions.
Fix this by doing the switch in sie_loop and sie_exit and saving the
address space in the gmap structure itself. Also use the preempt
notifier.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>

arch/s390/include/asm/pgtable.h

@@ -658,12 +658,14 @@ static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste)
  * struct gmap_struct - guest address space
  * @mm: pointer to the parent mm_struct
  * @table: pointer to the page directory
+ * @asce: address space control element for gmap page table
  * @crst_list: list of all crst tables used in the guest address space
  */
 struct gmap {
 	struct list_head list;
 	struct mm_struct *mm;
 	unsigned long *table;
+	unsigned long asce;
 	struct list_head crst_list;
 };
 

arch/s390/kernel/asm-offsets.c

@@ -10,6 +10,7 @@
 #include <linux/sched.h>
 #include <asm/vdso.h>
 #include <asm/sigp.h>
+#include <asm/pgtable.h>
 
 /*
  * Make sure that the compiler is new enough. We want a compiler that
@@ -126,6 +127,7 @@ int main(void)
 	DEFINE(__LC_KERNEL_STACK, offsetof(struct _lowcore, kernel_stack));
 	DEFINE(__LC_ASYNC_STACK, offsetof(struct _lowcore, async_stack));
 	DEFINE(__LC_PANIC_STACK, offsetof(struct _lowcore, panic_stack));
+	DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce));
 	DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock));
 	DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock));
 	DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags));
@@ -151,6 +153,7 @@ int main(void)
 	DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data));
 	DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap));
 	DEFINE(__LC_CMF_HPP, offsetof(struct _lowcore, cmf_hpp));
+	DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce));
 #endif /* CONFIG_32BIT */
 	return 0;
 }

arch/s390/kernel/entry64.S

@@ -1076,6 +1076,11 @@ sie_loop:
 	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
 	tm	__TI_flags+7(%r14),_TIF_EXIT_SIE
 	jnz	sie_exit
+	lg	%r14,__LC_GMAP			# get gmap pointer
+	ltgr	%r14,%r14
+	jz	sie_gmap
+	lctlg	%c1,%c1,__GMAP_ASCE(%r14)	# load primary asce
+sie_gmap:
 	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
 	SPP	__SF_EMPTY(%r15)		# set guest id
 	sie	0(%r14)
@@ -1083,6 +1088,7 @@ sie_done:
 	SPP	__LC_CMF_HPP			# set host id
 	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
 sie_exit:
+	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 	ni	__TI_flags+6(%r14),255-(_TIF_SIE>>8)
 	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
 	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13

arch/s390/kvm/kvm-s390.c

@@ -263,10 +263,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK;
 	restore_fp_regs(&vcpu->arch.guest_fpregs);
 	restore_access_regs(vcpu->arch.guest_acrs);
+	gmap_enable(vcpu->arch.gmap);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	gmap_disable(vcpu->arch.gmap);
 	save_fp_regs(&vcpu->arch.guest_fpregs);
 	save_access_regs(vcpu->arch.guest_acrs);
 	restore_fp_regs(&vcpu->arch.host_fpregs);
@@ -461,7 +463,6 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	local_irq_disable();
 	kvm_guest_enter();
 	local_irq_enable();
-	gmap_enable(vcpu->arch.gmap);
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
 	if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) {
@@ -470,7 +471,6 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	}
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
-	gmap_disable(vcpu->arch.gmap);
 	local_irq_disable();
 	kvm_guest_exit();
 	local_irq_enable();

arch/s390/mm/pgtable.c

@@ -160,6 +160,8 @@ struct gmap *gmap_alloc(struct mm_struct *mm)
 	table = (unsigned long *) page_to_phys(page);
 	crst_table_init(table, _REGION1_ENTRY_EMPTY);
 	gmap->table = table;
+	gmap->asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH |
+		     _ASCE_USER_BITS | __pa(table);
 	list_add(&gmap->list, &mm->context.gmap_list);
 	return gmap;
 
@@ -240,10 +242,6 @@ EXPORT_SYMBOL_GPL(gmap_free);
  */
 void gmap_enable(struct gmap *gmap)
 {
-	/* Load primary space page table origin. */
-	S390_lowcore.user_asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH |
-				 _ASCE_USER_BITS | __pa(gmap->table);
-	asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) );
 	S390_lowcore.gmap = (unsigned long) gmap;
 }
 EXPORT_SYMBOL_GPL(gmap_enable);
@@ -254,10 +252,6 @@ EXPORT_SYMBOL_GPL(gmap_enable);
  */
 void gmap_disable(struct gmap *gmap)
 {
-	/* Load primary space page table origin. */
-	S390_lowcore.user_asce =
-		gmap->mm->context.asce_bits | __pa(gmap->mm->pgd);
-	asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) );
 	S390_lowcore.gmap = 0UL;
 }
 EXPORT_SYMBOL_GPL(gmap_disable);