s390/kvm: remove delayed reallocation of page tables for KVM

Replacing a 2K page table with a 4K page table while a VMA is active
for the affected memory region is fundamentally broken. Rip out the
page table reallocation code and replace it with a simple system
control 'vm.allocate_pgste'. If the system control is set the page
tables for all processes are allocated as full 4K pages, even for
processes that do not need it.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

4 files changed, 16 insertions, 1 deletions

diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index a5e656260a70..d29ad9545b41 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -14,7 +14,9 @@ typedef struct {
         unsigned long asce_bits;
         unsigned long asce_limit;
         unsigned long vdso_base;
-        /* The mmu context has extended page tables. */
+        /* The mmu context allocates 4K page tables. */
+        unsigned int alloc_pgste:1;
+        /* The mmu context uses extended page tables. */
         unsigned int has_pgste:1;
         /* The mmu context uses storage keys. */
         unsigned int use_skey:1;
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index d25d9ff10ba8..fb1b93ea3e3f 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -20,8 +20,11 @@ static inline int init_new_context(struct task_struct *tsk,
         mm->context.flush_mm = 0;
         mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS;
         mm->context.asce_bits |= _ASCE_TYPE_REGION3;
+#ifdef CONFIG_PGSTE
+        mm->context.alloc_pgste = page_table_allocate_pgste;
         mm->context.has_pgste = 0;
         mm->context.use_skey = 0;
+#endif
         mm->context.asce_limit = STACK_TOP_MAX;
         crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
         return 0;
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 51e7fb634ebc..7b7858f158b4 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -21,6 +21,7 @@ void crst_table_free(struct mm_struct *, unsigned long *);
 unsigned long *page_table_alloc(struct mm_struct *);
 void page_table_free(struct mm_struct *, unsigned long *);
 void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long);
+extern int page_table_allocate_pgste;
 
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
                           unsigned long key, bool nq);
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 989cfae9e202..1fba63997d50 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -423,6 +423,15 @@ static inline int mm_has_pgste(struct mm_struct *mm)
         return 0;
 }
 
+static inline int mm_alloc_pgste(struct mm_struct *mm)
+{
+#ifdef CONFIG_PGSTE
+        if (unlikely(mm->context.alloc_pgste))
+                return 1;
+#endif
+        return 0;
+}
+
 /*
  * In the case that a guest uses storage keys
  * faults should no longer be backed by zero pages