KVM: s390: Fix to clear PTE when discarding a swapped page

KVM run fails when guests with 'cmm' cpu feature and host are
under memory pressure and use swap heavily. This is because
npages becomes ENOMEN (out of memory) in hva_to_pfn_slow()
which inturn propagates as EFAULT to qemu. Clearing the page
table entry when discarding an address that maps to a swap
entry resolves the issue.

Fixes: 200197908dc4 ("KVM: s390: Refactor and split some gmap helpers")
Cc: stable@vger.kernel.org
Suggested-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Gautam Gala <ggala@linux.ibm.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>

3 files changed, 34 insertions, 23 deletions

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 6d8bc27a366e..324f96485604 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -2010,4 +2010,26 @@ static inline unsigned long gmap_pgste_get_pgt_addr(unsigned long *pgt)
 	return res;
 }
 
+static inline pgste_t pgste_get_lock(pte_t *ptep)
+{
+	unsigned long value = 0;
+#ifdef CONFIG_PGSTE
+	unsigned long *ptr = (unsigned long *)(ptep + PTRS_PER_PTE);
+
+	do {
+		value = __atomic64_or_barrier(PGSTE_PCL_BIT, ptr);
+	} while (value & PGSTE_PCL_BIT);
+	value |= PGSTE_PCL_BIT;
+#endif
+	return __pgste(value);
+}
+
+static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
+{
+#ifdef CONFIG_PGSTE
+	barrier();
+	WRITE_ONCE(*(unsigned long *)(ptep + PTRS_PER_PTE), pgste_val(pgste) & ~PGSTE_PCL_BIT);
+#endif
+}
+
 #endif /* _S390_PAGE_H */
diff --git a/arch/s390/mm/gmap_helpers.c b/arch/s390/mm/gmap_helpers.c
index a45d417ad951..c382005577bd 100644
--- a/arch/s390/mm/gmap_helpers.c
+++ b/arch/s390/mm/gmap_helpers.c
@@ -13,6 +13,7 @@
 #include <linux/pagewalk.h>
 #include <linux/ksm.h>
 #include <asm/gmap_helpers.h>
+#include <asm/pgtable.h>
 
 /**
  * ptep_zap_swap_entry() - discard a swap entry.
@@ -45,6 +46,7 @@ void gmap_helper_zap_one_page(struct mm_struct *mm, unsigned long vmaddr)
 {
 	struct vm_area_struct *vma;
 	spinlock_t *ptl;
+	pgste_t pgste;
 	pte_t *ptep;
 
 	mmap_assert_locked(mm);
@@ -58,8 +60,16 @@ void gmap_helper_zap_one_page(struct mm_struct *mm, unsigned long vmaddr)
 	ptep = get_locked_pte(mm, vmaddr, &ptl);
 	if (unlikely(!ptep))
 		return;
-	if (pte_swap(*ptep))
+	if (pte_swap(*ptep)) {
+		preempt_disable();
+		pgste = pgste_get_lock(ptep);
+
 		ptep_zap_swap_entry(mm, pte_to_swp_entry(*ptep));
+		pte_clear(mm, vmaddr, ptep);
+
+		pgste_set_unlock(ptep, pgste);
+		preempt_enable();
+	}
 	pte_unmap_unlock(ptep, ptl);
 }
 EXPORT_SYMBOL_GPL(gmap_helper_zap_one_page);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 7df70cd8f739..6b92c348b56f 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -23,6 +23,7 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 #include <asm/page-states.h>
+#include <asm/pgtable.h>
 #include <asm/machine.h>
 
 pgprot_t pgprot_writecombine(pgprot_t prot)
@@ -114,28 +115,6 @@ static inline pte_t ptep_flush_lazy(struct mm_struct *mm,
 	return old;
 }
 
-static inline pgste_t pgste_get_lock(pte_t *ptep)
-{
-	unsigned long value = 0;
-#ifdef CONFIG_PGSTE
-	unsigned long *ptr = (unsigned long *)(ptep + PTRS_PER_PTE);
-
-	do {
-		value = __atomic64_or_barrier(PGSTE_PCL_BIT, ptr);
-	} while (value & PGSTE_PCL_BIT);
-	value |= PGSTE_PCL_BIT;
-#endif
-	return __pgste(value);
-}
-
-static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
-{
-#ifdef CONFIG_PGSTE
-	barrier();
-	WRITE_ONCE(*(unsigned long *)(ptep + PTRS_PER_PTE), pgste_val(pgste) & ~PGSTE_PCL_BIT);
-#endif
-}
-
 static inline pgste_t pgste_get(pte_t *ptep)
 {
 	unsigned long pgste = 0;