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

[Gautam Gala <ggala@linux.ibm.com>]

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.

Suggested-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Gautam Gala <ggala@linux.ibm.com>
---
 arch/s390/include/asm/pgtable.h | 22 ++++++++++++++++++++++
 arch/s390/mm/gmap_helpers.c     | 12 +++++++++++-
 arch/s390/mm/pgtable.c          | 23 +----------------------
 3 files changed, 34 insertions(+), 23 deletions(-)

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index c1a7a92f0575..b7100c6a4054 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -2055,4 +2055,26 @@ 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 b63f427e7289..d4c3c36855e2 100644
--- a/arch/s390/mm/gmap_helpers.c
+++ b/arch/s390/mm/gmap_helpers.c
@@ -15,6 +15,7 @@
 #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.
@@ -47,6 +48,7 @@ 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);
@@ -60,8 +62,16 @@ 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 60688be4e876..879f39366e6c 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -24,6 +24,7 @@
 #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)
@@ -115,28 +116,6 @@ 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;
-- 
2.51.0