s390: allow pte_offset_map_lock() to fail

In rare transient cases, not yet made possible, pte_offset_map() and
pte_offset_map_lock() may not find a page table: handle appropriately.

Add comment on mm's contract with s390 above __zap_zero_pages(),
and fix old comment there: must be called after THP was disabled.

Link: https://lkml.kernel.org/r/3ff29363-336a-9733-12a1-5c31a45c8aeb@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Greg Ungerer <gerg@linux-m68k.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: John David Anglin <dave.anglin@bell.net>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 19 insertions, 4 deletions

diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index cb2ee06df286..3c62d1b218b1 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -294,6 +294,8 @@ again:
 
 	rc = -ENXIO;
 	ptep = get_locked_pte(gmap->mm, uaddr, &ptelock);
+	if (!ptep)
+		goto out;
 	if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) {
 		page = pte_page(*ptep);
 		rc = -EAGAIN;
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index dc90d1eb0d55..3a2a31a15ea8 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2537,7 +2537,12 @@ static inline void thp_split_mm(struct mm_struct *mm)
  * Remove all empty zero pages from the mapping for lazy refaulting
  * - This must be called after mm->context.has_pgste is set, to avoid
  *   future creation of zero pages
- * - This must be called after THP was enabled
+ * - This must be called after THP was disabled.
+ *
+ * mm contracts with s390, that even if mm were to remove a page table,
+ * racing with the loop below and so causing pte_offset_map_lock() to fail,
+ * it will never insert a page table containing empty zero pages once
+ * mm_forbids_zeropage(mm) i.e. mm->context.has_pgste is set.
  */
 static int __zap_zero_pages(pmd_t *pmd, unsigned long start,
 			   unsigned long end, struct mm_walk *walk)
@@ -2549,6 +2554,8 @@ static int __zap_zero_pages(pmd_t *pmd, unsigned long start,
 		spinlock_t *ptl;
 
 		ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+		if (!ptep)
+			break;
 		if (is_zero_pfn(pte_pfn(*ptep)))
 			ptep_xchg_direct(walk->mm, addr, ptep, __pte(_PAGE_INVALID));
 		pte_unmap_unlock(ptep, ptl);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 6effb24de6d9..3bd2ab2a9a34 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -829,7 +829,7 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	default:
 		return -EFAULT;
 	}
-
+again:
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
 		spin_unlock(ptl);
@@ -850,6 +850,8 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	spin_unlock(ptl);
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!ptep)
+		goto again;
 	new = old = pgste_get_lock(ptep);
 	pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
 			    PGSTE_ACC_BITS | PGSTE_FP_BIT);
@@ -938,7 +940,7 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 	default:
 		return -EFAULT;
 	}
-
+again:
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
 		spin_unlock(ptl);
@@ -955,6 +957,8 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 	spin_unlock(ptl);
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!ptep)
+		goto again;
 	new = old = pgste_get_lock(ptep);
 	/* Reset guest reference bit only */
 	pgste_val(new) &= ~PGSTE_GR_BIT;
@@ -1000,7 +1004,7 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	default:
 		return -EFAULT;
 	}
-
+again:
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
 		spin_unlock(ptl);
@@ -1017,6 +1021,8 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	spin_unlock(ptl);
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	if (!ptep)
+		goto again;
 	pgste = pgste_get_lock(ptep);
 	*key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
 	paddr = pte_val(*ptep) & PAGE_MASK;