The quilt patch titled
Subject: s390: allow pte_offset_map_lock() to fail
has been removed from the -mm tree. Its filename was
s390-allow-pte_offset_map_lock-to-fail.patch
This patch was dropped because it was merged into the mm-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Hugh Dickins <hughd@xxxxxxxxxx>
Subject: s390: allow pte_offset_map_lock() to fail
Date: Thu, 8 Jun 2023 12:27:22 -0700 (PDT)
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@xxxxxxxxxx
Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Alexander Gordeev <agordeev@xxxxxxxxxxxxx>
Cc: Alexandre Ghiti <alexghiti@xxxxxxxxxxxx>
Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Christian Borntraeger <borntraeger@xxxxxxxxxxxxx>
Cc: Chris Zankel <chris@xxxxxxxxxx>
Cc: Claudio Imbrenda <imbrenda@xxxxxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
Cc: Geert Uytterhoeven <geert@xxxxxxxxxxxxxx>
Cc: Greg Ungerer <gerg@xxxxxxxxxxxxxx>
Cc: Heiko Carstens <hca@xxxxxxxxxxxxx>
Cc: Helge Deller <deller@xxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: John David Anglin <dave.anglin@xxxxxxxx>
Cc: John Paul Adrian Glaubitz <glaubitz@xxxxxxxxxxxxxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Max Filippov <jcmvbkbc@xxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Michal Simek <monstr@xxxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Mike Rapoport (IBM) <rppt@xxxxxxxxxx>
Cc: Palmer Dabbelt <palmer@xxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Qi Zheng <zhengqi.arch@xxxxxxxxxxxxx>
Cc: Russell King <linux@xxxxxxxxxxxxxxx>
Cc: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Cc: Thomas Bogendoerfer <tsbogend@xxxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/s390/kernel/uv.c | 2 ++
arch/s390/mm/gmap.c | 9 ++++++++-
arch/s390/mm/pgtable.c | 12 +++++++++---
3 files changed, 19 insertions(+), 4 deletions(-)
--- a/arch/s390/kernel/uv.c~s390-allow-pte_offset_map_lock-to-fail
+++ a/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;
--- a/arch/s390/mm/gmap.c~s390-allow-pte_offset_map_lock-to-fail
+++ a/arch/s390/mm/gmap.c
@@ -2537,7 +2537,12 @@ static inline void thp_split_mm(struct m
* 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,
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);
--- a/arch/s390/mm/pgtable.c~s390-allow-pte_offset_map_lock-to-fail
+++ a/arch/s390/mm/pgtable.c
@@ -829,7 +829,7 @@ int set_guest_storage_key(struct mm_stru
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_stru
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_
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_
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_stru
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_stru
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;
_
Patches currently in -mm which might be from hughd@xxxxxxxxxx are
