Merge tag 's390-6.13-2' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull more s390 updates from Heiko Carstens:

 - Add swap entry for hugetlbfs support

 - Add PTE_MARKER support for hugetlbs mappings; this fixes a regression
   (possible page fault loop) which was introduced when support for
   UFFDIO_POISON for hugetlbfs was added

 - Add ARCH_HAS_PREEMPT_LAZY and PREEMPT_DYNAMIC support

 - Mark IRQ entries in entry code, so that stack tracers can filter out
   the non-IRQ parts of stack traces. This fixes stack depot capacity
   limit warnings, since without filtering the number of unique stack
   traces is huge

 - In PCI code fix leak of struct zpci_dev object, and fix potential
   double remove of hotplug slot

 - Fix pagefault_disable() / pagefault_enable() unbalance in
   arch_stack_user_walk_common()

 - A couple of inline assembly optimizations, more cmpxchg() to
   try_cmpxchg() conversions, and removal of usages of xchg() and
   cmpxchg() on one and two byte memory areas

 - Various other small improvements and cleanups

* tag 's390-6.13-2' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (27 commits)
  Revert "s390/mm: Allow large pages for KASAN shadow mapping"
  s390/spinlock: Use flag output constraint for arch_cmpxchg_niai8()
  s390/spinlock: Use R constraint for arch_load_niai4()
  s390/spinlock: Generate shorter code for arch_spin_unlock()
  s390/spinlock: Remove condition code clobber from arch_spin_unlock()
  s390/spinlock: Use symbolic names in inline assemblies
  s390: Support PREEMPT_DYNAMIC
  s390/pci: Fix potential double remove of hotplug slot
  s390/pci: Fix leak of struct zpci_dev when zpci_add_device() fails
  s390/mm/hugetlbfs: Add missing includes
  s390/mm: Add PTE_MARKER support for hugetlbfs mappings
  s390/mm: Introduce region-third and segment table swap entries
  s390/mm: Introduce region-third and segment table entry present bits
  s390/mm: Rearrange region-third and segment table entry SW bits
  KVM: s390: Increase size of union sca_utility to four bytes
  KVM: s390: Remove one byte cmpxchg() usage
  KVM: s390: Use try_cmpxchg() instead of cmpxchg() loops
  s390/ap: Replace xchg() with WRITE_ONCE()
  s390/mm: Allow large pages for KASAN shadow mapping
  s390: Add ARCH_HAS_PREEMPT_LAZY support
  ...

1 files changed, 22 insertions, 9 deletions

diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 7c79cf1bc7d7..d9ce199953de 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -24,6 +24,7 @@
 
 static inline unsigned long __pte_to_rste(pte_t pte)
 {
+	swp_entry_t arch_entry;
 	unsigned long rste;
 
 	/*
@@ -48,6 +49,7 @@ static inline unsigned long __pte_to_rste(pte_t pte)
 	 */
 	if (pte_present(pte)) {
 		rste = pte_val(pte) & PAGE_MASK;
+		rste |= _SEGMENT_ENTRY_PRESENT;
 		rste |= move_set_bit(pte_val(pte), _PAGE_READ,
 				     _SEGMENT_ENTRY_READ);
 		rste |= move_set_bit(pte_val(pte), _PAGE_WRITE,
@@ -66,6 +68,10 @@ static inline unsigned long __pte_to_rste(pte_t pte)
 #endif
 		rste |= move_set_bit(pte_val(pte), _PAGE_NOEXEC,
 				     _SEGMENT_ENTRY_NOEXEC);
+	} else if (!pte_none(pte)) {
+		/* swap pte */
+		arch_entry = __pte_to_swp_entry(pte);
+		rste = mk_swap_rste(__swp_type(arch_entry), __swp_offset(arch_entry));
 	} else
 		rste = _SEGMENT_ENTRY_EMPTY;
 	return rste;
@@ -73,13 +79,18 @@ static inline unsigned long __pte_to_rste(pte_t pte)
 
 static inline pte_t __rste_to_pte(unsigned long rste)
 {
+	swp_entry_t arch_entry;
 	unsigned long pteval;
-	int present;
+	int present, none;
+	pte_t pte;
 
-	if ((rste & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
+	if ((rste & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) {
 		present = pud_present(__pud(rste));
-	else
+		none = pud_none(__pud(rste));
+	} else {
 		present = pmd_present(__pmd(rste));
+		none = pmd_none(__pmd(rste));
+	}
 
 	/*
 	 * Convert encoding		pmd / pud bits	    pte bits
@@ -114,6 +125,11 @@ static inline pte_t __rste_to_pte(unsigned long rste)
 		pteval |= move_set_bit(rste, _SEGMENT_ENTRY_SOFT_DIRTY, _PAGE_SOFT_DIRTY);
 #endif
 		pteval |= move_set_bit(rste, _SEGMENT_ENTRY_NOEXEC, _PAGE_NOEXEC);
+	} else if (!none) {
+		/* swap rste */
+		arch_entry = __rste_to_swp_entry(rste);
+		pte = mk_swap_pte(__swp_type_rste(arch_entry), __swp_offset_rste(arch_entry));
+		pteval = pte_val(pte);
 	} else
 		pteval = _PAGE_INVALID;
 	return __pte(pteval);
@@ -148,8 +164,6 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	unsigned long rste;
 
 	rste = __pte_to_rste(pte);
-	if (!MACHINE_HAS_NX)
-		rste &= ~_SEGMENT_ENTRY_NOEXEC;
 
 	/* Set correct table type for 2G hugepages */
 	if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) {
@@ -223,11 +237,10 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		p4dp = p4d_offset(pgdp, addr);
 		if (p4d_present(*p4dp)) {
 			pudp = pud_offset(p4dp, addr);
-			if (pud_present(*pudp)) {
-				if (pud_leaf(*pudp))
-					return (pte_t *) pudp;
+			if (sz == PUD_SIZE)
+				return (pte_t *)pudp;
+			if (pud_present(*pudp))
 				pmdp = pmd_offset(pudp, addr);
-			}
 		}
 	}
 	return (pte_t *) pmdp;