Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Martin Schwidefsky:
 "The bulk of the s390 patches for 4.13. Some new things but mostly bug
  fixes and cleanups. Noteworthy changes:

   - The SCM block driver is converted to blk-mq

   - Switch s390 to 5 level page tables. The virtual address space for a
     user space process can now have up to 16EB-4KB.

   - Introduce a ELF phdr flag for qemu to avoid the global
     vm.alloc_pgste which forces all processes to large page tables

   - A couple of PCI improvements to improve error recovery

   - Included is the merge of the base support for proper machine checks
     for KVM"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (52 commits)
  s390/dasd: Fix faulty ENODEV for RO sysfs attribute
  s390/pci: recognize name clashes with uids
  s390/pci: provide more debug information
  s390/pci: fix handling of PEC 306
  s390/pci: improve pci hotplug
  s390/pci: introduce clp_get_state
  s390/pci: improve error handling during fmb (de)registration
  s390/pci: improve unreg_ioat error handling
  s390/pci: improve error handling during interrupt deregistration
  s390/pci: don't cleanup in arch_setup_msi_irqs
  KVM: s390: Backup the guest's machine check info
  s390/nmi: s390: New low level handling for machine check happening in guest
  s390/fpu: export save_fpu_regs for all configs
  s390/kvm: avoid global config of vm.alloc_pgste=1
  s390: rename struct psw_bits members
  s390: rename psw_bits enums
  s390/mm: use correct address space when enabling DAT
  s390/cio: introduce io_subchannel_type
  s390/ipl: revert Load Normal semantics for LPAR CCW-type re-IPL
  s390/dumpstack: remove raw stack dump
  ...

1 files changed, 37 insertions, 20 deletions

diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index f502cbe657af..18918e394ce4 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -76,29 +76,46 @@ static void __crst_table_upgrade(void *arg)
 	__tlb_flush_local();
 }
 
-int crst_table_upgrade(struct mm_struct *mm)
+int crst_table_upgrade(struct mm_struct *mm, unsigned long end)
 {
 	unsigned long *table, *pgd;
+	int rc, notify;
 
-	/* upgrade should only happen from 3 to 4 levels */
-	BUG_ON(mm->context.asce_limit != (1UL << 42));
-
-	table = crst_table_alloc(mm);
-	if (!table)
+	/* upgrade should only happen from 3 to 4, 3 to 5, or 4 to 5 levels */
+	BUG_ON(mm->context.asce_limit < (1UL << 42));
+	if (end >= TASK_SIZE_MAX)
 		return -ENOMEM;
-
-	spin_lock_bh(&mm->page_table_lock);
-	pgd = (unsigned long *) mm->pgd;
-	crst_table_init(table, _REGION2_ENTRY_EMPTY);
-	pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
-	mm->pgd = (pgd_t *) table;
-	mm->context.asce_limit = 1UL << 53;
-	mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
-			   _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
-	spin_unlock_bh(&mm->page_table_lock);
-
-	on_each_cpu(__crst_table_upgrade, mm, 0);
-	return 0;
+	rc = 0;
+	notify = 0;
+	while (mm->context.asce_limit < end) {
+		table = crst_table_alloc(mm);
+		if (!table) {
+			rc = -ENOMEM;
+			break;
+		}
+		spin_lock_bh(&mm->page_table_lock);
+		pgd = (unsigned long *) mm->pgd;
+		if (mm->context.asce_limit == (1UL << 42)) {
+			crst_table_init(table, _REGION2_ENTRY_EMPTY);
+			p4d_populate(mm, (p4d_t *) table, (pud_t *) pgd);
+			mm->pgd = (pgd_t *) table;
+			mm->context.asce_limit = 1UL << 53;
+			mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+				_ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+		} else {
+			crst_table_init(table, _REGION1_ENTRY_EMPTY);
+			pgd_populate(mm, (pgd_t *) table, (p4d_t *) pgd);
+			mm->pgd = (pgd_t *) table;
+			mm->context.asce_limit = -PAGE_SIZE;
+			mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+				_ASCE_USER_BITS | _ASCE_TYPE_REGION1;
+		}
+		notify = 1;
+		spin_unlock_bh(&mm->page_table_lock);
+	}
+	if (notify)
+		on_each_cpu(__crst_table_upgrade, mm, 0);
+	return rc;
 }
 
 void crst_table_downgrade(struct mm_struct *mm)
@@ -274,7 +291,7 @@ static void __tlb_remove_table(void *_table)
 	struct page *page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 
 	switch (mask) {
-	case 0:		/* pmd or pud */
+	case 0:		/* pmd, pud, or p4d */
 		free_pages((unsigned long) table, 2);
 		break;
 	case 1:		/* lower 2K of a 4K page table */