From: Janosch Frank <frankja@linux.ibm.com>
Subject: s390/mm: Add huge page gmap linking support
Patch-mainline: v4.19-rc1
Git-commit: a9e00d8349c98e0973c8b0d671d69e838f7b5bcc
References: FATE#326372, LTC#169184, bsc#1113484

Summary:     kernel: Introduce huge page KVM backing support
Description: This adds the KVM support for libhugetlbfs backings of
             s390 KVM guests.

Upstream-Description:

             s390/mm: Add huge page gmap linking support

             Let's allow huge pmd linking when enabled through the
             KVM_CAP_S390_HPAGE_1M capability. Also we can now restrict gmap
             invalidation and notification to the cases where the capability has
             been activated and save some cycles when that's not the case.

             Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
             Reviewed-by: David Hildenbrand <david@redhat.com>

Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Acked-by: Petr Tesarik <ptesarik@suse.com>
---
 arch/s390/include/asm/mmu.h         |    2 ++
 arch/s390/include/asm/mmu_context.h |    1 +
 arch/s390/mm/gmap.c                 |    9 ++++++---
 arch/s390/mm/pgtable.c              |    8 ++++----
 4 files changed, 13 insertions(+), 7 deletions(-)

--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -25,6 +25,8 @@ typedef struct {
 	unsigned int uses_skeys:1;
 	/* The mmu context uses CMM. */
 	unsigned int uses_cmm:1;
+	/* The gmaps associated with this context are allowed to use huge pages. */
+	unsigned int allow_gmap_hpage_1m:1;
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						   \
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -33,6 +33,7 @@ static inline int init_new_context(struc
 	mm->context.has_pgste = 0;
 	mm->context.uses_skeys = 0;
 	mm->context.uses_cmm = 0;
+	mm->context.allow_gmap_hpage_1m = 0;
 #endif
 	switch (mm->context.asce_limit) {
 	case 1UL << 42:
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -1,8 +1,10 @@
 /*
  *  KVM guest address space mapping code
  *
- *    Copyright IBM Corp. 2007, 2016
+ *    Copyright IBM Corp. 2007, 2016, 2018
  *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *		 David Hildenbrand <david@redhat.com>
+ *		 Janosch Frank <frankja@linux.vnet.ibm.com>
  */
 
 #include <linux/kernel.h>
@@ -584,8 +586,8 @@ int __gmap_link(struct gmap *gmap, unsig
 		return -EFAULT;
 	pmd = pmd_offset(pud, vmaddr);
 	VM_BUG_ON(pmd_none(*pmd));
-	/* large pmds cannot yet be handled */
-	if (pmd_large(*pmd))
+	/* Are we allowed to use huge pages? */
+	if (pmd_large(*pmd) && !gmap->mm->context.allow_gmap_hpage_1m)
 		return -EFAULT;
 	/* Link gmap segment table entry location to page table. */
 	rc = radix_tree_preload(GFP_KERNEL);
@@ -1639,6 +1641,7 @@ struct gmap *gmap_shadow(struct gmap *pa
 	unsigned long limit;
 	int rc;
 
+	BUG_ON(parent->mm->context.allow_gmap_hpage_1m);
 	BUG_ON(gmap_is_shadow(parent));
 	spin_lock(&parent->shadow_lock);
 	sg = gmap_find_shadow(parent, asce, edat_level);
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -346,7 +346,7 @@ static inline void pmdp_idte_local(struc
 			    mm->context.asce, IDTE_LOCAL);
 	else
 		__pmdp_idte(addr, pmdp, 0, 0, IDTE_LOCAL);
-	if (mm_has_pgste(mm))
+	if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
 		gmap_pmdp_idte_local(mm, addr);
 }
 
@@ -356,15 +356,15 @@ static inline void pmdp_idte_global(stru
 	if (MACHINE_HAS_TLB_GUEST) {
 		__pmdp_idte(addr, pmdp, IDTE_NODAT | IDTE_GUEST_ASCE,
 			    mm->context.asce, IDTE_GLOBAL);
-		if (mm_has_pgste(mm))
+		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
 			gmap_pmdp_idte_global(mm, addr);
 	} else if (MACHINE_HAS_IDTE) {
 		__pmdp_idte(addr, pmdp, 0, 0, IDTE_GLOBAL);
-		if (mm_has_pgste(mm))
+		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
 			gmap_pmdp_idte_global(mm, addr);
 	} else {
 		__pmdp_csp(pmdp);
-		if (mm_has_pgste(mm))
+		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
 			gmap_pmdp_csp(mm, addr);
 	}
 }