[RFC/PATCH v3 10/16] s390/mm: Add VSIE reverse fake case

[Janosch Frank <frankja@linux.vnet.ibm.com>]

The fake VSIE case lets us run huge vsie guests on small hosts by
creating fake page tables. When running a small guest on a huge host,
we need to create fake tables once again.

The fake tables are needed to make sure, that the VSIE guest is only
able to access the memory that its host mapped for it.

Signed-off-by: Janosch Frank <frankja@linux.vnet.ibm.com>
---
 arch/s390/include/asm/gmap.h |  2 +-
 arch/s390/kvm/gaccess.c      | 20 +++++++++---
 arch/s390/mm/gmap.c          | 76 +++++++++++++++++++-------------------------
 3 files changed, 50 insertions(+), 48 deletions(-)

diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index 8387fdc..1347ff5 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -144,7 +144,7 @@ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt,
 		    int fake);
 int gmap_shadow_sgt_lookup(struct gmap *sg, unsigned long saddr,
 			   unsigned long *pgt, int *dat_protection,
-			   int *fake);
+			   int *fake, int *lvl);
 int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte);
 int gmap_shadow_segment(struct gmap *sg, unsigned long saddr, pmd_t pmd);
 
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 045d12e..de40d17 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -1144,10 +1144,22 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr,
 				*lvl = 1;
 				*pgt = ptr;
 				return 0;
+			} else {
+				/*
+				 * Reverse fake case.
+				 * We map a huge parent to a small guest, i.e.
+				 * we need fake shadow pagetables.
+				 *
+				 * We need pagetables here, because
+				 * guests not aligned on 1M could
+				 * read/write from/to the parent or
+				 * host.
+				 */
+				*lvl = 0;
 			}
 		}
 		/* Small to small and small to huge case */
-		if (ste.fc && sg->edat_level >= 1) {
+		if (!fc && ste.fc && sg->edat_level >= 1) {
 			*fake = 1;
 			ptr = ste.fc1.sfaa * _SEGMENT_SIZE;
 			ste.val = ptr;
@@ -1185,7 +1197,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
 	union page_table_entry pte;
 	union segment_table_entry ste;
 	unsigned long pgt;
-	int dat_protection, fake, lvl, fc;
+	int dat_protection, fake, lvl = 0, fc;
 	int rc;
 
 	down_read(&sg->mm->mmap_sem);
@@ -1196,7 +1208,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
 	 */
 	ipte_lock(vcpu);
 
-	rc = gmap_shadow_sgt_lookup(sg, saddr, &pgt, &dat_protection, &fake);
+	rc = gmap_shadow_sgt_lookup(sg, saddr, &pgt, &dat_protection, &fake, &lvl);
 	if (rc)
 		rc = kvm_s390_shadow_tables(sg, saddr, &pgt, &dat_protection,
 					    &fake, &lvl);
@@ -1204,7 +1216,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
 	vaddr.addr = saddr;
 
 	/* Shadow stopped at segment level, we map pmd to pmd */
-	if (lvl) {
+	if (!rc && lvl) {
 		if (!rc)
 			rc = gmap_read_table(sg->parent, pgt + vaddr.sx * 8,
 					     &ste.val, &fc);
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index f805ec9..ae25f76 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -841,38 +841,6 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap,
 }
 
 /**
- * gmap_pte_op_walk - walk the gmap page table, get the page table lock
- *		      and return the pte pointer
- * @gmap: pointer to guest mapping meta data structure
- * @gaddr: virtual address in the guest address space
- * @ptl: pointer to the spinlock pointer
- *
- * Returns a pointer to the locked pte for a guest address, or NULL
- *
- * Note: Can also be called for shadow gmaps.
- */
-static pte_t *gmap_pte_op_walk(struct gmap *gmap, unsigned long gaddr,
-			       spinlock_t **ptl)
-{
-	unsigned long *table;
-
-	if (gmap_is_shadow(gmap))
-		spin_lock(&gmap->guest_table_lock);
-	/* Walk the gmap page table, lock and get pte pointer */
-	table = gmap_table_walk(gmap, gaddr, 1); /* get segment pointer */
-	if (!table || *table & _SEGMENT_ENTRY_INVALID) {
-		if (gmap_is_shadow(gmap))
-			spin_unlock(&gmap->guest_table_lock);
-		return NULL;
-	}
-	if (gmap_is_shadow(gmap)) {
-		*ptl = &gmap->guest_table_lock;
-		return pte_offset_map((pmd_t *) table, gaddr);
-	}
-	return pte_alloc_map_lock(gmap->mm, (pmd_t *) table, gaddr, ptl);
-}
-
-/**
  * gmap_pte_op_fixup - force a page in and connect the gmap page table
  * @gmap: pointer to guest mapping meta data structure
  * @gaddr: virtual address in the guest address space
@@ -1557,7 +1525,7 @@ static void __gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr,
 
 	BUG_ON(!gmap_is_shadow(sg));
 	for (i = 0; i < _CRST_ENTRIES; i++, raddr += _SEGMENT_SIZE) {
-		if (!(sgt[i] & _SEGMENT_ENTRY_ORIGIN))
+		if (sgt[i] ==  _SEGMENT_ENTRY_EMPTY)
 			continue;
 
 		if (!(sgt[i] & _SEGMENT_ENTRY_LARGE)) {
@@ -2199,7 +2167,7 @@ EXPORT_SYMBOL_GPL(gmap_shadow_pgt_lookup);
 
 int gmap_shadow_sgt_lookup(struct gmap *sg, unsigned long saddr,
 			   unsigned long *pgt, int *dat_protection,
-			   int *fake)
+			   int *fake, int *lvl)
 {
 	unsigned long *sge, *r3e = NULL;
 	struct page *page;
@@ -2230,9 +2198,11 @@ int gmap_shadow_sgt_lookup(struct gmap *sg, unsigned long saddr,
 			*dat_protection = 0;
 			*fake = 0;
 		}
+		*lvl = 1;
 	} else {
 		gmap_shadow_pgt_lookup(sg, sge, saddr, pgt,
 				       dat_protection, fake);
+		*lvl = 0;
 	}
 out:
 	spin_unlock(&sg->guest_table_lock);
@@ -2421,6 +2391,7 @@ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte)
 	struct gmap_rmap *rmap;
 	unsigned long vmaddr, paddr;
 	spinlock_t *ptl;
+	pmd_t *spmdp;
 	pte_t *sptep, *tptep;
 	int prot;
 	int rc;
@@ -2445,26 +2416,42 @@ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte)
 		if (rc)
 			break;
 		rc = -EAGAIN;
-		sptep = gmap_pte_op_walk(parent, paddr, &ptl);
-		if (sptep) {
+		spmdp = gmap_pmd_op_walk(parent, paddr);
+		if (spmdp && !(pmd_val(*spmdp) & _SEGMENT_ENTRY_INVALID)) {
 			spin_lock(&sg->guest_table_lock);
 			/* Get page table pointer */
 			tptep = (pte_t *) gmap_table_walk(sg, saddr, 0);
 			if (!tptep) {
 				spin_unlock(&sg->guest_table_lock);
-				gmap_pte_op_end(ptl);
 				radix_tree_preload_end();
+				gmap_pmd_op_end(parent, spmdp);
 				break;
 			}
-			rc = ptep_shadow_pte(sg->mm, saddr, sptep, tptep, pte);
-			if (rc > 0) {
-				/* Success and a new mapping */
-				gmap_insert_rmap(sg, vmaddr, rmap);
+
+			if (pmd_large(*spmdp)) {
+				*tptep = __pte(((pmd_val(*spmdp) &
+						_SEGMENT_ENTRY_ORIGIN_LARGE)
+					       + (pte_index(paddr) << 12))
+					       | (pte_val(pte) & _PAGE_PROTECT));
+				pmd_val(*spmdp) |= _SEGMENT_ENTRY_GMAP_VSIE;
+				gmap_insert_rmap(sg, vmaddr & HPAGE_MASK, rmap);
 				rmap = NULL;
 				rc = 0;
+			} else {
+				sptep = gmap_pte_from_pmd(parent, spmdp, paddr, &ptl);
+				if (sptep) {
+					rc = ptep_shadow_pte(sg->mm, saddr, sptep, tptep, pte);
+					if (rc > 0) {
+						/* Success and a new mapping */
+						gmap_insert_rmap(sg, vmaddr, rmap);
+						rmap = NULL;
+						rc = 0;
+					}
+					gmap_pte_op_end(ptl);
+				}
 			}
-			gmap_pte_op_end(ptl);
 			spin_unlock(&sg->guest_table_lock);
+			gmap_pmd_op_end(parent, spmdp);
 		}
 		radix_tree_preload_end();
 		if (!rc)
@@ -2530,7 +2517,10 @@ static void gmap_shadow_notify_pmd(struct gmap *sg, unsigned long vmaddr,
 	gmap_for_each_rmap_safe(rmap, rnext, head) {
 		bits = rmap->raddr & _SHADOW_RMAP_MASK;
 		raddr = rmap->raddr ^ bits;
-		gmap_unshadow_segment(sg, raddr);
+		if (bits == _SHADOW_RMAP_SEGMENT_LP)
+			gmap_unshadow_segment(sg, raddr);
+		else
+			gmap_unshadow_page(sg, raddr);
 		kfree(rmap);
 	}
 	spin_unlock(&sg->guest_table_lock);
-- 
2.7.4