public inbox for linux-s390@vger.kernel.org
 help / color / mirror / Atom feed
From: Janosch Frank <frankja@linux.vnet.ibm.com>
To: kvm@vger.kernel.org
Cc: schwidefsky@de.ibm.com, borntraeger@de.ibm.com, david@redhat.com,
	dominik.dingel@gmail.com, linux-s390@vger.kernel.org
Subject: [RFC/PATCH 17/22] s390/mm: Add VSIE reverse fake case
Date: Mon,  6 Nov 2017 23:29:55 +0100	[thread overview]
Message-ID: <1510007400-42493-18-git-send-email-frankja@linux.vnet.ibm.com> (raw)
In-Reply-To: <1510007400-42493-1-git-send-email-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          | 52 +++++++++++++++++++++++++++++++++++---------
 3 files changed, 59 insertions(+), 15 deletions(-)

diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index 2ce861f..a50dbc6 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -131,7 +131,7 @@ 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 60a5dda..5c6e8d8 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -1143,10 +1143,22 @@ 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;
@@ -1184,7 +1196,7 @@ 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);
@@ -1195,7 +1207,7 @@ 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);
@@ -1203,7 +1215,7 @@ 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 75c32de..91a0824 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -1527,7 +1527,7 @@ static void __gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr,
 	BUG_ON(!gmap_is_shadow(sg));
 	asce = (unsigned long) sgt | _ASCE_TYPE_SEGMENT;
 	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)) {
@@ -2171,7 +2171,7 @@ 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;
@@ -2202,9 +2202,11 @@ 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);
@@ -2392,6 +2394,7 @@ 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;
@@ -2416,26 +2419,49 @@ 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)) {
+				/* TODO: Bits and pgstes */
+				*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 {
+				ptl = NULL;
+				if (gmap_is_shadow(parent))
+					sptep = pte_offset_map(spmdp, paddr);
+				else
+					sptep = pte_alloc_map_lock(parent->mm, 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;
+					}
+					if (ptl)
+						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)
@@ -2514,6 +2540,12 @@ static void gmap_shadow_notify_pmd(struct gmap *sg, unsigned long vmaddr,
 		case _SHADOW_RMAP_SEGMENT_LP:
 			gmap_unshadow_segment(sg, raddr);
 			break;
+		case _SHADOW_RMAP_SEGMENT:
+			gmap_unshadow_pgt(sg, raddr);
+			break;
+		case _SHADOW_RMAP_PGTABLE:
+			gmap_unshadow_page(sg, raddr);
+			break;
 		}
 		kfree(rmap);
 	}
-- 
2.7.4

  parent reply	other threads:[~2017-11-06 22:29 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-11-06 22:29 [RFC/PATCH 00/22] KVM/s390: Hugetlbfs enablement Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 01/22] s390/mm: make gmap_protect_range more modular Janosch Frank
2017-11-08 10:40   ` David Hildenbrand
2017-11-08 12:21     ` Janosch Frank
2017-11-08 12:26       ` David Hildenbrand
2017-11-06 22:29 ` [RFC/PATCH 02/22] s390/mm: Abstract gmap notify bit setting Janosch Frank
2017-11-10 12:57   ` David Hildenbrand
2017-11-13 15:57     ` Janosch Frank
2017-11-15  9:30       ` David Hildenbrand
2017-11-06 22:29 ` [RFC/PATCH 03/22] s390/mm: add gmap PMD invalidation notification Janosch Frank
2017-11-15  9:55   ` David Hildenbrand
2017-11-17  9:02     ` Janosch Frank
2017-11-17  9:19       ` Martin Schwidefsky
2017-11-06 22:29 ` [RFC/PATCH 04/22] s390/mm: Add gmap pmd invalidation and clearing Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 05/22] s390/mm: hugetlb pages within a gmap can not be freed Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 06/22] s390/mm: Introduce gmap_pmdp_xchg Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 07/22] RFC: s390/mm: Transfer guest pmd protection to host Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 08/22] s390/mm: Add huge page dirty sync support Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 09/22] s390/mm: clear huge page storage keys on enable_skey Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 10/22] s390/mm: Add huge pmd storage key handling Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 11/22] s390/mm: Remove superfluous parameter Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 12/22] s390/mm: Add gmap_protect_large read protection support Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 13/22] s390/mm: Make gmap_read_table EDAT1 compatible Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 14/22] s390/mm: Make protect_rmap " Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 15/22] s390/mm: GMAP read table extensions Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 16/22] s390/mm: Add shadow segment code Janosch Frank
2017-11-06 22:29 ` Janosch Frank [this message]
2017-11-06 22:29 ` [RFC/PATCH 18/22] s390/mm: Remove gmap_pte_op_walk Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 19/22] s390/mm: Split huge pages if granular protection is needed Janosch Frank
2017-12-07 16:32   ` David Hildenbrand
2017-12-08  7:00     ` Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 20/22] s390/mm: Enable gmap huge pmd support Janosch Frank
2017-11-15 10:08   ` David Hildenbrand
2017-11-15 12:24     ` Janosch Frank
2017-11-06 22:29 ` [RFC/PATCH 21/22] KVM: s390: Add KVM HPAGE capability Janosch Frank
2017-11-07 10:07   ` Cornelia Huck
2017-11-07 10:53     ` Janosch Frank
2017-11-15 10:06   ` David Hildenbrand
2017-11-15 12:02     ` Janosch Frank
2017-11-06 22:30 ` [RFC/PATCH 22/22] RFC: s390/mm: Add gmap lock classes Janosch Frank
2017-11-15 10:10   ` David Hildenbrand
2017-11-15 12:16     ` Janosch Frank

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1510007400-42493-18-git-send-email-frankja@linux.vnet.ibm.com \
    --to=frankja@linux.vnet.ibm.com \
    --cc=borntraeger@de.ibm.com \
    --cc=david@redhat.com \
    --cc=dominik.dingel@gmail.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=schwidefsky@de.ibm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox