KVM: PPC: Book3S PR: Better handling of host-side read-only pages

Currently we request write access to all pages that get mapped into the
guest, even if the guest is only loading from the page.  This reduces
the effectiveness of KSM because it means that we unshare every page we
access.  Also, we always set the changed (C) bit in the guest HPTE if
it allows writing, even for a guest load.

This fixes both these problems.  We pass an 'iswrite' flag to the
mmu.xlate() functions and to kvmppc_mmu_map_page() to indicate whether
the access is a load or a store.  The mmu.xlate() functions now only
set C for stores.  kvmppc_gfn_to_pfn() now calls gfn_to_pfn_prot()
instead of gfn_to_pfn() so that it can indicate whether we need write
access to the page, and get back a 'writable' flag to indicate whether
the page is writable or not.  If that 'writable' flag is clear, we then
make the host HPTE read-only even if the guest HPTE allowed writing.

This means that we can get a protection fault when the guest writes to a
page that it has mapped read-write but which is read-only on the host
side (perhaps due to KSM having merged the page).  Thus we now call
kvmppc_handle_pagefault() for protection faults as well as HPTE not found
faults.  In kvmppc_handle_pagefault(), if the access was allowed by the
guest HPTE and we thus need to install a new host HPTE, we then need to
remove the old host HPTE if there is one.  This is done with a new
function, kvmppc_mmu_unmap_page(), which uses kvmppc_mmu_pte_vflush() to
find and remove the old host HPTE.

Since the memslot-related functions require the KVM SRCU read lock to
be held, this adds srcu_read_lock/unlock pairs around the calls to
kvmppc_handle_pagefault().

Finally, this changes kvmppc_mmu_book3s_32_xlate_pte() to not ignore
guest HPTEs that don't permit access, and to return -EPERM for accesses
that are not permitted by the page protections.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

1 files changed, 17 insertions, 15 deletions

diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index b14af6d09347..76a64ce6a5b6 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -84,7 +84,8 @@ static inline bool sr_nx(u32 sr_raw)
 }
 
 static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
-					  struct kvmppc_pte *pte, bool data);
+					  struct kvmppc_pte *pte, bool data,
+					  bool iswrite);
 static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 					     u64 *vsid);
 
@@ -99,7 +100,7 @@ static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
 	u64 vsid;
 	struct kvmppc_pte pte;
 
-	if (!kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, &pte, data))
+	if (!kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, &pte, data, false))
 		return pte.vpage;
 
 	kvmppc_mmu_book3s_32_esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid);
@@ -146,7 +147,8 @@ static u32 kvmppc_mmu_book3s_32_get_ptem(u32 sre, gva_t eaddr, bool primary)
 }
 
 static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
-					  struct kvmppc_pte *pte, bool data)
+					  struct kvmppc_pte *pte, bool data,
+					  bool iswrite)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	struct kvmppc_bat *bat;
@@ -187,8 +189,7 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
 				printk(KERN_INFO "BAT is not readable!\n");
 				continue;
 			}
-			if (!pte->may_write) {
-				/* let's treat r/o BATs as not-readable for now */
+			if (iswrite && !pte->may_write) {
 				dprintk_pte("BAT is read-only!\n");
 				continue;
 			}
@@ -202,7 +203,7 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
 
 static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 				     struct kvmppc_pte *pte, bool data,
-				     bool primary)
+				     bool iswrite, bool primary)
 {
 	u32 sre;
 	hva_t ptegp;
@@ -258,9 +259,6 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 					break;
 			}
 
-			if ( !pte->may_read )
-				continue;
-
 			dprintk_pte("MMU: Found PTE -> %x %x - %x\n",
 				    pteg[i], pteg[i+1], pp);
 			found = 1;
@@ -282,11 +280,12 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 			pte_r |= PTEG_FLAG_ACCESSED;
 			put_user(pte_r >> 8, addr + 2);
 		}
-		if (pte->may_write && !(pte_r & PTEG_FLAG_DIRTY)) {
-			/* XXX should only set this for stores */
+		if (iswrite && pte->may_write && !(pte_r & PTEG_FLAG_DIRTY)) {
 			pte_r |= PTEG_FLAG_DIRTY;
 			put_user(pte_r, addr + 3);
 		}
+		if (!pte->may_read || (iswrite && !pte->may_write))
+			return -EPERM;
 		return 0;
 	}
 
@@ -305,7 +304,8 @@ no_page_found:
 }
 
 static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
-				      struct kvmppc_pte *pte, bool data)
+				      struct kvmppc_pte *pte, bool data,
+				      bool iswrite)
 {
 	int r;
 	ulong mp_ea = vcpu->arch.magic_page_ea;
@@ -327,11 +327,13 @@ static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		return 0;
 	}
 
-	r = kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, pte, data);
+	r = kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, pte, data, iswrite);
 	if (r < 0)
-	       r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, data, true);
+		r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte,
+						   data, iswrite, true);
 	if (r < 0)
-	       r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, data, false);
+		r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte,
+						   data, iswrite, false);
 
 	return r;
 }