KVM: propagate fault r/w information to gup(), allow read-only memory

As suggested by Andrea, pass r/w error code to gup(), upgrading read fault
to writable if host pte allows it.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

1 files changed, 9 insertions, 4 deletions

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index d6b281e989b1..ba00eefa7bcd 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -427,7 +427,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
                          struct guest_walker *gw,
                          int user_fault, int write_fault, int hlevel,
-                         int *ptwrite, pfn_t pfn)
+                         int *ptwrite, pfn_t pfn, bool map_writable)
 {
         unsigned access = gw->pt_access;
         struct kvm_mmu_page *sp = NULL;
@@ -501,7 +501,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 
         mmu_set_spte(vcpu, it.sptep, access, gw->pte_access & access,
                      user_fault, write_fault, dirty, ptwrite, it.level,
-                     gw->gfn, pfn, false, true);
+                     gw->gfn, pfn, false, map_writable);
         FNAME(pte_prefetch)(vcpu, gw, it.sptep);
 
         return it.sptep;
@@ -539,6 +539,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
         pfn_t pfn;
         int level = PT_PAGE_TABLE_LEVEL;
         unsigned long mmu_seq;
+        bool map_writable;
 
         pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 
@@ -569,13 +570,17 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
         mmu_seq = vcpu->kvm->mmu_notifier_seq;
         smp_rmb();
 
-        if (try_async_pf(vcpu, no_apf, walker.gfn, addr, &pfn))
+        if (try_async_pf(vcpu, no_apf, walker.gfn, addr, &pfn, write_fault,
+                         &map_writable))
                 return 0;
 
         /* mmio */
         if (is_error_pfn(pfn))
                 return kvm_handle_bad_page(vcpu->kvm, walker.gfn, pfn);
 
+        if (!map_writable)
+                walker.pte_access &= ~ACC_WRITE_MASK;
+
         spin_lock(&vcpu->kvm->mmu_lock);
         if (mmu_notifier_retry(vcpu, mmu_seq))
                 goto out_unlock;
@@ -583,7 +588,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
         trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
         kvm_mmu_free_some_pages(vcpu);
         sptep = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
-                             level, &write_pt, pfn);
+                             level, &write_pt, pfn, map_writable);
         (void)sptep;
         pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __func__,
                  sptep, *sptep, write_pt);