[RHEL7,COMMIT] KVM: nVMX: fix EPT permissions as reported in exit qualification

Submitted by Konstantin Khorenko on May 16, 2018, 9:50 a.m.

Details

Message ID 201805160950.w4G9okUo030009@finist_ce7.work
State New
Series "KVM: nVMX: fix EPT permissions as reported in exit qualification"
Headers show

Commit Message

Konstantin Khorenko May 16, 2018, 9:50 a.m.
The commit is pushed to "branch-rh7-3.10.0-693.21.1.vz7.50.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-693.21.1.vz7.47.6
------>
commit 083ba2f40d2c83f66e320943cd08784751d32e1c
Author: Paolo Bonzini <pbonzini@redhat.com>
Date:   Wed May 16 12:50:46 2018 +0300

    KVM: nVMX: fix EPT permissions as reported in exit qualification
    
    This fixes the new ept_access_test_read_only and ept_access_test_read_write
    testcases from vmx.flat.
    
    The problem is that gpte_access moves bits around to switch from EPT
    bit order (XWR) to ACC_*_MASK bit order (RWX).  This results in an
    incorrect exit qualification.  To fix this, make pt_access and
    pte_access operate on raw PTE values (only with NX flipped to mean
    "can execute") and call gpte_access at the end of the walk.  This
    lets us use pte_access to compute the exit qualification with XWR
    bit order.
    
    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
    Reviewed-by: Xiao Guangrong <xiaoguangrong@tencent.com>
    Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
    
    (cherry picked from commit 0780516a18f87e881e42ed815f189279b0a1743c)
    Signed-off-by: Jan Dakinevich <jan.dakinevich@virtuozzo.com>
    
    =====================
    Patchset description:
    
    EPT fixes and enhancements
    
    Backport of EPT fixes from upstream for
    https://jira.sw.ru/browse/PSBM-84046
    
    Bandan Das (3):
      kvm: mmu: don't set the present bit unconditionally
      kvm: mmu: track read permission explicitly for shadow EPT page tables
      kvm: vmx: advertise support for ept execute only
    
    Junaid Shahid (2):
      kvm: x86: mmu: Use symbolic constants for EPT Violation Exit
        Qualifications
      kvm: x86: mmu: Rename EPT_VIOLATION_READ/WRITE/INSTR constants
    
    KarimAllah Ahmed (2):
      kvm: Map PFN-type memory regions as writable (if possible)
      KVM: x86: Update the exit_qualification access bits while walking an
        address
    
    Paolo Bonzini (5):
      KVM: nVMX: we support 1GB EPT pages
      kvm: x86: MMU support for EPT accessed/dirty bits
      kvm: nVMX: support EPT accessed/dirty bits
      KVM: MMU: return page fault error code from permission_fault
      KVM: nVMX: fix EPT permissions as reported in exit qualification
---
 arch/x86/kvm/paging_tmpl.h | 35 +++++++++++++++++++++--------------
 1 file changed, 21 insertions(+), 14 deletions(-)

Patch hide | download patch | download mbox

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 176ec6b5a249..f96f2a4d5bb9 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -268,11 +268,13 @@  static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	pt_element_t pte;
 	pt_element_t __user *uninitialized_var(ptep_user);
 	gfn_t table_gfn;
-	unsigned index, pt_access, pte_access, accessed_dirty;
+	u64 pt_access, pte_access;
+	unsigned index, accessed_dirty;
 	unsigned nested_access;
 	gpa_t pte_gpa;
 	bool have_ad;
 	int offset;
+	u64 walk_nx_mask = 0;
 	const int write_fault = access & PFERR_WRITE_MASK;
 	const int user_fault  = access & PFERR_USER_MASK;
 	const int fetch_fault = access & PFERR_FETCH_MASK;
@@ -287,6 +289,7 @@  static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	have_ad       = PT_HAVE_ACCESSED_DIRTY(mmu);
 
 #if PTTYPE == 64
+	walk_nx_mask = 1ULL << PT64_NX_SHIFT;
 	if (walker->level == PT32E_ROOT_LEVEL) {
 		pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
 		trace_kvm_mmu_paging_element(pte, walker->level);
@@ -298,8 +301,6 @@  static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	walker->max_level = walker->level;
 	ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu)));
 
-	accessed_dirty = have_ad ? PT_GUEST_ACCESSED_MASK : 0;
-
 	/*
 	 * FIXME: on Intel processors, loads of the PDPTE registers for PAE paging
 	 * by the MOV to CR instruction are treated as reads and do not cause the
@@ -307,14 +308,14 @@  static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	 */
 	nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK;
 
-	pt_access = pte_access = ACC_ALL;
+	pte_access = ~0;
 	++walker->level;
 
 	do {
 		gfn_t real_gfn;
 		unsigned long host_addr;
 
-		pt_access &= pte_access;
+		pt_access = pte_access;
 		--walker->level;
 
 		index = PT_INDEX(addr, walker->level);
@@ -357,6 +358,12 @@  static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 
 		trace_kvm_mmu_paging_element(pte, walker->level);
 
+		/*
+		 * Inverting the NX it lets us AND it like other
+		 * permission bits.
+		 */
+		pte_access = pt_access & (pte ^ walk_nx_mask);
+
 		if (unlikely(!FNAME(is_present_gpte)(pte)))
 			goto error;
 
@@ -365,13 +372,15 @@  static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 			goto error;
 		}
 
-		accessed_dirty &= pte;
-		pte_access = pt_access & FNAME(gpte_access)(vcpu, pte);
-
 		walker->ptes[walker->level - 1] = pte;
 	} while (!is_last_gpte(mmu, walker->level, pte));
 
-	errcode = permission_fault(vcpu, mmu, pte_access, access);
+	accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0;
+
+	/* Convert to ACC_*_MASK flags for struct guest_walker.  */
+	walker->pt_access = FNAME(gpte_access)(vcpu, pt_access ^ walk_nx_mask);
+	walker->pte_access = FNAME(gpte_access)(vcpu, pte_access ^ walk_nx_mask);
+	errcode = permission_fault(vcpu, mmu, walker->pte_access, access);
 	if (unlikely(errcode))
 		goto error;
 
@@ -388,7 +397,7 @@  static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	walker->gfn = real_gpa >> PAGE_SHIFT;
 
 	if (!write_fault)
-		FNAME(protect_clean_gpte)(mmu, &pte_access, pte);
+		FNAME(protect_clean_gpte)(mmu, &walker->pte_access, pte);
 	else
 		/*
 		 * On a write fault, fold the dirty bit into accessed_dirty.
@@ -406,10 +415,8 @@  static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 			goto retry_walk;
 	}
 
-	walker->pt_access = pt_access;
-	walker->pte_access = pte_access;
 	pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
-		 __func__, (u64)pte, pte_access, pt_access);
+		 __func__, (u64)pte, walker->pte_access, walker->pt_access);
 	return 1;
 
 error:
@@ -437,7 +444,7 @@  static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	 */
 	if (!(errcode & PFERR_RSVD_MASK)) {
 		vcpu->arch.exit_qualification &= 0x187;
-		vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3;
+		vcpu->arch.exit_qualification |= (pte_access & 0x7) << 3;
 	}
 #endif
 	walker->fault.address = addr;