[PATCH v3 15/22] powerpc/kvm/book3s: use find_kvm_host_pte in pute_tce functions

[Aneesh Kumar K.V]

Current code just hold rmap lock to ensure parallel page table update is
prevented. That is not sufficient. The kernel should also check whether
a mmu_notifer callback was running in parallel.

Cc: Alexey Kardashevskiy <aik at ozlabs.ru>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar at linux.ibm.com>
---
 arch/powerpc/kvm/book3s_64_vio_hv.c | 30 +++++++++++++++++++++++------
 1 file changed, 24 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 6fcaf1fa8e02..acc3ce570be7 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -437,8 +437,8 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	return H_SUCCESS;
 }
 
-static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu,
-		unsigned long ua, unsigned long *phpa)
+static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu, unsigned long mmu_seq,
+				unsigned long ua, unsigned long *phpa)
 {
 	pte_t *ptep, pte;
 	unsigned shift = 0;
@@ -452,10 +452,17 @@ static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu,
 	 * to exit which will agains result in the below page table walk
 	 * to finish.
 	 */
-	ptep = __find_linux_pte(vcpu->arch.pgdir, ua, NULL, &shift);
-	if (!ptep || !pte_present(*ptep))
+	/* an rmap lock won't make it safe. because that just ensure hash
+	 * page table entries are removed with rmap lock held. After that
+	 * mmu notifier returns and we go ahead and removing ptes from Qemu page table.
+	 */
+	ptep = find_kvm_host_pte(vcpu->kvm, mmu_seq, ua, &shift);
+	if (!ptep)
+		return -ENXIO;
+
+	pte = READ_ONCE(*ptep);
+	if (!pte_present(pte))
 		return -ENXIO;
-	pte = *ptep;
 
 	if (!shift)
 		shift = PAGE_SHIFT;
@@ -477,10 +484,12 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		unsigned long liobn, unsigned long ioba,
 		unsigned long tce_list,	unsigned long npages)
 {
+	struct kvm *kvm = vcpu->kvm;
 	struct kvmppc_spapr_tce_table *stt;
 	long i, ret = H_SUCCESS;
 	unsigned long tces, entry, ua = 0;
 	unsigned long *rmap = NULL;
+	unsigned long mmu_seq;
 	bool prereg = false;
 	struct kvmppc_spapr_tce_iommu_table *stit;
 
@@ -488,6 +497,12 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	if (kvm_is_radix(vcpu->kvm))
 		return H_TOO_HARD;
 
+	/*
+	 * used to check for invalidations in progress
+	 */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
@@ -547,7 +562,9 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		 * real page.
 		 */
 		lock_rmap(rmap);
-		if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) {
+
+		arch_spin_lock(&kvm->mmu_lock.rlock.raw_lock);
+		if (kvmppc_rm_ua_to_hpa(vcpu, mmu_seq, ua, &tces)) {
 			ret = H_TOO_HARD;
 			goto unlock_exit;
 		}
@@ -593,6 +610,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	if (rmap)
 		unlock_rmap(rmap);
 
+	arch_spin_unlock(&kvm->mmu_lock.rlock.raw_lock);
 	return ret;
 }
 
-- 
2.25.3