1 files changed, 32 insertions, 34 deletions

diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 6fcaf1fa8e02..ac6ac192b8bb 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -74,8 +74,8 @@ struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(kvmppc_find_table);
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-static long kvmppc_rm_tce_to_ua(struct kvm *kvm, unsigned long tce,
-		unsigned long *ua, unsigned long **prmap)
+static long kvmppc_rm_tce_to_ua(struct kvm *kvm,
+				unsigned long tce, unsigned long *ua)
 {
 	unsigned long gfn = tce >> PAGE_SHIFT;
 	struct kvm_memory_slot *memslot;
@@ -87,9 +87,6 @@ static long kvmppc_rm_tce_to_ua(struct kvm *kvm, unsigned long tce,
 	*ua = __gfn_to_hva_memslot(memslot, gfn) |
 		(tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
 
-	if (prmap)
-		*prmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
-
 	return 0;
 }
 
@@ -116,7 +113,7 @@ static long kvmppc_rm_tce_validate(struct kvmppc_spapr_tce_table *stt,
 	if (iommu_tce_check_gpa(stt->page_shift, gpa))
 		return H_PARAMETER;
 
-	if (kvmppc_rm_tce_to_ua(stt->kvm, tce, &ua, NULL))
+	if (kvmppc_rm_tce_to_ua(stt->kvm, tce, &ua))
 		return H_TOO_HARD;
 
 	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
@@ -208,7 +205,7 @@ static long kvmppc_rm_ioba_validate(struct kvmppc_spapr_tce_table *stt,
 
 	idx = (ioba >> stt->page_shift) - stt->offset;
 	sttpage = idx / TCES_PER_PAGE;
-	sttpages = _ALIGN_UP(idx % TCES_PER_PAGE + npages, TCES_PER_PAGE) /
+	sttpages = ALIGN(idx % TCES_PER_PAGE + npages, TCES_PER_PAGE) /
 			TCES_PER_PAGE;
 	for (i = sttpage; i < sttpage + sttpages; ++i)
 		if (!stt->pages[i])
@@ -411,7 +408,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		return ret;
 
 	dir = iommu_tce_direction(tce);
-	if ((dir != DMA_NONE) && kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
+	if ((dir != DMA_NONE) && kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua))
 		return H_PARAMETER;
 
 	entry = ioba >> stt->page_shift;
@@ -437,8 +434,8 @@ 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 +449,17 @@ 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 +481,11 @@ 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 +493,12 @@ 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;
@@ -515,7 +526,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		 */
 		struct mm_iommu_table_group_mem_t *mem;
 
-		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua, NULL))
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua))
 			return H_TOO_HARD;
 
 		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
@@ -531,23 +542,11 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		 * We do not require memory to be preregistered in this case
 		 * so lock rmap and do __find_linux_pte_or_hugepte().
 		 */
-		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
-			return H_TOO_HARD;
-
-		rmap = (void *) vmalloc_to_phys(rmap);
-		if (WARN_ON_ONCE_RM(!rmap))
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua))
 			return H_TOO_HARD;
 
-		/*
-		 * Synchronize with the MMU notifier callbacks in
-		 * book3s_64_mmu_hv.c (kvm_unmap_hva_range_hv etc.).
-		 * While we have the rmap lock, code running on other CPUs
-		 * cannot finish unmapping the host real page that backs
-		 * this guest real page, so we are OK to access the host
-		 * 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;
 		}
@@ -565,7 +564,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		unsigned long tce = be64_to_cpu(((u64 *)tces)[i]);
 
 		ua = 0;
-		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) {
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua)) {
 			ret = H_PARAMETER;
 			goto invalidate_exit;
 		}
@@ -590,9 +589,8 @@ invalidate_exit:
 		iommu_tce_kill_rm(stit->tbl, entry, npages);
 
 unlock_exit:
-	if (rmap)
-		unlock_rmap(rmap);
-
+	if (!prereg)
+		arch_spin_unlock(&kvm->mmu_lock.rlock.raw_lock);
 	return ret;
 }