Merge tag 'powerpc-4.1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux

Pull powerpc fixes from Michael Ellerman:

 - fix for mm_dec_nr_pmds() from Scott.

 - fixes for oopses seen with KVM + THP from Aneesh.

 - build fixes from Aneesh & Shreyas.

* tag 'powerpc-4.1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux:
  powerpc/mm: Fix build error with CONFIG_PPC_TRANSACTIONAL_MEM disabled
  powerpc/kvm: Fix ppc64_defconfig + PPC_POWERNV=n build error
  powerpc/mm/thp: Return pte address if we find trans_splitting.
  powerpc/mm/thp: Make page table walk safe against thp split/collapse
  KVM: PPC: Remove page table walk helpers
  KVM: PPC: Use READ_ONCE when dereferencing pte_t pointer
  powerpc/hugetlb: Call mm_dec_nr_pmds() in hugetlb_free_pmd_range()

4 files changed, 77 insertions, 57 deletions

diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 2963e4d..3caec2c 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -75,7 +75,7 @@ config KVM_BOOK3S_64
 
 config KVM_BOOK3S_64_HV
 	tristate "KVM support for POWER7 and PPC970 using hypervisor mode in host"
-	depends on KVM_BOOK3S_64
+	depends on KVM_BOOK3S_64 && PPC_POWERNV
 	select KVM_BOOK3S_HV_POSSIBLE
 	select MMU_NOTIFIER
 	select CMA
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index d6fe308..1a4acf8 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -535,23 +535,21 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		}
 		/* if the guest wants write access, see if that is OK */
 		if (!writing && hpte_is_writable(r)) {
-			unsigned int hugepage_shift;
 			pte_t *ptep, pte;
-
+			unsigned long flags;
 			/*
 			 * We need to protect against page table destruction
-			 * while looking up and updating the pte.
+			 * hugepage split and collapse.
 			 */
-			rcu_read_lock_sched();
+			local_irq_save(flags);
 			ptep = find_linux_pte_or_hugepte(current->mm->pgd,
-							 hva, &hugepage_shift);
+							 hva, NULL);
 			if (ptep) {
-				pte = kvmppc_read_update_linux_pte(ptep, 1,
-							   hugepage_shift);
+				pte = kvmppc_read_update_linux_pte(ptep, 1);
 				if (pte_write(pte))
 					write_ok = 1;
 			}
-			rcu_read_unlock_sched();
+			local_irq_restore(flags);
 		}
 	}
 
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index f6bf0b1..b027a89 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -26,11 +26,14 @@ static void *real_vmalloc_addr(void *x)
 {
 	unsigned long addr = (unsigned long) x;
 	pte_t *p;
-
-	p = find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL);
+	/*
+	 * assume we don't have huge pages in vmalloc space...
+	 * So don't worry about THP collapse/split. Called
+	 * Only in realmode, hence won't need irq_save/restore.
+	 */
+	p = __find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL);
 	if (!p || !pte_present(*p))
 		return NULL;
-	/* assume we don't have huge pages in vmalloc space... */
 	addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
 	return __va(addr);
 }
@@ -131,25 +134,6 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index,
 	unlock_rmap(rmap);
 }
 
-static pte_t lookup_linux_pte_and_update(pgd_t *pgdir, unsigned long hva,
-			      int writing, unsigned long *pte_sizep)
-{
-	pte_t *ptep;
-	unsigned long ps = *pte_sizep;
-	unsigned int hugepage_shift;
-
-	ptep = find_linux_pte_or_hugepte(pgdir, hva, &hugepage_shift);
-	if (!ptep)
-		return __pte(0);
-	if (hugepage_shift)
-		*pte_sizep = 1ul << hugepage_shift;
-	else
-		*pte_sizep = PAGE_SIZE;
-	if (ps > *pte_sizep)
-		return __pte(0);
-	return kvmppc_read_update_linux_pte(ptep, writing, hugepage_shift);
-}
-
 long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		       long pte_index, unsigned long pteh, unsigned long ptel,
 		       pgd_t *pgdir, bool realmode, unsigned long *pte_idx_ret)
@@ -160,13 +144,13 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	struct revmap_entry *rev;
 	unsigned long g_ptel;
 	struct kvm_memory_slot *memslot;
-	unsigned long pte_size;
+	unsigned hpage_shift;
 	unsigned long is_io;
 	unsigned long *rmap;
-	pte_t pte;
+	pte_t *ptep;
 	unsigned int writing;
 	unsigned long mmu_seq;
-	unsigned long rcbits;
+	unsigned long rcbits, irq_flags = 0;
 
 	psize = hpte_page_size(pteh, ptel);
 	if (!psize)
@@ -202,22 +186,46 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 
 	/* Translate to host virtual address */
 	hva = __gfn_to_hva_memslot(memslot, gfn);
-
-	/* Look up the Linux PTE for the backing page */
-	pte_size = psize;
-	pte = lookup_linux_pte_and_update(pgdir, hva, writing, &pte_size);
-	if (pte_present(pte) && !pte_protnone(pte)) {
-		if (writing && !pte_write(pte))
-			/* make the actual HPTE be read-only */
-			ptel = hpte_make_readonly(ptel);
-		is_io = hpte_cache_bits(pte_val(pte));
-		pa = pte_pfn(pte) << PAGE_SHIFT;
-		pa |= hva & (pte_size - 1);
-		pa |= gpa & ~PAGE_MASK;
+	/*
+	 * If we had a page table table change after lookup, we would
+	 * retry via mmu_notifier_retry.
+	 */
+	if (realmode)
+		ptep = __find_linux_pte_or_hugepte(pgdir, hva, &hpage_shift);
+	else {
+		local_irq_save(irq_flags);
+		ptep = find_linux_pte_or_hugepte(pgdir, hva, &hpage_shift);
 	}
+	if (ptep) {
+		pte_t pte;
+		unsigned int host_pte_size;
 
-	if (pte_size < psize)
-		return H_PARAMETER;
+		if (hpage_shift)
+			host_pte_size = 1ul << hpage_shift;
+		else
+			host_pte_size = PAGE_SIZE;
+		/*
+		 * We should always find the guest page size
+		 * to <= host page size, if host is using hugepage
+		 */
+		if (host_pte_size < psize) {
+			if (!realmode)
+				local_irq_restore(flags);
+			return H_PARAMETER;
+		}
+		pte = kvmppc_read_update_linux_pte(ptep, writing);
+		if (pte_present(pte) && !pte_protnone(pte)) {
+			if (writing && !pte_write(pte))
+				/* make the actual HPTE be read-only */
+				ptel = hpte_make_readonly(ptel);
+			is_io = hpte_cache_bits(pte_val(pte));
+			pa = pte_pfn(pte) << PAGE_SHIFT;
+			pa |= hva & (host_pte_size - 1);
+			pa |= gpa & ~PAGE_MASK;
+		}
+	}
+	if (!realmode)
+		local_irq_restore(irq_flags);
 
 	ptel &= ~(HPTE_R_PP0 - psize);
 	ptel |= pa;
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index cc536d4..4d33e19 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -338,6 +338,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	pte_t *ptep;
 	unsigned int wimg = 0;
 	pgd_t *pgdir;
+	unsigned long flags;
 
 	/* used to check for invalidations in progress */
 	mmu_seq = kvm->mmu_notifier_seq;
@@ -468,15 +469,28 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 
 
 	pgdir = vcpu_e500->vcpu.arch.pgdir;
-	ptep = lookup_linux_ptep(pgdir, hva, &tsize_pages);
-	if (pte_present(*ptep))
-		wimg = (*ptep >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK;
-	else {
-		if (printk_ratelimit())
-			pr_err("%s: pte not present: gfn %lx, pfn %lx\n",
-				__func__, (long)gfn, pfn);
-		ret = -EINVAL;
-		goto out;
+	/*
+	 * We are just looking at the wimg bits, so we don't
+	 * care much about the trans splitting bit.
+	 * We are holding kvm->mmu_lock so a notifier invalidate
+	 * can't run hence pfn won't change.
+	 */
+	local_irq_save(flags);
+	ptep = find_linux_pte_or_hugepte(pgdir, hva, NULL);
+	if (ptep) {
+		pte_t pte = READ_ONCE(*ptep);
+
+		if (pte_present(pte)) {
+			wimg = (pte_val(pte) >> PTE_WIMGE_SHIFT) &
+				MAS2_WIMGE_MASK;
+			local_irq_restore(flags);
+		} else {
+			local_irq_restore(flags);
+			pr_err_ratelimited("%s: pte not present: gfn %lx,pfn %lx\n",
+					   __func__, (long)gfn, pfn);
+			ret = -EINVAL;
+			goto out;
+		}
 	}
 	kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg);