powerpc/mm/book3s: Update pmd_present to look at _PAGE_PRESENT bit

With this patch we use 0x8000000000000000UL (_PAGE_PRESENT) to indicate a valid
pgd/pud/pmd entry. We also switch the p**_present() to look at this bit.

With pmd_present, we have a special case. We need to make sure we consider a
pmd marked invalid during THP split as present. Right now we clear the
_PAGE_PRESENT bit during a pmdp_invalidate. Inorder to consider this special
case we add a new pte bit _PAGE_INVALID (mapped to _RPAGE_SW0). This bit is
only used with _PAGE_PRESENT cleared. Hence we are not really losing a pte bit
for this special case. pmd_present is also updated to look at _PAGE_INVALID.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

3 files changed, 12 insertions, 9 deletions

diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index f23a89d8e4ce..8ff03c7205a0 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1001,9 +1001,9 @@ void __init hash__early_init_mmu(void)
 	 * 4k use hugepd format, so for hash set then to
 	 * zero
 	 */
-	__pmd_val_bits = 0;
-	__pud_val_bits = 0;
-	__pgd_val_bits = 0;
+	__pmd_val_bits = HASH_PMD_VAL_BITS;
+	__pud_val_bits = HASH_PUD_VAL_BITS;
+	__pgd_val_bits = HASH_PGD_VAL_BITS;
 
 	__kernel_virt_start = H_KERN_VIRT_START;
 	__kernel_virt_size = H_KERN_VIRT_SIZE;
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index 01d7c0f7c4f0..654000da8b15 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -69,7 +69,11 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		pmd_t *pmdp, pmd_t pmd)
 {
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(pte_present(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp)));
+	/*
+	 * Make sure hardware valid bit is not set. We don't do
+	 * tlb flush for this update.
+	 */
+	WARN_ON(pte_val(pmd_pte(*pmdp)) & _PAGE_PRESENT);
 	assert_spin_locked(pmd_lockptr(mm, pmdp));
 	WARN_ON(!(pmd_trans_huge(pmd) || pmd_devmap(pmd)));
 #endif
@@ -106,7 +110,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 {
 	unsigned long old_pmd;
 
-	old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
+	old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, _PAGE_INVALID);
 	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	/*
 	 * This ensures that generic code that rely on IRQ disabling
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index d71c7777669c..aee04b209b51 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -188,11 +188,10 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 		pte_t pte)
 {
 	/*
-	 * When handling numa faults, we already have the pte marked
-	 * _PAGE_PRESENT, but we can be sure that it is not in hpte.
-	 * Hence we can use set_pte_at for them.
+	 * Make sure hardware valid bit is not set. We don't do
+	 * tlb flush for this update.
 	 */
-	VM_WARN_ON(pte_present(*ptep) && !pte_protnone(*ptep));
+	VM_WARN_ON(pte_val(*ptep) & _PAGE_PRESENT);
 
 	/* Add the pte bit when trying to set a pte */
 	pte = __pte(pte_val(pte) | _PAGE_PTE);