powerpc/mm/hash: Clear the invalid slot information correctly

We can get a hash pte fault with 4k base page size and find the pte
already inserted with 64K base page size. In that case we need to clear
the existing slot information from the old pte. Fix this correctly

With THP, we also clear the slot information with respect to all
the 64K hash pte mapping that 16MB page. They are all invalid
now. This make sure we don't find the slot valid when we fault with
4k base page size. Finding the slot valid should not result in any wrong
behavior because we do check again in hash page table for the validity.
But we can avoid that check completely.

Fixes: a43c0eb8364c022 ("powerpc/mm: Convert 4k hash insert to C")
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c
index 0762c1e08c88644f35cc8a3df5ba50c52c1801a2..edb09912f0c9b5ca316216bf3d912c7efe8d920a 100644 (file)
--- a/arch/powerpc/mm/hash64_64k.c
+++ b/arch/powerpc/mm/hash64_64k.c
@@ -111,7 +111,13 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
         */
        if (!(old_pte & _PAGE_COMBO)) {
                flush_hash_page(vpn, rpte, MMU_PAGE_64K, ssize, flags);
-               old_pte &= ~_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND;
+               /*
+                * clear the old slot details from the old and new pte.
+                * On hash insert failure we use old pte value and we don't
+                * want slot information there if we have a insert failure.
+                */
+               old_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND);
+               new_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND);
                goto htab_insert_hpte;
        }
        /*

diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 49b152b0f926289e1dcaa595988932a036df5325..eb2accdd76fd8bb70a762c4a57df8bc2c425ffad 100644 (file)
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -78,9 +78,19 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
                 * base page size. This is because demote_segment won't flush
                 * hash page table entries.
                 */
-               if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO))
+               if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO)) {
                        flush_hash_hugepage(vsid, ea, pmdp, MMU_PAGE_64K,
                                            ssize, flags);
+                       /*
+                        * With THP, we also clear the slot information with
+                        * respect to all the 64K hash pte mapping the 16MB
+                        * page. They are all invalid now. This make sure we
+                        * don't find the slot valid when we fault with 4k
+                        * base page size.
+                        *
+                        */
+                       memset(hpte_slot_array, 0, PTE_FRAG_SIZE);
+               }
        }
 
        valid = hpte_valid(hpte_slot_array, index);