[PATCH] powerpc/hugetlb: Fix 512k hugepages on 8xx with 16k page size

[Christophe Leroy]

Commit 55c8fc3f4930 ("powerpc/8xx: reintroduce 16K pages with HW
assistance") redefined pte_t as a struct of 4 pte_basic_t, because
in 16K pages mode there are four identical entries in the
page table. But the size of hugepage tables is calculated based
of the size of (void *). Therefore, we end up with page tables
of size 1k instead of 4k for 512k pages.

As 512k hugepage tables are the same size as standard page tables,
ie 4k, use the standard page tables instead of PGT_CACHE tables.

Fixes: 3fb69c6a1a13 ("powerpc/8xx: Enable 512k hugepage support with HW assistance")
Cc: stable at vger.kernel.org
Signed-off-by: Christophe Leroy <christophe.leroy at c-s.fr>
---
 arch/powerpc/mm/hugetlbpage.c | 29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index c61032580185..edf511c2a30a 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -54,20 +54,24 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 	if (pshift >= pdshift) {
 		cachep = PGT_CACHE(PTE_T_ORDER);
 		num_hugepd = 1 << (pshift - pdshift);
+		new = NULL;
 	} else if (IS_ENABLED(CONFIG_PPC_8xx)) {
-		cachep = PGT_CACHE(PTE_INDEX_SIZE);
+		cachep = NULL;
 		num_hugepd = 1;
+		new = pte_alloc_one(mm);
 	} else {
 		cachep = PGT_CACHE(pdshift - pshift);
 		num_hugepd = 1;
+		new = NULL;
 	}
 
-	if (!cachep) {
+	if (!cachep && !new) {
 		WARN_ONCE(1, "No page table cache created for hugetlb tables");
 		return -ENOMEM;
 	}
 
-	new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
+	if (cachep)
+		new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
 
 	BUG_ON(pshift > HUGEPD_SHIFT_MASK);
 	BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
@@ -98,7 +102,10 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 	if (i < num_hugepd) {
 		for (i = i - 1 ; i >= 0; i--, hpdp--)
 			*hpdp = __hugepd(0);
-		kmem_cache_free(cachep, new);
+		if (cachep)
+			kmem_cache_free(cachep, new);
+		else
+			pte_free(mm, new);
 	} else {
 		kmemleak_ignore(new);
 	}
@@ -325,8 +332,7 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
 	if (shift >= pdshift)
 		hugepd_free(tlb, hugepte);
 	else if (IS_ENABLED(CONFIG_PPC_8xx))
-		pgtable_free_tlb(tlb, hugepte,
-				 get_hugepd_cache_index(PTE_INDEX_SIZE));
+		pgtable_free_tlb(tlb, hugepte, 0);
 	else
 		pgtable_free_tlb(tlb, hugepte,
 				 get_hugepd_cache_index(pdshift - shift));
@@ -640,12 +646,13 @@ static int __init hugetlbpage_init(void)
 		 * if we have pdshift and shift value same, we don't
 		 * use pgt cache for hugepd.
 		 */
-		if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx))
-			pgtable_cache_add(PTE_INDEX_SIZE);
-		else if (pdshift > shift)
-			pgtable_cache_add(pdshift - shift);
-		else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || IS_ENABLED(CONFIG_PPC_8xx))
+		if (pdshift > shift) {
+			if (!IS_ENABLED(CONFIG_PPC_8xx))
+				pgtable_cache_add(pdshift - shift);
+		} else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) ||
+			   IS_ENABLED(CONFIG_PPC_8xx)) {
 			pgtable_cache_add(PTE_T_ORDER);
+		}
 
 		configured = true;
 	}
-- 
2.25.0