5 files changed, 64 insertions, 47 deletions

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 20fad59ff9f5..394846197974 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -183,9 +183,6 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!hpdp)
 		return NULL;
 
-	if (IS_ENABLED(CONFIG_PPC_8xx) && pshift < PMD_SHIFT)
-		return pte_alloc_huge(mm, (pmd_t *)hpdp, addr);
-
 	BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));
 
 	if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr,
@@ -218,8 +215,18 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!pmd)
 		return NULL;
 
-	if (sz >= PMD_SIZE)
+	if (sz >= PMD_SIZE) {
+		/* On 8xx, all hugepages are handled as contiguous PTEs */
+		if (IS_ENABLED(CONFIG_PPC_8xx)) {
+			int i;
+
+			for (i = 0; i < sz / PMD_SIZE; i++) {
+				if (!pte_alloc_huge(mm, pmd + i, addr))
+					return NULL;
+			}
+		}
 		return (pte_t *)pmd;
+	}
 
 	return pte_alloc_huge(mm, pmd, addr);
 }
@@ -617,10 +624,8 @@ static int __init hugetlbpage_init(void)
 		 * use pgt cache for hugepd.
 		 */
 		if (pdshift > shift) {
-			if (!IS_ENABLED(CONFIG_PPC_8xx))
-				pgtable_cache_add(pdshift - shift);
-		} else if (IS_ENABLED(CONFIG_PPC_E500) ||
-			   IS_ENABLED(CONFIG_PPC_8xx)) {
+			pgtable_cache_add(pdshift - shift);
+		} else if (IS_ENABLED(CONFIG_PPC_E500)) {
 			pgtable_cache_add(PTE_T_ORDER);
 		}
 
diff --git a/arch/powerpc/mm/kasan/8xx.c b/arch/powerpc/mm/kasan/8xx.c
index 2784224054f8..989d6cdf4141 100644
--- a/arch/powerpc/mm/kasan/8xx.c
+++ b/arch/powerpc/mm/kasan/8xx.c
@@ -6,28 +6,33 @@
 #include <linux/memblock.h>
 #include <linux/hugetlb.h>
 
+#include <asm/pgalloc.h>
+
 static int __init
 kasan_init_shadow_8M(unsigned long k_start, unsigned long k_end, void *block)
 {
 	pmd_t *pmd = pmd_off_k(k_start);
 	unsigned long k_cur, k_next;
 
-	for (k_cur = k_start; k_cur != k_end; k_cur = k_next, pmd += 2, block += SZ_8M) {
-		pte_basic_t *new;
+	for (k_cur = k_start; k_cur != k_end; k_cur = k_next, pmd++, block += SZ_4M) {
+		pte_t *ptep;
+		int i;
 
 		k_next = pgd_addr_end(k_cur, k_end);
-		k_next = pgd_addr_end(k_next, k_end);
 		if ((void *)pmd_page_vaddr(*pmd) != kasan_early_shadow_pte)
 			continue;
 
-		new = memblock_alloc(sizeof(pte_basic_t), SZ_4K);
-		if (!new)
+		ptep = memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE);
+		if (!ptep)
 			return -ENOMEM;
 
-		*new = pte_val(pte_mkhuge(pfn_pte(PHYS_PFN(__pa(block)), PAGE_KERNEL)));
+		for (i = 0; i < PTRS_PER_PTE; i++) {
+			pte_t pte = pte_mkhuge(pfn_pte(PHYS_PFN(__pa(block + i * PAGE_SIZE)), PAGE_KERNEL));
 
-		hugepd_populate_kernel((hugepd_t *)pmd, (pte_t *)new, PAGE_SHIFT_8M);
-		hugepd_populate_kernel((hugepd_t *)pmd + 1, (pte_t *)new, PAGE_SHIFT_8M);
+			__set_pte_at(&init_mm, k_cur, ptep + i, pte, 1);
+		}
+		pmd_populate_kernel(&init_mm, pmd, ptep);
+		*pmd = __pmd(pmd_val(*pmd) | _PMD_PAGE_8M);
 	}
 	return 0;
 }
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
index d93433e26ded..388bba0ab3e7 100644
--- a/arch/powerpc/mm/nohash/8xx.c
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -11,6 +11,7 @@
 #include <linux/hugetlb.h>
 
 #include <asm/fixmap.h>
+#include <asm/pgalloc.h>
 
 #include <mm/mmu_decl.h>
 
@@ -48,20 +49,6 @@ unsigned long p_block_mapped(phys_addr_t pa)
 	return 0;
 }
 
-static pte_t __init *early_hugepd_alloc_kernel(hugepd_t *pmdp, unsigned long va)
-{
-	if (hpd_val(*pmdp) == 0) {
-		pte_t *ptep = memblock_alloc(sizeof(pte_basic_t), SZ_4K);
-
-		if (!ptep)
-			return NULL;
-
-		hugepd_populate_kernel((hugepd_t *)pmdp, ptep, PAGE_SHIFT_8M);
-		hugepd_populate_kernel((hugepd_t *)pmdp + 1, ptep, PAGE_SHIFT_8M);
-	}
-	return hugepte_offset(*(hugepd_t *)pmdp, va, PGDIR_SHIFT);
-}
-
 static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa,
 					     pgprot_t prot, int psize, bool new)
 {
@@ -75,24 +62,33 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa,
 		if (WARN_ON(slab_is_available()))
 			return -EINVAL;
 
-		if (psize == MMU_PAGE_512K)
+		if (psize == MMU_PAGE_512K) {
 			ptep = early_pte_alloc_kernel(pmdp, va);
-		else
-			ptep = early_hugepd_alloc_kernel((hugepd_t *)pmdp, va);
+			/* The PTE should never be already present */
+			if (WARN_ON(pte_present(*ptep) && pgprot_val(prot)))
+				return -EINVAL;
+		} else {
+			if (WARN_ON(!pmd_none(*pmdp) || !pmd_none(*(pmdp + 1))))
+				return -EINVAL;
+
+			ptep = early_alloc_pgtable(PTE_FRAG_SIZE);
+			pmd_populate_kernel(&init_mm, pmdp, ptep);
+
+			ptep = early_alloc_pgtable(PTE_FRAG_SIZE);
+			pmd_populate_kernel(&init_mm, pmdp + 1, ptep);
+
+			ptep = (pte_t *)pmdp;
+		}
 	} else {
 		if (psize == MMU_PAGE_512K)
 			ptep = pte_offset_kernel(pmdp, va);
 		else
-			ptep = hugepte_offset(*(hugepd_t *)pmdp, va, PGDIR_SHIFT);
+			ptep = (pte_t *)pmdp;
 	}
 
 	if (WARN_ON(!ptep))
 		return -ENOMEM;
 
-	/* The PTE should never be already present */
-	if (new && WARN_ON(pte_present(*ptep) && pgprot_val(prot)))
-		return -EINVAL;
-
 	set_huge_pte_at(&init_mm, va, ptep,
 			pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)),
 			1UL << mmu_psize_to_shift(psize));
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 9010973f036c..294775c793ab 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -297,11 +297,8 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 }
 
 #if defined(CONFIG_PPC_8xx)
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
-		     pte_t pte, unsigned long sz)
+static void __set_huge_pte_at(pmd_t *pmd, pte_t *ptep, pte_basic_t val)
 {
-	pmd_t *pmd = pmd_off(mm, addr);
-	pte_basic_t val;
 	pte_basic_t *entry = (pte_basic_t *)ptep;
 	int num, i;
 
@@ -311,15 +308,29 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 	 */
 	VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
 
-	pte = set_pte_filter(pte, addr);
-
-	val = pte_val(pte);
-
 	num = number_of_cells_per_pte(pmd, val, 1);
 
 	for (i = 0; i < num; i++, entry++, val += SZ_4K)
 		*entry = val;
 }
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		     pte_t pte, unsigned long sz)
+{
+	pmd_t *pmdp = pmd_off(mm, addr);
+
+	pte = set_pte_filter(pte, addr);
+
+	if (sz == SZ_8M) { /* Flag both PMD entries as 8M and fill both page tables */
+		*pmdp = __pmd(pmd_val(*pmdp) | _PMD_PAGE_8M);
+		*(pmdp + 1) = __pmd(pmd_val(*(pmdp + 1)) | _PMD_PAGE_8M);
+
+		__set_huge_pte_at(pmdp, pte_offset_kernel(pmdp, 0), pte_val(pte));
+		__set_huge_pte_at(pmdp, pte_offset_kernel(pmdp + 1, 0), pte_val(pte) + SZ_4M);
+	} else {
+		__set_huge_pte_at(pmdp, ptep, pte_val(pte));
+	}
+}
 #endif
 #endif /* CONFIG_HUGETLB_PAGE */
 
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index cfd622ebf774..787b22206386 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -48,7 +48,7 @@ notrace void __init early_ioremap_init(void)
 	early_ioremap_setup();
 }
 
-static void __init *early_alloc_pgtable(unsigned long size)
+void __init *early_alloc_pgtable(unsigned long size)
 {
 	void *ptr = memblock_alloc(size, size);