Merge tag 'mm-stable-2024-07-21-14-50' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - In the series "mm: Avoid possible overflows in dirty throttling" Jan
   Kara addresses a couple of issues in the writeback throttling code.
   These fixes are also targetted at -stable kernels.

 - Ryusuke Konishi's series "nilfs2: fix potential issues related to
   reserved inodes" does that. This should actually be in the
   mm-nonmm-stable tree, along with the many other nilfs2 patches. My
   bad.

 - More folio conversions from Kefeng Wang in the series "mm: convert to
   folio_alloc_mpol()"

 - Kemeng Shi has sent some cleanups to the writeback code in the series
   "Add helper functions to remove repeated code and improve readability
   of cgroup writeback"

 - Kairui Song has made the swap code a little smaller and a little
   faster in the series "mm/swap: clean up and optimize swap cache
   index".

 - In the series "mm/memory: cleanly support zeropage in
   vm_insert_page*(), vm_map_pages*() and vmf_insert_mixed()" David
   Hildenbrand has reworked the rather sketchy handling of the use of
   the zeropage in MAP_SHARED mappings. I don't see any runtime effects
   here - more a cleanup/understandability/maintainablity thing.

 - Dev Jain has improved selftests/mm/va_high_addr_switch.c's handling
   of higher addresses, for aarch64. The (poorly named) series is
   "Restructure va_high_addr_switch".

 - The core TLB handling code gets some cleanups and possible slight
   optimizations in Bang Li's series "Add update_mmu_tlb_range() to
   simplify code".

 - Jane Chu has improved the handling of our
   fake-an-unrecoverable-memory-error testing feature MADV_HWPOISON in
   the series "Enhance soft hwpoison handling and injection".

 - Jeff Johnson has sent a billion patches everywhere to add
   MODULE_DESCRIPTION() to everything. Some landed in this pull.

 - In the series "mm: cleanup MIGRATE_SYNC_NO_COPY mode", Kefeng Wang
   has simplified migration's use of hardware-offload memory copying.

 - Yosry Ahmed performs more folio API conversions in his series "mm:
   zswap: trivial folio conversions".

 - In the series "large folios swap-in: handle refault cases first",
   Chuanhua Han inches us forward in the handling of large pages in the
   swap code. This is a cleanup and optimization, working toward the end
   objective of full support of large folio swapin/out.

 - In the series "mm,swap: cleanup VMA based swap readahead window
   calculation", Huang Ying has contributed some cleanups and a possible
   fixlet to his VMA based swap readahead code.

 - In the series "add mTHP support for anonymous shmem" Baolin Wang has
   taught anonymous shmem mappings to use multisize THP. By default this
   is a no-op - users must opt in vis sysfs controls. Dramatic
   improvements in pagefault latency are realized.

 - David Hildenbrand has some cleanups to our remaining use of
   page_mapcount() in the series "fs/proc: move page_mapcount() to
   fs/proc/internal.h".

 - David also has some highmem accounting cleanups in the series
   "mm/highmem: don't track highmem pages manually".

 - Build-time fixes and cleanups from John Hubbard in the series
   "cleanups, fixes, and progress towards avoiding "make headers"".

 - Cleanups and consolidation of the core pagemap handling from Barry
   Song in the series "mm: introduce pmd|pte_needs_soft_dirty_wp helpers
   and utilize them".

 - Lance Yang's series "Reclaim lazyfree THP without splitting" has
   reduced the latency of the reclaim of pmd-mapped THPs under fairly
   common circumstances. A 10x speedup is seen in a microbenchmark.

   It does this by punting to aother CPU but I guess that's a win unless
   all CPUs are pegged.

 - hugetlb_cgroup cleanups from Xiu Jianfeng in the series
   "mm/hugetlb_cgroup: rework on cftypes".

 - Miaohe Lin's series "Some cleanups for memory-failure" does just that
   thing.

 - Someone other than SeongJae has developed a DAMON feature in Honggyu
   Kim's series "DAMON based tiered memory management for CXL memory".
   This adds DAMON features which may be used to help determine the
   efficiency of our placement of CXL/PCIe attached DRAM.

 - DAMON user API centralization and simplificatio work in SeongJae
   Park's series "mm/damon: introduce DAMON parameters online commit
   function".

 - In the series "mm: page_type, zsmalloc and page_mapcount_reset()"
   David Hildenbrand does some maintenance work on zsmalloc - partially
   modernizing its use of pageframe fields.

 - Kefeng Wang provides more folio conversions in the series "mm: remove
   page_maybe_dma_pinned() and page_mkclean()".

 - More cleanup from David Hildenbrand, this time in the series
   "mm/memory_hotplug: use PageOffline() instead of PageReserved() for
   !ZONE_DEVICE". It "enlightens memory hotplug more about PageOffline()
   pages" and permits the removal of some virtio-mem hacks.

 - Barry Song's series "mm: clarify folio_add_new_anon_rmap() and
   __folio_add_anon_rmap()" is a cleanup to the anon folio handling in
   preparation for mTHP (multisize THP) swapin.

 - Kefeng Wang's series "mm: improve clear and copy user folio"
   implements more folio conversions, this time in the area of large
   folio userspace copying.

 - The series "Docs/mm/damon/maintaier-profile: document a mailing tool
   and community meetup series" tells people how to get better involved
   with other DAMON developers. From SeongJae Park.

 - A large series ("kmsan: Enable on s390") from Ilya Leoshkevich does
   that.

 - David Hildenbrand sends along more cleanups, this time against the
   migration code. The series is "mm/migrate: move NUMA hinting fault
   folio isolation + checks under PTL".

 - Jan Kara has found quite a lot of strangenesses and minor errors in
   the readahead code. He addresses this in the series "mm: Fix various
   readahead quirks".

 - SeongJae Park's series "selftests/damon: test DAMOS tried regions and
   {min,max}_nr_regions" adds features and addresses errors in DAMON's
   self testing code.

 - Gavin Shan has found a userspace-triggerable WARN in the pagecache
   code. The series "mm/filemap: Limit page cache size to that supported
   by xarray" addresses this. The series is marked cc:stable.

 - Chengming Zhou's series "mm/ksm: cmp_and_merge_page() optimizations
   and cleanup" cleans up and slightly optimizes KSM.

 - Roman Gushchin has separated the memcg-v1 and memcg-v2 code - lots of
   code motion. The series (which also makes the memcg-v1 code
   Kconfigurable) are "mm: memcg: separate legacy cgroup v1 code and put
   under config option" and "mm: memcg: put cgroup v1-specific memcg
   data under CONFIG_MEMCG_V1"

 - Dan Schatzberg's series "Add swappiness argument to memory.reclaim"
   adds an additional feature to this cgroup-v2 control file.

 - The series "Userspace controls soft-offline pages" from Jiaqi Yan
   permits userspace to stop the kernel's automatic treatment of
   excessive correctable memory errors. In order to permit userspace to
   monitor and handle this situation.

 - Kefeng Wang's series "mm: migrate: support poison recover from
   migrate folio" teaches the kernel to appropriately handle migration
   from poisoned source folios rather than simply panicing.

 - SeongJae Park's series "Docs/damon: minor fixups and improvements"
   does those things.

 - In the series "mm/zsmalloc: change back to per-size_class lock"
   Chengming Zhou improves zsmalloc's scalability and memory
   utilization.

 - Vivek Kasireddy's series "mm/gup: Introduce memfd_pin_folios() for
   pinning memfd folios" makes the GUP code use FOLL_PIN rather than
   bare refcount increments. So these paes can first be moved aside if
   they reside in the movable zone or a CMA block.

 - Andrii Nakryiko has added a binary ioctl()-based API to
   /proc/pid/maps for much faster reading of vma information. The series
   is "query VMAs from /proc/<pid>/maps".

 - In the series "mm: introduce per-order mTHP split counters" Lance
   Yang improves the kernel's presentation of developer information
   related to multisize THP splitting.

 - Michael Ellerman has developed the series "Reimplement huge pages
   without hugepd on powerpc (8xx, e500, book3s/64)". This permits
   userspace to use all available huge page sizes.

 - In the series "revert unconditional slab and page allocator fault
   injection calls" Vlastimil Babka removes a performance-affecting and
   not very useful feature from slab fault injection.

* tag 'mm-stable-2024-07-21-14-50' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (411 commits)
  mm/mglru: fix ineffective protection calculation
  mm/zswap: fix a white space issue
  mm/hugetlb: fix kernel NULL pointer dereference when migrating hugetlb folio
  mm/hugetlb: fix possible recursive locking detected warning
  mm/gup: clear the LRU flag of a page before adding to LRU batch
  mm/numa_balancing: teach mpol_to_str about the balancing mode
  mm: memcg1: convert charge move flags to unsigned long long
  alloc_tag: fix page_ext_get/page_ext_put sequence during page splitting
  lib: reuse page_ext_data() to obtain codetag_ref
  lib: add missing newline character in the warning message
  mm/mglru: fix overshooting shrinker memory
  mm/mglru: fix div-by-zero in vmpressure_calc_level()
  mm/kmemleak: replace strncpy() with strscpy()
  mm, page_alloc: put should_fail_alloc_page() back behing CONFIG_FAIL_PAGE_ALLOC
  mm, slab: put should_failslab() back behind CONFIG_SHOULD_FAILSLAB
  mm: ignore data-race in __swap_writepage
  hugetlbfs: ensure generic_hugetlb_get_unmapped_area() returns higher address than mmap_min_addr
  mm: shmem: rename mTHP shmem counters
  mm: swap_state: use folio_alloc_mpol() in __read_swap_cache_async()
  mm/migrate: putback split folios when numa hint migration fails
  ...

22 files changed, 195 insertions, 329 deletions

diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index dc5c039eb28e..dd4eb3063175 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -47,8 +47,6 @@ static inline void pgtable_free(void *table, unsigned index_size)
 	}
 }
 
-#define get_hugepd_cache_index(x)  (x)
-
 static inline void pgtable_free_tlb(struct mmu_gather *tlb,
 				    void *table, int shift)
 {
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 6472b08fa1b0..c654c376ef8b 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -74,21 +74,6 @@
 #define remap_4k_pfn(vma, addr, pfn, prot)	\
 	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot))
 
-#ifdef CONFIG_HUGETLB_PAGE
-static inline int hash__hugepd_ok(hugepd_t hpd)
-{
-	unsigned long hpdval = hpd_val(hpd);
-	/*
-	 * if it is not a pte and have hugepd shift mask
-	 * set, then it is a hugepd directory pointer
-	 */
-	if (!(hpdval & _PAGE_PTE) && (hpdval & _PAGE_PRESENT) &&
-	    ((hpdval & HUGEPD_SHIFT_MASK) != 0))
-		return true;
-	return false;
-}
-#endif
-
 /*
  * 4K PTE format is different from 64K PTE format. Saving the hash_slot is just
  * a matter of returning the PTE bits that need to be modified. On 64K PTE,
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index faf3e3b4e4b2..0755f2567021 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -4,6 +4,7 @@
 #ifdef __KERNEL__
 
 #include <asm/asm-const.h>
+#include <asm/book3s/64/slice.h>
 
 /*
  * Common bits between 4K and 64K pages in a linux-style PTE.
@@ -161,14 +162,10 @@ extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 			    pte_t *ptep, unsigned long pte, int huge);
 unsigned long htab_convert_pte_flags(unsigned long pteflags, unsigned long flags);
 /* Atomic PTE updates */
-static inline unsigned long hash__pte_update(struct mm_struct *mm,
-					 unsigned long addr,
-					 pte_t *ptep, unsigned long clr,
-					 unsigned long set,
-					 int huge)
+static inline unsigned long hash__pte_update_one(pte_t *ptep, unsigned long clr,
+						 unsigned long set)
 {
 	__be64 old_be, tmp_be;
-	unsigned long old;
 
 	__asm__ __volatile__(
 	"1:	ldarx	%0,0,%3		# pte_update\n\
@@ -182,11 +179,40 @@ static inline unsigned long hash__pte_update(struct mm_struct *mm,
 	: "r" (ptep), "r" (cpu_to_be64(clr)), "m" (*ptep),
 	  "r" (cpu_to_be64(H_PAGE_BUSY)), "r" (cpu_to_be64(set))
 	: "cc" );
+
+	return be64_to_cpu(old_be);
+}
+
+static inline unsigned long hash__pte_update(struct mm_struct *mm,
+					 unsigned long addr,
+					 pte_t *ptep, unsigned long clr,
+					 unsigned long set,
+					 int huge)
+{
+	unsigned long old;
+
+	old = hash__pte_update_one(ptep, clr, set);
+
+	if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && huge) {
+		unsigned int psize = get_slice_psize(mm, addr);
+		int nb, i;
+
+		if (psize == MMU_PAGE_16M)
+			nb = SZ_16M / PMD_SIZE;
+		else if (psize == MMU_PAGE_16G)
+			nb = SZ_16G / PUD_SIZE;
+		else
+			nb = 1;
+
+		WARN_ON_ONCE(nb == 1);	/* Should never happen */
+
+		for (i = 1; i < nb; i++)
+			hash__pte_update_one(ptep + i, clr, set);
+	}
 	/* huge pages use the old page table lock */
 	if (!huge)
 		assert_pte_locked(mm, addr);
 
-	old = be64_to_cpu(old_be);
 	if (old & H_PAGE_HASHPTE)
 		hpte_need_flush(mm, addr, ptep, old, huge);
 
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index aa1c67c8bfc8..f0bba9c5f9c3 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -49,9 +49,6 @@ static inline bool gigantic_page_runtime_supported(void)
 	return true;
 }
 
-/* hugepd entry valid bit */
-#define HUGEPD_VAL_BITS		(0x8000000000000000UL)
-
 #define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
 extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep);
@@ -60,29 +57,7 @@ extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
 extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep,
 					 pte_t old_pte, pte_t new_pte);
-/*
- * This should work for other subarchs too. But right now we use the
- * new format only for 64bit book3s
- */
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
-	BUG_ON(!hugepd_ok(hpd));
-	/*
-	 * We have only four bits to encode, MMU page size
-	 */
-	BUILD_BUG_ON((MMU_PAGE_COUNT - 1) > 0xf);
-	return __va(hpd_val(hpd) & HUGEPD_ADDR_MASK);
-}
-
-static inline unsigned int hugepd_mmu_psize(hugepd_t hpd)
-{
-	return (hpd_val(hpd) & HUGEPD_SHIFT_MASK) >> 2;
-}
 
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
-	return mmu_psize_to_shift(hugepd_mmu_psize(hpd));
-}
 static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 				      unsigned long vmaddr)
 {
@@ -90,19 +65,6 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 		return radix__flush_hugetlb_page(vma, vmaddr);
 }
 
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
-				    unsigned int pdshift)
-{
-	unsigned long idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(hpd);
-
-	return hugepd_page(hpd) + idx;
-}
-
-static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift)
-{
-	*hpdp = __hugepd(__pa(new) | HUGEPD_VAL_BITS | (shift_to_mmu_psize(pshift) << 2));
-}
-
 void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 
 static inline int check_and_get_huge_psize(int shift)
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h
deleted file mode 100644
index baf934578c3a..000000000000
--- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H
-#define _ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H
-/*
- * hash 4k can't share hugetlb and also doesn't support THP
- */
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_HUGETLB_PAGE
-/*
- * With radix , we have hugepage ptes in the pud and pmd entries. We don't
- * need to setup hugepage directory for them. Our pte and page directory format
- * enable us to have this enabled.
- */
-static inline int hugepd_ok(hugepd_t hpd)
-{
-	if (radix_enabled())
-		return 0;
-	return hash__hugepd_ok(hpd);
-}
-#define is_hugepd(hpd)		(hugepd_ok(hpd))
-
-/*
- * 16M and 16G huge page directory tables are allocated from slab cache
- *
- */
-#define H_16M_CACHE_INDEX (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE - 24)
-#define H_16G_CACHE_INDEX                                                      \
-	(PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + H_PUD_INDEX_SIZE - 34)
-
-static inline int get_hugepd_cache_index(int index)
-{
-	switch (index) {
-	case H_16M_CACHE_INDEX:
-		return HTLB_16M_INDEX;
-	case H_16G_CACHE_INDEX:
-		return HTLB_16G_INDEX;
-	default:
-		BUG();
-	}
-	/* should not reach */
-}
-
-#endif /* CONFIG_HUGETLB_PAGE */
-
-#endif /* __ASSEMBLY__ */
-
-#endif /*_ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
index 6ac73da7b80e..4d8d7b4ea16b 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
@@ -5,26 +5,6 @@
 #ifndef __ASSEMBLY__
 #ifdef CONFIG_HUGETLB_PAGE
 
-/*
- * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't
- * need to setup hugepage directory for them. Our pte and page directory format
- * enable us to have this enabled.
- */
-static inline int hugepd_ok(hugepd_t hpd)
-{
-	return 0;
-}
-
-#define is_hugepd(pdep)			0
-
-/*
- * This should never get called
- */
-static __always_inline int get_hugepd_cache_index(int index)
-{
-	BUILD_BUG();
-}
-
 #endif /* CONFIG_HUGETLB_PAGE */
 
 static inline int remap_4k_pfn(struct vm_area_struct *vma, unsigned long addr,
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 8f9432e3855a..519b1743a0f4 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -274,6 +274,24 @@ static inline bool pud_leaf(pud_t pud)
 {
 	return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
 }
+
+#define pmd_leaf_size pmd_leaf_size
+static inline unsigned long pmd_leaf_size(pmd_t pmd)
+{
+	if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !radix_enabled())
+		return SZ_16M;
+	else
+		return PMD_SIZE;
+}
+
+#define pud_leaf_size pud_leaf_size
+static inline unsigned long pud_leaf_size(pud_t pud)
+{
+	if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !radix_enabled())
+		return SZ_16G;
+	else
+		return PUD_SIZE;
+}
 #endif /* __ASSEMBLY__ */
 
 #include <asm/book3s/64/hash.h>
@@ -285,11 +303,9 @@ static inline bool pud_leaf(pud_t pud)
 #define  MAX_PHYSMEM_BITS	R_MAX_PHYSMEM_BITS
 #endif
 
-
+/* hash 4k can't share hugetlb and also doesn't support THP */
 #ifdef CONFIG_PPC_64K_PAGES
 #include <asm/book3s/64/pgtable-64k.h>
-#else
-#include <asm/book3s/64/pgtable-4k.h>
 #endif
 
 #include <asm/barrier.h>
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index ea71f7245a63..18a3028ac3b6 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -30,10 +30,9 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 }
 #define is_hugepage_only_range is_hugepage_only_range
 
-#define __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE
-void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
-			    unsigned long end, unsigned long floor,
-			    unsigned long ceiling);
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		     pte_t pte, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
@@ -67,14 +66,6 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 {
 }
 
-#define hugepd_shift(x) 0
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
-				    unsigned pdshift)
-{
-	return NULL;
-}
-
-
 static inline void __init gigantic_hugetlb_cma_reserve(void)
 {
 }
diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
index 92df40c6cc6b..014799557f60 100644
--- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
@@ -4,42 +4,12 @@
 
 #define PAGE_SHIFT_8M		23
 
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
-	BUG_ON(!hugepd_ok(hpd));
-
-	return (pte_t *)__va(hpd_val(hpd) & ~HUGEPD_SHIFT_MASK);
-}
-
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
-	return PAGE_SHIFT_8M;
-}
-
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
-				    unsigned int pdshift)
-{
-	unsigned long idx = (addr & (SZ_4M - 1)) >> PAGE_SHIFT;
-
-	return hugepd_page(hpd) + idx;
-}
-
 static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 				      unsigned long vmaddr)
 {
 	flush_tlb_page(vma, vmaddr);
 }
 
-static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift)
-{
-	*hpdp = __hugepd(__pa(new) | _PMD_USER | _PMD_PRESENT | _PMD_PAGE_8M);
-}
-
-static inline void hugepd_populate_kernel(hugepd_t *hpdp, pte_t *new, unsigned int pshift)
-{
-	*hpdp = __hugepd(__pa(new) | _PMD_PRESENT | _PMD_PAGE_8M);
-}
-
 static inline int check_and_get_huge_psize(int shift)
 {
 	return shift_to_mmu_psize(shift);
@@ -49,6 +19,14 @@ static inline int check_and_get_huge_psize(int shift)
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 		     pte_t pte, unsigned long sz);
 
+#define __HAVE_ARCH_HUGE_PTEP_GET
+static inline pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+	if (ptep_is_8m_pmdp(mm, addr, ptep))
+		ptep = pte_offset_kernel((pmd_t *)ptep, ALIGN_DOWN(addr, SZ_8M));
+	return ptep_get(ptep);
+}
+
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 				  pte_t *ptep, unsigned long sz)
diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
index 141d82e249a8..a756a1e59c54 100644
--- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
@@ -189,19 +189,14 @@ typedef struct {
 
 #define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000)
 
-/* Page size definitions, common between 32 and 64-bit
+/*
+ * Page size definitions for 8xx
  *
  *    shift : is the "PAGE_SHIFT" value for that page size
- *    penc  : is the pte encoding mask
  *
  */
 struct mmu_psize_def {
 	unsigned int	shift;	/* number of bits */
-	unsigned int	enc;	/* PTE encoding */
-	unsigned int    ind;    /* Corresponding indirect page size shift */
-	unsigned int	flags;
-#define MMU_PAGE_SIZE_DIRECT	0x1	/* Supported as a direct size */
-#define MMU_PAGE_SIZE_INDIRECT	0x2	/* Supported as an indirect size */
 };
 
 extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
diff --git a/arch/powerpc/include/asm/nohash/32/pte-44x.h b/arch/powerpc/include/asm/nohash/32/pte-44x.h
index 851813725237..da0469928273 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-44x.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-44x.h
@@ -75,9 +75,6 @@
 #define _PAGE_NO_CACHE	0x00000400		/* H: I bit */
 #define _PAGE_WRITETHRU	0x00000800		/* H: W bit */
 
-/* No page size encoding in the linux PTE */
-#define _PAGE_PSIZE		0
-
 /* TODO: Add large page lowmem mapping support */
 #define _PMD_PRESENT	0
 #define _PMD_PRESENT_MASK (PAGE_MASK)
diff --git a/arch/powerpc/include/asm/nohash/32/pte-85xx.h b/arch/powerpc/include/asm/nohash/32/pte-85xx.h
index 653a342d3b25..14d64b4f3f14 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-85xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-85xx.h
@@ -31,9 +31,6 @@
 #define _PAGE_WRITETHRU	0x00400	/* H: W bit */
 #define _PAGE_SPECIAL	0x00800 /* S: Special page */
 
-/* No page size encoding in the linux PTE */
-#define _PAGE_PSIZE		0
-
 #define _PMD_PRESENT	0
 #define _PMD_PRESENT_MASK (PAGE_MASK)
 #define _PMD_BAD	(~PAGE_MASK)
diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
index 137dc3c84e45..54ebb91dbdcf 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
@@ -74,12 +74,11 @@
 #define _PTE_NONE_MASK	0
 
 #ifdef CONFIG_PPC_16K_PAGES
-#define _PAGE_PSIZE	_PAGE_SPS
+#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_SPS)
 #else
-#define _PAGE_PSIZE		0
+#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED)
 #endif
 
-#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE)
 #define _PAGE_BASE	(_PAGE_BASE_NC)
 
 #include <asm/pgtable-masks.h>
@@ -120,7 +119,7 @@ static inline pte_t pte_mkhuge(pte_t pte)
 
 #define pte_mkhuge pte_mkhuge
 
-static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
+static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 				     unsigned long clr, unsigned long set, int huge);
 
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
@@ -142,19 +141,12 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, pte_t *pt
 }
 #define __ptep_set_access_flags __ptep_set_access_flags
 
-static inline unsigned long pgd_leaf_size(pgd_t pgd)
-{
-	if (pgd_val(pgd) & _PMD_PAGE_8M)
-		return SZ_8M;
-	return SZ_4M;
-}
-
-#define pgd_leaf_size pgd_leaf_size
-
-static inline unsigned long pte_leaf_size(pte_t pte)
+static inline unsigned long __pte_leaf_size(pmd_t pmd, pte_t pte)
 {
 	pte_basic_t val = pte_val(pte);
 
+	if (pmd_val(pmd) & _PMD_PAGE_8M)
+		return SZ_8M;
 	if (val & _PAGE_HUGE)
 		return SZ_512K;
 	if (val & _PAGE_SPS)
@@ -162,31 +154,38 @@ static inline unsigned long pte_leaf_size(pte_t pte)
 	return SZ_4K;
 }
 
-#define pte_leaf_size pte_leaf_size
+#define __pte_leaf_size __pte_leaf_size
 
 /*
  * On the 8xx, the page tables are a bit special. For 16k pages, we have
  * 4 identical entries. For 512k pages, we have 128 entries as if it was
  * 4k pages, but they are flagged as 512k pages for the hardware.
- * For other page sizes, we have a single entry in the table.
+ * For 8M pages, we have 1024 entries as if it was 4M pages (PMD_SIZE)
+ * but they are flagged as 8M pages for the hardware.
+ * For 4k pages, we have a single entry in the table.
  */
 static pmd_t *pmd_off(struct mm_struct *mm, unsigned long addr);
-static int hugepd_ok(hugepd_t hpd);
+static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address);
+
+static inline bool ptep_is_8m_pmdp(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+	return (pmd_t *)ptep == pmd_off(mm, ALIGN_DOWN(addr, SZ_8M));
+}
 
 static inline int number_of_cells_per_pte(pmd_t *pmd, pte_basic_t val, int huge)
 {
 	if (!huge)
 		return PAGE_SIZE / SZ_4K;
-	else if (hugepd_ok(*((hugepd_t *)pmd)))
-		return 1;
+	else if ((pmd_val(*pmd) & _PMD_PAGE_MASK) == _PMD_PAGE_8M)
+		return SZ_4M / SZ_4K;
 	else if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !(val & _PAGE_HUGE))
 		return SZ_16K / SZ_4K;
 	else
 		return SZ_512K / SZ_4K;
 }
 
-static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
-				     unsigned long clr, unsigned long set, int huge)
+static inline pte_basic_t __pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
+				       unsigned long clr, unsigned long set, int huge)
 {
 	pte_basic_t *entry = (pte_basic_t *)p;
 	pte_basic_t old = pte_val(*p);
@@ -198,7 +197,7 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
 
 	for (i = 0; i < num; i += PAGE_SIZE / SZ_4K, new += PAGE_SIZE) {
 		*entry++ = new;
-		if (IS_ENABLED(CONFIG_PPC_16K_PAGES) && num != 1) {
+		if (IS_ENABLED(CONFIG_PPC_16K_PAGES)) {
 			*entry++ = new;
 			*entry++ = new;
 			*entry++ = new;
@@ -208,6 +207,21 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
 	return old;
 }
 
+static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+				     unsigned long clr, unsigned long set, int huge)
+{
+	pte_basic_t old;
+
+	if (huge && ptep_is_8m_pmdp(mm, addr, ptep)) {
+		pmd_t *pmdp = (pmd_t *)ptep;
+
+		old = __pte_update(mm, addr, pte_offset_kernel(pmdp, 0), clr, set, huge);
+		__pte_update(mm, addr, pte_offset_kernel(pmdp + 1, 0), clr, set, huge);
+	} else {
+		old = __pte_update(mm, addr, ptep, clr, set, huge);
+	}
+	return old;
+}
 #define pte_update pte_update
 
 #ifdef CONFIG_PPC_16K_PAGES
diff --git a/arch/powerpc/include/asm/nohash/hugetlb-e500.h b/arch/powerpc/include/asm/nohash/hugetlb-e500.h
index 8f04ad20e040..cab0e1f1eea0 100644
--- a/arch/powerpc/include/asm/nohash/hugetlb-e500.h
+++ b/arch/powerpc/include/asm/nohash/hugetlb-e500.h
@@ -2,38 +2,8 @@
 #ifndef _ASM_POWERPC_NOHASH_HUGETLB_E500_H
 #define _ASM_POWERPC_NOHASH_HUGETLB_E500_H
 
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
-	if (WARN_ON(!hugepd_ok(hpd)))
-		return NULL;
-
-	return (pte_t *)((hpd_val(hpd) & ~HUGEPD_SHIFT_MASK) | PD_HUGE);
-}
-
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
-	return hpd_val(hpd) & HUGEPD_SHIFT_MASK;
-}
-
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
-				    unsigned int pdshift)
-{
-	/*
-	 * On FSL BookE, we have multiple higher-level table entries that
-	 * point to the same hugepte.  Just use the first one since they're all
-	 * identical.  So for that case, idx=0.
-	 */
-	return hugepd_page(hpd);
-}
-
 void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 
-static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift)
-{
-	/* We use the old format for PPC_E500 */
-	*hpdp = __hugepd(((unsigned long)new & ~PD_HUGE) | pshift);
-}
-
 static inline int check_and_get_huge_psize(int shift)
 {
 	if (shift & 1)	/* Not a power of 4 */
@@ -42,4 +12,13 @@ static inline int check_and_get_huge_psize(int shift)
 	return shift_to_mmu_psize(shift);
 }
 
+static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
+{
+	unsigned int tsize = shift - _PAGE_PSIZE_SHIFT_OFFSET;
+	pte_basic_t val = (tsize << _PAGE_PSIZE_SHIFT) & _PAGE_PSIZE_MSK;
+
+	return __pte((pte_val(entry) & ~(pte_basic_t)_PAGE_PSIZE_MSK) | val);
+}
+#define arch_make_huge_pte arch_make_huge_pte
+
 #endif /* _ASM_POWERPC_NOHASH_HUGETLB_E500_H */
diff --git a/arch/powerpc/include/asm/nohash/mmu-e500.h b/arch/powerpc/include/asm/nohash/mmu-e500.h
index 6ddced0415cb..b281d9eeaf1e 100644
--- a/arch/powerpc/include/asm/nohash/mmu-e500.h
+++ b/arch/powerpc/include/asm/nohash/mmu-e500.h
@@ -244,14 +244,11 @@ typedef struct {
 /* Page size definitions, common between 32 and 64-bit
  *
  *    shift : is the "PAGE_SHIFT" value for that page size
- *    penc  : is the pte encoding mask
  *
  */
 struct mmu_psize_def
 {
 	unsigned int	shift;	/* number of bits */
-	unsigned int	enc;	/* PTE encoding */
-	unsigned int    ind;    /* Corresponding indirect page size shift */
 	unsigned int	flags;
 #define MMU_PAGE_SIZE_DIRECT	0x1	/* Supported as a direct size */
 #define MMU_PAGE_SIZE_INDIRECT	0x2	/* Supported as an indirect size */
@@ -303,8 +300,7 @@ extern unsigned long linear_map_top;
 extern int book3e_htw_mode;
 
 #define PPC_HTW_NONE	0
-#define PPC_HTW_IBM	1
-#define PPC_HTW_E6500	2
+#define PPC_HTW_E6500	1
 
 /*
  * 64-bit booke platforms don't load the tlb in the tlb miss handler code.
diff --git a/arch/powerpc/include/asm/nohash/pgalloc.h b/arch/powerpc/include/asm/nohash/pgalloc.h
index 4b62376318e1..d06efac6d7aa 100644
--- a/arch/powerpc/include/asm/nohash/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/pgalloc.h
@@ -44,8 +44,6 @@ static inline void pgtable_free(void *table, int shift)
 	}
 }
 
-#define get_hugepd_cache_index(x)	(x)
-
 static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
 {
 	unsigned long pgf = (unsigned long)table;
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index f5f39d4f03c8..8d1f0b7062eb 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -31,6 +31,13 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
 
 extern int icache_44x_need_flush;
 
+#ifndef pte_huge_size
+static inline unsigned long pte_huge_size(pte_t pte)
+{
+	return PAGE_SIZE;
+}
+#endif
+
 /*
  * PTE updates. This function is called whenever an existing
  * valid PTE is updated. This does -not- include set_pte_at()
@@ -52,11 +59,34 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p
 {
 	pte_basic_t old = pte_val(*p);
 	pte_basic_t new = (old & ~(pte_basic_t)clr) | set;
+	unsigned long sz;
+	unsigned long pdsize;
+	int i;
 
 	if (new == old)
 		return old;
 
-	*p = __pte(new);
+	if (huge)
+		sz = pte_huge_size(__pte(old));
+	else
+		sz = PAGE_SIZE;
+
+	if (sz < PMD_SIZE)
+		pdsize = PAGE_SIZE;
+	else if (sz < PUD_SIZE)
+		pdsize = PMD_SIZE;
+	else if (sz < P4D_SIZE)
+		pdsize = PUD_SIZE;
+	else if (sz < PGDIR_SIZE)
+		pdsize = P4D_SIZE;
+	else
+		pdsize = PGDIR_SIZE;
+
+	for (i = 0; i < sz / pdsize; i++, p++) {
+		*p = __pte(new);
+		if (new)
+			new += (unsigned long long)(pdsize / PAGE_SIZE) << PTE_RPN_SHIFT;
+	}
 
 	if (IS_ENABLED(CONFIG_44x) && !is_kernel_addr(addr) && (old & _PAGE_EXEC))
 		icache_44x_need_flush = 1;
@@ -340,20 +370,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define pgprot_writecombine pgprot_noncached_wc
 
-#ifdef CONFIG_HUGETLB_PAGE
-static inline int hugepd_ok(hugepd_t hpd)
-{
-#ifdef CONFIG_PPC_8xx
-	return ((hpd_val(hpd) & _PMD_PAGE_MASK) == _PMD_PAGE_8M);
-#else
-	/* We clear the top bit to indicate hugepd */
-	return (hpd_val(hpd) && (hpd_val(hpd) & PD_HUGE) == 0);
-#endif
-}
-
-#define is_hugepd(hpd)		(hugepd_ok(hpd))
-#endif
-
 int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
 void unmap_kernel_page(unsigned long va);
 
diff --git a/arch/powerpc/include/asm/nohash/pte-e500.h b/arch/powerpc/include/asm/nohash/pte-e500.h
index f516f0b5b7a8..cb78392494da 100644
--- a/arch/powerpc/include/asm/nohash/pte-e500.h
+++ b/arch/powerpc/include/asm/nohash/pte-e500.h
@@ -19,20 +19,7 @@
 #define _PAGE_BAP_SX	0x000040
 #define _PAGE_BAP_UX	0x000080
 #define _PAGE_PSIZE_MSK	0x000f00
-#define _PAGE_PSIZE_4K	0x000200
-#define _PAGE_PSIZE_8K	0x000300
-#define _PAGE_PSIZE_16K	0x000400
-#define _PAGE_PSIZE_32K	0x000500
-#define _PAGE_PSIZE_64K	0x000600
-#define _PAGE_PSIZE_128K	0x000700
-#define _PAGE_PSIZE_256K	0x000800
-#define _PAGE_PSIZE_512K	0x000900
-#define _PAGE_PSIZE_1M	0x000a00
-#define _PAGE_PSIZE_2M	0x000b00
-#define _PAGE_PSIZE_4M	0x000c00
-#define _PAGE_PSIZE_8M	0x000d00
-#define _PAGE_PSIZE_16M	0x000e00
-#define _PAGE_PSIZE_32M	0x000f00
+#define _PAGE_TSIZE_4K	0x000100
 #define _PAGE_DIRTY	0x001000 /* C: page changed */
 #define _PAGE_SW0	0x002000
 #define _PAGE_U3	0x004000
@@ -46,6 +33,9 @@
 #define _PAGE_NO_CACHE	0x400000 /* I: cache inhibit */
 #define _PAGE_WRITETHRU	0x800000 /* W: cache write-through */
 
+#define _PAGE_PSIZE_SHIFT		7
+#define _PAGE_PSIZE_SHIFT_OFFSET	10
+
 /* "Higher level" linux bit combinations */
 #define _PAGE_EXEC		(_PAGE_BAP_SX | _PAGE_BAP_UX) /* .. and was cache cleaned */
 #define _PAGE_READ		(_PAGE_BAP_SR | _PAGE_BAP_UR) /* User read permission */
@@ -65,8 +55,6 @@
 
 #define _PAGE_SPECIAL	_PAGE_SW0
 
-/* Base page size */
-#define _PAGE_PSIZE	_PAGE_PSIZE_4K
 #define	PTE_RPN_SHIFT	(24)
 
 #define PTE_WIMGE_SHIFT (19)
@@ -89,7 +77,7 @@
  * pages. We always set _PAGE_COHERENT when SMP is enabled or
  * the processor might need it for DMA coherency.
  */
-#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE)
+#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_TSIZE_4K)
 #if defined(CONFIG_SMP)
 #define _PAGE_BASE	(_PAGE_BASE_NC | _PAGE_COHERENT)
 #else
@@ -105,6 +93,47 @@ static inline pte_t pte_mkexec(pte_t pte)
 }
 #define pte_mkexec pte_mkexec
 
+static inline unsigned long pte_huge_size(pte_t pte)
+{
+	pte_basic_t val = pte_val(pte);
+
+	return 1UL << (((val & _PAGE_PSIZE_MSK) >> _PAGE_PSIZE_SHIFT) + _PAGE_PSIZE_SHIFT_OFFSET);
+}
+#define pte_huge_size pte_huge_size
+
+static inline int pmd_leaf(pmd_t pmd)
+{
+	if (IS_ENABLED(CONFIG_PPC64))
+		return (long)pmd_val(pmd) > 0;
+	else
+		return pmd_val(pmd) & _PAGE_PSIZE_MSK;
+}
+#define pmd_leaf pmd_leaf
+
+static inline unsigned long pmd_leaf_size(pmd_t pmd)
+{
+	return pte_huge_size(__pte(pmd_val(pmd)));
+}
+#define pmd_leaf_size pmd_leaf_size
+
+#ifdef CONFIG_PPC64
+static inline int pud_leaf(pud_t pud)
+{
+	if (IS_ENABLED(CONFIG_PPC64))
+		return (long)pud_val(pud) > 0;
+	else
+		return pud_val(pud) & _PAGE_PSIZE_MSK;
+}
+#define pud_leaf pud_leaf
+
+static inline unsigned long pud_leaf_size(pud_t pud)
+{
+	return pte_huge_size(__pte(pud_val(pud)));
+}
+#define pud_leaf_size pud_leaf_size
+
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index e411e5a70ea3..83d0a4fc5f75 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -269,38 +269,6 @@ static inline const void *pfn_to_kaddr(unsigned long pfn)
 #define is_kernel_addr(x)	((x) >= TASK_SIZE)
 #endif
 
-#ifndef CONFIG_PPC_BOOK3S_64
-/*
- * Use the top bit of the higher-level page table entries to indicate whether
- * the entries we point to contain hugepages.  This works because we know that
- * the page tables live in kernel space.  If we ever decide to support having
- * page tables at arbitrary addresses, this breaks and will have to change.
- */
-#ifdef CONFIG_PPC64
-#define PD_HUGE 0x8000000000000000UL
-#else
-#define PD_HUGE 0x80000000
-#endif
-
-#else	/* CONFIG_PPC_BOOK3S_64 */
-/*
- * Book3S 64 stores real addresses in the hugepd entries to
- * avoid overlaps with _PAGE_PRESENT and _PAGE_PTE.
- */
-#define HUGEPD_ADDR_MASK	(0x0ffffffffffffffful & ~HUGEPD_SHIFT_MASK)
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
-/*
- * Some number of bits at the level of the page table that points to
- * a hugepte are used to encode the size.  This masks those bits.
- * On 8xx, HW assistance requires 4k alignment for the hugepte.
- */
-#ifdef CONFIG_PPC_8xx
-#define HUGEPD_SHIFT_MASK     0xfff
-#else
-#define HUGEPD_SHIFT_MASK     0x3f
-#endif
-
 #ifndef __ASSEMBLY__
 
 #ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/include/asm/pgtable-be-types.h b/arch/powerpc/include/asm/pgtable-be-types.h
index 82633200b500..6bd8f89b25dc 100644
--- a/arch/powerpc/include/asm/pgtable-be-types.h
+++ b/arch/powerpc/include/asm/pgtable-be-types.h
@@ -101,14 +101,4 @@ static inline bool pmd_xchg(pmd_t *pmdp, pmd_t old, pmd_t new)
 	return pmd_raw(old) == prev;
 }
 
-#ifdef CONFIG_ARCH_HAS_HUGEPD
-typedef struct { __be64 pdbe; } hugepd_t;
-#define __hugepd(x) ((hugepd_t) { cpu_to_be64(x) })
-
-static inline unsigned long hpd_val(hugepd_t x)
-{
-	return be64_to_cpu(x.pdbe);
-}
-#endif
-
 #endif /* _ASM_POWERPC_PGTABLE_BE_TYPES_H */
diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h
index 082c85cc09b1..7b3d4c592a10 100644
--- a/arch/powerpc/include/asm/pgtable-types.h
+++ b/arch/powerpc/include/asm/pgtable-types.h
@@ -49,7 +49,11 @@ static inline unsigned long pud_val(pud_t x)
 #endif /* CONFIG_PPC64 */
 
 /* PGD level */
+#if defined(CONFIG_PPC_E500) && defined(CONFIG_PTE_64BIT)
+typedef struct { unsigned long long pgd; } pgd_t;
+#else
 typedef struct { unsigned long pgd; } pgd_t;
+#endif
 #define __pgd(x)	((pgd_t) { (x) })
 static inline unsigned long pgd_val(pgd_t x)
 {
@@ -83,13 +87,4 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new)
 }
 #endif
 
-#ifdef CONFIG_ARCH_HAS_HUGEPD
-typedef struct { unsigned long pd; } hugepd_t;
-#define __hugepd(x) ((hugepd_t) { (x) })
-static inline unsigned long hpd_val(hugepd_t x)
-{
-	return x.pd;
-}
-#endif
-
 #endif /* _ASM_POWERPC_PGTABLE_TYPES_H */
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 239709a2f68e..264a6c09517a 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -106,6 +106,9 @@ unsigned long vmalloc_to_phys(void *vmalloc_addr);
 
 void pgtable_cache_add(unsigned int shift);
 
+#ifdef CONFIG_PPC32
+void __init *early_alloc_pgtable(unsigned long size);
+#endif
 pte_t *early_pte_alloc_kernel(pmd_t *pmdp, unsigned long va);
 
 #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_PPC32)