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
  ...

14 files changed, 460 insertions, 1351 deletions

diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 01c3b4b65241..6727a15ab94f 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1233,10 +1233,6 @@ void __init hash__early_init_mmu(void)
 	__pmd_table_size = H_PMD_TABLE_SIZE;
 	__pud_table_size = H_PUD_TABLE_SIZE;
 	__pgd_table_size = H_PGD_TABLE_SIZE;
-	/*
-	 * 4k use hugepd format, so for hash set then to
-	 * zero
-	 */
 	__pmd_val_bits = HASH_PMD_VAL_BITS;
 	__pud_val_bits = HASH_PUD_VAL_BITS;
 	__pgd_val_bits = HASH_PGD_VAL_BITS;
@@ -1546,6 +1542,13 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 		goto bail;
 	}
 
+	if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !radix_enabled()) {
+		if (hugeshift == PMD_SHIFT && psize == MMU_PAGE_16M)
+			hugeshift = mmu_psize_defs[MMU_PAGE_16M].shift;
+		if (hugeshift == PUD_SHIFT && psize == MMU_PAGE_16G)
+			hugeshift = mmu_psize_defs[MMU_PAGE_16G].shift;
+	}
+
 	/*
 	 * Add _PAGE_PRESENT to the required access perm. If there are parallel
 	 * updates to the pte that can possibly clear _PAGE_PTE, catch that too.
diff --git a/arch/powerpc/mm/book3s64/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c
index 5a2e512e96db..83c3361b358b 100644
--- a/arch/powerpc/mm/book3s64/hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/hugetlbpage.c
@@ -53,6 +53,16 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		/* If PTE permissions don't match, take page fault */
 		if (unlikely(!check_pte_access(access, old_pte)))
 			return 1;
+		/*
+		 * If hash-4k, hugepages use seeral contiguous PxD entries
+		 * so bail out and let mm make the page young or dirty
+		 */
+		if (IS_ENABLED(CONFIG_PPC_4K_PAGES)) {
+			if (!(old_pte & _PAGE_ACCESSED))
+				return 1;
+			if ((access & _PAGE_WRITE) && !(old_pte & _PAGE_DIRTY))
+				return 1;
+		}
 
 		/*
 		 * Try to lock the PTE, add ACCESSED and DIRTY if it was
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 2975ea0841ba..f4d8d3c40e5c 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -461,18 +461,6 @@ static inline void pgtable_free(void *table, int index)
 	case PUD_INDEX:
 		__pud_free(table);
 		break;
-#if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE)
-		/* 16M hugepd directory at pud level */
-	case HTLB_16M_INDEX:
-		BUILD_BUG_ON(H_16M_CACHE_INDEX <= 0);
-		kmem_cache_free(PGT_CACHE(H_16M_CACHE_INDEX), table);
-		break;
-		/* 16G hugepd directory at the pgd level */
-	case HTLB_16G_INDEX:
-		BUILD_BUG_ON(H_16G_CACHE_INDEX <= 0);
-		kmem_cache_free(PGT_CACHE(H_16G_CACHE_INDEX), table);
-		break;
-#endif
 		/* We don't free pgd table via RCU callback */
 	default:
 		BUG();
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 594a4b7b2ca2..6b043180220a 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -28,8 +28,6 @@
 
 bool hugetlb_disabled = false;
 
-#define hugepd_none(hpd)	(hpd_val(hpd) == 0)
-
 #define PTE_T_ORDER	(__builtin_ffs(sizeof(pte_basic_t)) - \
 			 __builtin_ffs(sizeof(void *)))
 
@@ -42,156 +40,43 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long s
 	return __find_linux_pte(mm->pgd, addr, NULL, NULL);
 }
 
-static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
-			   unsigned long address, unsigned int pdshift,
-			   unsigned int pshift, spinlock_t *ptl)
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, unsigned long sz)
 {
-	struct kmem_cache *cachep;
-	pte_t *new;
-	int i;
-	int num_hugepd;
-
-	if (pshift >= pdshift) {
-		cachep = PGT_CACHE(PTE_T_ORDER);
-		num_hugepd = 1 << (pshift - pdshift);
-	} else {
-		cachep = PGT_CACHE(pdshift - pshift);
-		num_hugepd = 1;
-	}
-
-	if (!cachep) {
-		WARN_ONCE(1, "No page table cache created for hugetlb tables");
-		return -ENOMEM;
-	}
-
-	new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
 
-	BUG_ON(pshift > HUGEPD_SHIFT_MASK);
-	BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
+	addr &= ~(sz - 1);
 
-	if (!new)
-		return -ENOMEM;
+	p4d = p4d_offset(pgd_offset(mm, addr), addr);
+	if (!mm_pud_folded(mm) && sz >= P4D_SIZE)
+		return (pte_t *)p4d;
 
-	/*
-	 * Make sure other cpus find the hugepd set only after a
-	 * properly initialized page table is visible to them.
-	 * For more details look for comment in __pte_alloc().
-	 */
-	smp_wmb();
+	pud = pud_alloc(mm, p4d, addr);
+	if (!pud)
+		return NULL;
+	if (!mm_pmd_folded(mm) && sz >= PUD_SIZE)
+		return (pte_t *)pud;
 
-	spin_lock(ptl);
-	/*
-	 * We have multiple higher-level entries that point to the same
-	 * actual pte location.  Fill in each as we go and backtrack on error.
-	 * We need all of these so the DTLB pgtable walk code can find the
-	 * right higher-level entry without knowing if it's a hugepage or not.
-	 */
-	for (i = 0; i < num_hugepd; i++, hpdp++) {
-		if (unlikely(!hugepd_none(*hpdp)))
-			break;
-		hugepd_populate(hpdp, new, pshift);
-	}
-	/* If we bailed from the for loop early, an error occurred, clean up */
-	if (i < num_hugepd) {
-		for (i = i - 1 ; i >= 0; i--, hpdp--)
-			*hpdp = __hugepd(0);
-		kmem_cache_free(cachep, new);
-	} else {
-		kmemleak_ignore(new);
-	}
-	spin_unlock(ptl);
-	return 0;
-}
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return NULL;
 
-/*
- * At this point we do the placement change only for BOOK3S 64. This would
- * possibly work on other subarchs.
- */
-pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
-		      unsigned long addr, unsigned long sz)
-{
-	pgd_t *pg;
-	p4d_t *p4;
-	pud_t *pu;
-	pmd_t *pm;
-	hugepd_t *hpdp = NULL;
-	unsigned pshift = __ffs(sz);
-	unsigned pdshift = PGDIR_SHIFT;
-	spinlock_t *ptl;
-
-	addr &= ~(sz-1);
-	pg = pgd_offset(mm, addr);
-	p4 = p4d_offset(pg, addr);
+	if (sz >= PMD_SIZE) {
+		/* On 8xx, all hugepages are handled as contiguous PTEs */
+		if (IS_ENABLED(CONFIG_PPC_8xx)) {
+			int i;
 
-#ifdef CONFIG_PPC_BOOK3S_64
-	if (pshift == PGDIR_SHIFT)
-		/* 16GB huge page */
-		return (pte_t *) p4;
-	else if (pshift > PUD_SHIFT) {
-		/*
-		 * We need to use hugepd table
-		 */
-		ptl = &mm->page_table_lock;
-		hpdp = (hugepd_t *)p4;
-	} else {
-		pdshift = PUD_SHIFT;
-		pu = pud_alloc(mm, p4, addr);
-		if (!pu)
-			return NULL;
-		if (pshift == PUD_SHIFT)
-			return (pte_t *)pu;
-		else if (pshift > PMD_SHIFT) {
-			ptl = pud_lockptr(mm, pu);
-			hpdp = (hugepd_t *)pu;
-		} else {
-			pdshift = PMD_SHIFT;
-			pm = pmd_alloc(mm, pu, addr);
-			if (!pm)
-				return NULL;
-			if (pshift == PMD_SHIFT)
-				/* 16MB hugepage */
-				return (pte_t *)pm;
-			else {
-				ptl = pmd_lockptr(mm, pm);
-				hpdp = (hugepd_t *)pm;
+			for (i = 0; i < sz / PMD_SIZE; i++) {
+				if (!pte_alloc_huge(mm, pmd + i, addr))
+					return NULL;
 			}
 		}
+		return (pte_t *)pmd;
 	}
-#else
-	if (pshift >= PGDIR_SHIFT) {
-		ptl = &mm->page_table_lock;
-		hpdp = (hugepd_t *)p4;
-	} else {
-		pdshift = PUD_SHIFT;
-		pu = pud_alloc(mm, p4, addr);
-		if (!pu)
-			return NULL;
-		if (pshift >= PUD_SHIFT) {
-			ptl = pud_lockptr(mm, pu);
-			hpdp = (hugepd_t *)pu;
-		} else {
-			pdshift = PMD_SHIFT;
-			pm = pmd_alloc(mm, pu, addr);
-			if (!pm)
-				return NULL;
-			ptl = pmd_lockptr(mm, pm);
-			hpdp = (hugepd_t *)pm;
-		}
-	}
-#endif
-	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,
-						  pdshift, pshift, ptl))
-		return NULL;
-
-	return hugepte_offset(*hpdp, addr, pdshift);
+	return pte_alloc_huge(mm, pmd, addr);
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -248,264 +133,6 @@ int __init alloc_bootmem_huge_page(struct hstate *h, int nid)
 	return __alloc_bootmem_huge_page(h, nid);
 }
 
-#ifndef CONFIG_PPC_BOOK3S_64
-#define HUGEPD_FREELIST_SIZE \
-	((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t))
-
-struct hugepd_freelist {
-	struct rcu_head	rcu;
-	unsigned int index;
-	void *ptes[];
-};
-
-static DEFINE_PER_CPU(struct hugepd_freelist *, hugepd_freelist_cur);
-
-static void hugepd_free_rcu_callback(struct rcu_head *head)
-{
-	struct hugepd_freelist *batch =
-		container_of(head, struct hugepd_freelist, rcu);
-	unsigned int i;
-
-	for (i = 0; i < batch->index; i++)
-		kmem_cache_free(PGT_CACHE(PTE_T_ORDER), batch->ptes[i]);
-
-	free_page((unsigned long)batch);
-}
-
-static void hugepd_free(struct mmu_gather *tlb, void *hugepte)
-{
-	struct hugepd_freelist **batchp;
-
-	batchp = &get_cpu_var(hugepd_freelist_cur);
-
-	if (atomic_read(&tlb->mm->mm_users) < 2 ||
-	    mm_is_thread_local(tlb->mm)) {
-		kmem_cache_free(PGT_CACHE(PTE_T_ORDER), hugepte);
-		put_cpu_var(hugepd_freelist_cur);
-		return;
-	}
-
-	if (*batchp == NULL) {
-		*batchp = (struct hugepd_freelist *)__get_free_page(GFP_ATOMIC);
-		(*batchp)->index = 0;
-	}
-
-	(*batchp)->ptes[(*batchp)->index++] = hugepte;
-	if ((*batchp)->index == HUGEPD_FREELIST_SIZE) {
-		call_rcu(&(*batchp)->rcu, hugepd_free_rcu_callback);
-		*batchp = NULL;
-	}
-	put_cpu_var(hugepd_freelist_cur);
-}
-#else
-static inline void hugepd_free(struct mmu_gather *tlb, void *hugepte) {}
-#endif
-
-/* Return true when the entry to be freed maps more than the area being freed */
-static bool range_is_outside_limits(unsigned long start, unsigned long end,
-				    unsigned long floor, unsigned long ceiling,
-				    unsigned long mask)
-{
-	if ((start & mask) < floor)
-		return true;
-	if (ceiling) {
-		ceiling &= mask;
-		if (!ceiling)
-			return true;
-	}
-	return end - 1 > ceiling - 1;
-}
-
-static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshift,
-			      unsigned long start, unsigned long end,
-			      unsigned long floor, unsigned long ceiling)
-{
-	pte_t *hugepte = hugepd_page(*hpdp);
-	int i;
-
-	unsigned long pdmask = ~((1UL << pdshift) - 1);
-	unsigned int num_hugepd = 1;
-	unsigned int shift = hugepd_shift(*hpdp);
-
-	/* Note: On fsl the hpdp may be the first of several */
-	if (shift > pdshift)
-		num_hugepd = 1 << (shift - pdshift);
-
-	if (range_is_outside_limits(start, end, floor, ceiling, pdmask))
-		return;
-
-	for (i = 0; i < num_hugepd; i++, hpdp++)
-		*hpdp = __hugepd(0);
-
-	if (shift >= pdshift)
-		hugepd_free(tlb, hugepte);
-	else
-		pgtable_free_tlb(tlb, hugepte,
-				 get_hugepd_cache_index(pdshift - shift));
-}
-
-static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
-				   unsigned long addr, unsigned long end,
-				   unsigned long floor, unsigned long ceiling)
-{
-	pgtable_t token = pmd_pgtable(*pmd);
-
-	if (range_is_outside_limits(addr, end, floor, ceiling, PMD_MASK))
-		return;
-
-	pmd_clear(pmd);
-	pte_free_tlb(tlb, token, addr);
-	mm_dec_nr_ptes(tlb->mm);
-}
-
-static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
-				   unsigned long addr, unsigned long end,
-				   unsigned long floor, unsigned long ceiling)
-{
-	pmd_t *pmd;
-	unsigned long next;
-	unsigned long start;
-
-	start = addr;
-	do {
-		unsigned long more;
-
-		pmd = pmd_offset(pud, addr);
-		next = pmd_addr_end(addr, end);
-		if (!is_hugepd(__hugepd(pmd_val(*pmd)))) {
-			if (pmd_none_or_clear_bad(pmd))
-				continue;
-
-			/*
-			 * if it is not hugepd pointer, we should already find
-			 * it cleared.
-			 */
-			WARN_ON(!IS_ENABLED(CONFIG_PPC_8xx));
-
-			hugetlb_free_pte_range(tlb, pmd, addr, end, floor, ceiling);
-
-			continue;
-		}
-		/*
-		 * Increment next by the size of the huge mapping since
-		 * there may be more than one entry at this level for a
-		 * single hugepage, but all of them point to
-		 * the same kmem cache that holds the hugepte.
-		 */
-		more = addr + (1UL << hugepd_shift(*(hugepd_t *)pmd));
-		if (more > next)
-			next = more;
-
-		free_hugepd_range(tlb, (hugepd_t *)pmd, PMD_SHIFT,
-				  addr, next, floor, ceiling);
-	} while (addr = next, addr != end);
-
-	if (range_is_outside_limits(start, end, floor, ceiling, PUD_MASK))
-		return;
-
-	pmd = pmd_offset(pud, start & PUD_MASK);
-	pud_clear(pud);
-	pmd_free_tlb(tlb, pmd, start & PUD_MASK);
-	mm_dec_nr_pmds(tlb->mm);
-}
-
-static void hugetlb_free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
-				   unsigned long addr, unsigned long end,
-				   unsigned long floor, unsigned long ceiling)
-{
-	pud_t *pud;
-	unsigned long next;
-	unsigned long start;
-
-	start = addr;
-	do {
-		pud = pud_offset(p4d, addr);
-		next = pud_addr_end(addr, end);
-		if (!is_hugepd(__hugepd(pud_val(*pud)))) {
-			if (pud_none_or_clear_bad(pud))
-				continue;
-			hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
-					       ceiling);
-		} else {
-			unsigned long more;
-			/*
-			 * Increment next by the size of the huge mapping since
-			 * there may be more than one entry at this level for a
-			 * single hugepage, but all of them point to
-			 * the same kmem cache that holds the hugepte.
-			 */
-			more = addr + (1UL << hugepd_shift(*(hugepd_t *)pud));
-			if (more > next)
-				next = more;
-
-			free_hugepd_range(tlb, (hugepd_t *)pud, PUD_SHIFT,
-					  addr, next, floor, ceiling);
-		}
-	} while (addr = next, addr != end);
-
-	if (range_is_outside_limits(start, end, floor, ceiling, PGDIR_MASK))
-		return;
-
-	pud = pud_offset(p4d, start & PGDIR_MASK);
-	p4d_clear(p4d);
-	pud_free_tlb(tlb, pud, start & PGDIR_MASK);
-	mm_dec_nr_puds(tlb->mm);
-}
-
-/*
- * This function frees user-level page tables of a process.
- */
-void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-			    unsigned long addr, unsigned long end,
-			    unsigned long floor, unsigned long ceiling)
-{
-	pgd_t *pgd;
-	p4d_t *p4d;
-	unsigned long next;
-
-	/*
-	 * Because there are a number of different possible pagetable
-	 * layouts for hugepage ranges, we limit knowledge of how
-	 * things should be laid out to the allocation path
-	 * (huge_pte_alloc(), above).  Everything else works out the
-	 * structure as it goes from information in the hugepd
-	 * pointers.  That means that we can't here use the
-	 * optimization used in the normal page free_pgd_range(), of
-	 * checking whether we're actually covering a large enough
-	 * range to have to do anything at the top level of the walk
-	 * instead of at the bottom.
-	 *
-	 * To make sense of this, you should probably go read the big
-	 * block comment at the top of the normal free_pgd_range(),
-	 * too.
-	 */
-
-	do {
-		next = pgd_addr_end(addr, end);
-		pgd = pgd_offset(tlb->mm, addr);
-		p4d = p4d_offset(pgd, addr);
-		if (!is_hugepd(__hugepd(pgd_val(*pgd)))) {
-			if (p4d_none_or_clear_bad(p4d))
-				continue;
-			hugetlb_free_pud_range(tlb, p4d, addr, next, floor, ceiling);
-		} else {
-			unsigned long more;
-			/*
-			 * Increment next by the size of the huge mapping since
-			 * there may be more than one entry at the pgd level
-			 * for a single hugepage, but all of them point to the
-			 * same kmem cache that holds the hugepte.
-			 */
-			more = addr + (1UL << hugepd_shift(*(hugepd_t *)pgd));
-			if (more > next)
-				next = more;
-
-			free_hugepd_range(tlb, (hugepd_t *)p4d, PGDIR_SHIFT,
-					  addr, next, floor, ceiling);
-		}
-	} while (addr = next, addr != end);
-}
-
 bool __init arch_hugetlb_valid_size(unsigned long size)
 {
 	int shift = __ffs(size);
@@ -552,44 +179,14 @@ static int __init hugetlbpage_init(void)
 
 	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
 		unsigned shift;
-		unsigned pdshift;
 
 		if (!mmu_psize_defs[psize].shift)
 			continue;
 
 		shift = mmu_psize_to_shift(psize);
 
-#ifdef CONFIG_PPC_BOOK3S_64
-		if (shift > PGDIR_SHIFT)
-			continue;
-		else if (shift > PUD_SHIFT)
-			pdshift = PGDIR_SHIFT;
-		else if (shift > PMD_SHIFT)
-			pdshift = PUD_SHIFT;
-		else
-			pdshift = PMD_SHIFT;
-#else
-		if (shift < PUD_SHIFT)
-			pdshift = PMD_SHIFT;
-		else if (shift < PGDIR_SHIFT)
-			pdshift = PUD_SHIFT;
-		else
-			pdshift = PGDIR_SHIFT;
-#endif
-
 		if (add_huge_page_size(1ULL << shift) < 0)
 			continue;
-		/*
-		 * if we have pdshift and shift value same, we don't
-		 * 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(PTE_T_ORDER);
-		}
 
 		configured = true;
 	}
diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
index 21131b96d209..9b4a675eb8f8 100644
--- a/arch/powerpc/mm/init-common.c
+++ b/arch/powerpc/mm/init-common.c
@@ -123,12 +123,8 @@ void pgtable_cache_add(unsigned int shift)
 	/* When batching pgtable pointers for RCU freeing, we store
 	 * the index size in the low bits.  Table alignment must be
 	 * big enough to fit it.
-	 *
-	 * Likewise, hugeapge pagetable pointers contain a (different)
-	 * shift value in the low bits.  All tables must be aligned so
-	 * as to leave enough 0 bits in the address to contain it. */
-	unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
-				     HUGEPD_SHIFT_MASK + 1);
+	 */
+	unsigned long minalign = MAX_PGTABLE_INDEX_SIZE + 1;
 	struct kmem_cache *new = NULL;
 
 	/* It would be nice if this was a BUILD_BUG_ON(), but at the
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 43d4842bb1c7..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)
 {
@@ -75,26 +62,36 @@ 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)), psize);
+			pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)),
+			1UL << mmu_psize_to_shift(psize));
 
 	return 0;
 }
diff --git a/arch/powerpc/mm/nohash/Makefile b/arch/powerpc/mm/nohash/Makefile
index 86d0fe434824..cf60c776c883 100644
--- a/arch/powerpc/mm/nohash/Makefile
+++ b/arch/powerpc/mm/nohash/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 obj-y				+= mmu_context.o tlb.o tlb_low.o kup.o
-obj-$(CONFIG_PPC_BOOK3E_64)  	+= tlb_low_64e.o book3e_pgtable.o
+obj-$(CONFIG_PPC_BOOK3E_64)  	+= tlb_64e.o tlb_low_64e.o book3e_pgtable.o
 obj-$(CONFIG_44x)		+= 44x.o
 obj-$(CONFIG_PPC_8xx)		+= 8xx.o
 obj-$(CONFIG_PPC_E500)		+= e500.o
diff --git a/arch/powerpc/mm/nohash/book3e_pgtable.c b/arch/powerpc/mm/nohash/book3e_pgtable.c
index 1c5e4ecbebeb..ad2a7c26f2a0 100644
--- a/arch/powerpc/mm/nohash/book3e_pgtable.c
+++ b/arch/powerpc/mm/nohash/book3e_pgtable.c
@@ -29,10 +29,10 @@ int __meminit vmemmap_create_mapping(unsigned long start,
 		_PAGE_KERNEL_RW;
 
 	/* PTEs only contain page size encodings up to 32M */
-	BUG_ON(mmu_psize_defs[mmu_vmemmap_psize].enc > 0xf);
+	BUG_ON(mmu_psize_defs[mmu_vmemmap_psize].shift - 10 > 0xf);
 
 	/* Encode the size in the PTE */
-	flags |= mmu_psize_defs[mmu_vmemmap_psize].enc << 8;
+	flags |= (mmu_psize_defs[mmu_vmemmap_psize].shift - 10) << 8;
 
 	/* For each PTE for that area, map things. Note that we don't
 	 * increment phys because all PTEs are of the large size and
diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c
index 5ffa0af4328a..b653a7be4cb1 100644
--- a/arch/powerpc/mm/nohash/tlb.c
+++ b/arch/powerpc/mm/nohash/tlb.c
@@ -53,37 +53,30 @@
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
 	[MMU_PAGE_4K] = {
 		.shift	= 12,
-		.enc	= BOOK3E_PAGESZ_4K,
 	},
 	[MMU_PAGE_2M] = {
 		.shift	= 21,
-		.enc	= BOOK3E_PAGESZ_2M,
 	},
 	[MMU_PAGE_4M] = {
 		.shift	= 22,
-		.enc	= BOOK3E_PAGESZ_4M,
 	},
 	[MMU_PAGE_16M] = {
 		.shift	= 24,
-		.enc	= BOOK3E_PAGESZ_16M,
 	},
 	[MMU_PAGE_64M] = {
 		.shift	= 26,
-		.enc	= BOOK3E_PAGESZ_64M,
 	},
 	[MMU_PAGE_256M] = {
 		.shift	= 28,
-		.enc	= BOOK3E_PAGESZ_256M,
 	},
 	[MMU_PAGE_1G] = {
 		.shift	= 30,
-		.enc	= BOOK3E_PAGESZ_1GB,
 	},
 };
 
 static inline int mmu_get_tsize(int psize)
 {
-	return mmu_psize_defs[psize].enc;
+	return mmu_psize_defs[psize].shift - 10;
 }
 #else
 static inline int mmu_get_tsize(int psize)
@@ -110,28 +103,6 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
 };
 #endif
 
-/* The variables below are currently only used on 64-bit Book3E
- * though this will probably be made common with other nohash
- * implementations at some point
- */
-#ifdef CONFIG_PPC64
-
-int mmu_pte_psize;		/* Page size used for PTE pages */
-int mmu_vmemmap_psize;		/* Page size used for the virtual mem map */
-int book3e_htw_mode;		/* HW tablewalk?  Value is PPC_HTW_* */
-unsigned long linear_map_top;	/* Top of linear mapping */
-
-
-/*
- * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug
- * exceptions.  This is used for bolted and e6500 TLB miss handlers which
- * do not modify this SPRG in the TLB miss code; for other TLB miss handlers,
- * this is set to zero.
- */
-int extlb_level_exc;
-
-#endif /* CONFIG_PPC64 */
-
 #ifdef CONFIG_PPC_E500
 /* next_tlbcam_idx is used to round-robin tlbcam entry assignment */
 DEFINE_PER_CPU(int, next_tlbcam_idx);
@@ -358,381 +329,7 @@ void tlb_flush(struct mmu_gather *tlb)
 	flush_tlb_mm(tlb->mm);
 }
 
-/*
- * Below are functions specific to the 64-bit variant of Book3E though that
- * may change in the future
- */
-
-#ifdef CONFIG_PPC64
-
-/*
- * Handling of virtual linear page tables or indirect TLB entries
- * flushing when PTE pages are freed
- */
-void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address)
-{
-	int tsize = mmu_psize_defs[mmu_pte_psize].enc;
-
-	if (book3e_htw_mode != PPC_HTW_NONE) {
-		unsigned long start = address & PMD_MASK;
-		unsigned long end = address + PMD_SIZE;
-		unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift;
-
-		/* This isn't the most optimal, ideally we would factor out the
-		 * while preempt & CPU mask mucking around, or even the IPI but
-		 * it will do for now
-		 */
-		while (start < end) {
-			__flush_tlb_page(tlb->mm, start, tsize, 1);
-			start += size;
-		}
-	} else {
-		unsigned long rmask = 0xf000000000000000ul;
-		unsigned long rid = (address & rmask) | 0x1000000000000000ul;
-		unsigned long vpte = address & ~rmask;
-
-		vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful;
-		vpte |= rid;
-		__flush_tlb_page(tlb->mm, vpte, tsize, 0);
-	}
-}
-
-static void __init setup_page_sizes(void)
-{
-	unsigned int tlb0cfg;
-	unsigned int tlb0ps;
-	unsigned int eptcfg;
-	int i, psize;
-
-#ifdef CONFIG_PPC_E500
-	unsigned int mmucfg = mfspr(SPRN_MMUCFG);
-	int fsl_mmu = mmu_has_feature(MMU_FTR_TYPE_FSL_E);
-
-	if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) {
-		unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG);
-		unsigned int min_pg, max_pg;
-
-		min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT;
-		max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT;
-
-		for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
-			struct mmu_psize_def *def;
-			unsigned int shift;
-
-			def = &mmu_psize_defs[psize];
-			shift = def->shift;
-
-			if (shift == 0 || shift & 1)
-				continue;
-
-			/* adjust to be in terms of 4^shift Kb */
-			shift = (shift - 10) >> 1;
-
-			if ((shift >= min_pg) && (shift <= max_pg))
-				def->flags |= MMU_PAGE_SIZE_DIRECT;
-		}
-
-		goto out;
-	}
-
-	if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) {
-		u32 tlb1cfg, tlb1ps;
-
-		tlb0cfg = mfspr(SPRN_TLB0CFG);
-		tlb1cfg = mfspr(SPRN_TLB1CFG);
-		tlb1ps = mfspr(SPRN_TLB1PS);
-		eptcfg = mfspr(SPRN_EPTCFG);
-
-		if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT))
-			book3e_htw_mode = PPC_HTW_E6500;
-
-		/*
-		 * We expect 4K subpage size and unrestricted indirect size.
-		 * The lack of a restriction on indirect size is a Freescale
-		 * extension, indicated by PSn = 0 but SPSn != 0.
-		 */
-		if (eptcfg != 2)
-			book3e_htw_mode = PPC_HTW_NONE;
-
-		for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
-			struct mmu_psize_def *def = &mmu_psize_defs[psize];
-
-			if (!def->shift)
-				continue;
-
-			if (tlb1ps & (1U << (def->shift - 10))) {
-				def->flags |= MMU_PAGE_SIZE_DIRECT;
-
-				if (book3e_htw_mode && psize == MMU_PAGE_2M)
-					def->flags |= MMU_PAGE_SIZE_INDIRECT;
-			}
-		}
-
-		goto out;
-	}
-#endif
-
-	tlb0cfg = mfspr(SPRN_TLB0CFG);
-	tlb0ps = mfspr(SPRN_TLB0PS);
-	eptcfg = mfspr(SPRN_EPTCFG);
-
-	/* Look for supported direct sizes */
-	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
-		struct mmu_psize_def *def = &mmu_psize_defs[psize];
-
-		if (tlb0ps & (1U << (def->shift - 10)))
-			def->flags |= MMU_PAGE_SIZE_DIRECT;
-	}
-
-	/* Indirect page sizes supported ? */
-	if ((tlb0cfg & TLBnCFG_IND) == 0 ||
-	    (tlb0cfg & TLBnCFG_PT) == 0)
-		goto out;
-
-	book3e_htw_mode = PPC_HTW_IBM;
-
-	/* Now, we only deal with one IND page size for each
-	 * direct size. Hopefully all implementations today are
-	 * unambiguous, but we might want to be careful in the
-	 * future.
-	 */
-	for (i = 0; i < 3; i++) {
-		unsigned int ps, sps;
-
-		sps = eptcfg & 0x1f;
-		eptcfg >>= 5;
-		ps = eptcfg & 0x1f;
-		eptcfg >>= 5;
-		if (!ps || !sps)
-			continue;
-		for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
-			struct mmu_psize_def *def = &mmu_psize_defs[psize];
-
-			if (ps == (def->shift - 10))
-				def->flags |= MMU_PAGE_SIZE_INDIRECT;
-			if (sps == (def->shift - 10))
-				def->ind = ps + 10;
-		}
-	}
-
-out:
-	/* Cleanup array and print summary */
-	pr_info("MMU: Supported page sizes\n");
-	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
-		struct mmu_psize_def *def = &mmu_psize_defs[psize];
-		const char *__page_type_names[] = {
-			"unsupported",
-			"direct",
-			"indirect",
-			"direct & indirect"
-		};
-		if (def->flags == 0) {
-			def->shift = 0;	
-			continue;
-		}
-		pr_info("  %8ld KB as %s\n", 1ul << (def->shift - 10),
-			__page_type_names[def->flags & 0x3]);
-	}
-}
-
-static void __init setup_mmu_htw(void)
-{
-	/*
-	 * If we want to use HW tablewalk, enable it by patching the TLB miss
-	 * handlers to branch to the one dedicated to it.
-	 */
-
-	switch (book3e_htw_mode) {
-	case PPC_HTW_IBM:
-		patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e);
-		patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e);
-		break;
-#ifdef CONFIG_PPC_E500
-	case PPC_HTW_E6500:
-		extlb_level_exc = EX_TLB_SIZE;
-		patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e);
-		patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e);
-		break;
-#endif
-	}
-	pr_info("MMU: Book3E HW tablewalk %s\n",
-		book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported");
-}
-
-/*
- * Early initialization of the MMU TLB code
- */
-static void early_init_this_mmu(void)
-{
-	unsigned int mas4;
-
-	/* Set MAS4 based on page table setting */
-
-	mas4 = 0x4 << MAS4_WIMGED_SHIFT;
-	switch (book3e_htw_mode) {
-	case PPC_HTW_E6500:
-		mas4 |= MAS4_INDD;
-		mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT;
-		mas4 |= MAS4_TLBSELD(1);
-		mmu_pte_psize = MMU_PAGE_2M;
-		break;
-
-	case PPC_HTW_IBM:
-		mas4 |= MAS4_INDD;
-		mas4 |=	BOOK3E_PAGESZ_1M << MAS4_TSIZED_SHIFT;
-		mmu_pte_psize = MMU_PAGE_1M;
-		break;
-
-	case PPC_HTW_NONE:
-		mas4 |=	BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT;
-		mmu_pte_psize = mmu_virtual_psize;
-		break;
-	}
-	mtspr(SPRN_MAS4, mas4);
-
-#ifdef CONFIG_PPC_E500
-	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
-		unsigned int num_cams;
-		bool map = true;
-
-		/* use a quarter of the TLBCAM for bolted linear map */
-		num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
-
-		/*
-		 * Only do the mapping once per core, or else the
-		 * transient mapping would cause problems.
-		 */
-#ifdef CONFIG_SMP
-		if (hweight32(get_tensr()) > 1)
-			map = false;
-#endif
-
-		if (map)
-			linear_map_top = map_mem_in_cams(linear_map_top,
-							 num_cams, false, true);
-	}
-#endif
-
-	/* A sync won't hurt us after mucking around with
-	 * the MMU configuration
-	 */
-	mb();
-}
-
-static void __init early_init_mmu_global(void)
-{
-	/* XXX This should be decided at runtime based on supported
-	 * page sizes in the TLB, but for now let's assume 16M is
-	 * always there and a good fit (which it probably is)
-	 *
-	 * Freescale booke only supports 4K pages in TLB0, so use that.
-	 */
-	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E))
-		mmu_vmemmap_psize = MMU_PAGE_4K;
-	else
-		mmu_vmemmap_psize = MMU_PAGE_16M;
-
-	/* XXX This code only checks for TLB 0 capabilities and doesn't
-	 *     check what page size combos are supported by the HW. It
-	 *     also doesn't handle the case where a separate array holds
-	 *     the IND entries from the array loaded by the PT.
-	 */
-	/* Look for supported page sizes */
-	setup_page_sizes();
-
-	/* Look for HW tablewalk support */
-	setup_mmu_htw();
-
-#ifdef CONFIG_PPC_E500
-	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
-		if (book3e_htw_mode == PPC_HTW_NONE) {
-			extlb_level_exc = EX_TLB_SIZE;
-			patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e);
-			patch_exception(0x1e0,
-				exc_instruction_tlb_miss_bolted_book3e);
-		}
-	}
-#endif
-
-	/* Set the global containing the top of the linear mapping
-	 * for use by the TLB miss code
-	 */
-	linear_map_top = memblock_end_of_DRAM();
-
-	ioremap_bot = IOREMAP_BASE;
-}
-
-static void __init early_mmu_set_memory_limit(void)
-{
-#ifdef CONFIG_PPC_E500
-	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
-		/*
-		 * Limit memory so we dont have linear faults.
-		 * Unlike memblock_set_current_limit, which limits
-		 * memory available during early boot, this permanently
-		 * reduces the memory available to Linux.  We need to
-		 * do this because highmem is not supported on 64-bit.
-		 */
-		memblock_enforce_memory_limit(linear_map_top);
-	}
-#endif
-
-	memblock_set_current_limit(linear_map_top);
-}
-
-/* boot cpu only */
-void __init early_init_mmu(void)
-{
-	early_init_mmu_global();
-	early_init_this_mmu();
-	early_mmu_set_memory_limit();
-}
-
-void early_init_mmu_secondary(void)
-{
-	early_init_this_mmu();
-}
-
-void setup_initial_memory_limit(phys_addr_t first_memblock_base,
-				phys_addr_t first_memblock_size)
-{
-	/* On non-FSL Embedded 64-bit, we adjust the RMA size to match
-	 * the bolted TLB entry. We know for now that only 1G
-	 * entries are supported though that may eventually
-	 * change.
-	 *
-	 * on FSL Embedded 64-bit, usually all RAM is bolted, but with
-	 * unusual memory sizes it's possible for some RAM to not be mapped
-	 * (such RAM is not used at all by Linux, since we don't support
-	 * highmem on 64-bit).  We limit ppc64_rma_size to what would be
-	 * mappable if this memblock is the only one.  Additional memblocks
-	 * can only increase, not decrease, the amount that ends up getting
-	 * mapped.  We still limit max to 1G even if we'll eventually map
-	 * more.  This is due to what the early init code is set up to do.
-	 *
-	 * We crop it to the size of the first MEMBLOCK to
-	 * avoid going over total available memory just in case...
-	 */
-#ifdef CONFIG_PPC_E500
-	if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
-		unsigned long linear_sz;
-		unsigned int num_cams;
-
-		/* use a quarter of the TLBCAM for bolted linear map */
-		num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
-
-		linear_sz = map_mem_in_cams(first_memblock_size, num_cams,
-					    true, true);
-
-		ppc64_rma_size = min_t(u64, linear_sz, 0x40000000);
-	} else
-#endif
-		ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
-
-	/* Finally limit subsequent allocations */
-	memblock_set_current_limit(first_memblock_base + ppc64_rma_size);
-}
-#else /* ! CONFIG_PPC64 */
+#ifndef CONFIG_PPC64
 void __init early_init_mmu(void)
 {
 	unsigned long root = of_get_flat_dt_root();
diff --git a/arch/powerpc/mm/nohash/tlb_64e.c b/arch/powerpc/mm/nohash/tlb_64e.c
new file mode 100644
index 000000000000..113edf76d3ce
--- /dev/null
+++ b/arch/powerpc/mm/nohash/tlb_64e.c
@@ -0,0 +1,314 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2008,2009 Ben Herrenschmidt <benh@kernel.crashing.org>
+ *                     IBM Corp.
+ *
+ *  Derived from arch/ppc/mm/init.c:
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ *    Copyright (C) 1996 Paul Mackerras
+ *
+ *  Derived from "arch/i386/mm/init.c"
+ *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/memblock.h>
+
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+#include <asm/code-patching.h>
+#include <asm/cputhreads.h>
+
+#include <mm/mmu_decl.h>
+
+/* The variables below are currently only used on 64-bit Book3E
+ * though this will probably be made common with other nohash
+ * implementations at some point
+ */
+int mmu_pte_psize;		/* Page size used for PTE pages */
+int mmu_vmemmap_psize;		/* Page size used for the virtual mem map */
+int book3e_htw_mode;		/* HW tablewalk?  Value is PPC_HTW_* */
+unsigned long linear_map_top;	/* Top of linear mapping */
+
+
+/*
+ * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug
+ * exceptions.  This is used for bolted and e6500 TLB miss handlers which
+ * do not modify this SPRG in the TLB miss code; for other TLB miss handlers,
+ * this is set to zero.
+ */
+int extlb_level_exc;
+
+/*
+ * Handling of virtual linear page tables or indirect TLB entries
+ * flushing when PTE pages are freed
+ */
+void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address)
+{
+	int tsize = mmu_psize_defs[mmu_pte_psize].shift - 10;
+
+	if (book3e_htw_mode != PPC_HTW_NONE) {
+		unsigned long start = address & PMD_MASK;
+		unsigned long end = address + PMD_SIZE;
+		unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift;
+
+		/* This isn't the most optimal, ideally we would factor out the
+		 * while preempt & CPU mask mucking around, or even the IPI but
+		 * it will do for now
+		 */
+		while (start < end) {
+			__flush_tlb_page(tlb->mm, start, tsize, 1);
+			start += size;
+		}
+	} else {
+		unsigned long rmask = 0xf000000000000000ul;
+		unsigned long rid = (address & rmask) | 0x1000000000000000ul;
+		unsigned long vpte = address & ~rmask;
+
+		vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful;
+		vpte |= rid;
+		__flush_tlb_page(tlb->mm, vpte, tsize, 0);
+	}
+}
+
+static void __init setup_page_sizes(void)
+{
+	unsigned int tlb0cfg;
+	unsigned int eptcfg;
+	int psize;
+
+	unsigned int mmucfg = mfspr(SPRN_MMUCFG);
+
+	if ((mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) {
+		unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG);
+		unsigned int min_pg, max_pg;
+
+		min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT;
+		max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT;
+
+		for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+			struct mmu_psize_def *def;
+			unsigned int shift;
+
+			def = &mmu_psize_defs[psize];
+			shift = def->shift;
+
+			if (shift == 0 || shift & 1)
+				continue;
+
+			/* adjust to be in terms of 4^shift Kb */
+			shift = (shift - 10) >> 1;
+
+			if ((shift >= min_pg) && (shift <= max_pg))
+				def->flags |= MMU_PAGE_SIZE_DIRECT;
+		}
+
+		goto out;
+	}
+
+	if ((mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) {
+		u32 tlb1cfg, tlb1ps;
+
+		tlb0cfg = mfspr(SPRN_TLB0CFG);
+		tlb1cfg = mfspr(SPRN_TLB1CFG);
+		tlb1ps = mfspr(SPRN_TLB1PS);
+		eptcfg = mfspr(SPRN_EPTCFG);
+
+		if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT))
+			book3e_htw_mode = PPC_HTW_E6500;
+
+		/*
+		 * We expect 4K subpage size and unrestricted indirect size.
+		 * The lack of a restriction on indirect size is a Freescale
+		 * extension, indicated by PSn = 0 but SPSn != 0.
+		 */
+		if (eptcfg != 2)
+			book3e_htw_mode = PPC_HTW_NONE;
+
+		for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+			struct mmu_psize_def *def = &mmu_psize_defs[psize];
+
+			if (!def->shift)
+				continue;
+
+			if (tlb1ps & (1U << (def->shift - 10))) {
+				def->flags |= MMU_PAGE_SIZE_DIRECT;
+
+				if (book3e_htw_mode && psize == MMU_PAGE_2M)
+					def->flags |= MMU_PAGE_SIZE_INDIRECT;
+			}
+		}
+
+		goto out;
+	}
+out:
+	/* Cleanup array and print summary */
+	pr_info("MMU: Supported page sizes\n");
+	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+		struct mmu_psize_def *def = &mmu_psize_defs[psize];
+		const char *__page_type_names[] = {
+			"unsupported",
+			"direct",
+			"indirect",
+			"direct & indirect"
+		};
+		if (def->flags == 0) {
+			def->shift = 0;
+			continue;
+		}
+		pr_info("  %8ld KB as %s\n", 1ul << (def->shift - 10),
+			__page_type_names[def->flags & 0x3]);
+	}
+}
+
+/*
+ * Early initialization of the MMU TLB code
+ */
+static void early_init_this_mmu(void)
+{
+	unsigned int mas4;
+
+	/* Set MAS4 based on page table setting */
+
+	mas4 = 0x4 << MAS4_WIMGED_SHIFT;
+	switch (book3e_htw_mode) {
+	case PPC_HTW_E6500:
+		mas4 |= MAS4_INDD;
+		mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT;
+		mas4 |= MAS4_TLBSELD(1);
+		mmu_pte_psize = MMU_PAGE_2M;
+		break;
+
+	case PPC_HTW_NONE:
+		mas4 |=	BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT;
+		mmu_pte_psize = mmu_virtual_psize;
+		break;
+	}
+	mtspr(SPRN_MAS4, mas4);
+
+	unsigned int num_cams;
+	bool map = true;
+
+	/* use a quarter of the TLBCAM for bolted linear map */
+	num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
+
+	/*
+	 * Only do the mapping once per core, or else the
+	 * transient mapping would cause problems.
+	 */
+#ifdef CONFIG_SMP
+	if (hweight32(get_tensr()) > 1)
+		map = false;
+#endif
+
+	if (map)
+		linear_map_top = map_mem_in_cams(linear_map_top,
+						 num_cams, false, true);
+
+	/* A sync won't hurt us after mucking around with
+	 * the MMU configuration
+	 */
+	mb();
+}
+
+static void __init early_init_mmu_global(void)
+{
+	/*
+	 * Freescale booke only supports 4K pages in TLB0, so use that.
+	 */
+	mmu_vmemmap_psize = MMU_PAGE_4K;
+
+	/* XXX This code only checks for TLB 0 capabilities and doesn't
+	 *     check what page size combos are supported by the HW. It
+	 *     also doesn't handle the case where a separate array holds
+	 *     the IND entries from the array loaded by the PT.
+	 */
+	/* Look for supported page sizes */
+	setup_page_sizes();
+
+	/*
+	 * If we want to use HW tablewalk, enable it by patching the TLB miss
+	 * handlers to branch to the one dedicated to it.
+	 */
+	extlb_level_exc = EX_TLB_SIZE;
+	switch (book3e_htw_mode) {
+	case PPC_HTW_E6500:
+		patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e);
+		patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e);
+		break;
+	}
+
+	pr_info("MMU: Book3E HW tablewalk %s\n",
+		book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported");
+
+	/* Set the global containing the top of the linear mapping
+	 * for use by the TLB miss code
+	 */
+	linear_map_top = memblock_end_of_DRAM();
+
+	ioremap_bot = IOREMAP_BASE;
+}
+
+static void __init early_mmu_set_memory_limit(void)
+{
+	/*
+	 * Limit memory so we dont have linear faults.
+	 * Unlike memblock_set_current_limit, which limits
+	 * memory available during early boot, this permanently
+	 * reduces the memory available to Linux.  We need to
+	 * do this because highmem is not supported on 64-bit.
+	 */
+	memblock_enforce_memory_limit(linear_map_top);
+
+	memblock_set_current_limit(linear_map_top);
+}
+
+/* boot cpu only */
+void __init early_init_mmu(void)
+{
+	early_init_mmu_global();
+	early_init_this_mmu();
+	early_mmu_set_memory_limit();
+}
+
+void early_init_mmu_secondary(void)
+{
+	early_init_this_mmu();
+}
+
+void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+				phys_addr_t first_memblock_size)
+{
+	/*
+	 * On FSL Embedded 64-bit, usually all RAM is bolted, but with
+	 * unusual memory sizes it's possible for some RAM to not be mapped
+	 * (such RAM is not used at all by Linux, since we don't support
+	 * highmem on 64-bit).  We limit ppc64_rma_size to what would be
+	 * mappable if this memblock is the only one.  Additional memblocks
+	 * can only increase, not decrease, the amount that ends up getting
+	 * mapped.  We still limit max to 1G even if we'll eventually map
+	 * more.  This is due to what the early init code is set up to do.
+	 *
+	 * We crop it to the size of the first MEMBLOCK to
+	 * avoid going over total available memory just in case...
+	 */
+	unsigned long linear_sz;
+	unsigned int num_cams;
+
+	/* use a quarter of the TLBCAM for bolted linear map */
+	num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
+
+	linear_sz = map_mem_in_cams(first_memblock_size, num_cams, true, true);
+	ppc64_rma_size = min_t(u64, linear_sz, 0x40000000);
+
+	/* Finally limit subsequent allocations */
+	memblock_set_current_limit(first_memblock_base + ppc64_rma_size);
+}
diff --git a/arch/powerpc/mm/nohash/tlb_low_64e.S b/arch/powerpc/mm/nohash/tlb_low_64e.S
index 7e0b8fe1c279..de568297d5c5 100644
--- a/arch/powerpc/mm/nohash/tlb_low_64e.S
+++ b/arch/powerpc/mm/nohash/tlb_low_64e.S
@@ -450,11 +450,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SMT)
 
 tlb_miss_huge_e6500:
 	beq	tlb_miss_fault_e6500
-	li	r10,1
-	andi.	r15,r14,HUGEPD_SHIFT_MASK@l /* r15 = psize */
-	rldimi	r14,r10,63,0		/* Set PD_HUGE */
-	xor	r14,r14,r15		/* Clear size bits */
-	ldx	r14,0,r14
+	rlwinm	r15,r14,32-_PAGE_PSIZE_SHIFT,0x1e
 
 	/*
 	 * Now we build the MAS for a huge page.
@@ -465,7 +461,6 @@ tlb_miss_huge_e6500:
 	 * MAS 2,3+7:	Needs to be redone similar to non-tablewalk handler
 	 */
 
-	subi	r15,r15,10		/* Convert psize to tsize */
 	mfspr	r10,SPRN_MAS1
 	rlwinm	r10,r10,0,~MAS1_IND
 	rlwimi	r10,r15,MAS1_TSIZE_SHIFT,MAS1_TSIZE_MASK
@@ -511,232 +506,6 @@ itlb_miss_fault_e6500:
 	tlb_epilog_bolted
 	b	exc_instruction_storage_book3e
 
-/**********************************************************************
- *                                                                    *
- * TLB miss handling for Book3E with TLB reservation and HES support  *
- *                                                                    *
- **********************************************************************/
-
-
-/* Data TLB miss */
-	START_EXCEPTION(data_tlb_miss)
-	TLB_MISS_PROLOG
-
-	/* Now we handle the fault proper. We only save DEAR in normal
-	 * fault case since that's the only interesting values here.
-	 * We could probably also optimize by not saving SRR0/1 in the
-	 * linear mapping case but I'll leave that for later
-	 */
-	mfspr	r14,SPRN_ESR
-	mfspr	r16,SPRN_DEAR		/* get faulting address */
-	srdi	r15,r16,44		/* get region */
-	xoris	r15,r15,0xc
-	cmpldi	cr0,r15,0		/* linear mapping ? */
-	beq	tlb_load_linear		/* yes -> go to linear map load */
-	cmpldi	cr1,r15,1		/* vmalloc mapping ? */
-
-	/* The page tables are mapped virtually linear. At this point, though,
-	 * we don't know whether we are trying to fault in a first level
-	 * virtual address or a virtual page table address. We can get that
-	 * from bit 0x1 of the region ID which we have set for a page table
-	 */
-	andis.	r10,r15,0x1
-	bne-	virt_page_table_tlb_miss
-
-	std	r14,EX_TLB_ESR(r12);	/* save ESR */
-	std	r16,EX_TLB_DEAR(r12);	/* save DEAR */
-
-	 /* We need _PAGE_PRESENT and  _PAGE_ACCESSED set */
-	li	r11,_PAGE_PRESENT
-	oris	r11,r11,_PAGE_ACCESSED@h
-
-	/* We do the user/kernel test for the PID here along with the RW test
-	 */
-	srdi.	r15,r16,60		/* Check for user region */
-
-	/* We pre-test some combination of permissions to avoid double
-	 * faults:
-	 *
-	 * We move the ESR:ST bit into the position of _PAGE_BAP_SW in the PTE
-	 * ESR_ST   is 0x00800000
-	 * _PAGE_BAP_SW is 0x00000010
-	 * So the shift is >> 19. This tests for supervisor writeability.
-	 * If the page happens to be supervisor writeable and not user
-	 * writeable, we will take a new fault later, but that should be
-	 * a rare enough case.
-	 *
-	 * We also move ESR_ST in _PAGE_DIRTY position
-	 * _PAGE_DIRTY is 0x00001000 so the shift is >> 11
-	 *
-	 * MAS1 is preset for all we need except for TID that needs to
-	 * be cleared for kernel translations
-	 */
-	rlwimi	r11,r14,32-19,27,27
-	rlwimi	r11,r14,32-16,19,19
-	beq	normal_tlb_miss_user
-	/* XXX replace the RMW cycles with immediate loads + writes */
-1:	mfspr	r10,SPRN_MAS1
-	rlwinm	r10,r10,0,16,1		/* Clear TID */
-	mtspr	SPRN_MAS1,r10
-	beq+	cr1,normal_tlb_miss
-
-	/* We got a crappy address, just fault with whatever DEAR and ESR
-	 * are here
-	 */
-	TLB_MISS_EPILOG_ERROR
-	b	exc_data_storage_book3e
-
-/* Instruction TLB miss */
-	START_EXCEPTION(instruction_tlb_miss)
-	TLB_MISS_PROLOG
-
-	/* If we take a recursive fault, the second level handler may need
-	 * to know whether we are handling a data or instruction fault in
-	 * order to get to the right store fault handler. We provide that
-	 * info by writing a crazy value in ESR in our exception frame
-	 */
-	li	r14,-1	/* store to exception frame is done later */
-
-	/* Now we handle the fault proper. We only save DEAR in the non
-	 * linear mapping case since we know the linear mapping case will
-	 * not re-enter. We could indeed optimize and also not save SRR0/1
-	 * in the linear mapping case but I'll leave that for later
-	 *
-	 * Faulting address is SRR0 which is already in r16
-	 */
-	srdi	r15,r16,44		/* get region */
-	xoris	r15,r15,0xc
-	cmpldi	cr0,r15,0		/* linear mapping ? */
-	beq	tlb_load_linear		/* yes -> go to linear map load */
-	cmpldi	cr1,r15,1		/* vmalloc mapping ? */
-
-	/* We do the user/kernel test for the PID here along with the RW test
-	 */
-	li	r11,_PAGE_PRESENT|_PAGE_BAP_UX	/* Base perm */
-	oris	r11,r11,_PAGE_ACCESSED@h
-
-	srdi.	r15,r16,60			/* Check for user region */
-	std	r14,EX_TLB_ESR(r12)		/* write crazy -1 to frame */
-	beq	normal_tlb_miss_user
-
-	li	r11,_PAGE_PRESENT|_PAGE_BAP_SX	/* Base perm */
-	oris	r11,r11,_PAGE_ACCESSED@h
-	/* XXX replace the RMW cycles with immediate loads + writes */
-	mfspr	r10,SPRN_MAS1
-	rlwinm	r10,r10,0,16,1			/* Clear TID */
-	mtspr	SPRN_MAS1,r10
-	beq+	cr1,normal_tlb_miss
-
-	/* We got a crappy address, just fault */
-	TLB_MISS_EPILOG_ERROR
-	b	exc_instruction_storage_book3e
-
-/*
- * This is the guts of the first-level TLB miss handler for direct
- * misses. We are entered with:
- *
- * r16 = faulting address
- * r15 = region ID
- * r14 = crap (free to use)
- * r13 = PACA
- * r12 = TLB exception frame in PACA
- * r11 = PTE permission mask
- * r10 = crap (free to use)
- */
-normal_tlb_miss_user:
-#ifdef CONFIG_PPC_KUAP
-	mfspr	r14,SPRN_MAS1
-	rlwinm.	r14,r14,0,0x3fff0000
-	beq-	normal_tlb_miss_access_fault /* KUAP fault */
-#endif
-normal_tlb_miss:
-	/* So we first construct the page table address. We do that by
-	 * shifting the bottom of the address (not the region ID) by
-	 * PAGE_SHIFT-3, clearing the bottom 3 bits (get a PTE ptr) and
-	 * or'ing the fourth high bit.
-	 *
-	 * NOTE: For 64K pages, we do things slightly differently in
-	 * order to handle the weird page table format used by linux
-	 */
-	srdi	r15,r16,44
-	oris	r10,r15,0x1
-	rldicl	r14,r16,64-(PAGE_SHIFT-3),PAGE_SHIFT-3+4
-	sldi	r15,r10,44
-	clrrdi	r14,r14,19
-	or	r10,r15,r14
-
-	ld	r14,0(r10)
-
-finish_normal_tlb_miss:
-	/* Check if required permissions are met */
-	andc.	r15,r11,r14
-	bne-	normal_tlb_miss_access_fault
-
-	/* Now we build the MAS:
-	 *
-	 * MAS 0   :	Fully setup with defaults in MAS4 and TLBnCFG
-	 * MAS 1   :	Almost fully setup
-	 *               - PID already updated by caller if necessary
-	 *               - TSIZE need change if !base page size, not
-	 *                 yet implemented for now
-	 * MAS 2   :	Defaults not useful, need to be redone
-	 * MAS 3+7 :	Needs to be done
-	 *
-	 * TODO: mix up code below for better scheduling
-	 */
-	clrrdi	r10,r16,12		/* Clear low crap in EA */
-	rlwimi	r10,r14,32-19,27,31	/* Insert WIMGE */
-	mtspr	SPRN_MAS2,r10
-
-	/* Check page size, if not standard, update MAS1 */
-	rldicl	r10,r14,64-8,64-8
-	cmpldi	cr0,r10,BOOK3E_PAGESZ_4K
-	beq-	1f
-	mfspr	r11,SPRN_MAS1
-	rlwimi	r11,r14,31,21,24
-	rlwinm	r11,r11,0,21,19
-	mtspr	SPRN_MAS1,r11
-1:
-	/* Move RPN in position */
-	rldicr	r11,r14,64-(PTE_RPN_SHIFT-PAGE_SHIFT),63-PAGE_SHIFT
-	clrldi	r15,r11,12		/* Clear crap at the top */
-	rlwimi	r15,r14,32-8,22,25	/* Move in U bits */
-	rlwimi	r15,r14,32-2,26,31	/* Move in BAP bits */
-
-	/* Mask out SW and UW if !DIRTY (XXX optimize this !) */
-	andi.	r11,r14,_PAGE_DIRTY
-	bne	1f
-	li	r11,MAS3_SW|MAS3_UW
-	andc	r15,r15,r11
-1:
-	srdi	r16,r15,32
-	mtspr	SPRN_MAS3,r15
-	mtspr	SPRN_MAS7,r16
-
-	tlbwe
-
-normal_tlb_miss_done:
-	/* We don't bother with restoring DEAR or ESR since we know we are
-	 * level 0 and just going back to userland. They are only needed
-	 * if you are going to take an access fault
-	 */
-	TLB_MISS_EPILOG_SUCCESS
-	rfi
-
-normal_tlb_miss_access_fault:
-	/* We need to check if it was an instruction miss */
-	andi.	r10,r11,_PAGE_BAP_UX
-	bne	1f
-	ld	r14,EX_TLB_DEAR(r12)
-	ld	r15,EX_TLB_ESR(r12)
-	mtspr	SPRN_DEAR,r14
-	mtspr	SPRN_ESR,r15
-	TLB_MISS_EPILOG_ERROR
-	b	exc_data_storage_book3e
-1:	TLB_MISS_EPILOG_ERROR
-	b	exc_instruction_storage_book3e
-
-
 /*
  * This is the guts of the second-level TLB miss handler for direct
  * misses. We are entered with:
@@ -893,201 +662,6 @@ virt_page_table_tlb_miss_whacko_fault:
 	TLB_MISS_EPILOG_ERROR
 	b	exc_data_storage_book3e
 
-
-/**************************************************************
- *                                                            *
- * TLB miss handling for Book3E with hw page table support    *
- *                                                            *
- **************************************************************/
-
-
-/* Data TLB miss */
-	START_EXCEPTION(data_tlb_miss_htw)
-	TLB_MISS_PROLOG
-
-	/* Now we handle the fault proper. We only save DEAR in normal
-	 * fault case since that's the only interesting values here.
-	 * We could probably also optimize by not saving SRR0/1 in the
-	 * linear mapping case but I'll leave that for later
-	 */
-	mfspr	r14,SPRN_ESR
-	mfspr	r16,SPRN_DEAR		/* get faulting address */
-	srdi	r11,r16,44		/* get region */
-	xoris	r11,r11,0xc
-	cmpldi	cr0,r11,0		/* linear mapping ? */
-	beq	tlb_load_linear		/* yes -> go to linear map load */
-	cmpldi	cr1,r11,1		/* vmalloc mapping ? */
-
-	/* We do the user/kernel test for the PID here along with the RW test
-	 */
-	srdi.	r11,r16,60		/* Check for user region */
-	ld	r15,PACAPGD(r13)	/* Load user pgdir */
-	beq	htw_tlb_miss
-
-	/* XXX replace the RMW cycles with immediate loads + writes */
-1:	mfspr	r10,SPRN_MAS1
-	rlwinm	r10,r10,0,16,1		/* Clear TID */
-	mtspr	SPRN_MAS1,r10
-	ld	r15,PACA_KERNELPGD(r13)	/* Load kernel pgdir */
-	beq+	cr1,htw_tlb_miss
-
-	/* We got a crappy address, just fault with whatever DEAR and ESR
-	 * are here
-	 */
-	TLB_MISS_EPILOG_ERROR
-	b	exc_data_storage_book3e
-
-/* Instruction TLB miss */
-	START_EXCEPTION(instruction_tlb_miss_htw)
-	TLB_MISS_PROLOG
-
-	/* If we take a recursive fault, the second level handler may need
-	 * to know whether we are handling a data or instruction fault in
-	 * order to get to the right store fault handler. We provide that
-	 * info by keeping a crazy value for ESR in r14
-	 */
-	li	r14,-1	/* store to exception frame is done later */
-
-	/* Now we handle the fault proper. We only save DEAR in the non
-	 * linear mapping case since we know the linear mapping case will
-	 * not re-enter. We could indeed optimize and also not save SRR0/1
-	 * in the linear mapping case but I'll leave that for later
-	 *
-	 * Faulting address is SRR0 which is already in r16
-	 */
-	srdi	r11,r16,44		/* get region */
-	xoris	r11,r11,0xc
-	cmpldi	cr0,r11,0		/* linear mapping ? */
-	beq	tlb_load_linear		/* yes -> go to linear map load */
-	cmpldi	cr1,r11,1		/* vmalloc mapping ? */
-
-	/* We do the user/kernel test for the PID here along with the RW test
-	 */
-	srdi.	r11,r16,60		/* Check for user region */
-	ld	r15,PACAPGD(r13)		/* Load user pgdir */
-	beq	htw_tlb_miss
-
-	/* XXX replace the RMW cycles with immediate loads + writes */
-1:	mfspr	r10,SPRN_MAS1
-	rlwinm	r10,r10,0,16,1			/* Clear TID */
-	mtspr	SPRN_MAS1,r10
-	ld	r15,PACA_KERNELPGD(r13)		/* Load kernel pgdir */
-	beq+	htw_tlb_miss
-
-	/* We got a crappy address, just fault */
-	TLB_MISS_EPILOG_ERROR
-	b	exc_instruction_storage_book3e
-
-
-/*
- * This is the guts of the second-level TLB miss handler for direct
- * misses. We are entered with:
- *
- * r16 = virtual page table faulting address
- * r15 = PGD pointer
- * r14 = ESR
- * r13 = PACA
- * r12 = TLB exception frame in PACA
- * r11 = crap (free to use)
- * r10 = crap (free to use)
- *
- * It can be re-entered by the linear mapping miss handler. However, to
- * avoid too much complication, it will save/restore things for us
- */
-htw_tlb_miss:
-#ifdef CONFIG_PPC_KUAP
-	mfspr	r10,SPRN_MAS1
-	rlwinm.	r10,r10,0,0x3fff0000
-	beq-	htw_tlb_miss_fault /* KUAP fault */
-#endif
-	/* Search if we already have a TLB entry for that virtual address, and
-	 * if we do, bail out.
-	 *
-	 * MAS1:IND should be already set based on MAS4
-	 */
-	PPC_TLBSRX_DOT(0,R16)
-	beq	htw_tlb_miss_done
-
-	/* Now, we need to walk the page tables. First check if we are in
-	 * range.
-	 */
-	rldicl.	r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4
-	bne-	htw_tlb_miss_fault
-
-	/* Get the PGD pointer */
-	cmpldi	cr0,r15,0
-	beq-	htw_tlb_miss_fault
-
-	/* Get to PGD entry */
-	rldicl	r11,r16,64-(PGDIR_SHIFT-3),64-PGD_INDEX_SIZE-3
-	clrrdi	r10,r11,3
-	ldx	r15,r10,r15
-	cmpdi	cr0,r15,0
-	bge	htw_tlb_miss_fault
-
-	/* Get to PUD entry */
-	rldicl	r11,r16,64-(PUD_SHIFT-3),64-PUD_INDEX_SIZE-3
-	clrrdi	r10,r11,3
-	ldx	r15,r10,r15
-	cmpdi	cr0,r15,0
-	bge	htw_tlb_miss_fault
-
-	/* Get to PMD entry */
-	rldicl	r11,r16,64-(PMD_SHIFT-3),64-PMD_INDEX_SIZE-3
-	clrrdi	r10,r11,3
-	ldx	r15,r10,r15
-	cmpdi	cr0,r15,0
-	bge	htw_tlb_miss_fault
-
-	/* Ok, we're all right, we can now create an indirect entry for
-	 * a 1M or 256M page.
-	 *
-	 * The last trick is now that because we use "half" pages for
-	 * the HTW (1M IND is 2K and 256M IND is 32K) we need to account
-	 * for an added LSB bit to the RPN. For 64K pages, there is no
-	 * problem as we already use 32K arrays (half PTE pages), but for
-	 * 4K page we need to extract a bit from the virtual address and
-	 * insert it into the "PA52" bit of the RPN.
-	 */
-	rlwimi	r15,r16,32-9,20,20
-	/* Now we build the MAS:
-	 *
-	 * MAS 0   :	Fully setup with defaults in MAS4 and TLBnCFG
-	 * MAS 1   :	Almost fully setup
-	 *               - PID already updated by caller if necessary
-	 *               - TSIZE for now is base ind page size always
-	 * MAS 2   :	Use defaults
-	 * MAS 3+7 :	Needs to be done
-	 */
-	ori	r10,r15,(BOOK3E_PAGESZ_4K << MAS3_SPSIZE_SHIFT)
-
-	srdi	r16,r10,32
-	mtspr	SPRN_MAS3,r10
-	mtspr	SPRN_MAS7,r16
-
-	tlbwe
-
-htw_tlb_miss_done:
-	/* We don't bother with restoring DEAR or ESR since we know we are
-	 * level 0 and just going back to userland. They are only needed
-	 * if you are going to take an access fault
-	 */
-	TLB_MISS_EPILOG_SUCCESS
-	rfi
-
-htw_tlb_miss_fault:
-	/* We need to check if it was an instruction miss. We know this
-	 * though because r14 would contain -1
-	 */
-	cmpdi	cr0,r14,-1
-	beq	1f
-	mtspr	SPRN_DEAR,r16
-	mtspr	SPRN_ESR,r14
-	TLB_MISS_EPILOG_ERROR
-	b	exc_data_storage_book3e
-1:	TLB_MISS_EPILOG_ERROR
-	b	exc_instruction_storage_book3e
-
 /*
  * This is the guts of "any" level TLB miss handler for kernel linear
  * mapping misses. We are entered with:
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 9e7ba9c3851f..ab0656115424 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 +308,60 @@ 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));
+	}
+}
+#else
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+		     pte_t pte, unsigned long sz)
+{
+	unsigned long pdsize;
+	int i;
+
+	pte = set_pte_filter(pte, addr);
+
+	/*
+	 * Make sure hardware valid bit is not set. We don't do
+	 * tlb flush for this update.
+	 */
+	VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
+
+	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++, ptep++, addr += pdsize) {
+		__set_pte_at(mm, addr, ptep, pte, 0);
+		pte = __pte(pte_val(pte) + ((unsigned long long)pdsize / PAGE_SIZE << PFN_PTE_SHIFT));
+	}
+}
 #endif
 #endif /* CONFIG_HUGETLB_PAGE */
 
@@ -367,11 +409,10 @@ unsigned long vmalloc_to_phys(void *va)
 EXPORT_SYMBOL_GPL(vmalloc_to_phys);
 
 /*
- * We have 4 cases for pgds and pmds:
+ * We have 3 cases for pgds and pmds:
  * (1) invalid (all zeroes)
  * (2) pointer to next table, as normal; bottom 6 bits == 0
  * (3) leaf pte for huge page _PAGE_PTE set
- * (4) hugepd pointer, _PAGE_PTE = 0 and bits [2..6] indicate size of table
  *
  * So long as we atomically load page table pointers we are safe against teardown,
  * we can follow the address down to the page and take a ref on it.
@@ -382,11 +423,12 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
 			bool *is_thp, unsigned *hpage_shift)
 {
 	pgd_t *pgdp;
+#ifdef CONFIG_PPC64
 	p4d_t p4d, *p4dp;
 	pud_t pud, *pudp;
+#endif
 	pmd_t pmd, *pmdp;
 	pte_t *ret_pte;
-	hugepd_t *hpdp = NULL;
 	unsigned pdshift;
 
 	if (hpage_shift)
@@ -401,8 +443,12 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
 	 * page fault or a page unmap. The return pte_t * is still not
 	 * stable. So should be checked there for above conditions.
 	 * Top level is an exception because it is folded into p4d.
+	 *
+	 * On PPC32, P4D/PUD/PMD are folded into PGD so go straight to
+	 * PMD level.
 	 */
 	pgdp = pgdir + pgd_index(ea);
+#ifdef CONFIG_PPC64
 	p4dp = p4d_offset(pgdp, ea);
 	p4d  = READ_ONCE(*p4dp);
 	pdshift = P4D_SHIFT;
@@ -415,11 +461,6 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
 		goto out;
 	}
 
-	if (is_hugepd(__hugepd(p4d_val(p4d)))) {
-		hpdp = (hugepd_t *)&p4d;
-		goto out_huge;
-	}
-
 	/*
 	 * Even if we end up with an unmap, the pgtable will not
 	 * be freed, because we do an rcu free and here we are
@@ -437,13 +478,11 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
 		goto out;
 	}
 
-	if (is_hugepd(__hugepd(pud_val(pud)))) {
-		hpdp = (hugepd_t *)&pud;
-		goto out_huge;
-	}
-
-	pdshift = PMD_SHIFT;
 	pmdp = pmd_offset(&pud, ea);
+#else
+	pmdp = pmd_offset(pud_offset(p4d_offset(pgdp, ea), ea), ea);
+#endif
+	pdshift = PMD_SHIFT;
 	pmd  = READ_ONCE(*pmdp);
 
 	/*
@@ -476,19 +515,8 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
 		goto out;
 	}
 
-	if (is_hugepd(__hugepd(pmd_val(pmd)))) {
-		hpdp = (hugepd_t *)&pmd;
-		goto out_huge;
-	}
-
 	return pte_offset_kernel(&pmd, ea);
 
-out_huge:
-	if (!hpdp)
-		return NULL;
-
-	ret_pte = hugepte_offset(*hpdp, ea, pdshift);
-	pdshift = hugepd_shift(*hpdp);
 out:
 	if (hpage_shift)
 		*hpage_shift = pdshift;
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);