[RFC 1/9] mm/hugetlb: Make GENERAL_HUGETLB functions PGD implementation aware

@@ -4251,6 +4251,11 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	pte_t *pte = NULL;
 
 	pgd = pgd_offset(mm, addr);
+	if (sz == PGDIR_SIZE) {
+		pte = (pte_t *)pgd;
+		goto huge_pgd;
+	}
+
 	pud = pud_alloc(mm, pgd, addr);
 	if (pud) {
 		if (sz == PUD_SIZE) {

@@ -4263,6 +4268,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 				pte = (pte_t *)pmd_alloc(mm, pud, addr);
 		}
 	}
+
+huge_pgd:
 	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
 
 	return pte;

@@ -4276,6 +4283,8 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 
 	pgd = pgd_offset(mm, addr);
 	if (pgd_present(*pgd)) {
+		if (pgd_huge(*pgd))
+			return (pte_t *)pgd;
 		pud = pud_offset(pgd, addr);
 		if (pud_present(*pud)) {
 			if (pud_huge(*pud))

@@ -115,6 +115,8 @@ struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 				pmd_t *pmd, int flags);
 struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
 				pud_t *pud, int flags);
+struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
+				pgd_t *pgd, int flags);
 int pmd_huge(pmd_t pmd);
 int pud_huge(pud_t pmd);
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,

@@ -143,6 +145,7 @@ static inline void hugetlb_show_meminfo(void)
 }
 #define follow_huge_pmd(mm, addr, pmd, flags)	NULL
 #define follow_huge_pud(mm, addr, pud, flags)	NULL
+#define follow_huge_pgd(mm, addr, pgd, flags)	NULL
 #define prepare_hugepage_range(file, addr, len)	(-EINVAL)
 #define pmd_huge(x)	0
 #define pud_huge(x)	0

@@ -4353,6 +4353,16 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address,
 	return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
 }
 
+struct page * __weak
+follow_huge_pgd(struct mm_struct *mm, unsigned long address,
+		pgd_t *pgd, int flags)
+{
+	if (flags & FOLL_GET)
+		return NULL;
+
+	return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT);
+}
+
 #ifdef CONFIG_MEMORY_FAILURE
 
 /*

@@ -232,6 +232,12 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	pgd = pgd_offset(mm, address);
 	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
 		return no_page_table(vma, flags);
+	if (pgd_huge(*pgd) && vma->vm_flags & VM_HUGETLB) {
+		page = follow_huge_pgd(mm, address, pgd, flags);
+		if (page)
+			return page;
+		return no_page_table(vma, flags);
+	}
 
 	pud = pud_offset(pgd, address);
 	if (pud_none(*pud))

@@ -53,11 +53,46 @@ static unsigned nr_gpages;
 
 #define hugepd_none(hpd)	((hpd).pd == 0)
 
+#if !defined(CONFIG_PPC_64K_PAGES) || !defined(CONFIG_PPC_BOOK3S_64)
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 {
 	/* Only called for hugetlbfs pages, hence can ignore THP */
 	return __find_linux_pte_or_hugepte(mm->pgd, addr, NULL, NULL);
 }
+#else
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t pgd, *pgdp;
+	pud_t pud, *pudp;
+	pmd_t pmd, *pmdp;
+
+	pgdp = mm->pgd + pgd_index(addr);
+	pgd  = READ_ONCE(*pgdp);
+
+	if (pgd_none(pgd))
+		return NULL;
+
+	if (pgd_huge(pgd))
+		return (pte_t *)pgdp;
+
+	pudp = pud_offset(&pgd, addr);
+	pud  = READ_ONCE(*pudp);
+	if (pud_none(pud))
+		return NULL;
+
+	if (pud_huge(pud))
+		return (pte_t *)pudp;
+
+	pmdp = pmd_offset(&pud, addr);
+	pmd  = READ_ONCE(*pmdp);
+	if (pmd_none(pmd))
+		return NULL;
+
+	if (pmd_huge(pmd))
+		return (pte_t *)pmdp;
+	return NULL;
+}
+#endif /* !defined(CONFIG_PPC_64K_PAGES) || !defined(CONFIG_PPC_BOOK3S_64) */
 
 #if !defined(CONFIG_PPC_64K_PAGES) || !defined(CONFIG_PPC_BOOK3S_64)
 static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,

@@ -59,6 +59,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	return __find_linux_pte_or_hugepte(mm->pgd, addr, NULL, NULL);
 }
 
+#if !defined(CONFIG_PPC_64K_PAGES) || !defined(CONFIG_PPC_BOOK3S_64)
 static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 			   unsigned long address, unsigned pdshift, unsigned pshift)
 {

@@ -117,6 +118,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 	spin_unlock(&mm->page_table_lock);
 	return 0;
 }
+#endif /* !defined(CONFIG_PPC_64K_PAGES) || !defined(CONFIG_PPC_BOOK3S_64) */
 
 /*
  * These macros define how to determine which level of the page table holds

@@ -131,6 +133,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 #endif
 
 #ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_PPC_4K_PAGES
 /*
  * At this point we do the placement change only for BOOK3S 64. This would
  * possibly work on other subarchs.

@@ -146,32 +149,23 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
 
 	addr &= ~(sz-1);
 	pg = pgd_offset(mm, addr);
-
-	if (pshift == PGDIR_SHIFT)
-		/* 16GB huge page */
-		return (pte_t *) pg;
-	else if (pshift > PUD_SHIFT)
-		/*
-		 * We need to use hugepd table
-		 */
+	if (pshift > PUD_SHIFT) {
 		hpdp = (hugepd_t *)pg;
-	else {
-		pdshift = PUD_SHIFT;
-		pu = pud_alloc(mm, pg, addr);
-		if (pshift == PUD_SHIFT)
-			return (pte_t *)pu;
-		else if (pshift > PMD_SHIFT)
-			hpdp = (hugepd_t *)pu;
-		else {
-			pdshift = PMD_SHIFT;
-			pm = pmd_alloc(mm, pu, addr);
-			if (pshift == PMD_SHIFT)
-				/* 16MB hugepage */
-				return (pte_t *)pm;
-			else
-				hpdp = (hugepd_t *)pm;
-		}
+		goto hugepd_search;
+	}
+
+	pdshift = PUD_SHIFT;
+	pu = pud_alloc(mm, pg, addr);
+	if (pshift > PMD_SHIFT) {
+		hpdp = (hugepd_t *)pu;
+		goto hugepd_search;
 	}
+
+	pdshift = PMD_SHIFT;
+	pm = pmd_alloc(mm, pu, addr);
+	hpdp = (hugepd_t *)pm;
+
+hugepd_search:
 	if (!hpdp)
 		return NULL;
 

@@ -184,6 +178,31 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
 }
 
 #else
+pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
+{
+	pgd_t *pg;
+	pud_t *pu;
+	pmd_t *pm;
+	unsigned pshift = __ffs(sz);
+
+	addr &= ~(sz-1);
+	pg = pgd_offset(mm, addr);
+
+	if (pshift == PGDIR_SHIFT)	/* 16GB Huge Page */
+		return (pte_t *)pg;
+
+	pu = pud_alloc(mm, pg, addr);	/* NA, skipped */
+	if (pshift == PUD_SHIFT)
+		return (pte_t *)pu;
+
+	pm = pmd_alloc(mm, pu, addr);	/* 16MB Huge Page */
+	if (pshift == PMD_SHIFT)
+		return (pte_t *)pm;
+
+	return NULL;
+}
+#endif
+#else
 
 pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
 {

@@ -631,6 +631,10 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
 	unsigned long mask, flags;
 	struct page *page = ERR_PTR(-EINVAL);
 
+#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC_BOOK3S_64)
+	return ERR_PTR(-EINVAL);
+#endif
+
 	local_irq_save(flags);
 	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &is_thp, &shift);
 	if (!ptep)

@@ -658,6 +662,7 @@ no_page:
 	return page;
 }
 
+#if !defined(CONFIG_PPC_64K_PAGES) || !defined(CONFIG_PPC_BOOK3S_64)
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)

@@ -674,6 +679,15 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address,
 	return NULL;
 }
 
+struct page *
+follow_huge_pgd(struct mm_struct *mm, unsigned long address,
+		pgd_t *pgd, int write)
+{
+	BUG();
+	return NULL;
+}
+#endif /* !defined(CONFIG_PPC_64K_PAGE) || !defined(CONFIG_BOOK3S_64) */
+
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 				      unsigned long sz)
 {

@@ -1,12 +1,16 @@
 noarg:
 	$(MAKE) -C ../
 
-TEST_PROGS := hugetlb_vs_thp_test subpage_prot
-TEST_FILES := tempfile
+TEST_PROGS := run_mmtests
+TEST_FILES := hugetlb_vs_thp_test
+TEST_FILES += subpage_prot
+TEST_FILES += tempfile
+TEST_FILES += hugepage-migration
+TEST_FILES += page-migration
 
-all: $(TEST_PROGS) $(TEST_FILES)
+all: $(TEST_FILES)
 
-$(TEST_PROGS): ../harness.c
+$(TEST_FILES): ../harness.c
 
 include ../../lib.mk
 

@@ -14,4 +18,4 @@ tempfile:
 	dd if=/dev/zero of=tempfile bs=64k count=1
 
 clean:
-	rm -f $(TEST_PROGS) tempfile
+	rm -f $(TEST_FILES)

@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2015, Anshuman Khandual, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+#include "migration.h"
+
+static int hugepage_migration(void)
+{
+	int ret = 0;
+
+	if ((unsigned long)getpagesize() == 0x1000)
+		printf("Running on base page size 4K\n");
+
+	if ((unsigned long)getpagesize() == 0x10000)
+		printf("Running on base page size 64K\n");
+
+	ret = test_huge_migration(16 * MEM_MB);
+	ret = test_huge_migration(256 * MEM_MB);
+	ret = test_huge_migration(512 * MEM_MB);
+
+	return ret;
+}
+
+int main(void)
+{
+	return test_harness(hugepage_migration, "hugepage_migration");
+}

@@ -0,0 +1,204 @@
+/*
+ * Copyright (C) 2015, Anshuman Khandual, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+
+#include "utils.h"
+
+#define HPAGE_OFF	0
+#define HPAGE_ON	1
+
+#define PAGE_SHIFT_4K	12
+#define PAGE_SHIFT_64K	16
+#define PAGE_SIZE_4K	0x1000
+#define PAGE_SIZE_64K	0x10000
+#define PAGE_SIZE_HUGE	16UL * 1024 * 1024
+
+#define MEM_GB		1024UL * 1024 * 1024
+#define MEM_MB		1024UL * 1024
+#define MME_KB		1024UL
+
+#define PMAP_FILE	"/proc/self/pagemap"
+#define PMAP_PFN	0x007FFFFFFFFFFFFFUL
+#define PMAP_SIZE	8
+
+#define SOFT_OFFLINE	"/sys/devices/system/memory/soft_offline_page"
+#define HARD_OFFLINE	"/sys/devices/system/memory/hard_offline_page"
+
+#define MMAP_LENGTH	(256 * MEM_MB)
+#define MMAP_ADDR	(void *)(0x0UL)
+#define MMAP_PROT	(PROT_READ | PROT_WRITE)
+#define MMAP_FLAGS	(MAP_PRIVATE | MAP_ANONYMOUS)
+#define MMAP_FLAGS_HUGE	(MAP_SHARED)
+
+#define FILE_NAME	"huge/hugepagefile"
+
+static void write_buffer(char *addr, unsigned long length)
+{
+	unsigned long i;
+
+	for (i = 0; i < length; i++)
+		*(addr + i) = (char)i;
+}
+
+static int read_buffer(char *addr, unsigned long length)
+{
+	unsigned long i;
+
+	for (i = 0; i < length; i++) {
+		if (*(addr + i) != (char)i) {
+			printf("Data miscompare at addr[%lu]\n", i);
+			return 1;
+		}
+	}
+	return 0;
+}
+
+static unsigned long get_npages(unsigned long length, unsigned long size)
+{
+	unsigned int tmp1 = length, tmp2 = size;
+
+	return tmp1/tmp2;
+}
+
+static void soft_offline_pages(int hugepage, void *addr,
+	unsigned long npages, unsigned long *skipped, unsigned long *failed)
+{
+	unsigned long psize, offset, pfn, paddr, fail, skip, i;
+	void *tmp;
+	int fd1, fd2;
+	char buf[20];
+
+	fd1 = open(PMAP_FILE, O_RDONLY);
+	if (fd1 == -1) {
+		perror("open() failed");
+		exit(-1);
+	}
+
+	fd2 = open(SOFT_OFFLINE, O_WRONLY);
+	if (fd2 == -1) {
+		perror("open() failed");
+		exit(-1);
+	}
+
+	fail = skip = 0;
+	psize = getpagesize();
+	for (i = 0; i < npages; i++) {
+		if (hugepage)
+			tmp = addr + i * PAGE_SIZE_HUGE;
+		else
+			tmp = addr + i * psize;
+
+		offset = ((unsigned long) tmp / psize) * PMAP_SIZE;
+
+		if (lseek(fd1, offset, SEEK_SET) == -1) {
+			perror("lseek() failed");
+			exit(-1);
+		}
+
+		if (read(fd1, &pfn, sizeof(pfn)) == -1) {
+			perror("read() failed");
+			exit(-1);
+		}
+
+		/* Skip if no valid PFN */
+		pfn = pfn & PMAP_PFN;
+		if (!pfn) {
+			skip++;
+			continue;
+		}
+
+		if (psize == PAGE_SIZE_4K)
+			paddr = pfn << PAGE_SHIFT_4K;
+
+		if (psize == PAGE_SIZE_64K)
+			paddr = pfn << PAGE_SHIFT_64K;
+
+		sprintf(buf, "0x%lx\n", paddr);
+
+		if (write(fd2, buf, strlen(buf)) == -1) {
+			perror("write() failed");
+			printf("[%ld] PFN: %lx BUF: %s\n",i, pfn, buf);
+			fail++;
+		}
+
+	}
+
+	if (failed)
+		*failed = fail;
+
+	if (skipped)
+		*skipped = skip;
+
+	close(fd1);
+	close(fd2);
+}
+
+int test_migration(unsigned long length)
+{
+	unsigned long skipped, failed;
+	void *addr;
+	int ret;
+
+	addr = mmap(MMAP_ADDR, length, MMAP_PROT, MMAP_FLAGS, -1, 0);
+	if (addr == MAP_FAILED) {
+		perror("mmap() failed");
+		exit(-1);
+	}
+
+	write_buffer(addr, length);
+	soft_offline_pages(HPAGE_OFF, addr, length/getpagesize(), &skipped, &failed);
+	ret = read_buffer(addr, length);
+
+	printf("%ld moved %ld skipped %ld failed\n", (length/getpagesize() - skipped - failed), skipped, failed);
+
+	munmap(addr, length);
+	return ret;
+}
+
+int test_huge_migration(unsigned long length)
+{
+	unsigned long skipped, failed, npages;
+	void *addr;
+	int fd, ret;
+
+	fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755);
+	if (fd < 0) {
+		perror("open() failed");
+		exit(-1);
+	}
+
+	addr = mmap(MMAP_ADDR, length, MMAP_PROT, MMAP_FLAGS_HUGE, fd, 0);
+	if (addr == MAP_FAILED) {
+		perror("mmap() failed");
+		unlink(FILE_NAME);
+		exit(-1);
+	}
+
+        if (mlock(addr, length) == -1) {
+                perror("mlock() failed");
+		munmap(addr, length);
+                unlink(FILE_NAME);
+                exit(-1);
+        }
+
+	write_buffer(addr, length);
+	npages = get_npages(length, PAGE_SIZE_HUGE);
+	soft_offline_pages(HPAGE_ON, addr, npages, &skipped, &failed);
+	ret = read_buffer(addr, length);
+
+	printf("%ld moved %ld skipped %ld failed\n", (npages - skipped - failed), skipped, failed);
+
+	munmap(addr, length);
+	unlink(FILE_NAME);
+	return ret;
+}

@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2015, Anshuman Khandual, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+#include "migration.h"
+
+static int page_migration(void)
+{
+	int ret = 0;
+
+	if ((unsigned long)getpagesize() == 0x1000)
+		printf("Running on base page size 4K\n");
+
+	if ((unsigned long)getpagesize() == 0x10000)
+		printf("Running on base page size 64K\n");
+
+	ret = test_migration(4 * MEM_MB);
+	ret = test_migration(64 * MEM_MB);
+	ret = test_migration(256 * MEM_MB);
+	ret = test_migration(512 * MEM_MB);
+	ret = test_migration(1 * MEM_GB);
+	ret = test_migration(2 * MEM_GB);
+
+	return ret;
+}
+
+int main(void)
+{
+	return test_harness(page_migration, "page_migration");
+}

@@ -0,0 +1,104 @@
+#!/bin/bash
+
+# Mostly borrowed from tools/testing/selftests/vm/run_vmtests
+
+# Please run this as root
+# Try allocating 2GB of 16MB huge pages, below is the size in kB.
+# Please change this needed memory if the test program changes
+needmem=2097152
+mnt=./huge
+exitcode=0
+
+# Get huge pagesize and freepages from /proc/meminfo
+while read name size unit; do
+	if [ "$name" = "HugePages_Free:" ]; then
+		freepgs=$size
+	fi
+	if [ "$name" = "Hugepagesize:" ]; then
+		pgsize=$size
+	fi
+done < /proc/meminfo
+
+# Set required nr_hugepages
+if [ -n "$freepgs" ] && [ -n "$pgsize" ]; then
+	nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
+	needpgs=`expr $needmem / $pgsize`
+	tries=2
+	while [ $tries -gt 0 ] && [ $freepgs -lt $needpgs ]; do
+		lackpgs=$(( $needpgs - $freepgs ))
+		echo 3 > /proc/sys/vm/drop_caches
+		echo $(( $lackpgs + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
+		if [ $? -ne 0 ]; then
+			echo "Please run this test as root"
+		fi
+		while read name size unit; do
+			if [ "$name" = "HugePages_Free:" ]; then
+				freepgs=$size
+			fi
+		done < /proc/meminfo
+		tries=$((tries - 1))
+	done
+	if [ $freepgs -lt $needpgs ]; then
+		printf "Not enough huge pages available (%d < %d)\n" \
+		       $freepgs $needpgs
+	fi
+else
+	echo "No hugetlbfs support in kernel ? check dmesg"
+fi
+
+mkdir $mnt
+mount -t hugetlbfs none $mnt
+
+# Run the test programs
+echo "...................."
+echo "Test HugeTLB vs THP"
+echo "...................."
+./hugetlb_vs_thp_test
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
+echo "........................."
+echo "Test subpage protection"
+echo "........................."
+./subpage_prot
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
+echo "..........................."
+echo "Test normal page migration"
+echo "..........................."
+./page-migration
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
+# Enable this after huge page migration is supported on POWER
+
+echo "........................."
+echo "Test huge page migration"
+echo "........................."
+./hugepage-migration
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
+# Huge pages cleanup
+umount $mnt
+rm -rf $mnt
+echo $nr_hugepgs > /proc/sys/vm/nr_hugepages
+
+exit $exitcode

@@ -86,6 +86,10 @@ config GENERIC_HWEIGHT
 config ARCH_HAS_DMA_SET_COHERENT_MASK
         bool
 
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+	def_bool y
+	depends on PPC_BOOK3S_64 && HUGETLB_PAGE && MIGRATION
+
 config PPC
 	bool
 	default y

@@ -33,6 +33,10 @@ config HAVE_SETUP_PER_CPU_AREA
 config NEED_PER_CPU_EMBED_FIRST_CHUNK
 	def_bool PPC64
 
+config ARCH_WANT_GENERAL_HUGETLB
+	depends on PPC_64K_PAGES && PPC_BOOK3S_64
+	def_bool y
+
 config NR_IRQS
 	int "Number of virtual interrupt numbers"
 	range 32 32768

@@ -143,6 +143,14 @@ extern bool __rpte_sub_valid(real_pte_t rpte, unsigned long index);
  * Defined in such a way that we can optimize away code block at build time
  * if CONFIG_HUGETLB_PAGE=n.
  */
+static inline int pte_huge(pte_t pte)
+{
+	/*
+	 * leaf pte for huge page
+	 */
+	return !!(pte_val(pte) & _PAGE_PTE);
+}
+
 static inline int pmd_huge(pmd_t pmd)
 {
 	/*

@@ -59,42 +59,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	/* Only called for hugetlbfs pages, hence can ignore THP */
 	return __find_linux_pte_or_hugepte(mm->pgd, addr, NULL, NULL);
 }
-#else
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
-{
-	pgd_t pgd, *pgdp;
-	pud_t pud, *pudp;
-	pmd_t pmd, *pmdp;
-
-	pgdp = mm->pgd + pgd_index(addr);
-	pgd  = READ_ONCE(*pgdp);
-
-	if (pgd_none(pgd))
-		return NULL;
-
-	if (pgd_huge(pgd))
-		return (pte_t *)pgdp;
-
-	pudp = pud_offset(&pgd, addr);
-	pud  = READ_ONCE(*pudp);
-	if (pud_none(pud))
-		return NULL;
-
-	if (pud_huge(pud))
-		return (pte_t *)pudp;
 
-	pmdp = pmd_offset(&pud, addr);
-	pmd  = READ_ONCE(*pmdp);
-	if (pmd_none(pmd))
-		return NULL;
-
-	if (pmd_huge(pmd))
-		return (pte_t *)pmdp;
-	return NULL;
-}
-#endif /* !defined(CONFIG_PPC_64K_PAGES) || !defined(CONFIG_PPC_BOOK3S_64) */
-
-#if !defined(CONFIG_PPC_64K_PAGES) || !defined(CONFIG_PPC_BOOK3S_64)
 static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 			   unsigned long address, unsigned pdshift, unsigned pshift)
 {

@@ -211,31 +176,6 @@ hugepd_search:
 
 	return hugepte_offset(*hpdp, addr, pdshift);
 }
-
-#else
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
-{
-	pgd_t *pg;
-	pud_t *pu;
-	pmd_t *pm;
-	unsigned pshift = __ffs(sz);
-
-	addr &= ~(sz-1);
-	pg = pgd_offset(mm, addr);
-
-	if (pshift == PGDIR_SHIFT)	/* 16GB Huge Page */
-		return (pte_t *)pg;
-
-	pu = pud_alloc(mm, pg, addr);	/* NA, skipped */
-	if (pshift == PUD_SHIFT)
-		return (pte_t *)pu;
-
-	pm = pmd_alloc(mm, pu, addr);	/* 16MB Huge Page */
-	if (pshift == PMD_SHIFT)
-		return (pte_t *)pm;
-
-	return NULL;
-}
 #endif
 #else