Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Ben Herrenschmidt:
 "This is the powerpc changes for the 3.11 merge window.  In addition to
  the usual bug fixes and small updates, the main highlights are:

   - Support for transparent huge pages by Aneesh Kumar for 64-bit
     server processors.  This allows the use of 16M pages as transparent
     huge pages on kernels compiled with a 64K base page size.

   - Base VFIO support for KVM on power by Alexey Kardashevskiy

   - Wiring up of our nvram to the pstore infrastructure, including
     putting compressed oopses in there by Aruna Balakrishnaiah

   - Move, rework and improve our "EEH" (basically PCI error handling
     and recovery) infrastructure.  It is no longer specific to pseries
     but is now usable by the new "powernv" platform as well (no
     hypervisor) by Gavin Shan.

   - I fixed some bugs in our math-emu instruction decoding and made it
     usable to emulate some optional FP instructions on processors with
     hard FP that lack them (such as fsqrt on Freescale embedded
     processors).

   - Support for Power8 "Event Based Branch" facility by Michael
     Ellerman.  This facility allows what is basically "userspace
     interrupts" for performance monitor events.

   - A bunch of Transactional Memory vs.  Signals bug fixes and HW
     breakpoint/watchpoint fixes by Michael Neuling.

  And more ...  I appologize in advance if I've failed to highlight
  something that somebody deemed worth it."

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (156 commits)
  pstore: Add hsize argument in write_buf call of pstore_ftrace_call
  powerpc/fsl: add MPIC timer wakeup support
  powerpc/mpic: create mpic subsystem object
  powerpc/mpic: add global timer support
  powerpc/mpic: add irq_set_wake support
  powerpc/85xx: enable coreint for all the 64bit boards
  powerpc/8xx: Erroneous double irq_eoi() on CPM IRQ in MPC8xx
  powerpc/fsl: Enable CONFIG_E1000E in mpc85xx_smp_defconfig
  powerpc/mpic: Add get_version API both for internal and external use
  powerpc: Handle both new style and old style reserve maps
  powerpc/hw_brk: Fix off by one error when validating DAWR region end
  powerpc/pseries: Support compression of oops text via pstore
  powerpc/pseries: Re-organise the oops compression code
  pstore: Pass header size in the pstore write callback
  powerpc/powernv: Fix iommu initialization again
  powerpc/pseries: Inform the hypervisor we are using EBB regs
  powerpc/perf: Add power8 EBB support
  powerpc/perf: Core EBB support for 64-bit book3s
  powerpc/perf: Drop MMCRA from thread_struct
  powerpc/perf: Don't enable if we have zero events
  ...

19 files changed, 1076 insertions, 263 deletions

diff --git a/arch/powerpc/mm/44x_mmu.c b/arch/powerpc/mm/44x_mmu.c
index 2c9441ee6bb..82b1ff759e2 100644
--- a/arch/powerpc/mm/44x_mmu.c
+++ b/arch/powerpc/mm/44x_mmu.c
@@ -41,7 +41,7 @@ int icache_44x_need_flush;
 
 unsigned long tlb_47x_boltmap[1024/8];
 
-static void __cpuinit ppc44x_update_tlb_hwater(void)
+static void ppc44x_update_tlb_hwater(void)
 {
 	extern unsigned int tlb_44x_patch_hwater_D[];
 	extern unsigned int tlb_44x_patch_hwater_I[];
@@ -134,7 +134,7 @@ static void __init ppc47x_update_boltmap(void)
 /*
  * "Pins" a 256MB TLB entry in AS0 for kernel lowmem for 47x type MMU
  */
-static void __cpuinit ppc47x_pin_tlb(unsigned int virt, unsigned int phys)
+static void ppc47x_pin_tlb(unsigned int virt, unsigned int phys)
 {
 	unsigned int rA;
 	int bolted;
@@ -229,7 +229,7 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 }
 
 #ifdef CONFIG_SMP
-void __cpuinit mmu_init_secondary(int cpu)
+void mmu_init_secondary(int cpu)
 {
 	unsigned long addr;
 	unsigned long memstart = memstart_addr & ~(PPC_PIN_SIZE - 1);
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index cf16b5733ea..51230ee6a40 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -6,17 +6,16 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
-obj-y				:= fault.o mem.o pgtable.o gup.o \
+obj-y				:= fault.o mem.o pgtable.o gup.o mmap.o \
 				   init_$(CONFIG_WORD_SIZE).o \
 				   pgtable_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_PPC_MMU_NOHASH)	+= mmu_context_nohash.o tlb_nohash.o \
 				   tlb_nohash_low.o
 obj-$(CONFIG_PPC_BOOK3E)	+= tlb_low_$(CONFIG_WORD_SIZE)e.o
-obj-$(CONFIG_PPC64)		+= mmap_64.o
 hash64-$(CONFIG_PPC_NATIVE)	:= hash_native_64.o
 obj-$(CONFIG_PPC_STD_MMU_64)	+= hash_utils_64.o \
 				   slb_low.o slb.o stab.o \
-				   mmap_64.o $(hash64-y)
+				   $(hash64-y)
 obj-$(CONFIG_PPC_STD_MMU_32)	+= ppc_mmu_32.o
 obj-$(CONFIG_PPC_STD_MMU)	+= hash_low_$(CONFIG_WORD_SIZE).o \
 				   tlb_hash$(CONFIG_WORD_SIZE).o \
@@ -28,11 +27,12 @@ obj-$(CONFIG_44x)		+= 44x_mmu.o
 obj-$(CONFIG_PPC_FSL_BOOK3E)	+= fsl_booke_mmu.o
 obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
 obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
-ifeq ($(CONFIG_HUGETLB_PAGE),y)
 obj-y				+= hugetlbpage.o
+ifeq ($(CONFIG_HUGETLB_PAGE),y)
 obj-$(CONFIG_PPC_STD_MMU_64)	+= hugetlbpage-hash64.o
 obj-$(CONFIG_PPC_BOOK3E_MMU)	+= hugetlbpage-book3e.o
 endif
+obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += hugepage-hash64.o
 obj-$(CONFIG_PPC_SUBPAGE_PROT)	+= subpage-prot.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c
index 4b921affa49..49822d90ea9 100644
--- a/arch/powerpc/mm/gup.c
+++ b/arch/powerpc/mm/gup.c
@@ -34,7 +34,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 
 	ptep = pte_offset_kernel(&pmd, addr);
 	do {
-		pte_t pte = *ptep;
+		pte_t pte = ACCESS_ONCE(*ptep);
 		struct page *page;
 
 		if ((pte_val(pte) & mask) != result)
@@ -63,12 +63,18 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 
 	pmdp = pmd_offset(&pud, addr);
 	do {
-		pmd_t pmd = *pmdp;
+		pmd_t pmd = ACCESS_ONCE(*pmdp);
 
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
+		/*
+		 * If we find a splitting transparent hugepage we
+		 * return zero. That will result in taking the slow
+		 * path which will call wait_split_huge_page()
+		 * if the pmd is still in splitting state
+		 */
+		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
-		if (pmd_huge(pmd)) {
+		if (pmd_huge(pmd) || pmd_large(pmd)) {
 			if (!gup_hugepte((pte_t *)pmdp, PMD_SIZE, addr, next,
 					 write, pages, nr))
 				return 0;
@@ -91,7 +97,7 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 
 	pudp = pud_offset(&pgd, addr);
 	do {
-		pud_t pud = *pudp;
+		pud_t pud = ACCESS_ONCE(*pudp);
 
 		next = pud_addr_end(addr, end);
 		if (pud_none(pud))
@@ -154,7 +160,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 
 	pgdp = pgd_offset(mm, addr);
 	do {
-		pgd_t pgd = *pgdp;
+		pgd_t pgd = ACCESS_ONCE(*pgdp);
 
 		pr_devel("  %016lx: normal pgd %p\n", addr,
 			 (void *)pgd_val(pgd));
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 0e980acae67..d3cbda62857 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -289,9 +289,10 @@ htab_modify_pte:
 
 	/* Call ppc_md.hpte_updatepp */
 	mr	r5,r29			/* vpn */
-	li	r6,MMU_PAGE_4K		/* page size */
-	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
-	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
+	li	r6,MMU_PAGE_4K		/* base page size */
+	li	r7,MMU_PAGE_4K		/* actual page size */
+	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
 _GLOBAL(htab_call_hpte_updatepp)
 	bl	.			/* Patched by htab_finish_init() */
 
@@ -649,9 +650,10 @@ htab_modify_pte:
 
 	/* Call ppc_md.hpte_updatepp */
 	mr	r5,r29			/* vpn */
-	li	r6,MMU_PAGE_4K		/* page size */
-	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
-	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
+	li	r6,MMU_PAGE_4K		/* base page size */
+	li	r7,MMU_PAGE_4K		/* actual page size */
+	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
 _GLOBAL(htab_call_hpte_updatepp)
 	bl	.			/* patched by htab_finish_init() */
 
@@ -937,9 +939,10 @@ ht64_modify_pte:
 
 	/* Call ppc_md.hpte_updatepp */
 	mr	r5,r29			/* vpn */
-	li	r6,MMU_PAGE_64K
-	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
-	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
+	li	r6,MMU_PAGE_64K		/* base page size */
+	li	r7,MMU_PAGE_64K		/* actual page size */
+	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
 _GLOBAL(ht64_call_hpte_updatepp)
 	bl	.			/* patched by htab_finish_init() */
 
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 4c122c3f162..3f0c30ae479 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -273,61 +273,15 @@ static long native_hpte_remove(unsigned long hpte_group)
 	return i;
 }
 
-static inline int __hpte_actual_psize(unsigned int lp, int psize)
-{
-	int i, shift;
-	unsigned int mask;
-
-	/* start from 1 ignoring MMU_PAGE_4K */
-	for (i = 1; i < MMU_PAGE_COUNT; i++) {
-
-		/* invalid penc */
-		if (mmu_psize_defs[psize].penc[i] == -1)
-			continue;
-		/*
-		 * encoding bits per actual page size
-		 *        PTE LP     actual page size
-		 *    rrrr rrrz		>=8KB
-		 *    rrrr rrzz		>=16KB
-		 *    rrrr rzzz		>=32KB
-		 *    rrrr zzzz		>=64KB
-		 * .......
-		 */
-		shift = mmu_psize_defs[i].shift - LP_SHIFT;
-		if (shift > LP_BITS)
-			shift = LP_BITS;
-		mask = (1 << shift) - 1;
-		if ((lp & mask) == mmu_psize_defs[psize].penc[i])
-			return i;
-	}
-	return -1;
-}
-
-static inline int hpte_actual_psize(struct hash_pte *hptep, int psize)
-{
-	/* Look at the 8 bit LP value */
-	unsigned int lp = (hptep->r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
-
-	if (!(hptep->v & HPTE_V_VALID))
-		return -1;
-
-	/* First check if it is large page */
-	if (!(hptep->v & HPTE_V_LARGE))
-		return MMU_PAGE_4K;
-
-	return __hpte_actual_psize(lp, psize);
-}
-
 static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
-				 unsigned long vpn, int psize, int ssize,
-				 int local)
+				 unsigned long vpn, int bpsize,
+				 int apsize, int ssize, int local)
 {
 	struct hash_pte *hptep = htab_address + slot;
 	unsigned long hpte_v, want_v;
 	int ret = 0;
-	int actual_psize;
 
-	want_v = hpte_encode_avpn(vpn, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, bpsize, ssize);
 
 	DBG_LOW("    update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)",
 		vpn, want_v & HPTE_V_AVPN, slot, newpp);
@@ -335,7 +289,6 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	native_lock_hpte(hptep);
 
 	hpte_v = hptep->v;
-	actual_psize = hpte_actual_psize(hptep, psize);
 	/*
 	 * We need to invalidate the TLB always because hpte_remove doesn't do
 	 * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
@@ -343,12 +296,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	 * (hpte_remove) because we assume the old translation is still
 	 * technically "valid".
 	 */
-	if (actual_psize < 0) {
-		actual_psize = psize;
-		ret = -1;
-		goto err_out;
-	}
-	if (!HPTE_V_COMPARE(hpte_v, want_v)) {
+	if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) {
 		DBG_LOW(" -> miss\n");
 		ret = -1;
 	} else {
@@ -357,11 +305,10 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 		hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
 			(newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C));
 	}
-err_out:
 	native_unlock_hpte(hptep);
 
 	/* Ensure it is out of the tlb too. */
-	tlbie(vpn, psize, actual_psize, ssize, local);
+	tlbie(vpn, bpsize, apsize, ssize, local);
 
 	return ret;
 }
@@ -402,7 +349,6 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize)
 static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 				       int psize, int ssize)
 {
-	int actual_psize;
 	unsigned long vpn;
 	unsigned long vsid;
 	long slot;
@@ -415,36 +361,33 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	if (slot == -1)
 		panic("could not find page to bolt\n");
 	hptep = htab_address + slot;
-	actual_psize = hpte_actual_psize(hptep, psize);
-	if (actual_psize < 0)
-		actual_psize = psize;
 
 	/* Update the HPTE */
 	hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
 		(newpp & (HPTE_R_PP | HPTE_R_N));
-
-	/* Ensure it is out of the tlb too. */
-	tlbie(vpn, psize, actual_psize, ssize, 0);
+	/*
+	 * Ensure it is out of the tlb too. Bolted entries base and
+	 * actual page size will be same.
+	 */
+	tlbie(vpn, psize, psize, ssize, 0);
 }
 
 static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
-				   int psize, int ssize, int local)
+				   int bpsize, int apsize, int ssize, int local)
 {
 	struct hash_pte *hptep = htab_address + slot;
 	unsigned long hpte_v;
 	unsigned long want_v;
 	unsigned long flags;
-	int actual_psize;
 
 	local_irq_save(flags);
 
 	DBG_LOW("    invalidate(vpn=%016lx, hash: %lx)\n", vpn, slot);
 
-	want_v = hpte_encode_avpn(vpn, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, bpsize, ssize);
 	native_lock_hpte(hptep);
 	hpte_v = hptep->v;
 
-	actual_psize = hpte_actual_psize(hptep, psize);
 	/*
 	 * We need to invalidate the TLB always because hpte_remove doesn't do
 	 * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
@@ -452,23 +395,120 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	 * (hpte_remove) because we assume the old translation is still
 	 * technically "valid".
 	 */
-	if (actual_psize < 0) {
-		actual_psize = psize;
-		native_unlock_hpte(hptep);
-		goto err_out;
-	}
-	if (!HPTE_V_COMPARE(hpte_v, want_v))
+	if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
 		native_unlock_hpte(hptep);
 	else
 		/* Invalidate the hpte. NOTE: this also unlocks it */
 		hptep->v = 0;
 
-err_out:
 	/* Invalidate the TLB */
-	tlbie(vpn, psize, actual_psize, ssize, local);
+	tlbie(vpn, bpsize, apsize, ssize, local);
+
+	local_irq_restore(flags);
+}
+
+static void native_hugepage_invalidate(struct mm_struct *mm,
+				       unsigned char *hpte_slot_array,
+				       unsigned long addr, int psize)
+{
+	int ssize = 0, i;
+	int lock_tlbie;
+	struct hash_pte *hptep;
+	int actual_psize = MMU_PAGE_16M;
+	unsigned int max_hpte_count, valid;
+	unsigned long flags, s_addr = addr;
+	unsigned long hpte_v, want_v, shift;
+	unsigned long hidx, vpn = 0, vsid, hash, slot;
+
+	shift = mmu_psize_defs[psize].shift;
+	max_hpte_count = 1U << (PMD_SHIFT - shift);
+
+	local_irq_save(flags);
+	for (i = 0; i < max_hpte_count; i++) {
+		valid = hpte_valid(hpte_slot_array, i);
+		if (!valid)
+			continue;
+		hidx =  hpte_hash_index(hpte_slot_array, i);
+
+		/* get the vpn */
+		addr = s_addr + (i * (1ul << shift));
+		if (!is_kernel_addr(addr)) {
+			ssize = user_segment_size(addr);
+			vsid = get_vsid(mm->context.id, addr, ssize);
+			WARN_ON(vsid == 0);
+		} else {
+			vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
+			ssize = mmu_kernel_ssize;
+		}
+
+		vpn = hpt_vpn(addr, vsid, ssize);
+		hash = hpt_hash(vpn, shift, ssize);
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+
+		hptep = htab_address + slot;
+		want_v = hpte_encode_avpn(vpn, psize, ssize);
+		native_lock_hpte(hptep);
+		hpte_v = hptep->v;
+
+		/* Even if we miss, we need to invalidate the TLB */
+		if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
+			native_unlock_hpte(hptep);
+		else
+			/* Invalidate the hpte. NOTE: this also unlocks it */
+			hptep->v = 0;
+	}
+	/*
+	 * Since this is a hugepage, we just need a single tlbie.
+	 * use the last vpn.
+	 */
+	lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+	if (lock_tlbie)
+		raw_spin_lock(&native_tlbie_lock);
+
+	asm volatile("ptesync":::"memory");
+	__tlbie(vpn, psize, actual_psize, ssize);
+	asm volatile("eieio; tlbsync; ptesync":::"memory");
+
+	if (lock_tlbie)
+		raw_spin_unlock(&native_tlbie_lock);
+
 	local_irq_restore(flags);
 }
 
+static inline int __hpte_actual_psize(unsigned int lp, int psize)
+{
+	int i, shift;
+	unsigned int mask;
+
+	/* start from 1 ignoring MMU_PAGE_4K */
+	for (i = 1; i < MMU_PAGE_COUNT; i++) {
+
+		/* invalid penc */
+		if (mmu_psize_defs[psize].penc[i] == -1)
+			continue;
+		/*
+		 * encoding bits per actual page size
+		 *        PTE LP     actual page size
+		 *    rrrr rrrz		>=8KB
+		 *    rrrr rrzz		>=16KB
+		 *    rrrr rzzz		>=32KB
+		 *    rrrr zzzz		>=64KB
+		 * .......
+		 */
+		shift = mmu_psize_defs[i].shift - LP_SHIFT;
+		if (shift > LP_BITS)
+			shift = LP_BITS;
+		mask = (1 << shift) - 1;
+		if ((lp & mask) == mmu_psize_defs[psize].penc[i])
+			return i;
+	}
+	return -1;
+}
+
 static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 			int *psize, int *apsize, int *ssize, unsigned long *vpn)
 {
@@ -672,4 +712,5 @@ void __init hpte_init_native(void)
 	ppc_md.hpte_remove	= native_hpte_remove;
 	ppc_md.hpte_clear_all	= native_hpte_clear;
 	ppc_md.flush_hash_range = native_flush_hash_range;
+	ppc_md.hugepage_invalidate   = native_hugepage_invalidate;
 }
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index e303a6d74e3..6ecc38bd5b2 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -807,7 +807,7 @@ void __init early_init_mmu(void)
 }
 
 #ifdef CONFIG_SMP
-void __cpuinit early_init_mmu_secondary(void)
+void early_init_mmu_secondary(void)
 {
 	/* Initialize hash table for that CPU */
 	if (!firmware_has_feature(FW_FEATURE_LPAR))
@@ -1050,13 +1050,26 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 		goto bail;
 	}
 
-#ifdef CONFIG_HUGETLB_PAGE
 	if (hugeshift) {
-		rc = __hash_page_huge(ea, access, vsid, ptep, trap, local,
-					ssize, hugeshift, psize);
+		if (pmd_trans_huge(*(pmd_t *)ptep))
+			rc = __hash_page_thp(ea, access, vsid, (pmd_t *)ptep,
+					     trap, local, ssize, psize);
+#ifdef CONFIG_HUGETLB_PAGE
+		else
+			rc = __hash_page_huge(ea, access, vsid, ptep, trap,
+					      local, ssize, hugeshift, psize);
+#else
+		else {
+			/*
+			 * if we have hugeshift, and is not transhuge with
+			 * hugetlb disabled, something is really wrong.
+			 */
+			rc = 1;
+			WARN_ON(1);
+		}
+#endif
 		goto bail;
 	}
-#endif /* CONFIG_HUGETLB_PAGE */
 
 #ifndef CONFIG_PPC_64K_PAGES
 	DBG_LOW(" i-pte: %016lx\n", pte_val(*ptep));
@@ -1145,6 +1158,7 @@ EXPORT_SYMBOL_GPL(hash_page);
 void hash_preload(struct mm_struct *mm, unsigned long ea,
 		  unsigned long access, unsigned long trap)
 {
+	int hugepage_shift;
 	unsigned long vsid;
 	pgd_t *pgdir;
 	pte_t *ptep;
@@ -1166,10 +1180,27 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 	pgdir = mm->pgd;
 	if (pgdir == NULL)
 		return;
-	ptep = find_linux_pte(pgdir, ea);
-	if (!ptep)
+
+	/* Get VSID */
+	ssize = user_segment_size(ea);
+	vsid = get_vsid(mm->context.id, ea, ssize);
+	if (!vsid)
 		return;
+	/*
+	 * Hash doesn't like irqs. Walking linux page table with irq disabled
+	 * saves us from holding multiple locks.
+	 */
+	local_irq_save(flags);
+
+	/*
+	 * THP pages use update_mmu_cache_pmd. We don't do
+	 * hash preload there. Hence can ignore THP here
+	 */
+	ptep = find_linux_pte_or_hugepte(pgdir, ea, &hugepage_shift);
+	if (!ptep)
+		goto out_exit;
 
+	WARN_ON(hugepage_shift);
 #ifdef CONFIG_PPC_64K_PAGES
 	/* If either _PAGE_4K_PFN or _PAGE_NO_CACHE is set (and we are on
 	 * a 64K kernel), then we don't preload, hash_page() will take
@@ -1178,18 +1209,9 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 	 * page size demotion here
 	 */
 	if (pte_val(*ptep) & (_PAGE_4K_PFN | _PAGE_NO_CACHE))
-		return;
+		goto out_exit;
 #endif /* CONFIG_PPC_64K_PAGES */
 
-	/* Get VSID */
-	ssize = user_segment_size(ea);
-	vsid = get_vsid(mm->context.id, ea, ssize);
-	if (!vsid)
-		return;
-
-	/* Hash doesn't like irqs */
-	local_irq_save(flags);
-
 	/* Is that local to this CPU ? */
 	if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
 		local = 1;
@@ -1211,7 +1233,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 				   mm->context.user_psize,
 				   mm->context.user_psize,
 				   pte_val(*ptep));
-
+out_exit:
 	local_irq_restore(flags);
 }
 
@@ -1232,7 +1254,11 @@ void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += hidx & _PTEIDX_GROUP_IX;
 		DBG_LOW(" sub %ld: hash=%lx, hidx=%lx\n", index, slot, hidx);
-		ppc_md.hpte_invalidate(slot, vpn, psize, ssize, local);
+		/*
+		 * We use same base page size and actual psize, because we don't
+		 * use these functions for hugepage
+		 */
+		ppc_md.hpte_invalidate(slot, vpn, psize, psize, ssize, local);
 	} pte_iterate_hashed_end();
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -1365,7 +1391,8 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
 		hash = ~hash;
 	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 	slot += hidx & _PTEIDX_GROUP_IX;
-	ppc_md.hpte_invalidate(slot, vpn, mmu_linear_psize, mmu_kernel_ssize, 0);
+	ppc_md.hpte_invalidate(slot, vpn, mmu_linear_psize, mmu_linear_psize,
+			       mmu_kernel_ssize, 0);
 }
 
 void kernel_map_pages(struct page *page, int numpages, int enable)
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
new file mode 100644
index 00000000000..34de9e0cdc3
--- /dev/null
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -0,0 +1,175 @@
+/*
+ * Copyright IBM Corporation, 2013
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+/*
+ * PPC64 THP Support for hash based MMUs
+ */
+#include <linux/mm.h>
+#include <asm/machdep.h>
+
+int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
+		    pmd_t *pmdp, unsigned long trap, int local, int ssize,
+		    unsigned int psize)
+{
+	unsigned int index, valid;
+	unsigned char *hpte_slot_array;
+	unsigned long rflags, pa, hidx;
+	unsigned long old_pmd, new_pmd;
+	int ret, lpsize = MMU_PAGE_16M;
+	unsigned long vpn, hash, shift, slot;
+
+	/*
+	 * atomically mark the linux large page PMD busy and dirty
+	 */
+	do {
+		old_pmd = pmd_val(*pmdp);
+		/* If PMD busy, retry the access */
+		if (unlikely(old_pmd & _PAGE_BUSY))
+			return 0;
+		/* If PMD is trans splitting retry the access */
+		if (unlikely(old_pmd & _PAGE_SPLITTING))
+			return 0;
+		/* If PMD permissions don't match, take page fault */
+		if (unlikely(access & ~old_pmd))
+			return 1;
+		/*
+		 * Try to lock the PTE, add ACCESSED and DIRTY if it was
+		 * a write access
+		 */
+		new_pmd = old_pmd | _PAGE_BUSY | _PAGE_ACCESSED;
+		if (access & _PAGE_RW)
+			new_pmd |= _PAGE_DIRTY;
+	} while (old_pmd != __cmpxchg_u64((unsigned long *)pmdp,
+					  old_pmd, new_pmd));
+	/*
+	 * PP bits. _PAGE_USER is already PP bit 0x2, so we only
+	 * need to add in 0x1 if it's a read-only user page
+	 */
+	rflags = new_pmd & _PAGE_USER;
+	if ((new_pmd & _PAGE_USER) && !((new_pmd & _PAGE_RW) &&
+					   (new_pmd & _PAGE_DIRTY)))
+		rflags |= 0x1;
+	/*
+	 * _PAGE_EXEC -> HW_NO_EXEC since it's inverted
+	 */
+	rflags |= ((new_pmd & _PAGE_EXEC) ? 0 : HPTE_R_N);
+
+#if 0
+	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) {
+
+		/*
+		 * No CPU has hugepages but lacks no execute, so we
+		 * don't need to worry about that case
+		 */
+		rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap);
+	}
+#endif
+	/*
+	 * Find the slot index details for this ea, using base page size.
+	 */
+	shift = mmu_psize_defs[psize].shift;
+	index = (ea & ~HPAGE_PMD_MASK) >> shift;
+	BUG_ON(index >= 4096);
+
+	vpn = hpt_vpn(ea, vsid, ssize);
+	hash = hpt_hash(vpn, shift, ssize);
+	hpte_slot_array = get_hpte_slot_array(pmdp);
+
+	valid = hpte_valid(hpte_slot_array, index);
+	if (valid) {
+		/* update the hpte bits */
+		hidx =  hpte_hash_index(hpte_slot_array, index);
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+
+		ret = ppc_md.hpte_updatepp(slot, rflags, vpn,
+					   psize, lpsize, ssize, local);
+		/*
+		 * We failed to update, try to insert a new entry.
+		 */
+		if (ret == -1) {
+			/*
+			 * large pte is marked busy, so we can be sure
+			 * nobody is looking at hpte_slot_array. hence we can
+			 * safely update this here.
+			 */
+			valid = 0;
+			new_pmd &= ~_PAGE_HPTEFLAGS;
+			hpte_slot_array[index] = 0;
+		} else
+			/* clear the busy bits and set the hash pte bits */
+			new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
+	}
+
+	if (!valid) {
+		unsigned long hpte_group;
+
+		/* insert new entry */
+		pa = pmd_pfn(__pmd(old_pmd)) << PAGE_SHIFT;
+repeat:
+		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
+
+		/* clear the busy bits and set the hash pte bits */
+		new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
+
+		/* Add in WIMG bits */
+		rflags |= (new_pmd & (_PAGE_WRITETHRU | _PAGE_NO_CACHE |
+				      _PAGE_COHERENT | _PAGE_GUARDED));
+
+		/* Insert into the hash table, primary slot */
+		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
+					  psize, lpsize, ssize);
+		/*
+		 * Primary is full, try the secondary
+		 */
+		if (unlikely(slot == -1)) {
+			hpte_group = ((~hash & htab_hash_mask) *
+				      HPTES_PER_GROUP) & ~0x7UL;
+			slot = ppc_md.hpte_insert(hpte_group, vpn, pa,
+						  rflags, HPTE_V_SECONDARY,
+						  psize, lpsize, ssize);
+			if (slot == -1) {
+				if (mftb() & 0x1)
+					hpte_group = ((hash & htab_hash_mask) *
+						      HPTES_PER_GROUP) & ~0x7UL;
+
+				ppc_md.hpte_remove(hpte_group);
+				goto repeat;
+			}
+		}
+		/*
+		 * Hypervisor failure. Restore old pmd and return -1
+		 * similar to __hash_page_*
+		 */
+		if (unlikely(slot == -2)) {
+			*pmdp = __pmd(old_pmd);
+			hash_failure_debug(ea, access, vsid, trap, ssize,
+					   psize, lpsize, old_pmd);
+			return -1;
+		}
+		/*
+		 * large pte is marked busy, so we can be sure
+		 * nobody is looking at hpte_slot_array. hence we can
+		 * safely update this here.
+		 */
+		mark_hpte_slot_valid(hpte_slot_array, index, slot);
+	}
+	/*
+	 * No need to use ldarx/stdcx here
+	 */
+	*pmdp = __pmd(new_pmd & ~_PAGE_BUSY);
+	return 0;
+}
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index 0f1d94a1fb8..0b7fb676101 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -81,7 +81,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		slot += (old_pte & _PAGE_F_GIX) >> 12;
 
 		if (ppc_md.hpte_updatepp(slot, rflags, vpn, mmu_psize,
-					 ssize, local) == -1)
+					 mmu_psize, ssize, local) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}
 
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 4210549ac95..834ca8eb38f 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -21,6 +21,9 @@
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 #include <asm/setup.h>
+#include <asm/hugetlb.h>
+
+#ifdef CONFIG_HUGETLB_PAGE
 
 #define PAGE_SHIFT_64K	16
 #define PAGE_SHIFT_16M	24
@@ -100,68 +103,9 @@ int pgd_huge(pgd_t pgd)
 }
 #endif
 
-/*
- * We have 4 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, bottom two bits != 00
- * (4) hugepd pointer, bottom two bits == 00, next 4 bits indicate size of table
- */
-pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
-{
-	pgd_t *pg;
-	pud_t *pu;
-	pmd_t *pm;
-	pte_t *ret_pte;
-	hugepd_t *hpdp = NULL;
-	unsigned pdshift = PGDIR_SHIFT;
-
-	if (shift)
-		*shift = 0;
-
-	pg = pgdir + pgd_index(ea);
-
-	if (pgd_huge(*pg)) {
-		ret_pte = (pte_t *) pg;
-		goto out;
-	} else if (is_hugepd(pg))
-		hpdp = (hugepd_t *)pg;
-	else if (!pgd_none(*pg)) {
-		pdshift = PUD_SHIFT;
-		pu = pud_offset(pg, ea);
-
-		if (pud_huge(*pu)) {
-			ret_pte = (pte_t *) pu;
-			goto out;
-		} else if (is_hugepd(pu))
-			hpdp = (hugepd_t *)pu;
-		else if (!pud_none(*pu)) {
-			pdshift = PMD_SHIFT;
-			pm = pmd_offset(pu, ea);
-
-			if (pmd_huge(*pm)) {
-				ret_pte = (pte_t *) pm;
-				goto out;
-			} else if (is_hugepd(pm))
-				hpdp = (hugepd_t *)pm;
-			else if (!pmd_none(*pm))
-				return pte_offset_kernel(pm, ea);
-		}
-	}
-	if (!hpdp)
-		return NULL;
-
-	ret_pte = hugepte_offset(hpdp, ea, pdshift);
-	pdshift = hugepd_shift(*hpdp);
-out:
-	if (shift)
-		*shift = pdshift;
-	return ret_pte;
-}
-EXPORT_SYMBOL_GPL(find_linux_pte_or_hugepte);
-
 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);
 }
 
@@ -736,11 +680,14 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
 	struct page *page;
 	unsigned shift;
 	unsigned long mask;
-
+	/*
+	 * Transparent hugepages are handled by generic code. We can skip them
+	 * here.
+	 */
 	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
 
 	/* Verify it is a huge page else bail. */
-	if (!ptep || !shift)
+	if (!ptep || !shift || pmd_trans_huge(*(pmd_t *)ptep))
 		return ERR_PTR(-EINVAL);
 
 	mask = (1UL << shift) - 1;
@@ -759,69 +706,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 	return NULL;
 }
 
-int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long mask;
-	unsigned long pte_end;
-	struct page *head, *page, *tail;
-	pte_t pte;
-	int refs;
-
-	pte_end = (addr + sz) & ~(sz-1);
-	if (pte_end < end)
-		end = pte_end;
-
-	pte = *ptep;
-	mask = _PAGE_PRESENT | _PAGE_USER;
-	if (write)
-		mask |= _PAGE_RW;
-
-	if ((pte_val(pte) & mask) != mask)
-		return 0;
-
-	/* hugepages are never "special" */
-	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-
-	refs = 0;
-	head = pte_page(pte);
-
-	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
-	tail = page;
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
-		return 0;
-	}
-
-	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-		/* Could be optimized better */
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
-		return 0;
-	}
-
-	/*
-	 * Any tail page need their mapcount reference taken before we
-	 * return.
-	 */
-	while (refs--) {
-		if (PageTail(tail))
-			get_huge_page_tail(tail);
-		tail++;
-	}
-
-	return 1;
-}
-
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 				      unsigned long sz)
 {
@@ -1038,3 +922,168 @@ void flush_dcache_icache_hugepage(struct page *page)
 		}
 	}
 }
+
+#endif /* CONFIG_HUGETLB_PAGE */
+
+/*
+ * We have 4 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, bottom two bits != 00
+ * (4) hugepd pointer, bottom two bits == 00, next 4 bits 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 the page and take a ref on it.
+ */
+
+pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
+{
+	pgd_t pgd, *pgdp;
+	pud_t pud, *pudp;
+	pmd_t pmd, *pmdp;
+	pte_t *ret_pte;
+	hugepd_t *hpdp = NULL;
+	unsigned pdshift = PGDIR_SHIFT;
+
+	if (shift)
+		*shift = 0;
+
+	pgdp = pgdir + pgd_index(ea);
+	pgd  = ACCESS_ONCE(*pgdp);
+	/*
+	 * Always operate on the local stack value. This make sure the
+	 * value don't get updated by a parallel THP split/collapse,
+	 * page fault or a page unmap. The return pte_t * is still not
+	 * stable. So should be checked there for above conditions.
+	 */
+	if (pgd_none(pgd))
+		return NULL;
+	else if (pgd_huge(pgd)) {
+		ret_pte = (pte_t *) pgdp;
+		goto out;
+	} else if (is_hugepd(&pgd))
+		hpdp = (hugepd_t *)&pgd;
+	else {
+		/*
+		 * Even if we end up with an unmap, the pgtable will not
+		 * be freed, because we do an rcu free and here we are
+		 * irq disabled
+		 */
+		pdshift = PUD_SHIFT;
+		pudp = pud_offset(&pgd, ea);
+		pud  = ACCESS_ONCE(*pudp);
+
+		if (pud_none(pud))
+			return NULL;
+		else if (pud_huge(pud)) {
+			ret_pte = (pte_t *) pudp;
+			goto out;
+		} else if (is_hugepd(&pud))
+			hpdp = (hugepd_t *)&pud;
+		else {
+			pdshift = PMD_SHIFT;
+			pmdp = pmd_offset(&pud, ea);
+			pmd  = ACCESS_ONCE(*pmdp);
+			/*
+			 * A hugepage collapse is captured by pmd_none, because
+			 * it mark the pmd none and do a hpte invalidate.
+			 *
+			 * A hugepage split is captured by pmd_trans_splitting
+			 * because we mark the pmd trans splitting and do a
+			 * hpte invalidate
+			 *
+			 */
+			if (pmd_none(pmd) || pmd_trans_splitting(pmd))
+				return NULL;
+
+			if (pmd_huge(pmd) || pmd_large(pmd)) {
+				ret_pte = (pte_t *) pmdp;
+				goto out;
+			} else if (is_hugepd(&pmd))
+				hpdp = (hugepd_t *)&pmd;
+			else
+				return pte_offset_kernel(&pmd, ea);
+		}
+	}
+	if (!hpdp)
+		return NULL;
+
+	ret_pte = hugepte_offset(hpdp, ea, pdshift);
+	pdshift = hugepd_shift(*hpdp);
+out:
+	if (shift)
+		*shift = pdshift;
+	return ret_pte;
+}
+EXPORT_SYMBOL_GPL(find_linux_pte_or_hugepte);
+
+int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
+		unsigned long end, int write, struct page **pages, int *nr)
+{
+	unsigned long mask;
+	unsigned long pte_end;
+	struct page *head, *page, *tail;
+	pte_t pte;
+	int refs;
+
+	pte_end = (addr + sz) & ~(sz-1);
+	if (pte_end < end)
+		end = pte_end;
+
+	pte = ACCESS_ONCE(*ptep);
+	mask = _PAGE_PRESENT | _PAGE_USER;
+	if (write)
+		mask |= _PAGE_RW;
+
+	if ((pte_val(pte) & mask) != mask)
+		return 0;
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	/*
+	 * check for splitting here
+	 */
+	if (pmd_trans_splitting(pte_pmd(pte)))
+		return 0;
+#endif
+
+	/* hugepages are never "special" */
+	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+	refs = 0;
+	head = pte_page(pte);
+
+	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+	tail = page;
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	if (!page_cache_add_speculative(head, refs)) {
+		*nr -= refs;
+		return 0;
+	}
+
+	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+		/* Could be optimized better */
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+
+	/*
+	 * Any tail page need their mapcount reference taken before we
+	 * return.
+	 */
+	while (refs--) {
+		if (PageTail(tail))
+			get_huge_page_tail(tail);
+		tail++;
+	}
+
+	return 1;
+}
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index a90b9c45899..d0cd9e4c683 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -88,7 +88,11 @@ static void pgd_ctor(void *addr)
 
 static void pmd_ctor(void *addr)
 {
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	memset(addr, 0, PMD_TABLE_SIZE * 2);
+#else
 	memset(addr, 0, PMD_TABLE_SIZE);
+#endif
 }
 
 struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
@@ -137,10 +141,9 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
 void pgtable_cache_init(void)
 {
 	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
-	pgtable_cache_add(PMD_INDEX_SIZE, pmd_ctor);
-	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_INDEX_SIZE))
+	pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
+	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_CACHE_INDEX))
 		panic("Couldn't allocate pgtable caches");
-
 	/* In all current configs, when the PUD index exists it's the
 	 * same size as either the pgd or pmd index.  Verify that the
 	 * initialization above has also created a PUD cache.  This
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 1cb1ea133a2..7f4bea16202 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -461,6 +461,10 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
 		      pte_t *ptep)
 {
 #ifdef CONFIG_PPC_STD_MMU
+	/*
+	 * We don't need to worry about _PAGE_PRESENT here because we are
+	 * called with either mm->page_table_lock held or ptl lock held
+	 */
 	unsigned long access = 0, trap;
 
 	/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
diff --git a/arch/powerpc/mm/mmap_64.c b/arch/powerpc/mm/mmap.c
index 67a42ed0d2f..67a42ed0d2f 100644
--- a/arch/powerpc/mm/mmap_64.c
+++ b/arch/powerpc/mm/mmap.c
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index e779642c25e..af3d78e1930 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -112,8 +112,10 @@ static unsigned int steal_context_smp(unsigned int id)
 		 */
 		for_each_cpu(cpu, mm_cpumask(mm)) {
 			for (i = cpu_first_thread_sibling(cpu);
-			     i <= cpu_last_thread_sibling(cpu); i++)
-				__set_bit(id, stale_map[i]);
+			     i <= cpu_last_thread_sibling(cpu); i++) {
+				if (stale_map[i])
+					__set_bit(id, stale_map[i]);
+			}
 			cpu = i - 1;
 		}
 		return id;
@@ -272,7 +274,8 @@ void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next)
 		/* XXX This clear should ultimately be part of local_flush_tlb_mm */
 		for (i = cpu_first_thread_sibling(cpu);
 		     i <= cpu_last_thread_sibling(cpu); i++) {
-			__clear_bit(id, stale_map[i]);
+			if (stale_map[i])
+				__clear_bit(id, stale_map[i]);
 		}
 	}
 
@@ -329,8 +332,8 @@ void destroy_context(struct mm_struct *mm)
 
 #ifdef CONFIG_SMP
 
-static int __cpuinit mmu_context_cpu_notify(struct notifier_block *self,
-					    unsigned long action, void *hcpu)
+static int mmu_context_cpu_notify(struct notifier_block *self,
+				  unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned int)(long)hcpu;
 
@@ -363,7 +366,7 @@ static int __cpuinit mmu_context_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata mmu_context_cpu_nb = {
+static struct notifier_block mmu_context_cpu_nb = {
 	.notifier_call	= mmu_context_cpu_notify,
 };
 
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 88c0425dc0a..08397217e8a 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -516,7 +516,7 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem,
  * Figure out to which domain a cpu belongs and stick it there.
  * Return the id of the domain used.
  */
-static int __cpuinit numa_setup_cpu(unsigned long lcpu)
+static int numa_setup_cpu(unsigned long lcpu)
 {
 	int nid = 0;
 	struct device_node *cpu = of_get_cpu_node(lcpu, NULL);
@@ -538,8 +538,7 @@ out:
 	return nid;
 }
 
-static int __cpuinit cpu_numa_callback(struct notifier_block *nfb,
-			     unsigned long action,
+static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action,
 			     void *hcpu)
 {
 	unsigned long lcpu = (unsigned long)hcpu;
@@ -919,7 +918,7 @@ static void __init *careful_zallocation(int nid, unsigned long size,
 	return ret;
 }
 
-static struct notifier_block __cpuinitdata ppc64_numa_nb = {
+static struct notifier_block ppc64_numa_nb = {
 	.notifier_call = cpu_numa_callback,
 	.priority = 1 /* Must run before sched domains notifier. */
 };
@@ -1433,11 +1432,9 @@ static int update_cpu_topology(void *data)
 		if (cpu != update->cpu)
 			continue;
 
-		unregister_cpu_under_node(update->cpu, update->old_nid);
 		unmap_cpu_from_node(update->cpu);
 		map_cpu_to_node(update->cpu, update->new_nid);
 		vdso_getcpu_init();
-		register_cpu_under_node(update->cpu, update->new_nid);
 	}
 
 	return 0;
@@ -1485,6 +1482,9 @@ int arch_update_cpu_topology(void)
 	stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
 
 	for (ud = &updates[0]; ud; ud = ud->next) {
+		unregister_cpu_under_node(ud->cpu, ud->old_nid);
+		register_cpu_under_node(ud->cpu, ud->new_nid);
+
 		dev = get_cpu_device(ud->cpu);
 		if (dev)
 			kobject_uevent(&dev->kobj, KOBJ_CHANGE);
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 214130a4edc..edda589795c 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -235,6 +235,14 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr)
 	pud = pud_offset(pgd, addr);
 	BUG_ON(pud_none(*pud));
 	pmd = pmd_offset(pud, addr);
+	/*
+	 * khugepaged to collapse normal pages to hugepage, first set
+	 * pmd to none to force page fault/gup to take mmap_sem. After
+	 * pmd is set to none, we do a pte_clear which does this assertion
+	 * so if we find pmd none, return.
+	 */
+	if (pmd_none(*pmd))
+		return;
 	BUG_ON(!pmd_present(*pmd));
 	assert_spin_locked(pte_lockptr(mm, pmd));
 }
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index a854096e102..536eec72c0f 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -338,6 +338,19 @@ EXPORT_SYMBOL(iounmap);
 EXPORT_SYMBOL(__iounmap);
 EXPORT_SYMBOL(__iounmap_at);
 
+/*
+ * For hugepage we have pfn in the pmd, we use PTE_RPN_SHIFT bits for flags
+ * For PTE page, we have a PTE_FRAG_SIZE (4K) aligned virtual address.
+ */
+struct page *pmd_page(pmd_t pmd)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (pmd_trans_huge(pmd))
+		return pfn_to_page(pmd_pfn(pmd));
+#endif
+	return virt_to_page(pmd_page_vaddr(pmd));
+}
+
 #ifdef CONFIG_PPC_64K_PAGES
 static pte_t *get_from_cache(struct mm_struct *mm)
 {
@@ -455,3 +468,404 @@ void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
 }
 #endif
 #endif /* CONFIG_PPC_64K_PAGES */
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+/*
+ * This is called when relaxing access to a hugepage. It's also called in the page
+ * fault path when we don't hit any of the major fault cases, ie, a minor
+ * update of _PAGE_ACCESSED, _PAGE_DIRTY, etc... The generic code will have
+ * handled those two for us, we additionally deal with missing execute
+ * permission here on some processors
+ */
+int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp, pmd_t entry, int dirty)
+{
+	int changed;
+#ifdef CONFIG_DEBUG_VM
+	WARN_ON(!pmd_trans_huge(*pmdp));
+	assert_spin_locked(&vma->vm_mm->page_table_lock);
+#endif
+	changed = !pmd_same(*(pmdp), entry);
+	if (changed) {
+		__ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry));
+		/*
+		 * Since we are not supporting SW TLB systems, we don't
+		 * have any thing similar to flush_tlb_page_nohash()
+		 */
+	}
+	return changed;
+}
+
+unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
+				  pmd_t *pmdp, unsigned long clr)
+{
+
+	unsigned long old, tmp;
+
+#ifdef CONFIG_DEBUG_VM
+	WARN_ON(!pmd_trans_huge(*pmdp));
+	assert_spin_locked(&mm->page_table_lock);
+#endif
+
+#ifdef PTE_ATOMIC_UPDATES
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%3\n\
+		andi.	%1,%0,%6\n\
+		bne-	1b \n\
+		andc	%1,%0,%4 \n\
+		stdcx.	%1,0,%3 \n\
+		bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*pmdp)
+	: "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY)
+	: "cc" );
+#else
+	old = pmd_val(*pmdp);
+	*pmdp = __pmd(old & ~clr);
+#endif
+	if (old & _PAGE_HASHPTE)
+		hpte_do_hugepage_flush(mm, addr, pmdp);
+	return old;
+}
+
+pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address,
+		       pmd_t *pmdp)
+{
+	pmd_t pmd;
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	if (pmd_trans_huge(*pmdp)) {
+		pmd = pmdp_get_and_clear(vma->vm_mm, address, pmdp);
+	} else {
+		/*
+		 * khugepaged calls this for normal pmd
+		 */
+		pmd = *pmdp;
+		pmd_clear(pmdp);
+		/*
+		 * Wait for all pending hash_page to finish. This is needed
+		 * in case of subpage collapse. When we collapse normal pages
+		 * to hugepage, we first clear the pmd, then invalidate all
+		 * the PTE entries. The assumption here is that any low level
+		 * page fault will see a none pmd and take the slow path that
+		 * will wait on mmap_sem. But we could very well be in a
+		 * hash_page with local ptep pointer value. Such a hash page
+		 * can result in adding new HPTE entries for normal subpages.
+		 * That means we could be modifying the page content as we
+		 * copy them to a huge page. So wait for parallel hash_page
+		 * to finish before invalidating HPTE entries. We can do this
+		 * by sending an IPI to all the cpus and executing a dummy
+		 * function there.
+		 */
+		kick_all_cpus_sync();
+		/*
+		 * Now invalidate the hpte entries in the range
+		 * covered by pmd. This make sure we take a
+		 * fault and will find the pmd as none, which will
+		 * result in a major fault which takes mmap_sem and
+		 * hence wait for collapse to complete. Without this
+		 * the __collapse_huge_page_copy can result in copying
+		 * the old content.
+		 */
+		flush_tlb_pmd_range(vma->vm_mm, &pmd, address);
+	}
+	return pmd;
+}
+
+int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+			      unsigned long address, pmd_t *pmdp)
+{
+	return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp);
+}
+
+/*
+ * We currently remove entries from the hashtable regardless of whether
+ * the entry was young or dirty. The generic routines only flush if the
+ * entry was young or dirty which is not good enough.
+ *
+ * We should be more intelligent about this but for the moment we override
+ * these functions and force a tlb flush unconditionally
+ */
+int pmdp_clear_flush_young(struct vm_area_struct *vma,
+				  unsigned long address, pmd_t *pmdp)
+{
+	return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp);
+}
+
+/*
+ * We mark the pmd splitting and invalidate all the hpte
+ * entries for this hugepage.
+ */
+void pmdp_splitting_flush(struct vm_area_struct *vma,
+			  unsigned long address, pmd_t *pmdp)
+{
+	unsigned long old, tmp;
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+
+#ifdef CONFIG_DEBUG_VM
+	WARN_ON(!pmd_trans_huge(*pmdp));
+	assert_spin_locked(&vma->vm_mm->page_table_lock);
+#endif
+
+#ifdef PTE_ATOMIC_UPDATES
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%3\n\
+		andi.	%1,%0,%6\n\
+		bne-	1b \n\
+		ori	%1,%0,%4 \n\
+		stdcx.	%1,0,%3 \n\
+		bne-	1b"
+	: "=&r" (old), "=&r" (tmp), "=m" (*pmdp)
+	: "r" (pmdp), "i" (_PAGE_SPLITTING), "m" (*pmdp), "i" (_PAGE_BUSY)
+	: "cc" );
+#else
+	old = pmd_val(*pmdp);
+	*pmdp = __pmd(old | _PAGE_SPLITTING);
+#endif
+	/*
+	 * If we didn't had the splitting flag set, go and flush the
+	 * HPTE entries.
+	 */
+	if (!(old & _PAGE_SPLITTING)) {
+		/* We need to flush the hpte */
+		if (old & _PAGE_HASHPTE)
+			hpte_do_hugepage_flush(vma->vm_mm, address, pmdp);
+	}
+}
+
+/*
+ * We want to put the pgtable in pmd and use pgtable for tracking
+ * the base page size hptes
+ */
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable)
+{
+	pgtable_t *pgtable_slot;
+	assert_spin_locked(&mm->page_table_lock);
+	/*
+	 * we store the pgtable in the second half of PMD
+	 */
+	pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD;
+	*pgtable_slot = pgtable;
+	/*
+	 * expose the deposited pgtable to other cpus.
+	 * before we set the hugepage PTE at pmd level
+	 * hash fault code looks at the deposted pgtable
+	 * to store hash index values.
+	 */
+	smp_wmb();
+}
+
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
+{
+	pgtable_t pgtable;
+	pgtable_t *pgtable_slot;
+
+	assert_spin_locked(&mm->page_table_lock);
+	pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD;
+	pgtable = *pgtable_slot;
+	/*
+	 * Once we withdraw, mark the entry NULL.
+	 */
+	*pgtable_slot = NULL;
+	/*
+	 * We store HPTE information in the deposited PTE fragment.
+	 * zero out the content on withdraw.
+	 */
+	memset(pgtable, 0, PTE_FRAG_SIZE);
+	return pgtable;
+}
+
+/*
+ * set a new huge pmd. We should not be called for updating
+ * an existing pmd entry. That should go via pmd_hugepage_update.
+ */
+void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+		pmd_t *pmdp, pmd_t pmd)
+{
+#ifdef CONFIG_DEBUG_VM
+	WARN_ON(!pmd_none(*pmdp));
+	assert_spin_locked(&mm->page_table_lock);
+	WARN_ON(!pmd_trans_huge(pmd));
+#endif
+	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
+}
+
+void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+		     pmd_t *pmdp)
+{
+	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT);
+}
+
+/*
+ * A linux hugepage PMD was changed and the corresponding hash table entries
+ * neesd to be flushed.
+ */
+void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
+			    pmd_t *pmdp)
+{
+	int ssize, i;
+	unsigned long s_addr;
+	int max_hpte_count;
+	unsigned int psize, valid;
+	unsigned char *hpte_slot_array;
+	unsigned long hidx, vpn, vsid, hash, shift, slot;
+
+	/*
+	 * Flush all the hptes mapping this hugepage
+	 */
+	s_addr = addr & HPAGE_PMD_MASK;
+	hpte_slot_array = get_hpte_slot_array(pmdp);
+	/*
+	 * IF we try to do a HUGE PTE update after a withdraw is done.
+	 * we will find the below NULL. This happens when we do
+	 * split_huge_page_pmd
+	 */
+	if (!hpte_slot_array)
+		return;
+
+	/* get the base page size */
+	psize = get_slice_psize(mm, s_addr);
+
+	if (ppc_md.hugepage_invalidate)
+		return ppc_md.hugepage_invalidate(mm, hpte_slot_array,
+						  s_addr, psize);
+	/*
+	 * No bluk hpte removal support, invalidate each entry
+	 */
+	shift = mmu_psize_defs[psize].shift;
+	max_hpte_count = HPAGE_PMD_SIZE >> shift;
+	for (i = 0; i < max_hpte_count; i++) {
+		/*
+		 * 8 bits per each hpte entries
+		 * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
+		 */
+		valid = hpte_valid(hpte_slot_array, i);
+		if (!valid)
+			continue;
+		hidx =  hpte_hash_index(hpte_slot_array, i);
+
+		/* get the vpn */
+		addr = s_addr + (i * (1ul << shift));
+		if (!is_kernel_addr(addr)) {
+			ssize = user_segment_size(addr);
+			vsid = get_vsid(mm->context.id, addr, ssize);
+			WARN_ON(vsid == 0);
+		} else {
+			vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
+			ssize = mmu_kernel_ssize;
+		}
+
+		vpn = hpt_vpn(addr, vsid, ssize);
+		hash = hpt_hash(vpn, shift, ssize);
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+		ppc_md.hpte_invalidate(slot, vpn, psize,
+				       MMU_PAGE_16M, ssize, 0);
+	}
+}
+
+static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot)
+{
+	pmd_val(pmd) |= pgprot_val(pgprot);
+	return pmd;
+}
+
+pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot)
+{
+	pmd_t pmd;
+	/*
+	 * For a valid pte, we would have _PAGE_PRESENT or _PAGE_FILE always
+	 * set. We use this to check THP page at pmd level.
+	 * leaf pte for huge page, bottom two bits != 00
+	 */
+	pmd_val(pmd) = pfn << PTE_RPN_SHIFT;
+	pmd_val(pmd) |= _PAGE_THP_HUGE;
+	pmd = pmd_set_protbits(pmd, pgprot);
+	return pmd;
+}
+
+pmd_t mk_pmd(struct page *page, pgprot_t pgprot)
+{
+	return pfn_pmd(page_to_pfn(page), pgprot);
+}
+
+pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+
+	pmd_val(pmd) &= _HPAGE_CHG_MASK;
+	pmd = pmd_set_protbits(pmd, newprot);
+	return pmd;
+}
+
+/*
+ * This is called at the end of handling a user page fault, when the
+ * fault has been handled by updating a HUGE PMD entry in the linux page tables.
+ * We use it to preload an HPTE into the hash table corresponding to
+ * the updated linux HUGE PMD entry.
+ */
+void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+			  pmd_t *pmd)
+{
+	return;
+}
+
+pmd_t pmdp_get_and_clear(struct mm_struct *mm,
+			 unsigned long addr, pmd_t *pmdp)
+{
+	pmd_t old_pmd;
+	pgtable_t pgtable;
+	unsigned long old;
+	pgtable_t *pgtable_slot;
+
+	old = pmd_hugepage_update(mm, addr, pmdp, ~0UL);
+	old_pmd = __pmd(old);
+	/*
+	 * We have pmd == none and we are holding page_table_lock.
+	 * So we can safely go and clear the pgtable hash
+	 * index info.
+	 */
+	pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD;
+	pgtable = *pgtable_slot;
+	/*
+	 * Let's zero out old valid and hash index details
+	 * hash fault look at them.
+	 */
+	memset(pgtable, 0, PTE_FRAG_SIZE);
+	return old_pmd;
+}
+
+int has_transparent_hugepage(void)
+{
+	if (!mmu_has_feature(MMU_FTR_16M_PAGE))
+		return 0;
+	/*
+	 * We support THP only if PMD_SIZE is 16MB.
+	 */
+	if (mmu_psize_defs[MMU_PAGE_16M].shift != PMD_SHIFT)
+		return 0;
+	/*
+	 * We need to make sure that we support 16MB hugepage in a segement
+	 * with base page size 64K or 4K. We only enable THP with a PAGE_SIZE
+	 * of 64K.
+	 */
+	/*
+	 * If we have 64K HPTE, we will be using that by default
+	 */
+	if (mmu_psize_defs[MMU_PAGE_64K].shift &&
+	    (mmu_psize_defs[MMU_PAGE_64K].penc[MMU_PAGE_16M] == -1))
+		return 0;
+	/*
+	 * Ok we only have 4K HPTE
+	 */
+	if (mmu_psize_defs[MMU_PAGE_4K].penc[MMU_PAGE_16M] == -1)
+		return 0;
+
+	return 1;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index 7c415ddde94..aa74acb0fdf 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -130,6 +130,53 @@ static void subpage_prot_clear(unsigned long addr, unsigned long len)
 	up_write(&mm->mmap_sem);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr,
+				  unsigned long end, struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->private;
+	split_huge_page_pmd(vma, addr, pmd);
+	return 0;
+}
+
+static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr,
+				    unsigned long len)
+{
+	struct vm_area_struct *vma;
+	struct mm_walk subpage_proto_walk = {
+		.mm = mm,
+		.pmd_entry = subpage_walk_pmd_entry,
+	};
+
+	/*
+	 * We don't try too hard, we just mark all the vma in that range
+	 * VM_NOHUGEPAGE and split them.
+	 */
+	vma = find_vma(mm, addr);
+	/*
+	 * If the range is in unmapped range, just return
+	 */
+	if (vma && ((addr + len) <= vma->vm_start))
+		return;
+
+	while (vma) {
+		if (vma->vm_start >= (addr + len))
+			break;
+		vma->vm_flags |= VM_NOHUGEPAGE;
+		subpage_proto_walk.private = vma;
+		walk_page_range(vma->vm_start, vma->vm_end,
+				&subpage_proto_walk);
+		vma = vma->vm_next;
+	}
+}
+#else
+static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr,
+				    unsigned long len)
+{
+	return;
+}
+#endif
+
 /*
  * Copy in a subpage protection map for an address range.
  * The map has 2 bits per 4k subpage, so 32 bits per 64k page.
@@ -168,6 +215,7 @@ long sys_subpage_prot(unsigned long addr, unsigned long len, u32 __user *map)
 		return -EFAULT;
 
 	down_write(&mm->mmap_sem);
+	subpage_mark_vma_nohuge(mm, addr, len);
 	for (limit = addr + len; addr < limit; addr = next) {
 		next = pmd_addr_end(addr, limit);
 		err = -ENOMEM;
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 7df1c5edda8..36e44b4260e 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -189,6 +189,7 @@ void tlb_flush(struct mmu_gather *tlb)
 void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
 			      unsigned long end)
 {
+	int hugepage_shift;
 	unsigned long flags;
 
 	start = _ALIGN_DOWN(start, PAGE_SIZE);
@@ -206,7 +207,8 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
 	local_irq_save(flags);
 	arch_enter_lazy_mmu_mode();
 	for (; start < end; start += PAGE_SIZE) {
-		pte_t *ptep = find_linux_pte(mm->pgd, start);
+		pte_t *ptep = find_linux_pte_or_hugepte(mm->pgd, start,
+							&hugepage_shift);
 		unsigned long pte;
 
 		if (ptep == NULL)
@@ -214,7 +216,37 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
 		pte = pte_val(*ptep);
 		if (!(pte & _PAGE_HASHPTE))
 			continue;
-		hpte_need_flush(mm, start, ptep, pte, 0);
+		if (unlikely(hugepage_shift && pmd_trans_huge(*(pmd_t *)pte)))
+			hpte_do_hugepage_flush(mm, start, (pmd_t *)pte);
+		else
+			hpte_need_flush(mm, start, ptep, pte, 0);
+	}
+	arch_leave_lazy_mmu_mode();
+	local_irq_restore(flags);
+}
+
+void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr)
+{
+	pte_t *pte;
+	pte_t *start_pte;
+	unsigned long flags;
+
+	addr = _ALIGN_DOWN(addr, PMD_SIZE);
+	/* Note: Normally, we should only ever use a batch within a
+	 * PTE locked section. This violates the rule, but will work
+	 * since we don't actually modify the PTEs, we just flush the
+	 * hash while leaving the PTEs intact (including their reference
+	 * to being hashed). This is not the most performance oriented
+	 * way to do things but is fine for our needs here.
+	 */
+	local_irq_save(flags);
+	arch_enter_lazy_mmu_mode();
+	start_pte = pte_offset_map(pmd, addr);
+	for (pte = start_pte; pte < start_pte + PTRS_PER_PTE; pte++) {
+		unsigned long pteval = pte_val(*pte);
+		if (pteval & _PAGE_HASHPTE)
+			hpte_need_flush(mm, addr, pte, pteval, 0);
+		addr += PAGE_SIZE;
 	}
 	arch_leave_lazy_mmu_mode();
 	local_irq_restore(flags);
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 6888cad5103..41cd68dee68 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -648,7 +648,7 @@ void __init early_init_mmu(void)
 	__early_init_mmu(1);
 }
 
-void __cpuinit early_init_mmu_secondary(void)
+void early_init_mmu_secondary(void)
 {
 	__early_init_mmu(0);
 }