Merge Linus' tree to be be to apply submitted patches to newer code than

current trivial.git base

22 files changed, 780 insertions, 576 deletions

diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 51230ee..325e861 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -13,9 +13,7 @@ obj-$(CONFIG_PPC_MMU_NOHASH)	+= mmu_context_nohash.o tlb_nohash.o \
 				   tlb_nohash_low.o
 obj-$(CONFIG_PPC_BOOK3E)	+= tlb_low_$(CONFIG_WORD_SIZE)e.o
 hash64-$(CONFIG_PPC_NATIVE)	:= hash_native_64.o
-obj-$(CONFIG_PPC_STD_MMU_64)	+= hash_utils_64.o \
-				   slb_low.o slb.o stab.o \
-				   $(hash64-y)
+obj-$(CONFIG_PPC_STD_MMU_64)	+= hash_utils_64.o slb_low.o slb.o $(hash64-y)
 obj-$(CONFIG_PPC_STD_MMU_32)	+= ppc_mmu_32.o
 obj-$(CONFIG_PPC_STD_MMU)	+= hash_low_$(CONFIG_WORD_SIZE).o \
 				   tlb_hash$(CONFIG_WORD_SIZE).o \
@@ -36,3 +34,4 @@ obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += hugepage-hash64.o
 obj-$(CONFIG_PPC_SUBPAGE_PROT)	+= subpage-prot.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
+obj-$(CONFIG_PPC_COPRO_BASE)	+= copro_fault.o
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
new file mode 100644
index 0000000..5a236f0
--- /dev/null
+++ b/arch/powerpc/mm/copro_fault.c
@@ -0,0 +1,148 @@
+/*
+ * CoProcessor (SPU/AFU) mm fault handler
+ *
+ * (C) Copyright IBM Deutschland Entwicklung GmbH 2007
+ *
+ * Author: Arnd Bergmann <arndb@de.ibm.com>
+ * Author: Jeremy Kerr <jk@ozlabs.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/export.h>
+#include <asm/reg.h>
+#include <asm/copro.h>
+#include <asm/spu.h>
+#include <misc/cxl.h>
+
+/*
+ * This ought to be kept in sync with the powerpc specific do_page_fault
+ * function. Currently, there are a few corner cases that we haven't had
+ * to handle fortunately.
+ */
+int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
+		unsigned long dsisr, unsigned *flt)
+{
+	struct vm_area_struct *vma;
+	unsigned long is_write;
+	int ret;
+
+	if (mm == NULL)
+		return -EFAULT;
+
+	if (mm->pgd == NULL)
+		return -EFAULT;
+
+	down_read(&mm->mmap_sem);
+	ret = -EFAULT;
+	vma = find_vma(mm, ea);
+	if (!vma)
+		goto out_unlock;
+
+	if (ea < vma->vm_start) {
+		if (!(vma->vm_flags & VM_GROWSDOWN))
+			goto out_unlock;
+		if (expand_stack(vma, ea))
+			goto out_unlock;
+	}
+
+	is_write = dsisr & DSISR_ISSTORE;
+	if (is_write) {
+		if (!(vma->vm_flags & VM_WRITE))
+			goto out_unlock;
+	} else {
+		if (dsisr & DSISR_PROTFAULT)
+			goto out_unlock;
+		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+			goto out_unlock;
+	}
+
+	ret = 0;
+	*flt = handle_mm_fault(mm, vma, ea, is_write ? FAULT_FLAG_WRITE : 0);
+	if (unlikely(*flt & VM_FAULT_ERROR)) {
+		if (*flt & VM_FAULT_OOM) {
+			ret = -ENOMEM;
+			goto out_unlock;
+		} else if (*flt & VM_FAULT_SIGBUS) {
+			ret = -EFAULT;
+			goto out_unlock;
+		}
+		BUG();
+	}
+
+	if (*flt & VM_FAULT_MAJOR)
+		current->maj_flt++;
+	else
+		current->min_flt++;
+
+out_unlock:
+	up_read(&mm->mmap_sem);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(copro_handle_mm_fault);
+
+int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
+{
+	u64 vsid;
+	int psize, ssize;
+
+	switch (REGION_ID(ea)) {
+	case USER_REGION_ID:
+		pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea);
+		psize = get_slice_psize(mm, ea);
+		ssize = user_segment_size(ea);
+		vsid = get_vsid(mm->context.id, ea, ssize);
+		break;
+	case VMALLOC_REGION_ID:
+		pr_devel("%s: 0x%llx -- VMALLOC_REGION_ID\n", __func__, ea);
+		if (ea < VMALLOC_END)
+			psize = mmu_vmalloc_psize;
+		else
+			psize = mmu_io_psize;
+		ssize = mmu_kernel_ssize;
+		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+		break;
+	case KERNEL_REGION_ID:
+		pr_devel("%s: 0x%llx -- KERNEL_REGION_ID\n", __func__, ea);
+		psize = mmu_linear_psize;
+		ssize = mmu_kernel_ssize;
+		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+		break;
+	default:
+		pr_debug("%s: invalid region access at %016llx\n", __func__, ea);
+		return 1;
+	}
+
+	vsid = (vsid << slb_vsid_shift(ssize)) | SLB_VSID_USER;
+
+	vsid |= mmu_psize_defs[psize].sllp |
+		((ssize == MMU_SEGSIZE_1T) ? SLB_VSID_B_1T : 0);
+
+	slb->esid = (ea & (ssize == MMU_SEGSIZE_1T ? ESID_MASK_1T : ESID_MASK)) | SLB_ESID_V;
+	slb->vsid = vsid;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(copro_calculate_slb);
+
+void copro_flush_all_slbs(struct mm_struct *mm)
+{
+#ifdef CONFIG_SPU_BASE
+	spu_flush_all_slbs(mm);
+#endif
+	cxl_slbia(mm);
+}
+EXPORT_SYMBOL_GPL(copro_flush_all_slbs);
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index 7b6c107..d85e86a 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -33,6 +33,7 @@
 #include <linux/export.h>
 
 #include <asm/tlbflush.h>
+#include <asm/dma.h>
 
 #include "mmu_decl.h"
 
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 51ab9e7..08d659a 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -30,9 +30,9 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/perf_event.h>
-#include <linux/magic.h>
 #include <linux/ratelimit.h>
 #include <linux/context_tracking.h>
+#include <linux/hugetlb.h>
 
 #include <asm/firmware.h>
 #include <asm/page.h>
@@ -114,22 +114,37 @@ static int store_updates_sp(struct pt_regs *regs)
 #define MM_FAULT_CONTINUE	-1
 #define MM_FAULT_ERR(sig)	(sig)
 
-static int do_sigbus(struct pt_regs *regs, unsigned long address)
+static int do_sigbus(struct pt_regs *regs, unsigned long address,
+		     unsigned int fault)
 {
 	siginfo_t info;
+	unsigned int lsb = 0;
 
 	up_read(&current->mm->mmap_sem);
 
-	if (user_mode(regs)) {
-		current->thread.trap_nr = BUS_ADRERR;
-		info.si_signo = SIGBUS;
-		info.si_errno = 0;
-		info.si_code = BUS_ADRERR;
-		info.si_addr = (void __user *)address;
-		force_sig_info(SIGBUS, &info, current);
-		return MM_FAULT_RETURN;
+	if (!user_mode(regs))
+		return MM_FAULT_ERR(SIGBUS);
+
+	current->thread.trap_nr = BUS_ADRERR;
+	info.si_signo = SIGBUS;
+	info.si_errno = 0;
+	info.si_code = BUS_ADRERR;
+	info.si_addr = (void __user *)address;
+#ifdef CONFIG_MEMORY_FAILURE
+	if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
+		pr_err("MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
+			current->comm, current->pid, address);
+		info.si_code = BUS_MCEERR_AR;
 	}
-	return MM_FAULT_ERR(SIGBUS);
+
+	if (fault & VM_FAULT_HWPOISON_LARGE)
+		lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+	if (fault & VM_FAULT_HWPOISON)
+		lsb = PAGE_SHIFT;
+#endif
+	info.si_addr_lsb = lsb;
+	force_sig_info(SIGBUS, &info, current);
+	return MM_FAULT_RETURN;
 }
 
 static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
@@ -170,11 +185,8 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
 		return MM_FAULT_RETURN;
 	}
 
-	/* Bus error. x86 handles HWPOISON here, we'll add this if/when
-	 * we support the feature in HW
-	 */
-	if (fault & VM_FAULT_SIGBUS)
-		return do_sigbus(regs, addr);
+	if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE))
+		return do_sigbus(regs, addr, fault);
 
 	/* We don't understand the fault code, this is fatal */
 	BUG();
@@ -508,7 +520,6 @@ bail:
 void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 {
 	const struct exception_table_entry *entry;
-	unsigned long *stackend;
 
 	/* Are we prepared to handle this fault?  */
 	if ((entry = search_exception_tables(regs->nip)) != NULL) {
@@ -537,8 +548,7 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 	printk(KERN_ALERT "Faulting instruction address: 0x%08lx\n",
 		regs->nip);
 
-	stackend = end_of_stack(current);
-	if (current != &init_task && *stackend != STACK_END_MAGIC)
+	if (task_stack_end_corrupted(current))
 		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
 
 	die("Kernel access of bad area", regs, sig);
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index cf1d325..ae4962a 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -29,6 +29,8 @@
 #include <asm/kexec.h>
 #include <asm/ppc-opcode.h>
 
+#include <misc/cxl.h>
+
 #ifdef DEBUG_LOW
 #define DBG_LOW(fmt...) udbg_printf(fmt)
 #else
@@ -149,9 +151,11 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 static inline void tlbie(unsigned long vpn, int psize, int apsize,
 			 int ssize, int local)
 {
-	unsigned int use_local = local && mmu_has_feature(MMU_FTR_TLBIEL);
+	unsigned int use_local;
 	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
+	use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) && !cxl_ctx_in_use();
+
 	if (use_local)
 		use_local = mmu_psize_defs[psize].tlbiel;
 	if (lock_tlbie && !use_local)
@@ -412,18 +416,18 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	local_irq_restore(flags);
 }
 
-static void native_hugepage_invalidate(struct mm_struct *mm,
+static void native_hugepage_invalidate(unsigned long vsid,
+				       unsigned long addr,
 				       unsigned char *hpte_slot_array,
-				       unsigned long addr, int psize)
+				       int psize, int ssize)
 {
-	int ssize = 0, i;
-	int lock_tlbie;
+	int i;
 	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;
+	unsigned long hidx, vpn = 0, hash, slot;
 
 	shift = mmu_psize_defs[psize].shift;
 	max_hpte_count = 1U << (PMD_SHIFT - shift);
@@ -437,15 +441,6 @@ static void native_hugepage_invalidate(struct mm_struct *mm,
 
 		/* 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)
@@ -465,22 +460,13 @@ static void native_hugepage_invalidate(struct mm_struct *mm,
 		else
 			/* Invalidate the hpte. NOTE: this also unlocks it */
 			hptep->v = 0;
+		/*
+		 * We need to do tlb invalidate for all the address, tlbie
+		 * instruction compares entry_VA in tlb with the VA specified
+		 * here
+		 */
+		tlbie(vpn, psize, actual_psize, ssize, 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);
 }
 
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 88fdd9d..d5339a3 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -51,7 +51,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cputable.h>
 #include <asm/sections.h>
-#include <asm/spu.h>
+#include <asm/copro.h>
 #include <asm/udbg.h>
 #include <asm/code-patching.h>
 #include <asm/fadump.h>
@@ -92,12 +92,14 @@ extern unsigned long dart_tablebase;
 
 static unsigned long _SDR1;
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
+EXPORT_SYMBOL_GPL(mmu_psize_defs);
 
 struct hash_pte *htab_address;
 unsigned long htab_size_bytes;
 unsigned long htab_hash_mask;
 EXPORT_SYMBOL_GPL(htab_hash_mask);
 int mmu_linear_psize = MMU_PAGE_4K;
+EXPORT_SYMBOL_GPL(mmu_linear_psize);
 int mmu_virtual_psize = MMU_PAGE_4K;
 int mmu_vmalloc_psize = MMU_PAGE_4K;
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
@@ -105,6 +107,7 @@ int mmu_vmemmap_psize = MMU_PAGE_4K;
 #endif
 int mmu_io_psize = MMU_PAGE_4K;
 int mmu_kernel_ssize = MMU_SEGSIZE_256M;
+EXPORT_SYMBOL_GPL(mmu_kernel_ssize);
 int mmu_highuser_ssize = MMU_SEGSIZE_256M;
 u16 mmu_slb_size = 64;
 EXPORT_SYMBOL_GPL(mmu_slb_size);
@@ -243,7 +246,7 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-static int htab_remove_mapping(unsigned long vstart, unsigned long vend,
+int htab_remove_mapping(unsigned long vstart, unsigned long vend,
 		      int psize, int ssize)
 {
 	unsigned long vaddr;
@@ -333,70 +336,69 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 		return 0;
 
 	prop = of_get_flat_dt_prop(node, "ibm,segment-page-sizes", &size);
-	if (prop != NULL) {
-		pr_info("Page sizes from device-tree:\n");
-		size /= 4;
-		cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE);
-		while(size > 0) {
-			unsigned int base_shift = be32_to_cpu(prop[0]);
-			unsigned int slbenc = be32_to_cpu(prop[1]);
-			unsigned int lpnum = be32_to_cpu(prop[2]);
-			struct mmu_psize_def *def;
-			int idx, base_idx;
-
-			size -= 3; prop += 3;
-			base_idx = get_idx_from_shift(base_shift);
-			if (base_idx < 0) {
-				/*
-				 * skip the pte encoding also
-				 */
-				prop += lpnum * 2; size -= lpnum * 2;
+	if (!prop)
+		return 0;
+
+	pr_info("Page sizes from device-tree:\n");
+	size /= 4;
+	cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE);
+	while(size > 0) {
+		unsigned int base_shift = be32_to_cpu(prop[0]);
+		unsigned int slbenc = be32_to_cpu(prop[1]);
+		unsigned int lpnum = be32_to_cpu(prop[2]);
+		struct mmu_psize_def *def;
+		int idx, base_idx;
+
+		size -= 3; prop += 3;
+		base_idx = get_idx_from_shift(base_shift);
+		if (base_idx < 0) {
+			/* skip the pte encoding also */
+			prop += lpnum * 2; size -= lpnum * 2;
+			continue;
+		}
+		def = &mmu_psize_defs[base_idx];
+		if (base_idx == MMU_PAGE_16M)
+			cur_cpu_spec->mmu_features |= MMU_FTR_16M_PAGE;
+
+		def->shift = base_shift;
+		if (base_shift <= 23)
+			def->avpnm = 0;
+		else
+			def->avpnm = (1 << (base_shift - 23)) - 1;
+		def->sllp = slbenc;
+		/*
+		 * We don't know for sure what's up with tlbiel, so
+		 * for now we only set it for 4K and 64K pages
+		 */
+		if (base_idx == MMU_PAGE_4K || base_idx == MMU_PAGE_64K)
+			def->tlbiel = 1;
+		else
+			def->tlbiel = 0;
+
+		while (size > 0 && lpnum) {
+			unsigned int shift = be32_to_cpu(prop[0]);
+			int penc  = be32_to_cpu(prop[1]);
+
+			prop += 2; size -= 2;
+			lpnum--;
+
+			idx = get_idx_from_shift(shift);
+			if (idx < 0)
 				continue;
-			}
-			def = &mmu_psize_defs[base_idx];
-			if (base_idx == MMU_PAGE_16M)
-				cur_cpu_spec->mmu_features |= MMU_FTR_16M_PAGE;
-
-			def->shift = base_shift;
-			if (base_shift <= 23)
-				def->avpnm = 0;
-			else
-				def->avpnm = (1 << (base_shift - 23)) - 1;
-			def->sllp = slbenc;
-			/*
-			 * We don't know for sure what's up with tlbiel, so
-			 * for now we only set it for 4K and 64K pages
-			 */
-			if (base_idx == MMU_PAGE_4K || base_idx == MMU_PAGE_64K)
-				def->tlbiel = 1;
-			else
-				def->tlbiel = 0;
-
-			while (size > 0 && lpnum) {
-				unsigned int shift = be32_to_cpu(prop[0]);
-				int penc  = be32_to_cpu(prop[1]);
-
-				prop += 2; size -= 2;
-				lpnum--;
-
-				idx = get_idx_from_shift(shift);
-				if (idx < 0)
-					continue;
-
-				if (penc == -1)
-					pr_err("Invalid penc for base_shift=%d "
-					       "shift=%d\n", base_shift, shift);
-
-				def->penc[idx] = penc;
-				pr_info("base_shift=%d: shift=%d, sllp=0x%04lx,"
-					" avpnm=0x%08lx, tlbiel=%d, penc=%d\n",
-					base_shift, shift, def->sllp,
-					def->avpnm, def->tlbiel, def->penc[idx]);
-			}
+
+			if (penc == -1)
+				pr_err("Invalid penc for base_shift=%d "
+				       "shift=%d\n", base_shift, shift);
+
+			def->penc[idx] = penc;
+			pr_info("base_shift=%d: shift=%d, sllp=0x%04lx,"
+				" avpnm=0x%08lx, tlbiel=%d, penc=%d\n",
+				base_shift, shift, def->sllp,
+				def->avpnm, def->tlbiel, def->penc[idx]);
 		}
-		return 1;
 	}
-	return 0;
+
+	return 1;
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
@@ -821,21 +823,14 @@ static void __init htab_initialize(void)
 
 void __init early_init_mmu(void)
 {
-	/* Setup initial STAB address in the PACA */
-	get_paca()->stab_real = __pa((u64)&initial_stab);
-	get_paca()->stab_addr = (u64)&initial_stab;
-
 	/* Initialize the MMU Hash table and create the linear mapping
-	 * of memory. Has to be done before stab/slb initialization as
-	 * this is currently where the page size encoding is obtained
+	 * of memory. Has to be done before SLB initialization as this is
+	 * currently where the page size encoding is obtained.
 	 */
 	htab_initialize();
 
-	/* Initialize stab / SLB management */
-	if (mmu_has_feature(MMU_FTR_SLB))
-		slb_initialize();
-	else
-		stab_initialize(get_paca()->stab_real);
+	/* Initialize SLB management */
+	slb_initialize();
 }
 
 #ifdef CONFIG_SMP
@@ -845,13 +840,8 @@ void early_init_mmu_secondary(void)
 	if (!firmware_has_feature(FW_FEATURE_LPAR))
 		mtspr(SPRN_SDR1, _SDR1);
 
-	/* Initialize STAB/SLB. We use a virtual address as it works
-	 * in real mode on pSeries.
-	 */
-	if (mmu_has_feature(MMU_FTR_SLB))
-		slb_initialize();
-	else
-		stab_initialize(get_paca()->stab_addr);
+	/* Initialize SLB */
+	slb_initialize();
 }
 #endif /* CONFIG_SMP */
 
@@ -879,7 +869,7 @@ unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
 }
 
 #ifdef CONFIG_PPC_MM_SLICES
-unsigned int get_paca_psize(unsigned long addr)
+static unsigned int get_paca_psize(unsigned long addr)
 {
 	u64 lpsizes;
 	unsigned char *hpsizes;
@@ -913,10 +903,8 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
 	if (get_slice_psize(mm, addr) == MMU_PAGE_4K)
 		return;
 	slice_set_range_psize(mm, addr, 1, MMU_PAGE_4K);
-#ifdef CONFIG_SPU_BASE
-	spu_flush_all_slbs(mm);
-#endif
-	if (get_paca_psize(addr) != MMU_PAGE_4K) {
+	copro_flush_all_slbs(mm);
+	if ((get_paca_psize(addr) != MMU_PAGE_4K) && (current->mm == mm)) {
 		get_paca()->context = mm->context;
 		slb_flush_and_rebolt();
 	}
@@ -1001,12 +989,11 @@ static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
  * -1 - critical hash insertion error
  * -2 - access not permitted by subpage protection mechanism
  */
-int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
+int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap)
 {
 	enum ctx_state prev_state = exception_enter();
 	pgd_t *pgdir;
 	unsigned long vsid;
-	struct mm_struct *mm;
 	pte_t *ptep;
 	unsigned hugeshift;
 	const struct cpumask *tmp;
@@ -1020,7 +1007,6 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
  	switch (REGION_ID(ea)) {
 	case USER_REGION_ID:
 		user_region = 1;
-		mm = current->mm;
 		if (! mm) {
 			DBG_LOW(" user region with no mm !\n");
 			rc = 1;
@@ -1031,7 +1017,6 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 		vsid = get_vsid(mm->context.id, ea, ssize);
 		break;
 	case VMALLOC_REGION_ID:
-		mm = &init_mm;
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
 		if (ea < VMALLOC_END)
 			psize = mmu_vmalloc_psize;
@@ -1116,7 +1101,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 			WARN_ON(1);
 		}
 #endif
-		check_paca_psize(ea, mm, psize, user_region);
+		if (current->mm == mm)
+			check_paca_psize(ea, mm, psize, user_region);
 
 		goto bail;
 	}
@@ -1153,13 +1139,12 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 			       "to 4kB pages because of "
 			       "non-cacheable mapping\n");
 			psize = mmu_vmalloc_psize = MMU_PAGE_4K;
-#ifdef CONFIG_SPU_BASE
-			spu_flush_all_slbs(mm);
-#endif
+			copro_flush_all_slbs(mm);
 		}
 	}
 
-	check_paca_psize(ea, mm, psize, user_region);
+	if (current->mm == mm)
+		check_paca_psize(ea, mm, psize, user_region);
 #endif /* CONFIG_PPC_64K_PAGES */
 
 #ifdef CONFIG_PPC_HAS_HASH_64K
@@ -1194,6 +1179,17 @@ bail:
 	exception_exit(prev_state);
 	return rc;
 }
+EXPORT_SYMBOL_GPL(hash_page_mm);
+
+int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
+{
+	struct mm_struct *mm = current->mm;
+
+	if (REGION_ID(ea) == VMALLOC_REGION_ID)
+		mm = &init_mm;
+
+	return hash_page_mm(mm, ea, access, trap);
+}
 EXPORT_SYMBOL_GPL(hash_page);
 
 void hash_preload(struct mm_struct *mm, unsigned long ea,
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 826893f..5f5e632 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -18,6 +18,57 @@
 #include <linux/mm.h>
 #include <asm/machdep.h>
 
+static void invalidate_old_hpte(unsigned long vsid, unsigned long addr,
+				pmd_t *pmdp, unsigned int psize, int ssize)
+{
+	int i, max_hpte_count, valid;
+	unsigned long s_addr;
+	unsigned char *hpte_slot_array;
+	unsigned long hidx, shift, vpn, hash, slot;
+
+	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;
+
+	if (ppc_md.hugepage_invalidate)
+		return ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
+						  psize, ssize);
+	/*
+	 * 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));
+		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);
+	}
+}
+
+
 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)
@@ -33,7 +84,9 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 	 * atomically mark the linux large page PMD busy and dirty
 	 */
 	do {
-		old_pmd = pmd_val(*pmdp);
+		pmd_t pmd = ACCESS_ONCE(*pmdp);
+
+		old_pmd = pmd_val(pmd);
 		/* If PMD busy, retry the access */
 		if (unlikely(old_pmd & _PAGE_BUSY))
 			return 0;
@@ -85,6 +138,15 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 	vpn = hpt_vpn(ea, vsid, ssize);
 	hash = hpt_hash(vpn, shift, ssize);
 	hpte_slot_array = get_hpte_slot_array(pmdp);
+	if (psize == MMU_PAGE_4K) {
+		/*
+		 * invalidate the old hpte entry if we have that mapped via 64K
+		 * base page size. This is because demote_segment won't flush
+		 * hash page table entries.
+		 */
+		if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO))
+			invalidate_old_hpte(vsid, ea, pmdp, MMU_PAGE_64K, ssize);
+	}
 
 	valid = hpte_valid(hpte_slot_array, index);
 	if (valid) {
@@ -107,11 +169,8 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 			 * 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) {
@@ -119,11 +178,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 
 		/* 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;
+		new_pmd |= _PAGE_HASHPTE;
 
 		/* Add in WIMG bits */
 		rflags |= (new_pmd & (_PAGE_WRITETHRU | _PAGE_NO_CACHE |
@@ -132,6 +187,8 @@ repeat:
 		 * enable the memory coherence always
 		 */
 		rflags |= HPTE_R_M;
+repeat:
+		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
 
 		/* Insert into the hash table, primary slot */
 		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
@@ -172,8 +229,17 @@ repeat:
 		mark_hpte_slot_valid(hpte_slot_array, index, slot);
 	}
 	/*
-	 * No need to use ldarx/stdcx here
+	 * Mark the pte with _PAGE_COMBO, if we are trying to hash it with
+	 * base page size 4k.
+	 */
+	if (psize == MMU_PAGE_4K)
+		new_pmd |= _PAGE_COMBO;
+	/*
+	 * The hpte valid is stored in the pgtable whose address is in the
+	 * second half of the PMD. Order this against clearing of the busy bit in
+	 * huge pmd.
 	 */
+	smp_wmb();
 	*pmdp = __pmd(new_pmd & ~_PAGE_BUSY);
 	return 0;
 }
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index cff59f1..415a51b 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -103,14 +103,14 @@ unsigned long __max_low_memory = MAX_LOW_MEM;
 /*
  * Check for command-line options that affect what MMU_init will do.
  */
-void MMU_setup(void)
+void __init MMU_setup(void)
 {
 	/* Check for nobats option (used in mapin_ram). */
-	if (strstr(cmd_line, "nobats")) {
+	if (strstr(boot_command_line, "nobats")) {
 		__map_without_bats = 1;
 	}
 
-	if (strstr(cmd_line, "noltlbs")) {
+	if (strstr(boot_command_line, "noltlbs")) {
 		__map_without_ltlbs = 1;
 	}
 #ifdef CONFIG_DEBUG_PAGEALLOC
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index e3734ed..3481556 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -175,9 +175,10 @@ static unsigned long __meminit vmemmap_section_start(unsigned long page)
 static int __meminit vmemmap_populated(unsigned long start, int page_size)
 {
 	unsigned long end = start + page_size;
+	start = (unsigned long)(pfn_to_page(vmemmap_section_start(start)));
 
 	for (; start < end; start += (PAGES_PER_SECTION * sizeof(struct page)))
-		if (pfn_valid(vmemmap_section_start(start)))
+		if (pfn_valid(page_to_pfn((struct page *)start)))
 			return 1;
 
 	return 0;
@@ -212,6 +213,13 @@ static void __meminit vmemmap_create_mapping(unsigned long start,
 	for (i = 0; i < page_size; i += PAGE_SIZE)
 		BUG_ON(map_kernel_page(start + i, phys, flags));
 }
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void vmemmap_remove_mapping(unsigned long start,
+				   unsigned long page_size)
+{
+}
+#endif
 #else /* CONFIG_PPC_BOOK3E */
 static void __meminit vmemmap_create_mapping(unsigned long start,
 					     unsigned long page_size,
@@ -223,17 +231,39 @@ static void __meminit vmemmap_create_mapping(unsigned long start,
 					mmu_kernel_ssize);
 	BUG_ON(mapped < 0);
 }
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void vmemmap_remove_mapping(unsigned long start,
+				   unsigned long page_size)
+{
+	int mapped = htab_remove_mapping(start, start + page_size,
+					 mmu_vmemmap_psize,
+					 mmu_kernel_ssize);
+	BUG_ON(mapped < 0);
+}
+#endif
+
 #endif /* CONFIG_PPC_BOOK3E */
 
 struct vmemmap_backing *vmemmap_list;
+static struct vmemmap_backing *next;
+static int num_left;
+static int num_freed;
 
 static __meminit struct vmemmap_backing * vmemmap_list_alloc(int node)
 {
-	static struct vmemmap_backing *next;
-	static int num_left;
+	struct vmemmap_backing *vmem_back;
+	/* get from freed entries first */
+	if (num_freed) {
+		num_freed--;
+		vmem_back = next;
+		next = next->list;
+
+		return vmem_back;
+	}
 
 	/* allocate a page when required and hand out chunks */
-	if (!next || !num_left) {
+	if (!num_left) {
 		next = vmemmap_alloc_block(PAGE_SIZE, node);
 		if (unlikely(!next)) {
 			WARN_ON(1);
@@ -296,10 +326,85 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 	return 0;
 }
 
-void vmemmap_free(unsigned long start, unsigned long end)
+#ifdef CONFIG_MEMORY_HOTPLUG
+static unsigned long vmemmap_list_free(unsigned long start)
 {
+	struct vmemmap_backing *vmem_back, *vmem_back_prev;
+
+	vmem_back_prev = vmem_back = vmemmap_list;
+
+	/* look for it with prev pointer recorded */
+	for (; vmem_back; vmem_back = vmem_back->list) {
+		if (vmem_back->virt_addr == start)
+			break;
+		vmem_back_prev = vmem_back;
+	}
+
+	if (unlikely(!vmem_back)) {
+		WARN_ON(1);
+		return 0;
+	}
+
+	/* remove it from vmemmap_list */
+	if (vmem_back == vmemmap_list) /* remove head */
+		vmemmap_list = vmem_back->list;
+	else
+		vmem_back_prev->list = vmem_back->list;
+
+	/* next point to this freed entry */
+	vmem_back->list = next;
+	next = vmem_back;
+	num_freed++;
+
+	return vmem_back->phys;
 }
 
+void __ref vmemmap_free(unsigned long start, unsigned long end)
+{
+	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
+
+	start = _ALIGN_DOWN(start, page_size);
+
+	pr_debug("vmemmap_free %lx...%lx\n", start, end);
+
+	for (; start < end; start += page_size) {
+		unsigned long addr;
+
+		/*
+		 * the section has already be marked as invalid, so
+		 * vmemmap_populated() true means some other sections still
+		 * in this page, so skip it.
+		 */
+		if (vmemmap_populated(start, page_size))
+			continue;
+
+		addr = vmemmap_list_free(start);
+		if (addr) {
+			struct page *page = pfn_to_page(addr >> PAGE_SHIFT);
+
+			if (PageReserved(page)) {
+				/* allocated from bootmem */
+				if (page_size < PAGE_SIZE) {
+					/*
+					 * this shouldn't happen, but if it is
+					 * the case, leave the memory there
+					 */
+					WARN_ON_ONCE(1);
+				} else {
+					unsigned int nr_pages =
+						1 << get_order(page_size);
+					while (nr_pages--)
+						free_reserved_page(page++);
+				}
+			} else
+				free_pages((unsigned long)(__va(addr)),
+							get_order(page_size));
+
+			vmemmap_remove_mapping(start, page_size);
+		}
+	}
+}
+#endif
 void register_page_bootmem_memmap(unsigned long section_nr,
 				  struct page *start_page, unsigned long size)
 {
@@ -331,16 +436,16 @@ struct page *realmode_pfn_to_page(unsigned long pfn)
 		if (pg_va < vmem_back->virt_addr)
 			continue;
 
-		/* Check that page struct is not split between real pages */
-		if ((pg_va + sizeof(struct page)) >
-				(vmem_back->virt_addr + page_size))
-			return NULL;
-
-		page = (struct page *) (vmem_back->phys + pg_va -
+		/* After vmemmap_list entry free is possible, need check all */
+		if ((pg_va + sizeof(struct page)) <=
+				(vmem_back->virt_addr + page_size)) {
+			page = (struct page *) (vmem_back->phys + pg_va -
 				vmem_back->virt_addr);
-		return page;
+			return page;
+		}
 	}
 
+	/* Probably that page struct is split between real pages */
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 2c8e90f..8ebaac7 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -128,7 +128,8 @@ int arch_add_memory(int nid, u64 start, u64 size)
 		return -EINVAL;
 
 	/* this should work for most non-highmem platforms */
-	zone = pgdata->node_zones;
+	zone = pgdata->node_zones +
+		zone_for_memory(nid, start, size, 0);
 
 	return __add_pages(nid, zone, start_pfn, nr_pages);
 }
@@ -259,6 +260,60 @@ static int __init mark_nonram_nosave(void)
 	}
 	return 0;
 }
+#else /* CONFIG_NEED_MULTIPLE_NODES */
+static int __init mark_nonram_nosave(void)
+{
+	return 0;
+}
+#endif
+
+static bool zone_limits_final;
+
+static unsigned long max_zone_pfns[MAX_NR_ZONES] = {
+	[0 ... MAX_NR_ZONES - 1] = ~0UL
+};
+
+/*
+ * Restrict the specified zone and all more restrictive zones
+ * to be below the specified pfn.  May not be called after
+ * paging_init().
+ */
+void __init limit_zone_pfn(enum zone_type zone, unsigned long pfn_limit)
+{
+	int i;
+
+	if (WARN_ON(zone_limits_final))
+		return;
+
+	for (i = zone; i >= 0; i--) {
+		if (max_zone_pfns[i] > pfn_limit)
+			max_zone_pfns[i] = pfn_limit;
+	}
+}
+
+/*
+ * Find the least restrictive zone that is entirely below the
+ * specified pfn limit.  Returns < 0 if no suitable zone is found.
+ *
+ * pfn_limit must be u64 because it can exceed 32 bits even on 32-bit
+ * systems -- the DMA limit can be higher than any possible real pfn.
+ */
+int dma_pfn_limit_to_zone(u64 pfn_limit)
+{
+	enum zone_type top_zone = ZONE_NORMAL;
+	int i;
+
+#ifdef CONFIG_HIGHMEM
+	top_zone = ZONE_HIGHMEM;
+#endif
+
+	for (i = top_zone; i >= 0; i--) {
+		if (max_zone_pfns[i] <= pfn_limit)
+			return i;
+	}
+
+	return -EPERM;
+}
 
 /*
  * paging_init() sets up the page tables - in fact we've already done this.
@@ -267,7 +322,7 @@ void __init paging_init(void)
 {
 	unsigned long long total_ram = memblock_phys_mem_size();
 	phys_addr_t top_of_ram = memblock_end_of_DRAM();
-	unsigned long max_zone_pfns[MAX_NR_ZONES];
+	enum zone_type top_zone;
 
 #ifdef CONFIG_PPC32
 	unsigned long v = __fix_to_virt(__end_of_fixed_addresses - 1);
@@ -289,18 +344,20 @@ void __init paging_init(void)
 	       (unsigned long long)top_of_ram, total_ram);
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (long int)((top_of_ram - total_ram) >> 20));
-	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+
 #ifdef CONFIG_HIGHMEM
-	max_zone_pfns[ZONE_DMA] = lowmem_end_addr >> PAGE_SHIFT;
-	max_zone_pfns[ZONE_HIGHMEM] = top_of_ram >> PAGE_SHIFT;
+	top_zone = ZONE_HIGHMEM;
+	limit_zone_pfn(ZONE_NORMAL, lowmem_end_addr >> PAGE_SHIFT);
 #else
-	max_zone_pfns[ZONE_DMA] = top_of_ram >> PAGE_SHIFT;
+	top_zone = ZONE_NORMAL;
 #endif
+
+	limit_zone_pfn(top_zone, top_of_ram >> PAGE_SHIFT);
+	zone_limits_final = true;
 	free_area_init_nodes(max_zone_pfns);
 
 	mark_nonram_nosave();
 }
-#endif /* ! CONFIG_NEED_MULTIPLE_NODES */
 
 static void __init register_page_bootmem_info(void)
 {
diff --git a/arch/powerpc/mm/mmu_context_hash32.c b/arch/powerpc/mm/mmu_context_hash32.c
index 78fef67..aa5a7fd 100644
--- a/arch/powerpc/mm/mmu_context_hash32.c
+++ b/arch/powerpc/mm/mmu_context_hash32.c
@@ -2,7 +2,7 @@
  * This file contains the routines for handling the MMU on those
  * PowerPC implementations where the MMU substantially follows the
  * architecture specification.  This includes the 6xx, 7xx, 7xxx,
- * 8260, and POWER3 implementations but excludes the 8xx and 4xx.
+ * and 8260 implementations but excludes the 8xx and 4xx.
  *  -- paulus
  *
  *  Derived from arch/ppc/mm/init.c:
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 3b181b2..b9d1dfd 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -8,6 +8,8 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  */
+#define pr_fmt(fmt) "numa: " fmt
+
 #include <linux/threads.h>
 #include <linux/bootmem.h>
 #include <linux/init.h>
@@ -538,7 +540,7 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem,
  */
 static int numa_setup_cpu(unsigned long lcpu)
 {
-	int nid;
+	int nid = -1;
 	struct device_node *cpu;
 
 	/*
@@ -555,19 +557,21 @@ static int numa_setup_cpu(unsigned long lcpu)
 
 	if (!cpu) {
 		WARN_ON(1);
-		nid = 0;
-		goto out;
+		if (cpu_present(lcpu))
+			goto out_present;
+		else
+			goto out;
 	}
 
 	nid = of_node_to_nid_single(cpu);
 
+out_present:
 	if (nid < 0 || !node_online(nid))
 		nid = first_online_node;
-out:
-	map_cpu_to_node(lcpu, nid);
 
+	map_cpu_to_node(lcpu, nid);
 	of_node_put(cpu);
-
+out:
 	return nid;
 }
 
@@ -611,8 +615,8 @@ static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action,
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
 		unmap_cpu_from_node(lcpu);
-		break;
 		ret = NOTIFY_OK;
+		break;
 #endif
 	}
 	return ret;
@@ -1049,7 +1053,7 @@ static void __init mark_reserved_regions_for_nid(int nid)
 
 void __init do_init_bootmem(void)
 {
-	int nid;
+	int nid, cpu;
 
 	min_low_pfn = 0;
 	max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
@@ -1122,16 +1126,14 @@ void __init do_init_bootmem(void)
 
 	reset_numa_cpu_lookup_table();
 	register_cpu_notifier(&ppc64_numa_nb);
-	cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE,
-			  (void *)(unsigned long)boot_cpuid);
-}
-
-void __init paging_init(void)
-{
-	unsigned long max_zone_pfns[MAX_NR_ZONES];
-	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-	max_zone_pfns[ZONE_DMA] = memblock_end_of_DRAM() >> PAGE_SHIFT;
-	free_area_init_nodes(max_zone_pfns);
+	/*
+	 * We need the numa_cpu_lookup_table to be accurate for all CPUs,
+	 * even before we online them, so that we can use cpu_to_{node,mem}
+	 * early in boot, cf. smp_prepare_cpus().
+	 */
+	for_each_present_cpu(cpu) {
+		numa_setup_cpu((unsigned long)cpu);
+	}
 }
 
 static int __init early_numa(char *p)
@@ -1153,6 +1155,22 @@ static int __init early_numa(char *p)
 }
 early_param("numa", early_numa);
 
+static bool topology_updates_enabled = true;
+
+static int __init early_topology_updates(char *p)
+{
+	if (!p)
+		return 0;
+
+	if (!strcmp(p, "off")) {
+		pr_info("Disabling topology updates\n");
+		topology_updates_enabled = false;
+	}
+
+	return 0;
+}
+early_param("topology_updates", early_topology_updates);
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * Find the node associated with a hot added memory section for
@@ -1442,8 +1460,11 @@ static long hcall_vphn(unsigned long cpu, __be32 *associativity)
 	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
 	u64 flags = 1;
 	int hwcpu = get_hard_smp_processor_id(cpu);
+	int i;
 
 	rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu);
+	for (i = 0; i < 6; i++)
+		retbuf[i] = cpu_to_be64(retbuf[i]);
 	vphn_unpack_associativity(retbuf, associativity);
 
 	return rc;
@@ -1488,11 +1509,14 @@ static int update_cpu_topology(void *data)
 	cpu = smp_processor_id();
 
 	for (update = data; update; update = update->next) {
+		int new_nid = update->new_nid;
 		if (cpu != update->cpu)
 			continue;
 
-		unmap_cpu_from_node(update->cpu);
-		map_cpu_to_node(update->cpu, update->new_nid);
+		unmap_cpu_from_node(cpu);
+		map_cpu_to_node(cpu, new_nid);
+		set_cpu_numa_node(cpu, new_nid);
+		set_cpu_numa_mem(cpu, local_memory_node(new_nid));
 		vdso_getcpu_init();
 	}
 
@@ -1539,6 +1563,9 @@ int arch_update_cpu_topology(void)
 	struct device *dev;
 	int weight, new_nid, i = 0;
 
+	if (!prrn_enabled && !vphn_enabled)
+		return 0;
+
 	weight = cpumask_weight(&cpu_associativity_changes_mask);
 	if (!weight)
 		return 0;
@@ -1592,6 +1619,15 @@ int arch_update_cpu_topology(void)
 		cpu = cpu_last_thread_sibling(cpu);
 	}
 
+	pr_debug("Topology update for the following CPUs:\n");
+	if (cpumask_weight(&updated_cpus)) {
+		for (ud = &updates[0]; ud; ud = ud->next) {
+			pr_debug("cpu %d moving from node %d "
+					  "to %d\n", ud->cpu,
+					  ud->old_nid, ud->new_nid);
+		}
+	}
+
 	/*
 	 * In cases where we have nothing to update (because the updates list
 	 * is too short or because the new topology is same as the old one),
@@ -1800,8 +1836,12 @@ static const struct file_operations topology_ops = {
 
 static int topology_update_init(void)
 {
-	start_topology_update();
-	proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops);
+	/* Do not poll for changes if disabled at boot */
+	if (topology_updates_enabled)
+		start_topology_update();
+
+	if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops))
+		return -ENOMEM;
 
 	return 0;
 }
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index c695943a..c90e602 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -48,7 +48,7 @@ static inline int pte_looks_normal(pte_t pte)
 	    (_PAGE_PRESENT | _PAGE_USER);
 }
 
-struct page * maybe_pte_to_page(pte_t pte)
+static struct page *maybe_pte_to_page(pte_t pte)
 {
 	unsigned long pfn = pte_pfn(pte);
 	struct page *page;
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 343a87f..cf11342 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -41,7 +41,7 @@ unsigned long ioremap_base;
 unsigned long ioremap_bot;
 EXPORT_SYMBOL(ioremap_bot);	/* aka VMALLOC_END */
 
-#if defined(CONFIG_6xx) || defined(CONFIG_POWER3)
+#ifdef CONFIG_6xx
 #define HAVE_BATS	1
 #endif
 
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index f6ce1f1..c8d709a 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -54,6 +54,9 @@
 
 #include "mmu_decl.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/thp.h>
+
 /* Some sanity checking */
 #if TASK_SIZE_USER64 > PGTABLE_RANGE
 #error TASK_SIZE_USER64 exceeds pagetable range
@@ -68,7 +71,7 @@
 unsigned long ioremap_bot = IOREMAP_BASE;
 
 #ifdef CONFIG_PPC_MMU_NOHASH
-static void *early_alloc_pgtable(unsigned long size)
+static __ref void *early_alloc_pgtable(unsigned long size)
 {
 	void *pt;
 
@@ -537,8 +540,9 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
 	old = pmd_val(*pmdp);
 	*pmdp = __pmd((old & ~clr) | set);
 #endif
+	trace_hugepage_update(addr, old, clr, set);
 	if (old & _PAGE_HASHPTE)
-		hpte_do_hugepage_flush(mm, addr, pmdp);
+		hpte_do_hugepage_flush(mm, addr, pmdp, old);
 	return old;
 }
 
@@ -642,10 +646,11 @@ void pmdp_splitting_flush(struct vm_area_struct *vma,
 	 * If we didn't had the splitting flag set, go and flush the
 	 * HPTE entries.
 	 */
+	trace_hugepage_splitting(address, old);
 	if (!(old & _PAGE_SPLITTING)) {
 		/* We need to flush the hpte */
 		if (old & _PAGE_HASHPTE)
-			hpte_do_hugepage_flush(vma->vm_mm, address, pmdp);
+			hpte_do_hugepage_flush(vma->vm_mm, address, pmdp, old);
 	}
 	/*
 	 * This ensures that generic code that rely on IRQ disabling
@@ -709,6 +714,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	assert_spin_locked(&mm->page_table_lock);
 	WARN_ON(!pmd_trans_huge(pmd));
 #endif
+	trace_hugepage_set_pmd(addr, pmd);
 	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
 }
 
@@ -723,7 +729,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
  * neesd to be flushed.
  */
 void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
-			    pmd_t *pmdp)
+			    pmd_t *pmdp, unsigned long old_pmd)
 {
 	int ssize, i;
 	unsigned long s_addr;
@@ -745,12 +751,29 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 	if (!hpte_slot_array)
 		return;
 
-	/* get the base page size */
+	/* get the base page size,vsid and segment size */
+#ifdef CONFIG_DEBUG_VM
 	psize = get_slice_psize(mm, s_addr);
+	BUG_ON(psize == MMU_PAGE_16M);
+#endif
+	if (old_pmd & _PAGE_COMBO)
+		psize = MMU_PAGE_4K;
+	else
+		psize = MMU_PAGE_64K;
+
+	if (!is_kernel_addr(s_addr)) {
+		ssize = user_segment_size(s_addr);
+		vsid = get_vsid(mm->context.id, s_addr, ssize);
+		WARN_ON(vsid == 0);
+	} else {
+		vsid = get_kernel_vsid(s_addr, mmu_kernel_ssize);
+		ssize = mmu_kernel_ssize;
+	}
 
 	if (ppc_md.hugepage_invalidate)
-		return ppc_md.hugepage_invalidate(mm, hpte_slot_array,
-						  s_addr, psize);
+		return ppc_md.hugepage_invalidate(vsid, s_addr,
+						  hpte_slot_array,
+						  psize, ssize);
 	/*
 	 * No bluk hpte removal support, invalidate each entry
 	 */
@@ -768,15 +791,6 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 
 		/* 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)
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index 11571e1..5029dc1 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -2,7 +2,7 @@
  * This file contains the routines for handling the MMU on those
  * PowerPC implementations where the MMU substantially follows the
  * architecture specification.  This includes the 6xx, 7xx, 7xxx,
- * 8260, and POWER3 implementations but excludes the 8xx and 4xx.
+ * and 8260 implementations but excludes the 8xx and 4xx.
  *  -- paulus
  *
  *  Derived from arch/ppc/mm/init.c:
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 0399a67..6e450ca 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -46,9 +46,6 @@ static inline unsigned long mk_esid_data(unsigned long ea, int ssize,
 	return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | slot;
 }
 
-#define slb_vsid_shift(ssize)	\
-	((ssize) == MMU_SEGSIZE_256M? SLB_VSID_SHIFT: SLB_VSID_SHIFT_1T)
-
 static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
 					 unsigned long flags)
 {
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index b0c75cc..ded0ea1 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -30,9 +30,11 @@
 #include <linux/err.h>
 #include <linux/spinlock.h>
 #include <linux/export.h>
+#include <linux/hugetlb.h>
 #include <asm/mman.h>
 #include <asm/mmu.h>
-#include <asm/spu.h>
+#include <asm/copro.h>
+#include <asm/hugetlb.h>
 
 /* some sanity checks */
 #if (PGTABLE_RANGE >> 43) > SLICE_MASK_SIZE
@@ -232,9 +234,7 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz
 
 	spin_unlock_irqrestore(&slice_convert_lock, flags);
 
-#ifdef CONFIG_SPU_BASE
-	spu_flush_all_slbs(mm);
-#endif
+	copro_flush_all_slbs(mm);
 }
 
 /*
@@ -671,9 +671,7 @@ void slice_set_psize(struct mm_struct *mm, unsigned long address,
 
 	spin_unlock_irqrestore(&slice_convert_lock, flags);
 
-#ifdef CONFIG_SPU_BASE
-	spu_flush_all_slbs(mm);
-#endif
+	copro_flush_all_slbs(mm);
 }
 
 void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
@@ -684,6 +682,7 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
 	slice_convert(mm, mask, psize);
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
 /*
  * is_hugepage_only_range() is used by generic code to verify whether
  * a normal mmap mapping (non hugetlbfs) is valid on a given area.
@@ -728,4 +727,4 @@ int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 #endif
 	return !slice_check_fit(mask, available);
 }
-
+#endif
diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c
deleted file mode 100644
index 3f8efa6..0000000
--- a/arch/powerpc/mm/stab.c
+++ /dev/null
@@ -1,286 +0,0 @@
-/*
- * PowerPC64 Segment Translation Support.
- *
- * Dave Engebretsen and Mike Corrigan {engebret|mikejc}@us.ibm.com
- *    Copyright (c) 2001 Dave Engebretsen
- *
- * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- */
-
-#include <linux/memblock.h>
-
-#include <asm/pgtable.h>
-#include <asm/mmu.h>
-#include <asm/mmu_context.h>
-#include <asm/paca.h>
-#include <asm/cputable.h>
-#include <asm/prom.h>
-
-struct stab_entry {
-	unsigned long esid_data;
-	unsigned long vsid_data;
-};
-
-#define NR_STAB_CACHE_ENTRIES 8
-static DEFINE_PER_CPU(long, stab_cache_ptr);
-static DEFINE_PER_CPU(long [NR_STAB_CACHE_ENTRIES], stab_cache);
-
-/*
- * Create a segment table entry for the given esid/vsid pair.
- */
-static int make_ste(unsigned long stab, unsigned long esid, unsigned long vsid)
-{
-	unsigned long esid_data, vsid_data;
-	unsigned long entry, group, old_esid, castout_entry, i;
-	unsigned int global_entry;
-	struct stab_entry *ste, *castout_ste;
-	unsigned long kernel_segment = (esid << SID_SHIFT) >= PAGE_OFFSET;
-
-	vsid_data = vsid << STE_VSID_SHIFT;
-	esid_data = esid << SID_SHIFT | STE_ESID_KP | STE_ESID_V;
-	if (! kernel_segment)
-		esid_data |= STE_ESID_KS;
-
-	/* Search the primary group first. */
-	global_entry = (esid & 0x1f) << 3;
-	ste = (struct stab_entry *)(stab | ((esid & 0x1f) << 7));
-
-	/* Find an empty entry, if one exists. */
-	for (group = 0; group < 2; group++) {
-		for (entry = 0; entry < 8; entry++, ste++) {
-			if (!(ste->esid_data & STE_ESID_V)) {
-				ste->vsid_data = vsid_data;
-				eieio();
-				ste->esid_data = esid_data;
-				return (global_entry | entry);
-			}
-		}
-		/* Now search the secondary group. */
-		global_entry = ((~esid) & 0x1f) << 3;
-		ste = (struct stab_entry *)(stab | (((~esid) & 0x1f) << 7));
-	}
-
-	/*
-	 * Could not find empty entry, pick one with a round robin selection.
-	 * Search all entries in the two groups.
-	 */
-	castout_entry = get_paca()->stab_rr;
-	for (i = 0; i < 16; i++) {
-		if (castout_entry < 8) {
-			global_entry = (esid & 0x1f) << 3;
-			ste = (struct stab_entry *)(stab | ((esid & 0x1f) << 7));
-			castout_ste = ste + castout_entry;
-		} else {
-			global_entry = ((~esid) & 0x1f) << 3;
-			ste = (struct stab_entry *)(stab | (((~esid) & 0x1f) << 7));
-			castout_ste = ste + (castout_entry - 8);
-		}
-
-		/* Dont cast out the first kernel segment */
-		if ((castout_ste->esid_data & ESID_MASK) != PAGE_OFFSET)
-			break;
-
-		castout_entry = (castout_entry + 1) & 0xf;
-	}
-
-	get_paca()->stab_rr = (castout_entry + 1) & 0xf;
-
-	/* Modify the old entry to the new value. */
-
-	/* Force previous translations to complete. DRENG */
-	asm volatile("isync" : : : "memory");
-
-	old_esid = castout_ste->esid_data >> SID_SHIFT;
-	castout_ste->esid_data = 0;		/* Invalidate old entry */
-
-	asm volatile("sync" : : : "memory");    /* Order update */
-
-	castout_ste->vsid_data = vsid_data;
-	eieio();				/* Order update */
-	castout_ste->esid_data = esid_data;
-
-	asm volatile("slbie  %0" : : "r" (old_esid << SID_SHIFT));
-	/* Ensure completion of slbie */
-	asm volatile("sync" : : : "memory");
-
-	return (global_entry | (castout_entry & 0x7));
-}
-
-/*
- * Allocate a segment table entry for the given ea and mm
- */
-static int __ste_allocate(unsigned long ea, struct mm_struct *mm)
-{
-	unsigned long vsid;
-	unsigned char stab_entry;
-	unsigned long offset;
-
-	/* Kernel or user address? */
-	if (is_kernel_addr(ea)) {
-		vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M);
-	} else {
-		if ((ea >= TASK_SIZE_USER64) || (! mm))
-			return 1;
-
-		vsid = get_vsid(mm->context.id, ea, MMU_SEGSIZE_256M);
-	}
-
-	stab_entry = make_ste(get_paca()->stab_addr, GET_ESID(ea), vsid);
-
-	if (!is_kernel_addr(ea)) {
-		offset = __get_cpu_var(stab_cache_ptr);
-		if (offset < NR_STAB_CACHE_ENTRIES)
-			__get_cpu_var(stab_cache[offset++]) = stab_entry;
-		else
-			offset = NR_STAB_CACHE_ENTRIES+1;
-		__get_cpu_var(stab_cache_ptr) = offset;
-
-		/* Order update */
-		asm volatile("sync":::"memory");
-	}
-
-	return 0;
-}
-
-int ste_allocate(unsigned long ea)
-{
-	return __ste_allocate(ea, current->mm);
-}
-
-/*
- * Do the segment table work for a context switch: flush all user
- * entries from the table, then preload some probably useful entries
- * for the new task
- */
-void switch_stab(struct task_struct *tsk, struct mm_struct *mm)
-{
-	struct stab_entry *stab = (struct stab_entry *) get_paca()->stab_addr;
-	struct stab_entry *ste;
-	unsigned long offset;
-	unsigned long pc = KSTK_EIP(tsk);
-	unsigned long stack = KSTK_ESP(tsk);
-	unsigned long unmapped_base;
-
-	/* Force previous translations to complete. DRENG */
-	asm volatile("isync" : : : "memory");
-
-	/*
-	 * We need interrupts hard-disabled here, not just soft-disabled,
-	 * so that a PMU interrupt can't occur, which might try to access
-	 * user memory (to get a stack trace) and possible cause an STAB miss
-	 * which would update the stab_cache/stab_cache_ptr per-cpu variables.
-	 */
-	hard_irq_disable();
-
-	offset = __get_cpu_var(stab_cache_ptr);
-	if (offset <= NR_STAB_CACHE_ENTRIES) {
-		int i;
-
-		for (i = 0; i < offset; i++) {
-			ste = stab + __get_cpu_var(stab_cache[i]);
-			ste->esid_data = 0; /* invalidate entry */
-		}
-	} else {
-		unsigned long entry;
-
-		/* Invalidate all entries. */
-		ste = stab;
-
-		/* Never flush the first entry. */
-		ste += 1;
-		for (entry = 1;
-		     entry < (HW_PAGE_SIZE / sizeof(struct stab_entry));
-		     entry++, ste++) {
-			unsigned long ea;
-			ea = ste->esid_data & ESID_MASK;
-			if (!is_kernel_addr(ea)) {
-				ste->esid_data = 0;
-			}
-		}
-	}
-
-	asm volatile("sync; slbia; sync":::"memory");
-
-	__get_cpu_var(stab_cache_ptr) = 0;
-
-	/* Now preload some entries for the new task */
-	if (test_tsk_thread_flag(tsk, TIF_32BIT))
-		unmapped_base = TASK_UNMAPPED_BASE_USER32;
-	else
-		unmapped_base = TASK_UNMAPPED_BASE_USER64;
-
-	__ste_allocate(pc, mm);
-
-	if (GET_ESID(pc) == GET_ESID(stack))
-		return;
-
-	__ste_allocate(stack, mm);
-
-	if ((GET_ESID(pc) == GET_ESID(unmapped_base))
-	    || (GET_ESID(stack) == GET_ESID(unmapped_base)))
-		return;
-
-	__ste_allocate(unmapped_base, mm);
-
-	/* Order update */
-	asm volatile("sync" : : : "memory");
-}
-
-/*
- * Allocate segment tables for secondary CPUs.  These must all go in
- * the first (bolted) segment, so that do_stab_bolted won't get a
- * recursive segment miss on the segment table itself.
- */
-void __init stabs_alloc(void)
-{
-	int cpu;
-
-	if (mmu_has_feature(MMU_FTR_SLB))
-		return;
-
-	for_each_possible_cpu(cpu) {
-		unsigned long newstab;
-
-		if (cpu == 0)
-			continue; /* stab for CPU 0 is statically allocated */
-
-		newstab = memblock_alloc_base(HW_PAGE_SIZE, HW_PAGE_SIZE,
-					 1<<SID_SHIFT);
-		newstab = (unsigned long)__va(newstab);
-
-		memset((void *)newstab, 0, HW_PAGE_SIZE);
-
-		paca[cpu].stab_addr = newstab;
-		paca[cpu].stab_real = __pa(newstab);
-		printk(KERN_INFO "Segment table for CPU %d at 0x%llx "
-		       "virtual, 0x%llx absolute\n",
-		       cpu, paca[cpu].stab_addr, paca[cpu].stab_real);
-	}
-}
-
-/*
- * Build an entry for the base kernel segment and put it into
- * the segment table or SLB.  All other segment table or SLB
- * entries are faulted in.
- */
-void stab_initialize(unsigned long stab)
-{
-	unsigned long vsid = get_kernel_vsid(PAGE_OFFSET, MMU_SEGSIZE_256M);
-	unsigned long stabreal;
-
-	asm volatile("isync; slbia; isync":::"memory");
-	make_ste(stab, GET_ESID(PAGE_OFFSET), vsid);
-
-	/* Order update */
-	asm volatile("sync":::"memory");
-
-	/* Set ASR */
-	stabreal = get_paca()->stab_real | 0x1ul;
-
-	mtspr(SPRN_ASR, stabreal);
-}
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index c99f651..d2a94b8 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -30,6 +30,8 @@
 #include <asm/tlb.h>
 #include <asm/bug.h>
 
+#include <trace/events/thp.h>
+
 DEFINE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch);
 
 /*
@@ -213,10 +215,12 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
 		if (ptep == NULL)
 			continue;
 		pte = pte_val(*ptep);
+		if (hugepage_shift)
+			trace_hugepage_invalidate(start, pte_val(pte));
 		if (!(pte & _PAGE_HASHPTE))
 			continue;
 		if (unlikely(hugepage_shift && pmd_trans_huge(*(pmd_t *)pte)))
-			hpte_do_hugepage_flush(mm, start, (pmd_t *)pte);
+			hpte_do_hugepage_flush(mm, start, (pmd_t *)ptep, pte);
 		else
 			hpte_need_flush(mm, start, ptep, pte, 0);
 	}
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index 356e8b4..89bf95b 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -296,9 +296,12 @@ itlb_miss_fault_bolted:
  * r14 = page table base
  * r13 = PACA
  * r11 = tlb_per_core ptr
- * r10 = cpu number
+ * r10 = crap (free to use)
  */
 tlb_miss_common_e6500:
+	crmove	cr2*4+2,cr0*4+2		/* cr2.eq != 0 if kernel address */
+
+BEGIN_FTR_SECTION		/* CPU_FTR_SMT */
 	/*
 	 * Search if we already have an indirect entry for that virtual
 	 * address, and if we do, bail out.
@@ -309,6 +312,7 @@ tlb_miss_common_e6500:
 	lhz	r10,PACAPACAINDEX(r13)
 	cmpdi	r15,0
 	cmpdi	cr1,r15,1	/* set cr1.eq = 0 for non-recursive */
+	addi	r10,r10,1
 	bne	2f
 	stbcx.	r10,0,r11
 	bne	1b
@@ -322,18 +326,62 @@ tlb_miss_common_e6500:
 	b	1b
 	.previous
 
+	/*
+	 * Erratum A-008139 says that we can't use tlbwe to change
+	 * an indirect entry in any way (including replacing or
+	 * invalidating) if the other thread could be in the process
+	 * of a lookup.  The workaround is to invalidate the entry
+	 * with tlbilx before overwriting.
+	 */
+
+	lbz	r15,TCD_ESEL_NEXT(r11)
+	rlwinm	r10,r15,16,0xff0000
+	oris	r10,r10,MAS0_TLBSEL(1)@h
+	mtspr	SPRN_MAS0,r10
+	isync
+	tlbre
+	mfspr	r15,SPRN_MAS1
+	andis.	r15,r15,MAS1_VALID@h
+	beq	5f
+
+BEGIN_FTR_SECTION_NESTED(532)
+	mfspr	r10,SPRN_MAS8
+	rlwinm	r10,r10,0,0x80000fff  /* tgs,tlpid -> sgs,slpid */
+	mtspr	SPRN_MAS5,r10
+END_FTR_SECTION_NESTED(CPU_FTR_EMB_HV,CPU_FTR_EMB_HV,532)
+
+	mfspr	r10,SPRN_MAS1
+	rlwinm	r15,r10,0,0x3fff0000  /* tid -> spid */
+	rlwimi	r15,r10,20,0x00000003 /* ind,ts -> sind,sas */
+	mfspr	r10,SPRN_MAS6
+	mtspr	SPRN_MAS6,r15
+
 	mfspr	r15,SPRN_MAS2
+	isync
+	tlbilxva 0,r15
+	isync
+
+	mtspr	SPRN_MAS6,r10
+
+5:
+BEGIN_FTR_SECTION_NESTED(532)
+	li	r10,0
+	mtspr	SPRN_MAS8,r10
+	mtspr	SPRN_MAS5,r10
+END_FTR_SECTION_NESTED(CPU_FTR_EMB_HV,CPU_FTR_EMB_HV,532)
 
 	tlbsx	0,r16
 	mfspr	r10,SPRN_MAS1
-	andis.	r10,r10,MAS1_VALID@h
+	andis.	r15,r10,MAS1_VALID@h
 	bne	tlb_miss_done_e6500
-
-	/* Undo MAS-damage from the tlbsx */
+FTR_SECTION_ELSE
 	mfspr	r10,SPRN_MAS1
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_SMT)
+
 	oris	r10,r10,MAS1_VALID@h
-	mtspr	SPRN_MAS1,r10
-	mtspr	SPRN_MAS2,r15
+	beq	cr2,4f
+	rlwinm	r10,r10,0,16,1		/* Clear TID */
+4:	mtspr	SPRN_MAS1,r10
 
 	/* Now, we need to walk the page tables. First check if we are in
 	 * range.
@@ -394,11 +442,13 @@ tlb_miss_common_e6500:
 
 tlb_miss_done_e6500:
 	.macro	tlb_unlock_e6500
+BEGIN_FTR_SECTION
 	beq	cr1,1f		/* no unlock if lock was recursively grabbed */
 	li	r15,0
 	isync
 	stb	r15,0(r11)
 1:
+END_FTR_SECTION_IFSET(CPU_FTR_SMT)
 	.endm
 
 	tlb_unlock_e6500
@@ -407,12 +457,9 @@ tlb_miss_done_e6500:
 	rfi
 
 tlb_miss_kernel_e6500:
-	mfspr	r10,SPRN_MAS1
 	ld	r14,PACA_KERNELPGD(r13)
-	cmpldi	cr0,r15,8		/* Check for vmalloc region */
-	rlwinm	r10,r10,0,16,1		/* Clear TID */
-	mtspr	SPRN_MAS1,r10
-	beq+	tlb_miss_common_e6500
+	cmpldi	cr1,r15,8		/* Check for vmalloc region */
+	beq+	cr1,tlb_miss_common_e6500
 
 tlb_miss_fault_e6500:
 	tlb_unlock_e6500
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 92cb18d..f38ea4d 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -581,42 +581,10 @@ static void setup_mmu_htw(void)
 /*
  * Early initialization of the MMU TLB code
  */
-static void __early_init_mmu(int boot_cpu)
+static void early_init_this_mmu(void)
 {
 	unsigned int mas4;
 
-	/* XXX This will have to be decided at runtime, but right
-	 * now our boot and TLB miss code hard wires it. Ideally
-	 * we should find out a suitable page size and patch the
-	 * TLB miss code (either that or use the PACA to store
-	 * the value we want)
-	 */
-	mmu_linear_psize = MMU_PAGE_1G;
-
-	/* 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.
-	 */
-	if (boot_cpu) {
-		/* Look for supported page sizes */
-		setup_page_sizes();
-
-		/* Look for HW tablewalk support */
-		setup_mmu_htw();
-	}
-
 	/* Set MAS4 based on page table setting */
 
 	mas4 = 0x4 << MAS4_WIMGED_SHIFT;
@@ -650,11 +618,6 @@ static void __early_init_mmu(int boot_cpu)
 	}
 	mtspr(SPRN_MAS4, mas4);
 
-	/* Set the global containing the top of the linear mapping
-	 * for use by the TLB miss code
-	 */
-	linear_map_top = memblock_end_of_DRAM();
-
 #ifdef CONFIG_PPC_FSL_BOOK3E
 	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
 		unsigned int num_cams;
@@ -662,10 +625,49 @@ static void __early_init_mmu(int boot_cpu)
 		/* use a quarter of the TLBCAM for bolted linear map */
 		num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
 		linear_map_top = map_mem_in_cams(linear_map_top, num_cams);
+	}
+#endif
 
-		/* limit memory so we dont have linear faults */
-		memblock_enforce_memory_limit(linear_map_top);
+	/* A sync won't hurt us after mucking around with
+	 * the MMU configuration
+	 */
+	mb();
+}
 
+static void __init early_init_mmu_global(void)
+{
+	/* XXX This will have to be decided at runtime, but right
+	 * now our boot and TLB miss code hard wires it. Ideally
+	 * we should find out a suitable page size and patch the
+	 * TLB miss code (either that or use the PACA to store
+	 * the value we want)
+	 */
+	mmu_linear_psize = MMU_PAGE_1G;
+
+	/* 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_FSL_BOOK3E
+	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);
@@ -675,22 +677,41 @@ static void __early_init_mmu(int boot_cpu)
 	}
 #endif
 
-	/* A sync won't hurt us after mucking around with
-	 * the MMU configuration
+	/* Set the global containing the top of the linear mapping
+	 * for use by the TLB miss code
 	 */
-	mb();
+	linear_map_top = memblock_end_of_DRAM();
+}
+
+static void __init early_mmu_set_memory_limit(void)
+{
+#ifdef CONFIG_PPC_FSL_BOOK3E
+	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(1);
+	early_init_mmu_global();
+	early_init_this_mmu();
+	early_mmu_set_memory_limit();
 }
 
 void early_init_mmu_secondary(void)
 {
-	__early_init_mmu(0);
+	early_init_this_mmu();
 }
 
 void setup_initial_memory_limit(phys_addr_t first_memblock_base,