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 new goodies for 3.17.  The short story:

  The biggest bit is Michael removing all of pre-POWER4 processor
  support from the 64-bit kernel.  POWER3 and rs64.  This gets rid of a
  ton of old cruft that has been bitrotting in a long while.  It was
  broken for quite a few versions already and nobody noticed.  Nobody
  uses those machines anymore.  While at it, he cleaned up a bunch of
  old dusty cabinets, getting rid of a skeletton or two.

  Then, we have some base VFIO support for KVM, which allows assigning
  of PCI devices to KVM guests, support for large 64-bit BARs on
  "powernv" platforms, support for HMI (Hardware Management Interrupts)
  on those same platforms, some sparse-vmemmap improvements (for memory
  hotplug),

  There is the usual batch of Freescale embedded updates (summary in the
  merge commit) and fixes here or there, I think that's it for the
  highlights"

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (102 commits)
  powerpc/eeh: Export eeh_iommu_group_to_pe()
  powerpc/eeh: Add missing #ifdef CONFIG_IOMMU_API
  powerpc: Reduce scariness of interrupt frames in stack traces
  powerpc: start loop at section start of start in vmemmap_populated()
  powerpc: implement vmemmap_free()
  powerpc: implement vmemmap_remove_mapping() for BOOK3S
  powerpc: implement vmemmap_list_free()
  powerpc: Fail remap_4k_pfn() if PFN doesn't fit inside PTE
  powerpc/book3s: Fix endianess issue for HMI handling on napping cpus.
  powerpc/book3s: handle HMIs for cpus in nap mode.
  powerpc/powernv: Invoke opal call to handle hmi.
  powerpc/book3s: Add basic infrastructure to handle HMI in Linux.
  powerpc/iommu: Fix comments with it_page_shift
  powerpc/powernv: Handle compound PE in config accessors
  powerpc/powernv: Handle compound PE for EEH
  powerpc/powernv: Handle compound PE
  powerpc/powernv: Split ioda_eeh_get_state()
  powerpc/powernv: Allow to freeze PE
  powerpc/powernv: Enable M64 aperatus for PHB3
  powerpc/eeh: Aux PE data for error log
  ...

10 files changed, 191 insertions, 336 deletions

diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 51230ee6a40..d0130fff20e 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 \
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 88fdd9d2507..daee7f4e5a1 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -243,7 +243,7 @@ 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;
@@ -821,21 +821,14 @@ 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 +838,8 @@ 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 */
 
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index e3734edffa6..253b4b971c8 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 +231,42 @@ static void __meminit vmemmap_create_mapping(unsigned long start,
 					mmu_kernel_ssize);
 	BUG_ON(mapped < 0);
 }
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+extern int htab_remove_mapping(unsigned long vstart, unsigned long vend,
+			int psize, int ssize);
+
+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 +329,85 @@ 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 +439,16 @@ 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/mmu_context_hash32.c b/arch/powerpc/mm/mmu_context_hash32.c
index 78fef6726e1..aa5a7fd8946 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 3b181b22cd4..d3e9a78eaed 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -611,8 +611,8 @@ 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;
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 343a87fa78b..cf11342bf51 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 f6ce1f111f5..3b3c4d34c7a 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -68,7 +68,7 @@
 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;
 
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index 11571e11883..5029dc19b51 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/stab.c b/arch/powerpc/mm/stab.c
deleted file mode 100644
index 3f8efa6f299..00000000000
--- 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_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index 356e8b41fb0..89bf95bd63b 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