Merge tag 'powerpc-4.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Support for 4PB user address space on 64-bit, opt-in via mmap().

   - Removal of POWER4 support, which was accidentally broken in 2016
     and no one noticed, and blocked use of some modern instructions.

   - Workarounds so that the hypervisor can enable Transactional Memory
     on Power9.

   - A series to disable the DAWR (Data Address Watchpoint Register) on
     Power9.

   - More information displayed in the meltdown/spectre_v1/v2 sysfs
     files.

   - A vpermxor (Power8 Altivec) implementation for the raid6 Q
     Syndrome.

   - A big series to make the allocation of our pacas (per cpu area),
     kernel page tables, and per-cpu stacks NUMA aware when using the
     Radix MMU on Power9.

  And as usual many fixes, reworks and cleanups.

  Thanks to: Aaro Koskinen, Alexandre Belloni, Alexey Kardashevskiy,
  Alistair Popple, Andy Shevchenko, Aneesh Kumar K.V, Anshuman Khandual,
  Balbir Singh, Benjamin Herrenschmidt, Christophe Leroy, Christophe
  Lombard, Cyril Bur, Daniel Axtens, Dave Young, Finn Thain, Frederic
  Barrat, Gustavo Romero, Horia Geantă, Jonathan Neuschäfer, Kees Cook,
  Larry Finger, Laurent Dufour, Laurent Vivier, Logan Gunthorpe,
  Madhavan Srinivasan, Mark Greer, Mark Hairgrove, Markus Elfring,
  Mathieu Malaterre, Matt Brown, Matt Evans, Mauricio Faria de Oliveira,
  Michael Neuling, Naveen N. Rao, Nicholas Piggin, Paul Mackerras,
  Philippe Bergheaud, Ram Pai, Rob Herring, Sam Bobroff, Segher
  Boessenkool, Simon Guo, Simon Horman, Stewart Smith, Sukadev
  Bhattiprolu, Suraj Jitindar Singh, Thiago Jung Bauermann, Vaibhav
  Jain, Vaidyanathan Srinivasan, Vasant Hegde, Wei Yongjun"

* tag 'powerpc-4.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (207 commits)
  powerpc/64s/idle: Fix restore of AMOR on POWER9 after deep sleep
  powerpc/64s: Fix POWER9 DD2.2 and above in cputable features
  powerpc/64s: Fix pkey support in dt_cpu_ftrs, add CPU_FTR_PKEY bit
  powerpc/64s: Fix dt_cpu_ftrs to have restore_cpu clear unwanted LPCR bits
  Revert "powerpc/64s/idle: POWER9 ESL=0 stop avoid save/restore overhead"
  powerpc: iomap.c: introduce io{read|write}64_{lo_hi|hi_lo}
  powerpc: io.h: move iomap.h include so that it can use readq/writeq defs
  cxl: Fix possible deadlock when processing page faults from cxllib
  powerpc/hw_breakpoint: Only disable hw breakpoint if cpu supports it
  powerpc/mm/radix: Update command line parsing for disable_radix
  powerpc/mm/radix: Parse disable_radix commandline correctly.
  powerpc/mm/hugetlb: initialize the pagetable cache correctly for hugetlb
  powerpc/mm/radix: Update pte fragment count from 16 to 256 on radix
  powerpc/mm/keys: Update documentation and remove unnecessary check
  powerpc/64s/idle: POWER9 ESL=0 stop avoid save/restore overhead
  powerpc/64s/idle: Consolidate power9_offline_stop()/power9_idle_stop()
  powerpc/powernv: Always stop secondaries before reboot/shutdown
  powerpc: hard disable irqs in smp_send_stop loop
  powerpc: use NMI IPI for smp_send_stop
  powerpc/powernv: Fix SMT4 forcing idle code
  ...

24 files changed, 662 insertions, 445 deletions

diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c
index 849f50cd62f2..cf77d755246d 100644
--- a/arch/powerpc/mm/8xx_mmu.c
+++ b/arch/powerpc/mm/8xx_mmu.c
@@ -192,7 +192,7 @@ void set_context(unsigned long id, pgd_t *pgd)
 	mtspr(SPRN_M_TW, __pa(pgd) - offset);
 
 	/* Update context */
-	mtspr(SPRN_M_CASID, id);
+	mtspr(SPRN_M_CASID, id - 1);
 	/* sync */
 	mb();
 }
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 697b70ad1195..7d0945bd3a61 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -112,7 +112,7 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
 			return 1;
 		psize = get_slice_psize(mm, ea);
 		ssize = user_segment_size(ea);
-		vsid = get_vsid(mm->context.id, ea, ssize);
+		vsid = get_user_vsid(&mm->context, ea, ssize);
 		vsidkey = SLB_VSID_USER;
 		break;
 	case VMALLOC_REGION_ID:
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 866446cf2d9a..c01d627e687a 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -297,7 +297,12 @@ static bool access_error(bool is_write, bool is_exec,
 
 	if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
 		return true;
-
+	/*
+	 * We should ideally do the vma pkey access check here. But in the
+	 * fault path, handle_mm_fault() also does the same check. To avoid
+	 * these multiple checks, we skip it here and handle access error due
+	 * to pkeys later.
+	 */
 	return false;
 }
 
@@ -518,25 +523,16 @@ good_area:
 
 #ifdef CONFIG_PPC_MEM_KEYS
 	/*
-	 * if the HPTE is not hashed, hardware will not detect
-	 * a key fault. Lets check if we failed because of a
-	 * software detected key fault.
+	 * we skipped checking for access error due to key earlier.
+	 * Check that using handle_mm_fault error return.
 	 */
 	if (unlikely(fault & VM_FAULT_SIGSEGV) &&
-		!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE,
-			is_exec, 0)) {
-		/*
-		 * The PGD-PDT...PMD-PTE tree may not have been fully setup.
-		 * Hence we cannot walk the tree to locate the PTE, to locate
-		 * the key. Hence let's use vma_pkey() to get the key; instead
-		 * of get_mm_addr_key().
-		 */
+		!arch_vma_access_permitted(vma, is_write, is_exec, 0)) {
+
 		int pkey = vma_pkey(vma);
 
-		if (likely(pkey)) {
-			up_read(&mm->mmap_sem);
-			return bad_key_fault_exception(regs, address, pkey);
-		}
+		up_read(&mm->mmap_sem);
+		return bad_key_fault_exception(regs, address, pkey);
 	}
 #endif /* CONFIG_PPC_MEM_KEYS */
 
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 656933c85925..1d049c78c82a 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -866,18 +866,6 @@ static void native_flush_hash_range(unsigned long number, int local)
 	local_irq_restore(flags);
 }
 
-static int native_register_proc_table(unsigned long base, unsigned long page_size,
-				      unsigned long table_size)
-{
-	unsigned long patb1 = base << 25; /* VSID */
-
-	patb1 |= (page_size << 5);  /* sllp */
-	patb1 |= table_size;
-
-	partition_tb->patb1 = cpu_to_be64(patb1);
-	return 0;
-}
-
 void __init hpte_init_native(void)
 {
 	mmu_hash_ops.hpte_invalidate	= native_hpte_invalidate;
@@ -889,7 +877,4 @@ void __init hpte_init_native(void)
 	mmu_hash_ops.hpte_clear_all	= native_hpte_clear;
 	mmu_hash_ops.flush_hash_range = native_flush_hash_range;
 	mmu_hash_ops.hugepage_invalidate   = native_hugepage_invalidate;
-
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
-		register_process_table = native_register_proc_table;
 }
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index cf290d415dcd..0bd3790d35df 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -132,9 +132,10 @@ EXPORT_SYMBOL(mmu_hash_ops);
  * is provided by the firmware.
  */
 
-/* Pre-POWER4 CPUs (4k pages only)
+/*
+ * Fallback (4k pages only)
  */
-static struct mmu_psize_def mmu_psize_defaults_old[] = {
+static struct mmu_psize_def mmu_psize_defaults[] = {
 	[MMU_PAGE_4K] = {
 		.shift	= 12,
 		.sllp	= 0,
@@ -554,8 +555,8 @@ static void __init htab_scan_page_sizes(void)
 	mmu_psize_set_default_penc();
 
 	/* Default to 4K pages only */
-	memcpy(mmu_psize_defs, mmu_psize_defaults_old,
-	       sizeof(mmu_psize_defaults_old));
+	memcpy(mmu_psize_defs, mmu_psize_defaults,
+	       sizeof(mmu_psize_defaults));
 
 	/*
 	 * Try to find the available page sizes in the device-tree
@@ -781,7 +782,7 @@ void resize_hpt_for_hotplug(unsigned long new_mem_size)
 	}
 }
 
-int hash__create_section_mapping(unsigned long start, unsigned long end)
+int hash__create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
 	int rc = htab_bolt_mapping(start, end, __pa(start),
 				   pgprot_val(PAGE_KERNEL), mmu_linear_psize,
@@ -875,6 +876,12 @@ static void __init htab_initialize(void)
 		/* Using a hypervisor which owns the htab */
 		htab_address = NULL;
 		_SDR1 = 0; 
+		/*
+		 * On POWER9, we need to do a H_REGISTER_PROC_TBL hcall
+		 * to inform the hypervisor that we wish to use the HPT.
+		 */
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			register_process_table(0, 0, 0);
 #ifdef CONFIG_FA_DUMP
 		/*
 		 * If firmware assisted dump is active firmware preserves
@@ -1110,19 +1117,18 @@ unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
 #ifdef CONFIG_PPC_MM_SLICES
 static unsigned int get_paca_psize(unsigned long addr)
 {
-	u64 lpsizes;
-	unsigned char *hpsizes;
+	unsigned char *psizes;
 	unsigned long index, mask_index;
 
 	if (addr < SLICE_LOW_TOP) {
-		lpsizes = get_paca()->mm_ctx_low_slices_psize;
+		psizes = get_paca()->mm_ctx_low_slices_psize;
 		index = GET_LOW_SLICE_INDEX(addr);
-		return (lpsizes >> (index * 4)) & 0xF;
+	} else {
+		psizes = get_paca()->mm_ctx_high_slices_psize;
+		index = GET_HIGH_SLICE_INDEX(addr);
 	}
-	hpsizes = get_paca()->mm_ctx_high_slices_psize;
-	index = GET_HIGH_SLICE_INDEX(addr);
 	mask_index = index & 0x1;
-	return (hpsizes[index >> 1] >> (mask_index * 4)) & 0xF;
+	return (psizes[index >> 1] >> (mask_index * 4)) & 0xF;
 }
 
 #else
@@ -1262,7 +1268,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 		}
 		psize = get_slice_psize(mm, ea);
 		ssize = user_segment_size(ea);
-		vsid = get_vsid(mm->context.id, ea, ssize);
+		vsid = get_user_vsid(&mm->context, ea, ssize);
 		break;
 	case VMALLOC_REGION_ID:
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
@@ -1527,7 +1533,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 
 	/* Get VSID */
 	ssize = user_segment_size(ea);
-	vsid = get_vsid(mm->context.id, ea, ssize);
+	vsid = get_user_vsid(&mm->context, ea, ssize);
 	if (!vsid)
 		return;
 	/*
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 3a08d211d2ee..f1153f8254e3 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -122,9 +122,6 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 #if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
 #define HUGEPD_PGD_SHIFT PGDIR_SHIFT
 #define HUGEPD_PUD_SHIFT PUD_SHIFT
-#else
-#define HUGEPD_PGD_SHIFT PUD_SHIFT
-#define HUGEPD_PUD_SHIFT PMD_SHIFT
 #endif
 
 /*
@@ -553,9 +550,11 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	struct hstate *hstate = hstate_file(file);
 	int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
 
+#ifdef CONFIG_PPC_RADIX_MMU
 	if (radix_enabled())
 		return radix__hugetlb_get_unmapped_area(file, addr, len,
 						       pgoff, flags);
+#endif
 	return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1);
 }
 #endif
@@ -563,10 +562,12 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 {
 #ifdef CONFIG_PPC_MM_SLICES
-	unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start);
 	/* With radix we don't use slice, so derive it from vma*/
-	if (!radix_enabled())
+	if (!radix_enabled()) {
+		unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start);
+
 		return 1UL << mmu_psize_to_shift(psize);
+	}
 #endif
 	return vma_kernel_pagesize(vma);
 }
@@ -663,15 +664,26 @@ static int __init hugetlbpage_init(void)
 
 		shift = mmu_psize_to_shift(psize);
 
-		if (add_huge_page_size(1ULL << shift) < 0)
+#ifdef CONFIG_PPC_BOOK3S_64
+		if (shift > PGDIR_SHIFT)
 			continue;
-
+		else if (shift > PUD_SHIFT)
+			pdshift = PGDIR_SHIFT;
+		else if (shift > PMD_SHIFT)
+			pdshift = PUD_SHIFT;
+		else
+			pdshift = PMD_SHIFT;
+#else
 		if (shift < HUGEPD_PUD_SHIFT)
 			pdshift = PMD_SHIFT;
 		else if (shift < HUGEPD_PGD_SHIFT)
 			pdshift = PUD_SHIFT;
 		else
 			pdshift = PGDIR_SHIFT;
+#endif
+
+		if (add_huge_page_size(1ULL << shift) < 0)
+			continue;
 		/*
 		 * if we have pdshift and shift value same, we don't
 		 * use pgt cache for hugepd.
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 6419b33ca309..3e59e5d64b01 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -88,18 +88,13 @@ void MMU_init(void);
 int __map_without_bats;
 int __map_without_ltlbs;
 
-/*
- * This tells the system to allow ioremapping memory marked as reserved.
- */
-int __allow_ioremap_reserved;
-
 /* max amount of low RAM to map in */
 unsigned long __max_low_memory = MAX_LOW_MEM;
 
 /*
  * Check for command-line options that affect what MMU_init will do.
  */
-void __init MMU_setup(void)
+static void __init MMU_setup(void)
 {
 	/* Check for nobats option (used in mapin_ram). */
 	if (strstr(boot_command_line, "nobats")) {
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index fdb424a29f03..51ce091914f9 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -68,12 +68,6 @@
 
 #include "mmu_decl.h"
 
-#ifdef CONFIG_PPC_BOOK3S_64
-#if H_PGTABLE_RANGE > USER_VSID_RANGE
-#warning Limited user VSID range means pagetable space is wasted
-#endif
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
 phys_addr_t memstart_addr = ~0;
 EXPORT_SYMBOL_GPL(memstart_addr);
 phys_addr_t kernstart_addr;
@@ -372,7 +366,7 @@ static int __init parse_disable_radix(char *p)
 {
 	bool val;
 
-	if (strlen(p) == 0)
+	if (!p)
 		val = true;
 	else if (kstrtobool(p, &val))
 		return -EINVAL;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index fe8c61149fb8..737f8a4632cc 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -82,17 +82,7 @@ static inline pte_t *virt_to_kpte(unsigned long vaddr)
 
 int page_is_ram(unsigned long pfn)
 {
-#ifndef CONFIG_PPC64	/* XXX for now */
-	return pfn < max_pfn;
-#else
-	unsigned long paddr = (pfn << PAGE_SHIFT);
-	struct memblock_region *reg;
-
-	for_each_memblock(memory, reg)
-		if (paddr >= reg->base && paddr < (reg->base + reg->size))
-			return 1;
-	return 0;
-#endif
+	return memblock_is_memory(__pfn_to_phys(pfn));
 }
 
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
@@ -117,7 +107,7 @@ int memory_add_physaddr_to_nid(u64 start)
 }
 #endif
 
-int __weak create_section_mapping(unsigned long start, unsigned long end)
+int __weak create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
 	return -ENODEV;
 }
@@ -127,7 +117,7 @@ int __weak remove_section_mapping(unsigned long start, unsigned long end)
 	return -ENODEV;
 }
 
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
+int __meminit arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 		bool want_memblock)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
@@ -137,7 +127,7 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 	resize_hpt_for_hotplug(memblock_phys_mem_size());
 
 	start = (unsigned long)__va(start);
-	rc = create_section_mapping(start, start + size);
+	rc = create_section_mapping(start, start + size, nid);
 	if (rc) {
 		pr_warn("Unable to create mapping for hot added memory 0x%llx..0x%llx: %d\n",
 			start, start + size, rc);
@@ -148,7 +138,7 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-int arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+int __meminit arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
@@ -212,7 +202,7 @@ walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 EXPORT_SYMBOL_GPL(walk_system_ram_range);
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-void __init initmem_init(void)
+void __init mem_topology_setup(void)
 {
 	max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
 	min_low_pfn = MEMORY_START >> PAGE_SHIFT;
@@ -224,7 +214,10 @@ void __init initmem_init(void)
 	 * memblock_regions
 	 */
 	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
+}
 
+void __init initmem_init(void)
+{
 	/* XXX need to clip this if using highmem? */
 	sparse_memory_present_with_active_regions(0);
 	sparse_init();
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index 3f980baade4c..b75194dff64c 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -94,13 +94,6 @@ static int hash__init_new_context(struct mm_struct *mm)
 		return index;
 
 	/*
-	 * In the case of exec, use the default limit,
-	 * otherwise inherit it from the mm we are duplicating.
-	 */
-	if (!mm->context.slb_addr_limit)
-		mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW_USER64;
-
-	/*
 	 * The old code would re-promote on fork, we don't do that when using
 	 * slices as it could cause problem promoting slices that have been
 	 * forced down to 4K.
@@ -115,7 +108,7 @@ static int hash__init_new_context(struct mm_struct *mm)
 	 * check against 0 is OK.
 	 */
 	if (mm->context.id == 0)
-		slice_set_user_psize(mm, mmu_virtual_psize);
+		slice_init_new_context_exec(mm);
 
 	subpage_prot_init_new_context(mm);
 
@@ -186,6 +179,19 @@ void __destroy_context(int context_id)
 }
 EXPORT_SYMBOL_GPL(__destroy_context);
 
+static void destroy_contexts(mm_context_t *ctx)
+{
+	int index, context_id;
+
+	spin_lock(&mmu_context_lock);
+	for (index = 0; index < ARRAY_SIZE(ctx->extended_id); index++) {
+		context_id = ctx->extended_id[index];
+		if (context_id)
+			ida_remove(&mmu_context_ida, context_id);
+	}
+	spin_unlock(&mmu_context_lock);
+}
+
 #ifdef CONFIG_PPC_64K_PAGES
 static void destroy_pagetable_page(struct mm_struct *mm)
 {
@@ -224,7 +230,7 @@ void destroy_context(struct mm_struct *mm)
 	else
 		subpage_prot_free(mm);
 	destroy_pagetable_page(mm);
-	__destroy_context(mm->context.id);
+	destroy_contexts(&mm->context);
 	mm->context.id = MMU_NO_CONTEXT;
 }
 
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index 4554d6527682..be8f5c9d4d08 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -331,6 +331,17 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm)
 {
 	pr_hard("initing context for mm @%p\n", mm);
 
+#ifdef	CONFIG_PPC_MM_SLICES
+	/*
+	 * We have MMU_NO_CONTEXT set to be ~0. Hence check
+	 * explicitly against context.id == 0. This ensures that we properly
+	 * initialize context slice details for newly allocated mm's (which will
+	 * have id == 0) and don't alter context slice inherited via fork (which
+	 * will have id != 0).
+	 */
+	if (mm->context.id == 0)
+		slice_init_new_context_exec(mm);
+#endif
 	mm->context.id = MMU_NO_CONTEXT;
 	mm->context.active = 0;
 	return 0;
@@ -428,8 +439,8 @@ void __init mmu_context_init(void)
 	 *      -- BenH
 	 */
 	if (mmu_has_feature(MMU_FTR_TYPE_8xx)) {
-		first_context = 0;
-		last_context = 15;
+		first_context = 1;
+		last_context = 16;
 		no_selective_tlbil = true;
 	} else if (mmu_has_feature(MMU_FTR_TYPE_47x)) {
 		first_context = 1;
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 57fbc554c785..c4c0a09a7775 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -98,7 +98,6 @@ extern void setbat(int index, unsigned long virt, phys_addr_t phys,
 		   unsigned int size, pgprot_t prot);
 
 extern int __map_without_bats;
-extern int __allow_ioremap_reserved;
 extern unsigned int rtas_data, rtas_size;
 
 struct hash_pte;
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index edd8d0bc9364..57a5029b4521 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -831,18 +831,13 @@ out:
 	of_node_put(rtas);
 }
 
-void __init initmem_init(void)
+void __init mem_topology_setup(void)
 {
-	int nid, cpu;
-
-	max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
-	max_pfn = max_low_pfn;
+	int cpu;
 
 	if (parse_numa_properties())
 		setup_nonnuma();
 
-	memblock_dump_all();
-
 	/*
 	 * Modify the set of possible NUMA nodes to reflect information
 	 * available about the set of online nodes, and the set of nodes
@@ -853,6 +848,23 @@ void __init initmem_init(void)
 
 	find_possible_nodes();
 
+	setup_node_to_cpumask_map();
+
+	reset_numa_cpu_lookup_table();
+
+	for_each_present_cpu(cpu)
+		numa_setup_cpu(cpu);
+}
+
+void __init initmem_init(void)
+{
+	int nid;
+
+	max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
+	max_pfn = max_low_pfn;
+
+	memblock_dump_all();
+
 	for_each_online_node(nid) {
 		unsigned long start_pfn, end_pfn;
 
@@ -863,10 +875,6 @@ void __init initmem_init(void)
 
 	sparse_init();
 
-	setup_node_to_cpumask_map();
-
-	reset_numa_cpu_lookup_table();
-
 	/*
 	 * 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}
@@ -876,8 +884,6 @@ void __init initmem_init(void)
 	 */
 	cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "powerpc/numa:prepare",
 				  ppc_numa_cpu_prepare, ppc_numa_cpu_dead);
-	for_each_present_cpu(cpu)
-		numa_setup_cpu(cpu);
 }
 
 static int __init early_numa(char *p)
@@ -1105,7 +1111,7 @@ static void setup_cpu_associativity_change_counters(void)
 	for_each_possible_cpu(cpu) {
 		int i;
 		u8 *counts = vphn_cpu_change_counts[cpu];
-		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
+		volatile u8 *hypervisor_counts = lppaca_of(cpu).vphn_assoc_counts;
 
 		for (i = 0; i < distance_ref_points_depth; i++)
 			counts[i] = hypervisor_counts[i];
@@ -1131,7 +1137,7 @@ static int update_cpu_associativity_changes_mask(void)
 	for_each_possible_cpu(cpu) {
 		int i, changed = 0;
 		u8 *counts = vphn_cpu_change_counts[cpu];
-		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
+		volatile u8 *hypervisor_counts = lppaca_of(cpu).vphn_assoc_counts;
 
 		for (i = 0; i < distance_ref_points_depth; i++) {
 			if (hypervisor_counts[i] != counts[i]) {
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index 422e80253a33..518518fb7c45 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -155,15 +155,15 @@ void mmu_cleanup_all(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int create_section_mapping(unsigned long start, unsigned long end)
+int __meminit create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
 	if (radix_enabled())
-		return radix__create_section_mapping(start, end);
+		return radix__create_section_mapping(start, end, nid);
 
-	return hash__create_section_mapping(start, end);
+	return hash__create_section_mapping(start, end, nid);
 }
 
-int remove_section_mapping(unsigned long start, unsigned long end)
+int __meminit remove_section_mapping(unsigned long start, unsigned long end)
 {
 	if (radix_enabled())
 		return radix__remove_section_mapping(start, end);
diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c
index 469808e77e58..199bfda5f0d9 100644
--- a/arch/powerpc/mm/pgtable-hash64.c
+++ b/arch/powerpc/mm/pgtable-hash64.c
@@ -24,6 +24,10 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/thp.h>
 
+#if H_PGTABLE_RANGE > (USER_VSID_RANGE * (TASK_SIZE_USER64 / TASK_CONTEXT_SIZE))
+#warning Limited user VSID range means pagetable space is wasted
+#endif
+
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 /*
  * vmemmap is the starting address of the virtual address space where
@@ -320,7 +324,7 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 
 	if (!is_kernel_addr(addr)) {
 		ssize = user_segment_size(addr);
-		vsid = get_vsid(mm->context.id, addr, ssize);
+		vsid = get_user_vsid(&mm->context, addr, ssize);
 		WARN_ON(vsid == 0);
 	} else {
 		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 2e10a964e290..f1891e215e39 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -48,20 +48,88 @@ static int native_register_process_table(unsigned long base, unsigned long pg_sz
 	return 0;
 }
 
-static __ref void *early_alloc_pgtable(unsigned long size)
+static __ref void *early_alloc_pgtable(unsigned long size, int nid,
+			unsigned long region_start, unsigned long region_end)
 {
+	unsigned long pa = 0;
 	void *pt;
 
-	pt = __va(memblock_alloc_base(size, size, MEMBLOCK_ALLOC_ANYWHERE));
+	if (region_start || region_end) /* has region hint */
+		pa = memblock_alloc_range(size, size, region_start, region_end,
+						MEMBLOCK_NONE);
+	else if (nid != -1) /* has node hint */
+		pa = memblock_alloc_base_nid(size, size,
+						MEMBLOCK_ALLOC_ANYWHERE,
+						nid, MEMBLOCK_NONE);
+
+	if (!pa)
+		pa = memblock_alloc_base(size, size, MEMBLOCK_ALLOC_ANYWHERE);
+
+	BUG_ON(!pa);
+
+	pt = __va(pa);
 	memset(pt, 0, size);
 
 	return pt;
 }
 
-int radix__map_kernel_page(unsigned long ea, unsigned long pa,
+static int early_map_kernel_page(unsigned long ea, unsigned long pa,
 			  pgprot_t flags,
-			  unsigned int map_page_size)
+			  unsigned int map_page_size,
+			  int nid,
+			  unsigned long region_start, unsigned long region_end)
 {
+	unsigned long pfn = pa >> PAGE_SHIFT;
+	pgd_t *pgdp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep;
+
+	pgdp = pgd_offset_k(ea);
+	if (pgd_none(*pgdp)) {
+		pudp = early_alloc_pgtable(PUD_TABLE_SIZE, nid,
+						region_start, region_end);
+		pgd_populate(&init_mm, pgdp, pudp);
+	}
+	pudp = pud_offset(pgdp, ea);
+	if (map_page_size == PUD_SIZE) {
+		ptep = (pte_t *)pudp;
+		goto set_the_pte;
+	}
+	if (pud_none(*pudp)) {
+		pmdp = early_alloc_pgtable(PMD_TABLE_SIZE, nid,
+						region_start, region_end);
+		pud_populate(&init_mm, pudp, pmdp);
+	}
+	pmdp = pmd_offset(pudp, ea);
+	if (map_page_size == PMD_SIZE) {
+		ptep = pmdp_ptep(pmdp);
+		goto set_the_pte;
+	}
+	if (!pmd_present(*pmdp)) {
+		ptep = early_alloc_pgtable(PAGE_SIZE, nid,
+						region_start, region_end);
+		pmd_populate_kernel(&init_mm, pmdp, ptep);
+	}
+	ptep = pte_offset_kernel(pmdp, ea);
+
+set_the_pte:
+	set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags));
+	smp_wmb();
+	return 0;
+}
+
+/*
+ * nid, region_start, and region_end are hints to try to place the page
+ * table memory in the same node or region.
+ */
+static int __map_kernel_page(unsigned long ea, unsigned long pa,
+			  pgprot_t flags,
+			  unsigned int map_page_size,
+			  int nid,
+			  unsigned long region_start, unsigned long region_end)
+{
+	unsigned long pfn = pa >> PAGE_SHIFT;
 	pgd_t *pgdp;
 	pud_t *pudp;
 	pmd_t *pmdp;
@@ -70,61 +138,48 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa,
 	 * Make sure task size is correct as per the max adddr
 	 */
 	BUILD_BUG_ON(TASK_SIZE_USER64 > RADIX_PGTABLE_RANGE);
-	if (slab_is_available()) {
-		pgdp = pgd_offset_k(ea);
-		pudp = pud_alloc(&init_mm, pgdp, ea);
-		if (!pudp)
-			return -ENOMEM;
-		if (map_page_size == PUD_SIZE) {
-			ptep = (pte_t *)pudp;
-			goto set_the_pte;
-		}
-		pmdp = pmd_alloc(&init_mm, pudp, ea);
-		if (!pmdp)
-			return -ENOMEM;
-		if (map_page_size == PMD_SIZE) {
-			ptep = pmdp_ptep(pmdp);
-			goto set_the_pte;
-		}
-		ptep = pte_alloc_kernel(pmdp, ea);
-		if (!ptep)
-			return -ENOMEM;
-	} else {
-		pgdp = pgd_offset_k(ea);
-		if (pgd_none(*pgdp)) {
-			pudp = early_alloc_pgtable(PUD_TABLE_SIZE);
-			BUG_ON(pudp == NULL);
-			pgd_populate(&init_mm, pgdp, pudp);
-		}
-		pudp = pud_offset(pgdp, ea);
-		if (map_page_size == PUD_SIZE) {
-			ptep = (pte_t *)pudp;
-			goto set_the_pte;
-		}
-		if (pud_none(*pudp)) {
-			pmdp = early_alloc_pgtable(PMD_TABLE_SIZE);
-			BUG_ON(pmdp == NULL);
-			pud_populate(&init_mm, pudp, pmdp);
-		}
-		pmdp = pmd_offset(pudp, ea);
-		if (map_page_size == PMD_SIZE) {
-			ptep = pmdp_ptep(pmdp);
-			goto set_the_pte;
-		}
-		if (!pmd_present(*pmdp)) {
-			ptep = early_alloc_pgtable(PAGE_SIZE);
-			BUG_ON(ptep == NULL);
-			pmd_populate_kernel(&init_mm, pmdp, ptep);
-		}
-		ptep = pte_offset_kernel(pmdp, ea);
+
+	if (unlikely(!slab_is_available()))
+		return early_map_kernel_page(ea, pa, flags, map_page_size,
+						nid, region_start, region_end);
+
+	/*
+	 * Should make page table allocation functions be able to take a
+	 * node, so we can place kernel page tables on the right nodes after
+	 * boot.
+	 */
+	pgdp = pgd_offset_k(ea);
+	pudp = pud_alloc(&init_mm, pgdp, ea);
+	if (!pudp)
+		return -ENOMEM;
+	if (map_page_size == PUD_SIZE) {
+		ptep = (pte_t *)pudp;
+		goto set_the_pte;
+	}
+	pmdp = pmd_alloc(&init_mm, pudp, ea);
+	if (!pmdp)
+		return -ENOMEM;
+	if (map_page_size == PMD_SIZE) {
+		ptep = pmdp_ptep(pmdp);
+		goto set_the_pte;
 	}
+	ptep = pte_alloc_kernel(pmdp, ea);
+	if (!ptep)
+		return -ENOMEM;
 
 set_the_pte:
-	set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, flags));
+	set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags));
 	smp_wmb();
 	return 0;
 }
 
+int radix__map_kernel_page(unsigned long ea, unsigned long pa,
+			  pgprot_t flags,
+			  unsigned int map_page_size)
+{
+	return __map_kernel_page(ea, pa, flags, map_page_size, -1, 0, 0);
+}
+
 #ifdef CONFIG_STRICT_KERNEL_RWX
 void radix__change_memory_range(unsigned long start, unsigned long end,
 				unsigned long clear)
@@ -211,7 +266,8 @@ static inline void __meminit print_mapping(unsigned long start,
 }
 
 static int __meminit create_physical_mapping(unsigned long start,
-					     unsigned long end)
+					     unsigned long end,
+					     int nid)
 {
 	unsigned long vaddr, addr, mapping_size = 0;
 	pgprot_t prot;
@@ -267,7 +323,7 @@ retry:
 		else
 			prot = PAGE_KERNEL;
 
-		rc = radix__map_kernel_page(vaddr, addr, prot, mapping_size);
+		rc = __map_kernel_page(vaddr, addr, prot, mapping_size, nid, start, end);
 		if (rc)
 			return rc;
 	}
@@ -276,7 +332,7 @@ retry:
 	return 0;
 }
 
-static void __init radix_init_pgtable(void)
+void __init radix_init_pgtable(void)
 {
 	unsigned long rts_field;
 	struct memblock_region *reg;
@@ -286,9 +342,16 @@ static void __init radix_init_pgtable(void)
 	/*
 	 * Create the linear mapping, using standard page size for now
 	 */
-	for_each_memblock(memory, reg)
+	for_each_memblock(memory, reg) {
+		/*
+		 * The memblock allocator  is up at this point, so the
+		 * page tables will be allocated within the range. No
+		 * need or a node (which we don't have yet).
+		 */
 		WARN_ON(create_physical_mapping(reg->base,
-						reg->base + reg->size));
+						reg->base + reg->size,
+						-1));
+	}
 
 	/* Find out how many PID bits are supported */
 	if (cpu_has_feature(CPU_FTR_HVMODE)) {
@@ -317,7 +380,7 @@ static void __init radix_init_pgtable(void)
 	 * host.
 	 */
 	BUG_ON(PRTB_SIZE_SHIFT > 36);
-	process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT);
+	process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT, -1, 0, 0);
 	/*
 	 * Fill in the process table.
 	 */
@@ -575,12 +638,8 @@ void __init radix__early_init_mmu(void)
 #ifdef CONFIG_PCI
 	pci_io_base = ISA_IO_BASE;
 #endif
-
-	/*
-	 * For now radix also use the same frag size
-	 */
-	__pte_frag_nr = H_PTE_FRAG_NR;
-	__pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT;
+	__pte_frag_nr = RADIX_PTE_FRAG_NR;
+	__pte_frag_size_shift = RADIX_PTE_FRAG_SIZE_SHIFT;
 
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
 		radix_init_native();
@@ -695,7 +754,7 @@ struct change_mapping_params {
 	unsigned long aligned_end;
 };
 
-static int stop_machine_change_mapping(void *data)
+static int __meminit stop_machine_change_mapping(void *data)
 {
 	struct change_mapping_params *params =
 			(struct change_mapping_params *)data;
@@ -705,8 +764,8 @@ static int stop_machine_change_mapping(void *data)
 
 	spin_unlock(&init_mm.page_table_lock);
 	pte_clear(&init_mm, params->aligned_start, params->pte);
-	create_physical_mapping(params->aligned_start, params->start);
-	create_physical_mapping(params->end, params->aligned_end);
+	create_physical_mapping(params->aligned_start, params->start, -1);
+	create_physical_mapping(params->end, params->aligned_end, -1);
 	spin_lock(&init_mm.page_table_lock);
 	return 0;
 }
@@ -742,7 +801,7 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr,
 /*
  * clear the pte and potentially split the mapping helper
  */
-static void split_kernel_mapping(unsigned long addr, unsigned long end,
+static void __meminit split_kernel_mapping(unsigned long addr, unsigned long end,
 				unsigned long size, pte_t *pte)
 {
 	unsigned long mask = ~(size - 1);
@@ -835,7 +894,7 @@ static void remove_pud_table(pud_t *pud_start, unsigned long addr,
 	}
 }
 
-static void remove_pagetable(unsigned long start, unsigned long end)
+static void __meminit remove_pagetable(unsigned long start, unsigned long end)
 {
 	unsigned long addr, next;
 	pud_t *pud_base;
@@ -863,12 +922,12 @@ static void remove_pagetable(unsigned long start, unsigned long end)
 	radix__flush_tlb_kernel_range(start, end);
 }
 
-int __ref radix__create_section_mapping(unsigned long start, unsigned long end)
+int __meminit radix__create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
-	return create_physical_mapping(start, end);
+	return create_physical_mapping(start, end, nid);
 }
 
-int radix__remove_section_mapping(unsigned long start, unsigned long end)
+int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end)
 {
 	remove_pagetable(start, end);
 	return 0;
@@ -876,19 +935,30 @@ int radix__remove_section_mapping(unsigned long start, unsigned long end)
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
+static int __map_kernel_page_nid(unsigned long ea, unsigned long pa,
+				 pgprot_t flags, unsigned int map_page_size,
+				 int nid)
+{
+	return __map_kernel_page(ea, pa, flags, map_page_size, nid, 0, 0);
+}
+
 int __meminit radix__vmemmap_create_mapping(unsigned long start,
 				      unsigned long page_size,
 				      unsigned long phys)
 {
 	/* Create a PTE encoding */
 	unsigned long flags = _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_KERNEL_RW;
+	int nid = early_pfn_to_nid(phys >> PAGE_SHIFT);
+	int ret;
+
+	ret = __map_kernel_page_nid(start, phys, __pgprot(flags), page_size, nid);
+	BUG_ON(ret);
 
-	BUG_ON(radix__map_kernel_page(start, phys, __pgprot(flags), page_size));
 	return 0;
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-void radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size)
+void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size)
 {
 	remove_pagetable(start, start + page_size);
 }
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index d35d9ad3c1cd..120a49bfb9c6 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -148,7 +148,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags,
 	 * mem_init() sets high_memory so only do the check after that.
 	 */
 	if (slab_is_available() && (p < virt_to_phys(high_memory)) &&
-	    !(__allow_ioremap_reserved && memblock_is_region_reserved(p, size))) {
+	    page_is_ram(__phys_to_pfn(p))) {
 		printk("__ioremap(): phys addr 0x%llx is RAM lr %ps\n",
 		       (unsigned long long)p, __builtin_return_address(0));
 		return NULL;
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index adf469f312f2..9bf659d5078c 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -57,11 +57,6 @@
 
 #include "mmu_decl.h"
 
-#ifdef CONFIG_PPC_BOOK3S_64
-#if TASK_SIZE_USER64 > (1UL << (ESID_BITS + SID_SHIFT))
-#error TASK_SIZE_USER64 exceeds user VSID range
-#endif
-#endif
 
 #ifdef CONFIG_PPC_BOOK3S_64
 /*
diff --git a/arch/powerpc/mm/pkeys.c b/arch/powerpc/mm/pkeys.c
index ba71c5481f42..0eafdf01edc7 100644
--- a/arch/powerpc/mm/pkeys.c
+++ b/arch/powerpc/mm/pkeys.c
@@ -119,18 +119,15 @@ int pkey_initialize(void)
 #else
 	os_reserved = 0;
 #endif
+	initial_allocation_mask = ~0x0;
+	pkey_amr_uamor_mask = ~0x0ul;
+	pkey_iamr_mask = ~0x0ul;
 	/*
-	 * Bits are in LE format. NOTE: 1, 0 are reserved.
+	 * key 0, 1 are reserved.
 	 * key 0 is the default key, which allows read/write/execute.
 	 * key 1 is recommended not to be used. PowerISA(3.0) page 1015,
 	 * programming note.
 	 */
-	initial_allocation_mask = ~0x0;
-
-	/* register mask is in BE format */
-	pkey_amr_uamor_mask = ~0x0ul;
-	pkey_iamr_mask = ~0x0ul;
-
 	for (i = 2; i < (pkeys_total - os_reserved); i++) {
 		initial_allocation_mask &= ~(0x1 << i);
 		pkey_amr_uamor_mask &= ~(0x3ul << pkeyshift(i));
@@ -308,9 +305,9 @@ void thread_pkey_regs_init(struct thread_struct *thread)
 	if (static_branch_likely(&pkey_disabled))
 		return;
 
-	write_amr(read_amr() & pkey_amr_uamor_mask);
-	write_iamr(read_iamr() & pkey_iamr_mask);
-	write_uamor(read_uamor() & pkey_amr_uamor_mask);
+	thread->amr = read_amr() & pkey_amr_uamor_mask;
+	thread->iamr = read_iamr() & pkey_iamr_mask;
+	thread->uamor = read_uamor() & pkey_amr_uamor_mask;
 }
 
 static inline bool pkey_allows_readwrite(int pkey)
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 13cfe413b40d..66577cc66dc9 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -22,6 +22,7 @@
 #include <asm/cacheflush.h>
 #include <asm/smp.h>
 #include <linux/compiler.h>
+#include <linux/context_tracking.h>
 #include <linux/mm_types.h>
 
 #include <asm/udbg.h>
@@ -340,3 +341,110 @@ void slb_initialize(void)
 
 	asm volatile("isync":::"memory");
 }
+
+static void insert_slb_entry(unsigned long vsid, unsigned long ea,
+			     int bpsize, int ssize)
+{
+	unsigned long flags, vsid_data, esid_data;
+	enum slb_index index;
+	int slb_cache_index;
+
+	/*
+	 * We are irq disabled, hence should be safe to access PACA.
+	 */
+	index = get_paca()->stab_rr;
+
+	/*
+	 * simple round-robin replacement of slb starting at SLB_NUM_BOLTED.
+	 */
+	if (index < (mmu_slb_size - 1))
+		index++;
+	else
+		index = SLB_NUM_BOLTED;
+
+	get_paca()->stab_rr = index;
+
+	flags = SLB_VSID_USER | mmu_psize_defs[bpsize].sllp;
+	vsid_data = (vsid << slb_vsid_shift(ssize)) | flags |
+		    ((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT);
+	esid_data = mk_esid_data(ea, ssize, index);
+
+	asm volatile("slbmte %0, %1" : : "r" (vsid_data), "r" (esid_data)
+		     : "memory");
+
+	/*
+	 * Now update slb cache entries
+	 */
+	slb_cache_index = get_paca()->slb_cache_ptr;
+	if (slb_cache_index < SLB_CACHE_ENTRIES) {
+		/*
+		 * We have space in slb cache for optimized switch_slb().
+		 * Top 36 bits from esid_data as per ISA
+		 */
+		get_paca()->slb_cache[slb_cache_index++] = esid_data >> 28;
+		get_paca()->slb_cache_ptr++;
+	} else {
+		/*
+		 * Our cache is full and the current cache content strictly
+		 * doesn't indicate the active SLB conents. Bump the ptr
+		 * so that switch_slb() will ignore the cache.
+		 */
+		get_paca()->slb_cache_ptr = SLB_CACHE_ENTRIES + 1;
+	}
+}
+
+static void handle_multi_context_slb_miss(int context_id, unsigned long ea)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long vsid;
+	int bpsize;
+
+	/*
+	 * We are always above 1TB, hence use high user segment size.
+	 */
+	vsid = get_vsid(context_id, ea, mmu_highuser_ssize);
+	bpsize = get_slice_psize(mm, ea);
+	insert_slb_entry(vsid, ea, bpsize, mmu_highuser_ssize);
+}
+
+void slb_miss_large_addr(struct pt_regs *regs)
+{
+	enum ctx_state prev_state = exception_enter();
+	unsigned long ea = regs->dar;
+	int context;
+
+	if (REGION_ID(ea) != USER_REGION_ID)
+		goto slb_bad_addr;
+
+	/*
+	 * Are we beyound what the page table layout supports ?
+	 */
+	if ((ea & ~REGION_MASK) >= H_PGTABLE_RANGE)
+		goto slb_bad_addr;
+
+	/* Lower address should have been handled by asm code */
+	if (ea < (1UL << MAX_EA_BITS_PER_CONTEXT))
+		goto slb_bad_addr;
+
+	/*
+	 * consider this as bad access if we take a SLB miss
+	 * on an address above addr limit.
+	 */
+	if (ea >= current->mm->context.slb_addr_limit)
+		goto slb_bad_addr;
+
+	context = get_ea_context(&current->mm->context, ea);
+	if (!context)
+		goto slb_bad_addr;
+
+	handle_multi_context_slb_miss(context, ea);
+	exception_exit(prev_state);
+	return;
+
+slb_bad_addr:
+	if (user_mode(regs))
+		_exception(SIGSEGV, regs, SEGV_BNDERR, ea);
+	else
+		bad_page_fault(regs, ea, SIGSEGV);
+	exception_exit(prev_state);
+}
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index 2cf5ef3fc50d..a83fbd2a4a24 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -75,10 +75,15 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_68_BIT_VA)
  */
 _GLOBAL(slb_allocate)
 	/*
-	 * check for bad kernel/user address
-	 * (ea & ~REGION_MASK) >= PGTABLE_RANGE
+	 * Check if the address falls within the range of the first context, or
+	 * if we may need to handle multi context. For the first context we
+	 * allocate the slb entry via the fast path below. For large address we
+	 * branch out to C-code and see if additional contexts have been
+	 * allocated.
+	 * The test here is:
+	 *   (ea & ~REGION_MASK) >= (1ull << MAX_EA_BITS_PER_CONTEXT)
 	 */
-	rldicr. r9,r3,4,(63 - H_PGTABLE_EADDR_SIZE - 4)
+	rldicr. r9,r3,4,(63 - MAX_EA_BITS_PER_CONTEXT - 4)
 	bne-	8f
 
 	srdi	r9,r3,60		/* get region */
@@ -200,10 +205,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 5:
 	/*
 	 * Handle lpsizes
-	 * r9 is get_paca()->context.low_slices_psize, r11 is index
+	 * r9 is get_paca()->context.low_slices_psize[index], r11 is mask_index
 	 */
-	ld	r9,PACALOWSLICESPSIZE(r13)
-	mr	r11,r10
+	srdi    r11,r10,1 /* index */
+	addi	r9,r11,PACALOWSLICESPSIZE
+	lbzx	r9,r13,r9		/* r9 is lpsizes[r11] */
+	rldicl	r11,r10,0,63		/* r11 = r10 & 0x1 */
 6:
 	sldi	r11,r11,2  /* index * 4 */
 	/* Extract the psize and multiply to get an array offset */
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 23ec2c5e3b78..9cd87d11fe4e 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -37,32 +37,25 @@
 #include <asm/hugetlb.h>
 
 static DEFINE_SPINLOCK(slice_convert_lock);
-/*
- * One bit per slice. We have lower slices which cover 256MB segments
- * upto 4G range. That gets us 16 low slices. For the rest we track slices
- * in 1TB size.
- */
-struct slice_mask {
-	u64 low_slices;
-	DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH);
-};
 
 #ifdef DEBUG
 int _slice_debug = 1;
 
-static void slice_print_mask(const char *label, struct slice_mask mask)
+static void slice_print_mask(const char *label, const struct slice_mask *mask)
 {
 	if (!_slice_debug)
 		return;
-	pr_devel("%s low_slice: %*pbl\n", label, (int)SLICE_NUM_LOW, &mask.low_slices);
-	pr_devel("%s high_slice: %*pbl\n", label, (int)SLICE_NUM_HIGH, mask.high_slices);
+	pr_devel("%s low_slice: %*pbl\n", label,
+			(int)SLICE_NUM_LOW, &mask->low_slices);
+	pr_devel("%s high_slice: %*pbl\n", label,
+			(int)SLICE_NUM_HIGH, mask->high_slices);
 }
 
 #define slice_dbg(fmt...) do { if (_slice_debug) pr_devel(fmt); } while (0)
 
 #else
 
-static void slice_print_mask(const char *label, struct slice_mask mask) {}
+static void slice_print_mask(const char *label, const struct slice_mask *mask) {}
 #define slice_dbg(fmt...)
 
 #endif
@@ -73,10 +66,12 @@ static void slice_range_to_mask(unsigned long start, unsigned long len,
 	unsigned long end = start + len - 1;
 
 	ret->low_slices = 0;
-	bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+	if (SLICE_NUM_HIGH)
+		bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
 
 	if (start < SLICE_LOW_TOP) {
-		unsigned long mend = min(end, (SLICE_LOW_TOP - 1));
+		unsigned long mend = min(end,
+					 (unsigned long)(SLICE_LOW_TOP - 1));
 
 		ret->low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1))
 			- (1u << GET_LOW_SLICE_INDEX(start));
@@ -113,11 +108,13 @@ static int slice_high_has_vma(struct mm_struct *mm, unsigned long slice)
 	unsigned long start = slice << SLICE_HIGH_SHIFT;
 	unsigned long end = start + (1ul << SLICE_HIGH_SHIFT);
 
+#ifdef CONFIG_PPC64
 	/* Hack, so that each addresses is controlled by exactly one
 	 * of the high or low area bitmaps, the first high area starts
 	 * at 4GB, not 0 */
 	if (start == 0)
 		start = SLICE_LOW_TOP;
+#endif
 
 	return !slice_area_is_free(mm, start, end - start);
 }
@@ -128,7 +125,8 @@ static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret,
 	unsigned long i;
 
 	ret->low_slices = 0;
-	bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+	if (SLICE_NUM_HIGH)
+		bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
 
 	for (i = 0; i < SLICE_NUM_LOW; i++)
 		if (!slice_low_has_vma(mm, i))
@@ -142,53 +140,75 @@ static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret,
 			__set_bit(i, ret->high_slices);
 }
 
-static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_mask *ret,
-				unsigned long high_limit)
+#ifdef CONFIG_PPC_BOOK3S_64
+static struct slice_mask *slice_mask_for_size(struct mm_struct *mm, int psize)
 {
-	unsigned char *hpsizes;
-	int index, mask_index;
-	unsigned long i;
-	u64 lpsizes;
-
-	ret->low_slices = 0;
-	bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);
+#ifdef CONFIG_PPC_64K_PAGES
+	if (psize == MMU_PAGE_64K)
+		return &mm->context.mask_64k;
+#endif
+	if (psize == MMU_PAGE_4K)
+		return &mm->context.mask_4k;
+#ifdef CONFIG_HUGETLB_PAGE
+	if (psize == MMU_PAGE_16M)
+		return &mm->context.mask_16m;
+	if (psize == MMU_PAGE_16G)
+		return &mm->context.mask_16g;
+#endif
+	BUG();
+}
+#elif defined(CONFIG_PPC_8xx)
+static struct slice_mask *slice_mask_for_size(struct mm_struct *mm, int psize)
+{
+	if (psize == mmu_virtual_psize)
+		return &mm->context.mask_base_psize;
+#ifdef CONFIG_HUGETLB_PAGE
+	if (psize == MMU_PAGE_512K)
+		return &mm->context.mask_512k;
+	if (psize == MMU_PAGE_8M)
+		return &mm->context.mask_8m;
+#endif
+	BUG();
+}
+#else
+#error "Must define the slice masks for page sizes supported by the platform"
+#endif
 
-	lpsizes = mm->context.low_slices_psize;
-	for (i = 0; i < SLICE_NUM_LOW; i++)
-		if (((lpsizes >> (i * 4)) & 0xf) == psize)
-			ret->low_slices |= 1u << i;
+static bool slice_check_range_fits(struct mm_struct *mm,
+			   const struct slice_mask *available,
+			   unsigned long start, unsigned long len)
+{
+	unsigned long end = start + len - 1;
+	u64 low_slices = 0;
 
-	if (high_limit <= SLICE_LOW_TOP)
-		return;
+	if (start < SLICE_LOW_TOP) {
+		unsigned long mend = min(end,
+					 (unsigned long)(SLICE_LOW_TOP - 1));
 
-	hpsizes = mm->context.high_slices_psize;
-	for (i = 0; i < GET_HIGH_SLICE_INDEX(high_limit); i++) {
-		mask_index = i & 0x1;
-		index = i >> 1;
-		if (((hpsizes[index] >> (mask_index * 4)) & 0xf) == psize)
-			__set_bit(i, ret->high_slices);
+		low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1))
+				- (1u << GET_LOW_SLICE_INDEX(start));
 	}
-}
+	if ((low_slices & available->low_slices) != low_slices)
+		return false;
 
-static int slice_check_fit(struct mm_struct *mm,
-			   struct slice_mask mask, struct slice_mask available)
-{
-	DECLARE_BITMAP(result, SLICE_NUM_HIGH);
-	/*
-	 * Make sure we just do bit compare only to the max
-	 * addr limit and not the full bit map size.
-	 */
-	unsigned long slice_count = GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit);
+	if (SLICE_NUM_HIGH && ((start + len) > SLICE_LOW_TOP)) {
+		unsigned long start_index = GET_HIGH_SLICE_INDEX(start);
+		unsigned long align_end = ALIGN(end, (1UL << SLICE_HIGH_SHIFT));
+		unsigned long count = GET_HIGH_SLICE_INDEX(align_end) - start_index;
+		unsigned long i;
 
-	bitmap_and(result, mask.high_slices,
-		   available.high_slices, slice_count);
+		for (i = start_index; i < start_index + count; i++) {
+			if (!test_bit(i, available->high_slices))
+				return false;
+		}
+	}
 
-	return (mask.low_slices & available.low_slices) == mask.low_slices &&
-		bitmap_equal(result, mask.high_slices, slice_count);
+	return true;
 }
 
 static void slice_flush_segments(void *parm)
 {
+#ifdef CONFIG_PPC64
 	struct mm_struct *mm = parm;
 	unsigned long flags;
 
@@ -200,40 +220,64 @@ static void slice_flush_segments(void *parm)
 	local_irq_save(flags);
 	slb_flush_and_rebolt();
 	local_irq_restore(flags);
+#endif
 }
 
-static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psize)
+static void slice_convert(struct mm_struct *mm,
+				const struct slice_mask *mask, int psize)
 {
 	int index, mask_index;
 	/* Write the new slice psize bits */
-	unsigned char *hpsizes;
-	u64 lpsizes;
+	unsigned char *hpsizes, *lpsizes;
+	struct slice_mask *psize_mask, *old_mask;
 	unsigned long i, flags;
+	int old_psize;
 
 	slice_dbg("slice_convert(mm=%p, psize=%d)\n", mm, psize);
 	slice_print_mask(" mask", mask);
 
+	psize_mask = slice_mask_for_size(mm, psize);
+
 	/* We need to use a spinlock here to protect against
 	 * concurrent 64k -> 4k demotion ...
 	 */
 	spin_lock_irqsave(&slice_convert_lock, flags);
 
 	lpsizes = mm->context.low_slices_psize;
-	for (i = 0; i < SLICE_NUM_LOW; i++)
-		if (mask.low_slices & (1u << i))
-			lpsizes = (lpsizes & ~(0xful << (i * 4))) |
-				(((unsigned long)psize) << (i * 4));
+	for (i = 0; i < SLICE_NUM_LOW; i++) {
+		if (!(mask->low_slices & (1u << i)))
+			continue;
+
+		mask_index = i & 0x1;
+		index = i >> 1;
 
-	/* Assign the value back */
-	mm->context.low_slices_psize = lpsizes;
+		/* Update the slice_mask */
+		old_psize = (lpsizes[index] >> (mask_index * 4)) & 0xf;
+		old_mask = slice_mask_for_size(mm, old_psize);
+		old_mask->low_slices &= ~(1u << i);
+		psize_mask->low_slices |= 1u << i;
+
+		/* Update the sizes array */
+		lpsizes[index] = (lpsizes[index] & ~(0xf << (mask_index * 4))) |
+				(((unsigned long)psize) << (mask_index * 4));
+	}
 
 	hpsizes = mm->context.high_slices_psize;
 	for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit); i++) {
+		if (!test_bit(i, mask->high_slices))
+			continue;
+
 		mask_index = i & 0x1;
 		index = i >> 1;
-		if (test_bit(i, mask.high_slices))
-			hpsizes[index] = (hpsizes[index] &
-					  ~(0xf << (mask_index * 4))) |
+
+		/* Update the slice_mask */
+		old_psize = (hpsizes[index] >> (mask_index * 4)) & 0xf;
+		old_mask = slice_mask_for_size(mm, old_psize);
+		__clear_bit(i, old_mask->high_slices);
+		__set_bit(i, psize_mask->high_slices);
+
+		/* Update the sizes array */
+		hpsizes[index] = (hpsizes[index] & ~(0xf << (mask_index * 4))) |
 				(((unsigned long)psize) << (mask_index * 4));
 	}
 
@@ -254,26 +298,25 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz
  * 'available' slice_mark.
  */
 static bool slice_scan_available(unsigned long addr,
-				 struct slice_mask available,
-				 int end,
-				 unsigned long *boundary_addr)
+				 const struct slice_mask *available,
+				 int end, unsigned long *boundary_addr)
 {
 	unsigned long slice;
 	if (addr < SLICE_LOW_TOP) {
 		slice = GET_LOW_SLICE_INDEX(addr);
 		*boundary_addr = (slice + end) << SLICE_LOW_SHIFT;
-		return !!(available.low_slices & (1u << slice));
+		return !!(available->low_slices & (1u << slice));
 	} else {
 		slice = GET_HIGH_SLICE_INDEX(addr);
 		*boundary_addr = (slice + end) ?
 			((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP;
-		return !!test_bit(slice, available.high_slices);
+		return !!test_bit(slice, available->high_slices);
 	}
 }
 
 static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
 					      unsigned long len,
-					      struct slice_mask available,
+					      const struct slice_mask *available,
 					      int psize, unsigned long high_limit)
 {
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
@@ -319,7 +362,7 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
 
 static unsigned long slice_find_area_topdown(struct mm_struct *mm,
 					     unsigned long len,
-					     struct slice_mask available,
+					     const struct slice_mask *available,
 					     int psize, unsigned long high_limit)
 {
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
@@ -377,7 +420,7 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm,
 
 
 static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len,
-				     struct slice_mask mask, int psize,
+				     const struct slice_mask *mask, int psize,
 				     int topdown, unsigned long high_limit)
 {
 	if (topdown)
@@ -386,23 +429,33 @@ static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len,
 		return slice_find_area_bottomup(mm, len, mask, psize, high_limit);
 }
 
-static inline void slice_or_mask(struct slice_mask *dst, struct slice_mask *src)
+static inline void slice_copy_mask(struct slice_mask *dst,
+					const struct slice_mask *src)
 {
-	DECLARE_BITMAP(result, SLICE_NUM_HIGH);
-
-	dst->low_slices |= src->low_slices;
-	bitmap_or(result, dst->high_slices, src->high_slices, SLICE_NUM_HIGH);
-	bitmap_copy(dst->high_slices, result, SLICE_NUM_HIGH);
+	dst->low_slices = src->low_slices;
+	if (!SLICE_NUM_HIGH)
+		return;
+	bitmap_copy(dst->high_slices, src->high_slices, SLICE_NUM_HIGH);
 }
 
-static inline void slice_andnot_mask(struct slice_mask *dst, struct slice_mask *src)
+static inline void slice_or_mask(struct slice_mask *dst,
+					const struct slice_mask *src1,
+					const struct slice_mask *src2)
 {
-	DECLARE_BITMAP(result, SLICE_NUM_HIGH);
-
-	dst->low_slices &= ~src->low_slices;
+	dst->low_slices = src1->low_slices | src2->low_slices;
+	if (!SLICE_NUM_HIGH)
+		return;
+	bitmap_or(dst->high_slices, src1->high_slices, src2->high_slices, SLICE_NUM_HIGH);
+}
 
-	bitmap_andnot(result, dst->high_slices, src->high_slices, SLICE_NUM_HIGH);
-	bitmap_copy(dst->high_slices, result, SLICE_NUM_HIGH);
+static inline void slice_andnot_mask(struct slice_mask *dst,
+					const struct slice_mask *src1,
+					const struct slice_mask *src2)
+{
+	dst->low_slices = src1->low_slices & ~src2->low_slices;
+	if (!SLICE_NUM_HIGH)
+		return;
+	bitmap_andnot(dst->high_slices, src1->high_slices, src2->high_slices, SLICE_NUM_HIGH);
 }
 
 #ifdef CONFIG_PPC_64K_PAGES
@@ -415,10 +468,10 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 				      unsigned long flags, unsigned int psize,
 				      int topdown)
 {
-	struct slice_mask mask;
 	struct slice_mask good_mask;
 	struct slice_mask potential_mask;
-	struct slice_mask compat_mask;
+	const struct slice_mask *maskp;
+	const struct slice_mask *compat_maskp = NULL;
 	int fixed = (flags & MAP_FIXED);
 	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
 	unsigned long page_size = 1UL << pshift;
@@ -442,23 +495,16 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	}
 
 	if (high_limit > mm->context.slb_addr_limit) {
+		/*
+		 * Increasing the slb_addr_limit does not require
+		 * slice mask cache to be recalculated because it should
+		 * be already initialised beyond the old address limit.
+		 */
 		mm->context.slb_addr_limit = high_limit;
+
 		on_each_cpu(slice_flush_segments, mm, 1);
 	}
 
-	/*
-	 * init different masks
-	 */
-	mask.low_slices = 0;
-	bitmap_zero(mask.high_slices, SLICE_NUM_HIGH);
-
-	/* silence stupid warning */;
-	potential_mask.low_slices = 0;
-	bitmap_zero(potential_mask.high_slices, SLICE_NUM_HIGH);
-
-	compat_mask.low_slices = 0;
-	bitmap_zero(compat_mask.high_slices, SLICE_NUM_HIGH);
-
 	/* Sanity checks */
 	BUG_ON(mm->task_size == 0);
 	BUG_ON(mm->context.slb_addr_limit == 0);
@@ -481,8 +527,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	/* First make up a "good" mask of slices that have the right size
 	 * already
 	 */
-	slice_mask_for_size(mm, psize, &good_mask, high_limit);
-	slice_print_mask(" good_mask", good_mask);
+	maskp = slice_mask_for_size(mm, psize);
 
 	/*
 	 * Here "good" means slices that are already the right page size,
@@ -503,40 +548,47 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	 *	search in good | compat | free, found => convert free.
 	 */
 
-#ifdef CONFIG_PPC_64K_PAGES
-	/* If we support combo pages, we can allow 64k pages in 4k slices */
-	if (psize == MMU_PAGE_64K) {
-		slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask, high_limit);
+	/*
+	 * If we support combo pages, we can allow 64k pages in 4k slices
+	 * The mask copies could be avoided in most cases here if we had
+	 * a pointer to good mask for the next code to use.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_64K_PAGES) && psize == MMU_PAGE_64K) {
+		compat_maskp = slice_mask_for_size(mm, MMU_PAGE_4K);
 		if (fixed)
-			slice_or_mask(&good_mask, &compat_mask);
+			slice_or_mask(&good_mask, maskp, compat_maskp);
+		else
+			slice_copy_mask(&good_mask, maskp);
+	} else {
+		slice_copy_mask(&good_mask, maskp);
 	}
-#endif
+
+	slice_print_mask(" good_mask", &good_mask);
+	if (compat_maskp)
+		slice_print_mask(" compat_mask", compat_maskp);
 
 	/* First check hint if it's valid or if we have MAP_FIXED */
 	if (addr != 0 || fixed) {
-		/* Build a mask for the requested range */
-		slice_range_to_mask(addr, len, &mask);
-		slice_print_mask(" mask", mask);
-
 		/* Check if we fit in the good mask. If we do, we just return,
 		 * nothing else to do
 		 */
-		if (slice_check_fit(mm, mask, good_mask)) {
+		if (slice_check_range_fits(mm, &good_mask, addr, len)) {
 			slice_dbg(" fits good !\n");
-			return addr;
+			newaddr = addr;
+			goto return_addr;
 		}
 	} else {
 		/* Now let's see if we can find something in the existing
 		 * slices for that size
 		 */
-		newaddr = slice_find_area(mm, len, good_mask,
+		newaddr = slice_find_area(mm, len, &good_mask,
 					  psize, topdown, high_limit);
 		if (newaddr != -ENOMEM) {
 			/* Found within the good mask, we don't have to setup,
 			 * we thus return directly
 			 */
 			slice_dbg(" found area at 0x%lx\n", newaddr);
-			return newaddr;
+			goto return_addr;
 		}
 	}
 	/*
@@ -544,12 +596,15 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	 * empty and thus can be converted
 	 */
 	slice_mask_for_free(mm, &potential_mask, high_limit);
-	slice_or_mask(&potential_mask, &good_mask);
-	slice_print_mask(" potential", potential_mask);
+	slice_or_mask(&potential_mask, &potential_mask, &good_mask);
+	slice_print_mask(" potential", &potential_mask);
 
-	if ((addr != 0 || fixed) && slice_check_fit(mm, mask, potential_mask)) {
-		slice_dbg(" fits potential !\n");
-		goto convert;
+	if (addr != 0 || fixed) {
+		if (slice_check_range_fits(mm, &potential_mask, addr, len)) {
+			slice_dbg(" fits potential !\n");
+			newaddr = addr;
+			goto convert;
+		}
 	}
 
 	/* If we have MAP_FIXED and failed the above steps, then error out */
@@ -562,46 +617,64 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 	 * anywhere in the good area.
 	 */
 	if (addr) {
-		addr = slice_find_area(mm, len, good_mask,
-				       psize, topdown, high_limit);
-		if (addr != -ENOMEM) {
-			slice_dbg(" found area at 0x%lx\n", addr);
-			return addr;
+		newaddr = slice_find_area(mm, len, &good_mask,
+					  psize, topdown, high_limit);
+		if (newaddr != -ENOMEM) {
+			slice_dbg(" found area at 0x%lx\n", newaddr);
+			goto return_addr;
 		}
 	}
 
 	/* Now let's see if we can find something in the existing slices
 	 * for that size plus free slices
 	 */
-	addr = slice_find_area(mm, len, potential_mask,
-			       psize, topdown, high_limit);
+	newaddr = slice_find_area(mm, len, &potential_mask,
+				  psize, topdown, high_limit);
 
 #ifdef CONFIG_PPC_64K_PAGES
-	if (addr == -ENOMEM && psize == MMU_PAGE_64K) {
+	if (newaddr == -ENOMEM && psize == MMU_PAGE_64K) {
 		/* retry the search with 4k-page slices included */
-		slice_or_mask(&potential_mask, &compat_mask);
-		addr = slice_find_area(mm, len, potential_mask,
-				       psize, topdown, high_limit);
+		slice_or_mask(&potential_mask, &potential_mask, compat_maskp);
+		newaddr = slice_find_area(mm, len, &potential_mask,
+					  psize, topdown, high_limit);
 	}
 #endif
 
-	if (addr == -ENOMEM)
+	if (newaddr == -ENOMEM)
 		return -ENOMEM;
 
-	slice_range_to_mask(addr, len, &mask);
-	slice_dbg(" found potential area at 0x%lx\n", addr);
-	slice_print_mask(" mask", mask);
+	slice_range_to_mask(newaddr, len, &potential_mask);
+	slice_dbg(" found potential area at 0x%lx\n", newaddr);
+	slice_print_mask(" mask", &potential_mask);
 
  convert:
-	slice_andnot_mask(&mask, &good_mask);
-	slice_andnot_mask(&mask, &compat_mask);
-	if (mask.low_slices || !bitmap_empty(mask.high_slices, SLICE_NUM_HIGH)) {
-		slice_convert(mm, mask, psize);
+	/*
+	 * Try to allocate the context before we do slice convert
+	 * so that we handle the context allocation failure gracefully.
+	 */
+	if (need_extra_context(mm, newaddr)) {
+		if (alloc_extended_context(mm, newaddr) < 0)
+			return -ENOMEM;
+	}
+
+	slice_andnot_mask(&potential_mask, &potential_mask, &good_mask);
+	if (compat_maskp && !fixed)
+		slice_andnot_mask(&potential_mask, &potential_mask, compat_maskp);
+	if (potential_mask.low_slices ||
+		(SLICE_NUM_HIGH &&
+		 !bitmap_empty(potential_mask.high_slices, SLICE_NUM_HIGH))) {
+		slice_convert(mm, &potential_mask, psize);
 		if (psize > MMU_PAGE_BASE)
 			on_each_cpu(slice_flush_segments, mm, 1);
 	}
-	return addr;
+	return newaddr;
 
+return_addr:
+	if (need_extra_context(mm, newaddr)) {
+		if (alloc_extended_context(mm, newaddr) < 0)
+			return -ENOMEM;
+	}
+	return newaddr;
 }
 EXPORT_SYMBOL_GPL(slice_get_unmapped_area);
 
@@ -627,94 +700,60 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp,
 
 unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr)
 {
-	unsigned char *hpsizes;
+	unsigned char *psizes;
 	int index, mask_index;
 
-	/*
-	 * Radix doesn't use slice, but can get enabled along with MMU_SLICE
-	 */
-	if (radix_enabled()) {
-#ifdef CONFIG_PPC_64K_PAGES
-		return MMU_PAGE_64K;
-#else
-		return MMU_PAGE_4K;
-#endif
-	}
+	VM_BUG_ON(radix_enabled());
+
 	if (addr < SLICE_LOW_TOP) {
-		u64 lpsizes;
-		lpsizes = mm->context.low_slices_psize;
+		psizes = mm->context.low_slices_psize;
 		index = GET_LOW_SLICE_INDEX(addr);
-		return (lpsizes >> (index * 4)) & 0xf;
+	} else {
+		psizes = mm->context.high_slices_psize;
+		index = GET_HIGH_SLICE_INDEX(addr);
 	}
-	hpsizes = mm->context.high_slices_psize;
-	index = GET_HIGH_SLICE_INDEX(addr);
 	mask_index = index & 0x1;
-	return (hpsizes[index >> 1] >> (mask_index * 4)) & 0xf;
+	return (psizes[index >> 1] >> (mask_index * 4)) & 0xf;
 }
 EXPORT_SYMBOL_GPL(get_slice_psize);
 
-/*
- * This is called by hash_page when it needs to do a lazy conversion of
- * an address space from real 64K pages to combo 4K pages (typically
- * when hitting a non cacheable mapping on a processor or hypervisor
- * that won't allow them for 64K pages).
- *
- * This is also called in init_new_context() to change back the user
- * psize from whatever the parent context had it set to
- * N.B. This may be called before mm->context.id has been set.
- *
- * This function will only change the content of the {low,high)_slice_psize
- * masks, it will not flush SLBs as this shall be handled lazily by the
- * caller.
- */
-void slice_set_user_psize(struct mm_struct *mm, unsigned int psize)
+void slice_init_new_context_exec(struct mm_struct *mm)
 {
-	int index, mask_index;
-	unsigned char *hpsizes;
-	unsigned long flags, lpsizes;
-	unsigned int old_psize;
-	int i;
+	unsigned char *hpsizes, *lpsizes;
+	struct slice_mask *mask;
+	unsigned int psize = mmu_virtual_psize;
 
-	slice_dbg("slice_set_user_psize(mm=%p, psize=%d)\n", mm, psize);
+	slice_dbg("slice_init_new_context_exec(mm=%p)\n", mm);
 
-	VM_BUG_ON(radix_enabled());
-	spin_lock_irqsave(&slice_convert_lock, flags);
-
-	old_psize = mm->context.user_psize;
-	slice_dbg(" old_psize=%d\n", old_psize);
-	if (old_psize == psize)
-		goto bail;
+	/*
+	 * In the case of exec, use the default limit. In the
+	 * case of fork it is just inherited from the mm being
+	 * duplicated.
+	 */
+#ifdef CONFIG_PPC64
+	mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW_USER64;
+#else
+	mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW;
+#endif
 
 	mm->context.user_psize = psize;
-	wmb();
 
+	/*
+	 * Set all slice psizes to the default.
+	 */
 	lpsizes = mm->context.low_slices_psize;
-	for (i = 0; i < SLICE_NUM_LOW; i++)
-		if (((lpsizes >> (i * 4)) & 0xf) == old_psize)
-			lpsizes = (lpsizes & ~(0xful << (i * 4))) |
-				(((unsigned long)psize) << (i * 4));
-	/* Assign the value back */
-	mm->context.low_slices_psize = lpsizes;
+	memset(lpsizes, (psize << 4) | psize, SLICE_NUM_LOW >> 1);
 
 	hpsizes = mm->context.high_slices_psize;
-	for (i = 0; i < SLICE_NUM_HIGH; i++) {
-		mask_index = i & 0x1;
-		index = i >> 1;
-		if (((hpsizes[index] >> (mask_index * 4)) & 0xf) == old_psize)
-			hpsizes[index] = (hpsizes[index] &
-					  ~(0xf << (mask_index * 4))) |
-				(((unsigned long)psize) << (mask_index * 4));
-	}
-
-
-
-
-	slice_dbg(" lsps=%lx, hsps=%lx\n",
-		  (unsigned long)mm->context.low_slices_psize,
-		  (unsigned long)mm->context.high_slices_psize);
+	memset(hpsizes, (psize << 4) | psize, SLICE_NUM_HIGH >> 1);
 
- bail:
-	spin_unlock_irqrestore(&slice_convert_lock, flags);
+	/*
+	 * Slice mask cache starts zeroed, fill the default size cache.
+	 */
+	mask = slice_mask_for_size(mm, psize);
+	mask->low_slices = ~0UL;
+	if (SLICE_NUM_HIGH)
+		bitmap_fill(mask->high_slices, SLICE_NUM_HIGH);
 }
 
 void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
@@ -725,7 +764,7 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
 	VM_BUG_ON(radix_enabled());
 
 	slice_range_to_mask(start, len, &mask);
-	slice_convert(mm, mask, psize);
+	slice_convert(mm, &mask, psize);
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
@@ -748,33 +787,27 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
  * for now as we only use slices with hugetlbfs enabled. This should
  * be fixed as the generic code gets fixed.
  */
-int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
+int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 			   unsigned long len)
 {
-	struct slice_mask mask, available;
+	const struct slice_mask *maskp;
 	unsigned int psize = mm->context.user_psize;
-	unsigned long high_limit = mm->context.slb_addr_limit;
 
-	if (radix_enabled())
-		return 0;
+	VM_BUG_ON(radix_enabled());
 
-	slice_range_to_mask(addr, len, &mask);
-	slice_mask_for_size(mm, psize, &available, high_limit);
+	maskp = slice_mask_for_size(mm, psize);
 #ifdef CONFIG_PPC_64K_PAGES
 	/* We need to account for 4k slices too */
 	if (psize == MMU_PAGE_64K) {
-		struct slice_mask compat_mask;
-		slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask, high_limit);
-		slice_or_mask(&available, &compat_mask);
+		const struct slice_mask *compat_maskp;
+		struct slice_mask available;
+
+		compat_maskp = slice_mask_for_size(mm, MMU_PAGE_4K);
+		slice_or_mask(&available, maskp, compat_maskp);
+		return !slice_check_range_fits(mm, &available, addr, len);
 	}
 #endif
 
-#if 0 /* too verbose */
-	slice_dbg("is_hugepage_only_range(mm=%p, addr=%lx, len=%lx)\n",
-		 mm, addr, len);
-	slice_print_mask(" mask", mask);
-	slice_print_mask(" available", available);
-#endif
-	return !slice_check_fit(mm, mask, available);
+	return !slice_check_range_fits(mm, maskp, addr, len);
 }
 #endif
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index a07f5372a4bf..2fba6170ab3f 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -98,7 +98,7 @@ static inline void __tlbiel_pid(unsigned long pid, int set,
 	rb |= set << PPC_BITLSHIFT(51);
 	rs = ((unsigned long)pid) << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
+	r = 1;   /* radix format */
 
 	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
@@ -112,7 +112,7 @@ static inline void __tlbie_pid(unsigned long pid, unsigned long ric)
 	rb = PPC_BIT(53); /* IS = 1 */
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
+	r = 1;   /* radix format */
 
 	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
@@ -128,7 +128,7 @@ static inline void __tlbiel_va(unsigned long va, unsigned long pid,
 	rb |= ap << PPC_BITLSHIFT(58);
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
+	r = 1;   /* radix format */
 
 	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
@@ -144,7 +144,7 @@ static inline void __tlbie_va(unsigned long va, unsigned long pid,
 	rb |= ap << PPC_BITLSHIFT(58);
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
-	r = 1;   /* raidx format */
+	r = 1;   /* radix format */
 
 	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
@@ -668,7 +668,7 @@ void radix__flush_tlb_all(void)
 
 	rb = 0x3 << PPC_BITLSHIFT(53); /* IS = 3 */
 	prs = 0; /* partition scoped */
-	r = 1;   /* raidx format */
+	r = 1;   /* radix format */
 	rs = 1 & ((1UL << 32) - 1); /* any LPID value to flush guest mappings */
 
 	asm volatile("ptesync": : :"memory");
@@ -706,7 +706,7 @@ void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
 {
-	unsigned int pid = mm->context.id;
+	unsigned long pid = mm->context.id;
 
 	if (unlikely(pid == MMU_NO_CONTEXT))
 		return;
@@ -734,7 +734,7 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
 		for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) {
 			if (sib == cpu)
 				continue;
-			if (paca[sib].kvm_hstate.kvm_vcpu)
+			if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu)
 				flush = true;
 		}
 		if (flush)
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 9b23f12e863c..87d71dd25441 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -89,7 +89,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 	/* Build full vaddr */
 	if (!is_kernel_addr(addr)) {
 		ssize = user_segment_size(addr);
-		vsid = get_vsid(mm->context.id, addr, ssize);
+		vsid = get_user_vsid(&mm->context, addr, ssize);
 	} else {
 		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
 		ssize = mmu_kernel_ssize;