Merge tag 'powerpc-4.8-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights:
   - PowerNV PCI hotplug support.
   - Lots more Power9 support.
   - eBPF JIT support on ppc64le.
   - Lots of cxl updates.
   - Boot code consolidation.

  Bug fixes:
   - Fix spin_unlock_wait() from Boqun Feng
   - Fix stack pointer corruption in __tm_recheckpoint() from Michael
     Neuling
   - Fix multiple bugs in memory_hotplug_max() from Bharata B Rao
   - mm: Ensure "special" zones are empty from Oliver O'Halloran
   - ftrace: Separate the heuristics for checking call sites from
     Michael Ellerman
   - modules: Never restore r2 for a mprofile-kernel style mcount() call
     from Michael Ellerman
   - Fix endianness when reading TCEs from Alexey Kardashevskiy
   - start rtasd before PCI probing from Greg Kurz
   - PCI: rpaphp: Fix slot registration for multiple slots under a PHB
     from Tyrel Datwyler
   - powerpc/mm: Add memory barrier in __hugepte_alloc() from Sukadev
     Bhattiprolu

  Cleanups & fixes:
   - Drop support for MPIC in pseries from Rashmica Gupta
   - Define and use PPC64_ELF_ABI_v2/v1 from Michael Ellerman
   - Remove unused symbols in asm-offsets.c from Rashmica Gupta
   - Fix SRIOV not building without EEH enabled from Russell Currey
   - Remove kretprobe_trampoline_holder from Thiago Jung Bauermann
   - Reduce log level of PCI I/O space warning from Benjamin
     Herrenschmidt
   - Add array bounds checking to crash_shutdown_handlers from Suraj
     Jitindar Singh
   - Avoid -maltivec when using clang integrated assembler from Anton
     Blanchard
   - Fix array overrun in ppc_rtas() syscall from Andrew Donnellan
   - Fix error return value in cmm_mem_going_offline() from Rasmus
     Villemoes
   - export cpu_to_core_id() from Mauricio Faria de Oliveira
   - Remove old symbols from defconfigs from Andrew Donnellan
   - Update obsolete comments in setup_32.c about entry conditions from
     Benjamin Herrenschmidt
   - Add comment explaining the purpose of setup_kdump_trampoline() from
     Benjamin Herrenschmidt
   - Merge the RELOCATABLE config entries for ppc32 and ppc64 from Kevin
     Hao
   - Remove RELOCATABLE_PPC32 from Kevin Hao
   - Fix .long's in tlb-radix.c to more meaningful from Balbir Singh

  Minor cleanups & fixes:
   - Andrew Donnellan, Anna-Maria Gleixner, Anton Blanchard, Benjamin
     Herrenschmidt, Bharata B Rao, Christophe Leroy, Colin Ian King,
     Geliang Tang, Greg Kurz, Madhavan Srinivasan, Michael Ellerman,
     Michael Ellerman, Stephen Rothwell, Stewart Smith.

  Freescale updates from Scott:
   - "Highlights include more 8xx optimizations, device tree updates,
     and MVME7100 support."

  PowerNV PCI hotplug from Gavin Shan:
   - PCI: Add pcibios_setup_bridge()
   - Override pcibios_setup_bridge()
   - Remove PCI_RESET_DELAY_US
   - Move pnv_pci_ioda_setup_opal_tce_kill() around
   - Increase PE# capacity
   - Allocate PE# in reverse order
   - Create PEs in pcibios_setup_bridge()
   - Setup PE for root bus
   - Extend PCI bridge resources
   - Make pnv_ioda_deconfigure_pe() visible
   - Dynamically release PE
   - Update bridge windows on PCI plug
   - Delay populating pdn
   - Support PCI slot ID
   - Use PCI slot reset infrastructure
   - Introduce pnv_pci_get_slot_id()
   - Functions to get/set PCI slot state
   - PCI/hotplug: PowerPC PowerNV PCI hotplug driver
   - Print correct PHB type names

  Power9 idle support from Shreyas B. Prabhu:
   - set power_save func after the idle states are initialized
   - Use PNV_THREAD_WINKLE macro while requesting for winkle
   - make hypervisor state restore a function
   - Rename idle_power7.S to idle_book3s.S
   - Rename reusable idle functions to hardware agnostic names
   - Make pnv_powersave_common more generic
   - abstraction for saving SPRs before entering deep idle states
   - Add platform support for stop instruction
   - cpuidle/powernv: Use CPUIDLE_STATE_MAX instead of MAX_POWERNV_IDLE_STATES
   - cpuidle/powernv: cleanup cpuidle-powernv.c
   - cpuidle/powernv: Add support for POWER ISA v3 idle states
   - Use deepest stop state when cpu is offlined

  Power9 PMU from Madhavan Srinivasan:
   - factor out power8 pmu macros and defines
   - factor out power8 pmu functions
   - factor out power8 __init_pmu code
   - Add power9 event list macros for generic and cache events
   - Power9 PMU support
   - Export Power9 generic and cache events to sysfs

  Power9 preliminary interrupt & PCI support from Benjamin Herrenschmidt:
   - Add XICS emulation APIs
   - Move a few exception common handlers to make room
   - Add support for HV virtualization interrupts
   - Add mechanism to force a replay of interrupts
   - Add ICP OPAL backend
   - Discover IODA3 PHBs
   - pci: Remove obsolete SW invalidate
   - opal: Add real mode call wrappers
   - Rename TCE invalidation calls
   - Remove SWINV constants and obsolete TCE code
   - Rework accessing the TCE invalidate register
   - Fallback to OPAL for TCE invalidations
   - Use the device-tree to get available range of M64's
   - Check status of a PHB before using it
   - pci: Don't try to allocate resources that will be reassigned

  Other Power9:
   - Send SIGBUS on unaligned copy and paste from Chris Smart
   - Large Decrementer support from Oliver O'Halloran
   - Load Monitor Register Support from Jack Miller

  Performance improvements from Anton Blanchard:
   - Avoid load hit store in __giveup_fpu() and __giveup_altivec()
   - Avoid load hit store in setup_sigcontext()
   - Remove assembly versions of strcpy, strcat, strlen and strcmp
   - Align hot loops of some string functions

  eBPF JIT from Naveen N. Rao:
   - Fix/enhance 32-bit Load Immediate implementation
   - Optimize 64-bit Immediate loads
   - Introduce rotate immediate instructions
   - A few cleanups
   - Isolate classic BPF JIT specifics into a separate header
   - Implement JIT compiler for extended BPF

  Operator Panel driver from Suraj Jitindar Singh:
   - devicetree/bindings: Add binding for operator panel on FSP machines
   - Add inline function to get rc from an ASYNC_COMP opal_msg
   - Add driver for operator panel on FSP machines

  Sparse fixes from Daniel Axtens:
   - make some things static
   - Introduce asm-prototypes.h
   - Include headers containing prototypes
   - Use #ifdef __BIG_ENDIAN__ #else for REG_BYTE
   - kvm: Clarify __user annotations
   - Pass endianness to sparse
   - Make ppc_md.{halt, restart} __noreturn

  MM fixes & cleanups from Aneesh Kumar K.V:
   - radix: Update LPCR HR bit as per ISA
   - use _raw variant of page table accessors
   - Compile out radix related functions if RADIX_MMU is disabled
   - Clear top 16 bits of va only on older cpus
   - Print formation regarding the the MMU mode
   - hash: Update SDR1 size encoding as documented in ISA 3.0
   - radix: Update PID switch sequence
   - radix: Update machine call back to support new HCALL.
   - radix: Add LPID based tlb flush helpers
   - radix: Add a kernel command line to disable radix
   - Cleanup LPCR defines

  Boot code consolidation from Benjamin Herrenschmidt:
   - Move epapr_paravirt_early_init() to early_init_devtree()
   - cell: Don't use flat device-tree after boot
   - ge_imp3a: Don't use the flat device-tree after boot
   - mpc85xx_ds: Don't use the flat device-tree after boot
   - mpc85xx_rdb: Don't use the flat device-tree after boot
   - Don't test for machine type in rtas_initialize()
   - Don't test for machine type in smp_setup_cpu_maps()
   - dt: Add of_device_compatible_match()
   - Factor do_feature_fixup calls
   - Move 64-bit feature fixup earlier
   - Move 64-bit memory reserves to setup_arch()
   - Use a cachable DART
   - Move FW feature probing out of pseries probe()
   - Put exception configuration in a common place
   - Remove early allocation of the SMU command buffer
   - Move MMU backend selection out of platform code
   - pasemi: Remove IOBMAP allocation from platform probe()
   - mm/hash: Don't use machine_is() early during boot
   - Don't test for machine type to detect HEA special case
   - pmac: Remove spurrious machine type test
   - Move hash table ops to a separate structure
   - Ensure that ppc_md is empty before probing for machine type
   - Move 64-bit probe_machine() to later in the boot process
   - Move 32-bit probe() machine to later in the boot process
   - Get rid of ppc_md.init_early()
   - Move the boot time info banner to a separate function
   - Move setting of {i,d}cache_bsize to initialize_cache_info()
   - Move the content of setup_system() to setup_arch()
   - Move cache info inits to a separate function
   - Re-order the call to smp_setup_cpu_maps()
   - Re-order setup_panic()
   - Make a few boot functions __init
   - Merge 32-bit and 64-bit setup_arch()

  Other new features:
   - tty/hvc: Use IRQF_SHARED for OPAL hvc consoles from Sam Mendoza-Jonas
   - tty/hvc: Use opal irqchip interface if available from Sam Mendoza-Jonas
   - powerpc: Add module autoloading based on CPU features from Alastair D'Silva
   - crypto: vmx - Convert to CPU feature based module autoloading from Alastair D'Silva
   - Wake up kopald polling thread before waiting for events from Benjamin Herrenschmidt
   - xmon: Dump ISA 2.06 SPRs from Michael Ellerman
   - xmon: Dump ISA 2.07 SPRs from Michael Ellerman
   - Add a parameter to disable 1TB segs from Oliver O'Halloran
   - powerpc/boot: Add OPAL console to epapr wrappers from Oliver O'Halloran
   - Assign fixed PHB number based on device-tree properties from Guilherme G. Piccoli
   - pseries: Add pseries hotplug workqueue from John Allen
   - pseries: Add support for hotplug interrupt source from John Allen
   - pseries: Use kernel hotplug queue for PowerVM hotplug events from John Allen
   - pseries: Move property cloning into its own routine from Nathan Fontenot
   - pseries: Dynamic add entires to associativity lookup array from Nathan Fontenot
   - pseries: Auto-online hotplugged memory from Nathan Fontenot
   - pseries: Remove call to memblock_add() from Nathan Fontenot

  cxl:
   - Add set and get private data to context struct from Michael Neuling
   - make base more explicitly non-modular from Paul Gortmaker
   - Use for_each_compatible_node() macro from Wei Yongjun
   - Frederic Barrat
   - Abstract the differences between the PSL and XSL
   - Make vPHB device node match adapter's
   - Philippe Bergheaud
   - Add mechanism for delivering AFU driver specific events
   - Ignore CAPI adapters misplaced in switched slots
   - Refine slice error debug messages
   - Andrew Donnellan
   - static-ify variables to fix sparse warnings
   - PCI/hotplug: pnv_php: export symbols and move struct types needed by cxl
   - PCI/hotplug: pnv_php: handle OPAL_PCI_SLOT_OFFLINE power state
   - Add cxl_check_and_switch_mode() API to switch bi-modal cards
   - remove dead Kconfig options
   - fix potential NULL dereference in free_adapter()
   - Ian Munsie
   - Update process element after allocating interrupts
   - Add support for CAPP DMA mode
   - Fix allowing bogus AFU descriptors with 0 maximum processes
   - Fix allocating a minimum of 2 pages for the SPA
   - Fix bug where AFU disable operation had no effect
   - Workaround XSL bug that does not clear the RA bit after a reset
   - Fix NULL pointer dereference on kernel contexts with no AFU interrupts
   - powerpc/powernv: Split cxl code out into a separate file
   - Add cxl_slot_is_supported API
   - Enable bus mastering for devices using CAPP DMA mode
   - Move cxl_afu_get / cxl_afu_put to base
   - Allow a default context to be associated with an external pci_dev
   - Do not create vPHB if there are no AFU configuration records
   - powerpc/powernv: Add support for the cxl kernel api on the real phb
   - Add support for using the kernel API with a real PHB
   - Add kernel APIs to get & set the max irqs per context
   - Add preliminary workaround for CX4 interrupt limitation
   - Add support for interrupts on the Mellanox CX4
   - Workaround PE=0 hardware limitation in Mellanox CX4
   - powerpc/powernv: Fix pci-cxl.c build when CONFIG_MODULES=n

  selftests:
   - Test unaligned copy and paste from Chris Smart
   - Load Monitor Register Tests from Jack Miller
   - Cyril Bur
   - exec() with suspended transaction
   - Use signed long to read perf_event_paranoid
   - Fix usage message in context_switch
   - Fix generation of vector instructions/types in context_switch
   - Michael Ellerman
   - Use "Delta" rather than "Error" in normal output
   - Import Anton's mmap & futex micro benchmarks
   - Add a test for PROT_SAO"

* tag 'powerpc-4.8-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (263 commits)
  powerpc/mm: Parenthesise IS_ENABLED() in if condition
  tty/hvc: Use opal irqchip interface if available
  tty/hvc: Use IRQF_SHARED for OPAL hvc consoles
  selftests/powerpc: exec() with suspended transaction
  powerpc: Improve comment explaining why we modify VRSAVE
  powerpc/mm: Drop unused externs for hpte_init_beat[_v3]()
  powerpc/mm: Rename hpte_init_lpar() and move the fallback to a header
  powerpc/mm: Fix build break when PPC_NATIVE=n
  crypto: vmx - Convert to CPU feature based module autoloading
  powerpc: Add module autoloading based on CPU features
  powerpc/powernv/ioda: Fix endianness when reading TCEs
  powerpc/mm: Add memory barrier in __hugepte_alloc()
  powerpc/modules: Never restore r2 for a mprofile-kernel style mcount() call
  powerpc/ftrace: Separate the heuristics for checking call sites
  powerpc: Merge 32-bit and 64-bit setup_arch()
  powerpc/64: Make a few boot functions __init
  powerpc: Re-order setup_panic()
  powerpc: Re-order the call to smp_setup_cpu_maps()
  powerpc/32: Move cache info inits to a separate function
  powerpc/64: Move the content of setup_system() to setup_arch()
  ...

15 files changed, 361 insertions, 193 deletions

diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c
index 949100577db5..6c5025e81236 100644
--- a/arch/powerpc/mm/8xx_mmu.c
+++ b/arch/powerpc/mm/8xx_mmu.c
@@ -13,62 +13,115 @@
  */
 
 #include <linux/memblock.h>
+#include <asm/fixmap.h>
+#include <asm/code-patching.h>
 
 #include "mmu_decl.h"
 
+#define IMMR_SIZE (FIX_IMMR_SIZE << PAGE_SHIFT)
+
 extern int __map_without_ltlbs;
+
 /*
- * MMU_init_hw does the chip-specific initialization of the MMU hardware.
+ * Return PA for this VA if it is in IMMR area, or 0
  */
-void __init MMU_init_hw(void)
+phys_addr_t v_block_mapped(unsigned long va)
 {
-	/* Nothing to do for the time being but keep it similar to other PPC */
+	unsigned long p = PHYS_IMMR_BASE;
+
+	if (__map_without_ltlbs)
+		return 0;
+	if (va >= VIRT_IMMR_BASE && va < VIRT_IMMR_BASE + IMMR_SIZE)
+		return p + va - VIRT_IMMR_BASE;
+	return 0;
+}
+
+/*
+ * Return VA for a given PA or 0 if not mapped
+ */
+unsigned long p_block_mapped(phys_addr_t pa)
+{
+	unsigned long p = PHYS_IMMR_BASE;
+
+	if (__map_without_ltlbs)
+		return 0;
+	if (pa >= p && pa < p + IMMR_SIZE)
+		return VIRT_IMMR_BASE + pa - p;
+	return 0;
 }
 
-#define LARGE_PAGE_SIZE_4M	(1<<22)
 #define LARGE_PAGE_SIZE_8M	(1<<23)
-#define LARGE_PAGE_SIZE_64M	(1<<26)
 
-unsigned long __init mmu_mapin_ram(unsigned long top)
+/*
+ * MMU_init_hw does the chip-specific initialization of the MMU hardware.
+ */
+void __init MMU_init_hw(void)
 {
-	unsigned long v, s, mapped;
-	phys_addr_t p;
+	/* PIN up to the 3 first 8Mb after IMMR in DTLB table */
+#ifdef CONFIG_PIN_TLB
+	unsigned long ctr = mfspr(SPRN_MD_CTR) & 0xfe000000;
+	unsigned long flags = 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY;
+#ifdef CONFIG_PIN_TLB_IMMR
+	int i = 29;
+#else
+	int i = 28;
+#endif
+	unsigned long addr = 0;
+	unsigned long mem = total_lowmem;
+
+	for (; i < 32 && mem >= LARGE_PAGE_SIZE_8M; i++) {
+		mtspr(SPRN_MD_CTR, ctr | (i << 8));
+		mtspr(SPRN_MD_EPN, (unsigned long)__va(addr) | MD_EVALID);
+		mtspr(SPRN_MD_TWC, MD_PS8MEG | MD_SVALID);
+		mtspr(SPRN_MD_RPN, addr | flags | _PAGE_PRESENT);
+		addr += LARGE_PAGE_SIZE_8M;
+		mem -= LARGE_PAGE_SIZE_8M;
+	}
+#endif
+}
 
-	v = KERNELBASE;
-	p = 0;
-	s = top;
+static void mmu_mapin_immr(void)
+{
+	unsigned long p = PHYS_IMMR_BASE;
+	unsigned long v = VIRT_IMMR_BASE;
+	unsigned long f = pgprot_val(PAGE_KERNEL_NCG);
+	int offset;
 
-	if (__map_without_ltlbs)
-		return 0;
+	for (offset = 0; offset < IMMR_SIZE; offset += PAGE_SIZE)
+		map_page(v + offset, p + offset, f);
+}
 
-#ifdef CONFIG_PPC_4K_PAGES
-	while (s >= LARGE_PAGE_SIZE_8M) {
-		pmd_t *pmdp;
-		unsigned long val = p | MD_PS8MEG;
+/* Address of instructions to patch */
+#ifndef CONFIG_PIN_TLB_IMMR
+extern unsigned int DTLBMiss_jmp;
+#endif
+extern unsigned int DTLBMiss_cmp, FixupDAR_cmp;
 
-		pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v);
-		*pmdp++ = __pmd(val);
-		*pmdp++ = __pmd(val + LARGE_PAGE_SIZE_4M);
+void mmu_patch_cmp_limit(unsigned int *addr, unsigned long mapped)
+{
+	unsigned int instr = *addr;
 
-		v += LARGE_PAGE_SIZE_8M;
-		p += LARGE_PAGE_SIZE_8M;
-		s -= LARGE_PAGE_SIZE_8M;
-	}
-#else /* CONFIG_PPC_16K_PAGES */
-	while (s >= LARGE_PAGE_SIZE_64M) {
-		pmd_t *pmdp;
-		unsigned long val = p | MD_PS8MEG;
+	instr &= 0xffff0000;
+	instr |= (unsigned long)__va(mapped) >> 16;
+	patch_instruction(addr, instr);
+}
 
-		pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v);
-		*pmdp++ = __pmd(val);
+unsigned long __init mmu_mapin_ram(unsigned long top)
+{
+	unsigned long mapped;
 
-		v += LARGE_PAGE_SIZE_64M;
-		p += LARGE_PAGE_SIZE_64M;
-		s -= LARGE_PAGE_SIZE_64M;
-	}
+	if (__map_without_ltlbs) {
+		mapped = 0;
+		mmu_mapin_immr();
+#ifndef CONFIG_PIN_TLB_IMMR
+		patch_instruction(&DTLBMiss_jmp, PPC_INST_NOP);
 #endif
+	} else {
+		mapped = top & ~(LARGE_PAGE_SIZE_8M - 1);
+	}
 
-	mapped = top - s;
+	mmu_patch_cmp_limit(&DTLBMiss_cmp, mapped);
+	mmu_patch_cmp_limit(&FixupDAR_cmp, mapped);
 
 	/* If the size of RAM is not an exact power of two, we may not
 	 * have covered RAM in its entirety with 8 MiB
@@ -77,7 +130,8 @@ unsigned long __init mmu_mapin_ram(unsigned long top)
 	 * coverage with normal-sized pages (or other reasons) do not
 	 * attempt to allocate outside the allowed range.
 	 */
-	memblock_set_current_limit(mapped);
+	if (mapped)
+		memblock_set_current_limit(mapped);
 
 	return mapped;
 }
@@ -90,13 +144,8 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 	 */
 	BUG_ON(first_memblock_base != 0);
 
-#ifdef CONFIG_PIN_TLB
 	/* 8xx can only access 24MB at the moment */
 	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01800000));
-#else
-	/* 8xx can only access 8MB at the moment */
-	memblock_set_current_limit(min_t(u64, first_memblock_size, 0x00800000));
-#endif
 }
 
 /*
diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c
index 6333b273d2d5..42c702b3be1f 100644
--- a/arch/powerpc/mm/hash64_4k.c
+++ b/arch/powerpc/mm/hash64_4k.c
@@ -70,8 +70,8 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT;
 
-		if (ppc_md.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_4K,
-					 MMU_PAGE_4K, ssize, flags) == -1)
+		if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_4K,
+					       MMU_PAGE_4K, ssize, flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}
 
@@ -84,21 +84,23 @@ repeat:
 		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
 
 		/* Insert into the hash table, primary slot */
-		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
-				  MMU_PAGE_4K, MMU_PAGE_4K, ssize);
+		slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0,
+						MMU_PAGE_4K, MMU_PAGE_4K, ssize);
 		/*
 		 * Primary is full, try the secondary
 		 */
 		if (unlikely(slot == -1)) {
 			hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
-			slot = ppc_md.hpte_insert(hpte_group, vpn, pa,
-						  rflags, HPTE_V_SECONDARY,
-						  MMU_PAGE_4K, MMU_PAGE_4K, ssize);
+			slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa,
+							rflags,
+							HPTE_V_SECONDARY,
+							MMU_PAGE_4K,
+							MMU_PAGE_4K, ssize);
 			if (slot == -1) {
 				if (mftb() & 0x1)
 					hpte_group = ((hash & htab_hash_mask) *
 						      HPTES_PER_GROUP) & ~0x7UL;
-				ppc_md.hpte_remove(hpte_group);
+				mmu_hash_ops.hpte_remove(hpte_group);
 				/*
 				 * FIXME!! Should be try the group from which we removed ?
 				 */
diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c
index 16644e1f4e6b..3bbbea07378c 100644
--- a/arch/powerpc/mm/hash64_64k.c
+++ b/arch/powerpc/mm/hash64_64k.c
@@ -133,9 +133,9 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += hidx & _PTEIDX_GROUP_IX;
 
-		ret = ppc_md.hpte_updatepp(slot, rflags, vpn,
-					   MMU_PAGE_4K, MMU_PAGE_4K,
-					   ssize, flags);
+		ret = mmu_hash_ops.hpte_updatepp(slot, rflags, vpn,
+						 MMU_PAGE_4K, MMU_PAGE_4K,
+						 ssize, flags);
 		/*
 		 *if we failed because typically the HPTE wasn't really here
 		 * we try an insertion.
@@ -166,21 +166,22 @@ repeat:
 	hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
 
 	/* Insert into the hash table, primary slot */
-	slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
-				  MMU_PAGE_4K, MMU_PAGE_4K, ssize);
+	slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0,
+					MMU_PAGE_4K, MMU_PAGE_4K, ssize);
 	/*
 	 * Primary is full, try the secondary
 	 */
 	if (unlikely(slot == -1)) {
 		hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
-		slot = ppc_md.hpte_insert(hpte_group, vpn, pa,
-					  rflags, HPTE_V_SECONDARY,
-					  MMU_PAGE_4K, MMU_PAGE_4K, ssize);
+		slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa,
+						rflags, HPTE_V_SECONDARY,
+						MMU_PAGE_4K, MMU_PAGE_4K,
+						ssize);
 		if (slot == -1) {
 			if (mftb() & 0x1)
 				hpte_group = ((hash & htab_hash_mask) *
 					      HPTES_PER_GROUP) & ~0x7UL;
-			ppc_md.hpte_remove(hpte_group);
+			mmu_hash_ops.hpte_remove(hpte_group);
 			/*
 			 * FIXME!! Should be try the group from which we removed ?
 			 */
@@ -272,8 +273,9 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT;
 
-		if (ppc_md.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_64K,
-					 MMU_PAGE_64K, ssize, flags) == -1)
+		if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_64K,
+					       MMU_PAGE_64K, ssize,
+					       flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}
 
@@ -286,21 +288,24 @@ repeat:
 		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
 
 		/* Insert into the hash table, primary slot */
-		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
-				  MMU_PAGE_64K, MMU_PAGE_64K, ssize);
+		slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0,
+						MMU_PAGE_64K, MMU_PAGE_64K,
+						ssize);
 		/*
 		 * Primary is full, try the secondary
 		 */
 		if (unlikely(slot == -1)) {
 			hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
-			slot = ppc_md.hpte_insert(hpte_group, vpn, pa,
-						  rflags, HPTE_V_SECONDARY,
-						  MMU_PAGE_64K, MMU_PAGE_64K, ssize);
+			slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa,
+							rflags,
+							HPTE_V_SECONDARY,
+							MMU_PAGE_64K,
+							MMU_PAGE_64K, ssize);
 			if (slot == -1) {
 				if (mftb() & 0x1)
 					hpte_group = ((hash & htab_hash_mask) *
 						      HPTES_PER_GROUP) & ~0x7UL;
-				ppc_md.hpte_remove(hpte_group);
+				mmu_hash_ops.hpte_remove(hpte_group);
 				/*
 				 * FIXME!! Should be try the group from which we removed ?
 				 */
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index f8a871a72985..88ce7d212320 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -55,7 +55,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 	 * We need 14 to 65 bits of va for a tlibe of 4K page
 	 * With vpn we ignore the lower VPN_SHIFT bits already.
 	 * And top two bits are already ignored because we can
-	 * only accomadate 76 bits in a 64 bit vpn with a VPN_SHIFT
+	 * only accomodate 76 bits in a 64 bit vpn with a VPN_SHIFT
 	 * of 12.
 	 */
 	va = vpn << VPN_SHIFT;
@@ -64,7 +64,8 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 	 * Older versions of the architecture (2.02 and earler) require the
 	 * masking of the top 16 bits.
 	 */
-	va &= ~(0xffffULL << 48);
+	if (mmu_has_feature(MMU_FTR_TLBIE_CROP_VA))
+		va &= ~(0xffffULL << 48);
 
 	switch (psize) {
 	case MMU_PAGE_4K:
@@ -113,7 +114,8 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 	 * Older versions of the architecture (2.02 and earler) require the
 	 * masking of the top 16 bits.
 	 */
-	va &= ~(0xffffULL << 48);
+	if (mmu_has_feature(MMU_FTR_TLBIE_CROP_VA))
+		va &= ~(0xffffULL << 48);
 
 	switch (psize) {
 	case MMU_PAGE_4K:
@@ -605,7 +607,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
  * crashdump and all bets are off anyway.
  *
  * TODO: add batching support when enabled.  remember, no dynamic memory here,
- * athough there is the control page available...
+ * although there is the control page available...
  */
 static void native_hpte_clear(void)
 {
@@ -723,23 +725,29 @@ static void native_flush_hash_range(unsigned long number, int local)
 	local_irq_restore(flags);
 }
 
-static int native_update_partition_table(u64 patb1)
+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)
 {
-	ppc_md.hpte_invalidate	= native_hpte_invalidate;
-	ppc_md.hpte_updatepp	= native_hpte_updatepp;
-	ppc_md.hpte_updateboltedpp = native_hpte_updateboltedpp;
-	ppc_md.hpte_insert	= native_hpte_insert;
-	ppc_md.hpte_remove	= native_hpte_remove;
-	ppc_md.hpte_clear_all	= native_hpte_clear;
-	ppc_md.flush_hash_range = native_flush_hash_range;
-	ppc_md.hugepage_invalidate   = native_hugepage_invalidate;
+	mmu_hash_ops.hpte_invalidate	= native_hpte_invalidate;
+	mmu_hash_ops.hpte_updatepp	= native_hpte_updatepp;
+	mmu_hash_ops.hpte_updateboltedpp = native_hpte_updateboltedpp;
+	mmu_hash_ops.hpte_insert	= native_hpte_insert;
+	mmu_hash_ops.hpte_remove	= native_hpte_remove;
+	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))
-		ppc_md.update_partition_table = native_update_partition_table;
+		ppc_md.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 2971ea18c768..b78b5d211278 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -34,6 +34,7 @@
 #include <linux/signal.h>
 #include <linux/memblock.h>
 #include <linux/context_tracking.h>
+#include <linux/libfdt.h>
 
 #include <asm/processor.h>
 #include <asm/pgtable.h>
@@ -58,6 +59,7 @@
 #include <asm/firmware.h>
 #include <asm/tm.h>
 #include <asm/trace.h>
+#include <asm/ps3.h>
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
@@ -87,10 +89,6 @@
  *
  */
 
-#ifdef CONFIG_U3_DART
-extern unsigned long dart_tablebase;
-#endif /* CONFIG_U3_DART */
-
 static unsigned long _SDR1;
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
 EXPORT_SYMBOL_GPL(mmu_psize_defs);
@@ -120,6 +118,8 @@ static u8 *linear_map_hash_slots;
 static unsigned long linear_map_hash_count;
 static DEFINE_SPINLOCK(linear_map_hash_lock);
 #endif /* CONFIG_DEBUG_PAGEALLOC */
+struct mmu_hash_ops mmu_hash_ops;
+EXPORT_SYMBOL(mmu_hash_ops);
 
 /* There are definitions of page sizes arrays to be used when none
  * is provided by the firmware.
@@ -278,9 +278,10 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 		hash = hpt_hash(vpn, shift, ssize);
 		hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
 
-		BUG_ON(!ppc_md.hpte_insert);
-		ret = ppc_md.hpte_insert(hpteg, vpn, paddr, tprot,
-					 HPTE_V_BOLTED, psize, psize, ssize);
+		BUG_ON(!mmu_hash_ops.hpte_insert);
+		ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot,
+					       HPTE_V_BOLTED, psize, psize,
+					       ssize);
 
 		if (ret < 0)
 			break;
@@ -305,11 +306,11 @@ int htab_remove_mapping(unsigned long vstart, unsigned long vend,
 	shift = mmu_psize_defs[psize].shift;
 	step = 1 << shift;
 
-	if (!ppc_md.hpte_removebolted)
+	if (!mmu_hash_ops.hpte_removebolted)
 		return -ENODEV;
 
 	for (vaddr = vstart; vaddr < vend; vaddr += step) {
-		rc = ppc_md.hpte_removebolted(vaddr, psize, ssize);
+		rc = mmu_hash_ops.hpte_removebolted(vaddr, psize, ssize);
 		if (rc == -ENOENT) {
 			ret = -ENOENT;
 			continue;
@@ -321,6 +322,15 @@ int htab_remove_mapping(unsigned long vstart, unsigned long vend,
 	return ret;
 }
 
+static bool disable_1tb_segments = false;
+
+static int __init parse_disable_1tb_segments(char *p)
+{
+	disable_1tb_segments = true;
+	return 0;
+}
+early_param("disable_1tb_segments", parse_disable_1tb_segments);
+
 static int __init htab_dt_scan_seg_sizes(unsigned long node,
 					 const char *uname, int depth,
 					 void *data)
@@ -339,6 +349,12 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node,
 	for (; size >= 4; size -= 4, ++prop) {
 		if (be32_to_cpu(prop[0]) == 40) {
 			DBG("1T segment support detected\n");
+
+			if (disable_1tb_segments) {
+				DBG("1T segments disabled by command line\n");
+				break;
+			}
+
 			cur_cpu_spec->mmu_features |= MMU_FTR_1T_SEGMENT;
 			return 1;
 		}
@@ -514,7 +530,8 @@ static bool might_have_hea(void)
 	 * we will never see an HEA ethernet device.
 	 */
 #ifdef CONFIG_IBMEBUS
-	return !cpu_has_feature(CPU_FTR_ARCH_207S);
+	return !cpu_has_feature(CPU_FTR_ARCH_207S) &&
+		!firmware_has_feature(FW_FEATURE_SPLPAR);
 #else
 	return false;
 #endif
@@ -580,7 +597,7 @@ found:
 			 * would stop us accessing the HEA ethernet. So if we
 			 * have the chance of ever seeing one, stay at 4k.
 			 */
-			if (!might_have_hea() || !machine_is(pseries))
+			if (!might_have_hea())
 				mmu_io_psize = MMU_PAGE_64K;
 		} else
 			mmu_ci_restrictions = 1;
@@ -699,10 +716,9 @@ int remove_section_mapping(unsigned long start, unsigned long end)
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 static void __init hash_init_partition_table(phys_addr_t hash_table,
-					     unsigned long pteg_count)
+					     unsigned long htab_size)
 {
 	unsigned long ps_field;
-	unsigned long htab_size;
 	unsigned long patb_size = 1UL << PATB_SIZE_SHIFT;
 
 	/*
@@ -710,7 +726,7 @@ static void __init hash_init_partition_table(phys_addr_t hash_table,
 	 * We can ignore that for lpid 0
 	 */
 	ps_field = 0;
-	htab_size =  __ilog2(pteg_count) - 11;
+	htab_size =  __ilog2(htab_size) - 18;
 
 	BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large.");
 	partition_tb = __va(memblock_alloc_base(patb_size, patb_size,
@@ -724,7 +740,7 @@ static void __init hash_init_partition_table(phys_addr_t hash_table,
 	 * For now UPRT is 0 for us.
 	 */
 	partition_tb->patb1 = 0;
-	DBG("Partition table %p\n", partition_tb);
+	pr_info("Partition table %p\n", partition_tb);
 	/*
 	 * update partition table control register,
 	 * 64 K size.
@@ -738,7 +754,7 @@ static void __init htab_initialize(void)
 	unsigned long table;
 	unsigned long pteg_count;
 	unsigned long prot;
-	unsigned long base = 0, size = 0, limit;
+	unsigned long base = 0, size = 0;
 	struct memblock_region *reg;
 
 	DBG(" -> htab_initialize()\n");
@@ -764,7 +780,8 @@ static void __init htab_initialize(void)
 
 	htab_hash_mask = pteg_count - 1;
 
-	if (firmware_has_feature(FW_FEATURE_LPAR)) {
+	if (firmware_has_feature(FW_FEATURE_LPAR) ||
+	    firmware_has_feature(FW_FEATURE_PS3_LV1)) {
 		/* Using a hypervisor which owns the htab */
 		htab_address = NULL;
 		_SDR1 = 0; 
@@ -775,20 +792,26 @@ static void __init htab_initialize(void)
 		 * Clear the htab if firmware assisted dump is active so
 		 * that we dont end up using old mappings.
 		 */
-		if (is_fadump_active() && ppc_md.hpte_clear_all)
-			ppc_md.hpte_clear_all();
+		if (is_fadump_active() && mmu_hash_ops.hpte_clear_all)
+			mmu_hash_ops.hpte_clear_all();
 #endif
 	} else {
-		/* Find storage for the HPT.  Must be contiguous in
-		 * the absolute address space. On cell we want it to be
-		 * in the first 2 Gig so we can use it for IOMMU hacks.
+		unsigned long limit = MEMBLOCK_ALLOC_ANYWHERE;
+
+#ifdef CONFIG_PPC_CELL
+		/*
+		 * Cell may require the hash table down low when using the
+		 * Axon IOMMU in order to fit the dynamic region over it, see
+		 * comments in cell/iommu.c
 		 */
-		if (machine_is(cell))
+		if (fdt_subnode_offset(initial_boot_params, 0, "axon") > 0) {
 			limit = 0x80000000;
-		else
-			limit = MEMBLOCK_ALLOC_ANYWHERE;
+			pr_info("Hash table forced below 2G for Axon IOMMU\n");
+		}
+#endif /* CONFIG_PPC_CELL */
 
-		table = memblock_alloc_base(htab_size_bytes, htab_size_bytes, limit);
+		table = memblock_alloc_base(htab_size_bytes, htab_size_bytes,
+					    limit);
 
 		DBG("Hash table allocated at %lx, size: %lx\n", table,
 		    htab_size_bytes);
@@ -796,7 +819,7 @@ static void __init htab_initialize(void)
 		htab_address = __va(table);
 
 		/* htab absolute addr + encoded htabsize */
-		_SDR1 = table + __ilog2(pteg_count) - 11;
+		_SDR1 = table + __ilog2(htab_size_bytes) - 18;
 
 		/* Initialize the HPT with no entries */
 		memset((void *)table, 0, htab_size_bytes);
@@ -805,7 +828,7 @@ static void __init htab_initialize(void)
 			/* Set SDR1 */
 			mtspr(SPRN_SDR1, _SDR1);
 		else
-			hash_init_partition_table(table, pteg_count);
+			hash_init_partition_table(table, htab_size_bytes);
 	}
 
 	prot = pgprot_val(PAGE_KERNEL);
@@ -832,34 +855,6 @@ static void __init htab_initialize(void)
 		DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",
 		    base, size, prot);
 
-#ifdef CONFIG_U3_DART
-		/* Do not map the DART space. Fortunately, it will be aligned
-		 * in such a way that it will not cross two memblock regions and
-		 * will fit within a single 16Mb page.
-		 * The DART space is assumed to be a full 16Mb region even if
-		 * we only use 2Mb of that space. We will use more of it later
-		 * for AGP GART. We have to use a full 16Mb large page.
-		 */
-		DBG("DART base: %lx\n", dart_tablebase);
-
-		if (dart_tablebase != 0 && dart_tablebase >= base
-		    && dart_tablebase < (base + size)) {
-			unsigned long dart_table_end = dart_tablebase + 16 * MB;
-			if (base != dart_tablebase)
-				BUG_ON(htab_bolt_mapping(base, dart_tablebase,
-							__pa(base), prot,
-							mmu_linear_psize,
-							mmu_kernel_ssize));
-			if ((base + size) > dart_table_end)
-				BUG_ON(htab_bolt_mapping(dart_tablebase+16*MB,
-							base + size,
-							__pa(dart_table_end),
-							 prot,
-							 mmu_linear_psize,
-							 mmu_kernel_ssize));
-			continue;
-		}
-#endif /* CONFIG_U3_DART */
 		BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
 				prot, mmu_linear_psize, mmu_kernel_ssize));
 	}
@@ -926,12 +921,24 @@ void __init hash__early_init_mmu(void)
 	pci_io_base = ISA_IO_BASE;
 #endif
 
+	/* Select appropriate backend */
+	if (firmware_has_feature(FW_FEATURE_PS3_LV1))
+		ps3_early_mm_init();
+	else if (firmware_has_feature(FW_FEATURE_LPAR))
+		hpte_init_pseries();
+	else if (IS_ENABLED(CONFIG_PPC_NATIVE))
+		hpte_init_native();
+
+	if (!mmu_hash_ops.hpte_insert)
+		panic("hash__early_init_mmu: No MMU hash ops defined!\n");
+
 	/* Initialize the MMU Hash table and create the linear mapping
 	 * of memory. Has to be done before SLB initialization as this is
 	 * currently where the page size encoding is obtained.
 	 */
 	htab_initialize();
 
+	pr_info("Initializing hash mmu with SLB\n");
 	/* Initialize SLB management */
 	slb_initialize();
 }
@@ -1474,7 +1481,8 @@ void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
 		 * We use same base page size and actual psize, because we don't
 		 * use these functions for hugepage
 		 */
-		ppc_md.hpte_invalidate(slot, vpn, psize, psize, ssize, local);
+		mmu_hash_ops.hpte_invalidate(slot, vpn, psize, psize,
+					     ssize, local);
 	} pte_iterate_hashed_end();
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -1515,9 +1523,9 @@ void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
 	if (!hpte_slot_array)
 		return;
 
-	if (ppc_md.hugepage_invalidate) {
-		ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
-					   psize, ssize, local);
+	if (mmu_hash_ops.hugepage_invalidate) {
+		mmu_hash_ops.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
+						 psize, ssize, local);
 		goto tm_abort;
 	}
 	/*
@@ -1544,8 +1552,8 @@ void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
 
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += hidx & _PTEIDX_GROUP_IX;
-		ppc_md.hpte_invalidate(slot, vpn, psize,
-				       MMU_PAGE_16M, ssize, local);
+		mmu_hash_ops.hpte_invalidate(slot, vpn, psize,
+					     MMU_PAGE_16M, ssize, local);
 	}
 tm_abort:
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -1569,8 +1577,8 @@ tm_abort:
 
 void flush_hash_range(unsigned long number, int local)
 {
-	if (ppc_md.flush_hash_range)
-		ppc_md.flush_hash_range(number, local);
+	if (mmu_hash_ops.flush_hash_range)
+		mmu_hash_ops.flush_hash_range(number, local);
 	else {
 		int i;
 		struct ppc64_tlb_batch *batch =
@@ -1615,22 +1623,22 @@ repeat:
 		       HPTES_PER_GROUP) & ~0x7UL;
 
 	/* Insert into the hash table, primary slot */
-	slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, vflags,
-				  psize, psize, ssize);
+	slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, vflags,
+					psize, psize, ssize);
 
 	/* Primary is full, try the secondary */
 	if (unlikely(slot == -1)) {
 		hpte_group = ((~hash & htab_hash_mask) *
 			      HPTES_PER_GROUP) & ~0x7UL;
-		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags,
-					  vflags | HPTE_V_SECONDARY,
-					  psize, psize, ssize);
+		slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags,
+						vflags | HPTE_V_SECONDARY,
+						psize, psize, ssize);
 		if (slot == -1) {
 			if (mftb() & 0x1)
 				hpte_group = ((hash & htab_hash_mask) *
 					      HPTES_PER_GROUP)&~0x7UL;
 
-			ppc_md.hpte_remove(hpte_group);
+			mmu_hash_ops.hpte_remove(hpte_group);
 			goto repeat;
 		}
 	}
@@ -1680,8 +1688,9 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
 		hash = ~hash;
 	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 	slot += hidx & _PTEIDX_GROUP_IX;
-	ppc_md.hpte_invalidate(slot, vpn, mmu_linear_psize, mmu_linear_psize,
-			       mmu_kernel_ssize, 0);
+	mmu_hash_ops.hpte_invalidate(slot, vpn, mmu_linear_psize,
+				     mmu_linear_psize,
+				     mmu_kernel_ssize, 0);
 }
 
 void __kernel_map_pages(struct page *page, int numpages, int enable)
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index ba3fc229468a..f20d16f849c5 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -103,8 +103,8 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += hidx & _PTEIDX_GROUP_IX;
 
-		ret = ppc_md.hpte_updatepp(slot, rflags, vpn,
-					   psize, lpsize, ssize, flags);
+		ret = mmu_hash_ops.hpte_updatepp(slot, rflags, vpn,
+						 psize, lpsize, ssize, flags);
 		/*
 		 * We failed to update, try to insert a new entry.
 		 */
@@ -131,23 +131,24 @@ repeat:
 		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
 
 		/* Insert into the hash table, primary slot */
-		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
-					  psize, lpsize, ssize);
+		slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, 0,
+						psize, lpsize, ssize);
 		/*
 		 * Primary is full, try the secondary
 		 */
 		if (unlikely(slot == -1)) {
 			hpte_group = ((~hash & htab_hash_mask) *
 				      HPTES_PER_GROUP) & ~0x7UL;
-			slot = ppc_md.hpte_insert(hpte_group, vpn, pa,
-						  rflags, HPTE_V_SECONDARY,
-						  psize, lpsize, ssize);
+			slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa,
+							rflags,
+							HPTE_V_SECONDARY,
+							psize, lpsize, ssize);
 			if (slot == -1) {
 				if (mftb() & 0x1)
 					hpte_group = ((hash & htab_hash_mask) *
 						      HPTES_PER_GROUP) & ~0x7UL;
 
-				ppc_md.hpte_remove(hpte_group);
+				mmu_hash_ops.hpte_remove(hpte_group);
 				goto repeat;
 			}
 		}
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index 3058560b6121..d5026f3800b6 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -79,8 +79,8 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 		slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT;
 
-		if (ppc_md.hpte_updatepp(slot, rflags, vpn, mmu_psize,
-					 mmu_psize, ssize, flags) == -1)
+		if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, mmu_psize,
+					       mmu_psize, ssize, flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}
 
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 119d18611500..7372ee13eb1e 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -81,6 +81,13 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 	if (! new)
 		return -ENOMEM;
 
+	/*
+	 * Make sure other cpus find the hugepd set only after a
+	 * properly initialized page table is visible to them.
+	 * For more details look for comment in __pte_alloc().
+	 */
+	smp_wmb();
+
 	spin_lock(&mm->page_table_lock);
 #ifdef CONFIG_PPC_FSL_BOOK3E
 	/*
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index c899fe340bbd..448685fbf27c 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -64,7 +64,7 @@ EXPORT_SYMBOL(memstart_addr);
 phys_addr_t kernstart_addr;
 EXPORT_SYMBOL(kernstart_addr);
 
-#ifdef CONFIG_RELOCATABLE_PPC32
+#ifdef CONFIG_RELOCATABLE
 /* Used in __va()/__pa() */
 long long virt_phys_offset;
 EXPORT_SYMBOL(virt_phys_offset);
@@ -80,9 +80,6 @@ EXPORT_SYMBOL(agp_special_page);
 
 void MMU_init(void);
 
-/* XXX should be in current.h  -- paulus */
-extern struct task_struct *current_set[NR_CPUS];
-
 /*
  * this tells the system to map all of ram with the segregs
  * (i.e. page tables) instead of the bats.
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 2fd57fa48429..5f844337de21 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -116,6 +116,16 @@ int memory_add_physaddr_to_nid(u64 start)
 }
 #endif
 
+int __weak create_section_mapping(unsigned long start, unsigned long end)
+{
+	return -ENODEV;
+}
+
+int __weak remove_section_mapping(unsigned long start, unsigned long end)
+{
+	return -ENODEV;
+}
+
 int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
 	struct pglist_data *pgdata;
@@ -239,8 +249,14 @@ static int __init mark_nonram_nosave(void)
 
 static bool zone_limits_final;
 
+/*
+ * The memory zones past TOP_ZONE are managed by generic mm code.
+ * These should be set to zero since that's what every other
+ * architecture does.
+ */
 static unsigned long max_zone_pfns[MAX_NR_ZONES] = {
-	[0 ... MAX_NR_ZONES - 1] = ~0UL
+	[0            ... TOP_ZONE        ] = ~0UL,
+	[TOP_ZONE + 1 ... MAX_NR_ZONES - 1] = 0
 };
 
 /*
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index 196222227e82..b114f8b93ec9 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -181,7 +181,10 @@ void destroy_context(struct mm_struct *mm)
 #ifdef CONFIG_PPC_RADIX_MMU
 void radix__switch_mmu_context(struct mm_struct *prev, struct mm_struct *next)
 {
-	mtspr(SPRN_PID, next->context.id);
 	asm volatile("isync": : :"memory");
+	mtspr(SPRN_PID, next->context.id);
+	asm volatile("isync \n"
+		     PPC_SLBIA(0x7)
+		     : : :"memory");
 }
 #endif
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 6af65327c993..f988db655e5b 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -154,9 +154,10 @@ struct tlbcam {
 };
 #endif
 
-#if defined(CONFIG_6xx) || defined(CONFIG_FSL_BOOKE)
+#if defined(CONFIG_6xx) || defined(CONFIG_FSL_BOOKE) || defined(CONFIG_PPC_8xx)
 /* 6xx have BATS */
 /* FSL_BOOKE have TLBCAM */
+/* 8xx have LTLB */
 phys_addr_t v_block_mapped(unsigned long va);
 unsigned long p_block_mapped(phys_addr_t pa);
 #else
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 6dc07ddbfd04..75b9cd6150cc 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1153,18 +1153,34 @@ int hot_add_scn_to_nid(unsigned long scn_addr)
 
 static u64 hot_add_drconf_memory_max(void)
 {
-        struct device_node *memory = NULL;
-        unsigned int drconf_cell_cnt = 0;
-        u64 lmb_size = 0;
+	struct device_node *memory = NULL;
+	struct device_node *dn = NULL;
+	unsigned int drconf_cell_cnt = 0;
+	u64 lmb_size = 0;
 	const __be32 *dm = NULL;
+	const __be64 *lrdr = NULL;
+	struct of_drconf_cell drmem;
+
+	dn = of_find_node_by_path("/rtas");
+	if (dn) {
+		lrdr = of_get_property(dn, "ibm,lrdr-capacity", NULL);
+		of_node_put(dn);
+		if (lrdr)
+			return be64_to_cpup(lrdr);
+	}
+
+	memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
+	if (memory) {
+		drconf_cell_cnt = of_get_drconf_memory(memory, &dm);
+		lmb_size = of_get_lmb_size(memory);
 
-        memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
-        if (memory) {
-                drconf_cell_cnt = of_get_drconf_memory(memory, &dm);
-                lmb_size = of_get_lmb_size(memory);
-                of_node_put(memory);
-        }
-        return lmb_size * drconf_cell_cnt;
+		/* Advance to the last cell, each cell has 6 32 bit integers */
+		dm += (drconf_cell_cnt - 1) * 6;
+		read_drconf_cell(&drmem, &dm);
+		of_node_put(memory);
+		return drmem.base_addr + lmb_size;
+	}
+	return 0;
 }
 
 /*
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 7931e1496f0d..003ff48a11b6 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -21,8 +21,11 @@
 
 #include <trace/events/thp.h>
 
-static int native_update_partition_table(u64 patb1)
+static int native_register_process_table(unsigned long base, unsigned long pg_sz,
+					 unsigned long table_size)
 {
+	unsigned long patb1 = base | table_size | PATB_GR;
+
 	partition_tb->patb1 = cpu_to_be64(patb1);
 	return 0;
 }
@@ -168,7 +171,7 @@ redo:
 	 * of process table here. But our linear mapping also enable us to use
 	 * physical address here.
 	 */
-	ppc_md.update_partition_table(__pa(process_tb) | (PRTB_SIZE_SHIFT - 12) | PATB_GR);
+	ppc_md.register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12);
 	pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd);
 }
 
@@ -182,7 +185,8 @@ static void __init radix_init_partition_table(void)
 	partition_tb = early_alloc_pgtable(1UL << PATB_SIZE_SHIFT);
 	partition_tb->patb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) |
 					  RADIX_PGD_INDEX_SIZE | PATB_HR);
-	printk("Partition table %p\n", partition_tb);
+	pr_info("Initializing Radix MMU\n");
+	pr_info("Partition table %p\n", partition_tb);
 
 	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
 	/*
@@ -194,7 +198,7 @@ static void __init radix_init_partition_table(void)
 
 void __init radix_init_native(void)
 {
-	ppc_md.update_partition_table = native_update_partition_table;
+	ppc_md.register_process_table = native_register_process_table;
 }
 
 static int __init get_idx_from_shift(unsigned int shift)
@@ -341,8 +345,9 @@ void __init radix__early_init_mmu(void)
 
 	radix_init_page_sizes();
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+		radix_init_native();
 		lpcr = mfspr(SPRN_LPCR);
-		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
+		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 		radix_init_partition_table();
 	}
 
@@ -357,7 +362,7 @@ void radix__early_init_mmu_secondary(void)
 	 */
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
 		lpcr = mfspr(SPRN_LPCR);
-		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
+		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 
 		mtspr(SPRN_PTCR,
 		      __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index ab2f60e812e2..e1f22700fb16 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -12,6 +12,7 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/memblock.h>
+#include <asm/ppc-opcode.h>
 
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
@@ -34,8 +35,7 @@ static inline void __tlbiel_pid(unsigned long pid, int set,
 	r = 1;   /* raidx format */
 
 	asm volatile("ptesync": : :"memory");
-	asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
-		     "(%2 << 17) | (%3 << 18) | (%4 << 21)"
+	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("ptesync": : :"memory");
 }
@@ -63,8 +63,7 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 	r = 1;   /* raidx format */
 
 	asm volatile("ptesync": : :"memory");
-	asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
-		     "(%2 << 17) | (%3 << 18) | (%4 << 21)"
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
@@ -81,8 +80,7 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 	r = 1;   /* raidx format */
 
 	asm volatile("ptesync": : :"memory");
-	asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
-		     "(%2 << 17) | (%3 << 18) | (%4 << 21)"
+	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("ptesync": : :"memory");
 }
@@ -99,8 +97,7 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid,
 	r = 1;   /* raidx format */
 
 	asm volatile("ptesync": : :"memory");
-	asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
-		     "(%2 << 17) | (%3 << 18) | (%4 << 21)"
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
@@ -285,9 +282,61 @@ void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 }
 EXPORT_SYMBOL(radix__flush_tlb_range);
 
+static int radix_get_mmu_psize(int page_size)
+{
+	int psize;
+
+	if (page_size == (1UL << mmu_psize_defs[mmu_virtual_psize].shift))
+		psize = mmu_virtual_psize;
+	else if (page_size == (1UL << mmu_psize_defs[MMU_PAGE_2M].shift))
+		psize = MMU_PAGE_2M;
+	else if (page_size == (1UL << mmu_psize_defs[MMU_PAGE_1G].shift))
+		psize = MMU_PAGE_1G;
+	else
+		return -1;
+	return psize;
+}
 
 void radix__tlb_flush(struct mmu_gather *tlb)
 {
 	struct mm_struct *mm = tlb->mm;
 	radix__flush_tlb_mm(mm);
 }
+
+void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,
+			      unsigned long page_size)
+{
+	unsigned long rb,rs,prs,r;
+	unsigned long ap;
+	unsigned long ric = RIC_FLUSH_TLB;
+
+	ap = mmu_get_ap(radix_get_mmu_psize(page_size));
+	rb = gpa & ~(PPC_BITMASK(52, 63));
+	rb |= ap << PPC_BITLSHIFT(58);
+	rs = lpid & ((1UL << 32) - 1);
+	prs = 0; /* process scoped */
+	r = 1;   /* raidx format */
+
+	asm volatile("ptesync": : :"memory");
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
+}
+EXPORT_SYMBOL(radix__flush_tlb_lpid_va);
+
+void radix__flush_tlb_lpid(unsigned long lpid)
+{
+	unsigned long rb,rs,prs,r;
+	unsigned long ric = RIC_FLUSH_ALL;
+
+	rb = 0x2 << PPC_BITLSHIFT(53); /* IS = 2 */
+	rs = lpid & ((1UL << 32) - 1);
+	prs = 0; /* partition scoped */
+	r = 1;   /* raidx format */
+
+	asm volatile("ptesync": : :"memory");
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
+}
+EXPORT_SYMBOL(radix__flush_tlb_lpid);