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()
  ...

8 files changed, 264 insertions, 115 deletions

diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index 0ac12e5fd8ab..911456d17713 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -28,6 +28,7 @@
 #include <asm/udbg.h>
 #include <asm/io.h>
 #include <asm/cpm.h>
+#include <asm/fixmap.h>
 #include <soc/fsl/qe/qe.h>
 
 #include <mm/mmu_decl.h>
@@ -37,25 +38,36 @@
 #endif
 
 #ifdef CONFIG_PPC_EARLY_DEBUG_CPM
-static u32 __iomem *cpm_udbg_txdesc =
-	(u32 __iomem __force *)CONFIG_PPC_EARLY_DEBUG_CPM_ADDR;
+static u32 __iomem *cpm_udbg_txdesc;
+static u8 __iomem *cpm_udbg_txbuf;
 
 static void udbg_putc_cpm(char c)
 {
-	u8 __iomem *txbuf = (u8 __iomem __force *)in_be32(&cpm_udbg_txdesc[1]);
-
 	if (c == '\n')
 		udbg_putc_cpm('\r');
 
 	while (in_be32(&cpm_udbg_txdesc[0]) & 0x80000000)
 		;
 
-	out_8(txbuf, c);
+	out_8(cpm_udbg_txbuf, c);
 	out_be32(&cpm_udbg_txdesc[0], 0xa0000001);
 }
 
 void __init udbg_init_cpm(void)
 {
+#ifdef CONFIG_PPC_8xx
+	cpm_udbg_txdesc = (u32 __iomem __force *)
+			  (CONFIG_PPC_EARLY_DEBUG_CPM_ADDR - PHYS_IMMR_BASE +
+			   VIRT_IMMR_BASE);
+	cpm_udbg_txbuf = (u8 __iomem __force *)
+			 (in_be32(&cpm_udbg_txdesc[1]) - PHYS_IMMR_BASE +
+			  VIRT_IMMR_BASE);
+#else
+	cpm_udbg_txdesc = (u32 __iomem __force *)
+			  CONFIG_PPC_EARLY_DEBUG_CPM_ADDR;
+	cpm_udbg_txbuf = (u8 __iomem __force *)in_be32(&cpm_udbg_txdesc[1]);
+#endif
+
 	if (cpm_udbg_txdesc) {
 #ifdef CONFIG_CPM2
 		setbat(1, 0xf0000000, 0xf0000000, 1024*1024, PAGE_KERNEL_NCG);
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index b7348637eae0..26904f4879ec 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -48,16 +48,10 @@
 
 #include "dart.h"
 
-/* Physical base address and size of the DART table */
-unsigned long dart_tablebase; /* exported to htab_initialize */
+/* DART table address and size */
+static u32 *dart_tablebase;
 static unsigned long dart_tablesize;
 
-/* Virtual base address of the DART table */
-static u32 *dart_vbase;
-#ifdef CONFIG_PM
-static u32 *dart_copy;
-#endif
-
 /* Mapped base address for the dart */
 static unsigned int __iomem *dart;
 
@@ -151,6 +145,34 @@ wait_more:
 	spin_unlock_irqrestore(&invalidate_lock, flags);
 }
 
+static void dart_cache_sync(unsigned int *base, unsigned int count)
+{
+	/*
+	 * We add 1 to the number of entries to flush, following a
+	 * comment in Darwin indicating that the memory controller
+	 * can prefetch unmapped memory under some circumstances.
+	 */
+	unsigned long start = (unsigned long)base;
+	unsigned long end = start + (count + 1) * sizeof(unsigned int);
+	unsigned int tmp;
+
+	/* Perform a standard cache flush */
+	flush_inval_dcache_range(start, end);
+
+	/*
+	 * Perform the sequence described in the CPC925 manual to
+	 * ensure all the data gets to a point the cache incoherent
+	 * DART hardware will see.
+	 */
+	asm volatile(" sync;"
+		     " isync;"
+		     " dcbf 0,%1;"
+		     " sync;"
+		     " isync;"
+		     " lwz %0,0(%1);"
+		     " isync" : "=r" (tmp) : "r" (end) : "memory");
+}
+
 static void dart_flush(struct iommu_table *tbl)
 {
 	mb();
@@ -165,13 +187,13 @@ static int dart_build(struct iommu_table *tbl, long index,
 		       enum dma_data_direction direction,
 		       struct dma_attrs *attrs)
 {
-	unsigned int *dp;
+	unsigned int *dp, *orig_dp;
 	unsigned int rpn;
 	long l;
 
 	DBG("dart: build at: %lx, %lx, addr: %x\n", index, npages, uaddr);
 
-	dp = ((unsigned int*)tbl->it_base) + index;
+	orig_dp = dp = ((unsigned int*)tbl->it_base) + index;
 
 	/* On U3, all memory is contiguous, so we can move this
 	 * out of the loop.
@@ -184,11 +206,7 @@ static int dart_build(struct iommu_table *tbl, long index,
 
 		uaddr += DART_PAGE_SIZE;
 	}
-
-	/* make sure all updates have reached memory */
-	mb();
-	in_be32((unsigned __iomem *)dp);
-	mb();
+	dart_cache_sync(orig_dp, npages);
 
 	if (dart_is_u4) {
 		rpn = index;
@@ -203,7 +221,8 @@ static int dart_build(struct iommu_table *tbl, long index,
 
 static void dart_free(struct iommu_table *tbl, long index, long npages)
 {
-	unsigned int *dp;
+	unsigned int *dp, *orig_dp;
+	long orig_npages = npages;
 
 	/* We don't worry about flushing the TLB cache. The only drawback of
 	 * not doing it is that we won't catch buggy device drivers doing
@@ -212,34 +231,30 @@ static void dart_free(struct iommu_table *tbl, long index, long npages)
 
 	DBG("dart: free at: %lx, %lx\n", index, npages);
 
-	dp  = ((unsigned int *)tbl->it_base) + index;
+	orig_dp = dp  = ((unsigned int *)tbl->it_base) + index;
 
 	while (npages--)
 		*(dp++) = dart_emptyval;
-}
 
+	dart_cache_sync(orig_dp, orig_npages);
+}
 
-static int __init dart_init(struct device_node *dart_node)
+static void allocate_dart(void)
 {
-	unsigned int i;
-	unsigned long tmp, base, size;
-	struct resource r;
-
-	if (dart_tablebase == 0 || dart_tablesize == 0) {
-		printk(KERN_INFO "DART: table not allocated, using "
-		       "direct DMA\n");
-		return -ENODEV;
-	}
+	unsigned long tmp;
 
-	if (of_address_to_resource(dart_node, 0, &r))
-		panic("DART: can't get register base ! ");
+	/* 512 pages (2MB) is max DART tablesize. */
+	dart_tablesize = 1UL << 21;
 
-	/* Make sure nothing from the DART range remains in the CPU cache
-	 * from a previous mapping that existed before the kernel took
-	 * over
+	/*
+	 * 16MB (1 << 24) alignment. We allocate a full 16Mb chuck since we
+	 * will blow up an entire large page anyway in the kernel mapping.
 	 */
-	flush_dcache_phys_range(dart_tablebase,
-				dart_tablebase + dart_tablesize);
+	dart_tablebase = __va(memblock_alloc_base(1UL<<24,
+						  1UL<<24, 0x80000000L));
+
+	/* There is no point scanning the DART space for leaks*/
+	kmemleak_no_scan((void *)dart_tablebase);
 
 	/* Allocate a spare page to map all invalid DART pages. We need to do
 	 * that to work around what looks like a problem with the HT bridge
@@ -249,20 +264,51 @@ static int __init dart_init(struct device_node *dart_node)
 	dart_emptyval = DARTMAP_VALID | ((tmp >> DART_PAGE_SHIFT) &
 					 DARTMAP_RPNMASK);
 
+	printk(KERN_INFO "DART table allocated at: %p\n", dart_tablebase);
+}
+
+static int __init dart_init(struct device_node *dart_node)
+{
+	unsigned int i;
+	unsigned long base, size;
+	struct resource r;
+
+	/* IOMMU disabled by the user ? bail out */
+	if (iommu_is_off)
+		return -ENODEV;
+
+	/*
+	 * Only use the DART if the machine has more than 1GB of RAM
+	 * or if requested with iommu=on on cmdline.
+	 *
+	 * 1GB of RAM is picked as limit because some default devices
+	 * (i.e. Airport Extreme) have 30 bit address range limits.
+	 */
+
+	if (!iommu_force_on && memblock_end_of_DRAM() <= 0x40000000ull)
+		return -ENODEV;
+
+	/* Get DART registers */
+	if (of_address_to_resource(dart_node, 0, &r))
+		panic("DART: can't get register base ! ");
+
 	/* Map in DART registers */
 	dart = ioremap(r.start, resource_size(&r));
 	if (dart == NULL)
 		panic("DART: Cannot map registers!");
 
-	/* Map in DART table */
-	dart_vbase = ioremap(__pa(dart_tablebase), dart_tablesize);
+	/* Allocate the DART and dummy page */
+	allocate_dart();
 
 	/* Fill initial table */
 	for (i = 0; i < dart_tablesize/4; i++)
-		dart_vbase[i] = dart_emptyval;
+		dart_tablebase[i] = dart_emptyval;
+
+	/* Push to memory */
+	dart_cache_sync(dart_tablebase, dart_tablesize / sizeof(u32));
 
 	/* Initialize DART with table base and enable it. */
-	base = dart_tablebase >> DART_PAGE_SHIFT;
+	base = ((unsigned long)dart_tablebase) >> DART_PAGE_SHIFT;
 	size = dart_tablesize >> DART_PAGE_SHIFT;
 	if (dart_is_u4) {
 		size &= DART_SIZE_U4_SIZE_MASK;
@@ -301,7 +347,7 @@ static void iommu_table_dart_setup(void)
 	iommu_table_dart.it_page_shift = IOMMU_PAGE_SHIFT_4K;
 
 	/* Initialize the common IOMMU code */
-	iommu_table_dart.it_base = (unsigned long)dart_vbase;
+	iommu_table_dart.it_base = (unsigned long)dart_tablebase;
 	iommu_table_dart.it_index = 0;
 	iommu_table_dart.it_blocksize = 1;
 	iommu_table_dart.it_ops = &iommu_dart_ops;
@@ -404,75 +450,21 @@ void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops)
 }
 
 #ifdef CONFIG_PM
-static void iommu_dart_save(void)
-{
-	memcpy(dart_copy, dart_vbase, 2*1024*1024);
-}
-
 static void iommu_dart_restore(void)
 {
-	memcpy(dart_vbase, dart_copy, 2*1024*1024);
+	dart_cache_sync(dart_tablebase, dart_tablesize / sizeof(u32));
 	dart_tlb_invalidate_all();
 }
 
 static int __init iommu_init_late_dart(void)
 {
-	unsigned long tbasepfn;
-	struct page *p;
-
-	/* if no dart table exists then we won't need to save it
-	 * and the area has also not been reserved */
 	if (!dart_tablebase)
 		return 0;
 
-	tbasepfn = __pa(dart_tablebase) >> PAGE_SHIFT;
-	register_nosave_region_late(tbasepfn,
-				    tbasepfn + ((1<<24) >> PAGE_SHIFT));
-
-	/* For suspend we need to copy the dart contents because
-	 * it is not part of the regular mapping (see above) and
-	 * thus not saved automatically. The memory for this copy
-	 * must be allocated early because we need 2 MB. */
-	p = alloc_pages(GFP_KERNEL, 21 - PAGE_SHIFT);
-	BUG_ON(!p);
-	dart_copy = page_address(p);
-
-	ppc_md.iommu_save = iommu_dart_save;
 	ppc_md.iommu_restore = iommu_dart_restore;
 
 	return 0;
 }
 
 late_initcall(iommu_init_late_dart);
-#endif
-
-void __init alloc_dart_table(void)
-{
-	/* Only reserve DART space if machine has more than 1GB of RAM
-	 * or if requested with iommu=on on cmdline.
-	 *
-	 * 1GB of RAM is picked as limit because some default devices
-	 * (i.e. Airport Extreme) have 30 bit address range limits.
-	 */
-
-	if (iommu_is_off)
-		return;
-
-	if (!iommu_force_on && memblock_end_of_DRAM() <= 0x40000000ull)
-		return;
-
-	/* 512 pages (2MB) is max DART tablesize. */
-	dart_tablesize = 1UL << 21;
-	/* 16MB (1 << 24) alignment. We allocate a full 16Mb chuck since we
-	 * will blow up an entire large page anyway in the kernel mapping
-	 */
-	dart_tablebase = (unsigned long)
-		__va(memblock_alloc_base(1UL<<24, 1UL<<24, 0x80000000L));
-	/*
-	 * The DART space is later unmapped from the kernel linear mapping and
-	 * accessing dart_tablebase during kmemleak scanning will fault.
-	 */
-	kmemleak_no_scan((void *)dart_tablebase);
-
-	printk(KERN_INFO "DART table allocated at: %lx\n", dart_tablebase);
-}
+#endif /* CONFIG_PM */
diff --git a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
index 861cebf9c292..c27058e5df26 100644
--- a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
+++ b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
@@ -90,12 +90,8 @@ static int mpc85xx_l2ctlr_of_probe(struct platform_device *dev)
 	}
 	l2cache_size = *prop;
 
-	if (get_cache_sram_params(&sram_params)) {
-		dev_err(&dev->dev,
-			"Entire L2 as cache, provide valid sram offset and size\n");
-		return -EINVAL;
-	}
-
+	if (get_cache_sram_params(&sram_params))
+		return 0; /* fall back to L2 cache only */
 
 	rem = l2cache_size % sram_params.sram_size;
 	ways = LOCK_WAYS_FULL * sram_params.sram_size / l2cache_size;
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index 99269c041615..a09ca704de58 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -204,7 +204,7 @@ static int __init setup_rstcr(void)
 
 arch_initcall(setup_rstcr);
 
-void fsl_rstcr_restart(char *cmd)
+void __noreturn fsl_rstcr_restart(char *cmd)
 {
 	local_irq_disable();
 	if (rstcr)
@@ -228,10 +228,11 @@ EXPORT_SYMBOL(diu_ops);
  * to initiate a partition restart when we're running under the Freescale
  * hypervisor.
  */
-void fsl_hv_restart(char *cmd)
+void __noreturn fsl_hv_restart(char *cmd)
 {
 	pr_info("hv restart\n");
 	fh_partition_restart(-1);
+	while (1) ;
 }
 
 /*
@@ -241,9 +242,10 @@ void fsl_hv_restart(char *cmd)
  * function pointers, to shut down the partition when we're running under
  * the Freescale hypervisor.
  */
-void fsl_hv_halt(void)
+void __noreturn fsl_hv_halt(void)
 {
 	pr_info("hv exit\n");
 	fh_partition_stop(-1);
+	while (1) ;
 }
 #endif
diff --git a/arch/powerpc/sysdev/fsl_soc.h b/arch/powerpc/sysdev/fsl_soc.h
index 4c5a19ef4f0b..433566a5ef19 100644
--- a/arch/powerpc/sysdev/fsl_soc.h
+++ b/arch/powerpc/sysdev/fsl_soc.h
@@ -19,7 +19,7 @@ extern u32 fsl_get_sys_freq(void);
 struct spi_board_info;
 struct device_node;
 
-extern void fsl_rstcr_restart(char *cmd);
+extern void __noreturn fsl_rstcr_restart(char *cmd);
 
 /* The different ports that the DIU can be connected to */
 enum fsl_diu_monitor_port {
@@ -42,8 +42,8 @@ struct platform_diu_data_ops {
 
 extern struct platform_diu_data_ops diu_ops;
 
-void fsl_hv_restart(char *cmd);
-void fsl_hv_halt(void);
+void __noreturn fsl_hv_restart(char *cmd);
+void __noreturn fsl_hv_halt(void);
 
 #endif
 #endif
diff --git a/arch/powerpc/sysdev/xics/Makefile b/arch/powerpc/sysdev/xics/Makefile
index c606aa8ba60a..5d7f5a6564de 100644
--- a/arch/powerpc/sysdev/xics/Makefile
+++ b/arch/powerpc/sysdev/xics/Makefile
@@ -4,4 +4,4 @@ obj-y				+= xics-common.o
 obj-$(CONFIG_PPC_ICP_NATIVE)	+= icp-native.o
 obj-$(CONFIG_PPC_ICP_HV)	+= icp-hv.o
 obj-$(CONFIG_PPC_ICS_RTAS)	+= ics-rtas.o
-obj-$(CONFIG_PPC_POWERNV)	+= ics-opal.o
+obj-$(CONFIG_PPC_POWERNV)	+= ics-opal.o icp-opal.o
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
new file mode 100644
index 000000000000..57d72f10a97f
--- /dev/null
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -0,0 +1,144 @@
+/*
+ * Copyright 2016 IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+
+#include <asm/smp.h>
+#include <asm/irq.h>
+#include <asm/errno.h>
+#include <asm/xics.h>
+#include <asm/io.h>
+#include <asm/opal.h>
+
+static void icp_opal_teardown_cpu(void)
+{
+	int cpu = smp_processor_id();
+
+	/* Clear any pending IPI */
+	opal_int_set_mfrr(cpu, 0xff);
+}
+
+static void icp_opal_flush_ipi(void)
+{
+	/*
+	 * We take the ipi irq but and never return so we need to EOI the IPI,
+	 * but want to leave our priority 0.
+	 *
+	 * Should we check all the other interrupts too?
+	 * Should we be flagging idle loop instead?
+	 * Or creating some task to be scheduled?
+	 */
+	opal_int_eoi((0x00 << 24) | XICS_IPI);
+}
+
+static unsigned int icp_opal_get_irq(void)
+{
+	unsigned int xirr;
+	unsigned int vec;
+	unsigned int irq;
+	int64_t rc;
+
+	rc = opal_int_get_xirr(&xirr, false);
+	if (rc < 0)
+		return NO_IRQ;
+	xirr = be32_to_cpu(xirr);
+	vec = xirr & 0x00ffffff;
+	if (vec == XICS_IRQ_SPURIOUS)
+		return NO_IRQ;
+
+	irq = irq_find_mapping(xics_host, vec);
+	if (likely(irq != NO_IRQ)) {
+		xics_push_cppr(vec);
+		return irq;
+	}
+
+	/* We don't have a linux mapping, so have rtas mask it. */
+	xics_mask_unknown_vec(vec);
+
+	/* We might learn about it later, so EOI it */
+	opal_int_eoi(xirr);
+
+	return NO_IRQ;
+}
+
+static void icp_opal_set_cpu_priority(unsigned char cppr)
+{
+	xics_set_base_cppr(cppr);
+	opal_int_set_cppr(cppr);
+	iosync();
+}
+
+static void icp_opal_eoi(struct irq_data *d)
+{
+	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+	int64_t rc;
+
+	iosync();
+	rc = opal_int_eoi((xics_pop_cppr() << 24) | hw_irq);
+
+	/*
+	 * EOI tells us whether there are more interrupts to fetch.
+	 *
+	 * Some HW implementations might not be able to send us another
+	 * external interrupt in that case, so we force a replay.
+	 */
+	if (rc > 0)
+		force_external_irq_replay();
+}
+
+#ifdef CONFIG_SMP
+
+static void icp_opal_cause_ipi(int cpu, unsigned long data)
+{
+	opal_int_set_mfrr(cpu, IPI_PRIORITY);
+}
+
+static irqreturn_t icp_opal_ipi_action(int irq, void *dev_id)
+{
+	int cpu = smp_processor_id();
+
+	opal_int_set_mfrr(cpu, 0xff);
+
+	return smp_ipi_demux();
+}
+
+#endif /* CONFIG_SMP */
+
+static const struct icp_ops icp_opal_ops = {
+	.get_irq	= icp_opal_get_irq,
+	.eoi		= icp_opal_eoi,
+	.set_priority	= icp_opal_set_cpu_priority,
+	.teardown_cpu	= icp_opal_teardown_cpu,
+	.flush_ipi	= icp_opal_flush_ipi,
+#ifdef CONFIG_SMP
+	.ipi_action	= icp_opal_ipi_action,
+	.cause_ipi	= icp_opal_cause_ipi,
+#endif
+};
+
+int icp_opal_init(void)
+{
+	struct device_node *np;
+
+	np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc");
+	if (!np)
+		return -ENODEV;
+
+	icp_ops = &icp_opal_ops;
+
+	printk("XICS: Using OPAL ICP fallbacks\n");
+
+	return 0;
+}
+
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 47e43b7b076b..a795a5f0301c 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -404,8 +404,11 @@ void __init xics_init(void)
 	/* Fist locate ICP */
 	if (firmware_has_feature(FW_FEATURE_LPAR))
 		rc = icp_hv_init();
-	if (rc < 0)
+	if (rc < 0) {
 		rc = icp_native_init();
+		if (rc == -ENODEV)
+		    rc = icp_opal_init();
+	}
 	if (rc < 0) {
 		pr_warning("XICS: Cannot find a Presentation Controller !\n");
 		return;