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()
  ...

1 files changed, 113 insertions, 35 deletions

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 3ed9a5a21d77..4e7759c8ca30 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -96,7 +96,8 @@ static struct clocksource clocksource_timebase = {
 	.read         = timebase_read,
 };
 
-#define DECREMENTER_MAX	0x7fffffff
+#define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF
+u64 decrementer_max = DECREMENTER_DEFAULT_MAX;
 
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev);
@@ -166,7 +167,15 @@ DEFINE_PER_CPU(unsigned long, cputime_scaled_last_delta);
 
 cputime_t cputime_one_jiffy;
 
+#ifdef CONFIG_PPC_SPLPAR
 void (*dtl_consumer)(struct dtl_entry *, u64);
+#endif
+
+#ifdef CONFIG_PPC64
+#define get_accounting(tsk)	(&get_paca()->accounting)
+#else
+#define get_accounting(tsk)	(&task_thread_info(tsk)->accounting)
+#endif
 
 static void calc_cputime_factors(void)
 {
@@ -186,7 +195,7 @@ static void calc_cputime_factors(void)
  * Read the SPURR on systems that have it, otherwise the PURR,
  * or if that doesn't exist return the timebase value passed in.
  */
-static u64 read_spurr(u64 tb)
+static unsigned long read_spurr(unsigned long tb)
 {
 	if (cpu_has_feature(CPU_FTR_SPURR))
 		return mfspr(SPRN_SPURR);
@@ -249,8 +258,8 @@ static u64 scan_dispatch_log(u64 stop_tb)
 void accumulate_stolen_time(void)
 {
 	u64 sst, ust;
-
 	u8 save_soft_enabled = local_paca->soft_enabled;
+	struct cpu_accounting_data *acct = &local_paca->accounting;
 
 	/* We are called early in the exception entry, before
 	 * soft/hard_enabled are sync'ed to the expected state
@@ -260,10 +269,10 @@ void accumulate_stolen_time(void)
 	 */
 	local_paca->soft_enabled = 0;
 
-	sst = scan_dispatch_log(local_paca->starttime_user);
-	ust = scan_dispatch_log(local_paca->starttime);
-	local_paca->system_time -= sst;
-	local_paca->user_time -= ust;
+	sst = scan_dispatch_log(acct->starttime_user);
+	ust = scan_dispatch_log(acct->starttime);
+	acct->system_time -= sst;
+	acct->user_time -= ust;
 	local_paca->stolen_time += ust + sst;
 
 	local_paca->soft_enabled = save_soft_enabled;
@@ -275,7 +284,7 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
 
 	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {
 		stolen = scan_dispatch_log(stop_tb);
-		get_paca()->system_time -= stolen;
+		get_paca()->accounting.system_time -= stolen;
 	}
 
 	stolen += get_paca()->stolen_time;
@@ -295,27 +304,29 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
  * Account time for a transition between system, hard irq
  * or soft irq state.
  */
-static u64 vtime_delta(struct task_struct *tsk,
-			u64 *sys_scaled, u64 *stolen)
+static unsigned long vtime_delta(struct task_struct *tsk,
+				 unsigned long *sys_scaled,
+				 unsigned long *stolen)
 {
-	u64 now, nowscaled, deltascaled;
-	u64 udelta, delta, user_scaled;
+	unsigned long now, nowscaled, deltascaled;
+	unsigned long udelta, delta, user_scaled;
+	struct cpu_accounting_data *acct = get_accounting(tsk);
 
 	WARN_ON_ONCE(!irqs_disabled());
 
 	now = mftb();
 	nowscaled = read_spurr(now);
-	get_paca()->system_time += now - get_paca()->starttime;
-	get_paca()->starttime = now;
-	deltascaled = nowscaled - get_paca()->startspurr;
-	get_paca()->startspurr = nowscaled;
+	acct->system_time += now - acct->starttime;
+	acct->starttime = now;
+	deltascaled = nowscaled - acct->startspurr;
+	acct->startspurr = nowscaled;
 
 	*stolen = calculate_stolen_time(now);
 
-	delta = get_paca()->system_time;
-	get_paca()->system_time = 0;
-	udelta = get_paca()->user_time - get_paca()->utime_sspurr;
-	get_paca()->utime_sspurr = get_paca()->user_time;
+	delta = acct->system_time;
+	acct->system_time = 0;
+	udelta = acct->user_time - acct->utime_sspurr;
+	acct->utime_sspurr = acct->user_time;
 
 	/*
 	 * Because we don't read the SPURR on every kernel entry/exit,
@@ -337,14 +348,14 @@ static u64 vtime_delta(struct task_struct *tsk,
 			*sys_scaled = deltascaled;
 		}
 	}
-	get_paca()->user_time_scaled += user_scaled;
+	acct->user_time_scaled += user_scaled;
 
 	return delta;
 }
 
 void vtime_account_system(struct task_struct *tsk)
 {
-	u64 delta, sys_scaled, stolen;
+	unsigned long delta, sys_scaled, stolen;
 
 	delta = vtime_delta(tsk, &sys_scaled, &stolen);
 	account_system_time(tsk, 0, delta, sys_scaled);
@@ -355,7 +366,7 @@ EXPORT_SYMBOL_GPL(vtime_account_system);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
-	u64 delta, sys_scaled, stolen;
+	unsigned long delta, sys_scaled, stolen;
 
 	delta = vtime_delta(tsk, &sys_scaled, &stolen);
 	account_idle_time(delta + stolen);
@@ -373,15 +384,32 @@ void vtime_account_idle(struct task_struct *tsk)
 void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t utime, utimescaled;
+	struct cpu_accounting_data *acct = get_accounting(tsk);
 
-	utime = get_paca()->user_time;
-	utimescaled = get_paca()->user_time_scaled;
-	get_paca()->user_time = 0;
-	get_paca()->user_time_scaled = 0;
-	get_paca()->utime_sspurr = 0;
+	utime = acct->user_time;
+	utimescaled = acct->user_time_scaled;
+	acct->user_time = 0;
+	acct->user_time_scaled = 0;
+	acct->utime_sspurr = 0;
 	account_user_time(tsk, utime, utimescaled);
 }
 
+#ifdef CONFIG_PPC32
+/*
+ * Called from the context switch with interrupts disabled, to charge all
+ * accumulated times to the current process, and to prepare accounting on
+ * the next process.
+ */
+void arch_vtime_task_switch(struct task_struct *prev)
+{
+	struct cpu_accounting_data *acct = get_accounting(current);
+
+	acct->starttime = get_accounting(prev)->starttime;
+	acct->system_time = 0;
+	acct->user_time = 0;
+}
+#endif /* CONFIG_PPC32 */
+
 #else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 #define calc_cputime_factors()
 #endif
@@ -504,8 +532,8 @@ static void __timer_interrupt(void)
 		__this_cpu_inc(irq_stat.timer_irqs_event);
 	} else {
 		now = *next_tb - now;
-		if (now <= DECREMENTER_MAX)
-			set_dec((int)now);
+		if (now <= decrementer_max)
+			set_dec(now);
 		/* We may have raced with new irq work */
 		if (test_irq_work_pending())
 			set_dec(1);
@@ -535,7 +563,7 @@ void timer_interrupt(struct pt_regs * regs)
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continue to take decrementer exceptions.
 	 */
-	set_dec(DECREMENTER_MAX);
+	set_dec(decrementer_max);
 
 	/* Some implementations of hotplug will get timer interrupts while
 	 * offline, just ignore these and we also need to set
@@ -583,9 +611,9 @@ static void generic_suspend_disable_irqs(void)
 	 * with suspending.
 	 */
 
-	set_dec(DECREMENTER_MAX);
+	set_dec(decrementer_max);
 	local_irq_disable();
-	set_dec(DECREMENTER_MAX);
+	set_dec(decrementer_max);
 }
 
 static void generic_suspend_enable_irqs(void)
@@ -866,7 +894,7 @@ static int decrementer_set_next_event(unsigned long evt,
 
 static int decrementer_shutdown(struct clock_event_device *dev)
 {
-	decrementer_set_next_event(DECREMENTER_MAX, dev);
+	decrementer_set_next_event(decrementer_max, dev);
 	return 0;
 }
 
@@ -892,6 +920,49 @@ static void register_decrementer_clockevent(int cpu)
 	clockevents_register_device(dec);
 }
 
+static void enable_large_decrementer(void)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+		return;
+
+	if (decrementer_max <= DECREMENTER_DEFAULT_MAX)
+		return;
+
+	/*
+	 * If we're running as the hypervisor we need to enable the LD manually
+	 * otherwise firmware should have done it for us.
+	 */
+	if (cpu_has_feature(CPU_FTR_HVMODE))
+		mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_LD);
+}
+
+static void __init set_decrementer_max(void)
+{
+	struct device_node *cpu;
+	u32 bits = 32;
+
+	/* Prior to ISAv3 the decrementer is always 32 bit */
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+		return;
+
+	cpu = of_find_node_by_type(NULL, "cpu");
+
+	if (of_property_read_u32(cpu, "ibm,dec-bits", &bits) == 0) {
+		if (bits > 64 || bits < 32) {
+			pr_warn("time_init: firmware supplied invalid ibm,dec-bits");
+			bits = 32;
+		}
+
+		/* calculate the signed maximum given this many bits */
+		decrementer_max = (1ul << (bits - 1)) - 1;
+	}
+
+	of_node_put(cpu);
+
+	pr_info("time_init: %u bit decrementer (max: %llx)\n",
+		bits, decrementer_max);
+}
+
 static void __init init_decrementer_clockevent(void)
 {
 	int cpu = smp_processor_id();
@@ -899,7 +970,7 @@ static void __init init_decrementer_clockevent(void)
 	clockevents_calc_mult_shift(&decrementer_clockevent, ppc_tb_freq, 4);
 
 	decrementer_clockevent.max_delta_ns =
-		clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent);
+		clockevent_delta2ns(decrementer_max, &decrementer_clockevent);
 	decrementer_clockevent.min_delta_ns =
 		clockevent_delta2ns(2, &decrementer_clockevent);
 
@@ -908,6 +979,9 @@ static void __init init_decrementer_clockevent(void)
 
 void secondary_cpu_time_init(void)
 {
+	/* Enable and test the large decrementer for this cpu */
+	enable_large_decrementer();
+
 	/* Start the decrementer on CPUs that have manual control
 	 * such as BookE
 	 */
@@ -973,6 +1047,10 @@ void __init time_init(void)
 	vdso_data->tb_update_count = 0;
 	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
 
+	/* initialise and enable the large decrementer (if we have one) */
+	set_decrementer_max();
+	enable_large_decrementer();
+
 	/* Start the decrementer on CPUs that have manual control
 	 * such as BookE
 	 */