Merge commit 'v2.6.35-rc6' into devicetree/next

Conflicts:
	arch/sparc/kernel/prom_64.c

23 files changed, 111 insertions, 143 deletions

diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index 26e58630ed7b..625942ae5585 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -7,7 +7,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/lmb.h>
+#include <linux/memblock.h>
 
 #include <asm/sections.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index b46f2e09bd81..417f7b05a9ce 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -24,7 +24,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/types.h>
-#include <linux/lmb.h>
+#include <linux/memblock.h>
 
 #include <asm/processor.h>
 #include <asm/machdep.h>
@@ -447,7 +447,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	crash_kexec_prepare_cpus(crashing_cpu);
 	cpu_set(crashing_cpu, cpus_in_crash);
 	crash_kexec_stop_spus();
-#ifdef CONFIG_PPC_STD_MMU_64
+#if defined(CONFIG_PPC_STD_MMU_64) && defined(CONFIG_SMP)
 	crash_kexec_wait_realmode(crashing_cpu);
 #endif
 	if (ppc_md.kexec_cpu_down)
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 5fb667a60894..40f524643ba6 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -13,7 +13,7 @@
 
 #include <linux/crash_dump.h>
 #include <linux/bootmem.h>
-#include <linux/lmb.h>
+#include <linux/memblock.h>
 #include <asm/code-patching.h>
 #include <asm/kdump.h>
 #include <asm/prom.h>
@@ -33,7 +33,7 @@ unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
 #ifndef CONFIG_RELOCATABLE
 void __init reserve_kdump_trampoline(void)
 {
-	lmb_reserve(0, KDUMP_RESERVE_LIMIT);
+	memblock_reserve(0, KDUMP_RESERVE_LIMIT);
 }
 
 static void __init create_trampoline(unsigned long addr)
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index e7fe218b8697..02f724f36753 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -71,7 +71,7 @@ static int ppc_swiotlb_bus_notify(struct notifier_block *nb,
 	sd->max_direct_dma_addr = 0;
 
 	/* May need to bounce if the device can't address all of DRAM */
-	if ((dma_get_mask(dev) + 1) < lmb_end_of_DRAM())
+	if ((dma_get_mask(dev) + 1) < memblock_end_of_DRAM())
 		set_dma_ops(dev, &swiotlb_dma_ops);
 
 	return NOTIFY_DONE;
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 8d1de6f31d5a..84d6367ec003 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -9,7 +9,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/dma-debug.h>
 #include <linux/gfp.h>
-#include <linux/lmb.h>
+#include <linux/memblock.h>
 #include <asm/bug.h>
 #include <asm/abs_addr.h>
 
@@ -89,7 +89,7 @@ static int dma_direct_dma_supported(struct device *dev, u64 mask)
 	/* Could be improved so platforms can set the limit in case
 	 * they have limited DMA windows
 	 */
-	return mask >= (lmb_end_of_DRAM() - 1);
+	return mask >= (memblock_end_of_DRAM() - 1);
 #else
 	return 1;
 #endif
diff --git a/arch/powerpc/kernel/fsl_booke_entry_mapping.S b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
index beb4d78a2304..a92c79be2728 100644
--- a/arch/powerpc/kernel/fsl_booke_entry_mapping.S
+++ b/arch/powerpc/kernel/fsl_booke_entry_mapping.S
@@ -205,8 +205,7 @@ next_tlb_setup:
 	bdnz+   next_tlb_setup
 
 /* 7. Jump to our 1:1 mapping */
-	li	r6, 0
-
+	mr	r6, r25
 #else
 	#error You need to specify the mapping or not use this at all.
 #endif
@@ -217,7 +216,6 @@ next_tlb_setup:
 1:	mflr	r9
 	rlwimi	r6,r9,0,20,31
 	addi	r6,r6,(2f - 1b)
-	add	r6, r6, r25
 	mtspr	SPRN_SRR0,r6
 	mtspr	SPRN_SRR1,r7
 	rfi				/* start execution out of TLB1[0] entry */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 2676ef288bf5..60d39b7414c0 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -297,7 +297,10 @@ void fixup_irqs(const struct cpumask *map)
 
 	for_each_irq(irq) {
 		desc = irq_to_desc(irq);
-		if (desc && desc->status & IRQ_PER_CPU)
+		if (!desc)
+			continue;
+
+		if (desc->status & IRQ_PER_CPU)
 			continue;
 
 		cpumask_and(mask, desc->affinity, map);
@@ -319,7 +322,6 @@ void fixup_irqs(const struct cpumask *map)
 }
 #endif
 
-#ifdef CONFIG_IRQSTACKS
 static inline void handle_one_irq(unsigned int irq)
 {
 	struct thread_info *curtp, *irqtp;
@@ -360,12 +362,6 @@ static inline void handle_one_irq(unsigned int irq)
 	if (irqtp->flags)
 		set_bits(irqtp->flags, &curtp->flags);
 }
-#else
-static inline void handle_one_irq(unsigned int irq)
-{
-	generic_handle_irq(irq);
-}
-#endif
 
 static inline void check_stack_overflow(void)
 {
@@ -457,7 +453,6 @@ void exc_lvl_ctx_init(void)
 }
 #endif
 
-#ifdef CONFIG_IRQSTACKS
 struct thread_info *softirq_ctx[NR_CPUS] __read_mostly;
 struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly;
 
@@ -494,10 +489,6 @@ static inline void do_softirq_onstack(void)
 	irqtp->task = NULL;
 }
 
-#else
-#define do_softirq_onstack()	__do_softirq()
-#endif /* CONFIG_IRQSTACKS */
-
 void do_softirq(void)
 {
 	unsigned long flags;
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index bb3d893a8353..89f005116aac 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -12,7 +12,7 @@
 #include <linux/kexec.h>
 #include <linux/reboot.h>
 #include <linux/threads.h>
-#include <linux/lmb.h>
+#include <linux/memblock.h>
 #include <linux/of.h>
 #include <asm/machdep.h>
 #include <asm/prom.h>
@@ -66,11 +66,11 @@ void __init reserve_crashkernel(void)
 	unsigned long long crash_size, crash_base;
 	int ret;
 
-	/* this is necessary because of lmb_phys_mem_size() */
-	lmb_analyze();
+	/* this is necessary because of memblock_phys_mem_size() */
+	memblock_analyze();
 
 	/* use common parsing */
-	ret = parse_crashkernel(boot_command_line, lmb_phys_mem_size(),
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 			&crash_size, &crash_base);
 	if (ret == 0 && crash_size > 0) {
 		crashk_res.start = crash_base;
@@ -133,9 +133,9 @@ void __init reserve_crashkernel(void)
 			"for crashkernel (System RAM: %ldMB)\n",
 			(unsigned long)(crash_size >> 20),
 			(unsigned long)(crashk_res.start >> 20),
-			(unsigned long)(lmb_phys_mem_size() >> 20));
+			(unsigned long)(memblock_phys_mem_size() >> 20));
 
-	lmb_reserve(crashk_res.start, crash_size);
+	memblock_reserve(crashk_res.start, crash_size);
 }
 
 int overlaps_crashkernel(unsigned long start, unsigned long size)
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 26f9900f773c..ed31a29c4ff7 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -182,28 +182,12 @@ static void kexec_prepare_cpus_wait(int wait_state)
 
 	my_cpu = get_cpu();
 	/* Make sure each CPU has atleast made it to the state we need */
-	for (i=0; i < NR_CPUS; i++) {
+	for_each_online_cpu(i) {
 		if (i == my_cpu)
 			continue;
 
 		while (paca[i].kexec_state < wait_state) {
 			barrier();
-			if (!cpu_possible(i)) {
-				printk("kexec: cpu %d hw_cpu_id %d is not"
-						" possible, ignoring\n",
-						i, paca[i].hw_cpu_id);
-				break;
-			}
-			if (!cpu_online(i)) {
-				/* Fixme: this can be spinning in
-				 * pSeries_secondary_wait with a paca
-				 * waiting for it to go online.
-				 */
-				printk("kexec: cpu %d hw_cpu_id %d is not"
-						" online, ignoring\n",
-						i, paca[i].hw_cpu_id);
-				break;
-			}
 			if (i != notified) {
 				printk( "kexec: waiting for cpu %d (physical"
 						" %d) to enter %i state\n",
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index dc66d52dcff5..6bbd7a604d24 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -33,7 +33,6 @@
 
 	.text
 
-#ifdef CONFIG_IRQSTACKS
 _GLOBAL(call_do_softirq)
 	mflr	r0
 	stw	r0,4(r1)
@@ -56,7 +55,6 @@ _GLOBAL(call_handle_irq)
 	lwz	r0,4(r1)
 	mtlr	r0
 	blr
-#endif /* CONFIG_IRQSTACKS */
 
 /*
  * This returns the high 64 bits of the product of two 64-bit numbers.
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index a2b18dffa03e..e5144906a56d 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -28,7 +28,6 @@
 
 	.text
 
-#ifdef CONFIG_IRQSTACKS
 _GLOBAL(call_do_softirq)
 	mflr	r0
 	std	r0,16(r1)
@@ -52,7 +51,6 @@ _GLOBAL(call_handle_irq)
 	ld	r0,16(r1)
 	mtlr	r0
 	blr
-#endif /* CONFIG_IRQSTACKS */
 
 	.section	".toc","aw"
 PPC64_CACHES:
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index f88acf0218db..139a773853f4 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -9,7 +9,7 @@
 
 #include <linux/threads.h>
 #include <linux/module.h>
-#include <linux/lmb.h>
+#include <linux/memblock.h>
 
 #include <asm/firmware.h>
 #include <asm/lppaca.h>
@@ -117,7 +117,7 @@ void __init allocate_pacas(void)
 	 * the first segment. On iSeries they must be within the area mapped
 	 * by the HV, which is HvPagesToMap * HVPAGESIZE bytes.
 	 */
-	limit = min(0x10000000ULL, lmb.rmo_size);
+	limit = min(0x10000000ULL, memblock.rmo_size);
 	if (firmware_has_feature(FW_FEATURE_ISERIES))
 		limit = min(limit, HvPagesToMap * HVPAGESIZE);
 
@@ -128,7 +128,7 @@ void __init allocate_pacas(void)
 
 	paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpus);
 
-	paca = __va(lmb_alloc_base(paca_size, PAGE_SIZE, limit));
+	paca = __va(memblock_alloc_base(paca_size, PAGE_SIZE, limit));
 	memset(paca, 0, paca_size);
 
 	printk(KERN_DEBUG "Allocated %u bytes for %d pacas at %p\n",
@@ -148,7 +148,7 @@ void __init free_unused_pacas(void)
 	if (new_size >= paca_size)
 		return;
 
-	lmb_free(__pa(paca) + new_size, paca_size - new_size);
+	memblock_free(__pa(paca) + new_size, paca_size - new_size);
 
 	printk(KERN_DEBUG "Freed %u bytes for unused pacas\n",
 		paca_size - new_size);
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 43b83c35cf54..5c14ffe51258 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -791,8 +791,11 @@ static void power_pmu_disable(struct perf_event *event)
 	cpuhw = &__get_cpu_var(cpu_hw_events);
 	for (i = 0; i < cpuhw->n_events; ++i) {
 		if (event == cpuhw->event[i]) {
-			while (++i < cpuhw->n_events)
+			while (++i < cpuhw->n_events) {
 				cpuhw->event[i-1] = cpuhw->event[i];
+				cpuhw->events[i-1] = cpuhw->events[i];
+				cpuhw->flags[i-1] = cpuhw->flags[i];
+			}
 			--cpuhw->n_events;
 			ppmu->disable_pmc(event->hw.idx - 1, cpuhw->mmcr);
 			if (event->hw.idx) {
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 9d255b4f0a0e..773424df828a 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1005,7 +1005,6 @@ out:
 	return error;
 }
 
-#ifdef CONFIG_IRQSTACKS
 static inline int valid_irq_stack(unsigned long sp, struct task_struct *p,
 				  unsigned long nbytes)
 {
@@ -1030,10 +1029,6 @@ static inline int valid_irq_stack(unsigned long sp, struct task_struct *p,
 	return 0;
 }
 
-#else
-#define valid_irq_stack(sp, p, nb)	0
-#endif /* CONFIG_IRQSTACKS */
-
 int validate_sp(unsigned long sp, struct task_struct *p,
 		       unsigned long nbytes)
 {
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 05131d634e73..9d3953983fb7 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -31,7 +31,7 @@
 #include <linux/kexec.h>
 #include <linux/debugfs.h>
 #include <linux/irq.h>
-#include <linux/lmb.h>
+#include <linux/memblock.h>
 
 #include <asm/prom.h>
 #include <asm/rtas.h>
@@ -98,7 +98,7 @@ static void __init move_device_tree(void)
 
 	if ((memory_limit && (start + size) > memory_limit) ||
 			overlaps_crashkernel(start, size)) {
-		p = __va(lmb_alloc_base(size, PAGE_SIZE, lmb.rmo_size));
+		p = __va(memblock_alloc_base(size, PAGE_SIZE, memblock.rmo_size));
 		memcpy(p, initial_boot_params, size);
 		initial_boot_params = (struct boot_param_header *)p;
 		DBG("Moved device tree to 0x%p\n", p);
@@ -411,13 +411,13 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 {
 	__be32 *dm, *ls, *usm;
 	unsigned long l, n, flags;
-	u64 base, size, lmb_size;
+	u64 base, size, memblock_size;
 	unsigned int is_kexec_kdump = 0, rngs;
 
-	ls = of_get_flat_dt_prop(node, "ibm,lmb-size", &l);
+	ls = of_get_flat_dt_prop(node, "ibm,memblock-size", &l);
 	if (ls == NULL || l < dt_root_size_cells * sizeof(__be32))
 		return 0;
-	lmb_size = dt_mem_next_cell(dt_root_size_cells, &ls);
+	memblock_size = dt_mem_next_cell(dt_root_size_cells, &ls);
 
 	dm = of_get_flat_dt_prop(node, "ibm,dynamic-memory", &l);
 	if (dm == NULL || l < sizeof(__be32))
@@ -442,11 +442,11 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 		   or if the block is not assigned to this partition (0x8) */
 		if ((flags & 0x80) || !(flags & 0x8))
 			continue;
-		size = lmb_size;
+		size = memblock_size;
 		rngs = 1;
 		if (is_kexec_kdump) {
 			/*
-			 * For each lmb in ibm,dynamic-memory, a corresponding
+			 * For each memblock in ibm,dynamic-memory, a corresponding
 			 * entry in linux,drconf-usable-memory property contains
 			 * a counter 'p' followed by 'p' (base, size) duple.
 			 * Now read the counter from
@@ -469,10 +469,10 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 				if ((base + size) > 0x80000000ul)
 					size = 0x80000000ul - base;
 			}
-			lmb_add(base, size);
+			memblock_add(base, size);
 		} while (--rngs);
 	}
-	lmb_dump_all();
+	memblock_dump_all();
 	return 0;
 }
 #else
@@ -501,14 +501,14 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	}
 #endif
 
-	lmb_add(base, size);
+	memblock_add(base, size);
 
 	memstart_addr = min((u64)memstart_addr, base);
 }
 
 u64 __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 {
-	return lmb_alloc(size, align);
+	return memblock_alloc(size, align);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -534,12 +534,12 @@ static void __init early_reserve_mem(void)
 	/* before we do anything, lets reserve the dt blob */
 	self_base = __pa((unsigned long)initial_boot_params);
 	self_size = initial_boot_params->totalsize;
-	lmb_reserve(self_base, self_size);
+	memblock_reserve(self_base, self_size);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* then reserve the initrd, if any */
 	if (initrd_start && (initrd_end > initrd_start))
-		lmb_reserve(__pa(initrd_start), initrd_end - initrd_start);
+		memblock_reserve(__pa(initrd_start), initrd_end - initrd_start);
 #endif /* CONFIG_BLK_DEV_INITRD */
 
 #ifdef CONFIG_PPC32
@@ -560,7 +560,7 @@ static void __init early_reserve_mem(void)
 			if (base_32 == self_base && size_32 == self_size)
 				continue;
 			DBG("reserving: %x -> %x\n", base_32, size_32);
-			lmb_reserve(base_32, size_32);
+			memblock_reserve(base_32, size_32);
 		}
 		return;
 	}
@@ -571,7 +571,7 @@ static void __init early_reserve_mem(void)
 		if (size == 0)
 			break;
 		DBG("reserving: %llx -> %llx\n", base, size);
-		lmb_reserve(base, size);
+		memblock_reserve(base, size);
 	}
 }
 
@@ -594,7 +594,7 @@ static inline unsigned long phyp_dump_calculate_reserve_size(void)
 		return phyp_dump_info->reserve_bootvar;
 
 	/* divide by 20 to get 5% of value */
-	tmp = lmb_end_of_DRAM();
+	tmp = memblock_end_of_DRAM();
 	do_div(tmp, 20);
 
 	/* round it down in multiples of 256 */
@@ -633,11 +633,11 @@ static void __init phyp_dump_reserve_mem(void)
 	if (phyp_dump_info->phyp_dump_is_active) {
 		/* Reserve *everything* above RMR.Area freed by userland tools*/
 		base = variable_reserve_size;
-		size = lmb_end_of_DRAM() - base;
+		size = memblock_end_of_DRAM() - base;
 
 		/* XXX crashed_ram_end is wrong, since it may be beyond
 		 * the memory_limit, it will need to be adjusted. */
-		lmb_reserve(base, size);
+		memblock_reserve(base, size);
 
 		phyp_dump_info->init_reserve_start = base;
 		phyp_dump_info->init_reserve_size = size;
@@ -645,8 +645,8 @@ static void __init phyp_dump_reserve_mem(void)
 		size = phyp_dump_info->cpu_state_size +
 			phyp_dump_info->hpte_region_size +
 			variable_reserve_size;
-		base = lmb_end_of_DRAM() - size;
-		lmb_reserve(base, size);
+		base = memblock_end_of_DRAM() - size;
+		memblock_reserve(base, size);
 		phyp_dump_info->init_reserve_start = base;
 		phyp_dump_info->init_reserve_size = size;
 	}
@@ -681,8 +681,8 @@ void __init early_init_devtree(void *params)
 	 */
 	of_scan_flat_dt(early_init_dt_scan_chosen, NULL);
 
-	/* Scan memory nodes and rebuild LMBs */
-	lmb_init();
+	/* Scan memory nodes and rebuild MEMBLOCKs */
+	memblock_init();
 	of_scan_flat_dt(early_init_dt_scan_root, NULL);
 	of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL);
 
@@ -690,11 +690,11 @@ void __init early_init_devtree(void *params)
 	strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE);
 	parse_early_param();
 
-	/* Reserve LMB regions used by kernel, initrd, dt, etc... */
-	lmb_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START);
+	/* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */
+	memblock_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START);
 	/* If relocatable, reserve first 32k for interrupt vectors etc. */
 	if (PHYSICAL_START > MEMORY_START)
-		lmb_reserve(MEMORY_START, 0x8000);
+		memblock_reserve(MEMORY_START, 0x8000);
 	reserve_kdump_trampoline();
 	reserve_crashkernel();
 	early_reserve_mem();
@@ -706,17 +706,17 @@ void __init early_init_devtree(void *params)
 
 		/* Ensure that total memory size is page-aligned, because
 		 * otherwise mark_bootmem() gets upset. */
-		lmb_analyze();
-		memsize = lmb_phys_mem_size();
+		memblock_analyze();
+		memsize = memblock_phys_mem_size();
 		if ((memsize & PAGE_MASK) != memsize)
 			limit = memsize & PAGE_MASK;
 	}
-	lmb_enforce_memory_limit(limit);
+	memblock_enforce_memory_limit(limit);
 
-	lmb_analyze();
-	lmb_dump_all();
+	memblock_analyze();
+	memblock_dump_all();
 
-	DBG("Phys. mem: %llx\n", lmb_phys_mem_size());
+	DBG("Phys. mem: %llx\n", memblock_phys_mem_size());
 
 	/* We may need to relocate the flat tree, do it now.
 	 * FIXME .. and the initrd too? */
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 97d4bd9442d3..3b6f8ae9b8cc 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -872,7 +872,7 @@ static void __init prom_send_capabilities(void)
 				    "ibm_architecture_vec structure inconsistent: 0x%x !\n",
 				    *cores);
 		} else {
-			*cores = NR_CPUS / prom_count_smt_threads();
+			*cores = DIV_ROUND_UP(NR_CPUS, prom_count_smt_threads());
 			prom_printf("Max number of cores passed to firmware: 0x%x\n",
 				    (unsigned long)*cores);
 		}
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index 1ac136b128f0..9f82f4937892 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -52,12 +52,18 @@ do
 	if [ "${UNDEF:0:9}" = "_restgpr_" ]; then
 		OK=1
 	fi
+	if [ "${UNDEF:0:10}" = "_restgpr0_" ]; then
+		OK=1
+	fi
 	if [ "${UNDEF:0:11}" = "_rest32gpr_" ]; then
 		OK=1
 	fi
 	if [ "${UNDEF:0:9}" = "_savegpr_" ]; then
 		OK=1
 	fi
+	if [ "${UNDEF:0:10}" = "_savegpr0_" ]; then
+		OK=1
+	fi
 	if [ "${UNDEF:0:11}" = "_save32gpr_" ]; then
 		OK=1
 	fi
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 0e1ec6f746f6..d0516dbee762 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -22,7 +22,7 @@
 #include <linux/smp.h>
 #include <linux/completion.h>
 #include <linux/cpumask.h>
-#include <linux/lmb.h>
+#include <linux/memblock.h>
 #include <linux/slab.h>
 
 #include <asm/prom.h>
@@ -934,11 +934,11 @@ void __init rtas_initialize(void)
 	 */
 #ifdef CONFIG_PPC64
 	if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR)) {
-		rtas_region = min(lmb.rmo_size, RTAS_INSTANTIATE_MAX);
+		rtas_region = min(memblock.rmo_size, RTAS_INSTANTIATE_MAX);
 		ibm_suspend_me_token = rtas_token("ibm,suspend-me");
 	}
 #endif
-	rtas_rmo_buf = lmb_alloc_base(RTAS_RMOBUF_MAX, PAGE_SIZE, rtas_region);
+	rtas_rmo_buf = memblock_alloc_base(RTAS_RMOBUF_MAX, PAGE_SIZE, rtas_region);
 
 #ifdef CONFIG_RTAS_ERROR_LOGGING
 	rtas_last_error_token = rtas_token("rtas-last-error");
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index bfc2abafac44..67a84d8f118d 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -94,12 +94,8 @@ struct flash_block_list {
 	struct flash_block_list *next;
 	struct flash_block blocks[FLASH_BLOCKS_PER_NODE];
 };
-struct flash_block_list_header { /* just the header of flash_block_list */
-	unsigned long num_blocks;
-	struct flash_block_list *next;
-};
 
-static struct flash_block_list_header rtas_firmware_flash_list = {0, NULL};
+static struct flash_block_list *rtas_firmware_flash_list;
 
 /* Use slab cache to guarantee 4k alignment */
 static struct kmem_cache *flash_block_cache = NULL;
@@ -108,13 +104,14 @@ static struct kmem_cache *flash_block_cache = NULL;
 
 /* Local copy of the flash block list.
  * We only allow one open of the flash proc file and create this
- * list as we go.  This list will be put in the
- * rtas_firmware_flash_list var once it is fully read.
+ * list as we go.  The rtas_firmware_flash_list varable will be
+ * set once the data is fully read.
  *
  * For convenience as we build the list we use virtual addrs,
  * we do not fill in the version number, and the length field
  * is treated as the number of entries currently in the block
- * (i.e. not a byte count).  This is all fixed on release.
+ * (i.e. not a byte count).  This is all fixed when calling 
+ * the flash routine.
  */
 
 /* Status int must be first member of struct */
@@ -201,16 +198,16 @@ static int rtas_flash_release(struct inode *inode, struct file *file)
 	if (uf->flist) {    
 		/* File was opened in write mode for a new flash attempt */
 		/* Clear saved list */
-		if (rtas_firmware_flash_list.next) {
-			free_flash_list(rtas_firmware_flash_list.next);
-			rtas_firmware_flash_list.next = NULL;
+		if (rtas_firmware_flash_list) {
+			free_flash_list(rtas_firmware_flash_list);
+			rtas_firmware_flash_list = NULL;
 		}
 
 		if (uf->status != FLASH_AUTH)  
 			uf->status = flash_list_valid(uf->flist);
 
 		if (uf->status == FLASH_IMG_READY) 
-			rtas_firmware_flash_list.next = uf->flist;
+			rtas_firmware_flash_list = uf->flist;
 		else
 			free_flash_list(uf->flist);
 
@@ -593,7 +590,7 @@ static void rtas_flash_firmware(int reboot_type)
 	unsigned long rtas_block_list;
 	int i, status, update_token;
 
-	if (rtas_firmware_flash_list.next == NULL)
+	if (rtas_firmware_flash_list == NULL)
 		return;		/* nothing to do */
 
 	if (reboot_type != SYS_RESTART) {
@@ -610,20 +607,25 @@ static void rtas_flash_firmware(int reboot_type)
 		return;
 	}
 
-	/* NOTE: the "first" block list is a global var with no data
-	 * blocks in the kernel data segment.  We do this because
-	 * we want to ensure this block_list addr is under 4GB.
+	/*
+	 * NOTE: the "first" block must be under 4GB, so we create
+	 * an entry with no data blocks in the reserved buffer in
+	 * the kernel data segment.
 	 */
-	rtas_firmware_flash_list.num_blocks = 0;
-	flist = (struct flash_block_list *)&rtas_firmware_flash_list;
+	spin_lock(&rtas_data_buf_lock);
+	flist = (struct flash_block_list *)&rtas_data_buf[0];
+	flist->num_blocks = 0;
+	flist->next = rtas_firmware_flash_list;
 	rtas_block_list = virt_to_abs(flist);
 	if (rtas_block_list >= 4UL*1024*1024*1024) {
 		printk(KERN_ALERT "FLASH: kernel bug...flash list header addr above 4GB\n");
+		spin_unlock(&rtas_data_buf_lock);
 		return;
 	}
 
 	printk(KERN_ALERT "FLASH: preparing saved firmware image for flash\n");
 	/* Update the block_list in place. */
+	rtas_firmware_flash_list = NULL; /* too hard to backout on error */
 	image_size = 0;
 	for (f = flist; f; f = next) {
 		/* Translate data addrs to absolute */
@@ -664,6 +666,7 @@ static void rtas_flash_firmware(int reboot_type)
 		printk(KERN_ALERT "FLASH: unknown flash return code %d\n", status);
 		break;
 	}
+	spin_unlock(&rtas_data_buf_lock);
 }
 
 static void remove_flash_pde(struct proc_dir_entry *dp)
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 5e4d852f640c..b7e6c7e193ae 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -33,7 +33,7 @@
 #include <linux/serial_8250.h>
 #include <linux/debugfs.h>
 #include <linux/percpu.h>
-#include <linux/lmb.h>
+#include <linux/memblock.h>
 #include <linux/of_platform.h>
 #include <asm/io.h>
 #include <asm/paca.h>
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 8f58986c2ad9..a10ffc85ada7 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -16,7 +16,7 @@
 #include <linux/root_dev.h>
 #include <linux/cpu.h>
 #include <linux/console.h>
-#include <linux/lmb.h>
+#include <linux/memblock.h>
 
 #include <asm/io.h>
 #include <asm/prom.h>
@@ -241,23 +241,19 @@ int __init ppc_init(void)
 
 arch_initcall(ppc_init);
 
-#ifdef CONFIG_IRQSTACKS
 static void __init irqstack_early_init(void)
 {
 	unsigned int i;
 
 	/* interrupt stacks must be in lowmem, we get that for free on ppc32
-	 * as the lmb is limited to lowmem by LMB_REAL_LIMIT */
+	 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */
 	for_each_possible_cpu(i) {
 		softirq_ctx[i] = (struct thread_info *)
-			__va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
 		hardirq_ctx[i] = (struct thread_info *)
-			__va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
 	}
 }
-#else
-#define irqstack_early_init()
-#endif
 
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
 static void __init exc_lvl_early_init(void)
@@ -265,15 +261,15 @@ static void __init exc_lvl_early_init(void)
 	unsigned int i;
 
 	/* interrupt stacks must be in lowmem, we get that for free on ppc32
-	 * as the lmb is limited to lowmem by LMB_REAL_LIMIT */
+	 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */
 	for_each_possible_cpu(i) {
 		critirq_ctx[i] = (struct thread_info *)
-			__va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
 #ifdef CONFIG_BOOKE
 		dbgirq_ctx[i] = (struct thread_info *)
-			__va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
 		mcheckirq_ctx[i] = (struct thread_info *)
-			__va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
 #endif
 	}
 }
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index f3fb5a79de52..d135f93cb0f6 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -34,7 +34,7 @@
 #include <linux/bootmem.h>
 #include <linux/pci.h>
 #include <linux/lockdep.h>
-#include <linux/lmb.h>
+#include <linux/memblock.h>
 #include <asm/io.h>
 #include <asm/kdump.h>
 #include <asm/prom.h>
@@ -158,7 +158,7 @@ static void __init setup_paca(struct paca_struct *new_paca)
  * the CPU that ignores the top 2 bits of the address in real
  * mode so we can access kernel globals normally provided we
  * only toy with things in the RMO region. From here, we do
- * some early parsing of the device-tree to setup out LMB
+ * some early parsing of the device-tree to setup out MEMBLOCK
  * data structures, and allocate & initialize the hash table
  * and segment tables so we can start running with translation
  * enabled.
@@ -404,7 +404,7 @@ void __init setup_system(void)
 
 	printk("-----------------------------------------------------\n");
 	printk("ppc64_pft_size                = 0x%llx\n", ppc64_pft_size);
-	printk("physicalMemorySize            = 0x%llx\n", lmb_phys_mem_size());
+	printk("physicalMemorySize            = 0x%llx\n", memblock_phys_mem_size());
 	if (ppc64_caches.dline_size != 0x80)
 		printk("ppc64_caches.dcache_line_size = 0x%x\n",
 		       ppc64_caches.dline_size);
@@ -432,7 +432,6 @@ static u64 slb0_limit(void)
 	return 1UL << SID_SHIFT;
 }
 
-#ifdef CONFIG_IRQSTACKS
 static void __init irqstack_early_init(void)
 {
 	u64 limit = slb0_limit();
@@ -444,16 +443,13 @@ static void __init irqstack_early_init(void)
 	 */
 	for_each_possible_cpu(i) {
 		softirq_ctx[i] = (struct thread_info *)
-			__va(lmb_alloc_base(THREAD_SIZE,
+			__va(memblock_alloc_base(THREAD_SIZE,
 					    THREAD_SIZE, limit));
 		hardirq_ctx[i] = (struct thread_info *)
-			__va(lmb_alloc_base(THREAD_SIZE,
+			__va(memblock_alloc_base(THREAD_SIZE,
 					    THREAD_SIZE, limit));
 	}
 }
-#else
-#define irqstack_early_init()
-#endif
 
 #ifdef CONFIG_PPC_BOOK3E
 static void __init exc_lvl_early_init(void)
@@ -462,11 +458,11 @@ static void __init exc_lvl_early_init(void)
 
 	for_each_possible_cpu(i) {
 		critirq_ctx[i] = (struct thread_info *)
-			__va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
 		dbgirq_ctx[i] = (struct thread_info *)
-			__va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
 		mcheckirq_ctx[i] = (struct thread_info *)
-			__va(lmb_alloc(THREAD_SIZE, THREAD_SIZE));
+			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
 	}
 }
 #else
@@ -491,11 +487,11 @@ static void __init emergency_stack_init(void)
 	 * bringup, we need to get at them in real mode. This means they
 	 * must also be within the RMO region.
 	 */
-	limit = min(slb0_limit(), lmb.rmo_size);
+	limit = min(slb0_limit(), memblock.rmo_size);
 
 	for_each_possible_cpu(i) {
 		unsigned long sp;
-		sp  = lmb_alloc_base(THREAD_SIZE, THREAD_SIZE, limit);
+		sp  = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit);
 		sp += THREAD_SIZE;
 		paca[i].emergency_sp = __va(sp);
 	}
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index d84d19224a95..13002fe206e7 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -22,7 +22,7 @@
 #include <linux/elf.h>
 #include <linux/security.h>
 #include <linux/bootmem.h>
-#include <linux/lmb.h>
+#include <linux/memblock.h>
 
 #include <asm/pgtable.h>
 #include <asm/system.h>
@@ -734,7 +734,7 @@ static int __init vdso_init(void)
 	vdso_data->platform = machine_is(iseries) ? 0x200 : 0x100;
 	if (firmware_has_feature(FW_FEATURE_LPAR))
 		vdso_data->platform |= 1;
-	vdso_data->physicalMemorySize = lmb_phys_mem_size();
+	vdso_data->physicalMemorySize = memblock_phys_mem_size();
 	vdso_data->dcache_size = ppc64_caches.dsize;
 	vdso_data->dcache_line_size = ppc64_caches.dline_size;
 	vdso_data->icache_size = ppc64_caches.isize;