Merge branch 'topic/paca' into next

Bring in yet another series that touches KVM code, and might need to
be merged into the kvm-ppc branch to resolve conflicts.

This required some changes in pnv_power9_force_smt4_catch/release()
due to the paca array becomming an array of pointers.

44 files changed, 552 insertions, 364 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 935adcd92a81..cc8cd656ccfe 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -212,7 +212,7 @@ extern int __meminit hash__vmemmap_create_mapping(unsigned long start,
 extern void hash__vmemmap_remove_mapping(unsigned long start,
 				     unsigned long page_size);
 
-int hash__create_section_mapping(unsigned long start, unsigned long end);
+int hash__create_section_mapping(unsigned long start, unsigned long end, int nid);
 int hash__remove_section_mapping(unsigned long start, unsigned long end);
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 365010f66570..705193e7192f 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -313,7 +313,7 @@ static inline unsigned long radix__get_tree_size(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int radix__create_section_mapping(unsigned long start, unsigned long end);
+int radix__create_section_mapping(unsigned long start, unsigned long end, int nid);
 int radix__remove_section_mapping(unsigned long start, unsigned long end);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 #endif /* __ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 7765a800ddae..b7d066b037da 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -436,15 +436,15 @@ struct openpic;
 extern void kvm_cma_reserve(void) __init;
 static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 {
-	paca[cpu].kvm_hstate.xics_phys = (void __iomem *)addr;
+	paca_ptrs[cpu]->kvm_hstate.xics_phys = (void __iomem *)addr;
 }
 
 static inline void kvmppc_set_xive_tima(int cpu,
 					unsigned long phys_addr,
 					void __iomem *virt_addr)
 {
-	paca[cpu].kvm_hstate.xive_tima_phys = (void __iomem *)phys_addr;
-	paca[cpu].kvm_hstate.xive_tima_virt = virt_addr;
+	paca_ptrs[cpu]->kvm_hstate.xive_tima_phys = (void __iomem *)phys_addr;
+	paca_ptrs[cpu]->kvm_hstate.xive_tima_virt = virt_addr;
 }
 
 static inline u32 kvmppc_get_xics_latch(void)
@@ -458,7 +458,7 @@ static inline u32 kvmppc_get_xics_latch(void)
 
 static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi)
 {
-	paca[cpu].kvm_hstate.host_ipi = host_ipi;
+	paca_ptrs[cpu]->kvm_hstate.host_ipi = host_ipi;
 }
 
 static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index d0a2a2f99564..65d589689f01 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -36,14 +36,16 @@
 #include <asm/mmu.h>
 
 /*
- * We only have to have statically allocated lppaca structs on
- * legacy iSeries, which supports at most 64 cpus.
- */
-#define NR_LPPACAS	1
-
-/*
- * The Hypervisor barfs if the lppaca crosses a page boundary.  A 1k
- * alignment is sufficient to prevent this
+ * The lppaca is the "virtual processor area" registered with the hypervisor,
+ * H_REGISTER_VPA etc.
+ *
+ * According to PAPR, the structure is 640 bytes long, must be L1 cache line
+ * aligned, and must not cross a 4kB boundary. Its size field must be at
+ * least 640 bytes (but may be more).
+ *
+ * Pre-v4.14 KVM hypervisors reject the VPA if its size field is smaller than
+ * 1kB, so we dynamically allocate 1kB and advertise size as 1kB, but keep
+ * this structure as the canonical 640 byte size.
  */
 struct lppaca {
 	/* cacheline 1 contains read-only data */
@@ -97,13 +99,11 @@ struct lppaca {
 
 	__be32	page_ins;		/* CMO Hint - # page ins by OS */
 	u8	reserved11[148];
-	volatile __be64 dtl_idx;		/* Dispatch Trace Log head index */
+	volatile __be64 dtl_idx;	/* Dispatch Trace Log head index */
 	u8	reserved12[96];
-} __attribute__((__aligned__(0x400)));
-
-extern struct lppaca lppaca[];
+} ____cacheline_aligned;
 
-#define lppaca_of(cpu)	(*paca[cpu].lppaca_ptr)
+#define lppaca_of(cpu)	(*paca_ptrs[cpu]->lppaca_ptr)
 
 /*
  * We are using a non architected field to determine if a partition is
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index c97b41185ab7..4185f1c96125 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -47,7 +47,10 @@ extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */
 #define get_paca()	local_paca
 #endif
 
+#ifdef CONFIG_PPC_PSERIES
 #define get_lppaca()	(get_paca()->lppaca_ptr)
+#endif
+
 #define get_slb_shadow()	(get_paca()->slb_shadow_ptr)
 
 struct task_struct;
@@ -59,7 +62,7 @@ struct task_struct;
  * processor.
  */
 struct paca_struct {
-#ifdef CONFIG_PPC_BOOK3S
+#ifdef CONFIG_PPC_PSERIES
 	/*
 	 * Because hw_cpu_id, unlike other paca fields, is accessed
 	 * routinely from other CPUs (from the IRQ code), we stick to
@@ -68,7 +71,8 @@ struct paca_struct {
 	 */
 
 	struct lppaca *lppaca_ptr;	/* Pointer to LpPaca for PLIC */
-#endif /* CONFIG_PPC_BOOK3S */
+#endif /* CONFIG_PPC_PSERIES */
+
 	/*
 	 * MAGIC: the spinlock functions in arch/powerpc/lib/locks.c 
 	 * load lock_token and paca_index with a single lwz
@@ -161,10 +165,14 @@ struct paca_struct {
 	u64 saved_msr;			/* MSR saved here by enter_rtas */
 	u16 trap_save;			/* Used when bad stack is encountered */
 	u8 irq_soft_mask;		/* mask for irq soft masking */
+	u8 soft_enabled;		/* irq soft-enable flag */
 	u8 irq_happened;		/* irq happened while soft-disabled */
 	u8 io_sync;			/* writel() needs spin_unlock sync */
 	u8 irq_work_pending;		/* IRQ_WORK interrupt while soft-disable */
 	u8 nap_state_lost;		/* NV GPR values lost in power7_idle */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	u8 pmcregs_in_use;		/* pseries puts this in lppaca */
+#endif
 	u64 sprg_vdso;			/* Saved user-visible sprg */
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	u64 tm_scratch;                 /* TM scratch area for reclaim */
@@ -244,18 +252,20 @@ struct paca_struct {
 	void *rfi_flush_fallback_area;
 	u64 l1d_flush_size;
 #endif
-};
+} ____cacheline_aligned;
 
 extern void copy_mm_to_paca(struct mm_struct *mm);
-extern struct paca_struct *paca;
+extern struct paca_struct **paca_ptrs;
 extern void initialise_paca(struct paca_struct *new_paca, int cpu);
 extern void setup_paca(struct paca_struct *new_paca);
-extern void allocate_pacas(void);
+extern void allocate_paca_ptrs(void);
+extern void allocate_paca(int cpu);
 extern void free_unused_pacas(void);
 
 #else /* CONFIG_PPC64 */
 
-static inline void allocate_pacas(void) { };
+static inline void allocate_paca_ptrs(void) { };
+static inline void allocate_paca(int cpu) { };
 static inline void free_unused_pacas(void) { };
 
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/include/asm/pmc.h b/arch/powerpc/include/asm/pmc.h
index 5a9ede4962cb..7ac3586c38ab 100644
--- a/arch/powerpc/include/asm/pmc.h
+++ b/arch/powerpc/include/asm/pmc.h
@@ -31,10 +31,21 @@ void ppc_enable_pmcs(void);
 
 #ifdef CONFIG_PPC_BOOK3S_64
 #include <asm/lppaca.h>
+#include <asm/firmware.h>
 
 static inline void ppc_set_pmu_inuse(int inuse)
 {
-	get_lppaca()->pmcregs_in_use = inuse;
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE)
+	if (firmware_has_feature(FW_FEATURE_LPAR)) {
+#ifdef CONFIG_PPC_PSERIES
+		get_lppaca()->pmcregs_in_use = inuse;
+#endif
+	} else {
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+		get_paca()->pmcregs_in_use = inuse;
+#endif
+	}
+#endif
 }
 
 extern void power4_enable_pmcs(void);
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index bbcdf929be54..27fa52ed6d00 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -23,6 +23,7 @@ extern void reloc_got2(unsigned long);
 #define PTRRELOC(x)	((typeof(x)) add_reloc_offset((unsigned long)(x)))
 
 void check_for_initrd(void);
+void mem_topology_setup(void);
 void initmem_init(void);
 void setup_panic(void);
 #define ARCH_PANIC_TIMEOUT 180
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index fac963e10d39..cfecfee1194b 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -31,6 +31,7 @@
 
 extern int boot_cpuid;
 extern int spinning_secondaries;
+extern u32 *cpu_to_phys_id;
 
 extern void cpu_die(void);
 extern int cpu_to_chip_id(int cpu);
@@ -170,12 +171,12 @@ static inline const struct cpumask *cpu_sibling_mask(int cpu)
 #ifdef CONFIG_PPC64
 static inline int get_hard_smp_processor_id(int cpu)
 {
-	return paca[cpu].hw_cpu_id;
+	return paca_ptrs[cpu]->hw_cpu_id;
 }
 
 static inline void set_hard_smp_processor_id(int cpu, int phys)
 {
-	paca[cpu].hw_cpu_id = phys;
+	paca_ptrs[cpu]->hw_cpu_id = phys;
 }
 #else
 /* 32-bit */
diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h
index a7916ee6dfb6..bc66712bdc3c 100644
--- a/arch/powerpc/include/asm/sparsemem.h
+++ b/arch/powerpc/include/asm/sparsemem.h
@@ -17,7 +17,7 @@
 #endif /* CONFIG_SPARSEMEM */
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-extern int create_section_mapping(unsigned long start, unsigned long end);
+extern int create_section_mapping(unsigned long start, unsigned long end, int nid);
 extern int remove_section_mapping(unsigned long start, unsigned long end);
 
 #ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index daf809a9b88e..6bee65f3cfd3 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -221,12 +221,17 @@ int main(void)
 	OFFSET(PACA_EXMC, paca_struct, exmc);
 	OFFSET(PACA_EXSLB, paca_struct, exslb);
 	OFFSET(PACA_EXNMI, paca_struct, exnmi);
+#ifdef CONFIG_PPC_PSERIES
 	OFFSET(PACALPPACAPTR, paca_struct, lppaca_ptr);
+#endif
 	OFFSET(PACA_SLBSHADOWPTR, paca_struct, slb_shadow_ptr);
 	OFFSET(SLBSHADOW_STACKVSID, slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid);
 	OFFSET(SLBSHADOW_STACKESID, slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid);
 	OFFSET(SLBSHADOW_SAVEAREA, slb_shadow, save_area);
 	OFFSET(LPPACA_PMCINUSE, lppaca, pmcregs_in_use);
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	OFFSET(PACA_PMCINUSE, paca_struct, pmcregs_in_use);
+#endif
 	OFFSET(LPPACA_DTLIDX, lppaca, dtl_idx);
 	OFFSET(LPPACA_YIELDCOUNT, lppaca, yield_count);
 	OFFSET(PACA_DTL_RIDX, paca_struct, dtl_ridx);
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 00b215125d3e..17c8b99680f2 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -238,7 +238,7 @@ static void __maybe_unused crash_kexec_wait_realmode(int cpu)
 		if (i == cpu)
 			continue;
 
-		while (paca[i].kexec_state < KEXEC_STATE_REAL_MODE) {
+		while (paca_ptrs[i]->kexec_state < KEXEC_STATE_REAL_MODE) {
 			barrier();
 			if (!cpu_possible(i) || !cpu_online(i) || (msecs <= 0))
 				break;
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index a61151a6ea5e..6eca15f25c73 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -392,19 +392,20 @@ generic_secondary_common_init:
 	 * physical cpu id in r24, we need to search the pacas to find
 	 * which logical id maps to our physical one.
 	 */
-	LOAD_REG_ADDR(r13, paca)	/* Load paca pointer		 */
-	ld	r13,0(r13)		/* Get base vaddr of paca array	 */
 #ifndef CONFIG_SMP
-	addi	r13,r13,PACA_SIZE	/* know r13 if used accidentally */
 	b	kexec_wait		/* wait for next kernel if !SMP	 */
 #else
+	LOAD_REG_ADDR(r8, paca_ptrs)	/* Load paca_ptrs pointe	 */
+	ld	r8,0(r8)		/* Get base vaddr of array	 */
 	LOAD_REG_ADDR(r7, nr_cpu_ids)	/* Load nr_cpu_ids address       */
 	lwz	r7,0(r7)		/* also the max paca allocated 	 */
 	li	r5,0			/* logical cpu id                */
-1:	lhz	r6,PACAHWCPUID(r13)	/* Load HW procid from paca      */
+1:
+	sldi	r9,r5,3			/* get paca_ptrs[] index from cpu id */
+	ldx	r13,r9,r8		/* r13 = paca_ptrs[cpu id]       */
+	lhz	r6,PACAHWCPUID(r13)	/* Load HW procid from paca      */
 	cmpw	r6,r24			/* Compare to our id             */
 	beq	2f
-	addi	r13,r13,PACA_SIZE	/* Loop to next PACA on miss     */
 	addi	r5,r5,1
 	cmpw	r5,r7			/* Check if more pacas exist     */
 	blt	1b
@@ -756,10 +757,10 @@ _GLOBAL(pmac_secondary_start)
 	mtmsrd	r3			/* RI on */
 
 	/* Set up a paca value for this processor. */
-	LOAD_REG_ADDR(r4,paca)		/* Load paca pointer		*/
-	ld	r4,0(r4)		/* Get base vaddr of paca array	*/
-	mulli	r13,r24,PACA_SIZE	/* Calculate vaddr of right paca */
-	add	r13,r13,r4		/* for this processor.		*/
+	LOAD_REG_ADDR(r4,paca_ptrs)	/* Load paca pointer		*/
+	ld	r4,0(r4)		/* Get base vaddr of paca_ptrs array */
+	sldi	r5,r24,3		/* get paca_ptrs[] index from cpu id */
+	ldx	r13,r5,r4		/* r13 = paca_ptrs[cpu id]       */
 	SET_PACA(r13)			/* Save vaddr of paca in an SPRG*/
 
 	/* Mark interrupts soft and hard disabled (they might be enabled
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 49d34d7271e7..1044bf15d5ed 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -168,24 +168,25 @@ static void kexec_prepare_cpus_wait(int wait_state)
 	 * are correctly onlined.  If somehow we start a CPU on boot with RTAS
 	 * start-cpu, but somehow that CPU doesn't write callin_cpu_map[] in
 	 * time, the boot CPU will timeout.  If it does eventually execute
-	 * stuff, the secondary will start up (paca[].cpu_start was written) and
-	 * get into a peculiar state.  If the platform supports
-	 * smp_ops->take_timebase(), the secondary CPU will probably be spinning
-	 * in there.  If not (i.e. pseries), the secondary will continue on and
-	 * try to online itself/idle/etc. If it survives that, we need to find
-	 * these possible-but-not-online-but-should-be CPUs and chaperone them
-	 * into kexec_smp_wait().
+	 * stuff, the secondary will start up (paca_ptrs[]->cpu_start was
+	 * written) and get into a peculiar state.
+	 * If the platform supports smp_ops->take_timebase(), the secondary CPU
+	 * will probably be spinning in there.  If not (i.e. pseries), the
+	 * secondary will continue on and try to online itself/idle/etc. If it
+	 * survives that, we need to find these
+	 * possible-but-not-online-but-should-be CPUs and chaperone them into
+	 * kexec_smp_wait().
 	 */
 	for_each_online_cpu(i) {
 		if (i == my_cpu)
 			continue;
 
-		while (paca[i].kexec_state < wait_state) {
+		while (paca_ptrs[i]->kexec_state < wait_state) {
 			barrier();
 			if (i != notified) {
 				printk(KERN_INFO "kexec: waiting for cpu %d "
 				       "(physical %d) to enter %i state\n",
-				       i, paca[i].hw_cpu_id, wait_state);
+				       i, paca_ptrs[i]->hw_cpu_id, wait_state);
 				notified = i;
 			}
 		}
@@ -322,18 +323,24 @@ void default_machine_kexec(struct kimage *image)
 	kexec_stack.thread_info.cpu = current_thread_info()->cpu;
 
 	/* We need a static PACA, too; copy this CPU's PACA over and switch to
-	 * it.  Also poison per_cpu_offset to catch anyone using non-static
-	 * data.
+	 * it. Also poison per_cpu_offset and NULL lppaca to catch anyone using
+	 * non-static data.
 	 */
 	memcpy(&kexec_paca, get_paca(), sizeof(struct paca_struct));
 	kexec_paca.data_offset = 0xedeaddeadeeeeeeeUL;
-	paca = (struct paca_struct *)RELOC_HIDE(&kexec_paca, 0) -
-		kexec_paca.paca_index;
+#ifdef CONFIG_PPC_PSERIES
+	kexec_paca.lppaca_ptr = NULL;
+#endif
+	paca_ptrs[kexec_paca.paca_index] = &kexec_paca;
+
 	setup_paca(&kexec_paca);
 
-	/* XXX: If anyone does 'dynamic lppacas' this will also need to be
-	 * switched to a static version!
+	/*
+	 * The lppaca should be unregistered at this point so the HV won't
+	 * touch it. In the case of a crash, none of the lppacas are
+	 * unregistered so there is not much we can do about it here.
 	 */
+
 	/*
 	 * On Book3S, the copy must happen with the MMU off if we are either
 	 * using Radix page tables or we are not in an LPAR since we can
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 2fd563d05831..0ee3e6d50f28 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -20,116 +20,105 @@
 
 #include "setup.h"
 
-#ifdef CONFIG_PPC_BOOK3S
+#ifndef CONFIG_SMP
+#define boot_cpuid 0
+#endif
+
+static void *__init alloc_paca_data(unsigned long size, unsigned long align,
+				unsigned long limit, int cpu)
+{
+	unsigned long pa;
+	int nid;
+
+	/*
+	 * boot_cpuid paca is allocated very early before cpu_to_node is up.
+	 * Set bottom-up mode, because the boot CPU should be on node-0,
+	 * which will put its paca in the right place.
+	 */
+	if (cpu == boot_cpuid) {
+		nid = -1;
+		memblock_set_bottom_up(true);
+	} else {
+		nid = early_cpu_to_node(cpu);
+	}
+
+	pa = memblock_alloc_base_nid(size, align, limit, nid, MEMBLOCK_NONE);
+	if (!pa) {
+		pa = memblock_alloc_base(size, align, limit);
+		if (!pa)
+			panic("cannot allocate paca data");
+	}
+
+	if (cpu == boot_cpuid)
+		memblock_set_bottom_up(false);
+
+	return __va(pa);
+}
+
+#ifdef CONFIG_PPC_PSERIES
 
 /*
- * The structure which the hypervisor knows about - this structure
- * should not cross a page boundary.  The vpa_init/register_vpa call
- * is now known to fail if the lppaca structure crosses a page
- * boundary.  The lppaca is also used on POWER5 pSeries boxes.
- * The lppaca is 640 bytes long, and cannot readily
- * change since the hypervisor knows its layout, so a 1kB alignment
- * will suffice to ensure that it doesn't cross a page boundary.
+ * See asm/lppaca.h for more detail.
+ *
+ * lppaca structures must must be 1kB in size, L1 cache line aligned,
+ * and not cross 4kB boundary. A 1kB size and 1kB alignment will satisfy
+ * these requirements.
  */
-struct lppaca lppaca[] = {
-	[0 ... (NR_LPPACAS-1)] = {
+static inline void init_lppaca(struct lppaca *lppaca)
+{
+	BUILD_BUG_ON(sizeof(struct lppaca) != 640);
+
+	*lppaca = (struct lppaca) {
 		.desc = cpu_to_be32(0xd397d781),	/* "LpPa" */
-		.size = cpu_to_be16(sizeof(struct lppaca)),
+		.size = cpu_to_be16(0x400),
 		.fpregs_in_use = 1,
 		.slb_count = cpu_to_be16(64),
 		.vmxregs_in_use = 0,
-		.page_ins = 0,
-	},
+		.page_ins = 0, };
 };
 
-static struct lppaca *extra_lppacas;
-static long __initdata lppaca_size;
-
-static void __init allocate_lppacas(int nr_cpus, unsigned long limit)
-{
-	if (nr_cpus <= NR_LPPACAS)
-		return;
-
-	lppaca_size = PAGE_ALIGN(sizeof(struct lppaca) *
-				 (nr_cpus - NR_LPPACAS));
-	extra_lppacas = __va(memblock_alloc_base(lppaca_size,
-						 PAGE_SIZE, limit));
-}
-
-static struct lppaca * __init new_lppaca(int cpu)
+static struct lppaca * __init new_lppaca(int cpu, unsigned long limit)
 {
 	struct lppaca *lp;
+	size_t size = 0x400;
 
-	if (cpu < NR_LPPACAS)
-		return &lppaca[cpu];
+	BUILD_BUG_ON(size < sizeof(struct lppaca));
+
+	if (early_cpu_has_feature(CPU_FTR_HVMODE))
+		return NULL;
 
-	lp = extra_lppacas + (cpu - NR_LPPACAS);
-	*lp = lppaca[0];
+	lp = alloc_paca_data(size, 0x400, limit, cpu);
+	init_lppaca(lp);
 
 	return lp;
 }
-
-static void __init free_lppacas(void)
-{
-	long new_size = 0, nr;
-
-	if (!lppaca_size)
-		return;
-	nr = num_possible_cpus() - NR_LPPACAS;
-	if (nr > 0)
-		new_size = PAGE_ALIGN(nr * sizeof(struct lppaca));
-	if (new_size >= lppaca_size)
-		return;
-
-	memblock_free(__pa(extra_lppacas) + new_size, lppaca_size - new_size);
-	lppaca_size = new_size;
-}
-
-#else
-
-static inline void allocate_lppacas(int nr_cpus, unsigned long limit) { }
-static inline void free_lppacas(void) { }
-
 #endif /* CONFIG_PPC_BOOK3S */
 
 #ifdef CONFIG_PPC_BOOK3S_64
 
 /*
- * 3 persistent SLBs are registered here.  The buffer will be zero
+ * 3 persistent SLBs are allocated here.  The buffer will be zero
  * initially, hence will all be invaild until we actually write them.
  *
  * If you make the number of persistent SLB entries dynamic, please also
  * update PR KVM to flush and restore them accordingly.
  */
-static struct slb_shadow * __initdata slb_shadow;
-
-static void __init allocate_slb_shadows(int nr_cpus, int limit)
-{
-	int size = PAGE_ALIGN(sizeof(struct slb_shadow) * nr_cpus);
-
-	if (early_radix_enabled())
-		return;
-
-	slb_shadow = __va(memblock_alloc_base(size, PAGE_SIZE, limit));
-	memset(slb_shadow, 0, size);
-}
-
-static struct slb_shadow * __init init_slb_shadow(int cpu)
+static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit)
 {
 	struct slb_shadow *s;
 
-	if (early_radix_enabled())
-		return NULL;
-
-	s = &slb_shadow[cpu];
+	if (cpu != boot_cpuid) {
+		/*
+		 * Boot CPU comes here before early_radix_enabled
+		 * is parsed (e.g., for disable_radix). So allocate
+		 * always and this will be fixed up in free_unused_pacas.
+		 */
+		if (early_radix_enabled())
+			return NULL;
+	}
 
-	/*
-	 * When we come through here to initialise boot_paca, the slb_shadow
-	 * buffers are not allocated yet. That's OK, we'll get one later in
-	 * boot, but make sure we don't corrupt memory at 0.
-	 */
-	if (!slb_shadow)
-		return NULL;
+	s = alloc_paca_data(sizeof(*s), L1_CACHE_BYTES, limit, cpu);
+	memset(s, 0, sizeof(*s));
 
 	s->persistent = cpu_to_be32(SLB_NUM_BOLTED);
 	s->buffer_length = cpu_to_be32(sizeof(*s));
@@ -137,10 +126,6 @@ static struct slb_shadow * __init init_slb_shadow(int cpu)
 	return s;
 }
 
-#else /* !CONFIG_PPC_BOOK3S_64 */
-
-static void __init allocate_slb_shadows(int nr_cpus, int limit) { }
-
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 /* The Paca is an array with one entry per processor.  Each contains an
@@ -152,14 +137,15 @@ static void __init allocate_slb_shadows(int nr_cpus, int limit) { }
  * processors.  The processor VPD array needs one entry per physical
  * processor (not thread).
  */
-struct paca_struct *paca;
-EXPORT_SYMBOL(paca);
+struct paca_struct **paca_ptrs __read_mostly;
+EXPORT_SYMBOL(paca_ptrs);
 
 void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 {
-#ifdef CONFIG_PPC_BOOK3S
-	new_paca->lppaca_ptr = new_lppaca(cpu);
-#else
+#ifdef CONFIG_PPC_PSERIES
+	new_paca->lppaca_ptr = NULL;
+#endif
+#ifdef CONFIG_PPC_BOOK3E
 	new_paca->kernel_pgd = swapper_pg_dir;
 #endif
 	new_paca->lock_token = 0x8000;
@@ -173,7 +159,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 	new_paca->__current = &init_task;
 	new_paca->data_offset = 0xfeeeeeeeeeeeeeeeULL;
 #ifdef CONFIG_PPC_BOOK3S_64
-	new_paca->slb_shadow_ptr = init_slb_shadow(cpu);
+	new_paca->slb_shadow_ptr = NULL;
 #endif
 
 #ifdef CONFIG_PPC_BOOK3E
@@ -203,12 +189,25 @@ void setup_paca(struct paca_struct *new_paca)
 
 }
 
-static int __initdata paca_size;
+static int __initdata paca_nr_cpu_ids;
+static int __initdata paca_ptrs_size;
+static int __initdata paca_struct_size;
+
+void __init allocate_paca_ptrs(void)
+{
+	paca_nr_cpu_ids = nr_cpu_ids;
+
+	paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
+	paca_ptrs = __va(memblock_alloc(paca_ptrs_size, 0));
+	memset(paca_ptrs, 0x88, paca_ptrs_size);
+}
 
-void __init allocate_pacas(void)
+void __init allocate_paca(int cpu)
 {
 	u64 limit;
-	int cpu;
+	struct paca_struct *paca;
+
+	BUG_ON(cpu >= paca_nr_cpu_ids);
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	/*
@@ -220,40 +219,44 @@ void __init allocate_pacas(void)
 	limit = ppc64_rma_size;
 #endif
 
-	paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids);
-
-	paca = __va(memblock_alloc_base(paca_size, PAGE_SIZE, limit));
-	memset(paca, 0, paca_size);
-
-	printk(KERN_DEBUG "Allocated %u bytes for %u pacas at %p\n",
-		paca_size, nr_cpu_ids, paca);
-
-	allocate_lppacas(nr_cpu_ids, limit);
-
-	allocate_slb_shadows(nr_cpu_ids, limit);
+	paca = alloc_paca_data(sizeof(struct paca_struct), L1_CACHE_BYTES,
+				limit, cpu);
+	paca_ptrs[cpu] = paca;
+	memset(paca, 0, sizeof(struct paca_struct));
 
-	/* Can't use for_each_*_cpu, as they aren't functional yet */
-	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
-		initialise_paca(&paca[cpu], cpu);
+	initialise_paca(paca, cpu);
+#ifdef CONFIG_PPC_PSERIES
+	paca->lppaca_ptr = new_lppaca(cpu, limit);
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	paca->slb_shadow_ptr = new_slb_shadow(cpu, limit);
+#endif
+	paca_struct_size += sizeof(struct paca_struct);
 }
 
 void __init free_unused_pacas(void)
 {
-	int new_size;
-
-	new_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids);
+	int new_ptrs_size;
 
-	if (new_size >= paca_size)
-		return;
+	new_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
+	if (new_ptrs_size < paca_ptrs_size)
+		memblock_free(__pa(paca_ptrs) + new_ptrs_size,
+					paca_ptrs_size - new_ptrs_size);
 
-	memblock_free(__pa(paca) + new_size, paca_size - new_size);
+	paca_nr_cpu_ids = nr_cpu_ids;
+	paca_ptrs_size = new_ptrs_size;
 
-	printk(KERN_DEBUG "Freed %u bytes for unused pacas\n",
-		paca_size - new_size);
-
-	paca_size = new_size;
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (early_radix_enabled()) {
+		/* Ugly fixup, see new_slb_shadow() */
+		memblock_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr),
+				sizeof(struct slb_shadow));
+		paca_ptrs[boot_cpuid]->slb_shadow_ptr = NULL;
+	}
+#endif
 
-	free_lppacas();
+	printk(KERN_DEBUG "Allocated %u bytes for %u pacas\n",
+			paca_ptrs_size + paca_struct_size, nr_cpu_ids);
 }
 
 void copy_mm_to_paca(struct mm_struct *mm)
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 330c65f04820..9dbed488aba1 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -365,7 +365,6 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 	DBG("boot cpu: logical %d physical %d\n", found,
 	    be32_to_cpu(intserv[found_thread]));
 	boot_cpuid = found;
-	set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread]));
 
 	/*
 	 * PAPR defines "logical" PVR values for cpus that
@@ -403,7 +402,9 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 		cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
 	else if (!dt_cpu_ftrs_in_use())
 		cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
+	allocate_paca(boot_cpuid);
 #endif
+	set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread]));
 
 	return 0;
 }
@@ -744,7 +745,7 @@ void __init early_init_devtree(void *params)
 	 * FIXME .. and the initrd too? */
 	move_device_tree();
 
-	allocate_pacas();
+	allocate_paca_ptrs();
 
 	DBG("Scanning CPUs ...\n");
 
@@ -874,5 +875,15 @@ EXPORT_SYMBOL(cpu_to_chip_id);
 
 bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {
+#ifdef CONFIG_SMP
+	/*
+	 * Early firmware scanning must use this rather than
+	 * get_hard_smp_processor_id because we don't have pacas allocated
+	 * until memory topology is discovered.
+	 */
+	if (cpu_to_phys_id != NULL)
+		return (int)phys_id == cpu_to_phys_id[cpu];
+#endif
+
 	return (int)phys_id == get_hard_smp_processor_id(cpu);
 }
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index a6002f9449b1..56f7a2b793e0 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -437,6 +437,8 @@ static void __init cpu_init_thread_core_maps(int tpc)
 }
 
 
+u32 *cpu_to_phys_id = NULL;
+
 /**
  * setup_cpu_maps - initialize the following cpu maps:
  *                  cpu_possible_mask
@@ -463,6 +465,10 @@ void __init smp_setup_cpu_maps(void)
 
 	DBG("smp_setup_cpu_maps()\n");
 
+	cpu_to_phys_id = __va(memblock_alloc(nr_cpu_ids * sizeof(u32),
+							__alignof__(u32)));
+	memset(cpu_to_phys_id, 0, nr_cpu_ids * sizeof(u32));
+
 	for_each_node_by_type(dn, "cpu") {
 		const __be32 *intserv;
 		__be32 cpu_be;
@@ -480,6 +486,7 @@ void __init smp_setup_cpu_maps(void)
 			intserv = of_get_property(dn, "reg", &len);
 			if (!intserv) {
 				cpu_be = cpu_to_be32(cpu);
+				/* XXX: what is this? uninitialized?? */
 				intserv = &cpu_be;	/* assume logical == phys */
 				len = 4;
 			}
@@ -499,8 +506,8 @@ void __init smp_setup_cpu_maps(void)
 						"enable-method", "spin-table");
 
 			set_cpu_present(cpu, avail);
-			set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j]));
 			set_cpu_possible(cpu, true);
+			cpu_to_phys_id[cpu] = be32_to_cpu(intserv[j]);
 			cpu++;
 		}
 
@@ -835,6 +842,23 @@ static __init void print_system_info(void)
 	pr_info("-----------------------------------------------------\n");
 }
 
+#ifdef CONFIG_SMP
+static void smp_setup_pacas(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == smp_processor_id())
+			continue;
+		allocate_paca(cpu);
+		set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]);
+	}
+
+	memblock_free(__pa(cpu_to_phys_id), nr_cpu_ids * sizeof(u32));
+	cpu_to_phys_id = NULL;
+}
+#endif
+
 /*
  * Called into from start_kernel this initializes memblock, which is used
  * to manage page allocation until mem_init is called.
@@ -888,6 +912,9 @@ void __init setup_arch(char **cmdline_p)
 	/* Check the SMT related command line arguments (ppc64). */
 	check_smt_enabled();
 
+	/* Parse memory topology */
+	mem_topology_setup();
+
 	/* On BookE, setup per-core TLB data structures. */
 	setup_tlb_core_data();
 
@@ -899,6 +926,7 @@ void __init setup_arch(char **cmdline_p)
 	 * so smp_release_cpus() does nothing for them.
 	 */
 #ifdef CONFIG_SMP
+	smp_setup_pacas();
 	smp_release_cpus();
 #endif
 
diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h
index 3fc11e30308f..d144df54ad40 100644
--- a/arch/powerpc/kernel/setup.h
+++ b/arch/powerpc/kernel/setup.h
@@ -46,13 +46,10 @@ static inline void emergency_stack_init(void) { };
 #endif
 
 #ifdef CONFIG_PPC64
-void record_spr_defaults(void);
-#else
-static inline void record_spr_defaults(void) { };
-#endif
-
-#ifdef CONFIG_PPC64
 u64 ppc64_bolted_size(void);
+
+/* Default SPR values from firmware/kexec */
+extern unsigned long spr_default_dscr;
 #endif
 
 /*
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 7f7621668613..66f2b6299c40 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -110,7 +110,7 @@ void __init setup_tlb_core_data(void)
 		if (cpu_first_thread_sibling(boot_cpuid) == first)
 			first = boot_cpuid;
 
-		paca[cpu].tcd_ptr = &paca[first].tcd;
+		paca_ptrs[cpu]->tcd_ptr = &paca_ptrs[first]->tcd;
 
 		/*
 		 * If we have threads, we need either tlbsrx.
@@ -254,6 +254,14 @@ static void cpu_ready_for_interrupts(void)
 	get_paca()->kernel_msr = MSR_KERNEL;
 }
 
+unsigned long spr_default_dscr = 0;
+
+void __init record_spr_defaults(void)
+{
+	if (early_cpu_has_feature(CPU_FTR_DSCR))
+		spr_default_dscr = mfspr(SPRN_DSCR);
+}
+
 /*
  * Early initialization entry point. This is called by head.S
  * with MMU translation disabled. We rely on the "feature" of
@@ -304,7 +312,11 @@ void __init early_setup(unsigned long dt_ptr)
 	early_init_devtree(__va(dt_ptr));
 
 	/* Now we know the logical id of our boot cpu, setup the paca. */
-	setup_paca(&paca[boot_cpuid]);
+	if (boot_cpuid != 0) {
+		/* Poison paca_ptrs[0] again if it's not the boot cpu */
+		memset(&paca_ptrs[0], 0x88, sizeof(paca_ptrs[0]));
+	}
+	setup_paca(paca_ptrs[boot_cpuid]);
 	fixup_boot_paca();
 
 	/*
@@ -599,6 +611,21 @@ __init u64 ppc64_bolted_size(void)
 #endif
 }
 
+static void *__init alloc_stack(unsigned long limit, int cpu)
+{
+	unsigned long pa;
+
+	pa = memblock_alloc_base_nid(THREAD_SIZE, THREAD_SIZE, limit,
+					early_cpu_to_node(cpu), MEMBLOCK_NONE);
+	if (!pa) {
+		pa = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit);
+		if (!pa)
+			panic("cannot allocate stacks");
+	}
+
+	return __va(pa);
+}
+
 void __init irqstack_early_init(void)
 {
 	u64 limit = ppc64_bolted_size();
@@ -610,12 +637,8 @@ void __init irqstack_early_init(void)
 	 * accessed in realmode.
 	 */
 	for_each_possible_cpu(i) {
-		softirq_ctx[i] = (struct thread_info *)
-			__va(memblock_alloc_base(THREAD_SIZE,
-					    THREAD_SIZE, limit));
-		hardirq_ctx[i] = (struct thread_info *)
-			__va(memblock_alloc_base(THREAD_SIZE,
-					    THREAD_SIZE, limit));
+		softirq_ctx[i] = alloc_stack(limit, i);
+		hardirq_ctx[i] = alloc_stack(limit, i);
 	}
 }
 
@@ -623,20 +646,21 @@ void __init irqstack_early_init(void)
 void __init exc_lvl_early_init(void)
 {
 	unsigned int i;
-	unsigned long sp;
 
 	for_each_possible_cpu(i) {
-		sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
-		critirq_ctx[i] = (struct thread_info *)__va(sp);
-		paca[i].crit_kstack = __va(sp + THREAD_SIZE);
+		void *sp;
+
+		sp = alloc_stack(ULONG_MAX, i);
+		critirq_ctx[i] = sp;
+		paca_ptrs[i]->crit_kstack = sp + THREAD_SIZE;
 
-		sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
-		dbgirq_ctx[i] = (struct thread_info *)__va(sp);
-		paca[i].dbg_kstack = __va(sp + THREAD_SIZE);
+		sp = alloc_stack(ULONG_MAX, i);
+		dbgirq_ctx[i] = sp;
+		paca_ptrs[i]->dbg_kstack = sp + THREAD_SIZE;
 
-		sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
-		mcheckirq_ctx[i] = (struct thread_info *)__va(sp);
-		paca[i].mc_kstack = __va(sp + THREAD_SIZE);
+		sp = alloc_stack(ULONG_MAX, i);
+		mcheckirq_ctx[i] = sp;
+		paca_ptrs[i]->mc_kstack = sp + THREAD_SIZE;
 	}
 
 	if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC))
@@ -690,23 +714,24 @@ void __init emergency_stack_init(void)
 
 	for_each_possible_cpu(i) {
 		struct thread_info *ti;
-		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
+
+		ti = alloc_stack(limit, i);
 		memset(ti, 0, THREAD_SIZE);
 		emerg_stack_init_thread_info(ti, i);
-		paca[i].emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE;
 
 #ifdef CONFIG_PPC_BOOK3S_64
 		/* emergency stack for NMI exception handling. */
-		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
+		ti = alloc_stack(limit, i);
 		memset(ti, 0, THREAD_SIZE);
 		emerg_stack_init_thread_info(ti, i);
-		paca[i].nmi_emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE;
 
 		/* emergency stack for machine check exception handling. */
-		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
+		ti = alloc_stack(limit, i);
 		memset(ti, 0, THREAD_SIZE);
 		emerg_stack_init_thread_info(ti, i);
-		paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;
 #endif
 	}
 }
@@ -762,7 +787,7 @@ void __init setup_per_cpu_areas(void)
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu) {
                 __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
-		paca[cpu].data_offset = __per_cpu_offset[cpu];
+		paca_ptrs[cpu]->data_offset = __per_cpu_offset[cpu];
 	}
 }
 #endif
@@ -876,8 +901,9 @@ static void init_fallback_flush(void)
 	memset(l1d_flush_fallback_area, 0, l1d_size * 2);
 
 	for_each_possible_cpu(cpu) {
-		paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area;
-		paca[cpu].l1d_flush_size = l1d_size;
+		struct paca_struct *paca = paca_ptrs[cpu];
+		paca->rfi_flush_fallback_area = l1d_flush_fallback_area;
+		paca->l1d_flush_size = l1d_size;
 	}
 }
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index bbe7634b3a43..cfc08b099c49 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -123,8 +123,8 @@ int smp_generic_kick_cpu(int nr)
 	 * cpu_start field to become non-zero After we set cpu_start,
 	 * the processor will continue on to secondary_start
 	 */
-	if (!paca[nr].cpu_start) {
-		paca[nr].cpu_start = 1;
+	if (!paca_ptrs[nr]->cpu_start) {
+		paca_ptrs[nr]->cpu_start = 1;
 		smp_mb();
 		return 0;
 	}
@@ -657,7 +657,7 @@ void smp_prepare_boot_cpu(void)
 {
 	BUG_ON(smp_processor_id() != boot_cpuid);
 #ifdef CONFIG_PPC64
-	paca[boot_cpuid].__current = current;
+	paca_ptrs[boot_cpuid]->__current = current;
 #endif
 	set_numa_node(numa_cpu_lookup_table[boot_cpuid]);
 	current_set[boot_cpuid] = task_thread_info(current);
@@ -748,8 +748,8 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
 	struct thread_info *ti = task_thread_info(idle);
 
 #ifdef CONFIG_PPC64
-	paca[cpu].__current = idle;
-	paca[cpu].kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
+	paca_ptrs[cpu]->__current = idle;
+	paca_ptrs[cpu]->kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
 #endif
 	ti->cpu = cpu;
 	secondary_ti = current_set[cpu] = ti;
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 04d0bbd7a1dd..755dc98a57ae 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -20,6 +20,7 @@
 #include <asm/firmware.h>
 
 #include "cacheinfo.h"
+#include "setup.h"
 
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
@@ -588,21 +589,18 @@ static DEVICE_ATTR(dscr_default, 0600,
 
 static void sysfs_create_dscr_default(void)
 {
-	int err = 0;
-	if (cpu_has_feature(CPU_FTR_DSCR))
-		err = device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default);
-}
+	if (cpu_has_feature(CPU_FTR_DSCR)) {
+		int err = 0;
+		int cpu;
 
-void __init record_spr_defaults(void)
-{
-	int cpu;
+		dscr_default = spr_default_dscr;
+		for_each_possible_cpu(cpu)
+			paca_ptrs[cpu]->dscr_default = dscr_default;
 
-	if (cpu_has_feature(CPU_FTR_DSCR)) {
-		dscr_default = mfspr(SPRN_DSCR);
-		for (cpu = 0; cpu < nr_cpu_ids; cpu++)
-			paca[cpu].dscr_default = dscr_default;
+		err = device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default);
 	}
 }
+
 #endif /* CONFIG_PPC64 */
 
 #ifdef HAS_PPC_PMC_PA6T
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 55c1022733c3..1e1211c66b26 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -170,7 +170,7 @@ static bool kvmppc_ipi_thread(int cpu)
 
 #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
 	if (cpu >= 0 && cpu < nr_cpu_ids) {
-		if (paca[cpu].kvm_hstate.xics_phys) {
+		if (paca_ptrs[cpu]->kvm_hstate.xics_phys) {
 			xics_wake_cpu(cpu);
 			return true;
 		}
@@ -498,7 +498,8 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
 		 * use 640 bytes of the structure though, so we should accept
 		 * clients that set a size of 640.
 		 */
-		if (len < 640)
+		BUILD_BUG_ON(sizeof(struct lppaca) != 640);
+		if (len < sizeof(struct lppaca))
 			break;
 		vpap = &tvcpu->arch.vpa;
 		err = 0;
@@ -2157,7 +2158,7 @@ static int kvmppc_grab_hwthread(int cpu)
 	struct paca_struct *tpaca;
 	long timeout = 10000;
 
-	tpaca = &paca[cpu];
+	tpaca = paca_ptrs[cpu];
 
 	/* Ensure the thread won't go into the kernel if it wakes */
 	tpaca->kvm_hstate.kvm_vcpu = NULL;
@@ -2190,7 +2191,7 @@ static void kvmppc_release_hwthread(int cpu)
 {
 	struct paca_struct *tpaca;
 
-	tpaca = &paca[cpu];
+	tpaca = paca_ptrs[cpu];
 	tpaca->kvm_hstate.hwthread_req = 0;
 	tpaca->kvm_hstate.kvm_vcpu = NULL;
 	tpaca->kvm_hstate.kvm_vcore = NULL;
@@ -2256,7 +2257,7 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc)
 		vcpu->arch.thread_cpu = cpu;
 		cpumask_set_cpu(cpu, &kvm->arch.cpu_in_guest);
 	}
-	tpaca = &paca[cpu];
+	tpaca = paca_ptrs[cpu];
 	tpaca->kvm_hstate.kvm_vcpu = vcpu;
 	tpaca->kvm_hstate.ptid = cpu - vc->pcpu;
 	tpaca->kvm_hstate.fake_suspend = 0;
@@ -2282,7 +2283,7 @@ static void kvmppc_wait_for_nap(int n_threads)
 		 * for any threads that still have a non-NULL vcore ptr.
 		 */
 		for (i = 1; i < n_threads; ++i)
-			if (paca[cpu + i].kvm_hstate.kvm_vcore)
+			if (paca_ptrs[cpu + i]->kvm_hstate.kvm_vcore)
 				break;
 		if (i == n_threads) {
 			HMT_medium();
@@ -2292,7 +2293,7 @@ static void kvmppc_wait_for_nap(int n_threads)
 	}
 	HMT_medium();
 	for (i = 1; i < n_threads; ++i)
-		if (paca[cpu + i].kvm_hstate.kvm_vcore)
+		if (paca_ptrs[cpu + i]->kvm_hstate.kvm_vcore)
 			pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
 }
 
@@ -2824,9 +2825,11 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	}
 
 	for (thr = 0; thr < controlled_threads; ++thr) {
-		paca[pcpu + thr].kvm_hstate.tid = thr;
-		paca[pcpu + thr].kvm_hstate.napping = 0;
-		paca[pcpu + thr].kvm_hstate.kvm_split_mode = sip;
+		struct paca_struct *paca = paca_ptrs[pcpu + thr];
+
+		paca->kvm_hstate.tid = thr;
+		paca->kvm_hstate.napping = 0;
+		paca->kvm_hstate.kvm_split_mode = sip;
 	}
 
 	/* Initiate micro-threading (split-core) on POWER8 if required */
@@ -2943,7 +2946,9 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	} else if (hpt_on_radix) {
 		/* Wait for all threads to have seen final sync */
 		for (thr = 1; thr < controlled_threads; ++thr) {
-			while (paca[pcpu + thr].kvm_hstate.kvm_split_mode) {
+			struct paca_struct *paca = paca_ptrs[pcpu + thr];
+
+			while (paca->kvm_hstate.kvm_split_mode) {
 				HMT_low();
 				barrier();
 			}
@@ -4405,7 +4410,7 @@ static int kvm_init_subcore_bitmap(void)
 		int node = cpu_to_node(first_cpu);
 
 		/* Ignore if it is already allocated. */
-		if (paca[first_cpu].sibling_subcore_state)
+		if (paca_ptrs[first_cpu]->sibling_subcore_state)
 			continue;
 
 		sibling_subcore_state =
@@ -4420,7 +4425,8 @@ static int kvm_init_subcore_bitmap(void)
 		for (j = 0; j < threads_per_core; j++) {
 			int cpu = first_cpu + j;
 
-			paca[cpu].sibling_subcore_state = sibling_subcore_state;
+			paca_ptrs[cpu]->sibling_subcore_state =
+						sibling_subcore_state;
 		}
 	}
 	return 0;
@@ -4447,7 +4453,7 @@ static int kvmppc_book3s_init_hv(void)
 
 	/*
 	 * We need a way of accessing the XICS interrupt controller,
-	 * either directly, via paca[cpu].kvm_hstate.xics_phys, or
+	 * either directly, via paca_ptrs[cpu]->kvm_hstate.xics_phys, or
 	 * indirectly, via OPAL.
 	 */
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 49a2c7825e04..de18299f92b7 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -251,7 +251,7 @@ void kvmhv_rm_send_ipi(int cpu)
 	    return;
 
 	/* Else poke the target with an IPI */
-	xics_phys = paca[cpu].kvm_hstate.xics_phys;
+	xics_phys = paca_ptrs[cpu]->kvm_hstate.xics_phys;
 	if (xics_phys)
 		__raw_rm_writeb(IPI_PRIORITY, xics_phys + XICS_MFRR);
 	else
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index dc54373c8780..0e8493033288 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -79,8 +79,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	li	r5, 0
 	mtspr	SPRN_MMCRA, r5
 	isync
-	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
-	lbz	r5, LPPACA_PMCINUSE(r3)
+	lbz	r5, PACA_PMCINUSE(r13)	/* is the host using the PMU? */
 	cmpwi	r5, 0
 	beq	31f			/* skip if not */
 	mfspr	r5, SPRN_MMCR1
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index af1772169eff..95c616f2da22 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -113,8 +113,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_SPRG_VDSO_WRITE,r3
 
 	/* Reload the host's PMU registers */
-	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
-	lbz	r4, LPPACA_PMCINUSE(r3)
+	lbz	r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */
 	cmpwi	r4, 0
 	beq	23f			/* skip if not */
 BEGIN_FTR_SECTION
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 4180b89b8922..7587a2ec8874 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -781,7 +781,7 @@ void resize_hpt_for_hotplug(unsigned long new_mem_size)
 	}
 }
 
-int hash__create_section_mapping(unsigned long start, unsigned long end)
+int hash__create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
 	int rc = htab_bolt_mapping(start, end, __pa(start),
 				   pgprot_val(PAGE_KERNEL), mmu_linear_psize,
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 85245ef97e72..e2f5025b03b0 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -117,7 +117,7 @@ int memory_add_physaddr_to_nid(u64 start)
 }
 #endif
 
-int __weak create_section_mapping(unsigned long start, unsigned long end)
+int __weak create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
 	return -ENODEV;
 }
@@ -137,7 +137,7 @@ int __meminit arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *
 	resize_hpt_for_hotplug(memblock_phys_mem_size());
 
 	start = (unsigned long)__va(start);
-	rc = create_section_mapping(start, start + size);
+	rc = create_section_mapping(start, start + size, nid);
 	if (rc) {
 		pr_warn("Unable to create mapping for hot added memory 0x%llx..0x%llx: %d\n",
 			start, start + size, rc);
@@ -212,7 +212,7 @@ walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 EXPORT_SYMBOL_GPL(walk_system_ram_range);
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-void __init initmem_init(void)
+void __init mem_topology_setup(void)
 {
 	max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
 	min_low_pfn = MEMORY_START >> PAGE_SHIFT;
@@ -224,7 +224,10 @@ void __init initmem_init(void)
 	 * memblock_regions
 	 */
 	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
+}
 
+void __init initmem_init(void)
+{
 	/* XXX need to clip this if using highmem? */
 	sparse_memory_present_with_active_regions(0);
 	sparse_init();
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index edd8d0bc9364..57a5029b4521 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -831,18 +831,13 @@ out:
 	of_node_put(rtas);
 }
 
-void __init initmem_init(void)
+void __init mem_topology_setup(void)
 {
-	int nid, cpu;
-
-	max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
-	max_pfn = max_low_pfn;
+	int cpu;
 
 	if (parse_numa_properties())
 		setup_nonnuma();
 
-	memblock_dump_all();
-
 	/*
 	 * Modify the set of possible NUMA nodes to reflect information
 	 * available about the set of online nodes, and the set of nodes
@@ -853,6 +848,23 @@ void __init initmem_init(void)
 
 	find_possible_nodes();
 
+	setup_node_to_cpumask_map();
+
+	reset_numa_cpu_lookup_table();
+
+	for_each_present_cpu(cpu)
+		numa_setup_cpu(cpu);
+}
+
+void __init initmem_init(void)
+{
+	int nid;
+
+	max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
+	max_pfn = max_low_pfn;
+
+	memblock_dump_all();
+
 	for_each_online_node(nid) {
 		unsigned long start_pfn, end_pfn;
 
@@ -863,10 +875,6 @@ void __init initmem_init(void)
 
 	sparse_init();
 
-	setup_node_to_cpumask_map();
-
-	reset_numa_cpu_lookup_table();
-
 	/*
 	 * We need the numa_cpu_lookup_table to be accurate for all CPUs,
 	 * even before we online them, so that we can use cpu_to_{node,mem}
@@ -876,8 +884,6 @@ void __init initmem_init(void)
 	 */
 	cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "powerpc/numa:prepare",
 				  ppc_numa_cpu_prepare, ppc_numa_cpu_dead);
-	for_each_present_cpu(cpu)
-		numa_setup_cpu(cpu);
 }
 
 static int __init early_numa(char *p)
@@ -1105,7 +1111,7 @@ static void setup_cpu_associativity_change_counters(void)
 	for_each_possible_cpu(cpu) {
 		int i;
 		u8 *counts = vphn_cpu_change_counts[cpu];
-		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
+		volatile u8 *hypervisor_counts = lppaca_of(cpu).vphn_assoc_counts;
 
 		for (i = 0; i < distance_ref_points_depth; i++)
 			counts[i] = hypervisor_counts[i];
@@ -1131,7 +1137,7 @@ static int update_cpu_associativity_changes_mask(void)
 	for_each_possible_cpu(cpu) {
 		int i, changed = 0;
 		u8 *counts = vphn_cpu_change_counts[cpu];
-		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
+		volatile u8 *hypervisor_counts = lppaca_of(cpu).vphn_assoc_counts;
 
 		for (i = 0; i < distance_ref_points_depth; i++) {
 			if (hypervisor_counts[i] != counts[i]) {
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index bd6ca74acf9e..518518fb7c45 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -155,12 +155,12 @@ void mmu_cleanup_all(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int __meminit create_section_mapping(unsigned long start, unsigned long end)
+int __meminit create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
 	if (radix_enabled())
-		return radix__create_section_mapping(start, end);
+		return radix__create_section_mapping(start, end, nid);
 
-	return hash__create_section_mapping(start, end);
+	return hash__create_section_mapping(start, end, nid);
 }
 
 int __meminit remove_section_mapping(unsigned long start, unsigned long end)
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index ab9db0afd2c8..7095384344b4 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -48,20 +48,88 @@ static int native_register_process_table(unsigned long base, unsigned long pg_sz
 	return 0;
 }
 
-static __ref void *early_alloc_pgtable(unsigned long size)
+static __ref void *early_alloc_pgtable(unsigned long size, int nid,
+			unsigned long region_start, unsigned long region_end)
 {
+	unsigned long pa = 0;
 	void *pt;
 
-	pt = __va(memblock_alloc_base(size, size, MEMBLOCK_ALLOC_ANYWHERE));
+	if (region_start || region_end) /* has region hint */
+		pa = memblock_alloc_range(size, size, region_start, region_end,
+						MEMBLOCK_NONE);
+	else if (nid != -1) /* has node hint */
+		pa = memblock_alloc_base_nid(size, size,
+						MEMBLOCK_ALLOC_ANYWHERE,
+						nid, MEMBLOCK_NONE);
+
+	if (!pa)
+		pa = memblock_alloc_base(size, size, MEMBLOCK_ALLOC_ANYWHERE);
+
+	BUG_ON(!pa);
+
+	pt = __va(pa);
 	memset(pt, 0, size);
 
 	return pt;
 }
 
-int radix__map_kernel_page(unsigned long ea, unsigned long pa,
+static int early_map_kernel_page(unsigned long ea, unsigned long pa,
 			  pgprot_t flags,
-			  unsigned int map_page_size)
+			  unsigned int map_page_size,
+			  int nid,
+			  unsigned long region_start, unsigned long region_end)
 {
+	unsigned long pfn = pa >> PAGE_SHIFT;
+	pgd_t *pgdp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep;
+
+	pgdp = pgd_offset_k(ea);
+	if (pgd_none(*pgdp)) {
+		pudp = early_alloc_pgtable(PUD_TABLE_SIZE, nid,
+						region_start, region_end);
+		pgd_populate(&init_mm, pgdp, pudp);
+	}
+	pudp = pud_offset(pgdp, ea);
+	if (map_page_size == PUD_SIZE) {
+		ptep = (pte_t *)pudp;
+		goto set_the_pte;
+	}
+	if (pud_none(*pudp)) {
+		pmdp = early_alloc_pgtable(PMD_TABLE_SIZE, nid,
+						region_start, region_end);
+		pud_populate(&init_mm, pudp, pmdp);
+	}
+	pmdp = pmd_offset(pudp, ea);
+	if (map_page_size == PMD_SIZE) {
+		ptep = pmdp_ptep(pmdp);
+		goto set_the_pte;
+	}
+	if (!pmd_present(*pmdp)) {
+		ptep = early_alloc_pgtable(PAGE_SIZE, nid,
+						region_start, region_end);
+		pmd_populate_kernel(&init_mm, pmdp, ptep);
+	}
+	ptep = pte_offset_kernel(pmdp, ea);
+
+set_the_pte:
+	set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags));
+	smp_wmb();
+	return 0;
+}
+
+/*
+ * nid, region_start, and region_end are hints to try to place the page
+ * table memory in the same node or region.
+ */
+static int __map_kernel_page(unsigned long ea, unsigned long pa,
+			  pgprot_t flags,
+			  unsigned int map_page_size,
+			  int nid,
+			  unsigned long region_start, unsigned long region_end)
+{
+	unsigned long pfn = pa >> PAGE_SHIFT;
 	pgd_t *pgdp;
 	pud_t *pudp;
 	pmd_t *pmdp;
@@ -70,61 +138,48 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa,
 	 * Make sure task size is correct as per the max adddr
 	 */
 	BUILD_BUG_ON(TASK_SIZE_USER64 > RADIX_PGTABLE_RANGE);
-	if (slab_is_available()) {
-		pgdp = pgd_offset_k(ea);
-		pudp = pud_alloc(&init_mm, pgdp, ea);
-		if (!pudp)
-			return -ENOMEM;
-		if (map_page_size == PUD_SIZE) {
-			ptep = (pte_t *)pudp;
-			goto set_the_pte;
-		}
-		pmdp = pmd_alloc(&init_mm, pudp, ea);
-		if (!pmdp)
-			return -ENOMEM;
-		if (map_page_size == PMD_SIZE) {
-			ptep = pmdp_ptep(pmdp);
-			goto set_the_pte;
-		}
-		ptep = pte_alloc_kernel(pmdp, ea);
-		if (!ptep)
-			return -ENOMEM;
-	} else {
-		pgdp = pgd_offset_k(ea);
-		if (pgd_none(*pgdp)) {
-			pudp = early_alloc_pgtable(PUD_TABLE_SIZE);
-			BUG_ON(pudp == NULL);
-			pgd_populate(&init_mm, pgdp, pudp);
-		}
-		pudp = pud_offset(pgdp, ea);
-		if (map_page_size == PUD_SIZE) {
-			ptep = (pte_t *)pudp;
-			goto set_the_pte;
-		}
-		if (pud_none(*pudp)) {
-			pmdp = early_alloc_pgtable(PMD_TABLE_SIZE);
-			BUG_ON(pmdp == NULL);
-			pud_populate(&init_mm, pudp, pmdp);
-		}
-		pmdp = pmd_offset(pudp, ea);
-		if (map_page_size == PMD_SIZE) {
-			ptep = pmdp_ptep(pmdp);
-			goto set_the_pte;
-		}
-		if (!pmd_present(*pmdp)) {
-			ptep = early_alloc_pgtable(PAGE_SIZE);
-			BUG_ON(ptep == NULL);
-			pmd_populate_kernel(&init_mm, pmdp, ptep);
-		}
-		ptep = pte_offset_kernel(pmdp, ea);
+
+	if (unlikely(!slab_is_available()))
+		return early_map_kernel_page(ea, pa, flags, map_page_size,
+						nid, region_start, region_end);
+
+	/*
+	 * Should make page table allocation functions be able to take a
+	 * node, so we can place kernel page tables on the right nodes after
+	 * boot.
+	 */
+	pgdp = pgd_offset_k(ea);
+	pudp = pud_alloc(&init_mm, pgdp, ea);
+	if (!pudp)
+		return -ENOMEM;
+	if (map_page_size == PUD_SIZE) {
+		ptep = (pte_t *)pudp;
+		goto set_the_pte;
 	}
+	pmdp = pmd_alloc(&init_mm, pudp, ea);
+	if (!pmdp)
+		return -ENOMEM;
+	if (map_page_size == PMD_SIZE) {
+		ptep = pmdp_ptep(pmdp);
+		goto set_the_pte;
+	}
+	ptep = pte_alloc_kernel(pmdp, ea);
+	if (!ptep)
+		return -ENOMEM;
 
 set_the_pte:
-	set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, flags));
+	set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags));
 	smp_wmb();
 	return 0;
 }
 
+int radix__map_kernel_page(unsigned long ea, unsigned long pa,
+			  pgprot_t flags,
+			  unsigned int map_page_size)
+{
+	return __map_kernel_page(ea, pa, flags, map_page_size, -1, 0, 0);
+}
+
 #ifdef CONFIG_STRICT_KERNEL_RWX
 void radix__change_memory_range(unsigned long start, unsigned long end,
 				unsigned long clear)
@@ -211,7 +266,8 @@ static inline void __meminit print_mapping(unsigned long start,
 }
 
 static int __meminit create_physical_mapping(unsigned long start,
-					     unsigned long end)
+					     unsigned long end,
+					     int nid)
 {
 	unsigned long vaddr, addr, mapping_size = 0;
 	pgprot_t prot;
@@ -267,7 +323,7 @@ retry:
 		else
 			prot = PAGE_KERNEL;
 
-		rc = radix__map_kernel_page(vaddr, addr, prot, mapping_size);
+		rc = __map_kernel_page(vaddr, addr, prot, mapping_size, nid, start, end);
 		if (rc)
 			return rc;
 	}
@@ -276,7 +332,7 @@ retry:
 	return 0;
 }
 
-static void __init radix_init_pgtable(void)
+void __init radix_init_pgtable(void)
 {
 	unsigned long rts_field;
 	struct memblock_region *reg;
@@ -286,9 +342,16 @@ static void __init radix_init_pgtable(void)
 	/*
 	 * Create the linear mapping, using standard page size for now
 	 */
-	for_each_memblock(memory, reg)
+	for_each_memblock(memory, reg) {
+		/*
+		 * The memblock allocator  is up at this point, so the
+		 * page tables will be allocated within the range. No
+		 * need or a node (which we don't have yet).
+		 */
 		WARN_ON(create_physical_mapping(reg->base,
-						reg->base + reg->size));
+						reg->base + reg->size,
+						-1));
+	}
 
 	/* Find out how many PID bits are supported */
 	if (cpu_has_feature(CPU_FTR_HVMODE)) {
@@ -317,7 +380,7 @@ static void __init radix_init_pgtable(void)
 	 * host.
 	 */
 	BUG_ON(PRTB_SIZE_SHIFT > 36);
-	process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT);
+	process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT, -1, 0, 0);
 	/*
 	 * Fill in the process table.
 	 */
@@ -705,8 +768,8 @@ static int __meminit stop_machine_change_mapping(void *data)
 
 	spin_unlock(&init_mm.page_table_lock);
 	pte_clear(&init_mm, params->aligned_start, params->pte);
-	create_physical_mapping(params->aligned_start, params->start);
-	create_physical_mapping(params->end, params->aligned_end);
+	create_physical_mapping(params->aligned_start, params->start, -1);
+	create_physical_mapping(params->end, params->aligned_end, -1);
 	spin_lock(&init_mm.page_table_lock);
 	return 0;
 }
@@ -863,9 +926,9 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end)
 	radix__flush_tlb_kernel_range(start, end);
 }
 
-int __meminit radix__create_section_mapping(unsigned long start, unsigned long end)
+int __meminit radix__create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
-	return create_physical_mapping(start, end);
+	return create_physical_mapping(start, end, nid);
 }
 
 int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end)
@@ -876,14 +939,25 @@ int __meminit radix__remove_section_mapping(unsigned long start, unsigned long e
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
+static int __map_kernel_page_nid(unsigned long ea, unsigned long pa,
+				 pgprot_t flags, unsigned int map_page_size,
+				 int nid)
+{
+	return __map_kernel_page(ea, pa, flags, map_page_size, nid, 0, 0);
+}
+
 int __meminit radix__vmemmap_create_mapping(unsigned long start,
 				      unsigned long page_size,
 				      unsigned long phys)
 {
 	/* Create a PTE encoding */
 	unsigned long flags = _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_KERNEL_RW;
+	int nid = early_pfn_to_nid(phys >> PAGE_SHIFT);
+	int ret;
+
+	ret = __map_kernel_page_nid(start, phys, __pgprot(flags), page_size, nid);
+	BUG_ON(ret);
 
-	BUG_ON(radix__map_kernel_page(start, phys, __pgprot(flags), page_size));
 	return 0;
 }
 
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 291eab4ed7cd..a8b178dd2e82 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -734,7 +734,7 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
 		for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) {
 			if (sib == cpu)
 				continue;
-			if (paca[sib].kvm_hstate.kvm_vcpu)
+			if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu)
 				flush = true;
 		}
 		if (flush)
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index f51fd35f4618..7e966f4cf19a 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -147,7 +147,7 @@ static void qoriq_cpu_kill(unsigned int cpu)
 	for (i = 0; i < 500; i++) {
 		if (is_cpu_dead(cpu)) {
 #ifdef CONFIG_PPC64
-			paca[cpu].cpu_start = 0;
+			paca_ptrs[cpu]->cpu_start = 0;
 #endif
 			return;
 		}
@@ -328,7 +328,7 @@ static int smp_85xx_kick_cpu(int nr)
 		return ret;
 
 done:
-	paca[nr].cpu_start = 1;
+	paca_ptrs[nr]->cpu_start = 1;
 	generic_set_cpu_up(nr);
 
 	return ret;
@@ -409,14 +409,14 @@ void mpc85xx_smp_kexec_cpu_down(int crash_shutdown, int secondary)
 	}
 
 	if (disable_threadbit) {
-		while (paca[disable_cpu].kexec_state < KEXEC_STATE_REAL_MODE) {
+		while (paca_ptrs[disable_cpu]->kexec_state < KEXEC_STATE_REAL_MODE) {
 			barrier();
 			now = mftb();
 			if (!notified && now - start > 1000000) {
 				pr_info("%s/%d: waiting for cpu %d to enter KEXEC_STATE_REAL_MODE (%d)\n",
 					__func__, smp_processor_id(),
 					disable_cpu,
-					paca[disable_cpu].kexec_state);
+					paca_ptrs[disable_cpu]->kexec_state);
 				notified = true;
 			}
 		}
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
index f84d52a2db40..1aeac5761e0b 100644
--- a/arch/powerpc/platforms/cell/smp.c
+++ b/arch/powerpc/platforms/cell/smp.c
@@ -83,7 +83,7 @@ static inline int smp_startup_cpu(unsigned int lcpu)
 	pcpu = get_hard_smp_processor_id(lcpu);
 
 	/* Fixup atomic count: it exited inside IRQ handler. */
-	task_thread_info(paca[lcpu].__current)->preempt_count	= 0;
+	task_thread_info(paca_ptrs[lcpu]->__current)->preempt_count	= 0;
 
 	/*
 	 * If the RTAS start-cpu token does not exist then presume the
@@ -126,7 +126,7 @@ static int smp_cell_kick_cpu(int nr)
 	 * cpu_start field to become non-zero After we set cpu_start,
 	 * the processor will continue on to secondary_start
 	 */
-	paca[nr].cpu_start = 1;
+	paca_ptrs[nr]->cpu_start = 1;
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 99a760eae964..d9e366bb23da 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -81,7 +81,7 @@ static int pnv_save_sprs_for_deep_states(void)
 
 	for_each_possible_cpu(cpu) {
 		uint64_t pir = get_hard_smp_processor_id(cpu);
-		uint64_t hsprg0_val = (uint64_t)&paca[cpu];
+		uint64_t hsprg0_val = (uint64_t)paca_ptrs[cpu];
 
 		rc = opal_slw_set_reg(pir, SPRN_HSPRG0, hsprg0_val);
 		if (rc != 0)
@@ -174,12 +174,12 @@ static void pnv_alloc_idle_core_states(void)
 		for (j = 0; j < threads_per_core; j++) {
 			int cpu = first_cpu + j;
 
-			paca[cpu].core_idle_state_ptr = core_idle_state;
-			paca[cpu].thread_idle_state = PNV_THREAD_RUNNING;
-			paca[cpu].thread_mask = 1 << j;
+			paca_ptrs[cpu]->core_idle_state_ptr = core_idle_state;
+			paca_ptrs[cpu]->thread_idle_state = PNV_THREAD_RUNNING;
+			paca_ptrs[cpu]->thread_mask = 1 << j;
 			if (!cpu_has_feature(CPU_FTR_POWER9_DD1))
 				continue;
-			paca[cpu].thread_sibling_pacas =
+			paca_ptrs[cpu]->thread_sibling_pacas =
 				kmalloc_node(paca_ptr_array_size,
 					     GFP_KERNEL, node);
 		}
@@ -405,22 +405,20 @@ void power9_idle(void)
 void pnv_power9_force_smt4_catch(void)
 {
 	int cpu, cpu0, thr;
-	struct paca_struct *tpaca;
 	int awake_threads = 1;		/* this thread is awake */
 	int poke_threads = 0;
 	int need_awake = threads_per_core;
 
 	cpu = smp_processor_id();
 	cpu0 = cpu & ~(threads_per_core - 1);
-	tpaca = &paca[cpu0];
 	for (thr = 0; thr < threads_per_core; ++thr) {
 		if (cpu != cpu0 + thr)
-			atomic_inc(&tpaca[thr].dont_stop);
+			atomic_inc(&paca_ptrs[cpu0+thr]->dont_stop);
 	}
 	/* order setting dont_stop vs testing requested_psscr */
 	mb();
 	for (thr = 0; thr < threads_per_core; ++thr) {
-		if (!tpaca[thr].requested_psscr)
+		if (!paca_ptrs[cpu0+thr]->requested_psscr)
 			++awake_threads;
 		else
 			poke_threads |= (1 << thr);
@@ -433,14 +431,14 @@ void pnv_power9_force_smt4_catch(void)
 			if (poke_threads & (1 << thr)) {
 				ppc_msgsnd_sync();
 				ppc_msgsnd(PPC_DBELL_MSGTYPE, 0,
-					   tpaca[thr].hw_cpu_id);
+					   paca_ptrs[cpu0+thr]->hw_cpu_id);
 			}
 		}
 		/* now spin until at least 3 threads are awake */
 		do {
 			for (thr = 0; thr < threads_per_core; ++thr) {
 				if ((poke_threads & (1 << thr)) &&
-				    !tpaca[thr].requested_psscr) {
+				    !paca_ptrs[cpu0+thr]->requested_psscr) {
 					++awake_threads;
 					poke_threads &= ~(1 << thr);
 				}
@@ -453,16 +451,14 @@ EXPORT_SYMBOL_GPL(pnv_power9_force_smt4_catch);
 void pnv_power9_force_smt4_release(void)
 {
 	int cpu, cpu0, thr;
-	struct paca_struct *tpaca;
 
 	cpu = smp_processor_id();
 	cpu0 = cpu & ~(threads_per_core - 1);
-	tpaca = &paca[cpu0];
 
 	/* clear all the dont_stop flags */
 	for (thr = 0; thr < threads_per_core; ++thr) {
 		if (cpu != cpu0 + thr)
-			atomic_dec(&tpaca[thr].dont_stop);
+			atomic_dec(&paca_ptrs[cpu0+thr]->dont_stop);
 	}
 }
 EXPORT_SYMBOL_GPL(pnv_power9_force_smt4_release);
@@ -830,7 +826,8 @@ static int __init pnv_init_idle_states(void)
 			for (i = 0; i < threads_per_core; i++) {
 				int j = base_cpu + i;
 
-				paca[j].thread_sibling_pacas[idx] = &paca[cpu];
+				paca_ptrs[j]->thread_sibling_pacas[idx] =
+					paca_ptrs[cpu];
 			}
 		}
 	}
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 7de050a3736b..5f963286232f 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -293,7 +293,7 @@ static void pnv_kexec_wait_secondaries_down(void)
 			if (i != notified) {
 				printk(KERN_INFO "kexec: waiting for cpu %d "
 				       "(physical %d) to enter OPAL\n",
-				       i, paca[i].hw_cpu_id);
+				       i, paca_ptrs[i]->hw_cpu_id);
 				notified = i;
 			}
 
@@ -305,7 +305,7 @@ static void pnv_kexec_wait_secondaries_down(void)
 			if (timeout-- == 0) {
 				printk(KERN_ERR "kexec: timed out waiting for "
 				       "cpu %d (physical %d) to enter OPAL\n",
-				       i, paca[i].hw_cpu_id);
+				       i, paca_ptrs[i]->hw_cpu_id);
 				break;
 			}
 		}
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 9664c8461f03..19af6de6b6f0 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -80,7 +80,7 @@ static int pnv_smp_kick_cpu(int nr)
 	 * If we already started or OPAL is not supported, we just
 	 * kick the CPU via the PACA
 	 */
-	if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPAL))
+	if (paca_ptrs[nr]->cpu_start || !firmware_has_feature(FW_FEATURE_OPAL))
 		goto kick;
 
 	/*
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 596ae2e98040..45563004feda 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -280,7 +280,7 @@ void update_subcore_sibling_mask(void)
 		int offset = (tid / threads_per_subcore) * threads_per_subcore;
 		int mask = sibling_mask_first_cpu << offset;
 
-		paca[cpu].subcore_sibling_mask = mask;
+		paca_ptrs[cpu]->subcore_sibling_mask = mask;
 
 	}
 }
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 652d3e96b812..6ef77caf7bcf 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -234,7 +234,7 @@ static void pseries_cpu_die(unsigned int cpu)
 	 * done here.  Change isolate state to Isolate and
 	 * change allocation-state to Unusable.
 	 */
-	paca[cpu].cpu_start = 0;
+	paca_ptrs[cpu]->cpu_start = 0;
 }
 
 /*
diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c
index eeb13429d685..3fe126796975 100644
--- a/arch/powerpc/platforms/pseries/kexec.c
+++ b/arch/powerpc/platforms/pseries/kexec.c
@@ -23,7 +23,12 @@
 
 void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 {
-	/* Don't risk a hypervisor call if we're crashing */
+	/*
+	 * Don't risk a hypervisor call if we're crashing
+	 * XXX: Why? The hypervisor is not crashing. It might be better
+	 * to at least attempt unregister to avoid the hypervisor stepping
+	 * on our memory.
+	 */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR) && !crash_shutdown) {
 		int ret;
 		int cpu = smp_processor_id();
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 238b55fb8007..adb996ed51e1 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -99,7 +99,7 @@ void vpa_init(int cpu)
 	 * reports that.  All SPLPAR support SLB shadow buffer.
 	 */
 	if (!radix_enabled() && firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		addr = __pa(paca[cpu].slb_shadow_ptr);
+		addr = __pa(paca_ptrs[cpu]->slb_shadow_ptr);
 		ret = register_slb_shadow(hwcpu, addr);
 		if (ret)
 			pr_err("WARNING: SLB shadow buffer registration for "
@@ -111,7 +111,7 @@ void vpa_init(int cpu)
 	/*
 	 * Register dispatch trace log, if one has been allocated.
 	 */
-	pp = &paca[cpu];
+	pp = paca_ptrs[cpu];
 	dtl = pp->dispatch_log;
 	if (dtl) {
 		pp->dtl_ridx = 0;
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index b11564f2a4c7..98bca8d9c9e0 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -247,7 +247,7 @@ static int alloc_dispatch_logs(void)
 		return 0;
 
 	for_each_possible_cpu(cpu) {
-		pp = &paca[cpu];
+		pp = paca_ptrs[cpu];
 		dtl = kmem_cache_alloc(dtl_cache, GFP_KERNEL);
 		if (!dtl) {
 			pr_warn("Failed to allocate dispatch trace log for cpu %d\n",
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 66b6f119d599..3df46123cce3 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -110,7 +110,7 @@ static inline int smp_startup_cpu(unsigned int lcpu)
 	}
 
 	/* Fixup atomic count: it exited inside IRQ handler. */
-	task_thread_info(paca[lcpu].__current)->preempt_count	= 0;
+	task_thread_info(paca_ptrs[lcpu]->__current)->preempt_count	= 0;
 #ifdef CONFIG_HOTPLUG_CPU
 	if (get_cpu_current_state(lcpu) == CPU_STATE_INACTIVE)
 		goto out;
@@ -165,7 +165,7 @@ static int smp_pSeries_kick_cpu(int nr)
 	 * cpu_start field to become non-zero After we set cpu_start,
 	 * the processor will continue on to secondary_start
 	 */
-	paca[nr].cpu_start = 1;
+	paca_ptrs[nr]->cpu_start = 1;
 #ifdef CONFIG_HOTPLUG_CPU
 	set_preferred_offline_state(nr, CPU_STATE_ONLINE);
 
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 73067805300a..1d4e0ef658d3 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -626,7 +626,7 @@ static inline u32 mpic_physmask(u32 cpumask)
 	int i;
 	u32 mask = 0;
 
-	for (i = 0; i < min(32, NR_CPUS); ++i, cpumask >>= 1)
+	for (i = 0; i < min(32, NR_CPUS) && cpu_possible(i); ++i, cpumask >>= 1)
 		mask |= (cpumask & 1) << get_hard_smp_processor_id(i);
 	return mask;
 }
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 1459f4e8b698..37bfbc54aacb 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -164,7 +164,7 @@ void icp_native_cause_ipi_rm(int cpu)
 	 * Just like the cause_ipi functions, it is required to
 	 * include a full barrier before causing the IPI.
 	 */
-	xics_phys = paca[cpu].kvm_hstate.xics_phys;
+	xics_phys = paca_ptrs[cpu]->kvm_hstate.xics_phys;
 	mb();
 	__raw_rm_writeb(IPI_PRIORITY, xics_phys + XICS_MFRR);
 }
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 53918023622e..a0842f1ff72c 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2341,7 +2341,7 @@ static void dump_one_paca(int cpu)
 	catch_memory_errors = 1;
 	sync();
 
-	p = &paca[cpu];
+	p = paca_ptrs[cpu];
 
 	printf("paca for cpu 0x%x @ %px:\n", cpu, p);