From 0834d627fbea00c1444075eb3e448e1974da452d Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 30 Mar 2018 23:27:25 +1100
Subject: [PATCH 01/15] powerpc/mpic: Check if cpu_possible() in
 mpic_physmask()

In mpic_physmask() we loop over all CPUs up to 32, then get the hard
SMP processor id of that CPU.

Currently that's possibly walking off the end of the paca array, but
in a future patch we will change the paca array to be an array of
pointers, and in that case we will get a NULL for missing CPUs and
oops. eg:

  Unable to handle kernel paging request for data at address 0x88888888888888b8
  Faulting instruction address: 0xc00000000004e380
  Oops: Kernel access of bad area, sig: 11 [#1]
  ...
  NIP .mpic_set_affinity+0x60/0x1a0
  LR  .irq_do_set_affinity+0x48/0x100

Fix it by checking the CPU is possible, this also fixes the code if
there are gaps in the CPU numbering which probably never happens on
mpic systems but who knows.

Debugged-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/sysdev/mpic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

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;
 }

From 8e0b634b132752ec3eba50afb952502b1a87d6ba Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:11 +1000
Subject: [PATCH 02/15] powerpc/64s: Do not allocate lppaca if we are not
 virtualized

The "lppaca" is a structure registered with the hypervisor. This is
unnecessary when running on non-virtualised platforms. One field from
the lppaca (pmcregs_in_use) is also used by the host, so move the host
part out into the paca (lppaca field is still updated in
guest mode).

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Fix non-pseries build with some #ifdefs]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/paca.h           | 12 ++++++++++--
 arch/powerpc/include/asm/plpar_wrappers.h |  4 ++++
 arch/powerpc/include/asm/pmc.h            | 13 ++++++++++++-
 arch/powerpc/kernel/asm-offsets.c         |  5 +++++
 arch/powerpc/kernel/paca.c                | 16 +++++++++++++---
 arch/powerpc/kvm/book3s_hv_interrupts.S   |  3 +--
 arch/powerpc/kvm/book3s_hv_rmhandlers.S   |  3 +--
 7 files changed, 46 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index b62c31037cad..6db5ab2a29a3 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -46,7 +46,10 @@ 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;
@@ -58,7 +61,7 @@ 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
@@ -67,7 +70,8 @@ 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
@@ -160,10 +164,14 @@ 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 */
diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h
index 55eddf50d149..540785d01f96 100644
--- a/arch/powerpc/include/asm/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_POWERPC_PLPAR_WRAPPERS_H
 #define _ASM_POWERPC_PLPAR_WRAPPERS_H
 
+#ifdef CONFIG_PPC_PSERIES
+
 #include <linux/string.h>
 #include <linux/irqflags.h>
 
@@ -340,4 +342,6 @@ static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p)
 	return rc;
 }
 
+#endif /* CONFIG_PPC_PSERIES */
+
 #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */
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/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index ea5eb91b836e..bbde55f408c7 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/paca.c b/arch/powerpc/kernel/paca.c
index 95ffedf14885..5900540e2ff8 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -20,7 +20,7 @@
 
 #include "setup.h"
 
-#ifdef CONFIG_PPC_BOOK3S
+#ifdef CONFIG_PPC_PSERIES
 
 /*
  * The structure which the hypervisor knows about - this structure
@@ -47,6 +47,9 @@ static long __initdata lppaca_size;
 
 static void __init allocate_lppacas(int nr_cpus, unsigned long limit)
 {
+	if (early_cpu_has_feature(CPU_FTR_HVMODE))
+		return;
+
 	if (nr_cpus <= NR_LPPACAS)
 		return;
 
@@ -60,6 +63,9 @@ static struct lppaca * __init new_lppaca(int cpu)
 {
 	struct lppaca *lp;
 
+	if (early_cpu_has_feature(CPU_FTR_HVMODE))
+		return NULL;
+
 	if (cpu < NR_LPPACAS)
 		return &lppaca[cpu];
 
@@ -73,6 +79,9 @@ static void __init free_lppacas(void)
 {
 	long new_size = 0, nr;
 
+	if (early_cpu_has_feature(CPU_FTR_HVMODE))
+		return;
+
 	if (!lppaca_size)
 		return;
 	nr = num_possible_cpus() - NR_LPPACAS;
@@ -157,9 +166,10 @@ EXPORT_SYMBOL(paca);
 
 void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 {
-#ifdef CONFIG_PPC_BOOK3S
+#ifdef CONFIG_PPC_PSERIES
 	new_paca->lppaca_ptr = new_lppaca(cpu);
-#else
+#endif
+#ifdef CONFIG_PPC_BOOK3E
 	new_paca->kernel_pgd = swapper_pg_dir;
 #endif
 	new_paca->lock_token = 0x8000;
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 f31f357b8c5a..a1c6ea26f568 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

From d2e60075a3d4422dc54b919f3b125d8066b839d4 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:12 +1000
Subject: [PATCH 03/15] powerpc/64: Use array of paca pointers and allocate
 pacas individually

Change the paca array into an array of pointers to pacas. Allocate
pacas individually.

This allows flexibility in where the PACAs are allocated. Future work
will allocate them node-local. Platforms that don't have address limits
on PACAs would be able to defer PACA allocations until later in boot
rather than allocate all possible ones up-front then freeing unused.

This is slightly more overhead (one additional indirection) for cross
CPU paca references, but those aren't too common.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/kvm_ppc.h           |  8 +--
 arch/powerpc/include/asm/lppaca.h            |  2 +-
 arch/powerpc/include/asm/paca.h              |  4 +-
 arch/powerpc/include/asm/smp.h               |  4 +-
 arch/powerpc/kernel/crash.c                  |  2 +-
 arch/powerpc/kernel/head_64.S                | 19 +++---
 arch/powerpc/kernel/machine_kexec_64.c       | 22 +++----
 arch/powerpc/kernel/paca.c                   | 66 ++++++++++++++------
 arch/powerpc/kernel/setup_64.c               | 23 +++----
 arch/powerpc/kernel/smp.c                    | 10 +--
 arch/powerpc/kernel/sysfs.c                  |  2 +-
 arch/powerpc/kvm/book3s_hv.c                 | 31 +++++----
 arch/powerpc/kvm/book3s_hv_builtin.c         |  2 +-
 arch/powerpc/mm/tlb-radix.c                  |  2 +-
 arch/powerpc/platforms/85xx/smp.c            |  8 +--
 arch/powerpc/platforms/cell/smp.c            |  4 +-
 arch/powerpc/platforms/powernv/idle.c        | 13 ++--
 arch/powerpc/platforms/powernv/setup.c       |  4 +-
 arch/powerpc/platforms/powernv/smp.c         |  2 +-
 arch/powerpc/platforms/powernv/subcore.c     |  2 +-
 arch/powerpc/platforms/pseries/hotplug-cpu.c |  2 +-
 arch/powerpc/platforms/pseries/lpar.c        |  4 +-
 arch/powerpc/platforms/pseries/setup.c       |  2 +-
 arch/powerpc/platforms/pseries/smp.c         |  4 +-
 arch/powerpc/sysdev/xics/icp-native.c        |  2 +-
 arch/powerpc/xmon/xmon.c                     |  2 +-
 26 files changed, 141 insertions(+), 105 deletions(-)

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..6e4589eee2da 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -103,7 +103,7 @@ struct lppaca {
 
 extern struct lppaca lppaca[];
 
-#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 6db5ab2a29a3..e89887f5e56f 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -249,10 +249,10 @@ 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);
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index fac963e10d39..ec7b299350d9 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -170,12 +170,12 @@ 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/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..a250e3331f94 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;
 			}
 		}
@@ -327,8 +328,7 @@ void default_machine_kexec(struct kimage *image)
 	 */
 	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;
+	paca_ptrs[kexec_paca.paca_index] = &kexec_paca;
 	setup_paca(&kexec_paca);
 
 	/* XXX: If anyone does 'dynamic lppacas' this will also need to be
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 5900540e2ff8..eef4891c9af6 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -161,8 +161,8 @@ 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)
 {
@@ -213,11 +213,13 @@ 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;
 
 void __init allocate_pacas(void)
 {
 	u64 limit;
+	unsigned long size = 0;
 	int cpu;
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -230,13 +232,27 @@ void __init allocate_pacas(void)
 	limit = ppc64_rma_size;
 #endif
 
-	paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids);
+	paca_nr_cpu_ids = nr_cpu_ids;
 
-	paca = __va(memblock_alloc_base(paca_size, PAGE_SIZE, limit));
-	memset(paca, 0, paca_size);
+	paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
+	paca_ptrs = __va(memblock_alloc_base(paca_ptrs_size, 0, limit));
+	memset(paca_ptrs, 0, paca_ptrs_size);
 
-	printk(KERN_DEBUG "Allocated %u bytes for %u pacas at %p\n",
-		paca_size, nr_cpu_ids, paca);
+	size += paca_ptrs_size;
+
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
+		unsigned long pa;
+
+		pa = memblock_alloc_base(sizeof(struct paca_struct),
+						L1_CACHE_BYTES, limit);
+		paca_ptrs[cpu] = __va(pa);
+		memset(paca_ptrs[cpu], 0, sizeof(struct paca_struct));
+
+		size += sizeof(struct paca_struct);
+	}
+
+	printk(KERN_DEBUG "Allocated %lu bytes for %u pacas\n",
+			size, nr_cpu_ids);
 
 	allocate_lppacas(nr_cpu_ids, limit);
 
@@ -244,26 +260,38 @@ void __init allocate_pacas(void)
 
 	/* 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_ptrs[cpu], cpu);
 }
 
 void __init free_unused_pacas(void)
 {
-	int new_size;
+	unsigned long size = 0;
+	int new_ptrs_size;
+	int cpu;
 
-	new_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids);
+	for (cpu = 0; cpu < paca_nr_cpu_ids; cpu++) {
+		if (!cpu_possible(cpu)) {
+			unsigned long pa = __pa(paca_ptrs[cpu]);
+			memblock_free(pa, sizeof(struct paca_struct));
+			paca_ptrs[cpu] = NULL;
+			size += sizeof(struct paca_struct);
+		}
+	}
 
-	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);
+		size += paca_ptrs_size - new_ptrs_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);
-
-	paca_size = new_size;
+	if (size)
+		printk(KERN_DEBUG "Freed %lu bytes for unused pacas\n", size);
 
 	free_lppacas();
+
+	paca_nr_cpu_ids = nr_cpu_ids;
+	paca_ptrs_size = new_ptrs_size;
 }
 
 void copy_mm_to_paca(struct mm_struct *mm)
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index c388cc3357fa..3ce12af4906f 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.
@@ -304,7 +304,7 @@ 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]);
+	setup_paca(paca_ptrs[boot_cpuid]);
 	fixup_boot_paca();
 
 	/*
@@ -628,15 +628,15 @@ void __init exc_lvl_early_init(void)
 	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);
+		paca_ptrs[i]->crit_kstack = __va(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);
+		paca_ptrs[i]->dbg_kstack = __va(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);
+		paca_ptrs[i]->mc_kstack = __va(sp + THREAD_SIZE);
 	}
 
 	if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC))
@@ -693,20 +693,20 @@ void __init emergency_stack_init(void)
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
 		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));
 		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));
 		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 +762,7 @@ 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
@@ -875,8 +875,9 @@ 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 5a8bfee6e187..1f9d94dac3a6 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -600,7 +600,7 @@ void __init record_spr_defaults(void)
 	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;
+			paca_ptrs[cpu]->dscr_default = dscr_default;
 	}
 }
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 89707354c2ef..41fce69714d5 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;
 		}
@@ -2140,7 +2140,7 @@ 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;
@@ -2173,7 +2173,7 @@ 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;
@@ -2239,7 +2239,7 @@ 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;
 	/* Order stores to hstate.kvm_vcpu etc. before store to kvm_vcore */
@@ -2264,7 +2264,7 @@ 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();
@@ -2274,7 +2274,7 @@ 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);
 }
 
@@ -2806,9 +2806,11 @@ 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 */
@@ -2925,7 +2927,9 @@ 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();
 			}
@@ -4387,7 +4391,7 @@ 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 =
@@ -4402,7 +4406,8 @@ 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;
@@ -4429,7 +4434,7 @@ 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/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 71d1b19ad1c0..e6016f4466f3 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -723,7 +723,7 @@ 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 443d5ca71995..5b2ca71ee551 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -80,7 +80,7 @@ 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)
@@ -173,12 +173,12 @@ 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);
 		}
@@ -749,7 +749,8 @@ 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 4fb21e17504a..b62ca0220ea5 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -254,7 +254,7 @@ 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;
 			}
 
@@ -266,7 +266,7 @@ 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 dceb51454d8d..357471aa99a6 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -233,7 +233,7 @@ 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/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 0ee4a469a4ae..b6d2ecce33eb 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 372d7ada1a0c..a66005a25c55 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -246,7 +246,7 @@ 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 2e184829e5d4..d506bf661f0f 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/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 82e1a3ee6e0f..b6574b6f7d4a 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2327,7 +2327,7 @@ 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);
 

From 499dcd41378ebab2a37a0df65735748d66e75599 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:13 +1000
Subject: [PATCH 04/15] powerpc/64s: Allocate LPPACAs individually

We no longer allocate lppacas in an array, so this patch removes the
1kB static alignment for the structure, and enforces the PAPR
alignment requirements at allocation time. We can not reduce the 1kB
allocation size however, due to existing KVM hypervisors.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/lppaca.h      | 24 +++----
 arch/powerpc/kernel/machine_kexec_64.c | 15 +++--
 arch/powerpc/kernel/paca.c             | 89 +++++++++-----------------
 arch/powerpc/kvm/book3s_hv.c           |  3 +-
 arch/powerpc/mm/numa.c                 |  4 +-
 arch/powerpc/platforms/pseries/kexec.c |  7 +-
 6 files changed, 63 insertions(+), 79 deletions(-)

diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 6e4589eee2da..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 */
@@ -97,11 +99,9 @@ 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_ptrs[cpu]->lppaca_ptr)
 
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index a250e3331f94..1044bf15d5ed 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -323,17 +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;
+#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 eef4891c9af6..6cddb9bdc151 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -23,82 +23,50 @@
 #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 (early_cpu_has_feature(CPU_FTR_HVMODE))
-		return;
-
-	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;
+
+	BUILD_BUG_ON(size < sizeof(struct lppaca));
 
 	if (early_cpu_has_feature(CPU_FTR_HVMODE))
 		return NULL;
 
-	if (cpu < NR_LPPACAS)
-		return &lppaca[cpu];
-
-	lp = extra_lppacas + (cpu - NR_LPPACAS);
-	*lp = lppaca[0];
+	lp = __va(memblock_alloc_base(size, 0x400, limit));
+	init_lppaca(lp);
 
 	return lp;
 }
 
-static void __init free_lppacas(void)
+static void __init free_lppaca(struct lppaca *lp)
 {
-	long new_size = 0, nr;
+	size_t size = 0x400;
 
 	if (early_cpu_has_feature(CPU_FTR_HVMODE))
 		return;
 
-	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;
+	memblock_free(__pa(lp), 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
@@ -167,7 +135,7 @@ EXPORT_SYMBOL(paca_ptrs);
 void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 {
 #ifdef CONFIG_PPC_PSERIES
-	new_paca->lppaca_ptr = new_lppaca(cpu);
+	new_paca->lppaca_ptr = NULL;
 #endif
 #ifdef CONFIG_PPC_BOOK3E
 	new_paca->kernel_pgd = swapper_pg_dir;
@@ -254,13 +222,15 @@ void __init allocate_pacas(void)
 	printk(KERN_DEBUG "Allocated %lu bytes for %u pacas\n",
 			size, nr_cpu_ids);
 
-	allocate_lppacas(nr_cpu_ids, limit);
-
 	allocate_slb_shadows(nr_cpu_ids, limit);
 
 	/* Can't use for_each_*_cpu, as they aren't functional yet */
-	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
 		initialise_paca(paca_ptrs[cpu], cpu);
+#ifdef CONFIG_PPC_PSERIES
+		paca_ptrs[cpu]->lppaca_ptr = new_lppaca(cpu, limit);
+#endif
+	}
 }
 
 void __init free_unused_pacas(void)
@@ -272,6 +242,9 @@ void __init free_unused_pacas(void)
 	for (cpu = 0; cpu < paca_nr_cpu_ids; cpu++) {
 		if (!cpu_possible(cpu)) {
 			unsigned long pa = __pa(paca_ptrs[cpu]);
+#ifdef CONFIG_PPC_PSERIES
+			free_lppaca(paca_ptrs[cpu]->lppaca_ptr);
+#endif
 			memblock_free(pa, sizeof(struct paca_struct));
 			paca_ptrs[cpu] = NULL;
 			size += sizeof(struct paca_struct);
@@ -288,8 +261,6 @@ void __init free_unused_pacas(void)
 	if (size)
 		printk(KERN_DEBUG "Freed %lu bytes for unused pacas\n", size);
 
-	free_lppacas();
-
 	paca_nr_cpu_ids = nr_cpu_ids;
 	paca_ptrs_size = new_ptrs_size;
 }
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 41fce69714d5..9b48d4a191ff 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -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;
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 314d19ab9385..e9ec465068f1 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1110,7 +1110,7 @@ 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];
@@ -1136,7 +1136,7 @@ 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/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();

From 384e8067844fc19f9c067d6b03cbc8781f98bd5d Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:14 +1000
Subject: [PATCH 05/15] powerpc/64s: Allocate slb_shadow structures
 individually

slb_shadow structures are avoided for radix environment.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/paca.c | 65 ++++++++++++++++++--------------------
 1 file changed, 30 insertions(+), 35 deletions(-)

diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 6cddb9bdc151..2699f9009286 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -72,41 +72,28 @@ static void __init free_lppaca(struct lppaca *lp)
 #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;
+	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;
+	}
 
-	s = &slb_shadow[cpu];
-
-	/*
-	 * 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 = __va(memblock_alloc_base(sizeof(*s), L1_CACHE_BYTES, limit));
+	memset(s, 0, sizeof(*s));
 
 	s->persistent = cpu_to_be32(SLB_NUM_BOLTED);
 	s->buffer_length = cpu_to_be32(sizeof(*s));
@@ -114,10 +101,6 @@ 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
@@ -151,7 +134,7 @@ 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
@@ -222,13 +205,16 @@ void __init allocate_pacas(void)
 	printk(KERN_DEBUG "Allocated %lu bytes for %u pacas\n",
 			size, nr_cpu_ids);
 
-	allocate_slb_shadows(nr_cpu_ids, limit);
-
 	/* Can't use for_each_*_cpu, as they aren't functional yet */
 	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
-		initialise_paca(paca_ptrs[cpu], cpu);
+		struct paca_struct *paca = paca_ptrs[cpu];
+
+		initialise_paca(paca, cpu);
 #ifdef CONFIG_PPC_PSERIES
-		paca_ptrs[cpu]->lppaca_ptr = new_lppaca(cpu, limit);
+		paca->lppaca_ptr = new_lppaca(cpu, limit);
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+		paca->slb_shadow_ptr = new_slb_shadow(cpu, limit);
 #endif
 	}
 }
@@ -263,6 +249,15 @@ void __init free_unused_pacas(void)
 
 	paca_nr_cpu_ids = nr_cpu_ids;
 	paca_ptrs_size = new_ptrs_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
 }
 
 void copy_mm_to_paca(struct mm_struct *mm)

From b575454fa330aab2d65cf17812ca8e1f405ae80d Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:15 +1000
Subject: [PATCH 06/15] mm: make memblock_alloc_base_nid() non-static

This will be used by powerpc to allocate per-cpu stacks and other
data structures node-local where possible.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Drop stray change to memblock_alloc_range() as noticed by akpm]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 include/linux/memblock.h | 3 +++
 mm/memblock.c            | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 8be5077efb5f..4e1e3d0b002a 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -319,6 +319,9 @@ static inline bool memblock_bottom_up(void)
 phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
 					phys_addr_t start, phys_addr_t end,
 					ulong flags);
+phys_addr_t memblock_alloc_base_nid(phys_addr_t size,
+					phys_addr_t align, phys_addr_t max_addr,
+					int nid, ulong flags);
 phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align,
 				phys_addr_t max_addr);
 phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align,
diff --git a/mm/memblock.c b/mm/memblock.c
index 5a9ca2a1751b..cea2af494da0 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1190,7 +1190,7 @@ phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
 					flags);
 }
 
-static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size,
+phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size,
 					phys_addr_t align, phys_addr_t max_addr,
 					int nid, ulong flags)
 {

From 9bd9be006c8ec0ccf7cb0422d35033af39d3f969 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:16 +1000
Subject: [PATCH 07/15] powerpc/mm/numa: move numa topology discovery earlier

Split sparsemem initialisation from basic numa topology discovery.
Move the parsing earlier in boot, before pacas are allocated.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/setup.h   |  1 +
 arch/powerpc/kernel/setup-common.c |  3 +++
 arch/powerpc/mm/mem.c              |  5 ++++-
 arch/powerpc/mm/numa.c             | 32 ++++++++++++++++++------------
 4 files changed, 27 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 469b7fdc9be4..d2bf233aebd5 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/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index d73ec518ef80..9eaf26318d20 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -888,6 +888,9 @@ 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();
 
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index fe8c61149fb8..4eee46ea4d96 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -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 e9ec465068f1..1eec1bcc03a6 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -836,18 +836,13 @@ static void __init find_possible_nodes(void)
 	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
@@ -858,6 +853,23 @@ 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;
 
@@ -868,10 +880,6 @@ 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}
@@ -881,8 +889,6 @@ 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)

From c0abd0c745bdabe027a8f013a866f385fba717b1 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:17 +1000
Subject: [PATCH 08/15] powerpc/64: move default SPR recording

Move this into the early setup code, and don't iterate over CPU masks.
We don't want to call into sysfs so early from setup, and a future patch
won't initialize CPU masks by the time this is called.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Fold in incremental fix from Nick for DSCR handling]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/setup.h    |  9 +++------
 arch/powerpc/kernel/setup_64.c |  8 ++++++++
 arch/powerpc/kernel/sysfs.c    | 20 +++++++++-----------
 3 files changed, 20 insertions(+), 17 deletions(-)

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
@@ -45,14 +45,11 @@ void emergency_stack_init(void);
 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 3ce12af4906f..dde34d35d1e7 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -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
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 1f9d94dac3a6..9f327483008c 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);
-}
-
-void __init record_spr_defaults(void)
-{
-	int cpu;
-
 	if (cpu_has_feature(CPU_FTR_DSCR)) {
-		dscr_default = mfspr(SPRN_DSCR);
-		for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		int err = 0;
+		int cpu;
+
+		dscr_default = spr_default_dscr;
+		for_each_possible_cpu(cpu)
 			paca_ptrs[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

From 9f593f131ed463dc571290980dd12cb9e56d8ea5 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:18 +1000
Subject: [PATCH 09/15] powerpc/setup: Add cpu_to_phys_id array

Build an array that finds hardware CPU number from logical CPU
number in firmware CPU discovery. Use that rather than setting
paca of other CPUs directly, to begin with. Subsequent patch will
not have pacas allocated at this point.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Fix SMP=n build by adding #ifdef in arch_match_cpu_phys_id()]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/smp.h     |  1 +
 arch/powerpc/kernel/prom.c         | 10 ++++++++++
 arch/powerpc/kernel/setup-common.c | 15 ++++++++++++++-
 3 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index ec7b299350d9..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);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 4dffef947b8a..0d59a7128deb 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -874,5 +874,15 @@ 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 9eaf26318d20..bd79a5644c78 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++;
 		}
 
@@ -570,6 +577,12 @@ void __init smp_setup_cpu_maps(void)
 	setup_nr_cpu_ids();
 
 	free_unused_pacas();
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == smp_processor_id())
+			continue;
+		set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]);
+	}
 }
 #endif /* CONFIG_SMP */
 

From 59f577743d71bf796ceac10961bf6cfa5ca26786 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:19 +1000
Subject: [PATCH 10/15] powerpc/64: Defer paca allocation until memory topology
 is discovered

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Rename the dummy allocate_pacas() to fix 32-bit build]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/paca.h    |  6 +-
 arch/powerpc/kernel/paca.c         | 90 ++++++++++--------------------
 arch/powerpc/kernel/prom.c         |  5 +-
 arch/powerpc/kernel/setup-common.c | 24 ++++++--
 4 files changed, 53 insertions(+), 72 deletions(-)

diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index e89887f5e56f..2d04c5575631 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -255,12 +255,14 @@ extern void copy_mm_to_paca(struct mm_struct *mm);
 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/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 2699f9009286..a186911791c7 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -57,16 +57,6 @@ static struct lppaca * __init new_lppaca(int cpu, unsigned long limit)
 
 	return lp;
 }
-
-static void __init free_lppaca(struct lppaca *lp)
-{
-	size_t size = 0x400;
-
-	if (early_cpu_has_feature(CPU_FTR_HVMODE))
-		return;
-
-	memblock_free(__pa(lp), size);
-}
 #endif /* CONFIG_PPC_BOOK3S */
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -166,12 +156,24 @@ void setup_paca(struct paca_struct *new_paca)
 
 static int __initdata paca_nr_cpu_ids;
 static int __initdata paca_ptrs_size;
+static int __initdata paca_struct_size;
 
-void __init allocate_pacas(void)
+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_paca(int cpu)
 {
 	u64 limit;
-	unsigned long size = 0;
-	int cpu;
+	unsigned long pa;
+	struct paca_struct *paca;
+
+	BUG_ON(cpu >= paca_nr_cpu_ids);
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	/*
@@ -183,69 +185,30 @@ void __init allocate_pacas(void)
 	limit = ppc64_rma_size;
 #endif
 
-	paca_nr_cpu_ids = nr_cpu_ids;
+	pa = memblock_alloc_base(sizeof(struct paca_struct),
+					L1_CACHE_BYTES, limit);
+	paca = __va(pa);
+	paca_ptrs[cpu] = paca;
+	memset(paca, 0, sizeof(struct paca_struct));
 
-	paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
-	paca_ptrs = __va(memblock_alloc_base(paca_ptrs_size, 0, limit));
-	memset(paca_ptrs, 0, paca_ptrs_size);
-
-	size += paca_ptrs_size;
-
-	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
-		unsigned long pa;
-
-		pa = memblock_alloc_base(sizeof(struct paca_struct),
-						L1_CACHE_BYTES, limit);
-		paca_ptrs[cpu] = __va(pa);
-		memset(paca_ptrs[cpu], 0, sizeof(struct paca_struct));
-
-		size += sizeof(struct paca_struct);
-	}
-
-	printk(KERN_DEBUG "Allocated %lu bytes for %u pacas\n",
-			size, nr_cpu_ids);
-
-	/* Can't use for_each_*_cpu, as they aren't functional yet */
-	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
-		struct paca_struct *paca = paca_ptrs[cpu];
-
-		initialise_paca(paca, cpu);
+	initialise_paca(paca, cpu);
 #ifdef CONFIG_PPC_PSERIES
-		paca->lppaca_ptr = new_lppaca(cpu, limit);
+	paca->lppaca_ptr = new_lppaca(cpu, limit);
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
-		paca->slb_shadow_ptr = new_slb_shadow(cpu, limit);
+	paca->slb_shadow_ptr = new_slb_shadow(cpu, limit);
 #endif
-	}
+	paca_struct_size += sizeof(struct paca_struct);
 }
 
 void __init free_unused_pacas(void)
 {
-	unsigned long size = 0;
 	int new_ptrs_size;
-	int cpu;
-
-	for (cpu = 0; cpu < paca_nr_cpu_ids; cpu++) {
-		if (!cpu_possible(cpu)) {
-			unsigned long pa = __pa(paca_ptrs[cpu]);
-#ifdef CONFIG_PPC_PSERIES
-			free_lppaca(paca_ptrs[cpu]->lppaca_ptr);
-#endif
-			memblock_free(pa, sizeof(struct paca_struct));
-			paca_ptrs[cpu] = NULL;
-			size += sizeof(struct paca_struct);
-		}
-	}
 
 	new_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
-	if (new_ptrs_size < paca_ptrs_size) {
+	if (new_ptrs_size < paca_ptrs_size)
 		memblock_free(__pa(paca_ptrs) + new_ptrs_size,
 					paca_ptrs_size - new_ptrs_size);
-		size += paca_ptrs_size - new_ptrs_size;
-	}
-
-	if (size)
-		printk(KERN_DEBUG "Freed %lu bytes for unused pacas\n", size);
 
 	paca_nr_cpu_ids = nr_cpu_ids;
 	paca_ptrs_size = new_ptrs_size;
@@ -258,6 +221,9 @@ void __init free_unused_pacas(void)
 		paca_ptrs[boot_cpuid]->slb_shadow_ptr = NULL;
 	}
 #endif
+
+	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 0d59a7128deb..e19f5e374200 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");
 
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index bd79a5644c78..af7a47c8fe10 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -577,12 +577,6 @@ void __init smp_setup_cpu_maps(void)
 	setup_nr_cpu_ids();
 
 	free_unused_pacas();
-
-	for_each_possible_cpu(cpu) {
-		if (cpu == smp_processor_id())
-			continue;
-		set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]);
-	}
 }
 #endif /* CONFIG_SMP */
 
@@ -848,6 +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.
@@ -915,6 +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
 

From 4890aea65ae7b5d424b5020e8be193b08a545990 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:20 +1000
Subject: [PATCH 11/15] powerpc/64: Allocate pacas per node

Per-node allocations are possible on 64s with radix that does
not have the bolted SLB limitation.

Hash would be able to do the same if all CPUs had the bottom of
their node-local memory bolted as well. This is left as an
exercise for the reader.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Add dummy definition of boot_cpuid for !SMP]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/paca.c     | 45 +++++++++++++++++++++++++++++-----
 arch/powerpc/kernel/setup_64.c |  4 +++
 2 files changed, 43 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index a186911791c7..0f7e2be23fa2 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -20,6 +20,41 @@
 
 #include "setup.h"
 
+#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
 
 /*
@@ -52,7 +87,7 @@ static struct lppaca * __init new_lppaca(int cpu, unsigned long limit)
 	if (early_cpu_has_feature(CPU_FTR_HVMODE))
 		return NULL;
 
-	lp = __va(memblock_alloc_base(size, 0x400, limit));
+	lp = alloc_paca_data(size, 0x400, limit, cpu);
 	init_lppaca(lp);
 
 	return lp;
@@ -82,7 +117,7 @@ static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit)
 			return NULL;
 	}
 
-	s = __va(memblock_alloc_base(sizeof(*s), L1_CACHE_BYTES, limit));
+	s = alloc_paca_data(sizeof(*s), L1_CACHE_BYTES, limit, cpu);
 	memset(s, 0, sizeof(*s));
 
 	s->persistent = cpu_to_be32(SLB_NUM_BOLTED);
@@ -170,7 +205,6 @@ void __init allocate_paca_ptrs(void)
 void __init allocate_paca(int cpu)
 {
 	u64 limit;
-	unsigned long pa;
 	struct paca_struct *paca;
 
 	BUG_ON(cpu >= paca_nr_cpu_ids);
@@ -185,9 +219,8 @@ void __init allocate_paca(int cpu)
 	limit = ppc64_rma_size;
 #endif
 
-	pa = memblock_alloc_base(sizeof(struct paca_struct),
-					L1_CACHE_BYTES, limit);
-	paca = __va(pa);
+	paca = alloc_paca_data(sizeof(struct paca_struct), L1_CACHE_BYTES,
+				limit, cpu);
 	paca_ptrs[cpu] = paca;
 	memset(paca, 0, sizeof(struct paca_struct));
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index dde34d35d1e7..02fa358982e6 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -312,6 +312,10 @@ 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. */
+	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();
 

From f3865f9a7112590f0cae02dce05ec3c3a09ff405 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:21 +1000
Subject: [PATCH 12/15] powerpc/64: Allocate per-cpu stacks node-local if
 possible

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/setup_64.c | 51 +++++++++++++++++++++-------------
 1 file changed, 32 insertions(+), 19 deletions(-)

diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 02fa358982e6..16ea71fa1ead 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -611,6 +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();
@@ -622,12 +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);
 	}
 }
 
@@ -635,20 +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_ptrs[i]->crit_kstack = __va(sp + THREAD_SIZE);
+		void *sp;
 
-		sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
-		dbgirq_ctx[i] = (struct thread_info *)__va(sp);
-		paca_ptrs[i]->dbg_kstack = __va(sp + THREAD_SIZE);
+		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);
-		mcheckirq_ctx[i] = (struct thread_info *)__va(sp);
-		paca_ptrs[i]->mc_kstack = __va(sp + THREAD_SIZE);
+		sp = alloc_stack(ULONG_MAX, i);
+		dbgirq_ctx[i] = sp;
+		paca_ptrs[i]->dbg_kstack = 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))
@@ -702,20 +714,21 @@ 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_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_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_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;

From 0633dafcf8921048eb1ddc8c6fcfbe1b1cf3e42c Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:23 +1000
Subject: [PATCH 13/15] powerpc/64s/radix: Split early page table mapping to
 its own function

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/mm/pgtable-radix.c | 112 ++++++++++++++++++--------------
 1 file changed, 65 insertions(+), 47 deletions(-)

diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 573a9a2ee455..5afff0eb57d4 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -56,6 +56,50 @@ static __ref void *early_alloc_pgtable(unsigned long size)
 	return pt;
 }
 
+static int early_map_kernel_page(unsigned long ea, unsigned long pa,
+			  pgprot_t flags,
+			  unsigned int map_page_size)
+{
+	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);
+		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);
+
+set_the_pte:
+	set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, flags));
+	smp_wmb();
+	return 0;
+}
+
+
 int radix__map_kernel_page(unsigned long ea, unsigned long pa,
 			  pgprot_t flags,
 			  unsigned int map_page_size)
@@ -68,54 +112,28 @@ 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 (!slab_is_available())
+		return early_map_kernel_page(ea, pa, flags, map_page_size);
+
+	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));

From 2ad452ffaaa8d2f1124208e507e7b045e8ee98a6 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:24 +1000
Subject: [PATCH 14/15] powerpc/64s/radix: Allocate kernel page tables
 node-local if possible

Try to allocate kernel page tables for direct mapping and vmemmap
according to the node of the memory they will map. The node is not
available for the linear map in early boot, so use range allocation
to allocate the page tables from the region they map, which is
effectively node-local.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Fix build error in radix__create_section_mapping()]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/mm/pgtable-radix.c | 104 ++++++++++++++++++++++++--------
 1 file changed, 80 insertions(+), 24 deletions(-)

diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 5afff0eb57d4..5f4b75315990 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -46,11 +46,26 @@ 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;
@@ -58,8 +73,11 @@ static __ref void *early_alloc_pgtable(unsigned long size)
 
 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;
@@ -67,8 +85,8 @@ static int early_map_kernel_page(unsigned long ea, unsigned long pa,
 
 	pgdp = pgd_offset_k(ea);
 	if (pgd_none(*pgdp)) {
-		pudp = early_alloc_pgtable(PUD_TABLE_SIZE);
-		BUG_ON(pudp == NULL);
+		pudp = early_alloc_pgtable(PUD_TABLE_SIZE, nid,
+						region_start, region_end);
 		pgd_populate(&init_mm, pgdp, pudp);
 	}
 	pudp = pud_offset(pgdp, ea);
@@ -77,8 +95,8 @@ static int early_map_kernel_page(unsigned long ea, unsigned long pa,
 		goto set_the_pte;
 	}
 	if (pud_none(*pudp)) {
-		pmdp = early_alloc_pgtable(PMD_TABLE_SIZE);
-		BUG_ON(pmdp == NULL);
+		pmdp = early_alloc_pgtable(PMD_TABLE_SIZE, nid,
+						region_start, region_end);
 		pud_populate(&init_mm, pudp, pmdp);
 	}
 	pmdp = pmd_offset(pudp, ea);
@@ -87,23 +105,29 @@ static int early_map_kernel_page(unsigned long ea, unsigned long pa,
 		goto set_the_pte;
 	}
 	if (!pmd_present(*pmdp)) {
-		ptep = early_alloc_pgtable(PAGE_SIZE);
-		BUG_ON(ptep == NULL);
+		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(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,
+/*
+ * 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)
+			  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;
@@ -113,9 +137,15 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa,
 	 */
 	BUILD_BUG_ON(TASK_SIZE_USER64 > RADIX_PGTABLE_RANGE);
 
-	if (!slab_is_available())
-		return early_map_kernel_page(ea, pa, flags, map_page_size);
+	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)
@@ -136,11 +166,25 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa,
 		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;
 }
 
+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 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)
@@ -227,7 +271,8 @@ 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;
@@ -283,7 +328,7 @@ static int __meminit create_physical_mapping(unsigned long start,
 		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;
 	}
@@ -292,7 +337,7 @@ static int __meminit create_physical_mapping(unsigned long start,
 	return 0;
 }
 
-static void __init radix_init_pgtable(void)
+void __init radix_init_pgtable(void)
 {
 	unsigned long rts_field;
 	struct memblock_region *reg;
@@ -302,9 +347,16 @@ 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)) {
@@ -333,7 +385,7 @@ 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.
 	 */
@@ -810,7 +862,7 @@ static void remove_pagetable(unsigned long start, unsigned long end)
 
 int __ref radix__create_section_mapping(unsigned long start, unsigned long end)
 {
-	return create_physical_mapping(start, end);
+	return create_physical_mapping(start, end, -1);
 }
 
 int radix__remove_section_mapping(unsigned long start, unsigned long end)
@@ -827,8 +879,12 @@ int __meminit radix__vmemmap_create_mapping(unsigned long start,
 {
 	/* 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;
 }
 

From 29ab6c4708a587bc27ea0c765ac36aef9c1a77c9 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Wed, 14 Feb 2018 01:08:22 +1000
Subject: [PATCH 15/15] powerpc/mm: Pass node id into create_section_mapping

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Move __map_kernel_page_nid() inside #ifdef SPARSEMEM_VMEMMAP]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/book3s/64/hash.h  |  2 +-
 arch/powerpc/include/asm/book3s/64/radix.h |  2 +-
 arch/powerpc/include/asm/sparsemem.h       |  2 +-
 arch/powerpc/mm/hash_utils_64.c            |  2 +-
 arch/powerpc/mm/mem.c                      |  4 ++--
 arch/powerpc/mm/pgtable-book3s64.c         |  6 +++---
 arch/powerpc/mm/pgtable-radix.c            | 18 +++++++++---------
 7 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 0920eff731b3..b1ace9619e94 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -201,7 +201,7 @@ 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/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/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 7d07c7e17db6..ceb5494804b2 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 4eee46ea4d96..f50ce66dd6bd 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 arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *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);
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index 422e80253a33..c736280068ce 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 create_section_mapping(unsigned long start, unsigned long end)
+int 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 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 5f4b75315990..a425636af8b4 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -171,13 +171,6 @@ static int __map_kernel_page(unsigned long ea, unsigned long pa,
 	return 0;
 }
 
-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 radix__map_kernel_page(unsigned long ea, unsigned long pa,
 			  pgprot_t flags,
 			  unsigned int map_page_size)
@@ -860,9 +853,9 @@ static void remove_pagetable(unsigned long start, unsigned long end)
 	radix__flush_tlb_kernel_range(start, end);
 }
 
-int __ref radix__create_section_mapping(unsigned long start, unsigned long end)
+int __ref radix__create_section_mapping(unsigned long start, unsigned long end, int nid)
 {
-	return create_physical_mapping(start, end, -1);
+	return create_physical_mapping(start, end, nid);
 }
 
 int radix__remove_section_mapping(unsigned long start, unsigned long end)
@@ -873,6 +866,13 @@ int radix__remove_section_mapping(unsigned long start, unsigned long end)
 #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)