[PATCH 1/3] Raise the upper limit of NR_CPUS.

[PATCH 1/3] Raise the upper limit of NR_CPUS.

[Tony Breeds]

As the pacas are statically initialised increasing NR_CPUS beyond 128,
means that any additional pacas will be empty  ... which is bad.

This patch adds the required functionality to fill in any excess pacas
at runtime.

Signed-off-by: Tony Breeds <tony@bakeyournoodle.com>
---
 arch/powerpc/kernel/paca.c             |   57 ++++++++++++++++++++------------
 arch/powerpc/kernel/setup_64.c         |    3 ++
 arch/powerpc/platforms/Kconfig.cputype |    4 +-
 include/asm-powerpc/paca.h             |   20 +++++++++++
 4 files changed, 61 insertions(+), 23 deletions(-)

diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index ac163bd..7cd55f2 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -18,6 +18,15 @@
 #include <asm/paca.h>
 #include <asm/mmu.h>
 
+/*
+ * In order to handle "strange" values of NR_CPUS, Make sure we use
+ * max(NR_CPUS, NR_STATIC_PACAS) for array sizes below
+ */
+#if NR_CPUS > NR_STATIC_PACAS
+#define MAX_CPUS	NR_CPUS
+#else
+#define MAX_CPUS	NR_STATIC_PACAS
+#endif
 
 /* This symbol is provided by the linker - let it fill in the paca
  * field correctly */
@@ -33,7 +42,7 @@ extern unsigned long __toc_start;
  * will suffice to ensure that it doesn't cross a page boundary.
  */
 struct lppaca lppaca[] = {
-	[0 ... (NR_CPUS-1)] = {
+	[0 ... (MAX_CPUS-1)] = {
 		.desc = 0xd397d781,	/* "LpPa" */
 		.size = sizeof(struct lppaca),
 		.dyn_proc_status = 2,
@@ -50,7 +59,7 @@ struct lppaca lppaca[] = {
  * initially, hence will all be invaild until we actually write them.
  */
 struct slb_shadow slb_shadow[] __cacheline_aligned = {
-	[0 ... (NR_CPUS-1)] = {
+	[0 ... (MAX_CPUS-1)] = {
 		.persistent = SLB_NUM_BOLTED,
 		.buffer_length = sizeof(struct slb_shadow),
 	},
@@ -76,7 +85,7 @@ struct slb_shadow slb_shadow[] __cacheline_aligned = {
 	.__current = &init_task,					    \
 }
 
-struct paca_struct paca[] = {
+struct paca_struct paca[MAX_CPUS] = {
 	PACA_INIT(0),
 #if NR_CPUS > 1
 	PACA_INIT(  1), PACA_INIT(  2), PACA_INIT(  3),
@@ -98,27 +107,33 @@ struct paca_struct paca[] = {
 	PACA_INIT( 52), PACA_INIT( 53), PACA_INIT( 54), PACA_INIT( 55),
 	PACA_INIT( 56), PACA_INIT( 57), PACA_INIT( 58), PACA_INIT( 59),
 	PACA_INIT( 60), PACA_INIT( 61), PACA_INIT( 62), PACA_INIT( 63),
-#if NR_CPUS > 64
-	PACA_INIT( 64), PACA_INIT( 65), PACA_INIT( 66), PACA_INIT( 67),
-	PACA_INIT( 68), PACA_INIT( 69), PACA_INIT( 70), PACA_INIT( 71),
-	PACA_INIT( 72), PACA_INIT( 73), PACA_INIT( 74), PACA_INIT( 75),
-	PACA_INIT( 76), PACA_INIT( 77), PACA_INIT( 78), PACA_INIT( 79),
-	PACA_INIT( 80), PACA_INIT( 81), PACA_INIT( 82), PACA_INIT( 83),
-	PACA_INIT( 84), PACA_INIT( 85), PACA_INIT( 86), PACA_INIT( 87),
-	PACA_INIT( 88), PACA_INIT( 89), PACA_INIT( 90), PACA_INIT( 91),
-	PACA_INIT( 92), PACA_INIT( 93), PACA_INIT( 94), PACA_INIT( 95),
-	PACA_INIT( 96), PACA_INIT( 97), PACA_INIT( 98), PACA_INIT( 99),
-	PACA_INIT(100), PACA_INIT(101), PACA_INIT(102), PACA_INIT(103),
-	PACA_INIT(104), PACA_INIT(105), PACA_INIT(106), PACA_INIT(107),
-	PACA_INIT(108), PACA_INIT(109), PACA_INIT(110), PACA_INIT(111),
-	PACA_INIT(112), PACA_INIT(113), PACA_INIT(114), PACA_INIT(115),
-	PACA_INIT(116), PACA_INIT(117), PACA_INIT(118), PACA_INIT(119),
-	PACA_INIT(120), PACA_INIT(121), PACA_INIT(122), PACA_INIT(123),
-	PACA_INIT(124), PACA_INIT(125), PACA_INIT(126), PACA_INIT(127),
-#endif
 #endif
 #endif
 #endif
 #endif
 };
 EXPORT_SYMBOL(paca);
+
+/*
+ * The first few (NR_STATIC_PACAS) paca entires are initiialised
+ * statically. populate the rest.
+ */
+void __init initialise_pacas(void)
+{
+	int cpu;
+	unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL;
+
+	/* Can't use for_each_*_cpu, as they aren't functional yet */
+	for (cpu = NR_STATIC_PACAS; cpu < NR_CPUS; cpu++) {
+		struct paca_struct *new_paca = &paca[cpu];
+
+		new_paca->lppaca_ptr = &lppaca[cpu];
+		new_paca->lock_token = 0x8000;
+		new_paca->paca_index = cpu;
+		new_paca->kernel_toc = kernel_toc;
+		new_paca->hw_cpu_id = 0xffff;
+		new_paca->slb_shadow_ptr = &slb_shadow[cpu];
+		new_paca->__current = &init_task;
+
+	}
+}
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 31ada9f..5e382ac 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -170,6 +170,9 @@ void __init setup_paca(int cpu)
 
 void __init early_setup(unsigned long dt_ptr)
 {
+	/* Fill in any unititialised pacas */
+	initialise_pacas();
+
 	/* Identify CPU type */
 	identify_cpu(0, mfspr(SPRN_PVR));
 
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 5fc7fac..f7efaa9 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -220,8 +220,8 @@ config SMP
 	  If you don't know what to do here, say N.
 
 config NR_CPUS
-	int "Maximum number of CPUs (2-128)"
-	range 2 128
+	int "Maximum number of CPUs (2-1024)"
+	range 2 1024
 	depends on SMP
 	default "32" if PPC64
 	default "4"
diff --git a/include/asm-powerpc/paca.h b/include/asm-powerpc/paca.h
index eb61b9c..871f693 100644
--- a/include/asm-powerpc/paca.h
+++ b/include/asm-powerpc/paca.h
@@ -16,10 +16,29 @@
 #define _ASM_POWERPC_PACA_H
 #ifdef __KERNEL__
 
+#include <linux/threads.h>
+
 #include	<asm/types.h>
 #include	<asm/lppaca.h>
 #include	<asm/mmu.h>
 
+/*
+ * iSeries needs the paca to be statically allocated and initialised.
+ * We will allocated this many, based on NR_CPUS.
+ */
+#if   NR_CPUS >= 32
+#define NR_STATIC_PACAS	64
+#elif NR_CPUS > 8
+#define NR_STATIC_PACAS	32
+#elif NR_CPUS > 4
+#define NR_STATIC_PACAS	8
+#elif NR_CPUS > 1
+#define NR_STATIC_PACAS	4
+#else
+#define NR_STATIC_PACAS	1
+#endif
+
+
 register struct paca_struct *local_paca asm("r13");
 
 #if defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_SMP)
@@ -108,6 +127,7 @@ struct paca_struct {
 };
 
 extern struct paca_struct paca[];
+extern void initialise_pacas(void);
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_PACA_H */
-- 
1.5.5

[PATCH 3/3] Move the paca array into the BSS.

[Tony Breeds]

With NR_CPUS=1024
text    data     bss     dec     hex filename
 137 1704032       0 1704169  1a00e9 arch/powerpc/kernel/paca.o :Before
 121 1179744  524288 1704153  1a00d9 arch/powerpc/kernel/paca.o :After

Now that we're not staatically allocating the paca, we don't need the
NR_STATIC_PACAS #define anymore.

Also remove unneeded #includes.

Signed-off-by: Tony Breeds <tony@bakeyournoodle.com>
---
 arch/powerpc/kernel/paca.c |   64 +++-----------------------------------------
 include/asm-powerpc/paca.h |   17 -----------
 2 files changed, 4 insertions(+), 77 deletions(-)

diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 7cd55f2..c4c02c6 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -7,26 +7,11 @@
  *      2 of the License, or (at your option) any later version.
  */
 
-#include <linux/types.h>
 #include <linux/threads.h>
 #include <linux/module.h>
 
-#include <asm/processor.h>
-#include <asm/ptrace.h>
-#include <asm/page.h>
 #include <asm/lppaca.h>
 #include <asm/paca.h>
-#include <asm/mmu.h>
-
-/*
- * In order to handle "strange" values of NR_CPUS, Make sure we use
- * max(NR_CPUS, NR_STATIC_PACAS) for array sizes below
- */
-#if NR_CPUS > NR_STATIC_PACAS
-#define MAX_CPUS	NR_CPUS
-#else
-#define MAX_CPUS	NR_STATIC_PACAS
-#endif
 
 /* This symbol is provided by the linker - let it fill in the paca
  * field correctly */
@@ -42,7 +27,7 @@ extern unsigned long __toc_start;
  * will suffice to ensure that it doesn't cross a page boundary.
  */
 struct lppaca lppaca[] = {
-	[0 ... (MAX_CPUS-1)] = {
+	[0 ... (NR_CPUS-1)] = {
 		.desc = 0xd397d781,	/* "LpPa" */
 		.size = sizeof(struct lppaca),
 		.dyn_proc_status = 2,
@@ -59,7 +44,7 @@ struct lppaca lppaca[] = {
  * initially, hence will all be invaild until we actually write them.
  */
 struct slb_shadow slb_shadow[] __cacheline_aligned = {
-	[0 ... (MAX_CPUS-1)] = {
+	[0 ... (NR_CPUS-1)] = {
 		.persistent = SLB_NUM_BOLTED,
 		.buffer_length = sizeof(struct slb_shadow),
 	},
@@ -74,57 +59,16 @@ struct slb_shadow slb_shadow[] __cacheline_aligned = {
  * processors.  The processor VPD array needs one entry per physical
  * processor (not thread).
  */
-#define PACA_INIT(number)						    \
-{									    \
-	.lppaca_ptr = &lppaca[number],					    \
-	.lock_token = 0x8000,						    \
-	.paca_index = (number),		/* Paca Index */		    \
-	.kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL,		    \
-	.hw_cpu_id = 0xffff,						    \
-	.slb_shadow_ptr = &slb_shadow[number],				    \
-	.__current = &init_task,					    \
-}
-
-struct paca_struct paca[MAX_CPUS] = {
-	PACA_INIT(0),
-#if NR_CPUS > 1
-	PACA_INIT(  1), PACA_INIT(  2), PACA_INIT(  3),
-#if NR_CPUS > 4
-	PACA_INIT(  4), PACA_INIT(  5), PACA_INIT(  6), PACA_INIT(  7),
-#if NR_CPUS > 8
-	PACA_INIT(  8), PACA_INIT(  9), PACA_INIT( 10), PACA_INIT( 11),
-	PACA_INIT( 12), PACA_INIT( 13), PACA_INIT( 14), PACA_INIT( 15),
-	PACA_INIT( 16), PACA_INIT( 17), PACA_INIT( 18), PACA_INIT( 19),
-	PACA_INIT( 20), PACA_INIT( 21), PACA_INIT( 22), PACA_INIT( 23),
-	PACA_INIT( 24), PACA_INIT( 25), PACA_INIT( 26), PACA_INIT( 27),
-	PACA_INIT( 28), PACA_INIT( 29), PACA_INIT( 30), PACA_INIT( 31),
-#if NR_CPUS > 32
-	PACA_INIT( 32), PACA_INIT( 33), PACA_INIT( 34), PACA_INIT( 35),
-	PACA_INIT( 36), PACA_INIT( 37), PACA_INIT( 38), PACA_INIT( 39),
-	PACA_INIT( 40), PACA_INIT( 41), PACA_INIT( 42), PACA_INIT( 43),
-	PACA_INIT( 44), PACA_INIT( 45), PACA_INIT( 46), PACA_INIT( 47),
-	PACA_INIT( 48), PACA_INIT( 49), PACA_INIT( 50), PACA_INIT( 51),
-	PACA_INIT( 52), PACA_INIT( 53), PACA_INIT( 54), PACA_INIT( 55),
-	PACA_INIT( 56), PACA_INIT( 57), PACA_INIT( 58), PACA_INIT( 59),
-	PACA_INIT( 60), PACA_INIT( 61), PACA_INIT( 62), PACA_INIT( 63),
-#endif
-#endif
-#endif
-#endif
-};
+struct paca_struct paca[NR_CPUS];
 EXPORT_SYMBOL(paca);
 
-/*
- * The first few (NR_STATIC_PACAS) paca entires are initiialised
- * statically. populate the rest.
- */
 void __init initialise_pacas(void)
 {
 	int cpu;
 	unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL;
 
 	/* Can't use for_each_*_cpu, as they aren't functional yet */
-	for (cpu = NR_STATIC_PACAS; cpu < NR_CPUS; cpu++) {
+	for (cpu = 0; cpu < NR_CPUS; cpu++) {
 		struct paca_struct *new_paca = &paca[cpu];
 
 		new_paca->lppaca_ptr = &lppaca[cpu];
diff --git a/include/asm-powerpc/paca.h b/include/asm-powerpc/paca.h
index 871f693..0bfc180 100644
--- a/include/asm-powerpc/paca.h
+++ b/include/asm-powerpc/paca.h
@@ -22,23 +22,6 @@
 #include	<asm/lppaca.h>
 #include	<asm/mmu.h>
 
-/*
- * iSeries needs the paca to be statically allocated and initialised.
- * We will allocated this many, based on NR_CPUS.
- */
-#if   NR_CPUS >= 32
-#define NR_STATIC_PACAS	64
-#elif NR_CPUS > 8
-#define NR_STATIC_PACAS	32
-#elif NR_CPUS > 4
-#define NR_STATIC_PACAS	8
-#elif NR_CPUS > 1
-#define NR_STATIC_PACAS	4
-#else
-#define NR_STATIC_PACAS	1
-#endif
-
-
 register struct paca_struct *local_paca asm("r13");
 
 #if defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_SMP)
-- 
1.5.5

[PATCH 2/3] Make iSeries spin on __secondary_hold_spinloop, like pSeries.

[Tony Breeds]

Currently all iSeries secondary CPU's spin directly on the cpu_start in thier
paca.  Make them spin on the global __secondary_hold_spinloop, until after the
pacas have been initialised.

Signed-off-by: Tony Breeds <tony@bakeyournoodle.com>
---
 arch/powerpc/platforms/iseries/exception.S |   27 ++++++++++++++++++++++++++-
 1 files changed, 26 insertions(+), 1 deletions(-)

diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S
index c775cd4..8ff330d 100644
--- a/arch/powerpc/platforms/iseries/exception.S
+++ b/arch/powerpc/platforms/iseries/exception.S
@@ -59,8 +59,33 @@ system_reset_iSeries:
 	andc	r4,r4,r5
 	mtspr	SPRN_CTRLT,r4
 
+/* Spin on __secondary_hold_spinloop until it is updated by the boot cpu. */
+/* In the UP case we'll yeild() later, and we will not access the paca anyway */
+#ifdef CONFIG_SMP
 1:
 	HMT_LOW
+	LOAD_REG_IMMEDIATE(r23, __secondary_hold_spinloop)
+	ld	r23,0(r23)
+	sync
+	LOAD_REG_IMMEDIATE(r3,current_set)
+	sldi	r28,r24,3		/* get current_set[cpu#] */
+	ldx	r3,r3,r28
+	addi	r1,r3,THREAD_SIZE
+	subi	r1,r1,STACK_FRAME_OVERHEAD
+
+	cmpwi	0,r23,0			/* Keep poking the Hypervisor until */
+	bne	2f			/* we're released */
+	/* Let the Hypervisor know we are alive */
+	/* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */
+	lis	r3,0x8002
+	rldicr	r3,r3,32,15		/* r0 = (r3 << 32) & 0xffff000000000000 */
+	li	r0,-1			/* r0=-1 indicates a Hypervisor call */
+	sc				/* Invoke the hypervisor via a system call */
+	b	1b
+#endif
+
+2:
+	HMT_LOW
 #ifdef CONFIG_SMP
 	lbz	r23,PACAPROCSTART(r13)	/* Test if this processor
 					 * should start */
@@ -91,7 +116,7 @@ iSeries_secondary_smp_loop:
 	li	r0,-1			/* r0=-1 indicates a Hypervisor call */
 	sc				/* Invoke the hypervisor via a system call */
 	mfspr	r13,SPRN_SPRG3		/* Put r13 back ???? */
-	b	1b			/* If SMP not configured, secondaries
+	b	2b			/* If SMP not configured, secondaries
 					 * loop forever */
 
 /***  ISeries-LPAR interrupt handlers ***/
-- 
1.5.5

Re: [PATCH 1/3] Raise the upper limit of NR_CPUS.

[Stephen Rothwell]

[-- Attachment #1: Type: text/plain, Size: 588 bytes --]

Hi Tony,

On Tue, 22 Apr 2008 13:30:06 +1000 (EST) Tony Breeds <tony@bakeyournoodle.com> wrote:
>
> +void __init initialise_pacas(void)
> +{
> +	int cpu;
> +	unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL;

This line could do with a comment saying what it is doing ...

> +++ b/include/asm-powerpc/paca.h
>
> +#if   NR_CPUS >= 32
> +#define NR_STATIC_PACAS	64

This allocates 64 pacas etc for NR_CPUS == 32 so surely that test should
be >?

-- 
Cheers,
Stephen Rothwell                    sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/

[-- Attachment #2: Type: application/pgp-signature, Size: 189 bytes --]

Re: [PATCH 2/3] Make iSeries spin on __secondary_hold_spinloop, like pSeries.

[Stephen Rothwell]

[-- Attachment #1: Type: text/plain, Size: 663 bytes --]

Hi Tony,

On Tue, 22 Apr 2008 13:30:06 +1000 (EST) Tony Breeds <tony@bakeyournoodle.com> wrote:
>
> Currently all iSeries secondary CPU's spin directly on the cpu_start in thier
> paca.  Make them spin on the global __secondary_hold_spinloop, until after the
> pacas have been initialised.
> 
> Signed-off-by: Tony Breeds <tony@bakeyournoodle.com>

Acked-by: Stephen Rothwell <sfr@canb.auug.org.au>

(Noting that the __secondary_hold_spinloop variable was already being set
for legacy iSeries even though it was not being used previously.)

-- 
Cheers,
Stephen Rothwell                    sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/

[-- Attachment #2: Type: application/pgp-signature, Size: 189 bytes --]

Re: [PATCH 1/3] Raise the upper limit of NR_CPUS.

[Tony Breeds]

On Tue, Apr 22, 2008 at 01:50:05PM +1000, Stephen Rothwell wrote:
> Hi Tony,
> 
> On Tue, 22 Apr 2008 13:30:06 +1000 (EST) Tony Breeds <tony@bakeyournoodle.com> wrote:
> >
> > +void __init initialise_pacas(void)
> > +{
> > +	int cpu;
> > +	unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL;
> 
> This line could do with a comment saying what it is doing ...

It does need a comment I agree, but I don't think I can do it justice :)
... I just used what was already there.
 
> > +++ b/include/asm-powerpc/paca.h
> >
> > +#if   NR_CPUS >= 32
> > +#define NR_STATIC_PACAS	64
> 
> This allocates 64 pacas etc for NR_CPUS == 32 so surely that test should
> be >?

Yes it should be.

Yours Tony

  linux.conf.au    http://www.marchsouth.org/
  Jan 19 - 24 2009 The Australian Linux Technical Conference!

Re: [PATCH 1/3] Raise the upper limit of NR_CPUS.

[Segher Boessenkool]

>>> +	unsigned long kernel_toc = (unsigned long)(&__toc_start) + 
>>> 0x8000UL;
>>
>> This line could do with a comment saying what it is doing ...
>
> It does need a comment I agree, but I don't think I can do it justice 
> :)
> ... I just used what was already there.

Here, have one:

"The TOC register (GPR2) points 32kB into the TOC, so that 64kB
of the TOC can be addressed using a single machine instruction."

or, perhaps simpler:

"The TOC register (GPR2) points 32kB into the TOC, because the
ABI says so."


Segher