From 0b05ac6e24807f0c26f763b3a546c0bcbf84125f Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Mon, 4 Apr 2011 13:46:58 +1000
Subject: powerpc/xics: Rewrite XICS driver

This is a significant rework of the XICS driver, too significant to
conveniently break it up into a series of smaller patches to be honest.

The driver is moved to a more generic location to allow new platforms
to use it, and is broken up into separate ICP and ICS "backends". For
now we have the native and "hypervisor" ICP backends and one common
RTAS ICS backend.

The driver supports one ICP backend instanciation, and many ICS ones,
in order to accomodate future platforms with multiple possibly different
interrupt "sources" mechanisms.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/irq.h  |   6 ++
 arch/powerpc/include/asm/xics.h | 139 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 145 insertions(+)
 create mode 100644 arch/powerpc/include/asm/xics.h

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 67ab5fb7d15..47b7905a636 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -142,6 +142,12 @@ extern struct irq_map_entry irq_map[NR_IRQS];
 
 extern irq_hw_number_t virq_to_hw(unsigned int virq);
 
+/* This will eventually -replace- virq_to_hw if/when we stash the
+ * HW number in the irq_data itself. We use a macro so we can inline
+ * it as irq_data isn't defined yet
+ */
+#define irq_data_to_hw(d) (irq_map[(d)->irq].hwirq)
+
 /**
  * irq_alloc_host - Allocate a new irq_host data structure
  * @of_node: optional device-tree node of the interrupt controller
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
new file mode 100644
index 00000000000..146aad8534d
--- /dev/null
+++ b/arch/powerpc/include/asm/xics.h
@@ -0,0 +1,139 @@
+/*
+ * Common definitions accross all variants of ICP and ICS interrupt
+ * controllers.
+ */
+
+#ifndef _XICS_H
+#define _XICS_H
+
+#define XICS_IPI		2
+#define XICS_IRQ_SPURIOUS	0
+
+/* Want a priority other than 0.  Various HW issues require this. */
+#define	DEFAULT_PRIORITY	5
+
+/*
+ * Mark IPIs as higher priority so we can take them inside interrupts that
+ * arent marked IRQF_DISABLED
+ */
+#define IPI_PRIORITY		4
+
+/* The least favored priority */
+#define LOWEST_PRIORITY		0xFF
+
+/* The number of priorities defined above */
+#define MAX_NUM_PRIORITIES	3
+
+/* Native ICP */
+extern int icp_native_init(void);
+
+/* PAPR ICP */
+extern int icp_hv_init(void);
+
+/* ICP ops */
+struct icp_ops {
+	unsigned int (*get_irq)(void);
+	void (*eoi)(struct irq_data *d);
+	void (*set_priority)(unsigned char prio);
+	void (*teardown_cpu)(void);
+	void (*flush_ipi)(void);
+#ifdef CONFIG_SMP
+	void (*message_pass)(int target, int msg);
+	irq_handler_t ipi_action;
+#endif
+};
+
+extern const struct icp_ops *icp_ops;
+
+/* Native ICS */
+extern int ics_native_init(void);
+
+/* RTAS ICS */
+extern int ics_rtas_init(void);
+
+/* ICS instance, hooked up to chip_data of an irq */
+struct ics {
+	struct list_head link;
+	int (*map)(struct ics *ics, unsigned int virq);
+	void (*mask_unknown)(struct ics *ics, unsigned long vec);
+	long (*get_server)(struct ics *ics, unsigned long vec);
+	char data[];
+};
+
+/* Commons */
+extern unsigned int xics_default_server;
+extern unsigned int xics_default_distrib_server;
+extern unsigned int xics_interrupt_server_size;
+extern struct irq_host *xics_host;
+
+struct xics_cppr {
+	unsigned char stack[MAX_NUM_PRIORITIES];
+	int index;
+};
+
+DECLARE_PER_CPU(struct xics_cppr, xics_cppr);
+
+static inline void xics_push_cppr(unsigned int vec)
+{
+	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+
+	if (WARN_ON(os_cppr->index >= MAX_NUM_PRIORITIES - 1))
+		return;
+
+	if (vec == XICS_IPI)
+		os_cppr->stack[++os_cppr->index] = IPI_PRIORITY;
+	else
+		os_cppr->stack[++os_cppr->index] = DEFAULT_PRIORITY;
+}
+
+static inline unsigned char xics_pop_cppr(void)
+{
+	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+
+	if (WARN_ON(os_cppr->index < 1))
+		return LOWEST_PRIORITY;
+
+	return os_cppr->stack[--os_cppr->index];
+}
+
+static inline void xics_set_base_cppr(unsigned char cppr)
+{
+	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+
+	/* we only really want to set the priority when there's
+	 * just one cppr value on the stack
+	 */
+	WARN_ON(os_cppr->index != 0);
+
+	os_cppr->stack[0] = cppr;
+}
+
+static inline unsigned char xics_cppr_top(void)
+{
+	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+	
+	return os_cppr->stack[os_cppr->index];
+}
+
+DECLARE_PER_CPU_SHARED_ALIGNED(unsigned long, xics_ipi_message);
+
+extern void xics_init(void);
+extern void xics_setup_cpu(void);
+extern void xics_update_irq_servers(void);
+extern void xics_set_cpu_giq(unsigned int gserver, unsigned int join);
+extern void xics_mask_unknown_vec(unsigned int vec);
+extern irqreturn_t xics_ipi_dispatch(int cpu);
+extern int xics_smp_probe(void);
+extern void xics_register_ics(struct ics *ics);
+extern void xics_teardown_cpu(void);
+extern void xics_kexec_teardown_cpu(int secondary);
+extern void xics_migrate_irqs_away(void);
+#ifdef CONFIG_SMP
+extern int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask,
+			       unsigned int strict_check);
+#else
+#define xics_get_irq_server(virq, cpumask, strict_check) (xics_default_server)
+#endif
+
+
+#endif /* _XICS_H */
-- 
cgit v1.2.3-70-g09d2


From 50fb8ebe7c4ad60d147700d253f78bd1e615a526 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Wed, 12 Jan 2011 17:41:28 +1100
Subject: powerpc: Add more Power7 specific definitions

This adds more SPR definitions used on newer processors when running
in hypervisor mode. Along with some other P7 specific bits and pieces

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/ppc_asm.h |  1 +
 arch/powerpc/include/asm/reg.h     | 46 +++++++++++++++++++++++++++++++++++++-
 2 files changed, 46 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 98210067c1c..1b422381fc1 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -170,6 +170,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #define HMT_MEDIUM	or	2,2,2
 #define HMT_MEDIUM_HIGH or	5,5,5		# medium high priority
 #define HMT_HIGH	or	3,3,3
+#define HMT_EXTRA_HIGH	or	7,7,7		# power7 only
 
 #ifdef __KERNEL__
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 7e4abebe76c..6eb1d77edb4 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -210,8 +210,43 @@
 #define SPRN_TBWL	0x11C	/* Time Base Lower Register (super, R/W) */
 #define SPRN_TBWU	0x11D	/* Time Base Upper Register (super, R/W) */
 #define SPRN_SPURR	0x134	/* Scaled PURR */
+#define SPRN_HSPRG0	0x130	/* Hypervisor Scratch 0 */
+#define SPRN_HSPRG1	0x131	/* Hypervisor Scratch 1 */
+#define SPRN_HDSISR     0x132
+#define SPRN_HDAR       0x133
+#define SPRN_HDEC	0x136	/* Hypervisor Decrementer */
 #define SPRN_HIOR	0x137	/* 970 Hypervisor interrupt offset */
+#define SPRN_RMOR	0x138	/* Real mode offset register */
+#define SPRN_HRMOR	0x139	/* Real mode offset register */
+#define SPRN_HSRR0	0x13A	/* Hypervisor Save/Restore 0 */
+#define SPRN_HSRR1	0x13B	/* Hypervisor Save/Restore 1 */
 #define SPRN_LPCR	0x13E	/* LPAR Control Register */
+#define   LPCR_VPM0	(1ul << (63-0))
+#define   LPCR_VPM1	(1ul << (63-1))
+#define   LPCR_ISL	(1ul << (63-2))
+#define   LPCR_DPFD_SH	(63-11)
+#define   LPCR_VRMA_L	(1ul << (63-12))
+#define   LPCR_VRMA_LP0	(1ul << (63-15))
+#define   LPCR_VRMA_LP1	(1ul << (63-16))
+#define   LPCR_RMLS    0x1C000000      /* impl dependent rmo limit sel */
+#define   LPCR_ILE     0x02000000      /* !HV irqs set MSR:LE */
+#define   LPCR_PECE	0x00007000	/* powersave exit cause enable */
+#define     LPCR_PECE0	0x00004000	/* ext. exceptions can cause exit */
+#define     LPCR_PECE1	0x00002000	/* decrementer can cause exit */
+#define     LPCR_PECE2	0x00001000	/* machine check etc can cause exit */
+#define   LPCR_MER	0x00000800	/* Mediated External Exception */
+#define   LPCR_LPES0   0x00000008      /* LPAR Env selector 0 */
+#define   LPCR_LPES1   0x00000004      /* LPAR Env selector 1 */
+#define   LPCR_RMI     0x00000002      /* real mode is cache inhibit */
+#define   LPCR_HDICE   0x00000001      /* Hyp Decr enable (HV,PR,EE) */
+#define SPRN_LPID	0x13F	/* Logical Partition Identifier */
+#define	SPRN_HMER	0x150	/* Hardware m? error recovery */
+#define	SPRN_HMEER	0x151	/* Hardware m? enable error recovery */
+#define	SPRN_HEIR	0x153	/* Hypervisor Emulated Instruction Register */
+#define SPRN_TLBINDEXR	0x154	/* P7 TLB control register */
+#define SPRN_TLBVPNR	0x155	/* P7 TLB control register */
+#define SPRN_TLBRPNR	0x156	/* P7 TLB control register */
+#define SPRN_TLBLPIDR	0x157	/* P7 TLB control register */
 #define SPRN_DBAT0L	0x219	/* Data BAT 0 Lower Register */
 #define SPRN_DBAT0U	0x218	/* Data BAT 0 Upper Register */
 #define SPRN_DBAT1L	0x21B	/* Data BAT 1 Lower Register */
@@ -434,16 +469,23 @@
 #define SPRN_SRR0	0x01A	/* Save/Restore Register 0 */
 #define SPRN_SRR1	0x01B	/* Save/Restore Register 1 */
 #define   SRR1_WAKEMASK		0x00380000 /* reason for wakeup */
-#define   SRR1_WAKERESET	0x00380000 /* System reset */
 #define   SRR1_WAKESYSERR	0x00300000 /* System error */
 #define   SRR1_WAKEEE		0x00200000 /* External interrupt */
 #define   SRR1_WAKEMT		0x00280000 /* mtctrl */
+#define	  SRR1_WAKEHMI		0x00280000 /* Hypervisor maintenance */
 #define   SRR1_WAKEDEC		0x00180000 /* Decrementer interrupt */
 #define   SRR1_WAKETHERM	0x00100000 /* Thermal management interrupt */
+#define	  SRR1_WAKERESET	0x00100000 /* System reset */
+#define	  SRR1_WAKESTATE	0x00030000 /* Powersave exit mask [46:47] */
+#define	  SRR1_WS_DEEPEST	0x00030000 /* Some resources not maintained,
+					  * may not be recoverable */
+#define	  SRR1_WS_DEEPER	0x00020000 /* Some resources not maintained */
+#define	  SRR1_WS_DEEP		0x00010000 /* All resources maintained */
 #define   SRR1_PROGFPE		0x00100000 /* Floating Point Enabled */
 #define   SRR1_PROGPRIV		0x00040000 /* Privileged instruction */
 #define   SRR1_PROGTRAP		0x00020000 /* Trap */
 #define   SRR1_PROGADDR		0x00010000 /* SRR0 contains subsequent addr */
+
 #define SPRN_HSRR0	0x13A	/* Save/Restore Register 0 */
 #define SPRN_HSRR1	0x13B	/* Save/Restore Register 1 */
 
@@ -894,6 +936,8 @@
 #define PV_POWER5p	0x003B
 #define PV_POWER7	0x003F
 #define PV_970FX	0x003C
+#define PV_POWER6	0x003E
+#define PV_POWER7	0x003F
 #define PV_630		0x0040
 #define PV_630p	0x0041
 #define PV_970MP	0x0044
-- 
cgit v1.2.3-70-g09d2


From 24cc67de62eebbda3ce0c46bdd56582c00dccd03 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 20 Jan 2011 18:50:55 +1100
Subject: powerpc: Define CPU feature for Architected 2.06 HV mode

This bit indicates that we are operating in hypervisor mode on a CPU
compliant to architecture 2.06 or later (currently server only).

We set it on POWER7 and have a boot-time CPU setup function that
clears it if MSR:HV isn't set (booting under a hypervisor).

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/cputable.h    |  3 +-
 arch/powerpc/kernel/Makefile           |  1 +
 arch/powerpc/kernel/cpu_setup_power7.S | 65 ++++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/cputable.c         |  6 ++++
 4 files changed, 74 insertions(+), 1 deletion(-)
 create mode 100644 arch/powerpc/kernel/cpu_setup_power7.S

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 1833d1a07e7..2fe37d78193 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -181,6 +181,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_SLB			LONG_ASM_CONST(0x0000000100000000)
 #define CPU_FTR_16M_PAGE		LONG_ASM_CONST(0x0000000200000000)
 #define CPU_FTR_TLBIEL			LONG_ASM_CONST(0x0000000400000000)
+#define CPU_FTR_HVMODE_206		LONG_ASM_CONST(0x0000000800000000)
 #define CPU_FTR_IABR			LONG_ASM_CONST(0x0000002000000000)
 #define CPU_FTR_MMCRA			LONG_ASM_CONST(0x0000004000000000)
 #define CPU_FTR_CTRL			LONG_ASM_CONST(0x0000008000000000)
@@ -418,7 +419,7 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB)
 #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_HVMODE_206 |\
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 3bb2a3e6a33..7c6eb4974f2 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -38,6 +38,7 @@ obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   paca.o nvram_64.o firmware.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power7.o
 obj64-$(CONFIG_RELOCATABLE)	+= reloc_64.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
 obj-$(CONFIG_PPC64)		+= vdso64/
diff --git a/arch/powerpc/kernel/cpu_setup_power7.S b/arch/powerpc/kernel/cpu_setup_power7.S
new file mode 100644
index 00000000000..f2b317817c4
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_setup_power7.S
@@ -0,0 +1,65 @@
+/*
+ * This file contains low level CPU setup functions.
+ *    Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/cache.h>
+
+/* Entry: r3 = crap, r4 = ptr to cputable entry
+ *
+ * Note that we can be called twice for pseudo-PVRs
+ */
+_GLOBAL(__setup_cpu_power7)
+	mflr	r11
+	bl	__init_hvmode_206
+	mtlr	r11
+	beqlr
+	bl	__init_LPCR
+	mtlr	r11
+	blr
+
+_GLOBAL(__restore_cpu_power7)
+	mflr	r11
+	mfmsr	r3
+	rldicl.	r0,r3,4,63
+	beqlr
+	bl	__init_LPCR
+	mtlr	r11
+	blr
+
+__init_hvmode_206:
+	/* Disable CPU_FTR_HVMODE_206 and exit if MSR:HV is not set */
+	mfmsr	r3
+	rldicl.	r0,r3,4,63
+	bnelr
+	ld	r5,CPU_SPEC_FEATURES(r4)
+	LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE_206)
+	xor	r5,r5,r6
+	std	r5,CPU_SPEC_FEATURES(r4)
+	blr
+
+__init_LPCR:
+	/* Setup a sane LPCR:
+	 *
+	 *   LPES = 0b11 (SRR0/1 used for 0x500)
+	 *   PECE = 0b111
+	 *
+	 * Other bits untouched for now
+	 */
+	mfspr	r3,SPRN_LPCR
+	ori	r3,r3,(LPCR_LPES0|LPCR_LPES1)
+	ori	r3,r3,(LPCR_PECE0|LPCR_PECE1|LPCR_PECE2)
+	mtspr	SPRN_LPCR,r3
+	isync
+	blr
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index b9602ee06de..b65b4908d3c 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -423,6 +423,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.oprofile_type		= PPC_OPROFILE_POWER4,
 		.oprofile_cpu_type	= "ppc64/ibm-compat-v1",
+		.cpu_setup		= __setup_cpu_power7,
+		.cpu_restore		= __restore_cpu_power7,
 		.platform		= "power7",
 	},
 	{	/* Power7 */
@@ -439,6 +441,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.pmc_type		= PPC_PMC_IBM,
 		.oprofile_cpu_type	= "ppc64/power7",
 		.oprofile_type		= PPC_OPROFILE_POWER4,
+		.cpu_setup		= __setup_cpu_power7,
+		.cpu_restore		= __restore_cpu_power7,
 		.platform		= "power7",
 	},
 	{	/* Power7+ */
@@ -455,6 +459,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.pmc_type		= PPC_PMC_IBM,
 		.oprofile_cpu_type	= "ppc64/power7",
 		.oprofile_type		= PPC_OPROFILE_POWER4,
+		.cpu_setup		= __setup_cpu_power7,
+		.cpu_restore		= __restore_cpu_power7,
 		.platform		= "power7+",
 	},
 	{	/* Cell Broadband Engine */
-- 
cgit v1.2.3-70-g09d2


From 2dd60d79e0202628a47af9812a84d502cc63628c Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 20 Jan 2011 17:50:21 +1100
Subject: powerpc: In HV mode, use HSPRG0 for PACA

When running in Hypervisor mode (arch 2.06 or later), we store the PACA
in HSPRG0 instead of SPRG1. The architecture specifies that SPRGs may be
lost during a "nap" power management operation (though they aren't
currently on POWER7) and this enables use of SPRG1 by KVM guests.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/exception-64s.h |  6 +++---
 arch/powerpc/include/asm/reg.h           | 27 ++++++++++++++++++++++++++-
 arch/powerpc/kernel/entry_64.S           |  4 ++--
 arch/powerpc/kernel/exceptions-64s.S     |  8 ++++----
 arch/powerpc/kernel/head_64.S            |  4 ++--
 arch/powerpc/kernel/paca.c               | 13 ++++++++++++-
 arch/powerpc/kvm/book3s_rmhandlers.S     |  4 +---
 7 files changed, 50 insertions(+), 16 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 7778d6f0c87..337b6fa2f8c 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -56,8 +56,8 @@
 #define LOAD_HANDLER(reg, label)					\
 	addi	reg,reg,(label)-_stext;	/* virt addr of handler ... */
 
-#define EXCEPTION_PROLOG_1(area)				\
-	mfspr	r13,SPRN_SPRG_PACA;	/* get paca address into r13 */	\
+#define EXCEPTION_PROLOG_1(area)					\
+	GET_PACA(r13);							\
 	std	r9,area+EX_R9(r13);	/* save r9 - r12 */		\
 	std	r10,area+EX_R10(r13);					\
 	std	r11,area+EX_R11(r13);					\
@@ -174,7 +174,7 @@ label##_pSeries:							\
 	HMT_MEDIUM;							\
 	DO_KVM	n;							\
 	mtspr	SPRN_SPRG_SCRATCH0,r13;	/* save r13 */			\
-	mfspr	r13,SPRN_SPRG_PACA;	/* get paca address into r13 */	\
+	GET_PACA(r13);							\
 	std	r9,PACA_EXGEN+EX_R9(r13);	/* save r9, r10 */	\
 	std	r10,PACA_EXGEN+EX_R10(r13);				\
 	lbz	r10,PACASOFTIRQEN(r13);					\
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 6eb1d77edb4..13429a0eba0 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -715,12 +715,15 @@
  * SPRG usage:
  *
  * All 64-bit:
- *	- SPRG1 stores PACA pointer
+ *	- SPRG1 stores PACA pointer except 64-bit server in
+ *        HV mode in which case it is HSPRG0
  *
  * 64-bit server:
  *	- SPRG0 unused (reserved for HV on Power4)
  *	- SPRG2 scratch for exception vectors
  *	- SPRG3 unused (user visible)
+ *      - HSPRG0 stores PACA in HV mode
+ *      - HSPRG1 scratch for "HV" exceptions
  *
  * 64-bit embedded
  *	- SPRG0 generic exception scratch
@@ -783,6 +786,22 @@
 
 #ifdef CONFIG_PPC_BOOK3S_64
 #define SPRN_SPRG_SCRATCH0	SPRN_SPRG2
+#define SPRN_SPRG_HPACA		SPRN_HSPRG0
+#define SPRN_SPRG_HSCRATCH0	SPRN_HSPRG1
+
+#define GET_PACA(rX)					\
+	BEGIN_FTR_SECTION_NESTED(66);			\
+	mfspr	rX,SPRN_SPRG_PACA;			\
+	FTR_SECTION_ELSE_NESTED(66);			\
+	mfspr	rX,SPRN_SPRG_HPACA;			\
+	ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66)
+
+#define SET_PACA(rX)					\
+	BEGIN_FTR_SECTION_NESTED(66);			\
+	mtspr	SPRN_SPRG_PACA,rX;			\
+	FTR_SECTION_ELSE_NESTED(66);			\
+	mtspr	SPRN_SPRG_HPACA,rX;			\
+	ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66)
 #endif
 
 #ifdef CONFIG_PPC_BOOK3E_64
@@ -792,6 +811,10 @@
 #define SPRN_SPRG_TLB_EXFRAME	SPRN_SPRG2
 #define SPRN_SPRG_TLB_SCRATCH	SPRN_SPRG6
 #define SPRN_SPRG_GEN_SCRATCH	SPRN_SPRG0
+
+#define SET_PACA(rX)	mtspr	SPRN_SPRG_PACA,rX
+#define GET_PACA(rX)	mfspr	rX,SPRN_SPRG_PACA
+
 #endif
 
 #ifdef CONFIG_PPC_BOOK3S_32
@@ -842,6 +865,8 @@
 #define SPRN_SPRG_SCRATCH1	SPRN_SPRG1
 #endif
 
+
+
 /*
  * An mtfsf instruction with the L bit set. On CPUs that support this a
  * full 64bits of FPSCR is restored and on other CPUs the L bit is ignored.
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index d82878c4daa..dbf5bfafd7b 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -838,7 +838,7 @@ _GLOBAL(enter_rtas)
 
 _STATIC(rtas_return_loc)
 	/* relocation is off at this point */
-	mfspr	r4,SPRN_SPRG_PACA	/* Get PACA */
+	GET_PACA(r4)
 	clrldi	r4,r4,2			/* convert to realmode address */
 
 	bcl	20,31,$+4
@@ -869,7 +869,7 @@ _STATIC(rtas_restore_regs)
 	REST_8GPRS(14, r1)		/* Restore the non-volatiles */
 	REST_10GPRS(22, r1)		/* ditto */
 
-	mfspr	r13,SPRN_SPRG_PACA
+	GET_PACA(r13)
 
 	ld	r4,_CCR(r1)
 	mtcr	r4
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index aeb739e1876..6784bf7090f 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -53,7 +53,7 @@ data_access_pSeries:
 	DO_KVM	0x300
 	mtspr	SPRN_SPRG_SCRATCH0,r13
 BEGIN_FTR_SECTION
-	mfspr	r13,SPRN_SPRG_PACA
+	GET_PACA(r13)
 	std	r9,PACA_EXSLB+EX_R9(r13)
 	std	r10,PACA_EXSLB+EX_R10(r13)
 	mfspr	r10,SPRN_DAR
@@ -82,7 +82,7 @@ data_access_slb_pSeries:
 	HMT_MEDIUM
 	DO_KVM	0x380
 	mtspr	SPRN_SPRG_SCRATCH0,r13
-	mfspr	r13,SPRN_SPRG_PACA		/* get paca address into r13 */
+	GET_PACA(r13)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_DAR
 	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
@@ -121,7 +121,7 @@ instruction_access_slb_pSeries:
 	HMT_MEDIUM
 	DO_KVM	0x480
 	mtspr	SPRN_SPRG_SCRATCH0,r13
-	mfspr	r13,SPRN_SPRG_PACA		/* get paca address into r13 */
+	GET_PACA(r13)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
 	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
@@ -165,7 +165,7 @@ BEGIN_FTR_SECTION
 	beq-	1f
 END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	mr	r9,r13
-	mfspr	r13,SPRN_SPRG_PACA
+	GET_PACA(r13)
 	mfspr	r11,SPRN_SRR0
 	ld	r12,PACAKBASE(r13)
 	ld	r10,PACAKMSR(r13)
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 3a319f9c9d3..39a40400f3f 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -228,7 +228,7 @@ generic_secondary_common_init:
 	mr	r3,r24			/* not found, copy phys to r3	 */
 	b	.kexec_wait		/* next kernel might do better	 */
 
-2:	mtspr	SPRN_SPRG_PACA,r13	/* Save vaddr of paca in an SPRG */
+2:	SET_PACA(r13)
 #ifdef CONFIG_PPC_BOOK3E
 	addi	r12,r13,PACA_EXTLB	/* and TLB exc frame in another  */
 	mtspr	SPRN_SPRG_TLB_EXFRAME,r12
@@ -534,7 +534,7 @@ _GLOBAL(pmac_secondary_start)
 	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.		*/
-	mtspr	SPRN_SPRG_PACA,r13	/* Save vaddr of paca in an SPRG*/
+	SET_PACA(r13)			/* Save vaddr of paca in an SPRG*/
 
 	/* Mark interrupts soft and hard disabled (they might be enabled
 	 * in the PACA when doing hotplug)
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 10f0aadee95..102244edecf 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -156,11 +156,22 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 /* Put the paca pointer into r13 and SPRG_PACA */
 void setup_paca(struct paca_struct *new_paca)
 {
+	/* Setup r13 */
 	local_paca = new_paca;
-	mtspr(SPRN_SPRG_PACA, local_paca);
+
 #ifdef CONFIG_PPC_BOOK3E
+	/* On Book3E, initialize the TLB miss exception frames */
 	mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb);
+#else
+	/* In HV mode, we setup both HPACA and PACA to avoid problems
+	 * if we do a GET_PACA() before the feature fixups have been
+	 * applied
+	 */
+	if (cpu_has_feature(CPU_FTR_HVMODE_206))
+		mtspr(SPRN_SPRG_HPACA, local_paca);
 #endif
+	mtspr(SPRN_SPRG_PACA, local_paca);
+
 }
 
 static int __initdata paca_size;
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 2b9c9088d00..b0ff5ff76e2 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -35,9 +35,7 @@
 
 #if defined(CONFIG_PPC_BOOK3S_64)
 
-#define LOAD_SHADOW_VCPU(reg)				\
-	mfspr	reg, SPRN_SPRG_PACA
-
+#define LOAD_SHADOW_VCPU(reg)	GET_PACA(reg)					
 #define SHADOW_VCPU_OFF		PACA_KVM_SVCPU
 #define MSR_NOIRQ		MSR_KERNEL & ~(MSR_IR | MSR_DR)
 #define FUNC(name) 		GLUE(.,name)
-- 
cgit v1.2.3-70-g09d2


From a5d4f3ad3a28cf046836b9bfae61d532b8f77036 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 5 Apr 2011 14:20:31 +1000
Subject: powerpc: Base support for exceptions using HSRR0/1

Pass the register type to the prolog, also provides alternate "HV"
version of hardware interrupt (0x500) and adjust LPES accordingly

We tag those interrupts by setting bit 0x2 in the trap number

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/exception-64s.h   | 65 +++++++++++++++---------------
 arch/powerpc/include/asm/kvm_asm.h         |  1 +
 arch/powerpc/include/asm/kvm_book3s_asm.h  |  1 +
 arch/powerpc/kernel/cpu_setup_power7.S     |  3 +-
 arch/powerpc/kernel/exceptions-64s.S       | 48 +++++++++++++++++-----
 arch/powerpc/kvm/book3s_rmhandlers.S       |  1 +
 arch/powerpc/kvm/book3s_segment.S          | 10 ++++-
 arch/powerpc/platforms/iseries/exception.S |  2 +-
 arch/powerpc/platforms/iseries/exception.h |  4 +-
 9 files changed, 86 insertions(+), 49 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 337b6fa2f8c..1d98e05be51 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -56,30 +56,37 @@
 #define LOAD_HANDLER(reg, label)					\
 	addi	reg,reg,(label)-_stext;	/* virt addr of handler ... */
 
-#define EXCEPTION_PROLOG_1(area)					\
+/* Exception register prefixes */
+#define EXC_HV	H
+#define EXC_STD
+
+#define __EXCEPTION_PROLOG_1(area, h)					\
 	GET_PACA(r13);							\
 	std	r9,area+EX_R9(r13);	/* save r9 - r12 */		\
 	std	r10,area+EX_R10(r13);					\
 	std	r11,area+EX_R11(r13);					\
 	std	r12,area+EX_R12(r13);					\
-	mfspr	r9,SPRN_SPRG_SCRATCH0;					\
+	mfspr	r9,SPRN_SPRG_##h##SCRATCH0;				\
 	std	r9,area+EX_R13(r13);					\
 	mfcr	r9
+#define EXCEPTION_PROLOG_1(area, h) __EXCEPTION_PROLOG_1(area, h)
 
-#define EXCEPTION_PROLOG_PSERIES_1(label)				\
+#define __EXCEPTION_PROLOG_PSERIES_1(label, h)				\
 	ld	r12,PACAKBASE(r13);	/* get high part of &label */	\
 	ld	r10,PACAKMSR(r13);	/* get MSR value for kernel */	\
-	mfspr	r11,SPRN_SRR0;		/* save SRR0 */			\
+	mfspr	r11,SPRN_##h##SRR0;	/* save SRR0 */			\
 	LOAD_HANDLER(r12,label)						\
-	mtspr	SPRN_SRR0,r12;						\
-	mfspr	r12,SPRN_SRR1;		/* and SRR1 */			\
-	mtspr	SPRN_SRR1,r10;						\
-	rfid;								\
+	mtspr	SPRN_##h##SRR0,r12;					\
+	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
+	mtspr	SPRN_##h##SRR1,r10;					\
+	h##rfid;							\
 	b	.	/* prevent speculative execution */
+#define EXCEPTION_PROLOG_PSERIES_1(label, h) \
+	__EXCEPTION_PROLOG_PSERIES_1(label, h)
 
-#define EXCEPTION_PROLOG_PSERIES(area, label)				\
-	EXCEPTION_PROLOG_1(area);					\
-	EXCEPTION_PROLOG_PSERIES_1(label);
+#define EXCEPTION_PROLOG_PSERIES(area, label, h)			\
+	EXCEPTION_PROLOG_1(area, h);					\
+	EXCEPTION_PROLOG_PSERIES_1(label, h);
 
 /*
  * The common exception prolog is used for all except a few exceptions
@@ -150,50 +157,44 @@ label##_pSeries:					\
 	HMT_MEDIUM;					\
 	DO_KVM	n;					\
 	mtspr	SPRN_SPRG_SCRATCH0,r13;		/* save r13 */	\
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, EXC_STD)
 
 #define HSTD_EXCEPTION_PSERIES(n, label)		\
 	. = n;						\
 	.globl label##_pSeries;				\
 label##_pSeries:					\
 	HMT_MEDIUM;					\
-	mtspr	SPRN_SPRG_SCRATCH0,r20;	/* save r20 */	\
-	mfspr	r20,SPRN_HSRR0;		/* copy HSRR0 to SRR0 */ \
-	mtspr	SPRN_SRR0,r20;				\
-	mfspr	r20,SPRN_HSRR1;		/* copy HSRR0 to SRR0 */ \
-	mtspr	SPRN_SRR1,r20;				\
-	mfspr	r20,SPRN_SPRG_SCRATCH0;	/* restore r20 */ \
-	mtspr	SPRN_SPRG_SCRATCH0,r13;		/* save r13 */	\
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common)
+	DO_KVM	n;					\
+	mtspr	SPRN_SPRG_HSCRATCH0,r13;/* save r13 */	\
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, EXC_HV)
 
 
-#define MASKABLE_EXCEPTION_PSERIES(n, label)				\
-	. = n;								\
-	.globl label##_pSeries;						\
-label##_pSeries:							\
+#define __MASKABLE_EXCEPTION_PSERIES(n, label, h)			\
 	HMT_MEDIUM;							\
 	DO_KVM	n;							\
-	mtspr	SPRN_SPRG_SCRATCH0,r13;	/* save r13 */			\
+	mtspr	SPRN_SPRG_##h##SCRATCH0,r13;    /* save r13 */		\
 	GET_PACA(r13);							\
 	std	r9,PACA_EXGEN+EX_R9(r13);	/* save r9, r10 */	\
 	std	r10,PACA_EXGEN+EX_R10(r13);				\
 	lbz	r10,PACASOFTIRQEN(r13);					\
 	mfcr	r9;							\
 	cmpwi	r10,0;							\
-	beq	masked_interrupt;					\
-	mfspr	r10,SPRN_SPRG_SCRATCH0;					\
+	beq	masked_##h##interrupt;					\
+	mfspr	r10,SPRN_SPRG_##h##SCRATCH0;				\
 	std	r10,PACA_EXGEN+EX_R13(r13);				\
 	std	r11,PACA_EXGEN+EX_R11(r13);				\
 	std	r12,PACA_EXGEN+EX_R12(r13);				\
 	ld	r12,PACAKBASE(r13);	/* get high part of &label */	\
 	ld	r10,PACAKMSR(r13);	/* get MSR value for kernel */	\
-	mfspr	r11,SPRN_SRR0;		/* save SRR0 */			\
+	mfspr	r11,SPRN_##h##SRR0;	/* save SRR0 */			\
 	LOAD_HANDLER(r12,label##_common)				\
-	mtspr	SPRN_SRR0,r12;						\
-	mfspr	r12,SPRN_SRR1;		/* and SRR1 */			\
-	mtspr	SPRN_SRR1,r10;						\
-	rfid;								\
+	mtspr	SPRN_##h##SRR0,r12;					\
+	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
+	mtspr	SPRN_##h##SRR1,r10;					\
+	h##rfid;							\
 	b	.	/* prevent speculative execution */
+#define MASKABLE_EXCEPTION_PSERIES(n, label, h)				\
+	__MASKABLE_EXCEPTION_PSERIES(n, label, h)
 
 #ifdef CONFIG_PPC_ISERIES
 #define DISABLE_INTS				\
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 5b750467439..0951b17f4eb 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -59,6 +59,7 @@
 #define BOOK3S_INTERRUPT_INST_SEGMENT	0x480
 #define BOOK3S_INTERRUPT_EXTERNAL	0x500
 #define BOOK3S_INTERRUPT_EXTERNAL_LEVEL	0x501
+#define BOOK3S_INTERRUPT_EXTERNAL_HV	0x502
 #define BOOK3S_INTERRUPT_ALIGNMENT	0x600
 #define BOOK3S_INTERRUPT_PROGRAM	0x700
 #define BOOK3S_INTERRUPT_FP_UNAVAIL	0x800
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 36fdb3aff30..d5a8a386163 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -34,6 +34,7 @@
 	    (\intno == BOOK3S_INTERRUPT_DATA_SEGMENT) || \
 	    (\intno == BOOK3S_INTERRUPT_INST_SEGMENT) || \
 	    (\intno == BOOK3S_INTERRUPT_EXTERNAL) || \
+	    (\intno == BOOK3S_INTERRUPT_EXTERNAL_HV) || \
 	    (\intno == BOOK3S_INTERRUPT_ALIGNMENT) || \
 	    (\intno == BOOK3S_INTERRUPT_PROGRAM) || \
 	    (\intno == BOOK3S_INTERRUPT_FP_UNAVAIL) || \
diff --git a/arch/powerpc/kernel/cpu_setup_power7.S b/arch/powerpc/kernel/cpu_setup_power7.S
index f2b317817c4..e801ef15d6d 100644
--- a/arch/powerpc/kernel/cpu_setup_power7.S
+++ b/arch/powerpc/kernel/cpu_setup_power7.S
@@ -52,13 +52,14 @@ __init_hvmode_206:
 __init_LPCR:
 	/* Setup a sane LPCR:
 	 *
-	 *   LPES = 0b11 (SRR0/1 used for 0x500)
+	 *   LPES = 0b01 (HSRR0/1 used for 0x500)
 	 *   PECE = 0b111
 	 *
 	 * Other bits untouched for now
 	 */
 	mfspr	r3,SPRN_LPCR
 	ori	r3,r3,(LPCR_LPES0|LPCR_LPES1)
+	xori	r3,r3, LPCR_LPES0
 	ori	r3,r3,(LPCR_PECE0|LPCR_PECE1|LPCR_PECE2)
 	mtspr	SPRN_LPCR,r3
 	isync
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 6784bf7090f..17f1d667063 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -44,7 +44,7 @@ _machine_check_pSeries:
 	HMT_MEDIUM
 	DO_KVM	0x200
 	mtspr	SPRN_SPRG_SCRATCH0,r13		/* save r13 */
-	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD)
 
 	. = 0x300
 	.globl data_access_pSeries
@@ -71,9 +71,9 @@ BEGIN_FTR_SECTION
 	std	r10,PACA_EXGEN+EX_R10(r13)
 	std	r11,PACA_EXGEN+EX_R9(r13)
 	std	r12,PACA_EXGEN+EX_R13(r13)
-	EXCEPTION_PROLOG_PSERIES_1(data_access_common)
+	EXCEPTION_PROLOG_PSERIES_1(data_access_common, EXC_STD)
 FTR_SECTION_ELSE
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD)
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_SLB)
 
 	. = 0x380
@@ -147,11 +147,24 @@ instruction_access_slb_pSeries:
 	bctr
 #endif
 
-	MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt)
+	. = 0x500;
+	.globl hardware_interrupt_pSeries
+hardware_interrupt_pSeries:
+	BEGIN_FTR_SECTION
+	MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD)
+	FTR_SECTION_ELSE
+	MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV)
+	ALT_FTR_SECTION_END_IFCLR(CPU_FTR_HVMODE_206)
+
 	STD_EXCEPTION_PSERIES(0x600, alignment)
 	STD_EXCEPTION_PSERIES(0x700, program_check)
 	STD_EXCEPTION_PSERIES(0x800, fp_unavailable)
-	MASKABLE_EXCEPTION_PSERIES(0x900, decrementer)
+
+	. = 0x900;
+	.globl decrementer_pSeries
+decrementer_pSeries:
+	MASKABLE_EXCEPTION_PSERIES(0x900, decrementer, EXC_STD)
+
 	STD_EXCEPTION_PSERIES(0xa00, trap_0a)
 	STD_EXCEPTION_PSERIES(0xb00, trap_0b)
 
@@ -207,15 +220,15 @@ vsx_unavailable_pSeries_1:
 	b	vsx_unavailable_pSeries
 
 #ifdef CONFIG_CBE_RAS
-	HSTD_EXCEPTION_PSERIES(0x1200, cbe_system_error)
+	HSTD_EXCEPTION_PSERIES(0x1202, cbe_system_error)
 #endif /* CONFIG_CBE_RAS */
 	STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint)
 #ifdef CONFIG_CBE_RAS
-	HSTD_EXCEPTION_PSERIES(0x1600, cbe_maintenance)
+	HSTD_EXCEPTION_PSERIES(0x1602, cbe_maintenance)
 #endif /* CONFIG_CBE_RAS */
 	STD_EXCEPTION_PSERIES(0x1700, altivec_assist)
 #ifdef CONFIG_CBE_RAS
-	HSTD_EXCEPTION_PSERIES(0x1800, cbe_thermal)
+	HSTD_EXCEPTION_PSERIES(0x1802, cbe_thermal)
 #endif /* CONFIG_CBE_RAS */
 
 	. = 0x3000
@@ -244,13 +257,26 @@ masked_interrupt:
 	rfid
 	b	.
 
+masked_Hinterrupt:
+	stb	r10,PACAHARDIRQEN(r13)
+	mtcrf	0x80,r9
+	ld	r9,PACA_EXGEN+EX_R9(r13)
+	mfspr	r10,SPRN_HSRR1
+	rldicl	r10,r10,48,1		/* clear MSR_EE */
+	rotldi	r10,r10,16
+	mtspr	SPRN_HSRR1,r10
+	ld	r10,PACA_EXGEN+EX_R10(r13)
+	mfspr	r13,SPRN_SPRG_HSCRATCH0
+	hrfid
+	b	.
+
 	.align	7
 do_stab_bolted_pSeries:
 	std	r11,PACA_EXSLB+EX_R11(r13)
 	std	r12,PACA_EXSLB+EX_R12(r13)
 	mfspr	r10,SPRN_SPRG_SCRATCH0
 	std	r10,PACA_EXSLB+EX_R13(r13)
-	EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted)
+	EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD)
 
 #ifdef CONFIG_PPC_PSERIES
 /*
@@ -261,14 +287,14 @@ do_stab_bolted_pSeries:
 system_reset_fwnmi:
 	HMT_MEDIUM
 	mtspr	SPRN_SPRG_SCRATCH0,r13		/* save r13 */
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD)
 
 	.globl machine_check_fwnmi
       .align 7
 machine_check_fwnmi:
 	HMT_MEDIUM
 	mtspr	SPRN_SPRG_SCRATCH0,r13		/* save r13 */
-	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD)
 
 #endif /* CONFIG_PPC_PSERIES */
 
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index b0ff5ff76e2..046e1f3d443 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -112,6 +112,7 @@ INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_MACHINE_CHECK
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_DATA_STORAGE
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_INST_STORAGE
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_EXTERNAL
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_EXTERNAL_HV
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_ALIGNMENT
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_PROGRAM
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_FP_UNAVAIL
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 7c52ed0b705..d842795d0f2 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -155,9 +155,15 @@ kvmppc_handler_trampoline_exit:
 	PPC_LL	r2, (SHADOW_VCPU_OFF + SVCPU_HOST_R2)(r13)
 
 	/* Save guest PC and MSR */
-	mfsrr0	r3
+	andi.	r0,r12,0x2
+	beq	1f
+	mfspr	r3,SPRN_HSRR0
+	mfspr	r4,SPRN_HSRR1
+	andi.	r12,r12,0x3ffd
+	b	2f
+1:	mfsrr0	r3
 	mfsrr1	r4
-
+2:
 	PPC_STL	r3, (SHADOW_VCPU_OFF + SVCPU_PC)(r13)
 	PPC_STL	r4, (SHADOW_VCPU_OFF + SVCPU_SHADOW_SRR1)(r13)
 
diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S
index 32a56c6dfa7..f7a487231a1 100644
--- a/arch/powerpc/platforms/iseries/exception.S
+++ b/arch/powerpc/platforms/iseries/exception.S
@@ -155,7 +155,7 @@ BEGIN_FTR_SECTION
 	std	r12,PACA_EXGEN+EX_R13(r13)
 	EXCEPTION_PROLOG_ISERIES_1
 FTR_SECTION_ELSE
-	EXCEPTION_PROLOG_1(PACA_EXGEN)
+	EXCEPTION_PROLOG_1(PACA_EXGEN, EXC_STD)
 	EXCEPTION_PROLOG_ISERIES_1
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_SLB)
 	b	data_access_common
diff --git a/arch/powerpc/platforms/iseries/exception.h b/arch/powerpc/platforms/iseries/exception.h
index bae3fba5ad8..57127d805fe 100644
--- a/arch/powerpc/platforms/iseries/exception.h
+++ b/arch/powerpc/platforms/iseries/exception.h
@@ -39,7 +39,7 @@
 label##_iSeries:							\
 	HMT_MEDIUM;							\
 	mtspr	SPRN_SPRG_SCRATCH0,r13;	/* save r13 */			\
-	EXCEPTION_PROLOG_1(area);					\
+	EXCEPTION_PROLOG_1(area, EXC_STD);				\
 	EXCEPTION_PROLOG_ISERIES_1;					\
 	b	label##_common
 
@@ -48,7 +48,7 @@ label##_iSeries:							\
 label##_iSeries:							\
 	HMT_MEDIUM;							\
 	mtspr	SPRN_SPRG_SCRATCH0,r13;	/* save r13 */			\
-	EXCEPTION_PROLOG_1(PACA_EXGEN);					\
+	EXCEPTION_PROLOG_1(PACA_EXGEN, EXC_STD);			\
 	lbz	r10,PACASOFTIRQEN(r13);					\
 	cmpwi	0,r10,0;						\
 	beq-	label##_iSeries_masked;					\
-- 
cgit v1.2.3-70-g09d2


From b3e6b5dfcf0974069a8ddcce7dd071120d20d79c Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 5 Apr 2011 14:27:11 +1000
Subject: powerpc: More work to support HV exceptions

Rework exception macros a bit to split offset from vector and add
some basic support for HDEC, HDSI, HISI and a few more.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/exception-64s.h  | 37 ++++++++-----
 arch/powerpc/include/asm/feature-fixups.h |  2 +-
 arch/powerpc/kernel/exceptions-64s.S      | 92 +++++++++++++++++++++----------
 3 files changed, 89 insertions(+), 42 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 1d98e05be51..fb5b0af30fc 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -150,28 +150,27 @@
 /*
  * Exception vectors.
  */
-#define STD_EXCEPTION_PSERIES(n, label)			\
-	. = n;						\
+#define STD_EXCEPTION_PSERIES(loc, vec, label)		\
+	. = loc;					\
 	.globl label##_pSeries;				\
 label##_pSeries:					\
 	HMT_MEDIUM;					\
-	DO_KVM	n;					\
+	DO_KVM	vec;					\
 	mtspr	SPRN_SPRG_SCRATCH0,r13;		/* save r13 */	\
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, EXC_STD)
 
-#define HSTD_EXCEPTION_PSERIES(n, label)		\
-	. = n;						\
-	.globl label##_pSeries;				\
-label##_pSeries:					\
+#define STD_EXCEPTION_HV(loc, vec, label)		\
+	. = loc;					\
+	.globl label##_hv;				\
+label##_hv:						\
 	HMT_MEDIUM;					\
-	DO_KVM	n;					\
+	DO_KVM	vec;					\
 	mtspr	SPRN_SPRG_HSCRATCH0,r13;/* save r13 */	\
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, EXC_HV)
 
-
-#define __MASKABLE_EXCEPTION_PSERIES(n, label, h)			\
+#define __MASKABLE_EXCEPTION_PSERIES(vec, label, h)			\
 	HMT_MEDIUM;							\
-	DO_KVM	n;							\
+	DO_KVM	vec;							\
 	mtspr	SPRN_SPRG_##h##SCRATCH0,r13;    /* save r13 */		\
 	GET_PACA(r13);							\
 	std	r9,PACA_EXGEN+EX_R9(r13);	/* save r9, r10 */	\
@@ -193,8 +192,20 @@ label##_pSeries:					\
 	mtspr	SPRN_##h##SRR1,r10;					\
 	h##rfid;							\
 	b	.	/* prevent speculative execution */
-#define MASKABLE_EXCEPTION_PSERIES(n, label, h)				\
-	__MASKABLE_EXCEPTION_PSERIES(n, label, h)
+#define _MASKABLE_EXCEPTION_PSERIES(vec, label, h)			\
+	__MASKABLE_EXCEPTION_PSERIES(vec, label, h)
+
+#define MASKABLE_EXCEPTION_PSERIES(loc, vec, label)			\
+	. = loc;							\
+	.globl label##_pSeries;						\
+label##_pSeries:							\
+	_MASKABLE_EXCEPTION_PSERIES(vec, label, EXC_STD)
+
+#define MASKABLE_EXCEPTION_HV(loc, vec, label)				\
+	. = loc;							\
+	.globl label##_hv;						\
+label##_hv:								\
+	_MASKABLE_EXCEPTION_PSERIES(vec, label, EXC_HV)
 
 #ifdef CONFIG_PPC_ISERIES
 #define DISABLE_INTS				\
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index 921a8470e18..bdc0d6877bc 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -49,7 +49,7 @@ label##5:							\
 	FTR_ENTRY_OFFSET label##2b-label##5b;			\
 	FTR_ENTRY_OFFSET label##3b-label##5b;			\
 	FTR_ENTRY_OFFSET label##4b-label##5b;			\
-	.ifgt (label##4b-label##3b)-(label##2b-label##1b);	\
+	.ifgt (label##4b- label##3b)-(label##2b- label##1b);	\
 	.error "Feature section else case larger than body";	\
 	.endif;							\
 	.popsection;
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 17f1d667063..805e2065786 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -37,7 +37,7 @@
 	.globl __start_interrupts
 __start_interrupts:
 
-	STD_EXCEPTION_PSERIES(0x100, system_reset)
+	STD_EXCEPTION_PSERIES(0x100, 0x100, system_reset)
 
 	. = 0x200
 _machine_check_pSeries:
@@ -113,7 +113,7 @@ data_access_slb_pSeries:
 	bctr
 #endif
 
-	STD_EXCEPTION_PSERIES(0x400, instruction_access)
+	STD_EXCEPTION_PSERIES(0x400, 0x400, instruction_access)
 
 	. = 0x480
 	.globl instruction_access_slb_pSeries
@@ -147,26 +147,29 @@ instruction_access_slb_pSeries:
 	bctr
 #endif
 
+	/* We open code these as we can't have a ". = x" (even with
+	 * x = "." within a feature section
+	 */
 	. = 0x500;
-	.globl hardware_interrupt_pSeries
+	.globl hardware_interrupt_pSeries;
+	.globl hardware_interrupt_hv;
 hardware_interrupt_pSeries:
+hardware_interrupt_hv:
 	BEGIN_FTR_SECTION
-	MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD)
+		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD)
 	FTR_SECTION_ELSE
-	MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV)
+		_MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV)
 	ALT_FTR_SECTION_END_IFCLR(CPU_FTR_HVMODE_206)
 
-	STD_EXCEPTION_PSERIES(0x600, alignment)
-	STD_EXCEPTION_PSERIES(0x700, program_check)
-	STD_EXCEPTION_PSERIES(0x800, fp_unavailable)
+	STD_EXCEPTION_PSERIES(0x600, 0x600, alignment)
+	STD_EXCEPTION_PSERIES(0x700, 0x700, program_check)
+	STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable)
 
-	. = 0x900;
-	.globl decrementer_pSeries
-decrementer_pSeries:
-	MASKABLE_EXCEPTION_PSERIES(0x900, decrementer, EXC_STD)
+	MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer)
+	MASKABLE_EXCEPTION_HV(0x980, 0x980, decrementer)
 
-	STD_EXCEPTION_PSERIES(0xa00, trap_0a)
-	STD_EXCEPTION_PSERIES(0xb00, trap_0b)
+	STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a)
+	STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b)
 
 	. = 0xc00
 	.globl	system_call_pSeries
@@ -196,8 +199,21 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	rfid		/* return to userspace */
 	b	.
 
-	STD_EXCEPTION_PSERIES(0xd00, single_step)
-	STD_EXCEPTION_PSERIES(0xe00, trap_0e)
+	STD_EXCEPTION_PSERIES(0xd00, 0xd00, single_step)
+
+	/* At 0xe??? we have a bunch of hypervisor exceptions, we branch
+	 * out of line to handle them
+	 */
+	. = 0xe00
+	b	h_data_storage_hv
+	. = 0xe20
+	b	h_instr_storage_hv
+	. = 0xe40
+	b	emulation_assist_hv
+	. = 0xe50
+	b	hmi_exception_hv
+	. = 0xe60
+	b	hmi_exception_hv
 
 	/* We need to deal with the Altivec unavailable exception
 	 * here which is at 0xf20, thus in the middle of the
@@ -206,39 +222,42 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	 */
 performance_monitor_pSeries_1:
 	. = 0xf00
-	DO_KVM	0xf00
 	b	performance_monitor_pSeries
 
 altivec_unavailable_pSeries_1:
 	. = 0xf20
-	DO_KVM	0xf20
 	b	altivec_unavailable_pSeries
 
 vsx_unavailable_pSeries_1:
 	. = 0xf40
-	DO_KVM	0xf40
 	b	vsx_unavailable_pSeries
 
 #ifdef CONFIG_CBE_RAS
-	HSTD_EXCEPTION_PSERIES(0x1202, cbe_system_error)
+	STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error)
 #endif /* CONFIG_CBE_RAS */
-	STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint)
+	STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint)
 #ifdef CONFIG_CBE_RAS
-	HSTD_EXCEPTION_PSERIES(0x1602, cbe_maintenance)
+	STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance)
 #endif /* CONFIG_CBE_RAS */
-	STD_EXCEPTION_PSERIES(0x1700, altivec_assist)
+	STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist)
 #ifdef CONFIG_CBE_RAS
-	HSTD_EXCEPTION_PSERIES(0x1802, cbe_thermal)
+	STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal)
 #endif /* CONFIG_CBE_RAS */
 
 	. = 0x3000
 
-/*** pSeries interrupt support ***/
+/*** Out of line interrupts support ***/
+
+	/* moved from 0xe00 */
+	STD_EXCEPTION_HV(., 0xe00, h_data_storage)
+	STD_EXCEPTION_HV(., 0xe20, h_instr_storage)
+	STD_EXCEPTION_HV(., 0xe40, emulation_assist)
+	STD_EXCEPTION_HV(., 0xe60, hmi_exception) /* need to flush cache ? */
 
 	/* moved from 0xf00 */
-	STD_EXCEPTION_PSERIES(., performance_monitor)
-	STD_EXCEPTION_PSERIES(., altivec_unavailable)
-	STD_EXCEPTION_PSERIES(., vsx_unavailable)
+	STD_EXCEPTION_PSERIES(., 0xf00, performance_monitor)
+	STD_EXCEPTION_PSERIES(., 0xf20, altivec_unavailable)
+	STD_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable)
 
 /*
  * An interrupt came in while soft-disabled; clear EE in SRR1,
@@ -368,6 +387,8 @@ machine_check_common:
 	STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
 	STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
 	STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
+        STD_EXCEPTION_COMMON(0xe40, emulation_assist, .program_check_exception)
+        STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception)
 	STD_EXCEPTION_COMMON_IDLE(0xf00, performance_monitor, .performance_monitor_exception)
 	STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception)
 #ifdef CONFIG_ALTIVEC
@@ -445,6 +466,19 @@ data_access_common:
 	li	r5,0x300
 	b	.do_hash_page	 	/* Try to handle as hpte fault */
 
+	.align  7
+        .globl  h_data_storage_common
+h_data_storage_common:
+        mfspr   r10,SPRN_HDAR
+        std     r10,PACA_EXGEN+EX_DAR(r13)
+        mfspr   r10,SPRN_HDSISR
+        stw     r10,PACA_EXGEN+EX_DSISR(r13)
+        EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN)
+        bl      .save_nvgprs
+        addi    r3,r1,STACK_FRAME_OVERHEAD
+        bl      .unknown_exception
+        b       .ret_from_except
+
 	.align	7
 	.globl instruction_access_common
 instruction_access_common:
@@ -454,6 +488,8 @@ instruction_access_common:
 	li	r5,0x400
 	b	.do_hash_page		/* Try to handle as hpte fault */
 
+        STD_EXCEPTION_COMMON(0xe20, h_instr_storage, .unknown_exception)
+
 /*
  * Here is the common SLB miss user that is used when going to virtual
  * mode for SLB misses, that is currently not used
-- 
cgit v1.2.3-70-g09d2


From 673b189a2e3353061fa8c49515d1014dab6ad9b9 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Tue, 5 Apr 2011 13:59:58 +1000
Subject: powerpc: Always use SPRN_SPRG_HSCRATCH0 when running in HV mode

This uses feature sections to arrange that we always use HSPRG1
as the scratch register in the interrupt entry code rather than
SPRG2 when we're running in hypervisor mode on POWER7.  This will
ensure that we don't trash the guest's SPRG2 when we are running
KVM guests.  To simplify the code, we define GET_SCRATCH0() and
SET_SCRATCH0() macros like the GET_PACA/SET_PACA macros.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/exception-64s.h   | 15 +++++++--------
 arch/powerpc/include/asm/reg.h             | 14 ++++++++++++++
 arch/powerpc/kernel/exceptions-64s.S       | 26 +++++++++++++-------------
 arch/powerpc/kvm/book3s_rmhandlers.S       |  6 +++---
 arch/powerpc/kvm/book3s_segment.S          |  2 +-
 arch/powerpc/platforms/iseries/exception.S |  2 +-
 arch/powerpc/platforms/iseries/exception.h |  4 ++--
 7 files changed, 41 insertions(+), 28 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index fb5b0af30fc..d6b4849df9b 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -60,16 +60,15 @@
 #define EXC_HV	H
 #define EXC_STD
 
-#define __EXCEPTION_PROLOG_1(area, h)					\
+#define EXCEPTION_PROLOG_1(area)					\
 	GET_PACA(r13);							\
 	std	r9,area+EX_R9(r13);	/* save r9 - r12 */		\
 	std	r10,area+EX_R10(r13);					\
 	std	r11,area+EX_R11(r13);					\
 	std	r12,area+EX_R12(r13);					\
-	mfspr	r9,SPRN_SPRG_##h##SCRATCH0;				\
+	GET_SCRATCH0(r9);						\
 	std	r9,area+EX_R13(r13);					\
 	mfcr	r9
-#define EXCEPTION_PROLOG_1(area, h) __EXCEPTION_PROLOG_1(area, h)
 
 #define __EXCEPTION_PROLOG_PSERIES_1(label, h)				\
 	ld	r12,PACAKBASE(r13);	/* get high part of &label */	\
@@ -85,7 +84,7 @@
 	__EXCEPTION_PROLOG_PSERIES_1(label, h)
 
 #define EXCEPTION_PROLOG_PSERIES(area, label, h)			\
-	EXCEPTION_PROLOG_1(area, h);					\
+	EXCEPTION_PROLOG_1(area);					\
 	EXCEPTION_PROLOG_PSERIES_1(label, h);
 
 /*
@@ -156,7 +155,7 @@
 label##_pSeries:					\
 	HMT_MEDIUM;					\
 	DO_KVM	vec;					\
-	mtspr	SPRN_SPRG_SCRATCH0,r13;		/* save r13 */	\
+	SET_SCRATCH0(r13);		/* save r13 */		\
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, EXC_STD)
 
 #define STD_EXCEPTION_HV(loc, vec, label)		\
@@ -165,13 +164,13 @@ label##_pSeries:					\
 label##_hv:						\
 	HMT_MEDIUM;					\
 	DO_KVM	vec;					\
-	mtspr	SPRN_SPRG_HSCRATCH0,r13;/* save r13 */	\
+	SET_SCRATCH0(r13);	/* save r13 */		\
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, EXC_HV)
 
 #define __MASKABLE_EXCEPTION_PSERIES(vec, label, h)			\
 	HMT_MEDIUM;							\
 	DO_KVM	vec;							\
-	mtspr	SPRN_SPRG_##h##SCRATCH0,r13;    /* save r13 */		\
+	SET_SCRATCH0(r13);    /* save r13 */				\
 	GET_PACA(r13);							\
 	std	r9,PACA_EXGEN+EX_R9(r13);	/* save r9, r10 */	\
 	std	r10,PACA_EXGEN+EX_R10(r13);				\
@@ -179,7 +178,7 @@ label##_hv:						\
 	mfcr	r9;							\
 	cmpwi	r10,0;							\
 	beq	masked_##h##interrupt;					\
-	mfspr	r10,SPRN_SPRG_##h##SCRATCH0;				\
+	GET_SCRATCH0(r10);						\
 	std	r10,PACA_EXGEN+EX_R13(r13);				\
 	std	r11,PACA_EXGEN+EX_R11(r13);				\
 	std	r12,PACA_EXGEN+EX_R12(r13);				\
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 13429a0eba0..76d7d5fea5b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -802,6 +802,20 @@
 	FTR_SECTION_ELSE_NESTED(66);			\
 	mtspr	SPRN_SPRG_HPACA,rX;			\
 	ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66)
+
+#define GET_SCRATCH0(rX)				\
+	BEGIN_FTR_SECTION_NESTED(66);			\
+	mfspr	rX,SPRN_SPRG_SCRATCH0;			\
+	FTR_SECTION_ELSE_NESTED(66);			\
+	mfspr	rX,SPRN_SPRG_HSCRATCH0;			\
+	ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66)
+
+#define SET_SCRATCH0(rX)				\
+	BEGIN_FTR_SECTION_NESTED(66);			\
+	mtspr	SPRN_SPRG_SCRATCH0,rX;			\
+	FTR_SECTION_ELSE_NESTED(66);			\
+	mtspr	SPRN_SPRG_HSCRATCH0,rX;			\
+	ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66)
 #endif
 
 #ifdef CONFIG_PPC_BOOK3E_64
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 805e2065786..e513c1d35b2 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -43,7 +43,7 @@ __start_interrupts:
 _machine_check_pSeries:
 	HMT_MEDIUM
 	DO_KVM	0x200
-	mtspr	SPRN_SPRG_SCRATCH0,r13		/* save r13 */
+	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD)
 
 	. = 0x300
@@ -51,7 +51,7 @@ _machine_check_pSeries:
 data_access_pSeries:
 	HMT_MEDIUM
 	DO_KVM	0x300
-	mtspr	SPRN_SPRG_SCRATCH0,r13
+	SET_SCRATCH0(r13)
 BEGIN_FTR_SECTION
 	GET_PACA(r13)
 	std	r9,PACA_EXSLB+EX_R9(r13)
@@ -67,7 +67,7 @@ BEGIN_FTR_SECTION
 	std	r11,PACA_EXGEN+EX_R11(r13)
 	ld	r11,PACA_EXSLB+EX_R9(r13)
 	std	r12,PACA_EXGEN+EX_R12(r13)
-	mfspr	r12,SPRN_SPRG_SCRATCH0
+	GET_SCRATCH0(r12)
 	std	r10,PACA_EXGEN+EX_R10(r13)
 	std	r11,PACA_EXGEN+EX_R9(r13)
 	std	r12,PACA_EXGEN+EX_R13(r13)
@@ -81,7 +81,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_SLB)
 data_access_slb_pSeries:
 	HMT_MEDIUM
 	DO_KVM	0x380
-	mtspr	SPRN_SPRG_SCRATCH0,r13
+	SET_SCRATCH0(r13)
 	GET_PACA(r13)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_DAR
@@ -95,7 +95,7 @@ data_access_slb_pSeries:
 	std	r10,PACA_EXSLB+EX_R10(r13)
 	std	r11,PACA_EXSLB+EX_R11(r13)
 	std	r12,PACA_EXSLB+EX_R12(r13)
-	mfspr	r10,SPRN_SPRG_SCRATCH0
+	GET_SCRATCH0(r10)
 	std	r10,PACA_EXSLB+EX_R13(r13)
 	mfspr	r12,SPRN_SRR1		/* and SRR1 */
 #ifndef CONFIG_RELOCATABLE
@@ -120,7 +120,7 @@ data_access_slb_pSeries:
 instruction_access_slb_pSeries:
 	HMT_MEDIUM
 	DO_KVM	0x480
-	mtspr	SPRN_SPRG_SCRATCH0,r13
+	SET_SCRATCH0(r13)
 	GET_PACA(r13)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
@@ -134,7 +134,7 @@ instruction_access_slb_pSeries:
 	std	r10,PACA_EXSLB+EX_R10(r13)
 	std	r11,PACA_EXSLB+EX_R11(r13)
 	std	r12,PACA_EXSLB+EX_R12(r13)
-	mfspr	r10,SPRN_SPRG_SCRATCH0
+	GET_SCRATCH0(r10)
 	std	r10,PACA_EXSLB+EX_R13(r13)
 	mfspr	r12,SPRN_SRR1		/* and SRR1 */
 #ifndef CONFIG_RELOCATABLE
@@ -272,7 +272,7 @@ masked_interrupt:
 	rotldi	r10,r10,16
 	mtspr	SPRN_SRR1,r10
 	ld	r10,PACA_EXGEN+EX_R10(r13)
-	mfspr	r13,SPRN_SPRG_SCRATCH0
+	GET_SCRATCH0(r13)
 	rfid
 	b	.
 
@@ -285,7 +285,7 @@ masked_Hinterrupt:
 	rotldi	r10,r10,16
 	mtspr	SPRN_HSRR1,r10
 	ld	r10,PACA_EXGEN+EX_R10(r13)
-	mfspr	r13,SPRN_SPRG_HSCRATCH0
+	GET_SCRATCH0(r13)
 	hrfid
 	b	.
 
@@ -293,7 +293,7 @@ masked_Hinterrupt:
 do_stab_bolted_pSeries:
 	std	r11,PACA_EXSLB+EX_R11(r13)
 	std	r12,PACA_EXSLB+EX_R12(r13)
-	mfspr	r10,SPRN_SPRG_SCRATCH0
+	GET_SCRATCH0(r10)
 	std	r10,PACA_EXSLB+EX_R13(r13)
 	EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD)
 
@@ -305,14 +305,14 @@ do_stab_bolted_pSeries:
       .align 7
 system_reset_fwnmi:
 	HMT_MEDIUM
-	mtspr	SPRN_SPRG_SCRATCH0,r13		/* save r13 */
+	SET_SCRATCH0(r13)		/* save r13 */
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD)
 
 	.globl machine_check_fwnmi
       .align 7
 machine_check_fwnmi:
 	HMT_MEDIUM
-	mtspr	SPRN_SPRG_SCRATCH0,r13		/* save r13 */
+	SET_SCRATCH0(r13)		/* save r13 */
 	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD)
 
 #endif /* CONFIG_PPC_PSERIES */
@@ -327,7 +327,7 @@ slb_miss_user_pseries:
 	std	r10,PACA_EXGEN+EX_R10(r13)
 	std	r11,PACA_EXGEN+EX_R11(r13)
 	std	r12,PACA_EXGEN+EX_R12(r13)
-	mfspr	r10,SPRG_SCRATCH0
+	GET_SCRATCH0(r10)
 	ld	r11,PACA_EXSLB+EX_R9(r13)
 	ld	r12,PACA_EXSLB+EX_R3(r13)
 	std	r10,PACA_EXGEN+EX_R13(r13)
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 046e1f3d443..ae99af66ca3 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -70,7 +70,7 @@
 .global kvmppc_trampoline_\intno
 kvmppc_trampoline_\intno:
 
-	mtspr	SPRN_SPRG_SCRATCH0, r13		/* Save r13 */
+	SET_SCRATCH0(r13)		/* Save r13 */
 
 	/*
 	 * First thing to do is to find out if we're coming
@@ -89,7 +89,7 @@ kvmppc_trampoline_\intno:
 	lwz	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13)
 	mtcr	r12
 	PPC_LL	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13)
-	mfspr	r13, SPRN_SPRG_SCRATCH0		/* r13 = original r13 */
+	GET_SCRATCH0(r13)			/* r13 = original r13 */
 	b	kvmppc_resume_\intno		/* Get back original handler */
 
 	/* Now we know we're handling a KVM guest */
@@ -157,7 +157,7 @@ kvmppc_handler_skip_ins:
 	lwz	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13)
 	mtcr	r12
 	PPC_LL	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13)
-	mfspr	r13, SPRN_SPRG_SCRATCH0
+	GET_SCRATCH0(r13)
 
 	/* And get back into the code */
 	RFI
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index d842795d0f2..451264274b8 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -168,7 +168,7 @@ kvmppc_handler_trampoline_exit:
 	PPC_STL	r4, (SHADOW_VCPU_OFF + SVCPU_SHADOW_SRR1)(r13)
 
 	/* Get scratch'ed off registers */
-	mfspr	r9, SPRN_SPRG_SCRATCH0
+	GET_SCRATCH0(r9)
 	PPC_LL	r8, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13)
 	lwz	r7, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13)
 
diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S
index f7a487231a1..32a56c6dfa7 100644
--- a/arch/powerpc/platforms/iseries/exception.S
+++ b/arch/powerpc/platforms/iseries/exception.S
@@ -155,7 +155,7 @@ BEGIN_FTR_SECTION
 	std	r12,PACA_EXGEN+EX_R13(r13)
 	EXCEPTION_PROLOG_ISERIES_1
 FTR_SECTION_ELSE
-	EXCEPTION_PROLOG_1(PACA_EXGEN, EXC_STD)
+	EXCEPTION_PROLOG_1(PACA_EXGEN)
 	EXCEPTION_PROLOG_ISERIES_1
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_SLB)
 	b	data_access_common
diff --git a/arch/powerpc/platforms/iseries/exception.h b/arch/powerpc/platforms/iseries/exception.h
index 57127d805fe..bae3fba5ad8 100644
--- a/arch/powerpc/platforms/iseries/exception.h
+++ b/arch/powerpc/platforms/iseries/exception.h
@@ -39,7 +39,7 @@
 label##_iSeries:							\
 	HMT_MEDIUM;							\
 	mtspr	SPRN_SPRG_SCRATCH0,r13;	/* save r13 */			\
-	EXCEPTION_PROLOG_1(area, EXC_STD);				\
+	EXCEPTION_PROLOG_1(area);					\
 	EXCEPTION_PROLOG_ISERIES_1;					\
 	b	label##_common
 
@@ -48,7 +48,7 @@ label##_iSeries:							\
 label##_iSeries:							\
 	HMT_MEDIUM;							\
 	mtspr	SPRN_SPRG_SCRATCH0,r13;	/* save r13 */			\
-	EXCEPTION_PROLOG_1(PACA_EXGEN, EXC_STD);			\
+	EXCEPTION_PROLOG_1(PACA_EXGEN);					\
 	lbz	r10,PACASOFTIRQEN(r13);					\
 	cmpwi	0,r10,0;						\
 	beq-	label##_iSeries_masked;					\
-- 
cgit v1.2.3-70-g09d2


From 9d07bc841c9779b4d7902e417f4e509996ce805d Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Wed, 16 Mar 2011 14:54:35 +1100
Subject: powerpc: Properly handshake CPUs going out of boot spin loop

We need to wait a bit for them to have done their CPU setup
or we might end up with translation and EE on with different
LPCR values between threads

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/smp.h |  1 +
 arch/powerpc/kernel/head_64.S  | 18 +++++++++++++-----
 arch/powerpc/kernel/prom.c     | 27 ++++++++++-----------------
 arch/powerpc/kernel/setup_32.c |  1 +
 arch/powerpc/kernel/setup_64.c | 13 ++++++++++++-
 5 files changed, 37 insertions(+), 23 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index a902a0d3ae0..bb4c033a8fb 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -29,6 +29,7 @@
 #include <asm/percpu.h>
 
 extern int boot_cpuid;
+extern int boot_cpu_count;
 
 extern void cpu_die(void);
 
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 95944278380..0700e1135c9 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -242,23 +242,31 @@ generic_secondary_common_init:
 	ld	r23,0(r23)
 	ld	r23,CPU_SPEC_RESTORE(r23)
 	cmpdi	0,r23,0
-	beq	4f
+	beq	3f
 	ld	r23,0(r23)
 	mtctr	r23
 	bctrl
 
-3:	HMT_LOW
+3:	LOAD_REG_ADDR(r3, boot_cpu_count) /* Decrement boot_cpu_count */
+	lwarx	r4,0,r3
+	subi	r4,r4,1
+	stwcx.	r4,0,r3
+	bne	3b
+	isync
+
+4:	HMT_LOW
 	lbz	r23,PACAPROCSTART(r13)	/* Test if this processor should */
 					/* start.			 */
 #ifndef CONFIG_SMP
-	b	3b			/* Never go on non-SMP		 */
+	b	4b			/* Never go on non-SMP		 */
 #else
 	cmpwi	0,r23,0
-	beq	3b			/* Loop until told to go	 */
+	beq	4b			/* Loop until told to go	 */
 
 	sync				/* order paca.run and cur_cpu_spec */
+	isync				/* In case code patching happened */
 
-4:	/* Create a temp kernel stack for use before relocation is on.	*/
+	/* Create a temp kernel stack for use before relocation is on.	*/
 	ld	r1,PACAEMERGSP(r13)
 	subi	r1,r1,STACK_FRAME_OVERHEAD
 
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index e74fa12afc8..c391dc4c8ba 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -268,13 +268,12 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 					  const char *uname, int depth,
 					  void *data)
 {
-	static int logical_cpuid = 0;
 	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
 	const u32 *prop;
 	const u32 *intserv;
 	int i, nthreads;
 	unsigned long len;
-	int found = 0;
+	int found = -1;
 
 	/* We are scanning "cpu" nodes only */
 	if (type == NULL || strcmp(type, "cpu") != 0)
@@ -299,11 +298,8 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 		 * booted proc.
 		 */
 		if (initial_boot_params && initial_boot_params->version >= 2) {
-			if (intserv[i] ==
-					initial_boot_params->boot_cpuid_phys) {
-				found = 1;
-				break;
-			}
+			if (intserv[i] == initial_boot_params->boot_cpuid_phys)
+				found = boot_cpu_count;
 		} else {
 			/*
 			 * Check if it's the boot-cpu, set it's hw index now,
@@ -311,23 +307,20 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 			 * off secondary threads.
 			 */
 			if (of_get_flat_dt_prop(node,
-					"linux,boot-cpu", NULL) != NULL) {
-				found = 1;
-				break;
-			}
+					"linux,boot-cpu", NULL) != NULL)
+				found = boot_cpu_count;
 		}
-
 #ifdef CONFIG_SMP
 		/* logical cpu id is always 0 on UP kernels */
-		logical_cpuid++;
+		boot_cpu_count++;
 #endif
 	}
 
-	if (found) {
-		DBG("boot cpu: logical %d physical %d\n", logical_cpuid,
+	if (found >= 0) {
+		DBG("boot cpu: logical %d physical %d\n", found,
 			intserv[i]);
-		boot_cpuid = logical_cpuid;
-		set_hard_smp_processor_id(boot_cpuid, intserv[i]);
+		boot_cpuid = found;
+		set_hard_smp_processor_id(found, intserv[i]);
 
 		/*
 		 * PAPR defines "logical" PVR values for cpus that
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 1d2fbc90530..620d792b52e 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -48,6 +48,7 @@ extern void bootx_init(unsigned long r4, unsigned long phys);
 
 int boot_cpuid = -1;
 EXPORT_SYMBOL_GPL(boot_cpuid);
+int __initdata boot_cpu_count;
 int boot_cpuid_phys;
 
 int smp_hw_index[NR_CPUS];
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 5a0401fcaeb..91a5cc5f0d0 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -72,6 +72,7 @@
 #endif
 
 int boot_cpuid = 0;
+int __initdata boot_cpu_count;
 u64 ppc64_pft_size;
 
 /* Pick defaults since we might want to patch instructions
@@ -233,6 +234,7 @@ void early_setup_secondary(void)
 void smp_release_cpus(void)
 {
 	unsigned long *ptr;
+	int i;
 
 	DBG(" -> smp_release_cpus()\n");
 
@@ -245,7 +247,16 @@ void smp_release_cpus(void)
 	ptr  = (unsigned long *)((unsigned long)&__secondary_hold_spinloop
 			- PHYSICAL_START);
 	*ptr = __pa(generic_secondary_smp_init);
-	mb();
+
+	/* And wait a bit for them to catch up */
+	for (i = 0; i < 100000; i++) {
+		mb();
+		HMT_low();
+		if (boot_cpu_count == 0)
+			break;
+		udelay(1);
+	}
+	DBG("boot_cpu_count = %d\n", boot_cpu_count);
 
 	DBG(" <- smp_release_cpus()\n");
 }
-- 
cgit v1.2.3-70-g09d2


From 948cf67c4726cca2fc57533dccadfb54d890689d Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Mon, 24 Jan 2011 18:42:41 +1100
Subject: powerpc: Add NAP mode support on Power7 in HV mode

Wakeup comes from the system reset handler with a potential loss of
the non-hypervisor CPU state. We save the non-volatile state on the
stack and a pointer to it in the PACA, which the system reset handler
uses to restore things

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/machdep.h    |  1 +
 arch/powerpc/include/asm/paca.h       |  2 +-
 arch/powerpc/include/asm/ppc-opcode.h |  6 +++
 arch/powerpc/kernel/Makefile          |  1 +
 arch/powerpc/kernel/exceptions-64s.S  | 30 ++++++++++-
 arch/powerpc/kernel/idle_power7.S     | 97 +++++++++++++++++++++++++++++++++++
 arch/powerpc/platforms/Kconfig        |  4 ++
 7 files changed, 139 insertions(+), 2 deletions(-)
 create mode 100644 arch/powerpc/kernel/idle_power7.S

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index e4f01915fbb..493dbb38e1b 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -267,6 +267,7 @@ struct machdep_calls {
 
 extern void e500_idle(void);
 extern void power4_idle(void);
+extern void power7_idle(void);
 extern void ppc6xx_idle(void);
 extern void book3e_idle(void);
 
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index ec57540cd7a..f6da4f517fc 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -125,7 +125,7 @@ struct paca_struct {
 	struct task_struct *__current;	/* Pointer to current */
 	u64 kstack;			/* Saved Kernel stack addr */
 	u64 stab_rr;			/* stab/slb round-robin counter */
-	u64 saved_r1;			/* r1 save for RTAS calls */
+	u64 saved_r1;			/* r1 save for RTAS calls or PM */
 	u64 saved_msr;			/* MSR saved here by enter_rtas */
 	u16 trap_save;			/* Used when bad stack is encountered */
 	u8 soft_enabled;		/* irq soft-enable flag */
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 1255569387b..384a96db794 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -56,6 +56,9 @@
 #define PPC_INST_TLBSRX_DOT		0x7c0006a5
 #define PPC_INST_XXLOR			0xf0000510
 
+#define PPC_INST_NAP			0x4c000364
+#define PPC_INST_SLEEP			0x4c0003a4
+
 /* macros to insert fields into opcodes */
 #define __PPC_RA(a)	(((a) & 0x1f) << 16)
 #define __PPC_RB(b)	(((b) & 0x1f) << 11)
@@ -126,4 +129,7 @@
 #define XXLOR(t, a, b)		stringify_in_c(.long PPC_INST_XXLOR | \
 					       VSX_XX3((t), (a), (b)))
 
+#define PPC_NAP			stringify_in_c(.long PPC_INST_NAP)
+#define PPC_SLEEP		stringify_in_c(.long PPC_INST_SLEEP)
+
 #endif /* _ASM_POWERPC_PPC_OPCODE_H */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 7c6eb4974f2..0fd6273bb8a 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -44,6 +44,7 @@ obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
+obj-$(CONFIG_PPC_P7_NAP)	+= idle_power7.o
 obj-$(CONFIG_PPC_OF)		+= of_platform.o prom_parse.o
 obj-$(CONFIG_PPC_CLOCK)		+= clock.o
 procfs-y			:= proc_powerpc.o
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e513c1d35b2..ad06333631a 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -37,7 +37,35 @@
 	.globl __start_interrupts
 __start_interrupts:
 
-	STD_EXCEPTION_PSERIES(0x100, 0x100, system_reset)
+	.globl system_reset_pSeries;
+system_reset_pSeries:
+	HMT_MEDIUM;
+	DO_KVM	0x100;
+	SET_SCRATCH0(r13)
+#ifdef CONFIG_PPC_P7_NAP
+BEGIN_FTR_SECTION
+	/* Running native on arch 2.06 or later, check if we are
+	 * waking up from nap. We only handle no state loss and
+	 * supervisor state loss. We do -not- handle hypervisor
+	 * state loss at this time.
+	 */
+	mfspr	r13,SPRN_SRR1
+	rlwinm	r13,r13,47-31,30,31
+	cmpwi	cr0,r13,1
+	bne	1f
+	b	.power7_wakeup_noloss
+1:	cmpwi	cr0,r13,2
+	bne	1f
+	b	.power7_wakeup_loss
+	/* Total loss of HV state is fatal, we could try to use the
+	 * PIR to locate a PACA, then use an emergency stack etc...
+	 * but for now, let's just stay stuck here
+	 */
+1:	cmpwi	cr0,r13,3
+	beq	.
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE_206)
+#endif /* CONFIG_PPC_P7_NAP */
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD)
 
 	. = 0x200
 _machine_check_pSeries:
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
new file mode 100644
index 00000000000..f8f0bc7f1d4
--- /dev/null
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -0,0 +1,97 @@
+/*
+ *  This file contains the power_save function for 970-family CPUs.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/threads.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ppc-opcode.h>
+
+#undef DEBUG
+
+	.text
+
+_GLOBAL(power7_idle)
+	/* Now check if user or arch enabled NAP mode */
+	LOAD_REG_ADDRBASE(r3,powersave_nap)
+	lwz	r4,ADDROFF(powersave_nap)(r3)
+	cmpwi	0,r4,0
+	beqlr
+
+	/* NAP is a state loss, we create a regs frame on the
+	 * stack, fill it up with the state we care about and
+	 * stick a pointer to it in PACAR1. We really only
+	 * need to save PC, some CR bits and the NV GPRs,
+	 * but for now an interrupt frame will do.
+	 */
+	mflr	r0
+	std	r0,16(r1)
+	stdu	r1,-INT_FRAME_SIZE(r1)
+	std	r0,_LINK(r1)
+	std	r0,_NIP(r1)
+
+#ifndef CONFIG_SMP
+	/* Make sure FPU, VSX etc... are flushed as we may lose
+	 * state when going to nap mode
+	 */
+	bl	.discard_lazy_cpu_state
+#endif /* CONFIG_SMP */
+
+	/* Hard disable interrupts */
+	mfmsr	r9
+	rldicl	r9,r9,48,1
+	rotldi	r9,r9,16
+	mtmsrd	r9,1			/* hard-disable interrupts */
+	li	r0,0
+	stb	r0,PACASOFTIRQEN(r13)	/* we'll hard-enable shortly */
+	stb	r0,PACAHARDIRQEN(r13)
+
+	/* Continue saving state */
+	SAVE_GPR(2, r1)
+	SAVE_NVGPRS(r1)
+	mfcr	r3
+	std	r3,_CCR(r1)
+	std	r9,_MSR(r1)
+	std	r1,PACAR1(r13)
+
+	/* Magic NAP mode enter sequence */
+	std	r0,0(r1)
+	ptesync
+	ld	r0,0(r1)
+1:	cmp	cr0,r0,r0
+	bne	1b
+	PPC_NAP
+	b	.
+
+_GLOBAL(power7_wakeup_loss)
+	GET_PACA(r13)
+	ld	r1,PACAR1(r13)
+	REST_NVGPRS(r1)
+	REST_GPR(2, r1)
+	ld	r3,_CCR(r1)
+	ld	r4,_MSR(r1)
+	ld	r5,_NIP(r1)
+	addi	r1,r1,INT_FRAME_SIZE
+	mtcr	r3
+	mtspr	SPRN_SRR1,r4
+	mtspr	SPRN_SRR0,r5
+	rfid
+
+_GLOBAL(power7_wakeup_noloss)
+	GET_PACA(r13)
+	ld	r1,PACAR1(r13)
+	ld	r4,_MSR(r1)
+	ld	r5,_NIP(r1)
+	addi	r1,r1,INT_FRAME_SIZE
+	mtspr	SPRN_SRR1,r4
+	mtspr	SPRN_SRR0,r5
+	rfid
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index f7b07720aa3..658ffc50493 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -147,6 +147,10 @@ config PPC_970_NAP
 	bool
 	default n
 
+config PPC_P7_NAP
+	bool
+	default n
+
 config PPC_INDIRECT_IO
 	bool
 	select GENERIC_IOMAP
-- 
cgit v1.2.3-70-g09d2


From 5e8e7b404ac965be45e25d5538676151de89aefb Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ozlabs.org>
Date: Tue, 12 Apr 2011 19:00:04 +0000
Subject: powerpc/mm: Standardise on MMU_NO_CONTEXT

Use MMU_NO_CONTEXT as the initialiser for mm_context.id on
nohash and hash64.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/tlbflush.h  | 2 ++
 arch/powerpc/mm/mmu_context_hash64.c | 3 +--
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index d50a380b2b6..81143fcbd11 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -79,6 +79,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
 
 #elif defined(CONFIG_PPC_STD_MMU_64)
 
+#define MMU_NO_CONTEXT		0
+
 /*
  * TLB flushing for 64-bit hash-MMU CPUs
  */
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index 2535828aa84..c5859448a0a 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -31,7 +31,6 @@ static DEFINE_IDA(mmu_context_ida);
  * Each segment contains 2^28 bytes.  Each context maps 2^44 bytes,
  * so we can support 2^19-1 contexts (19 == 35 + 28 - 44).
  */
-#define NO_CONTEXT	0
 #define MAX_CONTEXT	((1UL << 19) - 1)
 
 int __init_new_context(void)
@@ -95,5 +94,5 @@ void destroy_context(struct mm_struct *mm)
 {
 	__destroy_context(mm->context.id);
 	subpage_prot_free(mm);
-	mm->context.id = NO_CONTEXT;
+	mm->context.id = MMU_NO_CONTEXT;
 }
-- 
cgit v1.2.3-70-g09d2


From ee7a2aa3d3fd10a7157dd19f737b2bafdea0458f Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ozlabs.org>
Date: Tue, 12 Apr 2011 19:00:05 +0000
Subject: powerpc/mm: Fix slice state initialization for Book3E

On Book3E, MMU_NO_CONTEXT != 0, but the slice_mm_new_context()
macro assumes that it is.  This means that the map of the
page sizes for each slice is always initialized to zeroes
(which happens to be 4k pages), rather than to the correct
default base page size value - which might be 64k.

This patch corrects the problem.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/page_64.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index 812b2cd80ae..488c52eb64c 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -130,7 +130,7 @@ extern void slice_set_user_psize(struct mm_struct *mm, unsigned int psize);
 extern void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
 				  unsigned long len, unsigned int psize);
 
-#define slice_mm_new_context(mm)	((mm)->context.id == 0)
+#define slice_mm_new_context(mm)	((mm)->context.id == MMU_NO_CONTEXT)
 
 #endif /* __ASSEMBLY__ */
 #else
-- 
cgit v1.2.3-70-g09d2


From de300974761d92f71cb583730ac9e1d4eb1b7156 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ozlabs.org>
Date: Mon, 11 Apr 2011 21:46:19 +0000
Subject: powerpc/smp: smp_ops->kick_cpu() should be able to fail

When we start a cpu we use smp_ops->kick_cpu(), which currently
returns void, it should be able to fail. Convert it to return
int, and update all uses.

Convert all the current error cases to return -ENOENT, which is
what would eventually be returned by __cpu_up() currently when
it doesn't detect the cpu as coming up in time.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/machdep.h        |  2 +-
 arch/powerpc/include/asm/smp.h            |  2 +-
 arch/powerpc/kernel/smp.c                 | 10 ++++++++--
 arch/powerpc/platforms/44x/iss4xx.c       |  6 ++++--
 arch/powerpc/platforms/85xx/smp.c         |  6 ++++--
 arch/powerpc/platforms/86xx/mpc86xx_smp.c |  6 ++++--
 arch/powerpc/platforms/cell/beat_smp.c    |  5 ++---
 arch/powerpc/platforms/cell/smp.c         |  6 ++++--
 arch/powerpc/platforms/chrp/smp.c         |  4 +++-
 arch/powerpc/platforms/iseries/smp.c      |  6 ++++--
 arch/powerpc/platforms/powermac/smp.c     | 10 +++++++---
 arch/powerpc/platforms/pseries/smp.c      |  6 ++++--
 12 files changed, 46 insertions(+), 23 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 493dbb38e1b..c6345acf166 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -33,7 +33,7 @@ struct kimage;
 struct smp_ops_t {
 	void  (*message_pass)(int target, int msg);
 	int   (*probe)(void);
-	void  (*kick_cpu)(int nr);
+	int   (*kick_cpu)(int nr);
 	void  (*setup_cpu)(int nr);
 	void  (*bringup_done)(void);
 	void  (*take_timebase)(void);
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index bb4c033a8fb..50873493a97 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -150,7 +150,7 @@ extern int smt_enabled_at_boot;
 
 extern int smp_mpic_probe(void);
 extern void smp_mpic_setup_cpu(int cpu);
-extern void smp_generic_kick_cpu(int nr);
+extern int smp_generic_kick_cpu(int nr);
 
 extern void smp_generic_give_timebase(void);
 extern void smp_generic_take_timebase(void);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index cbdbb14be4b..b6083f4f39b 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -95,7 +95,7 @@ int smt_enabled_at_boot = 1;
 static void (*crash_ipi_function_ptr)(struct pt_regs *) = NULL;
 
 #ifdef CONFIG_PPC64
-void __devinit smp_generic_kick_cpu(int nr)
+int __devinit smp_generic_kick_cpu(int nr)
 {
 	BUG_ON(nr < 0 || nr >= NR_CPUS);
 
@@ -106,6 +106,8 @@ void __devinit smp_generic_kick_cpu(int nr)
 	 */
 	paca[nr].cpu_start = 1;
 	smp_mb();
+
+	return 0;
 }
 #endif
 
@@ -434,7 +436,11 @@ int __cpuinit __cpu_up(unsigned int cpu)
 
 	/* wake up cpus */
 	DBG("smp: kicking cpu %d\n", cpu);
-	smp_ops->kick_cpu(cpu);
+	rc = smp_ops->kick_cpu(cpu);
+	if (rc) {
+		pr_err("smp: failed starting cpu %d (rc %d)\n", cpu, rc);
+		return rc;
+	}
 
 	/*
 	 * wait to see if the cpu made a callin (is actually up).
diff --git a/arch/powerpc/platforms/44x/iss4xx.c b/arch/powerpc/platforms/44x/iss4xx.c
index aa46e9d1e77..19395f18b1d 100644
--- a/arch/powerpc/platforms/44x/iss4xx.c
+++ b/arch/powerpc/platforms/44x/iss4xx.c
@@ -87,7 +87,7 @@ static void __cpuinit smp_iss4xx_setup_cpu(int cpu)
 	mpic_setup_this_cpu();
 }
 
-static void __cpuinit smp_iss4xx_kick_cpu(int cpu)
+static int __cpuinit smp_iss4xx_kick_cpu(int cpu)
 {
 	struct device_node *cpunode = of_get_cpu_node(cpu, NULL);
 	const u64 *spin_table_addr_prop;
@@ -104,7 +104,7 @@ static void __cpuinit smp_iss4xx_kick_cpu(int cpu)
 					       NULL);
 	if (spin_table_addr_prop == NULL) {
 		pr_err("CPU%d: Can't start, missing cpu-release-addr !\n", cpu);
-		return;
+		return -ENOENT;
 	}
 
 	/* Assume it's mapped as part of the linear mapping. This is a bit
@@ -117,6 +117,8 @@ static void __cpuinit smp_iss4xx_kick_cpu(int cpu)
 	smp_wmb();
 	spin_table[1] = __pa(start_secondary_47x);
 	mb();
+
+	return 0;
 }
 
 static struct smp_ops_t iss_smp_ops = {
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 0d00ff9d05a..fe3f6a3a530 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -41,7 +41,7 @@ extern void __early_start(void);
 #define NUM_BOOT_ENTRY		8
 #define SIZE_BOOT_ENTRY		(NUM_BOOT_ENTRY * sizeof(u32))
 
-static void __init
+static int __init
 smp_85xx_kick_cpu(int nr)
 {
 	unsigned long flags;
@@ -60,7 +60,7 @@ smp_85xx_kick_cpu(int nr)
 
 	if (cpu_rel_addr == NULL) {
 		printk(KERN_ERR "No cpu-release-addr for cpu %d\n", nr);
-		return;
+		return -ENOENT;
 	}
 
 	/*
@@ -107,6 +107,8 @@ smp_85xx_kick_cpu(int nr)
 		iounmap(bptr_vaddr);
 
 	pr_debug("waited %d msecs for CPU #%d.\n", n, nr);
+
+	return 0;
 }
 
 static void __init
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_smp.c b/arch/powerpc/platforms/86xx/mpc86xx_smp.c
index eacea0e3fcc..af09baee22c 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_smp.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_smp.c
@@ -56,7 +56,7 @@ smp_86xx_release_core(int nr)
 }
 
 
-static void __init
+static int __init
 smp_86xx_kick_cpu(int nr)
 {
 	unsigned int save_vector;
@@ -65,7 +65,7 @@ smp_86xx_kick_cpu(int nr)
 	unsigned int *vector = (unsigned int *)(KERNELBASE + 0x100);
 
 	if (nr < 0 || nr >= NR_CPUS)
-		return;
+		return -ENOENT;
 
 	pr_debug("smp_86xx_kick_cpu: kick CPU #%d\n", nr);
 
@@ -92,6 +92,8 @@ smp_86xx_kick_cpu(int nr)
 	local_irq_restore(flags);
 
 	pr_debug("wait CPU #%d for %d msecs.\n", nr, n);
+
+	return 0;
 }
 
 
diff --git a/arch/powerpc/platforms/cell/beat_smp.c b/arch/powerpc/platforms/cell/beat_smp.c
index 26efc204c47..996df33165f 100644
--- a/arch/powerpc/platforms/cell/beat_smp.c
+++ b/arch/powerpc/platforms/cell/beat_smp.c
@@ -93,12 +93,11 @@ static void __devinit smp_beatic_setup_cpu(int cpu)
 	beatic_setup_cpu(cpu);
 }
 
-static void __devinit smp_celleb_kick_cpu(int nr)
+static int __devinit smp_celleb_kick_cpu(int nr)
 {
 	BUG_ON(nr < 0 || nr >= NR_CPUS);
 
-	if (!smp_startup_cpu(nr))
-		return;
+	return smp_startup_cpu(nr);
 }
 
 static int smp_celleb_cpu_bootable(unsigned int nr)
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
index f774530075b..03d638e2f44 100644
--- a/arch/powerpc/platforms/cell/smp.c
+++ b/arch/powerpc/platforms/cell/smp.c
@@ -137,12 +137,12 @@ static void __devinit smp_cell_setup_cpu(int cpu)
 	mtspr(SPRN_DABRX, DABRX_KERNEL | DABRX_USER);
 }
 
-static void __devinit smp_cell_kick_cpu(int nr)
+static int __devinit smp_cell_kick_cpu(int nr)
 {
 	BUG_ON(nr < 0 || nr >= NR_CPUS);
 
 	if (!smp_startup_cpu(nr))
-		return;
+		return -ENOENT;
 
 	/*
 	 * The processor is currently spinning, waiting for the
@@ -150,6 +150,8 @@ static void __devinit smp_cell_kick_cpu(int nr)
 	 * the processor will continue on to secondary_start
 	 */
 	paca[nr].cpu_start = 1;
+
+	return 0;
 }
 
 static int smp_cell_cpu_bootable(unsigned int nr)
diff --git a/arch/powerpc/platforms/chrp/smp.c b/arch/powerpc/platforms/chrp/smp.c
index 02cafecc90e..a800122e4dd 100644
--- a/arch/powerpc/platforms/chrp/smp.c
+++ b/arch/powerpc/platforms/chrp/smp.c
@@ -30,10 +30,12 @@
 #include <asm/mpic.h>
 #include <asm/rtas.h>
 
-static void __devinit smp_chrp_kick_cpu(int nr)
+static int __devinit smp_chrp_kick_cpu(int nr)
 {
 	*(unsigned long *)KERNELBASE = nr;
 	asm volatile("dcbf 0,%0"::"r"(KERNELBASE):"memory");
+
+	return 0;
 }
 
 static void __devinit smp_chrp_setup_cpu(int cpu_nr)
diff --git a/arch/powerpc/platforms/iseries/smp.c b/arch/powerpc/platforms/iseries/smp.c
index 6c6029914db..02a677a1f91 100644
--- a/arch/powerpc/platforms/iseries/smp.c
+++ b/arch/powerpc/platforms/iseries/smp.c
@@ -86,13 +86,13 @@ static int smp_iSeries_probe(void)
 	return cpumask_weight(cpu_possible_mask);
 }
 
-static void smp_iSeries_kick_cpu(int nr)
+static int smp_iSeries_kick_cpu(int nr)
 {
 	BUG_ON((nr < 0) || (nr >= NR_CPUS));
 
 	/* Verify that our partition has a processor nr */
 	if (lppaca_of(nr).dyn_proc_status >= 2)
-		return;
+		return -ENOENT;
 
 	/* The processor is currently spinning, waiting
 	 * for the cpu_start field to become non-zero
@@ -100,6 +100,8 @@ static void smp_iSeries_kick_cpu(int nr)
 	 * continue on to secondary_start in iSeries_head.S
 	 */
 	paca[nr].cpu_start = 1;
+
+	return 0;
 }
 
 static void __devinit smp_iSeries_setup_cpu(int nr)
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index bc5f0dc6ae1..621d4b7755f 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -329,7 +329,7 @@ static int __init smp_psurge_probe(void)
 	return ncpus;
 }
 
-static void __init smp_psurge_kick_cpu(int nr)
+static int __init smp_psurge_kick_cpu(int nr)
 {
 	unsigned long start = __pa(__secondary_start_pmac_0) + nr * 8;
 	unsigned long a, flags;
@@ -394,6 +394,8 @@ static void __init smp_psurge_kick_cpu(int nr)
 		psurge_set_ipi(1);
 
 	if (ppc_md.progress) ppc_md.progress("smp_psurge_kick_cpu - done", 0x354);
+
+	return 0;
 }
 
 static struct irqaction psurge_irqaction = {
@@ -791,14 +793,14 @@ static int __init smp_core99_probe(void)
 	return ncpus;
 }
 
-static void __devinit smp_core99_kick_cpu(int nr)
+static int __devinit smp_core99_kick_cpu(int nr)
 {
 	unsigned int save_vector;
 	unsigned long target, flags;
 	unsigned int *vector = (unsigned int *)(PAGE_OFFSET+0x100);
 
 	if (nr < 0 || nr > 3)
-		return;
+		return -ENOENT;
 
 	if (ppc_md.progress)
 		ppc_md.progress("smp_core99_kick_cpu", 0x346);
@@ -830,6 +832,8 @@ static void __devinit smp_core99_kick_cpu(int nr)
 
 	local_irq_restore(flags);
 	if (ppc_md.progress) ppc_md.progress("smp_core99_kick_cpu done", 0x347);
+
+	return 0;
 }
 
 static void __devinit smp_core99_setup_cpu(int cpu_nr)
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index fc72bfce732..95f578158ff 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -152,12 +152,12 @@ static void __devinit smp_xics_setup_cpu(int cpu)
 #endif
 }
 
-static void __devinit smp_pSeries_kick_cpu(int nr)
+static int __devinit smp_pSeries_kick_cpu(int nr)
 {
 	BUG_ON(nr < 0 || nr >= NR_CPUS);
 
 	if (!smp_startup_cpu(nr))
-		return;
+		return -ENOENT;
 
 	/*
 	 * The processor is currently spinning, waiting for the
@@ -179,6 +179,8 @@ static void __devinit smp_pSeries_kick_cpu(int nr)
 						"Ret= %ld\n", nr, rc);
 	}
 #endif
+
+	return 0;
 }
 
 static int smp_pSeries_cpu_bootable(unsigned int nr)
-- 
cgit v1.2.3-70-g09d2


From 931e1241a266e701157d3478d0d44fc58d6e84b4 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 14 Apr 2011 22:31:56 +0000
Subject: powerpc/a2: Add some #defines for A2 specific instructions

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/ppc-opcode.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 384a96db794..3e25b258568 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -59,6 +59,14 @@
 #define PPC_INST_NAP			0x4c000364
 #define PPC_INST_SLEEP			0x4c0003a4
 
+/* A2 specific instructions */
+#define PPC_INST_ERATWE			0x7c0001a6
+#define PPC_INST_ERATRE			0x7c000166
+#define PPC_INST_ERATILX		0x7c000066
+#define PPC_INST_ERATIVAX		0x7c000666
+#define PPC_INST_ERATSX			0x7c000126
+#define PPC_INST_ERATSX_DOT		0x7c000127
+
 /* macros to insert fields into opcodes */
 #define __PPC_RA(a)	(((a) & 0x1f) << 16)
 #define __PPC_RB(b)	(((b) & 0x1f) << 11)
@@ -70,6 +78,8 @@
 #define __PPC_XT(s)	__PPC_XS(s)
 #define __PPC_T_TLB(t)	(((t) & 0x3) << 21)
 #define __PPC_WC(w)	(((w) & 0x3) << 21)
+#define __PPC_WS(w)	(((w) & 0x1f) << 11)
+
 /*
  * Only use the larx hint bit on 64bit CPUs. e500v1/v2 based CPUs will treat a
  * larx with EH set as an illegal instruction.
@@ -116,6 +126,21 @@
 #define PPC_TLBIVAX(a,b)	stringify_in_c(.long PPC_INST_TLBIVAX | \
 					__PPC_RA(a) | __PPC_RB(b))
 
+#define PPC_ERATWE(s, a, w)	stringify_in_c(.long PPC_INST_ERATWE | \
+					__PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w))
+#define PPC_ERATRE(s, a, w)	stringify_in_c(.long PPC_INST_ERATRE | \
+					__PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w))
+#define PPC_ERATILX(t, a, b)	stringify_in_c(.long PPC_INST_ERATILX | \
+					__PPC_T_TLB(t) | __PPC_RA(a) | \
+					__PPC_RB(b))
+#define PPC_ERATIVAX(s, a, b)	stringify_in_c(.long PPC_INST_ERATIVAX | \
+					__PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b))
+#define PPC_ERATSX(t, a, w)	stringify_in_c(.long PPC_INST_ERATSX | \
+					__PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b))
+#define PPC_ERATSX_DOT(t, a, w)	stringify_in_c(.long PPC_INST_ERATSX_DOT | \
+					__PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b))
+
+
 /*
  * Define what the VSX XX1 form instructions will look like, then add
  * the 128 bit load store instructions based on that.
-- 
cgit v1.2.3-70-g09d2


From cd852579055bd8ad848415aaabb78b65d522fce0 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ellerman.id.au>
Date: Thu, 14 Apr 2011 22:31:58 +0000
Subject: powerpc/xics: xics.h relies on linux/interrupt.h

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/xics.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index 146aad8534d..c4ed4c5b646 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -6,6 +6,8 @@
 #ifndef _XICS_H
 #define _XICS_H
 
+#include <linux/interrupt.h>
+
 #define XICS_IPI		2
 #define XICS_IRQ_SPURIOUS	0
 
-- 
cgit v1.2.3-70-g09d2


From ab814b938d1d372bd2ac6268c15d4e0e6a5245c4 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 14 Apr 2011 22:31:58 +0000
Subject: powerpc: Add SCOM infrastructure

SCOM is a side-band configuration bus implemented on some processors.
This code provides a way for code to map and operate on devices via
SCOM, while the details of how that is implemented is left up to a
SCOM "controller" in the platform code.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/scom.h | 156 ++++++++++++++++++++++++++++++++
 arch/powerpc/sysdev/Kconfig     |   7 ++
 arch/powerpc/sysdev/Makefile    |   2 +
 arch/powerpc/sysdev/scom.c      | 192 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 357 insertions(+)
 create mode 100644 arch/powerpc/include/asm/scom.h
 create mode 100644 arch/powerpc/sysdev/scom.c

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/scom.h b/arch/powerpc/include/asm/scom.h
new file mode 100644
index 00000000000..0cabfd7bc2d
--- /dev/null
+++ b/arch/powerpc/include/asm/scom.h
@@ -0,0 +1,156 @@
+/*
+ * Copyright 2010 Benjamin Herrenschmidt, IBM Corp
+ *                <benh@kernel.crashing.org>
+ *     and        David Gibson, IBM Corporation.
+ *
+ *   This program is free software;  you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY;  without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
+ *   the GNU General Public License for more details.
+ *
+ *   You should have received a copy of the GNU General Public License
+ *   along with this program;  if not, write to the Free Software
+ *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _ASM_POWERPC_SCOM_H
+#define _ASM_POWERPC_SCOM_H
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_PPC_SCOM
+
+/*
+ * The SCOM bus is a sideband bus used for accessing various internal
+ * registers of the processor or the chipset. The implementation details
+ * differ between processors and platforms, and the access method as
+ * well.
+ *
+ * This API allows to "map" ranges of SCOM register numbers associated
+ * with a given SCOM controller. The later must be represented by a
+ * device node, though some implementations might support NULL if there
+ * is no possible ambiguity
+ *
+ * Then, scom_read/scom_write can be used to accesses registers inside
+ * that range. The argument passed is a register number relative to
+ * the beginning of the range mapped.
+ */
+
+typedef void *scom_map_t;
+
+/* Value for an invalid SCOM map */
+#define SCOM_MAP_INVALID	(NULL)
+
+/* The scom_controller data structure is what the platform passes
+ * to the core code in scom_init, it provides the actual implementation
+ * of all the SCOM functions
+ */
+struct scom_controller {
+	scom_map_t (*map)(struct device_node *ctrl_dev, u64 reg, u64 count);
+	void (*unmap)(scom_map_t map);
+
+	u64 (*read)(scom_map_t map, u32 reg);
+	void (*write)(scom_map_t map, u32 reg, u64 value);
+};
+
+extern const struct scom_controller *scom_controller;
+
+/**
+ * scom_init - Initialize the SCOM backend, called by the platform
+ * @controller: The platform SCOM controller
+ */
+static inline void scom_init(const struct scom_controller *controller)
+{
+	scom_controller = controller;
+}
+
+/**
+ * scom_map_ok - Test is a SCOM mapping is successful
+ * @map: The result of scom_map to test
+ */
+static inline int scom_map_ok(scom_map_t map)
+{
+	return map != SCOM_MAP_INVALID;
+}
+
+/**
+ * scom_map - Map a block of SCOM registers
+ * @ctrl_dev: Device node of the SCOM controller
+ *            some implementations allow NULL here
+ * @reg: first SCOM register to map
+ * @count: Number of SCOM registers to map
+ */
+
+static inline scom_map_t scom_map(struct device_node *ctrl_dev,
+				  u64 reg, u64 count)
+{
+	return scom_controller->map(ctrl_dev, reg, count);
+}
+
+/**
+ * scom_find_parent - Find the SCOM controller for a device
+ * @dev: OF node of the device
+ *
+ * This is not meant for general usage, but in combination with
+ * scom_map() allows to map registers not represented by the
+ * device own scom-reg property. Useful for applying HW workarounds
+ * on things not properly represented in the device-tree for example.
+ */
+struct device_node *scom_find_parent(struct device_node *dev);
+
+
+/**
+ * scom_map_device - Map a device's block of SCOM registers
+ * @dev: OF node of the device
+ * @index: Register bank index (index in "scom-reg" property)
+ *
+ * This function will use the device-tree binding for SCOM which
+ * is to follow "scom-parent" properties until it finds a node with
+ * a "scom-controller" property to find the controller. It will then
+ * use the "scom-reg" property which is made of reg/count pairs,
+ * each of them having a size defined by the controller's #scom-cells
+ * property
+ */
+extern scom_map_t scom_map_device(struct device_node *dev, int index);
+
+
+/**
+ * scom_unmap - Unmap a block of SCOM registers
+ * @map: Result of scom_map is to be unmapped
+ */
+static inline void scom_unmap(scom_map_t map)
+{
+	if (scom_map_ok(map))
+		scom_controller->unmap(map);
+}
+
+/**
+ * scom_read - Read a SCOM register
+ * @map: Result of scom_map
+ * @reg: Register index within that map
+ */
+static inline u64 scom_read(scom_map_t map, u32 reg)
+{
+	return scom_controller->read(map, reg);
+}
+
+/**
+ * scom_write - Write to a SCOM register
+ * @map: Result of scom_map
+ * @reg: Register index within that map
+ * @value: Value to write
+ */
+static inline void scom_write(scom_map_t map, u32 reg, u64 value)
+{
+	scom_controller->write(map, reg, value);
+}
+
+#endif /* CONFIG_PPC_SCOM */
+#endif /* __ASSEMBLY__ */
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_SCOM_H */
diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig
index cfc18770af7..d775fd148d1 100644
--- a/arch/powerpc/sysdev/Kconfig
+++ b/arch/powerpc/sysdev/Kconfig
@@ -15,3 +15,10 @@ config PPC_MSI_BITMAP
 
 source "arch/powerpc/sysdev/xics/Kconfig"
 
+config PPC_SCOM
+	bool
+
+config SCOM_DEBUGFS
+	bool "Expose SCOM controllers via debugfs"
+	depends on PPC_SCOM
+	default n
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index 9516e759857..6076e0074a8 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -58,6 +58,8 @@ ifeq ($(CONFIG_SUSPEND),y)
 obj-$(CONFIG_6xx)		+= 6xx-suspend.o
 endif
 
+obj-$(CONFIG_PPC_SCOM)		+= scom.o
+
 subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 obj-$(CONFIG_PPC_XICS)		+= xics/
diff --git a/arch/powerpc/sysdev/scom.c b/arch/powerpc/sysdev/scom.c
new file mode 100644
index 00000000000..b2593ce30c9
--- /dev/null
+++ b/arch/powerpc/sysdev/scom.c
@@ -0,0 +1,192 @@
+/*
+ * Copyright 2010 Benjamin Herrenschmidt, IBM Corp
+ *                <benh@kernel.crashing.org>
+ *     and        David Gibson, IBM Corporation.
+ *
+ *   This program is free software;  you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation; either version 2 of the License, or
+ *   (at your option) any later version.
+ *
+ *   This program is distributed in the hope that it will be useful,
+ *   but WITHOUT ANY WARRANTY;  without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
+ *   the GNU General Public License for more details.
+ *
+ *   You should have received a copy of the GNU General Public License
+ *   along with this program;  if not, write to the Free Software
+ *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+#include <asm/prom.h>
+#include <asm/scom.h>
+
+const struct scom_controller *scom_controller;
+EXPORT_SYMBOL_GPL(scom_controller);
+
+struct device_node *scom_find_parent(struct device_node *node)
+{
+	struct device_node *par, *tmp;
+	const u32 *p;
+
+	for (par = of_node_get(node); par;) {
+		if (of_get_property(par, "scom-controller", NULL))
+			break;
+		p = of_get_property(par, "scom-parent", NULL);
+		tmp = par;
+		if (p == NULL)
+			par = of_get_parent(par);
+		else
+			par = of_find_node_by_phandle(*p);
+		of_node_put(tmp);
+	}
+	return par;
+}
+EXPORT_SYMBOL_GPL(scom_find_parent);
+
+scom_map_t scom_map_device(struct device_node *dev, int index)
+{
+	struct device_node *parent;
+	unsigned int cells, size;
+	const u32 *prop;
+	u64 reg, cnt;
+	scom_map_t ret;
+
+	parent = scom_find_parent(dev);
+
+	if (parent == NULL)
+		return 0;
+
+	prop = of_get_property(parent, "#scom-cells", NULL);
+	cells = prop ? *prop : 1;
+
+	prop = of_get_property(dev, "scom-reg", &size);
+	if (!prop)
+		return 0;
+	size >>= 2;
+
+	if (index >= (size / (2*cells)))
+		return 0;
+
+	reg = of_read_number(&prop[index * cells * 2], cells);
+	cnt = of_read_number(&prop[index * cells * 2 + cells], cells);
+
+	ret = scom_map(parent, reg, cnt);
+	of_node_put(parent);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(scom_map_device);
+
+#ifdef CONFIG_SCOM_DEBUGFS
+struct scom_debug_entry {
+	struct device_node *dn;
+	unsigned long addr;
+	scom_map_t map;
+	spinlock_t lock;
+	char name[8];
+	struct debugfs_blob_wrapper blob;
+};
+
+static int scom_addr_set(void *data, u64 val)
+{
+	struct scom_debug_entry *ent = data;
+
+	ent->addr = 0;
+	scom_unmap(ent->map);
+
+	ent->map = scom_map(ent->dn, val, 1);
+	if (scom_map_ok(ent->map))
+		ent->addr = val;
+	else
+		return -EFAULT;
+
+	return 0;
+}
+
+static int scom_addr_get(void *data, u64 *val)
+{
+	struct scom_debug_entry *ent = data;
+	*val = ent->addr;
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(scom_addr_fops, scom_addr_get, scom_addr_set,
+			"0x%llx\n");
+
+static int scom_val_set(void *data, u64 val)
+{
+	struct scom_debug_entry *ent = data;
+
+	if (!scom_map_ok(ent->map))
+		return -EFAULT;
+
+	scom_write(ent->map, 0, val);
+
+	return 0;
+}
+
+static int scom_val_get(void *data, u64 *val)
+{
+	struct scom_debug_entry *ent = data;
+
+	if (!scom_map_ok(ent->map))
+		return -EFAULT;
+
+	*val = scom_read(ent->map, 0);
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(scom_val_fops, scom_val_get, scom_val_set,
+			"0x%llx\n");
+
+static int scom_debug_init_one(struct dentry *root, struct device_node *dn,
+			       int i)
+{
+	struct scom_debug_entry *ent;
+	struct dentry *dir;
+
+	ent = kzalloc(sizeof(*ent), GFP_KERNEL);
+	if (!ent)
+		return -ENOMEM;
+
+	ent->dn = of_node_get(dn);
+	ent->map = SCOM_MAP_INVALID;
+	spin_lock_init(&ent->lock);
+	snprintf(ent->name, 8, "scom%d", i);
+	ent->blob.data = dn->full_name;
+	ent->blob.size = strlen(dn->full_name);
+
+	dir = debugfs_create_dir(ent->name, root);
+	if (!dir) {
+		of_node_put(dn);
+		kfree(ent);
+		return -1;
+	}
+
+	debugfs_create_file("addr", 0600, dir, ent, &scom_addr_fops);
+	debugfs_create_file("value", 0600, dir, ent, &scom_val_fops);
+	debugfs_create_blob("path", 0400, dir, &ent->blob);
+
+	return 0;
+}
+
+static int scom_debug_init(void)
+{
+	struct device_node *dn;
+	struct dentry *root;
+	int i, rc;
+
+	root = debugfs_create_dir("scom", powerpc_debugfs_root);
+	if (!root)
+		return -1;
+
+	i = rc = 0;
+	for_each_node_with_property(dn, "scom-controller")
+		rc |= scom_debug_init_one(root, dn, i++);
+
+	return rc;
+}
+device_initcall(scom_debug_init);
+#endif /* CONFIG_SCOM_DEBUGFS */
-- 
cgit v1.2.3-70-g09d2


From 5ca123760177ed16cbd9bab609bff69eb8fc45bd Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ellerman.id.au>
Date: Thu, 14 Apr 2011 22:31:59 +0000
Subject: powerpc/xics: Move irq_host matching into the ics backend

An upcoming new ics backend will need to implement different matching
semantics to the current ones, which are essentially the RTAS ics
backends. So move the current match into the RTAS backend, and allow
other ics backends to override.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/xics.h        |  1 +
 arch/powerpc/sysdev/xics/ics-rtas.c    | 11 +++++++++++
 arch/powerpc/sysdev/xics/xics-common.c | 12 +++++++-----
 3 files changed, 19 insertions(+), 5 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index c4ed4c5b646..6c06306c410 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -59,6 +59,7 @@ struct ics {
 	int (*map)(struct ics *ics, unsigned int virq);
 	void (*mask_unknown)(struct ics *ics, unsigned long vec);
 	long (*get_server)(struct ics *ics, unsigned long vec);
+	int (*host_match)(struct ics *ics, struct device_node *node);
 	char data[];
 };
 
diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c
index 5b3ee387e89..610c148fedc 100644
--- a/arch/powerpc/sysdev/xics/ics-rtas.c
+++ b/arch/powerpc/sysdev/xics/ics-rtas.c
@@ -26,12 +26,14 @@ static int ibm_int_off;
 static int ics_rtas_map(struct ics *ics, unsigned int virq);
 static void ics_rtas_mask_unknown(struct ics *ics, unsigned long vec);
 static long ics_rtas_get_server(struct ics *ics, unsigned long vec);
+static int ics_rtas_host_match(struct ics *ics, struct device_node *node);
 
 /* Only one global & state struct ics */
 static struct ics ics_rtas = {
 	.map		= ics_rtas_map,
 	.mask_unknown	= ics_rtas_mask_unknown,
 	.get_server	= ics_rtas_get_server,
+	.host_match	= ics_rtas_host_match,
 };
 
 static void ics_rtas_unmask_irq(struct irq_data *d)
@@ -202,6 +204,15 @@ static long ics_rtas_get_server(struct ics *ics, unsigned long vec)
 	return status[0];
 }
 
+static int ics_rtas_host_match(struct ics *ics, struct device_node *node)
+{
+	/* IBM machines have interrupt parents of various funky types for things
+	 * like vdevices, events, etc... The trick we use here is to match
+	 * everything here except the legacy 8259 which is compatible "chrp,iic"
+	 */
+	return !of_device_is_compatible(node, "chrp,iic");
+}
+
 int ics_rtas_init(void)
 {
 	ibm_get_xive = rtas_token("ibm,get-xive");
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index e70175dfe32..c58844d7242 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -331,11 +331,13 @@ int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask,
 
 static int xics_host_match(struct irq_host *h, struct device_node *node)
 {
-	/* IBM machines have interrupt parents of various funky types for things
-	 * like vdevices, events, etc... The trick we use here is to match
-	 * everything here except the legacy 8259 which is compatible "chrp,iic"
-	 */
-	return !of_device_is_compatible(node, "chrp,iic");
+	struct ics *ics;
+
+	list_for_each_entry(ics, &ics_list, link)
+		if (ics->host_match(ics, node))
+			return 1;
+
+	return 0;
 }
 
 /* Dummies */
-- 
cgit v1.2.3-70-g09d2


From 76b4eda866c4936af8d696f040abea56bf688e16 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 14 Apr 2011 22:32:01 +0000
Subject: powerpc: Add A2 cpu support

Add the cputable entry, regs and setup & restore entries for
the PowerPC A2 core.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/cputable.h    |   8 +-
 arch/powerpc/include/asm/reg_a2.h      | 156 +++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/Makefile           |   1 +
 arch/powerpc/kernel/cpu_setup_a2.S     | 114 ++++++++++++++++++++++++
 arch/powerpc/kernel/cputable.c         |  25 +++++-
 arch/powerpc/platforms/Kconfig.cputype |   4 +
 6 files changed, 304 insertions(+), 4 deletions(-)
 create mode 100644 arch/powerpc/include/asm/reg_a2.h
 create mode 100644 arch/powerpc/kernel/cpu_setup_a2.S

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 2fe37d78193..2d71523ebb0 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -437,9 +437,13 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_NO_SLBIE_B)
 #define CPU_FTRS_COMPATIBLE	(CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2)
 
+#define CPU_FTRS_A2 (CPU_FTR_USE_TB | CPU_FTR_SMT | CPU_FTR_DBELL | \
+	    CPU_FTR_TLBIEL | CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN | \
+	    CPU_FTR_16M_PAGE)
+
 #ifdef __powerpc64__
 #ifdef CONFIG_PPC_BOOK3E
-#define CPU_FTRS_POSSIBLE	(CPU_FTRS_E5500)
+#define CPU_FTRS_POSSIBLE	(CPU_FTRS_E5500 | CPU_FTRS_A2)
 #else
 #define CPU_FTRS_POSSIBLE	\
 	    (CPU_FTRS_POWER3 | CPU_FTRS_RS64 | CPU_FTRS_POWER4 |	\
@@ -488,7 +492,7 @@ enum {
 
 #ifdef __powerpc64__
 #ifdef CONFIG_PPC_BOOK3E
-#define CPU_FTRS_ALWAYS		(CPU_FTRS_E5500)
+#define CPU_FTRS_ALWAYS		(CPU_FTRS_E5500 & CPU_FTRS_A2)
 #else
 #define CPU_FTRS_ALWAYS		\
 	    (CPU_FTRS_POWER3 & CPU_FTRS_RS64 & CPU_FTRS_POWER4 &	\
diff --git a/arch/powerpc/include/asm/reg_a2.h b/arch/powerpc/include/asm/reg_a2.h
new file mode 100644
index 00000000000..3ba9c6f096f
--- /dev/null
+++ b/arch/powerpc/include/asm/reg_a2.h
@@ -0,0 +1,156 @@
+/*
+ *  Register definitions specific to the A2 core
+ *
+ *  Copyright (C) 2008 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#ifndef __ASM_POWERPC_REG_A2_H__
+#define __ASM_POWERPC_REG_A2_H__
+
+#define SPRN_TENSR	0x1b5
+#define SPRN_TENS	0x1b6	/* Thread ENable Set */
+#define SPRN_TENC	0x1b7	/* Thread ENable Clear */
+
+#define SPRN_A2_CCR0	0x3f0	/* Core Configuration Register 0 */
+#define SPRN_A2_CCR1	0x3f1	/* Core Configuration Register 1 */
+#define SPRN_A2_CCR2	0x3f2	/* Core Configuration Register 2 */
+#define SPRN_MMUCR0	0x3fc	/* MMU Control Register 0 */
+#define SPRN_MMUCR1	0x3fd	/* MMU Control Register 1 */
+#define SPRN_MMUCR2	0x3fe	/* MMU Control Register 2 */
+#define SPRN_MMUCR3	0x3ff	/* MMU Control Register 3 */
+
+#define SPRN_IAR	0x372
+
+#define SPRN_IUCR0	0x3f3
+#define IUCR0_ICBI_ACK	0x1000
+
+#define SPRN_XUCR0	0x3f6	/* Execution Unit Config Register 0 */
+
+#define A2_IERAT_SIZE	16
+#define A2_DERAT_SIZE	32
+
+/* A2 MMUCR0 bits */
+#define MMUCR0_ECL	0x80000000	/* Extended Class for TLB fills */
+#define MMUCR0_TID_NZ	0x40000000	/* TID is non-zero */
+#define MMUCR0_TS	0x10000000	/* Translation space for TLB fills */
+#define MMUCR0_TGS	0x20000000	/* Guest space for TLB fills */
+#define MMUCR0_TLBSEL	0x0c000000	/* TLB or ERAT target for TLB fills */
+#define MMUCR0_TLBSEL_U	0x00000000	/*  TLBSEL = UTLB */
+#define MMUCR0_TLBSEL_I	0x08000000	/*  TLBSEL = I-ERAT */
+#define MMUCR0_TLBSEL_D	0x0c000000	/*  TLBSEL = D-ERAT */
+#define MMUCR0_LOCKSRSH	0x02000000	/* Use TLB lock on tlbsx. */
+#define MMUCR0_TID_MASK	0x000000ff	/* TID field */
+
+/* A2 MMUCR1 bits */
+#define MMUCR1_IRRE		0x80000000	/* I-ERAT round robin enable */
+#define MMUCR1_DRRE		0x40000000	/* D-ERAT round robin enable */
+#define MMUCR1_REE		0x20000000	/* Reference Exception Enable*/
+#define MMUCR1_CEE		0x10000000	/* Change exception enable */
+#define MMUCR1_CSINV_ALL	0x00000000	/* Inval ERAT on all CS evts */
+#define MMUCR1_CSINV_NISYNC	0x04000000	/* Inval ERAT on all ex isync*/
+#define MMUCR1_CSINV_NEVER	0x0c000000	/* Don't inval ERAT on CS */
+#define MMUCR1_ICTID		0x00080000	/* IERAT class field as TID */
+#define MMUCR1_ITTID		0x00040000	/* IERAT thdid field as TID */
+#define MMUCR1_DCTID		0x00020000	/* DERAT class field as TID */
+#define MMUCR1_DTTID		0x00010000	/* DERAT thdid field as TID */
+#define MMUCR1_DCCD		0x00008000	/* DERAT class ignore */
+#define MMUCR1_TLBWE_BINV	0x00004000	/* back invalidate on tlbwe */
+
+/* A2 MMUCR2 bits */
+#define MMUCR2_PSSEL_SHIFT	4
+
+/* A2 MMUCR3 bits */
+#define MMUCR3_THID		0x0000000f	/* Thread ID */
+
+/* *** ERAT TLB bits definitions */
+#define TLB0_EPN_MASK		ASM_CONST(0xfffffffffffff000)
+#define TLB0_CLASS_MASK		ASM_CONST(0x0000000000000c00)
+#define TLB0_CLASS_00		ASM_CONST(0x0000000000000000)
+#define TLB0_CLASS_01		ASM_CONST(0x0000000000000400)
+#define TLB0_CLASS_10		ASM_CONST(0x0000000000000800)
+#define TLB0_CLASS_11		ASM_CONST(0x0000000000000c00)
+#define TLB0_V			ASM_CONST(0x0000000000000200)
+#define TLB0_X			ASM_CONST(0x0000000000000100)
+#define TLB0_SIZE_MASK		ASM_CONST(0x00000000000000f0)
+#define TLB0_SIZE_4K		ASM_CONST(0x0000000000000010)
+#define TLB0_SIZE_64K		ASM_CONST(0x0000000000000030)
+#define TLB0_SIZE_1M		ASM_CONST(0x0000000000000050)
+#define TLB0_SIZE_16M		ASM_CONST(0x0000000000000070)
+#define TLB0_SIZE_1G		ASM_CONST(0x00000000000000a0)
+#define TLB0_THDID_MASK		ASM_CONST(0x000000000000000f)
+#define TLB0_THDID_0		ASM_CONST(0x0000000000000001)
+#define TLB0_THDID_1		ASM_CONST(0x0000000000000002)
+#define TLB0_THDID_2		ASM_CONST(0x0000000000000004)
+#define TLB0_THDID_3		ASM_CONST(0x0000000000000008)
+#define TLB0_THDID_ALL		ASM_CONST(0x000000000000000f)
+
+#define TLB1_RESVATTR		ASM_CONST(0x00f0000000000000)
+#define TLB1_U0			ASM_CONST(0x0008000000000000)
+#define TLB1_U1			ASM_CONST(0x0004000000000000)
+#define TLB1_U2			ASM_CONST(0x0002000000000000)
+#define TLB1_U3			ASM_CONST(0x0001000000000000)
+#define TLB1_R			ASM_CONST(0x0000800000000000)
+#define TLB1_C			ASM_CONST(0x0000400000000000)
+#define TLB1_RPN_MASK		ASM_CONST(0x000003fffffff000)
+#define TLB1_W			ASM_CONST(0x0000000000000800)
+#define TLB1_I			ASM_CONST(0x0000000000000400)
+#define TLB1_M			ASM_CONST(0x0000000000000200)
+#define TLB1_G			ASM_CONST(0x0000000000000100)
+#define TLB1_E			ASM_CONST(0x0000000000000080)
+#define TLB1_VF			ASM_CONST(0x0000000000000040)
+#define TLB1_UX			ASM_CONST(0x0000000000000020)
+#define TLB1_SX			ASM_CONST(0x0000000000000010)
+#define TLB1_UW			ASM_CONST(0x0000000000000008)
+#define TLB1_SW			ASM_CONST(0x0000000000000004)
+#define TLB1_UR			ASM_CONST(0x0000000000000002)
+#define TLB1_SR			ASM_CONST(0x0000000000000001)
+
+/* A2 erativax attributes definitions */
+#define ERATIVAX_RS_IS_ALL		0x000
+#define ERATIVAX_RS_IS_TID		0x040
+#define ERATIVAX_RS_IS_CLASS		0x080
+#define ERATIVAX_RS_IS_FULLMATCH	0x0c0
+#define ERATIVAX_CLASS_00		0x000
+#define ERATIVAX_CLASS_01		0x010
+#define ERATIVAX_CLASS_10		0x020
+#define ERATIVAX_CLASS_11		0x030
+#define ERATIVAX_PSIZE_4K		(TLB_PSIZE_4K >> 1)
+#define ERATIVAX_PSIZE_64K		(TLB_PSIZE_64K >> 1)
+#define ERATIVAX_PSIZE_1M		(TLB_PSIZE_1M >> 1)
+#define ERATIVAX_PSIZE_16M		(TLB_PSIZE_16M >> 1)
+#define ERATIVAX_PSIZE_1G		(TLB_PSIZE_1G >> 1)
+
+/* A2 eratilx attributes definitions */
+#define ERATILX_T_ALL			0
+#define ERATILX_T_TID			1
+#define ERATILX_T_TGS			2
+#define ERATILX_T_FULLMATCH		3
+#define ERATILX_T_CLASS0		4
+#define ERATILX_T_CLASS1		5
+#define ERATILX_T_CLASS2		6
+#define ERATILX_T_CLASS3		7
+
+/* XUCR0 bits */
+#define XUCR0_TRACE_UM_T0		0x40000000	/* Thread 0 */
+#define XUCR0_TRACE_UM_T1		0x20000000	/* Thread 1 */
+#define XUCR0_TRACE_UM_T2		0x10000000	/* Thread 2 */
+#define XUCR0_TRACE_UM_T3		0x08000000	/* Thread 3 */
+
+/* A2 CCR0 register */
+#define A2_CCR0_PME_DISABLED		0x00000000
+#define A2_CCR0_PME_SLEEP		0x40000000
+#define A2_CCR0_PME_RVW			0x80000000
+#define A2_CCR0_PME_DISABLED2		0xc0000000
+
+/* A2 CCR2 register */
+#define A2_CCR2_ERAT_ONLY_MODE		0x00000001
+#define A2_CCR2_ENABLE_ICSWX		0x00000002
+#define A2_CCR2_ENABLE_PC		0x20000000
+#define A2_CCR2_ENABLE_TRACE		0x40000000
+
+#endif /* __ASM_POWERPC_REG_A2_H__ */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 0fd6273bb8a..058bc8bac48 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power7.o
 obj64-$(CONFIG_RELOCATABLE)	+= reloc_64.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
+obj-$(CONFIG_PPC_A2)		+= cpu_setup_a2.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
diff --git a/arch/powerpc/kernel/cpu_setup_a2.S b/arch/powerpc/kernel/cpu_setup_a2.S
new file mode 100644
index 00000000000..7f818feaa7a
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_setup_a2.S
@@ -0,0 +1,114 @@
+/*
+ *  A2 specific assembly support code
+ *
+ *  Copyright 2009 Ben Herrenschmidt, IBM Corp.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/asm-offsets.h>
+#include <asm/ppc_asm.h>
+#include <asm/ppc-opcode.h>
+#include <asm/processor.h>
+#include <asm/reg_a2.h>
+#include <asm/reg.h>
+#include <asm/thread_info.h>
+
+/*
+ * Disable thdid and class fields in ERATs to bump PID to full 14 bits capacity.
+ * This also prevents external LPID accesses but that isn't a problem when not a
+ * guest. Under PV, this setting will be ignored and MMUCR will return the right
+ * number of PID bits we can use.
+ */
+#define MMUCR1_EXTEND_PID \
+	(MMUCR1_ICTID | MMUCR1_ITTID | MMUCR1_DCTID | \
+	 MMUCR1_DTTID | MMUCR1_DCCD)
+
+/*
+ * Use extended PIDs if enabled.
+ * Don't clear the ERATs on context sync events and enable I & D LRU.
+ * Enable ERAT back invalidate when tlbwe overwrites an entry.
+ */
+#define INITIAL_MMUCR1 \
+	(MMUCR1_EXTEND_PID | MMUCR1_CSINV_NEVER | MMUCR1_IRRE | \
+	 MMUCR1_DRRE | MMUCR1_TLBWE_BINV)
+
+_GLOBAL(__setup_cpu_a2)
+	/* Some of these are actually thread local and some are
+	 * core local but doing it always won't hurt
+	 */
+
+#ifdef CONFIG_PPC_WSP_COPRO
+	/* Make sure ACOP starts out as zero */
+	li	r3,0
+	mtspr   SPRN_ACOP,r3
+
+	/* Enable icswx instruction */
+	mfspr   r3,SPRN_A2_CCR2
+	ori     r3,r3,A2_CCR2_ENABLE_ICSWX
+	mtspr   SPRN_A2_CCR2,r3
+
+	/* Unmask all CTs in HACOP */
+	li      r3,-1
+	mtspr   SPRN_HACOP,r3
+#endif /* CONFIG_PPC_WSP_COPRO */
+
+	/* Enable doorbell */
+	mfspr   r3,SPRN_A2_CCR2
+	oris     r3,r3,A2_CCR2_ENABLE_PC@h
+	mtspr   SPRN_A2_CCR2,r3
+	isync
+
+	/* Setup CCR0 to disable power saving for now as it's busted
+	 * in the current implementations. Setup CCR1 to wake on
+	 * interrupts normally (we write the default value but who
+	 * knows what FW may have clobbered...)
+	 */
+	li	r3,0
+	mtspr	SPRN_A2_CCR0, r3
+	LOAD_REG_IMMEDIATE(r3,0x0f0f0f0f)
+	mtspr	SPRN_A2_CCR1, r3
+
+	/* Initialise MMUCR1 */
+	lis	r3,INITIAL_MMUCR1@h
+	ori	r3,r3,INITIAL_MMUCR1@l
+	mtspr	SPRN_MMUCR1,r3
+
+	/* Set MMUCR2 to enable 4K, 64K, 1M, 16M and 1G pages */
+	LOAD_REG_IMMEDIATE(r3, 0x000a7531)
+	mtspr	SPRN_MMUCR2,r3
+
+	/* Set MMUCR3 to write all thids bit to the TLB */
+	LOAD_REG_IMMEDIATE(r3, 0x0000000f)
+	mtspr	SPRN_MMUCR3,r3
+
+	/* Don't do ERAT stuff if running guest mode */
+	mfmsr	r3
+	andis.	r0,r3,MSR_GS@h
+	bne	1f
+
+	/* Now set the I-ERAT watermark to 15 */
+	lis	r4,(MMUCR0_TLBSEL_I|MMUCR0_ECL)@h
+	mtspr	SPRN_MMUCR0, r4
+	li	r4,A2_IERAT_SIZE-1
+	PPC_ERATWE(r4,r4,3)
+
+	/* Now set the D-ERAT watermark to 31 */
+	lis	r4,(MMUCR0_TLBSEL_D|MMUCR0_ECL)@h
+	mtspr	SPRN_MMUCR0, r4
+	li	r4,A2_DERAT_SIZE-1
+	PPC_ERATWE(r4,r4,3)
+
+	/* And invalidate the beast just in case. That won't get rid of
+	 * a bolted entry though it will be in LRU and so will go away eventually
+	 * but let's not bother for now
+	 */
+	PPC_ERATILX(0,0,0)
+1:
+	blr
+
+_GLOBAL(__restore_cpu_a2)
+	b	__setup_cpu_a2
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index b65b4908d3c..3d7b65ad496 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -62,10 +62,12 @@ extern void __setup_cpu_745x(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_ppc970MP(unsigned long offset, struct cpu_spec* spec);
 extern void __setup_cpu_pa6t(unsigned long offset, struct cpu_spec* spec);
+extern void __setup_cpu_a2(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_pa6t(void);
 extern void __restore_cpu_ppc970(void);
 extern void __setup_cpu_power7(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_power7(void);
+extern void __restore_cpu_a2(void);
 #endif /* CONFIG_PPC64 */
 #if defined(CONFIG_E500)
 extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
@@ -2011,7 +2013,26 @@ static struct cpu_spec __initdata cpu_specs[] = {
 #endif /* CONFIG_PPC32 */
 #endif /* CONFIG_E500 */
 
-#ifdef CONFIG_PPC_BOOK3E_64
+#ifdef CONFIG_PPC_A2
+	{	/* Standard A2 (>= DD2) + FPU core */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x00480000,
+		.cpu_name		= "A2 (>= DD2)",
+		.cpu_features		= CPU_FTRS_A2,
+		.cpu_user_features	= COMMON_USER_PPC64,
+		.mmu_features		= MMU_FTR_TYPE_3E | MMU_FTR_USE_TLBILX |
+					  MMU_FTR_USE_TLBIVAX_BCAST |
+					  MMU_FTR_LOCK_BCAST_INVAL |
+					  MMU_FTR_USE_TLBRSRV |
+					  MMU_FTR_USE_PAIRED_MAS,
+		.icache_bsize		= 64,
+		.dcache_bsize		= 64,
+		.num_pmcs		= 0,
+		.cpu_setup		= __setup_cpu_a2,
+		.cpu_restore		= __restore_cpu_a2,
+		.machine_check		= machine_check_generic,
+		.platform		= "ppca2",
+	},
 	{	/* This is a default entry to get going, to be replaced by
 		 * a real one at some stage
 		 */
@@ -2032,7 +2053,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check		= machine_check_generic,
 		.platform		= "power6",
 	},
-#endif
+#endif /* CONFIG_PPC_A2 */
 };
 
 static struct cpu_spec the_cpu_spec;
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 111138c55f9..7c1e1c64437 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -107,6 +107,10 @@ config POWER4
 	depends on PPC64 && PPC_BOOK3S
 	def_bool y
 
+config PPC_A2
+	bool
+	depends on PPC_BOOK3E_64
+
 config TUNE_CELL
 	bool "Optimize for Cell Broadband Engine"
 	depends on PPC64 && PPC_BOOK3S
-- 
cgit v1.2.3-70-g09d2


From bd491781097f150687906008d639936a0c00ed90 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 14 Apr 2011 22:32:02 +0000
Subject: powerpc: Add TLB size detection for TYPE_3E MMUs

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/mmu-book3e.h | 15 +++++++++++++++
 arch/powerpc/mm/mmu_context_nohash.c  | 12 +++++++++++-
 2 files changed, 26 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index 17194fcd404..80d68afb020 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -137,6 +137,21 @@
 #define MMUCSR0_TLB2PS	0x00078000	/* TLB2 Page Size */
 #define MMUCSR0_TLB3PS	0x00780000	/* TLB3 Page Size */
 
+/* MMUCFG bits */
+#define MMUCFG_MAVN_NASK	0x00000003
+#define MMUCFG_MAVN_V1_0	0x00000000
+#define MMUCFG_MAVN_V2_0	0x00000001
+#define MMUCFG_NTLB_MASK	0x0000000c
+#define MMUCFG_NTLB_SHIFT	2
+#define MMUCFG_PIDSIZE_MASK	0x000007c0
+#define MMUCFG_PIDSIZE_SHIFT	6
+#define MMUCFG_TWC		0x00008000
+#define MMUCFG_LRAT		0x00010000
+#define MMUCFG_RASIZE_MASK	0x00fe0000
+#define MMUCFG_RASIZE_SHIFT	17
+#define MMUCFG_LPIDSIZE_MASK	0x0f000000
+#define MMUCFG_LPIDSIZE_SHIFT	24
+
 /* TLBnCFG encoding */
 #define TLBnCFG_N_ENTRY		0x00000fff	/* number of entries */
 #define TLBnCFG_HES		0x00002000	/* HW select supported */
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index 4d8fa911c73..336807de550 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -409,7 +409,17 @@ void __init mmu_context_init(void)
 	} else if (mmu_has_feature(MMU_FTR_TYPE_47x)) {
 		first_context = 1;
 		last_context = 65535;
-	} else {
+	} else
+#ifdef CONFIG_PPC_BOOK3E_MMU
+	if (mmu_has_feature(MMU_FTR_TYPE_3E)) {
+		u32 mmucfg = mfspr(SPRN_MMUCFG);
+		u32 pid_bits = (mmucfg & MMUCFG_PIDSIZE_MASK)
+				>> MMUCFG_PIDSIZE_SHIFT;
+		first_context = 1;
+		last_context = (1UL << (pid_bits + 1)) - 1;
+	} else
+#endif
+	{
 		first_context = 1;
 		last_context = 255;
 	}
-- 
cgit v1.2.3-70-g09d2


From f0aae3238fc1c28b543cbaaa0e7c5d57685f5f89 Mon Sep 17 00:00:00 2001
From: Jack Miller <jack@codezen.org>
Date: Thu, 14 Apr 2011 22:32:05 +0000
Subject: powerpc/book3e: Flush IPROT protected TLB entries leftover by
 firmware

When we set up the TLB for ourselves on Book3E, we need to flush out any
old mappings established by the firmware or bootloader.  At present we
attempt this with a tlbilx to flush everything, but this will leave behind
any entries with the IPROT bit set.

There are several good reason firmware might establish mappings with IPROT,
and in fact ePAPR compliant firmwares are required to establish their
initial mapped area with IPROT.

This patch, therefore adds more complex code to scan through the TLB upon
entry and flush away any entries that are not our own.

Signed-off-by: Jack Miller <jack@codezen.org>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/mmu-book3e.h |  1 +
 arch/powerpc/kernel/exceptions-64e.S  | 45 ++++++++++++++++++++++++++++++++++-
 2 files changed, 45 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index 80d68afb020..ec61e7b998c 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -43,6 +43,7 @@
 #define MAS0_TLBSEL(x)		(((x) << 28) & 0x30000000)
 #define MAS0_ESEL(x)		(((x) << 16) & 0x0FFF0000)
 #define MAS0_NV(x)		((x) & 0x00000FFF)
+#define MAS0_ESEL_MASK		0x0FFF0000
 #define MAS0_HES		0x00004000
 #define MAS0_WQ_ALLWAYS		0x00000000
 #define MAS0_WQ_COND		0x00001000
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 8fe0fc233f0..23bd83b20be 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -886,8 +886,51 @@ have_hes:
 	bctr
 
 1:	/* We are now running at PAGE_OFFSET, clean the TLB of everything
-	 * else (XXX we should scan for bolted crap from the firmware too)
+	 * else (including IPROTed things left by firmware)
+	 * r4 = TLBnCFG
+	 * r3 = current address (more or less)
 	 */
+
+	li	r5,0
+	mtspr	SPRN_MAS6,r5
+	tlbsx	0,r3
+
+	rlwinm	r9,r4,0,TLBnCFG_N_ENTRY
+	rlwinm	r10,r4,8,0xff
+	addi	r10,r10,-1	/* Get inner loop mask */
+
+	li	r3,1
+
+	mfspr	r5,SPRN_MAS1
+	rlwinm	r5,r5,0,(~(MAS1_VALID|MAS1_IPROT))
+
+	mfspr	r6,SPRN_MAS2
+	rldicr	r6,r6,0,51		/* Extract EPN */
+
+	mfspr	r7,SPRN_MAS0
+	rlwinm	r7,r7,0,0xffff0fff	/* Clear HES and WQ */
+
+	rlwinm	r8,r7,16,0xfff		/* Extract ESEL */
+
+2:	add	r4,r3,r8
+	and	r4,r4,r10
+
+	rlwimi	r7,r4,16,MAS0_ESEL_MASK
+
+	mtspr	SPRN_MAS0,r7
+	mtspr	SPRN_MAS1,r5
+	mtspr	SPRN_MAS2,r6
+	tlbwe
+
+	addi	r3,r3,1
+	and.	r4,r3,r10
+
+	bne	3f
+	addis	r6,r6,(1<<30)@h
+3:
+	cmpw	r3,r9
+	blt	2b
+
 	PPC_TLBILX(0,0,0)
 	sync
 	isync
-- 
cgit v1.2.3-70-g09d2


From efcac6589a277c10060e4be44b9455cf43838dc1 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@au1.ibm.com>
Date: Wed, 2 Mar 2011 15:18:48 +0000
Subject: powerpc: Per process DSCR + some fixes (try#4)

The DSCR (aka Data Stream Control Register) is supported on some
server PowerPC chips and allow some control over the prefetch
of data streams.

This patch allows the value to be specified per thread by emulating
the corresponding mfspr and mtspr instructions. Children of such
threads inherit the value. Other threads use a default value that
can be specified in sysfs - /sys/devices/system/cpu/dscr_default.

If a thread starts with non default value in the sysfs entry,
all children threads inherit this non default value even if
the sysfs value is changed later.

Signed-off-by: Alexey Kardashevskiy <aik@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/emulated_ops.h |  4 ++++
 arch/powerpc/include/asm/ppc-opcode.h   |  4 ++++
 arch/powerpc/include/asm/processor.h    |  4 ++++
 arch/powerpc/kernel/asm-offsets.c       |  1 +
 arch/powerpc/kernel/entry_64.S          | 15 +++++++++++++
 arch/powerpc/kernel/process.c           | 16 ++++++++++++++
 arch/powerpc/kernel/sysfs.c             | 38 +++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/traps.c             | 24 +++++++++++++++++++++
 8 files changed, 106 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h
index f0fb4fc1f6e..45921672b97 100644
--- a/arch/powerpc/include/asm/emulated_ops.h
+++ b/arch/powerpc/include/asm/emulated_ops.h
@@ -52,6 +52,10 @@ extern struct ppc_emulated {
 #ifdef CONFIG_VSX
 	struct ppc_emulated_entry vsx;
 #endif
+#ifdef CONFIG_PPC64
+	struct ppc_emulated_entry mfdscr;
+	struct ppc_emulated_entry mtdscr;
+#endif
 } ppc_emulated;
 
 extern u32 ppc_warn_emulated;
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 3e25b258568..e472659d906 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -41,6 +41,10 @@
 #define PPC_INST_RFCI			0x4c000066
 #define PPC_INST_RFDI			0x4c00004e
 #define PPC_INST_RFMCI			0x4c00004c
+#define PPC_INST_MFSPR_DSCR		0x7c1102a6
+#define PPC_INST_MFSPR_DSCR_MASK	0xfc1fffff
+#define PPC_INST_MTSPR_DSCR		0x7c1103a6
+#define PPC_INST_MTSPR_DSCR_MASK	0xfc1fffff
 
 #define PPC_INST_STRING			0x7c00042a
 #define PPC_INST_STRING_MASK		0xfc0007fe
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index de1967a1ff5..d50c2b6d9bc 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -238,6 +238,10 @@ struct thread_struct {
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	void*		kvm_shadow_vcpu; /* KVM internal data */
 #endif /* CONFIG_KVM_BOOK3S_32_HANDLER */
+#ifdef CONFIG_PPC64
+	unsigned long	dscr;
+	int		dscr_inherit;
+#endif
 };
 
 #define ARCH_MIN_TASKALIGN 16
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 23e6a93145a..6887661ac07 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -74,6 +74,7 @@ int main(void)
 	DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context));
 	DEFINE(SIGSEGV, SIGSEGV);
 	DEFINE(NMI_MASK, NMI_MASK);
+	DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr));
 #else
 	DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index dbf5bfafd7b..64693706ebf 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -421,6 +421,12 @@ BEGIN_FTR_SECTION
 	std	r24,THREAD_VRSAVE(r3)
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_PPC64
+BEGIN_FTR_SECTION
+	mfspr	r25,SPRN_DSCR
+	std	r25,THREAD_DSCR(r3)
+END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
+#endif
 	and.	r0,r0,r22
 	beq+	1f
 	andc	r22,r22,r0
@@ -522,6 +528,15 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_VRSAVE,r0		/* if G4, restore VRSAVE reg */
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_PPC64
+BEGIN_FTR_SECTION
+	ld	r0,THREAD_DSCR(r4)
+	cmpd	r0,r25
+	beq	1f
+	mtspr	SPRN_DSCR,r0
+1:	
+END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
+#endif
 
 	/* r3-r13 are destroyed -- Cort */
 	REST_8GPRS(14, r1)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index f74f355a961..a01c2d93fd2 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -702,6 +702,8 @@ void prepare_to_copy(struct task_struct *tsk)
 /*
  * Copy a thread..
  */
+extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */
+
 int copy_thread(unsigned long clone_flags, unsigned long usp,
 		unsigned long unused, struct task_struct *p,
 		struct pt_regs *regs)
@@ -769,6 +771,20 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 		p->thread.ksp_vsid = sp_vsid;
 	}
 #endif /* CONFIG_PPC_STD_MMU_64 */
+#ifdef CONFIG_PPC64 
+	if (cpu_has_feature(CPU_FTR_DSCR)) {
+		if (current->thread.dscr_inherit) {
+			p->thread.dscr_inherit = 1;
+			p->thread.dscr = current->thread.dscr;
+		} else if (0 != dscr_default) {
+			p->thread.dscr_inherit = 1;
+			p->thread.dscr = dscr_default;
+		} else {
+			p->thread.dscr_inherit = 0;
+			p->thread.dscr = 0;
+		}
+	}
+#endif
 
 	/*
 	 * The PPC64 ABI makes use of a TOC to contain function 
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index c0d8c2006bf..f0f2199e64e 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -182,6 +182,41 @@ static SYSDEV_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
 static SYSDEV_ATTR(spurr, 0600, show_spurr, NULL);
 static SYSDEV_ATTR(dscr, 0600, show_dscr, store_dscr);
 static SYSDEV_ATTR(purr, 0600, show_purr, store_purr);
+
+unsigned long dscr_default = 0;
+EXPORT_SYMBOL(dscr_default);
+
+static ssize_t show_dscr_default(struct sysdev_class *class,
+		struct sysdev_class_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%lx\n", dscr_default);
+}
+
+static ssize_t __used store_dscr_default(struct sysdev_class *class,
+		struct sysdev_class_attribute *attr, const char *buf,
+		size_t count)
+{
+	unsigned long val;
+	int ret = 0;
+	
+	ret = sscanf(buf, "%lx", &val);
+	if (ret != 1)
+		return -EINVAL;
+	dscr_default = val;
+
+	return count;
+}
+
+static SYSDEV_CLASS_ATTR(dscr_default, 0600,
+		show_dscr_default, store_dscr_default);
+
+static void sysfs_create_dscr_default(void)
+{
+	int err = 0;
+	if (cpu_has_feature(CPU_FTR_DSCR))
+		err = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
+			&attr_dscr_default.attr);
+}
 #endif /* CONFIG_PPC64 */
 
 #ifdef HAS_PPC_PMC_PA6T
@@ -617,6 +652,9 @@ static int __init topology_init(void)
 		if (cpu_online(cpu))
 			register_cpu_online(cpu);
 	}
+#ifdef CONFIG_PPC64
+	sysfs_create_dscr_default();
+#endif /* CONFIG_PPC64 */
 
 	return 0;
 }
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 5ddb801bc15..cb71cf29ede 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -909,6 +909,26 @@ static int emulate_instruction(struct pt_regs *regs)
 		return emulate_isel(regs, instword);
 	}
 
+#ifdef CONFIG_PPC64
+	/* Emulate the mfspr rD, DSCR. */
+	if (((instword & PPC_INST_MFSPR_DSCR_MASK) == PPC_INST_MFSPR_DSCR) &&
+			cpu_has_feature(CPU_FTR_DSCR)) {
+		PPC_WARN_EMULATED(mfdscr, regs);
+		rd = (instword >> 21) & 0x1f;
+		regs->gpr[rd] = mfspr(SPRN_DSCR);
+		return 0;
+	}
+	/* Emulate the mtspr DSCR, rD. */
+	if (((instword & PPC_INST_MTSPR_DSCR_MASK) == PPC_INST_MTSPR_DSCR) &&
+			cpu_has_feature(CPU_FTR_DSCR)) {
+		PPC_WARN_EMULATED(mtdscr, regs);
+		rd = (instword >> 21) & 0x1f;
+		mtspr(SPRN_DSCR, regs->gpr[rd]);
+		current->thread.dscr_inherit = 1;
+		return 0;
+	}
+#endif
+
 	return -EINVAL;
 }
 
@@ -1506,6 +1526,10 @@ struct ppc_emulated ppc_emulated = {
 #ifdef CONFIG_VSX
 	WARN_EMULATED_SETUP(vsx),
 #endif
+#ifdef CONFIG_PPC64
+	WARN_EMULATED_SETUP(mfdscr),
+	WARN_EMULATED_SETUP(mtdscr),
+#endif
 };
 
 u32 ppc_warn_emulated;
-- 
cgit v1.2.3-70-g09d2


From 21176fed25c3b0cb17c6c42d71b4e3d68b8f9dd4 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ozlabs.org>
Date: Mon, 11 Apr 2011 21:25:01 +0000
Subject: powerpc/pci: Split IO vs MMIO indirect access hooks

The goal is to avoid adding overhead to MMIO when only PIO is needed

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/io.h          | 16 +++++++++++-----
 arch/powerpc/platforms/Kconfig         | 10 ++++++++--
 arch/powerpc/platforms/cell/Kconfig    |  3 ++-
 arch/powerpc/platforms/iseries/Kconfig |  3 ++-
 4 files changed, 23 insertions(+), 9 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 001f2f11c19..2f365f5007a 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -481,10 +481,16 @@ __do_out_asm(_rec_outl, "stwbrx")
 				_memcpy_fromio(dst,PCI_FIX_ADDR(src),n)
 #endif /* !CONFIG_EEH */
 
-#ifdef CONFIG_PPC_INDIRECT_IO
-#define DEF_PCI_HOOK(x)		x
+#ifdef CONFIG_PPC_INDIRECT_PIO
+#define DEF_PCI_HOOK_pio(x)	x
+#else
+#define DEF_PCI_HOOK_pio(x)	NULL
+#endif
+
+#ifdef CONFIG_PPC_INDIRECT_MMIO
+#define DEF_PCI_HOOK_mem(x)	x
 #else
-#define DEF_PCI_HOOK(x)		NULL
+#define DEF_PCI_HOOK_mem(x)	NULL
 #endif
 
 /* Structure containing all the hooks */
@@ -504,7 +510,7 @@ extern struct ppc_pci_io {
 #define DEF_PCI_AC_RET(name, ret, at, al, space, aa)		\
 static inline ret name at					\
 {								\
-	if (DEF_PCI_HOOK(ppc_pci_io.name) != NULL)		\
+	if (DEF_PCI_HOOK_##space(ppc_pci_io.name) != NULL)	\
 		return ppc_pci_io.name al;			\
 	return __do_##name al;					\
 }
@@ -512,7 +518,7 @@ static inline ret name at					\
 #define DEF_PCI_AC_NORET(name, at, al, space, aa)		\
 static inline void name at					\
 {								\
-	if (DEF_PCI_HOOK(ppc_pci_io.name) != NULL)		\
+	if (DEF_PCI_HOOK_##space(ppc_pci_io.name) != NULL)		\
 		ppc_pci_io.name al;				\
 	else							\
 		__do_##name al;					\
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 658ffc50493..54db9fbab1d 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -154,11 +154,17 @@ config PPC_P7_NAP
 config PPC_INDIRECT_IO
 	bool
 	select GENERIC_IOMAP
-	default n
+
+config PPC_INDIRECT_PIO
+	bool
+	select PPC_INDIRECT_IO
+
+config PPC_INDIRECT_MMIO
+	bool
+	select PPC_INDIRECT_IO
 
 config GENERIC_IOMAP
 	bool
-	default n
 
 source "drivers/cpufreq/Kconfig"
 
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 81239ebed83..3c7f1de06cd 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -6,7 +6,8 @@ config PPC_CELL_COMMON
 	bool
 	select PPC_CELL
 	select PPC_DCR_MMIO
-	select PPC_INDIRECT_IO
+	select PPC_INDIRECT_PIO
+	select PPC_INDIRECT_MMIO
 	select PPC_NATIVE
 	select PPC_RTAS
 	select IRQ_EDGE_EOI_HANDLER
diff --git a/arch/powerpc/platforms/iseries/Kconfig b/arch/powerpc/platforms/iseries/Kconfig
index e5bc9f75d47..ea1d3622b41 100644
--- a/arch/powerpc/platforms/iseries/Kconfig
+++ b/arch/powerpc/platforms/iseries/Kconfig
@@ -1,7 +1,8 @@
 config PPC_ISERIES
 	bool "IBM Legacy iSeries"
 	depends on PPC64 && PPC_BOOK3S
-	select PPC_INDIRECT_IO
+	select PPC_INDIRECT_PIO
+	select PPC_INDIRECT_MMIO
 	select PPC_PCI_CHOICE if EXPERT
 
 menu "iSeries device drivers"
-- 
cgit v1.2.3-70-g09d2


From 3cc30d0726d258ac336283bcde66a8ab58283b61 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ozlabs.org>
Date: Mon, 11 Apr 2011 21:25:01 +0000
Subject: powerpc/pci: Move IO workarounds to the common kernel dir

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/io-workarounds.h    |  49 +++++++
 arch/powerpc/kernel/Makefile                 |   2 +
 arch/powerpc/kernel/io-workarounds.c         | 184 ++++++++++++++++++++++++++
 arch/powerpc/platforms/Kconfig               |   3 +
 arch/powerpc/platforms/cell/Kconfig          |   1 +
 arch/powerpc/platforms/cell/Makefile         |   8 +-
 arch/powerpc/platforms/cell/celleb_pci.c     |   1 -
 arch/powerpc/platforms/cell/celleb_pci.h     |   3 +-
 arch/powerpc/platforms/cell/io-workarounds.c | 185 ---------------------------
 arch/powerpc/platforms/cell/io-workarounds.h |  49 -------
 arch/powerpc/platforms/cell/qpace_setup.c    |   1 -
 arch/powerpc/platforms/cell/setup.c          |   2 +-
 arch/powerpc/platforms/cell/spider-pci.c     |   3 +-
 13 files changed, 247 insertions(+), 244 deletions(-)
 create mode 100644 arch/powerpc/include/asm/io-workarounds.h
 create mode 100644 arch/powerpc/kernel/io-workarounds.c
 delete mode 100644 arch/powerpc/platforms/cell/io-workarounds.c
 delete mode 100644 arch/powerpc/platforms/cell/io-workarounds.h

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/io-workarounds.h b/arch/powerpc/include/asm/io-workarounds.h
new file mode 100644
index 00000000000..6efc7782ebf
--- /dev/null
+++ b/arch/powerpc/include/asm/io-workarounds.h
@@ -0,0 +1,49 @@
+/*
+ * Support PCI IO workaround
+ *
+ * (C) Copyright 2007-2008 TOSHIBA CORPORATION
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#ifndef _IO_WORKAROUNDS_H
+#define _IO_WORKAROUNDS_H
+
+#include <linux/io.h>
+#include <asm/pci-bridge.h>
+
+/* Bus info */
+struct iowa_bus {
+	struct pci_controller *phb;
+	struct ppc_pci_io *ops;
+	void   *private;
+};
+
+void __devinit io_workaround_init(void);
+void __devinit iowa_register_bus(struct pci_controller *, struct ppc_pci_io *,
+				 int (*)(struct iowa_bus *, void *), void *);
+struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR);
+struct iowa_bus *iowa_pio_find_bus(unsigned long);
+
+extern struct ppc_pci_io spiderpci_ops;
+extern int spiderpci_iowa_init(struct iowa_bus *, void *);
+
+#define SPIDER_PCI_REG_BASE		0xd000
+#define SPIDER_PCI_REG_SIZE		0x1000
+#define SPIDER_PCI_VCI_CNTL_STAT	0x0110
+#define SPIDER_PCI_DUMMY_READ		0x0810
+#define SPIDER_PCI_DUMMY_READ_BASE	0x0814
+
+#endif /* _IO_WORKAROUNDS_H */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 058bc8bac48..82e0bed0650 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -106,6 +106,8 @@ obj-$(CONFIG_KEXEC)		+= machine_kexec.o crash.o \
 obj-$(CONFIG_AUDIT)		+= audit.o
 obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
+obj-$(CONFIG_PPC_IO_WORKAROUNDS)	+= io-workarounds.o
+
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_callchain.o
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
new file mode 100644
index 00000000000..7e584579878
--- /dev/null
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -0,0 +1,184 @@
+/*
+ * Support PCI IO workaround
+ *
+ *  Copyright (C) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org>
+ *		       IBM, Corp.
+ *  (C) Copyright 2007-2008 TOSHIBA CORPORATION
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#undef DEBUG
+
+#include <linux/kernel.h>
+
+#include <asm/io.h>
+#include <asm/machdep.h>
+#include <asm/pgtable.h>
+#include <asm/ppc-pci.h>
+#include <asm/io-workarounds.h>
+
+#define IOWA_MAX_BUS	8
+
+static struct iowa_bus iowa_busses[IOWA_MAX_BUS];
+static unsigned int iowa_bus_count;
+
+static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr)
+{
+	int i, j;
+	struct resource *res;
+	unsigned long vstart, vend;
+
+	for (i = 0; i < iowa_bus_count; i++) {
+		struct iowa_bus *bus = &iowa_busses[i];
+		struct pci_controller *phb = bus->phb;
+
+		if (vaddr) {
+			vstart = (unsigned long)phb->io_base_virt;
+			vend = vstart + phb->pci_io_size - 1;
+			if ((vaddr >= vstart) && (vaddr <= vend))
+				return bus;
+		}
+
+		if (paddr)
+			for (j = 0; j < 3; j++) {
+				res = &phb->mem_resources[j];
+				if (paddr >= res->start && paddr <= res->end)
+					return bus;
+			}
+	}
+
+	return NULL;
+}
+
+struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
+{
+	struct iowa_bus *bus;
+	int token;
+
+	token = PCI_GET_ADDR_TOKEN(addr);
+
+	if (token && token <= iowa_bus_count)
+		bus = &iowa_busses[token - 1];
+	else {
+		unsigned long vaddr, paddr;
+		pte_t *ptep;
+
+		vaddr = (unsigned long)PCI_FIX_ADDR(addr);
+		if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
+			return NULL;
+
+		ptep = find_linux_pte(init_mm.pgd, vaddr);
+		if (ptep == NULL)
+			paddr = 0;
+		else
+			paddr = pte_pfn(*ptep) << PAGE_SHIFT;
+		bus = iowa_pci_find(vaddr, paddr);
+
+		if (bus == NULL)
+			return NULL;
+	}
+
+	return bus;
+}
+
+struct iowa_bus *iowa_pio_find_bus(unsigned long port)
+{
+	unsigned long vaddr = (unsigned long)pci_io_base + port;
+	return iowa_pci_find(vaddr, 0);
+}
+
+
+#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)		\
+static ret iowa_##name at					\
+{								\
+	struct iowa_bus *bus;					\
+	bus = iowa_##space##_find_bus(aa);			\
+	if (bus && bus->ops && bus->ops->name)			\
+		return bus->ops->name al;			\
+	return __do_##name al;					\
+}
+
+#define DEF_PCI_AC_NORET(name, at, al, space, aa)		\
+static void iowa_##name at					\
+{								\
+	struct iowa_bus *bus;					\
+	bus = iowa_##space##_find_bus(aa);			\
+	if (bus && bus->ops && bus->ops->name) {		\
+		bus->ops->name al;				\
+		return;						\
+	}							\
+	__do_##name al;						\
+}
+
+#include <asm/io-defs.h>
+
+#undef DEF_PCI_AC_RET
+#undef DEF_PCI_AC_NORET
+
+static const struct ppc_pci_io __devinitconst iowa_pci_io = {
+
+#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)	.name = iowa_##name,
+#define DEF_PCI_AC_NORET(name, at, al, space, aa)	.name = iowa_##name,
+
+#include <asm/io-defs.h>
+
+#undef DEF_PCI_AC_RET
+#undef DEF_PCI_AC_NORET
+
+};
+
+static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
+				  unsigned long flags, void *caller)
+{
+	struct iowa_bus *bus;
+	void __iomem *res = __ioremap_caller(addr, size, flags, caller);
+	int busno;
+
+	bus = iowa_pci_find(0, (unsigned long)addr);
+	if (bus != NULL) {
+		busno = bus - iowa_busses;
+		PCI_SET_ADDR_TOKEN(res, busno + 1);
+	}
+	return res;
+}
+
+/* Regist new bus to support workaround */
+void __devinit iowa_register_bus(struct pci_controller *phb,
+			struct ppc_pci_io *ops,
+			int (*initfunc)(struct iowa_bus *, void *), void *data)
+{
+	struct iowa_bus *bus;
+	struct device_node *np = phb->dn;
+
+	if (iowa_bus_count >= IOWA_MAX_BUS) {
+		pr_err("IOWA:Too many pci bridges, "
+		       "workarounds disabled for %s\n", np->full_name);
+		return;
+	}
+
+	bus = &iowa_busses[iowa_bus_count];
+	bus->phb = phb;
+	bus->ops = ops;
+
+	if (initfunc)
+		if ((*initfunc)(bus, data))
+			return;
+
+	iowa_bus_count++;
+
+	pr_debug("IOWA:[%d]Add bus, %s.\n", iowa_bus_count-1, np->full_name);
+}
+
+/* enable IO workaround */
+void __devinit io_workaround_init(void)
+{
+	static int io_workaround_inited;
+
+	if (io_workaround_inited)
+		return;
+	ppc_pci_io = iowa_pci_io;
+	ppc_md.ioremap = iowa_ioremap;
+	io_workaround_inited = 1;
+}
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 54db9fbab1d..f2352fc5cbb 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -163,6 +163,9 @@ config PPC_INDIRECT_MMIO
 	bool
 	select PPC_INDIRECT_IO
 
+config PPC_IO_WORKAROUNDS
+	bool
+
 config GENERIC_IOMAP
 	bool
 
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 3c7f1de06cd..67d5009b4e8 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -16,6 +16,7 @@ config PPC_CELL_NATIVE
 	bool
 	select PPC_CELL_COMMON
 	select MPIC
+	select PPC_IO_WORKAROUNDS
 	select IBM_NEW_EMAC_EMAC4
 	select IBM_NEW_EMAC_RGMII
 	select IBM_NEW_EMAC_ZMII #test only
diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile
index 83fafe92264..8839ef6c718 100644
--- a/arch/powerpc/platforms/cell/Makefile
+++ b/arch/powerpc/platforms/cell/Makefile
@@ -1,7 +1,7 @@
 obj-$(CONFIG_PPC_CELL_COMMON)		+= cbe_regs.o interrupt.o pervasive.o
 
 obj-$(CONFIG_PPC_CELL_NATIVE)		+= iommu.o setup.o spider-pic.o \
-					   pmu.o io-workarounds.o spider-pci.o
+					   pmu.o spider-pci.o
 obj-$(CONFIG_CBE_RAS)			+= ras.o
 
 obj-$(CONFIG_CBE_THERM)			+= cbe_thermal.o
@@ -39,9 +39,9 @@ obj-y					+= celleb_setup.o \
 					   celleb_pci.o celleb_scc_epci.o \
 					   celleb_scc_pciex.o \
 					   celleb_scc_uhc.o \
-					   io-workarounds.o spider-pci.o \
-					   beat.o beat_htab.o beat_hvCall.o \
-					   beat_interrupt.o beat_iommu.o
+					   spider-pci.o beat.o beat_htab.o \
+					   beat_hvCall.o beat_interrupt.o \
+					   beat_iommu.o
 
 obj-$(CONFIG_SMP)			+= beat_smp.o
 obj-$(CONFIG_PPC_UDBG_BEAT)		+= beat_udbg.o
diff --git a/arch/powerpc/platforms/cell/celleb_pci.c b/arch/powerpc/platforms/cell/celleb_pci.c
index 404d1fc04d5..c19b783a7c9 100644
--- a/arch/powerpc/platforms/cell/celleb_pci.c
+++ b/arch/powerpc/platforms/cell/celleb_pci.c
@@ -41,7 +41,6 @@
 #include <asm/pci-bridge.h>
 #include <asm/ppc-pci.h>
 
-#include "io-workarounds.h"
 #include "celleb_pci.h"
 
 #define MAX_PCI_DEVICES    32
diff --git a/arch/powerpc/platforms/cell/celleb_pci.h b/arch/powerpc/platforms/cell/celleb_pci.h
index 4cba1523ec5..a801fcc5f38 100644
--- a/arch/powerpc/platforms/cell/celleb_pci.h
+++ b/arch/powerpc/platforms/cell/celleb_pci.h
@@ -26,8 +26,9 @@
 #include <asm/pci-bridge.h>
 #include <asm/prom.h>
 #include <asm/ppc-pci.h>
+#include <asm/io-workarounds.h>
 
-#include "io-workarounds.h"
+struct iowa_bus;
 
 struct celleb_phb_spec {
 	int (*setup)(struct device_node *, struct pci_controller *);
diff --git a/arch/powerpc/platforms/cell/io-workarounds.c b/arch/powerpc/platforms/cell/io-workarounds.c
deleted file mode 100644
index 5c1118e3194..00000000000
--- a/arch/powerpc/platforms/cell/io-workarounds.c
+++ /dev/null
@@ -1,185 +0,0 @@
-/*
- * Support PCI IO workaround
- *
- *  Copyright (C) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org>
- *		       IBM, Corp.
- *  (C) Copyright 2007-2008 TOSHIBA CORPORATION
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#undef DEBUG
-
-#include <linux/kernel.h>
-
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/pgtable.h>
-#include <asm/ppc-pci.h>
-
-#include "io-workarounds.h"
-
-#define IOWA_MAX_BUS	8
-
-static struct iowa_bus iowa_busses[IOWA_MAX_BUS];
-static unsigned int iowa_bus_count;
-
-static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr)
-{
-	int i, j;
-	struct resource *res;
-	unsigned long vstart, vend;
-
-	for (i = 0; i < iowa_bus_count; i++) {
-		struct iowa_bus *bus = &iowa_busses[i];
-		struct pci_controller *phb = bus->phb;
-
-		if (vaddr) {
-			vstart = (unsigned long)phb->io_base_virt;
-			vend = vstart + phb->pci_io_size - 1;
-			if ((vaddr >= vstart) && (vaddr <= vend))
-				return bus;
-		}
-
-		if (paddr)
-			for (j = 0; j < 3; j++) {
-				res = &phb->mem_resources[j];
-				if (paddr >= res->start && paddr <= res->end)
-					return bus;
-			}
-	}
-
-	return NULL;
-}
-
-struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
-{
-	struct iowa_bus *bus;
-	int token;
-
-	token = PCI_GET_ADDR_TOKEN(addr);
-
-	if (token && token <= iowa_bus_count)
-		bus = &iowa_busses[token - 1];
-	else {
-		unsigned long vaddr, paddr;
-		pte_t *ptep;
-
-		vaddr = (unsigned long)PCI_FIX_ADDR(addr);
-		if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
-			return NULL;
-
-		ptep = find_linux_pte(init_mm.pgd, vaddr);
-		if (ptep == NULL)
-			paddr = 0;
-		else
-			paddr = pte_pfn(*ptep) << PAGE_SHIFT;
-		bus = iowa_pci_find(vaddr, paddr);
-
-		if (bus == NULL)
-			return NULL;
-	}
-
-	return bus;
-}
-
-struct iowa_bus *iowa_pio_find_bus(unsigned long port)
-{
-	unsigned long vaddr = (unsigned long)pci_io_base + port;
-	return iowa_pci_find(vaddr, 0);
-}
-
-
-#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)		\
-static ret iowa_##name at					\
-{								\
-	struct iowa_bus *bus;					\
-	bus = iowa_##space##_find_bus(aa);			\
-	if (bus && bus->ops && bus->ops->name)			\
-		return bus->ops->name al;			\
-	return __do_##name al;					\
-}
-
-#define DEF_PCI_AC_NORET(name, at, al, space, aa)		\
-static void iowa_##name at					\
-{								\
-	struct iowa_bus *bus;					\
-	bus = iowa_##space##_find_bus(aa);			\
-	if (bus && bus->ops && bus->ops->name) {		\
-		bus->ops->name al;				\
-		return;						\
-	}							\
-	__do_##name al;						\
-}
-
-#include <asm/io-defs.h>
-
-#undef DEF_PCI_AC_RET
-#undef DEF_PCI_AC_NORET
-
-static const struct ppc_pci_io __devinitconst iowa_pci_io = {
-
-#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)	.name = iowa_##name,
-#define DEF_PCI_AC_NORET(name, at, al, space, aa)	.name = iowa_##name,
-
-#include <asm/io-defs.h>
-
-#undef DEF_PCI_AC_RET
-#undef DEF_PCI_AC_NORET
-
-};
-
-static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
-				  unsigned long flags, void *caller)
-{
-	struct iowa_bus *bus;
-	void __iomem *res = __ioremap_caller(addr, size, flags, caller);
-	int busno;
-
-	bus = iowa_pci_find(0, (unsigned long)addr);
-	if (bus != NULL) {
-		busno = bus - iowa_busses;
-		PCI_SET_ADDR_TOKEN(res, busno + 1);
-	}
-	return res;
-}
-
-/* Regist new bus to support workaround */
-void __devinit iowa_register_bus(struct pci_controller *phb,
-			struct ppc_pci_io *ops,
-			int (*initfunc)(struct iowa_bus *, void *), void *data)
-{
-	struct iowa_bus *bus;
-	struct device_node *np = phb->dn;
-
-	if (iowa_bus_count >= IOWA_MAX_BUS) {
-		pr_err("IOWA:Too many pci bridges, "
-		       "workarounds disabled for %s\n", np->full_name);
-		return;
-	}
-
-	bus = &iowa_busses[iowa_bus_count];
-	bus->phb = phb;
-	bus->ops = ops;
-
-	if (initfunc)
-		if ((*initfunc)(bus, data))
-			return;
-
-	iowa_bus_count++;
-
-	pr_debug("IOWA:[%d]Add bus, %s.\n", iowa_bus_count-1, np->full_name);
-}
-
-/* enable IO workaround */
-void __devinit io_workaround_init(void)
-{
-	static int io_workaround_inited;
-
-	if (io_workaround_inited)
-		return;
-	ppc_pci_io = iowa_pci_io;
-	ppc_md.ioremap = iowa_ioremap;
-	io_workaround_inited = 1;
-}
diff --git a/arch/powerpc/platforms/cell/io-workarounds.h b/arch/powerpc/platforms/cell/io-workarounds.h
deleted file mode 100644
index 6efc7782ebf..00000000000
--- a/arch/powerpc/platforms/cell/io-workarounds.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- * Support PCI IO workaround
- *
- * (C) Copyright 2007-2008 TOSHIBA CORPORATION
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- */
-
-#ifndef _IO_WORKAROUNDS_H
-#define _IO_WORKAROUNDS_H
-
-#include <linux/io.h>
-#include <asm/pci-bridge.h>
-
-/* Bus info */
-struct iowa_bus {
-	struct pci_controller *phb;
-	struct ppc_pci_io *ops;
-	void   *private;
-};
-
-void __devinit io_workaround_init(void);
-void __devinit iowa_register_bus(struct pci_controller *, struct ppc_pci_io *,
-				 int (*)(struct iowa_bus *, void *), void *);
-struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR);
-struct iowa_bus *iowa_pio_find_bus(unsigned long);
-
-extern struct ppc_pci_io spiderpci_ops;
-extern int spiderpci_iowa_init(struct iowa_bus *, void *);
-
-#define SPIDER_PCI_REG_BASE		0xd000
-#define SPIDER_PCI_REG_SIZE		0x1000
-#define SPIDER_PCI_VCI_CNTL_STAT	0x0110
-#define SPIDER_PCI_DUMMY_READ		0x0810
-#define SPIDER_PCI_DUMMY_READ_BASE	0x0814
-
-#endif /* _IO_WORKAROUNDS_H */
diff --git a/arch/powerpc/platforms/cell/qpace_setup.c b/arch/powerpc/platforms/cell/qpace_setup.c
index d31c594cfdf..51e290126bc 100644
--- a/arch/powerpc/platforms/cell/qpace_setup.c
+++ b/arch/powerpc/platforms/cell/qpace_setup.c
@@ -42,7 +42,6 @@
 #include "interrupt.h"
 #include "pervasive.h"
 #include "ras.h"
-#include "io-workarounds.h"
 
 static void qpace_show_cpuinfo(struct seq_file *m)
 {
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index fd57bfe00ed..af7b13cd711 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -51,11 +51,11 @@
 #include <asm/udbg.h>
 #include <asm/mpic.h>
 #include <asm/cell-regs.h>
+#include <asm/io-workarounds.h>
 
 #include "interrupt.h"
 #include "pervasive.h"
 #include "ras.h"
-#include "io-workarounds.h"
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
diff --git a/arch/powerpc/platforms/cell/spider-pci.c b/arch/powerpc/platforms/cell/spider-pci.c
index ca7731c0b59..f1f7878893f 100644
--- a/arch/powerpc/platforms/cell/spider-pci.c
+++ b/arch/powerpc/platforms/cell/spider-pci.c
@@ -27,8 +27,7 @@
 
 #include <asm/ppc-pci.h>
 #include <asm/pci-bridge.h>
-
-#include "io-workarounds.h"
+#include <asm/io-workarounds.h>
 
 #define SPIDER_PCI_DISABLE_PREFETCH
 
-- 
cgit v1.2.3-70-g09d2


From d1109b7529f362c06c47140ae09dbd2b853ffddc Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ozlabs.org>
Date: Mon, 11 Apr 2011 21:25:02 +0000
Subject: powerpc/pci: Make IO workarounds init implicit when first bus is
 registered

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/io-workarounds.h |  1 -
 arch/powerpc/kernel/io-workarounds.c      | 27 +++++++++++++++------------
 arch/powerpc/platforms/cell/celleb_pci.c  | 18 +++++-------------
 arch/powerpc/platforms/cell/setup.c       |  2 --
 4 files changed, 20 insertions(+), 28 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/io-workarounds.h b/arch/powerpc/include/asm/io-workarounds.h
index 6efc7782ebf..fbae4928692 100644
--- a/arch/powerpc/include/asm/io-workarounds.h
+++ b/arch/powerpc/include/asm/io-workarounds.h
@@ -31,7 +31,6 @@ struct iowa_bus {
 	void   *private;
 };
 
-void __devinit io_workaround_init(void);
 void __devinit iowa_register_bus(struct pci_controller *, struct ppc_pci_io *,
 				 int (*)(struct iowa_bus *, void *), void *);
 struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR);
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
index 7e584579878..d36515eaa31 100644
--- a/arch/powerpc/kernel/io-workarounds.c
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -144,7 +144,19 @@ static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
 	return res;
 }
 
-/* Regist new bus to support workaround */
+/* Enable IO workaround */
+static void __devinit io_workaround_init(void)
+{
+	static int io_workaround_inited;
+
+	if (io_workaround_inited)
+		return;
+	ppc_pci_io = iowa_pci_io;
+	ppc_md.ioremap = iowa_ioremap;
+	io_workaround_inited = 1;
+}
+
+/* Register new bus to support workaround */
 void __devinit iowa_register_bus(struct pci_controller *phb,
 			struct ppc_pci_io *ops,
 			int (*initfunc)(struct iowa_bus *, void *), void *data)
@@ -152,6 +164,8 @@ void __devinit iowa_register_bus(struct pci_controller *phb,
 	struct iowa_bus *bus;
 	struct device_node *np = phb->dn;
 
+	io_workaround_init();
+
 	if (iowa_bus_count >= IOWA_MAX_BUS) {
 		pr_err("IOWA:Too many pci bridges, "
 		       "workarounds disabled for %s\n", np->full_name);
@@ -171,14 +185,3 @@ void __devinit iowa_register_bus(struct pci_controller *phb,
 	pr_debug("IOWA:[%d]Add bus, %s.\n", iowa_bus_count-1, np->full_name);
 }
 
-/* enable IO workaround */
-void __devinit io_workaround_init(void)
-{
-	static int io_workaround_inited;
-
-	if (io_workaround_inited)
-		return;
-	ppc_pci_io = iowa_pci_io;
-	ppc_md.ioremap = iowa_ioremap;
-	io_workaround_inited = 1;
-}
diff --git a/arch/powerpc/platforms/cell/celleb_pci.c b/arch/powerpc/platforms/cell/celleb_pci.c
index c19b783a7c9..2904b0a6b2c 100644
--- a/arch/powerpc/platforms/cell/celleb_pci.c
+++ b/arch/powerpc/platforms/cell/celleb_pci.c
@@ -468,18 +468,6 @@ static struct of_device_id celleb_phb_match[] __initdata = {
 	},
 };
 
-static int __init celleb_io_workaround_init(struct pci_controller *phb,
-					    struct celleb_phb_spec *phb_spec)
-{
-	if (phb_spec->ops) {
-		iowa_register_bus(phb, phb_spec->ops, phb_spec->iowa_init,
-				  phb_spec->iowa_data);
-		io_workaround_init();
-	}
-
-	return 0;
-}
-
 int __init celleb_setup_phb(struct pci_controller *phb)
 {
 	struct device_node *dev = phb->dn;
@@ -499,7 +487,11 @@ int __init celleb_setup_phb(struct pci_controller *phb)
 	if (rc)
 		return 1;
 
-	return celleb_io_workaround_init(phb, phb_spec);
+	if (phb_spec->ops)
+		iowa_register_bus(phb, phb_spec->ops,
+				  phb_spec->iowa_init,
+				  phb_spec->iowa_data);
+	return 0;
 }
 
 int celleb_pci_probe_mode(struct pci_bus *bus)
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index af7b13cd711..c73cf4c43fc 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -136,8 +136,6 @@ static int __devinit cell_setup_phb(struct pci_controller *phb)
 
 	iowa_register_bus(phb, &spiderpci_ops, &spiderpci_iowa_init,
 				  (void *)SPIDER_PCI_REG_BASE);
-	io_workaround_init();
-
 	return 0;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 9d4a2925c290a053bb279e75e7a649069fdcaf6b Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ellerman.id.au>
Date: Thu, 7 Apr 2011 21:56:02 +0000
Subject: powerpc: Add MSR_64BIT

The MSR bit which indicates 64-bit-ness is different between server and
booke, so add a #define which gives you the right mask regardless.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/reg.h       | 10 ++++++++--
 arch/powerpc/include/asm/reg_booke.h |  6 ++++--
 2 files changed, 12 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 76d7d5fea5b..1f9ac12742e 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -99,17 +99,23 @@
 #define MSR_LE		__MASK(MSR_LE_LG)	/* Little Endian */
 
 #if defined(CONFIG_PPC_BOOK3S_64)
+#define MSR_64BIT	MSR_SF
+
 /* Server variant */
 #define MSR_		MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV
-#define MSR_KERNEL      MSR_ | MSR_SF
+#define MSR_KERNEL	MSR_ | MSR_64BIT
 #define MSR_USER32	MSR_ | MSR_PR | MSR_EE
-#define MSR_USER64	MSR_USER32 | MSR_SF
+#define MSR_USER64	MSR_USER32 | MSR_64BIT
 #elif defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_8xx)
 /* Default MSR for kernel mode. */
 #define MSR_KERNEL	(MSR_ME|MSR_RI|MSR_IR|MSR_DR)
 #define MSR_USER	(MSR_KERNEL|MSR_PR|MSR_EE)
 #endif
 
+#ifndef MSR_64BIT
+#define MSR_64BIT	0
+#endif
+
 /* Floating Point Status and Control Register (FPSCR) Fields */
 #define FPSCR_FX	0x80000000	/* FPU exception summary */
 #define FPSCR_FEX	0x40000000	/* FPU enabled exception summary */
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index b316794aa2b..817bd1ac175 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -27,10 +27,12 @@
 #define MSR_CM		(1<<31) /* Computation Mode (0=32-bit, 1=64-bit) */
 
 #if defined(CONFIG_PPC_BOOK3E_64)
+#define MSR_64BIT	MSR_CM
+
 #define MSR_		MSR_ME | MSR_CE
-#define MSR_KERNEL      MSR_ | MSR_CM
+#define MSR_KERNEL	MSR_ | MSR_64BIT
 #define MSR_USER32	MSR_ | MSR_PR | MSR_EE | MSR_DE
-#define MSR_USER64	MSR_USER32 | MSR_CM | MSR_DE
+#define MSR_USER64	MSR_USER32 | MSR_64BIT
 #elif defined (CONFIG_40x)
 #define MSR_KERNEL	(MSR_ME|MSR_RI|MSR_IR|MSR_DR|MSR_CE)
 #define MSR_USER	(MSR_KERNEL|MSR_PR|MSR_EE)
-- 
cgit v1.2.3-70-g09d2


From a7b8ad405862fb10e496ce839d423dfc94ac821b Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ellerman.id.au>
Date: Thu, 7 Apr 2011 21:22:23 +0000
Subject: powerpc/book3e: Fix extlb size

The calculation of the size for the exception save area of the TLB
miss handler is wrong, luckily it's too big not too small.

Rework it to make it a bit clearer, and also correct. We want 3 save
areas, each EX_TLB_SIZE _bytes_.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Acked-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/paca.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index f6da4f517fc..65c13c48db4 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -106,7 +106,8 @@ struct paca_struct {
 	pgd_t *pgd;			/* Current PGD */
 	pgd_t *kernel_pgd;		/* Kernel PGD */
 	u64 exgen[8] __attribute__((aligned(0x80)));
-	u64 extlb[EX_TLB_SIZE*3] __attribute__((aligned(0x80)));
+	/* We can have up to 3 levels of reentrancy in the TLB miss handler */
+	u64 extlb[3][EX_TLB_SIZE / sizeof(u64)] __attribute__((aligned(0x80)));
 	u64 exmc[8];		/* used for machine checks */
 	u64 excrit[8];		/* used for crit interrupts */
 	u64 exdbg[8];		/* used for debug interrupts */
-- 
cgit v1.2.3-70-g09d2


From 44ae3ab3358e962039c36ad4ae461ae9fb29596c Mon Sep 17 00:00:00 2001
From: Matt Evans <matt@ozlabs.org>
Date: Wed, 6 Apr 2011 19:48:50 +0000
Subject: powerpc: Free up some CPU feature bits by moving out MMU-related
 features

Some of the 64bit PPC CPU features are MMU-related, so this patch moves
them to MMU_FTR_ bits.  All cpu_has_feature()-style tests are moved to
mmu_has_feature(), and seven feature bits are freed as a result.

Signed-off-by: Matt Evans <matt@ozlabs.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/cputable.h        | 37 +++++++++--------------
 arch/powerpc/include/asm/mmu.h             | 48 ++++++++++++++++++++++++++++++
 arch/powerpc/include/asm/mmu_context.h     |  2 +-
 arch/powerpc/kernel/cputable.c             | 45 ++++++++++++----------------
 arch/powerpc/kernel/entry_64.S             |  8 ++---
 arch/powerpc/kernel/exceptions-64s.S       |  4 +--
 arch/powerpc/kernel/process.c              |  4 +--
 arch/powerpc/kernel/prom.c                 | 17 ++++++-----
 arch/powerpc/kernel/setup_64.c             |  2 +-
 arch/powerpc/mm/hash_low_64.S              |  8 ++---
 arch/powerpc/mm/hash_native_64.c           |  8 ++---
 arch/powerpc/mm/hash_utils_64.c            | 18 +++++------
 arch/powerpc/mm/hugetlbpage.c              |  2 +-
 arch/powerpc/mm/slb.c                      |  4 +--
 arch/powerpc/mm/slb_low.S                  |  8 ++---
 arch/powerpc/mm/stab.c                     |  2 +-
 arch/powerpc/platforms/iseries/exception.S |  3 +-
 arch/powerpc/platforms/iseries/setup.c     |  4 +--
 arch/powerpc/platforms/pseries/lpar.c      |  2 +-
 arch/powerpc/xmon/xmon.c                   |  2 +-
 20 files changed, 132 insertions(+), 96 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 2d71523ebb0..3db2476704d 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -178,23 +178,17 @@ extern const char *powerpc_base_platform;
 #define LONG_ASM_CONST(x)		0
 #endif
 
-#define CPU_FTR_SLB			LONG_ASM_CONST(0x0000000100000000)
-#define CPU_FTR_16M_PAGE		LONG_ASM_CONST(0x0000000200000000)
-#define CPU_FTR_TLBIEL			LONG_ASM_CONST(0x0000000400000000)
+
 #define CPU_FTR_HVMODE_206		LONG_ASM_CONST(0x0000000800000000)
 #define CPU_FTR_IABR			LONG_ASM_CONST(0x0000002000000000)
 #define CPU_FTR_MMCRA			LONG_ASM_CONST(0x0000004000000000)
 #define CPU_FTR_CTRL			LONG_ASM_CONST(0x0000008000000000)
 #define CPU_FTR_SMT			LONG_ASM_CONST(0x0000010000000000)
-#define CPU_FTR_LOCKLESS_TLBIE		LONG_ASM_CONST(0x0000040000000000)
-#define CPU_FTR_CI_LARGE_PAGE		LONG_ASM_CONST(0x0000100000000000)
 #define CPU_FTR_PAUSE_ZERO		LONG_ASM_CONST(0x0000200000000000)
 #define CPU_FTR_PURR			LONG_ASM_CONST(0x0000400000000000)
 #define CPU_FTR_CELL_TB_BUG		LONG_ASM_CONST(0x0000800000000000)
 #define CPU_FTR_SPURR			LONG_ASM_CONST(0x0001000000000000)
 #define CPU_FTR_DSCR			LONG_ASM_CONST(0x0002000000000000)
-#define CPU_FTR_1T_SEGMENT		LONG_ASM_CONST(0x0004000000000000)
-#define CPU_FTR_NO_SLBIE_B		LONG_ASM_CONST(0x0008000000000000)
 #define CPU_FTR_VSX			LONG_ASM_CONST(0x0010000000000000)
 #define CPU_FTR_SAO			LONG_ASM_CONST(0x0020000000000000)
 #define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0040000000000000)
@@ -206,9 +200,10 @@ extern const char *powerpc_base_platform;
 
 #ifndef __ASSEMBLY__
 
-#define CPU_FTR_PPCAS_ARCH_V2	(CPU_FTR_SLB | \
-				 CPU_FTR_TLBIEL | CPU_FTR_NOEXECUTE | \
-				 CPU_FTR_NODSISRALIGN | CPU_FTR_16M_PAGE)
+#define CPU_FTR_PPCAS_ARCH_V2	(CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN)
+
+#define MMU_FTR_PPCAS_ARCH_V2 	(MMU_FTR_SLB | MMU_FTR_TLBIEL | \
+				 MMU_FTR_16M_PAGE)
 
 /* We only set the altivec features if the kernel was compiled with altivec
  * support
@@ -408,38 +403,34 @@ extern const char *powerpc_base_platform;
 #define CPU_FTRS_POWER5	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
-	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
-	    CPU_FTR_PURR | CPU_FTR_STCX_CHECKS_ADDRESS | \
-	    CPU_FTR_POPCNTB)
+	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_PURR | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB)
 #define CPU_FTRS_POWER6 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
-	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
+	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
 	    CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB)
 #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_HVMODE_206 |\
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
-	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
+	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
 	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
-	    CPU_FTR_PAUSE_ZERO | CPU_FTR_CI_LARGE_PAGE | \
-	    CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \
+	    CPU_FTR_PAUSE_ZERO  | CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \
 	    CPU_FTR_UNALIGNED_LD_STD)
 #define CPU_FTRS_PA6T (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
-	    CPU_FTR_PPCAS_ARCH_V2 | \
-	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_CI_LARGE_PAGE | \
-	    CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_NO_SLBIE_B)
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_PURR | CPU_FTR_REAL_LE)
 #define CPU_FTRS_COMPATIBLE	(CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2)
 
 #define CPU_FTRS_A2 (CPU_FTR_USE_TB | CPU_FTR_SMT | CPU_FTR_DBELL | \
-	    CPU_FTR_TLBIEL | CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN | \
-	    CPU_FTR_16M_PAGE)
+		     CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN)
 
 #ifdef __powerpc64__
 #ifdef CONFIG_PPC_BOOK3E
@@ -449,7 +440,7 @@ extern const char *powerpc_base_platform;
 	    (CPU_FTRS_POWER3 | CPU_FTRS_RS64 | CPU_FTRS_POWER4 |	\
 	    CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | CPU_FTRS_POWER6 |	\
 	    CPU_FTRS_POWER7 | CPU_FTRS_CELL | CPU_FTRS_PA6T |		\
-	    CPU_FTR_1T_SEGMENT | CPU_FTR_VSX)
+	    CPU_FTR_VSX)
 #endif
 #else
 enum {
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index bb40a06d3b7..a39304b74f8 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -70,6 +70,54 @@
  */
 #define MMU_FTR_USE_PAIRED_MAS		ASM_CONST(0x01000000)
 
+/* MMU is SLB-based
+ */
+#define MMU_FTR_SLB			ASM_CONST(0x02000000)
+
+/* Support 16M large pages
+ */
+#define MMU_FTR_16M_PAGE		ASM_CONST(0x04000000)
+
+/* Supports TLBIEL variant
+ */
+#define MMU_FTR_TLBIEL			ASM_CONST(0x08000000)
+
+/* Supports tlbies w/o locking
+ */
+#define MMU_FTR_LOCKLESS_TLBIE		ASM_CONST(0x10000000)
+
+/* Large pages can be marked CI
+ */
+#define MMU_FTR_CI_LARGE_PAGE		ASM_CONST(0x20000000)
+
+/* 1T segments available
+ */
+#define MMU_FTR_1T_SEGMENT		ASM_CONST(0x40000000)
+
+/* Doesn't support the B bit (1T segment) in SLBIE
+ */
+#define MMU_FTR_NO_SLBIE_B		ASM_CONST(0x80000000)
+
+/* MMU feature bit sets for various CPUs */
+#define MMU_FTRS_DEFAULT_HPTE_ARCH_V2	\
+	MMU_FTR_HPTE_TABLE | MMU_FTR_PPCAS_ARCH_V2
+#define MMU_FTRS_POWER4		MMU_FTRS_DEFAULT_HPTE_ARCH_V2
+#define MMU_FTRS_PPC970		MMU_FTRS_POWER4
+#define MMU_FTRS_POWER5		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
+#define MMU_FTRS_POWER6		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
+#define MMU_FTRS_POWER7		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | \
+				MMU_FTR_TLBIE_206
+#define MMU_FTRS_CELL		MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
+				MMU_FTR_CI_LARGE_PAGE
+#define MMU_FTRS_PA6T		MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
+				MMU_FTR_CI_LARGE_PAGE | MMU_FTR_NO_SLBIE_B
+#define MMU_FTRS_A2		MMU_FTR_TYPE_3E | MMU_FTR_USE_TLBILX | \
+				MMU_FTR_USE_TLBIVAX_BCAST | \
+				MMU_FTR_LOCK_BCAST_INVAL | \
+				MMU_FTR_USE_TLBRSRV | \
+				MMU_FTR_USE_PAIRED_MAS | \
+				MMU_FTR_TLBIEL | \
+				MMU_FTR_16M_PAGE
 #ifndef __ASSEMBLY__
 #include <asm/cputable.h>
 
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 81fb41289d6..8e13f65b498 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -67,7 +67,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	 * sub architectures.
 	 */
 #ifdef CONFIG_PPC_STD_MMU_64
-	if (cpu_has_feature(CPU_FTR_SLB))
+	if (mmu_has_feature(MMU_FTR_SLB))
 		switch_slb(tsk, next);
 	else
 		switch_stab(tsk, next);
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 3d7b65ad496..34d2722b945 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -201,7 +201,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER4 (gp)",
 		.cpu_features		= CPU_FTRS_POWER4,
 		.cpu_user_features	= COMMON_USER_POWER4,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_POWER4,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -216,7 +216,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER4+ (gq)",
 		.cpu_features		= CPU_FTRS_POWER4,
 		.cpu_user_features	= COMMON_USER_POWER4,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_POWER4,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -232,7 +232,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_PPC970,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -250,7 +250,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_PPC970,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -286,7 +286,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_PPC970,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -304,7 +304,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_PPC970,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -320,7 +320,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER5 (gr)",
 		.cpu_features		= CPU_FTRS_POWER5,
 		.cpu_user_features	= COMMON_USER_POWER5,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_POWER5,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -340,7 +340,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER5+ (gs)",
 		.cpu_features		= CPU_FTRS_POWER5,
 		.cpu_user_features	= COMMON_USER_POWER5_PLUS,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_POWER5,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -356,7 +356,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER5+ (gs)",
 		.cpu_features		= CPU_FTRS_POWER5,
 		.cpu_user_features	= COMMON_USER_POWER5_PLUS,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_POWER5,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -373,7 +373,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER5+",
 		.cpu_features		= CPU_FTRS_POWER5,
 		.cpu_user_features	= COMMON_USER_POWER5_PLUS,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_POWER5,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.oprofile_cpu_type	= "ppc64/ibm-compat-v1",
@@ -387,7 +387,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_POWER6,
 		.cpu_user_features	= COMMON_USER_POWER6 |
 			PPC_FEATURE_POWER6_EXT,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_POWER6,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -406,7 +406,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER6 (architected)",
 		.cpu_features		= CPU_FTRS_POWER6,
 		.cpu_user_features	= COMMON_USER_POWER6,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_POWER6,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.oprofile_cpu_type	= "ppc64/ibm-compat-v1",
@@ -419,8 +419,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER7 (architected)",
 		.cpu_features		= CPU_FTRS_POWER7,
 		.cpu_user_features	= COMMON_USER_POWER7,
-		.mmu_features		= MMU_FTR_HPTE_TABLE |
-			MMU_FTR_TLBIE_206,
+		.mmu_features		= MMU_FTRS_POWER7,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.oprofile_type		= PPC_OPROFILE_POWER4,
@@ -435,8 +434,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER7 (raw)",
 		.cpu_features		= CPU_FTRS_POWER7,
 		.cpu_user_features	= COMMON_USER_POWER7,
-		.mmu_features		= MMU_FTR_HPTE_TABLE |
-			MMU_FTR_TLBIE_206,
+		.mmu_features		= MMU_FTRS_POWER7,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -453,8 +451,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER7+ (raw)",
 		.cpu_features		= CPU_FTRS_POWER7,
 		.cpu_user_features	= COMMON_USER_POWER7,
-		.mmu_features		= MMU_FTR_HPTE_TABLE |
-			MMU_FTR_TLBIE_206,
+		.mmu_features		= MMU_FTRS_POWER7,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -473,7 +470,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_user_features	= COMMON_USER_PPC64 |
 			PPC_FEATURE_CELL | PPC_FEATURE_HAS_ALTIVEC_COMP |
 			PPC_FEATURE_SMT,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_CELL,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 4,
@@ -488,7 +485,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "PA6T",
 		.cpu_features		= CPU_FTRS_PA6T,
 		.cpu_user_features	= COMMON_USER_PA6T,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_PA6T,
 		.icache_bsize		= 64,
 		.dcache_bsize		= 64,
 		.num_pmcs		= 6,
@@ -505,7 +502,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER4 (compatible)",
 		.cpu_features		= CPU_FTRS_COMPATIBLE,
 		.cpu_user_features	= COMMON_USER_PPC64,
-		.mmu_features		= MMU_FTR_HPTE_TABLE,
+		.mmu_features		= MMU_FTRS_DEFAULT_HPTE_ARCH_V2,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -2020,11 +2017,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "A2 (>= DD2)",
 		.cpu_features		= CPU_FTRS_A2,
 		.cpu_user_features	= COMMON_USER_PPC64,
-		.mmu_features		= MMU_FTR_TYPE_3E | MMU_FTR_USE_TLBILX |
-					  MMU_FTR_USE_TLBIVAX_BCAST |
-					  MMU_FTR_LOCK_BCAST_INVAL |
-					  MMU_FTR_USE_TLBRSRV |
-					  MMU_FTR_USE_PAIRED_MAS,
+		.mmu_features		= MMU_FTRS_A2,
 		.icache_bsize		= 64,
 		.dcache_bsize		= 64,
 		.num_pmcs		= 0,
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 64693706ebf..d834425186a 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -468,10 +468,10 @@ BEGIN_FTR_SECTION
   FTR_SECTION_ELSE_NESTED(95)
 	clrrdi	r6,r8,40	/* get its 1T ESID */
 	clrrdi	r9,r1,40	/* get current sp 1T ESID */
-  ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_1T_SEGMENT, 95)
+  ALT_MMU_FTR_SECTION_END_NESTED_IFCLR(MMU_FTR_1T_SEGMENT, 95)
 FTR_SECTION_ELSE
 	b	2f
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_SLB)
+ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_SLB)
 	clrldi.	r0,r6,2		/* is new ESID c00000000? */
 	cmpd	cr1,r6,r9	/* or is new ESID the same as current ESID? */
 	cror	eq,4*cr1+eq,eq
@@ -485,7 +485,7 @@ BEGIN_FTR_SECTION
 	li	r9,MMU_SEGSIZE_1T	/* insert B field */
 	oris	r6,r6,(MMU_SEGSIZE_1T << SLBIE_SSIZE_SHIFT)@h
 	rldimi	r7,r9,SLB_VSID_SSIZE_SHIFT,0
-END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 
 	/* Update the last bolted SLB.  No write barriers are needed
 	 * here, provided we only update the current CPU's SLB shadow
@@ -497,7 +497,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
 	std	r7,SLBSHADOW_STACKVSID(r9)  /* Save VSID */
 	std	r0,SLBSHADOW_STACKESID(r9)  /* Save ESID */
 
-	/* No need to check for CPU_FTR_NO_SLBIE_B here, since when
+	/* No need to check for MMU_FTR_NO_SLBIE_B here, since when
 	 * we have 1TB segments, the only CPUs known to have the errata
 	 * only support less than 1TB of system memory and we'll never
 	 * actually hit this code path.
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index ad06333631a..226cc8c6222 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -102,7 +102,7 @@ BEGIN_FTR_SECTION
 	EXCEPTION_PROLOG_PSERIES_1(data_access_common, EXC_STD)
 FTR_SECTION_ELSE
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD)
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_SLB)
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_SLB)
 
 	. = 0x380
 	.globl data_access_slb_pSeries
@@ -840,7 +840,7 @@ _STATIC(do_hash_page)
 BEGIN_FTR_SECTION
 	andis.	r0,r4,0x0020		/* Is it a segment table fault? */
 	bne-	do_ste_alloc		/* If so handle it */
-END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
 
 	clrrdi	r11,r1,THREAD_SHIFT
 	lwz	r0,TI_PREEMPT(r11)	/* If we're in an "NMI" */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index a01c2d93fd2..095043d7994 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -757,11 +757,11 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 				_ALIGN_UP(sizeof(struct thread_info), 16);
 
 #ifdef CONFIG_PPC_STD_MMU_64
-	if (cpu_has_feature(CPU_FTR_SLB)) {
+	if (mmu_has_feature(MMU_FTR_SLB)) {
 		unsigned long sp_vsid;
 		unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp;
 
-		if (cpu_has_feature(CPU_FTR_1T_SEGMENT))
+		if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
 			sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T)
 				<< SLB_VSID_SHIFT_1T;
 		else
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index c391dc4c8ba..5f5e6aed2b7 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -123,18 +123,19 @@ static void __init move_device_tree(void)
  */
 static struct ibm_pa_feature {
 	unsigned long	cpu_features;	/* CPU_FTR_xxx bit */
+	unsigned long	mmu_features;	/* MMU_FTR_xxx bit */
 	unsigned int	cpu_user_ftrs;	/* PPC_FEATURE_xxx bit */
 	unsigned char	pabyte;		/* byte number in ibm,pa-features */
 	unsigned char	pabit;		/* bit number (big-endian) */
 	unsigned char	invert;		/* if 1, pa bit set => clear feature */
 } ibm_pa_features[] __initdata = {
-	{0, PPC_FEATURE_HAS_MMU,	0, 0, 0},
-	{0, PPC_FEATURE_HAS_FPU,	0, 1, 0},
-	{CPU_FTR_SLB, 0,		0, 2, 0},
-	{CPU_FTR_CTRL, 0,		0, 3, 0},
-	{CPU_FTR_NOEXECUTE, 0,		0, 6, 0},
-	{CPU_FTR_NODSISRALIGN, 0,	1, 1, 1},
-	{CPU_FTR_CI_LARGE_PAGE, 0,	1, 2, 0},
+	{0, 0, PPC_FEATURE_HAS_MMU,	0, 0, 0},
+	{0, 0, PPC_FEATURE_HAS_FPU,	0, 1, 0},
+	{0, MMU_FTR_SLB, 0,		0, 2, 0},
+	{CPU_FTR_CTRL, 0, 0,		0, 3, 0},
+	{CPU_FTR_NOEXECUTE, 0, 0,	0, 6, 0},
+	{CPU_FTR_NODSISRALIGN, 0, 0,	1, 1, 1},
+	{0, MMU_FTR_CI_LARGE_PAGE, 0,	1, 2, 0},
 	{CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0},
 };
 
@@ -166,9 +167,11 @@ static void __init scan_features(unsigned long node, unsigned char *ftrs,
 		if (bit ^ fp->invert) {
 			cur_cpu_spec->cpu_features |= fp->cpu_features;
 			cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs;
+			cur_cpu_spec->mmu_features |= fp->mmu_features;
 		} else {
 			cur_cpu_spec->cpu_features &= ~fp->cpu_features;
 			cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs;
+			cur_cpu_spec->mmu_features &= ~fp->mmu_features;
 		}
 	}
 }
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 91a5cc5f0d0..959c63cf62e 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -436,7 +436,7 @@ void __init setup_system(void)
 
 static u64 slb0_limit(void)
 {
-	if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) {
+	if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) {
 		return 1UL << SID_SHIFT_1T;
 	}
 	return 1UL << SID_SHIFT;
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 5b7dd4ea02b..a242b5d7cbe 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -118,7 +118,7 @@ _GLOBAL(__hash_page_4K)
 BEGIN_FTR_SECTION
 	cmpdi	r9,0			/* check segment size */
 	bne	3f
-END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	/* Calc va and put it in r29 */
 	rldicr	r29,r5,28,63-28
 	rldicl	r3,r3,0,36
@@ -401,7 +401,7 @@ _GLOBAL(__hash_page_4K)
 BEGIN_FTR_SECTION
 	cmpdi	r9,0			/* check segment size */
 	bne	3f
-END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	/* Calc va and put it in r29 */
 	rldicr	r29,r5,28,63-28		/* r29 = (vsid << 28) */
 	rldicl	r3,r3,0,36		/* r3 = (ea & 0x0fffffff) */
@@ -715,7 +715,7 @@ BEGIN_FTR_SECTION
 	andi.	r0,r31,_PAGE_NO_CACHE
 	/* If so, bail out and refault as a 4k page */
 	bne-	ht64_bail_ok
-END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE)
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_CI_LARGE_PAGE)
 	/* Prepare new PTE value (turn access RW into DIRTY, then
 	 * add BUSY and ACCESSED)
 	 */
@@ -736,7 +736,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE)
 BEGIN_FTR_SECTION
 	cmpdi	r9,0			/* check segment size */
 	bne	3f
-END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	/* Calc va and put it in r29 */
 	rldicr	r29,r5,28,63-28
 	rldicl	r3,r3,0,36
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 784a400e078..c23eef2b81a 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -98,8 +98,8 @@ static inline void __tlbiel(unsigned long va, int psize, int ssize)
 
 static inline void tlbie(unsigned long va, int psize, int ssize, int local)
 {
-	unsigned int use_local = local && cpu_has_feature(CPU_FTR_TLBIEL);
-	int lock_tlbie = !cpu_has_feature(CPU_FTR_LOCKLESS_TLBIE);
+	unsigned int use_local = local && mmu_has_feature(MMU_FTR_TLBIEL);
+	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
 	if (use_local)
 		use_local = mmu_psize_defs[psize].tlbiel;
@@ -503,7 +503,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 		} pte_iterate_hashed_end();
 	}
 
-	if (cpu_has_feature(CPU_FTR_TLBIEL) &&
+	if (mmu_has_feature(MMU_FTR_TLBIEL) &&
 	    mmu_psize_defs[psize].tlbiel && local) {
 		asm volatile("ptesync":::"memory");
 		for (i = 0; i < number; i++) {
@@ -517,7 +517,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 		}
 		asm volatile("ptesync":::"memory");
 	} else {
-		int lock_tlbie = !cpu_has_feature(CPU_FTR_LOCKLESS_TLBIE);
+		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
 		if (lock_tlbie)
 			raw_spin_lock(&native_tlbie_lock);
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index d95d8f484d2..26b2872b3d0 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -259,11 +259,11 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node,
 	for (; size >= 4; size -= 4, ++prop) {
 		if (prop[0] == 40) {
 			DBG("1T segment support detected\n");
-			cur_cpu_spec->cpu_features |= CPU_FTR_1T_SEGMENT;
+			cur_cpu_spec->mmu_features |= MMU_FTR_1T_SEGMENT;
 			return 1;
 		}
 	}
-	cur_cpu_spec->cpu_features &= ~CPU_FTR_NO_SLBIE_B;
+	cur_cpu_spec->mmu_features &= ~MMU_FTR_NO_SLBIE_B;
 	return 0;
 }
 
@@ -289,7 +289,7 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 	if (prop != NULL) {
 		DBG("Page sizes from device-tree:\n");
 		size /= 4;
-		cur_cpu_spec->cpu_features &= ~(CPU_FTR_16M_PAGE);
+		cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE);
 		while(size > 0) {
 			unsigned int shift = prop[0];
 			unsigned int slbenc = prop[1];
@@ -317,7 +317,7 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 				break;
 			case 0x18:
 				idx = MMU_PAGE_16M;
-				cur_cpu_spec->cpu_features |= CPU_FTR_16M_PAGE;
+				cur_cpu_spec->mmu_features |= MMU_FTR_16M_PAGE;
 				break;
 			case 0x22:
 				idx = MMU_PAGE_16G;
@@ -412,7 +412,7 @@ static void __init htab_init_page_sizes(void)
 	 * Not in the device-tree, let's fallback on known size
 	 * list for 16M capable GP & GR
 	 */
-	if (cpu_has_feature(CPU_FTR_16M_PAGE))
+	if (mmu_has_feature(MMU_FTR_16M_PAGE))
 		memcpy(mmu_psize_defs, mmu_psize_defaults_gp,
 		       sizeof(mmu_psize_defaults_gp));
  found:
@@ -442,7 +442,7 @@ static void __init htab_init_page_sizes(void)
 		mmu_vmalloc_psize = MMU_PAGE_64K;
 		if (mmu_linear_psize == MMU_PAGE_4K)
 			mmu_linear_psize = MMU_PAGE_64K;
-		if (cpu_has_feature(CPU_FTR_CI_LARGE_PAGE)) {
+		if (mmu_has_feature(MMU_FTR_CI_LARGE_PAGE)) {
 			/*
 			 * Don't use 64k pages for ioremap on pSeries, since
 			 * that would stop us accessing the HEA ethernet.
@@ -608,7 +608,7 @@ static void __init htab_initialize(void)
 	/* Initialize page sizes */
 	htab_init_page_sizes();
 
-	if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) {
+	if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) {
 		mmu_kernel_ssize = MMU_SEGSIZE_1T;
 		mmu_highuser_ssize = MMU_SEGSIZE_1T;
 		printk(KERN_INFO "Using 1TB segments\n");
@@ -749,7 +749,7 @@ void __init early_init_mmu(void)
 
 	/* Initialize stab / SLB management except on iSeries
 	 */
-	if (cpu_has_feature(CPU_FTR_SLB))
+	if (mmu_has_feature(MMU_FTR_SLB))
 		slb_initialize();
 	else if (!firmware_has_feature(FW_FEATURE_ISERIES))
 		stab_initialize(get_paca()->stab_real);
@@ -766,7 +766,7 @@ void __cpuinit early_init_mmu_secondary(void)
 	 * in real mode on pSeries and we want a virtual address on
 	 * iSeries anyway
 	 */
-	if (cpu_has_feature(CPU_FTR_SLB))
+	if (mmu_has_feature(MMU_FTR_SLB))
 		slb_initialize();
 	else
 		stab_initialize(get_paca()->stab_addr);
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 9bb249c3046..0b9a5c1901b 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -529,7 +529,7 @@ static int __init hugetlbpage_init(void)
 {
 	int psize;
 
-	if (!cpu_has_feature(CPU_FTR_16M_PAGE))
+	if (!mmu_has_feature(MMU_FTR_16M_PAGE))
 		return -ENODEV;
 
 	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 5500712781d..e22276cb67a 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -167,7 +167,7 @@ static inline int esids_match(unsigned long addr1, unsigned long addr2)
 	int esid_1t_count;
 
 	/* System is not 1T segment size capable. */
-	if (!cpu_has_feature(CPU_FTR_1T_SEGMENT))
+	if (!mmu_has_feature(MMU_FTR_1T_SEGMENT))
 		return (GET_ESID(addr1) == GET_ESID(addr2));
 
 	esid_1t_count = (((addr1 >> SID_SHIFT_1T) != 0) +
@@ -202,7 +202,7 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
 	 */
 	hard_irq_disable();
 	offset = get_paca()->slb_cache_ptr;
-	if (!cpu_has_feature(CPU_FTR_NO_SLBIE_B) &&
+	if (!mmu_has_feature(MMU_FTR_NO_SLBIE_B) &&
 	    offset <= SLB_CACHE_ENTRIES) {
 		int i;
 		asm volatile("isync" : : : "memory");
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index 95ce3558169..ef653dc95b6 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -58,7 +58,7 @@ _GLOBAL(slb_miss_kernel_load_linear)
 	li	r11,0
 BEGIN_FTR_SECTION
 	b	slb_finish_load
-END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 	b	slb_finish_load_1T
 
 1:
@@ -87,7 +87,7 @@ _GLOBAL(slb_miss_kernel_load_vmemmap)
 6:
 BEGIN_FTR_SECTION
 	b	slb_finish_load
-END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 	b	slb_finish_load_1T
 
 0:	/* user address: proto-VSID = context << 15 | ESID. First check
@@ -138,11 +138,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT)
 	ld	r9,PACACONTEXTID(r13)
 BEGIN_FTR_SECTION
 	cmpldi	r10,0x1000
-END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	rldimi	r10,r9,USER_ESID_BITS,0
 BEGIN_FTR_SECTION
 	bge	slb_finish_load_1T
-END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	b	slb_finish_load
 
 8:	/* invalid EA */
diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c
index 446a01842a7..41e31642a86 100644
--- a/arch/powerpc/mm/stab.c
+++ b/arch/powerpc/mm/stab.c
@@ -243,7 +243,7 @@ void __init stabs_alloc(void)
 {
 	int cpu;
 
-	if (cpu_has_feature(CPU_FTR_SLB))
+	if (mmu_has_feature(MMU_FTR_SLB))
 		return;
 
 	for_each_possible_cpu(cpu) {
diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S
index 32a56c6dfa7..a67984c0495 100644
--- a/arch/powerpc/platforms/iseries/exception.S
+++ b/arch/powerpc/platforms/iseries/exception.S
@@ -31,6 +31,7 @@
 #include <asm/thread_info.h>
 #include <asm/ptrace.h>
 #include <asm/cputable.h>
+#include <asm/mmu.h>
 
 #include "exception.h"
 
@@ -157,7 +158,7 @@ BEGIN_FTR_SECTION
 FTR_SECTION_ELSE
 	EXCEPTION_PROLOG_1(PACA_EXGEN)
 	EXCEPTION_PROLOG_ISERIES_1
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_SLB)
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_SLB)
 	b	data_access_common
 
 .do_stab_bolted_iSeries:
diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c
index 2946ae10fbf..81cb8d2c413 100644
--- a/arch/powerpc/platforms/iseries/setup.c
+++ b/arch/powerpc/platforms/iseries/setup.c
@@ -249,7 +249,7 @@ static unsigned long iSeries_process_mainstore_vpd(struct MemoryBlock *mb_array,
 	unsigned long i;
 	unsigned long mem_blocks = 0;
 
-	if (cpu_has_feature(CPU_FTR_SLB))
+	if (mmu_has_feature(MMU_FTR_SLB))
 		mem_blocks = iSeries_process_Regatta_mainstore_vpd(mb_array,
 				max_entries);
 	else
@@ -634,7 +634,7 @@ static int __init iseries_probe(void)
 
 	hpte_init_iSeries();
 	/* iSeries does not support 16M pages */
-	cur_cpu_spec->cpu_features &= ~CPU_FTR_16M_PAGE;
+	cur_cpu_spec->mmu_features &= ~MMU_FTR_16M_PAGE;
 
 	return 1;
 }
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index ca5d5898d32..6f0ed3aac77 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -573,7 +573,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
 	unsigned long i, pix, rc;
 	unsigned long flags = 0;
 	struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
-	int lock_tlbie = !cpu_has_feature(CPU_FTR_LOCKLESS_TLBIE);
+	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 	unsigned long param[9];
 	unsigned long va;
 	unsigned long hash, index, shift, hidx, slot;
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index ef9756ee284..60593ad861e 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2663,7 +2663,7 @@ static void dump_stab(void)
 
 void dump_segments(void)
 {
-	if (cpu_has_feature(CPU_FTR_SLB))
+	if (mmu_has_feature(MMU_FTR_SLB))
 		dump_slb();
 	else
 		dump_stab();
-- 
cgit v1.2.3-70-g09d2


From 476eb4912601a8c01e6702b9a029f476b4b131d2 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@secretlab.ca>
Date: Wed, 4 May 2011 15:02:15 +1000
Subject: powerpc/irq: Stop exporting irq_map

First step in eliminating irq_map[] table entirely

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/irq.h                   | 21 +------
 arch/powerpc/kernel/irq.c                        | 26 +++++++-
 arch/powerpc/platforms/512x/mpc5121_ads_cpld.c   |  4 +-
 arch/powerpc/platforms/52xx/media5200.c          |  4 +-
 arch/powerpc/platforms/52xx/mpc52xx_pic.c        | 79 ++++--------------------
 arch/powerpc/platforms/82xx/pq2ads-pci-pic.c     |  4 +-
 arch/powerpc/platforms/85xx/socrates_fpga_pic.c  | 26 ++------
 arch/powerpc/platforms/86xx/gef_pic.c            | 10 +--
 arch/powerpc/platforms/8xx/m8xx_setup.c          |  2 +-
 arch/powerpc/platforms/cell/axon_msi.c           |  2 +-
 arch/powerpc/platforms/cell/spider-pic.c         | 10 +--
 arch/powerpc/platforms/embedded6xx/flipper-pic.c |  8 +--
 arch/powerpc/platforms/embedded6xx/hlwd-pic.c    |  8 +--
 arch/powerpc/platforms/iseries/irq.c             | 10 +--
 arch/powerpc/platforms/powermac/pic.c            | 12 ++--
 arch/powerpc/platforms/pseries/ras.c             |  4 +-
 arch/powerpc/sysdev/cpm1.c                       |  8 +--
 arch/powerpc/sysdev/cpm2_pic.c                   | 10 +--
 arch/powerpc/sysdev/ipic.c                       | 16 +++--
 arch/powerpc/sysdev/mpc8xx_pic.c                 | 10 +--
 arch/powerpc/sysdev/mpc8xxx_gpio.c               | 12 ++--
 arch/powerpc/sysdev/mpic.c                       | 28 ++++-----
 arch/powerpc/sysdev/mv64x60_pic.c                | 14 ++---
 arch/powerpc/sysdev/qe_lib/qe_ic.c               |  6 +-
 arch/powerpc/sysdev/uic.c                        | 12 ++--
 arch/powerpc/sysdev/xics/icp-hv.c                |  2 +-
 arch/powerpc/sysdev/xics/icp-native.c            |  2 +-
 arch/powerpc/sysdev/xics/ics-rtas.c              |  8 +--
 arch/powerpc/sysdev/xics/xics-common.c           |  4 +-
 arch/powerpc/sysdev/xilinx_intc.c                |  8 +--
 30 files changed, 148 insertions(+), 222 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 47b7905a636..e1983d57768 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -128,25 +128,10 @@ struct irq_host {
 	struct device_node	*of_node;
 };
 
-/* The main irq map itself is an array of NR_IRQ entries containing the
- * associate host and irq number. An entry with a host of NULL is free.
- * An entry can be allocated if it's free, the allocator always then sets
- * hwirq first to the host's invalid irq number and then fills ops.
- */
-struct irq_map_entry {
-	irq_hw_number_t	hwirq;
-	struct irq_host	*host;
-};
-
-extern struct irq_map_entry irq_map[NR_IRQS];
-
+struct irq_data;
+extern irq_hw_number_t irqd_to_hwirq(struct irq_data *d);
 extern irq_hw_number_t virq_to_hw(unsigned int virq);
-
-/* This will eventually -replace- virq_to_hw if/when we stash the
- * HW number in the irq_data itself. We use a macro so we can inline
- * it as irq_data isn't defined yet
- */
-#define irq_data_to_hw(d) (irq_map[(d)->irq].hwirq)
+extern struct irq_host *virq_to_host(unsigned int virq);
 
 /**
  * irq_alloc_host - Allocate a new irq_host data structure
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 4f5d6e751a6..a81dd74414b 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -481,20 +481,42 @@ void do_softirq(void)
  * IRQ controller and virtual interrupts
  */
 
+/* The main irq map itself is an array of NR_IRQ entries containing the
+ * associate host and irq number. An entry with a host of NULL is free.
+ * An entry can be allocated if it's free, the allocator always then sets
+ * hwirq first to the host's invalid irq number and then fills ops.
+ */
+struct irq_map_entry {
+	irq_hw_number_t	hwirq;
+	struct irq_host	*host;
+};
+
 static LIST_HEAD(irq_hosts);
 static DEFINE_RAW_SPINLOCK(irq_big_lock);
 static unsigned int revmap_trees_allocated;
 static DEFINE_MUTEX(revmap_trees_mutex);
-struct irq_map_entry irq_map[NR_IRQS];
+static struct irq_map_entry irq_map[NR_IRQS];
 static unsigned int irq_virq_count = NR_IRQS;
 static struct irq_host *irq_default_host;
 
+irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
+{
+	return irq_map[d->irq].hwirq;
+}
+EXPORT_SYMBOL_GPL(irqd_to_hwirq);
+
 irq_hw_number_t virq_to_hw(unsigned int virq)
 {
 	return irq_map[virq].hwirq;
 }
 EXPORT_SYMBOL_GPL(virq_to_hw);
 
+struct irq_host *virq_to_host(unsigned int virq)
+{
+	return irq_map[virq].host;
+}
+EXPORT_SYMBOL_GPL(virq_to_host);
+
 static int default_irq_host_match(struct irq_host *h, struct device_node *np)
 {
 	return h->of_node != NULL && h->of_node == np;
@@ -1103,7 +1125,7 @@ static int virq_debug_show(struct seq_file *m, void *private)
 			struct irq_chip *chip;
 
 			seq_printf(m, "%5d  ", i);
-			seq_printf(m, "0x%05lx  ", virq_to_hw(i));
+			seq_printf(m, "0x%05lx  ", irq_map[i].hwirq);
 
 			chip = irq_desc_get_chip(desc);
 			if (chip && chip->name)
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
index cfc4b200998..a8bc0d44393 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
@@ -61,7 +61,7 @@ irq_to_pic_bit(unsigned int irq)
 static void
 cpld_mask_irq(struct irq_data *d)
 {
-	unsigned int cpld_irq = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int cpld_irq = (unsigned int)irqd_to_hwirq(d);
 	void __iomem *pic_mask = irq_to_pic_mask(cpld_irq);
 
 	out_8(pic_mask,
@@ -71,7 +71,7 @@ cpld_mask_irq(struct irq_data *d)
 static void
 cpld_unmask_irq(struct irq_data *d)
 {
-	unsigned int cpld_irq = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int cpld_irq = (unsigned int)irqd_to_hwirq(d);
 	void __iomem *pic_mask = irq_to_pic_mask(cpld_irq);
 
 	out_8(pic_mask,
diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c
index 57a6a349e93..96f85e5e0cd 100644
--- a/arch/powerpc/platforms/52xx/media5200.c
+++ b/arch/powerpc/platforms/52xx/media5200.c
@@ -56,7 +56,7 @@ static void media5200_irq_unmask(struct irq_data *d)
 
 	spin_lock_irqsave(&media5200_irq.lock, flags);
 	val = in_be32(media5200_irq.regs + MEDIA5200_IRQ_ENABLE);
-	val |= 1 << (MEDIA5200_IRQ_SHIFT + irq_map[d->irq].hwirq);
+	val |= 1 << (MEDIA5200_IRQ_SHIFT + irqd_to_hwirq(d));
 	out_be32(media5200_irq.regs + MEDIA5200_IRQ_ENABLE, val);
 	spin_unlock_irqrestore(&media5200_irq.lock, flags);
 }
@@ -68,7 +68,7 @@ static void media5200_irq_mask(struct irq_data *d)
 
 	spin_lock_irqsave(&media5200_irq.lock, flags);
 	val = in_be32(media5200_irq.regs + MEDIA5200_IRQ_ENABLE);
-	val &= ~(1 << (MEDIA5200_IRQ_SHIFT + irq_map[d->irq].hwirq));
+	val &= ~(1 << (MEDIA5200_IRQ_SHIFT + irqd_to_hwirq(d)));
 	out_be32(media5200_irq.regs + MEDIA5200_IRQ_ENABLE, val);
 	spin_unlock_irqrestore(&media5200_irq.lock, flags);
 }
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
index 1dd15400f6f..bb611819b83 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -157,48 +157,30 @@ static inline void io_be_clrbit(u32 __iomem *addr, int bitno)
  */
 static void mpc52xx_extirq_mask(struct irq_data *d)
 {
-	int irq;
-	int l2irq;
-
-	irq = irq_map[d->irq].hwirq;
-	l2irq = irq & MPC52xx_IRQ_L2_MASK;
-
+	int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK;
 	io_be_clrbit(&intr->ctrl, 11 - l2irq);
 }
 
 static void mpc52xx_extirq_unmask(struct irq_data *d)
 {
-	int irq;
-	int l2irq;
-
-	irq = irq_map[d->irq].hwirq;
-	l2irq = irq & MPC52xx_IRQ_L2_MASK;
-
+	int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK;
 	io_be_setbit(&intr->ctrl, 11 - l2irq);
 }
 
 static void mpc52xx_extirq_ack(struct irq_data *d)
 {
-	int irq;
-	int l2irq;
-
-	irq = irq_map[d->irq].hwirq;
-	l2irq = irq & MPC52xx_IRQ_L2_MASK;
-
+	int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK;
 	io_be_setbit(&intr->ctrl, 27-l2irq);
 }
 
 static int mpc52xx_extirq_set_type(struct irq_data *d, unsigned int flow_type)
 {
 	u32 ctrl_reg, type;
-	int irq;
-	int l2irq;
+	int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK;
 	void *handler = handle_level_irq;
 
-	irq = irq_map[d->irq].hwirq;
-	l2irq = irq & MPC52xx_IRQ_L2_MASK;
-
-	pr_debug("%s: irq=%x. l2=%d flow_type=%d\n", __func__, irq, l2irq, flow_type);
+	pr_debug("%s: irq=%x. l2=%d flow_type=%d\n", __func__,
+		(int) irqd_to_hwirq(d), l2irq, flow_type);
 
 	switch (flow_type) {
 	case IRQF_TRIGGER_HIGH: type = 0; break;
@@ -237,23 +219,13 @@ static int mpc52xx_null_set_type(struct irq_data *d, unsigned int flow_type)
 
 static void mpc52xx_main_mask(struct irq_data *d)
 {
-	int irq;
-	int l2irq;
-
-	irq = irq_map[d->irq].hwirq;
-	l2irq = irq & MPC52xx_IRQ_L2_MASK;
-
+	int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK;
 	io_be_setbit(&intr->main_mask, 16 - l2irq);
 }
 
 static void mpc52xx_main_unmask(struct irq_data *d)
 {
-	int irq;
-	int l2irq;
-
-	irq = irq_map[d->irq].hwirq;
-	l2irq = irq & MPC52xx_IRQ_L2_MASK;
-
+	int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK;
 	io_be_clrbit(&intr->main_mask, 16 - l2irq);
 }
 
@@ -270,23 +242,13 @@ static struct irq_chip mpc52xx_main_irqchip = {
  */
 static void mpc52xx_periph_mask(struct irq_data *d)
 {
-	int irq;
-	int l2irq;
-
-	irq = irq_map[d->irq].hwirq;
-	l2irq = irq & MPC52xx_IRQ_L2_MASK;
-
+	int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK;
 	io_be_setbit(&intr->per_mask, 31 - l2irq);
 }
 
 static void mpc52xx_periph_unmask(struct irq_data *d)
 {
-	int irq;
-	int l2irq;
-
-	irq = irq_map[d->irq].hwirq;
-	l2irq = irq & MPC52xx_IRQ_L2_MASK;
-
+	int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK;
 	io_be_clrbit(&intr->per_mask, 31 - l2irq);
 }
 
@@ -303,34 +265,19 @@ static struct irq_chip mpc52xx_periph_irqchip = {
  */
 static void mpc52xx_sdma_mask(struct irq_data *d)
 {
-	int irq;
-	int l2irq;
-
-	irq = irq_map[d->irq].hwirq;
-	l2irq = irq & MPC52xx_IRQ_L2_MASK;
-
+	int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK;
 	io_be_setbit(&sdma->IntMask, l2irq);
 }
 
 static void mpc52xx_sdma_unmask(struct irq_data *d)
 {
-	int irq;
-	int l2irq;
-
-	irq = irq_map[d->irq].hwirq;
-	l2irq = irq & MPC52xx_IRQ_L2_MASK;
-
+	int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK;
 	io_be_clrbit(&sdma->IntMask, l2irq);
 }
 
 static void mpc52xx_sdma_ack(struct irq_data *d)
 {
-	int irq;
-	int l2irq;
-
-	irq = irq_map[d->irq].hwirq;
-	l2irq = irq & MPC52xx_IRQ_L2_MASK;
-
+	int l2irq = irqd_to_hwirq(d) & MPC52xx_IRQ_L2_MASK;
 	out_be32(&sdma->IntPend, 1 << l2irq);
 }
 
diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
index 4a4eb6ffa12..5d6c34ce0cb 100644
--- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
+++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
@@ -42,7 +42,7 @@ struct pq2ads_pci_pic {
 static void pq2ads_pci_mask_irq(struct irq_data *d)
 {
 	struct pq2ads_pci_pic *priv = irq_data_get_irq_chip_data(d);
-	int irq = NUM_IRQS - virq_to_hw(d->irq) - 1;
+	int irq = NUM_IRQS - irqd_to_hwirq(d) - 1;
 
 	if (irq != -1) {
 		unsigned long flags;
@@ -58,7 +58,7 @@ static void pq2ads_pci_mask_irq(struct irq_data *d)
 static void pq2ads_pci_unmask_irq(struct irq_data *d)
 {
 	struct pq2ads_pci_pic *priv = irq_data_get_irq_chip_data(d);
-	int irq = NUM_IRQS - virq_to_hw(d->irq) - 1;
+	int irq = NUM_IRQS - irqd_to_hwirq(d) - 1;
 
 	if (irq != -1) {
 		unsigned long flags;
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index db864623b4a..12cb9bb2cc6 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -48,8 +48,6 @@ static struct socrates_fpga_irq_info fpga_irqs[SOCRATES_FPGA_NUM_IRQS] = {
 	[8] = {0, IRQ_TYPE_LEVEL_HIGH},
 };
 
-#define socrates_fpga_irq_to_hw(virq)    ((unsigned int)irq_map[virq].hwirq)
-
 static DEFINE_RAW_SPINLOCK(socrates_fpga_pic_lock);
 
 static void __iomem *socrates_fpga_pic_iobase;
@@ -110,11 +108,9 @@ void socrates_fpga_pic_cascade(unsigned int irq, struct irq_desc *desc)
 static void socrates_fpga_pic_ack(struct irq_data *d)
 {
 	unsigned long flags;
-	unsigned int hwirq, irq_line;
+	unsigned int irq_line, hwirq = irqd_to_hwirq(d);
 	uint32_t mask;
 
-	hwirq = socrates_fpga_irq_to_hw(d->irq);
-
 	irq_line = fpga_irqs[hwirq].irq_line;
 	raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
 	mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line))
@@ -127,12 +123,10 @@ static void socrates_fpga_pic_ack(struct irq_data *d)
 static void socrates_fpga_pic_mask(struct irq_data *d)
 {
 	unsigned long flags;
-	unsigned int hwirq;
+	unsigned int hwirq = irqd_to_hwirq(d);
 	int irq_line;
 	u32 mask;
 
-	hwirq = socrates_fpga_irq_to_hw(d->irq);
-
 	irq_line = fpga_irqs[hwirq].irq_line;
 	raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
 	mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line))
@@ -145,12 +139,10 @@ static void socrates_fpga_pic_mask(struct irq_data *d)
 static void socrates_fpga_pic_mask_ack(struct irq_data *d)
 {
 	unsigned long flags;
-	unsigned int hwirq;
+	unsigned int hwirq = irqd_to_hwirq(d);
 	int irq_line;
 	u32 mask;
 
-	hwirq = socrates_fpga_irq_to_hw(d->irq);
-
 	irq_line = fpga_irqs[hwirq].irq_line;
 	raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
 	mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line))
@@ -164,12 +156,10 @@ static void socrates_fpga_pic_mask_ack(struct irq_data *d)
 static void socrates_fpga_pic_unmask(struct irq_data *d)
 {
 	unsigned long flags;
-	unsigned int hwirq;
+	unsigned int hwirq = irqd_to_hwirq(d);
 	int irq_line;
 	u32 mask;
 
-	hwirq = socrates_fpga_irq_to_hw(d->irq);
-
 	irq_line = fpga_irqs[hwirq].irq_line;
 	raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
 	mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line))
@@ -182,12 +172,10 @@ static void socrates_fpga_pic_unmask(struct irq_data *d)
 static void socrates_fpga_pic_eoi(struct irq_data *d)
 {
 	unsigned long flags;
-	unsigned int hwirq;
+	unsigned int hwirq = irqd_to_hwirq(d);
 	int irq_line;
 	u32 mask;
 
-	hwirq = socrates_fpga_irq_to_hw(d->irq);
-
 	irq_line = fpga_irqs[hwirq].irq_line;
 	raw_spin_lock_irqsave(&socrates_fpga_pic_lock, flags);
 	mask = socrates_fpga_pic_read(FPGA_PIC_IRQMASK(irq_line))
@@ -201,12 +189,10 @@ static int socrates_fpga_pic_set_type(struct irq_data *d,
 		unsigned int flow_type)
 {
 	unsigned long flags;
-	unsigned int hwirq;
+	unsigned int hwirq = irqd_to_hwirq(d);
 	int polarity;
 	u32 mask;
 
-	hwirq = socrates_fpga_irq_to_hw(d->irq);
-
 	if (fpga_irqs[hwirq].type != IRQ_TYPE_NONE)
 		return -EINVAL;
 
diff --git a/arch/powerpc/platforms/86xx/gef_pic.c b/arch/powerpc/platforms/86xx/gef_pic.c
index 0beec7d5566..94594e58594 100644
--- a/arch/powerpc/platforms/86xx/gef_pic.c
+++ b/arch/powerpc/platforms/86xx/gef_pic.c
@@ -46,8 +46,6 @@
 #define GEF_PIC_CPU0_MCP_MASK	GEF_PIC_MCP_MASK(0)
 #define GEF_PIC_CPU1_MCP_MASK	GEF_PIC_MCP_MASK(1)
 
-#define gef_irq_to_hw(virq)    ((unsigned int)irq_map[virq].hwirq)
-
 
 static DEFINE_RAW_SPINLOCK(gef_pic_lock);
 
@@ -113,11 +111,9 @@ void gef_pic_cascade(unsigned int irq, struct irq_desc *desc)
 static void gef_pic_mask(struct irq_data *d)
 {
 	unsigned long flags;
-	unsigned int hwirq;
+	unsigned int hwirq = irqd_to_hwirq(d);
 	u32 mask;
 
-	hwirq = gef_irq_to_hw(d->irq);
-
 	raw_spin_lock_irqsave(&gef_pic_lock, flags);
 	mask = in_be32(gef_pic_irq_reg_base + GEF_PIC_INTR_MASK(0));
 	mask &= ~(1 << hwirq);
@@ -136,11 +132,9 @@ static void gef_pic_mask_ack(struct irq_data *d)
 static void gef_pic_unmask(struct irq_data *d)
 {
 	unsigned long flags;
-	unsigned int hwirq;
+	unsigned int hwirq = irqd_to_hwirq(d);
 	u32 mask;
 
-	hwirq = gef_irq_to_hw(d->irq);
-
 	raw_spin_lock_irqsave(&gef_pic_lock, flags);
 	mask = in_be32(gef_pic_irq_reg_base + GEF_PIC_INTR_MASK(0));
 	mask |= (1 << hwirq);
diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c
index 9ecce995dd4..1e121088826 100644
--- a/arch/powerpc/platforms/8xx/m8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/m8xx_setup.c
@@ -150,7 +150,7 @@ void __init mpc8xx_calibrate_decr(void)
 	 */
 	cpu = of_find_node_by_type(NULL, "cpu");
 	virq= irq_of_parse_and_map(cpu, 0);
-	irq = irq_map[virq].hwirq;
+	irq = virq_to_hw(virq);
 
 	sys_tmr2 = immr_map(im_sit);
 	out_be16(&sys_tmr2->sit_tbscr, ((1 << (7 - (irq/2))) << 8) |
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index bb5ebf8fa80..1e3329e8578 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -113,7 +113,7 @@ static void axon_msi_cascade(unsigned int irq, struct irq_desc *desc)
 		pr_devel("axon_msi: woff %x roff %x msi %x\n",
 			  write_offset, msic->read_offset, msi);
 
-		if (msi < NR_IRQS && irq_map[msi].host == msic->irq_host) {
+		if (msi < NR_IRQS && virq_to_host(msi) == msic->irq_host) {
 			generic_handle_irq(msi);
 			msic->fifo_virt[idx] = cpu_to_le32(0xffffffff);
 		} else {
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index c5cf50e6b45..34d2b99d10c 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -70,7 +70,7 @@ static struct spider_pic spider_pics[SPIDER_CHIP_COUNT];
 
 static struct spider_pic *spider_virq_to_pic(unsigned int virq)
 {
-	return irq_map[virq].host->host_data;
+	return virq_to_host(virq)->host_data;
 }
 
 static void __iomem *spider_get_irq_config(struct spider_pic *pic,
@@ -82,7 +82,7 @@ static void __iomem *spider_get_irq_config(struct spider_pic *pic,
 static void spider_unmask_irq(struct irq_data *d)
 {
 	struct spider_pic *pic = spider_virq_to_pic(d->irq);
-	void __iomem *cfg = spider_get_irq_config(pic, irq_map[d->irq].hwirq);
+	void __iomem *cfg = spider_get_irq_config(pic, irqd_to_hwirq(d));
 
 	out_be32(cfg, in_be32(cfg) | 0x30000000u);
 }
@@ -90,7 +90,7 @@ static void spider_unmask_irq(struct irq_data *d)
 static void spider_mask_irq(struct irq_data *d)
 {
 	struct spider_pic *pic = spider_virq_to_pic(d->irq);
-	void __iomem *cfg = spider_get_irq_config(pic, irq_map[d->irq].hwirq);
+	void __iomem *cfg = spider_get_irq_config(pic, irqd_to_hwirq(d));
 
 	out_be32(cfg, in_be32(cfg) & ~0x30000000u);
 }
@@ -98,7 +98,7 @@ static void spider_mask_irq(struct irq_data *d)
 static void spider_ack_irq(struct irq_data *d)
 {
 	struct spider_pic *pic = spider_virq_to_pic(d->irq);
-	unsigned int src = irq_map[d->irq].hwirq;
+	unsigned int src = irqd_to_hwirq(d);
 
 	/* Reset edge detection logic if necessary
 	 */
@@ -117,7 +117,7 @@ static int spider_set_irq_type(struct irq_data *d, unsigned int type)
 {
 	unsigned int sense = type & IRQ_TYPE_SENSE_MASK;
 	struct spider_pic *pic = spider_virq_to_pic(d->irq);
-	unsigned int hw = irq_map[d->irq].hwirq;
+	unsigned int hw = irqd_to_hwirq(d);
 	void __iomem *cfg = spider_get_irq_config(pic, hw);
 	u32 old_mask;
 	u32 ic;
diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
index 12aa62b6f22..77cbe4c8f95 100644
--- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
@@ -48,7 +48,7 @@
 
 static void flipper_pic_mask_and_ack(struct irq_data *d)
 {
-	int irq = virq_to_hw(d->irq);
+	int irq = irqd_to_hwirq(d);
 	void __iomem *io_base = irq_data_get_irq_chip_data(d);
 	u32 mask = 1 << irq;
 
@@ -59,7 +59,7 @@ static void flipper_pic_mask_and_ack(struct irq_data *d)
 
 static void flipper_pic_ack(struct irq_data *d)
 {
-	int irq = virq_to_hw(d->irq);
+	int irq = irqd_to_hwirq(d);
 	void __iomem *io_base = irq_data_get_irq_chip_data(d);
 
 	/* this is at least needed for RSW */
@@ -68,7 +68,7 @@ static void flipper_pic_ack(struct irq_data *d)
 
 static void flipper_pic_mask(struct irq_data *d)
 {
-	int irq = virq_to_hw(d->irq);
+	int irq = irqd_to_hwirq(d);
 	void __iomem *io_base = irq_data_get_irq_chip_data(d);
 
 	clrbits32(io_base + FLIPPER_IMR, 1 << irq);
@@ -76,7 +76,7 @@ static void flipper_pic_mask(struct irq_data *d)
 
 static void flipper_pic_unmask(struct irq_data *d)
 {
-	int irq = virq_to_hw(d->irq);
+	int irq = irqd_to_hwirq(d);
 	void __iomem *io_base = irq_data_get_irq_chip_data(d);
 
 	setbits32(io_base + FLIPPER_IMR, 1 << irq);
diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
index 2bdddfc9d52..44b398b0a2f 100644
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
@@ -43,7 +43,7 @@
 
 static void hlwd_pic_mask_and_ack(struct irq_data *d)
 {
-	int irq = virq_to_hw(d->irq);
+	int irq = irqd_to_hwirq(d);
 	void __iomem *io_base = irq_data_get_irq_chip_data(d);
 	u32 mask = 1 << irq;
 
@@ -53,7 +53,7 @@ static void hlwd_pic_mask_and_ack(struct irq_data *d)
 
 static void hlwd_pic_ack(struct irq_data *d)
 {
-	int irq = virq_to_hw(d->irq);
+	int irq = irqd_to_hwirq(d);
 	void __iomem *io_base = irq_data_get_irq_chip_data(d);
 
 	out_be32(io_base + HW_BROADWAY_ICR, 1 << irq);
@@ -61,7 +61,7 @@ static void hlwd_pic_ack(struct irq_data *d)
 
 static void hlwd_pic_mask(struct irq_data *d)
 {
-	int irq = virq_to_hw(d->irq);
+	int irq = irqd_to_hwirq(d);
 	void __iomem *io_base = irq_data_get_irq_chip_data(d);
 
 	clrbits32(io_base + HW_BROADWAY_IMR, 1 << irq);
@@ -69,7 +69,7 @@ static void hlwd_pic_mask(struct irq_data *d)
 
 static void hlwd_pic_unmask(struct irq_data *d)
 {
-	int irq = virq_to_hw(d->irq);
+	int irq = irqd_to_hwirq(d);
 	void __iomem *io_base = irq_data_get_irq_chip_data(d);
 
 	setbits32(io_base + HW_BROADWAY_IMR, 1 << irq);
diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c
index 52a6889832c..375c21ca660 100644
--- a/arch/powerpc/platforms/iseries/irq.c
+++ b/arch/powerpc/platforms/iseries/irq.c
@@ -171,7 +171,7 @@ static void iseries_enable_IRQ(struct irq_data *d)
 {
 	u32 bus, dev_id, function, mask;
 	const u32 sub_bus = 0;
-	unsigned int rirq = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
 
 	/* The IRQ has already been locked by the caller */
 	bus = REAL_IRQ_TO_BUS(rirq);
@@ -188,7 +188,7 @@ static unsigned int iseries_startup_IRQ(struct irq_data *d)
 {
 	u32 bus, dev_id, function, mask;
 	const u32 sub_bus = 0;
-	unsigned int rirq = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
 
 	bus = REAL_IRQ_TO_BUS(rirq);
 	function = REAL_IRQ_TO_FUNC(rirq);
@@ -234,7 +234,7 @@ static void iseries_shutdown_IRQ(struct irq_data *d)
 {
 	u32 bus, dev_id, function, mask;
 	const u32 sub_bus = 0;
-	unsigned int rirq = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
 
 	/* irq should be locked by the caller */
 	bus = REAL_IRQ_TO_BUS(rirq);
@@ -257,7 +257,7 @@ static void iseries_disable_IRQ(struct irq_data *d)
 {
 	u32 bus, dev_id, function, mask;
 	const u32 sub_bus = 0;
-	unsigned int rirq = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
 
 	/* The IRQ has already been locked by the caller */
 	bus = REAL_IRQ_TO_BUS(rirq);
@@ -271,7 +271,7 @@ static void iseries_disable_IRQ(struct irq_data *d)
 
 static void iseries_end_IRQ(struct irq_data *d)
 {
-	unsigned int rirq = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
 
 	HvCallPci_eoi(REAL_IRQ_TO_BUS(rirq), REAL_IRQ_TO_SUBBUS(rirq),
 		(REAL_IRQ_TO_IDSEL(rirq) << 4) + REAL_IRQ_TO_FUNC(rirq));
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 023f24086a0..2f34ad04029 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -84,7 +84,7 @@ static void __pmac_retrigger(unsigned int irq_nr)
 
 static void pmac_mask_and_ack_irq(struct irq_data *d)
 {
-	unsigned int src = irq_map[d->irq].hwirq;
+	unsigned int src = irqd_to_hwirq(d);
         unsigned long bit = 1UL << (src & 0x1f);
         int i = src >> 5;
         unsigned long flags;
@@ -106,7 +106,7 @@ static void pmac_mask_and_ack_irq(struct irq_data *d)
 
 static void pmac_ack_irq(struct irq_data *d)
 {
-	unsigned int src = irq_map[d->irq].hwirq;
+	unsigned int src = irqd_to_hwirq(d);
         unsigned long bit = 1UL << (src & 0x1f);
         int i = src >> 5;
         unsigned long flags;
@@ -152,7 +152,7 @@ static void __pmac_set_irq_mask(unsigned int irq_nr, int nokicklost)
 static unsigned int pmac_startup_irq(struct irq_data *d)
 {
 	unsigned long flags;
-	unsigned int src = irq_map[d->irq].hwirq;
+	unsigned int src = irqd_to_hwirq(d);
         unsigned long bit = 1UL << (src & 0x1f);
         int i = src >> 5;
 
@@ -169,7 +169,7 @@ static unsigned int pmac_startup_irq(struct irq_data *d)
 static void pmac_mask_irq(struct irq_data *d)
 {
 	unsigned long flags;
-	unsigned int src = irq_map[d->irq].hwirq;
+	unsigned int src = irqd_to_hwirq(d);
 
 	raw_spin_lock_irqsave(&pmac_pic_lock, flags);
         __clear_bit(src, ppc_cached_irq_mask);
@@ -180,7 +180,7 @@ static void pmac_mask_irq(struct irq_data *d)
 static void pmac_unmask_irq(struct irq_data *d)
 {
 	unsigned long flags;
-	unsigned int src = irq_map[d->irq].hwirq;
+	unsigned int src = irqd_to_hwirq(d);
 
 	raw_spin_lock_irqsave(&pmac_pic_lock, flags);
 	__set_bit(src, ppc_cached_irq_mask);
@@ -193,7 +193,7 @@ static int pmac_retrigger(struct irq_data *d)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&pmac_pic_lock, flags);
-	__pmac_retrigger(irq_map[d->irq].hwirq);
+	__pmac_retrigger(irqd_to_hwirq(d));
 	raw_spin_unlock_irqrestore(&pmac_pic_lock, flags);
 	return 1;
 }
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index c55d7ad9c64..164a8eb4592 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -122,7 +122,7 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id)
 
 	status = rtas_call(ras_check_exception_token, 6, 1, NULL,
 			   RTAS_VECTOR_EXTERNAL_INTERRUPT,
-			   irq_map[irq].hwirq,
+			   virq_to_hw(irq),
 			   RTAS_EPOW_WARNING | RTAS_POWERMGM_EVENTS,
 			   critical, __pa(&ras_log_buf),
 				rtas_get_error_log_max());
@@ -157,7 +157,7 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id)
 
 	status = rtas_call(ras_check_exception_token, 6, 1, NULL,
 			   RTAS_VECTOR_EXTERNAL_INTERRUPT,
-			   irq_map[irq].hwirq,
+			   virq_to_hw(irq),
 			   RTAS_INTERNAL_ERROR, 1 /*Time Critical */,
 			   __pa(&ras_log_buf),
 				rtas_get_error_log_max());
diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c
index e0bc944eb23..350787c83e2 100644
--- a/arch/powerpc/sysdev/cpm1.c
+++ b/arch/powerpc/sysdev/cpm1.c
@@ -58,21 +58,21 @@ static struct irq_host *cpm_pic_host;
 
 static void cpm_mask_irq(struct irq_data *d)
 {
-	unsigned int cpm_vec = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int cpm_vec = (unsigned int)irqd_to_hwirq(d);
 
 	clrbits32(&cpic_reg->cpic_cimr, (1 << cpm_vec));
 }
 
 static void cpm_unmask_irq(struct irq_data *d)
 {
-	unsigned int cpm_vec = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int cpm_vec = (unsigned int)irqd_to_hwirq(d);
 
 	setbits32(&cpic_reg->cpic_cimr, (1 << cpm_vec));
 }
 
 static void cpm_end_irq(struct irq_data *d)
 {
-	unsigned int cpm_vec = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int cpm_vec = (unsigned int)irqd_to_hwirq(d);
 
 	out_be32(&cpic_reg->cpic_cisr, (1 << cpm_vec));
 }
@@ -157,7 +157,7 @@ unsigned int cpm_pic_init(void)
 		goto end;
 
 	/* Initialize the CPM interrupt controller. */
-	hwirq = (unsigned int)irq_map[sirq].hwirq;
+	hwirq = (unsigned int)virq_to_hw(sirq);
 	out_be32(&cpic_reg->cpic_cicr,
 	    (CICR_SCD_SCC4 | CICR_SCC_SCC3 | CICR_SCB_SCC2 | CICR_SCA_SCC1) |
 		((hwirq/2) << 13) | CICR_HP_MASK);
diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c
index 5495c1be472..bcab50e2a9e 100644
--- a/arch/powerpc/sysdev/cpm2_pic.c
+++ b/arch/powerpc/sysdev/cpm2_pic.c
@@ -81,7 +81,7 @@ static const u_char irq_to_siubit[] = {
 static void cpm2_mask_irq(struct irq_data *d)
 {
 	int	bit, word;
-	unsigned int irq_nr = virq_to_hw(d->irq);
+	unsigned int irq_nr = irqd_to_hwirq(d);
 
 	bit = irq_to_siubit[irq_nr];
 	word = irq_to_siureg[irq_nr];
@@ -93,7 +93,7 @@ static void cpm2_mask_irq(struct irq_data *d)
 static void cpm2_unmask_irq(struct irq_data *d)
 {
 	int	bit, word;
-	unsigned int irq_nr = virq_to_hw(d->irq);
+	unsigned int irq_nr = irqd_to_hwirq(d);
 
 	bit = irq_to_siubit[irq_nr];
 	word = irq_to_siureg[irq_nr];
@@ -105,7 +105,7 @@ static void cpm2_unmask_irq(struct irq_data *d)
 static void cpm2_ack(struct irq_data *d)
 {
 	int	bit, word;
-	unsigned int irq_nr = virq_to_hw(d->irq);
+	unsigned int irq_nr = irqd_to_hwirq(d);
 
 	bit = irq_to_siubit[irq_nr];
 	word = irq_to_siureg[irq_nr];
@@ -116,7 +116,7 @@ static void cpm2_ack(struct irq_data *d)
 static void cpm2_end_irq(struct irq_data *d)
 {
 	int	bit, word;
-	unsigned int irq_nr = virq_to_hw(d->irq);
+	unsigned int irq_nr = irqd_to_hwirq(d);
 
 	bit = irq_to_siubit[irq_nr];
 	word = irq_to_siureg[irq_nr];
@@ -133,7 +133,7 @@ static void cpm2_end_irq(struct irq_data *d)
 
 static int cpm2_set_irq_type(struct irq_data *d, unsigned int flow_type)
 {
-	unsigned int src = virq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned int vold, vnew, edibit;
 
 	/* Port C interrupts are either IRQ_TYPE_EDGE_FALLING or
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index fa438be962b..f0ece79f9be 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -521,12 +521,10 @@ static inline struct ipic * ipic_from_irq(unsigned int virq)
 	return primary_ipic;
 }
 
-#define ipic_irq_to_hw(virq)	((unsigned int)irq_map[virq].hwirq)
-
 static void ipic_unmask_irq(struct irq_data *d)
 {
 	struct ipic *ipic = ipic_from_irq(d->irq);
-	unsigned int src = ipic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned long flags;
 	u32 temp;
 
@@ -542,7 +540,7 @@ static void ipic_unmask_irq(struct irq_data *d)
 static void ipic_mask_irq(struct irq_data *d)
 {
 	struct ipic *ipic = ipic_from_irq(d->irq);
-	unsigned int src = ipic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned long flags;
 	u32 temp;
 
@@ -562,7 +560,7 @@ static void ipic_mask_irq(struct irq_data *d)
 static void ipic_ack_irq(struct irq_data *d)
 {
 	struct ipic *ipic = ipic_from_irq(d->irq);
-	unsigned int src = ipic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned long flags;
 	u32 temp;
 
@@ -581,7 +579,7 @@ static void ipic_ack_irq(struct irq_data *d)
 static void ipic_mask_irq_and_ack(struct irq_data *d)
 {
 	struct ipic *ipic = ipic_from_irq(d->irq);
-	unsigned int src = ipic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned long flags;
 	u32 temp;
 
@@ -604,7 +602,7 @@ static void ipic_mask_irq_and_ack(struct irq_data *d)
 static int ipic_set_irq_type(struct irq_data *d, unsigned int flow_type)
 {
 	struct ipic *ipic = ipic_from_irq(d->irq);
-	unsigned int src = ipic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned int vold, vnew, edibit;
 
 	if (flow_type == IRQ_TYPE_NONE)
@@ -793,7 +791,7 @@ struct ipic * __init ipic_init(struct device_node *node, unsigned int flags)
 int ipic_set_priority(unsigned int virq, unsigned int priority)
 {
 	struct ipic *ipic = ipic_from_irq(virq);
-	unsigned int src = ipic_irq_to_hw(virq);
+	unsigned int src = virq_to_hw(virq);
 	u32 temp;
 
 	if (priority > 7)
@@ -821,7 +819,7 @@ int ipic_set_priority(unsigned int virq, unsigned int priority)
 void ipic_set_highest_priority(unsigned int virq)
 {
 	struct ipic *ipic = ipic_from_irq(virq);
-	unsigned int src = ipic_irq_to_hw(virq);
+	unsigned int src = virq_to_hw(virq);
 	u32 temp;
 
 	temp = ipic_read(ipic->regs, IPIC_SICFR);
diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c
index a88800ff4d0..20924f2246f 100644
--- a/arch/powerpc/sysdev/mpc8xx_pic.c
+++ b/arch/powerpc/sysdev/mpc8xx_pic.c
@@ -28,7 +28,7 @@ int cpm_get_irq(struct pt_regs *regs);
 static void mpc8xx_unmask_irq(struct irq_data *d)
 {
 	int	bit, word;
-	unsigned int irq_nr = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int irq_nr = (unsigned int)irqd_to_hwirq(d);
 
 	bit = irq_nr & 0x1f;
 	word = irq_nr >> 5;
@@ -40,7 +40,7 @@ static void mpc8xx_unmask_irq(struct irq_data *d)
 static void mpc8xx_mask_irq(struct irq_data *d)
 {
 	int	bit, word;
-	unsigned int irq_nr = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int irq_nr = (unsigned int)irqd_to_hwirq(d);
 
 	bit = irq_nr & 0x1f;
 	word = irq_nr >> 5;
@@ -52,7 +52,7 @@ static void mpc8xx_mask_irq(struct irq_data *d)
 static void mpc8xx_ack(struct irq_data *d)
 {
 	int	bit;
-	unsigned int irq_nr = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int irq_nr = (unsigned int)irqd_to_hwirq(d);
 
 	bit = irq_nr & 0x1f;
 	out_be32(&siu_reg->sc_sipend, 1 << (31-bit));
@@ -61,7 +61,7 @@ static void mpc8xx_ack(struct irq_data *d)
 static void mpc8xx_end_irq(struct irq_data *d)
 {
 	int bit, word;
-	unsigned int irq_nr = (unsigned int)irq_map[d->irq].hwirq;
+	unsigned int irq_nr = (unsigned int)irqd_to_hwirq(d);
 
 	bit = irq_nr & 0x1f;
 	word = irq_nr >> 5;
@@ -73,7 +73,7 @@ static void mpc8xx_end_irq(struct irq_data *d)
 static int mpc8xx_set_irq_type(struct irq_data *d, unsigned int flow_type)
 {
 	if (flow_type & IRQ_TYPE_EDGE_FALLING) {
-		irq_hw_number_t hw = (unsigned int)irq_map[d->irq].hwirq;
+		irq_hw_number_t hw = (unsigned int)irqd_to_hwirq(d);
 		unsigned int siel = in_be32(&siu_reg->sc_siel);
 
 		/* only external IRQ senses are programmable */
diff --git a/arch/powerpc/sysdev/mpc8xxx_gpio.c b/arch/powerpc/sysdev/mpc8xxx_gpio.c
index 0892a2841c2..fb4963abdf5 100644
--- a/arch/powerpc/sysdev/mpc8xxx_gpio.c
+++ b/arch/powerpc/sysdev/mpc8xxx_gpio.c
@@ -163,7 +163,7 @@ static void mpc8xxx_irq_unmask(struct irq_data *d)
 
 	spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
 
-	setbits32(mm->regs + GPIO_IMR, mpc8xxx_gpio2mask(virq_to_hw(d->irq)));
+	setbits32(mm->regs + GPIO_IMR, mpc8xxx_gpio2mask(irqd_to_hwirq(d)));
 
 	spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
 }
@@ -176,7 +176,7 @@ static void mpc8xxx_irq_mask(struct irq_data *d)
 
 	spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
 
-	clrbits32(mm->regs + GPIO_IMR, mpc8xxx_gpio2mask(virq_to_hw(d->irq)));
+	clrbits32(mm->regs + GPIO_IMR, mpc8xxx_gpio2mask(irqd_to_hwirq(d)));
 
 	spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
 }
@@ -186,7 +186,7 @@ static void mpc8xxx_irq_ack(struct irq_data *d)
 	struct mpc8xxx_gpio_chip *mpc8xxx_gc = irq_data_get_irq_chip_data(d);
 	struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc;
 
-	out_be32(mm->regs + GPIO_IER, mpc8xxx_gpio2mask(virq_to_hw(d->irq)));
+	out_be32(mm->regs + GPIO_IER, mpc8xxx_gpio2mask(irqd_to_hwirq(d)));
 }
 
 static int mpc8xxx_irq_set_type(struct irq_data *d, unsigned int flow_type)
@@ -199,14 +199,14 @@ static int mpc8xxx_irq_set_type(struct irq_data *d, unsigned int flow_type)
 	case IRQ_TYPE_EDGE_FALLING:
 		spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
 		setbits32(mm->regs + GPIO_ICR,
-			  mpc8xxx_gpio2mask(virq_to_hw(d->irq)));
+			  mpc8xxx_gpio2mask(irqd_to_hwirq(d)));
 		spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
 		break;
 
 	case IRQ_TYPE_EDGE_BOTH:
 		spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
 		clrbits32(mm->regs + GPIO_ICR,
-			  mpc8xxx_gpio2mask(virq_to_hw(d->irq)));
+			  mpc8xxx_gpio2mask(irqd_to_hwirq(d)));
 		spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
 		break;
 
@@ -221,7 +221,7 @@ static int mpc512x_irq_set_type(struct irq_data *d, unsigned int flow_type)
 {
 	struct mpc8xxx_gpio_chip *mpc8xxx_gc = irq_data_get_irq_chip_data(d);
 	struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc;
-	unsigned long gpio = virq_to_hw(d->irq);
+	unsigned long gpio = irqd_to_hwirq(d);
 	void __iomem *reg;
 	unsigned int shift;
 	unsigned long flags;
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index f91c065bed5..824a94fc413 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -607,8 +607,6 @@ static int irq_choose_cpu(const struct cpumask *mask)
 }
 #endif
 
-#define mpic_irq_to_hw(virq)	((unsigned int)irq_map[virq].hwirq)
-
 /* Find an mpic associated with a given linux interrupt */
 static struct mpic *mpic_find(unsigned int irq)
 {
@@ -621,7 +619,7 @@ static struct mpic *mpic_find(unsigned int irq)
 /* Determine if the linux irq is an IPI */
 static unsigned int mpic_is_ipi(struct mpic *mpic, unsigned int irq)
 {
-	unsigned int src = mpic_irq_to_hw(irq);
+	unsigned int src = virq_to_hw(irq);
 
 	return (src >= mpic->ipi_vecs[0] && src <= mpic->ipi_vecs[3]);
 }
@@ -674,7 +672,7 @@ void mpic_unmask_irq(struct irq_data *d)
 {
 	unsigned int loops = 100000;
 	struct mpic *mpic = mpic_from_irq_data(d);
-	unsigned int src = mpic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 
 	DBG("%p: %s: enable_irq: %d (src %d)\n", mpic, mpic->name, d->irq, src);
 
@@ -695,7 +693,7 @@ void mpic_mask_irq(struct irq_data *d)
 {
 	unsigned int loops = 100000;
 	struct mpic *mpic = mpic_from_irq_data(d);
-	unsigned int src = mpic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 
 	DBG("%s: disable_irq: %d (src %d)\n", mpic->name, d->irq, src);
 
@@ -733,7 +731,7 @@ void mpic_end_irq(struct irq_data *d)
 static void mpic_unmask_ht_irq(struct irq_data *d)
 {
 	struct mpic *mpic = mpic_from_irq_data(d);
-	unsigned int src = mpic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 
 	mpic_unmask_irq(d);
 
@@ -744,7 +742,7 @@ static void mpic_unmask_ht_irq(struct irq_data *d)
 static unsigned int mpic_startup_ht_irq(struct irq_data *d)
 {
 	struct mpic *mpic = mpic_from_irq_data(d);
-	unsigned int src = mpic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 
 	mpic_unmask_irq(d);
 	mpic_startup_ht_interrupt(mpic, src, irqd_is_level_type(d));
@@ -755,7 +753,7 @@ static unsigned int mpic_startup_ht_irq(struct irq_data *d)
 static void mpic_shutdown_ht_irq(struct irq_data *d)
 {
 	struct mpic *mpic = mpic_from_irq_data(d);
-	unsigned int src = mpic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 
 	mpic_shutdown_ht_interrupt(mpic, src);
 	mpic_mask_irq(d);
@@ -764,7 +762,7 @@ static void mpic_shutdown_ht_irq(struct irq_data *d)
 static void mpic_end_ht_irq(struct irq_data *d)
 {
 	struct mpic *mpic = mpic_from_irq_data(d);
-	unsigned int src = mpic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 
 #ifdef DEBUG_IRQ
 	DBG("%s: end_irq: %d\n", mpic->name, d->irq);
@@ -785,7 +783,7 @@ static void mpic_end_ht_irq(struct irq_data *d)
 static void mpic_unmask_ipi(struct irq_data *d)
 {
 	struct mpic *mpic = mpic_from_ipi(d);
-	unsigned int src = mpic_irq_to_hw(d->irq) - mpic->ipi_vecs[0];
+	unsigned int src = virq_to_hw(d->irq) - mpic->ipi_vecs[0];
 
 	DBG("%s: enable_ipi: %d (ipi %d)\n", mpic->name, d->irq, src);
 	mpic_ipi_write(src, mpic_ipi_read(src) & ~MPIC_VECPRI_MASK);
@@ -816,7 +814,7 @@ int mpic_set_affinity(struct irq_data *d, const struct cpumask *cpumask,
 		      bool force)
 {
 	struct mpic *mpic = mpic_from_irq_data(d);
-	unsigned int src = mpic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 
 	if (mpic->flags & MPIC_SINGLE_DEST_CPU) {
 		int cpuid = irq_choose_cpu(cpumask);
@@ -862,7 +860,7 @@ static unsigned int mpic_type_to_vecpri(struct mpic *mpic, unsigned int type)
 int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type)
 {
 	struct mpic *mpic = mpic_from_irq_data(d);
-	unsigned int src = mpic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned int vecpri, vold, vnew;
 
 	DBG("mpic: set_irq_type(mpic:@%p,virq:%d,src:0x%x,type:0x%x)\n",
@@ -898,7 +896,7 @@ int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type)
 void mpic_set_vector(unsigned int virq, unsigned int vector)
 {
 	struct mpic *mpic = mpic_from_irq(virq);
-	unsigned int src = mpic_irq_to_hw(virq);
+	unsigned int src = virq_to_hw(virq);
 	unsigned int vecpri;
 
 	DBG("mpic: set_vector(mpic:@%p,virq:%d,src:%d,vector:0x%x)\n",
@@ -916,7 +914,7 @@ void mpic_set_vector(unsigned int virq, unsigned int vector)
 void mpic_set_destination(unsigned int virq, unsigned int cpuid)
 {
 	struct mpic *mpic = mpic_from_irq(virq);
-	unsigned int src = mpic_irq_to_hw(virq);
+	unsigned int src = virq_to_hw(virq);
 
 	DBG("mpic: set_destination(mpic:@%p,virq:%d,src:%d,cpuid:0x%x)\n",
 	    mpic, virq, src, cpuid);
@@ -1427,7 +1425,7 @@ void __init mpic_set_serial_int(struct mpic *mpic, int enable)
 void mpic_irq_set_priority(unsigned int irq, unsigned int pri)
 {
 	struct mpic *mpic = mpic_find(irq);
-	unsigned int src = mpic_irq_to_hw(irq);
+	unsigned int src = virq_to_hw(irq);
 	unsigned long flags;
 	u32 reg;
 
diff --git a/arch/powerpc/sysdev/mv64x60_pic.c b/arch/powerpc/sysdev/mv64x60_pic.c
index e9c633c7c08..14d130268e7 100644
--- a/arch/powerpc/sysdev/mv64x60_pic.c
+++ b/arch/powerpc/sysdev/mv64x60_pic.c
@@ -78,7 +78,7 @@ static struct irq_host *mv64x60_irq_host;
 
 static void mv64x60_mask_low(struct irq_data *d)
 {
-	int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK;
+	int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK;
 	unsigned long flags;
 
 	spin_lock_irqsave(&mv64x60_lock, flags);
@@ -91,7 +91,7 @@ static void mv64x60_mask_low(struct irq_data *d)
 
 static void mv64x60_unmask_low(struct irq_data *d)
 {
-	int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK;
+	int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK;
 	unsigned long flags;
 
 	spin_lock_irqsave(&mv64x60_lock, flags);
@@ -115,7 +115,7 @@ static struct irq_chip mv64x60_chip_low = {
 
 static void mv64x60_mask_high(struct irq_data *d)
 {
-	int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK;
+	int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK;
 	unsigned long flags;
 
 	spin_lock_irqsave(&mv64x60_lock, flags);
@@ -128,7 +128,7 @@ static void mv64x60_mask_high(struct irq_data *d)
 
 static void mv64x60_unmask_high(struct irq_data *d)
 {
-	int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK;
+	int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK;
 	unsigned long flags;
 
 	spin_lock_irqsave(&mv64x60_lock, flags);
@@ -152,7 +152,7 @@ static struct irq_chip mv64x60_chip_high = {
 
 static void mv64x60_mask_gpp(struct irq_data *d)
 {
-	int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK;
+	int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK;
 	unsigned long flags;
 
 	spin_lock_irqsave(&mv64x60_lock, flags);
@@ -165,7 +165,7 @@ static void mv64x60_mask_gpp(struct irq_data *d)
 
 static void mv64x60_mask_ack_gpp(struct irq_data *d)
 {
-	int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK;
+	int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK;
 	unsigned long flags;
 
 	spin_lock_irqsave(&mv64x60_lock, flags);
@@ -180,7 +180,7 @@ static void mv64x60_mask_ack_gpp(struct irq_data *d)
 
 static void mv64x60_unmask_gpp(struct irq_data *d)
 {
-	int level2 = irq_map[d->irq].hwirq & MV64x60_LEVEL2_MASK;
+	int level2 = irqd_to_hwirq(d) & MV64x60_LEVEL2_MASK;
 	unsigned long flags;
 
 	spin_lock_irqsave(&mv64x60_lock, flags);
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c
index 832d6924ad1..b2acda07220 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c
@@ -197,12 +197,10 @@ static inline struct qe_ic *qe_ic_from_irq_data(struct irq_data *d)
 	return irq_data_get_irq_chip_data(d);
 }
 
-#define virq_to_hw(virq)	((unsigned int)irq_map[virq].hwirq)
-
 static void qe_ic_unmask_irq(struct irq_data *d)
 {
 	struct qe_ic *qe_ic = qe_ic_from_irq_data(d);
-	unsigned int src = virq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned long flags;
 	u32 temp;
 
@@ -218,7 +216,7 @@ static void qe_ic_unmask_irq(struct irq_data *d)
 static void qe_ic_mask_irq(struct irq_data *d)
 {
 	struct qe_ic *qe_ic = qe_ic_from_irq_data(d);
-	unsigned int src = virq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned long flags;
 	u32 temp;
 
diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c
index 5d913851662..984cd202915 100644
--- a/arch/powerpc/sysdev/uic.c
+++ b/arch/powerpc/sysdev/uic.c
@@ -41,8 +41,6 @@
 #define UIC_VR		0x7
 #define UIC_VCR		0x8
 
-#define uic_irq_to_hw(virq)	(irq_map[virq].hwirq)
-
 struct uic *primary_uic;
 
 struct uic {
@@ -58,7 +56,7 @@ struct uic {
 static void uic_unmask_irq(struct irq_data *d)
 {
 	struct uic *uic = irq_data_get_irq_chip_data(d);
-	unsigned int src = uic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned long flags;
 	u32 er, sr;
 
@@ -76,7 +74,7 @@ static void uic_unmask_irq(struct irq_data *d)
 static void uic_mask_irq(struct irq_data *d)
 {
 	struct uic *uic = irq_data_get_irq_chip_data(d);
-	unsigned int src = uic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned long flags;
 	u32 er;
 
@@ -90,7 +88,7 @@ static void uic_mask_irq(struct irq_data *d)
 static void uic_ack_irq(struct irq_data *d)
 {
 	struct uic *uic = irq_data_get_irq_chip_data(d);
-	unsigned int src = uic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned long flags;
 
 	spin_lock_irqsave(&uic->lock, flags);
@@ -101,7 +99,7 @@ static void uic_ack_irq(struct irq_data *d)
 static void uic_mask_ack_irq(struct irq_data *d)
 {
 	struct uic *uic = irq_data_get_irq_chip_data(d);
-	unsigned int src = uic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned long flags;
 	u32 er, sr;
 
@@ -126,7 +124,7 @@ static void uic_mask_ack_irq(struct irq_data *d)
 static int uic_set_irq_type(struct irq_data *d, unsigned int flow_type)
 {
 	struct uic *uic = irq_data_get_irq_chip_data(d);
-	unsigned int src = uic_irq_to_hw(d->irq);
+	unsigned int src = irqd_to_hwirq(d);
 	unsigned long flags;
 	int trigger, polarity;
 	u32 tr, pr, mask;
diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index b03d348b19a..76e87245bbf 100644
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -58,7 +58,7 @@ static inline void icp_hv_set_qirr(int n_cpu , u8 value)
 
 static void icp_hv_eoi(struct irq_data *d)
 {
-	unsigned int hw_irq = (unsigned int)irq_data_to_hw(d);
+	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
 
 	iosync();
 	icp_hv_set_xirr((xics_pop_cppr() << 24) | hw_irq);
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index be5e3d748ed..d9e0515592c 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -80,7 +80,7 @@ static void icp_native_set_cpu_priority(unsigned char cppr)
 
 static void icp_native_eoi(struct irq_data *d)
 {
-	unsigned int hw_irq = (unsigned int)irq_data_to_hw(d);
+	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
 
 	iosync();
 	icp_native_set_xirr((xics_pop_cppr() << 24) | hw_irq);
diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c
index 610c148fedc..c782f85cf7e 100644
--- a/arch/powerpc/sysdev/xics/ics-rtas.c
+++ b/arch/powerpc/sysdev/xics/ics-rtas.c
@@ -38,7 +38,7 @@ static struct ics ics_rtas = {
 
 static void ics_rtas_unmask_irq(struct irq_data *d)
 {
-	unsigned int hw_irq = (unsigned int)irq_data_to_hw(d);
+	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
 	int call_status;
 	int server;
 
@@ -109,7 +109,7 @@ static void ics_rtas_mask_real_irq(unsigned int hw_irq)
 
 static void ics_rtas_mask_irq(struct irq_data *d)
 {
-	unsigned int hw_irq = (unsigned int)irq_data_to_hw(d);
+	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
 
 	pr_devel("xics: mask virq %d [hw 0x%x]\n", d->irq, hw_irq);
 
@@ -122,7 +122,7 @@ static int ics_rtas_set_affinity(struct irq_data *d,
 				 const struct cpumask *cpumask,
 				 bool force)
 {
-	unsigned int hw_irq = (unsigned int)irq_data_to_hw(d);
+	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
 	int status;
 	int xics_status[2];
 	int irq_server;
@@ -171,7 +171,7 @@ static struct irq_chip ics_rtas_irq_chip = {
 
 static int ics_rtas_map(struct ics *ics, unsigned int virq)
 {
-	unsigned int hw_irq = (unsigned int)irq_map[virq].hwirq;
+	unsigned int hw_irq = (unsigned int)virq_to_hw(virq);
 	int status[2];
 	int rc;
 
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index c58844d7242..a0576b705dd 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -240,9 +240,9 @@ void xics_migrate_irqs_away(void)
 		/* We can't set affinity on ISA interrupts */
 		if (virq < NUM_ISA_INTERRUPTS)
 			continue;
-		if (irq_map[virq].host != xics_host)
+		if (virq_to_host(virq) != xics_host)
 			continue;
-		irq = (unsigned int)irq_map[virq].hwirq;
+		irq = (unsigned int)virq_to_hw(virq);
 		/* We need to get IPIs still. */
 		if (irq == XICS_IPI || irq == XICS_IRQ_SPURIOUS)
 			continue;
diff --git a/arch/powerpc/sysdev/xilinx_intc.c b/arch/powerpc/sysdev/xilinx_intc.c
index 0a13fc19e28..6183799754a 100644
--- a/arch/powerpc/sysdev/xilinx_intc.c
+++ b/arch/powerpc/sysdev/xilinx_intc.c
@@ -71,7 +71,7 @@ static unsigned char xilinx_intc_map_senses[] = {
  */
 static void xilinx_intc_mask(struct irq_data *d)
 {
-	int irq = virq_to_hw(d->irq);
+	int irq = irqd_to_hwirq(d);
 	void * regs = irq_data_get_irq_chip_data(d);
 	pr_debug("mask: %d\n", irq);
 	out_be32(regs + XINTC_CIE, 1 << irq);
@@ -87,7 +87,7 @@ static int xilinx_intc_set_type(struct irq_data *d, unsigned int flow_type)
  */
 static void xilinx_intc_level_unmask(struct irq_data *d)
 {
-	int irq = virq_to_hw(d->irq);
+	int irq = irqd_to_hwirq(d);
 	void * regs = irq_data_get_irq_chip_data(d);
 	pr_debug("unmask: %d\n", irq);
 	out_be32(regs + XINTC_SIE, 1 << irq);
@@ -112,7 +112,7 @@ static struct irq_chip xilinx_intc_level_irqchip = {
  */
 static void xilinx_intc_edge_unmask(struct irq_data *d)
 {
-	int irq = virq_to_hw(d->irq);
+	int irq = irqd_to_hwirq(d);
 	void *regs = irq_data_get_irq_chip_data(d);
 	pr_debug("unmask: %d\n", irq);
 	out_be32(regs + XINTC_SIE, 1 << irq);
@@ -120,7 +120,7 @@ static void xilinx_intc_edge_unmask(struct irq_data *d)
 
 static void xilinx_intc_edge_ack(struct irq_data *d)
 {
-	int irq = virq_to_hw(d->irq);
+	int irq = irqd_to_hwirq(d);
 	void * regs = irq_data_get_irq_chip_data(d);
 	pr_debug("ack: %d\n", irq);
 	out_be32(regs + XINTC_IAR, 1 << irq);
-- 
cgit v1.2.3-70-g09d2


From a32e252f7cdfb3675a4e50215cfac356ed8952c4 Mon Sep 17 00:00:00 2001
From: Michael Neuling <mikey@neuling.org>
Date: Wed, 6 Apr 2011 18:23:29 +0000
Subject: powerpc: Use new CPU feature bit to select 2.06 tlbie

This removes MMU_FTR_TLBIE_206 as we can now use CPU_FTR_HVMODE_206.  It
also changes the logic to select which tlbie to use to be based on this
new CPU feature bit.

This also duplicates the ASM_FTR_IF/SET/CLR defines for CPU features
(copied from MMU features).

Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/feature-fixups.h | 13 +++++++++++++
 arch/powerpc/include/asm/mmu.h            |  8 +-------
 arch/powerpc/mm/hash_native_64.c          | 10 ++++------
 3 files changed, 18 insertions(+), 13 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index bdc0d6877bc..9a67a38bf7b 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -146,6 +146,19 @@ label##5:							\
 
 #ifndef __ASSEMBLY__
 
+#define ASM_FTR_IF(section_if, section_else, msk, val)	\
+	stringify_in_c(BEGIN_FTR_SECTION)			\
+	section_if "; "						\
+	stringify_in_c(FTR_SECTION_ELSE)			\
+	section_else "; "					\
+	stringify_in_c(ALT_FTR_SECTION_END((msk), (val)))
+
+#define ASM_FTR_IFSET(section_if, section_else, msk)	\
+	ASM_FTR_IF(section_if, section_else, (msk), (msk))
+
+#define ASM_FTR_IFCLR(section_if, section_else, msk)	\
+	ASM_FTR_IF(section_if, section_else, (msk), 0)
+
 #define ASM_MMU_FTR_IF(section_if, section_else, msk, val)	\
 	stringify_in_c(BEGIN_MMU_FTR_SECTION)			\
 	section_if "; "						\
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index a39304b74f8..4138b21ae80 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -56,11 +56,6 @@
  */
 #define MMU_FTR_NEED_DTLB_SW_LRU	ASM_CONST(0x00200000)
 
-/* This indicates that the processor uses the ISA 2.06 server tlbie
- * mnemonics
- */
-#define MMU_FTR_TLBIE_206		ASM_CONST(0x00400000)
-
 /* Enable use of TLB reservation.  Processor should support tlbsrx.
  * instruction and MAS0[WQ].
  */
@@ -105,8 +100,7 @@
 #define MMU_FTRS_PPC970		MMU_FTRS_POWER4
 #define MMU_FTRS_POWER5		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
 #define MMU_FTRS_POWER6		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
-#define MMU_FTRS_POWER7		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE | \
-				MMU_FTR_TLBIE_206
+#define MMU_FTRS_POWER7		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
 #define MMU_FTRS_CELL		MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
 				MMU_FTR_CI_LARGE_PAGE
 #define MMU_FTRS_PA6T		MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index c23eef2b81a..dfd764896db 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -50,9 +50,8 @@ static inline void __tlbie(unsigned long va, int psize, int ssize)
 	case MMU_PAGE_4K:
 		va &= ~0xffful;
 		va |= ssize << 8;
-		asm volatile(ASM_MMU_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0),
-					       %2)
-			     : : "r" (va), "r"(0), "i" (MMU_FTR_TLBIE_206)
+		asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2)
+			     : : "r" (va), "r"(0), "i" (CPU_FTR_HVMODE_206)
 			     : "memory");
 		break;
 	default:
@@ -61,9 +60,8 @@ static inline void __tlbie(unsigned long va, int psize, int ssize)
 		va |= penc << 12;
 		va |= ssize << 8;
 		va |= 1; /* L */
-		asm volatile(ASM_MMU_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0),
-					       %2)
-			     : : "r" (va), "r"(0), "i" (MMU_FTR_TLBIE_206)
+		asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2)
+			     : : "r" (va), "r"(0), "i" (CPU_FTR_HVMODE_206)
 			     : "memory");
 		break;
 	}
-- 
cgit v1.2.3-70-g09d2


From 851d2e2fe8dbcbe3afcad6fc4569c881d8ad4ce9 Mon Sep 17 00:00:00 2001
From: "Tseng-Hui (Frank) Lin" <thlin@linux.vnet.ibm.com>
Date: Mon, 2 May 2011 20:43:04 +0000
Subject: powerpc: Add Initiate Coprocessor Store Word (icswx) support

Icswx is a PowerPC instruction to send data to a co-processor. On Book-S
processors the LPAR_ID and process ID (PID) of the owning process are
registered in the window context of the co-processor at initialization
time. When the icswx instruction is executed the L2 generates a cop-reg
transaction on PowerBus. The transaction has no address and the
processor does not perform an MMU access to authenticate the transaction.
The co-processor compares the LPAR_ID and the PID included in the
transaction and the LPAR_ID and PID held in the window context to
determine if the process is authorized to generate the transaction.

The OS needs to assign a 16-bit PID for the process. This cop-PID needs
to be updated during context switch. The cop-PID needs to be destroyed
when the context is destroyed.

Signed-off-by: Sonny Rao <sonnyrao@linux.vnet.ibm.com>
Signed-off-by: Tseng-Hui (Frank) Lin <thlin@linux.vnet.ibm.com>
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/cputable.h    |   4 +-
 arch/powerpc/include/asm/mmu-hash64.h  |   6 +
 arch/powerpc/include/asm/mmu_context.h |  10 ++
 arch/powerpc/include/asm/reg.h         |   1 +
 arch/powerpc/mm/mmu_context_hash64.c   | 211 +++++++++++++++++++++++++++++++++
 arch/powerpc/platforms/Kconfig.cputype |  18 +++
 6 files changed, 249 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 3db2476704d..a3e1a9e96a7 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -197,6 +197,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_STCX_CHECKS_ADDRESS	LONG_ASM_CONST(0x0200000000000000)
 #define CPU_FTR_POPCNTB			LONG_ASM_CONST(0x0400000000000000)
 #define CPU_FTR_POPCNTD			LONG_ASM_CONST(0x0800000000000000)
+#define CPU_FTR_ICSWX			LONG_ASM_CONST(0x1000000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -418,7 +419,8 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
 	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
-	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD)
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_ICSWX)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index ae7b3efec8e..d865bd909c7 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -408,6 +408,7 @@ static inline void subpage_prot_init_new_context(struct mm_struct *mm) { }
 #endif /* CONFIG_PPC_SUBPAGE_PROT */
 
 typedef unsigned long mm_context_id_t;
+struct spinlock;
 
 typedef struct {
 	mm_context_id_t id;
@@ -423,6 +424,11 @@ typedef struct {
 #ifdef CONFIG_PPC_SUBPAGE_PROT
 	struct subpage_prot_table spt;
 #endif /* CONFIG_PPC_SUBPAGE_PROT */
+#ifdef CONFIG_PPC_ICSWX
+	struct spinlock *cop_lockp; /* guard acop and cop_pid */
+	unsigned long acop;	/* mask of enabled coprocessor types */
+	unsigned int cop_pid;	/* pid value used with coprocessors */
+#endif /* CONFIG_PPC_ICSWX */
 } mm_context_t;
 
 
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 8e13f65b498..a73668a5f30 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -32,6 +32,10 @@ extern void __destroy_context(unsigned long context_id);
 extern void mmu_context_init(void);
 #endif
 
+extern void switch_cop(struct mm_struct *next);
+extern int use_cop(unsigned long acop, struct mm_struct *mm);
+extern void drop_cop(unsigned long acop, struct mm_struct *mm);
+
 /*
  * switch_mm is the entry point called from the architecture independent
  * code in kernel/sched.c
@@ -55,6 +59,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	if (prev == next)
 		return;
 
+#ifdef CONFIG_PPC_ICSWX
+	/* Switch coprocessor context only if prev or next uses a coprocessor */
+	if (prev->context.acop || next->context.acop)
+		switch_cop(next);
+#endif /* CONFIG_PPC_ICSWX */
+
 	/* We must stop all altivec streams before changing the HW
 	 * context
 	 */
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 1f9ac12742e..632e78e1444 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -188,6 +188,7 @@
 
 #define SPRN_CTR	0x009	/* Count Register */
 #define SPRN_DSCR	0x11
+#define SPRN_ACOP	0x1F	/* Available Coprocessor Register */
 #define SPRN_CTRLF	0x088
 #define SPRN_CTRLT	0x098
 #define   CTRL_CT	0xc0000000	/* current thread */
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index c5859448a0a..c517815404c 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -20,9 +20,205 @@
 #include <linux/idr.h>
 #include <linux/module.h>
 #include <linux/gfp.h>
+#include <linux/slab.h>
 
 #include <asm/mmu_context.h>
 
+#ifdef CONFIG_PPC_ICSWX
+/*
+ * The processor and its L2 cache cause the icswx instruction to
+ * generate a COP_REQ transaction on PowerBus. The transaction has
+ * no address, and the processor does not perform an MMU access
+ * to authenticate the transaction. The command portion of the
+ * PowerBus COP_REQ transaction includes the LPAR_ID (LPID) and
+ * the coprocessor Process ID (PID), which the coprocessor compares
+ * to the authorized LPID and PID held in the coprocessor, to determine
+ * if the process is authorized to generate the transaction.
+ * The data of the COP_REQ transaction is 128-byte or less and is
+ * placed in cacheable memory on a 128-byte cache line boundary.
+ *
+ * The task to use a coprocessor should use use_cop() to allocate
+ * a coprocessor PID before executing icswx instruction. use_cop()
+ * also enables the coprocessor context switching. Drop_cop() is
+ * used to free the coprocessor PID.
+ *
+ * Example:
+ * Host Fabric Interface (HFI) is a PowerPC network coprocessor.
+ * Each HFI have multiple windows. Each HFI window serves as a
+ * network device sending to and receiving from HFI network.
+ * HFI immediate send function uses icswx instruction. The immediate
+ * send function allows small (single cache-line) packets be sent
+ * without using the regular HFI send FIFO and doorbell, which are
+ * much slower than immediate send.
+ *
+ * For each task intending to use HFI immediate send, the HFI driver
+ * calls use_cop() to obtain a coprocessor PID for the task.
+ * The HFI driver then allocate a free HFI window and save the
+ * coprocessor PID to the HFI window to allow the task to use the
+ * HFI window.
+ *
+ * The HFI driver repeatedly creates immediate send packets and
+ * issues icswx instruction to send data through the HFI window.
+ * The HFI compares the coprocessor PID in the CPU PID register
+ * to the PID held in the HFI window to determine if the transaction
+ * is allowed.
+ *
+ * When the task to release the HFI window, the HFI driver calls
+ * drop_cop() to release the coprocessor PID.
+ */
+
+#define COP_PID_NONE 0
+#define COP_PID_MIN (COP_PID_NONE + 1)
+#define COP_PID_MAX (0xFFFF)
+
+static DEFINE_SPINLOCK(mmu_context_acop_lock);
+static DEFINE_IDA(cop_ida);
+
+void switch_cop(struct mm_struct *next)
+{
+	mtspr(SPRN_PID, next->context.cop_pid);
+	mtspr(SPRN_ACOP, next->context.acop);
+}
+
+static int new_cop_pid(struct ida *ida, int min_id, int max_id,
+		       spinlock_t *lock)
+{
+	int index;
+	int err;
+
+again:
+	if (!ida_pre_get(ida, GFP_KERNEL))
+		return -ENOMEM;
+
+	spin_lock(lock);
+	err = ida_get_new_above(ida, min_id, &index);
+	spin_unlock(lock);
+
+	if (err == -EAGAIN)
+		goto again;
+	else if (err)
+		return err;
+
+	if (index > max_id) {
+		spin_lock(lock);
+		ida_remove(ida, index);
+		spin_unlock(lock);
+		return -ENOMEM;
+	}
+
+	return index;
+}
+
+static void sync_cop(void *arg)
+{
+	struct mm_struct *mm = arg;
+
+	if (mm == current->active_mm)
+		switch_cop(current->active_mm);
+}
+
+/**
+ * Start using a coprocessor.
+ * @acop: mask of coprocessor to be used.
+ * @mm: The mm the coprocessor to associate with. Most likely current mm.
+ *
+ * Return a positive PID if successful. Negative errno otherwise.
+ * The returned PID will be fed to the coprocessor to determine if an
+ * icswx transaction is authenticated.
+ */
+int use_cop(unsigned long acop, struct mm_struct *mm)
+{
+	int ret;
+
+	if (!cpu_has_feature(CPU_FTR_ICSWX))
+		return -ENODEV;
+
+	if (!mm || !acop)
+		return -EINVAL;
+
+	/* We need to make sure mm_users doesn't change */
+	down_read(&mm->mmap_sem);
+	spin_lock(mm->context.cop_lockp);
+
+	if (mm->context.cop_pid == COP_PID_NONE) {
+		ret = new_cop_pid(&cop_ida, COP_PID_MIN, COP_PID_MAX,
+				  &mmu_context_acop_lock);
+		if (ret < 0)
+			goto out;
+
+		mm->context.cop_pid = ret;
+	}
+	mm->context.acop |= acop;
+
+	sync_cop(mm);
+
+	/*
+	 * If this is a threaded process then there might be other threads
+	 * running. We need to send an IPI to force them to pick up any
+	 * change in PID and ACOP.
+	 */
+	if (atomic_read(&mm->mm_users) > 1)
+		smp_call_function(sync_cop, mm, 1);
+
+	ret = mm->context.cop_pid;
+
+out:
+	spin_unlock(mm->context.cop_lockp);
+	up_read(&mm->mmap_sem);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(use_cop);
+
+/**
+ * Stop using a coprocessor.
+ * @acop: mask of coprocessor to be stopped.
+ * @mm: The mm the coprocessor associated with.
+ */
+void drop_cop(unsigned long acop, struct mm_struct *mm)
+{
+	int free_pid = COP_PID_NONE;
+
+	if (!cpu_has_feature(CPU_FTR_ICSWX))
+		return;
+
+	if (WARN_ON_ONCE(!mm))
+		return;
+
+	/* We need to make sure mm_users doesn't change */
+	down_read(&mm->mmap_sem);
+	spin_lock(mm->context.cop_lockp);
+
+	mm->context.acop &= ~acop;
+
+	if ((!mm->context.acop) && (mm->context.cop_pid != COP_PID_NONE)) {
+		free_pid = mm->context.cop_pid;
+		mm->context.cop_pid = COP_PID_NONE;
+	}
+
+	sync_cop(mm);
+
+	/*
+	 * If this is a threaded process then there might be other threads
+	 * running. We need to send an IPI to force them to pick up any
+	 * change in PID and ACOP.
+	 */
+	if (atomic_read(&mm->mm_users) > 1)
+		smp_call_function(sync_cop, mm, 1);
+
+	if (free_pid != COP_PID_NONE) {
+		spin_lock(&mmu_context_acop_lock);
+		ida_remove(&cop_ida, free_pid);
+		spin_unlock(&mmu_context_acop_lock);
+	}
+
+	spin_unlock(mm->context.cop_lockp);
+	up_read(&mm->mmap_sem);
+}
+EXPORT_SYMBOL_GPL(drop_cop);
+
+#endif /* CONFIG_PPC_ICSWX */
+
 static DEFINE_SPINLOCK(mmu_context_lock);
 static DEFINE_IDA(mmu_context_ida);
 
@@ -78,6 +274,16 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 		slice_set_user_psize(mm, mmu_virtual_psize);
 	subpage_prot_init_new_context(mm);
 	mm->context.id = index;
+#ifdef CONFIG_PPC_ICSWX
+	mm->context.cop_lockp = kmalloc(sizeof(spinlock_t), GFP_KERNEL);
+	if (!mm->context.cop_lockp) {
+		__destroy_context(index);
+		subpage_prot_free(mm);
+		mm->context.id = NO_CONTEXT;
+		return -ENOMEM;
+	}
+	spin_lock_init(mm->context.cop_lockp);
+#endif /* CONFIG_PPC_ICSWX */
 
 	return 0;
 }
@@ -92,6 +298,11 @@ EXPORT_SYMBOL_GPL(__destroy_context);
 
 void destroy_context(struct mm_struct *mm)
 {
+#ifdef CONFIG_PPC_ICSWX
+	drop_cop(mm->context.acop, mm);
+	kfree(mm->context.cop_lockp);
+	mm->context.cop_lockp = NULL;
+#endif /* CONFIG_PPC_ICSWX */
 	__destroy_context(mm->context.id);
 	subpage_prot_free(mm);
 	mm->context.id = MMU_NO_CONTEXT;
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 7c1e1c64437..a1e623822a3 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -230,6 +230,24 @@ config VSX
 
 	  If in doubt, say Y here.
 
+config PPC_ICSWX
+	bool "Support for PowerPC icswx coprocessor instruction"
+	depends on POWER4
+	default n
+	---help---
+
+	  This option enables kernel support for the PowerPC Initiate
+	  Coprocessor Store Word (icswx) coprocessor instruction on POWER7
+	  or newer processors.
+
+	  This option is only useful if you have a processor that supports
+	  the icswx coprocessor instruction. It does not have any effect
+	  on processors without the icswx coprocessor instruction.
+
+	  This option slightly increases kernel memory usage.
+
+	  If in doubt, say N here.
+
 config SPE
 	bool "SPE Support"
 	depends on E200 || (E500 && !PPC_E500MC)
-- 
cgit v1.2.3-70-g09d2


From 1977b502120d44b9b4897703adfb2e2fab346880 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Sun, 1 May 2011 19:46:44 +0000
Subject: powerpc: Save register r9-r13 values accurately on interrupt with bad
 stack

When we take an interrupt or exception from kernel mode and the stack
pointer is obviously not a kernel address (i.e. the top bit is 0), we
switch to an emergency stack, save register values and panic.  However,
on 64-bit server machines, we don't actually save the values of r9 - r13
at the time of the interrupt, but rather values corrupted by the
exception entry code for r12-r13, and nothing at all for r9-r11.

This fixes it by passing a pointer to the register save area in the paca
through to the bad_stack code in r3.  The register values are saved in
one of the paca register save areas (depending on which exception this
is).  Using the pointer in r3, the bad_stack code now retrieves the
saved values of r9 - r13 and stores them in the exception frame on the
emergency stack.  This also stores the normal exception frame marker
("regshere") in the exception frame.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/exception-64s.h |  7 ++++---
 arch/powerpc/kernel/exceptions-64s.S     | 20 +++++++++++++++++---
 2 files changed, 21 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index d6b4849df9b..96ccef136ca 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -104,10 +104,11 @@
 	beq-	1f;							   \
 	ld	r1,PACAKSAVE(r13);	/* kernel stack to use		*/ \
 1:	cmpdi	cr1,r1,0;		/* check if r1 is in userspace	*/ \
-	bge-	cr1,2f;			/* abort if it is		*/ \
-	b	3f;							   \
-2:	li	r1,(n);			/* will be reloaded later	*/ \
+	blt+	cr1,3f;			/* abort if it is		*/ \
+	li	r1,(n);			/* will be reloaded later	*/ \
 	sth	r1,PACA_TRAP_SAVE(r13);					   \
+	std	r3,area+EX_R3(r13);					   \
+	addi	r3,r13,area;		/* r3 -> where regs are saved*/	   \
 	b	bad_stack;						   \
 3:	std	r9,_CCR(r1);		/* save CR in stackframe	*/ \
 	std	r11,_NIP(r1);		/* save SRR0 in stackframe	*/ \
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 226cc8c6222..27ca8b7c600 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -461,9 +461,20 @@ bad_stack:
 	std	r12,_XER(r1)
 	SAVE_GPR(0,r1)
 	SAVE_GPR(2,r1)
-	SAVE_4GPRS(3,r1)
-	SAVE_2GPRS(7,r1)
-	SAVE_10GPRS(12,r1)
+	ld	r10,EX_R3(r3)
+	std	r10,GPR3(r1)
+	SAVE_GPR(4,r1)
+	SAVE_4GPRS(5,r1)
+	ld	r9,EX_R9(r3)
+	ld	r10,EX_R10(r3)
+	SAVE_2GPRS(9,r1)
+	ld	r9,EX_R11(r3)
+	ld	r10,EX_R12(r3)
+	ld	r11,EX_R13(r3)
+	std	r9,GPR11(r1)
+	std	r10,GPR12(r1)
+	std	r11,GPR13(r1)
+	SAVE_8GPRS(14,r1)
 	SAVE_10GPRS(22,r1)
 	lhz	r12,PACA_TRAP_SAVE(r13)
 	std	r12,_TRAP(r1)
@@ -472,6 +483,9 @@ bad_stack:
 	li	r12,0
 	std	r12,0(r11)
 	ld	r2,PACATOC(r13)
+	ld	r11,exception_marker@toc(r2)
+	std	r12,RESULT(r1)
+	std	r11,STACK_FRAME_OVERHEAD-16(r1)
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	.kernel_bad_stack
 	b	1b
-- 
cgit v1.2.3-70-g09d2


From 48404f2e95ef0ffd8134d89c8abcd1a15e15f1b0 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Sun, 1 May 2011 19:48:20 +0000
Subject: powerpc: Save Come-From Address Register (CFAR) in exception frame

Recent 64-bit server processors (POWER6 and POWER7) have a "Come-From
Address Register" (CFAR), that records the address of the most recent
branch or rfid (return from interrupt) instruction for debugging purposes.

This saves the value of the CFAR in the exception entry code and stores
it in the exception frame.  We also make xmon print the CFAR value in
its register dump code.

Rather than extend the pt_regs struct at this time, we steal the orig_gpr3
field, which is only used for system calls, and use it for the CFAR value
for all exceptions/interrupts other than system calls.  This means we
don't save the CFAR on system calls, which is not a great problem since
system calls tend not to happen unexpectedly, and also avoids adding the
overhead of reading the CFAR to the system call entry path.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/cputable.h      | 5 +++--
 arch/powerpc/include/asm/exception-64s.h | 9 +++++++++
 arch/powerpc/include/asm/paca.h          | 6 +++---
 arch/powerpc/include/asm/reg.h           | 1 +
 arch/powerpc/kernel/exceptions-64s.S     | 4 ++++
 arch/powerpc/xmon/xmon.c                 | 4 ++++
 6 files changed, 24 insertions(+), 5 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index a3e1a9e96a7..4efbfb3f325 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -180,6 +180,7 @@ extern const char *powerpc_base_platform;
 
 
 #define CPU_FTR_HVMODE_206		LONG_ASM_CONST(0x0000000800000000)
+#define CPU_FTR_CFAR			LONG_ASM_CONST(0x0000001000000000)
 #define CPU_FTR_IABR			LONG_ASM_CONST(0x0000002000000000)
 #define CPU_FTR_MMCRA			LONG_ASM_CONST(0x0000004000000000)
 #define CPU_FTR_CTRL			LONG_ASM_CONST(0x0000008000000000)
@@ -412,7 +413,7 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
 	    CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD | \
-	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB)
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_CFAR)
 #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_HVMODE_206 |\
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
@@ -420,7 +421,7 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
 	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
-	    CPU_FTR_ICSWX)
+	    CPU_FTR_ICSWX | CPU_FTR_CFAR)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 96ccef136ca..f5dfe3411f6 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -46,6 +46,7 @@
 #define EX_CCR		60
 #define EX_R3		64
 #define EX_LR		72
+#define EX_CFAR		80
 
 /*
  * We're short on space and time in the exception prolog, so we can't
@@ -66,6 +67,10 @@
 	std	r10,area+EX_R10(r13);					\
 	std	r11,area+EX_R11(r13);					\
 	std	r12,area+EX_R12(r13);					\
+	BEGIN_FTR_SECTION_NESTED(66);					\
+	mfspr	r10,SPRN_CFAR;						\
+	std	r10,area+EX_CFAR(r13);					\
+	END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66);		\
 	GET_SCRATCH0(r9);						\
 	std	r9,area+EX_R13(r13);					\
 	mfcr	r9
@@ -130,6 +135,10 @@
 	std	r9,GPR11(r1);						   \
 	std	r10,GPR12(r1);						   \
 	std	r11,GPR13(r1);						   \
+	BEGIN_FTR_SECTION_NESTED(66);					   \
+	ld	r10,area+EX_CFAR(r13);					   \
+	std	r10,ORIG_GPR3(r1);					   \
+	END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66);		   \
 	ld	r2,PACATOC(r13);	/* get kernel TOC into r2	*/ \
 	mflr	r9;			/* save LR in stackframe	*/ \
 	std	r9,_LINK(r1);						   \
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 65c13c48db4..74126765106 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -92,9 +92,9 @@ struct paca_struct {
 	 * Now, starting in cacheline 2, the exception save areas
 	 */
 	/* used for most interrupts/exceptions */
-	u64 exgen[10] __attribute__((aligned(0x80)));
-	u64 exmc[10];		/* used for machine checks */
-	u64 exslb[10];		/* used for SLB/segment table misses
+	u64 exgen[11] __attribute__((aligned(0x80)));
+	u64 exmc[11];		/* used for machine checks */
+	u64 exslb[11];		/* used for SLB/segment table misses
  				 * on the linear mapping */
 	/* SLB related definitions */
 	u16 vmalloc_sllp;
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 632e78e1444..fdec5933305 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -188,6 +188,7 @@
 
 #define SPRN_CTR	0x009	/* Count Register */
 #define SPRN_DSCR	0x11
+#define SPRN_CFAR	0x1c	/* Come From Address Register */
 #define SPRN_ACOP	0x1F	/* Available Coprocessor Register */
 #define SPRN_CTRLF	0x088
 #define SPRN_CTRLT	0x098
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 27ca8b7c600..0ec3b42717d 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -474,6 +474,10 @@ bad_stack:
 	std	r9,GPR11(r1)
 	std	r10,GPR12(r1)
 	std	r11,GPR13(r1)
+BEGIN_FTR_SECTION
+	ld	r10,EX_CFAR(r3)
+	std	r10,ORIG_GPR3(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	SAVE_8GPRS(14,r1)
 	SAVE_10GPRS(22,r1)
 	lhz	r12,PACA_TRAP_SAVE(r13)
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 60593ad861e..909804aaeeb 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1497,6 +1497,10 @@ static void prregs(struct pt_regs *fp)
 #endif
 	printf("pc  = ");
 	xmon_print_symbol(fp->nip, " ", "\n");
+	if (TRAP(fp) != 0xc00 && cpu_has_feature(CPU_FTR_CFAR)) {
+		printf("cfar= ");
+		xmon_print_symbol(fp->orig_gpr3, " ", "\n");
+	}
 	printf("lr  = ");
 	xmon_print_symbol(fp->link, " ", "\n");
 	printf("msr = "REG"   cr  = %.8lx\n", fp->msr, fp->ccr);
-- 
cgit v1.2.3-70-g09d2


From 104699c0ab473535793b5fea156adaf309afd29b Mon Sep 17 00:00:00 2001
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Date: Thu, 28 Apr 2011 05:07:23 +0000
Subject: powerpc: Convert old cpumask API into new one

Adapt new API.

Almost change is trivial. Most important change is the below line
because we plan to change task->cpus_allowed implementation.

-       ctx->cpus_allowed = current->cpus_allowed;

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/cputhreads.h        | 12 +++++------
 arch/powerpc/include/asm/kexec.h             |  2 +-
 arch/powerpc/kernel/crash.c                  | 32 ++++++++++++++--------------
 arch/powerpc/kernel/setup-common.c           |  4 ++--
 arch/powerpc/kernel/smp.c                    |  4 ++--
 arch/powerpc/kernel/traps.c                  |  2 +-
 arch/powerpc/mm/numa.c                       |  2 +-
 arch/powerpc/platforms/cell/beat_smp.c       |  2 +-
 arch/powerpc/platforms/cell/cbe_regs.c       | 11 +++++-----
 arch/powerpc/platforms/cell/smp.c            | 13 ++++++-----
 arch/powerpc/platforms/cell/spufs/sched.c    |  2 +-
 arch/powerpc/platforms/pseries/hotplug-cpu.c |  2 +-
 arch/powerpc/xmon/xmon.c                     | 16 +++++++-------
 13 files changed, 52 insertions(+), 52 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index f71bb4c118b..ce516e5eb0d 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -37,16 +37,16 @@ extern cpumask_t threads_core_mask;
  * This can typically be used for things like IPI for tlb invalidations
  * since those need to be done only once per core/TLB
  */
-static inline cpumask_t cpu_thread_mask_to_cores(cpumask_t threads)
+static inline cpumask_t cpu_thread_mask_to_cores(const struct cpumask *threads)
 {
 	cpumask_t	tmp, res;
 	int		i;
 
-	res = CPU_MASK_NONE;
+	cpumask_clear(&res);
 	for (i = 0; i < NR_CPUS; i += threads_per_core) {
-		cpus_shift_left(tmp, threads_core_mask, i);
-		if (cpus_intersects(threads, tmp))
-			cpu_set(i, res);
+		cpumask_shift_left(&tmp, &threads_core_mask, i);
+		if (cpumask_intersects(threads, &tmp))
+			cpumask_set_cpu(i, &res);
 	}
 	return res;
 }
@@ -58,7 +58,7 @@ static inline int cpu_nr_cores(void)
 
 static inline cpumask_t cpu_online_cores_map(void)
 {
-	return cpu_thread_mask_to_cores(cpu_online_map);
+	return cpu_thread_mask_to_cores(cpu_online_mask);
 }
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index f54408d995b..8a33698c61b 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -76,7 +76,7 @@ extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *));
 extern cpumask_t cpus_in_sr;
 static inline int kexec_sr_activated(int cpu)
 {
-	return cpu_isset(cpu,cpus_in_sr);
+	return cpumask_test_cpu(cpu, &cpus_in_sr);
 }
 
 struct kimage;
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 5b5e1f002a8..ccc2198e6b2 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -64,9 +64,9 @@ void crash_ipi_callback(struct pt_regs *regs)
 		return;
 
 	hard_irq_disable();
-	if (!cpu_isset(cpu, cpus_in_crash))
+	if (!cpumask_test_cpu(cpu, &cpus_in_crash))
 		crash_save_cpu(regs, cpu);
-	cpu_set(cpu, cpus_in_crash);
+	cpumask_set_cpu(cpu, &cpus_in_crash);
 
 	/*
 	 * Entered via soft-reset - could be the kdump
@@ -77,8 +77,8 @@ void crash_ipi_callback(struct pt_regs *regs)
 	 * Tell the kexec CPU that entered via soft-reset and ready
 	 * to go down.
 	 */
-	if (cpu_isset(cpu, cpus_in_sr)) {
-		cpu_clear(cpu, cpus_in_sr);
+	if (cpumask_test_cpu(cpu, &cpus_in_sr)) {
+		cpumask_clear_cpu(cpu, &cpus_in_sr);
 		atomic_inc(&enter_on_soft_reset);
 	}
 
@@ -87,7 +87,7 @@ void crash_ipi_callback(struct pt_regs *regs)
 	 * This barrier is needed to make sure that all CPUs are stopped.
 	 * If not, soft-reset will be invoked to bring other CPUs.
 	 */
-	while (!cpu_isset(crashing_cpu, cpus_in_crash))
+	while (!cpumask_test_cpu(crashing_cpu, &cpus_in_crash))
 		cpu_relax();
 
 	if (ppc_md.kexec_cpu_down)
@@ -109,7 +109,7 @@ static void crash_soft_reset_check(int cpu)
 {
 	unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */
 
-	cpu_clear(cpu, cpus_in_sr);
+	cpumask_clear_cpu(cpu, &cpus_in_sr);
 	while (atomic_read(&enter_on_soft_reset) != ncpus)
 		cpu_relax();
 }
@@ -132,7 +132,7 @@ static void crash_kexec_prepare_cpus(int cpu)
 	 */
 	printk(KERN_EMERG "Sending IPI to other cpus...\n");
 	msecs = 10000;
-	while ((cpus_weight(cpus_in_crash) < ncpus) && (--msecs > 0)) {
+	while ((cpumask_weight(&cpus_in_crash) < ncpus) && (--msecs > 0)) {
 		cpu_relax();
 		mdelay(1);
 	}
@@ -144,20 +144,20 @@ static void crash_kexec_prepare_cpus(int cpu)
 	 * user to do soft reset such that we get all.
 	 * Soft-reset will be used until better mechanism is implemented.
 	 */
-	if (cpus_weight(cpus_in_crash) < ncpus) {
+	if (cpumask_weight(&cpus_in_crash) < ncpus) {
 		printk(KERN_EMERG "done waiting: %d cpu(s) not responding\n",
-			ncpus - cpus_weight(cpus_in_crash));
+			ncpus - cpumask_weight(&cpus_in_crash));
 		printk(KERN_EMERG "Activate soft-reset to stop other cpu(s)\n");
-		cpus_in_sr = CPU_MASK_NONE;
+		cpumask_clear(&cpus_in_sr);
 		atomic_set(&enter_on_soft_reset, 0);
-		while (cpus_weight(cpus_in_crash) < ncpus)
+		while (cpumask_weight(&cpus_in_crash) < ncpus)
 			cpu_relax();
 	}
 	/*
 	 * Make sure all CPUs are entered via soft-reset if the kdump is
 	 * invoked using soft-reset.
 	 */
-	if (cpu_isset(cpu, cpus_in_sr))
+	if (cpumask_test_cpu(cpu, &cpus_in_sr))
 		crash_soft_reset_check(cpu);
 	/* Leave the IPI callback set */
 }
@@ -210,7 +210,7 @@ void crash_kexec_secondary(struct pt_regs *regs)
 			 * exited using 'x'(exit and recover) or
 			 * kexec_should_crash() failed for all running tasks.
 			 */
-			cpu_clear(cpu, cpus_in_sr);
+			cpumask_clear_cpu(cpu, &cpus_in_sr);
 			local_irq_restore(flags);
 			return;
 		}
@@ -224,7 +224,7 @@ void crash_kexec_secondary(struct pt_regs *regs)
 		 * then start kexec boot.
 		 */
 		crash_soft_reset_check(cpu);
-		cpu_set(crashing_cpu, cpus_in_crash);
+		cpumask_set_cpu(crashing_cpu, &cpus_in_crash);
 		if (ppc_md.kexec_cpu_down)
 			ppc_md.kexec_cpu_down(1, 0);
 		machine_kexec(kexec_crash_image);
@@ -253,7 +253,7 @@ static void crash_kexec_prepare_cpus(int cpu)
 
 void crash_kexec_secondary(struct pt_regs *regs)
 {
-	cpus_in_sr = CPU_MASK_NONE;
+	cpumask_clear(&cpus_in_sr);
 }
 #endif	/* CONFIG_SMP */
 
@@ -345,7 +345,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	crashing_cpu = smp_processor_id();
 	crash_save_cpu(regs, crashing_cpu);
 	crash_kexec_prepare_cpus(crashing_cpu);
-	cpu_set(crashing_cpu, cpus_in_crash);
+	cpumask_set_cpu(crashing_cpu, &cpus_in_crash);
 	crash_kexec_wait_realmode(crashing_cpu);
 
 	machine_kexec_mask_interrupts();
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 21f30cb6807..1475df6e403 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -381,7 +381,7 @@ static void __init cpu_init_thread_core_maps(int tpc)
 	int i;
 
 	threads_per_core = tpc;
-	threads_core_mask = CPU_MASK_NONE;
+	cpumask_clear(&threads_core_mask);
 
 	/* This implementation only supports power of 2 number of threads
 	 * for simplicity and performance
@@ -390,7 +390,7 @@ static void __init cpu_init_thread_core_maps(int tpc)
 	BUG_ON(tpc != (1 << threads_shift));
 
 	for (i = 0; i < tpc; i++)
-		cpu_set(i, threads_core_mask);
+		cpumask_set_cpu(i, &threads_core_mask);
 
 	printk(KERN_INFO "CPU maps initialized for %d thread%s per core\n",
 	       tpc, tpc > 1 ? "s" : "");
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index b6083f4f39b..87517ab6d36 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -513,7 +513,7 @@ int cpu_first_thread_of_core(int core)
 }
 EXPORT_SYMBOL_GPL(cpu_first_thread_of_core);
 
-/* Must be called when no change can occur to cpu_present_map,
+/* Must be called when no change can occur to cpu_present_mask,
  * i.e. during cpu online or offline.
  */
 static struct device_node *cpu_to_l2cache(int cpu)
@@ -614,7 +614,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 	 * se we pin us down to CPU 0 for a short while
 	 */
 	alloc_cpumask_var(&old_mask, GFP_NOWAIT);
-	cpumask_copy(old_mask, &current->cpus_allowed);
+	cpumask_copy(old_mask, tsk_cpus_allowed(current));
 	set_cpus_allowed_ptr(current, cpumask_of(boot_cpuid));
 	
 	if (smp_ops && smp_ops->setup_cpu)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 4a6a109b681..06b9d457d0a 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -221,7 +221,7 @@ void system_reset_exception(struct pt_regs *regs)
 	}
 
 #ifdef CONFIG_KEXEC
-	cpu_set(smp_processor_id(), cpus_in_sr);
+	cpumask_set_cpu(smp_processor_id(), &cpus_in_sr);
 #endif
 
 	die("System Reset", regs, SIGABRT);
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index e49b799b59a..2164006fe17 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1452,7 +1452,7 @@ int arch_update_cpu_topology(void)
 	unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	struct sys_device *sysdev;
 
-	for_each_cpu_mask(cpu, cpu_associativity_changes_mask) {
+	for_each_cpu(cpu,&cpu_associativity_changes_mask) {
 		vphn_get_associativity(cpu, associativity);
 		nid = associativity_to_nid(associativity);
 
diff --git a/arch/powerpc/platforms/cell/beat_smp.c b/arch/powerpc/platforms/cell/beat_smp.c
index 996df33165f..3e86acbb0fb 100644
--- a/arch/powerpc/platforms/cell/beat_smp.c
+++ b/arch/powerpc/platforms/cell/beat_smp.c
@@ -85,7 +85,7 @@ static void smp_beatic_message_pass(int target, int msg)
 
 static int __init smp_beatic_probe(void)
 {
-	return cpus_weight(cpu_possible_map);
+	return cpumask_weight(cpu_possible_mask);
 }
 
 static void __devinit smp_beatic_setup_cpu(int cpu)
diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c
index dbc338f187a..f3917e7a5b4 100644
--- a/arch/powerpc/platforms/cell/cbe_regs.c
+++ b/arch/powerpc/platforms/cell/cbe_regs.c
@@ -45,8 +45,8 @@ static struct cbe_thread_map
 	unsigned int cbe_id;
 } cbe_thread_map[NR_CPUS];
 
-static cpumask_t cbe_local_mask[MAX_CBE] = { [0 ... MAX_CBE-1] = CPU_MASK_NONE };
-static cpumask_t cbe_first_online_cpu = CPU_MASK_NONE;
+static cpumask_t cbe_local_mask[MAX_CBE] = { [0 ... MAX_CBE-1] = {CPU_BITS_NONE} };
+static cpumask_t cbe_first_online_cpu = { CPU_BITS_NONE };
 
 static struct cbe_regs_map *cbe_find_map(struct device_node *np)
 {
@@ -159,7 +159,8 @@ EXPORT_SYMBOL_GPL(cbe_cpu_to_node);
 
 u32 cbe_node_to_cpu(int node)
 {
-	return find_first_bit( (unsigned long *) &cbe_local_mask[node], sizeof(cpumask_t));
+	return cpumask_first(&cbe_local_mask[node]);
+
 }
 EXPORT_SYMBOL_GPL(cbe_node_to_cpu);
 
@@ -268,9 +269,9 @@ void __init cbe_regs_init(void)
 				thread->regs = map;
 				thread->cbe_id = cbe_id;
 				map->be_node = thread->be_node;
-				cpu_set(i, cbe_local_mask[cbe_id]);
+				cpumask_set_cpu(i, &cbe_local_mask[cbe_id]);
 				if(thread->thread_id == 0)
-					cpu_set(i, cbe_first_online_cpu);
+					cpumask_set_cpu(i, &cbe_first_online_cpu);
 			}
 		}
 
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
index 03d638e2f44..a2161b91b0b 100644
--- a/arch/powerpc/platforms/cell/smp.c
+++ b/arch/powerpc/platforms/cell/smp.c
@@ -77,7 +77,7 @@ static inline int __devinit smp_startup_cpu(unsigned int lcpu)
 	unsigned int pcpu;
 	int start_cpu;
 
-	if (cpu_isset(lcpu, of_spin_map))
+	if (cpumask_test_cpu(lcpu, &of_spin_map))
 		/* Already started by OF and sitting in spin loop */
 		return 1;
 
@@ -123,7 +123,7 @@ static int __init smp_iic_probe(void)
 {
 	iic_request_IPIs();
 
-	return cpus_weight(cpu_possible_map);
+	return cpumask_weight(cpu_possible_mask);
 }
 
 static void __devinit smp_cell_setup_cpu(int cpu)
@@ -188,13 +188,12 @@ void __init smp_init_cell(void)
 	if (cpu_has_feature(CPU_FTR_SMT)) {
 		for_each_present_cpu(i) {
 			if (cpu_thread_in_core(i) == 0)
-				cpu_set(i, of_spin_map);
+				cpumask_set_cpu(i, &of_spin_map);
 		}
-	} else {
-		of_spin_map = cpu_present_map;
-	}
+	} else
+		cpumask_copy(&of_spin_map, cpu_present_mask);
 
-	cpu_clear(boot_cpuid, of_spin_map);
+	cpumask_clear_cpu(boot_cpuid, &of_spin_map);
 
 	/* Non-lpar has additional take/give timebase */
 	if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 65203857b0c..32cb4e66d2c 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -141,7 +141,7 @@ void __spu_update_sched_info(struct spu_context *ctx)
 	 * runqueue. The context will be rescheduled on the proper node
 	 * if it is timesliced or preempted.
 	 */
-	ctx->cpus_allowed = current->cpus_allowed;
+	cpumask_copy(&ctx->cpus_allowed, tsk_cpus_allowed(current));
 
 	/* Save the current cpu id for spu interrupt routing. */
 	ctx->last_ran = raw_smp_processor_id();
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index ae6c27df4dc..46f13a3c5d0 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -281,7 +281,7 @@ static int pseries_add_processor(struct device_node *np)
 	}
 
 	for_each_cpu(cpu, tmp) {
-		BUG_ON(cpumask_test_cpu(cpu, cpu_present_mask));
+		BUG_ON(cpu_present(cpu));
 		set_cpu_present(cpu, true);
 		set_hard_smp_processor_id(cpu, *intserv++);
 	}
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 909804aaeeb..91309c5c00d 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -334,7 +334,7 @@ static void release_output_lock(void)
 
 int cpus_are_in_xmon(void)
 {
-	return !cpus_empty(cpus_in_xmon);
+	return !cpumask_empty(&cpus_in_xmon);
 }
 #endif
 
@@ -373,7 +373,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 
 #ifdef CONFIG_SMP
 	cpu = smp_processor_id();
-	if (cpu_isset(cpu, cpus_in_xmon)) {
+	if (cpumask_test_cpu(cpu, &cpus_in_xmon)) {
 		get_output_lock();
 		excprint(regs);
 		printf("cpu 0x%x: Exception %lx %s in xmon, "
@@ -396,7 +396,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 	}
 
 	xmon_fault_jmp[cpu] = recurse_jmp;
-	cpu_set(cpu, cpus_in_xmon);
+	cpumask_set_cpu(cpu, &cpus_in_xmon);
 
 	bp = NULL;
 	if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT))
@@ -440,7 +440,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 			smp_send_debugger_break(MSG_ALL_BUT_SELF);
 			/* wait for other cpus to come in */
 			for (timeout = 100000000; timeout != 0; --timeout) {
-				if (cpus_weight(cpus_in_xmon) >= ncpus)
+				if (cpumask_weight(&cpus_in_xmon) >= ncpus)
 					break;
 				barrier();
 			}
@@ -484,7 +484,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 		}
 	}
  leave:
-	cpu_clear(cpu, cpus_in_xmon);
+	cpumask_clear_cpu(cpu, &cpus_in_xmon);
 	xmon_fault_jmp[cpu] = NULL;
 #else
 	/* UP is simple... */
@@ -630,7 +630,7 @@ static int xmon_iabr_match(struct pt_regs *regs)
 static int xmon_ipi(struct pt_regs *regs)
 {
 #ifdef CONFIG_SMP
-	if (in_xmon && !cpu_isset(smp_processor_id(), cpus_in_xmon))
+	if (in_xmon && !cpumask_test_cpu(smp_processor_id(), &cpus_in_xmon))
 		xmon_core(regs, 1);
 #endif
 	return 0;
@@ -976,7 +976,7 @@ static int cpu_cmd(void)
 		printf("cpus stopped:");
 		count = 0;
 		for (cpu = 0; cpu < NR_CPUS; ++cpu) {
-			if (cpu_isset(cpu, cpus_in_xmon)) {
+			if (cpumask_test_cpu(cpu, &cpus_in_xmon)) {
 				if (count == 0)
 					printf(" %x", cpu);
 				++count;
@@ -992,7 +992,7 @@ static int cpu_cmd(void)
 		return 0;
 	}
 	/* try to switch to cpu specified */
-	if (!cpu_isset(cpu, cpus_in_xmon)) {
+	if (!cpumask_test_cpu(cpu, &cpus_in_xmon)) {
 		printf("cpu 0x%x isn't in xmon\n", cpu);
 		return 0;
 	}
-- 
cgit v1.2.3-70-g09d2


From 9ee820fa005254dfc816330f6654f14dcb2beee1 Mon Sep 17 00:00:00 2001
From: Brian King <brking@linux.vnet.ibm.com>
Date: Wed, 4 May 2011 16:01:20 +1000
Subject: powerpc/pseries: Add page coalescing support

Adds support for page coalescing, which is a feature on IBM Power servers
which allows for coalescing identical pages between logical partitions.
Hint text pages as coalesce candidates, since they are the most likely
pages to be able to be coalesced between partitions. This patch also
exports some page coalescing statistics available from firmware via
lparcfg.

[BenH: Moved a couple of things around to fix compile problems]

Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/firmware.h         |  3 +-
 arch/powerpc/include/asm/hvcall.h           | 12 +++++++
 arch/powerpc/include/asm/pSeries_reconfig.h |  5 +++
 arch/powerpc/kernel/lparcfg.c               | 53 ++++++++++++++---------------
 arch/powerpc/kernel/prom_init.c             |  4 ++-
 arch/powerpc/kernel/rtas.c                  |  2 ++
 arch/powerpc/platforms/pseries/lpar.c       | 46 +++++++++++++++++++++++++
 arch/powerpc/platforms/pseries/setup.c      | 11 ++++++
 8 files changed, 106 insertions(+), 30 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 4ef662e4a31..3a6c586c4e4 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -47,6 +47,7 @@
 #define FW_FEATURE_BEAT		ASM_CONST(0x0000000001000000)
 #define FW_FEATURE_CMO		ASM_CONST(0x0000000002000000)
 #define FW_FEATURE_VPHN		ASM_CONST(0x0000000004000000)
+#define FW_FEATURE_XCMO		ASM_CONST(0x0000000008000000)
 
 #ifndef __ASSEMBLY__
 
@@ -60,7 +61,7 @@ enum {
 		FW_FEATURE_VIO | FW_FEATURE_RDMA | FW_FEATURE_LLAN |
 		FW_FEATURE_BULK_REMOVE | FW_FEATURE_XDABR |
 		FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
-		FW_FEATURE_CMO | FW_FEATURE_VPHN,
+		FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
 	FW_FEATURE_ISERIES_POSSIBLE = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,
 	FW_FEATURE_ISERIES_ALWAYS = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 8edec710cc6..852b8c1c09d 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -102,6 +102,7 @@
 #define H_ANDCOND		(1UL<<(63-33))
 #define H_ICACHE_INVALIDATE	(1UL<<(63-40))	/* icbi, etc.  (ignored for IO pages) */
 #define H_ICACHE_SYNCHRONIZE	(1UL<<(63-41))	/* dcbst, icbi, etc (ignored for IO pages */
+#define H_COALESCE_CAND	(1UL<<(63-42))	/* page is a good candidate for coalescing */
 #define H_ZERO_PAGE		(1UL<<(63-48))	/* zero the page before mapping (ignored for IO pages) */
 #define H_COPY_PAGE		(1UL<<(63-49))
 #define H_N			(1UL<<(63-61))
@@ -234,6 +235,7 @@
 #define H_GET_MPP		0x2D4
 #define H_HOME_NODE_ASSOCIATIVITY 0x2EC
 #define H_BEST_ENERGY		0x2F4
+#define H_GET_MPP_X		0x314
 #define MAX_HCALL_OPCODE	H_BEST_ENERGY
 
 #ifndef __ASSEMBLY__
@@ -312,6 +314,16 @@ struct hvcall_mpp_data {
 
 int h_get_mpp(struct hvcall_mpp_data *);
 
+struct hvcall_mpp_x_data {
+	unsigned long coalesced_bytes;
+	unsigned long pool_coalesced_bytes;
+	unsigned long pool_purr_cycles;
+	unsigned long pool_spurr_cycles;
+	unsigned long reserved[3];
+};
+
+int h_get_mpp_x(struct hvcall_mpp_x_data *mpp_x_data);
+
 #ifdef CONFIG_PPC_PSERIES
 extern int CMO_PrPSP;
 extern int CMO_SecPSP;
diff --git a/arch/powerpc/include/asm/pSeries_reconfig.h b/arch/powerpc/include/asm/pSeries_reconfig.h
index d4b4bfa26fb..89d2f99c1bf 100644
--- a/arch/powerpc/include/asm/pSeries_reconfig.h
+++ b/arch/powerpc/include/asm/pSeries_reconfig.h
@@ -18,13 +18,18 @@
 extern int pSeries_reconfig_notifier_register(struct notifier_block *);
 extern void pSeries_reconfig_notifier_unregister(struct notifier_block *);
 extern struct blocking_notifier_head pSeries_reconfig_chain;
+/* Not the best place to put this, will be fixed when we move some
+ * of the rtas suspend-me stuff to pseries */
+extern void pSeries_coalesce_init(void);
 #else /* !CONFIG_PPC_PSERIES */
 static inline int pSeries_reconfig_notifier_register(struct notifier_block *nb)
 {
 	return 0;
 }
 static inline void pSeries_reconfig_notifier_unregister(struct notifier_block *nb) { }
+static inline void pSeries_coalesce_init(void) { }
 #endif /* CONFIG_PPC_PSERIES */
 
+
 #endif /* __KERNEL__ */
 #endif /* _PPC64_PSERIES_RECONFIG_H */
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index 301db65f05a..84daabe2fcb 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -132,34 +132,6 @@ static int iseries_lparcfg_data(struct seq_file *m, void *v)
 /*
  * Methods used to fetch LPAR data when running on a pSeries platform.
  */
-/**
- * h_get_mpp
- * H_GET_MPP hcall returns info in 7 parms
- */
-int h_get_mpp(struct hvcall_mpp_data *mpp_data)
-{
-	int rc;
-	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
-
-	rc = plpar_hcall9(H_GET_MPP, retbuf);
-
-	mpp_data->entitled_mem = retbuf[0];
-	mpp_data->mapped_mem = retbuf[1];
-
-	mpp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff;
-	mpp_data->pool_num = retbuf[2] & 0xffff;
-
-	mpp_data->mem_weight = (retbuf[3] >> 7 * 8) & 0xff;
-	mpp_data->unallocated_mem_weight = (retbuf[3] >> 6 * 8) & 0xff;
-	mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffff;
-
-	mpp_data->pool_size = retbuf[4];
-	mpp_data->loan_request = retbuf[5];
-	mpp_data->backing_mem = retbuf[6];
-
-	return rc;
-}
-EXPORT_SYMBOL(h_get_mpp);
 
 struct hvcall_ppp_data {
 	u64	entitlement;
@@ -345,6 +317,30 @@ static void parse_mpp_data(struct seq_file *m)
 	seq_printf(m, "backing_memory=%ld bytes\n", mpp_data.backing_mem);
 }
 
+/**
+ * parse_mpp_x_data
+ * Parse out data returned from h_get_mpp_x
+ */
+static void parse_mpp_x_data(struct seq_file *m)
+{
+	struct hvcall_mpp_x_data mpp_x_data;
+
+	if (!firmware_has_feature(FW_FEATURE_XCMO))
+		return;
+	if (h_get_mpp_x(&mpp_x_data))
+		return;
+
+	seq_printf(m, "coalesced_bytes=%ld\n", mpp_x_data.coalesced_bytes);
+
+	if (mpp_x_data.pool_coalesced_bytes)
+		seq_printf(m, "pool_coalesced_bytes=%ld\n",
+			   mpp_x_data.pool_coalesced_bytes);
+	if (mpp_x_data.pool_purr_cycles)
+		seq_printf(m, "coalesce_pool_purr=%ld\n", mpp_x_data.pool_purr_cycles);
+	if (mpp_x_data.pool_spurr_cycles)
+		seq_printf(m, "coalesce_pool_spurr=%ld\n", mpp_x_data.pool_spurr_cycles);
+}
+
 #define SPLPAR_CHARACTERISTICS_TOKEN 20
 #define SPLPAR_MAXLENGTH 1026*(sizeof(char))
 
@@ -520,6 +516,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 		parse_system_parameter_string(m);
 		parse_ppp_data(m);
 		parse_mpp_data(m);
+		parse_mpp_x_data(m);
 		pseries_cmo_data(m);
 		splpar_dispatch_data(m);
 
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 7839bd7bfd1..c016033ba78 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -700,8 +700,10 @@ static void __init early_cmdline_parse(void)
 #endif /* CONFIG_PCI_MSI */
 #ifdef CONFIG_PPC_SMLPAR
 #define OV5_CMO			0x80	/* Cooperative Memory Overcommitment */
+#define OV5_XCMO			0x40	/* Page Coalescing */
 #else
 #define OV5_CMO			0x00
+#define OV5_XCMO			0x00
 #endif
 #define OV5_TYPE1_AFFINITY	0x80	/* Type 1 NUMA affinity */
 
@@ -756,7 +758,7 @@ static unsigned char ibm_architecture_vec[] = {
 	OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY |
 	OV5_DONATE_DEDICATE_CPU | OV5_MSI,
 	0,
-	OV5_CMO,
+	OV5_CMO | OV5_XCMO,
 	OV5_TYPE1_AFFINITY,
 	0,
 	0,
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index f48446635c8..271ff6318ed 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -42,6 +42,7 @@
 #include <asm/time.h>
 #include <asm/mmu.h>
 #include <asm/topology.h>
+#include <asm/pSeries_reconfig.h>
 
 struct rtas_t rtas = {
 	.lock = __ARCH_SPIN_LOCK_UNLOCKED
@@ -731,6 +732,7 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w
 
 	atomic_set(&data->error, rc);
 	start_topology_update();
+	pSeries_coalesce_init();
 
 	if (wake_when_done) {
 		atomic_set(&data->done, 1);
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 6f0ed3aac77..39e6e0a7b2f 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -329,6 +329,8 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 	/* Make pHyp happy */
 	if ((rflags & _PAGE_NO_CACHE) & !(rflags & _PAGE_WRITETHRU))
 		hpte_r &= ~_PAGE_COHERENT;
+	if (firmware_has_feature(FW_FEATURE_XCMO) && !(hpte_r & HPTE_R_N))
+		flags |= H_COALESCE_CAND;
 
 	lpar_rc = plpar_pte_enter(flags, hpte_group, hpte_v, hpte_r, &slot);
 	if (unlikely(lpar_rc == H_PTEG_FULL)) {
@@ -771,3 +773,47 @@ out:
 	local_irq_restore(flags);
 }
 #endif
+
+/**
+ * h_get_mpp
+ * H_GET_MPP hcall returns info in 7 parms
+ */
+int h_get_mpp(struct hvcall_mpp_data *mpp_data)
+{
+	int rc;
+	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+
+	rc = plpar_hcall9(H_GET_MPP, retbuf);
+
+	mpp_data->entitled_mem = retbuf[0];
+	mpp_data->mapped_mem = retbuf[1];
+
+	mpp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff;
+	mpp_data->pool_num = retbuf[2] & 0xffff;
+
+	mpp_data->mem_weight = (retbuf[3] >> 7 * 8) & 0xff;
+	mpp_data->unallocated_mem_weight = (retbuf[3] >> 6 * 8) & 0xff;
+	mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffff;
+
+	mpp_data->pool_size = retbuf[4];
+	mpp_data->loan_request = retbuf[5];
+	mpp_data->backing_mem = retbuf[6];
+
+	return rc;
+}
+EXPORT_SYMBOL(h_get_mpp);
+
+int h_get_mpp_x(struct hvcall_mpp_x_data *mpp_x_data)
+{
+	int rc;
+	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = { 0 };
+
+	rc = plpar_hcall9(H_GET_MPP_X, retbuf);
+
+	mpp_x_data->coalesced_bytes = retbuf[0];
+	mpp_x_data->pool_coalesced_bytes = retbuf[1];
+	mpp_x_data->pool_purr_cycles = retbuf[2];
+	mpp_x_data->pool_spurr_cycles = retbuf[3];
+
+	return rc;
+}
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index ab73ad2ff59..1689adccc6d 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -405,6 +405,16 @@ static int pseries_set_xdabr(unsigned long dabr)
 #define CMO_CHARACTERISTICS_TOKEN 44
 #define CMO_MAXLENGTH 1026
 
+void pSeries_coalesce_init(void)
+{
+	struct hvcall_mpp_x_data mpp_x_data;
+
+	if (firmware_has_feature(FW_FEATURE_CMO) && !h_get_mpp_x(&mpp_x_data))
+		powerpc_firmware_features |= FW_FEATURE_XCMO;
+	else
+		powerpc_firmware_features &= ~FW_FEATURE_XCMO;
+}
+
 /**
  * fw_cmo_feature_init - FW_FEATURE_CMO is not stored in ibm,hypertas-functions,
  * handle that here. (Stolen from parse_system_parameter_string)
@@ -474,6 +484,7 @@ void pSeries_cmo_feature_init(void)
 		pr_debug("CMO enabled, PrPSP=%d, SecPSP=%d\n", CMO_PrPSP,
 		         CMO_SecPSP);
 		powerpc_firmware_features |= FW_FEATURE_CMO;
+		pSeries_coalesce_init();
 	} else
 		pr_debug("CMO not enabled, PrPSP=%d, SecPSP=%d\n", CMO_PrPSP,
 		         CMO_SecPSP);
-- 
cgit v1.2.3-70-g09d2


From 4cb4638079a487627232ffee5b48ca19c127aed8 Mon Sep 17 00:00:00 2001
From: "Tseng-Hui (Frank) Lin" <thlin@linux.vnet.ibm.com>
Date: Tue, 3 May 2011 18:28:43 +0000
Subject: powerpc/pseries: Add RTAS event log v6 definition

This patch adds definitions of non-IBM specific v6 extended log
definitions to rtas.h.

Signed-off-by: Tseng-Hui (Frank) Lin <tsenglin@us.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/rtas.h | 45 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 44 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 9a1193e30f2..58625d1e780 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -158,7 +158,50 @@ struct rtas_error_log {
 	unsigned long target:4;			/* Target of failed operation */
 	unsigned long type:8;			/* General event or error*/
 	unsigned long extended_log_length:32;	/* length in bytes */
-	unsigned char buffer[1];
+	unsigned char buffer[1];		/* Start of extended log */
+						/* Variable length.      */
+};
+
+#define RTAS_V6EXT_LOG_FORMAT_EVENT_LOG	14
+
+#define RTAS_V6EXT_COMPANY_ID_IBM	(('I' << 24) | ('B' << 16) | ('M' << 8))
+
+/* RTAS general extended event log, Version 6. The extended log starts
+ * from "buffer" field of struct rtas_error_log defined above.
+ */
+struct rtas_ext_event_log_v6 {
+	/* Byte 0 */
+	uint32_t log_valid:1;		/* 1:Log valid */
+	uint32_t unrecoverable_error:1;	/* 1:Unrecoverable error */
+	uint32_t recoverable_error:1;	/* 1:recoverable (correctable	*/
+					/*   or successfully retried)	*/
+	uint32_t degraded_operation:1;	/* 1:Unrecoverable err, bypassed*/
+					/*   - degraded operation (e.g.	*/
+					/*   CPU or mem taken off-line)	*/
+	uint32_t predictive_error:1;
+	uint32_t new_log:1;		/* 1:"New" log (Always 1 for	*/
+					/*   data returned from RTAS	*/
+	uint32_t big_endian:1;		/* 1: Big endian */
+	uint32_t :1;			/* reserved */
+	/* Byte 1 */
+	uint32_t :8;			/* reserved */
+	/* Byte 2 */
+	uint32_t powerpc_format:1;	/* Set to 1 (indicating log is	*/
+					/* in PowerPC format		*/
+	uint32_t :3;			/* reserved */
+	uint32_t log_format:4;		/* Log format indicator. Define	*/
+					/* format used for byte 12-2047	*/
+	/* Byte 3 */
+	uint32_t :8;			/* reserved */
+	/* Byte 4-11 */
+	uint8_t reserved[8];		/* reserved */
+	/* Byte 12-15 */
+	uint32_t company_id;		/* Company ID of the company	*/
+					/* that defines the format for	*/
+					/* the vendor specific log type	*/
+	/* Byte 16-end of log */
+	uint8_t vendor_log[1];		/* Start of vendor specific log	*/
+					/* Variable length.		*/
 };
 
 /*
-- 
cgit v1.2.3-70-g09d2


From 77eafe101a65b609b0693ee4eda381f60a4a5bab Mon Sep 17 00:00:00 2001
From: "Tseng-Hui (Frank) Lin" <thlin@linux.vnet.ibm.com>
Date: Thu, 5 May 2011 12:32:48 +0000
Subject: powerpc/pseries: Add support for IO event interrupts

This patch adds support for handling IO Event interrupts which come
through at the /event-sources/ibm,io-events device tree node.

The interrupts come through ibm,io-events device tree node are generated
by the firmware to report IO events. The firmware uses the same interrupt
to report multiple types of events for multiple devices. Each device may
have its own event handler. This patch implements a plateform interrupt
handler that is triggered by the IO event interrupts come through
ibm,io-events device tree node, pull in the IO events from RTAS and call
device event handlers registered in the notifier list.

Device event handlers are expected to use atomic_notifier_chain_register()
and atomic_notifier_chain_unregister() to register/unregister their
event handler in pseries_ioei_notifier_list list with IO event interrupt.
Device event handlers are responsible to identify if the event belongs
to the device event handler. The device event handle should return NOTIFY_OK
after the event is handled if the event belongs to the device event handler,
or NOTIFY_DONE otherwise.

Signed-off-by: Tseng-Hui (Frank) Lin <thlin@us.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/io_event_irq.h       |  54 ++++++
 arch/powerpc/platforms/pseries/Kconfig        |  18 ++
 arch/powerpc/platforms/pseries/Makefile       |   1 +
 arch/powerpc/platforms/pseries/io_event_irq.c | 231 ++++++++++++++++++++++++++
 4 files changed, 304 insertions(+)
 create mode 100644 arch/powerpc/include/asm/io_event_irq.h
 create mode 100644 arch/powerpc/platforms/pseries/io_event_irq.c

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/io_event_irq.h b/arch/powerpc/include/asm/io_event_irq.h
new file mode 100644
index 00000000000..b1a9a1be3c2
--- /dev/null
+++ b/arch/powerpc/include/asm/io_event_irq.h
@@ -0,0 +1,54 @@
+/*
+ * Copyright 2010, 2011 Mark Nelson and Tseng-Hui (Frank) Lin, IBM Corporation
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ASM_POWERPC_IO_EVENT_IRQ_H
+#define _ASM_POWERPC_IO_EVENT_IRQ_H
+
+#include <linux/types.h>
+#include <linux/notifier.h>
+
+#define PSERIES_IOEI_RPC_MAX_LEN 216
+
+#define PSERIES_IOEI_TYPE_ERR_DETECTED		0x01
+#define PSERIES_IOEI_TYPE_ERR_RECOVERED		0x02
+#define PSERIES_IOEI_TYPE_EVENT			0x03
+#define PSERIES_IOEI_TYPE_RPC_PASS_THRU		0x04
+
+#define PSERIES_IOEI_SUBTYPE_NOT_APP		0x00
+#define PSERIES_IOEI_SUBTYPE_REBALANCE_REQ	0x01
+#define PSERIES_IOEI_SUBTYPE_NODE_ONLINE	0x03
+#define PSERIES_IOEI_SUBTYPE_NODE_OFFLINE	0x04
+#define PSERIES_IOEI_SUBTYPE_DUMP_SIZE_CHANGE	0x05
+#define PSERIES_IOEI_SUBTYPE_TORRENT_IRV_UPDATE	0x06
+#define PSERIES_IOEI_SUBTYPE_TORRENT_HFI_CFGED	0x07
+
+#define PSERIES_IOEI_SCOPE_NOT_APP		0x00
+#define PSERIES_IOEI_SCOPE_RIO_HUB		0x36
+#define PSERIES_IOEI_SCOPE_RIO_BRIDGE		0x37
+#define PSERIES_IOEI_SCOPE_PHB			0x38
+#define PSERIES_IOEI_SCOPE_EADS_GLOBAL		0x39
+#define PSERIES_IOEI_SCOPE_EADS_SLOT		0x3A
+#define PSERIES_IOEI_SCOPE_TORRENT_HUB		0x3B
+#define PSERIES_IOEI_SCOPE_SERVICE_PROC		0x51
+
+/* Platform Event Log Format, Version 6, data portition of IO event section */
+struct pseries_io_event {
+	uint8_t event_type;		/* 0x00 IO-Event Type		*/
+	uint8_t rpc_data_len;		/* 0x01 RPC data length		*/
+	uint8_t scope;			/* 0x02 Error/Event Scope	*/
+	uint8_t event_subtype;		/* 0x03 I/O-Event Sub-Type	*/
+	uint32_t drc_index;		/* 0x04 DRC Index		*/
+	uint8_t rpc_data[PSERIES_IOEI_RPC_MAX_LEN];
+					/* 0x08 RPC Data (0-216 bytes,	*/
+					/* padded to 4 bytes alignment)	*/
+};
+
+extern struct atomic_notifier_head pseries_ioei_notifier_list;
+
+#endif /* _ASM_POWERPC_IO_EVENT_IRQ_H */
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index b0449229836..71af4c5d6c0 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -50,6 +50,24 @@ config SCANLOG
 	tristate "Scanlog dump interface"
 	depends on RTAS_PROC && PPC_PSERIES
 
+config IO_EVENT_IRQ
+	bool "IO Event Interrupt support"
+	depends on PPC_PSERIES
+	default y
+	help
+	  Select this option, if you want to enable support for IO Event
+	  interrupts. IO event interrupt is a mechanism provided by RTAS
+	  to return information about hardware error and non-error events
+	  which may need OS attention. RTAS returns events for multiple
+	  event types and scopes. Device drivers can register their handlers
+	  to receive events.
+
+	  This option will only enable the IO event platform code. You
+	  will still need to enable or compile the actual drivers
+	  that use this infrastruture to handle IO event interrupts.
+
+	  Say Y if you are unsure.
+
 config LPARCFG
 	bool "LPAR Configuration Data"
 	depends on PPC_PSERIES || PPC_ISERIES
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 4cfefbaccd5..3556e402cbf 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -21,6 +21,7 @@ obj-$(CONFIG_HCALL_STATS)	+= hvCall_inst.o
 obj-$(CONFIG_PHYP_DUMP)		+= phyp_dump.o
 obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_DTL)		+= dtl.o
+obj-$(CONFIG_IO_EVENT_IRQ)	+= io_event_irq.o
 
 ifeq ($(CONFIG_PPC_PSERIES),y)
 obj-$(CONFIG_SUSPEND)		+= suspend.o
diff --git a/arch/powerpc/platforms/pseries/io_event_irq.c b/arch/powerpc/platforms/pseries/io_event_irq.c
new file mode 100644
index 00000000000..c829e6067d5
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/io_event_irq.c
@@ -0,0 +1,231 @@
+/*
+ * Copyright 2010 2011 Mark Nelson and Tseng-Hui (Frank) Lin, IBM Corporation
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/list.h>
+#include <linux/notifier.h>
+
+#include <asm/machdep.h>
+#include <asm/rtas.h>
+#include <asm/irq.h>
+#include <asm/io_event_irq.h>
+
+#include "pseries.h"
+
+/*
+ * IO event interrupt is a mechanism provided by RTAS to return
+ * information about hardware error and non-error events. Device
+ * drivers can register their event handlers to receive events.
+ * Device drivers are expected to use atomic_notifier_chain_register()
+ * and atomic_notifier_chain_unregister() to register and unregister
+ * their event handlers. Since multiple IO event types and scopes
+ * share an IO event interrupt, the event handlers are called one
+ * by one until the IO event is claimed by one of the handlers.
+ * The event handlers are expected to return NOTIFY_OK if the
+ * event is handled by the event handler or NOTIFY_DONE if the
+ * event does not belong to the handler.
+ *
+ * Usage:
+ *
+ * Notifier function:
+ * #include <asm/io_event_irq.h>
+ * int event_handler(struct notifier_block *nb, unsigned long val, void *data) {
+ * 	p = (struct pseries_io_event_sect_data *) data;
+ * 	if (! is_my_event(p->scope, p->event_type)) return NOTIFY_DONE;
+ * 		:
+ * 		:
+ * 	return NOTIFY_OK;
+ * }
+ * struct notifier_block event_nb = {
+ * 	.notifier_call = event_handler,
+ * }
+ *
+ * Registration:
+ * atomic_notifier_chain_register(&pseries_ioei_notifier_list, &event_nb);
+ *
+ * Unregistration:
+ * atomic_notifier_chain_unregister(&pseries_ioei_notifier_list, &event_nb);
+ */
+
+ATOMIC_NOTIFIER_HEAD(pseries_ioei_notifier_list);
+EXPORT_SYMBOL_GPL(pseries_ioei_notifier_list);
+
+static int ioei_check_exception_token;
+
+/* pSeries event log format */
+
+/* Two bytes ASCII section IDs */
+#define PSERIES_ELOG_SECT_ID_PRIV_HDR		(('P' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_USER_HDR		(('U' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_PRIMARY_SRC	(('P' << 8) | 'S')
+#define PSERIES_ELOG_SECT_ID_EXTENDED_UH	(('E' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_FAILING_MTMS	(('M' << 8) | 'T')
+#define PSERIES_ELOG_SECT_ID_SECONDARY_SRC	(('S' << 8) | 'S')
+#define PSERIES_ELOG_SECT_ID_DUMP_LOCATOR	(('D' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_FW_ERROR		(('S' << 8) | 'W')
+#define PSERIES_ELOG_SECT_ID_IMPACT_PART_ID	(('L' << 8) | 'P')
+#define PSERIES_ELOG_SECT_ID_LOGIC_RESOURCE_ID	(('L' << 8) | 'R')
+#define PSERIES_ELOG_SECT_ID_HMC_ID		(('H' << 8) | 'M')
+#define PSERIES_ELOG_SECT_ID_EPOW		(('E' << 8) | 'P')
+#define PSERIES_ELOG_SECT_ID_IO_EVENT		(('I' << 8) | 'E')
+#define PSERIES_ELOG_SECT_ID_MANUFACT_INFO	(('M' << 8) | 'I')
+#define PSERIES_ELOG_SECT_ID_CALL_HOME		(('C' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_USER_DEF		(('U' << 8) | 'D')
+
+/* Vendor specific Platform Event Log Format, Version 6, section header */
+struct pseries_elog_section {
+	uint16_t id;			/* 0x00 2-byte ASCII section ID	*/
+	uint16_t length;		/* 0x02 Section length in bytes	*/
+	uint8_t version;		/* 0x04 Section version		*/
+	uint8_t subtype;		/* 0x05 Section subtype		*/
+	uint16_t creator_component;	/* 0x06 Creator component ID	*/
+	uint8_t data[];			/* 0x08 Start of section data	*/
+};
+
+static char ioei_rtas_buf[RTAS_DATA_BUF_SIZE] __cacheline_aligned;
+
+/**
+ * Find data portion of a specific section in RTAS extended event log.
+ * @elog: RTAS error/event log.
+ * @sect_id: secsion ID.
+ *
+ * Return:
+ *	pointer to the section data of the specified section
+ *	NULL if not found
+ */
+static struct pseries_elog_section *find_xelog_section(struct rtas_error_log *elog,
+						       uint16_t sect_id)
+{
+	struct rtas_ext_event_log_v6 *xelog =
+		(struct rtas_ext_event_log_v6 *) elog->buffer;
+	struct pseries_elog_section *sect;
+	unsigned char *p, *log_end;
+
+	/* Check that we understand the format */
+	if (elog->extended_log_length < sizeof(struct rtas_ext_event_log_v6) ||
+	    xelog->log_format != RTAS_V6EXT_LOG_FORMAT_EVENT_LOG ||
+	    xelog->company_id != RTAS_V6EXT_COMPANY_ID_IBM)
+		return NULL;
+
+	log_end = elog->buffer + elog->extended_log_length;
+	p = xelog->vendor_log;
+	while (p < log_end) {
+		sect = (struct pseries_elog_section *)p;
+		if (sect->id == sect_id)
+			return sect;
+		p += sect->length;
+	}
+	return NULL;
+}
+
+/**
+ * Find the data portion of an IO Event section from event log.
+ * @elog: RTAS error/event log.
+ *
+ * Return:
+ * 	pointer to a valid IO event section data. NULL if not found.
+ */
+static struct pseries_io_event * ioei_find_event(struct rtas_error_log *elog)
+{
+	struct pseries_elog_section *sect;
+
+	/* We should only ever get called for io-event interrupts, but if
+	 * we do get called for another type then something went wrong so
+	 * make some noise about it.
+	 * RTAS_TYPE_IO only exists in extended event log version 6 or later.
+	 * No need to check event log version.
+	 */
+	if (unlikely(elog->type != RTAS_TYPE_IO)) {
+		printk_once(KERN_WARNING "io_event_irq: Unexpected event type %d",
+			    elog->type);
+		return NULL;
+	}
+
+	sect = find_xelog_section(elog, PSERIES_ELOG_SECT_ID_IO_EVENT);
+	if (unlikely(!sect)) {
+		printk_once(KERN_WARNING "io_event_irq: RTAS extended event "
+			    "log does not contain an IO Event section. "
+			    "Could be a bug in system firmware!\n");
+		return NULL;
+	}
+	return (struct pseries_io_event *) &sect->data;
+}
+
+/*
+ * PAPR:
+ * - check-exception returns the first found error or event and clear that
+ *   error or event so it is reported once.
+ * - Each interrupt returns one event. If a plateform chooses to report
+ *   multiple events through a single interrupt, it must ensure that the
+ *   interrupt remains asserted until check-exception has been used to
+ *   process all out-standing events for that interrupt.
+ *
+ * Implementation notes:
+ * - Events must be processed in the order they are returned. Hence,
+ *   sequential in nature.
+ * - The owner of an event is determined by combinations of scope,
+ *   event type, and sub-type. There is no easy way to pre-sort clients
+ *   by scope or event type alone. For example, Torrent ISR route change
+ *   event is reported with scope 0x00 (Not Applicatable) rather than
+ *   0x3B (Torrent-hub). It is better to let the clients to identify
+ *   who owns the the event.
+ */
+
+static irqreturn_t ioei_interrupt(int irq, void *dev_id)
+{
+	struct pseries_io_event *event;
+	int rtas_rc;
+
+	for (;;) {
+		rtas_rc = rtas_call(ioei_check_exception_token, 6, 1, NULL,
+				    RTAS_VECTOR_EXTERNAL_INTERRUPT,
+				    virq_to_hw(irq),
+				    RTAS_IO_EVENTS, 1 /* Time Critical */,
+				    __pa(ioei_rtas_buf),
+				    RTAS_DATA_BUF_SIZE);
+		if (rtas_rc != 0)
+			break;
+
+		event = ioei_find_event((struct rtas_error_log *)ioei_rtas_buf);
+		if (!event)
+			continue;
+
+		atomic_notifier_call_chain(&pseries_ioei_notifier_list,
+					   0, event);
+	}
+	return IRQ_HANDLED;
+}
+
+static int __init ioei_init(void)
+{
+	struct device_node *np;
+
+	ioei_check_exception_token = rtas_token("check-exception");
+	if (ioei_check_exception_token == RTAS_UNKNOWN_SERVICE) {
+		pr_warning("IO Event IRQ not supported on this system !\n");
+		return -ENODEV;
+	}
+	np = of_find_node_by_path("/event-sources/ibm,io-events");
+	if (np) {
+		request_event_sources_irqs(np, ioei_interrupt, "IO_EVENT");
+		of_node_put(np);
+	} else {
+		pr_err("io_event_irq: No ibm,io-events on system! "
+		       "IO Event interrupt disabled.\n");
+		return -ENODEV;
+	}
+	return 0;
+}
+machine_subsys_initcall(pseries, ioei_init);
+
-- 
cgit v1.2.3-70-g09d2


From 40bd587a88fcd425f489f3d9f0be7daa84014141 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 3 May 2011 14:07:01 +0000
Subject: powerpc: Rename slb0_limit() to safe_stack_limit() and add Book3E
 support

slb0_limit() wasn't a very descriptive name. This changes it along with
a comment explaining what it's used for, and provides a 64-bit BookE
implementation.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/mmu-book3e.h |  4 ++++
 arch/powerpc/kernel/setup_64.c        | 23 ++++++++++++++++++-----
 2 files changed, 22 insertions(+), 5 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index ec61e7b998c..3ea0f9a259d 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -245,6 +245,10 @@ extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
 extern int mmu_linear_psize;
 extern int mmu_vmemmap_psize;
 
+#ifdef CONFIG_PPC64
+extern unsigned long linear_map_top;
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_MMU_BOOK3E_H_ */
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 959c63cf62e..c2ec0a12e14 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -434,17 +434,30 @@ void __init setup_system(void)
 	DBG(" <- setup_system()\n");
 }
 
-static u64 slb0_limit(void)
+/* This returns the limit below which memory accesses to the linear
+ * mapping are guarnateed not to cause a TLB or SLB miss. This is
+ * used to allocate interrupt or emergency stacks for which our
+ * exception entry path doesn't deal with being interrupted.
+ */
+static u64 safe_stack_limit(void)
 {
-	if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) {
+#ifdef CONFIG_PPC_BOOK3E
+	/* Freescale BookE bolts the entire linear mapping */
+	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E))
+		return linear_map_top;
+	/* Other BookE, we assume the first GB is bolted */
+	return 1ul << 30;
+#else
+	/* BookS, the first segment is bolted */
+	if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
 		return 1UL << SID_SHIFT_1T;
-	}
 	return 1UL << SID_SHIFT;
+#endif
 }
 
 static void __init irqstack_early_init(void)
 {
-	u64 limit = slb0_limit();
+	u64 limit = safe_stack_limit();
 	unsigned int i;
 
 	/*
@@ -497,7 +510,7 @@ static void __init emergency_stack_init(void)
 	 * bringup, we need to get at them in real mode. This means they
 	 * must also be within the RMO region.
 	 */
-	limit = min(slb0_limit(), ppc64_rma_size);
+	limit = min(safe_stack_limit(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
 		unsigned long sp;
-- 
cgit v1.2.3-70-g09d2


From a1d0d98daf6ce580d017a43b09fe30a375cde3e8 Mon Sep 17 00:00:00 2001
From: David Gibson <david@gibson.dropbear.id.au>
Date: Thu, 14 Apr 2011 22:32:06 +0000
Subject: powerpc: Add WSP platform

Add a platform for the Wire Speed Processor, based on the PPC A2.

This includes code for the ICS & OPB interrupt controllers, as well
as a SCOM backend, and SCOM based cpu bringup.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Jack Miller <jack@codezen.org>
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/wsp.h        |  14 +
 arch/powerpc/kernel/exceptions-64e.S  |  23 ++
 arch/powerpc/platforms/Kconfig        |   1 +
 arch/powerpc/platforms/Makefile       |   1 +
 arch/powerpc/platforms/wsp/Kconfig    |  28 ++
 arch/powerpc/platforms/wsp/Makefile   |   6 +
 arch/powerpc/platforms/wsp/ics.c      | 712 ++++++++++++++++++++++++++++++++++
 arch/powerpc/platforms/wsp/ics.h      |  20 +
 arch/powerpc/platforms/wsp/opb_pic.c  | 332 ++++++++++++++++
 arch/powerpc/platforms/wsp/psr2.c     |  95 +++++
 arch/powerpc/platforms/wsp/scom_smp.c | 427 ++++++++++++++++++++
 arch/powerpc/platforms/wsp/scom_wsp.c |  77 ++++
 arch/powerpc/platforms/wsp/setup.c    |  36 ++
 arch/powerpc/platforms/wsp/smp.c      |  87 +++++
 arch/powerpc/platforms/wsp/wsp.h      |  17 +
 arch/powerpc/sysdev/xics/icp-native.c |   1 +
 16 files changed, 1877 insertions(+)
 create mode 100644 arch/powerpc/include/asm/wsp.h
 create mode 100644 arch/powerpc/platforms/wsp/Kconfig
 create mode 100644 arch/powerpc/platforms/wsp/Makefile
 create mode 100644 arch/powerpc/platforms/wsp/ics.c
 create mode 100644 arch/powerpc/platforms/wsp/ics.h
 create mode 100644 arch/powerpc/platforms/wsp/opb_pic.c
 create mode 100644 arch/powerpc/platforms/wsp/psr2.c
 create mode 100644 arch/powerpc/platforms/wsp/scom_smp.c
 create mode 100644 arch/powerpc/platforms/wsp/scom_wsp.c
 create mode 100644 arch/powerpc/platforms/wsp/setup.c
 create mode 100644 arch/powerpc/platforms/wsp/smp.c
 create mode 100644 arch/powerpc/platforms/wsp/wsp.h

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/wsp.h b/arch/powerpc/include/asm/wsp.h
new file mode 100644
index 00000000000..c7dc83088a3
--- /dev/null
+++ b/arch/powerpc/include/asm/wsp.h
@@ -0,0 +1,14 @@
+/*
+ *  Copyright 2011 Michael Ellerman, IBM Corp.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+#ifndef __ASM_POWERPC_WSP_H
+#define __ASM_POWERPC_WSP_H
+
+extern int wsp_get_chip_id(struct device_node *dn);
+
+#endif /* __ASM_POWERPC_WSP_H */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 23bd83b20be..c98e9d26062 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -864,6 +864,20 @@ have_hes:
 	 * that will have to be made dependent on whether we are running under
 	 * a hypervisor I suppose.
 	 */
+
+	/* BEWARE, MAGIC
+	 * This code is called as an ordinary function on the boot CPU. But to
+	 * avoid duplication, this code is also used in SCOM bringup of
+	 * secondary CPUs. We read the code between the initial_tlb_code_start
+	 * and initial_tlb_code_end labels one instruction at a time and RAM it
+	 * into the new core via SCOM. That doesn't process branches, so there
+	 * must be none between those two labels. It also means if this code
+	 * ever takes any parameters, the SCOM code must also be updated to
+	 * provide them.
+	 */
+	.globl a2_tlbinit_code_start
+a2_tlbinit_code_start:
+
 	ori	r11,r3,MAS0_WQ_ALLWAYS
 	oris	r11,r11,MAS0_ESEL(3)@h /* Use way 3: workaround A2 erratum 376 */
 	mtspr	SPRN_MAS0,r11
@@ -880,6 +894,9 @@ have_hes:
 	/* Write the TLB entry */
 	tlbwe
 
+	.globl a2_tlbinit_after_linear_map
+a2_tlbinit_after_linear_map:
+
 	/* Now we branch the new virtual address mapped by this entry */
 	LOAD_REG_IMMEDIATE(r3,1f)
 	mtctr	r3
@@ -931,10 +948,16 @@ have_hes:
 	cmpw	r3,r9
 	blt	2b
 
+	.globl  a2_tlbinit_after_iprot_flush
+a2_tlbinit_after_iprot_flush:
+
 	PPC_TLBILX(0,0,0)
 	sync
 	isync
 
+	.globl a2_tlbinit_code_end
+a2_tlbinit_code_end:
+
 	/* We translate LR and return */
 	mflr	r3
 	tovirt(r3,r3)
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index f2352fc5cbb..6059053e715 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -20,6 +20,7 @@ source "arch/powerpc/platforms/embedded6xx/Kconfig"
 source "arch/powerpc/platforms/44x/Kconfig"
 source "arch/powerpc/platforms/40x/Kconfig"
 source "arch/powerpc/platforms/amigaone/Kconfig"
+source "arch/powerpc/platforms/wsp/Kconfig"
 
 config KVM_GUEST
 	bool "KVM Guest support"
diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile
index fdb9f0b0d7a..73e2116cfee 100644
--- a/arch/powerpc/platforms/Makefile
+++ b/arch/powerpc/platforms/Makefile
@@ -22,3 +22,4 @@ obj-$(CONFIG_PPC_CELL)		+= cell/
 obj-$(CONFIG_PPC_PS3)		+= ps3/
 obj-$(CONFIG_EMBEDDED6xx)	+= embedded6xx/
 obj-$(CONFIG_AMIGAONE)		+= amigaone/
+obj-$(CONFIG_PPC_WSP)		+= wsp/
diff --git a/arch/powerpc/platforms/wsp/Kconfig b/arch/powerpc/platforms/wsp/Kconfig
new file mode 100644
index 00000000000..c3c48eb62cc
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/Kconfig
@@ -0,0 +1,28 @@
+config PPC_WSP
+	bool
+	default n
+
+menu "WSP platform selection"
+	depends on PPC_BOOK3E_64
+
+config PPC_PSR2
+	bool "PSR-2 platform"
+	select PPC_A2
+	select GENERIC_TBSYNC
+	select PPC_SCOM
+	select EPAPR_BOOT
+	select PPC_WSP
+	select PPC_XICS
+	select PPC_ICP_NATIVE
+	default y
+
+endmenu
+
+config PPC_A2_DD2
+	bool "Support for DD2 based A2/WSP systems"
+	depends on PPC_A2
+
+config WORKAROUND_ERRATUM_463
+	depends on PPC_A2_DD2
+	bool "Workaround erratum 463"
+	default y
diff --git a/arch/powerpc/platforms/wsp/Makefile b/arch/powerpc/platforms/wsp/Makefile
new file mode 100644
index 00000000000..095be73d6cd
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/Makefile
@@ -0,0 +1,6 @@
+ccflags-y			+= -mno-minimal-toc
+
+obj-y				+= setup.o ics.o
+obj-$(CONFIG_PPC_PSR2)		+= psr2.o opb_pic.o
+obj-$(CONFIG_PPC_WSP)		+= scom_wsp.o
+obj-$(CONFIG_SMP)		+= smp.o scom_smp.o
diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c
new file mode 100644
index 00000000000..e53bd9e7b12
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/ics.c
@@ -0,0 +1,712 @@
+/*
+ * Copyright 2008-2011 IBM Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/msi.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/xics.h>
+
+#include "wsp.h"
+#include "ics.h"
+
+
+/* WSP ICS */
+
+struct wsp_ics {
+	struct ics ics;
+	struct device_node *dn;
+	void __iomem *regs;
+	spinlock_t lock;
+	unsigned long *bitmap;
+	u32 chip_id;
+	u32 lsi_base;
+	u32 lsi_count;
+	u64 hwirq_start;
+	u64 count;
+#ifdef CONFIG_SMP
+	int *hwirq_cpu_map;
+#endif
+};
+
+#define to_wsp_ics(ics)	container_of(ics, struct wsp_ics, ics)
+
+#define INT_SRC_LAYER_BUID_REG(base)	((base) + 0x00)
+#define IODA_TBL_ADDR_REG(base)		((base) + 0x18)
+#define IODA_TBL_DATA_REG(base)		((base) + 0x20)
+#define XIVE_UPDATE_REG(base)		((base) + 0x28)
+#define ICS_INT_CAPS_REG(base)		((base) + 0x30)
+
+#define TBL_AUTO_INCREMENT	((1UL << 63) | (1UL << 15))
+#define TBL_SELECT_XIST		(1UL << 48)
+#define TBL_SELECT_XIVT		(1UL << 49)
+
+#define IODA_IRQ(irq)		((irq) & (0x7FFULL))	/* HRM 5.1.3.4 */
+
+#define XIST_REQUIRED		0x8
+#define XIST_REJECTED		0x4
+#define XIST_PRESENTED		0x2
+#define XIST_PENDING		0x1
+
+#define XIVE_SERVER_SHIFT	42
+#define XIVE_SERVER_MASK	0xFFFFULL
+#define XIVE_PRIORITY_MASK	0xFFULL
+#define XIVE_PRIORITY_SHIFT	32
+#define XIVE_WRITE_ENABLE	(1ULL << 63)
+
+/*
+ * The docs refer to a 6 bit field called ChipID, which consists of a
+ * 3 bit NodeID and a 3 bit ChipID. On WSP the ChipID is always zero
+ * so we ignore it, and every where we use "chip id" in this code we
+ * mean the NodeID.
+ */
+#define WSP_ICS_CHIP_SHIFT		17
+
+
+static struct wsp_ics *ics_list;
+static int num_ics;
+
+/* ICS Source controller accessors */
+
+static u64 wsp_ics_get_xive(struct wsp_ics *ics, unsigned int irq)
+{
+	unsigned long flags;
+	u64 xive;
+
+	spin_lock_irqsave(&ics->lock, flags);
+	out_be64(IODA_TBL_ADDR_REG(ics->regs), TBL_SELECT_XIVT | IODA_IRQ(irq));
+	xive = in_be64(IODA_TBL_DATA_REG(ics->regs));
+	spin_unlock_irqrestore(&ics->lock, flags);
+
+	return xive;
+}
+
+static void wsp_ics_set_xive(struct wsp_ics *ics, unsigned int irq, u64 xive)
+{
+	xive &= ~XIVE_ADDR_MASK;
+	xive |= (irq & XIVE_ADDR_MASK);
+	xive |= XIVE_WRITE_ENABLE;
+
+	out_be64(XIVE_UPDATE_REG(ics->regs), xive);
+}
+
+static u64 xive_set_server(u64 xive, unsigned int server)
+{
+	u64 mask = ~(XIVE_SERVER_MASK << XIVE_SERVER_SHIFT);
+
+	xive &= mask;
+	xive |= (server & XIVE_SERVER_MASK) << XIVE_SERVER_SHIFT;
+
+	return xive;
+}
+
+static u64 xive_set_priority(u64 xive, unsigned int priority)
+{
+	u64 mask = ~(XIVE_PRIORITY_MASK << XIVE_PRIORITY_SHIFT);
+
+	xive &= mask;
+	xive |= (priority & XIVE_PRIORITY_MASK) << XIVE_PRIORITY_SHIFT;
+
+	return xive;
+}
+
+
+#ifdef CONFIG_SMP
+/* Find logical CPUs within mask on a given chip and store result in ret */
+void cpus_on_chip(int chip_id, cpumask_t *mask, cpumask_t *ret)
+{
+	int cpu, chip;
+	struct device_node *cpu_dn, *dn;
+	const u32 *prop;
+
+	cpumask_clear(ret);
+	for_each_cpu(cpu, mask) {
+		cpu_dn = of_get_cpu_node(cpu, NULL);
+		if (!cpu_dn)
+			continue;
+
+		prop = of_get_property(cpu_dn, "at-node", NULL);
+		if (!prop) {
+			of_node_put(cpu_dn);
+			continue;
+		}
+
+		dn = of_find_node_by_phandle(*prop);
+		of_node_put(cpu_dn);
+
+		chip = wsp_get_chip_id(dn);
+		if (chip == chip_id)
+			cpumask_set_cpu(cpu, ret);
+
+		of_node_put(dn);
+	}
+}
+
+/* Store a suitable CPU to handle a hwirq in the ics->hwirq_cpu_map cache */
+static int cache_hwirq_map(struct wsp_ics *ics, unsigned int hwirq,
+			   const cpumask_t *affinity)
+{
+	cpumask_var_t avail, newmask;
+	int ret = -ENOMEM, cpu, cpu_rover = 0, target;
+	int index = hwirq - ics->hwirq_start;
+	unsigned int nodeid;
+
+	BUG_ON(index < 0 || index >= ics->count);
+
+	if (!ics->hwirq_cpu_map)
+		return -ENOMEM;
+
+	if (!distribute_irqs) {
+		ics->hwirq_cpu_map[hwirq - ics->hwirq_start] = xics_default_server;
+		return 0;
+	}
+
+	/* Allocate needed CPU masks */
+	if (!alloc_cpumask_var(&avail, GFP_KERNEL))
+		goto ret;
+	if (!alloc_cpumask_var(&newmask, GFP_KERNEL))
+		goto freeavail;
+
+	/* Find PBus attached to the source of this IRQ */
+	nodeid = (hwirq >> WSP_ICS_CHIP_SHIFT) & 0x3; /* 12:14 */
+
+	/* Find CPUs that could handle this IRQ */
+	if (affinity)
+		cpumask_and(avail, cpu_online_mask, affinity);
+	else
+		cpumask_copy(avail, cpu_online_mask);
+
+	/* Narrow selection down to logical CPUs on the same chip */
+	cpus_on_chip(nodeid, avail, newmask);
+
+	/* Ensure we haven't narrowed it down to 0 */
+	if (unlikely(cpumask_empty(newmask))) {
+		if (unlikely(cpumask_empty(avail))) {
+			ret = -1;
+			goto out;
+		}
+		cpumask_copy(newmask, avail);
+	}
+
+	/* Choose a CPU out of those we narrowed it down to in round robin */
+	target = hwirq % cpumask_weight(newmask);
+	for_each_cpu(cpu, newmask) {
+		if (cpu_rover++ >= target) {
+			ics->hwirq_cpu_map[index] = get_hard_smp_processor_id(cpu);
+			ret = 0;
+			goto out;
+		}
+	}
+
+	/* Shouldn't happen */
+	WARN_ON(1);
+
+out:
+	free_cpumask_var(newmask);
+freeavail:
+	free_cpumask_var(avail);
+ret:
+	if (ret < 0) {
+		ics->hwirq_cpu_map[index] = cpumask_first(cpu_online_mask);
+		pr_warning("Error, falling hwirq 0x%x routing back to CPU %i\n",
+			   hwirq, ics->hwirq_cpu_map[index]);
+	}
+	return ret;
+}
+
+static void alloc_irq_map(struct wsp_ics *ics)
+{
+	int i;
+
+	ics->hwirq_cpu_map = kmalloc(sizeof(int) * ics->count, GFP_KERNEL);
+	if (!ics->hwirq_cpu_map) {
+		pr_warning("Allocate hwirq_cpu_map failed, "
+			   "IRQ balancing disabled\n");
+		return;
+	}
+
+	for (i=0; i < ics->count; i++)
+		ics->hwirq_cpu_map[i] = xics_default_server;
+}
+
+static int get_irq_server(struct wsp_ics *ics, unsigned int hwirq)
+{
+	int index = hwirq - ics->hwirq_start;
+
+	BUG_ON(index < 0 || index >= ics->count);
+
+	if (!ics->hwirq_cpu_map)
+		return xics_default_server;
+
+	return ics->hwirq_cpu_map[index];
+}
+#else /* !CONFIG_SMP */
+static int cache_hwirq_map(struct wsp_ics *ics, unsigned int hwirq,
+			   const cpumask_t *affinity)
+{
+	return 0;
+}
+
+static int get_irq_server(struct wsp_ics *ics, unsigned int hwirq)
+{
+	return xics_default_server;
+}
+
+static void alloc_irq_map(struct wsp_ics *ics) { }
+#endif
+
+static void wsp_chip_unmask_irq(struct irq_data *d)
+{
+	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+	struct wsp_ics *ics;
+	int server;
+	u64 xive;
+
+	if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS)
+		return;
+
+	ics = d->chip_data;
+	if (WARN_ON(!ics))
+		return;
+
+	server = get_irq_server(ics, hw_irq);
+
+	xive = wsp_ics_get_xive(ics, hw_irq);
+	xive = xive_set_server(xive, server);
+	xive = xive_set_priority(xive, DEFAULT_PRIORITY);
+	wsp_ics_set_xive(ics, hw_irq, xive);
+}
+
+static unsigned int wsp_chip_startup(struct irq_data *d)
+{
+	/* unmask it */
+	wsp_chip_unmask_irq(d);
+	return 0;
+}
+
+static void wsp_mask_real_irq(unsigned int hw_irq, struct wsp_ics *ics)
+{
+	u64 xive;
+
+	if (hw_irq == XICS_IPI)
+		return;
+
+	if (WARN_ON(!ics))
+		return;
+	xive = wsp_ics_get_xive(ics, hw_irq);
+	xive = xive_set_server(xive, xics_default_server);
+	xive = xive_set_priority(xive, LOWEST_PRIORITY);
+	wsp_ics_set_xive(ics, hw_irq, xive);
+}
+
+static void wsp_chip_mask_irq(struct irq_data *d)
+{
+	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+	struct wsp_ics *ics = d->chip_data;
+
+	if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS)
+		return;
+
+	wsp_mask_real_irq(hw_irq, ics);
+}
+
+static int wsp_chip_set_affinity(struct irq_data *d,
+				 const struct cpumask *cpumask, bool force)
+{
+	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+	struct wsp_ics *ics;
+	int ret;
+	u64 xive;
+
+	if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS)
+		return -1;
+
+	ics = d->chip_data;
+	if (WARN_ON(!ics))
+		return -1;
+	xive = wsp_ics_get_xive(ics, hw_irq);
+
+	/*
+	 * For the moment only implement delivery to all cpus or one cpu.
+	 * Get current irq_server for the given irq
+	 */
+	ret = cache_hwirq_map(ics, d->irq, cpumask);
+	if (ret == -1) {
+		char cpulist[128];
+		cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask);
+		pr_warning("%s: No online cpus in the mask %s for irq %d\n",
+			   __func__, cpulist, d->irq);
+		return -1;
+	} else if (ret == -ENOMEM) {
+		pr_warning("%s: Out of memory\n", __func__);
+		return -1;
+	}
+
+	xive = xive_set_server(xive, get_irq_server(ics, hw_irq));
+	wsp_ics_set_xive(ics, hw_irq, xive);
+
+	return 0;
+}
+
+static struct irq_chip wsp_irq_chip = {
+	.name = "WSP ICS",
+	.irq_startup		= wsp_chip_startup,
+	.irq_mask		= wsp_chip_mask_irq,
+	.irq_unmask		= wsp_chip_unmask_irq,
+	.irq_set_affinity	= wsp_chip_set_affinity
+};
+
+static int wsp_ics_host_match(struct ics *ics, struct device_node *dn)
+{
+	/* All ICSs in the system implement a global irq number space,
+	 * so match against them all. */
+	return of_device_is_compatible(dn, "ibm,ppc-xics");
+}
+
+static int wsp_ics_match_hwirq(struct wsp_ics *wsp_ics, unsigned int hwirq)
+{
+	if (hwirq >= wsp_ics->hwirq_start &&
+	    hwirq <  wsp_ics->hwirq_start + wsp_ics->count)
+		return 1;
+
+	return 0;
+}
+
+static int wsp_ics_map(struct ics *ics, unsigned int virq)
+{
+	struct wsp_ics *wsp_ics = to_wsp_ics(ics);
+	unsigned int hw_irq = virq_to_hw(virq);
+	unsigned long flags;
+
+	if (!wsp_ics_match_hwirq(wsp_ics, hw_irq))
+		return -ENOENT;
+
+	irq_set_chip_and_handler(virq, &wsp_irq_chip, handle_fasteoi_irq);
+
+	irq_set_chip_data(virq, wsp_ics);
+
+	spin_lock_irqsave(&wsp_ics->lock, flags);
+	bitmap_allocate_region(wsp_ics->bitmap, hw_irq - wsp_ics->hwirq_start, 0);
+	spin_unlock_irqrestore(&wsp_ics->lock, flags);
+
+	return 0;
+}
+
+static void wsp_ics_mask_unknown(struct ics *ics, unsigned long hw_irq)
+{
+	struct wsp_ics *wsp_ics = to_wsp_ics(ics);
+
+	if (!wsp_ics_match_hwirq(wsp_ics, hw_irq))
+		return;
+
+	pr_err("%s: IRQ %lu (real) is invalid, disabling it.\n", __func__, hw_irq);
+	wsp_mask_real_irq(hw_irq, wsp_ics);
+}
+
+static long wsp_ics_get_server(struct ics *ics, unsigned long hw_irq)
+{
+	struct wsp_ics *wsp_ics = to_wsp_ics(ics);
+
+	if (!wsp_ics_match_hwirq(wsp_ics, hw_irq))
+		return -ENOENT;
+
+	return get_irq_server(wsp_ics, hw_irq);
+}
+
+/* HW Number allocation API */
+
+static struct wsp_ics *wsp_ics_find_dn_ics(struct device_node *dn)
+{
+	struct device_node *iparent;
+	int i;
+
+	iparent = of_irq_find_parent(dn);
+	if (!iparent) {
+		pr_err("wsp_ics: Failed to find interrupt parent!\n");
+		return NULL;
+	}
+
+	for(i = 0; i < num_ics; i++) {
+		if(ics_list[i].dn == iparent)
+			break;
+	}
+
+	if (i >= num_ics) {
+		pr_err("wsp_ics: Unable to find parent bitmap!\n");
+		return NULL;
+	}
+
+	return &ics_list[i];
+}
+
+int wsp_ics_alloc_irq(struct device_node *dn, int num)
+{
+	struct wsp_ics *ics;
+	int order, offset;
+
+	ics = wsp_ics_find_dn_ics(dn);
+	if (!ics)
+		return -ENODEV;
+
+	/* Fast, but overly strict if num isn't a power of two */
+	order = get_count_order(num);
+
+	spin_lock_irq(&ics->lock);
+	offset = bitmap_find_free_region(ics->bitmap, ics->count, order);
+	spin_unlock_irq(&ics->lock);
+
+	if (offset < 0)
+		return offset;
+
+	return offset + ics->hwirq_start;
+}
+
+void wsp_ics_free_irq(struct device_node *dn, unsigned int irq)
+{
+	struct wsp_ics *ics;
+
+	ics = wsp_ics_find_dn_ics(dn);
+	if (WARN_ON(!ics))
+		return;
+
+	spin_lock_irq(&ics->lock);
+	bitmap_release_region(ics->bitmap, irq, 0);
+	spin_unlock_irq(&ics->lock);
+}
+
+/* Initialisation */
+
+static int __init wsp_ics_bitmap_setup(struct wsp_ics *ics,
+				      struct device_node *dn)
+{
+	int len, i, j, size;
+	u32 start, count;
+	const u32 *p;
+
+	size = BITS_TO_LONGS(ics->count) * sizeof(long);
+	ics->bitmap = kzalloc(size, GFP_KERNEL);
+	if (!ics->bitmap) {
+		pr_err("wsp_ics: ENOMEM allocating IRQ bitmap!\n");
+		return -ENOMEM;
+	}
+
+	spin_lock_init(&ics->lock);
+
+	p = of_get_property(dn, "available-ranges", &len);
+	if (!p || !len) {
+		/* FIXME this should be a WARN() once mambo is updated */
+		pr_err("wsp_ics: No available-ranges defined for %s\n",
+			dn->full_name);
+		return 0;
+	}
+
+	if (len % (2 * sizeof(u32)) != 0) {
+		/* FIXME this should be a WARN() once mambo is updated */
+		pr_err("wsp_ics: Invalid available-ranges for %s\n",
+			dn->full_name);
+		return 0;
+	}
+
+	bitmap_fill(ics->bitmap, ics->count);
+
+	for (i = 0; i < len / sizeof(u32); i += 2) {
+		start = of_read_number(p + i, 1);
+		count = of_read_number(p + i + 1, 1);
+
+		pr_devel("%s: start: %d count: %d\n", __func__, start, count);
+
+		if ((start + count) > (ics->hwirq_start + ics->count) ||
+		     start < ics->hwirq_start) {
+			pr_err("wsp_ics: Invalid range! -> %d to %d\n",
+					start, start + count);
+			break;
+		}
+
+		for (j = 0; j < count; j++)
+			bitmap_release_region(ics->bitmap,
+				(start + j) - ics->hwirq_start, 0);
+	}
+
+	/* Ensure LSIs are not available for allocation */
+	bitmap_allocate_region(ics->bitmap, ics->lsi_base,
+			       get_count_order(ics->lsi_count));
+
+	return 0;
+}
+
+static int __init wsp_ics_setup(struct wsp_ics *ics, struct device_node *dn)
+{
+	u32 lsi_buid, msi_buid, msi_base, msi_count;
+	void __iomem *regs;
+	const u32 *p;
+	int rc, len, i;
+	u64 caps, buid;
+
+	p = of_get_property(dn, "interrupt-ranges", &len);
+	if (!p || len < (2 * sizeof(u32))) {
+		pr_err("wsp_ics: No/bad interrupt-ranges found on %s\n",
+			dn->full_name);
+		return -ENOENT;
+	}
+
+	if (len > (2 * sizeof(u32))) {
+		pr_err("wsp_ics: Multiple ics ranges not supported.\n");
+		return -EINVAL;
+	}
+
+	regs = of_iomap(dn, 0);
+	if (!regs) {
+		pr_err("wsp_ics: of_iomap(%s) failed\n", dn->full_name);
+		return -ENXIO;
+	}
+
+	ics->hwirq_start = of_read_number(p, 1);
+	ics->count = of_read_number(p + 1, 1);
+	ics->regs = regs;
+
+	ics->chip_id = wsp_get_chip_id(dn);
+	if (WARN_ON(ics->chip_id < 0))
+		ics->chip_id = 0;
+
+	/* Get some informations about the critter */
+	caps = in_be64(ICS_INT_CAPS_REG(ics->regs));
+	buid = in_be64(INT_SRC_LAYER_BUID_REG(ics->regs));
+	ics->lsi_count = caps >> 56;
+	msi_count = (caps >> 44) & 0x7ff;
+
+	/* Note: LSI BUID is 9 bits, but really only 3 are BUID and the
+	 * rest is mixed in the interrupt number. We store the whole
+	 * thing though
+	 */
+	lsi_buid = (buid >> 48) & 0x1ff;
+	ics->lsi_base = (ics->chip_id << WSP_ICS_CHIP_SHIFT) | lsi_buid << 5;
+	msi_buid = (buid >> 37) & 0x7;
+	msi_base = (ics->chip_id << WSP_ICS_CHIP_SHIFT) | msi_buid << 11;
+
+	pr_info("wsp_ics: Found %s\n", dn->full_name);
+	pr_info("wsp_ics:    irq range : 0x%06llx..0x%06llx\n",
+		ics->hwirq_start, ics->hwirq_start + ics->count - 1);
+	pr_info("wsp_ics:    %4d LSIs : 0x%06x..0x%06x\n",
+		ics->lsi_count, ics->lsi_base,
+		ics->lsi_base + ics->lsi_count - 1);
+	pr_info("wsp_ics:    %4d MSIs : 0x%06x..0x%06x\n",
+		msi_count, msi_base,
+		msi_base + msi_count - 1);
+
+	/* Let's check the HW config is sane */
+	if (ics->lsi_base < ics->hwirq_start ||
+	    (ics->lsi_base + ics->lsi_count) > (ics->hwirq_start + ics->count))
+		pr_warning("wsp_ics: WARNING ! LSIs out of interrupt-ranges !\n");
+	if (msi_base < ics->hwirq_start ||
+	    (msi_base + msi_count) > (ics->hwirq_start + ics->count))
+		pr_warning("wsp_ics: WARNING ! MSIs out of interrupt-ranges !\n");
+
+	/* We don't check for overlap between LSI and MSI, which will happen
+	 * if we use the same BUID, I'm not sure yet how legit that is.
+	 */
+
+	rc = wsp_ics_bitmap_setup(ics, dn);
+	if (rc) {
+		iounmap(regs);
+		return rc;
+	}
+
+	ics->dn = of_node_get(dn);
+	alloc_irq_map(ics);
+
+	for(i = 0; i < ics->count; i++)
+		wsp_mask_real_irq(ics->hwirq_start + i, ics);
+
+	ics->ics.map = wsp_ics_map;
+	ics->ics.mask_unknown = wsp_ics_mask_unknown;
+	ics->ics.get_server = wsp_ics_get_server;
+	ics->ics.host_match = wsp_ics_host_match;
+
+	xics_register_ics(&ics->ics);
+
+	return 0;
+}
+
+static void __init wsp_ics_set_default_server(void)
+{
+	struct device_node *np;
+	u32 hwid;
+
+	/* Find the server number for the boot cpu. */
+	np = of_get_cpu_node(boot_cpuid, NULL);
+	BUG_ON(!np);
+
+	hwid = get_hard_smp_processor_id(boot_cpuid);
+
+	pr_info("wsp_ics: default server is %#x, CPU %s\n", hwid, np->full_name);
+	xics_default_server = hwid;
+
+	of_node_put(np);
+}
+
+static int __init wsp_ics_init(void)
+{
+	struct device_node *dn;
+	struct wsp_ics *ics;
+	int rc, found;
+
+	wsp_ics_set_default_server();
+
+	found = 0;
+	for_each_compatible_node(dn, NULL, "ibm,ppc-xics")
+		found++;
+
+	if (found == 0) {
+		pr_err("wsp_ics: No ICS's found!\n");
+		return -ENODEV;
+	}
+
+	ics_list = kmalloc(sizeof(*ics) * found, GFP_KERNEL);
+	if (!ics_list) {
+		pr_err("wsp_ics: No memory for structs.\n");
+		return -ENOMEM;
+	}
+
+	num_ics = 0;
+	ics = ics_list;
+	for_each_compatible_node(dn, NULL, "ibm,wsp-xics") {
+		rc = wsp_ics_setup(ics, dn);
+		if (rc == 0) {
+			ics++;
+			num_ics++;
+		}
+	}
+
+	if (found != num_ics) {
+		pr_err("wsp_ics: Failed setting up %d ICS's\n",
+			found - num_ics);
+		return -1;
+	}
+
+	return 0;
+}
+
+void __init wsp_init_irq(void)
+{
+	wsp_ics_init();
+	xics_init();
+
+	/* We need to patch our irq chip's EOI to point to the right ICP */
+	wsp_irq_chip.irq_eoi = icp_ops->eoi;
+}
diff --git a/arch/powerpc/platforms/wsp/ics.h b/arch/powerpc/platforms/wsp/ics.h
new file mode 100644
index 00000000000..e34d5310264
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/ics.h
@@ -0,0 +1,20 @@
+/*
+ * Copyright 2009 IBM Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#ifndef __ICS_H
+#define __ICS_H
+
+#define XIVE_ADDR_MASK		0x7FFULL
+
+extern void wsp_init_irq(void);
+
+extern int wsp_ics_alloc_irq(struct device_node *dn, int num);
+extern void wsp_ics_free_irq(struct device_node *dn, unsigned int irq);
+
+#endif /* __ICS_H */
diff --git a/arch/powerpc/platforms/wsp/opb_pic.c b/arch/powerpc/platforms/wsp/opb_pic.c
new file mode 100644
index 00000000000..be05631a3c1
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/opb_pic.c
@@ -0,0 +1,332 @@
+/*
+ * IBM Onboard Peripheral Bus Interrupt Controller
+ *
+ * Copyright 2010 Jack Miller, IBM Corporation.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+
+#include <asm/reg_a2.h>
+#include <asm/irq.h>
+
+#define OPB_NR_IRQS 32
+
+#define OPB_MLSASIER	0x04    /* MLS Accumulated Status IER */
+#define OPB_MLSIR	0x50	/* MLS Interrupt Register */
+#define OPB_MLSIER	0x54	/* MLS Interrupt Enable Register */
+#define OPB_MLSIPR	0x58	/* MLS Interrupt Polarity Register */
+#define OPB_MLSIIR	0x5c	/* MLS Interrupt Inputs Register */
+
+static int opb_index = 0;
+
+struct opb_pic {
+	struct irq_host *host;
+	void *regs;
+	int index;
+	spinlock_t lock;
+};
+
+static u32 opb_in(struct opb_pic *opb, int offset)
+{
+	return in_be32(opb->regs + offset);
+}
+
+static void opb_out(struct opb_pic *opb, int offset, u32 val)
+{
+	out_be32(opb->regs + offset, val);
+}
+
+static void opb_unmask_irq(struct irq_data *d)
+{
+	struct opb_pic *opb;
+	unsigned long flags;
+	u32 ier, bitset;
+
+	opb = d->chip_data;
+	bitset = (1 << (31 - irqd_to_hwirq(d)));
+
+	spin_lock_irqsave(&opb->lock, flags);
+
+	ier = opb_in(opb, OPB_MLSIER);
+	opb_out(opb, OPB_MLSIER, ier | bitset);
+	ier = opb_in(opb, OPB_MLSIER);
+
+	spin_unlock_irqrestore(&opb->lock, flags);
+}
+
+static void opb_mask_irq(struct irq_data *d)
+{
+	struct opb_pic *opb;
+	unsigned long flags;
+	u32 ier, mask;
+
+	opb = d->chip_data;
+	mask = ~(1 << (31 - irqd_to_hwirq(d)));
+
+	spin_lock_irqsave(&opb->lock, flags);
+
+	ier = opb_in(opb, OPB_MLSIER);
+	opb_out(opb, OPB_MLSIER, ier & mask);
+	ier = opb_in(opb, OPB_MLSIER); // Flush posted writes
+
+	spin_unlock_irqrestore(&opb->lock, flags);
+}
+
+static void opb_ack_irq(struct irq_data *d)
+{
+	struct opb_pic *opb;
+	unsigned long flags;
+	u32 bitset;
+
+	opb = d->chip_data;
+	bitset = (1 << (31 - irqd_to_hwirq(d)));
+
+	spin_lock_irqsave(&opb->lock, flags);
+
+	opb_out(opb, OPB_MLSIR, bitset);
+	opb_in(opb, OPB_MLSIR); // Flush posted writes
+
+	spin_unlock_irqrestore(&opb->lock, flags);
+}
+
+static void opb_mask_ack_irq(struct irq_data *d)
+{
+	struct opb_pic *opb;
+	unsigned long flags;
+	u32 bitset;
+	u32 ier, ir;
+
+	opb = d->chip_data;
+	bitset = (1 << (31 - irqd_to_hwirq(d)));
+
+	spin_lock_irqsave(&opb->lock, flags);
+
+	ier = opb_in(opb, OPB_MLSIER);
+	opb_out(opb, OPB_MLSIER, ier & ~bitset);
+	ier = opb_in(opb, OPB_MLSIER); // Flush posted writes
+
+	opb_out(opb, OPB_MLSIR, bitset);
+	ir = opb_in(opb, OPB_MLSIR); // Flush posted writes
+
+	spin_unlock_irqrestore(&opb->lock, flags);
+}
+
+static int opb_set_irq_type(struct irq_data *d, unsigned int flow)
+{
+	struct opb_pic *opb;
+	unsigned long flags;
+	int invert, ipr, mask, bit;
+
+	opb = d->chip_data;
+
+	/* The only information we're interested in in the type is whether it's
+	 * a high or low trigger. For high triggered interrupts, the polarity
+	 * set for it in the MLS Interrupt Polarity Register is 0, for low
+	 * interrupts it's 1 so that the proper input in the MLS Interrupt Input
+	 * Register is interrupted as asserting the interrupt. */
+
+	switch (flow) {
+		case IRQ_TYPE_NONE:
+			opb_mask_irq(d);
+			return 0;
+
+		case IRQ_TYPE_LEVEL_HIGH:
+			invert = 0;
+			break;
+
+		case IRQ_TYPE_LEVEL_LOW:
+			invert = 1;
+			break;
+
+		default:
+			return -EINVAL;
+	}
+
+	bit = (1 << (31 - irqd_to_hwirq(d)));
+	mask = ~bit;
+
+	spin_lock_irqsave(&opb->lock, flags);
+
+	ipr = opb_in(opb, OPB_MLSIPR);
+	ipr = (ipr & mask) | (invert ? bit : 0);
+	opb_out(opb, OPB_MLSIPR, ipr);
+	ipr = opb_in(opb, OPB_MLSIPR);  // Flush posted writes
+
+	spin_unlock_irqrestore(&opb->lock, flags);
+
+	/* Record the type in the interrupt descriptor */
+	irqd_set_trigger_type(d, flow);
+
+	return 0;
+}
+
+static struct irq_chip opb_irq_chip = {
+	.name		= "OPB",
+	.irq_mask	= opb_mask_irq,
+	.irq_unmask	= opb_unmask_irq,
+	.irq_mask_ack	= opb_mask_ack_irq,
+	.irq_ack	= opb_ack_irq,
+	.irq_set_type	= opb_set_irq_type
+};
+
+static int opb_host_map(struct irq_host *host, unsigned int virq,
+		irq_hw_number_t hwirq)
+{
+	struct opb_pic *opb;
+
+	opb = host->host_data;
+
+	/* Most of the important stuff is handled by the generic host code, like
+	 * the lookup, so just attach some info to the virtual irq */
+
+	irq_set_chip_data(virq, opb);
+	irq_set_chip_and_handler(virq, &opb_irq_chip, handle_level_irq);
+	irq_set_irq_type(virq, IRQ_TYPE_NONE);
+
+	return 0;
+}
+
+static int opb_host_xlate(struct irq_host *host, struct device_node *dn,
+		const u32 *intspec, unsigned int intsize,
+		irq_hw_number_t *out_hwirq, unsigned int *out_type)
+{
+	/* Interrupt size must == 2 */
+	BUG_ON(intsize != 2);
+	*out_hwirq = intspec[0];
+	*out_type = intspec[1];
+	return 0;
+}
+
+static struct irq_host_ops opb_host_ops = {
+	.map = opb_host_map,
+	.xlate = opb_host_xlate,
+};
+
+irqreturn_t opb_irq_handler(int irq, void *private)
+{
+	struct opb_pic *opb;
+	u32 ir, src, subvirq;
+
+	opb = (struct opb_pic *) private;
+
+	/* Read the OPB MLS Interrupt Register for
+	 * asserted interrupts */
+	ir = opb_in(opb, OPB_MLSIR);
+	if (!ir)
+		return IRQ_NONE;
+
+	do {
+		/* Get 1 - 32 source, *NOT* bit */
+		src = 32 - ffs(ir);
+
+		/* Translate from the OPB's conception of interrupt number to
+		 * Linux's virtual IRQ */
+
+		subvirq = irq_linear_revmap(opb->host, src);
+
+		generic_handle_irq(subvirq);
+	} while ((ir = opb_in(opb, OPB_MLSIR)));
+
+	return IRQ_HANDLED;
+}
+
+struct opb_pic *opb_pic_init_one(struct device_node *dn)
+{
+	struct opb_pic *opb;
+	struct resource res;
+
+	if (of_address_to_resource(dn, 0, &res)) {
+		printk(KERN_ERR "opb: Couldn't translate resource\n");
+		return  NULL;
+	}
+
+	opb = kzalloc(sizeof(struct opb_pic), GFP_KERNEL);
+	if (!opb) {
+		printk(KERN_ERR "opb: Failed to allocate opb struct!\n");
+		return NULL;
+	}
+
+	/* Get access to the OPB MMIO registers */
+	opb->regs = ioremap(res.start + 0x10000, 0x1000);
+	if (!opb->regs) {
+		printk(KERN_ERR "opb: Failed to allocate register space!\n");
+		goto free_opb;
+	}
+
+	/* Allocate an irq host so that Linux knows that despite only
+	 * having one interrupt to issue, we're the controller for multiple
+	 * hardware IRQs, so later we can lookup their virtual IRQs. */
+
+	opb->host = irq_alloc_host(dn, IRQ_HOST_MAP_LINEAR,
+			OPB_NR_IRQS, &opb_host_ops, -1);
+
+	if (!opb->host) {
+		printk(KERN_ERR "opb: Failed to allocate IRQ host!\n");
+		goto free_regs;
+	}
+
+	opb->index = opb_index++;
+	spin_lock_init(&opb->lock);
+	opb->host->host_data = opb;
+
+	/* Disable all interrupts by default */
+	opb_out(opb, OPB_MLSASIER, 0);
+	opb_out(opb, OPB_MLSIER, 0);
+
+	/* ACK any interrupts left by FW */
+	opb_out(opb, OPB_MLSIR, 0xFFFFFFFF);
+
+	return opb;
+
+free_regs:
+	iounmap(opb->regs);
+free_opb:
+	kfree(opb);
+	return NULL;
+}
+
+void __init opb_pic_init(void)
+{
+	struct device_node *dn;
+	struct opb_pic *opb;
+	int virq;
+	int rc;
+
+	/* Call init_one for each OPB device */
+	for_each_compatible_node(dn, NULL, "ibm,opb") {
+
+		/* Fill in an OPB struct */
+		opb = opb_pic_init_one(dn);
+		if (!opb) {
+			printk(KERN_WARNING "opb: Failed to init node, skipped!\n");
+			continue;
+		}
+
+		/* Map / get opb's hardware virtual irq */
+		virq = irq_of_parse_and_map(dn, 0);
+		if (virq <= 0) {
+			printk("opb: irq_op_parse_and_map failed!\n");
+			continue;
+		}
+
+		/* Attach opb interrupt handler to new virtual IRQ */
+		rc = request_irq(virq, opb_irq_handler, 0, "OPB LS Cascade", opb);
+		if (rc) {
+			printk("opb: request_irq failed: %d\n", rc);
+			continue;
+		}
+
+		printk("OPB%d init with %d IRQs at %p\n", opb->index,
+				OPB_NR_IRQS, opb->regs);
+	}
+}
diff --git a/arch/powerpc/platforms/wsp/psr2.c b/arch/powerpc/platforms/wsp/psr2.c
new file mode 100644
index 00000000000..40f28916ff6
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/psr2.c
@@ -0,0 +1,95 @@
+/*
+ * Copyright 2008-2011, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/of.h>
+#include <linux/smp.h>
+
+#include <asm/machdep.h>
+#include <asm/system.h>
+#include <asm/time.h>
+#include <asm/udbg.h>
+
+#include "ics.h"
+#include "wsp.h"
+
+
+static void psr2_spin(void)
+{
+	hard_irq_disable();
+	for (;;) ;
+}
+
+static void psr2_restart(char *cmd)
+{
+	psr2_spin();
+}
+
+static int psr2_probe_devices(void)
+{
+	struct device_node *np;
+
+	/* Our RTC is a ds1500. It seems to be programatically compatible
+	 * with the ds1511 for which we have a driver so let's use that
+	 */
+	np = of_find_compatible_node(NULL, NULL, "dallas,ds1500");
+	if (np != NULL) {
+		struct resource res;
+		if (of_address_to_resource(np, 0, &res) == 0)
+			platform_device_register_simple("ds1511", 0, &res, 1);
+	}
+	return 0;
+}
+machine_arch_initcall(psr2_md, psr2_probe_devices);
+
+static void __init psr2_setup_arch(void)
+{
+	/* init to some ~sane value until calibrate_delay() runs */
+	loops_per_jiffy = 50000000;
+
+	scom_init_wsp();
+
+	/* Setup SMP callback */
+#ifdef CONFIG_SMP
+	a2_setup_smp();
+#endif
+}
+
+static int __init psr2_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	if (!of_flat_dt_is_compatible(root, "ibm,psr2"))
+		return 0;
+
+	return 1;
+}
+
+static void __init psr2_init_irq(void)
+{
+	wsp_init_irq();
+	opb_pic_init();
+}
+
+define_machine(psr2_md) {
+	.name			= "PSR2 A2",
+	.probe			= psr2_probe,
+	.setup_arch		= psr2_setup_arch,
+	.restart		= psr2_restart,
+	.power_off		= psr2_spin,
+	.halt			= psr2_spin,
+	.calibrate_decr		= generic_calibrate_decr,
+	.init_IRQ		= psr2_init_irq,
+	.progress		= udbg_progress,
+	.power_save		= book3e_idle,
+};
diff --git a/arch/powerpc/platforms/wsp/scom_smp.c b/arch/powerpc/platforms/wsp/scom_smp.c
new file mode 100644
index 00000000000..141e7803209
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/scom_smp.c
@@ -0,0 +1,427 @@
+/*
+ * SCOM support for A2 platforms
+ *
+ * Copyright 2007-2011 Benjamin Herrenschmidt, David Gibson,
+ *		       Michael Ellerman, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/cpumask.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include <asm/cputhreads.h>
+#include <asm/reg_a2.h>
+#include <asm/scom.h>
+#include <asm/udbg.h>
+
+#include "wsp.h"
+
+#define SCOM_RAMC		0x2a		/* Ram Command */
+#define SCOM_RAMC_TGT1_EXT	0x80000000
+#define SCOM_RAMC_SRC1_EXT	0x40000000
+#define SCOM_RAMC_SRC2_EXT	0x20000000
+#define SCOM_RAMC_SRC3_EXT	0x10000000
+#define SCOM_RAMC_ENABLE	0x00080000
+#define SCOM_RAMC_THREADSEL	0x00060000
+#define SCOM_RAMC_EXECUTE	0x00010000
+#define SCOM_RAMC_MSR_OVERRIDE	0x00008000
+#define SCOM_RAMC_MSR_PR	0x00004000
+#define SCOM_RAMC_MSR_GS	0x00002000
+#define SCOM_RAMC_FORCE		0x00001000
+#define SCOM_RAMC_FLUSH		0x00000800
+#define SCOM_RAMC_INTERRUPT	0x00000004
+#define SCOM_RAMC_ERROR		0x00000002
+#define SCOM_RAMC_DONE		0x00000001
+#define SCOM_RAMI		0x29		/* Ram Instruction */
+#define SCOM_RAMIC		0x28		/* Ram Instruction and Command */
+#define SCOM_RAMIC_INSN		0xffffffff00000000
+#define SCOM_RAMD		0x2d		/* Ram Data */
+#define SCOM_RAMDH		0x2e		/* Ram Data High */
+#define SCOM_RAMDL		0x2f		/* Ram Data Low */
+#define SCOM_PCCR0		0x33		/* PC Configuration Register 0 */
+#define SCOM_PCCR0_ENABLE_DEBUG	0x80000000
+#define SCOM_PCCR0_ENABLE_RAM	0x40000000
+#define SCOM_THRCTL		0x30		/* Thread Control and Status */
+#define SCOM_THRCTL_T0_STOP	0x80000000
+#define SCOM_THRCTL_T1_STOP	0x40000000
+#define SCOM_THRCTL_T2_STOP	0x20000000
+#define SCOM_THRCTL_T3_STOP	0x10000000
+#define SCOM_THRCTL_T0_STEP	0x08000000
+#define SCOM_THRCTL_T1_STEP	0x04000000
+#define SCOM_THRCTL_T2_STEP	0x02000000
+#define SCOM_THRCTL_T3_STEP	0x01000000
+#define SCOM_THRCTL_T0_RUN	0x00800000
+#define SCOM_THRCTL_T1_RUN	0x00400000
+#define SCOM_THRCTL_T2_RUN	0x00200000
+#define SCOM_THRCTL_T3_RUN	0x00100000
+#define SCOM_THRCTL_T0_PM	0x00080000
+#define SCOM_THRCTL_T1_PM	0x00040000
+#define SCOM_THRCTL_T2_PM	0x00020000
+#define SCOM_THRCTL_T3_PM	0x00010000
+#define SCOM_THRCTL_T0_UDE	0x00008000
+#define SCOM_THRCTL_T1_UDE	0x00004000
+#define SCOM_THRCTL_T2_UDE	0x00002000
+#define SCOM_THRCTL_T3_UDE	0x00001000
+#define SCOM_THRCTL_ASYNC_DIS	0x00000800
+#define SCOM_THRCTL_TB_DIS	0x00000400
+#define SCOM_THRCTL_DEC_DIS	0x00000200
+#define SCOM_THRCTL_AND		0x31		/* Thread Control and Status */
+#define SCOM_THRCTL_OR		0x32		/* Thread Control and Status */
+
+
+static DEFINE_PER_CPU(scom_map_t, scom_ptrs);
+
+static scom_map_t get_scom(int cpu, struct device_node *np, int *first_thread)
+{
+	scom_map_t scom = per_cpu(scom_ptrs, cpu);
+	int tcpu;
+
+	if (scom_map_ok(scom)) {
+		*first_thread = 0;
+		return scom;
+	}
+
+	*first_thread = 1;
+
+	scom = scom_map_device(np, 0);
+
+	for (tcpu = cpu_first_thread_sibling(cpu);
+	     tcpu <= cpu_last_thread_sibling(cpu); tcpu++)
+		per_cpu(scom_ptrs, tcpu) = scom;
+
+	/* Hack: for the boot core, this will actually get called on
+	 * the second thread up, not the first so our test above will
+	 * set first_thread incorrectly. */
+	if (cpu_first_thread_sibling(cpu) == 0)
+		*first_thread = 0;
+
+	return scom;
+}
+
+static int a2_scom_ram(scom_map_t scom, int thread, u32 insn, int extmask)
+{
+	u64 cmd, mask, val;
+	int n = 0;
+
+	cmd = ((u64)insn << 32) | (((u64)extmask & 0xf) << 28)
+		| ((u64)thread << 17) | SCOM_RAMC_ENABLE | SCOM_RAMC_EXECUTE;
+	mask = SCOM_RAMC_DONE | SCOM_RAMC_INTERRUPT | SCOM_RAMC_ERROR;
+
+	scom_write(scom, SCOM_RAMIC, cmd);
+
+	while (!((val = scom_read(scom, SCOM_RAMC)) & mask)) {
+		pr_devel("Waiting on RAMC = 0x%llx\n", val);
+		if (++n == 3) {
+			pr_err("RAMC timeout on instruction 0x%08x, thread %d\n",
+			       insn, thread);
+			return -1;
+		}
+	}
+
+	if (val & SCOM_RAMC_INTERRUPT) {
+		pr_err("RAMC interrupt on instruction 0x%08x, thread %d\n",
+		       insn, thread);
+		return -SCOM_RAMC_INTERRUPT;
+	}
+
+	if (val & SCOM_RAMC_ERROR) {
+		pr_err("RAMC error on instruction 0x%08x, thread %d\n",
+		       insn, thread);
+		return -SCOM_RAMC_ERROR;
+	}
+
+	return 0;
+}
+
+static int a2_scom_getgpr(scom_map_t scom, int thread, int gpr, int alt,
+			  u64 *out_gpr)
+{
+	int rc;
+
+	/* or rN, rN, rN */
+	u32 insn = 0x7c000378 | (gpr << 21) | (gpr << 16) | (gpr << 11);
+	rc = a2_scom_ram(scom, thread, insn, alt ? 0xf : 0x0);
+	if (rc)
+		return rc;
+
+	*out_gpr = scom_read(scom, SCOM_RAMD);
+
+	return 0;
+}
+
+static int a2_scom_getspr(scom_map_t scom, int thread, int spr, u64 *out_spr)
+{
+	int rc, sprhi, sprlo;
+	u32 insn;
+
+	sprhi = spr >> 5;
+	sprlo = spr & 0x1f;
+	insn = 0x7c2002a6 | (sprlo << 16) | (sprhi << 11); /* mfspr r1,spr */
+
+	if (spr == 0x0ff0)
+		insn = 0x7c2000a6; /* mfmsr r1 */
+
+	rc = a2_scom_ram(scom, thread, insn, 0xf);
+	if (rc)
+		return rc;
+	return a2_scom_getgpr(scom, thread, 1, 1, out_spr);
+}
+
+static int a2_scom_setgpr(scom_map_t scom, int thread, int gpr,
+			  int alt, u64 val)
+{
+	u32 lis = 0x3c000000 | (gpr << 21);
+	u32 li = 0x38000000 | (gpr << 21);
+	u32 oris = 0x64000000 | (gpr << 21) | (gpr << 16);
+	u32 ori = 0x60000000 | (gpr << 21) | (gpr << 16);
+	u32 rldicr32 = 0x780007c6 | (gpr << 21) | (gpr << 16);
+	u32 highest = val >> 48;
+	u32 higher = (val >> 32) & 0xffff;
+	u32 high = (val >> 16) & 0xffff;
+	u32 low = val & 0xffff;
+	int lext = alt ? 0x8 : 0x0;
+	int oext = alt ? 0xf : 0x0;
+	int rc = 0;
+
+	if (highest)
+		rc |= a2_scom_ram(scom, thread, lis | highest, lext);
+
+	if (higher) {
+		if (highest)
+			rc |= a2_scom_ram(scom, thread, oris | higher, oext);
+		else
+			rc |= a2_scom_ram(scom, thread, li | higher, lext);
+	}
+
+	if (highest || higher)
+		rc |= a2_scom_ram(scom, thread, rldicr32, oext);
+
+	if (high) {
+		if (highest || higher)
+			rc |= a2_scom_ram(scom, thread, oris | high, oext);
+		else
+			rc |= a2_scom_ram(scom, thread, lis | high, lext);
+	}
+
+	if (highest || higher || high)
+		rc |= a2_scom_ram(scom, thread, ori | low, oext);
+	else
+		rc |= a2_scom_ram(scom, thread, li | low, lext);
+
+	return rc;
+}
+
+static int a2_scom_setspr(scom_map_t scom, int thread, int spr, u64 val)
+{
+	int sprhi = spr >> 5;
+	int sprlo = spr & 0x1f;
+	/* mtspr spr, r1 */
+	u32 insn = 0x7c2003a6 | (sprlo << 16) | (sprhi << 11);
+
+	if (spr == 0x0ff0)
+		insn = 0x7c200124; /* mtmsr r1 */
+
+	if (a2_scom_setgpr(scom, thread, 1, 1, val))
+		return -1;
+
+	return a2_scom_ram(scom, thread, insn, 0xf);
+}
+
+static int a2_scom_initial_tlb(scom_map_t scom, int thread)
+{
+	extern u32 a2_tlbinit_code_start[], a2_tlbinit_code_end[];
+	extern u32 a2_tlbinit_after_iprot_flush[];
+	extern u32 a2_tlbinit_after_linear_map[];
+	u32 assoc, entries, i;
+	u64 epn, tlbcfg;
+	u32 *p;
+	int rc;
+
+	/* Invalidate all entries (including iprot) */
+
+	rc = a2_scom_getspr(scom, thread, SPRN_TLB0CFG, &tlbcfg);
+	if (rc)
+		goto scom_fail;
+	entries = tlbcfg & TLBnCFG_N_ENTRY;
+	assoc = (tlbcfg & TLBnCFG_ASSOC) >> 24;
+	epn = 0;
+
+	/* Set MMUCR2 to enable 4K, 64K, 1M, 16M and 1G pages */
+	a2_scom_setspr(scom, thread, SPRN_MMUCR2, 0x000a7531);
+	/* Set MMUCR3 to write all thids bit to the TLB */
+	a2_scom_setspr(scom, thread, SPRN_MMUCR3, 0x0000000f);
+
+	/* Set MAS1 for 1G page size, and MAS2 to our initial EPN */
+	a2_scom_setspr(scom, thread, SPRN_MAS1, MAS1_TSIZE(BOOK3E_PAGESZ_1GB));
+	a2_scom_setspr(scom, thread, SPRN_MAS2, epn);
+	for (i = 0; i < entries; i++) {
+
+		a2_scom_setspr(scom, thread, SPRN_MAS0, MAS0_ESEL(i % assoc));
+
+		/* tlbwe */
+		rc = a2_scom_ram(scom, thread, 0x7c0007a4, 0);
+		if (rc)
+			goto scom_fail;
+
+		/* Next entry is new address? */
+		if((i + 1) % assoc == 0) {
+			epn += (1 << 30);
+			a2_scom_setspr(scom, thread, SPRN_MAS2, epn);
+		}
+	}
+
+	/* Setup args for linear mapping */
+	rc = a2_scom_setgpr(scom, thread, 3, 0, MAS0_TLBSEL(0));
+	if (rc)
+		goto scom_fail;
+
+	/* Linear mapping */
+	for (p = a2_tlbinit_code_start; p < a2_tlbinit_after_linear_map; p++) {
+		rc = a2_scom_ram(scom, thread, *p, 0);
+		if (rc)
+			goto scom_fail;
+	}
+
+	/*
+	 * For the boot thread, between the linear mapping and the debug
+	 * mappings there is a loop to flush iprot mappings. Ramming doesn't do
+	 * branches, but the secondary threads don't need to be nearly as smart
+	 * (i.e. we don't need to worry about invalidating the mapping we're
+	 * standing on).
+	 */
+
+	/* Debug mappings. Expects r11 = MAS0 from linear map (set above) */
+	for (p = a2_tlbinit_after_iprot_flush; p < a2_tlbinit_code_end; p++) {
+		rc = a2_scom_ram(scom, thread, *p, 0);
+		if (rc)
+			goto scom_fail;
+	}
+
+scom_fail:
+	if (rc)
+		pr_err("Setting up initial TLB failed, err %d\n", rc);
+
+	if (rc == -SCOM_RAMC_INTERRUPT) {
+		/* Interrupt, dump some status */
+		int rc[10];
+		u64 iar, srr0, srr1, esr, mas0, mas1, mas2, mas7_3, mas8, ccr2;
+		rc[0] = a2_scom_getspr(scom, thread, SPRN_IAR, &iar);
+		rc[1] = a2_scom_getspr(scom, thread, SPRN_SRR0, &srr0);
+		rc[2] = a2_scom_getspr(scom, thread, SPRN_SRR1, &srr1);
+		rc[3] = a2_scom_getspr(scom, thread, SPRN_ESR, &esr);
+		rc[4] = a2_scom_getspr(scom, thread, SPRN_MAS0, &mas0);
+		rc[5] = a2_scom_getspr(scom, thread, SPRN_MAS1, &mas1);
+		rc[6] = a2_scom_getspr(scom, thread, SPRN_MAS2, &mas2);
+		rc[7] = a2_scom_getspr(scom, thread, SPRN_MAS7_MAS3, &mas7_3);
+		rc[8] = a2_scom_getspr(scom, thread, SPRN_MAS8, &mas8);
+		rc[9] = a2_scom_getspr(scom, thread, SPRN_A2_CCR2, &ccr2);
+		pr_err(" -> retreived IAR =0x%llx (err %d)\n", iar, rc[0]);
+		pr_err("    retreived SRR0=0x%llx (err %d)\n", srr0, rc[1]);
+		pr_err("    retreived SRR1=0x%llx (err %d)\n", srr1, rc[2]);
+		pr_err("    retreived ESR =0x%llx (err %d)\n", esr, rc[3]);
+		pr_err("    retreived MAS0=0x%llx (err %d)\n", mas0, rc[4]);
+		pr_err("    retreived MAS1=0x%llx (err %d)\n", mas1, rc[5]);
+		pr_err("    retreived MAS2=0x%llx (err %d)\n", mas2, rc[6]);
+		pr_err("    retreived MS73=0x%llx (err %d)\n", mas7_3, rc[7]);
+		pr_err("    retreived MAS8=0x%llx (err %d)\n", mas8, rc[8]);
+		pr_err("    retreived CCR2=0x%llx (err %d)\n", ccr2, rc[9]);
+	}
+
+	return rc;
+}
+
+int __devinit a2_scom_startup_cpu(unsigned int lcpu, int thr_idx,
+				  struct device_node *np)
+{
+	u64 init_iar, init_msr, init_ccr2;
+	unsigned long start_here;
+	int rc, core_setup;
+	scom_map_t scom;
+	u64 pccr0;
+
+	scom = get_scom(lcpu, np, &core_setup);
+	if (!scom) {
+		printk(KERN_ERR "Couldn't map SCOM for CPU%d\n", lcpu);
+		return -1;
+	}
+
+	pr_devel("Bringing up CPU%d using SCOM...\n", lcpu);
+
+	pccr0 = scom_read(scom, SCOM_PCCR0);
+	scom_write(scom, SCOM_PCCR0, pccr0 | SCOM_PCCR0_ENABLE_DEBUG |
+				     SCOM_PCCR0_ENABLE_RAM);
+
+	/* Stop the thead with THRCTL. If we are setting up the TLB we stop all
+	 * threads. We also disable asynchronous interrupts while RAMing.
+	 */
+	if (core_setup)
+		scom_write(scom, SCOM_THRCTL_OR,
+			      SCOM_THRCTL_T0_STOP |
+			      SCOM_THRCTL_T1_STOP |
+			      SCOM_THRCTL_T2_STOP |
+			      SCOM_THRCTL_T3_STOP |
+			      SCOM_THRCTL_ASYNC_DIS);
+	else
+		scom_write(scom, SCOM_THRCTL_OR, SCOM_THRCTL_T0_STOP >> thr_idx);
+
+	/* Flush its pipeline just in case */
+	scom_write(scom, SCOM_RAMC, ((u64)thr_idx << 17) |
+		      SCOM_RAMC_FLUSH | SCOM_RAMC_ENABLE);
+
+	a2_scom_getspr(scom, thr_idx, SPRN_IAR, &init_iar);
+	a2_scom_getspr(scom, thr_idx, 0x0ff0, &init_msr);
+	a2_scom_getspr(scom, thr_idx, SPRN_A2_CCR2, &init_ccr2);
+
+	/* Set MSR to MSR_CM (0x0ff0 is magic value for MSR_CM) */
+	rc = a2_scom_setspr(scom, thr_idx, 0x0ff0, MSR_CM);
+	if (rc) {
+		pr_err("Failed to set MSR ! err %d\n", rc);
+		return rc;
+	}
+
+	/* RAM in an sync/isync for the sake of it */
+	a2_scom_ram(scom, thr_idx, 0x7c0004ac, 0);
+	a2_scom_ram(scom, thr_idx, 0x4c00012c, 0);
+
+	if (core_setup) {
+		pr_devel("CPU%d is first thread in core, initializing TLB...\n",
+			 lcpu);
+		rc = a2_scom_initial_tlb(scom, thr_idx);
+		if (rc)
+			goto fail;
+	}
+
+	start_here = *(unsigned long *)(core_setup ? generic_secondary_smp_init
+					: generic_secondary_thread_init);
+	pr_devel("CPU%d entry point at 0x%lx...\n", lcpu, start_here);
+
+	rc |= a2_scom_setspr(scom, thr_idx, SPRN_IAR, start_here);
+	rc |= a2_scom_setgpr(scom, thr_idx, 3, 0,
+			     get_hard_smp_processor_id(lcpu));
+	/*
+	 * Tell book3e_secondary_core_init not to set up the TLB, we've
+	 * already done that.
+	 */
+	rc |= a2_scom_setgpr(scom, thr_idx, 4, 0, 1);
+
+	rc |= a2_scom_setspr(scom, thr_idx, SPRN_TENS, 0x1 << thr_idx);
+
+	scom_write(scom, SCOM_RAMC, 0);
+	scom_write(scom, SCOM_THRCTL_AND, ~(SCOM_THRCTL_T0_STOP >> thr_idx));
+	scom_write(scom, SCOM_PCCR0, pccr0);
+fail:
+	pr_devel("  SCOM initialization %s\n", rc ? "failed" : "succeeded");
+	if (rc) {
+		pr_err("Old IAR=0x%08llx MSR=0x%08llx CCR2=0x%08llx\n",
+		       init_iar, init_msr, init_ccr2);
+	}
+
+	return rc;
+}
diff --git a/arch/powerpc/platforms/wsp/scom_wsp.c b/arch/powerpc/platforms/wsp/scom_wsp.c
new file mode 100644
index 00000000000..4052e2259f3
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/scom_wsp.c
@@ -0,0 +1,77 @@
+/*
+ *  SCOM backend for WSP
+ *
+ *  Copyright 2010 Benjamin Herrenschmidt, IBM Corp.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/cpumask.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include <asm/cputhreads.h>
+#include <asm/reg_a2.h>
+#include <asm/scom.h>
+#include <asm/udbg.h>
+
+#include "wsp.h"
+
+
+static scom_map_t wsp_scom_map(struct device_node *dev, u64 reg, u64 count)
+{
+	struct resource r;
+	u64 xscom_addr;
+
+	if (!of_get_property(dev, "scom-controller", NULL)) {
+		pr_err("%s: device %s is not a SCOM controller\n",
+			__func__, dev->full_name);
+		return SCOM_MAP_INVALID;
+	}
+
+	if (of_address_to_resource(dev, 0, &r)) {
+		pr_debug("Failed to find SCOM controller address\n");
+		return 0;
+	}
+
+	/* Transform the SCOM address into an XSCOM offset */
+	xscom_addr = ((reg & 0x7f000000) >> 1) | ((reg & 0xfffff) << 3);
+
+	return (scom_map_t)ioremap(r.start + xscom_addr, count << 3);
+}
+
+static void wsp_scom_unmap(scom_map_t map)
+{
+	iounmap((void *)map);
+}
+
+static u64 wsp_scom_read(scom_map_t map, u32 reg)
+{
+	u64 __iomem *addr = (u64 __iomem *)map;
+
+	return in_be64(addr + reg);
+}
+
+static void wsp_scom_write(scom_map_t map, u32 reg, u64 value)
+{
+	u64 __iomem *addr = (u64 __iomem *)map;
+
+	return out_be64(addr + reg, value);
+}
+
+static const struct scom_controller wsp_scom_controller = {
+	.map	= wsp_scom_map,
+	.unmap	= wsp_scom_unmap,
+	.read	= wsp_scom_read,
+	.write	= wsp_scom_write
+};
+
+void scom_init_wsp(void)
+{
+	scom_init(&wsp_scom_controller);
+}
diff --git a/arch/powerpc/platforms/wsp/setup.c b/arch/powerpc/platforms/wsp/setup.c
new file mode 100644
index 00000000000..11ac2f05e01
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/setup.c
@@ -0,0 +1,36 @@
+/*
+ * Copyright 2010 Michael Ellerman, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/of_platform.h>
+
+#include "wsp.h"
+
+/*
+ * Find chip-id by walking up device tree looking for ibm,wsp-chip-id property.
+ * Won't work for nodes that are not a descendant of a wsp node.
+ */
+int wsp_get_chip_id(struct device_node *dn)
+{
+	const u32 *p;
+	int rc;
+
+	/* Start looking at the specified node, not its parent */
+	dn = of_node_get(dn);
+	while (dn && !(p = of_get_property(dn, "ibm,wsp-chip-id", NULL)))
+		dn = of_get_next_parent(dn);
+
+	if (!dn)
+		return -1;
+
+	rc = *p;
+	of_node_put(dn);
+
+	return rc;
+}
diff --git a/arch/powerpc/platforms/wsp/smp.c b/arch/powerpc/platforms/wsp/smp.c
new file mode 100644
index 00000000000..c7b8db9ed9b
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/smp.c
@@ -0,0 +1,87 @@
+/*
+ *  SMP Support for A2 platforms
+ *
+ *  Copyright 2007 Benjamin Herrenschmidt, IBM Corp.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/smp.h>
+
+#include <asm/dbell.h>
+#include <asm/machdep.h>
+#include <asm/xics.h>
+
+#include "ics.h"
+#include "wsp.h"
+
+static void __devinit smp_a2_setup_cpu(int cpu)
+{
+	doorbell_setup_this_cpu();
+
+	if (cpu != boot_cpuid)
+		xics_setup_cpu();
+}
+
+int __devinit smp_a2_kick_cpu(int nr)
+{
+	const char *enable_method;
+	struct device_node *np;
+	int thr_idx;
+
+	if (nr < 0 || nr >= NR_CPUS)
+		return -ENOENT;
+
+	np = of_get_cpu_node(nr, &thr_idx);
+	if (!np)
+		return -ENODEV;
+
+	enable_method = of_get_property(np, "enable-method", NULL);
+	pr_devel("CPU%d has enable-method: \"%s\"\n", nr, enable_method);
+
+	if (!enable_method) {
+                printk(KERN_ERR "CPU%d has no enable-method\n", nr);
+		return -ENOENT;
+	} else if (strcmp(enable_method, "ibm,a2-scom") == 0) {
+		if (a2_scom_startup_cpu(nr, thr_idx, np))
+			return -1;
+	} else {
+		printk(KERN_ERR "CPU%d: Don't understand enable-method \"%s\"\n",
+                       nr, enable_method);
+		return -EINVAL;
+	}
+
+	/*
+	 * The processor is currently spinning, waiting for the
+	 * 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;
+
+	return 0;
+}
+
+static int __init smp_a2_probe(void)
+{
+	return cpus_weight(cpu_possible_map);
+}
+
+static struct smp_ops_t a2_smp_ops = {
+	.message_pass	= doorbell_message_pass,
+	.probe		= smp_a2_probe,
+	.kick_cpu	= smp_a2_kick_cpu,
+	.setup_cpu	= smp_a2_setup_cpu,
+};
+
+void __init a2_setup_smp(void)
+{
+	smp_ops = &a2_smp_ops;
+}
diff --git a/arch/powerpc/platforms/wsp/wsp.h b/arch/powerpc/platforms/wsp/wsp.h
new file mode 100644
index 00000000000..7c3e087fd2f
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/wsp.h
@@ -0,0 +1,17 @@
+#ifndef __WSP_H
+#define __WSP_H
+
+#include <asm/wsp.h>
+
+extern void wsp_setup_pci(void);
+extern void scom_init_wsp(void);
+
+extern void a2_setup_smp(void);
+extern int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx,
+			       struct device_node *np);
+int smp_a2_cpu_bootable(unsigned int nr);
+int __devinit smp_a2_kick_cpu(int nr);
+
+void opb_pic_init(void);
+
+#endif /*  __WSP_H */
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index d9e0515592c..3508321c450 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -7,6 +7,7 @@
  *  2 of the License, or (at your option) any later version.
  *
  */
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/irq.h>
-- 
cgit v1.2.3-70-g09d2


From a0496d450ab8c17f6c4d86979b1f6ba486fe9365 Mon Sep 17 00:00:00 2001
From: Jack Miller <jack@codezen.org>
Date: Thu, 14 Apr 2011 22:32:08 +0000
Subject: powerpc: Add early debug for WSP platforms

Signed-off-by: Jack Miller <jack@codezen.org>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/Kconfig.debug           |  5 ++++
 arch/powerpc/include/asm/reg_a2.h    |  9 +++++++
 arch/powerpc/include/asm/udbg.h      |  1 +
 arch/powerpc/kernel/exceptions-64e.S | 17 ++++++++++++
 arch/powerpc/kernel/udbg.c           |  2 ++
 arch/powerpc/kernel/udbg_16550.c     | 51 ++++++++++++++++++++++++++++++++++++
 6 files changed, 85 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 2d38a50e66b..a597dd77b90 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -267,6 +267,11 @@ config PPC_EARLY_DEBUG_USBGECKO
 	  Select this to enable early debugging for Nintendo GameCube/Wii
 	  consoles via an external USB Gecko adapter.
 
+config PPC_EARLY_DEBUG_WSP
+	bool "Early debugging via WSP's internal UART"
+	depends on PPC_WSP
+	select PPC_UDBG_16550
+
 endchoice
 
 config PPC_EARLY_DEBUG_44x_PHYSLOW
diff --git a/arch/powerpc/include/asm/reg_a2.h b/arch/powerpc/include/asm/reg_a2.h
index 3ba9c6f096f..3d52a1132f3 100644
--- a/arch/powerpc/include/asm/reg_a2.h
+++ b/arch/powerpc/include/asm/reg_a2.h
@@ -110,6 +110,15 @@
 #define TLB1_UR			ASM_CONST(0x0000000000000002)
 #define TLB1_SR			ASM_CONST(0x0000000000000001)
 
+#ifdef CONFIG_PPC_EARLY_DEBUG_WSP
+#define WSP_UART_PHYS	0xffc000c000
+/* This needs to be careful chosen to hit a !0 congruence class
+ * in the TLB since we bolt it in way 3, which is already occupied
+ * by our linear mapping primary bolted entry in CC 0.
+ */
+#define WSP_UART_VIRT	0xf000000000001000
+#endif
+
 /* A2 erativax attributes definitions */
 #define ERATIVAX_RS_IS_ALL		0x000
 #define ERATIVAX_RS_IS_TID		0x040
diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h
index 11ae699135b..58580e94a2b 100644
--- a/arch/powerpc/include/asm/udbg.h
+++ b/arch/powerpc/include/asm/udbg.h
@@ -52,6 +52,7 @@ extern void __init udbg_init_44x_as1(void);
 extern void __init udbg_init_40x_realmode(void);
 extern void __init udbg_init_cpm(void);
 extern void __init udbg_init_usbgecko(void);
+extern void __init udbg_init_wsp(void);
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_UDBG_H */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index c98e9d26062..4d0abb4930a 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -17,6 +17,7 @@
 #include <asm/cputable.h>
 #include <asm/setup.h>
 #include <asm/thread_info.h>
+#include <asm/reg_a2.h>
 #include <asm/exception-64e.h>
 #include <asm/bug.h>
 #include <asm/irqflags.h>
@@ -951,6 +952,22 @@ a2_tlbinit_after_linear_map:
 	.globl  a2_tlbinit_after_iprot_flush
 a2_tlbinit_after_iprot_flush:
 
+#ifdef CONFIG_PPC_EARLY_DEBUG_WSP
+	/* Now establish early debug mappings if applicable */
+	/* Restore the MAS0 we used for linear mapping load */
+	mtspr	SPRN_MAS0,r11
+
+	lis	r3,(MAS1_VALID | MAS1_IPROT)@h
+	ori	r3,r3,(BOOK3E_PAGESZ_4K << MAS1_TSIZE_SHIFT)
+	mtspr	SPRN_MAS1,r3
+	LOAD_REG_IMMEDIATE(r3, WSP_UART_VIRT | MAS2_I | MAS2_G)
+	mtspr	SPRN_MAS2,r3
+	LOAD_REG_IMMEDIATE(r3, WSP_UART_PHYS | MAS3_SR | MAS3_SW)
+	mtspr	SPRN_MAS7_MAS3,r3
+	/* re-use the MAS8 value from the linear mapping */
+	tlbwe
+#endif /* CONFIG_PPC_EARLY_DEBUG_WSP */
+
 	PPC_TLBILX(0,0,0)
 	sync
 	isync
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index e39cad83c88..23d65abbedc 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -62,6 +62,8 @@ void __init udbg_early_init(void)
 	udbg_init_cpm();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_USBGECKO)
 	udbg_init_usbgecko();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_WSP)
+	udbg_init_wsp();
 #endif
 
 #ifdef CONFIG_PPC_EARLY_DEBUG
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index baa33a7517b..6837f839ab7 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include <asm/udbg.h>
 #include <asm/io.h>
+#include <asm/reg_a2.h>
 
 extern u8 real_readb(volatile u8 __iomem  *addr);
 extern void real_writeb(u8 data, volatile u8 __iomem *addr);
@@ -298,3 +299,53 @@ void __init udbg_init_40x_realmode(void)
 	udbg_getc_poll = NULL;
 }
 #endif /* CONFIG_PPC_EARLY_DEBUG_40x */
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_WSP
+static void udbg_wsp_flush(void)
+{
+	if (udbg_comport) {
+		while ((readb(&udbg_comport->lsr) & LSR_THRE) == 0)
+			/* wait for idle */;
+	}
+}
+
+static void udbg_wsp_putc(char c)
+{
+	if (udbg_comport) {
+		if (c == '\n')
+			udbg_wsp_putc('\r');
+		udbg_wsp_flush();
+		writeb(c, &udbg_comport->thr); eieio();
+	}
+}
+
+static int udbg_wsp_getc(void)
+{
+	if (udbg_comport) {
+		while ((readb(&udbg_comport->lsr) & LSR_DR) == 0)
+			; /* wait for char */
+		return readb(&udbg_comport->rbr);
+	}
+	return -1;
+}
+
+static int udbg_wsp_getc_poll(void)
+{
+	if (udbg_comport)
+		if (readb(&udbg_comport->lsr) & LSR_DR)
+			return readb(&udbg_comport->rbr);
+	return -1;
+}
+
+void __init udbg_init_wsp(void)
+{
+	udbg_comport = (struct NS16550 __iomem *)WSP_UART_VIRT;
+
+	udbg_init_uart(udbg_comport, 57600, 50000000);
+
+	udbg_putc = udbg_wsp_putc;
+	udbg_flush = udbg_wsp_flush;
+	udbg_getc = udbg_wsp_getc;
+	udbg_getc_poll = udbg_wsp_getc_poll;
+}
+#endif /* CONFIG_PPC_EARLY_DEBUG_WSP */
-- 
cgit v1.2.3-70-g09d2


From af442a1baa6d00117cc7e7377ce7e6a545268684 Mon Sep 17 00:00:00 2001
From: Nishanth Aravamudan <nacc@us.ibm.com>
Date: Wed, 4 May 2011 12:54:16 +0000
Subject: powerpc: Ensure dtl buffers do not cross 4k boundary

Future releases of fimrware will enforce a requirement that DTL buffers
do not cross a 4k boundary. Commit
127493d5dc73589cbe00ea5ec8357cc2a4c0d82a satisfies this requirement for
CONFIG_VIRT_CPU_ACCOUNTING=y kernels, but if !CONFIG_VIRT_CPU_ACCOUNTING
&& CONFIG_DTL=y, the current code will fail at dtl registration time.
Fix this by making the kmem cache from
127493d5dc73589cbe00ea5ec8357cc2a4c0d82a visible outside of setup.c and
using the same cache in both dtl.c and setup.c. This requires a bit of
reorganization to ensure ordering of the kmem cache and buffer
allocations.

Note: Since firmware now limits the size of the buffer, I made
dtl_buf_entries read-only in debugfs.

Tested with upcoming firmware with the 4 combinations of
CONFIG_VIRT_CPU_ACCOUNTING and CONFIG_DTL.

Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Anton Blanchard <anton@samba.org>
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/lppaca.h      |  2 ++
 arch/powerpc/platforms/pseries/dtl.c   | 20 +++++++++++---------
 arch/powerpc/platforms/pseries/setup.c | 31 ++++++++++++++++++++++---------
 3 files changed, 35 insertions(+), 18 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index a077adc0b35..e0298d26ce5 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -210,6 +210,8 @@ struct dtl_entry {
 #define DISPATCH_LOG_BYTES	4096	/* bytes per cpu */
 #define N_DISPATCH_LOG		(DISPATCH_LOG_BYTES / sizeof(struct dtl_entry))
 
+extern struct kmem_cache *dtl_cache;
+
 /*
  * When CONFIG_VIRT_CPU_ACCOUNTING = y, the cpu accounting code controls
  * reading from the dispatch trace log.  If other code wants to consume
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index c371bc06434..e9190073bb9 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -52,10 +52,10 @@ static u8 dtl_event_mask = 0x7;
 
 
 /*
- * Size of per-cpu log buffers. Default is just under 16 pages worth.
+ * Size of per-cpu log buffers. Firmware requires that the buffer does
+ * not cross a 4k boundary.
  */
-static int dtl_buf_entries = (16 * 85);
-
+static int dtl_buf_entries = N_DISPATCH_LOG;
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 struct dtl_ring {
@@ -151,7 +151,7 @@ static int dtl_start(struct dtl *dtl)
 
 	/* Register our dtl buffer with the hypervisor. The HV expects the
 	 * buffer size to be passed in the second word of the buffer */
-	((u32 *)dtl->buf)[1] = dtl->buf_entries * sizeof(struct dtl_entry);
+	((u32 *)dtl->buf)[1] = DISPATCH_LOG_BYTES;
 
 	hwcpu = get_hard_smp_processor_id(dtl->cpu);
 	addr = __pa(dtl->buf);
@@ -196,13 +196,15 @@ static int dtl_enable(struct dtl *dtl)
 	long int rc;
 	struct dtl_entry *buf = NULL;
 
+	if (!dtl_cache)
+		return -ENOMEM;
+
 	/* only allow one reader */
 	if (dtl->buf)
 		return -EBUSY;
 
 	n_entries = dtl_buf_entries;
-	buf = kmalloc_node(n_entries * sizeof(struct dtl_entry),
-			GFP_KERNEL, cpu_to_node(dtl->cpu));
+	buf = kmem_cache_alloc_node(dtl_cache, GFP_KERNEL, cpu_to_node(dtl->cpu));
 	if (!buf) {
 		printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n",
 				__func__, dtl->cpu);
@@ -223,7 +225,7 @@ static int dtl_enable(struct dtl *dtl)
 	spin_unlock(&dtl->lock);
 
 	if (rc)
-		kfree(buf);
+		kmem_cache_free(dtl_cache, buf);
 	return rc;
 }
 
@@ -231,7 +233,7 @@ static void dtl_disable(struct dtl *dtl)
 {
 	spin_lock(&dtl->lock);
 	dtl_stop(dtl);
-	kfree(dtl->buf);
+	kmem_cache_free(dtl_cache, dtl->buf);
 	dtl->buf = NULL;
 	dtl->buf_entries = 0;
 	spin_unlock(&dtl->lock);
@@ -365,7 +367,7 @@ static int dtl_init(void)
 
 	event_mask_file = debugfs_create_x8("dtl_event_mask", 0600,
 				dtl_dir, &dtl_event_mask);
-	buf_entries_file = debugfs_create_u32("dtl_buf_entries", 0600,
+	buf_entries_file = debugfs_create_u32("dtl_buf_entries", 0400,
 				dtl_dir, &dtl_buf_entries);
 
 	if (!event_mask_file || !buf_entries_file) {
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 1689adccc6d..593acceeff9 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -278,6 +278,8 @@ static struct notifier_block pci_dn_reconfig_nb = {
 	.notifier_call = pci_dn_reconfig_notifier,
 };
 
+struct kmem_cache *dtl_cache;
+
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 /*
  * Allocate space for the dispatch trace log for all possible cpus
@@ -289,18 +291,12 @@ static int alloc_dispatch_logs(void)
 	int cpu, ret;
 	struct paca_struct *pp;
 	struct dtl_entry *dtl;
-	struct kmem_cache *dtl_cache;
 
 	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
 		return 0;
 
-	dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES,
-						DISPATCH_LOG_BYTES, 0, NULL);
-	if (!dtl_cache) {
-		pr_warn("Failed to create dispatch trace log buffer cache\n");
-		pr_warn("Stolen time statistics will be unreliable\n");
+	if (!dtl_cache)
 		return 0;
-	}
 
 	for_each_possible_cpu(cpu) {
 		pp = &paca[cpu];
@@ -334,10 +330,27 @@ static int alloc_dispatch_logs(void)
 
 	return 0;
 }
-
-early_initcall(alloc_dispatch_logs);
+#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
+static inline int alloc_dispatch_logs(void)
+{
+	return 0;
+}
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 
+static int alloc_dispatch_log_kmem_cache(void)
+{
+	dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES,
+						DISPATCH_LOG_BYTES, 0, NULL);
+	if (!dtl_cache) {
+		pr_warn("Failed to create dispatch trace log buffer cache\n");
+		pr_warn("Stolen time statistics will be unreliable\n");
+		return 0;
+	}
+
+	return alloc_dispatch_logs();
+}
+early_initcall(alloc_dispatch_log_kmem_cache);
+
 static void __init pSeries_setup_arch(void)
 {
 	/* Discover PIC type and setup ppc_md accordingly */
-- 
cgit v1.2.3-70-g09d2


From 2a2c29c1a581319f4485af55e8d628d89e8f2583 Mon Sep 17 00:00:00 2001
From: Stratos Psomadakis <psomas@cslab.ece.ntua.gr>
Date: Sat, 7 May 2011 04:11:31 +0000
Subject: powerpc/mm: Fix compiler warning in pgtable-ppc64.h
 [-Wunused-but-set-variable]

The variable 'old' is set but not used in the wrprotect functions in
arch/powerpc/include/asm/pgtable-ppc64.h, which can trigger a compiler warning.

Remove the variable, since it's not used anyway.

Signed-off-by: Stratos Psomadakis <psomas@ece.ntua.gr>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/pgtable-ppc64.h | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 2b09cd522d3..81576ee0cfb 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -257,21 +257,20 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pte_t *ptep)
 {
-	unsigned long old;
 
-       	if ((pte_val(*ptep) & _PAGE_RW) == 0)
-       		return;
-	old = pte_update(mm, addr, ptep, _PAGE_RW, 0);
+	if ((pte_val(*ptep) & _PAGE_RW) == 0)
+		return;
+
+	pte_update(mm, addr, ptep, _PAGE_RW, 0);
 }
 
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	unsigned long old;
-
 	if ((pte_val(*ptep) & _PAGE_RW) == 0)
 		return;
-	old = pte_update(mm, addr, ptep, _PAGE_RW, 1);
+
+	pte_update(mm, addr, ptep, _PAGE_RW, 1);
 }
 
 /*
-- 
cgit v1.2.3-70-g09d2


From d988f0e3f84cb8a4f85ccdbca6f6fefcc37bedcb Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Sun, 8 May 2011 21:18:38 +0000
Subject: powerpc: Simplify 4k/64k copy_page logic

To make it easier to add optimised versions of copy_page, remove
the 4kB loop for 64kB pages and just do all the work in copy_page.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/page_64.h | 19 +------------------
 arch/powerpc/kernel/ppc_ksyms.c    |  5 +----
 arch/powerpc/lib/copypage_64.S     |  7 ++++---
 3 files changed, 6 insertions(+), 25 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index 488c52eb64c..9356262fd3c 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -59,24 +59,7 @@ static __inline__ void clear_page(void *addr)
 	: "ctr", "memory");
 }
 
-extern void copy_4K_page(void *to, void *from);
-
-#ifdef CONFIG_PPC_64K_PAGES
-static inline void copy_page(void *to, void *from)
-{
-	unsigned int i;
-	for (i=0; i < (1 << (PAGE_SHIFT - 12)); i++) {
-		copy_4K_page(to, from);
-		to += 4096;
-		from += 4096;
-	}
-}
-#else /* CONFIG_PPC_64K_PAGES */
-static inline void copy_page(void *to, void *from)
-{
-	copy_4K_page(to, from);
-}
-#endif /* CONFIG_PPC_64K_PAGES */
+extern void copy_page(void *to, void *from);
 
 /* Log 2 of page table size */
 extern u64 ppc64_pft_size;
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index ef3ef566235..7d28f540200 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -54,7 +54,6 @@ extern void single_step_exception(struct pt_regs *regs);
 extern int sys_sigreturn(struct pt_regs *regs);
 
 EXPORT_SYMBOL(clear_pages);
-EXPORT_SYMBOL(copy_page);
 EXPORT_SYMBOL(ISA_DMA_THRESHOLD);
 EXPORT_SYMBOL(DMA_MODE_READ);
 EXPORT_SYMBOL(DMA_MODE_WRITE);
@@ -88,9 +87,7 @@ EXPORT_SYMBOL(__copy_tofrom_user);
 EXPORT_SYMBOL(__clear_user);
 EXPORT_SYMBOL(__strncpy_from_user);
 EXPORT_SYMBOL(__strnlen_user);
-#ifdef CONFIG_PPC64
-EXPORT_SYMBOL(copy_4K_page);
-#endif
+EXPORT_SYMBOL(copy_page);
 
 #if defined(CONFIG_PCI) && defined(CONFIG_PPC32)
 EXPORT_SYMBOL(isa_io_base);
diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S
index 4d4eeb90048..53dcb6b1b70 100644
--- a/arch/powerpc/lib/copypage_64.S
+++ b/arch/powerpc/lib/copypage_64.S
@@ -6,6 +6,7 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  */
+#include <asm/page.h>
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
@@ -15,9 +16,9 @@ PPC64_CACHES:
         .tc             ppc64_caches[TC],ppc64_caches
         .section        ".text"
 
-
-_GLOBAL(copy_4K_page)
-	li	r5,4096		/* 4K page size */
+_GLOBAL(copy_page)
+	lis	r5,PAGE_SIZE@h
+	ori	r5,r5,PAGE_SIZE@l
 BEGIN_FTR_SECTION
 	ld      r10,PPC64_CACHES@toc(r2)
 	lwz	r11,DCACHEL1LOGLINESIZE(r10)	/* log2 of cache line size */
-- 
cgit v1.2.3-70-g09d2


From be135f40899cb3334faa7d2e27025055da311ec4 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Sun, 8 May 2011 21:41:59 +0000
Subject: powerpc: Add ioremap_wc

Add ioremap_wc so drivers can request write combining on kernel
mappings.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/io.h |  5 +++++
 arch/powerpc/mm/pgtable_32.c  |  8 ++++++++
 arch/powerpc/mm/pgtable_64.c  | 11 +++++++++++
 3 files changed, 24 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 2f365f5007a..662d2edae76 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -2,6 +2,8 @@
 #define _ASM_POWERPC_IO_H
 #ifdef __KERNEL__
 
+#define ARCH_HAS_IOREMAP_WC
+
 /*
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -628,6 +630,8 @@ static inline void iosync(void)
  *
  * * ioremap_nocache is identical to ioremap
  *
+ * * ioremap_wc enables write combining
+ *
  * * iounmap undoes such a mapping and can be hooked
  *
  * * __ioremap_at (and the pending __iounmap_at) are low level functions to
@@ -648,6 +652,7 @@ static inline void iosync(void)
 extern void __iomem *ioremap(phys_addr_t address, unsigned long size);
 extern void __iomem *ioremap_flags(phys_addr_t address, unsigned long size,
 				   unsigned long flags);
+extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size);
 #define ioremap_nocache(addr, size)	ioremap((addr), (size))
 #define ioremap_prot(addr, size, prot)	ioremap_flags((addr), (size), (prot))
 
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 8dc41c0157f..fca98f8fb60 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -132,6 +132,14 @@ ioremap(phys_addr_t addr, unsigned long size)
 }
 EXPORT_SYMBOL(ioremap);
 
+void __iomem *
+ioremap_wc(phys_addr_t addr, unsigned long size)
+{
+	return __ioremap_caller(addr, size, _PAGE_NO_CACHE,
+				__builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wc);
+
 void __iomem *
 ioremap_flags(phys_addr_t addr, unsigned long size, unsigned long flags)
 {
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 88927a05cdc..1146fc6e892 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -255,6 +255,16 @@ void __iomem * ioremap(phys_addr_t addr, unsigned long size)
 	return __ioremap_caller(addr, size, flags, caller);
 }
 
+void __iomem * ioremap_wc(phys_addr_t addr, unsigned long size)
+{
+	unsigned long flags = _PAGE_NO_CACHE;
+	void *caller = __builtin_return_address(0);
+
+	if (ppc_md.ioremap)
+		return ppc_md.ioremap(addr, size, flags, caller);
+	return __ioremap_caller(addr, size, flags, caller);
+}
+
 void __iomem * ioremap_flags(phys_addr_t addr, unsigned long size,
 			     unsigned long flags)
 {
@@ -311,6 +321,7 @@ void iounmap(volatile void __iomem *token)
 }
 
 EXPORT_SYMBOL(ioremap);
+EXPORT_SYMBOL(ioremap_wc);
 EXPORT_SYMBOL(ioremap_flags);
 EXPORT_SYMBOL(__ioremap);
 EXPORT_SYMBOL(__ioremap_at);
-- 
cgit v1.2.3-70-g09d2


From 40f1ce7fb7e8b5d4d0821c0f3dc866cb1d47d99c Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Sun, 8 May 2011 21:43:47 +0000
Subject: powerpc: Remove ioremap_flags

We have a confusing number of ioremap functions. Make things just a
bit simpler by merging ioremap_flags and ioremap_prot.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/io.h             | 12 +++++-------
 arch/powerpc/lib/devres.c                 |  6 +++---
 arch/powerpc/mm/pgtable_32.c              |  4 ++--
 arch/powerpc/mm/pgtable_64.c              |  4 ++--
 arch/powerpc/platforms/ps3/spu.c          |  4 ++--
 arch/powerpc/sysdev/axonram.c             |  2 +-
 arch/powerpc/sysdev/fsl_85xx_cache_sram.c |  4 ++--
 7 files changed, 17 insertions(+), 19 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 662d2edae76..45698d55cd6 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -624,9 +624,8 @@ static inline void iosync(void)
  * * ioremap is the standard one and provides non-cacheable guarded mappings
  *   and can be hooked by the platform via ppc_md
  *
- * * ioremap_flags allows to specify the page flags as an argument and can
- *   also be hooked by the platform via ppc_md. ioremap_prot is the exact
- *   same thing as ioremap_flags.
+ * * ioremap_prot allows to specify the page flags as an argument and can
+ *   also be hooked by the platform via ppc_md.
  *
  * * ioremap_nocache is identical to ioremap
  *
@@ -639,7 +638,7 @@ static inline void iosync(void)
  *   currently be hooked. Must be page aligned.
  *
  * * __ioremap is the low level implementation used by ioremap and
- *   ioremap_flags and cannot be hooked (but can be used by a hook on one
+ *   ioremap_prot and cannot be hooked (but can be used by a hook on one
  *   of the previous ones)
  *
  * * __ioremap_caller is the same as above but takes an explicit caller
@@ -650,11 +649,10 @@ static inline void iosync(void)
  *
  */
 extern void __iomem *ioremap(phys_addr_t address, unsigned long size);
-extern void __iomem *ioremap_flags(phys_addr_t address, unsigned long size,
-				   unsigned long flags);
+extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size,
+				  unsigned long flags);
 extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size);
 #define ioremap_nocache(addr, size)	ioremap((addr), (size))
-#define ioremap_prot(addr, size, prot)	ioremap_flags((addr), (size), (prot))
 
 extern void iounmap(volatile void __iomem *addr);
 
diff --git a/arch/powerpc/lib/devres.c b/arch/powerpc/lib/devres.c
index deac4d30daf..e91615abae6 100644
--- a/arch/powerpc/lib/devres.c
+++ b/arch/powerpc/lib/devres.c
@@ -9,11 +9,11 @@
 
 #include <linux/device.h>	/* devres_*(), devm_ioremap_release() */
 #include <linux/gfp.h>
-#include <linux/io.h>		/* ioremap_flags() */
+#include <linux/io.h>		/* ioremap_prot() */
 #include <linux/module.h>	/* EXPORT_SYMBOL() */
 
 /**
- * devm_ioremap_prot - Managed ioremap_flags()
+ * devm_ioremap_prot - Managed ioremap_prot()
  * @dev: Generic device to remap IO address for
  * @offset: BUS offset to map
  * @size: Size of map
@@ -31,7 +31,7 @@ void __iomem *devm_ioremap_prot(struct device *dev, resource_size_t offset,
 	if (!ptr)
 		return NULL;
 
-	addr = ioremap_flags(offset, size, flags);
+	addr = ioremap_prot(offset, size, flags);
 	if (addr) {
 		*ptr = addr;
 		devres_add(dev, ptr);
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index fca98f8fb60..51f87956f8f 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -141,7 +141,7 @@ ioremap_wc(phys_addr_t addr, unsigned long size)
 EXPORT_SYMBOL(ioremap_wc);
 
 void __iomem *
-ioremap_flags(phys_addr_t addr, unsigned long size, unsigned long flags)
+ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
 {
 	/* writeable implies dirty for kernel addresses */
 	if (flags & _PAGE_RW)
@@ -160,7 +160,7 @@ ioremap_flags(phys_addr_t addr, unsigned long size, unsigned long flags)
 
 	return __ioremap_caller(addr, size, flags, __builtin_return_address(0));
 }
-EXPORT_SYMBOL(ioremap_flags);
+EXPORT_SYMBOL(ioremap_prot);
 
 void __iomem *
 __ioremap(phys_addr_t addr, unsigned long size, unsigned long flags)
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 1146fc6e892..6e595f6496d 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -265,7 +265,7 @@ void __iomem * ioremap_wc(phys_addr_t addr, unsigned long size)
 	return __ioremap_caller(addr, size, flags, caller);
 }
 
-void __iomem * ioremap_flags(phys_addr_t addr, unsigned long size,
+void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size,
 			     unsigned long flags)
 {
 	void *caller = __builtin_return_address(0);
@@ -322,7 +322,7 @@ void iounmap(volatile void __iomem *token)
 
 EXPORT_SYMBOL(ioremap);
 EXPORT_SYMBOL(ioremap_wc);
-EXPORT_SYMBOL(ioremap_flags);
+EXPORT_SYMBOL(ioremap_prot);
 EXPORT_SYMBOL(__ioremap);
 EXPORT_SYMBOL(__ioremap_at);
 EXPORT_SYMBOL(iounmap);
diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c
index 39a472e9e80..375a9f92158 100644
--- a/arch/powerpc/platforms/ps3/spu.c
+++ b/arch/powerpc/platforms/ps3/spu.c
@@ -197,7 +197,7 @@ static void spu_unmap(struct spu *spu)
  * The current HV requires the spu shadow regs to be mapped with the
  * PTE page protection bits set as read-only (PP=3).  This implementation
  * uses the low level __ioremap() to bypass the page protection settings
- * inforced by ioremap_flags() to get the needed PTE bits set for the
+ * inforced by ioremap_prot() to get the needed PTE bits set for the
  * shadow regs.
  */
 
@@ -214,7 +214,7 @@ static int __init setup_areas(struct spu *spu)
 		goto fail_ioremap;
 	}
 
-	spu->local_store = (__force void *)ioremap_flags(spu->local_store_phys,
+	spu->local_store = (__force void *)ioremap_prot(spu->local_store_phys,
 		LS_SIZE, _PAGE_NO_CACHE);
 
 	if (!spu->local_store) {
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index 1636dd89670..bd0d54060b9 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -216,7 +216,7 @@ static int axon_ram_probe(struct platform_device *device)
 			AXON_RAM_DEVICE_NAME, axon_ram_bank_id, bank->size >> 20);
 
 	bank->ph_addr = resource.start;
-	bank->io_addr = (unsigned long) ioremap_flags(
+	bank->io_addr = (unsigned long) ioremap_prot(
 			bank->ph_addr, bank->size, _PAGE_NO_CACHE);
 	if (bank->io_addr == 0) {
 		dev_err(&device->dev, "ioremap() failed\n");
diff --git a/arch/powerpc/sysdev/fsl_85xx_cache_sram.c b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c
index 54fb1922fe3..11641589917 100644
--- a/arch/powerpc/sysdev/fsl_85xx_cache_sram.c
+++ b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c
@@ -106,10 +106,10 @@ int __init instantiate_cache_sram(struct platform_device *dev,
 		goto out_free;
 	}
 
-	cache_sram->base_virt = ioremap_flags(cache_sram->base_phys,
+	cache_sram->base_virt = ioremap_prot(cache_sram->base_phys,
 				cache_sram->size, _PAGE_COHERENT | PAGE_KERNEL);
 	if (!cache_sram->base_virt) {
-		dev_err(&dev->dev, "%s: ioremap_flags failed\n",
+		dev_err(&dev->dev, "%s: ioremap_prot failed\n",
 				dev->dev.of_node->full_name);
 		ret = -ENOMEM;
 		goto out_release;
-- 
cgit v1.2.3-70-g09d2


From e04763713286b1e00e1c2a33fe2741caf9470f2b Mon Sep 17 00:00:00 2001
From: Milton Miller <miltonm@bga.com>
Date: Tue, 10 May 2011 19:29:06 +0000
Subject: powerpc: Remove call sites of MSG_ALL_BUT_SELF

The only user of MSG_ALL_BUT_SELF in the whole kernel tree is powerpc,
and it only uses it to start the debugger. Both debuggers always call
smp_send_debugger_break with MSG_ALL_BUT_SELF, and only mpic can do
anything more optimal than a loop over all online cpus, but all message
passing implementations have to code for this special delivery target.

Convert smp_send_debugger_break to take void and loop calling the smp_ops
message_pass function for each of the other cpus in the online cpumask.

Use raw_smp_processor_id() because we are either entering the debugger
or trying to start kdump and the additional warning it not useful were
it to trigger.

Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/smp.h |  2 +-
 arch/powerpc/kernel/kgdb.c     |  2 +-
 arch/powerpc/kernel/smp.c      | 19 +++++++++++++------
 arch/powerpc/xmon/xmon.c       |  2 +-
 4 files changed, 16 insertions(+), 9 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 50873493a97..91472c56800 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -35,7 +35,7 @@ extern void cpu_die(void);
 
 #ifdef CONFIG_SMP
 
-extern void smp_send_debugger_break(int cpu);
+extern void smp_send_debugger_break(void);
 extern void smp_message_recv(int);
 extern void start_secondary_resume(void);
 
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 42850ee00ad..bd9d35f59cf 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -109,7 +109,7 @@ static int kgdb_call_nmi_hook(struct pt_regs *regs)
 #ifdef CONFIG_SMP
 void kgdb_roundup_cpus(unsigned long flags)
 {
-	smp_send_debugger_break(MSG_ALL_BUT_SELF);
+	smp_send_debugger_break();
 }
 #endif
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 87517ab6d36..b7441144692 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -218,11 +218,18 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 		smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION);
 }
 
-#ifdef CONFIG_DEBUGGER
-void smp_send_debugger_break(int cpu)
+#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
+void smp_send_debugger_break(void)
 {
-	if (likely(smp_ops))
-		smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK);
+	int cpu;
+	int me = raw_smp_processor_id();
+
+	if (unlikely(!smp_ops))
+		return;
+
+	for_each_online_cpu(cpu)
+		if (cpu != me)
+			smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK);
 }
 #endif
 
@@ -230,9 +237,9 @@ void smp_send_debugger_break(int cpu)
 void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
 {
 	crash_ipi_function_ptr = crash_ipi_callback;
-	if (crash_ipi_callback && smp_ops) {
+	if (crash_ipi_callback) {
 		mb();
-		smp_ops->message_pass(MSG_ALL_BUT_SELF, PPC_MSG_DEBUGGER_BREAK);
+		smp_send_debugger_break();
 	}
 }
 #endif
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 91309c5c00d..42541bbcc7f 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -437,7 +437,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 		xmon_owner = cpu;
 		mb();
 		if (ncpus > 1) {
-			smp_send_debugger_break(MSG_ALL_BUT_SELF);
+			smp_send_debugger_break();
 			/* wait for other cpus to come in */
 			for (timeout = 100000000; timeout != 0; --timeout) {
 				if (cpumask_weight(&cpus_in_xmon) >= ncpus)
-- 
cgit v1.2.3-70-g09d2


From f1072939b6dd01d038d47db0bdc01b33e5f90f28 Mon Sep 17 00:00:00 2001
From: Milton Miller <miltonm@bga.com>
Date: Tue, 10 May 2011 19:29:10 +0000
Subject: powerpc: Remove checks for MSG_ALL and MSG_ALL_BUT_SELF

Now that smp_ops->smp_message_pass is always called with an (online) cpu
number for the target remove the checks for MSG_ALL and MSG_ALL_BUT_SELF.

Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/dbell.h       |  2 +-
 arch/powerpc/include/asm/machdep.h     |  2 +-
 arch/powerpc/include/asm/xics.h        |  2 +-
 arch/powerpc/kernel/dbell.c            | 29 +++++------------------------
 arch/powerpc/platforms/cell/beat_smp.c | 18 +-----------------
 arch/powerpc/platforms/cell/smp.c      | 18 +-----------------
 arch/powerpc/platforms/iseries/smp.c   | 18 +-----------------
 arch/powerpc/platforms/powermac/smp.c  | 17 +++--------------
 arch/powerpc/platforms/ps3/smp.c       | 22 +++-------------------
 arch/powerpc/sysdev/mpic.c             | 20 ++------------------
 arch/powerpc/sysdev/xics/icp-hv.c      | 18 +-----------------
 arch/powerpc/sysdev/xics/icp-native.c  | 18 +-----------------
 12 files changed, 21 insertions(+), 163 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h
index 0893ab9343a..3269eb49640 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -27,7 +27,7 @@ enum ppc_dbell {
 	PPC_G_DBELL_MC = 4,	/* guest mcheck doorbell */
 };
 
-extern void doorbell_message_pass(int target, int msg);
+extern void doorbell_message_pass(int cpu, int msg);
 extern void doorbell_exception(struct pt_regs *regs);
 extern void doorbell_check_self(void);
 extern void doorbell_setup_this_cpu(void);
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index c6345acf166..b0802a5bd74 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -31,7 +31,7 @@ struct kimage;
 
 #ifdef CONFIG_SMP
 struct smp_ops_t {
-	void  (*message_pass)(int target, int msg);
+	void  (*message_pass)(int cpu, int msg);
 	int   (*probe)(void);
 	int   (*kick_cpu)(int nr);
 	void  (*setup_cpu)(int nr);
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index 6c06306c410..1750c8dae1f 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -40,7 +40,7 @@ struct icp_ops {
 	void (*teardown_cpu)(void);
 	void (*flush_ipi)(void);
 #ifdef CONFIG_SMP
-	void (*message_pass)(int target, int msg);
+	void (*message_pass)(int cpu, int msg);
 	irq_handler_t ipi_action;
 #endif
 };
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 3307a52d797..e49b24c8413 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -34,32 +34,13 @@ void doorbell_setup_this_cpu(void)
 	info->tag = mfspr(SPRN_PIR) & 0x3fff;
 }
 
-void doorbell_message_pass(int target, int msg)
+void doorbell_message_pass(int cpu, int msg)
 {
 	struct doorbell_cpu_info *info;
-	int i;
-
-	if (target < NR_CPUS) {
-		info = &per_cpu(doorbell_cpu_info, target);
-		set_bit(msg, &info->messages);
-		ppc_msgsnd(PPC_DBELL, 0, info->tag);
-	}
-	else if (target == MSG_ALL_BUT_SELF) {
-		for_each_online_cpu(i) {
-			if (i == smp_processor_id())
-				continue;
-			info = &per_cpu(doorbell_cpu_info, i);
-			set_bit(msg, &info->messages);
-			ppc_msgsnd(PPC_DBELL, 0, info->tag);
-		}
-	}
-	else { /* target == MSG_ALL */
-		for_each_online_cpu(i) {
-			info = &per_cpu(doorbell_cpu_info, i);
-			set_bit(msg, &info->messages);
-		}
-		ppc_msgsnd(PPC_DBELL, PPC_DBELL_MSG_BRDCAST, 0);
-	}
+
+	info = &per_cpu(doorbell_cpu_info, cpu);
+	set_bit(msg, &info->messages);
+	ppc_msgsnd(PPC_DBELL, 0, info->tag);
 }
 
 void doorbell_exception(struct pt_regs *regs)
diff --git a/arch/powerpc/platforms/cell/beat_smp.c b/arch/powerpc/platforms/cell/beat_smp.c
index 3e86acbb0fb..23bbe6e08c8 100644
--- a/arch/powerpc/platforms/cell/beat_smp.c
+++ b/arch/powerpc/platforms/cell/beat_smp.c
@@ -67,22 +67,6 @@ static inline int __devinit smp_startup_cpu(unsigned int lcpu)
 	return 0;
 }
 
-static void smp_beatic_message_pass(int target, int msg)
-{
-	unsigned int i;
-
-	if (target < NR_CPUS) {
-		beatic_cause_IPI(target, msg);
-	} else {
-		for_each_online_cpu(i) {
-			if (target == MSG_ALL_BUT_SELF
-			    && i == smp_processor_id())
-				continue;
-			beatic_cause_IPI(i, msg);
-		}
-	}
-}
-
 static int __init smp_beatic_probe(void)
 {
 	return cpumask_weight(cpu_possible_mask);
@@ -105,7 +89,7 @@ static int smp_celleb_cpu_bootable(unsigned int nr)
 	return 1;
 }
 static struct smp_ops_t bpa_beatic_smp_ops = {
-	.message_pass	= smp_beatic_message_pass,
+	.message_pass	= beatic_cause_IPI,
 	.probe		= smp_beatic_probe,
 	.kick_cpu	= smp_celleb_kick_cpu,
 	.setup_cpu	= smp_beatic_setup_cpu,
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
index a2161b91b0b..d176e6148e3 100644
--- a/arch/powerpc/platforms/cell/smp.c
+++ b/arch/powerpc/platforms/cell/smp.c
@@ -103,22 +103,6 @@ static inline int __devinit smp_startup_cpu(unsigned int lcpu)
 	return 1;
 }
 
-static void smp_iic_message_pass(int target, int msg)
-{
-	unsigned int i;
-
-	if (target < NR_CPUS) {
-		iic_cause_IPI(target, msg);
-	} else {
-		for_each_online_cpu(i) {
-			if (target == MSG_ALL_BUT_SELF
-			    && i == smp_processor_id())
-				continue;
-			iic_cause_IPI(i, msg);
-		}
-	}
-}
-
 static int __init smp_iic_probe(void)
 {
 	iic_request_IPIs();
@@ -168,7 +152,7 @@ static int smp_cell_cpu_bootable(unsigned int nr)
 	return 1;
 }
 static struct smp_ops_t bpa_iic_smp_ops = {
-	.message_pass	= smp_iic_message_pass,
+	.message_pass	= iic_cause_IPI,
 	.probe		= smp_iic_probe,
 	.kick_cpu	= smp_cell_kick_cpu,
 	.setup_cpu	= smp_cell_setup_cpu,
diff --git a/arch/powerpc/platforms/iseries/smp.c b/arch/powerpc/platforms/iseries/smp.c
index 02a677a1f91..dcdbc5dc5aa 100644
--- a/arch/powerpc/platforms/iseries/smp.c
+++ b/arch/powerpc/platforms/iseries/smp.c
@@ -59,28 +59,12 @@ void iSeries_smp_message_recv(void)
 			smp_message_recv(msg);
 }
 
-static inline void smp_iSeries_do_message(int cpu, int msg)
+static void smp_iSeries_message_pass(int cpu, int msg)
 {
 	set_bit(msg, &iSeries_smp_message[cpu]);
 	HvCall_sendIPI(&(paca[cpu]));
 }
 
-static void smp_iSeries_message_pass(int target, int msg)
-{
-	int i;
-
-	if (target < NR_CPUS)
-		smp_iSeries_do_message(target, msg);
-	else {
-		for_each_online_cpu(i) {
-			if ((target == MSG_ALL_BUT_SELF) &&
-					(i == smp_processor_id()))
-				continue;
-			smp_iSeries_do_message(i, msg);
-		}
-	}
-}
-
 static int smp_iSeries_probe(void)
 {
 	return cpumask_weight(cpu_possible_mask);
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 621d4b7755f..c49e71926a5 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -186,21 +186,10 @@ irqreturn_t psurge_primary_intr(int irq, void *d)
 	return IRQ_HANDLED;
 }
 
-static void smp_psurge_message_pass(int target, int msg)
+static void smp_psurge_message_pass(int cpu, int msg)
 {
-	int i;
-
-	if (num_online_cpus() < 2)
-		return;
-
-	for_each_online_cpu(i) {
-		if (target == MSG_ALL
-		    || (target == MSG_ALL_BUT_SELF && i != smp_processor_id())
-		    || target == i) {
-			set_bit(msg, &psurge_smp_message[i]);
-			psurge_set_ipi(i);
-		}
-	}
+	set_bit(msg, &psurge_smp_message[cpu]);
+	psurge_set_ipi(cpu);
 }
 
 /*
diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c
index 51ffde40af2..4c44794faac 100644
--- a/arch/powerpc/platforms/ps3/smp.c
+++ b/arch/powerpc/platforms/ps3/smp.c
@@ -39,7 +39,7 @@
 #define MSG_COUNT 4
 static DEFINE_PER_CPU(unsigned int [MSG_COUNT], ps3_ipi_virqs);
 
-static void do_message_pass(int target, int msg)
+static void ps3_smp_message_pass(int cpu, int msg)
 {
 	int result;
 	unsigned int virq;
@@ -49,28 +49,12 @@ static void do_message_pass(int target, int msg)
 		return;
 	}
 
-	virq = per_cpu(ps3_ipi_virqs, target)[msg];
+	virq = per_cpu(ps3_ipi_virqs, cpu)[msg];
 	result = ps3_send_event_locally(virq);
 
 	if (result)
 		DBG("%s:%d: ps3_send_event_locally(%d, %d) failed"
-			" (%d)\n", __func__, __LINE__, target, msg, result);
-}
-
-static void ps3_smp_message_pass(int target, int msg)
-{
-	int cpu;
-
-	if (target < NR_CPUS)
-		do_message_pass(target, msg);
-	else if (target == MSG_ALL_BUT_SELF) {
-		for_each_online_cpu(cpu)
-			if (cpu != smp_processor_id())
-				do_message_pass(cpu, msg);
-	} else {
-		for_each_online_cpu(cpu)
-			do_message_pass(cpu, msg);
-	}
+			" (%d)\n", __func__, __LINE__, cpu, msg, result);
 }
 
 static int ps3_smp_probe(void)
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 116695b7a5c..68ea50c4190 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -1628,31 +1628,15 @@ static void mpic_send_ipi(unsigned int ipi_no, const struct cpumask *cpu_mask)
 		       mpic_physmask(cpumask_bits(cpu_mask)[0]));
 }
 
-void smp_mpic_message_pass(int target, int msg)
+void smp_mpic_message_pass(int cpu, int msg)
 {
-	cpumask_var_t tmp;
-
 	/* make sure we're sending something that translates to an IPI */
 	if ((unsigned int)msg > 3) {
 		printk("SMP %d: smp_message_pass: unknown msg %d\n",
 		       smp_processor_id(), msg);
 		return;
 	}
-	switch (target) {
-	case MSG_ALL:
-		mpic_send_ipi(msg, cpu_online_mask);
-		break;
-	case MSG_ALL_BUT_SELF:
-		alloc_cpumask_var(&tmp, GFP_NOWAIT);
-		cpumask_andnot(tmp, cpu_online_mask,
-			       cpumask_of(smp_processor_id()));
-		mpic_send_ipi(msg, tmp);
-		free_cpumask_var(tmp);
-		break;
-	default:
-		mpic_send_ipi(msg, cpumask_of(target));
-		break;
-	}
+	mpic_send_ipi(msg, cpumask_of(cpu));
 }
 
 int __init smp_mpic_probe(void)
diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index 76e87245bbf..234764c189a 100644
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -118,7 +118,7 @@ static void icp_hv_set_cpu_priority(unsigned char cppr)
 
 #ifdef CONFIG_SMP
 
-static inline void icp_hv_do_message(int cpu, int msg)
+static void icp_hv_message_pass(int cpu, int msg)
 {
 	unsigned long *tgt = &per_cpu(xics_ipi_message, cpu);
 
@@ -127,22 +127,6 @@ static inline void icp_hv_do_message(int cpu, int msg)
 	icp_hv_set_qirr(cpu, IPI_PRIORITY);
 }
 
-static void icp_hv_message_pass(int target, int msg)
-{
-	unsigned int i;
-
-	if (target < NR_CPUS) {
-		icp_hv_do_message(target, msg);
-	} else {
-		for_each_online_cpu(i) {
-			if (target == MSG_ALL_BUT_SELF
-			    && i == smp_processor_id())
-				continue;
-			icp_hv_do_message(i, msg);
-		}
-	}
-}
-
 static irqreturn_t icp_hv_ipi_action(int irq, void *dev_id)
 {
 	int cpu = smp_processor_id();
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 3508321c450..246500eefbf 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -134,7 +134,7 @@ static unsigned int icp_native_get_irq(void)
 
 #ifdef CONFIG_SMP
 
-static inline void icp_native_do_message(int cpu, int msg)
+static void icp_native_message_pass(int cpu, int msg)
 {
 	unsigned long *tgt = &per_cpu(xics_ipi_message, cpu);
 
@@ -143,22 +143,6 @@ static inline void icp_native_do_message(int cpu, int msg)
 	icp_native_set_qirr(cpu, IPI_PRIORITY);
 }
 
-static void icp_native_message_pass(int target, int msg)
-{
-	unsigned int i;
-
-	if (target < NR_CPUS) {
-		icp_native_do_message(target, msg);
-	} else {
-		for_each_online_cpu(i) {
-			if (target == MSG_ALL_BUT_SELF
-			    && i == smp_processor_id())
-				continue;
-			icp_native_do_message(i, msg);
-		}
-	}
-}
-
 static irqreturn_t icp_native_ipi_action(int irq, void *dev_id)
 {
 	int cpu = smp_processor_id();
-- 
cgit v1.2.3-70-g09d2


From a56555e573d3740d588d912aada506d57759cf5d Mon Sep 17 00:00:00 2001
From: Milton Miller <miltonm@bga.com>
Date: Tue, 10 May 2011 19:29:24 +0000
Subject: powerpc: Remove alloc_maybe_bootmem for zalloc version

Replace all remaining callers of alloc_maybe_bootmem with
zalloc_maybe_bootmem.   The callsite in pci_dn is followed with a
memset to clear the memory, and not zeroing at the other callsites
in the celleb fake pci code could lead to following uninitialized
memory as pointers or even freeing said pointers on error paths.

Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/system.h        | 2 --
 arch/powerpc/kernel/pci_dn.c             | 3 +--
 arch/powerpc/lib/alloc.c                 | 8 --------
 arch/powerpc/platforms/cell/celleb_pci.c | 6 +++---
 4 files changed, 4 insertions(+), 15 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h
index 5e474ddd227..2dc595dda03 100644
--- a/arch/powerpc/include/asm/system.h
+++ b/arch/powerpc/include/asm/system.h
@@ -219,8 +219,6 @@ extern int mem_init_done;	/* set on boot once kmalloc can be called */
 extern int init_bootmem_done;	/* set once bootmem is available */
 extern phys_addr_t memory_limit;
 extern unsigned long klimit;
-
-extern void *alloc_maybe_bootmem(size_t size, gfp_t mask);
 extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
 
 extern int powersave_nap;	/* set if nap mode can be used in idle loop */
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index d225d99fe39..6baabc13306 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -43,10 +43,9 @@ void * __devinit update_dn_pci_info(struct device_node *dn, void *data)
 	const u32 *regs;
 	struct pci_dn *pdn;
 
-	pdn = alloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL);
+	pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL);
 	if (pdn == NULL)
 		return NULL;
-	memset(pdn, 0, sizeof(*pdn));
 	dn->data = pdn;
 	pdn->node = dn;
 	pdn->phb = phb;
diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c
index f53e09c7dac..13b676c20d1 100644
--- a/arch/powerpc/lib/alloc.c
+++ b/arch/powerpc/lib/alloc.c
@@ -6,14 +6,6 @@
 
 #include <asm/system.h>
 
-void * __init_refok alloc_maybe_bootmem(size_t size, gfp_t mask)
-{
-	if (mem_init_done)
-		return kmalloc(size, mask);
-	else
-		return alloc_bootmem(size);
-}
-
 void * __init_refok zalloc_maybe_bootmem(size_t size, gfp_t mask)
 {
 	void *p;
diff --git a/arch/powerpc/platforms/cell/celleb_pci.c b/arch/powerpc/platforms/cell/celleb_pci.c
index 2904b0a6b2c..5822141aa63 100644
--- a/arch/powerpc/platforms/cell/celleb_pci.c
+++ b/arch/powerpc/platforms/cell/celleb_pci.c
@@ -319,7 +319,7 @@ static int __init celleb_setup_fake_pci_device(struct device_node *node,
 
 	size = 256;
 	config = &private->fake_config[devno][fn];
-	*config = alloc_maybe_bootmem(size, GFP_KERNEL);
+	*config = zalloc_maybe_bootmem(size, GFP_KERNEL);
 	if (*config == NULL) {
 		printk(KERN_ERR "PCI: "
 		       "not enough memory for fake configuration space\n");
@@ -330,7 +330,7 @@ static int __init celleb_setup_fake_pci_device(struct device_node *node,
 
 	size = sizeof(struct celleb_pci_resource);
 	res = &private->res[devno][fn];
-	*res = alloc_maybe_bootmem(size, GFP_KERNEL);
+	*res = zalloc_maybe_bootmem(size, GFP_KERNEL);
 	if (*res == NULL) {
 		printk(KERN_ERR
 		       "PCI: not enough memory for resource data space\n");
@@ -431,7 +431,7 @@ static int __init phb_set_bus_ranges(struct device_node *dev,
 static void __init celleb_alloc_private_mem(struct pci_controller *hose)
 {
 	hose->private_data =
-		alloc_maybe_bootmem(sizeof(struct celleb_pci_private),
+		zalloc_maybe_bootmem(sizeof(struct celleb_pci_private),
 			GFP_KERNEL);
 }
 
-- 
cgit v1.2.3-70-g09d2


From 17f9c8a73bac2c7dfe28a520516ea6b8bbbe977e Mon Sep 17 00:00:00 2001
From: Milton Miller <miltonm@bga.com>
Date: Tue, 10 May 2011 19:29:35 +0000
Subject: powerpc: Move smp_ops_t from machdep.h to smp.h

I can't see any reason these functions are needed by machdep.h
and they are all hidden by CONFIG_SMP with no UP alternative.

Also move the declarations for the fallback timebase ops, which
are used to fill in the smp ops.

Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/machdep.h | 21 ---------------------
 arch/powerpc/include/asm/smp.h     | 15 +++++++++++++++
 2 files changed, 15 insertions(+), 21 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index b0802a5bd74..47cacddb14c 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -29,21 +29,6 @@ struct file;
 struct pci_controller;
 struct kimage;
 
-#ifdef CONFIG_SMP
-struct smp_ops_t {
-	void  (*message_pass)(int cpu, int msg);
-	int   (*probe)(void);
-	int   (*kick_cpu)(int nr);
-	void  (*setup_cpu)(int nr);
-	void  (*bringup_done)(void);
-	void  (*take_timebase)(void);
-	void  (*give_timebase)(void);
-	int   (*cpu_disable)(void);
-	void  (*cpu_die)(unsigned int nr);
-	int   (*cpu_bootable)(unsigned int nr);
-};
-#endif
-
 struct machdep_calls {
 	char		*name;
 #ifdef CONFIG_PPC64
@@ -312,12 +297,6 @@ extern sys_ctrler_t sys_ctrler;
 
 #endif /* CONFIG_PPC_PMAC */
 
-#ifdef CONFIG_SMP
-/* Poor default implementations */
-extern void __devinit smp_generic_give_timebase(void);
-extern void __devinit smp_generic_take_timebase(void);
-#endif /* CONFIG_SMP */
-
 
 /* Functions to produce codes on the leds.
  * The SRC code should be unique for the message category and should
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 91472c56800..6f7c95c0027 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -35,9 +35,24 @@ extern void cpu_die(void);
 
 #ifdef CONFIG_SMP
 
+struct smp_ops_t {
+	void  (*message_pass)(int cpu, int msg);
+	int   (*probe)(void);
+	int   (*kick_cpu)(int nr);
+	void  (*setup_cpu)(int nr);
+	void  (*bringup_done)(void);
+	void  (*take_timebase)(void);
+	void  (*give_timebase)(void);
+	int   (*cpu_disable)(void);
+	void  (*cpu_die)(unsigned int nr);
+	int   (*cpu_bootable)(unsigned int nr);
+};
+
 extern void smp_send_debugger_break(void);
 extern void smp_message_recv(int);
 extern void start_secondary_resume(void);
+extern void __devinit smp_generic_give_timebase(void);
+extern void __devinit smp_generic_take_timebase(void);
 
 DECLARE_PER_CPU(unsigned int, cpu_pvr);
 
-- 
cgit v1.2.3-70-g09d2


From 23d72bfd8f9f24aa9efafed3586a99f5669c23d7 Mon Sep 17 00:00:00 2001
From: Milton Miller <miltonm@bga.com>
Date: Tue, 10 May 2011 19:29:39 +0000
Subject: powerpc: Consolidate ipi message mux and demux

Consolidate the mux and demux of ipi messages into smp.c and call
a new smp_ops callback to actually trigger the ipi.

The powerpc architecture code is optimised for having 4 distinct
ipi triggers, which are mapped to 4 distinct messages (ipi many, ipi
single, scheduler ipi, and enter debugger).  However, several interrupt
controllers only provide a single software triggered interrupt that
can be delivered to each cpu.  To resolve this limitation, each smp_ops
implementation created a per-cpu variable that is manipulated with atomic
bitops.  Since these lines will be contended they are optimialy marked as
shared_aligned and take a full cache line for each cpu.  Distro kernels
may have 2 or 3 of these in their config, each taking per-cpu space
even though at most one will be in use.

This consolidation removes smp_message_recv and replaces the single call
actions cases with direct calls from the common message recognition loop.
The complicated debugger ipi case with its muxed crash handling code is
moved to debug_ipi_action which is now called from the demux code (instead
of the multi-message action calling smp_message_recv).

I put a call to reschedule_action to increase the likelyhood of correctly
merging the anticipated scheduler_ipi() hook coming from the scheduler
tree; that single required call can be inlined later.

The actual message decode is a copy of the old pseries xics code with its
memory barriers and cache line spacing, augmented with a per-cpu unsigned
long based on the book-e doorbell code.  The optional data is set via a
callback from the implementation and is passed to the new cause-ipi hook
along with the logical cpu number.  While currently only the doorbell
implemntation uses this data it should be almost zero cost to retrieve and
pass it -- it adds a single register load for the argument from the same
cache line to which we just completed a store and the register is dead
on return from the call.  I extended the data element from unsigned int
to unsigned long in case some other code wanted to associate a pointer.

The doorbell check_self is replaced by a call to smp_muxed_ipi_resend,
conditioned on the CPU_DBELL feature.  The ifdef guard could be relaxed
to CONFIG_SMP but I left it with BOOKE for now.

Also, the doorbell interrupt vector for book-e was not calling irq_enter
and irq_exit, which throws off cpu accounting and causes code to not
realize it is running in interrupt context.  Add the missing calls.

Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/dbell.h        |  3 +-
 arch/powerpc/include/asm/smp.h          | 16 ++++--
 arch/powerpc/include/asm/xics.h         |  2 +-
 arch/powerpc/kernel/dbell.c             | 46 +++-------------
 arch/powerpc/kernel/irq.c               |  4 +-
 arch/powerpc/kernel/smp.c               | 94 ++++++++++++++++++++++-----------
 arch/powerpc/platforms/85xx/smp.c       |  6 ++-
 arch/powerpc/platforms/cell/interrupt.c | 16 +++++-
 arch/powerpc/platforms/iseries/irq.c    |  3 +-
 arch/powerpc/platforms/iseries/smp.c    | 23 ++------
 arch/powerpc/platforms/iseries/smp.h    |  6 ---
 arch/powerpc/platforms/powermac/smp.c   | 27 +++-------
 arch/powerpc/platforms/pseries/smp.c    |  3 +-
 arch/powerpc/platforms/wsp/smp.c        |  3 +-
 arch/powerpc/sysdev/xics/icp-hv.c       | 10 ++--
 arch/powerpc/sysdev/xics/icp-native.c   | 10 ++--
 arch/powerpc/sysdev/xics/xics-common.c  | 30 +----------
 17 files changed, 126 insertions(+), 176 deletions(-)
 delete mode 100644 arch/powerpc/platforms/iseries/smp.h

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h
index 3269eb49640..9c70d0ca96d 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -27,9 +27,8 @@ enum ppc_dbell {
 	PPC_G_DBELL_MC = 4,	/* guest mcheck doorbell */
 };
 
-extern void doorbell_message_pass(int cpu, int msg);
+extern void doorbell_cause_ipi(int cpu, unsigned long data);
 extern void doorbell_exception(struct pt_regs *regs);
-extern void doorbell_check_self(void);
 extern void doorbell_setup_this_cpu(void);
 
 static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag)
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 6f7c95c0027..26f861560c5 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -20,6 +20,7 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/kernel.h>
+#include <linux/irqreturn.h>
 
 #ifndef __ASSEMBLY__
 
@@ -37,6 +38,7 @@ extern void cpu_die(void);
 
 struct smp_ops_t {
 	void  (*message_pass)(int cpu, int msg);
+	void  (*cause_ipi)(int cpu, unsigned long data);
 	int   (*probe)(void);
 	int   (*kick_cpu)(int nr);
 	void  (*setup_cpu)(int nr);
@@ -49,7 +51,6 @@ struct smp_ops_t {
 };
 
 extern void smp_send_debugger_break(void);
-extern void smp_message_recv(int);
 extern void start_secondary_resume(void);
 extern void __devinit smp_generic_give_timebase(void);
 extern void __devinit smp_generic_take_timebase(void);
@@ -109,13 +110,16 @@ extern int cpu_to_core_id(int cpu);
 #define PPC_MSG_CALL_FUNC_SINGLE	2
 #define PPC_MSG_DEBUGGER_BREAK  3
 
-/*
- * irq controllers that have dedicated ipis per message and don't
- * need additional code in the action handler may use this
- */
+/* for irq controllers that have dedicated ipis per message (4) */
 extern int smp_request_message_ipi(int virq, int message);
 extern const char *smp_ipi_name[];
 
+/* for irq controllers with only a single ipi */
+extern void smp_muxed_ipi_set_data(int cpu, unsigned long data);
+extern void smp_muxed_ipi_message_pass(int cpu, int msg);
+extern void smp_muxed_ipi_resend(void);
+extern irqreturn_t smp_ipi_demux(void);
+
 void smp_init_iSeries(void);
 void smp_init_pSeries(void);
 void smp_init_cell(void);
@@ -185,6 +189,8 @@ extern unsigned long __secondary_hold_spinloop;
 extern unsigned long __secondary_hold_acknowledge;
 extern char __secondary_hold;
 
+extern irqreturn_t debug_ipi_action(int irq, void *data);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index 1750c8dae1f..b183a406201 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -40,7 +40,7 @@ struct icp_ops {
 	void (*teardown_cpu)(void);
 	void (*flush_ipi)(void);
 #ifdef CONFIG_SMP
-	void (*message_pass)(int cpu, int msg);
+	void (*cause_ipi)(int cpu, unsigned long data);
 	irq_handler_t ipi_action;
 #endif
 };
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index e49b24c8413..2cc451aaaca 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -13,65 +13,35 @@
 #include <linux/kernel.h>
 #include <linux/smp.h>
 #include <linux/threads.h>
-#include <linux/percpu.h>
+#include <linux/hardirq.h>
 
 #include <asm/dbell.h>
 #include <asm/irq_regs.h>
 
 #ifdef CONFIG_SMP
-struct doorbell_cpu_info {
-	unsigned long	messages;	/* current messages bits */
-	unsigned int	tag;		/* tag value */
-};
-
-static DEFINE_PER_CPU(struct doorbell_cpu_info, doorbell_cpu_info);
-
 void doorbell_setup_this_cpu(void)
 {
-	struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info);
+	unsigned long tag = mfspr(SPRN_PIR) & 0x3fff;
 
-	info->messages = 0;
-	info->tag = mfspr(SPRN_PIR) & 0x3fff;
+	smp_muxed_ipi_set_data(smp_processor_id(), tag);
 }
 
-void doorbell_message_pass(int cpu, int msg)
+void doorbell_cause_ipi(int cpu, unsigned long data)
 {
-	struct doorbell_cpu_info *info;
-
-	info = &per_cpu(doorbell_cpu_info, cpu);
-	set_bit(msg, &info->messages);
-	ppc_msgsnd(PPC_DBELL, 0, info->tag);
+	ppc_msgsnd(PPC_DBELL, 0, data);
 }
 
 void doorbell_exception(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-	struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info);
-	int msg;
 
-	/* Warning: regs can be NULL when called from irq enable */
+	irq_enter();
 
-	if (!info->messages || (num_online_cpus() < 2))
-		goto out;
+	smp_ipi_demux();
 
-	for (msg = 0; msg < 4; msg++)
-		if (test_and_clear_bit(msg, &info->messages))
-			smp_message_recv(msg);
-
-out:
+	irq_exit();
 	set_irq_regs(old_regs);
 }
-
-void doorbell_check_self(void)
-{
-	struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info);
-
-	if (!info->messages)
-		return;
-
-	ppc_msgsnd(PPC_DBELL, 0, info->tag);
-}
-
 #else /* CONFIG_SMP */
 void doorbell_exception(struct pt_regs *regs)
 {
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index a81dd74414b..826552ceceb 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -66,7 +66,6 @@
 #include <asm/ptrace.h>
 #include <asm/machdep.h>
 #include <asm/udbg.h>
-#include <asm/dbell.h>
 #include <asm/smp.h>
 
 #ifdef CONFIG_PPC64
@@ -160,7 +159,8 @@ notrace void arch_local_irq_restore(unsigned long en)
 
 #if defined(CONFIG_BOOKE) && defined(CONFIG_SMP)
 	/* Check for pending doorbell interrupts and resend to ourself */
-	doorbell_check_self();
+	if (cpu_has_feature(CPU_FTR_DBELL))
+		smp_muxed_ipi_resend();
 #endif
 
 	/*
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index b7441144692..fa8e8700064 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -111,35 +111,6 @@ int __devinit smp_generic_kick_cpu(int nr)
 }
 #endif
 
-void smp_message_recv(int msg)
-{
-	switch(msg) {
-	case PPC_MSG_CALL_FUNCTION:
-		generic_smp_call_function_interrupt();
-		break;
-	case PPC_MSG_RESCHEDULE:
-		/* we notice need_resched on exit */
-		break;
-	case PPC_MSG_CALL_FUNC_SINGLE:
-		generic_smp_call_function_single_interrupt();
-		break;
-	case PPC_MSG_DEBUGGER_BREAK:
-		if (crash_ipi_function_ptr) {
-			crash_ipi_function_ptr(get_irq_regs());
-			break;
-		}
-#ifdef CONFIG_DEBUGGER
-		debugger_ipi(get_irq_regs());
-		break;
-#endif /* CONFIG_DEBUGGER */
-		/* FALLTHROUGH */
-	default:
-		printk("SMP %d: smp_message_recv(): unknown msg %d\n",
-		       smp_processor_id(), msg);
-		break;
-	}
-}
-
 static irqreturn_t call_function_action(int irq, void *data)
 {
 	generic_smp_call_function_interrupt();
@@ -158,9 +129,17 @@ static irqreturn_t call_function_single_action(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t debug_ipi_action(int irq, void *data)
+irqreturn_t debug_ipi_action(int irq, void *data)
 {
-	smp_message_recv(PPC_MSG_DEBUGGER_BREAK);
+	if (crash_ipi_function_ptr) {
+		crash_ipi_function_ptr(get_irq_regs());
+		return IRQ_HANDLED;
+	}
+
+#ifdef CONFIG_DEBUGGER
+	debugger_ipi(get_irq_regs());
+#endif /* CONFIG_DEBUGGER */
+
 	return IRQ_HANDLED;
 }
 
@@ -199,6 +178,59 @@ int smp_request_message_ipi(int virq, int msg)
 	return err;
 }
 
+struct cpu_messages {
+	unsigned long messages;		/* current messages bits */
+	unsigned long data;		/* data for cause ipi */
+};
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_messages, ipi_message);
+
+void smp_muxed_ipi_set_data(int cpu, unsigned long data)
+{
+	struct cpu_messages *info = &per_cpu(ipi_message, cpu);
+
+	info->data = data;
+}
+
+void smp_muxed_ipi_message_pass(int cpu, int msg)
+{
+	struct cpu_messages *info = &per_cpu(ipi_message, cpu);
+	unsigned long *tgt = &info->messages;
+
+	set_bit(msg, tgt);
+	mb();
+	smp_ops->cause_ipi(cpu, info->data);
+}
+
+void smp_muxed_ipi_resend(void)
+{
+	struct cpu_messages *info = &__get_cpu_var(ipi_message);
+	unsigned long *tgt = &info->messages;
+
+	if (*tgt)
+		smp_ops->cause_ipi(smp_processor_id(), info->data);
+}
+
+irqreturn_t smp_ipi_demux(void)
+{
+	struct cpu_messages *info = &__get_cpu_var(ipi_message);
+	unsigned long *tgt = &info->messages;
+
+	mb();	/* order any irq clear */
+	while (*tgt) {
+		if (test_and_clear_bit(PPC_MSG_CALL_FUNCTION, tgt))
+			generic_smp_call_function_interrupt();
+		if (test_and_clear_bit(PPC_MSG_RESCHEDULE, tgt))
+			reschedule_action(0, NULL); /* upcoming sched hook */
+		if (test_and_clear_bit(PPC_MSG_CALL_FUNC_SINGLE, tgt))
+			generic_smp_call_function_single_interrupt();
+#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
+		if (test_and_clear_bit(PPC_MSG_DEBUGGER_BREAK, tgt))
+			debug_ipi_action(0, NULL);
+#endif
+	}
+	return IRQ_HANDLED;
+}
+
 void smp_send_reschedule(int cpu)
 {
 	if (likely(smp_ops))
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index fe3f6a3a530..d6a93a10c0f 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -235,8 +235,10 @@ void __init mpc85xx_smp_init(void)
 		smp_85xx_ops.message_pass = smp_mpic_message_pass;
 	}
 
-	if (cpu_has_feature(CPU_FTR_DBELL))
-		smp_85xx_ops.message_pass = doorbell_message_pass;
+	if (cpu_has_feature(CPU_FTR_DBELL)) {
+		smp_85xx_ops.message_pass = smp_muxed_ipi_message_pass;
+		smp_85xx_ops.cause_ipi = doorbell_cause_ipi;
+	}
 
 	BUG_ON(!smp_85xx_ops.message_pass);
 
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 44cfd1bef89..6a58744d66c 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -196,8 +196,20 @@ static irqreturn_t iic_ipi_action(int irq, void *dev_id)
 {
 	int ipi = (int)(long)dev_id;
 
-	smp_message_recv(ipi);
-
+	switch(ipi) {
+	case PPC_MSG_CALL_FUNCTION:
+		generic_smp_call_function_interrupt();
+		break;
+	case PPC_MSG_RESCHEDULE:
+		/* Upcoming sched hook */
+		break;
+	case PPC_MSG_CALL_FUNC_SINGLE:
+		generic_smp_call_function_single_interrupt();
+		break;
+	case PPC_MSG_DEBUGGER_BREAK:
+		debug_ipi_action(0, NULL);
+		break;
+	}
 	return IRQ_HANDLED;
 }
 static void iic_request_ipi(int ipi, const char *name)
diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c
index 375c21ca660..b2103453eb0 100644
--- a/arch/powerpc/platforms/iseries/irq.c
+++ b/arch/powerpc/platforms/iseries/irq.c
@@ -42,7 +42,6 @@
 #include "irq.h"
 #include "pci.h"
 #include "call_pci.h"
-#include "smp.h"
 
 #ifdef CONFIG_PCI
 
@@ -316,7 +315,7 @@ unsigned int iSeries_get_irq(void)
 #ifdef CONFIG_SMP
 	if (get_lppaca()->int_dword.fields.ipi_cnt) {
 		get_lppaca()->int_dword.fields.ipi_cnt = 0;
-		iSeries_smp_message_recv();
+		smp_ipi_demux();
 	}
 #endif /* CONFIG_SMP */
 	if (hvlpevent_is_pending())
diff --git a/arch/powerpc/platforms/iseries/smp.c b/arch/powerpc/platforms/iseries/smp.c
index dcdbc5dc5aa..e3265adde5d 100644
--- a/arch/powerpc/platforms/iseries/smp.c
+++ b/arch/powerpc/platforms/iseries/smp.c
@@ -42,26 +42,8 @@
 #include <asm/cputable.h>
 #include <asm/system.h>
 
-#include "smp.h"
-
-static unsigned long iSeries_smp_message[NR_CPUS];
-
-void iSeries_smp_message_recv(void)
-{
-	int cpu = smp_processor_id();
-	int msg;
-
-	if (num_online_cpus() < 2)
-		return;
-
-	for (msg = 0; msg < 4; msg++)
-		if (test_and_clear_bit(msg, &iSeries_smp_message[cpu]))
-			smp_message_recv(msg);
-}
-
-static void smp_iSeries_message_pass(int cpu, int msg)
+static void smp_iSeries_cause_ipi(int cpu, unsigned long data)
 {
-	set_bit(msg, &iSeries_smp_message[cpu]);
 	HvCall_sendIPI(&(paca[cpu]));
 }
 
@@ -93,7 +75,8 @@ static void __devinit smp_iSeries_setup_cpu(int nr)
 }
 
 static struct smp_ops_t iSeries_smp_ops = {
-	.message_pass = smp_iSeries_message_pass,
+	.message_pass = smp_muxed_ipi_message_pass,
+	.cause_ipi    = smp_iSeries_cause_ipi,
 	.probe        = smp_iSeries_probe,
 	.kick_cpu     = smp_iSeries_kick_cpu,
 	.setup_cpu    = smp_iSeries_setup_cpu,
diff --git a/arch/powerpc/platforms/iseries/smp.h b/arch/powerpc/platforms/iseries/smp.h
deleted file mode 100644
index d501f7de01e..00000000000
--- a/arch/powerpc/platforms/iseries/smp.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _PLATFORMS_ISERIES_SMP_H
-#define _PLATFORMS_ISERIES_SMP_H
-
-extern void iSeries_smp_message_recv(void);
-
-#endif	/* _PLATFORMS_ISERIES_SMP_H */
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index c49e71926a5..a3401071abf 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -156,28 +156,13 @@ static inline void psurge_clr_ipi(int cpu)
 /*
  * On powersurge (old SMP powermac architecture) we don't have
  * separate IPIs for separate messages like openpic does.  Instead
- * we have a bitmap for each processor, where a 1 bit means that
- * the corresponding message is pending for that processor.
- * Ideally each cpu's entry would be in a different cache line.
+ * use the generic demux helpers
  *  -- paulus.
  */
-static unsigned long psurge_smp_message[NR_CPUS];
-
 void psurge_smp_message_recv(void)
 {
-	int cpu = smp_processor_id();
-	int msg;
-
-	/* clear interrupt */
-	psurge_clr_ipi(cpu);
-
-	if (num_online_cpus() < 2)
-		return;
-
-	/* make sure there is a message there */
-	for (msg = 0; msg < 4; msg++)
-		if (test_and_clear_bit(msg, &psurge_smp_message[cpu]))
-			smp_message_recv(msg);
+	psurge_clr_ipi(smp_processor_id());
+	smp_ipi_demux();
 }
 
 irqreturn_t psurge_primary_intr(int irq, void *d)
@@ -186,9 +171,8 @@ irqreturn_t psurge_primary_intr(int irq, void *d)
 	return IRQ_HANDLED;
 }
 
-static void smp_psurge_message_pass(int cpu, int msg)
+static void smp_psurge_cause_ipi(int cpu, unsigned long data)
 {
-	set_bit(msg, &psurge_smp_message[cpu]);
 	psurge_set_ipi(cpu);
 }
 
@@ -428,7 +412,8 @@ void __init smp_psurge_give_timebase(void)
 
 /* PowerSurge-style Macs */
 struct smp_ops_t psurge_smp_ops = {
-	.message_pass	= smp_psurge_message_pass,
+	.message_pass	= smp_muxed_ipi_message_pass,
+	.cause_ipi	= smp_psurge_cause_ipi,
 	.probe		= smp_psurge_probe,
 	.kick_cpu	= smp_psurge_kick_cpu,
 	.setup_cpu	= smp_psurge_setup_cpu,
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 95f578158ff..fbffd7e47ab 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -207,7 +207,8 @@ static struct smp_ops_t pSeries_mpic_smp_ops = {
 };
 
 static struct smp_ops_t pSeries_xics_smp_ops = {
-	.message_pass	= NULL,	/* Filled at runtime by xics_smp_probe() */
+	.message_pass	= smp_muxed_ipi_message_pass,
+	.cause_ipi	= NULL,	/* Filled at runtime by xics_smp_probe() */
 	.probe		= xics_smp_probe,
 	.kick_cpu	= smp_pSeries_kick_cpu,
 	.setup_cpu	= smp_xics_setup_cpu,
diff --git a/arch/powerpc/platforms/wsp/smp.c b/arch/powerpc/platforms/wsp/smp.c
index c7b8db9ed9b..9d20fa9d371 100644
--- a/arch/powerpc/platforms/wsp/smp.c
+++ b/arch/powerpc/platforms/wsp/smp.c
@@ -75,7 +75,8 @@ static int __init smp_a2_probe(void)
 }
 
 static struct smp_ops_t a2_smp_ops = {
-	.message_pass	= doorbell_message_pass,
+	.message_pass	= smp_muxed_ipi_message_pass,
+	.cause_ipi	= doorbell_cause_ipi,
 	.probe		= smp_a2_probe,
 	.kick_cpu	= smp_a2_kick_cpu,
 	.setup_cpu	= smp_a2_setup_cpu,
diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index 234764c189a..9518d367a64 100644
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -118,12 +118,8 @@ static void icp_hv_set_cpu_priority(unsigned char cppr)
 
 #ifdef CONFIG_SMP
 
-static void icp_hv_message_pass(int cpu, int msg)
+static void icp_hv_cause_ipi(int cpu, unsigned long data)
 {
-	unsigned long *tgt = &per_cpu(xics_ipi_message, cpu);
-
-	set_bit(msg, tgt);
-	mb();
 	icp_hv_set_qirr(cpu, IPI_PRIORITY);
 }
 
@@ -133,7 +129,7 @@ static irqreturn_t icp_hv_ipi_action(int irq, void *dev_id)
 
 	icp_hv_set_qirr(cpu, 0xff);
 
-	return xics_ipi_dispatch(cpu);
+	return smp_ipi_demux();
 }
 
 #endif /* CONFIG_SMP */
@@ -146,7 +142,7 @@ static const struct icp_ops icp_hv_ops = {
 	.flush_ipi	= icp_hv_flush_ipi,
 #ifdef CONFIG_SMP
 	.ipi_action	= icp_hv_ipi_action,
-	.message_pass	= icp_hv_message_pass,
+	.cause_ipi	= icp_hv_cause_ipi,
 #endif
 };
 
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 246500eefbf..1f15ad43614 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -134,12 +134,8 @@ static unsigned int icp_native_get_irq(void)
 
 #ifdef CONFIG_SMP
 
-static void icp_native_message_pass(int cpu, int msg)
+static void icp_native_cause_ipi(int cpu, unsigned long data)
 {
-	unsigned long *tgt = &per_cpu(xics_ipi_message, cpu);
-
-	set_bit(msg, tgt);
-	mb();
 	icp_native_set_qirr(cpu, IPI_PRIORITY);
 }
 
@@ -149,7 +145,7 @@ static irqreturn_t icp_native_ipi_action(int irq, void *dev_id)
 
 	icp_native_set_qirr(cpu, 0xff);
 
-	return xics_ipi_dispatch(cpu);
+	return smp_ipi_demux();
 }
 
 #endif /* CONFIG_SMP */
@@ -267,7 +263,7 @@ static const struct icp_ops icp_native_ops = {
 	.flush_ipi	= icp_native_flush_ipi,
 #ifdef CONFIG_SMP
 	.ipi_action	= icp_native_ipi_action,
-	.message_pass	= icp_native_message_pass,
+	.cause_ipi	= icp_native_cause_ipi,
 #endif
 };
 
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index a0576b705dd..a31a7103218 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -126,32 +126,6 @@ void xics_mask_unknown_vec(unsigned int vec)
 
 #ifdef CONFIG_SMP
 
-DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, xics_ipi_message);
-
-irqreturn_t xics_ipi_dispatch(int cpu)
-{
-	unsigned long *tgt = &per_cpu(xics_ipi_message, cpu);
-
-	mb();	/* order mmio clearing qirr */
-	while (*tgt) {
-		if (test_and_clear_bit(PPC_MSG_CALL_FUNCTION, tgt)) {
-			smp_message_recv(PPC_MSG_CALL_FUNCTION);
-		}
-		if (test_and_clear_bit(PPC_MSG_RESCHEDULE, tgt)) {
-			smp_message_recv(PPC_MSG_RESCHEDULE);
-		}
-		if (test_and_clear_bit(PPC_MSG_CALL_FUNC_SINGLE, tgt)) {
-			smp_message_recv(PPC_MSG_CALL_FUNC_SINGLE);
-		}
-#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
-		if (test_and_clear_bit(PPC_MSG_DEBUGGER_BREAK, tgt)) {
-			smp_message_recv(PPC_MSG_DEBUGGER_BREAK);
-		}
-#endif
-	}
-	return IRQ_HANDLED;
-}
-
 static void xics_request_ipi(void)
 {
 	unsigned int ipi;
@@ -170,8 +144,8 @@ static void xics_request_ipi(void)
 
 int __init xics_smp_probe(void)
 {
-	/* Setup message_pass callback  based on which ICP is used */
-	smp_ops->message_pass = icp_ops->message_pass;
+	/* Setup cause_ipi callback  based on which ICP is used */
+	smp_ops->cause_ipi = icp_ops->cause_ipi;
 
 	/* Register all the IPIs */
 	xics_request_ipi();
-- 
cgit v1.2.3-70-g09d2


From 1ece355b6825b7c61d1dc39a5c6cf49dc746e193 Mon Sep 17 00:00:00 2001
From: Milton Miller <miltonm@bga.com>
Date: Tue, 10 May 2011 19:29:42 +0000
Subject: powerpc: Add kconfig for muxed smp ipi support

Compile the new smp ipi mux and demux code only if a platform
will make use of it.  The new config is selected as required.

The new cause_ipi smp op is only available conditionally to point out
configs where the select is required; this makes setting the op an
immediate fail instead of a deferred unresolved symbol at link.

This also creates a new config for power surge powermac upgrade support
that can be disabled in expert mode but is default on.

I also removed the depends / default y on CONFIG_XICS since it is selected
by PSERIES.

Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/smp.h          |  2 ++
 arch/powerpc/kernel/smp.c               |  2 ++
 arch/powerpc/platforms/Kconfig          |  8 ++++++++
 arch/powerpc/platforms/Kconfig.cputype  |  2 ++
 arch/powerpc/platforms/iseries/Kconfig  |  1 +
 arch/powerpc/platforms/powermac/Kconfig | 11 ++++++++++-
 arch/powerpc/platforms/powermac/pic.c   |  4 ++--
 arch/powerpc/platforms/powermac/smp.c   |  8 ++++----
 arch/powerpc/sysdev/xics/Kconfig        |  1 +
 9 files changed, 32 insertions(+), 7 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 26f861560c5..880b8c1e6e5 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -38,7 +38,9 @@ extern void cpu_die(void);
 
 struct smp_ops_t {
 	void  (*message_pass)(int cpu, int msg);
+#ifdef CONFIG_PPC_SMP_MUXED_IPI
 	void  (*cause_ipi)(int cpu, unsigned long data);
+#endif
 	int   (*probe)(void);
 	int   (*kick_cpu)(int nr);
 	void  (*setup_cpu)(int nr);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index fa8e8700064..d76f7d7929b 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -178,6 +178,7 @@ int smp_request_message_ipi(int virq, int msg)
 	return err;
 }
 
+#ifdef CONFIG_PPC_SMP_MUXED_IPI
 struct cpu_messages {
 	unsigned long messages;		/* current messages bits */
 	unsigned long data;		/* data for cause ipi */
@@ -230,6 +231,7 @@ irqreturn_t smp_ipi_demux(void)
 	}
 	return IRQ_HANDLED;
 }
+#endif /* CONFIG_PPC_SMP_MUXED_IPI */
 
 void smp_send_reschedule(int cpu)
 {
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 6059053e715..83c704a637b 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -57,6 +57,14 @@ config UDBG_RTAS_CONSOLE
 	depends on PPC_RTAS
 	default n
 
+config PPC_SMP_MUXED_IPI
+	bool
+	help
+	  Select this opton if your platform supports SMP and your
+	  interrupt controller provides less than 4 interrupts to each
+	  cpu.	This will enable the generic code to multiplex the 4
+	  messages on to one ipi.
+
 config PPC_UDBG_BEAT
 	bool "BEAT based debug console"
 	depends on PPC_CELLEB
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index a1e623822a3..2165b65876f 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -73,6 +73,7 @@ config PPC_BOOK3S_64
 config PPC_BOOK3E_64
 	bool "Embedded processors"
 	select PPC_FPU # Make it a choice ?
+	select PPC_SMP_MUXED_IPI
 
 endchoice
 
@@ -178,6 +179,7 @@ config FSL_BOOKE
 config PPC_FSL_BOOK3E
 	bool
 	select FSL_EMB_PERFMON
+	select PPC_SMP_MUXED_IPI
 	default y if FSL_BOOKE
 
 config PTE_64BIT
diff --git a/arch/powerpc/platforms/iseries/Kconfig b/arch/powerpc/platforms/iseries/Kconfig
index ea1d3622b41..b57cda3a081 100644
--- a/arch/powerpc/platforms/iseries/Kconfig
+++ b/arch/powerpc/platforms/iseries/Kconfig
@@ -1,6 +1,7 @@
 config PPC_ISERIES
 	bool "IBM Legacy iSeries"
 	depends on PPC64 && PPC_BOOK3S
+	select PPC_SMP_MUXED_IPI
 	select PPC_INDIRECT_PIO
 	select PPC_INDIRECT_MMIO
 	select PPC_PCI_CHOICE if EXPERT
diff --git a/arch/powerpc/platforms/powermac/Kconfig b/arch/powerpc/platforms/powermac/Kconfig
index 1e1a0873e1d..1afd10f6785 100644
--- a/arch/powerpc/platforms/powermac/Kconfig
+++ b/arch/powerpc/platforms/powermac/Kconfig
@@ -18,4 +18,13 @@ config PPC_PMAC64
 	select PPC_970_NAP
 	default y
 
-
+config PPC_PMAC32_PSURGE
+	bool "Support for powersurge upgrade cards" if EXPERT
+	depends on SMP && PPC32 && PPC_PMAC
+	select PPC_SMP_MUXED_IPI
+	default y
+	help
+	  The powersurge cpu boards can be used in the generation
+	  of powermacs that have a socket for an upgradeable cpu card,
+	  including the 7500, 8500, 9500, 9600.  Support exists for
+	  both dual and quad socket upgrade cards.
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 2f34ad04029..b706cb3ad99 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -239,7 +239,7 @@ static unsigned int pmac_pic_get_irq(void)
 	unsigned long bits = 0;
 	unsigned long flags;
 
-#ifdef CONFIG_SMP
+#ifdef CONFIG_PPC_PMAC32_PSURGE
 	void psurge_smp_message_recv(void);
 
        	/* IPI's are a hack on the powersurge -- Cort */
@@ -247,7 +247,7 @@ static unsigned int pmac_pic_get_irq(void)
 		psurge_smp_message_recv();
 		return NO_IRQ_IGNORE;	/* ignore, already handled */
         }
-#endif /* CONFIG_SMP */
+#endif /* CONFIG_PPC_PMAC32_PSURGE */
 	raw_spin_lock_irqsave(&pmac_pic_lock, flags);
 	for (irq = max_real_irqs; (irq -= 32) >= 0; ) {
 		int i = irq >> 5;
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index a3401071abf..67b6e1432be 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -70,7 +70,7 @@ static void (*pmac_tb_freeze)(int freeze);
 static u64 timebase;
 static int tb_req;
 
-#ifdef CONFIG_PPC32
+#ifdef CONFIG_PPC_PMAC32_PSURGE
 
 /*
  * Powersurge (old powermac SMP) support.
@@ -420,7 +420,7 @@ struct smp_ops_t psurge_smp_ops = {
 	.give_timebase	= smp_psurge_give_timebase,
 	.take_timebase	= smp_psurge_take_timebase,
 };
-#endif /* CONFIG_PPC32 - actually powersurge support */
+#endif /* CONFIG_PPC_PMAC32_PSURGE */
 
 /*
  * Core 99 and later support
@@ -980,7 +980,7 @@ void __init pmac_setup_smp(void)
 		of_node_put(np);
 		smp_ops = &core99_smp_ops;
 	}
-#ifdef CONFIG_PPC32
+#ifdef CONFIG_PPC_PMAC32_PSURGE
 	else {
 		/* We have to set bits in cpu_possible_mask here since the
 		 * secondary CPU(s) aren't in the device tree. Various
@@ -993,7 +993,7 @@ void __init pmac_setup_smp(void)
 			set_cpu_possible(cpu, true);
 		smp_ops = &psurge_smp_ops;
 	}
-#endif /* CONFIG_PPC32 */
+#endif /* CONFIG_PPC_PMAC32_PSURGE */
 
 #ifdef CONFIG_HOTPLUG_CPU
 	ppc_md.cpu_die = pmac_cpu_die;
diff --git a/arch/powerpc/sysdev/xics/Kconfig b/arch/powerpc/sysdev/xics/Kconfig
index 123b8ddf281..0031eda320c 100644
--- a/arch/powerpc/sysdev/xics/Kconfig
+++ b/arch/powerpc/sysdev/xics/Kconfig
@@ -1,5 +1,6 @@
 config PPC_XICS
        def_bool n
+       select PPC_SMP_MUXED_IPI
 
 config PPC_ICP_NATIVE
        def_bool n
-- 
cgit v1.2.3-70-g09d2


From da0519800260a3c791b4fe3317a0c7560027a372 Mon Sep 17 00:00:00 2001
From: Milton Miller <miltonm@bga.com>
Date: Tue, 10 May 2011 19:30:26 +0000
Subject: powerpc: Remove irq_host_ops->remap hook

It was called from irq_create_mapping if that was called for a host
and hwirq that was previously mapped, "to update the flags".  But the
only implementation was in beat_interrupt and all it did was repeat a
hypervisor call without error checking that was performed with error
checking at the beginning of the map hook.  In addition, the comment on
the beat remap hook says it will only called once for a given mapping,
which would apply to map not remap.

All flags should be known by the time the match hook is called, before
we call the map hook.  Removing this mostly unused hook will simpify
the requirements of irq_domain concept.

Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/irq.h               |  3 ---
 arch/powerpc/kernel/irq.c                    |  2 --
 arch/powerpc/platforms/cell/beat_interrupt.c | 11 -----------
 3 files changed, 16 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index e1983d57768..6f4a3efb59a 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -88,9 +88,6 @@ struct irq_host_ops {
 	/* Dispose of such a mapping */
 	void (*unmap)(struct irq_host *h, unsigned int virq);
 
-	/* Update of such a mapping  */
-	void (*remap)(struct irq_host *h, unsigned int virq, irq_hw_number_t hw);
-
 	/* Translate device-tree interrupt specifier from raw format coming
 	 * from the firmware to a irq_hw_number_t (interrupt line number) and
 	 * type (sense) that can be passed to set_irq_type(). In the absence
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 4a5aa8ca97a..0715a09a410 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -732,8 +732,6 @@ unsigned int irq_create_mapping(struct irq_host *host,
 	 */
 	virq = irq_find_mapping(host, hwirq);
 	if (virq != NO_IRQ) {
-		if (host->ops->remap)
-			host->ops->remap(host, virq, hwirq);
 		pr_debug("irq: -> existing mapping on virq %d\n", virq);
 		return virq;
 	}
diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c
index d46f7e47a1d..55015e1f693 100644
--- a/arch/powerpc/platforms/cell/beat_interrupt.c
+++ b/arch/powerpc/platforms/cell/beat_interrupt.c
@@ -147,16 +147,6 @@ static int beatic_pic_host_map(struct irq_host *h, unsigned int virq,
 	return 0;
 }
 
-/*
- * Update binding hardware IRQ number (hw) and Virtuql
- * IRQ number (virq). This is called only once for a given mapping.
- */
-static void beatic_pic_host_remap(struct irq_host *h, unsigned int virq,
-			       irq_hw_number_t hw)
-{
-	beat_construct_and_connect_irq_plug(virq, hw);
-}
-
 /*
  * Translate device-tree interrupt spec to irq_hw_number_t style (ulong),
  * to pass away to irq_create_mapping().
@@ -184,7 +174,6 @@ static int beatic_pic_host_match(struct irq_host *h, struct device_node *np)
 
 static struct irq_host_ops beatic_pic_host_ops = {
 	.map = beatic_pic_host_map,
-	.remap = beatic_pic_host_remap,
 	.unmap = beatic_pic_host_unmap,
 	.xlate = beatic_pic_host_xlate,
 	.match = beatic_pic_host_match,
-- 
cgit v1.2.3-70-g09d2


From 3ee62d365b519c0c18c774049efcde84fe51c60c Mon Sep 17 00:00:00 2001
From: Milton Miller <miltonm@bga.com>
Date: Tue, 10 May 2011 19:30:36 +0000
Subject: powerpc: Add virq_is_host to reduce virq_to_host usage

Some irq_host implementations are using virq_to_host to check if
they are the irq_host for a virtual irq.  To allow us to make space
versus time tradeoffs, replace this usage with an assertive
virq_is_host that confirms or denies the irq is associated with the
given irq_host.

Signed-off-by: Milton Miller <miltonm@bga.com>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/irq.h         | 1 +
 arch/powerpc/kernel/irq.c              | 6 ++++++
 arch/powerpc/sysdev/xics/xics-common.c | 2 +-
 3 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 6f4a3efb59a..a65d1702643 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -128,6 +128,7 @@ struct irq_host {
 struct irq_data;
 extern irq_hw_number_t irqd_to_hwirq(struct irq_data *d);
 extern irq_hw_number_t virq_to_hw(unsigned int virq);
+extern bool virq_is_host(unsigned int virq, struct irq_host *host);
 extern struct irq_host *virq_to_host(unsigned int virq);
 
 /**
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 0715a09a410..73cf29078fe 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -510,6 +510,12 @@ irq_hw_number_t virq_to_hw(unsigned int virq)
 }
 EXPORT_SYMBOL_GPL(virq_to_hw);
 
+bool virq_is_host(unsigned int virq, struct irq_host *host)
+{
+	return irq_map[virq].host == host;
+}
+EXPORT_SYMBOL_GPL(virq_is_host);
+
 struct irq_host *virq_to_host(unsigned int virq)
 {
 	return irq_map[virq].host;
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 43b2a791e20..445c5a01b76 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -213,7 +213,7 @@ void xics_migrate_irqs_away(void)
 		/* We can't set affinity on ISA interrupts */
 		if (virq < NUM_ISA_INTERRUPTS)
 			continue;
-		if (virq_to_host(virq) != xics_host)
+		if (!virq_is_host(virq, xics_host))
 			continue;
 		irq = (unsigned int)virq_to_hw(virq);
 		/* We need to get IPIs still. */
-- 
cgit v1.2.3-70-g09d2


From 1e8c23013ed0d535e531b3b9cc30200e884f3ff0 Mon Sep 17 00:00:00 2001
From: Milton Miller <miltonm@bga.com>
Date: Tue, 10 May 2011 19:30:40 +0000
Subject: powerpc: Remove virq_to_host

The only references to the irq_map[].host field are internal to
arch/powerpc/kernel/irq.c

Signed-off-by: Milton Miller <miltonm@bga.com>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/irq.h | 1 -
 arch/powerpc/kernel/irq.c      | 6 ------
 2 files changed, 7 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index a65d1702643..1bff591f7f7 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -129,7 +129,6 @@ struct irq_data;
 extern irq_hw_number_t irqd_to_hwirq(struct irq_data *d);
 extern irq_hw_number_t virq_to_hw(unsigned int virq);
 extern bool virq_is_host(unsigned int virq, struct irq_host *host);
-extern struct irq_host *virq_to_host(unsigned int virq);
 
 /**
  * irq_alloc_host - Allocate a new irq_host data structure
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 73cf29078fe..4368b5ed560 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -516,12 +516,6 @@ bool virq_is_host(unsigned int virq, struct irq_host *host)
 }
 EXPORT_SYMBOL_GPL(virq_is_host);
 
-struct irq_host *virq_to_host(unsigned int virq)
-{
-	return irq_map[virq].host;
-}
-EXPORT_SYMBOL_GPL(virq_to_host);
-
 static int default_irq_host_match(struct irq_host *h, struct device_node *np)
 {
 	return h->of_node != NULL && h->of_node == np;
-- 
cgit v1.2.3-70-g09d2


From d36b4c4f3cc6caae6d4a12d9f995513e4c3acdd5 Mon Sep 17 00:00:00 2001
From: Kumar Gala <galak@kernel.crashing.org>
Date: Wed, 6 Apr 2011 00:18:48 -0500
Subject: powerpc/fsl-booke64: Add support for Debug Level exception handler

Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/include/asm/cputable.h  |  4 ++-
 arch/powerpc/kernel/exceptions-64e.S | 65 ++++++++++++++++++++++++++++++++++--
 arch/powerpc/kernel/setup_64.c       |  8 +++++
 3 files changed, 73 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 4efbfb3f325..c0d842cfd01 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -157,6 +157,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_476_DD2			ASM_CONST(0x0000000000010000)
 #define CPU_FTR_NEED_COHERENT		ASM_CONST(0x0000000000020000)
 #define CPU_FTR_NO_BTIC			ASM_CONST(0x0000000000040000)
+#define CPU_FTR_DEBUG_LVL_EXC		ASM_CONST(0x0000000000080000)
 #define CPU_FTR_NODSISRALIGN		ASM_CONST(0x0000000000100000)
 #define CPU_FTR_PPC_LE			ASM_CONST(0x0000000000200000)
 #define CPU_FTR_REAL_LE			ASM_CONST(0x0000000000400000)
@@ -385,7 +386,8 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_DBELL)
 #define CPU_FTRS_E5500	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
-	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD)
+	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_DEBUG_LVL_EXC)
 #define CPU_FTRS_GENERIC_32	(CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN)
 
 /* 64-bit CPUs */
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 4d0abb4930a..cf27a8fa0d2 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -253,9 +253,6 @@ exception_marker:
 	.balign	0x1000
 	.globl interrupt_base_book3e
 interrupt_base_book3e:					/* fake trap */
-	/* Note: If real debug exceptions are supported by the HW, the vector
-	 * below will have to be patched up to point to an appropriate handler
-	 */
 	EXCEPTION_STUB(0x000, machine_check)		/* 0x0200 */
 	EXCEPTION_STUB(0x020, critical_input)		/* 0x0580 */
 	EXCEPTION_STUB(0x040, debug_crit)		/* 0x0d00 */
@@ -455,6 +452,68 @@ interrupt_end_book3e:
 kernel_dbg_exc:
 	b	.	/* NYI */
 
+/* Debug exception as a debug interrupt*/
+	START_EXCEPTION(debug_debug);
+	DBG_EXCEPTION_PROLOG(0xd00, PROLOG_ADDITION_2REGS)
+
+	/*
+	 * If there is a single step or branch-taken exception in an
+	 * exception entry sequence, it was probably meant to apply to
+	 * the code where the exception occurred (since exception entry
+	 * doesn't turn off DE automatically).  We simulate the effect
+	 * of turning off DE on entry to an exception handler by turning
+	 * off DE in the DSRR1 value and clearing the debug status.
+	 */
+
+	mfspr	r14,SPRN_DBSR		/* check single-step/branch taken */
+	andis.	r15,r14,DBSR_IC@h
+	beq+	1f
+
+	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
+	LOAD_REG_IMMEDIATE(r15,interrupt_end_book3e)
+	cmpld	cr0,r10,r14
+	cmpld	cr1,r10,r15
+	blt+	cr0,1f
+	bge+	cr1,1f
+
+	/* here it looks like we got an inappropriate debug exception. */
+	lis	r14,DBSR_IC@h		/* clear the IC event */
+	rlwinm	r11,r11,0,~MSR_DE	/* clear DE in the DSRR1 value */
+	mtspr	SPRN_DBSR,r14
+	mtspr	SPRN_DSRR1,r11
+	lwz	r10,PACA_EXDBG+EX_CR(r13)	/* restore registers */
+	ld	r1,PACA_EXDBG+EX_R1(r13)
+	ld	r14,PACA_EXDBG+EX_R14(r13)
+	ld	r15,PACA_EXDBG+EX_R15(r13)
+	mtcr	r10
+	ld	r10,PACA_EXDBG+EX_R10(r13)	/* restore registers */
+	ld	r11,PACA_EXDBG+EX_R11(r13)
+	mfspr	r13,SPRN_SPRG_DBG_SCRATCH
+	rfdi
+
+	/* Normal debug exception */
+	/* XXX We only handle coming from userspace for now since we can't
+	 *     quite save properly an interrupted kernel state yet
+	 */
+1:	andi.	r14,r11,MSR_PR;		/* check for userspace again */
+	beq	kernel_dbg_exc;		/* if from kernel mode */
+
+	/* Now we mash up things to make it look like we are coming on a
+	 * normal exception
+	 */
+	mfspr	r15,SPRN_SPRG_DBG_SCRATCH
+	mtspr	SPRN_SPRG_GEN_SCRATCH,r15
+	mfspr	r14,SPRN_DBSR
+	EXCEPTION_COMMON(0xd00, PACA_EXDBG, INTS_DISABLE_ALL)
+	std	r14,_DSISR(r1)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	mr	r4,r14
+	ld	r14,PACA_EXDBG+EX_R14(r13)
+	ld	r15,PACA_EXDBG+EX_R15(r13)
+	bl	.save_nvgprs
+	bl	.DebugException
+	b	.ret_from_except
+
 /* Doorbell interrupt */
 	MASKABLE_EXCEPTION(0x2070, doorbell, .doorbell_exception, ACK_NONE)
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index c2ec0a12e14..a88bf2713d4 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -62,6 +62,7 @@
 #include <asm/udbg.h>
 #include <asm/kexec.h>
 #include <asm/mmu_context.h>
+#include <asm/code-patching.h>
 
 #include "setup.h"
 
@@ -477,6 +478,9 @@ static void __init irqstack_early_init(void)
 #ifdef CONFIG_PPC_BOOK3E
 static void __init exc_lvl_early_init(void)
 {
+	extern unsigned int interrupt_base_book3e;
+	extern unsigned int exc_debug_debug_book3e;
+
 	unsigned int i;
 
 	for_each_possible_cpu(i) {
@@ -487,6 +491,10 @@ static void __init exc_lvl_early_init(void)
 		mcheckirq_ctx[i] = (struct thread_info *)
 			__va(memblock_alloc(THREAD_SIZE, THREAD_SIZE));
 	}
+
+	if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC))
+		patch_branch(&interrupt_base_book3e + (0x040 / 4) + 1,
+			     (unsigned long)&exc_debug_debug_book3e, 0);
 }
 #else
 #define exc_lvl_early_init()
-- 
cgit v1.2.3-70-g09d2


From 3a6e9bd7f60b29efc205485ceb11a768032c40d4 Mon Sep 17 00:00:00 2001
From: Scott Wood <scottwood@freescale.com>
Date: Mon, 9 May 2011 16:26:00 -0500
Subject: powerpc/e5500: set non-base IVORs

Without this, we attempt to use doorbells for IPIs, and end up
branching to some bad address.  Plus, even for the exceptions
we don't implement, it's good to handle it and get a message out.

Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/include/asm/reg_booke.h      |  4 +++
 arch/powerpc/kernel/cpu_setup_fsl_booke.S |  3 ++
 arch/powerpc/kernel/exceptions-64e.S      | 47 +++++++++++++++++++++++++++++++
 3 files changed, 54 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 817bd1ac175..0f0ad9fa01c 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -83,6 +83,10 @@
 #define SPRN_IVOR13	0x19D	/* Interrupt Vector Offset Register 13 */
 #define SPRN_IVOR14	0x19E	/* Interrupt Vector Offset Register 14 */
 #define SPRN_IVOR15	0x19F	/* Interrupt Vector Offset Register 15 */
+#define SPRN_IVOR38	0x1B0	/* Interrupt Vector Offset Register 38 */
+#define SPRN_IVOR39	0x1B1	/* Interrupt Vector Offset Register 39 */
+#define SPRN_IVOR40	0x1B2	/* Interrupt Vector Offset Register 40 */
+#define SPRN_IVOR41	0x1B3	/* Interrupt Vector Offset Register 41 */
 #define SPRN_SPEFSCR	0x200	/* SPE & Embedded FP Status & Control */
 #define SPRN_BBEAR	0x201	/* Branch Buffer Entry Address Register */
 #define SPRN_BBTAR	0x202	/* Branch Buffer Target Address Register */
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index 913611105c1..8053db02b85 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -88,6 +88,9 @@ _GLOBAL(__setup_cpu_e5500)
 	bl	__e500_dcache_setup
 #ifdef CONFIG_PPC_BOOK3E_64
 	bl	.__setup_base_ivors
+	bl	.setup_perfmon_ivor
+	bl	.setup_doorbell_ivors
+	bl	.setup_ehv_ivors
 #else
 	bl	__setup_e500mc_ivors
 #endif
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index cf27a8fa0d2..d24d4400cc7 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -269,8 +269,13 @@ interrupt_base_book3e:					/* fake trap */
 	EXCEPTION_STUB(0x1a0, watchdog)			/* 0x09f0 */
 	EXCEPTION_STUB(0x1c0, data_tlb_miss)
 	EXCEPTION_STUB(0x1e0, instruction_tlb_miss)
+	EXCEPTION_STUB(0x260, perfmon)
 	EXCEPTION_STUB(0x280, doorbell)
 	EXCEPTION_STUB(0x2a0, doorbell_crit)
+	EXCEPTION_STUB(0x2c0, guest_doorbell)
+	EXCEPTION_STUB(0x2e0, guest_doorbell_crit)
+	EXCEPTION_STUB(0x300, hypercall)
+	EXCEPTION_STUB(0x320, ehpriv)
 
 	.globl interrupt_end_book3e
 interrupt_end_book3e:
@@ -514,6 +519,8 @@ kernel_dbg_exc:
 	bl	.DebugException
 	b	.ret_from_except
 
+	MASKABLE_EXCEPTION(0x260, perfmon, .performance_monitor_exception, ACK_NONE)
+
 /* Doorbell interrupt */
 	MASKABLE_EXCEPTION(0x2070, doorbell, .doorbell_exception, ACK_NONE)
 
@@ -528,6 +535,11 @@ kernel_dbg_exc:
 //	b	ret_from_crit_except
 	b	.
 
+	MASKABLE_EXCEPTION(0x2c0, guest_doorbell, .unknown_exception, ACK_NONE)
+	MASKABLE_EXCEPTION(0x2e0, guest_doorbell_crit, .unknown_exception, ACK_NONE)
+	MASKABLE_EXCEPTION(0x310, hypercall, .unknown_exception, ACK_NONE)
+	MASKABLE_EXCEPTION(0x320, ehpriv, .unknown_exception, ACK_NONE)
+
 
 /*
  * An interrupt came in while soft-disabled; clear EE in SRR1,
@@ -647,7 +659,12 @@ fast_exception_return:
 BAD_STACK_TRAMPOLINE(0x000)
 BAD_STACK_TRAMPOLINE(0x100)
 BAD_STACK_TRAMPOLINE(0x200)
+BAD_STACK_TRAMPOLINE(0x260)
+BAD_STACK_TRAMPOLINE(0x2c0)
+BAD_STACK_TRAMPOLINE(0x2e0)
 BAD_STACK_TRAMPOLINE(0x300)
+BAD_STACK_TRAMPOLINE(0x310)
+BAD_STACK_TRAMPOLINE(0x320)
 BAD_STACK_TRAMPOLINE(0x400)
 BAD_STACK_TRAMPOLINE(0x500)
 BAD_STACK_TRAMPOLINE(0x600)
@@ -1183,3 +1200,33 @@ _GLOBAL(__setup_base_ivors)
 	sync
 
 	blr
+
+_GLOBAL(setup_perfmon_ivor)
+	SET_IVOR(35, 0x260) /* Performance Monitor */
+	blr
+
+_GLOBAL(setup_doorbell_ivors)
+	SET_IVOR(36, 0x280) /* Processor Doorbell */
+	SET_IVOR(37, 0x2a0) /* Processor Doorbell Crit */
+
+	/* Check MMUCFG[LPIDSIZE] to determine if we have category E.HV */
+	mfspr	r10,SPRN_MMUCFG
+	rlwinm.	r10,r10,0,MMUCFG_LPIDSIZE
+	beqlr
+
+	SET_IVOR(38, 0x2c0) /* Guest Processor Doorbell */
+	SET_IVOR(39, 0x2e0) /* Guest Processor Doorbell Crit/MC */
+	blr
+
+_GLOBAL(setup_ehv_ivors)
+	/*
+	 * We may be running as a guest and lack E.HV even on a chip
+	 * that normally has it.
+	 */
+	mfspr	r10,SPRN_MMUCFG
+	rlwinm.	r10,r10,0,MMUCFG_LPIDSIZE
+	beqlr
+
+	SET_IVOR(40, 0x300) /* Embedded Hypervisor System Call */
+	SET_IVOR(41, 0x320) /* Embedded Hypervisor Privilege */
+	blr
-- 
cgit v1.2.3-70-g09d2


From 22d168ce60272ca112e86e58c5ebde82f20f9c83 Mon Sep 17 00:00:00 2001
From: Scott Wood <scottwood@freescale.com>
Date: Thu, 24 Mar 2011 16:43:54 -0500
Subject: powerpc/mpic: parse 4-cell intspec types other than zero

Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/include/asm/mpic.h |  2 ++
 arch/powerpc/sysdev/mpic.c      | 37 ++++++++++++++++++++++++++++++++++++-
 2 files changed, 38 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h
index 7005ee0b074..25a0cb3a79f 100644
--- a/arch/powerpc/include/asm/mpic.h
+++ b/arch/powerpc/include/asm/mpic.h
@@ -371,6 +371,8 @@ struct mpic
  * NOTE: This flag trumps MPIC_WANTS_RESET.
  */
 #define MPIC_NO_RESET			0x00004000
+/* Freescale MPIC (compatible includes "fsl,mpic") */
+#define MPIC_FSL			0x00008000
 
 /* MPIC HW modification ID */
 #define MPIC_REGSET_MASK		0xf0000000
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 824a94fc413..0a3c1c20115 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -6,6 +6,7 @@
  *  with various broken implementations of this HW.
  *
  *  Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
+ *  Copyright 2010-2011 Freescale Semiconductor, Inc.
  *
  *  This file is subject to the terms and conditions of the GNU General Public
  *  License.  See the file COPYING in the main directory of this archive
@@ -1023,6 +1024,7 @@ static int mpic_host_xlate(struct irq_host *h, struct device_node *ct,
 			   irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 
 {
+	struct mpic *mpic = h->host_data;
 	static unsigned char map_mpic_senses[4] = {
 		IRQ_TYPE_EDGE_RISING,
 		IRQ_TYPE_LEVEL_LOW,
@@ -1031,7 +1033,38 @@ static int mpic_host_xlate(struct irq_host *h, struct device_node *ct,
 	};
 
 	*out_hwirq = intspec[0];
-	if (intsize > 1) {
+	if (intsize >= 4 && (mpic->flags & MPIC_FSL)) {
+		/*
+		 * Freescale MPIC with extended intspec:
+		 * First two cells are as usual.  Third specifies
+		 * an "interrupt type".  Fourth is type-specific data.
+		 *
+		 * See Documentation/devicetree/bindings/powerpc/fsl/mpic.txt
+		 */
+		switch (intspec[2]) {
+		case 0:
+		case 1: /* no EISR/EIMR support for now, treat as shared IRQ */
+			break;
+		case 2:
+			if (intspec[0] >= ARRAY_SIZE(mpic->ipi_vecs))
+				return -EINVAL;
+
+			*out_hwirq = mpic->ipi_vecs[intspec[0]];
+			break;
+		case 3:
+			if (intspec[0] >= ARRAY_SIZE(mpic->timer_vecs))
+				return -EINVAL;
+
+			*out_hwirq = mpic->timer_vecs[intspec[0]];
+			break;
+		default:
+			pr_debug("%s: unknown irq type %u\n",
+				 __func__, intspec[2]);
+			return -EINVAL;
+		}
+
+		*out_flags = map_mpic_senses[intspec[1] & 3];
+	} else if (intsize > 1) {
 		u32 mask = 0x3;
 
 		/* Apple invented a new race of encoding on machines with
@@ -1130,6 +1163,8 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	/* Check for "big-endian" in device-tree */
 	if (node && of_get_property(node, "big-endian", NULL) != NULL)
 		mpic->flags |= MPIC_BIG_ENDIAN;
+	if (node && of_device_is_compatible(node, "fsl,mpic"))
+		mpic->flags |= MPIC_FSL;
 
 	/* Look for protected sources */
 	if (node) {
-- 
cgit v1.2.3-70-g09d2


From ea94187face757e723aa461a60698ca43c09fbb9 Mon Sep 17 00:00:00 2001
From: Scott Wood <scottwood@freescale.com>
Date: Thu, 24 Mar 2011 16:43:55 -0500
Subject: powerpc/mpic: add the mpic global timer support

Add support for MPIC timers as requestable interrupt sources.

Based on http://patchwork.ozlabs.org/patch/20941/ by Dave Liu.

Signed-off-by: Dave Liu <daveliu@freescale.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/include/asm/mpic.h |  3 +-
 arch/powerpc/sysdev/mpic.c      | 92 ++++++++++++++++++++++++++++++++++++++---
 2 files changed, 88 insertions(+), 7 deletions(-)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h
index 25a0cb3a79f..664bee6622e 100644
--- a/arch/powerpc/include/asm/mpic.h
+++ b/arch/powerpc/include/asm/mpic.h
@@ -263,6 +263,7 @@ struct mpic
 #ifdef CONFIG_SMP
 	struct irq_chip		hc_ipi;
 #endif
+	struct irq_chip		hc_tm;
 	const char		*name;
 	/* Flags */
 	unsigned int		flags;
@@ -281,7 +282,7 @@ struct mpic
 
 	/* vector numbers used for internal sources (ipi/timers) */
 	unsigned int		ipi_vecs[4];
-	unsigned int		timer_vecs[4];
+	unsigned int		timer_vecs[8];
 
 	/* Spurious vector to program into unused sources */
 	unsigned int		spurious_vec;
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 0a3c1c20115..0e47bce5f69 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -219,6 +219,28 @@ static inline void _mpic_ipi_write(struct mpic *mpic, unsigned int ipi, u32 valu
 	_mpic_write(mpic->reg_type, &mpic->gregs, offset, value);
 }
 
+static inline u32 _mpic_tm_read(struct mpic *mpic, unsigned int tm)
+{
+	unsigned int offset = MPIC_INFO(TIMER_VECTOR_PRI) +
+			      ((tm & 3) * MPIC_INFO(TIMER_STRIDE));
+
+	if (tm >= 4)
+		offset += 0x1000 / 4;
+
+	return _mpic_read(mpic->reg_type, &mpic->tmregs, offset);
+}
+
+static inline void _mpic_tm_write(struct mpic *mpic, unsigned int tm, u32 value)
+{
+	unsigned int offset = MPIC_INFO(TIMER_VECTOR_PRI) +
+			      ((tm & 3) * MPIC_INFO(TIMER_STRIDE));
+
+	if (tm >= 4)
+		offset += 0x1000 / 4;
+
+	_mpic_write(mpic->reg_type, &mpic->tmregs, offset, value);
+}
+
 static inline u32 _mpic_cpu_read(struct mpic *mpic, unsigned int reg)
 {
 	unsigned int cpu = mpic_processor_id(mpic);
@@ -269,6 +291,8 @@ static inline void _mpic_irq_write(struct mpic *mpic, unsigned int src_no,
 #define mpic_write(b,r,v)	_mpic_write(mpic->reg_type,&(b),(r),(v))
 #define mpic_ipi_read(i)	_mpic_ipi_read(mpic,(i))
 #define mpic_ipi_write(i,v)	_mpic_ipi_write(mpic,(i),(v))
+#define mpic_tm_read(i)		_mpic_tm_read(mpic,(i))
+#define mpic_tm_write(i,v)	_mpic_tm_write(mpic,(i),(v))
 #define mpic_cpu_read(i)	_mpic_cpu_read(mpic,(i))
 #define mpic_cpu_write(i,v)	_mpic_cpu_write(mpic,(i),(v))
 #define mpic_irq_read(s,r)	_mpic_irq_read(mpic,(s),(r))
@@ -625,6 +649,13 @@ static unsigned int mpic_is_ipi(struct mpic *mpic, unsigned int irq)
 	return (src >= mpic->ipi_vecs[0] && src <= mpic->ipi_vecs[3]);
 }
 
+/* Determine if the linux irq is a timer */
+static unsigned int mpic_is_tm(struct mpic *mpic, unsigned int irq)
+{
+	unsigned int src = virq_to_hw(irq);
+
+	return (src >= mpic->timer_vecs[0] && src <= mpic->timer_vecs[7]);
+}
 
 /* Convert a cpu mask from logical to physical cpu numbers. */
 static inline u32 mpic_physmask(u32 cpumask)
@@ -811,6 +842,25 @@ static void mpic_end_ipi(struct irq_data *d)
 
 #endif /* CONFIG_SMP */
 
+static void mpic_unmask_tm(struct irq_data *d)
+{
+	struct mpic *mpic = mpic_from_irq_data(d);
+	unsigned int src = virq_to_hw(d->irq) - mpic->timer_vecs[0];
+
+	DBG("%s: enable_tm: %d (tm %d)\n", mpic->name, irq, src);
+	mpic_tm_write(src, mpic_tm_read(src) & ~MPIC_VECPRI_MASK);
+	mpic_tm_read(src);
+}
+
+static void mpic_mask_tm(struct irq_data *d)
+{
+	struct mpic *mpic = mpic_from_irq_data(d);
+	unsigned int src = virq_to_hw(d->irq) - mpic->timer_vecs[0];
+
+	mpic_tm_write(src, mpic_tm_read(src) | MPIC_VECPRI_MASK);
+	mpic_tm_read(src);
+}
+
 int mpic_set_affinity(struct irq_data *d, const struct cpumask *cpumask,
 		      bool force)
 {
@@ -941,6 +991,12 @@ static struct irq_chip mpic_ipi_chip = {
 };
 #endif /* CONFIG_SMP */
 
+static struct irq_chip mpic_tm_chip = {
+	.irq_mask	= mpic_mask_tm,
+	.irq_unmask	= mpic_unmask_tm,
+	.irq_eoi	= mpic_end_irq,
+};
+
 #ifdef CONFIG_MPIC_U3_HT_IRQS
 static struct irq_chip mpic_irq_ht_chip = {
 	.irq_startup	= mpic_startup_ht_irq,
@@ -984,6 +1040,16 @@ static int mpic_host_map(struct irq_host *h, unsigned int virq,
 	}
 #endif /* CONFIG_SMP */
 
+	if (hw >= mpic->timer_vecs[0] && hw <= mpic->timer_vecs[7]) {
+		WARN_ON(!(mpic->flags & MPIC_PRIMARY));
+
+		DBG("mpic: mapping as timer\n");
+		irq_set_chip_data(virq, mpic);
+		irq_set_chip_and_handler(virq, &mpic->hc_tm,
+					 handle_fasteoi_irq);
+		return 0;
+	}
+
 	if (hw >= mpic->irq_count)
 		return -EINVAL;
 
@@ -1140,6 +1206,9 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	mpic->hc_ipi.name = name;
 #endif /* CONFIG_SMP */
 
+	mpic->hc_tm = mpic_tm_chip;
+	mpic->hc_tm.name = name;
+
 	mpic->flags = flags;
 	mpic->isu_size = isu_size;
 	mpic->irq_count = irq_count;
@@ -1150,10 +1219,14 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	else
 		intvec_top = 255;
 
-	mpic->timer_vecs[0] = intvec_top - 8;
-	mpic->timer_vecs[1] = intvec_top - 7;
-	mpic->timer_vecs[2] = intvec_top - 6;
-	mpic->timer_vecs[3] = intvec_top - 5;
+	mpic->timer_vecs[0] = intvec_top - 12;
+	mpic->timer_vecs[1] = intvec_top - 11;
+	mpic->timer_vecs[2] = intvec_top - 10;
+	mpic->timer_vecs[3] = intvec_top - 9;
+	mpic->timer_vecs[4] = intvec_top - 8;
+	mpic->timer_vecs[5] = intvec_top - 7;
+	mpic->timer_vecs[6] = intvec_top - 6;
+	mpic->timer_vecs[7] = intvec_top - 5;
 	mpic->ipi_vecs[0]   = intvec_top - 4;
 	mpic->ipi_vecs[1]   = intvec_top - 3;
 	mpic->ipi_vecs[2]   = intvec_top - 2;
@@ -1356,15 +1429,17 @@ void __init mpic_init(struct mpic *mpic)
 	/* Set current processor priority to max */
 	mpic_cpu_write(MPIC_INFO(CPU_CURRENT_TASK_PRI), 0xf);
 
-	/* Initialize timers: just disable them all */
+	/* Initialize timers to our reserved vectors and mask them for now */
 	for (i = 0; i < 4; i++) {
 		mpic_write(mpic->tmregs,
 			   i * MPIC_INFO(TIMER_STRIDE) +
-			   MPIC_INFO(TIMER_DESTINATION), 0);
+			   MPIC_INFO(TIMER_DESTINATION),
+			   1 << hard_smp_processor_id());
 		mpic_write(mpic->tmregs,
 			   i * MPIC_INFO(TIMER_STRIDE) +
 			   MPIC_INFO(TIMER_VECTOR_PRI),
 			   MPIC_VECPRI_MASK |
+			   (9 << MPIC_VECPRI_PRIORITY_SHIFT) |
 			   (mpic->timer_vecs[0] + i));
 	}
 
@@ -1473,6 +1548,11 @@ void mpic_irq_set_priority(unsigned int irq, unsigned int pri)
 			~MPIC_VECPRI_PRIORITY_MASK;
 		mpic_ipi_write(src - mpic->ipi_vecs[0],
 			       reg | (pri << MPIC_VECPRI_PRIORITY_SHIFT));
+	} else if (mpic_is_tm(mpic, irq)) {
+		reg = mpic_tm_read(src - mpic->timer_vecs[0]) &
+			~MPIC_VECPRI_PRIORITY_MASK;
+		mpic_tm_write(src - mpic->timer_vecs[0],
+			      reg | (pri << MPIC_VECPRI_PRIORITY_SHIFT));
 	} else {
 		reg = mpic_irq_read(src, MPIC_INFO(IRQ_VECTOR_PRI))
 			& ~MPIC_VECPRI_PRIORITY_MASK;
-- 
cgit v1.2.3-70-g09d2


From 593adf317cf165f7c66facf2285db9d4befbd1c0 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Wed, 11 May 2011 00:39:50 +0000
Subject: powerpc/kvm: Fix the build for 32-bit Book 3S (classic) processors

Commits a5d4f3ad3a ("powerpc: Base support for exceptions using
HSRR0/1") and 673b189a2e ("powerpc: Always use SPRN_SPRG_HSCRATCH0
when running in HV mode") cause compile and link errors for 32-bit
classic Book 3S processors when KVM is enabled.  This fixes these
errors.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/reg.h       | 5 +++++
 arch/powerpc/kvm/book3s_rmhandlers.S | 2 ++
 2 files changed, 7 insertions(+)

(limited to 'arch/powerpc/include')

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index fdec5933305..c5cae0dd176 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -824,6 +824,11 @@
 	FTR_SECTION_ELSE_NESTED(66);			\
 	mtspr	SPRN_SPRG_HSCRATCH0,rX;			\
 	ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66)
+
+#else /* CONFIG_PPC_BOOK3S_64 */
+#define GET_SCRATCH0(rX)	mfspr	rX,SPRN_SPRG_SCRATCH0
+#define SET_SCRATCH0(rX)	mtspr	SPRN_SPRG_SCRATCH0,rX
+
 #endif
 
 #ifdef CONFIG_PPC_BOOK3E_64
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index ae99af66ca3..1a1b34487e7 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -112,7 +112,9 @@ INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_MACHINE_CHECK
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_DATA_STORAGE
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_INST_STORAGE
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_EXTERNAL
+#ifdef CONFIG_PPC_BOOK3S_64
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_EXTERNAL_HV
+#endif
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_ALIGNMENT
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_PROGRAM
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_FP_UNAVAIL
-- 
cgit v1.2.3-70-g09d2