Merge git://oak/home/sfr/kernels/iseries/work

10 files changed, 518 insertions, 10 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 103cb8128ef4..92cfabf929bc 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -12,7 +12,7 @@ CFLAGS_btext.o		+= -fPIC
 endif
 
 obj-y				:= semaphore.o cputable.o ptrace.o syscalls.o \
-				   signal_32.o pmc.o
+				   irq.o signal_32.o pmc.o
 obj-$(CONFIG_PPC64)		+= setup_64.o binfmt_elf32.o sys_ppc32.o \
 				   signal_64.o ptrace32.o systbl.o \
 				   paca.o ioctl32.o cpu_setup_power4.o \
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
new file mode 100644
index 000000000000..4b7940693f3d
--- /dev/null
+++ b/arch/powerpc/kernel/irq.c
@@ -0,0 +1,478 @@
+/*
+ *  arch/ppc/kernel/irq.c
+ *
+ *  Derived from arch/i386/kernel/irq.c
+ *    Copyright (C) 1992 Linus Torvalds
+ *  Adapted from arch/i386 by Gary Thomas
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *  Updated and modified by Cort Dougan <cort@fsmlabs.com>
+ *    Copyright (C) 1996-2001 Cort Dougan
+ *  Adapted for Power Macintosh by Paul Mackerras
+ *    Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au)
+ *  Amiga/APUS changes by Jesper Skov (jskov@cygnus.co.uk).
+ *
+ * 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 file contains the code used by various IRQ handling routines:
+ * asking for different IRQ's should be done through these routines
+ * instead of just grabbing them. Thus setups with different IRQ numbers
+ * shouldn't result in any weird surprises, and installing new handlers
+ * should be easier.
+ *
+ * The MPC8xx has an interrupt mask in the SIU.  If a bit is set, the
+ * interrupt is _enabled_.  As expected, IRQ0 is bit 0 in the 32-bit
+ * mask register (of which only 16 are defined), hence the weird shifting
+ * and complement of the cached_irq_mask.  I want to be able to stuff
+ * this right into the SIU SMASK register.
+ * Many of the prep/chrp functions are conditional compiled on CONFIG_8xx
+ * to reduce code space and undefined function references.
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/threads.h>
+#include <linux/kernel_stat.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/proc_fs.h>
+#include <linux/random.h>
+#include <linux/seq_file.h>
+#include <linux/cpumask.h>
+#include <linux/profile.h>
+#include <linux/bitops.h>
+#ifdef CONFIG_PPC64
+#include <linux/kallsyms.h>
+#endif
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/pgtable.h>
+#include <asm/irq.h>
+#include <asm/cache.h>
+#include <asm/prom.h>
+#include <asm/ptrace.h>
+#include <asm/machdep.h>
+#ifdef CONFIG_PPC64
+#include <asm/iseries/it_lp_queue.h>
+#include <asm/paca.h>
+#endif
+
+static int ppc_spurious_interrupts;
+
+#if defined(CONFIG_PPC_ISERIES) && defined(CONFIG_SMP)
+extern void iSeries_smp_message_recv(struct pt_regs *);
+#endif
+
+#ifdef CONFIG_PPC32
+#define NR_MASK_WORDS	((NR_IRQS + 31) / 32)
+
+unsigned long ppc_cached_irq_mask[NR_MASK_WORDS];
+atomic_t ppc_n_lost_interrupts;
+
+#ifdef CONFIG_TAU_INT
+extern int tau_initialized;
+extern int tau_interrupts(int);
+#endif
+
+#if defined(CONFIG_SMP) && !defined(CONFIG_PPC_MERGE)
+extern atomic_t ipi_recv;
+extern atomic_t ipi_sent;
+#endif
+#endif /* CONFIG_PPC32 */
+
+#ifdef CONFIG_PPC64
+EXPORT_SYMBOL(irq_desc);
+
+int distribute_irqs = 1;
+int __irq_offset_value;
+u64 ppc64_interrupt_controller;
+#endif /* CONFIG_PPC64 */
+
+int show_interrupts(struct seq_file *p, void *v)
+{
+	int i = *(loff_t *)v, j;
+	struct irqaction *action;
+	irq_desc_t *desc;
+	unsigned long flags;
+
+	if (i == 0) {
+		seq_puts(p, "           ");
+		for_each_online_cpu(j)
+			seq_printf(p, "CPU%d       ", j);
+		seq_putc(p, '\n');
+	}
+
+	if (i < NR_IRQS) {
+		desc = get_irq_desc(i);
+		spin_lock_irqsave(&desc->lock, flags);
+		action = desc->action;
+		if (!action || !action->handler)
+			goto skip;
+		seq_printf(p, "%3d: ", i);
+#ifdef CONFIG_SMP
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+#else
+		seq_printf(p, "%10u ", kstat_irqs(i));
+#endif /* CONFIG_SMP */
+		if (desc->handler)
+			seq_printf(p, " %s ", desc->handler->typename);
+		else
+			seq_puts(p, "  None      ");
+		seq_printf(p, "%s", (desc->status & IRQ_LEVEL) ? "Level " : "Edge  ");
+		seq_printf(p, "    %s", action->name);
+		for (action = action->next; action; action = action->next)
+			seq_printf(p, ", %s", action->name);
+		seq_putc(p, '\n');
+skip:
+		spin_unlock_irqrestore(&desc->lock, flags);
+	} else if (i == NR_IRQS) {
+#ifdef CONFIG_PPC32
+#ifdef CONFIG_TAU_INT
+		if (tau_initialized){
+			seq_puts(p, "TAU: ");
+			for (j = 0; j < NR_CPUS; j++)
+				if (cpu_online(j))
+					seq_printf(p, "%10u ", tau_interrupts(j));
+			seq_puts(p, "  PowerPC             Thermal Assist (cpu temp)\n");
+		}
+#endif
+#if defined(CONFIG_SMP) && !defined(CONFIG_PPC_MERGE)
+		/* should this be per processor send/receive? */
+		seq_printf(p, "IPI (recv/sent): %10u/%u\n",
+				atomic_read(&ipi_recv), atomic_read(&ipi_sent));
+#endif
+#endif /* CONFIG_PPC32 */
+		seq_printf(p, "BAD: %10u\n", ppc_spurious_interrupts);
+	}
+	return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+void fixup_irqs(cpumask_t map)
+{
+	unsigned int irq;
+	static int warned;
+
+	for_each_irq(irq) {
+		cpumask_t mask;
+
+		if (irq_desc[irq].status & IRQ_PER_CPU)
+			continue;
+
+		cpus_and(mask, irq_affinity[irq], map);
+		if (any_online_cpu(mask) == NR_CPUS) {
+			printk("Breaking affinity for irq %i\n", irq);
+			mask = map;
+		}
+		if (irq_desc[irq].handler->set_affinity)
+			irq_desc[irq].handler->set_affinity(irq, mask);
+		else if (irq_desc[irq].action && !(warned++))
+			printk("Cannot set affinity for irq %i\n", irq);
+	}
+
+	local_irq_enable();
+	mdelay(1);
+	local_irq_disable();
+}
+#endif
+
+#ifdef CONFIG_PPC_ISERIES
+void do_IRQ(struct pt_regs *regs)
+{
+	struct paca_struct *lpaca;
+
+	irq_enter();
+
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+	/* Debugging check for stack overflow: is there less than 2KB free? */
+	{
+		long sp;
+
+		sp = __get_SP() & (THREAD_SIZE-1);
+
+		if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
+			printk("do_IRQ: stack overflow: %ld\n",
+				sp - sizeof(struct thread_info));
+			dump_stack();
+		}
+	}
+#endif
+
+	lpaca = get_paca();
+#ifdef CONFIG_SMP
+	if (lpaca->lppaca.int_dword.fields.ipi_cnt) {
+		lpaca->lppaca.int_dword.fields.ipi_cnt = 0;
+		iSeries_smp_message_recv(regs);
+	}
+#endif /* CONFIG_SMP */
+	if (hvlpevent_is_pending())
+		process_hvlpevents(regs);
+
+	irq_exit();
+
+	if (lpaca->lppaca.int_dword.fields.decr_int) {
+		lpaca->lppaca.int_dword.fields.decr_int = 0;
+		/* Signal a fake decrementer interrupt */
+		timer_interrupt(regs);
+	}
+}
+
+#else	/* CONFIG_PPC_ISERIES */
+
+void do_IRQ(struct pt_regs *regs)
+{
+	int irq;
+#ifdef CONFIG_IRQSTACKS
+	struct thread_info *curtp, *irqtp;
+#endif
+
+        irq_enter();
+
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+	/* Debugging check for stack overflow: is there less than 2KB free? */
+	{
+		long sp;
+
+		sp = __get_SP() & (THREAD_SIZE-1);
+
+		if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
+			printk("do_IRQ: stack overflow: %ld\n",
+				sp - sizeof(struct thread_info));
+			dump_stack();
+		}
+	}
+#endif
+
+	/*
+	 * Every platform is required to implement ppc_md.get_irq.
+	 * This function will either return an irq number or -1 to
+	 * indicate there are no more pending.
+	 * The value -2 is for buggy hardware and means that this IRQ
+	 * has already been handled. -- Tom
+	 */
+	irq = ppc_md.get_irq(regs);
+
+	if (irq >= 0) {
+#ifdef CONFIG_IRQSTACKS
+		/* Switch to the irq stack to handle this */
+		curtp = current_thread_info();
+		irqtp = hardirq_ctx[smp_processor_id()];
+		if (curtp != irqtp) {
+			irqtp->task = curtp->task;
+			irqtp->flags = 0;
+			call___do_IRQ(irq, regs, irqtp);
+			irqtp->task = NULL;
+			if (irqtp->flags)
+				set_bits(irqtp->flags, &curtp->flags);
+		} else
+#endif
+			__do_IRQ(irq, regs);
+	} else
+#ifdef CONFIG_PPC32
+		if (irq != -2)
+#endif
+			/* That's not SMP safe ... but who cares ? */
+			ppc_spurious_interrupts++;
+        irq_exit();
+}
+
+#endif	/* CONFIG_PPC_ISERIES */
+
+void __init init_IRQ(void)
+{
+#ifdef CONFIG_PPC64
+	static int once = 0;
+
+	if (once)
+		return;
+
+	once++;
+
+#endif
+	ppc_md.init_IRQ();
+#ifdef CONFIG_PPC64
+	irq_ctx_init();
+#endif
+}
+
+#ifdef CONFIG_PPC64
+#ifndef CONFIG_PPC_ISERIES
+/*
+ * Virtual IRQ mapping code, used on systems with XICS interrupt controllers.
+ */
+
+#define UNDEFINED_IRQ 0xffffffff
+unsigned int virt_irq_to_real_map[NR_IRQS];
+
+/*
+ * Don't use virtual irqs 0, 1, 2 for devices.
+ * The pcnet32 driver considers interrupt numbers < 2 to be invalid,
+ * and 2 is the XICS IPI interrupt.
+ * We limit virtual irqs to 17 less than NR_IRQS so that when we
+ * offset them by 16 (to reserve the first 16 for ISA interrupts)
+ * we don't end up with an interrupt number >= NR_IRQS.
+ */
+#define MIN_VIRT_IRQ	3
+#define MAX_VIRT_IRQ	(NR_IRQS - NUM_ISA_INTERRUPTS - 1)
+#define NR_VIRT_IRQS	(MAX_VIRT_IRQ - MIN_VIRT_IRQ + 1)
+
+void
+virt_irq_init(void)
+{
+	int i;
+	for (i = 0; i < NR_IRQS; i++)
+		virt_irq_to_real_map[i] = UNDEFINED_IRQ;
+}
+
+/* Create a mapping for a real_irq if it doesn't already exist.
+ * Return the virtual irq as a convenience.
+ */
+int virt_irq_create_mapping(unsigned int real_irq)
+{
+	unsigned int virq, first_virq;
+	static int warned;
+
+	if (ppc64_interrupt_controller == IC_OPEN_PIC)
+		return real_irq;	/* no mapping for openpic (for now) */
+
+	if (ppc64_interrupt_controller == IC_CELL_PIC)
+		return real_irq;	/* no mapping for iic either */
+
+	/* don't map interrupts < MIN_VIRT_IRQ */
+	if (real_irq < MIN_VIRT_IRQ) {
+		virt_irq_to_real_map[real_irq] = real_irq;
+		return real_irq;
+	}
+
+	/* map to a number between MIN_VIRT_IRQ and MAX_VIRT_IRQ */
+	virq = real_irq;
+	if (virq > MAX_VIRT_IRQ)
+		virq = (virq % NR_VIRT_IRQS) + MIN_VIRT_IRQ;
+
+	/* search for this number or a free slot */
+	first_virq = virq;
+	while (virt_irq_to_real_map[virq] != UNDEFINED_IRQ) {
+		if (virt_irq_to_real_map[virq] == real_irq)
+			return virq;
+		if (++virq > MAX_VIRT_IRQ)
+			virq = MIN_VIRT_IRQ;
+		if (virq == first_virq)
+			goto nospace;	/* oops, no free slots */
+	}
+
+	virt_irq_to_real_map[virq] = real_irq;
+	return virq;
+
+ nospace:
+	if (!warned) {
+		printk(KERN_CRIT "Interrupt table is full\n");
+		printk(KERN_CRIT "Increase NR_IRQS (currently %d) "
+		       "in your kernel sources and rebuild.\n", NR_IRQS);
+		warned = 1;
+	}
+	return NO_IRQ;
+}
+
+/*
+ * In most cases will get a hit on the very first slot checked in the
+ * virt_irq_to_real_map.  Only when there are a large number of
+ * IRQs will this be expensive.
+ */
+unsigned int real_irq_to_virt_slowpath(unsigned int real_irq)
+{
+	unsigned int virq;
+	unsigned int first_virq;
+
+	virq = real_irq;
+
+	if (virq > MAX_VIRT_IRQ)
+		virq = (virq % NR_VIRT_IRQS) + MIN_VIRT_IRQ;
+
+	first_virq = virq;
+
+	do {
+		if (virt_irq_to_real_map[virq] == real_irq)
+			return virq;
+
+		virq++;
+
+		if (virq >= MAX_VIRT_IRQ)
+			virq = 0;
+
+	} while (first_virq != virq);
+
+	return NO_IRQ;
+
+}
+
+#endif /* CONFIG_PPC_ISERIES */
+
+#ifdef CONFIG_IRQSTACKS
+struct thread_info *softirq_ctx[NR_CPUS];
+struct thread_info *hardirq_ctx[NR_CPUS];
+
+void irq_ctx_init(void)
+{
+	struct thread_info *tp;
+	int i;
+
+	for_each_cpu(i) {
+		memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
+		tp = softirq_ctx[i];
+		tp->cpu = i;
+		tp->preempt_count = SOFTIRQ_OFFSET;
+
+		memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
+		tp = hardirq_ctx[i];
+		tp->cpu = i;
+		tp->preempt_count = HARDIRQ_OFFSET;
+	}
+}
+
+void do_softirq(void)
+{
+	unsigned long flags;
+	struct thread_info *curtp, *irqtp;
+
+	if (in_interrupt())
+		return;
+
+	local_irq_save(flags);
+
+	if (local_softirq_pending()) {
+		curtp = current_thread_info();
+		irqtp = softirq_ctx[smp_processor_id()];
+		irqtp->task = curtp->task;
+		call_do_softirq(irqtp);
+		irqtp->task = NULL;
+	}
+
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(do_softirq);
+
+#endif /* CONFIG_IRQSTACKS */
+
+static int __init setup_noirqdistrib(char *str)
+{
+	distribute_irqs = 0;
+	return 1;
+}
+
+__setup("noirqdistrib", setup_noirqdistrib);
+#endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index ae1433da09b2..ae48a002f81a 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -89,12 +89,12 @@ _GLOBAL(call_do_softirq)
 	mtlr	r0
 	blr
 
-_GLOBAL(call_handle_IRQ_event)
+_GLOBAL(call___do_IRQ)
 	mflr	r0
 	std	r0,16(r1)
-	stdu	r1,THREAD_SIZE-112(r6)
-	mr	r1,r6
-	bl	.handle_IRQ_event
+	stdu	r1,THREAD_SIZE-112(r5)
+	mr	r1,r5
+	bl	.__do_IRQ
 	ld	r1,0(r1)
 	ld	r0,16(r1)
 	mtlr	r0
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 26bb1fe6384b..17c46a2e356d 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -53,6 +53,8 @@
 #include <asm/lmb.h>
 #include <asm/xmon.h>
 
+#include "setup.h"
+
 #undef DEBUG
 
 #ifdef DEBUG
diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h
new file mode 100644
index 000000000000..2ebba755272e
--- /dev/null
+++ b/arch/powerpc/kernel/setup.h
@@ -0,0 +1,6 @@
+#ifndef _POWERPC_KERNEL_SETUP_H
+#define _POWERPC_KERNEL_SETUP_H
+
+void check_for_initrd(void);
+
+#endif /* _POWERPC_KERNEL_SETUP_H */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 0fbc73f7f828..55f485f78c00 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -40,6 +40,8 @@
 #include <asm/xmon.h>
 #include <asm/time.h>
 
+#include "setup.h"
+
 #define DBG(fmt...)
 
 #if defined CONFIG_KGDB
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 54c606f680b3..fe39aac4f24d 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -61,6 +61,8 @@
 #include <asm/xmon.h>
 #include <asm/udbg.h>
 
+#include "setup.h"
+
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
 #else
diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c
index a06603d84a45..01090e9ce0cf 100644
--- a/arch/powerpc/platforms/iseries/irq.c
+++ b/arch/powerpc/platforms/iseries/irq.c
@@ -103,6 +103,9 @@ static void intReceived(struct XmPciLpEvent *eventParm,
 		struct pt_regs *regsParm)
 {
 	int irq;
+#ifdef CONFIG_IRQSTACKS
+	struct thread_info *curtp, *irqtp;
+#endif
 
 	++Pci_Interrupt_Count;
 
@@ -110,7 +113,20 @@ static void intReceived(struct XmPciLpEvent *eventParm,
 	case XmPciLpEvent_SlotInterrupt:
 		irq = eventParm->hvLpEvent.xCorrelationToken;
 		/* Dispatch the interrupt handlers for this irq */
-		ppc_irq_dispatch_handler(regsParm, irq);
+#ifdef CONFIG_IRQSTACKS
+		/* Switch to the irq stack to handle this */
+		curtp = current_thread_info();
+		irqtp = hardirq_ctx[smp_processor_id()];
+		if (curtp != irqtp) {
+			irqtp->task = curtp->task;
+			irqtp->flags = 0;
+			call___do_IRQ(irq, regsParm, irqtp);
+			irqtp->task = NULL;
+			if (irqtp->flags)
+				set_bits(irqtp->flags, &curtp->flags);
+		} else
+#endif
+			__do_IRQ(irq, regsParm);
 		HvCallPci_eoi(eventParm->eventData.slotInterrupt.busNumber,
 			eventParm->eventData.slotInterrupt.subBusNumber,
 			eventParm->eventData.slotInterrupt.deviceId);
@@ -310,10 +326,8 @@ static void iSeries_disable_IRQ(unsigned int irq)
 }
 
 /*
- * Need to define this so ppc_irq_dispatch_handler will NOT call
- * enable_IRQ at the end of interrupt handling.  However, this does
- * nothing because there is not enough information provided to do
- * the EOI HvCall.  This is done by XmPciLpEvent.c
+ * This does nothing because there is not enough information
+ * provided to do the EOI HvCall.  This is done by XmPciLpEvent.c
  */
 static void iSeries_end_IRQ(unsigned int irq)
 {
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 83a49e80ac29..90040c49494d 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -74,6 +74,9 @@ static DEFINE_SPINLOCK(pmac_pic_lock);
 #define GATWICK_IRQ_POOL_SIZE        10
 static struct interrupt_info gatwick_int_pool[GATWICK_IRQ_POOL_SIZE];
 
+#define NR_MASK_WORDS	((NR_IRQS + 31) / 32)
+static unsigned long ppc_lost_interrupts[NR_MASK_WORDS];
+
 /*
  * Mark an irq as "lost".  This is only used on the pmac
  * since it can lose interrupts (see pmac_set_irq_mask).
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index c72c86f05cb6..405c4f3229b3 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -567,6 +567,7 @@ nextnode:
 
 	xics_8259_pic.enable = i8259_pic.enable;
 	xics_8259_pic.disable = i8259_pic.disable;
+	xics_8259_pic.end = i8259_pic.end;
 	for (i = 0; i < 16; ++i)
 		get_irq_desc(i)->handler = &xics_8259_pic;
 	for (; i < NR_IRQS; ++i)