Merge branch 'master'

19 files changed, 1710 insertions, 81 deletions

diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index ecd32d5d85f..4099ddab920 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -361,7 +361,9 @@ static void __init chrp_find_openpic(void)
 	printk(KERN_INFO "OpenPIC at %lx\n", opaddr);
 
 	irq_count = NR_IRQS - NUM_ISA_INTERRUPTS - 4; /* leave room for IPIs */
-	prom_get_irq_senses(init_senses, NUM_8259_INTERRUPTS, NR_IRQS - 4);
+	prom_get_irq_senses(init_senses, NUM_ISA_INTERRUPTS, NR_IRQS - 4);
+	/* i8259 cascade is always positive level */
+	init_senses[0] = IRQ_SENSE_LEVEL | IRQ_POLARITY_POSITIVE;
 
 	iranges = (unsigned int *) get_property(np, "interrupt-ranges", &len);
 	if (iranges == NULL)
diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c
index a06603d84a4..01090e9ce0c 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/iseries/misc.S b/arch/powerpc/platforms/iseries/misc.S
index 09f14522e17..dfe7aa1ba09 100644
--- a/arch/powerpc/platforms/iseries/misc.S
+++ b/arch/powerpc/platforms/iseries/misc.S
@@ -15,6 +15,7 @@
 
 #include <asm/processor.h>
 #include <asm/asm-offsets.h>
+#include <asm/ppc_asm.h>
 
 	.text
 
diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c
index d3e4bf756c8..6a29f301436 100644
--- a/arch/powerpc/platforms/iseries/setup.c
+++ b/arch/powerpc/platforms/iseries/setup.c
@@ -39,7 +39,8 @@
 #include <asm/sections.h>
 #include <asm/iommu.h>
 #include <asm/firmware.h>
-
+#include <asm/systemcfg.h>
+#include <asm/system.h>
 #include <asm/time.h>
 #include <asm/paca.h>
 #include <asm/cache.h>
@@ -71,7 +72,7 @@ extern void hvlog(char *fmt, ...);
 #endif
 
 /* Function Prototypes */
-static void build_iSeries_Memory_Map(void);
+static unsigned long build_iSeries_Memory_Map(void);
 static void iseries_shared_idle(void);
 static void iseries_dedicated_idle(void);
 #ifdef CONFIG_PCI
@@ -84,7 +85,6 @@ static void iSeries_pci_final_fixup(void) { }
 int piranha_simulator;
 
 extern int rd_size;		/* Defined in drivers/block/rd.c */
-extern unsigned long klimit;
 extern unsigned long embedded_sysmap_start;
 extern unsigned long embedded_sysmap_end;
 
@@ -403,9 +403,11 @@ void mschunks_alloc(unsigned long num_chunks)
  * a table used to translate Linux's physical addresses to these
  * absolute addresses.  Absolute addresses are needed when
  * communicating with the hypervisor (e.g. to build HPT entries)
+ *
+ * Returns the physical memory size
  */
 
-static void __init build_iSeries_Memory_Map(void)
+static unsigned long __init build_iSeries_Memory_Map(void)
 {
 	u32 loadAreaFirstChunk, loadAreaLastChunk, loadAreaSize;
 	u32 nextPhysChunk;
@@ -538,7 +540,7 @@ static void __init build_iSeries_Memory_Map(void)
 	 * which should be equal to
 	 *   nextPhysChunk
 	 */
-	systemcfg->physicalMemorySize = chunk_to_addr(nextPhysChunk);
+	return chunk_to_addr(nextPhysChunk);
 }
 
 /*
@@ -564,8 +566,8 @@ static void __init iSeries_setup_arch(void)
 	printk("Max physical processors = %d\n",
 			itVpdAreas.xSlicMaxPhysicalProcs);
 
-	systemcfg->processor = xIoHriProcessorVpd[procIx].xPVR;
-	printk("Processor version = %x\n", systemcfg->processor);
+	_systemcfg->processor = xIoHriProcessorVpd[procIx].xPVR;
+	printk("Processor version = %x\n", _systemcfg->processor);
 }
 
 static void iSeries_show_cpuinfo(struct seq_file *m)
@@ -694,20 +696,18 @@ static void iseries_shared_idle(void)
 		if (hvlpevent_is_pending())
 			process_iSeries_events();
 
+		preempt_enable_no_resched();
 		schedule();
+		preempt_disable();
 	}
 }
 
 static void iseries_dedicated_idle(void)
 {
-	long oldval;
+	set_thread_flag(TIF_POLLING_NRFLAG);
 
 	while (1) {
-		oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);
-
-		if (!oldval) {
-			set_thread_flag(TIF_POLLING_NRFLAG);
-
+		if (!need_resched()) {
 			while (!need_resched()) {
 				ppc64_runlatch_off();
 				HMT_low();
@@ -720,13 +720,12 @@ static void iseries_dedicated_idle(void)
 			}
 
 			HMT_medium();
-			clear_thread_flag(TIF_POLLING_NRFLAG);
-		} else {
-			set_need_resched();
 		}
 
 		ppc64_runlatch_on();
+		preempt_enable_no_resched();
 		schedule();
+		preempt_disable();
 	}
 }
 
@@ -931,7 +930,7 @@ void dt_cpus(struct iseries_flat_dt *dt)
 	dt_end_node(dt);
 }
 
-void build_flat_dt(struct iseries_flat_dt *dt)
+void build_flat_dt(struct iseries_flat_dt *dt, unsigned long phys_mem_size)
 {
 	u64 tmp[2];
 
@@ -947,7 +946,7 @@ void build_flat_dt(struct iseries_flat_dt *dt)
 	dt_prop_str(dt, "name", "memory");
 	dt_prop_str(dt, "device_type", "memory");
 	tmp[0] = 0;
-	tmp[1] = systemcfg->physicalMemorySize;
+	tmp[1] = phys_mem_size;
 	dt_prop_u64_list(dt, "reg", tmp, 2);
 	dt_end_node(dt);
 
@@ -967,13 +966,15 @@ void build_flat_dt(struct iseries_flat_dt *dt)
 
 void * __init iSeries_early_setup(void)
 {
+	unsigned long phys_mem_size;
+
 	iSeries_fixup_klimit();
 
 	/*
 	 * Initialize the table which translate Linux physical addresses to
 	 * AS/400 absolute addresses
 	 */
-	build_iSeries_Memory_Map();
+	phys_mem_size = build_iSeries_Memory_Map();
 
 	iSeries_get_cmdline();
 
@@ -983,7 +984,7 @@ void * __init iSeries_early_setup(void)
 	/* Parse early parameters, in particular mem=x */
 	parse_early_param();
 
-	build_flat_dt(&iseries_dt);
+	build_flat_dt(&iseries_dt, phys_mem_size);
 
 	return (void *) __pa(&iseries_dt);
 }
diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c
index 340c21caeae..895aeb3f75d 100644
--- a/arch/powerpc/platforms/maple/pci.c
+++ b/arch/powerpc/platforms/maple/pci.c
@@ -380,9 +380,6 @@ void __init maple_pcibios_fixup(void)
 	for_each_pci_dev(dev)
 		pci_read_irq_line(dev);
 
-	/* Do the mapping of the IO space */
-	phbs_remap_io();
-
 	DBG(" <- maple_pcibios_fixup\n");
 }
 
diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c
index 8f818d092e2..dfd41b9781a 100644
--- a/arch/powerpc/platforms/powermac/pci.c
+++ b/arch/powerpc/platforms/powermac/pci.c
@@ -918,9 +918,6 @@ void __init pmac_pci_init(void)
 			PCI_DN(np)->busno = 0xf0;
 	}
 
-	/* map in PCI I/O space */
-	phbs_remap_io();
-
 	/* pmac_check_ht_link(); */
 
 	/* Tell pci.c to not use the common resource allocation mechanism */
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 83a49e80ac2..90040c49494 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/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index e1f9443cc87..957b0910342 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -305,9 +305,19 @@ static int __init smp_psurge_probe(void)
 	psurge_start = ioremap(PSURGE_START, 4);
 	psurge_pri_intr = ioremap(PSURGE_PRI_INTR, 4);
 
-	/* this is not actually strictly necessary -- paulus. */
-	for (i = 1; i < ncpus; ++i)
-		smp_hw_index[i] = i;
+	/*
+	 * This is necessary because OF doesn't know about the
+	 * secondary cpu(s), and thus there aren't nodes in the
+	 * device tree for them, and smp_setup_cpu_maps hasn't
+	 * set their bits in cpu_possible_map and cpu_present_map.
+	 */
+	if (ncpus > NR_CPUS)
+		ncpus = NR_CPUS;
+	for (i = 1; i < ncpus ; ++i) {
+		cpu_set(i, cpu_present_map);
+		cpu_set(i, cpu_possible_map);
+		set_hard_smp_processor_id(i, i);
+	}
 
 	if (ppc_md.progress) ppc_md.progress("smp_psurge_probe - done", 0x352);
 
@@ -348,6 +358,7 @@ static void __init psurge_dual_sync_tb(int cpu_nr)
 	int t;
 
 	set_dec(tb_ticks_per_jiffy);
+	/* XXX fixme */
 	set_tb(0, 0);
 	last_jiffy_stamp(cpu_nr) = 0;
 
@@ -363,8 +374,6 @@ static void __init psurge_dual_sync_tb(int cpu_nr)
 
 	/* now interrupt the secondary, starting both TBs */
 	psurge_set_ipi(1);
-
-	smp_tb_synchronized = 1;
 }
 
 static struct irqaction psurge_irqaction = {
@@ -625,9 +634,8 @@ void smp_core99_give_timebase(void)
 	for (t = 100000; t > 0 && sec_tb_reset; --t)
 		udelay(10);
 	if (sec_tb_reset)
+		/* XXX BUG_ON here? */
 		printk(KERN_WARNING "Timeout waiting sync(2) on second CPU\n");
-	else
-		smp_tb_synchronized = 1;
 
 	/* Now, restart the timebase by leaving the GPIO to an open collector */
        	pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, core99_tb_gpio, 0);
@@ -810,19 +818,9 @@ static void __devinit smp_core99_setup_cpu(int cpu_nr)
 }
 
 
-/* Core99 Macs (dual G4s and G5s) */
-struct smp_ops_t core99_smp_ops = {
-	.message_pass	= smp_mpic_message_pass,
-	.probe		= smp_core99_probe,
-	.kick_cpu	= smp_core99_kick_cpu,
-	.setup_cpu	= smp_core99_setup_cpu,
-	.give_timebase	= smp_core99_give_timebase,
-	.take_timebase	= smp_core99_take_timebase,
-};
-
 #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC32)
 
-int __cpu_disable(void)
+int smp_core99_cpu_disable(void)
 {
 	cpu_clear(smp_processor_id(), cpu_online_map);
 
@@ -846,7 +844,7 @@ void cpu_die(void)
 	low_cpu_die();
 }
 
-void __cpu_die(unsigned int cpu)
+void smp_core99_cpu_die(unsigned int cpu)
 {
 	int timeout;
 
@@ -858,8 +856,21 @@ void __cpu_die(unsigned int cpu)
 		}
 		msleep(1);
 	}
-	cpu_callin_map[cpu] = 0;
 	cpu_dead[cpu] = 0;
 }
 
 #endif
+
+/* Core99 Macs (dual G4s and G5s) */
+struct smp_ops_t core99_smp_ops = {
+	.message_pass	= smp_mpic_message_pass,
+	.probe		= smp_core99_probe,
+	.kick_cpu	= smp_core99_kick_cpu,
+	.setup_cpu	= smp_core99_setup_cpu,
+	.give_timebase	= smp_core99_give_timebase,
+	.take_timebase	= smp_core99_take_timebase,
+#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC32)
+	.cpu_disable	= smp_core99_cpu_disable,
+	.cpu_die	= smp_core99_cpu_die,
+#endif
+};
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index b9938fece78..e7ca5b1f591 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -3,3 +3,5 @@ obj-y			:= pci.o lpar.o hvCall.o nvram.o reconfig.o \
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_IBMVIO)	+= vio.o
 obj-$(CONFIG_XICS)	+= xics.o
+obj-$(CONFIG_SCANLOG)	+= scanlog.o
+obj-$(CONFIG_EEH)    += eeh.o eeh_event.o
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
new file mode 100644
index 00000000000..79de2310e70
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -0,0 +1,1212 @@
+/*
+ * eeh.c
+ * Copyright (C) 2001 Dave Engebretsen & Todd Inglett 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/delay.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/proc_fs.h>
+#include <linux/rbtree.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <asm/atomic.h>
+#include <asm/eeh.h>
+#include <asm/eeh_event.h>
+#include <asm/io.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/rtas.h>
+
+#undef DEBUG
+
+/** Overview:
+ *  EEH, or "Extended Error Handling" is a PCI bridge technology for
+ *  dealing with PCI bus errors that can't be dealt with within the
+ *  usual PCI framework, except by check-stopping the CPU.  Systems
+ *  that are designed for high-availability/reliability cannot afford
+ *  to crash due to a "mere" PCI error, thus the need for EEH.
+ *  An EEH-capable bridge operates by converting a detected error
+ *  into a "slot freeze", taking the PCI adapter off-line, making
+ *  the slot behave, from the OS'es point of view, as if the slot
+ *  were "empty": all reads return 0xff's and all writes are silently
+ *  ignored.  EEH slot isolation events can be triggered by parity
+ *  errors on the address or data busses (e.g. during posted writes),
+ *  which in turn might be caused by low voltage on the bus, dust,
+ *  vibration, humidity, radioactivity or plain-old failed hardware.
+ *
+ *  Note, however, that one of the leading causes of EEH slot
+ *  freeze events are buggy device drivers, buggy device microcode,
+ *  or buggy device hardware.  This is because any attempt by the
+ *  device to bus-master data to a memory address that is not
+ *  assigned to the device will trigger a slot freeze.   (The idea
+ *  is to prevent devices-gone-wild from corrupting system memory).
+ *  Buggy hardware/drivers will have a miserable time co-existing
+ *  with EEH.
+ *
+ *  Ideally, a PCI device driver, when suspecting that an isolation
+ *  event has occured (e.g. by reading 0xff's), will then ask EEH
+ *  whether this is the case, and then take appropriate steps to
+ *  reset the PCI slot, the PCI device, and then resume operations.
+ *  However, until that day,  the checking is done here, with the
+ *  eeh_check_failure() routine embedded in the MMIO macros.  If
+ *  the slot is found to be isolated, an "EEH Event" is synthesized
+ *  and sent out for processing.
+ */
+
+/* If a device driver keeps reading an MMIO register in an interrupt
+ * handler after a slot isolation event has occurred, we assume it
+ * is broken and panic.  This sets the threshold for how many read
+ * attempts we allow before panicking.
+ */
+#define EEH_MAX_FAILS	100000
+
+/* Misc forward declaraions */
+static void eeh_save_bars(struct pci_dev * pdev, struct pci_dn *pdn);
+
+/* RTAS tokens */
+static int ibm_set_eeh_option;
+static int ibm_set_slot_reset;
+static int ibm_read_slot_reset_state;
+static int ibm_read_slot_reset_state2;
+static int ibm_slot_error_detail;
+
+static int eeh_subsystem_enabled;
+
+/* Lock to avoid races due to multiple reports of an error */
+static DEFINE_SPINLOCK(confirm_error_lock);
+
+/* Buffer for reporting slot-error-detail rtas calls */
+static unsigned char slot_errbuf[RTAS_ERROR_LOG_MAX];
+static DEFINE_SPINLOCK(slot_errbuf_lock);
+static int eeh_error_buf_size;
+
+/* System monitoring statistics */
+static DEFINE_PER_CPU(unsigned long, no_device);
+static DEFINE_PER_CPU(unsigned long, no_dn);
+static DEFINE_PER_CPU(unsigned long, no_cfg_addr);
+static DEFINE_PER_CPU(unsigned long, ignored_check);
+static DEFINE_PER_CPU(unsigned long, total_mmio_ffs);
+static DEFINE_PER_CPU(unsigned long, false_positives);
+static DEFINE_PER_CPU(unsigned long, ignored_failures);
+static DEFINE_PER_CPU(unsigned long, slot_resets);
+
+/**
+ * The pci address cache subsystem.  This subsystem places
+ * PCI device address resources into a red-black tree, sorted
+ * according to the address range, so that given only an i/o
+ * address, the corresponding PCI device can be **quickly**
+ * found. It is safe to perform an address lookup in an interrupt
+ * context; this ability is an important feature.
+ *
+ * Currently, the only customer of this code is the EEH subsystem;
+ * thus, this code has been somewhat tailored to suit EEH better.
+ * In particular, the cache does *not* hold the addresses of devices
+ * for which EEH is not enabled.
+ *
+ * (Implementation Note: The RB tree seems to be better/faster
+ * than any hash algo I could think of for this problem, even
+ * with the penalty of slow pointer chases for d-cache misses).
+ */
+struct pci_io_addr_range
+{
+	struct rb_node rb_node;
+	unsigned long addr_lo;
+	unsigned long addr_hi;
+	struct pci_dev *pcidev;
+	unsigned int flags;
+};
+
+static struct pci_io_addr_cache
+{
+	struct rb_root rb_root;
+	spinlock_t piar_lock;
+} pci_io_addr_cache_root;
+
+static inline struct pci_dev *__pci_get_device_by_addr(unsigned long addr)
+{
+	struct rb_node *n = pci_io_addr_cache_root.rb_root.rb_node;
+
+	while (n) {
+		struct pci_io_addr_range *piar;
+		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
+
+		if (addr < piar->addr_lo) {
+			n = n->rb_left;
+		} else {
+			if (addr > piar->addr_hi) {
+				n = n->rb_right;
+			} else {
+				pci_dev_get(piar->pcidev);
+				return piar->pcidev;
+			}
+		}
+	}
+
+	return NULL;
+}
+
+/**
+ * pci_get_device_by_addr - Get device, given only address
+ * @addr: mmio (PIO) phys address or i/o port number
+ *
+ * Given an mmio phys address, or a port number, find a pci device
+ * that implements this address.  Be sure to pci_dev_put the device
+ * when finished.  I/O port numbers are assumed to be offset
+ * from zero (that is, they do *not* have pci_io_addr added in).
+ * It is safe to call this function within an interrupt.
+ */
+static struct pci_dev *pci_get_device_by_addr(unsigned long addr)
+{
+	struct pci_dev *dev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
+	dev = __pci_get_device_by_addr(addr);
+	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
+	return dev;
+}
+
+#ifdef DEBUG
+/*
+ * Handy-dandy debug print routine, does nothing more
+ * than print out the contents of our addr cache.
+ */
+static void pci_addr_cache_print(struct pci_io_addr_cache *cache)
+{
+	struct rb_node *n;
+	int cnt = 0;
+
+	n = rb_first(&cache->rb_root);
+	while (n) {
+		struct pci_io_addr_range *piar;
+		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
+		printk(KERN_DEBUG "PCI: %s addr range %d [%lx-%lx]: %s\n",
+		       (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", cnt,
+		       piar->addr_lo, piar->addr_hi, pci_name(piar->pcidev));
+		cnt++;
+		n = rb_next(n);
+	}
+}
+#endif
+
+/* Insert address range into the rb tree. */
+static struct pci_io_addr_range *
+pci_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
+		      unsigned long ahi, unsigned int flags)
+{
+	struct rb_node **p = &pci_io_addr_cache_root.rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct pci_io_addr_range *piar;
+
+	/* Walk tree, find a place to insert into tree */
+	while (*p) {
+		parent = *p;
+		piar = rb_entry(parent, struct pci_io_addr_range, rb_node);
+		if (ahi < piar->addr_lo) {
+			p = &parent->rb_left;
+		} else if (alo > piar->addr_hi) {
+			p = &parent->rb_right;
+		} else {
+			if (dev != piar->pcidev ||
+			    alo != piar->addr_lo || ahi != piar->addr_hi) {
+				printk(KERN_WARNING "PIAR: overlapping address range\n");
+			}
+			return piar;
+		}
+	}
+	piar = (struct pci_io_addr_range *)kmalloc(sizeof(struct pci_io_addr_range), GFP_ATOMIC);
+	if (!piar)
+		return NULL;
+
+	piar->addr_lo = alo;
+	piar->addr_hi = ahi;
+	piar->pcidev = dev;
+	piar->flags = flags;
+
+#ifdef DEBUG
+	printk(KERN_DEBUG "PIAR: insert range=[%lx:%lx] dev=%s\n",
+	                  alo, ahi, pci_name (dev));
+#endif
+
+	rb_link_node(&piar->rb_node, parent, p);
+	rb_insert_color(&piar->rb_node, &pci_io_addr_cache_root.rb_root);
+
+	return piar;
+}
+
+static void __pci_addr_cache_insert_device(struct pci_dev *dev)
+{
+	struct device_node *dn;
+	struct pci_dn *pdn;
+	int i;
+	int inserted = 0;
+
+	dn = pci_device_to_OF_node(dev);
+	if (!dn) {
+		printk(KERN_WARNING "PCI: no pci dn found for dev=%s\n", pci_name(dev));
+		return;
+	}
+
+	/* Skip any devices for which EEH is not enabled. */
+	pdn = PCI_DN(dn);
+	if (!(pdn->eeh_mode & EEH_MODE_SUPPORTED) ||
+	    pdn->eeh_mode & EEH_MODE_NOCHECK) {
+#ifdef DEBUG
+		printk(KERN_INFO "PCI: skip building address cache for=%s - %s\n",
+		       pci_name(dev), pdn->node->full_name);
+#endif
+		return;
+	}
+
+	/* The cache holds a reference to the device... */
+	pci_dev_get(dev);
+
+	/* Walk resources on this device, poke them into the tree */
+	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+		unsigned long start = pci_resource_start(dev,i);
+		unsigned long end = pci_resource_end(dev,i);
+		unsigned int flags = pci_resource_flags(dev,i);
+
+		/* We are interested only bus addresses, not dma or other stuff */
+		if (0 == (flags & (IORESOURCE_IO | IORESOURCE_MEM)))
+			continue;
+		if (start == 0 || ~start == 0 || end == 0 || ~end == 0)
+			 continue;
+		pci_addr_cache_insert(dev, start, end, flags);
+		inserted = 1;
+	}
+
+	/* If there was nothing to add, the cache has no reference... */
+	if (!inserted)
+		pci_dev_put(dev);
+}
+
+/**
+ * pci_addr_cache_insert_device - Add a device to the address cache
+ * @dev: PCI device whose I/O addresses we are interested in.
+ *
+ * In order to support the fast lookup of devices based on addresses,
+ * we maintain a cache of devices that can be quickly searched.
+ * This routine adds a device to that cache.
+ */
+static void pci_addr_cache_insert_device(struct pci_dev *dev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
+	__pci_addr_cache_insert_device(dev);
+	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
+}
+
+static inline void __pci_addr_cache_remove_device(struct pci_dev *dev)
+{
+	struct rb_node *n;
+	int removed = 0;
+
+restart:
+	n = rb_first(&pci_io_addr_cache_root.rb_root);
+	while (n) {
+		struct pci_io_addr_range *piar;
+		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
+
+		if (piar->pcidev == dev) {
+			rb_erase(n, &pci_io_addr_cache_root.rb_root);
+			removed = 1;
+			kfree(piar);
+			goto restart;
+		}
+		n = rb_next(n);
+	}
+
+	/* The cache no longer holds its reference to this device... */
+	if (removed)
+		pci_dev_put(dev);
+}
+
+/**
+ * pci_addr_cache_remove_device - remove pci device from addr cache
+ * @dev: device to remove
+ *
+ * Remove a device from the addr-cache tree.
+ * This is potentially expensive, since it will walk
+ * the tree multiple times (once per resource).
+ * But so what; device removal doesn't need to be that fast.
+ */
+static void pci_addr_cache_remove_device(struct pci_dev *dev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
+	__pci_addr_cache_remove_device(dev);
+	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
+}
+
+/**
+ * pci_addr_cache_build - Build a cache of I/O addresses
+ *
+ * Build a cache of pci i/o addresses.  This cache will be used to
+ * find the pci device that corresponds to a given address.
+ * This routine scans all pci busses to build the cache.
+ * Must be run late in boot process, after the pci controllers
+ * have been scaned for devices (after all device resources are known).
+ */
+void __init pci_addr_cache_build(void)
+{
+	struct device_node *dn;
+	struct pci_dev *dev = NULL;
+
+	if (!eeh_subsystem_enabled)
+		return;
+
+	spin_lock_init(&pci_io_addr_cache_root.piar_lock);
+
+	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+		/* Ignore PCI bridges ( XXX why ??) */
+		if ((dev->class >> 16) == PCI_BASE_CLASS_BRIDGE) {
+			continue;
+		}
+		pci_addr_cache_insert_device(dev);
+
+		/* Save the BAR's; firmware doesn't restore these after EEH reset */
+		dn = pci_device_to_OF_node(dev);
+		eeh_save_bars(dev, PCI_DN(dn));
+	}
+
+#ifdef DEBUG
+	/* Verify tree built up above, echo back the list of addrs. */
+	pci_addr_cache_print(&pci_io_addr_cache_root);
+#endif
+}
+
+/* --------------------------------------------------------------- */
+/* Above lies the PCI Address Cache. Below lies the EEH event infrastructure */
+
+void eeh_slot_error_detail (struct pci_dn *pdn, int severity)
+{
+	unsigned long flags;
+	int rc;
+
+	/* Log the error with the rtas logger */
+	spin_lock_irqsave(&slot_errbuf_lock, flags);
+	memset(slot_errbuf, 0, eeh_error_buf_size);
+
+	rc = rtas_call(ibm_slot_error_detail,
+	               8, 1, NULL, pdn->eeh_config_addr,
+	               BUID_HI(pdn->phb->buid),
+	               BUID_LO(pdn->phb->buid), NULL, 0,
+	               virt_to_phys(slot_errbuf),
+	               eeh_error_buf_size,
+	               severity);
+
+	if (rc == 0)
+		log_error(slot_errbuf, ERR_TYPE_RTAS_LOG, 0);
+	spin_unlock_irqrestore(&slot_errbuf_lock, flags);
+}
+
+/**
+ * read_slot_reset_state - Read the reset state of a device node's slot
+ * @dn: device node to read
+ * @rets: array to return results in
+ */
+static int read_slot_reset_state(struct pci_dn *pdn, int rets[])
+{
+	int token, outputs;
+
+	if (ibm_read_slot_reset_state2 != RTAS_UNKNOWN_SERVICE) {
+		token = ibm_read_slot_reset_state2;
+		outputs = 4;
+	} else {
+		token = ibm_read_slot_reset_state;
+		rets[2] = 0; /* fake PE Unavailable info */
+		outputs = 3;
+	}
+
+	return rtas_call(token, 3, outputs, rets, pdn->eeh_config_addr,
+			 BUID_HI(pdn->phb->buid), BUID_LO(pdn->phb->buid));
+}
+
+/**
+ * eeh_token_to_phys - convert EEH address token to phys address
+ * @token i/o token, should be address in the form 0xA....
+ */
+static inline unsigned long eeh_token_to_phys(unsigned long token)
+{
+	pte_t *ptep;
+	unsigned long pa;
+
+	ptep = find_linux_pte(init_mm.pgd, token);
+	if (!ptep)
+		return token;
+	pa = pte_pfn(*ptep) << PAGE_SHIFT;
+
+	return pa | (token & (PAGE_SIZE-1));
+}
+
+/** 
+ * Return the "partitionable endpoint" (pe) under which this device lies
+ */
+static struct device_node * find_device_pe(struct device_node *dn)
+{
+	while ((dn->parent) && PCI_DN(dn->parent) &&
+	      (PCI_DN(dn->parent)->eeh_mode & EEH_MODE_SUPPORTED)) {
+		dn = dn->parent;
+	}
+	return dn;
+}
+
+/** Mark all devices that are peers of this device as failed.
+ *  Mark the device driver too, so that it can see the failure
+ *  immediately; this is critical, since some drivers poll
+ *  status registers in interrupts ... If a driver is polling,
+ *  and the slot is frozen, then the driver can deadlock in
+ *  an interrupt context, which is bad.
+ */
+
+static void __eeh_mark_slot (struct device_node *dn, int mode_flag)
+{
+	while (dn) {
+		if (PCI_DN(dn)) {
+			PCI_DN(dn)->eeh_mode |= mode_flag;
+
+			if (dn->child)
+				__eeh_mark_slot (dn->child, mode_flag);
+		}
+		dn = dn->sibling;
+	}
+}
+
+void eeh_mark_slot (struct device_node *dn, int mode_flag)
+{
+	dn = find_device_pe (dn);
+	PCI_DN(dn)->eeh_mode |= mode_flag;
+	__eeh_mark_slot (dn->child, mode_flag);
+}
+
+static void __eeh_clear_slot (struct device_node *dn, int mode_flag)
+{
+	while (dn) {
+		if (PCI_DN(dn)) {
+			PCI_DN(dn)->eeh_mode &= ~mode_flag;
+			PCI_DN(dn)->eeh_check_count = 0;
+			if (dn->child)
+				__eeh_clear_slot (dn->child, mode_flag);
+		}
+		dn = dn->sibling;
+	}
+}
+
+void eeh_clear_slot (struct device_node *dn, int mode_flag)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&confirm_error_lock, flags);
+	dn = find_device_pe (dn);
+	PCI_DN(dn)->eeh_mode &= ~mode_flag;
+	PCI_DN(dn)->eeh_check_count = 0;
+	__eeh_clear_slot (dn->child, mode_flag);
+	spin_unlock_irqrestore(&confirm_error_lock, flags);
+}
+
+/**
+ * eeh_dn_check_failure - check if all 1's data is due to EEH slot freeze
+ * @dn device node
+ * @dev pci device, if known
+ *
+ * Check for an EEH failure for the given device node.  Call this
+ * routine if the result of a read was all 0xff's and you want to
+ * find out if this is due to an EEH slot freeze.  This routine
+ * will query firmware for the EEH status.
+ *
+ * Returns 0 if there has not been an EEH error; otherwise returns
+ * a non-zero value and queues up a slot isolation event notification.
+ *
+ * It is safe to call this routine in an interrupt context.
+ */
+int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
+{
+	int ret;
+	int rets[3];
+	unsigned long flags;
+	struct pci_dn *pdn;
+	int rc = 0;
+
+	__get_cpu_var(total_mmio_ffs)++;
+
+	if (!eeh_subsystem_enabled)
+		return 0;
+
+	if (!dn) {
+		__get_cpu_var(no_dn)++;
+		return 0;
+	}
+	pdn = PCI_DN(dn);
+
+	/* Access to IO BARs might get this far and still not want checking. */
+	if (!(pdn->eeh_mode & EEH_MODE_SUPPORTED) ||
+	    pdn->eeh_mode & EEH_MODE_NOCHECK) {
+		__get_cpu_var(ignored_check)++;
+#ifdef DEBUG
+		printk ("EEH:ignored check (%x) for %s %s\n", 
+		        pdn->eeh_mode, pci_name (dev), dn->full_name);
+#endif
+		return 0;
+	}
+
+	if (!pdn->eeh_config_addr) {
+		__get_cpu_var(no_cfg_addr)++;
+		return 0;
+	}
+
+	/* If we already have a pending isolation event for this
+	 * slot, we know it's bad already, we don't need to check.
+	 * Do this checking under a lock; as multiple PCI devices
+	 * in one slot might report errors simultaneously, and we
+	 * only want one error recovery routine running.
+	 */
+	spin_lock_irqsave(&confirm_error_lock, flags);
+	rc = 1;
+	if (pdn->eeh_mode & EEH_MODE_ISOLATED) {
+		pdn->eeh_check_count ++;
+		if (pdn->eeh_check_count >= EEH_MAX_FAILS) {
+			printk (KERN_ERR "EEH: Device driver ignored %d bad reads, panicing\n",
+			        pdn->eeh_check_count);
+			dump_stack();
+			
+			/* re-read the slot reset state */
+			if (read_slot_reset_state(pdn, rets) != 0)
+				rets[0] = -1;	/* reset state unknown */
+
+			/* If we are here, then we hit an infinite loop. Stop. */
+			panic("EEH: MMIO halt (%d) on device:%s\n", rets[0], pci_name(dev));
+		}
+		goto dn_unlock;
+	}
+
+	/*
+	 * Now test for an EEH failure.  This is VERY expensive.
+	 * Note that the eeh_config_addr may be a parent device
+	 * in the case of a device behind a bridge, or it may be
+	 * function zero of a multi-function device.
+	 * In any case they must share a common PHB.
+	 */
+	ret = read_slot_reset_state(pdn, rets);
+
+	/* If the call to firmware failed, punt */
+	if (ret != 0) {
+		printk(KERN_WARNING "EEH: read_slot_reset_state() failed; rc=%d dn=%s\n",
+		       ret, dn->full_name);
+		__get_cpu_var(false_positives)++;
+		rc = 0;
+		goto dn_unlock;
+	}
+
+	/* If EEH is not supported on this device, punt. */
+	if (rets[1] != 1) {
+		printk(KERN_WARNING "EEH: event on unsupported device, rc=%d dn=%s\n",
+		       ret, dn->full_name);
+		__get_cpu_var(false_positives)++;
+		rc = 0;
+		goto dn_unlock;
+	}
+
+	/* If not the kind of error we know about, punt. */
+	if (rets[0] != 2 && rets[0] != 4 && rets[0] != 5) {
+		__get_cpu_var(false_positives)++;
+		rc = 0;
+		goto dn_unlock;
+	}
+
+	/* Note that config-io to empty slots may fail;
+	 * we recognize empty because they don't have children. */
+	if ((rets[0] == 5) && (dn->child == NULL)) {
+		__get_cpu_var(false_positives)++;
+		rc = 0;
+		goto dn_unlock;
+	}
+
+	__get_cpu_var(slot_resets)++;
+ 
+	/* Avoid repeated reports of this failure, including problems
+	 * with other functions on this device, and functions under
+	 * bridges. */
+	eeh_mark_slot (dn, EEH_MODE_ISOLATED);
+	spin_unlock_irqrestore(&confirm_error_lock, flags);
+
+	eeh_send_failure_event (dn, dev, rets[0], rets[2]);
+	
+	/* Most EEH events are due to device driver bugs.  Having
+	 * a stack trace will help the device-driver authors figure
+	 * out what happened.  So print that out. */
+	if (rets[0] != 5) dump_stack();
+	return 1;
+
+dn_unlock:
+	spin_unlock_irqrestore(&confirm_error_lock, flags);
+	return rc;
+}
+
+EXPORT_SYMBOL_GPL(eeh_dn_check_failure);
+
+/**
+ * eeh_check_failure - check if all 1's data is due to EEH slot freeze
+ * @token i/o token, should be address in the form 0xA....
+ * @val value, should be all 1's (XXX why do we need this arg??)
+ *
+ * Check for an EEH failure at the given token address.  Call this
+ * routine if the result of a read was all 0xff's and you want to
+ * find out if this is due to an EEH slot freeze event.  This routine
+ * will query firmware for the EEH status.
+ *
+ * Note this routine is safe to call in an interrupt context.
+ */
+unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val)
+{
+	unsigned long addr;
+	struct pci_dev *dev;
+	struct device_node *dn;
+
+	/* Finding the phys addr + pci device; this is pretty quick. */
+	addr = eeh_token_to_phys((unsigned long __force) token);
+	dev = pci_get_device_by_addr(addr);
+	if (!dev) {
+		__get_cpu_var(no_device)++;
+		return val;
+	}
+
+	dn = pci_device_to_OF_node(dev);
+	eeh_dn_check_failure (dn, dev);
+
+	pci_dev_put(dev);
+	return val;
+}
+
+EXPORT_SYMBOL(eeh_check_failure);
+
+/* ------------------------------------------------------------- */
+/* The code below deals with error recovery */
+
+/** Return negative value if a permanent error, else return
+ * a number of milliseconds to wait until the PCI slot is
+ * ready to be used.
+ */
+static int
+eeh_slot_availability(struct pci_dn *pdn)
+{
+	int rc;
+	int rets[3];
+
+	rc = read_slot_reset_state(pdn, rets);
+
+	if (rc) return rc;
+
+	if (rets[1] == 0) return -1;  /* EEH is not supported */
+	if (rets[0] == 0)  return 0;  /* Oll Korrect */
+	if (rets[0] == 5) {
+		if (rets[2] == 0) return -1; /* permanently unavailable */
+		return rets[2]; /* number of millisecs to wait */
+	}
+	return -1;
+}
+
+/** rtas_pci_slot_reset raises/lowers the pci #RST line
+ *  state: 1/0 to raise/lower the #RST
+ *
+ * Clear the EEH-frozen condition on a slot.  This routine
+ * asserts the PCI #RST line if the 'state' argument is '1',
+ * and drops the #RST line if 'state is '0'.  This routine is
+ * safe to call in an interrupt context.
+ *
+ */
+
+static void
+rtas_pci_slot_reset(struct pci_dn *pdn, int state)
+{
+	int rc;
+
+	BUG_ON (pdn==NULL); 
+
+	if (!pdn->phb) {
+		printk (KERN_WARNING "EEH: in slot reset, device node %s has no phb\n",
+		        pdn->node->full_name);
+		return;
+	}
+
+	rc = rtas_call(ibm_set_slot_reset,4,1, NULL,
+	               pdn->eeh_config_addr,
+	               BUID_HI(pdn->phb->buid),
+	               BUID_LO(pdn->phb->buid),
+	               state);
+	if (rc) {
+		printk (KERN_WARNING "EEH: Unable to reset the failed slot, (%d) #RST=%d dn=%s\n", 
+		        rc, state, pdn->node->full_name);
+		return;
+	}
+}
+
+/** rtas_set_slot_reset -- assert the pci #RST line for 1/4 second
+ *  dn -- device node to be reset.
+ */
+
+void
+rtas_set_slot_reset(struct pci_dn *pdn)
+{
+	int i, rc;
+
+	rtas_pci_slot_reset (pdn, 1);
+
+	/* The PCI bus requires that the reset be held high for at least
+	 * a 100 milliseconds. We wait a bit longer 'just in case'.  */
+
+#define PCI_BUS_RST_HOLD_TIME_MSEC 250
+	msleep (PCI_BUS_RST_HOLD_TIME_MSEC);
+	
+	/* We might get hit with another EEH freeze as soon as the 
+	 * pci slot reset line is dropped. Make sure we don't miss
+	 * these, and clear the flag now. */
+	eeh_clear_slot (pdn->node, EEH_MODE_ISOLATED);
+
+	rtas_pci_slot_reset (pdn, 0);
+
+	/* After a PCI slot has been reset, the PCI Express spec requires
+	 * a 1.5 second idle time for the bus to stabilize, before starting
+	 * up traffic. */
+#define PCI_BUS_SETTLE_TIME_MSEC 1800
+	msleep (PCI_BUS_SETTLE_TIME_MSEC);
+
+	/* Now double check with the firmware to make sure the device is
+	 * ready to be used; if not, wait for recovery. */
+	for (i=0; i<10; i++) {
+		rc = eeh_slot_availability (pdn);
+		if (rc <= 0) break;
+
+		msleep (rc+100);
+	}
+}
+
+/* ------------------------------------------------------- */
+/** Save and restore of PCI BARs
+ *
+ * Although firmware will set up BARs during boot, it doesn't
+ * set up device BAR's after a device reset, although it will,
+ * if requested, set up bridge configuration. Thus, we need to
+ * configure the PCI devices ourselves.  
+ */
+
+/**
+ * __restore_bars - Restore the Base Address Registers
+ * Loads the PCI configuration space base address registers,
+ * the expansion ROM base address, the latency timer, and etc.
+ * from the saved values in the device node.
+ */
+static inline void __restore_bars (struct pci_dn *pdn)
+{
+	int i;
+
+	if (NULL==pdn->phb) return;
+	for (i=4; i<10; i++) {
+		rtas_write_config(pdn, i*4, 4, pdn->config_space[i]);
+	}
+
+	/* 12 == Expansion ROM Address */
+	rtas_write_config(pdn, 12*4, 4, pdn->config_space[12]);
+
+#define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF))
+#define SAVED_BYTE(OFF) (((u8 *)(pdn->config_space))[BYTE_SWAP(OFF)])
+
+	rtas_write_config (pdn, PCI_CACHE_LINE_SIZE, 1,
+	            SAVED_BYTE(PCI_CACHE_LINE_SIZE));
+
+	rtas_write_config (pdn, PCI_LATENCY_TIMER, 1,
+	            SAVED_BYTE(PCI_LATENCY_TIMER));
+
+	/* max latency, min grant, interrupt pin and line */
+	rtas_write_config(pdn, 15*4, 4, pdn->config_space[15]);
+}
+
+/**
+ * eeh_restore_bars - restore the PCI config space info
+ *
+ * This routine performs a recursive walk to the children
+ * of this device as well.
+ */
+void eeh_restore_bars(struct pci_dn *pdn)
+{
+	struct device_node *dn;
+	if (!pdn) 
+		return;
+	
+	if (! pdn->eeh_is_bridge)
+		__restore_bars (pdn);
+
+	dn = pdn->node->child;
+	while (dn) {
+		eeh_restore_bars (PCI_DN(dn));
+		dn = dn->sibling;
+	}
+}
+
+/**
+ * eeh_save_bars - save device bars
+ *
+ * Save the values of the device bars. Unlike the restore
+ * routine, this routine is *not* recursive. This is because
+ * PCI devices are added individuallly; but, for the restore,
+ * an entire slot is reset at a time.
+ */
+static void eeh_save_bars(struct pci_dev * pdev, struct pci_dn *pdn)
+{
+	int i;
+
+	if (!pdev || !pdn )
+		return;
+	
+	for (i = 0; i < 16; i++)
+		pci_read_config_dword(pdev, i * 4, &pdn->config_space[i]);
+
+	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+		pdn->eeh_is_bridge = 1;
+}
+
+void
+rtas_configure_bridge(struct pci_dn *pdn)
+{
+	int token = rtas_token ("ibm,configure-bridge");
+	int rc;
+
+	if (token == RTAS_UNKNOWN_SERVICE)
+		return;
+	rc = rtas_call(token,3,1, NULL,
+	               pdn->eeh_config_addr,
+	               BUID_HI(pdn->phb->buid),
+	               BUID_LO(pdn->phb->buid));
+	if (rc) {
+		printk (KERN_WARNING "EEH: Unable to configure device bridge (%d) for %s\n",
+		        rc, pdn->node->full_name);
+	}
+}
+
+/* ------------------------------------------------------------- */
+/* The code below deals with enabling EEH for devices during  the
+ * early boot sequence.  EEH must be enabled before any PCI probing
+ * can be done.
+ */
+
+#define EEH_ENABLE 1
+
+struct eeh_early_enable_info {
+	unsigned int buid_hi;
+	unsigned int buid_lo;
+};
+
+/* Enable eeh for the given device node. */
+static void *early_enable_eeh(struct device_node *dn, void *data)
+{
+	struct eeh_early_enable_info *info = data;
+	int ret;
+	char *status = get_property(dn, "status", NULL);
+	u32 *class_code = (u32 *)get_property(dn, "class-code", NULL);
+	u32 *vendor_id = (u32 *)get_property(dn, "vendor-id", NULL);
+	u32 *device_id = (u32 *)get_property(dn, "device-id", NULL);
+	u32 *regs;
+	int enable;
+	struct pci_dn *pdn = PCI_DN(dn);
+
+	pdn->eeh_mode = 0;
+	pdn->eeh_check_count = 0;
+	pdn->eeh_freeze_count = 0;
+
+	if (status && strcmp(status, "ok") != 0)
+		return NULL;	/* ignore devices with bad status */
+
+	/* Ignore bad nodes. */
+	if (!class_code || !vendor_id || !device_id)
+		return NULL;
+
+	/* There is nothing to check on PCI to ISA bridges */
+	if (dn->type && !strcmp(dn->type, "isa")) {
+		pdn->eeh_mode |= EEH_MODE_NOCHECK;
+		return NULL;
+	}
+
+	/*
+	 * Now decide if we are going to "Disable" EEH checking
+	 * for this device.  We still run with the EEH hardware active,
+	 * but we won't be checking for ff's.  This means a driver
+	 * could return bad data (very bad!), an interrupt handler could
+	 * hang waiting on status bits that won't change, etc.
+	 * But there are a few cases like display devices that make sense.
+	 */
+	enable = 1;	/* i.e. we will do checking */
+	if ((*class_code >> 16) == PCI_BASE_CLASS_DISPLAY)
+		enable = 0;
+
+	if (!enable)
+		pdn->eeh_mode |= EEH_MODE_NOCHECK;
+
+	/* Ok... see if this device supports EEH.  Some do, some don't,
+	 * and the only way to find out is to check each and every one. */
+	regs = (u32 *)get_property(dn, "reg", NULL);
+	if (regs) {
+		/* First register entry is addr (00BBSS00)  */
+		/* Try to enable eeh */
+		ret = rtas_call(ibm_set_eeh_option, 4, 1, NULL,
+		                regs[0], info->buid_hi, info->buid_lo,
+		                EEH_ENABLE);
+
+		if (ret == 0) {
+			eeh_subsystem_enabled = 1;
+			pdn->eeh_mode |= EEH_MODE_SUPPORTED;
+			pdn->eeh_config_addr = regs[0];
+#ifdef DEBUG
+			printk(KERN_DEBUG "EEH: %s: eeh enabled\n", dn->full_name);
+#endif
+		} else {
+
+			/* This device doesn't support EEH, but it may have an
+			 * EEH parent, in which case we mark it as supported. */
+			if (dn->parent && PCI_DN(dn->parent)
+			    && (PCI_DN(dn->parent)->eeh_mode & EEH_MODE_SUPPORTED)) {
+				/* Parent supports EEH. */
+				pdn->eeh_mode |= EEH_MODE_SUPPORTED;
+				pdn->eeh_config_addr = PCI_DN(dn->parent)->eeh_config_addr;
+				return NULL;
+			}
+		}
+	} else {
+		printk(KERN_WARNING "EEH: %s: unable to get reg property.\n",
+		       dn->full_name);
+	}
+
+	return NULL;
+}
+
+/*
+ * Initialize EEH by trying to enable it for all of the adapters in the system.
+ * As a side effect we can determine here if eeh is supported at all.
+ * Note that we leave EEH on so failed config cycles won't cause a machine
+ * check.  If a user turns off EEH for a particular adapter they are really
+ * telling Linux to ignore errors.  Some hardware (e.g. POWER5) won't
+ * grant access to a slot if EEH isn't enabled, and so we always enable
+ * EEH for all slots/all devices.
+ *
+ * The eeh-force-off option disables EEH checking globally, for all slots.
+ * Even if force-off is set, the EEH hardware is still enabled, so that
+ * newer systems can boot.
+ */
+void __init eeh_init(void)
+{
+	struct device_node *phb, *np;
+	struct eeh_early_enable_info info;
+
+	spin_lock_init(&confirm_error_lock);
+	spin_lock_init(&slot_errbuf_lock);
+
+	np = of_find_node_by_path("/rtas");
+	if (np == NULL)
+		return;
+
+	ibm_set_eeh_option = rtas_token("ibm,set-eeh-option");
+	ibm_set_slot_reset = rtas_token("ibm,set-slot-reset");
+	ibm_read_slot_reset_state2 = rtas_token("ibm,read-slot-reset-state2");
+	ibm_read_slot_reset_state = rtas_token("ibm,read-slot-reset-state");
+	ibm_slot_error_detail = rtas_token("ibm,slot-error-detail");
+
+	if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE)
+		return;
+
+	eeh_error_buf_size = rtas_token("rtas-error-log-max");
+	if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) {
+		eeh_error_buf_size = 1024;
+	}
+	if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) {
+		printk(KERN_WARNING "EEH: rtas-error-log-max is bigger than allocated "
+		      "buffer ! (%d vs %d)", eeh_error_buf_size, RTAS_ERROR_LOG_MAX);
+		eeh_error_buf_size = RTAS_ERROR_LOG_MAX;
+	}
+
+	/* Enable EEH for all adapters.  Note that eeh requires buid's */
+	for (phb = of_find_node_by_name(NULL, "pci"); phb;
+	     phb = of_find_node_by_name(phb, "pci")) {
+		unsigned long buid;
+
+		buid = get_phb_buid(phb);
+		if (buid == 0 || PCI_DN(phb) == NULL)
+			continue;
+
+		info.buid_lo = BUID_LO(buid);
+		info.buid_hi = BUID_HI(buid);
+		traverse_pci_devices(phb, early_enable_eeh, &info);
+	}
+
+	if (eeh_subsystem_enabled)
+		printk(KERN_INFO "EEH: PCI Enhanced I/O Error Handling Enabled\n");
+	else
+		printk(KERN_WARNING "EEH: No capable adapters found\n");
+}
+
+/**
+ * eeh_add_device_early - enable EEH for the indicated device_node
+ * @dn: device node for which to set up EEH
+ *
+ * This routine must be used to perform EEH initialization for PCI
+ * devices that were added after system boot (e.g. hotplug, dlpar).
+ * This routine must be called before any i/o is performed to the
+ * adapter (inluding any config-space i/o).
+ * Whether this actually enables EEH or not for this device depends
+ * on the CEC architecture, type of the device, on earlier boot
+ * command-line arguments & etc.
+ */
+void eeh_add_device_early(struct device_node *dn)
+{
+	struct pci_controller *phb;
+	struct eeh_early_enable_info info;
+
+	if (!dn || !PCI_DN(dn))
+		return;
+	phb = PCI_DN(dn)->phb;
+	if (NULL == phb || 0 == phb->buid) {
+		printk(KERN_WARNING "EEH: Expected buid but found none for %s\n",
+		       dn->full_name);
+		dump_stack();
+		return;
+	}
+
+	info.buid_hi = BUID_HI(phb->buid);
+	info.buid_lo = BUID_LO(phb->buid);
+	early_enable_eeh(dn, &info);
+}
+EXPORT_SYMBOL_GPL(eeh_add_device_early);
+
+/**
+ * eeh_add_device_late - perform EEH initialization for the indicated pci device
+ * @dev: pci device for which to set up EEH
+ *
+ * This routine must be used to complete EEH initialization for PCI
+ * devices that were added after system boot (e.g. hotplug, dlpar).
+ */
+void eeh_add_device_late(struct pci_dev *dev)
+{
+	struct device_node *dn;
+	struct pci_dn *pdn;
+
+	if (!dev || !eeh_subsystem_enabled)
+		return;
+
+#ifdef DEBUG
+	printk(KERN_DEBUG "EEH: adding device %s\n", pci_name(dev));
+#endif
+
+	pci_dev_get (dev);
+	dn = pci_device_to_OF_node(dev);
+	pdn = PCI_DN(dn);
+	pdn->pcidev = dev;
+
+	pci_addr_cache_insert_device (dev);
+	eeh_save_bars(dev, pdn);
+}
+EXPORT_SYMBOL_GPL(eeh_add_device_late);
+
+/**
+ * eeh_remove_device - undo EEH setup for the indicated pci device
+ * @dev: pci device to be removed
+ *
+ * This routine should be when a device is removed from a running
+ * system (e.g. by hotplug or dlpar).
+ */
+void eeh_remove_device(struct pci_dev *dev)
+{
+	struct device_node *dn;
+	if (!dev || !eeh_subsystem_enabled)
+		return;
+
+	/* Unregister the device with the EEH/PCI address search system */
+#ifdef DEBUG
+	printk(KERN_DEBUG "EEH: remove device %s\n", pci_name(dev));
+#endif
+	pci_addr_cache_remove_device(dev);
+
+	dn = pci_device_to_OF_node(dev);
+	PCI_DN(dn)->pcidev = NULL;
+	pci_dev_put (dev);
+}
+EXPORT_SYMBOL_GPL(eeh_remove_device);
+
+static int proc_eeh_show(struct seq_file *m, void *v)
+{
+	unsigned int cpu;
+	unsigned long ffs = 0, positives = 0, failures = 0;
+	unsigned long resets = 0;
+	unsigned long no_dev = 0, no_dn = 0, no_cfg = 0, no_check = 0;
+
+	for_each_cpu(cpu) {
+		ffs += per_cpu(total_mmio_ffs, cpu);
+		positives += per_cpu(false_positives, cpu);
+		failures += per_cpu(ignored_failures, cpu);
+		resets += per_cpu(slot_resets, cpu);
+		no_dev += per_cpu(no_device, cpu);
+		no_dn += per_cpu(no_dn, cpu);
+		no_cfg += per_cpu(no_cfg_addr, cpu);
+		no_check += per_cpu(ignored_check, cpu);
+	}
+
+	if (0 == eeh_subsystem_enabled) {
+		seq_printf(m, "EEH Subsystem is globally disabled\n");
+		seq_printf(m, "eeh_total_mmio_ffs=%ld\n", ffs);
+	} else {
+		seq_printf(m, "EEH Subsystem is enabled\n");
+		seq_printf(m,
+				"no device=%ld\n"
+				"no device node=%ld\n"
+				"no config address=%ld\n"
+				"check not wanted=%ld\n"
+				"eeh_total_mmio_ffs=%ld\n"
+				"eeh_false_positives=%ld\n"
+				"eeh_ignored_failures=%ld\n"
+				"eeh_slot_resets=%ld\n",
+				no_dev, no_dn, no_cfg, no_check,
+				ffs, positives, failures, resets);
+	}
+
+	return 0;
+}
+
+static int proc_eeh_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, proc_eeh_show, NULL);
+}
+
+static struct file_operations proc_eeh_operations = {
+	.open      = proc_eeh_open,
+	.read      = seq_read,
+	.llseek    = seq_lseek,
+	.release   = single_release,
+};
+
+static int __init eeh_init_proc(void)
+{
+	struct proc_dir_entry *e;
+
+	if (platform_is_pseries()) {
+		e = create_proc_entry("ppc64/eeh", 0, NULL);
+		if (e)
+			e->proc_fops = &proc_eeh_operations;
+	}
+
+	return 0;
+}
+__initcall(eeh_init_proc);
diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c
new file mode 100644
index 00000000000..92497333c2b
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/eeh_event.c
@@ -0,0 +1,155 @@
+/*
+ * eeh_event.c
+ *
+ * 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
+ *
+ * Copyright (c) 2005 Linas Vepstas <linas@linas.org>
+ */
+
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <asm/eeh_event.h>
+
+/** Overview:
+ *  EEH error states may be detected within exception handlers;
+ *  however, the recovery processing needs to occur asynchronously
+ *  in a normal kernel context and not an interrupt context.
+ *  This pair of routines creates an event and queues it onto a
+ *  work-queue, where a worker thread can drive recovery.
+ */
+
+/* EEH event workqueue setup. */
+static spinlock_t eeh_eventlist_lock = SPIN_LOCK_UNLOCKED;
+LIST_HEAD(eeh_eventlist);
+static void eeh_thread_launcher(void *);
+DECLARE_WORK(eeh_event_wq, eeh_thread_launcher, NULL);
+
+/**
+ * eeh_panic - call panic() for an eeh event that cannot be handled.
+ * The philosophy of this routine is that it is better to panic and
+ * halt the OS than it is to risk possible data corruption by
+ * oblivious device drivers that don't know better.
+ *
+ * @dev pci device that had an eeh event
+ * @reset_state current reset state of the device slot
+ */
+static void eeh_panic(struct pci_dev *dev, int reset_state)
+{
+	/*
+	 * Since the panic_on_oops sysctl is used to halt the system
+	 * in light of potential corruption, we can use it here.
+	 */
+	if (panic_on_oops) {
+		panic("EEH: MMIO failure (%d) on device:%s\n", reset_state,
+		      pci_name(dev));
+	}
+	else {
+		printk(KERN_INFO "EEH: Ignored MMIO failure (%d) on device:%s\n",
+		       reset_state, pci_name(dev));
+	}
+}
+
+/**
+ * eeh_event_handler - dispatch EEH events.  The detection of a frozen
+ * slot can occur inside an interrupt, where it can be hard to do
+ * anything about it.  The goal of this routine is to pull these
+ * detection events out of the context of the interrupt handler, and
+ * re-dispatch them for processing at a later time in a normal context.
+ *
+ * @dummy - unused
+ */
+static int eeh_event_handler(void * dummy)
+{
+	unsigned long flags;
+	struct eeh_event	*event;
+
+	daemonize ("eehd");
+
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		spin_lock_irqsave(&eeh_eventlist_lock, flags);
+		event = NULL;
+		if (!list_empty(&eeh_eventlist)) {
+			event = list_entry(eeh_eventlist.next, struct eeh_event, list);
+			list_del(&event->list);
+		}
+		spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+		if (event == NULL)
+			break;
+
+		printk(KERN_INFO "EEH: Detected PCI bus error on device %s\n",
+		       pci_name(event->dev));
+
+		eeh_panic (event->dev, event->state);
+
+		kfree(event);
+	}
+
+	return 0;
+}
+
+/**
+ * eeh_thread_launcher
+ *
+ * @dummy - unused
+ */
+static void eeh_thread_launcher(void *dummy)
+{
+	if (kernel_thread(eeh_event_handler, NULL, CLONE_KERNEL) < 0)
+		printk(KERN_ERR "Failed to start EEH daemon\n");
+}
+
+/**
+ * eeh_send_failure_event - generate a PCI error event
+ * @dev pci device
+ *
+ * This routine can be called within an interrupt context;
+ * the actual event will be delivered in a normal context
+ * (from a workqueue).
+ */
+int eeh_send_failure_event (struct device_node *dn,
+                            struct pci_dev *dev,
+                            int state,
+                            int time_unavail)
+{
+	unsigned long flags;
+	struct eeh_event *event;
+
+	event = kmalloc(sizeof(*event), GFP_ATOMIC);
+	if (event == NULL) {
+		printk (KERN_ERR "EEH: out of memory, event not handled\n");
+		return 1;
+ 	}
+
+	if (dev)
+		pci_dev_get(dev);
+
+	event->dn = dn;
+	event->dev = dev;
+	event->state = state;
+	event->time_unavail = time_unavail;
+
+	/* We may or may not be called in an interrupt context */
+	spin_lock_irqsave(&eeh_eventlist_lock, flags);
+	list_add(&event->list, &eeh_eventlist);
+	spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+
+	schedule_work(&eeh_event_wq);
+
+	return 0;
+}
+
+/********************** END OF FILE ******************************/
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index fcc50bfd43f..97ba5214417 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -42,7 +42,6 @@
 #include <asm/machdep.h>
 #include <asm/abs_addr.h>
 #include <asm/pSeries_reconfig.h>
-#include <asm/systemcfg.h>
 #include <asm/firmware.h>
 #include <asm/tce.h>
 #include <asm/ppc-pci.h>
@@ -582,7 +581,7 @@ void iommu_init_early_pSeries(void)
 		return;
 	}
 
-	if (systemcfg->platform & PLATFORM_LPAR) {
+	if (platform_is_lpar()) {
 		if (firmware_has_feature(FW_FEATURE_MULTITCE)) {
 			ppc_md.tce_build = tce_buildmulti_pSeriesLP;
 			ppc_md.tce_free	 = tce_freemulti_pSeriesLP;
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index c198656a3bb..999a9620b5c 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -107,7 +107,6 @@ static void __init pSeries_request_regions(void)
 
 void __init pSeries_final_fixup(void)
 {
-	phbs_remap_io();
 	pSeries_request_regions();
 
 	pci_addr_cache_build();
@@ -123,7 +122,7 @@ static void fixup_winbond_82c105(struct pci_dev* dev)
 	int i;
 	unsigned int reg;
 
-	if (!(systemcfg->platform & PLATFORM_PSERIES))
+	if (!platform_is_pseries())
 		return;
 
 	printk("Using INTC for W82c105 IDE controller.\n");
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index d7d40033945..d8864164dbe 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -408,7 +408,7 @@ static int proc_ppc64_create_ofdt(void)
 {
 	struct proc_dir_entry *ent;
 
-	if (!(systemcfg->platform & PLATFORM_PSERIES))
+	if (!platform_is_pseries())
 		return 0;
 
 	ent = create_proc_entry("ppc64/ofdt", S_IWUSR, NULL);
diff --git a/arch/powerpc/platforms/pseries/rtasd.c b/arch/powerpc/platforms/pseries/rtasd.c
index e26b0420b6d..a6f628d4c9d 100644
--- a/arch/powerpc/platforms/pseries/rtasd.c
+++ b/arch/powerpc/platforms/pseries/rtasd.c
@@ -27,7 +27,6 @@
 #include <asm/prom.h>
 #include <asm/nvram.h>
 #include <asm/atomic.h>
-#include <asm/systemcfg.h>
 
 #if 0
 #define DEBUG(A...)	printk(KERN_ERR A)
@@ -482,10 +481,12 @@ static int __init rtas_init(void)
 {
 	struct proc_dir_entry *entry;
 
-	/* No RTAS, only warn if we are on a pSeries box  */
+	if (!platform_is_pseries())
+		return 0;
+
+	/* No RTAS */
 	if (rtas_token("event-scan") == RTAS_UNKNOWN_SERVICE) {
-		if (systemcfg->platform & PLATFORM_PSERIES)
-			printk(KERN_INFO "rtasd: no event-scan on system\n");
+		printk(KERN_INFO "rtasd: no event-scan on system\n");
 		return 1;
 	}
 
diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c
new file mode 100644
index 00000000000..2edc947f7c4
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/scanlog.c
@@ -0,0 +1,235 @@
+/*
+ *  c 2001 PPC 64 Team, 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.
+ *
+ * scan-log-data driver for PPC64  Todd Inglett <tinglett@vnet.ibm.com>
+ *
+ * When ppc64 hardware fails the service processor dumps internal state
+ * of the system.  After a reboot the operating system can access a dump
+ * of this data using this driver.  A dump exists if the device-tree
+ * /chosen/ibm,scan-log-data property exists.
+ *
+ * This driver exports /proc/ppc64/scan-log-dump which can be read.
+ * The driver supports only sequential reads.
+ *
+ * The driver looks at a write to the driver for the single word "reset".
+ * If given, the driver will reset the scanlog so the platform can free it.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/proc_fs.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <asm/uaccess.h>
+#include <asm/rtas.h>
+#include <asm/prom.h>
+
+#define MODULE_VERS "1.0"
+#define MODULE_NAME "scanlog"
+
+/* Status returns from ibm,scan-log-dump */
+#define SCANLOG_COMPLETE 0
+#define SCANLOG_HWERROR -1
+#define SCANLOG_CONTINUE 1
+
+#define DEBUG(A...) do { if (scanlog_debug) printk(KERN_ERR "scanlog: " A); } while (0)
+
+static int scanlog_debug;
+static unsigned int ibm_scan_log_dump;			/* RTAS token */
+static struct proc_dir_entry *proc_ppc64_scan_log_dump;	/* The proc file */
+
+static ssize_t scanlog_read(struct file *file, char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+        struct inode * inode = file->f_dentry->d_inode;
+	struct proc_dir_entry *dp;
+	unsigned int *data;
+	int status;
+	unsigned long len, off;
+	unsigned int wait_time;
+
+        dp = PDE(inode);
+ 	data = (unsigned int *)dp->data;
+
+	if (!data) {
+		printk(KERN_ERR "scanlog: read failed no data\n");
+		return -EIO;
+	}
+
+	if (count > RTAS_DATA_BUF_SIZE)
+		count = RTAS_DATA_BUF_SIZE;
+
+	if (count < 1024) {
+		/* This is the min supported by this RTAS call.  Rather
+		 * than do all the buffering we insist the user code handle
+		 * larger reads.  As long as cp works... :)
+		 */
+		printk(KERN_ERR "scanlog: cannot perform a small read (%ld)\n", count);
+		return -EINVAL;
+	}
+
+	if (!access_ok(VERIFY_WRITE, buf, count))
+		return -EFAULT;
+
+	for (;;) {
+		wait_time = 500;	/* default wait if no data */
+		spin_lock(&rtas_data_buf_lock);
+		memcpy(rtas_data_buf, data, RTAS_DATA_BUF_SIZE);
+		status = rtas_call(ibm_scan_log_dump, 2, 1, NULL,
+				   (u32) __pa(rtas_data_buf), (u32) count);
+		memcpy(data, rtas_data_buf, RTAS_DATA_BUF_SIZE);
+		spin_unlock(&rtas_data_buf_lock);
+
+		DEBUG("status=%d, data[0]=%x, data[1]=%x, data[2]=%x\n",
+		      status, data[0], data[1], data[2]);
+		switch (status) {
+		    case SCANLOG_COMPLETE:
+			DEBUG("hit eof\n");
+			return 0;
+		    case SCANLOG_HWERROR:
+			DEBUG("hardware error reading scan log data\n");
+			return -EIO;
+		    case SCANLOG_CONTINUE:
+			/* We may or may not have data yet */
+			len = data[1];
+			off = data[2];
+			if (len > 0) {
+				if (copy_to_user(buf, ((char *)data)+off, len))
+					return -EFAULT;
+				return len;
+			}
+			/* Break to sleep default time */
+			break;
+		    default:
+			if (status > 9900 && status <= 9905) {
+				wait_time = rtas_extended_busy_delay_time(status);
+			} else {
+				printk(KERN_ERR "scanlog: unknown error from rtas: %d\n", status);
+				return -EIO;
+			}
+		}
+		/* Apparently no data yet.  Wait and try again. */
+		msleep_interruptible(wait_time);
+	}
+	/*NOTREACHED*/
+}
+
+static ssize_t scanlog_write(struct file * file, const char __user * buf,
+			     size_t count, loff_t *ppos)
+{
+	char stkbuf[20];
+	int status;
+
+	if (count > 19) count = 19;
+	if (copy_from_user (stkbuf, buf, count)) {
+		return -EFAULT;
+	}
+	stkbuf[count] = 0;
+
+	if (buf) {
+		if (strncmp(stkbuf, "reset", 5) == 0) {
+			DEBUG("reset scanlog\n");
+			status = rtas_call(ibm_scan_log_dump, 2, 1, NULL, 0, 0);
+			DEBUG("rtas returns %d\n", status);
+		} else if (strncmp(stkbuf, "debugon", 7) == 0) {
+			printk(KERN_ERR "scanlog: debug on\n");
+			scanlog_debug = 1;
+		} else if (strncmp(stkbuf, "debugoff", 8) == 0) {
+			printk(KERN_ERR "scanlog: debug off\n");
+			scanlog_debug = 0;
+		}
+	}
+	return count;
+}
+
+static int scanlog_open(struct inode * inode, struct file * file)
+{
+	struct proc_dir_entry *dp = PDE(inode);
+	unsigned int *data = (unsigned int *)dp->data;
+
+	if (!data) {
+		printk(KERN_ERR "scanlog: open failed no data\n");
+		return -EIO;
+	}
+
+	if (data[0] != 0) {
+		/* This imperfect test stops a second copy of the
+		 * data (or a reset while data is being copied)
+		 */
+		return -EBUSY;
+	}
+
+	data[0] = 0;	/* re-init so we restart the scan */
+
+	return 0;
+}
+
+static int scanlog_release(struct inode * inode, struct file * file)
+{
+	struct proc_dir_entry *dp = PDE(inode);
+	unsigned int *data = (unsigned int *)dp->data;
+
+	if (!data) {
+		printk(KERN_ERR "scanlog: release failed no data\n");
+		return -EIO;
+	}
+	data[0] = 0;
+
+	return 0;
+}
+
+struct file_operations scanlog_fops = {
+	.owner		= THIS_MODULE,
+	.read		= scanlog_read,
+	.write		= scanlog_write,
+	.open		= scanlog_open,
+	.release	= scanlog_release,
+};
+
+int __init scanlog_init(void)
+{
+	struct proc_dir_entry *ent;
+
+	ibm_scan_log_dump = rtas_token("ibm,scan-log-dump");
+	if (ibm_scan_log_dump == RTAS_UNKNOWN_SERVICE) {
+		printk(KERN_ERR "scan-log-dump not implemented on this system\n");
+		return -EIO;
+	}
+
+        ent = create_proc_entry("ppc64/rtas/scan-log-dump",  S_IRUSR, NULL);
+	if (ent) {
+		ent->proc_fops = &scanlog_fops;
+		/* Ideally we could allocate a buffer < 4G */
+		ent->data = kmalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL);
+		if (!ent->data) {
+			printk(KERN_ERR "Failed to allocate a buffer\n");
+			remove_proc_entry("scan-log-dump", ent->parent);
+			return -ENOMEM;
+		}
+		((unsigned int *)ent->data)[0] = 0;
+	} else {
+		printk(KERN_ERR "Failed to create ppc64/scan-log-dump proc entry\n");
+		return -EIO;
+	}
+	proc_ppc64_scan_log_dump = ent;
+
+	return 0;
+}
+
+void __exit scanlog_cleanup(void)
+{
+	if (proc_ppc64_scan_log_dump) {
+		kfree(proc_ppc64_scan_log_dump->data);
+		remove_proc_entry("scan-log-dump", proc_ppc64_scan_log_dump->parent);
+	}
+}
+
+module_init(scanlog_init);
+module_exit(scanlog_cleanup);
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index e78c3936884..31990829310 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -249,7 +249,7 @@ static void __init pSeries_setup_arch(void)
 		ppc_md.idle_loop = default_idle;
 	}
 
-	if (systemcfg->platform & PLATFORM_LPAR)
+	if (platform_is_lpar())
 		ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;
 	else
 		ppc_md.enable_pmcs = power4_enable_pmcs;
@@ -306,9 +306,7 @@ static void __init fw_feature_init(void)
 	}
 
 	of_node_put(dn);
- no_rtas:
-	printk(KERN_INFO "firmware_features = 0x%lx\n", 
-	       ppc64_firmware_features);
+no_rtas:
 
 	DBG(" <- fw_feature_init()\n");
 }
@@ -378,7 +376,7 @@ static void __init pSeries_init_early(void)
 
 	fw_feature_init();
 	
-	if (systemcfg->platform & PLATFORM_LPAR)
+	if (platform_is_lpar())
 		hpte_init_lpar();
 	else {
 		hpte_init_native();
@@ -388,7 +386,7 @@ static void __init pSeries_init_early(void)
 
 	generic_find_legacy_serial_ports(&physport, &default_speed);
 
-	if (systemcfg->platform & PLATFORM_LPAR)
+	if (platform_is_lpar())
 		find_udbg_vterm();
 	else if (physport) {
 		/* Map the uart for udbg. */
@@ -469,6 +467,7 @@ static inline void dedicated_idle_sleep(unsigned int cpu)
 		 * more.
 		 */
 		clear_thread_flag(TIF_POLLING_NRFLAG);
+		smp_mb__after_clear_bit();
 
 		/*
 		 * SMT dynamic mode. Cede will result in this thread going
@@ -481,6 +480,7 @@ static inline void dedicated_idle_sleep(unsigned int cpu)
 			cede_processor();
 		else
 			local_irq_enable();
+		set_thread_flag(TIF_POLLING_NRFLAG);
 	} else {
 		/*
 		 * Give the HV an opportunity at the processor, since we are
@@ -492,11 +492,11 @@ static inline void dedicated_idle_sleep(unsigned int cpu)
 
 static void pseries_dedicated_idle(void)
 { 
-	long oldval;
 	struct paca_struct *lpaca = get_paca();
 	unsigned int cpu = smp_processor_id();
 	unsigned long start_snooze;
 	unsigned long *smt_snooze_delay = &__get_cpu_var(smt_snooze_delay);
+	set_thread_flag(TIF_POLLING_NRFLAG);
 
 	while (1) {
 		/*
@@ -505,10 +505,7 @@ static void pseries_dedicated_idle(void)
 		 */
 		lpaca->lppaca.idle = 1;
 
-		oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);
-		if (!oldval) {
-			set_thread_flag(TIF_POLLING_NRFLAG);
-
+		if (!need_resched()) {
 			start_snooze = __get_tb() +
 				*smt_snooze_delay * tb_ticks_per_usec;
 
@@ -531,15 +528,14 @@ static void pseries_dedicated_idle(void)
 			}
 
 			HMT_medium();
-			clear_thread_flag(TIF_POLLING_NRFLAG);
-		} else {
-			set_need_resched();
 		}
 
 		lpaca->lppaca.idle = 0;
 		ppc64_runlatch_on();
 
+		preempt_enable_no_resched();
 		schedule();
+		preempt_disable();
 
 		if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING)
 			cpu_die();
@@ -583,7 +579,9 @@ static void pseries_shared_idle(void)
 		lpaca->lppaca.idle = 0;
 		ppc64_runlatch_on();
 
+		preempt_enable_no_resched();
 		schedule();
+		preempt_disable();
 
 		if (cpu_is_offline(cpu) && system_state == SYSTEM_RUNNING)
 			cpu_die();
@@ -592,7 +590,7 @@ static void pseries_shared_idle(void)
 
 static int pSeries_pci_probe_mode(struct pci_bus *bus)
 {
-	if (systemcfg->platform & PLATFORM_LPAR)
+	if (platform_is_lpar())
 		return PCI_PROBE_DEVTREE;
 	return PCI_PROBE_NORMAL;
 }
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 7a243e8ccd7..5800cde7d5a 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -46,6 +46,7 @@
 #include <asm/rtas.h>
 #include <asm/pSeries_reconfig.h>
 #include <asm/mpic.h>
+#include <asm/vdso_datapage.h>
 
 #include "plpar_wrappers.h"
 
@@ -96,7 +97,7 @@ int pSeries_cpu_disable(void)
 	int cpu = smp_processor_id();
 
 	cpu_clear(cpu, cpu_online_map);
-	systemcfg->processorCount--;
+	vdso_data->processorCount--;
 
 	/*fix boot_cpuid here*/
 	if (cpu == boot_cpuid)
@@ -441,7 +442,7 @@ void __init smp_init_pSeries(void)
 	smp_ops->cpu_die = pSeries_cpu_die;
 
 	/* Processors can be added/removed only on LPAR */
-	if (systemcfg->platform == PLATFORM_PSERIES_LPAR)
+	if (platform_is_lpar())
 		pSeries_reconfig_notifier_register(&pSeries_smp_nb);
 #endif
 
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index c72c86f05cb..72ac18067ec 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -545,7 +545,9 @@ nextnode:
 		of_node_put(np);
 	}
 
-	if (systemcfg->platform == PLATFORM_PSERIES) {
+	if (platform_is_lpar())
+		ops = &pSeriesLP_ops;
+	else {
 #ifdef CONFIG_SMP
 		for_each_cpu(i) {
 			int hard_id;
@@ -561,12 +563,11 @@ nextnode:
 #else
 		xics_per_cpu[0] = ioremap(intr_base, intr_size);
 #endif /* CONFIG_SMP */
-	} else if (systemcfg->platform == PLATFORM_PSERIES_LPAR) {
-		ops = &pSeriesLP_ops;
 	}
 
 	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)