Merge branch 'master'

17 files changed, 310 insertions, 335 deletions

diff --git a/arch/ia64/sn/kernel/Makefile b/arch/ia64/sn/kernel/Makefile
index 4351c4ff9845..3e9b4eea7418 100644
--- a/arch/ia64/sn/kernel/Makefile
+++ b/arch/ia64/sn/kernel/Makefile
@@ -7,6 +7,8 @@
 # Copyright (C) 1999,2001-2005 Silicon Graphics, Inc.  All Rights Reserved.
 #
 
+CPPFLAGS += -I$(srctree)/arch/ia64/sn/include
+
 obj-y				+= setup.o bte.o bte_error.o irq.o mca.o idle.o \
 				   huberror.o io_init.o iomv.o klconflib.o sn2/
 obj-$(CONFIG_IA64_GENERIC)      += machvec.o
diff --git a/arch/ia64/sn/kernel/bte.c b/arch/ia64/sn/kernel/bte.c
index dd73c0cb754b..1f11db470d90 100644
--- a/arch/ia64/sn/kernel/bte.c
+++ b/arch/ia64/sn/kernel/bte.c
@@ -3,7 +3,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (c) 2000-2005 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (c) 2000-2006 Silicon Graphics, Inc.  All Rights Reserved.
  */
 
 #include <linux/config.h>
@@ -186,18 +186,13 @@ retry_bteop:
 
 	/* Initialize the notification to a known value. */
 	*bte->most_rcnt_na = BTE_WORD_BUSY;
-	notif_phys_addr = TO_PHYS(ia64_tpa((unsigned long)bte->most_rcnt_na));
+	notif_phys_addr = (u64)bte->most_rcnt_na;
 
-	if (is_shub2()) {
-		src = SH2_TIO_PHYS_TO_DMA(src);
-		dest = SH2_TIO_PHYS_TO_DMA(dest);
-		notif_phys_addr = SH2_TIO_PHYS_TO_DMA(notif_phys_addr);
-	}
 	/* Set the source and destination registers */
-	BTE_PRINTKV(("IBSA = 0x%lx)\n", (TO_PHYS(src))));
-	BTE_SRC_STORE(bte, TO_PHYS(src));
-	BTE_PRINTKV(("IBDA = 0x%lx)\n", (TO_PHYS(dest))));
-	BTE_DEST_STORE(bte, TO_PHYS(dest));
+	BTE_PRINTKV(("IBSA = 0x%lx)\n", src));
+	BTE_SRC_STORE(bte, src);
+	BTE_PRINTKV(("IBDA = 0x%lx)\n", dest));
+	BTE_DEST_STORE(bte, dest);
 
 	/* Set the notification register */
 	BTE_PRINTKV(("IBNA = 0x%lx)\n", notif_phys_addr));
diff --git a/arch/ia64/sn/kernel/io_init.c b/arch/ia64/sn/kernel/io_init.c
index 00700f7e6837..3edef0d32f86 100644
--- a/arch/ia64/sn/kernel/io_init.c
+++ b/arch/ia64/sn/kernel/io_init.c
@@ -10,6 +10,7 @@
 #include <linux/nodemask.h>
 #include <asm/sn/types.h>
 #include <asm/sn/addrs.h>
+#include <asm/sn/sn_feature_sets.h>
 #include <asm/sn/geo.h>
 #include <asm/sn/io.h>
 #include <asm/sn/pcibr_provider.h>
@@ -22,6 +23,10 @@
 #include "xtalk/hubdev.h"
 #include "xtalk/xwidgetdev.h"
 
+
+extern void sn_init_cpei_timer(void);
+extern void register_sn_procfs(void);
+
 static struct list_head sn_sysdata_list;
 
 /* sysdata list struct */
@@ -39,12 +44,12 @@ struct brick {
 	struct slab_info slab_info[MAX_SLABS + 1];
 };
 
-int sn_ioif_inited = 0;		/* SN I/O infrastructure initialized? */
+int sn_ioif_inited;		/* SN I/O infrastructure initialized? */
 
 struct sn_pcibus_provider *sn_pci_provider[PCIIO_ASIC_MAX_TYPES];	/* indexed by asic type */
 
-static int max_segment_number = 0; /* Default highest segment number */
-static int max_pcibus_number = 255; /* Default highest pci bus number */
+static int max_segment_number;		 /* Default highest segment number */
+static int max_pcibus_number = 255;	/* Default highest pci bus number */
 
 /*
  * Hooks and struct for unsupported pci providers
@@ -83,7 +88,6 @@ static inline u64
 sal_get_device_dmaflush_list(u64 nasid, u64 widget_num, u64 device_num,
 			     u64 address)
 {
-
 	struct ia64_sal_retval ret_stuff;
 	ret_stuff.status = 0;
 	ret_stuff.v0 = 0;
@@ -93,7 +97,6 @@ sal_get_device_dmaflush_list(u64 nasid, u64 widget_num, u64 device_num,
 			(u64) nasid, (u64) widget_num,
 			(u64) device_num, (u64) address, 0, 0, 0);
 	return ret_stuff.status;
-
 }
 
 /*
@@ -101,7 +104,6 @@ sal_get_device_dmaflush_list(u64 nasid, u64 widget_num, u64 device_num,
  */
 static inline u64 sal_get_hubdev_info(u64 handle, u64 address)
 {
-
 	struct ia64_sal_retval ret_stuff;
 	ret_stuff.status = 0;
 	ret_stuff.v0 = 0;
@@ -117,7 +119,6 @@ static inline u64 sal_get_hubdev_info(u64 handle, u64 address)
  */
 static inline u64 sal_get_pcibus_info(u64 segment, u64 busnum, u64 address)
 {
-
 	struct ia64_sal_retval ret_stuff;
 	ret_stuff.status = 0;
 	ret_stuff.v0 = 0;
@@ -173,8 +174,8 @@ sn_pcidev_info_get(struct pci_dev *dev)
  */
 static u8 war_implemented = 0;
 
-static void sn_device_fixup_war(u64 nasid, u64 widget, int device,
-				struct sn_flush_device_common *common)
+static s64 sn_device_fixup_war(u64 nasid, u64 widget, int device,
+			       struct sn_flush_device_common *common)
 {
 	struct sn_flush_device_war *war_list;
 	struct sn_flush_device_war *dev_entry;
@@ -198,22 +199,23 @@ static void sn_device_fixup_war(u64 nasid, u64 widget, int device,
 
 	dev_entry = war_list + device;
 	memcpy(common,dev_entry, sizeof(*common));
-
 	kfree(war_list);
+
+	return isrv.status;
 }
 
 /*
  * sn_fixup_ionodes() - This routine initializes the HUB data strcuture for
  *	each node in the system.
  */
-static void sn_fixup_ionodes(void)
+static void __init sn_fixup_ionodes(void)
 {
 	struct sn_flush_device_kernel *sn_flush_device_kernel;
 	struct sn_flush_device_kernel *dev_entry;
 	struct hubdev_info *hubdev;
 	u64 status;
 	u64 nasid;
-	int i, widget, device;
+	int i, widget, device, size;
 
 	/*
 	 * Get SGI Specific HUB chipset information.
@@ -249,53 +251,40 @@ static void sn_fixup_ionodes(void)
 		if (!hubdev->hdi_flush_nasid_list.widget_p)
 			continue;
 
+		size = (HUB_WIDGET_ID_MAX + 1) *
+			sizeof(struct sn_flush_device_kernel *);
 		hubdev->hdi_flush_nasid_list.widget_p =
-		    kmalloc((HUB_WIDGET_ID_MAX + 1) *
-			    sizeof(struct sn_flush_device_kernel *),
-			    GFP_KERNEL);
-		memset(hubdev->hdi_flush_nasid_list.widget_p, 0x0,
-		       (HUB_WIDGET_ID_MAX + 1) *
-		       sizeof(struct sn_flush_device_kernel *));
+			kzalloc(size, GFP_KERNEL);
+		if (!hubdev->hdi_flush_nasid_list.widget_p)
+			BUG();
 
 		for (widget = 0; widget <= HUB_WIDGET_ID_MAX; widget++) {
-			sn_flush_device_kernel = kmalloc(DEV_PER_WIDGET *
-						         sizeof(struct
-						        sn_flush_device_kernel),
-						        GFP_KERNEL);
+			size = DEV_PER_WIDGET *
+				sizeof(struct sn_flush_device_kernel);
+			sn_flush_device_kernel = kzalloc(size, GFP_KERNEL);
 			if (!sn_flush_device_kernel)
 				BUG();
-			memset(sn_flush_device_kernel, 0x0,
-			       DEV_PER_WIDGET *
-			       sizeof(struct sn_flush_device_kernel));
 
 			dev_entry = sn_flush_device_kernel;
 			for (device = 0; device < DEV_PER_WIDGET;
 			     device++,dev_entry++) {
-				dev_entry->common = kmalloc(sizeof(struct
-					      	        sn_flush_device_common),
-					                    GFP_KERNEL);
+				size = sizeof(struct sn_flush_device_common);
+				dev_entry->common = kzalloc(size, GFP_KERNEL);
 				if (!dev_entry->common)
 					BUG();
-				memset(dev_entry->common, 0x0, sizeof(struct
-					     	       sn_flush_device_common));
-
-				status = sal_get_device_dmaflush_list(nasid,
-									widget,
-								       	device,
-						      (u64)(dev_entry->common));
-				if (status) {
-					if (sn_sal_rev() < 0x0450) {
-						/* shortlived WAR for older
-						 * PROM images
-						 */
-						sn_device_fixup_war(nasid,
-								    widget,
-								    device,
-							     dev_entry->common);
-					}
-					else
-						BUG();
-				}
+
+				if (sn_prom_feature_available(
+						       PRF_DEVICE_FLUSH_LIST))
+					status = sal_get_device_dmaflush_list(
+						     nasid, widget, device,
+						     (u64)(dev_entry->common));
+				else
+					status = sn_device_fixup_war(nasid,
+						     widget, device,
+						     dev_entry->common);
+				if (status != SALRET_OK)
+					panic("SAL call failed: %s\n",
+					      ia64_sal_strerror(status));
 
 				spin_lock_init(&dev_entry->sfdl_flush_lock);
 			}
@@ -383,13 +372,12 @@ void sn_pci_fixup_slot(struct pci_dev *dev)
 
 	pci_dev_get(dev); /* for the sysdata pointer */
 	pcidev_info = kzalloc(sizeof(struct pcidev_info), GFP_KERNEL);
-	if (pcidev_info <= 0)
+	if (!pcidev_info)
 		BUG();		/* Cannot afford to run out of memory */
 
-	sn_irq_info = kmalloc(sizeof(struct sn_irq_info), GFP_KERNEL);
-	if (sn_irq_info <= 0)
+	sn_irq_info = kzalloc(sizeof(struct sn_irq_info), GFP_KERNEL);
+	if (!sn_irq_info)
 		BUG();		/* Cannot afford to run out of memory */
-	memset(sn_irq_info, 0, sizeof(struct sn_irq_info));
 
 	/* Call to retrieve pci device information needed by kernel. */
 	status = sal_get_pcidev_info((u64) segment, (u64) dev->bus->number, 
@@ -467,6 +455,13 @@ void sn_pci_fixup_slot(struct pci_dev *dev)
 		pcidev_info->pdi_sn_irq_info = NULL;
 		kfree(sn_irq_info);
 	}
+
+	/*
+	 * MSI currently not supported on altix.  Remove this when
+	 * the MSI abstraction patches are integrated into the kernel
+	 * (sometime after 2.6.16 releases)
+	 */
+	dev->no_msi = 1;
 }
 
 /*
@@ -475,13 +470,13 @@ void sn_pci_fixup_slot(struct pci_dev *dev)
  */
 void sn_pci_controller_fixup(int segment, int busnum, struct pci_bus *bus)
 {
-	int status = 0;
+	int status;
 	int nasid, cnode;
 	struct pci_controller *controller;
 	struct sn_pci_controller *sn_controller;
 	struct pcibus_bussoft *prom_bussoft_ptr;
 	struct hubdev_info *hubdev_info;
-	void *provider_soft = NULL;
+	void *provider_soft;
 	struct sn_pcibus_provider *provider;
 
  	status = sal_get_pcibus_info((u64) segment, (u64) busnum,
@@ -528,6 +523,8 @@ void sn_pci_controller_fixup(int segment, int busnum, struct pci_bus *bus)
 	bus->sysdata = controller;
 	if (provider->bus_fixup)
 		provider_soft = (*provider->bus_fixup) (prom_bussoft_ptr, controller);
+	else
+		provider_soft = NULL;
 
 	if (provider_soft == NULL) {
 		/* fixup failed or not applicable */
@@ -610,15 +607,15 @@ void sn_bus_store_sysdata(struct pci_dev *dev)
 void sn_bus_free_sysdata(void)
 {
 	struct sysdata_el *element;
-	struct list_head *list;
+	struct list_head *list, *safe;
 
-sn_sysdata_free_start:
-	list_for_each(list, &sn_sysdata_list) {
+	list_for_each_safe(list, safe, &sn_sysdata_list) {
 		element = list_entry(list, struct sysdata_el, entry);
 		list_del(&element->entry);
+		list_del(&(((struct pcidev_info *)
+			     (element->sysdata))->pdi_list));
 		kfree(element->sysdata);
 		kfree(element);
-		goto sn_sysdata_free_start;
 	}
 	return;
 }
@@ -631,13 +628,8 @@ sn_sysdata_free_start:
 
 static int __init sn_pci_init(void)
 {
-	int i = 0;
-	int j = 0;
+	int i, j;
 	struct pci_dev *pci_dev = NULL;
-	extern void sn_init_cpei_timer(void);
-#ifdef CONFIG_PROC_FS
-	extern void register_sn_procfs(void);
-#endif
 
 	if (!ia64_platform_is("sn2") || IS_RUNNING_ON_FAKE_PROM())
 		return 0;
@@ -693,32 +685,29 @@ static int __init sn_pci_init(void)
  */
 void hubdev_init_node(nodepda_t * npda, cnodeid_t node)
 {
-
 	struct hubdev_info *hubdev_info;
+	int size;
+	pg_data_t *pg;
+
+	size = sizeof(struct hubdev_info);
 
 	if (node >= num_online_nodes())	/* Headless/memless IO nodes */
-		hubdev_info =
-		    (struct hubdev_info *)alloc_bootmem_node(NODE_DATA(0),
-							     sizeof(struct
-								    hubdev_info));
+		pg = NODE_DATA(0);
 	else
-		hubdev_info =
-		    (struct hubdev_info *)alloc_bootmem_node(NODE_DATA(node),
-							     sizeof(struct
-								    hubdev_info));
-	npda->pdinfo = (void *)hubdev_info;
+		pg = NODE_DATA(node);
+
+	hubdev_info = (struct hubdev_info *)alloc_bootmem_node(pg, size);
 
+	npda->pdinfo = (void *)hubdev_info;
 }
 
 geoid_t
 cnodeid_get_geoid(cnodeid_t cnode)
 {
-
 	struct hubdev_info *hubdev;
 
 	hubdev = (struct hubdev_info *)(NODEPDA(cnode)->pdinfo);
 	return hubdev->hdi_geoid;
-
 }
 
 subsys_initcall(sn_pci_init);
@@ -727,3 +716,4 @@ EXPORT_SYMBOL(sn_pci_unfixup_slot);
 EXPORT_SYMBOL(sn_pci_controller_fixup);
 EXPORT_SYMBOL(sn_bus_store_sysdata);
 EXPORT_SYMBOL(sn_bus_free_sysdata);
+EXPORT_SYMBOL(sn_pcidev_info_get);
diff --git a/arch/ia64/sn/kernel/irq.c b/arch/ia64/sn/kernel/irq.c
index ec37084bdc17..c373113d073a 100644
--- a/arch/ia64/sn/kernel/irq.c
+++ b/arch/ia64/sn/kernel/irq.c
@@ -5,11 +5,12 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (c) 2000-2005 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (c) 2000-2006 Silicon Graphics, Inc.  All Rights Reserved.
  */
 
 #include <linux/irq.h>
 #include <linux/spinlock.h>
+#include <linux/init.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/intr.h>
@@ -76,17 +77,15 @@ static void sn_enable_irq(unsigned int irq)
 
 static void sn_ack_irq(unsigned int irq)
 {
-	u64 event_occurred, mask = 0;
+	u64 event_occurred, mask;
 
 	irq = irq & 0xff;
-	event_occurred =
-	    HUB_L((u64*)LOCAL_MMR_ADDR(SH_EVENT_OCCURRED));
+	event_occurred = HUB_L((u64*)LOCAL_MMR_ADDR(SH_EVENT_OCCURRED));
 	mask = event_occurred & SH_ALL_INT_MASK;
-	HUB_S((u64*)LOCAL_MMR_ADDR(SH_EVENT_OCCURRED_ALIAS),
-	      mask);
+	HUB_S((u64*)LOCAL_MMR_ADDR(SH_EVENT_OCCURRED_ALIAS), mask);
 	__set_bit(irq, (volatile void *)pda->sn_in_service_ivecs);
 
-	move_irq(irq);
+	move_native_irq(irq);
 }
 
 static void sn_end_irq(unsigned int irq)
@@ -219,9 +218,8 @@ static void register_intr_pda(struct sn_irq_info *sn_irq_info)
 		pdacpu(cpu)->sn_last_irq = irq;
 	}
 
-	if (pdacpu(cpu)->sn_first_irq == 0 || pdacpu(cpu)->sn_first_irq > irq) {
+	if (pdacpu(cpu)->sn_first_irq == 0 || pdacpu(cpu)->sn_first_irq > irq)
 		pdacpu(cpu)->sn_first_irq = irq;
-	}
 }
 
 static void unregister_intr_pda(struct sn_irq_info *sn_irq_info)
@@ -289,7 +287,7 @@ void sn_irq_fixup(struct pci_dev *pci_dev, struct sn_irq_info *sn_irq_info)
 	list_add_rcu(&sn_irq_info->list, sn_irq_lh[sn_irq_info->irq_irq]);
 	spin_unlock(&sn_irq_info_lock);
 
-	(void)register_intr_pda(sn_irq_info);
+	register_intr_pda(sn_irq_info);
 }
 
 void sn_irq_unfixup(struct pci_dev *pci_dev)
@@ -301,7 +299,9 @@ void sn_irq_unfixup(struct pci_dev *pci_dev)
 		return;
 
 	sn_irq_info = SN_PCIDEV_INFO(pci_dev)->pdi_sn_irq_info;
-	if (!sn_irq_info || !sn_irq_info->irq_irq) {
+	if (!sn_irq_info)
+		return;
+	if (!sn_irq_info->irq_irq) {
 		kfree(sn_irq_info);
 		return;
 	}
@@ -419,7 +419,7 @@ void sn_lb_int_war_check(void)
 	rcu_read_unlock();
 }
 
-void sn_irq_lh_init(void)
+void __init sn_irq_lh_init(void)
 {
 	int i;
 
@@ -434,5 +434,4 @@ void sn_irq_lh_init(void)
 
 		INIT_LIST_HEAD(sn_irq_lh[i]);
 	}
-
 }
diff --git a/arch/ia64/sn/kernel/klconflib.c b/arch/ia64/sn/kernel/klconflib.c
index 0f11a3299cd2..87682b48ef83 100644
--- a/arch/ia64/sn/kernel/klconflib.c
+++ b/arch/ia64/sn/kernel/klconflib.c
@@ -78,31 +78,30 @@ format_module_id(char *buffer, moduleid_t m, int fmt)
 	position = MODULE_GET_BPOS(m);
 
 	if ((fmt == MODULE_FORMAT_BRIEF) || (fmt == MODULE_FORMAT_LCD)) {
-	    /* Brief module number format, eg. 002c15 */
+		/* Brief module number format, eg. 002c15 */
 
-	    /* Decompress the rack number */
-	    *buffer++ = '0' + RACK_GET_CLASS(rack);
-	    *buffer++ = '0' + RACK_GET_GROUP(rack);
-	    *buffer++ = '0' + RACK_GET_NUM(rack);
+		/* Decompress the rack number */
+		*buffer++ = '0' + RACK_GET_CLASS(rack);
+		*buffer++ = '0' + RACK_GET_GROUP(rack);
+		*buffer++ = '0' + RACK_GET_NUM(rack);
 
-	    /* Add the brick type */
-	    *buffer++ = brickchar;
+		/* Add the brick type */
+		*buffer++ = brickchar;
 	}
 	else if (fmt == MODULE_FORMAT_LONG) {
-	    /* Fuller hwgraph format, eg. rack/002/bay/15 */
+		/* Fuller hwgraph format, eg. rack/002/bay/15 */
 
-	    strcpy(buffer, "rack" "/");  buffer += strlen(buffer);
+		strcpy(buffer, "rack" "/");  buffer += strlen(buffer);
 
-	    *buffer++ = '0' + RACK_GET_CLASS(rack);
-	    *buffer++ = '0' + RACK_GET_GROUP(rack);
-	    *buffer++ = '0' + RACK_GET_NUM(rack);
+		*buffer++ = '0' + RACK_GET_CLASS(rack);
+		*buffer++ = '0' + RACK_GET_GROUP(rack);
+		*buffer++ = '0' + RACK_GET_NUM(rack);
 
-	    strcpy(buffer, "/" "bay" "/");  buffer += strlen(buffer);
+		strcpy(buffer, "/" "bay" "/");  buffer += strlen(buffer);
 	}
 
 	/* Add the bay position, using at least two digits */
 	if (position < 10)
-	    *buffer++ = '0';
+		*buffer++ = '0';
 	sprintf(buffer, "%d", position);
-
 }
diff --git a/arch/ia64/sn/kernel/mca.c b/arch/ia64/sn/kernel/mca.c
index 9ab684d1bb55..3db62f24596c 100644
--- a/arch/ia64/sn/kernel/mca.c
+++ b/arch/ia64/sn/kernel/mca.c
@@ -3,7 +3,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (c) 2000-2004 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (c) 2000-2006 Silicon Graphics, Inc.  All Rights Reserved.
  */
 
 #include <linux/types.h>
@@ -137,7 +137,8 @@ int sn_salinfo_platform_oemdata(const u8 *sect_header, u8 **oemdata, u64 *oemdat
 
 static int __init sn_salinfo_init(void)
 {
-	salinfo_platform_oemdata = &sn_salinfo_platform_oemdata;
+	if (ia64_platform_is("sn2"))
+		salinfo_platform_oemdata = &sn_salinfo_platform_oemdata;
 	return 0;
 }
 
diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c
index e510dce9971f..5b84836c2171 100644
--- a/arch/ia64/sn/kernel/setup.c
+++ b/arch/ia64/sn/kernel/setup.c
@@ -67,6 +67,7 @@ extern unsigned long last_time_offset;
 extern void (*ia64_mark_idle) (int);
 extern void snidle(int);
 extern unsigned char acpi_kbd_controller_present;
+extern unsigned long long (*ia64_printk_clock)(void);
 
 unsigned long sn_rtc_cycles_per_second;
 EXPORT_SYMBOL(sn_rtc_cycles_per_second);
@@ -74,7 +75,7 @@ EXPORT_SYMBOL(sn_rtc_cycles_per_second);
 DEFINE_PER_CPU(struct sn_hub_info_s, __sn_hub_info);
 EXPORT_PER_CPU_SYMBOL(__sn_hub_info);
 
-DEFINE_PER_CPU(short, __sn_cnodeid_to_nasid[MAX_NUMNODES]);
+DEFINE_PER_CPU(short, __sn_cnodeid_to_nasid[MAX_COMPACT_NODES]);
 EXPORT_PER_CPU_SYMBOL(__sn_cnodeid_to_nasid);
 
 DEFINE_PER_CPU(struct nodepda_s *, __sn_nodepda);
@@ -125,20 +126,6 @@ struct screen_info sn_screen_info = {
 };
 
 /*
- * This is here so we can use the CMOS detection in ide-probe.c to
- * determine what drives are present.  In theory, we don't need this
- * as the auto-detection could be done via ide-probe.c:do_probe() but
- * in practice that would be much slower, which is painful when
- * running in the simulator.  Note that passing zeroes in DRIVE_INFO
- * is sufficient (the IDE driver will autodetect the drive geometry).
- */
-#ifdef CONFIG_IA64_GENERIC
-extern char drive_info[4 * 16];
-#else
-char drive_info[4 * 16];
-#endif
-
-/*
  * This routine can only be used during init, since
  * smp_boot_data is an init data structure.
  * We have to use smp_boot_data.cpu_phys_id to find
@@ -209,7 +196,7 @@ void __init early_sn_setup(void)
 }
 
 extern int platform_intr_list[];
-static int __initdata shub_1_1_found = 0;
+static int __initdata shub_1_1_found;
 
 /*
  * sn_check_for_wars
@@ -330,6 +317,7 @@ struct pcdp_vga_device {
 #define PCDP_PCI_TRANS_IOPORT	0x02
 #define PCDP_PCI_TRANS_MMIO	0x01
 
+#if defined(CONFIG_VT) && defined(CONFIG_VGA_CONSOLE)
 static void
 sn_scan_pcdp(void)
 {
@@ -371,6 +359,17 @@ sn_scan_pcdp(void)
 		break; /* once we find the primary, we're done */
 	}
 }
+#endif
+
+static unsigned long sn2_rtc_initial;
+
+static unsigned long long ia64_sn2_printk_clock(void)
+{
+	unsigned long rtc_now = rtc_time();
+
+	return (rtc_now - sn2_rtc_initial) *
+		(1000000000 / sn_rtc_cycles_per_second);
+}
 
 /**
  * sn_setup - SN platform setup routine
@@ -386,6 +385,7 @@ void __init sn_setup(char **cmdline_p)
 	u32 version = sn_sal_rev();
 	extern void sn_cpu_init(void);
 
+	sn2_rtc_initial = rtc_time();
 	ia64_sn_plat_set_error_handling_features();	// obsolete
 	ia64_sn_set_os_feature(OSF_MCA_SLV_TO_OS_INIT_SLV);
 	ia64_sn_set_os_feature(OSF_FEAT_LOG_SBES);
@@ -437,19 +437,6 @@ void __init sn_setup(char **cmdline_p)
 	 */
 	build_cnode_tables();
 
-	/*
-	 * Old PROMs do not provide an ACPI FADT. Disable legacy keyboard
-	 * support here so we don't have to listen to failed keyboard probe
-	 * messages.
-	 */
-	if (version <= 0x0209 && acpi_kbd_controller_present) {
-		printk(KERN_INFO "Disabling legacy keyboard support as prom "
-		       "is too old and doesn't provide FADT\n");
-		acpi_kbd_controller_present = 0;
-	}
-
-	printk("SGI SAL version %x.%02x\n", version >> 8, version & 0x00FF);
-
 	status =
 	    ia64_sal_freq_base(SAL_FREQ_BASE_REALTIME_CLOCK, &ticks_per_sec,
 			       &drift);
@@ -463,6 +450,21 @@ void __init sn_setup(char **cmdline_p)
 
 	platform_intr_list[ACPI_INTERRUPT_CPEI] = IA64_CPE_VECTOR;
 
+	ia64_printk_clock = ia64_sn2_printk_clock;
+
+	/*
+	 * Old PROMs do not provide an ACPI FADT. Disable legacy keyboard
+	 * support here so we don't have to listen to failed keyboard probe
+	 * messages.
+	 */
+	if (version <= 0x0209 && acpi_kbd_controller_present) {
+		printk(KERN_INFO "Disabling legacy keyboard support as prom "
+		       "is too old and doesn't provide FADT\n");
+		acpi_kbd_controller_present = 0;
+	}
+
+	printk("SGI SAL version %x.%02x\n", version >> 8, version & 0x00FF);
+
 	/*
 	 * we set the default root device to /dev/hda
 	 * to make simulation easy
@@ -578,13 +580,17 @@ void __init sn_cpu_init(void)
 			sn_prom_type = 2;
 		else
 			sn_prom_type = 1;
-		printk("Running on medusa with %s PROM\n", (sn_prom_type == 1) ? "real" : "fake");
+		printk(KERN_INFO "Running on medusa with %s PROM\n",
+		       (sn_prom_type == 1) ? "real" : "fake");
 	}
 
 	memset(pda, 0, sizeof(pda));
-	if (ia64_sn_get_sn_info(0, &sn_hub_info->shub2, &sn_hub_info->nasid_bitmask, &sn_hub_info->nasid_shift,
-				&sn_system_size, &sn_sharing_domain_size, &sn_partition_id,
-				&sn_coherency_id, &sn_region_size))
+	if (ia64_sn_get_sn_info(0, &sn_hub_info->shub2,
+				&sn_hub_info->nasid_bitmask,
+				&sn_hub_info->nasid_shift,
+				&sn_system_size, &sn_sharing_domain_size,
+				&sn_partition_id, &sn_coherency_id,
+				&sn_region_size))
 		BUG();
 	sn_hub_info->as_shift = sn_hub_info->nasid_shift - 2;
 
@@ -716,7 +722,8 @@ void __init build_cnode_tables(void)
 	for_each_online_node(node) {
 		kl_config_hdr_t *klgraph_header;
 		nasid = cnodeid_to_nasid(node);
-		if ((klgraph_header = ia64_sn_get_klconfig_addr(nasid)) == NULL)
+		klgraph_header = ia64_sn_get_klconfig_addr(nasid);
+		if (klgraph_header == NULL)
 			BUG();
 		brd = NODE_OFFSET_TO_LBOARD(nasid, klgraph_header->ch_board_info);
 		while (brd) {
@@ -734,7 +741,7 @@ nasid_slice_to_cpuid(int nasid, int slice)
 {
 	long cpu;
 
-	for (cpu=0; cpu < NR_CPUS; cpu++)
+	for (cpu = 0; cpu < NR_CPUS; cpu++)
 		if (cpuid_to_nasid(cpu) == nasid &&
 					cpuid_to_slice(cpu) == slice)
 			return cpu;
diff --git a/arch/ia64/sn/kernel/sn2/Makefile b/arch/ia64/sn/kernel/sn2/Makefile
index 170bde4549da..99e177693234 100644
--- a/arch/ia64/sn/kernel/sn2/Makefile
+++ b/arch/ia64/sn/kernel/sn2/Makefile
@@ -9,5 +9,7 @@
 # sn2 specific kernel files
 #
 
+CPPFLAGS += -I$(srctree)/arch/ia64/sn/include
+
 obj-y += cache.o io.o ptc_deadlock.o sn2_smp.o sn_proc_fs.o \
 	 prominfo_proc.o timer.o timer_interrupt.o sn_hwperf.o
diff --git a/arch/ia64/sn/kernel/sn2/prominfo_proc.c b/arch/ia64/sn/kernel/sn2/prominfo_proc.c
index 81c63b2f8ae9..6ae276d5d50c 100644
--- a/arch/ia64/sn/kernel/sn2/prominfo_proc.c
+++ b/arch/ia64/sn/kernel/sn2/prominfo_proc.c
@@ -3,7 +3,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 1999,2001-2004 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (C) 1999,2001-2004, 2006 Silicon Graphics, Inc.  All Rights Reserved.
  *
  * Module to export the system's Firmware Interface Tables, including
  * PROM revision numbers and banners, in /proc
@@ -190,7 +190,7 @@ static int
 read_version_entry(char *page, char **start, off_t off, int count, int *eof,
 		   void *data)
 {
-	int len = 0;
+	int len;
 
 	/* data holds the NASID of the node */
 	len = dump_version(page, (unsigned long)data);
@@ -202,7 +202,7 @@ static int
 read_fit_entry(char *page, char **start, off_t off, int count, int *eof,
 	       void *data)
 {
-	int len = 0;
+	int len;
 
 	/* data holds the NASID of the node */
 	len = dump_fit(page, (unsigned long)data);
@@ -229,13 +229,16 @@ int __init prominfo_init(void)
 	struct proc_dir_entry *p;
 	cnodeid_t cnodeid;
 	unsigned long nasid;
+	int size;
 	char name[NODE_NAME_LEN];
 
 	if (!ia64_platform_is("sn2"))
 		return 0;
 
-	proc_entries = kmalloc(num_online_nodes() * sizeof(struct proc_dir_entry *),
-			       GFP_KERNEL);
+	size = num_online_nodes() * sizeof(struct proc_dir_entry *);
+	proc_entries = kzalloc(size, GFP_KERNEL);
+	if (!proc_entries)
+		return -ENOMEM;
 
 	sgi_prominfo_entry = proc_mkdir("sgi_prominfo", NULL);
 
@@ -244,14 +247,12 @@ int __init prominfo_init(void)
 		sprintf(name, "node%d", cnodeid);
 		*entp = proc_mkdir(name, sgi_prominfo_entry);
 		nasid = cnodeid_to_nasid(cnodeid);
-		p = create_proc_read_entry(
-			"fit", 0, *entp, read_fit_entry,
-			(void *)nasid);
+		p = create_proc_read_entry("fit", 0, *entp, read_fit_entry,
+					   (void *)nasid);
 		if (p)
 			p->owner = THIS_MODULE;
-		p = create_proc_read_entry(
-			"version", 0, *entp, read_version_entry,
-			(void *)nasid);
+		p = create_proc_read_entry("version", 0, *entp,
+					   read_version_entry, (void *)nasid);
 		if (p)
 			p->owner = THIS_MODULE;
 		entp++;
@@ -263,7 +264,7 @@ int __init prominfo_init(void)
 void __exit prominfo_exit(void)
 {
 	struct proc_dir_entry **entp;
-	unsigned cnodeid;
+	unsigned int cnodeid;
 	char name[NODE_NAME_LEN];
 
 	entp = proc_entries;
diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c
index 471bbaa65d1b..24eefb2fc55f 100644
--- a/arch/ia64/sn/kernel/sn2/sn2_smp.c
+++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c
@@ -5,7 +5,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 2000-2005 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2000-2006 Silicon Graphics, Inc. All rights reserved.
  */
 
 #include <linux/init.h>
@@ -46,104 +46,24 @@ DECLARE_PER_CPU(struct ptc_stats, ptcstats);
 
 static  __cacheline_aligned DEFINE_SPINLOCK(sn2_global_ptc_lock);
 
-void sn2_ptc_deadlock_recovery(short *, short, int, volatile unsigned long *, unsigned long data0,
-	volatile unsigned long *, unsigned long data1);
+extern unsigned long
+sn2_ptc_deadlock_recovery_core(volatile unsigned long *, unsigned long,
+			       volatile unsigned long *, unsigned long,
+			       volatile unsigned long *, unsigned long);
+void
+sn2_ptc_deadlock_recovery(short *, short, short, int,
+			  volatile unsigned long *, unsigned long,
+			  volatile unsigned long *, unsigned long);
 
-#ifdef DEBUG_PTC
 /*
- * ptctest:
- *
- * 	xyz - 3 digit hex number:
- * 		x - Force PTC purges to use shub:
- * 			0 - no force
- * 			1 - force
- * 		y - interupt enable
- * 			0 - disable interrupts
- * 			1 - leave interuupts enabled
- * 		z - type of lock:
- * 			0 - global lock
- * 			1 - node local lock
- * 			2 - no lock
- *
- *   	Note: on shub1, only ptctest == 0 is supported. Don't try other values!
+ * Note: some is the following is captured here to make degugging easier
+ * (the macros make more sense if you see the debug patch - not posted)
  */
-
-static unsigned int sn2_ptctest = 0;
-
-static int __init ptc_test(char *str)
-{
-	get_option(&str, &sn2_ptctest);
-	return 1;
-}
-__setup("ptctest=", ptc_test);
-
-static inline int ptc_lock(unsigned long *flagp)
-{
-	unsigned long opt = sn2_ptctest & 255;
-
-	switch (opt) {
-	case 0x00:
-		spin_lock_irqsave(&sn2_global_ptc_lock, *flagp);
-		break;
-	case 0x01:
-		spin_lock_irqsave(&sn_nodepda->ptc_lock, *flagp);
-		break;
-	case 0x02:
-		local_irq_save(*flagp);
-		break;
-	case 0x10:
-		spin_lock(&sn2_global_ptc_lock);
-		break;
-	case 0x11:
-		spin_lock(&sn_nodepda->ptc_lock);
-		break;
-	case 0x12:
-		break;
-	default:
-		BUG();
-	}
-	return opt;
-}
-
-static inline void ptc_unlock(unsigned long flags, int opt)
-{
-	switch (opt) {
-	case 0x00:
-		spin_unlock_irqrestore(&sn2_global_ptc_lock, flags);
-		break;
-	case 0x01:
-		spin_unlock_irqrestore(&sn_nodepda->ptc_lock, flags);
-		break;
-	case 0x02:
-		local_irq_restore(flags);
-		break;
-	case 0x10:
-		spin_unlock(&sn2_global_ptc_lock);
-		break;
-	case 0x11:
-		spin_unlock(&sn_nodepda->ptc_lock);
-		break;
-	case 0x12:
-		break;
-	default:
-		BUG();
-	}
-}
-#else
-
 #define sn2_ptctest	0
-
-static inline int ptc_lock(unsigned long *flagp)
-{
-	spin_lock_irqsave(&sn2_global_ptc_lock, *flagp);
-	return 0;
-}
-
-static inline void ptc_unlock(unsigned long flags, int opt)
-{
-	spin_unlock_irqrestore(&sn2_global_ptc_lock, flags);
-}
-#endif
+#define local_node_uses_ptc_ga(sh1)	((sh1) ? 1 : 0)
+#define max_active_pio(sh1)		((sh1) ? 32 : 7)
+#define reset_max_active_on_deadlock()	1
+#define PTC_LOCK(sh1)			((sh1) ? &sn2_global_ptc_lock : &sn_nodepda->ptc_lock)
 
 struct ptc_stats {
 	unsigned long ptc_l;
@@ -151,27 +71,32 @@ struct ptc_stats {
 	unsigned long shub_ptc_flushes;
 	unsigned long nodes_flushed;
 	unsigned long deadlocks;
+	unsigned long deadlocks2;
 	unsigned long lock_itc_clocks;
 	unsigned long shub_itc_clocks;
 	unsigned long shub_itc_clocks_max;
+	unsigned long shub_ptc_flushes_not_my_mm;
 };
 
+#define sn2_ptctest	0
+
 static inline unsigned long wait_piowc(void)
 {
-	volatile unsigned long *piows, zeroval;
-	unsigned long ws;
+	volatile unsigned long *piows;
+	unsigned long zeroval, ws;
 
 	piows = pda->pio_write_status_addr;
 	zeroval = pda->pio_write_status_val;
 	do {
 		cpu_relax();
 	} while (((ws = *piows) & SH_PIO_WRITE_STATUS_PENDING_WRITE_COUNT_MASK) != zeroval);
-	return ws;
+	return (ws & SH_PIO_WRITE_STATUS_WRITE_DEADLOCK_MASK) != 0;
 }
 
 void sn_tlb_migrate_finish(struct mm_struct *mm)
 {
-	if (mm == current->mm)
+	/* flush_tlb_mm is inefficient if more than 1 users of mm */
+	if (mm == current->mm && mm && atomic_read(&mm->mm_users) == 1)
 		flush_tlb_mm(mm);
 }
 
@@ -201,12 +126,14 @@ void
 sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 		     unsigned long end, unsigned long nbits)
 {
-	int i, opt, shub1, cnode, mynasid, cpu, lcpu = 0, nasid, flushed = 0;
-	int mymm = (mm == current->active_mm && current->mm);
+	int i, ibegin, shub1, cnode, mynasid, cpu, lcpu = 0, nasid;
+	int mymm = (mm == current->active_mm && mm == current->mm);
+	int use_cpu_ptcga;
 	volatile unsigned long *ptc0, *ptc1;
-	unsigned long itc, itc2, flags, data0 = 0, data1 = 0, rr_value;
+	unsigned long itc, itc2, flags, data0 = 0, data1 = 0, rr_value, old_rr = 0;
 	short nasids[MAX_NUMNODES], nix;
 	nodemask_t nodes_flushed;
+	int active, max_active, deadlock;
 
 	nodes_clear(nodes_flushed);
 	i = 0;
@@ -267,41 +194,56 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 	
 
 	mynasid = get_nasid();
+	use_cpu_ptcga = local_node_uses_ptc_ga(shub1);
+	max_active = max_active_pio(shub1);
 
 	itc = ia64_get_itc();
-	opt = ptc_lock(&flags);
+	spin_lock_irqsave(PTC_LOCK(shub1), flags);
 	itc2 = ia64_get_itc();
+
 	__get_cpu_var(ptcstats).lock_itc_clocks += itc2 - itc;
 	__get_cpu_var(ptcstats).shub_ptc_flushes++;
 	__get_cpu_var(ptcstats).nodes_flushed += nix;
+	if (!mymm)
+		 __get_cpu_var(ptcstats).shub_ptc_flushes_not_my_mm++;
 
+	if (use_cpu_ptcga && !mymm) {
+		old_rr = ia64_get_rr(start);
+		ia64_set_rr(start, (old_rr & 0xff) | (rr_value << 8));
+		ia64_srlz_d();
+	}
+
+	wait_piowc();
 	do {
 		if (shub1)
 			data1 = start | (1UL << SH1_PTC_1_START_SHFT);
 		else
 			data0 = (data0 & ~SH2_PTC_ADDR_MASK) | (start & SH2_PTC_ADDR_MASK);
-		for (i = 0; i < nix; i++) {
+		deadlock = 0;
+		active = 0;
+		for (ibegin = 0, i = 0; i < nix; i++) {
 			nasid = nasids[i];
-			if ((!(sn2_ptctest & 3)) && unlikely(nasid == mynasid && mymm)) {
+			if (use_cpu_ptcga && unlikely(nasid == mynasid)) {
 				ia64_ptcga(start, nbits << 2);
 				ia64_srlz_i();
 			} else {
 				ptc0 = CHANGE_NASID(nasid, ptc0);
 				if (ptc1)
 					ptc1 = CHANGE_NASID(nasid, ptc1);
-				pio_atomic_phys_write_mmrs(ptc0, data0, ptc1,
-							   data1);
-				flushed = 1;
+				pio_atomic_phys_write_mmrs(ptc0, data0, ptc1, data1);
+				active++;
+			}
+			if (active >= max_active || i == (nix - 1)) {
+				if ((deadlock = wait_piowc())) {
+					sn2_ptc_deadlock_recovery(nasids, ibegin, i, mynasid, ptc0, data0, ptc1, data1);
+					if (reset_max_active_on_deadlock())
+						max_active = 1;
+				}
+				active = 0;
+				ibegin = i + 1;
 			}
 		}
-		if (flushed
-		    && (wait_piowc() &
-				(SH_PIO_WRITE_STATUS_WRITE_DEADLOCK_MASK))) {
-			sn2_ptc_deadlock_recovery(nasids, nix, mynasid, ptc0, data0, ptc1, data1);
-		}
-
 		start += (1UL << nbits);
-
 	} while (start < end);
 
 	itc2 = ia64_get_itc() - itc2;
@@ -309,7 +251,12 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 	if (itc2 > __get_cpu_var(ptcstats).shub_itc_clocks_max)
 		__get_cpu_var(ptcstats).shub_itc_clocks_max = itc2;
 
-	ptc_unlock(flags, opt);
+	if (old_rr) {
+		ia64_set_rr(start, old_rr);
+		ia64_srlz_d();
+	}
+
+	spin_unlock_irqrestore(PTC_LOCK(shub1), flags);
 
 	preempt_enable();
 }
@@ -321,27 +268,31 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
  * TLB flush transaction.  The recovery sequence is somewhat tricky & is
  * coded in assembly language.
  */
-void sn2_ptc_deadlock_recovery(short *nasids, short nix, int mynasid, volatile unsigned long *ptc0, unsigned long data0,
-	volatile unsigned long *ptc1, unsigned long data1)
+
+void
+sn2_ptc_deadlock_recovery(short *nasids, short ib, short ie, int mynasid,
+			  volatile unsigned long *ptc0, unsigned long data0,
+			  volatile unsigned long *ptc1, unsigned long data1)
 {
-	extern void sn2_ptc_deadlock_recovery_core(volatile unsigned long *, unsigned long,
-	        volatile unsigned long *, unsigned long, volatile unsigned long *, unsigned long);
 	short nasid, i;
-	unsigned long *piows, zeroval;
+	unsigned long *piows, zeroval, n;
 
 	__get_cpu_var(ptcstats).deadlocks++;
 
 	piows = (unsigned long *) pda->pio_write_status_addr;
 	zeroval = pda->pio_write_status_val;
 
-	for (i=0; i < nix; i++) {
+
+	for (i=ib; i <= ie; i++) {
 		nasid = nasids[i];
-		if (!(sn2_ptctest & 3) && nasid == mynasid)
+		if (local_node_uses_ptc_ga(is_shub1()) && nasid == mynasid)
 			continue;
 		ptc0 = CHANGE_NASID(nasid, ptc0);
 		if (ptc1)
 			ptc1 = CHANGE_NASID(nasid, ptc1);
-		sn2_ptc_deadlock_recovery_core(ptc0, data0, ptc1, data1, piows, zeroval);
+
+		n = sn2_ptc_deadlock_recovery_core(ptc0, data0, ptc1, data1, piows, zeroval);
+		__get_cpu_var(ptcstats).deadlocks2 += n;
 	}
 
 }
@@ -452,20 +403,22 @@ static int sn2_ptc_seq_show(struct seq_file *file, void *data)
 	cpu = *(loff_t *) data;
 
 	if (!cpu) {
-		seq_printf(file, "# ptc_l change_rid shub_ptc_flushes shub_nodes_flushed deadlocks lock_nsec shub_nsec shub_nsec_max\n");
+		seq_printf(file,
+			   "# cpu ptc_l newrid ptc_flushes nodes_flushed deadlocks lock_nsec shub_nsec shub_nsec_max not_my_mm deadlock2\n");
 		seq_printf(file, "# ptctest %d\n", sn2_ptctest);
 	}
 
 	if (cpu < NR_CPUS && cpu_online(cpu)) {
 		stat = &per_cpu(ptcstats, cpu);
-		seq_printf(file, "cpu %d %ld %ld %ld %ld %ld %ld %ld %ld\n", cpu, stat->ptc_l,
+		seq_printf(file, "cpu %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld\n", cpu, stat->ptc_l,
 				stat->change_rid, stat->shub_ptc_flushes, stat->nodes_flushed,
 				stat->deadlocks,
 				1000 * stat->lock_itc_clocks / per_cpu(cpu_info, cpu).cyc_per_usec,
 				1000 * stat->shub_itc_clocks / per_cpu(cpu_info, cpu).cyc_per_usec,
-				1000 * stat->shub_itc_clocks_max / per_cpu(cpu_info, cpu).cyc_per_usec);
+				1000 * stat->shub_itc_clocks_max / per_cpu(cpu_info, cpu).cyc_per_usec,
+				stat->shub_ptc_flushes_not_my_mm,
+				stat->deadlocks2);
 	}
-
 	return 0;
 }
 
@@ -476,7 +429,7 @@ static struct seq_operations sn2_ptc_seq_ops = {
 	.show = sn2_ptc_seq_show
 };
 
-int sn2_ptc_proc_open(struct inode *inode, struct file *file)
+static int sn2_ptc_proc_open(struct inode *inode, struct file *file)
 {
 	return seq_open(file, &sn2_ptc_seq_ops);
 }
diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
index 19b54fbcd7ea..70db21f3df21 100644
--- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c
+++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
@@ -3,7 +3,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 2004-2005 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2004-2006 Silicon Graphics, Inc. All rights reserved.
  *
  * SGI Altix topology and hardware performance monitoring API.
  * Mark Goodwin <markgw@sgi.com>. 
@@ -973,6 +973,9 @@ static int __devinit sn_hwperf_misc_register_init(void)
 {
 	int e;
 
+	if (!ia64_platform_is("sn2"))
+		return 0;
+
 	sn_hwperf_init();
 
 	/*
diff --git a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
index a06719d752a0..c686d9c12f7b 100644
--- a/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
+++ b/arch/ia64/sn/kernel/sn2/sn_proc_fs.c
@@ -6,11 +6,11 @@
  * Copyright (C) 2000-2005 Silicon Graphics, Inc. All rights reserved.
  */
 #include <linux/config.h>
-#include <asm/uaccess.h>
 
 #ifdef CONFIG_PROC_FS
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <asm/uaccess.h>
 #include <asm/sn/sn_sal.h>
 
 static int partition_id_show(struct seq_file *s, void *p)
@@ -90,10 +90,10 @@ static int coherence_id_open(struct inode *inode, struct file *file)
 	return single_open(file, coherence_id_show, NULL);
 }
 
-static struct proc_dir_entry *sn_procfs_create_entry(
-	const char *name, struct proc_dir_entry *parent,
-	int (*openfunc)(struct inode *, struct file *),
-	int (*releasefunc)(struct inode *, struct file *))
+static struct proc_dir_entry
+*sn_procfs_create_entry(const char *name, struct proc_dir_entry *parent,
+			int (*openfunc)(struct inode *, struct file *),
+			int (*releasefunc)(struct inode *, struct file *))
 {
 	struct proc_dir_entry *e = create_proc_entry(name, 0444, parent);
 
@@ -126,24 +126,24 @@ void register_sn_procfs(void)
 		return;
 
 	sn_procfs_create_entry("partition_id", sgi_proc_dir,
-		partition_id_open, single_release);
+			       partition_id_open, single_release);
 
 	sn_procfs_create_entry("system_serial_number", sgi_proc_dir,
-		system_serial_number_open, single_release);
+			       system_serial_number_open, single_release);
 
 	sn_procfs_create_entry("licenseID", sgi_proc_dir, 
-		licenseID_open, single_release);
+			       licenseID_open, single_release);
 
 	e = sn_procfs_create_entry("sn_force_interrupt", sgi_proc_dir, 
-		sn_force_interrupt_open, single_release);
+				   sn_force_interrupt_open, single_release);
 	if (e) 
 		e->proc_fops->write = sn_force_interrupt_write_proc;
 
 	sn_procfs_create_entry("coherence_id", sgi_proc_dir, 
-		coherence_id_open, single_release);
+			       coherence_id_open, single_release);
 	
 	sn_procfs_create_entry("sn_topology", sgi_proc_dir,
-		sn_topology_open, sn_topology_release);
+			       sn_topology_open, sn_topology_release);
 }
 
 #endif /* CONFIG_PROC_FS */
diff --git a/arch/ia64/sn/kernel/sn2/timer.c b/arch/ia64/sn/kernel/sn2/timer.c
index deb9baf4d473..56a88b6df4b4 100644
--- a/arch/ia64/sn/kernel/sn2/timer.c
+++ b/arch/ia64/sn/kernel/sn2/timer.c
@@ -14,6 +14,7 @@
 
 #include <asm/hw_irq.h>
 #include <asm/system.h>
+#include <asm/timex.h>
 
 #include <asm/sn/leds.h>
 #include <asm/sn/shub_mmr.h>
@@ -28,9 +29,27 @@ static struct time_interpolator sn2_interpolator = {
 	.source = TIME_SOURCE_MMIO64
 };
 
+/*
+ * sn udelay uses the RTC instead of the ITC because the ITC is not
+ * synchronized across all CPUs, and the thread may migrate to another CPU
+ * if preemption is enabled.
+ */
+static void
+ia64_sn_udelay (unsigned long usecs)
+{
+	unsigned long start = rtc_time();
+	unsigned long end = start +
+			usecs * sn_rtc_cycles_per_second / 1000000;
+
+	while (time_before((unsigned long)rtc_time(), end))
+		cpu_relax();
+}
+
 void __init sn_timer_init(void)
 {
 	sn2_interpolator.frequency = sn_rtc_cycles_per_second;
 	sn2_interpolator.addr = RTC_COUNTER_ADDR;
 	register_time_interpolator(&sn2_interpolator);
+
+	ia64_udelay = &ia64_sn_udelay;
 }
diff --git a/arch/ia64/sn/kernel/sn2/timer_interrupt.c b/arch/ia64/sn/kernel/sn2/timer_interrupt.c
index adf5db2e2afe..fa7f69945917 100644
--- a/arch/ia64/sn/kernel/sn2/timer_interrupt.c
+++ b/arch/ia64/sn/kernel/sn2/timer_interrupt.c
@@ -1,7 +1,7 @@
 /*
  *
  *
- * Copyright (c) 2005 Silicon Graphics, Inc.  All Rights Reserved.
+ * Copyright (c) 2005, 2006 Silicon Graphics, Inc.  All Rights Reserved.
  * 
  * This program is free software; you can redistribute it and/or modify it 
  * under the terms of version 2 of the GNU General Public License 
@@ -22,11 +22,6 @@
  * License along with this program; if not, write the Free Software 
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
  * 
- * Contact information:  Silicon Graphics, Inc., 1600 Amphitheatre Pkwy, 
- * Mountain View, CA  94043, or:
- * 
- * http://www.sgi.com 
- * 
  * For further information regarding this notice, see: 
  * 
  * http://oss.sgi.com/projects/GenInfo/NoticeExplan
diff --git a/arch/ia64/sn/kernel/tiocx.c b/arch/ia64/sn/kernel/tiocx.c
index d263d3e8fbb9..8a56f8b5ffa2 100644
--- a/arch/ia64/sn/kernel/tiocx.c
+++ b/arch/ia64/sn/kernel/tiocx.c
@@ -284,12 +284,10 @@ struct sn_irq_info *tiocx_irq_alloc(nasid_t nasid, int widget, int irq,
 	if ((nasid & 1) == 0)
 		return NULL;
 
-	sn_irq_info = kmalloc(sn_irq_size, GFP_KERNEL);
+	sn_irq_info = kzalloc(sn_irq_size, GFP_KERNEL);
 	if (sn_irq_info == NULL)
 		return NULL;
 
-	memset(sn_irq_info, 0x0, sn_irq_size);
-
 	status = tiocx_intr_alloc(nasid, widget, __pa(sn_irq_info), irq,
 				  req_nasid, slice);
 	if (status) {
diff --git a/arch/ia64/sn/kernel/xpc_channel.c b/arch/ia64/sn/kernel/xpc_channel.c
index 8d950c778bb6..cdf6856ce089 100644
--- a/arch/ia64/sn/kernel/xpc_channel.c
+++ b/arch/ia64/sn/kernel/xpc_channel.c
@@ -447,7 +447,7 @@ xpc_allocate_local_msgqueue(struct xpc_channel *ch)
 
 		nbytes = nentries * ch->msg_size;
 		ch->local_msgqueue = xpc_kmalloc_cacheline_aligned(nbytes,
-						(GFP_KERNEL | GFP_DMA),
+						GFP_KERNEL,
 						&ch->local_msgqueue_base);
 		if (ch->local_msgqueue == NULL) {
 			continue;
@@ -455,7 +455,7 @@ xpc_allocate_local_msgqueue(struct xpc_channel *ch)
 		memset(ch->local_msgqueue, 0, nbytes);
 
 		nbytes = nentries * sizeof(struct xpc_notify);
-		ch->notify_queue = kmalloc(nbytes, (GFP_KERNEL | GFP_DMA));
+		ch->notify_queue = kmalloc(nbytes, GFP_KERNEL);
 		if (ch->notify_queue == NULL) {
 			kfree(ch->local_msgqueue_base);
 			ch->local_msgqueue = NULL;
@@ -502,7 +502,7 @@ xpc_allocate_remote_msgqueue(struct xpc_channel *ch)
 
 		nbytes = nentries * ch->msg_size;
 		ch->remote_msgqueue = xpc_kmalloc_cacheline_aligned(nbytes,
-						(GFP_KERNEL | GFP_DMA),
+						GFP_KERNEL,
 						&ch->remote_msgqueue_base);
 		if (ch->remote_msgqueue == NULL) {
 			continue;
@@ -738,7 +738,9 @@ xpc_process_disconnect(struct xpc_channel *ch, unsigned long *irq_flags)
 
 	/* make sure all activity has settled down first */
 
-	if (atomic_read(&ch->references) > 0) {
+	if (atomic_read(&ch->references) > 0 ||
+			((ch->flags & XPC_C_CONNECTEDCALLOUT_MADE) &&
+			!(ch->flags & XPC_C_DISCONNECTINGCALLOUT_MADE))) {
 		return;
 	}
 	DBUG_ON(atomic_read(&ch->kthreads_assigned) != 0);
@@ -775,7 +777,7 @@ xpc_process_disconnect(struct xpc_channel *ch, unsigned long *irq_flags)
 
 	/* both sides are disconnected now */
 
-	if (ch->flags & XPC_C_CONNECTCALLOUT) {
+	if (ch->flags & XPC_C_DISCONNECTINGCALLOUT_MADE) {
 		spin_unlock_irqrestore(&ch->lock, *irq_flags);
 		xpc_disconnect_callout(ch, xpcDisconnected);
 		spin_lock_irqsave(&ch->lock, *irq_flags);
@@ -1300,7 +1302,7 @@ xpc_process_msg_IPI(struct xpc_partition *part, int ch_number)
 				"delivered=%d, partid=%d, channel=%d\n",
 				nmsgs_sent, ch->partid, ch->number);
 
-			if (ch->flags & XPC_C_CONNECTCALLOUT) {
+			if (ch->flags & XPC_C_CONNECTEDCALLOUT_MADE) {
 				xpc_activate_kthreads(ch, nmsgs_sent);
 			}
 		}
diff --git a/arch/ia64/sn/kernel/xpc_main.c b/arch/ia64/sn/kernel/xpc_main.c
index c75f8aeefc2b..8cbf16432570 100644
--- a/arch/ia64/sn/kernel/xpc_main.c
+++ b/arch/ia64/sn/kernel/xpc_main.c
@@ -575,18 +575,21 @@ xpc_activate_partition(struct xpc_partition *part)
 
 	spin_lock_irqsave(&part->act_lock, irq_flags);
 
-	pid = kernel_thread(xpc_activating, (void *) ((u64) partid), 0);
-
 	DBUG_ON(part->act_state != XPC_P_INACTIVE);
 
-	if (pid > 0) {
-		part->act_state = XPC_P_ACTIVATION_REQ;
-		XPC_SET_REASON(part, xpcCloneKThread, __LINE__);
-	} else {
-		XPC_SET_REASON(part, xpcCloneKThreadFailed, __LINE__);
-	}
+	part->act_state = XPC_P_ACTIVATION_REQ;
+	XPC_SET_REASON(part, xpcCloneKThread, __LINE__);
 
 	spin_unlock_irqrestore(&part->act_lock, irq_flags);
+
+	pid = kernel_thread(xpc_activating, (void *) ((u64) partid), 0);
+
+	if (unlikely(pid <= 0)) {
+		spin_lock_irqsave(&part->act_lock, irq_flags);
+		part->act_state = XPC_P_INACTIVE;
+		XPC_SET_REASON(part, xpcCloneKThreadFailed, __LINE__);
+		spin_unlock_irqrestore(&part->act_lock, irq_flags);
+	}
 }
 
 
@@ -747,12 +750,16 @@ xpc_daemonize_kthread(void *args)
 		/* let registerer know that connection has been established */
 
 		spin_lock_irqsave(&ch->lock, irq_flags);
-		if (!(ch->flags & XPC_C_CONNECTCALLOUT)) {
-			ch->flags |= XPC_C_CONNECTCALLOUT;
+		if (!(ch->flags & XPC_C_CONNECTEDCALLOUT)) {
+			ch->flags |= XPC_C_CONNECTEDCALLOUT;
 			spin_unlock_irqrestore(&ch->lock, irq_flags);
 
 			xpc_connected_callout(ch);
 
+			spin_lock_irqsave(&ch->lock, irq_flags);
+			ch->flags |= XPC_C_CONNECTEDCALLOUT_MADE;
+			spin_unlock_irqrestore(&ch->lock, irq_flags);
+
 			/*
 			 * It is possible that while the callout was being
 			 * made that the remote partition sent some messages.
@@ -774,15 +781,17 @@ xpc_daemonize_kthread(void *args)
 
 	if (atomic_dec_return(&ch->kthreads_assigned) == 0) {
 		spin_lock_irqsave(&ch->lock, irq_flags);
-		if ((ch->flags & XPC_C_CONNECTCALLOUT) &&
-				!(ch->flags & XPC_C_DISCONNECTCALLOUT)) {
-			ch->flags |= XPC_C_DISCONNECTCALLOUT;
+		if ((ch->flags & XPC_C_CONNECTEDCALLOUT_MADE) &&
+				!(ch->flags & XPC_C_DISCONNECTINGCALLOUT)) {
+			ch->flags |= XPC_C_DISCONNECTINGCALLOUT;
 			spin_unlock_irqrestore(&ch->lock, irq_flags);
 
 			xpc_disconnect_callout(ch, xpcDisconnecting);
-		} else {
-			spin_unlock_irqrestore(&ch->lock, irq_flags);
+
+			spin_lock_irqsave(&ch->lock, irq_flags);
+			ch->flags |= XPC_C_DISCONNECTINGCALLOUT_MADE;
 		}
+		spin_unlock_irqrestore(&ch->lock, irq_flags);
 		if (atomic_dec_return(&part->nchannels_engaged) == 0) {
 			xpc_mark_partition_disengaged(part);
 			xpc_IPI_send_disengage(part);