Merge branch 'upstream'

16 files changed, 200 insertions, 230 deletions

diff --git a/arch/ia64/sn/Makefile b/arch/ia64/sn/Makefile
index a269f6d84c2..79a7df02e81 100644
--- a/arch/ia64/sn/Makefile
+++ b/arch/ia64/sn/Makefile
@@ -9,6 +9,4 @@
 # Makefile for the sn ia64 subplatform
 #
 
-CPPFLAGS += -I$(srctree)/arch/ia64/sn/include
-
 obj-y += kernel/ pci/
diff --git a/arch/ia64/sn/kernel/Makefile b/arch/ia64/sn/kernel/Makefile
index 4351c4ff984..3e9b4eea741 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 dd73c0cb754..1f11db470d9 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 00700f7e683..d7e4d79e16a 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>
@@ -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;
@@ -198,15 +199,16 @@ 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;
@@ -279,23 +281,21 @@ static void sn_fixup_ionodes(void)
 				memset(dev_entry->common, 0x0, sizeof(struct
 					     	       sn_flush_device_common));
 
-				status = sal_get_device_dmaflush_list(nasid,
-									widget,
-								       	device,
+				if (sn_prom_feature_available(
+						       PRF_DEVICE_FLUSH_LIST))
+					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,
+				else
+					status = sn_device_fixup_war(nasid,
+								     widget,
+							    	     device,
 							     dev_entry->common);
-					}
-					else
-						BUG();
-				}
+				if (status != SALRET_OK)
+					panic("SAL call failed: %s\n",
+					      ia64_sal_strerror(status));
 
 				spin_lock_init(&dev_entry->sfdl_flush_lock);
 			}
@@ -467,6 +467,13 @@ 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;
 }
 
 /*
diff --git a/arch/ia64/sn/kernel/irq.c b/arch/ia64/sn/kernel/irq.c
index ec37084bdc1..74d87d903d5 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)
@@ -419,7 +417,7 @@ 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 +432,4 @@ 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 0f11a3299cd..87682b48ef8 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 9ab684d1bb5..3db62f24596 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 e510dce9971..48645ac120f 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);
@@ -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
@@ -372,6 +359,16 @@ sn_scan_pcdp(void)
 	}
 }
 
+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
  * @cmdline_p: kernel command line
@@ -386,6 +383,7 @@ 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 +435,6 @@ 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 +448,21 @@ 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 +578,17 @@ 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 +720,8 @@ 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 +739,7 @@ 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 170bde4549d..99e17769323 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/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c
index 471bbaa65d1..f153a4c35c7 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 +46,28 @@ 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);
+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
+#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)
 
-static inline int ptc_lock(unsigned long *flagp)
+static inline void ptc_lock(int sh1, unsigned long *flagp)
 {
-	spin_lock_irqsave(&sn2_global_ptc_lock, *flagp);
-	return 0;
+	spin_lock_irqsave(PTC_LOCK(sh1), *flagp);
 }
 
-static inline void ptc_unlock(unsigned long flags, int opt)
+static inline void ptc_unlock(int sh1, unsigned long flags)
 {
-	spin_unlock_irqrestore(&sn2_global_ptc_lock, flags);
+	spin_unlock_irqrestore(PTC_LOCK(sh1), flags);
 }
-#endif
 
 struct ptc_stats {
 	unsigned long ptc_l;
@@ -151,27 +75,30 @@ 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;
 };
 
 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 +128,14 @@ 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 +196,56 @@ 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);
+	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 +253,12 @@ 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();
+	}
+
+	ptc_unlock(shub1, flags);
 
 	preempt_enable();
 }
@@ -321,27 +270,30 @@ 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,
+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,
+	extern unsigned long 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 +404,22 @@ 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 +430,7 @@ 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 19b54fbcd7e..70db21f3df2 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/xpc_channel.c b/arch/ia64/sn/kernel/xpc_channel.c
index 8d950c778bb..36e5437a0fb 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;
diff --git a/arch/ia64/sn/kernel/xpc_main.c b/arch/ia64/sn/kernel/xpc_main.c
index c75f8aeefc2..9cd460dfe27 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);
+	}
 }
 
 
diff --git a/arch/ia64/sn/pci/Makefile b/arch/ia64/sn/pci/Makefile
index 321576b1b42..c6946784a6a 100644
--- a/arch/ia64/sn/pci/Makefile
+++ b/arch/ia64/sn/pci/Makefile
@@ -7,4 +7,6 @@
 #
 # Makefile for the sn pci general routines.
 
+CPPFLAGS += -I$(srctree)/arch/ia64/sn/include
+
 obj-y := pci_dma.o tioca_provider.o tioce_provider.o pcibr/
diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c
index 9bf9f23b9a1..5a36292388e 100644
--- a/arch/ia64/sn/pci/pci_dma.c
+++ b/arch/ia64/sn/pci/pci_dma.c
@@ -90,14 +90,14 @@ void *sn_dma_alloc_coherent(struct device *dev, size_t size,
 	 */
 	node = pcibus_to_node(pdev->bus);
 	if (likely(node >=0)) {
-		struct page *p = alloc_pages_node(node, GFP_ATOMIC, get_order(size));
+		struct page *p = alloc_pages_node(node, flags, get_order(size));
 
 		if (likely(p))
 			cpuaddr = page_address(p);
 		else
 			return NULL;
 	} else
-		cpuaddr = (void *)__get_free_pages(GFP_ATOMIC, get_order(size));
+		cpuaddr = (void *)__get_free_pages(flags, get_order(size));
 
 	if (unlikely(!cpuaddr))
 		return NULL;
diff --git a/arch/ia64/sn/pci/pcibr/Makefile b/arch/ia64/sn/pci/pcibr/Makefile
index 1850c4a94c4..3b403ea456f 100644
--- a/arch/ia64/sn/pci/pcibr/Makefile
+++ b/arch/ia64/sn/pci/pcibr/Makefile
@@ -7,5 +7,7 @@
 #
 # Makefile for the sn2 io routines.
 
+CPPFLAGS += -I$(srctree)/arch/ia64/sn/include
+
 obj-y				+=  pcibr_dma.o pcibr_reg.o \
 				    pcibr_ate.o pcibr_provider.o