26 files changed, 520 insertions, 187 deletions

diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 307514f7a28..09a0dbc17fb 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -13,6 +13,11 @@ obj-$(CONFIG_IA64_BRL_EMU)	+= brl_emu.o
 obj-$(CONFIG_IA64_GENERIC)	+= acpi-ext.o
 obj-$(CONFIG_IA64_HP_ZX1)	+= acpi-ext.o
 obj-$(CONFIG_IA64_HP_ZX1_SWIOTLB) += acpi-ext.o
+
+ifneq ($(CONFIG_ACPI_PROCESSOR),)
+obj-y				+= acpi-processor.o
+endif
+
 obj-$(CONFIG_IA64_PALINFO)	+= palinfo.o
 obj-$(CONFIG_IOSAPIC)		+= iosapic.o
 obj-$(CONFIG_MODULES)		+= module.o
diff --git a/arch/ia64/kernel/acpi-ext.c b/arch/ia64/kernel/acpi-ext.c
index 13a5b3b49bf..4a5574ff007 100644
--- a/arch/ia64/kernel/acpi-ext.c
+++ b/arch/ia64/kernel/acpi-ext.c
@@ -33,33 +33,33 @@ acpi_vendor_resource_match(struct acpi_resource *resource, void *context)
 	struct acpi_vendor_info *info = (struct acpi_vendor_info *)context;
 	struct acpi_resource_vendor *vendor;
 	struct acpi_vendor_descriptor *descriptor;
-	u32 length;
+	u32 byte_length;
 
-	if (resource->id != ACPI_RSTYPE_VENDOR)
+	if (resource->type != ACPI_RESOURCE_TYPE_VENDOR)
 		return AE_OK;
 
 	vendor = (struct acpi_resource_vendor *)&resource->data;
-	descriptor = (struct acpi_vendor_descriptor *)vendor->reserved;
-	if (vendor->length <= sizeof(*info->descriptor) ||
+	descriptor = (struct acpi_vendor_descriptor *)vendor->byte_data;
+	if (vendor->byte_length <= sizeof(*info->descriptor) ||
 	    descriptor->guid_id != info->descriptor->guid_id ||
 	    efi_guidcmp(descriptor->guid, info->descriptor->guid))
 		return AE_OK;
 
-	length = vendor->length - sizeof(struct acpi_vendor_descriptor);
-	info->data = acpi_os_allocate(length);
+	byte_length = vendor->byte_length - sizeof(struct acpi_vendor_descriptor);
+	info->data = acpi_os_allocate(byte_length);
 	if (!info->data)
 		return AE_NO_MEMORY;
 
 	memcpy(info->data,
-	       vendor->reserved + sizeof(struct acpi_vendor_descriptor),
-	       length);
-	info->length = length;
+	       vendor->byte_data + sizeof(struct acpi_vendor_descriptor),
+	       byte_length);
+	info->length = byte_length;
 	return AE_CTRL_TERMINATE;
 }
 
 acpi_status
 acpi_find_vendor_resource(acpi_handle obj, struct acpi_vendor_descriptor * id,
-			  u8 ** data, u32 * length)
+			  u8 ** data, u32 * byte_length)
 {
 	struct acpi_vendor_info info;
 
@@ -72,7 +72,7 @@ acpi_find_vendor_resource(acpi_handle obj, struct acpi_vendor_descriptor * id,
 		return AE_NOT_FOUND;
 
 	*data = info.data;
-	*length = info.length;
+	*byte_length = info.length;
 	return AE_OK;
 }
 
diff --git a/arch/ia64/kernel/acpi-processor.c b/arch/ia64/kernel/acpi-processor.c
new file mode 100644
index 00000000000..e683630c8ce
--- /dev/null
+++ b/arch/ia64/kernel/acpi-processor.c
@@ -0,0 +1,67 @@
+/*
+ * arch/ia64/kernel/cpufreq/processor.c
+ *
+ * Copyright (C) 2005 Intel Corporation
+ * 	Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+ * 	- Added _PDC for platforms with Intel CPUs
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+
+#include <acpi/processor.h>
+#include <asm/acpi.h>
+
+static void init_intel_pdc(struct acpi_processor *pr)
+{
+	struct acpi_object_list *obj_list;
+	union acpi_object *obj;
+	u32 *buf;
+
+	/* allocate and initialize pdc. It will be used later. */
+	obj_list = kmalloc(sizeof(struct acpi_object_list), GFP_KERNEL);
+	if (!obj_list) {
+		printk(KERN_ERR "Memory allocation error\n");
+		return;
+	}
+
+	obj = kmalloc(sizeof(union acpi_object), GFP_KERNEL);
+	if (!obj) {
+		printk(KERN_ERR "Memory allocation error\n");
+		kfree(obj_list);
+		return;
+	}
+
+	buf = kmalloc(12, GFP_KERNEL);
+	if (!buf) {
+		printk(KERN_ERR "Memory allocation error\n");
+		kfree(obj);
+		kfree(obj_list);
+		return;
+	}
+
+	buf[0] = ACPI_PDC_REVISION_ID;
+	buf[1] = 1;
+	buf[2] |= ACPI_PDC_EST_CAPABILITY_SMP;
+
+	obj->type = ACPI_TYPE_BUFFER;
+	obj->buffer.length = 12;
+	obj->buffer.pointer = (u8 *) buf;
+	obj_list->count = 1;
+	obj_list->pointer = obj;
+	pr->pdc = obj_list;
+
+	return;
+}
+
+/* Initialize _PDC data based on the CPU vendor */
+void arch_acpi_processor_init_pdc(struct acpi_processor *pr)
+{
+	pr->pdc = NULL;
+	init_intel_pdc(pr);
+	return;
+}
+
+EXPORT_SYMBOL(arch_acpi_processor_init_pdc);
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 9ad94ddf668..4722ec51c70 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -284,19 +284,24 @@ acpi_parse_plat_int_src(acpi_table_entry_header * header,
 	return 0;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 unsigned int can_cpei_retarget(void)
 {
 	extern int cpe_vector;
+	extern unsigned int force_cpei_retarget;
 
 	/*
 	 * Only if CPEI is supported and the override flag
 	 * is present, otherwise return that its re-targettable
 	 * if we are in polling mode.
 	 */
-	if (cpe_vector > 0 && !acpi_cpei_override)
-		return 0;
-	else
-		return 1;
+	if (cpe_vector > 0) {
+		if (acpi_cpei_override || force_cpei_retarget)
+			return 1;
+		else
+			return 0;
+	}
+	return 1;
 }
 
 unsigned int is_cpu_cpei_target(unsigned int cpu)
@@ -315,6 +320,7 @@ void set_cpei_target_cpu(unsigned int cpu)
 {
 	acpi_cpei_phys_cpuid = cpu_physical_id(cpu);
 }
+#endif
 
 unsigned int get_cpei_target_cpu(void)
 {
@@ -567,16 +573,16 @@ void __init acpi_numa_arch_fixup(void)
  * success: return IRQ number (>=0)
  * failure: return < 0
  */
-int acpi_register_gsi(u32 gsi, int edge_level, int active_high_low)
+int acpi_register_gsi(u32 gsi, int triggering, int polarity)
 {
 	if (has_8259 && gsi < 16)
 		return isa_irq_to_vector(gsi);
 
 	return iosapic_register_intr(gsi,
-				     (active_high_low ==
+				     (polarity ==
 				      ACPI_ACTIVE_HIGH) ? IOSAPIC_POL_HIGH :
 				     IOSAPIC_POL_LOW,
-				     (edge_level ==
+				     (triggering ==
 				      ACPI_EDGE_SENSITIVE) ? IOSAPIC_EDGE :
 				     IOSAPIC_LEVEL);
 }
@@ -761,6 +767,59 @@ int acpi_map_cpu2node(acpi_handle handle, int cpu, long physid)
 	return (0);
 }
 
+int additional_cpus __initdata = -1;
+
+static __init int setup_additional_cpus(char *s)
+{
+	if (s)
+		additional_cpus = simple_strtol(s, NULL, 0);
+
+	return 0;
+}
+
+early_param("additional_cpus", setup_additional_cpus);
+
+/*
+ * cpu_possible_map should be static, it cannot change as cpu's
+ * are onlined, or offlined. The reason is per-cpu data-structures
+ * are allocated by some modules at init time, and dont expect to
+ * do this dynamically on cpu arrival/departure.
+ * cpu_present_map on the other hand can change dynamically.
+ * In case when cpu_hotplug is not compiled, then we resort to current
+ * behaviour, which is cpu_possible == cpu_present.
+ * - Ashok Raj
+ *
+ * Three ways to find out the number of additional hotplug CPUs:
+ * - If the BIOS specified disabled CPUs in ACPI/mptables use that.
+ * - The user can overwrite it with additional_cpus=NUM
+ * - Otherwise don't reserve additional CPUs.
+ */
+__init void prefill_possible_map(void)
+{
+	int i;
+	int possible, disabled_cpus;
+
+	disabled_cpus = total_cpus - available_cpus;
+
+ 	if (additional_cpus == -1) {
+ 		if (disabled_cpus > 0)
+			additional_cpus = disabled_cpus;
+ 		else
+			additional_cpus = 0;
+ 	}
+
+	possible = available_cpus + additional_cpus;
+
+	if (possible > NR_CPUS)
+		possible = NR_CPUS;
+
+	printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n",
+		possible, max((possible - available_cpus), 0));
+
+	for (i = 0; i < possible; i++)
+		cpu_set(i, cpu_possible_map);
+}
+
 int acpi_map_lsapic(acpi_handle handle, int *pcpu)
 {
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
diff --git a/arch/ia64/kernel/cpufreq/Makefile b/arch/ia64/kernel/cpufreq/Makefile
index f748d34c02f..4838f2a57c7 100644
--- a/arch/ia64/kernel/cpufreq/Makefile
+++ b/arch/ia64/kernel/cpufreq/Makefile
@@ -1 +1,2 @@
 obj-$(CONFIG_IA64_ACPI_CPUFREQ)		+= acpi-cpufreq.o
+
diff --git a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c b/arch/ia64/kernel/cpufreq/acpi-cpufreq.c
index da4d5cf80a4..5a1bf815282 100644
--- a/arch/ia64/kernel/cpufreq/acpi-cpufreq.c
+++ b/arch/ia64/kernel/cpufreq/acpi-cpufreq.c
@@ -269,48 +269,6 @@ acpi_cpufreq_verify (
 }
 
 
-/*
- * processor_init_pdc - let BIOS know about the SMP capabilities
- * of this driver
- * @perf: processor-specific acpi_io_data struct
- * @cpu: CPU being initialized
- *
- * To avoid issues with legacy OSes, some BIOSes require to be informed of
- * the SMP capabilities of OS P-state driver. Here we set the bits in _PDC
- * accordingly. Actual call to _PDC is done in driver/acpi/processor.c
- */
-static void
-processor_init_pdc (
-		struct acpi_processor_performance *perf,
-		unsigned int cpu,
-		struct acpi_object_list *obj_list
-		)
-{
-	union acpi_object *obj;
-	u32 *buf;
-
-	dprintk("processor_init_pdc\n");
-
-	perf->pdc = NULL;
-	/* Initialize pdc. It will be used later. */
-	if (!obj_list)
-		return;
-
-	if (!(obj_list->count && obj_list->pointer))
-		return;
-
-	obj = obj_list->pointer;
-	if ((obj->buffer.length == 12) && obj->buffer.pointer) {
-		buf = (u32 *)obj->buffer.pointer;
-       		buf[0] = ACPI_PDC_REVISION_ID;
-       		buf[1] = 1;
-       		buf[2] = ACPI_PDC_EST_CAPABILITY_SMP;
-		perf->pdc = obj_list;
-	}
-	return;
-}
-
-
 static int
 acpi_cpufreq_cpu_init (
 	struct cpufreq_policy   *policy)
@@ -320,14 +278,7 @@ acpi_cpufreq_cpu_init (
 	struct cpufreq_acpi_io	*data;
 	unsigned int		result = 0;
 
-	union acpi_object		arg0 = {ACPI_TYPE_BUFFER};
-	u32				arg0_buf[3];
-	struct acpi_object_list 	arg_list = {1, &arg0};
-
 	dprintk("acpi_cpufreq_cpu_init\n");
-	/* setup arg_list for _PDC settings */
-        arg0.buffer.length = 12;
-        arg0.buffer.pointer = (u8 *) arg0_buf;
 
 	data = kmalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL);
 	if (!data)
@@ -337,9 +288,7 @@ acpi_cpufreq_cpu_init (
 
 	acpi_io_data[cpu] = data;
 
-	processor_init_pdc(&data->acpi_data, cpu, &arg_list);
 	result = acpi_processor_register_performance(&data->acpi_data, cpu);
-	data->acpi_data.pdc = NULL;
 
 	if (result)
 		goto err_free;
diff --git a/arch/ia64/kernel/cyclone.c b/arch/ia64/kernel/cyclone.c
index 6ade3790ce0..e00b21514f7 100644
--- a/arch/ia64/kernel/cyclone.c
+++ b/arch/ia64/kernel/cyclone.c
@@ -36,7 +36,7 @@ int __init init_cyclone_clock(void)
 	u32* volatile cyclone_timer;	/* Cyclone MPMC0 register */
 
 	if (!use_cyclone)
-		return -ENODEV;
+		return 0;
 
 	printk(KERN_INFO "Summit chipset: Starting Cyclone Counter.\n");
 
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index c485a3b32ba..9990320b6f9 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -410,24 +410,16 @@ efi_init (void)
 	efi_config_table_t *config_tables;
 	efi_char16_t *c16;
 	u64 efi_desc_size;
-	char *cp, *end, vendor[100] = "unknown";
+	char *cp, vendor[100] = "unknown";
 	extern char saved_command_line[];
 	int i;
 
 	/* it's too early to be able to use the standard kernel command line support... */
 	for (cp = saved_command_line; *cp; ) {
 		if (memcmp(cp, "mem=", 4) == 0) {
-			cp += 4;
-			mem_limit = memparse(cp, &end);
-			if (end != cp)
-				break;
-			cp = end;
+			mem_limit = memparse(cp + 4, &cp);
 		} else if (memcmp(cp, "max_addr=", 9) == 0) {
-			cp += 9;
-			max_addr = GRANULEROUNDDOWN(memparse(cp, &end));
-			if (end != cp)
-				break;
-			cp = end;
+			max_addr = GRANULEROUNDDOWN(memparse(cp + 9, &cp));
 		} else {
 			while (*cp != ' ' && *cp)
 				++cp;
@@ -458,7 +450,7 @@ efi_init (void)
 	/* Show what we know for posterity */
 	c16 = __va(efi.systab->fw_vendor);
 	if (c16) {
-		for (i = 0;i < (int) sizeof(vendor) && *c16; ++i)
+		for (i = 0;i < (int) sizeof(vendor) - 1 && *c16; ++i)
 			vendor[i] = *c16++;
 		vendor[i] = '\0';
 	}
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 9dda7a36d1e..0e3eda99e54 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -569,7 +569,9 @@ GLOBAL_ENTRY(ia64_trace_syscall)
 .mem.offset 0,0; st8.spill [r2]=r8		// store return value in slot for r8
 .mem.offset 8,0; st8.spill [r3]=r10		// clear error indication in slot for r10
 	br.call.sptk.many rp=syscall_trace_leave // give parent a chance to catch return value
-.ret3:	br.cond.sptk .work_pending_syscall_end
+.ret3:
+(pUStk)	cmp.eq.unc p6,p0=r0,r0			// p6 <- pUStk
+	br.cond.sptk .work_pending_syscall_end
 
 strace_error:
 	ld8 r3=[r2]				// load pt_regs.r8
@@ -1587,5 +1589,21 @@ sys_call_table:
 	data8 sys_inotify_add_watch
 	data8 sys_inotify_rm_watch
 	data8 sys_migrate_pages			// 1280
+	data8 sys_openat
+	data8 sys_mkdirat
+	data8 sys_mknodat
+	data8 sys_fchownat
+	data8 sys_futimesat			// 1285
+	data8 sys_newfstatat
+	data8 sys_unlinkat
+	data8 sys_renameat
+	data8 sys_linkat
+	data8 sys_symlinkat			// 1290
+	data8 sys_readlinkat
+	data8 sys_fchmodat
+	data8 sys_faccessat
+	data8 sys_ni_syscall			// reserved for pselect
+	data8 sys_ni_syscall			// 1295 reserved for ppoll
+	data8 sys_unshare
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index ce423910ca9..7a05b1cb2ad 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -878,31 +878,7 @@ fsyscall_table:
 	data8 0				// timer_delete
 	data8 0				// clock_settime
 	data8 fsys_clock_gettime	// clock_gettime
-	data8 0				// clock_getres		// 1255
-	data8 0				// clock_nanosleep
-	data8 0				// fstatfs64
-	data8 0				// statfs64
-	data8 0
-	data8 0							// 1260
-	data8 0
-	data8 0				// mq_open
-	data8 0				// mq_unlink
-	data8 0				// mq_timedsend
-	data8 0				// mq_timedreceive	// 1265
-	data8 0				// mq_notify
-	data8 0				// mq_getsetattr
-	data8 0				// kexec_load
-	data8 0
-	data8 0							// 1270
-	data8 0
-	data8 0
-	data8 0
-	data8 0
-	data8 0							// 1275
-	data8 0
-	data8 0
-	data8 0
-	data8 0
-	data8 0							// 1280
 
-	.org fsyscall_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
+	// fill in zeros for the remaining entries
+	.zero:
+	.space fsyscall_table + 8*NR_syscalls - .zero, 0
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index fbc7ea35dd5..f1778a84ea6 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -352,6 +352,7 @@ start_ap:
 	mov ar.rsc=0		// place RSE in enforced lazy mode
 	;;
 	loadrs			// clear the dirty partition
+	mov IA64_KR(PER_CPU_DATA)=r0	// clear physical per-CPU base
 	;;
 	mov ar.bspstore=r2	// establish the new RSE stack
 	;;
diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c
index e72de580ebb..bbcfd08378a 100644
--- a/arch/ia64/kernel/ia64_ksyms.c
+++ b/arch/ia64/kernel/ia64_ksyms.c
@@ -10,23 +10,8 @@
 
 #include <linux/string.h>
 EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memchr);
-EXPORT_SYMBOL(memcmp);
 EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memmove);
-EXPORT_SYMBOL(memscan);
-EXPORT_SYMBOL(strcat);
-EXPORT_SYMBOL(strchr);
-EXPORT_SYMBOL(strcmp);
-EXPORT_SYMBOL(strcpy);
 EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strncat);
-EXPORT_SYMBOL(strncmp);
-EXPORT_SYMBOL(strncpy);
-EXPORT_SYMBOL(strnlen);
-EXPORT_SYMBOL(strrchr);
-EXPORT_SYMBOL(strstr);
-EXPORT_SYMBOL(strpbrk);
 
 #include <asm/checksum.h>
 EXPORT_SYMBOL(ip_fast_csum);		/* hand-coded assembly */
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index 574084f343f..8832c553230 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -631,6 +631,7 @@ get_target_cpu (unsigned int gsi, int vector)
 {
 #ifdef CONFIG_SMP
 	static int cpu = -1;
+	extern int cpe_vector;
 
 	/*
 	 * In case of vector shared by multiple RTEs, all RTEs that
@@ -653,6 +654,11 @@ get_target_cpu (unsigned int gsi, int vector)
 	if (!cpu_online(smp_processor_id()))
 		return cpu_physical_id(smp_processor_id());
 
+#ifdef CONFIG_ACPI
+	if (cpe_vector > 0 && vector == IA64_CPEP_VECTOR)
+		return get_cpei_target_cpu();
+#endif
+
 #ifdef CONFIG_NUMA
 	{
 		int num_cpus, cpu_index, iosapic_index, numa_cpu, i = 0;
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index d33244c3275..5ce908ef9c9 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -163,8 +163,19 @@ void fixup_irqs(void)
 {
 	unsigned int irq;
 	extern void ia64_process_pending_intr(void);
+	extern void ia64_disable_timer(void);
+	extern volatile int time_keeper_id;
+
+	ia64_disable_timer();
+
+	/*
+	 * Find a new timesync master
+	 */
+	if (smp_processor_id() == time_keeper_id) {
+		time_keeper_id = first_cpu(cpu_online_map);
+		printk ("CPU %d is now promoted to time-keeper master\n", time_keeper_id);
+	}
 
-	ia64_set_itv(1<<16);
 	/*
 	 * Phase 1: Locate irq's bound to this cpu and
 	 * relocate them for cpu removal.
diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index 301f2e9d262..dcd906fe574 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -561,11 +561,12 @@ ENTRY(dirty_bit)
 	;;					// avoid RAW on r18
 	mov ar.ccv=r18				// set compare value for cmpxchg
 	or r25=_PAGE_D|_PAGE_A,r18		// set the dirty and accessed bits
+	tbit.z p7,p6 = r18,_PAGE_P_BIT		// Check present bit
 	;;
-	cmpxchg8.acq r26=[r17],r25,ar.ccv
+(p6)	cmpxchg8.acq r26=[r17],r25,ar.ccv	// Only update if page is present
 	mov r24=PAGE_SHIFT<<2
 	;;
-	cmp.eq p6,p7=r26,r18
+(p6)	cmp.eq p6,p7=r26,r18			// Only compare if page is present
 	;;
 (p6)	itc.d r25				// install updated PTE
 	;;
@@ -626,11 +627,12 @@ ENTRY(iaccess_bit)
 	;;
 	mov ar.ccv=r18				// set compare value for cmpxchg
 	or r25=_PAGE_A,r18			// set the accessed bit
+	tbit.z p7,p6 = r18,_PAGE_P_BIT	 	// Check present bit
 	;;
-	cmpxchg8.acq r26=[r17],r25,ar.ccv
+(p6)	cmpxchg8.acq r26=[r17],r25,ar.ccv	// Only if page present
 	mov r24=PAGE_SHIFT<<2
 	;;
-	cmp.eq p6,p7=r26,r18
+(p6)	cmp.eq p6,p7=r26,r18			// Only if page present
 	;;
 (p6)	itc.i r25				// install updated PTE
 	;;
@@ -680,11 +682,12 @@ ENTRY(daccess_bit)
 	;;					// avoid RAW on r18
 	mov ar.ccv=r18				// set compare value for cmpxchg
 	or r25=_PAGE_A,r18			// set the dirty bit
+	tbit.z p7,p6 = r18,_PAGE_P_BIT		// Check present bit
 	;;
-	cmpxchg8.acq r26=[r17],r25,ar.ccv
+(p6)	cmpxchg8.acq r26=[r17],r25,ar.ccv	// Only if page is present
 	mov r24=PAGE_SHIFT<<2
 	;;
-	cmp.eq p6,p7=r26,r18
+(p6)	cmp.eq p6,p7=r26,r18			// Only if page is present
 	;;
 (p6)	itc.d r25				// install updated PTE
 	/*
@@ -1362,7 +1365,6 @@ END(debug_vector)
 // 0x5a00 Entry 30 (size 16 bundles) Unaligned Reference (57)
 ENTRY(unaligned_access)
 	DBG_FAULT(30)
-	mov r16=cr.ipsr
 	mov r31=pr		// prepare to save predicates
 	;;
 	br.sptk.many dispatch_unaligned_handler
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index ee7eec9ee57..87fb7cecead 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -289,6 +289,7 @@ ia64_mca_log_sal_error_record(int sal_info_type)
 #ifdef CONFIG_ACPI
 
 int cpe_vector = -1;
+int ia64_cpe_irq = -1;
 
 static irqreturn_t
 ia64_mca_cpe_int_handler (int cpe_irq, void *arg, struct pt_regs *ptregs)
@@ -1444,11 +1445,13 @@ void __devinit
 ia64_mca_cpu_init(void *cpu_data)
 {
 	void *pal_vaddr;
+	static int first_time = 1;
 
-	if (smp_processor_id() == 0) {
+	if (first_time) {
 		void *mca_data;
 		int cpu;
 
+		first_time = 0;
 		mca_data = alloc_bootmem(sizeof(struct ia64_mca_cpu)
 					 * NR_CPUS + KERNEL_STACK_SIZE);
 		mca_data = (void *)(((unsigned long)mca_data +
@@ -1704,6 +1707,7 @@ ia64_mca_late_init(void)
 					desc = irq_descp(irq);
 					desc->status |= IRQ_PER_CPU;
 					setup_irq(irq, &mca_cpe_irqaction);
+					ia64_cpe_irq = irq;
 				}
 			ia64_mca_register_cpev(cpe_vector);
 			IA64_MCA_DEBUG("%s: CPEI/P setup and enabled.\n", __FUNCTION__);
diff --git a/arch/ia64/kernel/mca_asm.S b/arch/ia64/kernel/mca_asm.S
index 403a80a58c1..60a464bfd9e 100644
--- a/arch/ia64/kernel/mca_asm.S
+++ b/arch/ia64/kernel/mca_asm.S
@@ -512,7 +512,7 @@ ia64_state_save:
 	st8 [temp1]=r12		// os_status, default is cold boot
 	mov r6=IA64_MCA_SAME_CONTEXT
 	;;
-	st8 [temp1]=r6		// context, default is same context
+	st8 [temp2]=r6		// context, default is same context
 
 	// Save the pt_regs data that is not in minstate.  The previous code
 	// left regs at sos.
diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c
index 3492e3211a4..e883d85906d 100644
--- a/arch/ia64/kernel/mca_drv.c
+++ b/arch/ia64/kernel/mca_drv.c
@@ -123,8 +123,9 @@ mca_page_isolate(unsigned long paddr)
 void
 mca_handler_bh(unsigned long paddr)
 {
-	printk(KERN_DEBUG "OS_MCA: process [pid: %d](%s) encounters MCA.\n",
-		current->pid, current->comm);
+	printk(KERN_ERR
+		"OS_MCA: process [pid: %d](%s) encounters MCA (paddr=%lx)\n",
+		current->pid, current->comm, paddr);
 
 	spin_lock(&mca_bh_lock);
 	switch (mca_page_isolate(paddr)) {
@@ -132,7 +133,7 @@ mca_handler_bh(unsigned long paddr)
 		printk(KERN_DEBUG "Page isolation: ( %lx ) success.\n", paddr);
 		break;
 	case ISOLATE_NG:
-		printk(KERN_DEBUG "Page isolation: ( %lx ) failure.\n", paddr);
+		printk(KERN_CRIT "Page isolation: ( %lx ) failure.\n", paddr);
 		break;
 	default:
 		break;
@@ -437,6 +438,9 @@ recover_from_read_error(slidx_table_t *slidx,
 	 *    the process not have any locks of kernel.
 	 */
 
+	/* Is minstate valid? */
+	if (!peidx_bottom(peidx) || !(peidx_bottom(peidx)->valid.minstate))
+		return 0;
 	psr1 =(struct ia64_psr *)&(peidx_minstate_area(peidx)->pmsa_ipsr);
 
 	/*
@@ -564,10 +568,15 @@ recover_from_processor_error(int platform, slidx_table_t *slidx,
 		return 0;
 
 	/*
-	 * If there is no bus error, record is weird but we need not to recover.
+	 * The cache check and bus check bits have four possible states
+	 *   cc bc
+	 *    0  0	Weird record, not recovered
+	 *    1  0	Cache error, not recovered
+	 *    0  1	I/O error, attempt recovery
+	 *    1  1	Memory error, attempt recovery
 	 */
 	if (psp->bc == 0 || pbci == NULL)
-		return 1;
+		return 0;
 
 	/*
 	 * Sorry, we cannot handle so many.
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 9c5194b385d..077f21216b6 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -6722,6 +6722,7 @@ __initcall(pfm_init);
 void
 pfm_init_percpu (void)
 {
+	static int first_time=1;
 	/*
 	 * make sure no measurement is active
 	 * (may inherit programmed PMCs from EFI).
@@ -6734,8 +6735,10 @@ pfm_init_percpu (void)
 	 */
 	pfm_unfreeze_pmu();
 
-	if (smp_processor_id() == 0)
+	if (first_time) {
 		register_percpu_irq(IA64_PERFMON_VECTOR, &perfmon_irqaction);
+		first_time=0;
+	}
 
 	ia64_setreg(_IA64_REG_CR_PMV, IA64_PERFMON_VECTOR);
 	ia64_srlz_d();
diff --git a/arch/ia64/kernel/sal.c b/arch/ia64/kernel/sal.c
index acc0f132f86..056f7a6eedc 100644
--- a/arch/ia64/kernel/sal.c
+++ b/arch/ia64/kernel/sal.c
@@ -14,6 +14,7 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 
+#include <asm/delay.h>
 #include <asm/page.h>
 #include <asm/sal.h>
 #include <asm/pal.h>
@@ -214,6 +215,78 @@ chk_nointroute_opt(void)
 static void __init sal_desc_ap_wakeup(void *p) { }
 #endif
 
+/*
+ * HP rx5670 firmware polls for interrupts during SAL_CACHE_FLUSH by reading
+ * cr.ivr, but it never writes cr.eoi.  This leaves any interrupt marked as
+ * "in-service" and masks other interrupts of equal or lower priority.
+ *
+ * HP internal defect reports: F1859, F2775, F3031.
+ */
+static int sal_cache_flush_drops_interrupts;
+
+static void __init
+check_sal_cache_flush (void)
+{
+	unsigned long flags, itv;
+	int cpu;
+	u64 vector;
+
+	cpu = get_cpu();
+	local_irq_save(flags);
+
+	/*
+	 * Schedule a timer interrupt, wait until it's reported, and see if
+	 * SAL_CACHE_FLUSH drops it.
+	 */
+	itv = ia64_get_itv();
+	BUG_ON((itv & (1 << 16)) == 0);
+
+	ia64_set_itv(IA64_TIMER_VECTOR);
+	ia64_set_itm(ia64_get_itc() + 1000);
+
+	while (!ia64_get_irr(IA64_TIMER_VECTOR))
+		cpu_relax();
+
+	ia64_sal_cache_flush(3);
+
+	if (ia64_get_irr(IA64_TIMER_VECTOR)) {
+		vector = ia64_get_ivr();
+		ia64_eoi();
+		WARN_ON(vector != IA64_TIMER_VECTOR);
+	} else {
+		sal_cache_flush_drops_interrupts = 1;
+		printk(KERN_ERR "SAL: SAL_CACHE_FLUSH drops interrupts; "
+			"PAL_CACHE_FLUSH will be used instead\n");
+		ia64_eoi();
+	}
+
+	ia64_set_itv(itv);
+	local_irq_restore(flags);
+	put_cpu();
+}
+
+s64
+ia64_sal_cache_flush (u64 cache_type)
+{
+	struct ia64_sal_retval isrv;
+
+	if (sal_cache_flush_drops_interrupts) {
+		unsigned long flags;
+		u64 progress;
+		s64 rc;
+
+		progress = 0;
+		local_irq_save(flags);
+		rc = ia64_pal_cache_flush(cache_type,
+			PAL_CACHE_FLUSH_INVALIDATE, &progress, NULL);
+		local_irq_restore(flags);
+		return rc;
+	}
+
+	SAL_CALL(isrv, SAL_CACHE_FLUSH, cache_type, 0, 0, 0, 0, 0, 0);
+	return isrv.status;
+}
+
 void __init
 ia64_sal_init (struct ia64_sal_systab *systab)
 {
@@ -262,6 +335,8 @@ ia64_sal_init (struct ia64_sal_systab *systab)
 		}
 		p += SAL_DESC_SIZE(*p);
 	}
+
+	check_sal_cache_flush();
 }
 
 int
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index c0766575a3a..3258e09278d 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -71,6 +71,8 @@ unsigned long __per_cpu_offset[NR_CPUS];
 EXPORT_SYMBOL(__per_cpu_offset);
 #endif
 
+extern void ia64_setup_printk_clock(void);
+
 DEFINE_PER_CPU(struct cpuinfo_ia64, cpu_info);
 DEFINE_PER_CPU(unsigned long, local_per_cpu_offset);
 DEFINE_PER_CPU(unsigned long, ia64_phys_stacked_size_p8);
@@ -428,6 +430,7 @@ setup_arch (char **cmdline_p)
 	if (early_console_setup(*cmdline_p) == 0)
 		mark_bsp_online();
 
+	parse_early_param();
 #ifdef CONFIG_ACPI
 	/* Initialize the ACPI boot-time table parser */
 	acpi_table_init();
@@ -445,6 +448,8 @@ setup_arch (char **cmdline_p)
 	/* process SAL system table: */
 	ia64_sal_init(efi.sal_systab);
 
+	ia64_setup_printk_clock();
+
 #ifdef CONFIG_SMP
 	cpu_physical_id(0) = hard_smp_processor_id();
 
@@ -684,6 +689,9 @@ void
 setup_per_cpu_areas (void)
 {
 	/* start_kernel() requires this... */
+#ifdef CONFIG_ACPI_HOTPLUG_CPU
+	prefill_possible_map();
+#endif
 }
 
 /*
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 8f44e7d2df6..c4b633b36da 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -70,6 +70,12 @@
 #endif
 
 #ifdef CONFIG_HOTPLUG_CPU
+#ifdef CONFIG_PERMIT_BSP_REMOVE
+#define bsp_remove_ok	1
+#else
+#define bsp_remove_ok	0
+#endif
+
 /*
  * Store all idle threads, this can be reused instead of creating
  * a new thread. Also avoids complicated thread destroy functionality
@@ -104,7 +110,7 @@ struct sal_to_os_boot *sal_state_for_booting_cpu = &sal_boot_rendez_state[0];
 /*
  * ITC synchronization related stuff:
  */
-#define MASTER	0
+#define MASTER	(0)
 #define SLAVE	(SMP_CACHE_BYTES/8)
 
 #define NUM_ROUNDS	64	/* magic value */
@@ -129,7 +135,7 @@ DEFINE_PER_CPU(int, cpu_state);
 /* Bitmasks of currently online, and possible CPUs */
 cpumask_t cpu_online_map;
 EXPORT_SYMBOL(cpu_online_map);
-cpumask_t cpu_possible_map;
+cpumask_t cpu_possible_map = CPU_MASK_NONE;
 EXPORT_SYMBOL(cpu_possible_map);
 
 cpumask_t cpu_core_map[NR_CPUS] __cacheline_aligned;
@@ -151,6 +157,27 @@ char __initdata no_int_routing;
 
 unsigned char smp_int_redirect; /* are INT and IPI redirectable by the chipset? */
 
+#ifdef CONFIG_FORCE_CPEI_RETARGET
+#define CPEI_OVERRIDE_DEFAULT	(1)
+#else
+#define CPEI_OVERRIDE_DEFAULT	(0)
+#endif
+
+unsigned int force_cpei_retarget = CPEI_OVERRIDE_DEFAULT;
+
+static int __init
+cmdl_force_cpei(char *str)
+{
+	int value=0;
+
+	get_option (&str, &value);
+	force_cpei_retarget = value;
+
+	return 1;
+}
+
+__setup("force_cpei=", cmdl_force_cpei);
+
 static int __init
 nointroute (char *str)
 {
@@ -161,6 +188,27 @@ nointroute (char *str)
 
 __setup("nointroute", nointroute);
 
+static void fix_b0_for_bsp(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	int cpuid;
+	static int fix_bsp_b0 = 1;
+
+	cpuid = smp_processor_id();
+
+	/*
+	 * Cache the b0 value on the first AP that comes up
+	 */
+	if (!(fix_bsp_b0 && cpuid))
+		return;
+
+	sal_boot_rendez_state[0].br[0] = sal_boot_rendez_state[cpuid].br[0];
+	printk ("Fixed BSP b0 value from CPU %d\n", cpuid);
+
+	fix_bsp_b0 = 0;
+#endif
+}
+
 void
 sync_master (void *arg)
 {
@@ -327,8 +375,9 @@ smp_setup_percpu_timer (void)
 static void __devinit
 smp_callin (void)
 {
-	int cpuid, phys_id;
+	int cpuid, phys_id, itc_master;
 	extern void ia64_init_itm(void);
+	extern volatile int time_keeper_id;
 
 #ifdef CONFIG_PERFMON
 	extern void pfm_init_percpu(void);
@@ -336,6 +385,7 @@ smp_callin (void)
 
 	cpuid = smp_processor_id();
 	phys_id = hard_smp_processor_id();
+	itc_master = time_keeper_id;
 
 	if (cpu_online(cpuid)) {
 		printk(KERN_ERR "huh, phys CPU#0x%x, CPU#0x%x already present??\n",
@@ -343,6 +393,8 @@ smp_callin (void)
 		BUG();
 	}
 
+	fix_b0_for_bsp();
+
 	lock_ipi_calllock();
 	cpu_set(cpuid, cpu_online_map);
 	unlock_ipi_calllock();
@@ -365,8 +417,8 @@ smp_callin (void)
 		 * calls spin_unlock_bh(), which calls spin_unlock_bh(), which calls
 		 * local_bh_enable(), which bugs out if irqs are not enabled...
 		 */
-		Dprintk("Going to syncup ITC with BP.\n");
-		ia64_sync_itc(0);
+		Dprintk("Going to syncup ITC with ITC Master.\n");
+		ia64_sync_itc(itc_master);
 	}
 
 	/*
@@ -506,9 +558,6 @@ smp_build_cpu_map (void)
 
 	for (cpu = 0; cpu < NR_CPUS; cpu++) {
 		ia64_cpu_to_sapicid[cpu] = -1;
-#ifdef CONFIG_HOTPLUG_CPU
-		cpu_set(cpu, cpu_possible_map);
-#endif
 	}
 
 	ia64_cpu_to_sapicid[0] = boot_cpu_id;
@@ -638,6 +687,47 @@ remove_siblinginfo(int cpu)
 }
 
 extern void fixup_irqs(void);
+
+int migrate_platform_irqs(unsigned int cpu)
+{
+	int new_cpei_cpu;
+	irq_desc_t *desc = NULL;
+	cpumask_t 	mask;
+	int 		retval = 0;
+
+	/*
+	 * dont permit CPEI target to removed.
+	 */
+	if (cpe_vector > 0 && is_cpu_cpei_target(cpu)) {
+		printk ("CPU (%d) is CPEI Target\n", cpu);
+		if (can_cpei_retarget()) {
+			/*
+			 * Now re-target the CPEI to a different processor
+			 */
+			new_cpei_cpu = any_online_cpu(cpu_online_map);
+			mask = cpumask_of_cpu(new_cpei_cpu);
+			set_cpei_target_cpu(new_cpei_cpu);
+			desc = irq_descp(ia64_cpe_irq);
+			/*
+			 * Switch for now, immediatly, we need to do fake intr
+			 * as other interrupts, but need to study CPEI behaviour with
+			 * polling before making changes.
+			 */
+			if (desc) {
+				desc->handler->disable(ia64_cpe_irq);
+				desc->handler->set_affinity(ia64_cpe_irq, mask);
+				desc->handler->enable(ia64_cpe_irq);
+				printk ("Re-targetting CPEI to cpu %d\n", new_cpei_cpu);
+			}
+		}
+		if (!desc) {
+			printk ("Unable to retarget CPEI, offline cpu [%d] failed\n", cpu);
+			retval = -EBUSY;
+		}
+	}
+	return retval;
+}
+
 /* must be called with cpucontrol mutex held */
 int __cpu_disable(void)
 {
@@ -646,8 +736,17 @@ int __cpu_disable(void)
 	/*
 	 * dont permit boot processor for now
 	 */
-	if (cpu == 0)
-		return -EBUSY;
+	if (cpu == 0 && !bsp_remove_ok) {
+		printk ("Your platform does not support removal of BSP\n");
+		return (-EBUSY);
+	}
+
+	cpu_clear(cpu, cpu_online_map);
+
+	if (migrate_platform_irqs(cpu)) {
+		cpu_set(cpu, cpu_online_map);
+		return (-EBUSY);
+	}
 
 	remove_siblinginfo(cpu);
 	cpu_clear(cpu, cpu_online_map);
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 028a2b95936..ac167436e93 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -32,7 +32,7 @@
 
 extern unsigned long wall_jiffies;
 
-#define TIME_KEEPER_ID	0	/* smp_processor_id() of time-keeper */
+volatile int time_keeper_id = 0; /* smp_processor_id() of time-keeper */
 
 #ifdef CONFIG_IA64_DEBUG_IRQ
 
@@ -71,7 +71,7 @@ timer_interrupt (int irq, void *dev_id, struct pt_regs *regs)
 
 		new_itm += local_cpu_data->itm_delta;
 
-		if (smp_processor_id() == TIME_KEEPER_ID) {
+		if (smp_processor_id() == time_keeper_id) {
 			/*
 			 * Here we are in the timer irq handler. We have irqs locally
 			 * disabled, but we don't know if the timer_bh is running on
@@ -236,6 +236,11 @@ static struct irqaction timer_irqaction = {
 	.name =		"timer"
 };
 
+void __devinit ia64_disable_timer(void)
+{
+	ia64_set_itv(1 << 16);
+}
+
 void __init
 time_init (void)
 {
@@ -250,31 +255,53 @@ time_init (void)
 	set_normalized_timespec(&wall_to_monotonic, -xtime.tv_sec, -xtime.tv_nsec);
 }
 
-#define SMALLUSECS 100
+/*
+ * Generic udelay assumes that if preemption is allowed and the thread
+ * migrates to another CPU, that the ITC values are synchronized across
+ * all CPUs.
+ */
+static void
+ia64_itc_udelay (unsigned long usecs)
+{
+	unsigned long start = ia64_get_itc();
+	unsigned long end = start + usecs*local_cpu_data->cyc_per_usec;
+
+	while (time_before(ia64_get_itc(), end))
+		cpu_relax();
+}
+
+void (*ia64_udelay)(unsigned long usecs) = &ia64_itc_udelay;
 
 void
 udelay (unsigned long usecs)
 {
-	unsigned long start;
-	unsigned long cycles;
-	unsigned long smallusecs;
+	(*ia64_udelay)(usecs);
+}
+EXPORT_SYMBOL(udelay);
 
-	/*
-	 * Execute the non-preemptible delay loop (because the ITC might
-	 * not be synchronized between CPUS) in relatively short time
-	 * chunks, allowing preemption between the chunks.
-	 */
-	while (usecs > 0) {
-		smallusecs = (usecs > SMALLUSECS) ? SMALLUSECS : usecs;
-		preempt_disable();
-		cycles = smallusecs*local_cpu_data->cyc_per_usec;
-		start = ia64_get_itc();
+static unsigned long long ia64_itc_printk_clock(void)
+{
+	if (ia64_get_kr(IA64_KR_PER_CPU_DATA))
+		return sched_clock();
+	return 0;
+}
+
+static unsigned long long ia64_default_printk_clock(void)
+{
+	return (unsigned long long)(jiffies_64 - INITIAL_JIFFIES) *
+		(1000000000/HZ);
+}
 
-		while (ia64_get_itc() - start < cycles)
-			cpu_relax();
+unsigned long long (*ia64_printk_clock)(void) = &ia64_default_printk_clock;
 
-		preempt_enable();
-		usecs -= smallusecs;
-	}
+unsigned long long printk_clock(void)
+{
+	return ia64_printk_clock();
+}
+
+void __init
+ia64_setup_printk_clock(void)
+{
+	if (!(sal_platform_features & IA64_SAL_PLATFORM_FEATURE_ITC_DRIFT))
+		ia64_printk_clock = ia64_itc_printk_clock;
 }
-EXPORT_SYMBOL(udelay);
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index 706b7734e19..3b6fd798c4d 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -36,7 +36,7 @@ int arch_register_cpu(int num)
 	parent = &sysfs_nodes[cpu_to_node(num)];
 #endif /* CONFIG_NUMA */
 
-#ifdef CONFIG_ACPI
+#if defined (CONFIG_ACPI) && defined (CONFIG_HOTPLUG_CPU)
 	/*
 	 * If CPEI cannot be re-targetted, and this is
 	 * CPEI target, then dont create the control file
@@ -71,31 +71,33 @@ static int __init topology_init(void)
 	int i, err = 0;
 
 #ifdef CONFIG_NUMA
-	sysfs_nodes = kmalloc(sizeof(struct node) * MAX_NUMNODES, GFP_KERNEL);
+	sysfs_nodes = kzalloc(sizeof(struct node) * MAX_NUMNODES, GFP_KERNEL);
 	if (!sysfs_nodes) {
 		err = -ENOMEM;
 		goto out;
 	}
-	memset(sysfs_nodes, 0, sizeof(struct node) * MAX_NUMNODES);
 
-	/* MCD - Do we want to register all ONLINE nodes, or all POSSIBLE nodes? */
-	for_each_online_node(i)
+	/*
+	 * MCD - Do we want to register all ONLINE nodes, or all POSSIBLE nodes?
+	 */
+	for_each_online_node(i) {
 		if ((err = register_node(&sysfs_nodes[i], i, 0)))
 			goto out;
+	}
 #endif
 
-	sysfs_cpus = kmalloc(sizeof(struct ia64_cpu) * NR_CPUS, GFP_KERNEL);
+	sysfs_cpus = kzalloc(sizeof(struct ia64_cpu) * NR_CPUS, GFP_KERNEL);
 	if (!sysfs_cpus) {
 		err = -ENOMEM;
 		goto out;
 	}
-	memset(sysfs_cpus, 0, sizeof(struct ia64_cpu) * NR_CPUS);
 
-	for_each_present_cpu(i)
+	for_each_present_cpu(i) {
 		if((err = arch_register_cpu(i)))
 			goto out;
+	}
 out:
 	return err;
 }
 
-__initcall(topology_init);
+subsys_initcall(topology_init);
diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c
index 55391901b01..dabd6c32641 100644
--- a/arch/ia64/kernel/traps.c
+++ b/arch/ia64/kernel/traps.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>       /* for EXPORT_SYMBOL */
 #include <linux/hardirq.h>
 #include <linux/kprobes.h>
+#include <linux/delay.h>		/* for ssleep() */
 
 #include <asm/fpswa.h>
 #include <asm/ia32.h>
@@ -116,6 +117,13 @@ die (const char *str, struct pt_regs *regs, long err)
 	bust_spinlocks(0);
 	die.lock_owner = -1;
 	spin_unlock_irq(&die.lock);
+
+	if (panic_on_oops) {
+		printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n");
+		ssleep(5);
+		panic("Fatal exception");
+	}
+
   	do_exit(SIGSEGV);
 }
 
diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c
index 43b45b65ee5..1e357550c77 100644
--- a/arch/ia64/kernel/unaligned.c
+++ b/arch/ia64/kernel/unaligned.c
@@ -24,7 +24,7 @@
 #include <asm/uaccess.h>
 #include <asm/unaligned.h>
 
-extern void die_if_kernel(char *str, struct pt_regs *regs, long err) __attribute__ ((noreturn));
+extern void die_if_kernel(char *str, struct pt_regs *regs, long err);
 
 #undef DEBUG_UNALIGNED_TRAP
 
@@ -53,6 +53,15 @@ dump (const char *str, void *vp, size_t len)
 #define SIGN_EXT9		0xffffffffffffff00ul
 
 /*
+ *  sysctl settable hook which tells the kernel whether to honor the
+ *  IA64_THREAD_UAC_NOPRINT prctl.  Because this is user settable, we want
+ *  to allow the super user to enable/disable this for security reasons
+ *  (i.e. don't allow attacker to fill up logs with unaligned accesses).
+ */
+int no_unaligned_warning;
+static int noprint_warning;
+
+/*
  * For M-unit:
  *
  *  opcode |   m  |   x6    |
@@ -1283,8 +1292,9 @@ within_logging_rate_limit (void)
 
 	if (jiffies - last_time > 5*HZ)
 		count = 0;
-	if (++count < 5) {
+	if (count < 5) {
 		last_time = jiffies;
+		count++;
 		return 1;
 	}
 	return 0;
@@ -1323,8 +1333,9 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs)
 		if ((current->thread.flags & IA64_THREAD_UAC_SIGBUS) != 0)
 			goto force_sigbus;
 
-		if (!(current->thread.flags & IA64_THREAD_UAC_NOPRINT)
-		    && within_logging_rate_limit())
+		if (!no_unaligned_warning &&
+		    !(current->thread.flags & IA64_THREAD_UAC_NOPRINT) &&
+		    within_logging_rate_limit())
 		{
 			char buf[200];	/* comm[] is at most 16 bytes... */
 			size_t len;
@@ -1339,7 +1350,22 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs)
 			if (user_mode(regs))
 				tty_write_message(current->signal->tty, buf);
 			buf[len-1] = '\0';	/* drop '\r' */
-			printk(KERN_WARNING "%s", buf);	/* watch for command names containing %s */
+			/* watch for command names containing %s */
+			printk(KERN_WARNING "%s", buf);
+		} else {
+			if (no_unaligned_warning && !noprint_warning) {
+				noprint_warning = 1;
+				printk(KERN_WARNING "%s(%d) encountered an "
+				       "unaligned exception which required\n"
+				       "kernel assistance, which degrades "
+				       "the performance of the application.\n"
+				       "Unaligned exception warnings have "
+				       "been disabled by the system "
+				       "administrator\n"
+				       "echo 0 > /proc/sys/kernel/ignore-"
+				       "unaligned-usertrap to re-enable\n",
+				       current->comm, current->pid);
+			}
 		}
 	} else {
 		if (within_logging_rate_limit())