Merge linux-2.6 with linux-acpi-2.6

16 files changed, 120 insertions, 504 deletions

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index e1c9ea03f31f..00151a8320d8 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -408,6 +408,11 @@ config GENERIC_IRQ_PROBE
 	bool
 	default y
 
+config GENERIC_PENDING_IRQ
+	bool
+	depends on GENERIC_HARDIRQS && SMP
+	default y
+
 source "arch/ia64/hp/sim/Kconfig"
 
 source "arch/ia64/oprofile/Kconfig"
diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c
index 7dcb8582ae0d..b42ec37be51c 100644
--- a/arch/ia64/hp/sim/simserial.c
+++ b/arch/ia64/hp/sim/simserial.c
@@ -130,7 +130,7 @@ static void rs_stop(struct tty_struct *tty)
 
 static void rs_start(struct tty_struct *tty)
 {
-#if SIMSERIAL_DEBUG
+#ifdef SIMSERIAL_DEBUG
 	printk("rs_start: tty->stopped=%d tty->hw_stopped=%d tty->flow_stopped=%d\n",
 		tty->stopped, tty->hw_stopped, tty->flow_stopped);
 #endif
diff --git a/arch/ia64/ia32/ia32_entry.S b/arch/ia64/ia32/ia32_entry.S
index 829a6d80711c..0708edb06cc4 100644
--- a/arch/ia64/ia32/ia32_entry.S
+++ b/arch/ia64/ia32/ia32_entry.S
@@ -215,7 +215,7 @@ ia32_syscall_table:
 	data8 sys32_fork
 	data8 sys_read
 	data8 sys_write
-	data8 sys32_open	  /* 5 */
+	data8 compat_sys_open	  /* 5 */
 	data8 sys_close
 	data8 sys32_waitpid
 	data8 sys_creat
diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c
index c1e20d65dd6c..e29a8a55486a 100644
--- a/arch/ia64/ia32/sys_ia32.c
+++ b/arch/ia64/ia32/sys_ia32.c
@@ -2359,37 +2359,6 @@ sys32_brk (unsigned int brk)
 	return ret;
 }
 
-/*
- * Exactly like fs/open.c:sys_open(), except that it doesn't set the O_LARGEFILE flag.
- */
-asmlinkage long
-sys32_open (const char __user * filename, int flags, int mode)
-{
-	char * tmp;
-	int fd, error;
-
-	tmp = getname(filename);
-	fd = PTR_ERR(tmp);
-	if (!IS_ERR(tmp)) {
-		fd = get_unused_fd();
-		if (fd >= 0) {
-			struct file *f = filp_open(tmp, flags, mode);
-			error = PTR_ERR(f);
-			if (IS_ERR(f))
-				goto out_error;
-			fd_install(fd, f);
-		}
-out:
-		putname(tmp);
-	}
-	return fd;
-
-out_error:
-	put_unused_fd(fd);
-	fd = error;
-	goto out;
-}
-
 /* Structure for ia32 emulation on ia64 */
 struct epoll_event32
 {
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index b242594be55b..307514f7a282 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -16,7 +16,7 @@ obj-$(CONFIG_IA64_HP_ZX1_SWIOTLB) += acpi-ext.o
 obj-$(CONFIG_IA64_PALINFO)	+= palinfo.o
 obj-$(CONFIG_IOSAPIC)		+= iosapic.o
 obj-$(CONFIG_MODULES)		+= module.o
-obj-$(CONFIG_SMP)		+= smp.o smpboot.o domain.o
+obj-$(CONFIG_SMP)		+= smp.o smpboot.o
 obj-$(CONFIG_NUMA)		+= numa.o
 obj-$(CONFIG_PERFMON)		+= perfmon_default_smpl.o
 obj-$(CONFIG_IA64_CYCLONE)	+= cyclone.o
diff --git a/arch/ia64/kernel/domain.c b/arch/ia64/kernel/domain.c
deleted file mode 100644
index bbb8efe126b7..000000000000
--- a/arch/ia64/kernel/domain.c
+++ /dev/null
@@ -1,396 +0,0 @@
-/*
- * arch/ia64/kernel/domain.c
- * Architecture specific sched-domains builder.
- *
- * Copyright (C) 2004 Jesse Barnes
- * Copyright (C) 2004 Silicon Graphics, Inc.
- */
-
-#include <linux/sched.h>
-#include <linux/percpu.h>
-#include <linux/slab.h>
-#include <linux/cpumask.h>
-#include <linux/init.h>
-#include <linux/topology.h>
-#include <linux/nodemask.h>
-
-#define SD_NODES_PER_DOMAIN 16
-
-#ifdef CONFIG_NUMA
-/**
- * find_next_best_node - find the next node to include in a sched_domain
- * @node: node whose sched_domain we're building
- * @used_nodes: nodes already in the sched_domain
- *
- * Find the next node to include in a given scheduling domain.  Simply
- * finds the closest node not already in the @used_nodes map.
- *
- * Should use nodemask_t.
- */
-static int find_next_best_node(int node, unsigned long *used_nodes)
-{
-	int i, n, val, min_val, best_node = 0;
-
-	min_val = INT_MAX;
-
-	for (i = 0; i < MAX_NUMNODES; i++) {
-		/* Start at @node */
-		n = (node + i) % MAX_NUMNODES;
-
-		if (!nr_cpus_node(n))
-			continue;
-
-		/* Skip already used nodes */
-		if (test_bit(n, used_nodes))
-			continue;
-
-		/* Simple min distance search */
-		val = node_distance(node, n);
-
-		if (val < min_val) {
-			min_val = val;
-			best_node = n;
-		}
-	}
-
-	set_bit(best_node, used_nodes);
-	return best_node;
-}
-
-/**
- * sched_domain_node_span - get a cpumask for a node's sched_domain
- * @node: node whose cpumask we're constructing
- * @size: number of nodes to include in this span
- *
- * Given a node, construct a good cpumask for its sched_domain to span.  It
- * should be one that prevents unnecessary balancing, but also spreads tasks
- * out optimally.
- */
-static cpumask_t sched_domain_node_span(int node)
-{
-	int i;
-	cpumask_t span, nodemask;
-	DECLARE_BITMAP(used_nodes, MAX_NUMNODES);
-
-	cpus_clear(span);
-	bitmap_zero(used_nodes, MAX_NUMNODES);
-
-	nodemask = node_to_cpumask(node);
-	cpus_or(span, span, nodemask);
-	set_bit(node, used_nodes);
-
-	for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
-		int next_node = find_next_best_node(node, used_nodes);
-		nodemask = node_to_cpumask(next_node);
-		cpus_or(span, span, nodemask);
-	}
-
-	return span;
-}
-#endif
-
-/*
- * At the moment, CONFIG_SCHED_SMT is never defined, but leave it in so we
- * can switch it on easily if needed.
- */
-#ifdef CONFIG_SCHED_SMT
-static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
-static struct sched_group sched_group_cpus[NR_CPUS];
-static int cpu_to_cpu_group(int cpu)
-{
-	return cpu;
-}
-#endif
-
-static DEFINE_PER_CPU(struct sched_domain, phys_domains);
-static struct sched_group sched_group_phys[NR_CPUS];
-static int cpu_to_phys_group(int cpu)
-{
-#ifdef CONFIG_SCHED_SMT
-	return first_cpu(cpu_sibling_map[cpu]);
-#else
-	return cpu;
-#endif
-}
-
-#ifdef CONFIG_NUMA
-/*
- * The init_sched_build_groups can't handle what we want to do with node
- * groups, so roll our own. Now each node has its own list of groups which
- * gets dynamically allocated.
- */
-static DEFINE_PER_CPU(struct sched_domain, node_domains);
-static struct sched_group *sched_group_nodes[MAX_NUMNODES];
-
-static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
-static struct sched_group sched_group_allnodes[MAX_NUMNODES];
-
-static int cpu_to_allnodes_group(int cpu)
-{
-	return cpu_to_node(cpu);
-}
-#endif
-
-/*
- * Build sched domains for a given set of cpus and attach the sched domains
- * to the individual cpus
- */
-void build_sched_domains(const cpumask_t *cpu_map)
-{
-	int i;
-
-	/*
-	 * Set up domains for cpus specified by the cpu_map.
-	 */
-	for_each_cpu_mask(i, *cpu_map) {
-		int group;
-		struct sched_domain *sd = NULL, *p;
-		cpumask_t nodemask = node_to_cpumask(cpu_to_node(i));
-
-		cpus_and(nodemask, nodemask, *cpu_map);
-
-#ifdef CONFIG_NUMA
-		if (num_online_cpus()
-				> SD_NODES_PER_DOMAIN*cpus_weight(nodemask)) {
-			sd = &per_cpu(allnodes_domains, i);
-			*sd = SD_ALLNODES_INIT;
-			sd->span = *cpu_map;
-			group = cpu_to_allnodes_group(i);
-			sd->groups = &sched_group_allnodes[group];
-			p = sd;
-		} else
-			p = NULL;
-
-		sd = &per_cpu(node_domains, i);
-		*sd = SD_NODE_INIT;
-		sd->span = sched_domain_node_span(cpu_to_node(i));
-		sd->parent = p;
-		cpus_and(sd->span, sd->span, *cpu_map);
-#endif
-
-		p = sd;
-		sd = &per_cpu(phys_domains, i);
-		group = cpu_to_phys_group(i);
-		*sd = SD_CPU_INIT;
-		sd->span = nodemask;
-		sd->parent = p;
-		sd->groups = &sched_group_phys[group];
-
-#ifdef CONFIG_SCHED_SMT
-		p = sd;
-		sd = &per_cpu(cpu_domains, i);
-		group = cpu_to_cpu_group(i);
-		*sd = SD_SIBLING_INIT;
-		sd->span = cpu_sibling_map[i];
-		cpus_and(sd->span, sd->span, *cpu_map);
-		sd->parent = p;
-		sd->groups = &sched_group_cpus[group];
-#endif
-	}
-
-#ifdef CONFIG_SCHED_SMT
-	/* Set up CPU (sibling) groups */
-	for_each_cpu_mask(i, *cpu_map) {
-		cpumask_t this_sibling_map = cpu_sibling_map[i];
-		cpus_and(this_sibling_map, this_sibling_map, *cpu_map);
-		if (i != first_cpu(this_sibling_map))
-			continue;
-
-		init_sched_build_groups(sched_group_cpus, this_sibling_map,
-						&cpu_to_cpu_group);
-	}
-#endif
-
-	/* Set up physical groups */
-	for (i = 0; i < MAX_NUMNODES; i++) {
-		cpumask_t nodemask = node_to_cpumask(i);
-
-		cpus_and(nodemask, nodemask, *cpu_map);
-		if (cpus_empty(nodemask))
-			continue;
-
-		init_sched_build_groups(sched_group_phys, nodemask,
-						&cpu_to_phys_group);
-	}
-
-#ifdef CONFIG_NUMA
-	init_sched_build_groups(sched_group_allnodes, *cpu_map,
-				&cpu_to_allnodes_group);
-
-	for (i = 0; i < MAX_NUMNODES; i++) {
-		/* Set up node groups */
-		struct sched_group *sg, *prev;
-		cpumask_t nodemask = node_to_cpumask(i);
-		cpumask_t domainspan;
-		cpumask_t covered = CPU_MASK_NONE;
-		int j;
-
-		cpus_and(nodemask, nodemask, *cpu_map);
-		if (cpus_empty(nodemask))
-			continue;
-
-		domainspan = sched_domain_node_span(i);
-		cpus_and(domainspan, domainspan, *cpu_map);
-
-		sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL);
-		sched_group_nodes[i] = sg;
-		for_each_cpu_mask(j, nodemask) {
-			struct sched_domain *sd;
-			sd = &per_cpu(node_domains, j);
-			sd->groups = sg;
-			if (sd->groups == NULL) {
-				/* Turn off balancing if we have no groups */
-				sd->flags = 0;
-			}
-		}
-		if (!sg) {
-			printk(KERN_WARNING
-			"Can not alloc domain group for node %d\n", i);
-			continue;
-		}
-		sg->cpu_power = 0;
-		sg->cpumask = nodemask;
-		cpus_or(covered, covered, nodemask);
-		prev = sg;
-
-		for (j = 0; j < MAX_NUMNODES; j++) {
-			cpumask_t tmp, notcovered;
-			int n = (i + j) % MAX_NUMNODES;
-
-			cpus_complement(notcovered, covered);
-			cpus_and(tmp, notcovered, *cpu_map);
-			cpus_and(tmp, tmp, domainspan);
-			if (cpus_empty(tmp))
-				break;
-
-			nodemask = node_to_cpumask(n);
-			cpus_and(tmp, tmp, nodemask);
-			if (cpus_empty(tmp))
-				continue;
-
-			sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL);
-			if (!sg) {
-				printk(KERN_WARNING
-				"Can not alloc domain group for node %d\n", j);
-				break;
-			}
-			sg->cpu_power = 0;
-			sg->cpumask = tmp;
-			cpus_or(covered, covered, tmp);
-			prev->next = sg;
-			prev = sg;
-		}
-		prev->next = sched_group_nodes[i];
-	}
-#endif
-
-	/* Calculate CPU power for physical packages and nodes */
-	for_each_cpu_mask(i, *cpu_map) {
-		int power;
-		struct sched_domain *sd;
-#ifdef CONFIG_SCHED_SMT
-		sd = &per_cpu(cpu_domains, i);
-		power = SCHED_LOAD_SCALE;
-		sd->groups->cpu_power = power;
-#endif
-
-		sd = &per_cpu(phys_domains, i);
-		power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
-				(cpus_weight(sd->groups->cpumask)-1) / 10;
-		sd->groups->cpu_power = power;
-
-#ifdef CONFIG_NUMA
-		sd = &per_cpu(allnodes_domains, i);
-		if (sd->groups) {
-			power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
-				(cpus_weight(sd->groups->cpumask)-1) / 10;
-			sd->groups->cpu_power = power;
-		}
-#endif
-	}
-
-#ifdef CONFIG_NUMA
-	for (i = 0; i < MAX_NUMNODES; i++) {
-		struct sched_group *sg = sched_group_nodes[i];
-		int j;
-
-		if (sg == NULL)
-			continue;
-next_sg:
-		for_each_cpu_mask(j, sg->cpumask) {
-			struct sched_domain *sd;
-			int power;
-
-			sd = &per_cpu(phys_domains, j);
-			if (j != first_cpu(sd->groups->cpumask)) {
-				/*
-				 * Only add "power" once for each
-				 * physical package.
-				 */
-				continue;
-			}
-			power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
-				(cpus_weight(sd->groups->cpumask)-1) / 10;
-
-			sg->cpu_power += power;
-		}
-		sg = sg->next;
-		if (sg != sched_group_nodes[i])
-			goto next_sg;
-	}
-#endif
-
-	/* Attach the domains */
-	for_each_cpu_mask(i, *cpu_map) {
-		struct sched_domain *sd;
-#ifdef CONFIG_SCHED_SMT
-		sd = &per_cpu(cpu_domains, i);
-#else
-		sd = &per_cpu(phys_domains, i);
-#endif
-		cpu_attach_domain(sd, i);
-	}
-}
-/*
- * Set up scheduler domains and groups.  Callers must hold the hotplug lock.
- */
-void arch_init_sched_domains(const cpumask_t *cpu_map)
-{
-	cpumask_t cpu_default_map;
-
-	/*
-	 * Setup mask for cpus without special case scheduling requirements.
-	 * For now this just excludes isolated cpus, but could be used to
-	 * exclude other special cases in the future.
-	 */
-	cpus_andnot(cpu_default_map, *cpu_map, cpu_isolated_map);
-
-	build_sched_domains(&cpu_default_map);
-}
-
-void arch_destroy_sched_domains(const cpumask_t *cpu_map)
-{
-#ifdef CONFIG_NUMA
-	int i;
-	for (i = 0; i < MAX_NUMNODES; i++) {
-		cpumask_t nodemask = node_to_cpumask(i);
-		struct sched_group *oldsg, *sg = sched_group_nodes[i];
-
-		cpus_and(nodemask, nodemask, *cpu_map);
-		if (cpus_empty(nodemask))
-			continue;
-
-		if (sg == NULL)
-			continue;
-		sg = sg->next;
-next_sg:
-		oldsg = sg;
-		sg = sg->next;
-		kfree(oldsg);
-		if (oldsg != sched_group_nodes[i])
-			goto next_sg;
-		sched_group_nodes[i] = NULL;
-	}
-#endif
-}
-
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index 28f2aadc38d0..205d98028261 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -91,23 +91,8 @@ skip:
 }
 
 #ifdef CONFIG_SMP
-/*
- * This is updated when the user sets irq affinity via /proc
- */
-static cpumask_t __cacheline_aligned pending_irq_cpumask[NR_IRQS];
-static unsigned long pending_irq_redir[BITS_TO_LONGS(NR_IRQS)];
-
 static char irq_redir [NR_IRQS]; // = { [0 ... NR_IRQS-1] = 1 };
 
-/*
- * Arch specific routine for deferred write to iosapic rte to reprogram
- * intr destination.
- */
-void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val)
-{
-	pending_irq_cpumask[irq] = mask_val;
-}
-
 void set_irq_affinity_info (unsigned int irq, int hwid, int redir)
 {
 	cpumask_t mask = CPU_MASK_NONE;
@@ -116,32 +101,10 @@ void set_irq_affinity_info (unsigned int irq, int hwid, int redir)
 
 	if (irq < NR_IRQS) {
 		irq_affinity[irq] = mask;
+		set_irq_info(irq, mask);
 		irq_redir[irq] = (char) (redir & 0xff);
 	}
 }
-
-
-void move_irq(int irq)
-{
-	/* note - we hold desc->lock */
-	cpumask_t tmp;
-	irq_desc_t *desc = irq_descp(irq);
-	int redir = test_bit(irq, pending_irq_redir);
-
-	if (unlikely(!desc->handler->set_affinity))
-		return;
-
-	if (!cpus_empty(pending_irq_cpumask[irq])) {
-		cpus_and(tmp, pending_irq_cpumask[irq], cpu_online_map);
-		if (unlikely(!cpus_empty(tmp))) {
-			desc->handler->set_affinity(irq | (redir ? IA64_IRQ_REDIRECTED : 0),
-						    pending_irq_cpumask[irq]);
-		}
-		cpus_clear(pending_irq_cpumask[irq]);
-	}
-}
-
-
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/ia64/kernel/jprobes.S b/arch/ia64/kernel/jprobes.S
index b7fa3ccd2b0f..2323377e3695 100644
--- a/arch/ia64/kernel/jprobes.S
+++ b/arch/ia64/kernel/jprobes.S
@@ -49,6 +49,7 @@
 	/*
 	 * void jprobe_break(void)
 	 */
+	.section .kprobes.text, "ax"
 ENTRY(jprobe_break)
 	break.m 0x80300
 END(jprobe_break)
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 884f5cd27d8a..471086b808a4 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -87,12 +87,25 @@ static enum instruction_type bundle_encoding[32][3] = {
  * is IP relative instruction and update the kprobe
  * inst flag accordingly
  */
-static void update_kprobe_inst_flag(uint template, uint  slot, uint major_opcode,
-	unsigned long kprobe_inst, struct kprobe *p)
+static void __kprobes update_kprobe_inst_flag(uint template, uint  slot,
+					      uint major_opcode,
+					      unsigned long kprobe_inst,
+					      struct kprobe *p)
 {
 	p->ainsn.inst_flag = 0;
 	p->ainsn.target_br_reg = 0;
 
+	/* Check for Break instruction
+ 	 * Bits 37:40 Major opcode to be zero
+	 * Bits 27:32 X6 to be zero
+	 * Bits 32:35 X3 to be zero
+	 */
+	if ((!major_opcode) && (!((kprobe_inst >> 27) & 0x1FF)) ) {
+		/* is a break instruction */
+	 	p->ainsn.inst_flag |= INST_FLAG_BREAK_INST;
+		return;
+	}
+
 	if (bundle_encoding[template][slot] == B) {
 		switch (major_opcode) {
 		  case INDIRECT_CALL_OPCODE:
@@ -126,8 +139,10 @@ static void update_kprobe_inst_flag(uint template, uint  slot, uint major_opcode
  * Returns 0 if supported
  * Returns -EINVAL if unsupported
  */
-static int unsupported_inst(uint template, uint  slot, uint major_opcode,
-	unsigned long kprobe_inst, struct kprobe *p)
+static int __kprobes unsupported_inst(uint template, uint  slot,
+				      uint major_opcode,
+				      unsigned long kprobe_inst,
+				      struct kprobe *p)
 {
 	unsigned long addr = (unsigned long)p->addr;
 
@@ -168,8 +183,9 @@ static int unsupported_inst(uint template, uint  slot, uint major_opcode,
  * on which we are inserting kprobe is cmp instruction
  * with ctype as unc.
  */
-static uint is_cmp_ctype_unc_inst(uint template, uint slot, uint major_opcode,
-unsigned long kprobe_inst)
+static uint __kprobes is_cmp_ctype_unc_inst(uint template, uint slot,
+					    uint major_opcode,
+					    unsigned long kprobe_inst)
 {
 	cmp_inst_t cmp_inst;
 	uint ctype_unc = 0;
@@ -201,8 +217,10 @@ out:
  * In this function we override the bundle with
  * the break instruction at the given slot.
  */
-static void prepare_break_inst(uint template, uint  slot, uint major_opcode,
-	unsigned long kprobe_inst, struct kprobe *p)
+static void __kprobes prepare_break_inst(uint template, uint  slot,
+					 uint major_opcode,
+					 unsigned long kprobe_inst,
+					 struct kprobe *p)
 {
 	unsigned long break_inst = BREAK_INST;
 	bundle_t *bundle = &p->ainsn.insn.bundle;
@@ -271,7 +289,8 @@ static inline int in_ivt_functions(unsigned long addr)
 		&& addr < (unsigned long)__end_ivt_text);
 }
 
-static int valid_kprobe_addr(int template, int slot, unsigned long addr)
+static int __kprobes valid_kprobe_addr(int template, int slot,
+				       unsigned long addr)
 {
 	if ((slot > 2) || ((bundle_encoding[template][1] == L) && slot > 1)) {
 		printk(KERN_WARNING "Attempting to insert unaligned kprobe "
@@ -323,7 +342,7 @@ static void kretprobe_trampoline(void)
  *    - cleanup by marking the instance as unused
  *    - long jump back to the original return address
  */
-int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head;
@@ -381,7 +400,8 @@ int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
         return 1;
 }
 
-void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
+void __kprobes arch_prepare_kretprobe(struct kretprobe *rp,
+				      struct pt_regs *regs)
 {
 	struct kretprobe_instance *ri;
 
@@ -399,7 +419,7 @@ void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
 	}
 }
 
-int arch_prepare_kprobe(struct kprobe *p)
+int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
 	unsigned long addr = (unsigned long) p->addr;
 	unsigned long *kprobe_addr = (unsigned long *)(addr & ~0xFULL);
@@ -430,7 +450,7 @@ int arch_prepare_kprobe(struct kprobe *p)
 	return 0;
 }
 
-void arch_arm_kprobe(struct kprobe *p)
+void __kprobes arch_arm_kprobe(struct kprobe *p)
 {
 	unsigned long addr = (unsigned long)p->addr;
 	unsigned long arm_addr = addr & ~0xFULL;
@@ -439,7 +459,7 @@ void arch_arm_kprobe(struct kprobe *p)
 	flush_icache_range(arm_addr, arm_addr + sizeof(bundle_t));
 }
 
-void arch_disarm_kprobe(struct kprobe *p)
+void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
 	unsigned long addr = (unsigned long)p->addr;
 	unsigned long arm_addr = addr & ~0xFULL;
@@ -449,7 +469,7 @@ void arch_disarm_kprobe(struct kprobe *p)
 	flush_icache_range(arm_addr, arm_addr + sizeof(bundle_t));
 }
 
-void arch_remove_kprobe(struct kprobe *p)
+void __kprobes arch_remove_kprobe(struct kprobe *p)
 {
 }
 
@@ -461,7 +481,7 @@ void arch_remove_kprobe(struct kprobe *p)
  * to original stack address, handle the case where we need to fixup the
  * relative IP address and/or fixup branch register.
  */
-static void resume_execution(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
 {
   	unsigned long bundle_addr = ((unsigned long) (&p->opcode.bundle)) & ~0xFULL;
   	unsigned long resume_addr = (unsigned long)p->addr & ~0xFULL;
@@ -528,13 +548,16 @@ turn_ss_off:
   	ia64_psr(regs)->ss = 0;
 }
 
-static void prepare_ss(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes prepare_ss(struct kprobe *p, struct pt_regs *regs)
 {
 	unsigned long bundle_addr = (unsigned long) &p->opcode.bundle;
 	unsigned long slot = (unsigned long)p->addr & 0xf;
 
-	/* Update instruction pointer (IIP) and slot number (IPSR.ri) */
-	regs->cr_iip = bundle_addr & ~0xFULL;
+	/* single step inline if break instruction */
+	if (p->ainsn.inst_flag == INST_FLAG_BREAK_INST)
+		regs->cr_iip = (unsigned long)p->addr & ~0xFULL;
+	else
+		regs->cr_iip = bundle_addr & ~0xFULL;
 
 	if (slot > 2)
 		slot = 0;
@@ -545,7 +568,39 @@ static void prepare_ss(struct kprobe *p, struct pt_regs *regs)
 	ia64_psr(regs)->ss = 1;
 }
 
-static int pre_kprobes_handler(struct die_args *args)
+static int __kprobes is_ia64_break_inst(struct pt_regs *regs)
+{
+	unsigned int slot = ia64_psr(regs)->ri;
+	unsigned int template, major_opcode;
+	unsigned long kprobe_inst;
+	unsigned long *kprobe_addr = (unsigned long *)regs->cr_iip;
+	bundle_t bundle;
+
+	memcpy(&bundle, kprobe_addr, sizeof(bundle_t));
+	template = bundle.quad0.template;
+
+	/* Move to slot 2, if bundle is MLX type and kprobe slot is 1 */
+	if (slot == 1 && bundle_encoding[template][1] == L)
+  		slot++;
+
+	/* Get Kprobe probe instruction at given slot*/
+	get_kprobe_inst(&bundle, slot, &kprobe_inst, &major_opcode);
+
+	/* For break instruction,
+	 * Bits 37:40 Major opcode to be zero
+	 * Bits 27:32 X6 to be zero
+	 * Bits 32:35 X3 to be zero
+	 */
+	if (major_opcode || ((kprobe_inst >> 27) & 0x1FF) ) {
+		/* Not a break instruction */
+		return 0;
+	}
+
+	/* Is a break instruction */
+	return 1;
+}
+
+static int __kprobes pre_kprobes_handler(struct die_args *args)
 {
 	struct kprobe *p;
 	int ret = 0;
@@ -558,7 +613,9 @@ static int pre_kprobes_handler(struct die_args *args)
 	if (kprobe_running()) {
 		p = get_kprobe(addr);
 		if (p) {
-			if (kprobe_status == KPROBE_HIT_SS) {
+			if ( (kprobe_status == KPROBE_HIT_SS) &&
+	 		     (p->ainsn.inst_flag == INST_FLAG_BREAK_INST)) {
+  				ia64_psr(regs)->ss = 0;
 				unlock_kprobes();
 				goto no_kprobe;
 			}
@@ -592,6 +649,19 @@ static int pre_kprobes_handler(struct die_args *args)
 	p = get_kprobe(addr);
 	if (!p) {
 		unlock_kprobes();
+		if (!is_ia64_break_inst(regs)) {
+			/*
+			 * The breakpoint instruction was removed right
+			 * after we hit it.  Another cpu has removed
+			 * either a probepoint or a debugger breakpoint
+			 * at this address.  In either case, no further
+			 * handling of this interrupt is appropriate.
+			 */
+			ret = 1;
+
+		}
+
+		/* Not one of our break, let kernel handle it */
 		goto no_kprobe;
 	}
 
@@ -616,7 +686,7 @@ no_kprobe:
 	return ret;
 }
 
-static int post_kprobes_handler(struct pt_regs *regs)
+static int __kprobes post_kprobes_handler(struct pt_regs *regs)
 {
 	if (!kprobe_running())
 		return 0;
@@ -641,7 +711,7 @@ out:
 	return 1;
 }
 
-static int kprobes_fault_handler(struct pt_regs *regs, int trapnr)
+static int __kprobes kprobes_fault_handler(struct pt_regs *regs, int trapnr)
 {
 	if (!kprobe_running())
 		return 0;
@@ -659,8 +729,8 @@ static int kprobes_fault_handler(struct pt_regs *regs, int trapnr)
 	return 0;
 }
 
-int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
-			     void *data)
+int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
+				       unsigned long val, void *data)
 {
 	struct die_args *args = (struct die_args *)data;
 	switch(val) {
@@ -681,7 +751,7 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
 	return NOTIFY_DONE;
 }
 
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
+int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct jprobe *jp = container_of(p, struct jprobe, kp);
 	unsigned long addr = ((struct fnptr *)(jp->entry))->ip;
@@ -703,7 +773,7 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	return 1;
 }
 
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
+int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	*regs = jprobe_saved_regs;
 	return 1;
diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c
index 4440c8343fa4..f970359e7edf 100644
--- a/arch/ia64/kernel/traps.c
+++ b/arch/ia64/kernel/traps.c
@@ -15,6 +15,7 @@
 #include <linux/vt_kern.h>		/* For unblank_screen() */
 #include <linux/module.h>       /* for EXPORT_SYMBOL */
 #include <linux/hardirq.h>
+#include <linux/kprobes.h>
 
 #include <asm/fpswa.h>
 #include <asm/ia32.h>
@@ -122,7 +123,7 @@ die_if_kernel (char *str, struct pt_regs *regs, long err)
 }
 
 void
-ia64_bad_break (unsigned long break_num, struct pt_regs *regs)
+__kprobes ia64_bad_break (unsigned long break_num, struct pt_regs *regs)
 {
 	siginfo_t siginfo;
 	int sig, code;
@@ -444,7 +445,7 @@ ia64_illegal_op_fault (unsigned long ec, long arg1, long arg2, long arg3,
 	return rv;
 }
 
-void
+void __kprobes
 ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
 	    unsigned long iim, unsigned long itir, long arg5, long arg6,
 	    long arg7, struct pt_regs regs)
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index a676e79e0681..30d8564e9603 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -48,6 +48,7 @@ SECTIONS
 	*(.text)
 	SCHED_TEXT
 	LOCK_TEXT
+	KPROBES_TEXT
 	*(.gnu.linkonce.t*)
     }
   .text2 : AT(ADDR(.text2) - LOAD_OFFSET)
diff --git a/arch/ia64/lib/flush.S b/arch/ia64/lib/flush.S
index 3e2cfa2c6d39..2a0d27f2f21b 100644
--- a/arch/ia64/lib/flush.S
+++ b/arch/ia64/lib/flush.S
@@ -20,6 +20,7 @@
 	 *
 	 *	Note: "in0" and "in1" are preserved for debugging purposes.
 	 */
+	.section .kprobes.text,"ax"
 GLOBAL_ENTRY(flush_icache_range)
 
 	.prologue
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index ff62551eb3a1..24614869e866 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/smp_lock.h>
 #include <linux/interrupt.h>
+#include <linux/kprobes.h>
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -76,7 +77,7 @@ mapped_kernel_page_is_present (unsigned long address)
 	return pte_present(pte);
 }
 
-void
+void __kprobes
 ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *regs)
 {
 	int signal = SIGSEGV, code = SEGV_MAPERR;
diff --git a/arch/ia64/sn/kernel/io_init.c b/arch/ia64/sn/kernel/io_init.c
index 4564ed0b5ff3..906622d9f933 100644
--- a/arch/ia64/sn/kernel/io_init.c
+++ b/arch/ia64/sn/kernel/io_init.c
@@ -431,7 +431,7 @@ void sn_bus_store_sysdata(struct pci_dev *dev)
 {
 	struct sysdata_el *element;
 
-	element = kcalloc(1, sizeof(struct sysdata_el), GFP_KERNEL);
+	element = kzalloc(sizeof(struct sysdata_el), GFP_KERNEL);
 	if (!element) {
 		dev_dbg(dev, "%s: out of memory!\n", __FUNCTION__);
 		return;
diff --git a/arch/ia64/sn/kernel/tiocx.c b/arch/ia64/sn/kernel/tiocx.c
index 254fe15c064b..b45db5133f55 100644
--- a/arch/ia64/sn/kernel/tiocx.c
+++ b/arch/ia64/sn/kernel/tiocx.c
@@ -191,7 +191,7 @@ cx_device_register(nasid_t nasid, int part_num, int mfg_num,
 {
 	struct cx_dev *cx_dev;
 
-	cx_dev = kcalloc(1, sizeof(struct cx_dev), GFP_KERNEL);
+	cx_dev = kzalloc(sizeof(struct cx_dev), GFP_KERNEL);
 	DBG("cx_dev= 0x%p\n", cx_dev);
 	if (cx_dev == NULL)
 		return -ENOMEM;
diff --git a/arch/ia64/sn/pci/tioca_provider.c b/arch/ia64/sn/pci/tioca_provider.c
index ea09c12f0258..19bced34d5f1 100644
--- a/arch/ia64/sn/pci/tioca_provider.c
+++ b/arch/ia64/sn/pci/tioca_provider.c
@@ -148,7 +148,7 @@ tioca_gart_init(struct tioca_kernel *tioca_kern)
 	tioca_kern->ca_pcigart_entries =
 	    tioca_kern->ca_pciap_size / tioca_kern->ca_ap_pagesize;
 	tioca_kern->ca_pcigart_pagemap =
-	    kcalloc(1, tioca_kern->ca_pcigart_entries / 8, GFP_KERNEL);
+	    kzalloc(tioca_kern->ca_pcigart_entries / 8, GFP_KERNEL);
 	if (!tioca_kern->ca_pcigart_pagemap) {
 		free_pages((unsigned long)tioca_kern->ca_gart,
 			   get_order(tioca_kern->ca_gart_size));
@@ -392,7 +392,7 @@ tioca_dma_mapped(struct pci_dev *pdev, uint64_t paddr, size_t req_size)
 	 * allocate a map struct
 	 */
 
-	ca_dmamap = kcalloc(1, sizeof(struct tioca_dmamap), GFP_ATOMIC);
+	ca_dmamap = kzalloc(sizeof(struct tioca_dmamap), GFP_ATOMIC);
 	if (!ca_dmamap)
 		goto map_return;
 
@@ -600,7 +600,7 @@ tioca_bus_fixup(struct pcibus_bussoft *prom_bussoft, struct pci_controller *cont
 	 * Allocate kernel bus soft and copy from prom.
 	 */
 
-	tioca_common = kcalloc(1, sizeof(struct tioca_common), GFP_KERNEL);
+	tioca_common = kzalloc(sizeof(struct tioca_common), GFP_KERNEL);
 	if (!tioca_common)
 		return NULL;
 
@@ -609,7 +609,7 @@ tioca_bus_fixup(struct pcibus_bussoft *prom_bussoft, struct pci_controller *cont
 
 	/* init kernel-private area */
 
-	tioca_kern = kcalloc(1, sizeof(struct tioca_kernel), GFP_KERNEL);
+	tioca_kern = kzalloc(sizeof(struct tioca_kernel), GFP_KERNEL);
 	if (!tioca_kern) {
 		kfree(tioca_common);
 		return NULL;