Merge commit 'block/for-next'

Conflicts:

	arch/powerpc/Kconfig
	arch/x86/kernel/apic_32.c
	arch/x86/kernel/i8259_64.c
	arch/x86/xen/smp.c
	include/asm-x86/hw_irq_32.h
	include/asm-x86/hw_irq_64.h
	include/asm-x86/mach-default/irq_vectors.h
	include/asm-x86/mach-voyager/irq_vectors.h
	kernel/Makefile

36 files changed, 245 insertions, 1518 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 3ea332b009e5..ad89a33d8c6e 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -39,3 +39,6 @@ config HAVE_KRETPROBES
 
 config HAVE_DMA_ATTRS
 	def_bool n
+
+config USE_GENERIC_SMP_HELPERS
+	def_bool n
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 729cdbdf8036..dbe8c280fea9 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -528,6 +528,7 @@ config ARCH_MAY_HAVE_PC_FDC
 config SMP
 	bool "Symmetric multi-processing support"
 	depends on ALPHA_SABLE || ALPHA_LYNX || ALPHA_RAWHIDE || ALPHA_DP264 || ALPHA_WILDFIRE || ALPHA_TITAN || ALPHA_GENERIC || ALPHA_SHARK || ALPHA_MARVEL
+	select USE_GENERIC_SMP_HELPERS
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c
index b04f1feb1dda..ced4aae8b804 100644
--- a/arch/alpha/kernel/core_marvel.c
+++ b/arch/alpha/kernel/core_marvel.c
@@ -660,9 +660,9 @@ __marvel_rtc_io(u8 b, unsigned long addr, int write)
 
 #ifdef CONFIG_SMP
 		if (smp_processor_id() != boot_cpuid)
-			smp_call_function_on_cpu(__marvel_access_rtc,
-						 &rtc_access, 1, 1,
-						 cpumask_of_cpu(boot_cpuid));
+			smp_call_function_single(boot_cpuid,
+						 __marvel_access_rtc,
+						 &rtc_access, 1, 1);
 		else
 			__marvel_access_rtc(&rtc_access);
 #else
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 2525692db0ab..95c905be9154 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -62,6 +62,7 @@ static struct {
 enum ipi_message_type {
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
+	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP,
 };
 
@@ -558,51 +559,6 @@ send_ipi_message(cpumask_t to_whom, enum ipi_message_type operation)
 		wripir(i);
 }
 
-/* Structure and data for smp_call_function.  This is designed to 
-   minimize static memory requirements.  Plus it looks cleaner.  */
-
-struct smp_call_struct {
-	void (*func) (void *info);
-	void *info;
-	long wait;
-	atomic_t unstarted_count;
-	atomic_t unfinished_count;
-};
-
-static struct smp_call_struct *smp_call_function_data;
-
-/* Atomicly drop data into a shared pointer.  The pointer is free if
-   it is initially locked.  If retry, spin until free.  */
-
-static int
-pointer_lock (void *lock, void *data, int retry)
-{
-	void *old, *tmp;
-
-	mb();
- again:
-	/* Compare and swap with zero.  */
-	asm volatile (
-	"1:	ldq_l	%0,%1\n"
-	"	mov	%3,%2\n"
-	"	bne	%0,2f\n"
-	"	stq_c	%2,%1\n"
-	"	beq	%2,1b\n"
-	"2:"
-	: "=&r"(old), "=m"(*(void **)lock), "=&r"(tmp)
-	: "r"(data)
-	: "memory");
-
-	if (old == 0)
-		return 0;
-	if (! retry)
-		return -EBUSY;
-
-	while (*(void **)lock)
-		barrier();
-	goto again;
-}
-
 void
 handle_ipi(struct pt_regs *regs)
 {
@@ -632,31 +588,12 @@ handle_ipi(struct pt_regs *regs)
 			break;
 
 		case IPI_CALL_FUNC:
-		    {
-			struct smp_call_struct *data;
-			void (*func)(void *info);
-			void *info;
-			int wait;
-
-			data = smp_call_function_data;
-			func = data->func;
-			info = data->info;
-			wait = data->wait;
-
-			/* Notify the sending CPU that the data has been
-			   received, and execution is about to begin.  */
-			mb();
-			atomic_dec (&data->unstarted_count);
-
-			/* At this point the structure may be gone unless
-			   wait is true.  */
-			(*func)(info);
-
-			/* Notify the sending CPU that the task is done.  */
-			mb();
-			if (wait) atomic_dec (&data->unfinished_count);
+			generic_smp_call_function_interrupt();
+			break;
+
+		case IPI_CALL_FUNC_SINGLE:
+			generic_smp_call_function_single_interrupt();
 			break;
-		    }
 
 		case IPI_CPU_STOP:
 			halt();
@@ -700,102 +637,15 @@ smp_send_stop(void)
 	send_ipi_message(to_whom, IPI_CPU_STOP);
 }
 
-/*
- * Run a function on all other CPUs.
- *  <func>	The function to run. This must be fast and non-blocking.
- *  <info>	An arbitrary pointer to pass to the function.
- *  <retry>	If true, keep retrying until ready.
- *  <wait>	If true, wait until function has completed on other CPUs.
- *  [RETURNS]   0 on success, else a negative status code.
- *
- * Does not return until remote CPUs are nearly ready to execute <func>
- * or are or have executed.
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-
-int
-smp_call_function_on_cpu (void (*func) (void *info), void *info, int retry,
-			  int wait, cpumask_t to_whom)
+void arch_send_call_function_ipi(cpumask_t mask)
 {
-	struct smp_call_struct data;
-	unsigned long timeout;
-	int num_cpus_to_call;
-	
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	data.func = func;
-	data.info = info;
-	data.wait = wait;
-
-	cpu_clear(smp_processor_id(), to_whom);
-	num_cpus_to_call = cpus_weight(to_whom);
-
-	atomic_set(&data.unstarted_count, num_cpus_to_call);
-	atomic_set(&data.unfinished_count, num_cpus_to_call);
-
-	/* Acquire the smp_call_function_data mutex.  */
-	if (pointer_lock(&smp_call_function_data, &data, retry))
-		return -EBUSY;
-
-	/* Send a message to the requested CPUs.  */
-	send_ipi_message(to_whom, IPI_CALL_FUNC);
-
-	/* Wait for a minimal response.  */
-	timeout = jiffies + HZ;
-	while (atomic_read (&data.unstarted_count) > 0
-	       && time_before (jiffies, timeout))
-		barrier();
-
-	/* If there's no response yet, log a message but allow a longer
-	 * timeout period -- if we get a response this time, log
-	 * a message saying when we got it.. 
-	 */
-	if (atomic_read(&data.unstarted_count) > 0) {
-		long start_time = jiffies;
-		printk(KERN_ERR "%s: initial timeout -- trying long wait\n",
-		       __func__);
-		timeout = jiffies + 30 * HZ;
-		while (atomic_read(&data.unstarted_count) > 0
-		       && time_before(jiffies, timeout))
-			barrier();
-		if (atomic_read(&data.unstarted_count) <= 0) {
-			long delta = jiffies - start_time;
-			printk(KERN_ERR 
-			       "%s: response %ld.%ld seconds into long wait\n",
-			       __func__, delta / HZ,
-			       (100 * (delta - ((delta / HZ) * HZ))) / HZ);
-		}
-	}
-
-	/* We either got one or timed out -- clear the lock. */
-	mb();
-	smp_call_function_data = NULL;
-
-	/* 
-	 * If after both the initial and long timeout periods we still don't
-	 * have a response, something is very wrong...
-	 */
-	BUG_ON(atomic_read (&data.unstarted_count) > 0);
-
-	/* Wait for a complete response, if needed.  */
-	if (wait) {
-		while (atomic_read (&data.unfinished_count) > 0)
-			barrier();
-	}
-
-	return 0;
+	send_ipi_message(mask, IPI_CALL_FUNC);
 }
-EXPORT_SYMBOL(smp_call_function_on_cpu);
 
-int
-smp_call_function (void (*func) (void *info), void *info, int retry, int wait)
+void arch_send_call_function_single_ipi(int cpu)
 {
-	return smp_call_function_on_cpu (func, info, retry, wait,
-					 cpu_online_map);
+	send_ipi_message(cpumask_of_cpu(cpu), IPI_CALL_FUNC_SINGLE);
 }
-EXPORT_SYMBOL(smp_call_function);
 
 static void
 ipi_imb(void *ignored)
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index ca65945970f6..621b7d3b9324 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -648,6 +648,7 @@ source "kernel/time/Kconfig"
 config SMP
 	bool "Symmetric Multi-Processing (EXPERIMENTAL)"
 	depends on EXPERIMENTAL && (REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP)
+	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index eefae1de334c..6344466b2113 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -68,20 +68,10 @@ enum ipi_msg_type {
 	IPI_TIMER,
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
+	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP,
 };
 
-struct smp_call_struct {
-	void (*func)(void *info);
-	void *info;
-	int wait;
-	cpumask_t pending;
-	cpumask_t unfinished;
-};
-
-static struct smp_call_struct * volatile smp_call_function_data;
-static DEFINE_SPINLOCK(smp_call_function_lock);
-
 int __cpuinit __cpu_up(unsigned int cpu)
 {
 	struct cpuinfo_arm *ci = &per_cpu(cpu_data, cpu);
@@ -366,114 +356,15 @@ static void send_ipi_message(cpumask_t callmap, enum ipi_msg_type msg)
 	local_irq_restore(flags);
 }
 
-/*
- * You must not call this function with disabled interrupts, from a
- * hardware interrupt handler, nor from a bottom half handler.
- */
-static int smp_call_function_on_cpu(void (*func)(void *info), void *info,
-				    int retry, int wait, cpumask_t callmap)
-{
-	struct smp_call_struct data;
-	unsigned long timeout;
-	int ret = 0;
-
-	data.func = func;
-	data.info = info;
-	data.wait = wait;
-
-	cpu_clear(smp_processor_id(), callmap);
-	if (cpus_empty(callmap))
-		goto out;
-
-	data.pending = callmap;
-	if (wait)
-		data.unfinished = callmap;
-
-	/*
-	 * try to get the mutex on smp_call_function_data
-	 */
-	spin_lock(&smp_call_function_lock);
-	smp_call_function_data = &data;
-
-	send_ipi_message(callmap, IPI_CALL_FUNC);
-
-	timeout = jiffies + HZ;
-	while (!cpus_empty(data.pending) && time_before(jiffies, timeout))
-		barrier();
-
-	/*
-	 * did we time out?
-	 */
-	if (!cpus_empty(data.pending)) {
-		/*
-		 * this may be causing our panic - report it
-		 */
-		printk(KERN_CRIT
-		       "CPU%u: smp_call_function timeout for %p(%p)\n"
-		       "      callmap %lx pending %lx, %swait\n",
-		       smp_processor_id(), func, info, *cpus_addr(callmap),
-		       *cpus_addr(data.pending), wait ? "" : "no ");
-
-		/*
-		 * TRACE
-		 */
-		timeout = jiffies + (5 * HZ);
-		while (!cpus_empty(data.pending) && time_before(jiffies, timeout))
-			barrier();
-
-		if (cpus_empty(data.pending))
-			printk(KERN_CRIT "     RESOLVED\n");
-		else
-			printk(KERN_CRIT "     STILL STUCK\n");
-	}
-
-	/*
-	 * whatever happened, we're done with the data, so release it
-	 */
-	smp_call_function_data = NULL;
-	spin_unlock(&smp_call_function_lock);
-
-	if (!cpus_empty(data.pending)) {
-		ret = -ETIMEDOUT;
-		goto out;
-	}
-
-	if (wait)
-		while (!cpus_empty(data.unfinished))
-			barrier();
- out:
-
-	return 0;
-}
-
-int smp_call_function(void (*func)(void *info), void *info, int retry,
-                      int wait)
+void arch_send_call_function_ipi(cpumask_t mask)
 {
-	return smp_call_function_on_cpu(func, info, retry, wait,
-					cpu_online_map);
+	send_ipi_message(mask, IPI_CALL_FUNC);
 }
-EXPORT_SYMBOL_GPL(smp_call_function);
 
-int smp_call_function_single(int cpu, void (*func)(void *info), void *info,
-			     int retry, int wait)
+void arch_send_call_function_single_ipi(int cpu)
 {
-	/* prevent preemption and reschedule on another processor */
-	int current_cpu = get_cpu();
-	int ret = 0;
-
-	if (cpu == current_cpu) {
-		local_irq_disable();
-		func(info);
-		local_irq_enable();
-	} else
-		ret = smp_call_function_on_cpu(func, info, retry, wait,
-					       cpumask_of_cpu(cpu));
-
-	put_cpu();
-
-	return ret;
+	send_ipi_message(cpumask_of_cpu(cpu), IPI_CALL_FUNC_SINGLE);
 }
-EXPORT_SYMBOL_GPL(smp_call_function_single);
 
 void show_ipi_list(struct seq_file *p)
 {
@@ -521,27 +412,6 @@ asmlinkage void __exception do_local_timer(struct pt_regs *regs)
 }
 #endif
 
-/*
- * ipi_call_function - handle IPI from smp_call_function()
- *
- * Note that we copy data out of the cross-call structure and then
- * let the caller know that we're here and have done with their data
- */
-static void ipi_call_function(unsigned int cpu)
-{
-	struct smp_call_struct *data = smp_call_function_data;
-	void (*func)(void *info) = data->func;
-	void *info = data->info;
-	int wait = data->wait;
-
-	cpu_clear(cpu, data->pending);
-
-	func(info);
-
-	if (wait)
-		cpu_clear(cpu, data->unfinished);
-}
-
 static DEFINE_SPINLOCK(stop_lock);
 
 /*
@@ -611,7 +481,11 @@ asmlinkage void __exception do_IPI(struct pt_regs *regs)
 				break;
 
 			case IPI_CALL_FUNC:
-				ipi_call_function(cpu);
+				generic_smp_call_function_interrupt();
+				break;
+
+			case IPI_CALL_FUNC_SINGLE:
+				generic_smp_call_function_single_interrupt();
 				break;
 
 			case IPI_CPU_STOP:
@@ -662,14 +536,13 @@ int setup_profiling_timer(unsigned int multiplier)
 }
 
 static int
-on_each_cpu_mask(void (*func)(void *), void *info, int retry, int wait,
-		 cpumask_t mask)
+on_each_cpu_mask(void (*func)(void *), void *info, int wait, cpumask_t mask)
 {
 	int ret = 0;
 
 	preempt_disable();
 
-	ret = smp_call_function_on_cpu(func, info, retry, wait, mask);
+	ret = smp_call_function_mask(mask, func, info, wait);
 	if (cpu_isset(smp_processor_id(), mask))
 		func(info);
 
@@ -738,7 +611,7 @@ void flush_tlb_mm(struct mm_struct *mm)
 {
 	cpumask_t mask = mm->cpu_vm_mask;
 
-	on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, 1, mask);
+	on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mask);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
@@ -749,7 +622,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 	ta.ta_vma = vma;
 	ta.ta_start = uaddr;
 
-	on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, 1, mask);
+	on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mask);
 }
 
 void flush_tlb_kernel_page(unsigned long kaddr)
@@ -771,7 +644,7 @@ void flush_tlb_range(struct vm_area_struct *vma,
 	ta.ta_start = start;
 	ta.ta_end = end;
 
-	on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, 1, mask);
+	on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, mask);
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 16be41446b5b..18bcc10903b4 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -303,6 +303,7 @@ config VIRT_CPU_ACCOUNTING
 
 config SMP
 	bool "Symmetric multi-processing support"
+	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, say N.  If you have a system with more
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index 983296f1c813..70b7b35c224b 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -60,25 +60,9 @@ static struct local_tlb_flush_counts {
 
 static DEFINE_PER_CPU(unsigned int, shadow_flush_counts[NR_CPUS]) ____cacheline_aligned;
 
-
-/*
- * Structure and data for smp_call_function(). This is designed to minimise static memory
- * requirements. It also looks cleaner.
- */
-static  __cacheline_aligned DEFINE_SPINLOCK(call_lock);
-
-struct call_data_struct {
-	void (*func) (void *info);
-	void *info;
-	long wait;
-	atomic_t started;
-	atomic_t finished;
-};
-
-static volatile struct call_data_struct *call_data;
-
 #define IPI_CALL_FUNC		0
 #define IPI_CPU_STOP		1
+#define IPI_CALL_FUNC_SINGLE	2
 #define IPI_KDUMP_CPU_STOP	3
 
 /* This needs to be cacheline aligned because it is written to by *other* CPUs.  */
@@ -89,38 +73,13 @@ extern void cpu_halt (void);
 void
 lock_ipi_calllock(void)
 {
-	spin_lock_irq(&call_lock);
+	spin_lock_irq(&call_function_lock);
 }
 
 void
 unlock_ipi_calllock(void)
 {
-	spin_unlock_irq(&call_lock);
-}
-
-static inline void
-handle_call_data(void)
-{
-	struct call_data_struct *data;
-	void (*func)(void *info);
-	void *info;
-	int wait;
-
-	/* release the 'pointer lock' */
-	data = (struct call_data_struct *)call_data;
-	func = data->func;
-	info = data->info;
-	wait = data->wait;
-
-	mb();
-	atomic_inc(&data->started);
-	/* At this point the structure may be gone unless wait is true. */
-	(*func)(info);
-
-	/* Notify the sending CPU that the task is done. */
-	mb();
-	if (wait)
-		atomic_inc(&data->finished);
+	spin_unlock_irq(&call_function_lock);
 }
 
 static void
@@ -163,13 +122,15 @@ handle_IPI (int irq, void *dev_id)
 			ops &= ~(1 << which);
 
 			switch (which) {
-			case IPI_CALL_FUNC:
-				handle_call_data();
-				break;
-
 			case IPI_CPU_STOP:
 				stop_this_cpu();
 				break;
+			case IPI_CALL_FUNC:
+				generic_smp_call_function_interrupt();
+				break;
+			case IPI_CALL_FUNC_SINGLE:
+				generic_smp_call_function_single_interrupt();
+				break;
 #ifdef CONFIG_KEXEC
 			case IPI_KDUMP_CPU_STOP:
 				unw_init_running(kdump_cpu_freeze, NULL);
@@ -187,6 +148,8 @@ handle_IPI (int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+
+
 /*
  * Called with preemption disabled.
  */
@@ -360,190 +323,15 @@ smp_flush_tlb_mm (struct mm_struct *mm)
 	on_each_cpu((void (*)(void *))local_finish_flush_tlb_mm, mm, 1, 1);
 }
 
-/*
- * Run a function on a specific CPU
- *  <func>	The function to run. This must be fast and non-blocking.
- *  <info>	An arbitrary pointer to pass to the function.
- *  <nonatomic>	Currently unused.
- *  <wait>	If true, wait until function has completed on other CPUs.
- *  [RETURNS]   0 on success, else a negative status code.
- *
- * Does not return until the remote CPU is nearly ready to execute <func>
- * or is or has executed.
- */
-
-int
-smp_call_function_single (int cpuid, void (*func) (void *info), void *info, int nonatomic,
-			  int wait)
-{
-	struct call_data_struct data;
-	int cpus = 1;
-	int me = get_cpu(); /* prevent preemption and reschedule on another processor */
-
-	if (cpuid == me) {
-		local_irq_disable();
-		func(info);
-		local_irq_enable();
-		put_cpu();
-		return 0;
-	}
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	spin_lock_bh(&call_lock);
-
-	call_data = &data;
-	mb();	/* ensure store to call_data precedes setting of IPI_CALL_FUNC */
-  	send_IPI_single(cpuid, IPI_CALL_FUNC);
-
-	/* Wait for response */
-	while (atomic_read(&data.started) != cpus)
-		cpu_relax();
-
-	if (wait)
-		while (atomic_read(&data.finished) != cpus)
-			cpu_relax();
-	call_data = NULL;
-
-	spin_unlock_bh(&call_lock);
-	put_cpu();
-	return 0;
-}
-EXPORT_SYMBOL(smp_call_function_single);
-
-/**
- * smp_call_function_mask(): Run a function on a set of other CPUs.
- * <mask>	The set of cpus to run on.  Must not include the current cpu.
- * <func> 	The function to run. This must be fast and non-blocking.
- * <info>	An arbitrary pointer to pass to the function.
- * <wait>	If true, wait (atomically) until function
- *		has completed on other CPUs.
- *
- * Returns 0 on success, else a negative status code.
- *
- * If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-int smp_call_function_mask(cpumask_t mask,
-			   void (*func)(void *), void *info,
-			   int wait)
+void arch_send_call_function_single_ipi(int cpu)
 {
-	struct call_data_struct data;
-	cpumask_t allbutself;
-	int cpus;
-
-	spin_lock(&call_lock);
-	allbutself = cpu_online_map;
-	cpu_clear(smp_processor_id(), allbutself);
-
-	cpus_and(mask, mask, allbutself);
-	cpus = cpus_weight(mask);
-	if (!cpus) {
-		spin_unlock(&call_lock);
-		return 0;
-	}
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	call_data = &data;
-	mb(); /* ensure store to call_data precedes setting of IPI_CALL_FUNC*/
-
-	/* Send a message to other CPUs */
-	if (cpus_equal(mask, allbutself))
-		send_IPI_allbutself(IPI_CALL_FUNC);
-	else
-		send_IPI_mask(mask, IPI_CALL_FUNC);
-
-	/* Wait for response */
-	while (atomic_read(&data.started) != cpus)
-		cpu_relax();
-
-	if (wait)
-		while (atomic_read(&data.finished) != cpus)
-			cpu_relax();
-	call_data = NULL;
-
-	spin_unlock(&call_lock);
-	return 0;
-
+	send_IPI_single(cpu, IPI_CALL_FUNC_SINGLE);
 }
-EXPORT_SYMBOL(smp_call_function_mask);
-
-/*
- * this function sends a 'generic call function' IPI to all other CPUs
- * in the system.
- */
 
-/*
- *  [SUMMARY]	Run a function on all other CPUs.
- *  <func>	The function to run. This must be fast and non-blocking.
- *  <info>	An arbitrary pointer to pass to the function.
- *  <nonatomic>	currently unused.
- *  <wait>	If true, wait (atomically) until function has completed on other CPUs.
- *  [RETURNS]   0 on success, else a negative status code.
- *
- * Does not return until remote CPUs are nearly ready to execute <func> or are or have
- * executed.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-int
-smp_call_function (void (*func) (void *info), void *info, int nonatomic, int wait)
+void arch_send_call_function_ipi(cpumask_t mask)
 {
-	struct call_data_struct data;
-	int cpus;
-
-	spin_lock(&call_lock);
-	cpus = num_online_cpus() - 1;
-	if (!cpus) {
-		spin_unlock(&call_lock);
-		return 0;
-	}
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	call_data = &data;
-	mb();	/* ensure store to call_data precedes setting of IPI_CALL_FUNC */
-	send_IPI_allbutself(IPI_CALL_FUNC);
-
-	/* Wait for response */
-	while (atomic_read(&data.started) != cpus)
-		cpu_relax();
-
-	if (wait)
-		while (atomic_read(&data.finished) != cpus)
-			cpu_relax();
-	call_data = NULL;
-
-	spin_unlock(&call_lock);
-	return 0;
+	send_IPI_mask(mask, IPI_CALL_FUNC);
 }
-EXPORT_SYMBOL(smp_call_function);
 
 /*
  * this function calls the 'stop' function on all other CPUs in the system.
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index de153de2ea9f..a5f864c445b2 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -296,6 +296,7 @@ config PREEMPT
 
 config SMP
 	bool "Symmetric multi-processing support"
+	select USE_GENERIC_SMP_HELPERS
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/m32r/kernel/m32r_ksyms.c b/arch/m32r/kernel/m32r_ksyms.c
index e6709fe950ba..16bcb189a383 100644
--- a/arch/m32r/kernel/m32r_ksyms.c
+++ b/arch/m32r/kernel/m32r_ksyms.c
@@ -43,9 +43,6 @@ EXPORT_SYMBOL(dcache_dummy);
 #endif
 EXPORT_SYMBOL(cpu_data);
 
-/* Global SMP stuff */
-EXPORT_SYMBOL(smp_call_function);
-
 /* TLB flushing */
 EXPORT_SYMBOL(smp_flush_tlb_page);
 #endif
diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c
index c837bc13b015..74eb7bcd5a40 100644
--- a/arch/m32r/kernel/smp.c
+++ b/arch/m32r/kernel/smp.c
@@ -35,22 +35,6 @@
 /*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*/
 
 /*
- * Structure and data for smp_call_function(). This is designed to minimise
- * static memory requirements. It also looks cleaner.
- */
-static DEFINE_SPINLOCK(call_lock);
-
-struct call_data_struct {
-	void (*func) (void *info);
-	void *info;
-	atomic_t started;
-	atomic_t finished;
-	int wait;
-} __attribute__ ((__aligned__(SMP_CACHE_BYTES)));
-
-static struct call_data_struct *call_data;
-
-/*
  * For flush_cache_all()
  */
 static DEFINE_SPINLOCK(flushcache_lock);
@@ -96,9 +80,6 @@ void smp_invalidate_interrupt(void);
 void smp_send_stop(void);
 static void stop_this_cpu(void *);
 
-int smp_call_function(void (*) (void *), void *, int, int);
-void smp_call_function_interrupt(void);
-
 void smp_send_timer(void);
 void smp_ipi_timer_interrupt(struct pt_regs *);
 void smp_local_timer_interrupt(void);
@@ -565,86 +546,14 @@ static void stop_this_cpu(void *dummy)
 	for ( ; ; );
 }
 
-/*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*/
-/* Call function Routines                                                    */
-/*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*/
-
-/*==========================================================================*
- * Name:         smp_call_function
- *
- * Description:  This routine sends a 'CALL_FUNCTION_IPI' to all other CPUs
- *               in the system.
- *
- * Born on Date: 2002.02.05
- *
- * Arguments:    *func - The function to run. This must be fast and
- *                       non-blocking.
- *               *info - An arbitrary pointer to pass to the function.
- *               nonatomic - currently unused.
- *               wait - If true, wait (atomically) until function has
- *                      completed on other CPUs.
- *
- * Returns:      0 on success, else a negative status code. Does not return
- *               until remote CPUs are nearly ready to execute <<func>> or
- *               are or have executed.
- *
- * Cautions:     You must not call this function with disabled interrupts or
- *               from a hardware interrupt handler, you may call it from a
- *               bottom half handler.
- *
- * Modification log:
- * Date       Who Description
- * ---------- --- --------------------------------------------------------
- *
- *==========================================================================*/
-int smp_call_function(void (*func) (void *info), void *info, int nonatomic,
-	int wait)
+void arch_send_call_function_ipi(cpumask_t mask)
 {
-	struct call_data_struct data;
-	int cpus;
-
-#ifdef DEBUG_SMP
-	unsigned long flags;
-	__save_flags(flags);
-	if (!(flags & 0x0040))	/* Interrupt Disable NONONO */
-		BUG();
-#endif /* DEBUG_SMP */
-
-	/* Holding any lock stops cpus from going down. */
-	spin_lock(&call_lock);
-	cpus = num_online_cpus() - 1;
-
-	if (!cpus) {
-		spin_unlock(&call_lock);
-		return 0;
-	}
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	call_data = &data;
-	mb();
-
-	/* Send a message to all other CPUs and wait for them to respond */
-	send_IPI_allbutself(CALL_FUNCTION_IPI, 0);
-
-	/* Wait for response */
-	while (atomic_read(&data.started) != cpus)
-		barrier();
-
-	if (wait)
-		while (atomic_read(&data.finished) != cpus)
-			barrier();
-	spin_unlock(&call_lock);
+	send_IPI_mask(mask, CALL_FUNCTION_IPI, 0);
+}
 
-	return 0;
+void arch_send_call_function_single_ipi(int cpu)
+{
+	send_IPI_mask(cpumask_of_cpu(cpu), CALL_FUNC_SINGLE_IPI, 0);
 }
 
 /*==========================================================================*
@@ -666,27 +575,16 @@ int smp_call_function(void (*func) (void *info), void *info, int nonatomic,
  *==========================================================================*/
 void smp_call_function_interrupt(void)
 {
-	void (*func) (void *info) = call_data->func;
-	void *info = call_data->info;
-	int wait = call_data->wait;
-
-	/*
-	 * Notify initiating CPU that I've grabbed the data and am
-	 * about to execute the function
-	 */
-	mb();
-	atomic_inc(&call_data->started);
-	/*
-	 * At this point the info structure may be out of scope unless wait==1
-	 */
 	irq_enter();
-	(*func)(info);
+	generic_smp_call_function_interrupt();
 	irq_exit();
+}
 
-	if (wait) {
-		mb();
-		atomic_inc(&call_data->finished);
-	}
+void smp_call_function_single_interrupt(void)
+{
+	irq_enter();
+	generic_smp_call_function_single_interrupt();
+	irq_exit();
 }
 
 /*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*/
diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c
index 89ba4a0b5d51..46159a4e644b 100644
--- a/arch/m32r/kernel/traps.c
+++ b/arch/m32r/kernel/traps.c
@@ -40,6 +40,7 @@ extern void smp_invalidate_interrupt(void);
 extern void smp_call_function_interrupt(void);
 extern void smp_ipi_timer_interrupt(void);
 extern void smp_flush_cache_all_interrupt(void);
+extern void smp_call_function_single_interrupt(void);
 
 /*
  * for Boot AP function
@@ -103,7 +104,7 @@ void	set_eit_vector_entries(void)
 	eit_vector[186] = (unsigned long)smp_call_function_interrupt;
 	eit_vector[187] = (unsigned long)smp_ipi_timer_interrupt;
 	eit_vector[188] = (unsigned long)smp_flush_cache_all_interrupt;
-	eit_vector[189] = 0;
+	eit_vector[189] = (unsigned long)smp_call_function_single_interrupt;
 	eit_vector[190] = 0;
 	eit_vector[191] = 0;
 #endif
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index e5a7c5d96364..ea70d5a225ca 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1763,6 +1763,7 @@ config SMP
 	bool "Multi-Processing support"
 	depends on SYS_SUPPORTS_SMP
 	select IRQ_PER_CPU
+	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 63370cdd3c90..c75b26cb61df 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -131,145 +131,28 @@ asmlinkage __cpuinit void start_secondary(void)
 	cpu_idle();
 }
 
-DEFINE_SPINLOCK(smp_call_lock);
-
-struct call_data_struct *call_data;
-
-/*
- * Run a function on all other CPUs.
- *
- *  <mask>	cpuset_t of all processors to run the function on.
- *  <func>      The function to run. This must be fast and non-blocking.
- *  <info>      An arbitrary pointer to pass to the function.
- *  <retry>     If true, keep retrying until ready.
- *  <wait>      If true, wait until function has completed on other CPUs.
- *  [RETURNS]   0 on success, else a negative status code.
- *
- * Does not return until remote CPUs are nearly ready to execute <func>
- * or are or have executed.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler:
- *
- * CPU A                               CPU B
- * Disable interrupts
- *                                     smp_call_function()
- *                                     Take call_lock
- *                                     Send IPIs
- *                                     Wait for all cpus to acknowledge IPI
- *                                     CPU A has not responded, spin waiting
- *                                     for cpu A to respond, holding call_lock
- * smp_call_function()
- * Spin waiting for call_lock
- * Deadlock                            Deadlock
- */
-int smp_call_function_mask(cpumask_t mask, void (*func) (void *info),
-	void *info, int retry, int wait)
+void arch_send_call_function_ipi(cpumask_t mask)
 {
-	struct call_data_struct data;
-	int cpu = smp_processor_id();
-	int cpus;
-
-	/*
-	 * Can die spectacularly if this CPU isn't yet marked online
-	 */
-	BUG_ON(!cpu_online(cpu));
-
-	cpu_clear(cpu, mask);
-	cpus = cpus_weight(mask);
-	if (!cpus)
-		return 0;
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	spin_lock(&smp_call_lock);
-	call_data = &data;
-	smp_mb();
-
-	/* Send a message to all other CPUs and wait for them to respond */
 	mp_ops->send_ipi_mask(mask, SMP_CALL_FUNCTION);
-
-	/* Wait for response */
-	/* FIXME: lock-up detection, backtrace on lock-up */
-	while (atomic_read(&data.started) != cpus)
-		barrier();
-
-	if (wait)
-		while (atomic_read(&data.finished) != cpus)
-			barrier();
-	call_data = NULL;
-	spin_unlock(&smp_call_lock);
-
-	return 0;
 }
 
-int smp_call_function(void (*func) (void *info), void *info, int retry,
-	int wait)
+/*
+ * We reuse the same vector for the single IPI
+ */
+void arch_send_call_function_single_ipi(int cpu)
 {
-	return smp_call_function_mask(cpu_online_map, func, info, retry, wait);
+	mp_ops->send_ipi_mask(cpumask_of_cpu(cpu), SMP_CALL_FUNCTION);
 }
 
+/*
+ * Call into both interrupt handlers, as we share the IPI for them
+ */
 void smp_call_function_interrupt(void)
 {
-	void (*func) (void *info) = call_data->func;
-	void *info = call_data->info;
-	int wait = call_data->wait;
-
-	/*
-	 * Notify initiating CPU that I've grabbed the data and am
-	 * about to execute the function.
-	 */
-	smp_mb();
-	atomic_inc(&call_data->started);
-
-	/*
-	 * At this point the info structure may be out of scope unless wait==1.
-	 */
 	irq_enter();
-	(*func)(info);
+	generic_smp_call_function_single_interrupt();
+	generic_smp_call_function_interrupt();
 	irq_exit();
-
-	if (wait) {
-		smp_mb();
-		atomic_inc(&call_data->finished);
-	}
-}
-
-int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
-			     int retry, int wait)
-{
-	int ret, me;
-
-	/*
-	 * Can die spectacularly if this CPU isn't yet marked online
-	 */
-	if (!cpu_online(cpu))
-		return 0;
-
-	me = get_cpu();
-	BUG_ON(!cpu_online(me));
-
-	if (cpu == me) {
-		local_irq_disable();
-		func(info);
-		local_irq_enable();
-		put_cpu();
-		return 0;
-	}
-
-	ret = smp_call_function_mask(cpumask_of_cpu(cpu), func, info, retry,
-				     wait);
-
-	put_cpu();
-	return 0;
 }
 
 static void stop_this_cpu(void *dummy)
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index 3e863186cd22..a516286532ab 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -877,7 +877,6 @@ static void ipi_resched_interrupt(void)
 	/* Return from interrupt should be enough to cause scheduler check */
 }
 
-
 static void ipi_call_interrupt(void)
 {
 	/* Invoke generic function invocation code in smp.c */
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index bc7a19da6245..a7d4fd353c2b 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -199,6 +199,7 @@ endchoice
 
 config SMP
 	bool "Symmetric multi-processing support"
+	select USE_GENERIC_SMP_HELPERS
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 85fc7754ec25..126105c76a44 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -84,19 +84,11 @@ EXPORT_SYMBOL(cpu_possible_map);
 
 DEFINE_PER_CPU(spinlock_t, ipi_lock) = SPIN_LOCK_UNLOCKED;
 
-struct smp_call_struct {
-	void (*func) (void *info);
-	void *info;
-	long wait;
-	atomic_t unstarted_count;
-	atomic_t unfinished_count;
-};
-static volatile struct smp_call_struct *smp_call_function_data;
-
 enum ipi_message_type {
 	IPI_NOP=0,
 	IPI_RESCHEDULE=1,
 	IPI_CALL_FUNC,
+	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_START,
 	IPI_CPU_STOP,
 	IPI_CPU_TEST
@@ -187,33 +179,12 @@ ipi_interrupt(int irq, void *dev_id)
 
 			case IPI_CALL_FUNC:
 				smp_debug(100, KERN_DEBUG "CPU%d IPI_CALL_FUNC\n", this_cpu);
-				{
-					volatile struct smp_call_struct *data;
-					void (*func)(void *info);
-					void *info;
-					int wait;
-
-					data = smp_call_function_data;
-					func = data->func;
-					info = data->info;
-					wait = data->wait;
-
-					mb();
-					atomic_dec ((atomic_t *)&data->unstarted_count);
-
-					/* At this point, *data can't
-					 * be relied upon.
-					 */
-
-					(*func)(info);
-
-					/* Notify the sending CPU that the
-					 * task is done.
-					 */
-					mb();
-					if (wait)
-						atomic_dec ((atomic_t *)&data->unfinished_count);
-				}
+				generic_smp_call_function_interrupt();
+				break;
+
+			case IPI_CALL_FUNC_SINGLE:
+				smp_debug(100, KERN_DEBUG "CPU%d IPI_CALL_FUNC_SINGLE\n", this_cpu);
+				generic_smp_call_function_single_interrupt();
 				break;
 
 			case IPI_CPU_START:
@@ -256,6 +227,14 @@ ipi_send(int cpu, enum ipi_message_type op)
 	spin_unlock_irqrestore(lock, flags);
 }
 
+static void
+send_IPI_mask(cpumask_t mask, enum ipi_message_type op)
+{
+	int cpu;
+
+	for_each_cpu_mask(cpu, mask)
+		ipi_send(cpu, op);
+}
 
 static inline void
 send_IPI_single(int dest_cpu, enum ipi_message_type op)
@@ -295,86 +274,15 @@ smp_send_all_nop(void)
 	send_IPI_allbutself(IPI_NOP);
 }
 
-
-/**
- * Run a function on all other CPUs.
- *  <func>	The function to run. This must be fast and non-blocking.
- *  <info>	An arbitrary pointer to pass to the function.
- *  <retry>	If true, keep retrying until ready.
- *  <wait>	If true, wait until function has completed on other CPUs.
- *  [RETURNS]   0 on success, else a negative status code.
- *
- * Does not return until remote CPUs are nearly ready to execute <func>
- * or have executed.
- */
-
-int
-smp_call_function (void (*func) (void *info), void *info, int retry, int wait)
+void arch_send_call_function_ipi(cpumask_t mask)
 {
-	struct smp_call_struct data;
-	unsigned long timeout;
-	static DEFINE_SPINLOCK(lock);
-	int retries = 0;
-
-	if (num_online_cpus() < 2)
-		return 0;
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	/* can also deadlock if IPIs are disabled */
-	WARN_ON((get_eiem() & (1UL<<(CPU_IRQ_MAX - IPI_IRQ))) == 0);
-
-	
-	data.func = func;
-	data.info = info;
-	data.wait = wait;
-	atomic_set(&data.unstarted_count, num_online_cpus() - 1);
-	atomic_set(&data.unfinished_count, num_online_cpus() - 1);
-
-	if (retry) {
-		spin_lock (&lock);
-		while (smp_call_function_data != 0)
-			barrier();
-	}
-	else {
-		spin_lock (&lock);
-		if (smp_call_function_data) {
-			spin_unlock (&lock);
-			return -EBUSY;
-		}
-	}
-
-	smp_call_function_data = &data;
-	spin_unlock (&lock);
-	
-	/*  Send a message to all other CPUs and wait for them to respond  */
-	send_IPI_allbutself(IPI_CALL_FUNC);
-
- retry:
-	/*  Wait for response  */
-	timeout = jiffies + HZ;
-	while ( (atomic_read (&data.unstarted_count) > 0) &&
-		time_before (jiffies, timeout) )
-		barrier ();
-
-	if (atomic_read (&data.unstarted_count) > 0) {
-		printk(KERN_CRIT "SMP CALL FUNCTION TIMED OUT! (cpu=%d), try %d\n",
-		      smp_processor_id(), ++retries);
-		goto retry;
-	}
-	/* We either got one or timed out. Release the lock */
-
-	mb();
-	smp_call_function_data = NULL;
-
-	while (wait && atomic_read (&data.unfinished_count) > 0)
-			barrier ();
-
-	return 0;
+	send_IPI_mask(mask, IPI_CALL_FUNC);
 }
 
-EXPORT_SYMBOL(smp_call_function);
+void arch_send_call_function_single_ipi(int cpu)
+{
+	send_IPI_single(cpu, IPI_CALL_FUNC_SINGLE);
+}
 
 /*
  * Flush all other CPU's tlb and then mine.  Do this with on_each_cpu()
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a7258691f00f..70931dae5fdf 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -112,6 +112,7 @@ config PPC
 	select HAVE_KRETPROBES
 	select HAVE_LMB
 	select HAVE_OPROFILE
+	select USE_GENERIC_SMP_HELPERS if SMP
 
 config EARLY_PRINTK
 	bool
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ba7989ffaeee..0a8772006053 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -72,12 +72,8 @@ struct smp_ops_t *smp_ops;
 
 static volatile unsigned int cpu_callin_map[NR_CPUS];
 
-void smp_call_function_interrupt(void);
-
 int smt_enabled_at_boot = 1;
 
-static int ipi_fail_ok;
-
 static void (*crash_ipi_function_ptr)(struct pt_regs *) = NULL;
 
 #ifdef CONFIG_PPC64
@@ -99,12 +95,15 @@ void smp_message_recv(int msg)
 {
 	switch(msg) {
 	case PPC_MSG_CALL_FUNCTION:
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 		break;
 	case PPC_MSG_RESCHEDULE:
 		/* XXX Do we have to do this? */
 		set_need_resched();
 		break;
+	case PPC_MSG_CALL_FUNC_SINGLE:
+		generic_smp_call_function_single_interrupt();
+		break;
 	case PPC_MSG_DEBUGGER_BREAK:
 		if (crash_ipi_function_ptr) {
 			crash_ipi_function_ptr(get_irq_regs());
@@ -128,6 +127,19 @@ void smp_send_reschedule(int cpu)
 		smp_ops->message_pass(cpu, PPC_MSG_RESCHEDULE);
 }
 
+void arch_send_call_function_single_ipi(int cpu)
+{
+	smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNC_SINGLE);
+}
+
+void arch_send_call_function_ipi(cpumask_t mask)
+{
+	unsigned int cpu;
+
+	for_each_cpu_mask(cpu, mask)
+		smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION);
+}
+
 #ifdef CONFIG_DEBUGGER
 void smp_send_debugger_break(int cpu)
 {
@@ -154,215 +166,9 @@ static void stop_this_cpu(void *dummy)
 		;
 }
 
-/*
- * Structure and data for smp_call_function(). This is designed to minimise
- * static memory requirements. It also looks cleaner.
- * Stolen from the i386 version.
- */
-static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(call_lock);
-
-static struct call_data_struct {
-	void (*func) (void *info);
-	void *info;
-	atomic_t started;
-	atomic_t finished;
-	int wait;
-} *call_data;
-
-/* delay of at least 8 seconds */
-#define SMP_CALL_TIMEOUT	8
-
-/*
- * These functions send a 'generic call function' IPI to other online
- * CPUS in the system.
- *
- * [SUMMARY] Run a function on other CPUs.
- * <func> The function to run. This must be fast and non-blocking.
- * <info> An arbitrary pointer to pass to the function.
- * <nonatomic> currently unused.
- * <wait> If true, wait (atomically) until function has completed on other CPUs.
- * [RETURNS] 0 on success, else a negative status code. Does not return until
- * remote CPUs are nearly ready to execute <<func>> or are or have executed.
- * <map> is a cpu map of the cpus to send IPI to.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-static int __smp_call_function_map(void (*func) (void *info), void *info,
-				   int nonatomic, int wait, cpumask_t map)
-{
-	struct call_data_struct data;
-	int ret = -1, num_cpus;
-	int cpu;
-	u64 timeout;
-
-	if (unlikely(smp_ops == NULL))
-		return ret;
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	/* remove 'self' from the map */
-	if (cpu_isset(smp_processor_id(), map))
-		cpu_clear(smp_processor_id(), map);
-
-	/* sanity check the map, remove any non-online processors. */
-	cpus_and(map, map, cpu_online_map);
-
-	num_cpus = cpus_weight(map);
-	if (!num_cpus)
-		goto done;
-
-	call_data = &data;
-	smp_wmb();
-	/* Send a message to all CPUs in the map */
-	for_each_cpu_mask(cpu, map)
-		smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION);
-
-	timeout = get_tb() + (u64) SMP_CALL_TIMEOUT * tb_ticks_per_sec;
-
-	/* Wait for indication that they have received the message */
-	while (atomic_read(&data.started) != num_cpus) {
-		HMT_low();
-		if (get_tb() >= timeout) {
-			printk("smp_call_function on cpu %d: other cpus not "
-				"responding (%d)\n", smp_processor_id(),
-				atomic_read(&data.started));
-			if (!ipi_fail_ok)
-				debugger(NULL);
-			goto out;
-		}
-	}
-
-	/* optionally wait for the CPUs to complete */
-	if (wait) {
-		while (atomic_read(&data.finished) != num_cpus) {
-			HMT_low();
-			if (get_tb() >= timeout) {
-				printk("smp_call_function on cpu %d: other "
-					"cpus not finishing (%d/%d)\n",
-					smp_processor_id(),
-					atomic_read(&data.finished),
-					atomic_read(&data.started));
-				debugger(NULL);
-				goto out;
-			}
-		}
-	}
-
- done:
-	ret = 0;
-
- out:
-	call_data = NULL;
-	HMT_medium();
-	return ret;
-}
-
-static int __smp_call_function(void (*func)(void *info), void *info,
-			       int nonatomic, int wait)
-{
-	int ret;
-	spin_lock(&call_lock);
-	ret =__smp_call_function_map(func, info, nonatomic, wait,
-				       cpu_online_map);
-	spin_unlock(&call_lock);
-	return ret;
-}
-
-int smp_call_function(void (*func) (void *info), void *info, int nonatomic,
-			int wait)
-{
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	return __smp_call_function(func, info, nonatomic, wait);
-}
-EXPORT_SYMBOL(smp_call_function);
-
-int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
-			     int nonatomic, int wait)
-{
-	cpumask_t map = CPU_MASK_NONE;
-	int ret = 0;
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	if (!cpu_online(cpu))
-		return -EINVAL;
-
-	cpu_set(cpu, map);
-	if (cpu != get_cpu()) {
-		spin_lock(&call_lock);
-		ret = __smp_call_function_map(func, info, nonatomic, wait, map);
-		spin_unlock(&call_lock);
-	} else {
-		local_irq_disable();
-		func(info);
-		local_irq_enable();
-	}
-	put_cpu();
-	return ret;
-}
-EXPORT_SYMBOL(smp_call_function_single);
-
 void smp_send_stop(void)
 {
-	int nolock;
-
-	/* It's OK to fail sending the IPI, since the alternative is to
-	 * be stuck forever waiting on the other CPU to take the interrupt.
-	 *
-	 * It's better to at least continue and go through reboot, since this
-	 * function is usually called at panic or reboot time in the first
-	 * place.
-	 */
-	ipi_fail_ok = 1;
-
-	/* Don't deadlock in case we got called through panic */
-	nolock = !spin_trylock(&call_lock);
-	__smp_call_function_map(stop_this_cpu, NULL, 1, 0, cpu_online_map);
-	if (!nolock)
-		spin_unlock(&call_lock);
-}
-
-void smp_call_function_interrupt(void)
-{
-	void (*func) (void *info);
-	void *info;
-	int wait;
-
-	/* call_data will be NULL if the sender timed out while
-	 * waiting on us to receive the call.
-	 */
-	if (!call_data)
-		return;
-
-	func = call_data->func;
-	info = call_data->info;
-	wait = call_data->wait;
-
-	if (!wait)
-		smp_mb__before_atomic_inc();
-
-	/*
-	 * Notify initiating CPU that I've grabbed the data and am
-	 * about to execute the function
-	 */
-	atomic_inc(&call_data->started);
-	/*
-	 * At this point the info structure may be out of scope unless wait==1
-	 */
-	(*func)(info);
-	if (wait) {
-		smp_mb__before_atomic_inc();
-		atomic_inc(&call_data->finished);
-	}
+	smp_call_function(stop_this_cpu, NULL, 0, 0);
 }
 
 struct thread_info *current_set[NR_CPUS];
@@ -592,9 +398,9 @@ int __devinit start_secondary(void *unused)
 
 	secondary_cpu_time_init();
 
-	spin_lock(&call_lock);
+	spin_lock(&call_function_lock);
 	cpu_set(cpu, cpu_online_map);
-	spin_unlock(&call_lock);
+	spin_unlock(&call_function_lock);
 
 	local_irq_enable();
 
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 5bf7df146022..2d5bb22d6c09 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -218,6 +218,7 @@ void iic_request_IPIs(void)
 {
 	iic_request_ipi(PPC_MSG_CALL_FUNCTION, "IPI-call");
 	iic_request_ipi(PPC_MSG_RESCHEDULE, "IPI-resched");
+	iic_request_ipi(PPC_MSG_CALL_FUNC_SINGLE, "IPI-call-single");
 #ifdef CONFIG_DEBUGGER
 	iic_request_ipi(PPC_MSG_DEBUGGER_BREAK, "IPI-debug");
 #endif /* CONFIG_DEBUGGER */
diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c
index f0b12f212363..a0927a3bacb7 100644
--- a/arch/powerpc/platforms/ps3/smp.c
+++ b/arch/powerpc/platforms/ps3/smp.c
@@ -105,9 +105,10 @@ static void __init ps3_smp_setup_cpu(int cpu)
 	 * to index needs to be setup.
 	 */
 
-	BUILD_BUG_ON(PPC_MSG_CALL_FUNCTION  != 0);
-	BUILD_BUG_ON(PPC_MSG_RESCHEDULE     != 1);
-	BUILD_BUG_ON(PPC_MSG_DEBUGGER_BREAK != 3);
+	BUILD_BUG_ON(PPC_MSG_CALL_FUNCTION    != 0);
+	BUILD_BUG_ON(PPC_MSG_RESCHEDULE       != 1);
+	BUILD_BUG_ON(PPC_MSG_CALL_FUNC_SINGLE != 2);
+	BUILD_BUG_ON(PPC_MSG_DEBUGGER_BREAK   != 3);
 
 	for (i = 0; i < MSG_COUNT; i++) {
 		result = ps3_event_receive_port_setup(cpu, &virqs[i]);
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index ebebc28fe895..0fc830f576f5 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -383,13 +383,11 @@ static irqreturn_t xics_ipi_dispatch(int cpu)
 			mb();
 			smp_message_recv(PPC_MSG_RESCHEDULE);
 		}
-#if 0
-		if (test_and_clear_bit(PPC_MSG_MIGRATE_TASK,
+		if (test_and_clear_bit(PPC_MSG_CALL_FUNC_SINGLE,
 				       &xics_ipi_message[cpu].value)) {
 			mb();
-			smp_message_recv(PPC_MSG_MIGRATE_TASK);
+			smp_message_recv(PPC_MSG_CALL_FUNC_SINGLE);
 		}
-#endif
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
 		if (test_and_clear_bit(PPC_MSG_DEBUGGER_BREAK,
 				       &xics_ipi_message[cpu].value)) {
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 5788a6ab1254..8e3478c995ef 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -1496,7 +1496,7 @@ void mpic_request_ipis(void)
 	static char *ipi_names[] = {
 		"IPI0 (call function)",
 		"IPI1 (reschedule)",
-		"IPI2 (unused)",
+		"IPI2 (call function single)",
 		"IPI3 (debugger break)",
 	};
 	BUG_ON(mpic == NULL);
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 10a0c184444e..a724077ccf35 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -706,6 +706,7 @@ config CRASH_DUMP
 config SMP
 	bool "Symmetric multi-processing support"
 	depends on SYS_SUPPORTS_SMP
+	select USE_GENERIC_SMP_HELPERS
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index 5d039d168f57..2ed8dceb297b 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -36,13 +36,6 @@ EXPORT_SYMBOL(cpu_possible_map);
 cpumask_t cpu_online_map;
 EXPORT_SYMBOL(cpu_online_map);
 
-static atomic_t cpus_booted = ATOMIC_INIT(0);
-
-/*
- * Run specified function on a particular processor.
- */
-void __smp_call_function(unsigned int cpu);
-
 static inline void __init smp_store_cpu_info(unsigned int cpu)
 {
 	struct sh_cpuinfo *c = cpu_data + cpu;
@@ -178,42 +171,17 @@ void smp_send_stop(void)
 	smp_call_function(stop_this_cpu, 0, 1, 0);
 }
 
-struct smp_fn_call_struct smp_fn_call = {
-	.lock		= __SPIN_LOCK_UNLOCKED(smp_fn_call.lock),
-	.finished	= ATOMIC_INIT(0),
-};
-
-/*
- * The caller of this wants the passed function to run on every cpu.  If wait
- * is set, wait until all cpus have finished the function before returning.
- * The lock is here to protect the call structure.
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-int smp_call_function(void (*func)(void *info), void *info, int retry, int wait)
+void arch_send_call_function_ipi(cpumask_t mask)
 {
-	unsigned int nr_cpus = atomic_read(&cpus_booted);
-	int i;
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	spin_lock(&smp_fn_call.lock);
-
-	atomic_set(&smp_fn_call.finished, 0);
-	smp_fn_call.fn = func;
-	smp_fn_call.data = info;
-
-	for (i = 0; i < nr_cpus; i++)
-		if (i != smp_processor_id())
-			plat_send_ipi(i, SMP_MSG_FUNCTION);
-
-	if (wait)
-		while (atomic_read(&smp_fn_call.finished) != (nr_cpus - 1));
+	int cpu;
 
-	spin_unlock(&smp_fn_call.lock);
+	for_each_cpu_mask(cpu, mask)
+		plat_send_ipi(cpu, SMP_MSG_FUNCTION);
+}
 
-	return 0;
+void arch_send_call_function_single_ipi(int cpu)
+{
+	plat_send_ipi(cpu, SMP_MSG_FUNCTION_SINGLE);
 }
 
 /* Not really SMP stuff ... */
diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c
index fa63c68a1819..b82d017a1744 100644
--- a/arch/sparc64/kernel/smp.c
+++ b/arch/sparc64/kernel/smp.c
@@ -816,8 +816,9 @@ extern unsigned long xcall_call_function;
  * You must not call this function with disabled interrupts or from a
  * hardware interrupt handler or from a bottom half handler.
  */
-static int smp_call_function_mask(void (*func)(void *info), void *info,
-				  int nonatomic, int wait, cpumask_t mask)
+static int sparc64_smp_call_function_mask(void (*func)(void *info), void *info,
+					  int nonatomic, int wait,
+					  cpumask_t mask)
 {
 	struct call_data_struct data;
 	int cpus;
@@ -855,8 +856,8 @@ out_unlock:
 int smp_call_function(void (*func)(void *info), void *info,
 		      int nonatomic, int wait)
 {
-	return smp_call_function_mask(func, info, nonatomic, wait,
-				      cpu_online_map);
+	return sparc64_smp_call_function_mask(func, info, nonatomic, wait,
+						cpu_online_map);
 }
 
 void smp_call_function_client(int irq, struct pt_regs *regs)
@@ -893,7 +894,7 @@ static void tsb_sync(void *info)
 
 void smp_tsb_sync(struct mm_struct *mm)
 {
-	smp_call_function_mask(tsb_sync, mm, 0, 1, mm->cpu_vm_mask);
+	sparc64_smp_call_function_mask(tsb_sync, mm, 0, 1, mm->cpu_vm_mask);
 }
 
 extern unsigned long xcall_flush_tlb_mm;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9e3ee5431e31..01db61fdd8bb 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -170,6 +170,7 @@ config GENERIC_PENDING_IRQ
 config X86_SMP
 	bool
 	depends on SMP && ((X86_32 && !X86_VOYAGER) || X86_64)
+	select USE_GENERIC_SMP_HELPERS
 	default y
 
 config X86_32_SMP
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 84ce106b33c8..8913741bc5a4 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -1364,6 +1364,10 @@ void __init smp_intr_init(void)
 
 	/* IPI for generic function call */
 	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
+
+	/* IPI for single call function */
+	alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
+				call_function_single_interrupt);
 }
 #endif
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 4e354fe90f9a..e539cb4ca3b3 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -813,6 +813,9 @@ END(invalidate_interrupt\num)
 ENTRY(call_function_interrupt)
 	apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt
 END(call_function_interrupt)
+ENTRY(call_function_single_interrupt)
+	apicinterrupt CALL_FUNCTION_SINGLE_VECTOR,smp_call_function_single_interrupt
+END(call_function_single_interrupt)
 ENTRY(irq_move_cleanup_interrupt)
 	apicinterrupt IRQ_MOVE_CLEANUP_VECTOR,smp_irq_move_cleanup_interrupt
 END(irq_move_cleanup_interrupt)
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index 31f49e8f46a7..7d8b58857ecd 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -199,6 +199,10 @@ void __init native_init_IRQ(void)
 	/* IPI for generic function call */
 	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
 
+	/* IPI for generic single function call */
+	alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
+				call_function_single_interrupt);
+
 	/* Low priority IPI to cleanup after moving an irq */
 	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
 #endif
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 0cb7aadc87cd..3e051ae02681 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -121,132 +121,33 @@ static void native_smp_send_reschedule(int cpu)
 	send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR);
 }
 
-/*
- * Structure and data for smp_call_function(). This is designed to minimise
- * static memory requirements. It also looks cleaner.
- */
-static DEFINE_SPINLOCK(call_lock);
-
-struct call_data_struct {
-	void (*func) (void *info);
-	void *info;
-	atomic_t started;
-	atomic_t finished;
-	int wait;
-};
-
 void lock_ipi_call_lock(void)
 {
-	spin_lock_irq(&call_lock);
+	spin_lock_irq(&call_function_lock);
 }
 
 void unlock_ipi_call_lock(void)
 {
-	spin_unlock_irq(&call_lock);
+	spin_unlock_irq(&call_function_lock);
 }
 
-static struct call_data_struct *call_data;
-
-static void __smp_call_function(void (*func) (void *info), void *info,
-				int nonatomic, int wait)
+void native_send_call_func_single_ipi(int cpu)
 {
-	struct call_data_struct data;
-	int cpus = num_online_cpus() - 1;
-
-	if (!cpus)
-		return;
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	call_data = &data;
-	mb();
-
-	/* Send a message to all other CPUs and wait for them to respond */
-	send_IPI_allbutself(CALL_FUNCTION_VECTOR);
-
-	/* Wait for response */
-	while (atomic_read(&data.started) != cpus)
-		cpu_relax();
-
-	if (wait)
-		while (atomic_read(&data.finished) != cpus)
-			cpu_relax();
+	send_IPI_mask(cpumask_of_cpu(cpu), CALL_FUNCTION_SINGLE_VECTOR);
 }
 
-
-/**
- * smp_call_function_mask(): Run a function on a set of other CPUs.
- * @mask: The set of cpus to run on.  Must not include the current cpu.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
- *
-  * Returns 0 on success, else a negative status code.
- *
- * If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-static int
-native_smp_call_function_mask(cpumask_t mask,
-			      void (*func)(void *), void *info,
-			      int wait)
+void native_send_call_func_ipi(cpumask_t mask)
 {
-	struct call_data_struct data;
 	cpumask_t allbutself;
-	int cpus;
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	/* Holding any lock stops cpus from going down. */
-	spin_lock(&call_lock);
 
 	allbutself = cpu_online_map;
 	cpu_clear(smp_processor_id(), allbutself);
 
-	cpus_and(mask, mask, allbutself);
-	cpus = cpus_weight(mask);
-
-	if (!cpus) {
-		spin_unlock(&call_lock);
-		return 0;
-	}
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	call_data = &data;
-	wmb();
-
-	/* Send a message to other CPUs */
 	if (cpus_equal(mask, allbutself) &&
 	    cpus_equal(cpu_online_map, cpu_callout_map))
 		send_IPI_allbutself(CALL_FUNCTION_VECTOR);
 	else
 		send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
-
-	/* Wait for response */
-	while (atomic_read(&data.started) != cpus)
-		cpu_relax();
-
-	if (wait)
-		while (atomic_read(&data.finished) != cpus)
-			cpu_relax();
-	spin_unlock(&call_lock);
-
-	return 0;
 }
 
 static void stop_this_cpu(void *dummy)
@@ -268,18 +169,13 @@ static void stop_this_cpu(void *dummy)
 
 static void native_smp_send_stop(void)
 {
-	int nolock;
 	unsigned long flags;
 
 	if (reboot_force)
 		return;
 
-	/* Don't deadlock on the call lock in panic */
-	nolock = !spin_trylock(&call_lock);
+	smp_call_function(stop_this_cpu, NULL, 0, 0);
 	local_irq_save(flags);
-	__smp_call_function(stop_this_cpu, NULL, 0, 0);
-	if (!nolock)
-		spin_unlock(&call_lock);
 	disable_local_APIC();
 	local_irq_restore(flags);
 }
@@ -301,33 +197,28 @@ void smp_reschedule_interrupt(struct pt_regs *regs)
 
 void smp_call_function_interrupt(struct pt_regs *regs)
 {
-	void (*func) (void *info) = call_data->func;
-	void *info = call_data->info;
-	int wait = call_data->wait;
-
 	ack_APIC_irq();
-	/*
-	 * Notify initiating CPU that I've grabbed the data and am
-	 * about to execute the function
-	 */
-	mb();
-	atomic_inc(&call_data->started);
-	/*
-	 * At this point the info structure may be out of scope unless wait==1
-	 */
 	irq_enter();
-	(*func)(info);
+	generic_smp_call_function_interrupt();
 #ifdef CONFIG_X86_32
 	__get_cpu_var(irq_stat).irq_call_count++;
 #else
 	add_pda(irq_call_count, 1);
 #endif
 	irq_exit();
+}
 
-	if (wait) {
-		mb();
-		atomic_inc(&call_data->finished);
-	}
+void smp_call_function_single_interrupt(void)
+{
+	ack_APIC_irq();
+	irq_enter();
+	generic_smp_call_function_single_interrupt();
+#ifdef CONFIG_X86_32
+	__get_cpu_var(irq_stat).irq_call_count++;
+#else
+	add_pda(irq_call_count, 1);
+#endif
+	irq_exit();
 }
 
 struct smp_ops smp_ops = {
@@ -338,7 +229,8 @@ struct smp_ops smp_ops = {
 
 	.smp_send_stop = native_smp_send_stop,
 	.smp_send_reschedule = native_smp_send_reschedule,
-	.smp_call_function_mask = native_smp_call_function_mask,
+
+	.send_call_func_ipi = native_send_call_func_ipi,
+	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };
 EXPORT_SYMBOL_GPL(smp_ops);
-
diff --git a/arch/x86/kernel/smpcommon.c b/arch/x86/kernel/smpcommon.c
index 3449064d141a..99941b37eca0 100644
--- a/arch/x86/kernel/smpcommon.c
+++ b/arch/x86/kernel/smpcommon.c
@@ -25,59 +25,3 @@ __cpuinit void init_gdt(int cpu)
 	per_cpu(cpu_number, cpu) = cpu;
 }
 #endif
-
-/**
- * smp_call_function(): Run a function on all other CPUs.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @nonatomic: Unused.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
- *
- * Returns 0 on success, else a negative status code.
- *
- * If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-int smp_call_function(void (*func) (void *info), void *info, int nonatomic,
-		      int wait)
-{
-	return smp_call_function_mask(cpu_online_map, func, info, wait);
-}
-EXPORT_SYMBOL(smp_call_function);
-
-/**
- * smp_call_function_single - Run a function on a specific CPU
- * @cpu: The target CPU.  Cannot be the calling CPU.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @nonatomic: Unused.
- * @wait: If true, wait until function has completed on other CPUs.
- *
- * Returns 0 on success, else a negative status code.
- *
- * If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func.
- */
-int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
-			     int nonatomic, int wait)
-{
-	/* prevent preemption and reschedule on another processor */
-	int ret;
-	int me = get_cpu();
-	if (cpu == me) {
-		local_irq_disable();
-		func(info);
-		local_irq_enable();
-		put_cpu();
-		return 0;
-	}
-
-	ret = smp_call_function_mask(cpumask_of_cpu(cpu), func, info, wait);
-
-	put_cpu();
-	return ret;
-}
-EXPORT_SYMBOL(smp_call_function_single);
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 8dedd01e909f..fe323422e71f 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -950,94 +950,24 @@ static void smp_stop_cpu_function(void *dummy)
 		halt();
 }
 
-static DEFINE_SPINLOCK(call_lock);
-
-struct call_data_struct {
-	void (*func) (void *info);
-	void *info;
-	volatile unsigned long started;
-	volatile unsigned long finished;
-	int wait;
-};
-
-static struct call_data_struct *call_data;
-
 /* execute a thread on a new CPU.  The function to be called must be
  * previously set up.  This is used to schedule a function for
  * execution on all CPUs - set up the function then broadcast a
  * function_interrupt CPI to come here on each CPU */
 static void smp_call_function_interrupt(void)
 {
-	void (*func) (void *info) = call_data->func;
-	void *info = call_data->info;
-	/* must take copy of wait because call_data may be replaced
-	 * unless the function is waiting for us to finish */
-	int wait = call_data->wait;
-	__u8 cpu = smp_processor_id();
-
-	/*
-	 * Notify initiating CPU that I've grabbed the data and am
-	 * about to execute the function
-	 */
-	mb();
-	if (!test_and_clear_bit(cpu, &call_data->started)) {
-		/* If the bit wasn't set, this could be a replay */
-		printk(KERN_WARNING "VOYAGER SMP: CPU %d received call funtion"
-		       " with no call pending\n", cpu);
-		return;
-	}
-	/*
-	 * At this point the info structure may be out of scope unless wait==1
-	 */
 	irq_enter();
-	(*func) (info);
+	generic_smp_call_function_interrupt();
 	__get_cpu_var(irq_stat).irq_call_count++;
 	irq_exit();
-	if (wait) {
-		mb();
-		clear_bit(cpu, &call_data->finished);
-	}
 }
 
-static int
-voyager_smp_call_function_mask(cpumask_t cpumask,
-			       void (*func) (void *info), void *info, int wait)
+static void smp_call_function_single_interrupt(void)
 {
-	struct call_data_struct data;
-	u32 mask = cpus_addr(cpumask)[0];
-
-	mask &= ~(1 << smp_processor_id());
-
-	if (!mask)
-		return 0;
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	data.func = func;
-	data.info = info;
-	data.started = mask;
-	data.wait = wait;
-	if (wait)
-		data.finished = mask;
-
-	spin_lock(&call_lock);
-	call_data = &data;
-	wmb();
-	/* Send a message to all other CPUs and wait for them to respond */
-	send_CPI(mask, VIC_CALL_FUNCTION_CPI);
-
-	/* Wait for response */
-	while (data.started)
-		barrier();
-
-	if (wait)
-		while (data.finished)
-			barrier();
-
-	spin_unlock(&call_lock);
-
-	return 0;
+	irq_enter();
+	generic_smp_call_function_single_interrupt();
+	__get_cpu_var(irq_stat).irq_call_count++;
+	irq_exit();
 }
 
 /* Sorry about the name.  In an APIC based system, the APICs
@@ -1094,6 +1024,12 @@ void smp_qic_call_function_interrupt(struct pt_regs *regs)
 	smp_call_function_interrupt();
 }
 
+void smp_qic_call_function_single_interrupt(struct pt_regs *regs)
+{
+	ack_QIC_CPI(QIC_CALL_FUNCTION_SINGLE_CPI);
+	smp_call_function_single_interrupt();
+}
+
 void smp_vic_cpi_interrupt(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
@@ -1114,6 +1050,8 @@ void smp_vic_cpi_interrupt(struct pt_regs *regs)
 		smp_enable_irq_interrupt();
 	if (test_and_clear_bit(VIC_CALL_FUNCTION_CPI, &vic_cpi_mailbox[cpu]))
 		smp_call_function_interrupt();
+	if (test_and_clear_bit(VIC_CALL_FUNCTION_SINGLE_CPI, &vic_cpi_mailbox[cpu]))
+		smp_call_function_single_interrupt();
 	set_irq_regs(old_regs);
 }
 
@@ -1848,5 +1786,7 @@ struct smp_ops smp_ops = {
 
 	.smp_send_stop = voyager_smp_send_stop,
 	.smp_send_reschedule = voyager_smp_send_reschedule,
-	.smp_call_function_mask = voyager_smp_call_function_mask,
+
+	.send_call_func_ipi = native_send_call_func_ipi,
+	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 6e03b94c69d5..52f0cf6db93c 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1173,7 +1173,9 @@ static const struct smp_ops xen_smp_ops __initdata = {
 
 	.smp_send_stop = xen_smp_send_stop,
 	.smp_send_reschedule = xen_smp_send_reschedule,
-	.smp_call_function_mask = xen_smp_call_function_mask,
+
+	.send_call_func_ipi = xen_smp_send_call_function_ipi,
+	.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi,
 };
 #endif	/* CONFIG_SMP */
 
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index c5b5e39ef287..42c6e358497c 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -36,27 +36,14 @@
 #include "mmu.h"
 
 cpumask_t xen_cpu_initialized_map;
-static DEFINE_PER_CPU(int, resched_irq) = -1;
-static DEFINE_PER_CPU(int, callfunc_irq) = -1;
-static DEFINE_PER_CPU(int, debug_irq) = -1;
-
-/*
- * Structure and data for smp_call_function(). This is designed to minimise
- * static memory requirements. It also looks cleaner.
- */
-static DEFINE_SPINLOCK(call_lock);
 
-struct call_data_struct {
-	void (*func) (void *info);
-	void *info;
-	atomic_t started;
-	atomic_t finished;
-	int wait;
-};
+static DEFINE_PER_CPU(int, resched_irq);
+static DEFINE_PER_CPU(int, callfunc_irq);
+static DEFINE_PER_CPU(int, callfuncsingle_irq);
+static DEFINE_PER_CPU(int, debug_irq) = -1;
 
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
-
-static struct call_data_struct *call_data;
+static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
 
 /*
  * Reschedule call back. Nothing to do,
@@ -128,6 +115,17 @@ static int xen_smp_intr_init(unsigned int cpu)
 		goto fail;
 	per_cpu(debug_irq, cpu) = rc;
 
+	callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
+	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
+				    cpu,
+				    xen_call_function_single_interrupt,
+				    IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
+				    callfunc_name,
+				    NULL);
+	if (rc < 0)
+		goto fail;
+	per_cpu(callfuncsingle_irq, cpu) = rc;
+
 	return 0;
 
  fail:
@@ -137,6 +135,9 @@ static int xen_smp_intr_init(unsigned int cpu)
 		unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL);
 	if (per_cpu(debug_irq, cpu) >= 0)
 		unbind_from_irqhandler(per_cpu(debug_irq, cpu), NULL);
+	if (per_cpu(callfuncsingle_irq, cpu) >= 0)
+		unbind_from_irqhandler(per_cpu(callfuncsingle_irq, cpu), NULL);
+
 	return rc;
 }
 
@@ -344,7 +345,6 @@ void xen_smp_send_reschedule(int cpu)
 	xen_send_IPI_one(cpu, XEN_RESCHEDULE_VECTOR);
 }
 
-
 static void xen_send_IPI_mask(cpumask_t mask, enum ipi_vector vector)
 {
 	unsigned cpu;
@@ -355,83 +355,42 @@ static void xen_send_IPI_mask(cpumask_t mask, enum ipi_vector vector)
 		xen_send_IPI_one(cpu, vector);
 }
 
+void xen_smp_send_call_function_ipi(cpumask_t mask)
+{
+	int cpu;
+
+	xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);
+
+	/* Make sure other vcpus get a chance to run if they need to. */
+	for_each_cpu_mask(cpu, mask) {
+		if (xen_vcpu_stolen(cpu)) {
+			HYPERVISOR_sched_op(SCHEDOP_yield, 0);
+			break;
+		}
+	}
+}
+
+void xen_smp_send_call_function_single_ipi(int cpu)
+{
+	xen_send_IPI_mask(cpumask_of_cpu(cpu), XEN_CALL_FUNCTION_SINGLE_VECTOR);
+}
+
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
 {
-	void (*func) (void *info) = call_data->func;
-	void *info = call_data->info;
-	int wait = call_data->wait;
-
-	/*
-	 * Notify initiating CPU that I've grabbed the data and am
-	 * about to execute the function
-	 */
-	mb();
-	atomic_inc(&call_data->started);
-	/*
-	 * At this point the info structure may be out of scope unless wait==1
-	 */
 	irq_enter();
-	(*func)(info);
+	generic_smp_call_function_interrupt();
 	__get_cpu_var(irq_stat).irq_call_count++;
 	irq_exit();
 
-	if (wait) {
-		mb();		/* commit everything before setting finished */
-		atomic_inc(&call_data->finished);
-	}
-
 	return IRQ_HANDLED;
 }
 
-int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *),
-			       void *info, int wait)
+static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id)
 {
-	struct call_data_struct data;
-	int cpus, cpu;
-	bool yield;
-
-	/* Holding any lock stops cpus from going down. */
-	spin_lock(&call_lock);
-
-	cpu_clear(smp_processor_id(), mask);
-
-	cpus = cpus_weight(mask);
-	if (!cpus) {
-		spin_unlock(&call_lock);
-		return 0;
-	}
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	call_data = &data;
-	mb();			/* write everything before IPI */
-
-	/* Send a message to other CPUs and wait for them to respond */
-	xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);
-
-	/* Make sure other vcpus get a chance to run if they need to. */
-	yield = false;
-	for_each_cpu_mask_nr(cpu, mask)
-		if (xen_vcpu_stolen(cpu))
-			yield = true;
-
-	if (yield)
-		HYPERVISOR_sched_op(SCHEDOP_yield, 0);
-
-	/* Wait for response */
-	while (atomic_read(&data.started) != cpus ||
-	       (wait && atomic_read(&data.finished) != cpus))
-		cpu_relax();
-
-	spin_unlock(&call_lock);
+	irq_enter();
+	generic_smp_call_function_single_interrupt();
+	__get_cpu_var(irq_stat).irq_call_count++;
+	irq_exit();
 
-	return 0;
+	return IRQ_HANDLED;
 }
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 9a055592a307..1574d3a84273 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -55,13 +55,8 @@ void xen_smp_cpus_done(unsigned int max_cpus);
 
 void xen_smp_send_stop(void);
 void xen_smp_send_reschedule(int cpu);
-int xen_smp_call_function (void (*func) (void *info), void *info, int nonatomic,
-			   int wait);
-int xen_smp_call_function_single(int cpu, void (*func) (void *info), void *info,
-				 int nonatomic, int wait);
-
-int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *),
-			       void *info, int wait);
+void xen_smp_send_call_function_ipi(cpumask_t mask);
+void xen_smp_send_call_function_single_ipi(int cpu);
 
 extern cpumask_t xen_cpu_initialized_map;