From 7a14ce1d8c1d3a6118d406e64eaf9aa70375e085 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Mon, 12 May 2008 15:43:53 +0200
Subject: nohz: reduce jiffies polling overhead

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/time/tick-sched.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'kernel/time')

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index b854a895591e..cb75394ed00e 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -48,6 +48,13 @@ static void tick_do_update_jiffies64(ktime_t now)
 	unsigned long ticks = 0;
 	ktime_t delta;
 
+	/*
+	 * Do a quick check without holding xtime_lock:
+	 */
+	delta = ktime_sub(now, last_jiffies_update);
+	if (delta.tv64 < tick_period.tv64)
+		return;
+
 	/* Reevalute with xtime_lock held */
 	write_seqlock(&xtime_lock);
 
-- 
cgit v1.2.3


From 8691e5a8f691cc2a4fda0651e8d307aaba0e7d68 Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Fri, 6 Jun 2008 11:18:06 +0200
Subject: smp_call_function: get rid of the unused nonatomic/retry argument

It's never used and the comments refer to nonatomic and retry
interchangably. So get rid of it.

Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 arch/alpha/kernel/core_marvel.c      |  2 +-
 arch/alpha/kernel/smp.c              |  6 +++---
 arch/alpha/oprofile/common.c         |  6 +++---
 arch/arm/oprofile/op_model_mpcore.c  |  2 +-
 arch/arm/vfp/vfpmodule.c             |  2 +-
 arch/cris/arch-v32/kernel/smp.c      |  5 ++---
 arch/ia64/kernel/mca.c               |  2 +-
 arch/ia64/kernel/palinfo.c           |  2 +-
 arch/ia64/kernel/perfmon.c           |  2 +-
 arch/ia64/kernel/process.c           |  2 +-
 arch/ia64/kernel/smpboot.c           |  2 +-
 arch/ia64/kernel/uncached.c          |  5 ++---
 arch/ia64/sn/kernel/sn2/sn_hwperf.c  |  2 +-
 arch/m32r/kernel/smp.c               |  4 ++--
 arch/mips/kernel/smp.c               |  4 ++--
 arch/mips/mm/c-r4k.c                 | 18 +++++++++---------
 arch/mips/pmc-sierra/yosemite/prom.c |  2 +-
 arch/mips/sibyte/cfe/setup.c         |  2 +-
 arch/mips/sibyte/sb1250/prom.c       |  2 +-
 arch/powerpc/kernel/smp.c            |  2 +-
 arch/s390/appldata/appldata_base.c   |  4 ++--
 arch/s390/kernel/smp.c               | 16 ++++++----------
 arch/s390/kernel/time.c              |  4 ++--
 arch/sh/kernel/smp.c                 | 10 +++++-----
 arch/sparc64/kernel/smp.c            | 12 ++++--------
 arch/um/kernel/smp.c                 |  3 +--
 arch/x86/kernel/cpu/mtrr/main.c      |  4 ++--
 arch/x86/kernel/cpuid.c              |  2 +-
 arch/x86/kernel/ldt.c                |  2 +-
 arch/x86/kernel/nmi_32.c             |  2 +-
 arch/x86/kernel/nmi_64.c             |  2 +-
 arch/x86/kernel/smp.c                |  2 +-
 arch/x86/kernel/vsyscall_64.c        |  2 +-
 arch/x86/kvm/vmx.c                   |  2 +-
 arch/x86/kvm/x86.c                   |  2 +-
 arch/x86/lib/msr-on-cpu.c            |  8 ++++----
 arch/x86/mach-voyager/voyager_smp.c  |  2 +-
 arch/x86/xen/smp.c                   |  2 +-
 drivers/acpi/processor_idle.c        |  2 +-
 drivers/cpuidle/cpuidle.c            |  2 +-
 include/asm-alpha/smp.h              |  2 +-
 include/asm-sparc/smp.h              |  2 +-
 include/linux/smp.h                  |  8 ++++----
 kernel/smp.c                         |  6 ++----
 kernel/softirq.c                     |  2 +-
 kernel/time/tick-broadcast.c         |  2 +-
 net/core/flow.c                      |  2 +-
 net/iucv/iucv.c                      | 14 +++++++-------
 virt/kvm/kvm_main.c                  |  6 +++---
 49 files changed, 95 insertions(+), 108 deletions(-)

(limited to 'kernel/time')

diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c
index ced4aae8b804..04dcc5e5d4c1 100644
--- a/arch/alpha/kernel/core_marvel.c
+++ b/arch/alpha/kernel/core_marvel.c
@@ -662,7 +662,7 @@ __marvel_rtc_io(u8 b, unsigned long addr, int write)
 		if (smp_processor_id() != boot_cpuid)
 			smp_call_function_single(boot_cpuid,
 						 __marvel_access_rtc,
-						 &rtc_access, 1, 1);
+						 &rtc_access, 1);
 		else
 			__marvel_access_rtc(&rtc_access);
 #else
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 95c905be9154..44114c8dbb2a 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -710,7 +710,7 @@ flush_tlb_mm(struct mm_struct *mm)
 		}
 	}
 
-	if (smp_call_function(ipi_flush_tlb_mm, mm, 1, 1)) {
+	if (smp_call_function(ipi_flush_tlb_mm, mm, 1)) {
 		printk(KERN_CRIT "flush_tlb_mm: timed out\n");
 	}
 
@@ -763,7 +763,7 @@ flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 	data.mm = mm;
 	data.addr = addr;
 
-	if (smp_call_function(ipi_flush_tlb_page, &data, 1, 1)) {
+	if (smp_call_function(ipi_flush_tlb_page, &data, 1)) {
 		printk(KERN_CRIT "flush_tlb_page: timed out\n");
 	}
 
@@ -815,7 +815,7 @@ flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
 		}
 	}
 
-	if (smp_call_function(ipi_flush_icache_page, mm, 1, 1)) {
+	if (smp_call_function(ipi_flush_icache_page, mm, 1)) {
 		printk(KERN_CRIT "flush_icache_page: timed out\n");
 	}
 
diff --git a/arch/alpha/oprofile/common.c b/arch/alpha/oprofile/common.c
index 9fc0eeb4f0ab..7c3d5ec6ec67 100644
--- a/arch/alpha/oprofile/common.c
+++ b/arch/alpha/oprofile/common.c
@@ -65,7 +65,7 @@ op_axp_setup(void)
 	model->reg_setup(&reg, ctr, &sys);
 
 	/* Configure the registers on all cpus.  */
-	(void)smp_call_function(model->cpu_setup, &reg, 0, 1);
+	(void)smp_call_function(model->cpu_setup, &reg, 1);
 	model->cpu_setup(&reg);
 	return 0;
 }
@@ -86,7 +86,7 @@ op_axp_cpu_start(void *dummy)
 static int
 op_axp_start(void)
 {
-	(void)smp_call_function(op_axp_cpu_start, NULL, 0, 1);
+	(void)smp_call_function(op_axp_cpu_start, NULL, 1);
 	op_axp_cpu_start(NULL);
 	return 0;
 }
@@ -101,7 +101,7 @@ op_axp_cpu_stop(void *dummy)
 static void
 op_axp_stop(void)
 {
-	(void)smp_call_function(op_axp_cpu_stop, NULL, 0, 1);
+	(void)smp_call_function(op_axp_cpu_stop, NULL, 1);
 	op_axp_cpu_stop(NULL);
 }
 
diff --git a/arch/arm/oprofile/op_model_mpcore.c b/arch/arm/oprofile/op_model_mpcore.c
index 74fae6045650..4458705021e0 100644
--- a/arch/arm/oprofile/op_model_mpcore.c
+++ b/arch/arm/oprofile/op_model_mpcore.c
@@ -201,7 +201,7 @@ static int em_call_function(int (*fn)(void))
 	data.ret = 0;
 
 	preempt_disable();
-	smp_call_function(em_func, &data, 1, 1);
+	smp_call_function(em_func, &data, 1);
 	em_func(&data);
 	preempt_enable();
 
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 32455c633f1c..c0d2c9bb952b 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -352,7 +352,7 @@ static int __init vfp_init(void)
 	else if (vfpsid & FPSID_NODOUBLE) {
 		printk("no double precision support\n");
 	} else {
-		smp_call_function(vfp_enable, NULL, 1, 1);
+		smp_call_function(vfp_enable, NULL, 1);
 
 		VFP_arch = (vfpsid & FPSID_ARCH_MASK) >> FPSID_ARCH_BIT;  /* Extract the architecture version */
 		printk("implementor %02x architecture %d part %02x variant %x rev %x\n",
diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c
index a9c3334e46c9..952a24b2f5a9 100644
--- a/arch/cris/arch-v32/kernel/smp.c
+++ b/arch/cris/arch-v32/kernel/smp.c
@@ -194,7 +194,7 @@ void stop_this_cpu(void* dummy)
 /* Other calls */
 void smp_send_stop(void)
 {
-	smp_call_function(stop_this_cpu, NULL, 1, 0);
+	smp_call_function(stop_this_cpu, NULL, 0);
 }
 
 int setup_profiling_timer(unsigned int multiplier)
@@ -316,8 +316,7 @@ int send_ipi(int vector, int wait, cpumask_t cpu_mask)
  * 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)
+int smp_call_function(void (*func)(void *info), void *info, int wait)
 {
 	cpumask_t cpu_mask = CPU_MASK_ALL;
 	struct call_data_struct data;
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 705176b434b3..9cd818cc7008 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1881,7 +1881,7 @@ static int __cpuinit mca_cpu_callback(struct notifier_block *nfb,
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
 		smp_call_function_single(hotcpu, ia64_mca_cmc_vector_adjust,
-					 NULL, 1, 0);
+					 NULL, 0);
 		break;
 	}
 	return NOTIFY_OK;
diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c
index 9dc00f7fe10e..e5c57f413ca2 100644
--- a/arch/ia64/kernel/palinfo.c
+++ b/arch/ia64/kernel/palinfo.c
@@ -921,7 +921,7 @@ int palinfo_handle_smp(pal_func_cpu_u_t *f, char *page)
 
 
 	/* will send IPI to other CPU and wait for completion of remote call */
-	if ((ret=smp_call_function_single(f->req_cpu, palinfo_smp_call, &ptr, 0, 1))) {
+	if ((ret=smp_call_function_single(f->req_cpu, palinfo_smp_call, &ptr, 1))) {
 		printk(KERN_ERR "palinfo: remote CPU call from %d to %d on function %d: "
 		       "error %d\n", smp_processor_id(), f->req_cpu, f->func_id, ret);
 		return 0;
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 7714a97b0104..9baa48255c12 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -1820,7 +1820,7 @@ pfm_syswide_cleanup_other_cpu(pfm_context_t *ctx)
 	int ret;
 
 	DPRINT(("calling CPU%d for cleanup\n", ctx->ctx_cpu));
-	ret = smp_call_function_single(ctx->ctx_cpu, pfm_syswide_force_stop, ctx, 0, 1);
+	ret = smp_call_function_single(ctx->ctx_cpu, pfm_syswide_force_stop, ctx, 1);
 	DPRINT(("called CPU%d for cleanup ret=%d\n", ctx->ctx_cpu, ret));
 }
 #endif /* CONFIG_SMP */
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index a3a34b4eb038..fabaf08d9a69 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -286,7 +286,7 @@ void cpu_idle_wait(void)
 {
 	smp_mb();
 	/* kick all the CPUs so that they exit out of pm_idle */
-	smp_call_function(do_nothing, NULL, 0, 1);
+	smp_call_function(do_nothing, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(cpu_idle_wait);
 
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index eaa1b6795a13..9d1d429c6c59 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -317,7 +317,7 @@ ia64_sync_itc (unsigned int master)
 
 	go[MASTER] = 1;
 
-	if (smp_call_function_single(master, sync_master, NULL, 1, 0) < 0) {
+	if (smp_call_function_single(master, sync_master, NULL, 0) < 0) {
 		printk(KERN_ERR "sync_itc: failed to get attention of CPU %u!\n", master);
 		return;
 	}
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index e77995a6e3ed..8eff8c1d40a6 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -123,8 +123,7 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid)
 	status = ia64_pal_prefetch_visibility(PAL_VISIBILITY_PHYSICAL);
 	if (status == PAL_VISIBILITY_OK_REMOTE_NEEDED) {
 		atomic_set(&uc_pool->status, 0);
-		status = smp_call_function(uncached_ipi_visibility, uc_pool,
-					   0, 1);
+		status = smp_call_function(uncached_ipi_visibility, uc_pool, 1);
 		if (status || atomic_read(&uc_pool->status))
 			goto failed;
 	} else if (status != PAL_VISIBILITY_OK)
@@ -146,7 +145,7 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid)
 	if (status != PAL_STATUS_SUCCESS)
 		goto failed;
 	atomic_set(&uc_pool->status, 0);
-	status = smp_call_function(uncached_ipi_mc_drain, uc_pool, 0, 1);
+	status = smp_call_function(uncached_ipi_mc_drain, uc_pool, 1);
 	if (status || atomic_read(&uc_pool->status))
 		goto failed;
 
diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
index 8cc0c4753d89..636588e7e068 100644
--- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c
+++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
@@ -629,7 +629,7 @@ static int sn_hwperf_op_cpu(struct sn_hwperf_op_info *op_info)
 		if (use_ipi) {
 			/* use an interprocessor interrupt to call SAL */
 			smp_call_function_single(cpu, sn_hwperf_call_sal,
-				op_info, 1, 1);
+				op_info, 1);
 		}
 		else {
 			/* migrate the task before calling SAL */ 
diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c
index 74eb7bcd5a40..7577f971ea4e 100644
--- a/arch/m32r/kernel/smp.c
+++ b/arch/m32r/kernel/smp.c
@@ -212,7 +212,7 @@ void smp_flush_tlb_all(void)
 	local_irq_save(flags);
 	__flush_tlb_all();
 	local_irq_restore(flags);
-	smp_call_function(flush_tlb_all_ipi, NULL, 1, 1);
+	smp_call_function(flush_tlb_all_ipi, NULL, 1);
 	preempt_enable();
 }
 
@@ -505,7 +505,7 @@ void smp_invalidate_interrupt(void)
  *==========================================================================*/
 void smp_send_stop(void)
 {
-	smp_call_function(stop_this_cpu, NULL, 1, 0);
+	smp_call_function(stop_this_cpu, NULL, 0);
 }
 
 /*==========================================================================*
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index c75b26cb61df..7a9ae830be86 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -167,7 +167,7 @@ static void stop_this_cpu(void *dummy)
 
 void smp_send_stop(void)
 {
-	smp_call_function(stop_this_cpu, NULL, 1, 0);
+	smp_call_function(stop_this_cpu, NULL, 0);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
@@ -266,7 +266,7 @@ static void flush_tlb_mm_ipi(void *mm)
 static inline void smp_on_other_tlbs(void (*func) (void *info), void *info)
 {
 #ifndef CONFIG_MIPS_MT_SMTC
-	smp_call_function(func, info, 1, 1);
+	smp_call_function(func, info, 1);
 #endif
 }
 
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 27096751ddce..71df3390c07b 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -43,12 +43,12 @@
  *    primary cache.
  */
 static inline void r4k_on_each_cpu(void (*func) (void *info), void *info,
-                                   int retry, int wait)
+                                   int wait)
 {
 	preempt_disable();
 
 #if !defined(CONFIG_MIPS_MT_SMP) && !defined(CONFIG_MIPS_MT_SMTC)
-	smp_call_function(func, info, retry, wait);
+	smp_call_function(func, info, wait);
 #endif
 	func(info);
 	preempt_enable();
@@ -350,7 +350,7 @@ static inline void local_r4k___flush_cache_all(void * args)
 
 static void r4k___flush_cache_all(void)
 {
-	r4k_on_each_cpu(local_r4k___flush_cache_all, NULL, 1, 1);
+	r4k_on_each_cpu(local_r4k___flush_cache_all, NULL, 1);
 }
 
 static inline int has_valid_asid(const struct mm_struct *mm)
@@ -397,7 +397,7 @@ static void r4k_flush_cache_range(struct vm_area_struct *vma,
 	int exec = vma->vm_flags & VM_EXEC;
 
 	if (cpu_has_dc_aliases || (exec && !cpu_has_ic_fills_f_dc))
-		r4k_on_each_cpu(local_r4k_flush_cache_range, vma, 1, 1);
+		r4k_on_each_cpu(local_r4k_flush_cache_range, vma, 1);
 }
 
 static inline void local_r4k_flush_cache_mm(void * args)
@@ -429,7 +429,7 @@ static void r4k_flush_cache_mm(struct mm_struct *mm)
 	if (!cpu_has_dc_aliases)
 		return;
 
-	r4k_on_each_cpu(local_r4k_flush_cache_mm, mm, 1, 1);
+	r4k_on_each_cpu(local_r4k_flush_cache_mm, mm, 1);
 }
 
 struct flush_cache_page_args {
@@ -521,7 +521,7 @@ static void r4k_flush_cache_page(struct vm_area_struct *vma,
 	args.addr = addr;
 	args.pfn = pfn;
 
-	r4k_on_each_cpu(local_r4k_flush_cache_page, &args, 1, 1);
+	r4k_on_each_cpu(local_r4k_flush_cache_page, &args, 1);
 }
 
 static inline void local_r4k_flush_data_cache_page(void * addr)
@@ -535,7 +535,7 @@ static void r4k_flush_data_cache_page(unsigned long addr)
 		local_r4k_flush_data_cache_page((void *)addr);
 	else
 		r4k_on_each_cpu(local_r4k_flush_data_cache_page, (void *) addr,
-			        1, 1);
+			        1);
 }
 
 struct flush_icache_range_args {
@@ -571,7 +571,7 @@ static void r4k_flush_icache_range(unsigned long start, unsigned long end)
 	args.start = start;
 	args.end = end;
 
-	r4k_on_each_cpu(local_r4k_flush_icache_range, &args, 1, 1);
+	r4k_on_each_cpu(local_r4k_flush_icache_range, &args, 1);
 	instruction_hazard();
 }
 
@@ -672,7 +672,7 @@ static void local_r4k_flush_cache_sigtramp(void * arg)
 
 static void r4k_flush_cache_sigtramp(unsigned long addr)
 {
-	r4k_on_each_cpu(local_r4k_flush_cache_sigtramp, (void *) addr, 1, 1);
+	r4k_on_each_cpu(local_r4k_flush_cache_sigtramp, (void *) addr, 1);
 }
 
 static void r4k_flush_icache_all(void)
diff --git a/arch/mips/pmc-sierra/yosemite/prom.c b/arch/mips/pmc-sierra/yosemite/prom.c
index 35dc435846a6..cf4c868715ac 100644
--- a/arch/mips/pmc-sierra/yosemite/prom.c
+++ b/arch/mips/pmc-sierra/yosemite/prom.c
@@ -64,7 +64,7 @@ static void prom_exit(void)
 #ifdef CONFIG_SMP
 	if (smp_processor_id())
 		/* CPU 1 */
-		smp_call_function(prom_cpu0_exit, NULL, 1, 1);
+		smp_call_function(prom_cpu0_exit, NULL, 1);
 #endif
 	prom_cpu0_exit(NULL);
 }
diff --git a/arch/mips/sibyte/cfe/setup.c b/arch/mips/sibyte/cfe/setup.c
index 33fce826f8bf..fd9604d5555a 100644
--- a/arch/mips/sibyte/cfe/setup.c
+++ b/arch/mips/sibyte/cfe/setup.c
@@ -74,7 +74,7 @@ static void __noreturn cfe_linux_exit(void *arg)
 		if (!reboot_smp) {
 			/* Get CPU 0 to do the cfe_exit */
 			reboot_smp = 1;
-			smp_call_function(cfe_linux_exit, arg, 1, 0);
+			smp_call_function(cfe_linux_exit, arg, 0);
 		}
 	} else {
 		printk("Passing control back to CFE...\n");
diff --git a/arch/mips/sibyte/sb1250/prom.c b/arch/mips/sibyte/sb1250/prom.c
index cf8f6b3de86c..65b1af66b674 100644
--- a/arch/mips/sibyte/sb1250/prom.c
+++ b/arch/mips/sibyte/sb1250/prom.c
@@ -66,7 +66,7 @@ static void prom_linux_exit(void)
 {
 #ifdef CONFIG_SMP
 	if (smp_processor_id()) {
-		smp_call_function(prom_cpu0_exit, NULL, 1, 1);
+		smp_call_function(prom_cpu0_exit, NULL, 1);
 	}
 #endif
 	while(1);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 37a5ab410dcc..5191b46a611e 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -168,7 +168,7 @@ static void stop_this_cpu(void *dummy)
 
 void smp_send_stop(void)
 {
-	smp_call_function(stop_this_cpu, NULL, 0, 0);
+	smp_call_function(stop_this_cpu, NULL, 0);
 }
 
 extern struct gettimeofday_struct do_gtod;
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index ad40729bec3d..837a3b3e7759 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -209,7 +209,7 @@ __appldata_vtimer_setup(int cmd)
 			per_cpu(appldata_timer, i).expires = per_cpu_interval;
 			smp_call_function_single(i, add_virt_timer_periodic,
 						 &per_cpu(appldata_timer, i),
-						 0, 1);
+						 1);
 		}
 		appldata_timer_active = 1;
 		P_INFO("Monitoring timer started.\n");
@@ -236,7 +236,7 @@ __appldata_vtimer_setup(int cmd)
 			args.timer = &per_cpu(appldata_timer, i);
 			args.expires = per_cpu_interval;
 			smp_call_function_single(i, __appldata_mod_vtimer_wrap,
-						 &args, 0, 1);
+						 &args, 1);
 		}
 	}
 }
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 5d4fa4b1c74c..276b105fb2a4 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -109,7 +109,7 @@ static void do_call_function(void)
 }
 
 static void __smp_call_function_map(void (*func) (void *info), void *info,
-				    int nonatomic, int wait, cpumask_t map)
+				    int wait, cpumask_t map)
 {
 	struct call_data_struct data;
 	int cpu, local = 0;
@@ -162,7 +162,6 @@ out:
  * smp_call_function:
  * @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
  *
  * Run a function on all other CPUs.
@@ -170,15 +169,14 @@ out:
  * You must not call this function with disabled interrupts, from a
  * hardware interrupt handler or from a bottom half.
  */
-int smp_call_function(void (*func) (void *info), void *info, int nonatomic,
-		      int wait)
+int smp_call_function(void (*func) (void *info), void *info, int wait)
 {
 	cpumask_t map;
 
 	spin_lock(&call_lock);
 	map = cpu_online_map;
 	cpu_clear(smp_processor_id(), map);
-	__smp_call_function_map(func, info, nonatomic, wait, map);
+	__smp_call_function_map(func, info, wait, map);
 	spin_unlock(&call_lock);
 	return 0;
 }
@@ -189,7 +187,6 @@ EXPORT_SYMBOL(smp_call_function);
  * @cpu: the CPU where func should run
  * @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
  *
  * Run a function on one processor.
@@ -198,11 +195,10 @@ EXPORT_SYMBOL(smp_call_function);
  * hardware interrupt handler or from a bottom half.
  */
 int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
-			     int nonatomic, int wait)
+			     int wait)
 {
 	spin_lock(&call_lock);
-	__smp_call_function_map(func, info, nonatomic, wait,
-				cpumask_of_cpu(cpu));
+	__smp_call_function_map(func, info, wait, cpumask_of_cpu(cpu));
 	spin_unlock(&call_lock);
 	return 0;
 }
@@ -228,7 +224,7 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
 {
 	spin_lock(&call_lock);
 	cpu_clear(smp_processor_id(), mask);
-	__smp_call_function_map(func, info, 0, wait, mask);
+	__smp_call_function_map(func, info, wait, mask);
 	spin_unlock(&call_lock);
 	return 0;
 }
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 7aec676fefd5..bf7bf2c2236a 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -690,7 +690,7 @@ static int etr_sync_clock(struct etr_aib *aib, int port)
 	 */
 	memset(&etr_sync, 0, sizeof(etr_sync));
 	preempt_disable();
-	smp_call_function(etr_sync_cpu_start, NULL, 0, 0);
+	smp_call_function(etr_sync_cpu_start, NULL, 0);
 	local_irq_disable();
 	etr_enable_sync_clock();
 
@@ -729,7 +729,7 @@ static int etr_sync_clock(struct etr_aib *aib, int port)
 		rc = -EAGAIN;
 	}
 	local_irq_enable();
-	smp_call_function(etr_sync_cpu_end,NULL,0,0);
+	smp_call_function(etr_sync_cpu_end,NULL,0);
 	preempt_enable();
 	return rc;
 }
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index 2ed8dceb297b..71781ba2675b 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -168,7 +168,7 @@ static void stop_this_cpu(void *unused)
 
 void smp_send_stop(void)
 {
-	smp_call_function(stop_this_cpu, 0, 1, 0);
+	smp_call_function(stop_this_cpu, 0, 0);
 }
 
 void arch_send_call_function_ipi(cpumask_t mask)
@@ -223,7 +223,7 @@ void flush_tlb_mm(struct mm_struct *mm)
 	preempt_disable();
 
 	if ((atomic_read(&mm->mm_users) != 1) || (current->mm != mm)) {
-		smp_call_function(flush_tlb_mm_ipi, (void *)mm, 1, 1);
+		smp_call_function(flush_tlb_mm_ipi, (void *)mm, 1);
 	} else {
 		int i;
 		for (i = 0; i < num_online_cpus(); i++)
@@ -260,7 +260,7 @@ void flush_tlb_range(struct vm_area_struct *vma,
 		fd.vma = vma;
 		fd.addr1 = start;
 		fd.addr2 = end;
-		smp_call_function(flush_tlb_range_ipi, (void *)&fd, 1, 1);
+		smp_call_function(flush_tlb_range_ipi, (void *)&fd, 1);
 	} else {
 		int i;
 		for (i = 0; i < num_online_cpus(); i++)
@@ -303,7 +303,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
 
 		fd.vma = vma;
 		fd.addr1 = page;
-		smp_call_function(flush_tlb_page_ipi, (void *)&fd, 1, 1);
+		smp_call_function(flush_tlb_page_ipi, (void *)&fd, 1);
 	} else {
 		int i;
 		for (i = 0; i < num_online_cpus(); i++)
@@ -327,6 +327,6 @@ void flush_tlb_one(unsigned long asid, unsigned long vaddr)
 	fd.addr1 = asid;
 	fd.addr2 = vaddr;
 
-	smp_call_function(flush_tlb_one_ipi, (void *)&fd, 1, 1);
+	smp_call_function(flush_tlb_one_ipi, (void *)&fd, 1);
 	local_flush_tlb_one(asid, vaddr);
 }
diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c
index b82d017a1744..c099d96f1239 100644
--- a/arch/sparc64/kernel/smp.c
+++ b/arch/sparc64/kernel/smp.c
@@ -807,7 +807,6 @@ extern unsigned long xcall_call_function;
  * 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: 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
@@ -817,8 +816,7 @@ extern unsigned long xcall_call_function;
  * hardware interrupt handler or from a bottom half handler.
  */
 static int sparc64_smp_call_function_mask(void (*func)(void *info), void *info,
-					  int nonatomic, int wait,
-					  cpumask_t mask)
+					  int wait, cpumask_t mask)
 {
 	struct call_data_struct data;
 	int cpus;
@@ -853,11 +851,9 @@ out_unlock:
 	return 0;
 }
 
-int smp_call_function(void (*func)(void *info), void *info,
-		      int nonatomic, int wait)
+int smp_call_function(void (*func)(void *info), void *info, int wait)
 {
-	return sparc64_smp_call_function_mask(func, info, nonatomic, wait,
-						cpu_online_map);
+	return sparc64_smp_call_function_mask(func, info, wait, cpu_online_map);
 }
 
 void smp_call_function_client(int irq, struct pt_regs *regs)
@@ -894,7 +890,7 @@ static void tsb_sync(void *info)
 
 void smp_tsb_sync(struct mm_struct *mm)
 {
-	sparc64_smp_call_function_mask(tsb_sync, mm, 0, 1, mm->cpu_vm_mask);
+	sparc64_smp_call_function_mask(tsb_sync, mm, 1, mm->cpu_vm_mask);
 }
 
 extern unsigned long xcall_flush_tlb_mm;
diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c
index e1062ec36d40..be2d50c3aa95 100644
--- a/arch/um/kernel/smp.c
+++ b/arch/um/kernel/smp.c
@@ -214,8 +214,7 @@ void smp_call_function_slave(int cpu)
 	atomic_inc(&scf_finished);
 }
 
-int smp_call_function(void (*_func)(void *info), void *_info, int nonatomic,
-		      int wait)
+int smp_call_function(void (*_func)(void *info), void *_info, int wait)
 {
 	int cpus = num_online_cpus() - 1;
 	int i;
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 6a1e278d9323..290652cefddb 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -222,7 +222,7 @@ static void set_mtrr(unsigned int reg, unsigned long base,
 	atomic_set(&data.gate,0);
 
 	/*  Start the ball rolling on other CPUs  */
-	if (smp_call_function(ipi_handler, &data, 1, 0) != 0)
+	if (smp_call_function(ipi_handler, &data, 0) != 0)
 		panic("mtrr: timed out waiting for other CPUs\n");
 
 	local_irq_save(flags);
@@ -822,7 +822,7 @@ void mtrr_ap_init(void)
  */
 void mtrr_save_state(void)
 {
-	smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1);
+	smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1);
 }
 
 static int __init mtrr_init_finialize(void)
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index daff52a62248..336dd43c9158 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -95,7 +95,7 @@ static ssize_t cpuid_read(struct file *file, char __user *buf,
 	for (; count; count -= 16) {
 		cmd.eax = pos;
 		cmd.ecx = pos >> 32;
-		smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1, 1);
+		smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1);
 		if (copy_to_user(tmp, &cmd, 16))
 			return -EFAULT;
 		tmp += 16;
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 0224c3637c73..cb0a6398c64b 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -68,7 +68,7 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
 		load_LDT(pc);
 		mask = cpumask_of_cpu(smp_processor_id());
 		if (!cpus_equal(current->mm->cpu_vm_mask, mask))
-			smp_call_function(flush_ldt, NULL, 1, 1);
+			smp_call_function(flush_ldt, NULL, 1);
 		preempt_enable();
 #else
 		load_LDT(pc);
diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c
index 84160f74eeb0..5562dab0bd20 100644
--- a/arch/x86/kernel/nmi_32.c
+++ b/arch/x86/kernel/nmi_32.c
@@ -87,7 +87,7 @@ int __init check_nmi_watchdog(void)
 
 #ifdef CONFIG_SMP
 	if (nmi_watchdog == NMI_LOCAL_APIC)
-		smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0);
+		smp_call_function(nmi_cpu_busy, (void *)&endflag, 0);
 #endif
 
 	for_each_possible_cpu(cpu)
diff --git a/arch/x86/kernel/nmi_64.c b/arch/x86/kernel/nmi_64.c
index 5a29ded994fa..2f1e4f503c9e 100644
--- a/arch/x86/kernel/nmi_64.c
+++ b/arch/x86/kernel/nmi_64.c
@@ -96,7 +96,7 @@ int __init check_nmi_watchdog(void)
 
 #ifdef CONFIG_SMP
 	if (nmi_watchdog == NMI_LOCAL_APIC)
-		smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0);
+		smp_call_function(nmi_cpu_busy, (void *)&endflag, 0);
 #endif
 
 	for (cpu = 0; cpu < NR_CPUS; cpu++)
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 575aa3d7248a..56546e8a13ac 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -164,7 +164,7 @@ static void native_smp_send_stop(void)
 	if (reboot_force)
 		return;
 
-	smp_call_function(stop_this_cpu, NULL, 0, 0);
+	smp_call_function(stop_this_cpu, NULL, 0);
 	local_irq_save(flags);
 	disable_local_APIC();
 	local_irq_restore(flags);
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 61efa2f7d564..0a03d57f9b3b 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -278,7 +278,7 @@ cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg)
 {
 	long cpu = (long)arg;
 	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
-		smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 0, 1);
+		smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 1);
 	return NOTIFY_DONE;
 }
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 540e95179074..5534fe59b5fc 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -335,7 +335,7 @@ static void vcpu_clear(struct vcpu_vmx *vmx)
 {
 	if (vmx->vcpu.cpu == -1)
 		return;
-	smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear, vmx, 0, 1);
+	smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear, vmx, 1);
 	vmx->launched = 0;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 63a77caa59f1..0faa2546b1cd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4044,6 +4044,6 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 	 * So need not to call smp_call_function_single() in that case.
 	 */
 	if (vcpu->guest_mode && vcpu->cpu != cpu)
-		smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0, 0);
+		smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0);
 	put_cpu();
 }
diff --git a/arch/x86/lib/msr-on-cpu.c b/arch/x86/lib/msr-on-cpu.c
index 57d043fa893e..d5a2b39f882b 100644
--- a/arch/x86/lib/msr-on-cpu.c
+++ b/arch/x86/lib/msr-on-cpu.c
@@ -30,10 +30,10 @@ static int _rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h, int safe)
 
 	rv.msr_no = msr_no;
 	if (safe) {
-		smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 0, 1);
+		smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1);
 		err = rv.err;
 	} else {
-		smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 0, 1);
+		smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
 	}
 	*l = rv.l;
 	*h = rv.h;
@@ -64,10 +64,10 @@ static int _wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h, int safe)
 	rv.l = l;
 	rv.h = h;
 	if (safe) {
-		smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 0, 1);
+		smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1);
 		err = rv.err;
 	} else {
-		smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 0, 1);
+		smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
 	}
 
 	return err;
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index cb34407a9930..04f596eab749 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -1113,7 +1113,7 @@ int safe_smp_processor_id(void)
 /* broadcast a halt to all other CPUs */
 static void voyager_smp_send_stop(void)
 {
-	smp_call_function(smp_stop_cpu_function, NULL, 1, 1);
+	smp_call_function(smp_stop_cpu_function, NULL, 1);
 }
 
 /* this function is triggered in time.c when a clock tick fires
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index b3786e749b8e..a1651d029ea8 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -331,7 +331,7 @@ static void stop_self(void *v)
 
 void xen_smp_send_stop(void)
 {
-	smp_call_function(stop_self, NULL, 0, 0);
+	smp_call_function(stop_self, NULL, 0);
 }
 
 void xen_smp_send_reschedule(int cpu)
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 556ee1585192..4976e5db2b3f 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -1339,7 +1339,7 @@ static void smp_callback(void *v)
 static int acpi_processor_latency_notify(struct notifier_block *b,
 		unsigned long l, void *v)
 {
-	smp_call_function(smp_callback, NULL, 0, 1);
+	smp_call_function(smp_callback, NULL, 1);
 	return NOTIFY_OK;
 }
 
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 23554b676d6e..5405769020a1 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -340,7 +340,7 @@ static void smp_callback(void *v)
 static int cpuidle_latency_notify(struct notifier_block *b,
 		unsigned long l, void *v)
 {
-	smp_call_function(smp_callback, NULL, 0, 1);
+	smp_call_function(smp_callback, NULL, 1);
 	return NOTIFY_OK;
 }
 
diff --git a/include/asm-alpha/smp.h b/include/asm-alpha/smp.h
index 2f60a362d75e..544c69af8168 100644
--- a/include/asm-alpha/smp.h
+++ b/include/asm-alpha/smp.h
@@ -53,7 +53,7 @@ extern void arch_send_call_function_ipi(cpumask_t mask);
 #else /* CONFIG_SMP */
 
 #define hard_smp_processor_id()		0
-#define smp_call_function_on_cpu(func,info,retry,wait,cpu)    ({ 0; })
+#define smp_call_function_on_cpu(func,info,wait,cpu)    ({ 0; })
 
 #endif /* CONFIG_SMP */
 
diff --git a/include/asm-sparc/smp.h b/include/asm-sparc/smp.h
index e6d561599726..b61e74bea06a 100644
--- a/include/asm-sparc/smp.h
+++ b/include/asm-sparc/smp.h
@@ -72,7 +72,7 @@ static inline void xc5(smpfunc_t func, unsigned long arg1, unsigned long arg2,
 			   unsigned long arg3, unsigned long arg4, unsigned long arg5)
 { smp_cross_call(func, arg1, arg2, arg3, arg4, arg5); }
 
-static inline int smp_call_function(void (*func)(void *info), void *info, int nonatomic, int wait)
+static inline int smp_call_function(void (*func)(void *info), void *info, int wait)
 {
 	xc1((smpfunc_t)func, (unsigned long)info);
 	return 0;
diff --git a/include/linux/smp.h b/include/linux/smp.h
index eac3e062250f..338cad1b9548 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -62,11 +62,11 @@ extern void smp_cpus_done(unsigned int max_cpus);
 /*
  * Call a function on all other processors
  */
-int smp_call_function(void(*func)(void *info), void *info, int retry, int wait);
+int smp_call_function(void(*func)(void *info), void *info, int wait);
 int smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info,
 				int wait);
 int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
-				int retry, int wait);
+				int wait);
 void __smp_call_function_single(int cpuid, struct call_single_data *data);
 
 /*
@@ -119,7 +119,7 @@ static inline int up_smp_call_function(void (*func)(void *), void *info)
 {
 	return 0;
 }
-#define smp_call_function(func, info, retry, wait) \
+#define smp_call_function(func, info, wait) \
 			(up_smp_call_function(func, info))
 #define on_each_cpu(func,info,retry,wait)	\
 	({					\
@@ -131,7 +131,7 @@ static inline int up_smp_call_function(void (*func)(void *), void *info)
 static inline void smp_send_reschedule(int cpu) { }
 #define num_booting_cpus()			1
 #define smp_prepare_boot_cpu()			do {} while (0)
-#define smp_call_function_single(cpuid, func, info, retry, wait) \
+#define smp_call_function_single(cpuid, func, info, wait) \
 ({ \
 	WARN_ON(cpuid != 0);	\
 	local_irq_disable();	\
diff --git a/kernel/smp.c b/kernel/smp.c
index f77b75c027ad..7e0432a4a0e2 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -195,7 +195,6 @@ void generic_smp_call_function_single_interrupt(void)
  * smp_call_function_single - 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.
- * @retry: Unused
  * @wait: If true, wait until function has completed on other CPUs.
  *
  * Returns 0 on success, else a negative status code. Note that @wait
@@ -203,7 +202,7 @@ void generic_smp_call_function_single_interrupt(void)
  * we fall back to on-stack allocation.
  */
 int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
-			     int retry, int wait)
+			     int wait)
 {
 	struct call_single_data d;
 	unsigned long flags;
@@ -339,7 +338,6 @@ EXPORT_SYMBOL(smp_call_function_mask);
  * 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.
- * @natomic: Unused
  * @wait: If true, wait (atomically) until function has completed on other CPUs.
  *
  * Returns 0 on success, else a negative status code.
@@ -351,7 +349,7 @@ EXPORT_SYMBOL(smp_call_function_mask);
  * 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 *), void *info, int natomic, int wait)
+int smp_call_function(void (*func)(void *), void *info, int wait)
 {
 	int ret;
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 36e061740047..d73afb4764ef 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -679,7 +679,7 @@ int on_each_cpu(void (*func) (void *info), void *info, int retry, int wait)
 	int ret = 0;
 
 	preempt_disable();
-	ret = smp_call_function(func, info, retry, wait);
+	ret = smp_call_function(func, info, wait);
 	local_irq_disable();
 	func(info);
 	local_irq_enable();
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 57a1f02e5ec0..75e718539dcb 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -266,7 +266,7 @@ void tick_broadcast_on_off(unsigned long reason, int *oncpu)
 		       "offline CPU #%d\n", *oncpu);
 	else
 		smp_call_function_single(*oncpu, tick_do_broadcast_on_off,
-					 &reason, 1, 1);
+					 &reason, 1);
 }
 
 /*
diff --git a/net/core/flow.c b/net/core/flow.c
index 19991175fdeb..5cf81052d044 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -298,7 +298,7 @@ void flow_cache_flush(void)
 	init_completion(&info.completion);
 
 	local_bh_disable();
-	smp_call_function(flow_cache_flush_per_cpu, &info, 1, 0);
+	smp_call_function(flow_cache_flush_per_cpu, &info, 0);
 	flow_cache_flush_tasklet((unsigned long)&info);
 	local_bh_enable();
 
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index 918970762131..94d5a45c3a57 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -480,7 +480,7 @@ static void iucv_setmask_mp(void)
 		if (cpu_isset(cpu, iucv_buffer_cpumask) &&
 		    !cpu_isset(cpu, iucv_irq_cpumask))
 			smp_call_function_single(cpu, iucv_allow_cpu,
-						 NULL, 0, 1);
+						 NULL, 1);
 	preempt_enable();
 }
 
@@ -498,7 +498,7 @@ static void iucv_setmask_up(void)
 	cpumask = iucv_irq_cpumask;
 	cpu_clear(first_cpu(iucv_irq_cpumask), cpumask);
 	for_each_cpu_mask(cpu, cpumask)
-		smp_call_function_single(cpu, iucv_block_cpu, NULL, 0, 1);
+		smp_call_function_single(cpu, iucv_block_cpu, NULL, 1);
 }
 
 /**
@@ -523,7 +523,7 @@ static int iucv_enable(void)
 	rc = -EIO;
 	preempt_disable();
 	for_each_online_cpu(cpu)
-		smp_call_function_single(cpu, iucv_declare_cpu, NULL, 0, 1);
+		smp_call_function_single(cpu, iucv_declare_cpu, NULL, 1);
 	preempt_enable();
 	if (cpus_empty(iucv_buffer_cpumask))
 		/* No cpu could declare an iucv buffer. */
@@ -580,7 +580,7 @@ static int __cpuinit iucv_cpu_notify(struct notifier_block *self,
 	case CPU_ONLINE_FROZEN:
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
-		smp_call_function_single(cpu, iucv_declare_cpu, NULL, 0, 1);
+		smp_call_function_single(cpu, iucv_declare_cpu, NULL, 1);
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
@@ -589,10 +589,10 @@ static int __cpuinit iucv_cpu_notify(struct notifier_block *self,
 		if (cpus_empty(cpumask))
 			/* Can't offline last IUCV enabled cpu. */
 			return NOTIFY_BAD;
-		smp_call_function_single(cpu, iucv_retrieve_cpu, NULL, 0, 1);
+		smp_call_function_single(cpu, iucv_retrieve_cpu, NULL, 1);
 		if (cpus_empty(iucv_irq_cpumask))
 			smp_call_function_single(first_cpu(iucv_buffer_cpumask),
-						 iucv_allow_cpu, NULL, 0, 1);
+						 iucv_allow_cpu, NULL, 1);
 		break;
 	}
 	return NOTIFY_OK;
@@ -652,7 +652,7 @@ static void iucv_cleanup_queue(void)
 	 * pending interrupts force them to the work queue by calling
 	 * an empty function on all cpus.
 	 */
-	smp_call_function(__iucv_cleanup_queue, NULL, 0, 1);
+	smp_call_function(__iucv_cleanup_queue, NULL, 1);
 	spin_lock_irq(&iucv_queue_lock);
 	list_for_each_entry_safe(p, n, &iucv_task_queue, list) {
 		/* Remove stale work items from the task queue. */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2d29e260da3d..ea1f595f8a87 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1266,12 +1266,12 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 	case CPU_UP_CANCELED:
 		printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
 		       cpu);
-		smp_call_function_single(cpu, hardware_disable, NULL, 0, 1);
+		smp_call_function_single(cpu, hardware_disable, NULL, 1);
 		break;
 	case CPU_ONLINE:
 		printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
 		       cpu);
-		smp_call_function_single(cpu, hardware_enable, NULL, 0, 1);
+		smp_call_function_single(cpu, hardware_enable, NULL, 1);
 		break;
 	}
 	return NOTIFY_OK;
@@ -1474,7 +1474,7 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 	for_each_online_cpu(cpu) {
 		smp_call_function_single(cpu,
 				kvm_arch_check_processor_compat,
-				&r, 0, 1);
+				&r, 1);
 		if (r < 0)
 			goto out_free_1;
 	}
-- 
cgit v1.2.3


From aa276e1cafb3ce9d01d1e837bcd67e92616013ac Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 9 Jun 2008 19:15:00 +0200
Subject: x86, clockevents: add C1E aware idle function

C1E on AMD machines is like C3 but without control from the OS. Up to
now we disabled the local apic timer for those machines as it stops
when the CPU goes into C1E. This excludes those machines from high
resolution timers / dynamic ticks, which hurts especially X2 based
laptops.

The current boot time C1E detection has another, more serious flaw
as well: some BIOSes do not enable C1E until the ACPI processor module
is loaded. This causes systems to stop working after that point.

To work nicely with C1E enabled machines we use a separate idle
function, which checks on idle entry whether C1E was enabled in the
Interrupt Pending Message MSR. This allows us to do timer broadcasting
for C1E and covers the late enablement of C1E as well.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/apic_32.c    |  5 ++--
 arch/x86/kernel/apic_64.c    | 26 +----------------
 arch/x86/kernel/cpu/amd.c    | 30 --------------------
 arch/x86/kernel/cpu/amd_64.c | 25 -----------------
 arch/x86/kernel/process.c    | 66 ++++++++++++++++++++++++++++++++++++++++++++
 include/asm-x86/apic.h       |  3 --
 kernel/time/tick-broadcast.c |  6 ++--
 7 files changed, 73 insertions(+), 88 deletions(-)

(limited to 'kernel/time')

diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 4b99b1bdeb6c..c44206e731d4 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -64,9 +64,8 @@ static int enable_local_apic __initdata;
 
 /* Local APIC timer verification ok */
 static int local_apic_timer_verify_ok;
-/* Disable local APIC timer from the kernel commandline or via dmi quirk
-   or using CPU MSR check */
-int local_apic_timer_disabled;
+/* Disable local APIC timer from the kernel commandline or via dmi quirk */
+static int local_apic_timer_disabled;
 /* Local APIC timer works in C2 */
 int local_apic_timer_c2_ok;
 EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 0633cfd0dc29..a5cc8447cf4d 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -43,7 +43,7 @@
 #include <mach_ipi.h>
 #include <mach_apic.h>
 
-int disable_apic_timer __cpuinitdata;
+static int disable_apic_timer __cpuinitdata;
 static int apic_calibrate_pmtmr __initdata;
 int disable_apic;
 
@@ -422,32 +422,8 @@ void __init setup_boot_APIC_clock(void)
 	setup_APIC_timer();
 }
 
-/*
- * AMD C1E enabled CPUs have a real nasty problem: Some BIOSes set the
- * C1E flag only in the secondary CPU, so when we detect the wreckage
- * we already have enabled the boot CPU local apic timer. Check, if
- * disable_apic_timer is set and the DUMMY flag is cleared. If yes,
- * set the DUMMY flag again and force the broadcast mode in the
- * clockevents layer.
- */
-static void __cpuinit check_boot_apic_timer_broadcast(void)
-{
-	if (!disable_apic_timer ||
-	    (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY))
-		return;
-
-	printk(KERN_INFO "AMD C1E detected late. Force timer broadcast.\n");
-	lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY;
-
-	local_irq_enable();
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
-			   &boot_cpu_physical_apicid);
-	local_irq_disable();
-}
-
 void __cpuinit setup_secondary_APIC_clock(void)
 {
-	check_boot_apic_timer_broadcast();
 	setup_APIC_timer();
 }
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e76b49e7a916..acc891ae5901 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -24,31 +24,6 @@
 extern void vide(void);
 __asm__(".align 4\nvide: ret");
 
-#ifdef CONFIG_X86_LOCAL_APIC
-
-/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
-static __cpuinit int amd_apic_timer_broken(struct cpuinfo_x86 *c)
-{
-	u32 lo, hi;
-
-	if (c->x86 < 0x0F)
-		return 0;
-
-	/* Family 0x0f models < rev F do not have this MSR */
-	if (c->x86 == 0x0f && c->x86_model < 0x40)
-		return 0;
-
-	rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
-	if (lo & K8_INTP_C1E_ACTIVE_MASK) {
-		if (smp_processor_id() != boot_cpu_physical_apicid)
-			printk(KERN_INFO "AMD C1E detected late. "
-			       "Force timer broadcast.\n");
-		return 1;
-	}
-	return 0;
-}
-#endif
-
 int force_mwait __cpuinitdata;
 
 static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
@@ -285,11 +260,6 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 			num_cache_leaves = 3;
 	}
 
-#ifdef CONFIG_X86_LOCAL_APIC
-	if (amd_apic_timer_broken(c))
-		local_apic_timer_disabled = 1;
-#endif
-
 	/* K6s reports MCEs but don't actually have all the MSRs */
 	if (c->x86 < 6)
 		clear_cpu_cap(c, X86_FEATURE_MCE);
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
index f5fc161d8f2a..f8d20588bde9 100644
--- a/arch/x86/kernel/cpu/amd_64.c
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -110,28 +110,6 @@ static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
 #endif
 }
 
-/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
-static __cpuinit int amd_apic_timer_broken(struct cpuinfo_x86 *c)
-{
-	u32 lo, hi;
-
-	if (c->x86 < 0x0F)
-		return 0;
-
-	/* Family 0x0f models < rev F do not have this MSR */
-	if (c->x86 == 0x0f && c->x86_model < 0x40)
-		return 0;
-
-	rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
-	if (lo & K8_INTP_C1E_ACTIVE_MASK) {
-		if (smp_processor_id() != boot_cpu_physical_apicid)
-			printk(KERN_INFO "AMD C1E detected late. "
-			       "Force timer broadcast.\n");
-		return 1;
-	}
-	return 0;
-}
-
 void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 {
 	early_init_amd_mc(c);
@@ -212,9 +190,6 @@ void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 == 0x10)
 		amd_enable_pci_ext_cfg(c);
 
-	if (amd_apic_timer_broken(c))
-		disable_apic_timer = 1;
-
 	if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
 		unsigned long long tseg;
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9fea14607dfe..68ad3539b143 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -6,6 +6,7 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/pm.h>
+#include <linux/clockchips.h>
 
 struct kmem_cache *task_xstate_cachep;
 
@@ -219,6 +220,68 @@ static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
 	return (edx & MWAIT_EDX_C1);
 }
 
+/*
+ * Check for AMD CPUs, which have potentially C1E support
+ */
+static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
+{
+	if (c->x86_vendor != X86_VENDOR_AMD)
+		return 0;
+
+	if (c->x86 < 0x0F)
+		return 0;
+
+	/* Family 0x0f models < rev F do not have C1E */
+	if (c->x86 == 0x0f && c->x86_model < 0x40)
+		return 0;
+
+	return 1;
+}
+
+/*
+ * C1E aware idle routine. We check for C1E active in the interrupt
+ * pending message MSR. If we detect C1E, then we handle it the same
+ * way as C3 power states (local apic timer and TSC stop)
+ */
+static void c1e_idle(void)
+{
+	static cpumask_t c1e_mask = CPU_MASK_NONE;
+	static int c1e_detected;
+
+	if (need_resched())
+		return;
+
+	if (!c1e_detected) {
+		u32 lo, hi;
+
+		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
+		if (lo & K8_INTP_C1E_ACTIVE_MASK) {
+			c1e_detected = 1;
+			mark_tsc_unstable("TSC halt in C1E");
+			printk(KERN_INFO "System has C1E enabled\n");
+		}
+	}
+
+	if (c1e_detected) {
+		int cpu = smp_processor_id();
+
+		if (!cpu_isset(cpu, c1e_mask)) {
+			cpu_set(cpu, c1e_mask);
+			/* Force broadcast so ACPI can not interfere */
+			clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
+					   &cpu);
+			printk(KERN_INFO "Switch to broadcast mode on CPU%d\n",
+			       cpu);
+		}
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
+		default_idle();
+		local_irq_disable();
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+		local_irq_enable();
+	} else
+		default_idle();
+}
+
 void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_SMP
@@ -236,6 +299,9 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 		 */
 		printk(KERN_INFO "using mwait in idle threads.\n");
 		pm_idle = mwait_idle;
+	} else if (check_c1e_idle(c)) {
+		printk(KERN_INFO "using C1E aware idle routine\n");
+		pm_idle = c1e_idle;
 	} else
 		pm_idle = default_idle;
 }
diff --git a/include/asm-x86/apic.h b/include/asm-x86/apic.h
index be9639a9a186..3c387cda95fa 100644
--- a/include/asm-x86/apic.h
+++ b/include/asm-x86/apic.h
@@ -38,12 +38,9 @@ extern void generic_apic_probe(void);
 extern int apic_verbosity;
 extern int timer_over_8254;
 extern int local_apic_timer_c2_ok;
-extern int local_apic_timer_disabled;
 
-extern int apic_runs_main_timer;
 extern int ioapic_force;
 extern int disable_apic;
-extern int disable_apic_timer;
 
 /*
  * Basic functions accessing APICs.
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 57a1f02e5ec0..67f80c261709 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -30,6 +30,7 @@
 struct tick_device tick_broadcast_device;
 static cpumask_t tick_broadcast_mask;
 static DEFINE_SPINLOCK(tick_broadcast_lock);
+static int tick_broadcast_force;
 
 #ifdef CONFIG_TICK_ONESHOT
 static void tick_broadcast_clear_oneshot(int cpu);
@@ -232,10 +233,11 @@ static void tick_do_broadcast_on_off(void *why)
 						     CLOCK_EVT_MODE_SHUTDOWN);
 		}
 		if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
-			dev->features |= CLOCK_EVT_FEAT_DUMMY;
+			tick_broadcast_force = 1;
 		break;
 	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
-		if (cpu_isset(cpu, tick_broadcast_mask)) {
+		if (!tick_broadcast_force &&
+		    cpu_isset(cpu, tick_broadcast_mask)) {
 			cpu_clear(cpu, tick_broadcast_mask);
 			if (td->mode == TICKDEV_MODE_PERIODIC)
 				tick_setup_periodic(dev, 0);
-- 
cgit v1.2.3


From 857f3fd7a496ddf4329345af65a4a2b16dd25fe8 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Fri, 11 Jul 2008 11:09:22 +0200
Subject: nohz: don't stop idle tick if softirqs are pending.

In case a cpu goes idle but softirqs are pending only an error message is
printed to the console. It may take a very long time until the pending
softirqs will finally be executed. Worst case would be a hanging system.

With this patch the timer tick just continues and the softirqs will be
executed after the next interrupt. Still a delay but better than a
hanging system.

Currently we have at least two device drivers on s390 which under certain
circumstances schedule a tasklet from process context. This is a reason
why we can end up with pending softirqs when going idle. Fixing these
drivers seems to be non-trivial.
However there is no question that the drivers should be fixed.
This patch shouldn't be considered as a bug fix. It just is intended to
keep a system running even if device drivers are buggy.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jan Glauber <jan.glauber@de.ibm.com>
Cc: Stefan Weinhuber <wein@de.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/time/tick-sched.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'kernel/time')

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index cb75394ed00e..86baa4f0dfe4 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -235,6 +235,7 @@ void tick_nohz_stop_sched_tick(void)
 			       local_softirq_pending());
 			ratelimit++;
 		}
+		goto end;
 	}
 
 	ts->idle_calls++;
-- 
cgit v1.2.3


From af52a90a14cdaa54ecbfb6e6982abb13466a4b56 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Mon, 7 Jul 2008 14:16:52 -0400
Subject: sched_clock: stop maximum check on NO HZ

Working with ftrace I would get large jumps of 11 millisecs or more with
the clock tracer. This killed the latencing timings of ftrace and also
caused the irqoff self tests to fail.

What was happening is with NO_HZ the idle would stop the jiffy counter and
before the jiffy counter was updated the sched_clock would have a bad
delta jiffies to compare with the gtod with the maximum.

The jiffies would stop and the last sched_tick would record the last gtod.
On wakeup, the sched clock update would compare the gtod + delta jiffies
(which would be zero) and compare it to the TSC. The TSC would have
correctly (with a stable TSC) moved forward several jiffies. But because the
jiffies has not been updated yet the clock would be prevented from moving
forward because it would appear that the TSC jumped too far ahead.

The clock would then virtually stop, until the jiffies are updated. Then
the next sched clock update would see that the clock was very much behind
since the delta jiffies is now correct. This would then jump the clock
forward by several jiffies.

This caused ftrace to report several milliseconds of interrupts off
latency at every resume from NO_HZ idle.

This patch adds hooks into the nohz code to disable the checking of the
maximum clock update when nohz is in effect. It resumes the max check
when nohz has updated the jiffies again.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Cc: Steven Rostedt <srostedt@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/sched.h    | 17 ++++++++++++++++-
 kernel/sched_clock.c     | 39 ++++++++++++++++++++++++++++++++++++++-
 kernel/time/tick-sched.c |  2 ++
 3 files changed, 56 insertions(+), 2 deletions(-)

(limited to 'kernel/time')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index c5d3f847ca8d..33a8f42041fa 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1573,13 +1573,28 @@ static inline void sched_clock_idle_sleep_event(void)
 static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
 {
 }
-#else
+
+#ifdef CONFIG_NO_HZ
+static inline void sched_clock_tick_stop(int cpu)
+{
+}
+
+static inline void sched_clock_tick_start(int cpu)
+{
+}
+#endif
+
+#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 extern void sched_clock_init(void);
 extern u64 sched_clock_cpu(int cpu);
 extern void sched_clock_tick(void);
 extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
+#ifdef CONFIG_NO_HZ
+extern void sched_clock_tick_stop(int cpu);
+extern void sched_clock_tick_start(int cpu);
 #endif
+#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
 /*
  * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index 42b81fa38cbd..97159e225a77 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -45,6 +45,9 @@ struct sched_clock_data {
 	u64			tick_raw;
 	u64			tick_gtod;
 	u64			clock;
+#ifdef CONFIG_NO_HZ
+	int			check_max;
+#endif
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
@@ -76,11 +79,45 @@ void sched_clock_init(void)
 		scd->tick_raw = 0;
 		scd->tick_gtod = ktime_now;
 		scd->clock = ktime_now;
+#ifdef CONFIG_NO_HZ
+		scd->check_max = 1;
+#endif
 	}
 
 	sched_clock_running = 1;
 }
 
+#ifdef CONFIG_NO_HZ
+/*
+ * The dynamic ticks makes the delta jiffies inaccurate. This
+ * prevents us from checking the maximum time update.
+ * Disable the maximum check during stopped ticks.
+ */
+void sched_clock_tick_stop(int cpu)
+{
+	struct sched_clock_data *scd = cpu_sdc(cpu);
+
+	scd->check_max = 0;
+}
+
+void sched_clock_tick_start(int cpu)
+{
+	struct sched_clock_data *scd = cpu_sdc(cpu);
+
+	scd->check_max = 1;
+}
+
+static int check_max(struct sched_clock_data *scd)
+{
+	return scd->check_max;
+}
+#else
+static int check_max(struct sched_clock_data *scd)
+{
+	return 1;
+}
+#endif /* CONFIG_NO_HZ */
+
 /*
  * update the percpu scd from the raw @now value
  *
@@ -112,7 +149,7 @@ static void __update_sched_clock(struct sched_clock_data *scd, u64 now)
 	 */
 	max_clock = scd->tick_gtod + (2 + delta_jiffies) * TICK_NSEC;
 
-	if (unlikely(clock + delta > max_clock)) {
+	if (unlikely(clock + delta > max_clock) && check_max(scd)) {
 		if (clock < max_clock)
 			clock = max_clock;
 		else
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index b854a895591e..d63008b09a4c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -276,6 +276,7 @@ void tick_nohz_stop_sched_tick(void)
 			ts->tick_stopped = 1;
 			ts->idle_jiffies = last_jiffies;
 			rcu_enter_nohz();
+			sched_clock_tick_stop(cpu);
 		}
 
 		/*
@@ -375,6 +376,7 @@ void tick_nohz_restart_sched_tick(void)
 	select_nohz_load_balancer(0);
 	now = ktime_get();
 	tick_do_update_jiffies64(now);
+	sched_clock_tick_start(cpu);
 	cpu_clear(cpu, nohz_cpu_mask);
 
 	/*
-- 
cgit v1.2.3