7 files changed, 31 insertions, 36 deletions

diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 40fc86161d92..58b7f27cb3e9 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -100,13 +100,8 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
 	irqctx->tinfo.task = curctx->tinfo.task;
 	irqctx->tinfo.previous_esp = current_stack_pointer;
 
-	/*
-	 * Copy the softirq bits in preempt_count so that the
-	 * softirq checks work in the hardirq context.
-	 */
-	irqctx->tinfo.preempt_count =
-		(irqctx->tinfo.preempt_count & ~SOFTIRQ_MASK) |
-		(curctx->tinfo.preempt_count & SOFTIRQ_MASK);
+	/* Copy the preempt_count so that the [soft]irq checks work. */
+	irqctx->tinfo.preempt_count = curctx->tinfo.preempt_count;
 
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
@@ -196,7 +191,7 @@ bool handle_irq(unsigned irq, struct pt_regs *regs)
 	if (unlikely(!desc))
 		return false;
 
-	if (!execute_on_irq_stack(overflow, desc, irq)) {
+	if (user_mode_vm(regs) || !execute_on_irq_stack(overflow, desc, irq)) {
 		if (unlikely(overflow))
 			print_stack_overflow();
 		desc->handle_irq(irq, desc);
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index c08d1ff12b7c..49888fefe794 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -119,9 +119,7 @@ void cpu_idle(void)
 		}
 		rcu_idle_exit();
 		tick_nohz_idle_exit();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index cfa5c90c01db..e34257c70c28 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -156,9 +156,7 @@ void cpu_idle(void)
 		}
 
 		tick_nohz_idle_exit();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 66d250c00d11..58f78165d308 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -291,19 +291,6 @@ notrace static void __cpuinit start_secondary(void *unused)
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
 	x86_platform.nmi_init();
 
-	/*
-	 * Wait until the cpu which brought this one up marked it
-	 * online before enabling interrupts. If we don't do that then
-	 * we can end up waking up the softirq thread before this cpu
-	 * reached the active state, which makes the scheduler unhappy
-	 * and schedule the softirq thread on the wrong cpu. This is
-	 * only observable with forced threaded interrupts, but in
-	 * theory it could also happen w/o them. It's just way harder
-	 * to achieve.
-	 */
-	while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask))
-		cpu_relax();
-
 	/* enable local interrupts */
 	local_irq_enable();
 
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index dd5fbf4101fc..c6eba2b42673 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -57,9 +57,6 @@ EXPORT_SYMBOL(profile_pc);
  */
 static irqreturn_t timer_interrupt(int irq, void *dev_id)
 {
-	/* Keep nmi watchdog up to date */
-	inc_irq_stat(irq0_irqs);
-
 	global_clock_event->event_handler(global_clock_event);
 
 	/* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index a62c201c97ec..183c5925a9fe 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -620,7 +620,8 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 
 	if (cpu_khz) {
 		*scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz;
-		*offset = ns_now - (tsc_now * *scale >> CYC2NS_SCALE_FACTOR);
+		*offset = ns_now - mult_frac(tsc_now, *scale,
+					     (1UL << CYC2NS_SCALE_FACTOR));
 	}
 
 	sched_clock_idle_wakeup_event(0);
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 9eba29b46cb7..fc25e60a5884 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -42,7 +42,7 @@ static __cpuinitdata int nr_warps;
 /*
  * TSC-warp measurement loop running on both CPUs:
  */
-static __cpuinit void check_tsc_warp(void)
+static __cpuinit void check_tsc_warp(unsigned int timeout)
 {
 	cycles_t start, now, prev, end;
 	int i;
@@ -51,9 +51,9 @@ static __cpuinit void check_tsc_warp(void)
 	start = get_cycles();
 	rdtsc_barrier();
 	/*
-	 * The measurement runs for 20 msecs:
+	 * The measurement runs for 'timeout' msecs:
 	 */
-	end = start + tsc_khz * 20ULL;
+	end = start + (cycles_t) tsc_khz * timeout;
 	now = start;
 
 	for (i = 0; ; i++) {
@@ -99,6 +99,25 @@ static __cpuinit void check_tsc_warp(void)
 }
 
 /*
+ * If the target CPU coming online doesn't have any of its core-siblings
+ * online, a timeout of 20msec will be used for the TSC-warp measurement
+ * loop. Otherwise a smaller timeout of 2msec will be used, as we have some
+ * information about this socket already (and this information grows as we
+ * have more and more logical-siblings in that socket).
+ *
+ * Ideally we should be able to skip the TSC sync check on the other
+ * core-siblings, if the first logical CPU in a socket passed the sync test.
+ * But as the TSC is per-logical CPU and can potentially be modified wrongly
+ * by the bios, TSC sync test for smaller duration should be able
+ * to catch such errors. Also this will catch the condition where all the
+ * cores in the socket doesn't get reset at the same time.
+ */
+static inline unsigned int loop_timeout(int cpu)
+{
+	return (cpumask_weight(cpu_core_mask(cpu)) > 1) ? 2 : 20;
+}
+
+/*
  * Source CPU calls into this - it waits for the freshly booted
  * target CPU to arrive and then starts the measurement:
  */
@@ -135,7 +154,7 @@ void __cpuinit check_tsc_sync_source(int cpu)
 	 */
 	atomic_inc(&start_count);
 
-	check_tsc_warp();
+	check_tsc_warp(loop_timeout(cpu));
 
 	while (atomic_read(&stop_count) != cpus-1)
 		cpu_relax();
@@ -183,7 +202,7 @@ void __cpuinit check_tsc_sync_target(void)
 	while (atomic_read(&start_count) != cpus)
 		cpu_relax();
 
-	check_tsc_warp();
+	check_tsc_warp(loop_timeout(smp_processor_id()));
 
 	/*
 	 * Ok, we are done: