diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h
index b561584d04a1..68870c776671 100644
--- a/arch/arm/include/asm/mmu.h
+++ b/arch/arm/include/asm/mmu.h
@@ -6,6 +6,7 @@
 typedef struct {
 #ifdef CONFIG_CPU_HAS_ASID
 	unsigned int id;
+	spinlock_t id_lock;
 #endif
 	unsigned int kvm_seq;
 } mm_context_t;
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index de6cefb329dd..a0b3cac0547c 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -43,12 +43,23 @@ void __check_kvm_seq(struct mm_struct *mm);
 #define ASID_FIRST_VERSION	(1 << ASID_BITS)
 
 extern unsigned int cpu_last_asid;
+#ifdef CONFIG_SMP
+DECLARE_PER_CPU(struct mm_struct *, current_mm);
+#endif
 
 void __init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void __new_context(struct mm_struct *mm);
 
 static inline void check_context(struct mm_struct *mm)
 {
+	/*
+	 * This code is executed with interrupts enabled. Therefore,
+	 * mm->context.id cannot be updated to the latest ASID version
+	 * on a different CPU (and condition below not triggered)
+	 * without first getting an IPI to reset the context. The
+	 * alternative is to take a read_lock on mm->context.id_lock
+	 * (after changing its type to rwlock_t).
+	 */
 	if (unlikely((mm->context.id ^ cpu_last_asid) >> ASID_BITS))
 		__new_context(mm);
 
@@ -108,6 +119,10 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		__flush_icache_all();
 #endif
 	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) {
+#ifdef CONFIG_SMP
+		struct mm_struct **crt_mm = &per_cpu(current_mm, cpu);
+		*crt_mm = next;
+#endif
 		check_context(next);
 		cpu_switch_mm(next->pgd, next);
 		if (cache_is_vivt())
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index a9e22e31eaa1..b0ee9ba3cfab 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -10,12 +10,17 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/percpu.h>
 
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
 
 static DEFINE_SPINLOCK(cpu_asid_lock);
 unsigned int cpu_last_asid = ASID_FIRST_VERSION;
+#ifdef CONFIG_SMP
+DEFINE_PER_CPU(struct mm_struct *, current_mm);
+#endif
 
 /*
  * We fork()ed a process, and we need a new context for the child
@@ -26,13 +31,109 @@ unsigned int cpu_last_asid = ASID_FIRST_VERSION;
 void __init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
 	mm->context.id = 0;
+	spin_lock_init(&mm->context.id_lock);
 }
 
+static void flush_context(void)
+{
+	/* set the reserved ASID before flushing the TLB */
+	asm("mcr	p15, 0, %0, c13, c0, 1\n" : : "r" (0));
+	isb();
+	local_flush_tlb_all();
+	if (icache_is_vivt_asid_tagged()) {
+		__flush_icache_all();
+		dsb();
+	}
+}
+
+#ifdef CONFIG_SMP
+
+static void set_mm_context(struct mm_struct *mm, unsigned int asid)
+{
+	unsigned long flags;
+
+	/*
+	 * Locking needed for multi-threaded applications where the
+	 * same mm->context.id could be set from different CPUs during
+	 * the broadcast. This function is also called via IPI so the
+	 * mm->context.id_lock has to be IRQ-safe.
+	 */
+	spin_lock_irqsave(&mm->context.id_lock, flags);
+	if (likely((mm->context.id ^ cpu_last_asid) >> ASID_BITS)) {
+		/*
+		 * Old version of ASID found. Set the new one and
+		 * reset mm_cpumask(mm).
+		 */
+		mm->context.id = asid;
+		cpumask_clear(mm_cpumask(mm));
+	}
+	spin_unlock_irqrestore(&mm->context.id_lock, flags);
+
+	/*
+	 * Set the mm_cpumask(mm) bit for the current CPU.
+	 */
+	cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+}
+
+/*
+ * Reset the ASID on the current CPU. This function call is broadcast
+ * from the CPU handling the ASID rollover and holding cpu_asid_lock.
+ */
+static void reset_context(void *info)
+{
+	unsigned int asid;
+	unsigned int cpu = smp_processor_id();
+	struct mm_struct *mm = per_cpu(current_mm, cpu);
+
+	/*
+	 * Check if a current_mm was set on this CPU as it might still
+	 * be in the early booting stages and using the reserved ASID.
+	 */
+	if (!mm)
+		return;
+
+	smp_rmb();
+	asid = cpu_last_asid + cpu + 1;
+
+	flush_context();
+	set_mm_context(mm, asid);
+
+	/* set the new ASID */
+	asm("mcr	p15, 0, %0, c13, c0, 1\n" : : "r" (mm->context.id));
+	isb();
+}
+
+#else
+
+static inline void set_mm_context(struct mm_struct *mm, unsigned int asid)
+{
+	mm->context.id = asid;
+	cpumask_copy(mm_cpumask(mm), cpumask_of(smp_processor_id()));
+}
+
+#endif
+
 void __new_context(struct mm_struct *mm)
 {
 	unsigned int asid;
 
 	spin_lock(&cpu_asid_lock);
+#ifdef CONFIG_SMP
+	/*
+	 * Check the ASID again, in case the change was broadcast from
+	 * another CPU before we acquired the lock.
+	 */
+	if (unlikely(((mm->context.id ^ cpu_last_asid) >> ASID_BITS) == 0)) {
+		cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+		spin_unlock(&cpu_asid_lock);
+		return;
+	}
+#endif
+	/*
+	 * At this point, it is guaranteed that the current mm (with
+	 * an old ASID) isn't active on any other CPU since the ASIDs
+	 * are changed simultaneously via IPI.
+	 */
 	asid = ++cpu_last_asid;
 	if (asid == 0)
 		asid = cpu_last_asid = ASID_FIRST_VERSION;
@@ -42,20 +143,15 @@ void __new_context(struct mm_struct *mm)
 	 * to start a new version and flush the TLB.
 	 */
 	if (unlikely((asid & ~ASID_MASK) == 0)) {
-		asid = ++cpu_last_asid;
-		/* set the reserved ASID before flushing the TLB */
-		asm("mcr	p15, 0, %0, c13, c0, 1	@ set reserved context ID\n"
-		    :
-		    : "r" (0));
-		isb();
-		flush_tlb_all();
-		if (icache_is_vivt_asid_tagged()) {
-			__flush_icache_all();
-			dsb();
-		}
+		asid = cpu_last_asid + smp_processor_id() + 1;
+		flush_context();
+#ifdef CONFIG_SMP
+		smp_wmb();
+		smp_call_function(reset_context, NULL, 1);
+#endif
+		cpu_last_asid += NR_CPUS;
 	}
-	spin_unlock(&cpu_asid_lock);
 
-	cpumask_copy(mm_cpumask(mm), cpumask_of(smp_processor_id()));
-	mm->context.id = asid;
+	set_mm_context(mm, asid);
+	spin_unlock(&cpu_asid_lock);
 }