Merge branch 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull CPU hotplug updates from Thomas Gleixner:
 "A small update for the SMP hotplug code code:

   - Track "booted once" CPUs in a cpumask so the x86 APIC code has an
     easy way to decide whether broadcast IPIs are safe to use or not.

   - Implement a cpumask_or_equal() helper for the IPI broadcast
     evaluation.

     The above two changes have been also pulled into the x86/apic
     branch for implementing the conditional IPI broadcast feature.

   - Cache the number of online CPUs instead of reevaluating it over and
     over. num_online_cpus() is an unreliable snapshot anyway except
     when it is used outside a cpu hotplug locked region. The cached
     access is not changing this, but it's definitely faster than
     calculating the bitmap wheight especially in hot paths"

* 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  cpu/hotplug: Cache number of online CPUs
  cpumask: Implement cpumask_or_equal()
  smp/hotplug: Track booted once CPUs in a cpumask

2 files changed, 55 insertions, 9 deletions

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index f58e97446abc..90528f12bdfa 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -120,6 +120,10 @@ extern int __bitmap_empty(const unsigned long *bitmap, unsigned int nbits);
 extern int __bitmap_full(const unsigned long *bitmap, unsigned int nbits);
 extern int __bitmap_equal(const unsigned long *bitmap1,
 			  const unsigned long *bitmap2, unsigned int nbits);
+extern bool __pure __bitmap_or_equal(const unsigned long *src1,
+				     const unsigned long *src2,
+				     const unsigned long *src3,
+				     unsigned int nbits);
 extern void __bitmap_complement(unsigned long *dst, const unsigned long *src,
 			unsigned int nbits);
 extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src,
@@ -321,6 +325,25 @@ static inline int bitmap_equal(const unsigned long *src1,
 	return __bitmap_equal(src1, src2, nbits);
 }
 
+/**
+ * bitmap_or_equal - Check whether the or of two bitnaps is equal to a third
+ * @src1:	Pointer to bitmap 1
+ * @src2:	Pointer to bitmap 2 will be or'ed with bitmap 1
+ * @src3:	Pointer to bitmap 3. Compare to the result of *@src1 | *@src2
+ *
+ * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise
+ */
+static inline bool bitmap_or_equal(const unsigned long *src1,
+				   const unsigned long *src2,
+				   const unsigned long *src3,
+				   unsigned int nbits)
+{
+	if (!small_const_nbits(nbits))
+		return __bitmap_or_equal(src1, src2, src3, nbits);
+
+	return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits));
+}
+
 static inline int bitmap_intersects(const unsigned long *src1,
 			const unsigned long *src2, unsigned int nbits)
 {
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 21755471b1c3..b5a5a1ed9efd 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/threads.h>
 #include <linux/bitmap.h>
+#include <linux/atomic.h>
 #include <linux/bug.h>
 
 /* Don't assign or return these: may not be this big! */
@@ -95,8 +96,21 @@ extern struct cpumask __cpu_active_mask;
 #define cpu_present_mask  ((const struct cpumask *)&__cpu_present_mask)
 #define cpu_active_mask   ((const struct cpumask *)&__cpu_active_mask)
 
+extern atomic_t __num_online_cpus;
+
 #if NR_CPUS > 1
-#define num_online_cpus()	cpumask_weight(cpu_online_mask)
+/**
+ * num_online_cpus() - Read the number of online CPUs
+ *
+ * Despite the fact that __num_online_cpus is of type atomic_t, this
+ * interface gives only a momentary snapshot and is not protected against
+ * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held
+ * region.
+ */
+static inline unsigned int num_online_cpus(void)
+{
+	return atomic_read(&__num_online_cpus);
+}
 #define num_possible_cpus()	cpumask_weight(cpu_possible_mask)
 #define num_present_cpus()	cpumask_weight(cpu_present_mask)
 #define num_active_cpus()	cpumask_weight(cpu_active_mask)
@@ -115,6 +129,8 @@ extern struct cpumask __cpu_active_mask;
 #define cpu_active(cpu)		((cpu) == 0)
 #endif
 
+extern cpumask_t cpus_booted_once_mask;
+
 static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits)
 {
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
@@ -474,6 +490,20 @@ static inline bool cpumask_equal(const struct cpumask *src1p,
 }
 
 /**
+ * cpumask_or_equal - *src1p | *src2p == *src3p
+ * @src1p: the first input
+ * @src2p: the second input
+ * @src3p: the third input
+ */
+static inline bool cpumask_or_equal(const struct cpumask *src1p,
+				    const struct cpumask *src2p,
+				    const struct cpumask *src3p)
+{
+	return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p),
+			       cpumask_bits(src3p), nr_cpumask_bits);
+}
+
+/**
  * cpumask_intersects - (*src1p & *src2p) != 0
  * @src1p: the first input
  * @src2p: the second input
@@ -805,14 +835,7 @@ set_cpu_present(unsigned int cpu, bool present)
 		cpumask_clear_cpu(cpu, &__cpu_present_mask);
 }
 
-static inline void
-set_cpu_online(unsigned int cpu, bool online)
-{
-	if (online)
-		cpumask_set_cpu(cpu, &__cpu_online_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_online_mask);
-}
+void set_cpu_online(unsigned int cpu, bool online);
 
 static inline void
 set_cpu_active(unsigned int cpu, bool active)