[PATCH 1/3] bitmap: cpumask: introduce and_andnot search helper and iterator

["Yury Norov (NVIDIA)" <yury.norov@gmail.com>]

Like other similar iterators, *_and_andnot helps to get rid of temporary
on-stack bitmaps and associate housekeeping code.

Signed-off-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
---
 include/linux/cpumask.h | 22 ++++++++++++++++++++++
 include/linux/find.h    | 38 ++++++++++++++++++++++++++++++++++++++
 lib/find_bit.c          |  9 +++++++++
 3 files changed, 69 insertions(+)

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index ff8f41ab7ce6..6de16a0e6e7b 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -406,6 +406,28 @@ unsigned int cpumask_random(const struct cpumask *src)
 #define for_each_cpu_and(cpu, mask1, mask2)				\
 	for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits)
 
+/**
+ * for_each_cpu_and_andnot_from - iterate over every cpu in all masks
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask1: the first cpumask pointer
+ * @mask2: the second cpumask pointer
+ * @mask3: the third cpumask pointer
+ *
+ * This saves a temporary CPU mask in many places.  It is equivalent to:
+ *	struct cpumask tmp;
+ *	cpumask_and(&tmp, &mask1, &mask2);
+ *	cpumask_andnot(&tmp, &tmp, &mask3);
+ *	for_each_cpu_from(cpu, &tmp)
+ *		...
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_and_andnot_from(cpu, mask1, mask2, mask3)				\
+	for_each_and_andnot_bit_from(cpu, cpumask_bits(mask1),				\
+					  cpumask_bits(mask2),				\
+					  cpumask_bits(mask3),				\
+					  small_cpumask_bits)
+
 /**
  * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding
  *			 those present in another.
diff --git a/include/linux/find.h b/include/linux/find.h
index 9d720ad92bc1..daf72078c25e 100644
--- a/include/linux/find.h
+++ b/include/linux/find.h
@@ -14,6 +14,9 @@ unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long
 					unsigned long nbits, unsigned long start);
 unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
 					unsigned long nbits, unsigned long start);
+unsigned long _find_next_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
+					 const unsigned long *addr3, unsigned long size,
+					 unsigned long n);
 unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2,
 					unsigned long nbits, unsigned long start);
 unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits,
@@ -135,6 +138,36 @@ unsigned long find_next_andnot_bit(const unsigned long *addr1,
 }
 #endif
 
+/**
+ * find_next_and_andnot_bit - find the next set bit in *addr1 and *addr2
+ *			      excluding all the bits in *addr3
+ * @addr1: The first address to base the search on
+ * @addr2: The second address to base the search on
+ * @addr3: The second address to base the search on
+ * @size: The bitmap size in bits
+ * @offset: The bitnumber to start searching at
+ *
+ * Returns the bit number for the next set bit
+ * If no bits found, returns >= @size.
+ */
+static __always_inline
+unsigned long find_next_and_andnot_bit(const unsigned long *addr1,
+		const unsigned long *addr2, const unsigned long *addr3,
+		unsigned long size, unsigned long offset)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val;
+
+		if (unlikely(offset >= size))
+			return size;
+
+		val = *addr1 & *addr2 & ~*addr3;
+		return val ? __ffs(val) : size;
+	}
+
+	return _find_next_and_andnot_bit(addr1, addr2, addr3, size, offset);
+}
+
 #ifndef find_next_or_bit
 /**
  * find_next_or_bit - find the next set bit in either memory regions
@@ -595,6 +628,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned
 	     (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\
 	     (bit)++)
 
+#define for_each_and_andnot_bit_from(bit, addr1, addr2, addr3, size)			\
+	for (; (bit) = find_next_and_andnot_bit((addr1), (addr2), (addr3),		\
+						 (size), (bit)), (bit) < (size);	\
+	       (bit)++)
+
 #define for_each_or_bit(bit, addr1, addr2, size) \
 	for ((bit) = 0;									\
 	     (bit) = find_next_or_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\
diff --git a/lib/find_bit.c b/lib/find_bit.c
index d4b5a29e3e72..aec79207c566 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -206,6 +206,15 @@ unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned l
 EXPORT_SYMBOL(_find_next_andnot_bit);
 #endif
 
+unsigned long _find_next_and_andnot_bit(const unsigned long *addr1,
+					const unsigned long *addr2,
+					const unsigned long *addr3,
+					unsigned long nbits, unsigned long start)
+{
+	return FIND_NEXT_BIT(addr1[idx] & addr2[idx] & ~addr3[idx], /* nop */, nbits, start);
+}
+EXPORT_SYMBOL(_find_next_and_andnot_bit);
+
 #ifndef find_next_or_bit
 unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2,
 					unsigned long nbits, unsigned long start)
-- 
2.43.0