Merge tag 'bitmap-for-6.15' of https://github.com/norov/linux

Pull bitmap updates from Yury Norov:

 - cpumask_next_wrap() rework (me)

 - GENMASK() simplification (I Hsin)

 - rust bindings for cpumasks (Viresh and me)

 - scattered cleanups (Andy, Tamir, Vincent, Ignacio and Joel)

* tag 'bitmap-for-6.15' of https://github.com/norov/linux: (22 commits)
  cpumask: align text in comment
  riscv: fix test_and_{set,clear}_bit ordering documentation
  treewide: fix typo 'unsigned __init128' -> 'unsigned __int128'
  MAINTAINERS: add rust bindings entry for bitmap API
  rust: Add cpumask helpers
  uapi: Revert "bitops: avoid integer overflow in GENMASK(_ULL)"
  cpumask: drop cpumask_next_wrap_old()
  PCI: hv: Switch hv_compose_multi_msi_req_get_cpu() to using cpumask_next_wrap()
  scsi: lpfc: rework lpfc_next_{online,present}_cpu()
  scsi: lpfc: switch lpfc_irq_rebalance() to using cpumask_next_wrap()
  s390: switch stop_machine_yield() to using cpumask_next_wrap()
  padata: switch padata_find_next() to using cpumask_next_wrap()
  cpumask: use cpumask_next_wrap() where appropriate
  cpumask: re-introduce cpumask_next{,_and}_wrap()
  cpumask: deprecate cpumask_next_wrap()
  powerpc/xmon: simplify xmon_batch_next_cpu()
  ibmvnic: simplify ibmvnic_set_queue_affinity()
  virtio_net: simplify virtnet_set_affinity()
  objpool: rework objpool_pop()
  cpumask: add for_each_{possible,online}_cpu_wrap
  ...

4 files changed, 58 insertions, 30 deletions

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 2026953e2c4e..595217b7a6e7 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -560,9 +560,9 @@ void bitmap_replace(unsigned long *dst,
  *	      ...0..11...0..10
  *	dst:  0000001100000010
  *
- * A relationship exists between bitmap_scatter() and bitmap_gather().
+ * A relationship exists between bitmap_scatter() and bitmap_gather(). See
+ * bitmap_gather() for the bitmap gather detailed operations. TL;DR:
  * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation.
- * See bitmap_scatter() for details related to this relationship.
  */
 static __always_inline
 void bitmap_scatter(unsigned long *dst, const unsigned long *src,
@@ -608,7 +608,9 @@ void bitmap_scatter(unsigned long *dst, const unsigned long *src,
  *	dst:  0000000000011010
  *
  * A relationship exists between bitmap_gather() and bitmap_scatter(). See
- * bitmap_scatter() for the bitmap scatter detailed operations.
+ * bitmap_scatter() for the bitmap scatter detailed operations. TL;DR:
+ * bitmap_scatter() can be seen as the 'reverse' bitmap_gather() operation.
+ *
  * Suppose scattered computed using bitmap_scatter(scattered, src, mask, n).
  * The operation bitmap_gather(result, scattered, mask, n) leads to a result
  * equal or equivalent to src.
diff --git a/include/linux/bits.h b/include/linux/bits.h
index 61a75d3f294b..14fd0ca9a6cd 100644
--- a/include/linux/bits.h
+++ b/include/linux/bits.h
@@ -40,7 +40,7 @@
  * Missing asm support
  *
  * __GENMASK_U128() depends on _BIT128() which would not work
- * in the asm code, as it shifts an 'unsigned __init128' data
+ * in the asm code, as it shifts an 'unsigned __int128' data
  * type instead of direct representation of 128 bit constants
  * such as long and unsigned long. The fundamental problem is
  * that a 128 bit constant will get silently truncated by the
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 36a890d0dd57..f9a868384083 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -81,7 +81,7 @@ static __always_inline void set_nr_cpu_ids(unsigned int nr)
  *
  *     cpu_possible_mask- has bit 'cpu' set iff cpu is populatable
  *     cpu_present_mask - has bit 'cpu' set iff cpu is populated
- *     cpu_enabled_mask  - has bit 'cpu' set iff cpu can be brought online
+ *     cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online
  *     cpu_online_mask  - has bit 'cpu' set iff cpu available to scheduler
  *     cpu_active_mask  - has bit 'cpu' set iff cpu available to migration
  *
@@ -285,35 +285,52 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
 }
 
 /**
- * for_each_cpu - iterate over every cpu in a mask
- * @cpu: the (optionally unsigned) integer iterator
- * @mask: the cpumask pointer
+ * cpumask_next_and_wrap - get the next cpu in *src1p & *src2p, starting from
+ *			   @n+1. If nothing found, wrap around and start from
+ *			   the beginning
+ * @n: the cpu prior to the place to search (i.e. search starts from @n+1)
+ * @src1p: the first cpumask pointer
+ * @src2p: the second cpumask pointer
  *
- * After the loop, cpu is >= nr_cpu_ids.
+ * Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src1p & @src2p is empty.
  */
-#define for_each_cpu(cpu, mask)				\
-	for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits)
-
-#if NR_CPUS == 1
 static __always_inline
-unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
+unsigned int cpumask_next_and_wrap(int n, const struct cpumask *src1p,
+			      const struct cpumask *src2p)
 {
-	cpumask_check(start);
+	/* -1 is a legal arg here. */
 	if (n != -1)
 		cpumask_check(n);
+	return find_next_and_bit_wrap(cpumask_bits(src1p), cpumask_bits(src2p),
+		small_cpumask_bits, n + 1);
+}
 
-	/*
-	 * Return the first available CPU when wrapping, or when starting before cpu0,
-	 * since there is only one valid option.
-	 */
-	if (wrap && n >= 0)
-		return nr_cpumask_bits;
-
-	return cpumask_first(mask);
+/**
+ * cpumask_next_wrap - get the next cpu in *src, starting from @n+1. If nothing
+ *		       found, wrap around and start from the beginning
+ * @n: the cpu prior to the place to search (i.e. search starts from @n+1)
+ * @src: cpumask pointer
+ *
+ * Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src is empty.
+ */
+static __always_inline
+unsigned int cpumask_next_wrap(int n, const struct cpumask *src)
+{
+	/* -1 is a legal arg here. */
+	if (n != -1)
+		cpumask_check(n);
+	return find_next_bit_wrap(cpumask_bits(src), small_cpumask_bits, n + 1);
 }
-#else
-unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
-#endif
+
+/**
+ * for_each_cpu - iterate over every cpu in a mask
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask: the cpumask pointer
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu(cpu, mask)				\
+	for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits)
 
 /**
  * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
@@ -1033,11 +1050,21 @@ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS);
 #define for_each_possible_cpu(cpu)	for ((cpu) = 0; (cpu) < 1; (cpu)++)
 #define for_each_online_cpu(cpu)	for ((cpu) = 0; (cpu) < 1; (cpu)++)
 #define for_each_present_cpu(cpu)	for ((cpu) = 0; (cpu) < 1; (cpu)++)
+
+#define for_each_possible_cpu_wrap(cpu, start)	\
+	for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++)
+#define for_each_online_cpu_wrap(cpu, start)	\
+	for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++)
 #else
 #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask)
 #define for_each_online_cpu(cpu)   for_each_cpu((cpu), cpu_online_mask)
 #define for_each_enabled_cpu(cpu)   for_each_cpu((cpu), cpu_enabled_mask)
 #define for_each_present_cpu(cpu)  for_each_cpu((cpu), cpu_present_mask)
+
+#define for_each_possible_cpu_wrap(cpu, start)	\
+	for_each_cpu_wrap((cpu), cpu_possible_mask, (start))
+#define for_each_online_cpu_wrap(cpu, start)	\
+	for_each_cpu_wrap((cpu), cpu_online_mask, (start))
 #endif
 
 /* Wrappers for arch boot code to manipulate normally-constant masks */
diff --git a/include/linux/objpool.h b/include/linux/objpool.h
index cb1758eaa2d3..b713a1fe7521 100644
--- a/include/linux/objpool.h
+++ b/include/linux/objpool.h
@@ -170,17 +170,16 @@ static inline void *objpool_pop(struct objpool_head *pool)
 {
 	void *obj = NULL;
 	unsigned long flags;
-	int i, cpu;
+	int start, cpu;
 
 	/* disable local irq to avoid preemption & interruption */
 	raw_local_irq_save(flags);
 
-	cpu = raw_smp_processor_id();
-	for (i = 0; i < pool->nr_possible_cpus; i++) {
+	start = raw_smp_processor_id();
+	for_each_possible_cpu_wrap(cpu, start) {
 		obj = __objpool_try_get_slot(pool, cpu);
 		if (obj)
 			break;
-		cpu = cpumask_next_wrap(cpu, cpu_possible_mask, -1, 1);
 	}
 	raw_local_irq_restore(flags);