Merge tag 'bitmap-for-6.10v2' of https://github.com/norov/linux

Pull bitmap updates from Yury Norov:

 - topology_span_sane() optimization from Kyle Meyer

 - fns() rework from Kuan-Wei Chiu (used in cpumask_local_spread() and
   other places)

 - headers cleanup from Andy

 - add a MAINTAINERS record for bitops API

* tag 'bitmap-for-6.10v2' of https://github.com/norov/linux:
  usercopy: Don't use "proxy" headers
  bitops: Move aligned_byte_mask() to wordpart.h
  MAINTAINERS: add BITOPS API record
  bitmap: relax find_nth_bit() limitation on return value
  lib: make test_bitops compilable into the kernel image
  bitops: Optimize fns() for improved performance
  lib/test_bitops: Add benchmark test for fns()
  Compiler Attributes: Add __always_used macro
  sched/topology: Optimize topology_span_sane()
  cpumask: Add for_each_cpu_from()

12 files changed, 88 insertions, 27 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 94872dce51ed..f63013898f40 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3725,6 +3725,20 @@ F:	tools/include/vdso/bits.h
 F:	tools/lib/bitmap.c
 F:	tools/lib/find_bit.c
 
+BITOPS API
+M:	Yury Norov <yury.norov@gmail.com>
+R:	Rasmus Villemoes <linux@rasmusvillemoes.dk>
+S:	Maintained
+F:	arch/*/include/asm/bitops.h
+F:	arch/*/include/asm/bitops_32.h
+F:	arch/*/include/asm/bitops_64.h
+F:	arch/*/lib/bitops.c
+F:	include/asm-generic/bitops
+F:	include/asm-generic/bitops.h
+F:	include/linux/bitops.h
+F:	lib/test_bitops.c
+F:	tools/*/bitops*
+
 BLINKM RGB LED DRIVER
 M:	Jan-Simon Moeller <jansimon.moeller@gmx.de>
 S:	Maintained
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 3112ae7d6524..46d4bdc634c0 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -8,13 +8,6 @@
 
 #include <uapi/linux/kernel.h>
 
-/* Set bits in the first 'n' bytes when loaded from memory */
-#ifdef __LITTLE_ENDIAN
-#  define aligned_byte_mask(n) ((1UL << 8*(n))-1)
-#else
-#  define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n)))
-#endif
-
 #define BITS_PER_TYPE(type)	(sizeof(type) * BITS_PER_BYTE)
 #define BITS_TO_LONGS(nr)	__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
 #define BITS_TO_U64(nr)		__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u64))
@@ -257,16 +250,10 @@ static inline unsigned int __ffs64(u64 word)
  */
 static inline unsigned int fns(unsigned long word, unsigned int n)
 {
-	unsigned int bit;
-
-	while (word) {
-		bit = __ffs(word);
-		if (n-- == 0)
-			return bit;
-		__clear_bit(bit, &word);
-	}
+	while (word && n--)
+		word &= word - 1;
 
-	return BITS_PER_LONG;
+	return word ? __ffs(word) : BITS_PER_LONG;
 }
 
 /**
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 8bdf6e0918c1..32284cd26d52 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -362,6 +362,19 @@
 #define __used                          __attribute__((__used__))
 
 /*
+ * The __used attribute guarantees that the attributed variable will be
+ * always emitted by a compiler. It doesn't prevent the compiler from
+ * throwing 'unused' warnings when it can't detect how the variable is
+ * actually used. It's a compiler implementation details either emit
+ * the warning in that case or not.
+ *
+ * The combination of both 'used' and 'unused' attributes ensures that
+ * the variable would be emitted, and will not trigger 'unused' warnings.
+ * The attribute is applicable for functions, static and global variables.
+ */
+#define __always_used			__used __maybe_unused
+
+/*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-warn_005funused_005fresult-function-attribute
  * clang: https://clang.llvm.org/docs/AttributeReference.html#nodiscard-warn-unused-result
  */
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 7600e877908f..4d3bef644add 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -386,6 +386,16 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
 	for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits)
 
 /**
+ * for_each_cpu_from - iterate over CPUs present in @mask, from @cpu to the end of @mask.
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask: the cpumask pointer
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_from(cpu, mask)				\
+	for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits)
+
+/**
  * cpumask_any_but - return a "random" in a cpumask, but not this one.
  * @mask: the cpumask to search
  * @cpu: the cpu to ignore.
diff --git a/include/linux/find.h b/include/linux/find.h
index 28ec5a03393a..5dfca4225fef 100644
--- a/include/linux/find.h
+++ b/include/linux/find.h
@@ -222,7 +222,7 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
  *	 idx = find_first_bit(addr, size);
  *
  * Returns the bit number of the N'th set bit.
- * If no such, returns @size.
+ * If no such, returns >= @size.
  */
 static inline
 unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n)
diff --git a/include/linux/wordpart.h b/include/linux/wordpart.h
index f6f8f83b15b0..4ca1ba66d2f0 100644
--- a/include/linux/wordpart.h
+++ b/include/linux/wordpart.h
@@ -39,4 +39,11 @@
  */
 #define REPEAT_BYTE(x)	((~0ul / 0xff) * (x))
 
+/* Set bits in the first 'n' bytes when loaded from memory */
+#ifdef __LITTLE_ENDIAN
+#  define aligned_byte_mask(n) ((1UL << 8*(n))-1)
+#else
+#  define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n)))
+#endif
+
 #endif // _LINUX_WORDPART_H
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 329c82faca9b..a6994a1fcc90 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -2353,7 +2353,7 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve
 static bool topology_span_sane(struct sched_domain_topology_level *tl,
 			      const struct cpumask *cpu_map, int cpu)
 {
-	int i;
+	int i = cpu + 1;
 
 	/* NUMA levels are allowed to overlap */
 	if (tl->flags & SDTL_OVERLAP)
@@ -2365,9 +2365,7 @@ static bool topology_span_sane(struct sched_domain_topology_level *tl,
 	 * breaking the sched_group lists - i.e. a later get_group() pass
 	 * breaks the linking done for an earlier span.
 	 */
-	for_each_cpu(i, cpu_map) {
-		if (i == cpu)
-			continue;
+	for_each_cpu_from(i, cpu_map) {
 		/*
 		 * We should 'and' all those masks with 'cpu_map' to exactly
 		 * match the topology we're about to build, but that can only
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index c1c1b19525a5..4bcdb2fd17d8 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2482,7 +2482,6 @@ config TEST_LKM
 
 config TEST_BITOPS
 	tristate "Test module for compilation of bitops operations"
-	depends on m
 	help
 	  This builds the "test_bitops" module that is much like the
 	  TEST_LKM module except that it does a basic exercise of the
diff --git a/lib/find_bit.c b/lib/find_bit.c
index dacadd904250..0836bb3d76c5 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -87,7 +87,7 @@ out:										\
 	if (sz % BITS_PER_LONG)							\
 		tmp = (FETCH) & BITMAP_LAST_WORD_MASK(sz);			\
 found:										\
-	sz = min(idx * BITS_PER_LONG + fns(tmp, nr), sz);			\
+	sz = idx * BITS_PER_LONG + fns(tmp, nr);				\
 out:										\
 	sz;									\
 })
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index 83019beabce4..6dfb8d46a4ff 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -244,7 +244,7 @@ static void __init test_find_nth_bit(void)
 	expect_eq_uint(60,  find_nth_bit(bmap, 64 * 3, 5));
 	expect_eq_uint(80,  find_nth_bit(bmap, 64 * 3, 6));
 	expect_eq_uint(123, find_nth_bit(bmap, 64 * 3, 7));
-	expect_eq_uint(64 * 3, find_nth_bit(bmap, 64 * 3, 8));
+	expect_eq_uint(0,   !!(find_nth_bit(bmap, 64 * 3, 8) < 64 * 3));
 
 	expect_eq_uint(10,  find_nth_bit(bmap, 64 * 3 - 1, 0));
 	expect_eq_uint(20,  find_nth_bit(bmap, 64 * 3 - 1, 1));
@@ -254,7 +254,7 @@ static void __init test_find_nth_bit(void)
 	expect_eq_uint(60,  find_nth_bit(bmap, 64 * 3 - 1, 5));
 	expect_eq_uint(80,  find_nth_bit(bmap, 64 * 3 - 1, 6));
 	expect_eq_uint(123, find_nth_bit(bmap, 64 * 3 - 1, 7));
-	expect_eq_uint(64 * 3 - 1, find_nth_bit(bmap, 64 * 3 - 1, 8));
+	expect_eq_uint(0,   !!(find_nth_bit(bmap, 64 * 3 - 1, 8) < 64 * 3 - 1));
 
 	for_each_set_bit(bit, exp1, EXP1_IN_BITS) {
 		b = find_nth_bit(exp1, EXP1_IN_BITS, cnt++);
diff --git a/lib/test_bitops.c b/lib/test_bitops.c
index 3b7bcbee84db..55669624bb28 100644
--- a/lib/test_bitops.c
+++ b/lib/test_bitops.c
@@ -5,9 +5,11 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/cleanup.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/printk.h>
+#include <linux/slab.h>
 
 /* a tiny module only meant to test
  *
@@ -50,6 +52,30 @@ static unsigned long order_comb_long[][2] = {
 };
 #endif
 
+static int __init test_fns(void)
+{
+	static volatile __always_used unsigned long tmp __initdata;
+	unsigned long *buf __free(kfree) = NULL;
+	unsigned int i, n;
+	ktime_t time;
+
+	buf = kmalloc_array(10000, sizeof(unsigned long), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	get_random_bytes(buf, 10000 * sizeof(unsigned long));
+	time = ktime_get();
+
+	for (n = 0; n < BITS_PER_LONG; n++)
+		for (i = 0; i < 10000; i++)
+			tmp = fns(buf[i], n);
+
+	time = ktime_get() - time;
+	pr_err("fns:  %18llu ns\n", time);
+
+	return 0;
+}
+
 static int __init test_bitops_startup(void)
 {
 	int i, bit_set;
@@ -94,6 +120,8 @@ static int __init test_bitops_startup(void)
 	if (bit_set != BITOPS_LAST)
 		pr_err("ERROR: FOUND SET BIT %d\n", bit_set);
 
+	test_fns();
+
 	pr_info("Completed bitops test\n");
 
 	return 0;
diff --git a/lib/usercopy.c b/lib/usercopy.c
index d29fe29c6849..499a7a7d54db 100644
--- a/lib/usercopy.c
+++ b/lib/usercopy.c
@@ -1,9 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/export.h>
 #include <linux/fault-inject-usercopy.h>
 #include <linux/instrumented.h>
-#include <linux/uaccess.h>
+#include <linux/kernel.h>
 #include <linux/nospec.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/wordpart.h>
 
 /* out-of-line parts */