Merge tag 'bitmap-6.1-rc1' of https://github.com/norov/linux

Pull bitmap updates from Yury Norov:

 - Fix unsigned comparison to -1 in CPUMAP_FILE_MAX_BYTES (Phil Auld)

 - cleanup nr_cpu_ids vs nr_cpumask_bits mess (me)

   This series cleans that mess and adds new config FORCE_NR_CPUS that
   allows to optimize cpumask subsystem if the number of CPUs is known
   at compile-time.

 - optimize find_bit() functions (me)

   Reworks find_bit() functions based on new FIND_{FIRST,NEXT}_BIT()
   macros.

 - add find_nth_bit() (me)

   Adds find_nth_bit(), which is ~70 times faster than bitcounting with
   for_each() loop:

	for_each_set_bit(bit, mask, size)
		if (n-- == 0)
			return bit;

   Also adds bitmap_weight_and() to let people replace this pattern:

	tmp = bitmap_alloc(nbits);
	bitmap_and(tmp, map1, map2, nbits);
	weight = bitmap_weight(tmp, nbits);
	bitmap_free(tmp);

   with a single bitmap_weight_and() call.

 - repair cpumask_check() (me)

   After switching cpumask to use nr_cpu_ids, cpumask_check() started
   generating many false-positive warnings. This series fixes it.

 - Add for_each_cpu_andnot() and for_each_cpu_andnot() (Valentin
   Schneider)

   Extends the API with one more function and applies it in sched/core.

* tag 'bitmap-6.1-rc1' of https://github.com/norov/linux: (28 commits)
  sched/core: Merge cpumask_andnot()+for_each_cpu() into for_each_cpu_andnot()
  lib/test_cpumask: Add for_each_cpu_and(not) tests
  cpumask: Introduce for_each_cpu_andnot()
  lib/find_bit: Introduce find_next_andnot_bit()
  cpumask: fix checking valid cpu range
  lib/bitmap: add tests for for_each() loops
  lib/find: optimize for_each() macros
  lib/bitmap: introduce for_each_set_bit_wrap() macro
  lib/find_bit: add find_next{,_and}_bit_wrap
  cpumask: switch for_each_cpu{,_not} to use for_each_bit()
  net: fix cpu_max_bits_warn() usage in netif_attrmask_next{,_and}
  cpumask: add cpumask_nth_{,and,andnot}
  lib/bitmap: remove bitmap_ord_to_pos
  lib/bitmap: add tests for find_nth_bit()
  lib: add find_nth{,_and,_andnot}_bit()
  lib/bitmap: add bitmap_weight_and()
  lib/bitmap: don't call __bitmap_weight() in kernel code
  tools: sync find_bit() implementation
  lib/find_bit: optimize find_next_bit() functions
  lib/find_bit: create find_first_zero_bit_le()
  ...

2 files changed, 81 insertions, 129 deletions

diff --git a/tools/include/linux/find.h b/tools/include/linux/find.h
index 47e2bd6c5174..38c0a542b0e2 100644
--- a/tools/include/linux/find.h
+++ b/tools/include/linux/find.h
@@ -8,21 +8,23 @@
 
 #include <linux/bitops.h>
 
-extern unsigned long _find_next_bit(const unsigned long *addr1,
-		const unsigned long *addr2, unsigned long nbits,
-		unsigned long start, unsigned long invert, unsigned long le);
+unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits,
+				unsigned long start);
+unsigned long _find_next_and_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,
+					 unsigned long start);
 extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size);
 extern unsigned long _find_first_and_bit(const unsigned long *addr1,
 					 const unsigned long *addr2, unsigned long size);
 extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size);
-extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size);
 
 #ifndef find_next_bit
 /**
  * find_next_bit - find the next set bit in a memory region
  * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
  * @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 are set, returns @size.
@@ -41,7 +43,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
 		return val ? __ffs(val) : size;
 	}
 
-	return _find_next_bit(addr, NULL, size, offset, 0UL, 0);
+	return _find_next_bit(addr, size, offset);
 }
 #endif
 
@@ -50,8 +52,8 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
  * find_next_and_bit - find the next set bit in both memory regions
  * @addr1: The first address to base the search on
  * @addr2: The second address to base the search on
- * @offset: The bitnumber to start searching at
  * @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 are set, returns @size.
@@ -71,7 +73,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1,
 		return val ? __ffs(val) : size;
 	}
 
-	return _find_next_bit(addr1, addr2, size, offset, 0UL, 0);
+	return _find_next_and_bit(addr1, addr2, size, offset);
 }
 #endif
 
@@ -79,8 +81,8 @@ unsigned long find_next_and_bit(const unsigned long *addr1,
 /**
  * find_next_zero_bit - find the next cleared bit in a memory region
  * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
  * @size: The bitmap size in bits
+ * @offset: The bitnumber to start searching at
  *
  * Returns the bit number of the next zero bit
  * If no bits are zero, returns @size.
@@ -99,7 +101,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
 		return val == ~0UL ? size : ffz(val);
 	}
 
-	return _find_next_bit(addr, NULL, size, offset, ~0UL, 0);
+	return _find_next_zero_bit(addr, size, offset);
 }
 #endif
 
@@ -172,43 +174,4 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
 }
 #endif
 
-#ifndef find_last_bit
-/**
- * find_last_bit - find the last set bit in a memory region
- * @addr: The address to start the search at
- * @size: The number of bits to search
- *
- * Returns the bit number of the last set bit, or size.
- */
-static inline
-unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
-{
-	if (small_const_nbits(size)) {
-		unsigned long val = *addr & GENMASK(size - 1, 0);
-
-		return val ? __fls(val) : size;
-	}
-
-	return _find_last_bit(addr, size);
-}
-#endif
-
-/**
- * find_next_clump8 - find next 8-bit clump with set bits in a memory region
- * @clump: location to store copy of found clump
- * @addr: address to base the search on
- * @size: bitmap size in number of bits
- * @offset: bit offset at which to start searching
- *
- * Returns the bit offset for the next set clump; the found clump value is
- * copied to the location pointed by @clump. If no bits are set, returns @size.
- */
-extern unsigned long find_next_clump8(unsigned long *clump,
-				      const unsigned long *addr,
-				      unsigned long size, unsigned long offset);
-
-#define find_first_clump8(clump, bits, size) \
-	find_next_clump8((clump), (bits), (size), 0)
-
-
 #endif /*__LINUX_FIND_H_ */
diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c
index ba4b8d94e004..6a3dc167d30e 100644
--- a/tools/lib/find_bit.c
+++ b/tools/lib/find_bit.c
@@ -18,66 +18,54 @@
 #include <linux/bitmap.h>
 #include <linux/kernel.h>
 
-#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \
-		!defined(find_next_and_bit)
-
 /*
- * This is a common helper function for find_next_bit, find_next_zero_bit, and
- * find_next_and_bit. The differences are:
- *  - The "invert" argument, which is XORed with each fetched word before
- *    searching it for one bits.
- *  - The optional "addr2", which is anded with "addr1" if present.
+ * Common helper for find_bit() function family
+ * @FETCH: The expression that fetches and pre-processes each word of bitmap(s)
+ * @MUNGE: The expression that post-processes a word containing found bit (may be empty)
+ * @size: The bitmap size in bits
  */
-unsigned long _find_next_bit(const unsigned long *addr1,
-		const unsigned long *addr2, unsigned long nbits,
-		unsigned long start, unsigned long invert, unsigned long le)
-{
-	unsigned long tmp, mask;
-	(void) le;
-
-	if (unlikely(start >= nbits))
-		return nbits;
-
-	tmp = addr1[start / BITS_PER_LONG];
-	if (addr2)
-		tmp &= addr2[start / BITS_PER_LONG];
-	tmp ^= invert;
-
-	/* Handle 1st word. */
-	mask = BITMAP_FIRST_WORD_MASK(start);
-
-	/*
-	 * Due to the lack of swab() in tools, and the fact that it doesn't
-	 * need little-endian support, just comment it out
-	 */
-#if (0)
-	if (le)
-		mask = swab(mask);
-#endif
-
-	tmp &= mask;
+#define FIND_FIRST_BIT(FETCH, MUNGE, size)					\
+({										\
+	unsigned long idx, val, sz = (size);					\
+										\
+	for (idx = 0; idx * BITS_PER_LONG < sz; idx++) {			\
+		val = (FETCH);							\
+		if (val) {							\
+			sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(val)), sz);	\
+			break;							\
+		}								\
+	}									\
+										\
+	sz;									\
+})
 
-	start = round_down(start, BITS_PER_LONG);
-
-	while (!tmp) {
-		start += BITS_PER_LONG;
-		if (start >= nbits)
-			return nbits;
-
-		tmp = addr1[start / BITS_PER_LONG];
-		if (addr2)
-			tmp &= addr2[start / BITS_PER_LONG];
-		tmp ^= invert;
-	}
-
-#if (0)
-	if (le)
-		tmp = swab(tmp);
-#endif
-
-	return min(start + __ffs(tmp), nbits);
-}
-#endif
+/*
+ * Common helper for find_next_bit() function family
+ * @FETCH: The expression that fetches and pre-processes each word of bitmap(s)
+ * @MUNGE: The expression that post-processes a word containing found bit (may be empty)
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ */
+#define FIND_NEXT_BIT(FETCH, MUNGE, size, start)				\
+({										\
+	unsigned long mask, idx, tmp, sz = (size), __start = (start);		\
+										\
+	if (unlikely(__start >= sz))						\
+		goto out;							\
+										\
+	mask = MUNGE(BITMAP_FIRST_WORD_MASK(__start));				\
+	idx = __start / BITS_PER_LONG;						\
+										\
+	for (tmp = (FETCH) & mask; !tmp; tmp = (FETCH)) {			\
+		if ((idx + 1) * BITS_PER_LONG >= sz)				\
+			goto out;						\
+		idx++;								\
+	}									\
+										\
+	sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(tmp)), sz);			\
+out:										\
+	sz;									\
+})
 
 #ifndef find_first_bit
 /*
@@ -85,14 +73,7 @@ unsigned long _find_next_bit(const unsigned long *addr1,
  */
 unsigned long _find_first_bit(const unsigned long *addr, unsigned long size)
 {
-	unsigned long idx;
-
-	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
-		if (addr[idx])
-			return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size);
-	}
-
-	return size;
+	return FIND_FIRST_BIT(addr[idx], /* nop */, size);
 }
 #endif
 
@@ -104,15 +85,7 @@ unsigned long _find_first_and_bit(const unsigned long *addr1,
 				  const unsigned long *addr2,
 				  unsigned long size)
 {
-	unsigned long idx, val;
-
-	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
-		val = addr1[idx] & addr2[idx];
-		if (val)
-			return min(idx * BITS_PER_LONG + __ffs(val), size);
-	}
-
-	return size;
+	return FIND_FIRST_BIT(addr1[idx] & addr2[idx], /* nop */, size);
 }
 #endif
 
@@ -122,13 +95,29 @@ unsigned long _find_first_and_bit(const unsigned long *addr1,
  */
 unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size)
 {
-	unsigned long idx;
+	return FIND_FIRST_BIT(~addr[idx], /* nop */, size);
+}
+#endif
 
-	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
-		if (addr[idx] != ~0UL)
-			return min(idx * BITS_PER_LONG + ffz(addr[idx]), size);
-	}
+#ifndef find_next_bit
+unsigned long _find_next_bit(const unsigned long *addr, unsigned long nbits, unsigned long start)
+{
+	return FIND_NEXT_BIT(addr[idx], /* nop */, nbits, start);
+}
+#endif
 
-	return size;
+#ifndef find_next_and_bit
+unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2,
+					unsigned long nbits, unsigned long start)
+{
+	return FIND_NEXT_BIT(addr1[idx] & addr2[idx], /* nop */, nbits, start);
+}
+#endif
+
+#ifndef find_next_zero_bit
+unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits,
+					 unsigned long start)
+{
+	return FIND_NEXT_BIT(~addr[idx], /* nop */, nbits, start);
 }
 #endif