Merge tag 'bitmap-for-v7.1' of https://github.com/norov/linux

Pull bitmap updates from Yury Norov:

 - new API: bitmap_weight_from() and bitmap_weighted_xor() (Yury)

 - drop unused __find_nth_andnot_bit() (Yury)

 - new tests and test improvements (Andy, Akinobu, Yury)

 - fixes for count_zeroes API (Yury)

 - cleanup bitmap_print_to_pagebuf() mess (Yury)

 - documentation updates (Andy, Kai, Kit).

* tag 'bitmap-for-v7.1' of https://github.com/norov/linux: (24 commits)
  bitops: Update kernel-doc for sign_extendXX()
  powerpc/xive: simplify xive_spapr_debug_show()
  thermal: intel: switch cpumask_get() to using cpumask_print_to_pagebuf()
  coresight: don't use bitmap_print_to_pagebuf()
  lib/prime_numbers: drop temporary buffer in dump_primes()
  drm/xe: switch xe_pagefault_queue_init() to using bitmap_weighted_or()
  ice: use bitmap_empty() in ice_vf_has_no_qs_ena
  ice: use bitmap_weighted_xor() in ice_find_free_recp_res_idx()
  bitmap: introduce bitmap_weighted_xor()
  bitmap: add test_zero_nbits()
  bitmap: exclude nbits == 0 cases from bitmap test
  bitmap: test bitmap_weight() for more
  asm-generic/bitops: Fix a comment typo in instrumented-atomic.h
  bitops: fix kernel-doc parameter name for parity8()
  lib: count_zeros: unify count_{leading,trailing}_zeros()
  lib: count_zeros: fix 32/64-bit inconsistency in count_trailing_zeros()
  lib: crypto: fix comments for count_leading_zeros()
  x86/topology: use bitmap_weight_from()
  bitmap: add bitmap_weight_from()
  lib/find_bit_benchmark: avoid clearing randomly filled bitmap in test_find_first_bit()
  ...

19 files changed, 230 insertions, 97 deletions

diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c
index 003bd773e11c..2ab7fafa86d5 100644
--- a/arch/loongarch/kvm/intc/eiointc.c
+++ b/arch/loongarch/kvm/intc/eiointc.c
@@ -16,7 +16,7 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s)
 		ipnum = (s->ipmap >> (irq / 32 * 8)) & 0xff;
 		if (!(s->status & BIT(EIOINTC_ENABLE_INT_ENCODE))) {
 			ipnum = count_trailing_zeros(ipnum);
-			ipnum = (ipnum >= 0 && ipnum < 4) ? ipnum : 0;
+			ipnum = ipnum < 4 ? ipnum : 0;
 		}
 
 		cpuid = ((u8 *)s->coremap)[irq];
@@ -41,7 +41,7 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level)
 	ipnum = (s->ipmap >> (irq / 32 * 8)) & 0xff;
 	if (!(s->status & BIT(EIOINTC_ENABLE_INT_ENCODE))) {
 		ipnum = count_trailing_zeros(ipnum);
-		ipnum = (ipnum >= 0 && ipnum < 4) ? ipnum : 0;
+		ipnum = ipnum < 4 ? ipnum : 0;
 	}
 
 	cpu = s->sw_coremap[irq];
diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c
index 61f8a8acf81f..fdf52c78ac02 100644
--- a/arch/powerpc/sysdev/xive/spapr.c
+++ b/arch/powerpc/sysdev/xive/spapr.c
@@ -667,17 +667,9 @@ static void xive_spapr_sync_source(u32 hw_irq)
 static int xive_spapr_debug_show(struct seq_file *m, void *private)
 {
 	struct xive_irq_bitmap *xibm;
-	char *buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
 
-	if (!buf)
-		return -ENOMEM;
-
-	list_for_each_entry(xibm, &xive_irq_bitmaps, list) {
-		memset(buf, 0, PAGE_SIZE);
-		bitmap_print_to_pagebuf(true, buf, xibm->bitmap, xibm->count);
-		seq_printf(m, "bitmap #%d: %s", xibm->count, buf);
-	}
-	kfree(buf);
+	list_for_each_entry(xibm, &xive_irq_bitmaps, list)
+		seq_printf(m, "bitmap #%d: %*pbl\n", xibm->count, xibm->count, xibm->bitmap);
 
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index eafcb1fc185a..4913b64ec592 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -204,15 +204,11 @@ fwbug:
 static unsigned int topo_unit_count(u32 lvlid, enum x86_topology_domains at_level,
 				    unsigned long *map)
 {
-	unsigned int id, end, cnt = 0;
+	unsigned int end;
 
 	/* Calculate the exclusive end */
 	end = lvlid + (1U << x86_topo_system.dom_shifts[at_level]);
-
-	/* Unfortunately there is no bitmap_weight_range() */
-	for (id = find_next_bit(map, end, lvlid); id < end; id = find_next_bit(map, end, ++id))
-		cnt++;
-	return cnt;
+	return bitmap_weight_from(map, lvlid, end);
 }
 
 static __init void topo_register_apic(u32 apic_id, u32 acpi_id, bool present)
diff --git a/drivers/gpu/drm/xe/xe_pagefault.c b/drivers/gpu/drm/xe/xe_pagefault.c
index 922a4f3344b1..5b30fd369769 100644
--- a/drivers/gpu/drm/xe/xe_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_pagefault.c
@@ -291,10 +291,9 @@ static int xe_pagefault_queue_init(struct xe_device *xe,
 		xe_dss_mask_t all_dss;
 		int num_dss, num_eus;
 
-		bitmap_or(all_dss, gt->fuse_topo.g_dss_mask,
+		num_dss = bitmap_weighted_or(all_dss, gt->fuse_topo.g_dss_mask,
 			  gt->fuse_topo.c_dss_mask, XE_MAX_DSS_FUSE_BITS);
 
-		num_dss = bitmap_weight(all_dss, XE_MAX_DSS_FUSE_BITS);
 		num_eus = bitmap_weight(gt->fuse_topo.eu_mask_per_dss,
 					XE_MAX_EU_FUSE_BITS) * num_dss;
 
diff --git a/drivers/hwtracing/coresight/coresight-cti-sysfs.c b/drivers/hwtracing/coresight/coresight-cti-sysfs.c
index 572b80ee96fb..26ec0d8ed181 100644
--- a/drivers/hwtracing/coresight/coresight-cti-sysfs.c
+++ b/drivers/hwtracing/coresight/coresight-cti-sysfs.c
@@ -606,14 +606,11 @@ static ssize_t chan_gate_enable_show(struct device *dev,
 	struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent);
 	struct cti_config *cfg = &drvdata->config;
 	unsigned long ctigate_bitmask = cfg->ctigate;
-	int size = 0;
 
 	if (cfg->ctigate == 0)
-		size = sprintf(buf, "\n");
-	else
-		size = bitmap_print_to_pagebuf(true, buf, &ctigate_bitmask,
-					       cfg->nr_ctm_channels);
-	return size;
+		return sprintf(buf, "\n");
+
+	return sysfs_emit(buf, "%*pbl\n", cfg->nr_ctm_channels, &ctigate_bitmask);
 }
 static DEVICE_ATTR_RW(chan_gate_enable);
 
@@ -710,12 +707,13 @@ static ssize_t trigout_filtered_show(struct device *dev,
 {
 	struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent);
 	struct cti_config *cfg = &drvdata->config;
-	int size = 0, nr_trig_max = cfg->nr_trig_max;
+	int nr_trig_max = cfg->nr_trig_max;
 	unsigned long mask = cfg->trig_out_filter;
 
-	if (mask)
-		size = bitmap_print_to_pagebuf(true, buf, &mask, nr_trig_max);
-	return size;
+	if (mask == 0)
+		return 0;
+
+	return sysfs_emit(buf, "%*pbl\n", nr_trig_max, &mask);
 }
 static DEVICE_ATTR_RO(trigout_filtered);
 
@@ -834,7 +832,7 @@ static ssize_t print_chan_list(struct device *dev,
 {
 	struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent);
 	struct cti_config *config = &drvdata->config;
-	int size, i;
+	int i;
 	unsigned long inuse_bits = 0, chan_mask;
 
 	/* scan regs to get bitmap of channels in use. */
@@ -852,11 +850,9 @@ static ssize_t print_chan_list(struct device *dev,
 	/* list of channels, or 'none' */
 	chan_mask = GENMASK(config->nr_ctm_channels - 1, 0);
 	if (inuse_bits & chan_mask)
-		size = bitmap_print_to_pagebuf(true, buf, &inuse_bits,
-					       config->nr_ctm_channels);
-	else
-		size = sprintf(buf, "\n");
-	return size;
+		return sysfs_emit(buf, "%*pbl\n", config->nr_ctm_channels, &inuse_bits);
+
+	return sprintf(buf, "\n");
 }
 
 static ssize_t chan_inuse_show(struct device *dev,
@@ -928,7 +924,7 @@ static ssize_t trigin_sig_show(struct device *dev,
 	struct cti_config *cfg = &drvdata->config;
 	unsigned long mask = con->con_in->used_mask;
 
-	return bitmap_print_to_pagebuf(true, buf, &mask, cfg->nr_trig_max);
+	return sysfs_emit(buf, "%*pbl\n", cfg->nr_trig_max, &mask);
 }
 
 static ssize_t trigout_sig_show(struct device *dev,
@@ -942,7 +938,7 @@ static ssize_t trigout_sig_show(struct device *dev,
 	struct cti_config *cfg = &drvdata->config;
 	unsigned long mask = con->con_out->used_mask;
 
-	return bitmap_print_to_pagebuf(true, buf, &mask, cfg->nr_trig_max);
+	return sysfs_emit(buf, "%*pbl\n", cfg->nr_trig_max, &mask);
 }
 
 /* convert a sig type id to a name */
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index bb0f990fa2c6..6a5875bd9c6b 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -4984,10 +4984,8 @@ ice_find_free_recp_res_idx(struct ice_hw *hw, const unsigned long *profiles,
 			  hw->switch_info->recp_list[bit].res_idxs,
 			  ICE_MAX_FV_WORDS);
 
-	bitmap_xor(free_idx, used_idx, possible_idx, ICE_MAX_FV_WORDS);
-
 	/* return number of free indexes */
-	return (u16)bitmap_weight(free_idx, ICE_MAX_FV_WORDS);
+	return (u16)bitmap_weighted_xor(free_idx, used_idx, possible_idx, ICE_MAX_FV_WORDS);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index c8bc952f05cd..772f6b07340d 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -1210,8 +1210,8 @@ bool ice_is_vf_trusted(struct ice_vf *vf)
  */
 bool ice_vf_has_no_qs_ena(struct ice_vf *vf)
 {
-	return (!bitmap_weight(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF) &&
-		!bitmap_weight(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF));
+	return bitmap_empty(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF) &&
+		bitmap_empty(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF);
 }
 
 /**
diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c
index 9a4cec000910..ccf380da12f2 100644
--- a/drivers/thermal/intel/intel_powerclamp.c
+++ b/drivers/thermal/intel/intel_powerclamp.c
@@ -200,8 +200,7 @@ static int cpumask_get(char *buf, const struct kernel_param *kp)
 	if (!cpumask_available(idle_injection_cpu_mask))
 		return -ENODEV;
 
-	return bitmap_print_to_pagebuf(false, buf, cpumask_bits(idle_injection_cpu_mask),
-				       nr_cpumask_bits);
+	return cpumap_print_to_pagebuf(false, buf, idle_injection_cpu_mask);
 }
 
 static const struct kernel_param_ops cpumask_ops = {
diff --git a/include/asm-generic/bitops/instrumented-atomic.h b/include/asm-generic/bitops/instrumented-atomic.h
index 4225a8ca9c1a..c010d54275e4 100644
--- a/include/asm-generic/bitops/instrumented-atomic.h
+++ b/include/asm-generic/bitops/instrumented-atomic.h
@@ -100,4 +100,4 @@ static __always_inline bool test_and_change_bit(long nr, volatile unsigned long
 	return arch_test_and_change_bit(nr, addr);
 }
 
-#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
+#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H */
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index b0395e4ccf90..b007d54a9036 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -46,6 +46,7 @@ struct device;
  *  bitmap_and(dst, src1, src2, nbits)          *dst = *src1 & *src2
  *  bitmap_or(dst, src1, src2, nbits)           *dst = *src1 | *src2
  *  bitmap_weighted_or(dst, src1, src2, nbits)	*dst = *src1 | *src2. Returns Hamming Weight of dst
+ *  bitmap_weighted_xor(dst, src1, src2, nbits)	*dst = *src1 ^ *src2. Returns Hamming Weight of dst
  *  bitmap_xor(dst, src1, src2, nbits)          *dst = *src1 ^ *src2
  *  bitmap_andnot(dst, src1, src2, nbits)       *dst = *src1 & ~(*src2)
  *  bitmap_complement(dst, src, nbits)          *dst = ~(*src)
@@ -57,6 +58,7 @@ struct device;
  *  bitmap_weight(src, nbits)                   Hamming Weight: number set bits
  *  bitmap_weight_and(src1, src2, nbits)        Hamming Weight of and'ed bitmap
  *  bitmap_weight_andnot(src1, src2, nbits)     Hamming Weight of andnot'ed bitmap
+ *  bitmap_weight_from(src, start, end)         Hamming Weight starting from @start
  *  bitmap_set(dst, pos, nbits)                 Set specified bit area
  *  bitmap_clear(dst, pos, nbits)               Clear specified bit area
  *  bitmap_find_next_zero_area(buf, len, pos, n, mask)  Find bit free area
@@ -168,6 +170,8 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int nbits);
 unsigned int __bitmap_weighted_or(unsigned long *dst, const unsigned long *bitmap1,
 				  const unsigned long *bitmap2, unsigned int nbits);
+unsigned int __bitmap_weighted_xor(unsigned long *dst, const unsigned long *bitmap1,
+				  const unsigned long *bitmap2, unsigned int nbits);
 void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
 		  const unsigned long *bitmap2, unsigned int nbits);
 bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
@@ -353,6 +357,18 @@ unsigned int bitmap_weighted_or(unsigned long *dst, const unsigned long *src1,
 }
 
 static __always_inline
+unsigned int bitmap_weighted_xor(unsigned long *dst, const unsigned long *src1,
+				const unsigned long *src2, unsigned int nbits)
+{
+	if (small_const_nbits(nbits)) {
+		*dst = *src1 ^ *src2;
+		return hweight_long(*dst & BITMAP_LAST_WORD_MASK(nbits));
+	} else {
+		return __bitmap_weighted_xor(dst, src1, src2, nbits);
+	}
+}
+
+static __always_inline
 void bitmap_xor(unsigned long *dst, const unsigned long *src1,
 		const unsigned long *src2, unsigned int nbits)
 {
@@ -479,6 +495,38 @@ unsigned long bitmap_weight_andnot(const unsigned long *src1,
 	return __bitmap_weight_andnot(src1, src2, nbits);
 }
 
+/**
+ * bitmap_weight_from - Hamming weight for a memory region
+ * @bitmap: The base address
+ * @start: The bitnumber to starts weighting
+ * @end: the bitmap size in bits
+ *
+ * Returns the number of set bits in the region. If @start >= @end,
+ * return >= end.
+ */
+static __always_inline
+unsigned long bitmap_weight_from(const unsigned long *bitmap,
+				   unsigned int start, unsigned int end)
+{
+	unsigned long w;
+
+	if (unlikely(start >= end))
+		return end;
+
+	if (small_const_nbits(end))
+		return hweight_long(*bitmap & GENMASK(end - 1, start));
+
+	bitmap += start / BITS_PER_LONG;
+	/* Opencode round_down() to not include math.h */
+	end -= start & ~(BITS_PER_LONG - 1);
+	start %= BITS_PER_LONG;
+	w = bitmap_weight(bitmap, end);
+	if (start)
+		w -= hweight_long(*bitmap & BITMAP_LAST_WORD_MASK(start));
+
+	return w;
+}
+
 static __always_inline
 void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits)
 {
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index ea7898cc5903..657eab2725ce 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -179,9 +179,11 @@ static inline __u8 ror8(__u8 word, unsigned int shift)
 /**
  * sign_extend32 - sign extend a 32-bit value using specified bit as sign-bit
  * @value: value to sign extend
- * @index: 0 based bit index (0<=index<32) to sign bit
+ * @index: 0 based bit index (0 <= index < 32) to sign bit
  *
  * This is safe to use for 16- and 8-bit types as well.
+ *
+ * Return: 32-bit sign extended value
  */
 static __always_inline __s32 sign_extend32(__u32 value, int index)
 {
@@ -192,7 +194,11 @@ static __always_inline __s32 sign_extend32(__u32 value, int index)
 /**
  * sign_extend64 - sign extend a 64-bit value using specified bit as sign-bit
  * @value: value to sign extend
- * @index: 0 based bit index (0<=index<64) to sign bit
+ * @index: 0 based bit index (0 <= index < 64) to sign bit
+ *
+ * This is safe to use for 32-, 16- and 8-bit types as well.
+ *
+ * Return: 64-bit sign extended value
  */
 static __always_inline __s64 sign_extend64(__u64 value, int index)
 {
@@ -230,7 +236,7 @@ static inline int get_count_order_long(unsigned long l)
 
 /**
  * parity8 - get the parity of an u8 value
- * @value: the value to be examined
+ * @val: the value to be examined
  *
  * Determine the parity of the u8 argument.
  *
diff --git a/include/linux/count_zeros.h b/include/linux/count_zeros.h
index 5b8ff5ac660d..b72ba3faa036 100644
--- a/include/linux/count_zeros.h
+++ b/include/linux/count_zeros.h
@@ -18,7 +18,7 @@
  *
  * If the MSB of @x is set, the result is 0.
  * If only the LSB of @x is set, then the result is BITS_PER_LONG-1.
- * If @x is 0 then the result is COUNT_LEADING_ZEROS_0.
+ * If @x is 0 then the result is BITS_PER_LONG.
  */
 static inline int count_leading_zeros(unsigned long x)
 {
@@ -28,8 +28,6 @@ static inline int count_leading_zeros(unsigned long x)
 		return BITS_PER_LONG - fls64(x);
 }
 
-#define COUNT_LEADING_ZEROS_0 BITS_PER_LONG
-
 /**
  * count_trailing_zeros - Count the number of zeros from the LSB forwards
  * @x: The value
@@ -38,16 +36,11 @@ static inline int count_leading_zeros(unsigned long x)
  *
  * If the LSB of @x is set, the result is 0.
  * If only the MSB of @x is set, then the result is BITS_PER_LONG-1.
- * If @x is 0 then the result is COUNT_TRAILING_ZEROS_0.
+ * If @x is 0 then the result is BITS_PER_LONG.
  */
 static inline int count_trailing_zeros(unsigned long x)
 {
-#define COUNT_TRAILING_ZEROS_0 (-1)
-
-	if (sizeof(x) == 4)
-		return ffs(x);
-	else
-		return (x != 0) ? __ffs(x) : COUNT_TRAILING_ZEROS_0;
+	return x ? __ffs(x) : BITS_PER_LONG;
 }
 
 #endif /* _LINUX_BITOPS_COUNT_ZEROS_H_ */
diff --git a/include/linux/find.h b/include/linux/find.h
index 9d720ad92bc1..6c2be8ca615d 100644
--- a/include/linux/find.h
+++ b/include/linux/find.h
@@ -22,8 +22,6 @@ extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long si
 unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n);
 unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2,
 				unsigned long size, unsigned long n);
-unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
-					unsigned long size, unsigned long n);
 unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
 					const unsigned long *addr3, unsigned long size,
 					unsigned long n);
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 9dc526507875..b9bfa157e095 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -69,6 +69,7 @@ bool __bitmap_or_equal(const unsigned long *bitmap1,
 	tmp = (bitmap1[k] | bitmap2[k]) ^ bitmap3[k];
 	return (tmp & BITMAP_LAST_WORD_MASK(bits)) == 0;
 }
+EXPORT_SYMBOL(__bitmap_or_equal);
 
 void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int bits)
 {
@@ -360,6 +361,14 @@ unsigned int __bitmap_weighted_or(unsigned long *dst, const unsigned long *bitma
 {
 	return BITMAP_WEIGHT(({dst[idx] = bitmap1[idx] | bitmap2[idx]; dst[idx]; }), bits);
 }
+EXPORT_SYMBOL(__bitmap_weighted_or);
+
+unsigned int __bitmap_weighted_xor(unsigned long *dst, const unsigned long *bitmap1,
+				  const unsigned long *bitmap2, unsigned int bits)
+{
+	return BITMAP_WEIGHT(({dst[idx] = bitmap1[idx] ^ bitmap2[idx]; dst[idx]; }), bits);
+}
+EXPORT_SYMBOL(__bitmap_weighted_xor);
 
 void __bitmap_set(unsigned long *map, unsigned int start, int len)
 {
diff --git a/lib/crypto/mpi/longlong.h b/lib/crypto/mpi/longlong.h
index b6fa1d08fb55..6d31c3a729f1 100644
--- a/lib/crypto/mpi/longlong.h
+++ b/lib/crypto/mpi/longlong.h
@@ -66,12 +66,12 @@
  * denominator).  Like udiv_qrnnd but the numbers are signed.  The quotient
  * is rounded towards 0.
  *
- * 5) count_leading_zeros(count, x) counts the number of zero-bits from the
+ * 5) count_leading_zeros(x) counts the number of zero-bits from the
  * msb to the first non-zero bit in the UWtype X.  This is the number of
- * steps X needs to be shifted left to set the msb.  Undefined for X == 0,
- * unless the symbol COUNT_LEADING_ZEROS_0 is defined to some value.
+ * steps X needs to be shifted left to set the msb.
+ * count_leading_zeros(0) == BITS_PER_LONG
  *
- * 6) count_trailing_zeros(count, x) like count_leading_zeros, but counts
+ * 6) count_trailing_zeros() like count_leading_zeros(), but counts
  * from the least significant end.
  *
  * 7) add_ssaaaa(high_sum, low_sum, high_addend_1, low_addend_1,
diff --git a/lib/find_bit.c b/lib/find_bit.c
index 5a0066c26d9a..5ac52dfce730 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -172,13 +172,6 @@ unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long
 }
 EXPORT_SYMBOL(__find_nth_and_bit);
 
-unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
-				 unsigned long size, unsigned long n)
-{
-	return FIND_NTH_BIT(addr1[idx] & ~addr2[idx], size, n);
-}
-EXPORT_SYMBOL(__find_nth_andnot_bit);
-
 unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1,
 					const unsigned long *addr2,
 					const unsigned long *addr3,
diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c
index 402e160e7186..00d9dc61cd46 100644
--- a/lib/find_bit_benchmark.c
+++ b/lib/find_bit_benchmark.c
@@ -30,18 +30,20 @@ static DECLARE_BITMAP(bitmap, BITMAP_LEN) __initdata;
 static DECLARE_BITMAP(bitmap2, BITMAP_LEN) __initdata;
 
 /*
- * This is Schlemiel the Painter's algorithm. It should be called after
- * all other tests for the same bitmap because it sets all bits of bitmap to 1.
+ * This is Schlemiel the Painter's algorithm.
  */
-static int __init test_find_first_bit(void *bitmap, unsigned long len)
+static int __init test_find_first_bit(const void *bitmap, unsigned long len)
 {
+	static DECLARE_BITMAP(cp, BITMAP_LEN) __initdata;
 	unsigned long i, cnt;
 	ktime_t time;
 
+	bitmap_copy(cp, bitmap, BITMAP_LEN);
+
 	time = ktime_get();
 	for (cnt = i = 0; i < len; cnt++) {
-		i = find_first_bit(bitmap, len);
-		__clear_bit(i, bitmap);
+		i = find_first_bit(cp, len);
+		__clear_bit(i, cp);
 	}
 	time = ktime_get() - time;
 	pr_err("find_first_bit:     %18llu ns, %6ld iterations\n", time, cnt);
@@ -49,7 +51,8 @@ static int __init test_find_first_bit(void *bitmap, unsigned long len)
 	return 0;
 }
 
-static int __init test_find_first_and_bit(void *bitmap, const void *bitmap2, unsigned long len)
+static int __init test_find_first_and_bit(const void *bitmap, const void *bitmap2,
+		unsigned long len)
 {
 	static DECLARE_BITMAP(cp, BITMAP_LEN) __initdata;
 	unsigned long i, cnt;
diff --git a/lib/math/tests/prime_numbers_kunit.c b/lib/math/tests/prime_numbers_kunit.c
index 2f1643208c66..55ac160c6dfa 100644
--- a/lib/math/tests/prime_numbers_kunit.c
+++ b/lib/math/tests/prime_numbers_kunit.c
@@ -8,12 +8,10 @@
 
 static void dump_primes(void *ctx, const struct primes *p)
 {
-	static char buf[PAGE_SIZE];
 	struct kunit_suite *suite = ctx;
 
-	bitmap_print_to_pagebuf(true, buf, p->primes, p->sz);
-	kunit_info(suite, "primes.{last=%lu, .sz=%lu, .primes[]=...x%lx} = %s",
-		   p->last, p->sz, p->primes[BITS_TO_LONGS(p->sz) - 1], buf);
+	kunit_info(suite, "primes.{last=%lu, .sz=%lu, .primes[]=...x%lx} = %*pbl",
+		   p->last, p->sz, p->primes[BITS_TO_LONGS(p->sz) - 1], (int)p->sz, p->primes);
 }
 
 static void prime_numbers_test(struct kunit *test)
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index c83829ef557f..69813c10e6c0 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -354,18 +354,22 @@ static void __init test_replace(void)
 
 static const unsigned long sg_mask[] __initconst = {
 	BITMAP_FROM_U64(0x000000000000035aULL),
+	BITMAP_FROM_U64(0x0000000000000000ULL),
 };
 
 static const unsigned long sg_src[] __initconst = {
 	BITMAP_FROM_U64(0x0000000000000667ULL),
+	BITMAP_FROM_U64(0x0000000000000000ULL),
 };
 
 static const unsigned long sg_gather_exp[] __initconst = {
 	BITMAP_FROM_U64(0x0000000000000029ULL),
+	BITMAP_FROM_U64(0x0000000000000000ULL),
 };
 
 static const unsigned long sg_scatter_exp[] __initconst = {
 	BITMAP_FROM_U64(0x000000000000021aULL),
+	BITMAP_FROM_U64(0x0000000000000000ULL),
 };
 
 static void __init test_bitmap_sg(void)
@@ -379,18 +383,18 @@ static void __init test_bitmap_sg(void)
 	/* Simple gather call */
 	bitmap_zero(bmap_gather, 100);
 	bitmap_gather(bmap_gather, sg_src, sg_mask, nbits);
-	expect_eq_bitmap(sg_gather_exp, bmap_gather, nbits);
+	expect_eq_bitmap(sg_gather_exp, bmap_gather, 100);
 
 	/* Simple scatter call */
 	bitmap_zero(bmap_scatter, 100);
 	bitmap_scatter(bmap_scatter, sg_src, sg_mask, nbits);
-	expect_eq_bitmap(sg_scatter_exp, bmap_scatter, nbits);
+	expect_eq_bitmap(sg_scatter_exp, bmap_scatter, 100);
 
 	/* Scatter/gather relationship */
 	bitmap_zero(bmap_tmp, 100);
 	bitmap_gather(bmap_tmp, bmap_scatter, sg_mask, nbits);
 	bitmap_scatter(bmap_res, bmap_tmp, sg_mask, nbits);
-	expect_eq_bitmap(bmap_scatter, bmap_res, nbits);
+	expect_eq_bitmap(bmap_scatter, bmap_res, 100);
 }
 
 #define PARSE_TIME	0x1
@@ -520,8 +524,7 @@ static void __init test_bitmap_parselist(void)
 		}
 
 		if (ptest.flags & PARSE_TIME)
-			pr_info("parselist: %d: input is '%s' OK, Time: %llu\n",
-					i, ptest.in, time);
+			pr_info("parselist('%s'):\t%llu\n", ptest.in, time);
 
 #undef ptest
 	}
@@ -544,22 +547,22 @@ static void __init test_bitmap_printlist(void)
 		goto out;
 
 	time = ktime_get();
-	ret = bitmap_print_to_pagebuf(true, buf, bmap, PAGE_SIZE * 8);
+	ret = scnprintf(buf, PAGE_SIZE, "%*pbl", (int)PAGE_SIZE * 8, bmap);
 	time = ktime_get() - time;
 
-	if (ret != slen + 1) {
-		pr_err("bitmap_print_to_pagebuf: result is %d, expected %d\n", ret, slen);
+	if (ret != slen) {
+		pr_err("scnprintf(\"%%*pbl\"): result is %d, expected %d\n", ret, slen);
 		failed_tests++;
 		goto out;
 	}
 
 	if (strncmp(buf, expected, slen)) {
-		pr_err("bitmap_print_to_pagebuf: result is %s, expected %s\n", buf, expected);
+		pr_err("scnprintf(\"%%*pbl\"): result is %s, expected %s\n", buf, expected);
 		failed_tests++;
 		goto out;
 	}
 
-	pr_info("bitmap_print_to_pagebuf: input is '%s', Time: %llu\n", buf, time);
+	pr_info("scnprintf(\"%%*pbl\", '%s'):\t%llu\n", buf, time);
 out:
 	kfree(buf);
 	kfree(bmap);
@@ -650,7 +653,7 @@ static void __init test_bitmap_arr32(void)
 
 	memset(arr, 0xa5, sizeof(arr));
 
-	for (nbits = 0; nbits < EXP1_IN_BITS; ++nbits) {
+	for (nbits = 1; nbits < EXP1_IN_BITS; ++nbits) {
 		bitmap_to_arr32(arr, exp1, nbits);
 		bitmap_from_arr32(bmap2, arr, nbits);
 		expect_eq_bitmap(bmap2, exp1, nbits);
@@ -678,7 +681,7 @@ static void __init test_bitmap_arr64(void)
 
 	memset(arr, 0xa5, sizeof(arr));
 
-	for (nbits = 0; nbits < EXP1_IN_BITS; ++nbits) {
+	for (nbits = 1; nbits < EXP1_IN_BITS; ++nbits) {
 		memset(bmap2, 0xff, sizeof(arr));
 		bitmap_to_arr64(arr, exp1, nbits);
 		bitmap_from_arr64(bmap2, arr, nbits);
@@ -711,7 +714,7 @@ static void noinline __init test_mem_optimisations(void)
 	unsigned int start, nbits;
 
 	for (start = 0; start < 1024; start += 8) {
-		for (nbits = 0; nbits < 1024 - start; nbits += 8) {
+		for (nbits = 1; nbits < 1024 - start; nbits += 8) {
 			memset(bmap1, 0x5a, sizeof(bmap1));
 			memset(bmap2, 0x5a, sizeof(bmap2));
 
@@ -851,6 +854,50 @@ static void __init test_for_each_set_bit_from(void)
 	}
 }
 
+static void __init test_bitmap_weight(void)
+{
+	unsigned int bit, w1, w2, w;
+	DECLARE_BITMAP(b, 30);
+	DECLARE_BITMAP(b1, 128);
+
+	bitmap_parselist("all:1/2", b, 30);
+
+	/* Test inline implementation */
+	w = bitmap_weight(b, 30);
+	w1 = bitmap_weight(b, 15);
+	w2 = bitmap_weight_from(b, 15, 30);
+
+	expect_eq_uint(15, w);
+	expect_eq_uint(8, w1);
+	expect_eq_uint(7, w2);
+
+	/* Test outline implementation */
+	w = bitmap_weight(exp1, EXP1_IN_BITS);
+	for (bit = 1; bit < EXP1_IN_BITS; bit++) {
+		w1 = bitmap_weight(exp1, bit);
+		w2 = bitmap_weight_from(exp1, bit, EXP1_IN_BITS);
+		expect_eq_uint(w1 + w2, w);
+	}
+
+	/* Test out-of-range */
+	w = bitmap_weight_from(b, 31, 30);
+	expect_eq_uint(0, !!(w < 30));
+
+	/*
+	 * Test bitmap_weight() for correctness in case of some bits set between
+	 * nbits and end of the last word.
+	 */
+	bitmap_fill(b1, 128);
+
+	/* Inline */
+	expect_eq_uint(30, bitmap_weight(b1, 30));
+	expect_eq_uint(100, bitmap_weight(b1, 100));
+
+	/* Outline */
+	for (int i  = 1; i < 128; i++)
+		expect_eq_uint(i, bitmap_weight(b1, i));
+}
+
 static void __init test_for_each_clear_bit(void)
 {
 	DECLARE_BITMAP(orig, 500);
@@ -1395,7 +1442,7 @@ static void __init test_bitmap_read_perf(void)
 		}
 	}
 	time = ktime_get() - time;
-	pr_info("Time spent in %s:\t%llu\n", __func__, time);
+	pr_info("%s:\t\t%llu\n", __func__, time);
 }
 
 static void __init test_bitmap_write_perf(void)
@@ -1417,7 +1464,63 @@ static void __init test_bitmap_write_perf(void)
 		}
 	}
 	time = ktime_get() - time;
-	pr_info("Time spent in %s:\t%llu\n", __func__, time);
+	pr_info("%s:\t\t%llu\n", __func__, time);
+}
+
+/*
+ * nbits == 0 is most commonly not a valid case. Bitmap users should revisit
+ * the caller logic. Bitmap API doesn't provide any guarantees on returned
+ * value. The pointers are not dereferenced. The return value is intentionally
+ * ignored.
+ */
+static void __init test_zero_nbits(void)
+{
+	static volatile __always_used unsigned long ret __initdata;
+
+	bitmap_clear(NULL, 0, 0);
+	bitmap_complement(NULL, NULL, 0);
+	bitmap_copy(NULL, NULL, 0);
+	bitmap_copy_clear_tail(NULL, NULL, 0);
+	bitmap_fill(NULL, 0);
+	bitmap_from_arr32(NULL, NULL, 0);
+	bitmap_from_arr64(NULL, NULL, 0);
+	bitmap_or(NULL, NULL, NULL, 0);
+	bitmap_set(NULL, 0, 0);
+	bitmap_shift_left(NULL, NULL, 0, 0);
+	bitmap_shift_right(NULL, NULL, 0, 0);
+	bitmap_to_arr32(NULL, NULL, 0);
+	bitmap_to_arr64(NULL, NULL, 0);
+	bitmap_write(NULL, 0, 0, 0);
+	bitmap_xor(NULL, NULL, NULL, 0);
+	bitmap_zero(NULL, 0);
+
+	ret = bitmap_and(NULL, NULL, NULL, 0);
+	ret = bitmap_empty(NULL, 0);
+	ret = bitmap_equal(NULL, NULL, 0);
+	ret = bitmap_full(NULL, 0);
+	ret = bitmap_or_equal(NULL, NULL, NULL, 0);
+	ret = bitmap_read(NULL, 0, 0);
+	ret = bitmap_subset(NULL, NULL, 0);
+	ret = bitmap_weight(NULL, 0);
+	ret = bitmap_weight_and(NULL, NULL, 0);
+	ret = bitmap_weight_andnot(NULL, NULL, 0);
+	ret = bitmap_weight_from(NULL, 0, 0);
+	ret = bitmap_weighted_or(NULL, NULL, NULL, 0);
+
+	ret = find_first_and_and_bit(NULL, NULL, NULL, 0);
+	ret = find_first_and_bit(NULL, NULL, 0);
+	ret = find_first_andnot_bit(NULL, NULL, 0);
+	ret = find_first_bit(NULL, 0);
+	ret = find_first_zero_bit(NULL, 0);
+	ret = find_last_bit(NULL, 0);
+	ret = find_next_and_bit(NULL, NULL, 0, 0);
+	ret = find_next_andnot_bit(NULL, NULL, 0, 0);
+	ret = find_next_bit(NULL, 0, 0);
+	ret = find_next_clump8(NULL, NULL, 0, 0);
+	ret = find_next_zero_bit(NULL, 0, 0);
+	ret = find_nth_and_bit(NULL, NULL, 0, 0);
+	ret = find_nth_bit(NULL, 0, 0);
+	ret = find_random_bit(NULL, 0);
 }
 
 #undef TEST_BIT_LEN
@@ -1441,7 +1544,9 @@ static void __init selftest(void)
 	test_bitmap_const_eval();
 	test_bitmap_read_write();
 	test_bitmap_read_perf();
+	test_bitmap_weight();
 	test_bitmap_write_perf();
+	test_zero_nbits();
 
 	test_find_nth_bit();
 	test_for_each_set_bit();