Merge tag 'bitmap-for-5.19-rc1' of https://github.com/norov/linux

Pull bitmap updates from Yury Norov:

- bitmap: optimize bitmap_weight() usage, from me

- lib/bitmap.c make bitmap_print_bitmask_to_buf parseable, from Mauro
Carvalho Chehab

- include/linux/find: Fix documentation, from Anna-Maria Behnsen

- bitmap: fix conversion from/to fix-sized arrays, from me

- bitmap: Fix return values to be unsigned, from Kees Cook

It has been in linux-next for at least a week with no problems.

* tag 'bitmap-for-5.19-rc1' of https://github.com/norov/linux: (31 commits)
nodemask: Fix return values to be unsigned
bitmap: Fix return values to be unsigned
KVM: x86: hyper-v: replace bitmap_weight() with hweight64()
KVM: x86: hyper-v: fix type of valid_bank_mask
ia64: cleanup remove_siblinginfo()
drm/amd/pm: use bitmap_{from,to}_arr32 where appropriate
KVM: s390: replace bitmap_copy with bitmap_{from,to}_arr64 where appropriate
lib/bitmap: add test for bitmap_{from,to}_arr64
lib: add bitmap_{from,to}_arr64
lib/bitmap: extend comment for bitmap_(from,to)_arr32()
include/linux/find: Fix documentation
lib/bitmap.c make bitmap_print_bitmask_to_buf parseable
MAINTAINERS: add cpumask and nodemask files to BITMAP_API
arch/x86: replace nodes_weight with nodes_empty where appropriate
mm/vmstat: replace cpumask_weight with cpumask_empty where appropriate
clocksource: replace cpumask_weight with cpumask_empty in clocksource.c
genirq/affinity: replace cpumask_weight with cpumask_empty where appropriate
irq: mips: replace cpumask_weight with cpumask_empty where appropriate
drm/i915/pmu: replace cpumask_weight with cpumask_empty where appropriate
arch/x86: replace cpumask_weight with cpumask_empty where appropriate
...

MAINTAINERS

···
 R:	Rasmus Villemoes <[e-mail]>
 S:	Maintained
 F:	include/linux/bitmap.h
+F:	include/linux/cpumask.h
 F:	include/linux/find.h
+F:	include/linux/nodemask.h
 F:	lib/bitmap.c
+F:	lib/cpumask.c
 F:	lib/find_bit.c
 F:	lib/find_bit_benchmark.c
+F:	lib/nodemask.c
 F:	lib/test_bitmap.c
 F:	tools/include/linux/bitmap.h
 F:	tools/include/linux/find.h

arch/alpha/kernel/process.c

···
 	/* Wait for the secondaries to halt. */
 	set_cpu_present(boot_cpuid, false);
 	set_cpu_possible(boot_cpuid, false);
-	while (cpumask_weight(cpu_present_mask))
+	while (!cpumask_empty(cpu_present_mask))
 		barrier();
 #endif
 

arch/ia64/kernel/setup.c

···
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 	prefill_possible_map();
 #endif
-	per_cpu_scan_finalize((cpumask_weight(&early_cpu_possible_map) == 0 ?
+	per_cpu_scan_finalize((cpumask_empty(&early_cpu_possible_map) ?
 		32 : cpumask_weight(&early_cpu_possible_map)),
 		additional_cpus > 0 ? additional_cpus : 0);
 #endif /* CONFIG_ACPI_NUMA */

arch/ia64/kernel/smpboot.c

···
 static void
 remove_siblinginfo(int cpu)
 {
-	int last = 0;
-
 	if (cpu_data(cpu)->threads_per_core == 1 &&
 	    cpu_data(cpu)->cores_per_socket == 1) {
 		cpumask_clear_cpu(cpu, &cpu_core_map[cpu]);
 		cpumask_clear_cpu(cpu, &per_cpu(cpu_sibling_map, cpu));
 		return;
 	}
-
-	last = (cpumask_weight(&cpu_core_map[cpu]) == 1 ? 1 : 0);
 
 	/* remove it from all sibling map's */
 	clear_cpu_sibling_map(cpu);

arch/riscv/kernel/cpufeature.c

···
 		else
 			elf_hwcap = this_hwcap;
 
-		if (bitmap_weight(riscv_isa, RISCV_ISA_EXT_MAX))
-			bitmap_and(riscv_isa, riscv_isa, this_isa, RISCV_ISA_EXT_MAX);
-		else
+		if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX))
 			bitmap_copy(riscv_isa, this_isa, RISCV_ISA_EXT_MAX);
-
+		else
+			bitmap_and(riscv_isa, riscv_isa, this_isa, RISCV_ISA_EXT_MAX);
 	}
 
 	/* We don't support systems with F but without D, so mask those out

arch/s390/kvm/kvm-s390.c

···
 		mutex_unlock(&kvm->lock);
 		return -EBUSY;
 	}
-	bitmap_copy(kvm->arch.cpu_feat, (unsigned long *) data.feat,
-		    KVM_S390_VM_CPU_FEAT_NR_BITS);
+	bitmap_from_arr64(kvm->arch.cpu_feat, data.feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
 	mutex_unlock(&kvm->lock);
 	VM_EVENT(kvm, 3, "SET: guest feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx",
 			 data.feat[0],
···
 {
 	struct kvm_s390_vm_cpu_feat data;
 
-	bitmap_copy((unsigned long *) data.feat, kvm->arch.cpu_feat,
-		    KVM_S390_VM_CPU_FEAT_NR_BITS);
+	bitmap_to_arr64(data.feat, kvm->arch.cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
 	if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
 		return -EFAULT;
 	VM_EVENT(kvm, 3, "GET: guest feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx",
···
 {
 	struct kvm_s390_vm_cpu_feat data;
 
-	bitmap_copy((unsigned long *) data.feat,
-		    kvm_s390_available_cpu_feat,
-		    KVM_S390_VM_CPU_FEAT_NR_BITS);
+	bitmap_to_arr64(data.feat, kvm_s390_available_cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
 	if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
 		return -EFAULT;
 	VM_EVENT(kvm, 3, "GET: host feat:  0x%16.16llx.0x%16.16llx.0x%16.16llx",

arch/x86/kvm/hyperv.c

···
 {
 	struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic);
 	struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
-	int auto_eoi_old, auto_eoi_new;
+	bool auto_eoi_old, auto_eoi_new;
 
 	if (vector < HV_SYNIC_FIRST_VALID_VECTOR)
 		return;
···
 	else
 		__clear_bit(vector, synic->vec_bitmap);
 
-	auto_eoi_old = bitmap_weight(synic->auto_eoi_bitmap, 256);
+	auto_eoi_old = !bitmap_empty(synic->auto_eoi_bitmap, 256);
 
 	if (synic_has_vector_auto_eoi(synic, vector))
 		__set_bit(vector, synic->auto_eoi_bitmap);
 	else
 		__clear_bit(vector, synic->auto_eoi_bitmap);
 
-	auto_eoi_new = bitmap_weight(synic->auto_eoi_bitmap, 256);
+	auto_eoi_new = !bitmap_empty(synic->auto_eoi_bitmap, 256);
 
-	if (!!auto_eoi_old == !!auto_eoi_new)
+	if (auto_eoi_old == auto_eoi_new)
 		return;
 
 	if (!enable_apicv)
···
 		all_cpus = flush_ex.hv_vp_set.format !=
 			HV_GENERIC_SET_SPARSE_4K;
 
-		if (hc->var_cnt != bitmap_weight((unsigned long *)&valid_bank_mask, 64))
+		if (hc->var_cnt != hweight64(valid_bank_mask))
 			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 
 		if (all_cpus)
···
 		valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask;
 		all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL;
 
-		if (hc->var_cnt != bitmap_weight((unsigned long *)&valid_bank_mask, 64))
+		if (hc->var_cnt != hweight64(valid_bank_mask))
 			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 
 		if (all_cpus)

drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c

···
 		goto failed;
 	}
 
-	bitmap_copy((unsigned long *)feature_mask, feature->allowed, 64);
+	bitmap_to_arr32(feature_mask, feature->allowed, 64);
 
 	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetAllowedFeaturesMaskHigh,
 					  feature_mask[1], NULL);

drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c

···
 	    feature->feature_num < 64)
 		return -EINVAL;
 
-	bitmap_copy((unsigned long *)feature_mask, feature->allowed, 64);
+	bitmap_to_arr32(feature_mask, feature->allowed, 64);
 
 	ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetAllowedFeaturesMaskHigh,
 					      feature_mask[1], NULL);

drivers/gpu/drm/i915/i915_pmu.c

···
 	GEM_BUG_ON(!pmu->base.event_init);
 
 	/* Select the first online CPU as a designated reader. */
-	if (!cpumask_weight(&i915_pmu_cpumask))
+	if (cpumask_empty(&i915_pmu_cpumask))
 		cpumask_set_cpu(cpu, &i915_pmu_cpumask);
 
 	return 0;

drivers/iio/dummy/iio_simple_dummy_buffer.c

···
 {
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
+	int i = 0, j;
 	u16 *data;
 
 	data = kmalloc(indio_dev->scan_bytes, GFP_KERNEL);
 	if (!data)
 		goto done;
 
-	if (!bitmap_empty(indio_dev->active_scan_mask, indio_dev->masklength)) {
-		/*
-		 * Three common options here:
-		 * hardware scans: certain combinations of channels make
-		 *   up a fast read.  The capture will consist of all of them.
-		 *   Hence we just call the grab data function and fill the
-		 *   buffer without processing.
-		 * software scans: can be considered to be random access
-		 *   so efficient reading is just a case of minimal bus
-		 *   transactions.
-		 * software culled hardware scans:
-		 *   occasionally a driver may process the nearest hardware
-		 *   scan to avoid storing elements that are not desired. This
-		 *   is the fiddliest option by far.
-		 * Here let's pretend we have random access. And the values are
-		 * in the constant table fakedata.
-		 */
-		int i, j;
-
-		for (i = 0, j = 0;
-		     i < bitmap_weight(indio_dev->active_scan_mask,
-				       indio_dev->masklength);
-		     i++, j++) {
-			j = find_next_bit(indio_dev->active_scan_mask,
-					  indio_dev->masklength, j);
-			/* random access read from the 'device' */
-			data[i] = fakedata[j];
-		}
-	}
+	/*
+	 * Three common options here:
+	 * hardware scans:
+	 *   certain combinations of channels make up a fast read. The capture
+	 *   will consist of all of them. Hence we just call the grab data
+	 *   function and fill the buffer without processing.
+	 * software scans:
+	 *   can be considered to be random access so efficient reading is just
+	 *   a case of minimal bus transactions.
+	 * software culled hardware scans:
+	 *   occasionally a driver may process the nearest hardware scan to avoid
+	 *   storing elements that are not desired. This is the fiddliest option
+	 *   by far.
+	 * Here let's pretend we have random access. And the values are in the
+	 * constant table fakedata.
+	 */
+	for_each_set_bit(j, indio_dev->active_scan_mask, indio_dev->masklength)
+		data[i++] = fakedata[j];
 
 	iio_push_to_buffers_with_timestamp(indio_dev, data,
 					   iio_get_time_ns(indio_dev));

drivers/net/dsa/b53/b53_common.c

···
 		return 0;
 	}
 
-	if (bitmap_weight(free_bins, dev->num_arl_bins) == 0)
-		return -ENOSPC;
-
 	*idx = find_first_bit(free_bins, dev->num_arl_bins);
-
-	return -ENOENT;
+	return *idx >= dev->num_arl_bins ? -ENOSPC : -ENOENT;
 }
 
 static int b53_arl_op(struct b53_device *dev, int op, int port,

drivers/net/ethernet/broadcom/bcmsysport.c

···
 	if (nfc->fs.ring_cookie != RX_CLS_FLOW_WAKE)
 		return -EOPNOTSUPP;
 
-	/* All filters are already in use, we cannot match more rules */
-	if (bitmap_weight(priv->filters, RXCHK_BRCM_TAG_MAX) ==
-	    RXCHK_BRCM_TAG_MAX)
-		return -ENOSPC;
-
 	index = find_first_zero_bit(priv->filters, RXCHK_BRCM_TAG_MAX);
 	if (index >= RXCHK_BRCM_TAG_MAX)
+		/* All filters are already in use, we cannot match more rules */
 		return -ENOSPC;
 
 	/* Location is the classification ID, and index is the position

drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c

···
 {
 	struct otx2_nic *pf = netdev_priv(netdev);
 
-	if (bitmap_weight(&pf->flow_cfg->dmacflt_bmap,
+	if (!bitmap_empty(&pf->flow_cfg->dmacflt_bmap,
 			  pf->flow_cfg->dmacflt_max_flows))
 		netdev_warn(netdev,
 			    "Add %pM to CGX/RPM DMAC filters list as well\n",
···
 		return 0;
 
 	if (flow_cfg->nr_flows == flow_cfg->max_flows ||
-	    bitmap_weight(&flow_cfg->dmacflt_bmap,
+	    !bitmap_empty(&flow_cfg->dmacflt_bmap,
 			  flow_cfg->dmacflt_max_flows))
 		return flow_cfg->max_flows + flow_cfg->dmacflt_max_flows;
 	else

drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c

···
 	struct msg_req *msg;
 	int err;
 
-	if (enable && bitmap_weight(&pf->flow_cfg->dmacflt_bmap,
+	if (enable && !bitmap_empty(&pf->flow_cfg->dmacflt_bmap,
 				    pf->flow_cfg->dmacflt_max_flows))
 		netdev_warn(pf->netdev,
 			    "CGX/RPM internal loopback might not work as DMAC filters are active\n");

drivers/net/ethernet/mellanox/mlx4/cmd.c

···
 
 static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave)
 {
-	int port, err;
+	int p, port, err;
 	struct mlx4_vport_state *vp_admin;
 	struct mlx4_vport_oper_state *vp_oper;
 	struct mlx4_slave_state *slave_state =
 		&priv->mfunc.master.slave_state[slave];
 	struct mlx4_active_ports actv_ports = mlx4_get_active_ports(
 			&priv->dev, slave);
-	int min_port = find_first_bit(actv_ports.ports,
-				      priv->dev.caps.num_ports) + 1;
-	int max_port = min_port - 1 +
-		bitmap_weight(actv_ports.ports, priv->dev.caps.num_ports);
 
-	for (port = min_port; port <= max_port; port++) {
-		if (!test_bit(port - 1, actv_ports.ports))
-			continue;
+	for_each_set_bit(p, actv_ports.ports, priv->dev.caps.num_ports) {
+		port = p + 1;
 		priv->mfunc.master.vf_oper[slave].smi_enabled[port] =
 			priv->mfunc.master.vf_admin[slave].enable_smi[port];
 		vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
···
 
 static void mlx4_master_deactivate_admin_state(struct mlx4_priv *priv, int slave)
 {
-	int port;
+	int p, port;
 	struct mlx4_vport_oper_state *vp_oper;
 	struct mlx4_active_ports actv_ports = mlx4_get_active_ports(
 			&priv->dev, slave);
-	int min_port = find_first_bit(actv_ports.ports,
-				      priv->dev.caps.num_ports) + 1;
-	int max_port = min_port - 1 +
-		bitmap_weight(actv_ports.ports, priv->dev.caps.num_ports);
 
-
-	for (port = min_port; port <= max_port; port++) {
-		if (!test_bit(port - 1, actv_ports.ports))
-			continue;
+	for_each_set_bit(p, actv_ports.ports, priv->dev.caps.num_ports) {
+		port = p + 1;
 		priv->mfunc.master.vf_oper[slave].smi_enabled[port] =
 			MLX4_VF_SMI_DISABLED;
 		vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];

drivers/net/ethernet/qlogic/qed/qed_rdma.c

···
 void qed_rdma_bmap_free(struct qed_hwfn *p_hwfn,
 			struct qed_bmap *bmap, bool check)
 {
-	int weight = bitmap_weight(bmap->bitmap, bmap->max_count);
-	int last_line = bmap->max_count / (64 * 8);
-	int last_item = last_line * 8 +
-	    DIV_ROUND_UP(bmap->max_count % (64 * 8), 64);
-	u64 *pmap = (u64 *)bmap->bitmap;
-	int line, item, offset;
-	u8 str_last_line[200] = { 0 };
+	unsigned int bit, weight, nbits;
+	unsigned long *b;
 
-	if (!weight || !check)
+	if (!check)
+		goto end;
+
+	weight = bitmap_weight(bmap->bitmap, bmap->max_count);
+	if (!weight)
 		goto end;
 
 	DP_NOTICE(p_hwfn,
 		  "%s bitmap not free - size=%d, weight=%d, 512 bits per line\n",
 		  bmap->name, bmap->max_count, weight);
 
-	/* print aligned non-zero lines, if any */
-	for (item = 0, line = 0; line < last_line; line++, item += 8)
-		if (bitmap_weight((unsigned long *)&pmap[item], 64 * 8))
-			DP_NOTICE(p_hwfn,
-				  "line 0x%04x: 0x%016llx 0x%016llx 0x%016llx 0x%016llx 0x%016llx 0x%016llx 0x%016llx 0x%016llx\n",
-				  line,
-				  pmap[item],
-				  pmap[item + 1],
-				  pmap[item + 2],
-				  pmap[item + 3],
-				  pmap[item + 4],
-				  pmap[item + 5],
-				  pmap[item + 6], pmap[item + 7]);
+	for (bit = 0; bit < bmap->max_count; bit += 512) {
+		b =  bmap->bitmap + BITS_TO_LONGS(bit);
+		nbits = min(bmap->max_count - bit, 512U);
 
-	/* print last unaligned non-zero line, if any */
-	if ((bmap->max_count % (64 * 8)) &&
-	    (bitmap_weight((unsigned long *)&pmap[item],
-			   bmap->max_count - item * 64))) {
-		offset = sprintf(str_last_line, "line 0x%04x: ", line);
-		for (; item < last_item; item++)
-			offset += sprintf(str_last_line + offset,
-					  "0x%016llx ", pmap[item]);
-		DP_NOTICE(p_hwfn, "%s\n", str_last_line);
+		if (!bitmap_empty(b, nbits))
+			DP_NOTICE(p_hwfn,
+				  "line 0x%04x: %*pb\n", bit / 512, nbits, b);
 	}
 
 end:

drivers/net/ethernet/qlogic/qed/qed_roce.c

···
 	 * We delay for a short while if an async destroy QP is still expected.
 	 * Beyond the added delay we clear the bitmap anyway.
 	 */
-	while (bitmap_weight(rcid_map->bitmap, rcid_map->max_count)) {
+	while (!bitmap_empty(rcid_map->bitmap, rcid_map->max_count)) {
 		/* If the HW device is during recovery, all resources are
 		 * immediately reset without receiving a per-cid indication
 		 * from HW. In this case we don't expect the cid bitmap to be

include/linux/bitmap.h

···
  *  bitmap_allocate_region(bitmap, pos, order)  Allocate specified bit region
  *  bitmap_from_arr32(dst, buf, nbits)          Copy nbits from u32[] buf to dst
  *  bitmap_to_arr32(buf, src, nbits)            Copy nbits from buf to u32[] dst
+ *  bitmap_to_arr64(buf, src, nbits)            Copy nbits from buf to u64[] dst
+ *  bitmap_to_arr64(buf, src, nbits)            Copy nbits from buf to u64[] dst
  *  bitmap_get_value8(map, start)               Get 8bit value from map at start
  *  bitmap_set_value8(map, value, start)        Set 8bit value to map at start
  *
···
  * lib/bitmap.c provides these functions:
  */
 
-int __bitmap_equal(const unsigned long *bitmap1,
-		   const unsigned long *bitmap2, unsigned int nbits);
+bool __bitmap_equal(const unsigned long *bitmap1,
+		    const unsigned long *bitmap2, unsigned int nbits);
 bool __pure __bitmap_or_equal(const unsigned long *src1,
 			      const unsigned long *src2,
 			      const unsigned long *src3,
···
 void __bitmap_replace(unsigned long *dst,
 		      const unsigned long *old, const unsigned long *new,
 		      const unsigned long *mask, unsigned int nbits);
-int __bitmap_intersects(const unsigned long *bitmap1,
-			const unsigned long *bitmap2, unsigned int nbits);
-int __bitmap_subset(const unsigned long *bitmap1,
-		    const unsigned long *bitmap2, unsigned int nbits);
+bool __bitmap_intersects(const unsigned long *bitmap1,
+			 const unsigned long *bitmap2, unsigned int nbits);
+bool __bitmap_subset(const unsigned long *bitmap1,
+		     const unsigned long *bitmap2, unsigned int nbits);
 int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
 void __bitmap_set(unsigned long *map, unsigned int start, int len);
 void __bitmap_clear(unsigned long *map, unsigned int start, int len);
···
 }
 
 /*
- * On 32-bit systems bitmaps are represented as u32 arrays internally, and
- * therefore conversion is not needed when copying data from/to arrays of u32.
+ * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64
+ * machines the order of hi and lo parts of numbers match the bitmap structure.
+ * In both cases conversion is not needed when copying data from/to arrays of
+ * u32. But in LE64 case, typecast in bitmap_copy_clear_tail() may lead
+ * to out-of-bound access. To avoid that, both LE and BE variants of 64-bit
+ * architectures are not using bitmap_copy_clear_tail().
  */
 #if BITS_PER_LONG == 64
 void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf,
···
 #define bitmap_to_arr32(buf, bitmap, nbits)			\
 	bitmap_copy_clear_tail((unsigned long *) (buf),		\
 			(const unsigned long *) (bitmap), (nbits))
+#endif
+
+/*
+ * On 64-bit systems bitmaps are represented as u64 arrays internally. On LE32
+ * machines the order of hi and lo parts of numbers match the bitmap structure.
+ * In both cases conversion is not needed when copying data from/to arrays of
+ * u64.
+ */
+#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN)
+void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits);
+void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits);
+#else
+#define bitmap_from_arr64(bitmap, buf, nbits)			\
+	bitmap_copy_clear_tail((unsigned long *)(bitmap), (const unsigned long *)(buf), (nbits))
+#define bitmap_to_arr64(buf, bitmap, nbits)			\
+	bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits))
 #endif
 
 static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
···
 #endif
 #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1)
 
-static inline int bitmap_equal(const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static inline bool bitmap_equal(const unsigned long *src1,
+				const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
···
 	return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits));
 }
 
-static inline int bitmap_intersects(const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static inline bool bitmap_intersects(const unsigned long *src1,
+				     const unsigned long *src2,
+				     unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
···
 		return __bitmap_intersects(src1, src2, nbits);
 }
 
-static inline int bitmap_subset(const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static inline bool bitmap_subset(const unsigned long *src1,
+				 const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits));
···
  */
 static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
 {
-	dst[0] = mask & ULONG_MAX;
-
-	if (sizeof(mask) > sizeof(unsigned long))
-		dst[1] = mask >> 32;
+	bitmap_from_arr64(dst, &mask, 64);
 }
 
 /**

include/linux/find.h

···
 /**
  * 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.
···
  * 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.
···
 /**
  * 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.

include/linux/nodemask.h

···
  * void nodes_shift_right(dst, src, n)	Shift right
  * void nodes_shift_left(dst, src, n)	Shift left
  *
- * int first_node(mask)			Number lowest set bit, or MAX_NUMNODES
- * int next_node(node, mask)		Next node past 'node', or MAX_NUMNODES
- * int next_node_in(node, mask)		Next node past 'node', or wrap to first,
+ * unsigned int first_node(mask)	Number lowest set bit, or MAX_NUMNODES
+ * unsigend int next_node(node, mask)	Next node past 'node', or MAX_NUMNODES
+ * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first,
  *					or MAX_NUMNODES
- * int first_unset_node(mask)		First node not set in mask, or 
+ * unsigned int first_unset_node(mask)	First node not set in mask, or
  *					MAX_NUMNODES
  *
  * nodemask_t nodemask_of_node(node)	Return nodemask with bit 'node' set
···
 
 #define node_test_and_set(node, nodemask) \
 			__node_test_and_set((node), &(nodemask))
-static inline int __node_test_and_set(int node, nodemask_t *addr)
+static inline bool __node_test_and_set(int node, nodemask_t *addr)
 {
 	return test_and_set_bit(node, addr->bits);
 }
···
 
 #define nodes_equal(src1, src2) \
 			__nodes_equal(&(src1), &(src2), MAX_NUMNODES)
-static inline int __nodes_equal(const nodemask_t *src1p,
+static inline bool __nodes_equal(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_equal(src1p->bits, src2p->bits, nbits);
···
 
 #define nodes_intersects(src1, src2) \
 			__nodes_intersects(&(src1), &(src2), MAX_NUMNODES)
-static inline int __nodes_intersects(const nodemask_t *src1p,
+static inline bool __nodes_intersects(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_intersects(src1p->bits, src2p->bits, nbits);
···
 
 #define nodes_subset(src1, src2) \
 			__nodes_subset(&(src1), &(src2), MAX_NUMNODES)
-static inline int __nodes_subset(const nodemask_t *src1p,
+static inline bool __nodes_subset(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_subset(src1p->bits, src2p->bits, nbits);
 }
 
 #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES)
-static inline int __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
+static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_empty(srcp->bits, nbits);
 }
 
 #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES)
-static inline int __nodes_full(const nodemask_t *srcp, unsigned int nbits)
+static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_full(srcp->bits, nbits);
 }
···
           > MAX_NUMNODES, then the silly min_ts could be dropped. */
 
 #define first_node(src) __first_node(&(src))
-static inline int __first_node(const nodemask_t *srcp)
+static inline unsigned int __first_node(const nodemask_t *srcp)
 {
-	return min_t(int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES));
+	return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES));
 }
 
 #define next_node(n, src) __next_node((n), &(src))
-static inline int __next_node(int n, const nodemask_t *srcp)
+static inline unsigned int __next_node(int n, const nodemask_t *srcp)
 {
-	return min_t(int,MAX_NUMNODES,find_next_bit(srcp->bits, MAX_NUMNODES, n+1));
+	return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1));
 }
 
 /*
···
  * the first node in src if needed.  Returns MAX_NUMNODES if src is empty.
  */
 #define next_node_in(n, src) __next_node_in((n), &(src))
-int __next_node_in(int node, const nodemask_t *srcp);
+unsigned int __next_node_in(int node, const nodemask_t *srcp);
 
 static inline void init_nodemask_of_node(nodemask_t *mask, int node)
 {
···
 })
 
 #define first_unset_node(mask) __first_unset_node(&(mask))
-static inline int __first_unset_node(const nodemask_t *maskp)
+static inline unsigned int __first_unset_node(const nodemask_t *maskp)
 {
-	return min_t(int,MAX_NUMNODES,
+	return min_t(unsigned int, MAX_NUMNODES,
 			find_first_zero_bit(maskp->bits, MAX_NUMNODES));
 }
 
···
 
 #define first_online_node	first_node(node_states[N_ONLINE])
 #define first_memory_node	first_node(node_states[N_MEMORY])
-static inline int next_online_node(int nid)
+static inline unsigned int next_online_node(int nid)
 {
 	return next_node(nid, node_states[N_ONLINE]);
 }
-static inline int next_memory_node(int nid)
+static inline unsigned int next_memory_node(int nid)
 {
 	return next_node(nid, node_states[N_MEMORY]);
 }

lib/bitmap.c

···
  * for the best explanations of this ordering.
  */
 
-int __bitmap_equal(const unsigned long *bitmap1,
-		const unsigned long *bitmap2, unsigned int bits)
+bool __bitmap_equal(const unsigned long *bitmap1,
+		    const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k, lim = bits/BITS_PER_LONG;
 	for (k = 0; k < lim; ++k)
 		if (bitmap1[k] != bitmap2[k])
-			return 0;
+			return false;
 
 	if (bits % BITS_PER_LONG)
 		if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
-			return 0;
+			return false;
 
-	return 1;
+	return true;
 }
 EXPORT_SYMBOL(__bitmap_equal);
 
···
 }
 EXPORT_SYMBOL(__bitmap_replace);
 
-int __bitmap_intersects(const unsigned long *bitmap1,
-			const unsigned long *bitmap2, unsigned int bits)
+bool __bitmap_intersects(const unsigned long *bitmap1,
+			 const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k, lim = bits/BITS_PER_LONG;
 	for (k = 0; k < lim; ++k)
 		if (bitmap1[k] & bitmap2[k])
-			return 1;
+			return true;
 
 	if (bits % BITS_PER_LONG)
 		if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
-			return 1;
-	return 0;
+			return true;
+	return false;
 }
 EXPORT_SYMBOL(__bitmap_intersects);
 
-int __bitmap_subset(const unsigned long *bitmap1,
-		    const unsigned long *bitmap2, unsigned int bits)
+bool __bitmap_subset(const unsigned long *bitmap1,
+		     const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k, lim = bits/BITS_PER_LONG;
 	for (k = 0; k < lim; ++k)
 		if (bitmap1[k] & ~bitmap2[k])
-			return 0;
+			return false;
 
 	if (bits % BITS_PER_LONG)
 		if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
-			return 0;
-	return 1;
+			return false;
+	return true;
 }
 EXPORT_SYMBOL(__bitmap_subset);
 
···
  * cpumap_print_to_pagebuf() or directly by drivers to export hexadecimal
  * bitmask and decimal list to userspace by sysfs ABI.
  * Drivers might be using a normal attribute for this kind of ABIs. A
- * normal attribute typically has show entry as below:
- * static ssize_t example_attribute_show(struct device *dev,
+ * normal attribute typically has show entry as below::
+ *
+ *   static ssize_t example_attribute_show(struct device *dev,
  * 		struct device_attribute *attr, char *buf)
- * {
+ *   {
  * 	...
  * 	return bitmap_print_to_pagebuf(true, buf, &mask, nr_trig_max);
- * }
+ *   }
+ *
  * show entry of attribute has no offset and count parameters and this
  * means the file is limited to one page only.
  * bitmap_print_to_pagebuf() API works terribly well for this kind of
- * normal attribute with buf parameter and without offset, count:
- * bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp,
+ * normal attribute with buf parameter and without offset, count::
+ *
+ *   bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp,
  * 			   int nmaskbits)
- * {
- * }
+ *   {
+ *   }
+ *
  * The problem is once we have a large bitmap, we have a chance to get a
  * bitmask or list more than one page. Especially for list, it could be
  * as complex as 0,3,5,7,9,... We have no simple way to know it exact size.
  * It turns out bin_attribute is a way to break this limit. bin_attribute
- * has show entry as below:
- * static ssize_t
- * example_bin_attribute_show(struct file *filp, struct kobject *kobj,
+ * has show entry as below::
+ *
+ *   static ssize_t
+ *   example_bin_attribute_show(struct file *filp, struct kobject *kobj,
  * 		struct bin_attribute *attr, char *buf,
  * 		loff_t offset, size_t count)
- * {
+ *   {
  * 	...
- * }
+ *   }
+ *
  * With the new offset and count parameters, this makes sysfs ABI be able
  * to support file size more than one page. For example, offset could be
  * >= 4096.
···
  * This function is not a replacement for sprintf() or bitmap_print_to_pagebuf().
  * It is intended to workaround sysfs limitations discussed above and should be
  * used carefully in general case for the following reasons:
+ *
  *  - Time complexity is O(nbits^2/count), comparing to O(nbits) for snprintf().
  *  - Memory complexity is O(nbits), comparing to O(1) for snprintf().
  *  - @off and @count are NOT offset and number of bits to print.
···
 		buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31));
 }
 EXPORT_SYMBOL(bitmap_to_arr32);
+#endif
 
+#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN)
+/**
+ * bitmap_from_arr64 - copy the contents of u64 array of bits to bitmap
+ *	@bitmap: array of unsigned longs, the destination bitmap
+ *	@buf: array of u64 (in host byte order), the source bitmap
+ *	@nbits: number of bits in @bitmap
+ */
+void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits)
+{
+	int n;
+
+	for (n = nbits; n > 0; n -= 64) {
+		u64 val = *buf++;
+
+		*bitmap++ = val;
+		if (n > 32)
+			*bitmap++ = val >> 32;
+	}
+
+	/*
+	 * Clear tail bits in the last word beyond nbits.
+	 *
+	 * Negative index is OK because here we point to the word next
+	 * to the last word of the bitmap, except for nbits == 0, which
+	 * is tested implicitly.
+	 */
+	if (nbits % BITS_PER_LONG)
+		bitmap[-1] &= BITMAP_LAST_WORD_MASK(nbits);
+}
+EXPORT_SYMBOL(bitmap_from_arr64);
+
+/**
+ * bitmap_to_arr64 - copy the contents of bitmap to a u64 array of bits
+ *	@buf: array of u64 (in host byte order), the dest bitmap
+ *	@bitmap: array of unsigned longs, the source bitmap
+ *	@nbits: number of bits in @bitmap
+ */
+void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits)
+{
+	const unsigned long *end = bitmap + BITS_TO_LONGS(nbits);
+
+	while (bitmap < end) {
+		*buf = *bitmap++;
+		if (bitmap < end)
+			*buf |= (u64)(*bitmap++) << 32;
+		buf++;
+	}
+
+	/* Clear tail bits in the last element of array beyond nbits. */
+	if (nbits % 64)
+		buf[-1] &= GENMASK_ULL(nbits % 64, 0);
+}
+EXPORT_SYMBOL(bitmap_to_arr64);
 #endif

lib/nodemask.c

···
 #include <linux/module.h>
 #include <linux/random.h>
 
-int __next_node_in(int node, const nodemask_t *srcp)
+unsigned int __next_node_in(int node, const nodemask_t *srcp)
 {
-	int ret = __next_node(node, srcp);
+	unsigned int ret = __next_node(node, srcp);
 
 	if (ret == MAX_NUMNODES)
 		ret = __first_node(srcp);

lib/test_bitmap.c

···
 	}
 }
 
+static void __init test_bitmap_arr64(void)
+{
+	unsigned int nbits, next_bit;
+	u64 arr[EXP1_IN_BITS / 64];
+	DECLARE_BITMAP(bmap2, EXP1_IN_BITS);
+
+	memset(arr, 0xa5, sizeof(arr));
+
+	for (nbits = 0; nbits < EXP1_IN_BITS; ++nbits) {
+		memset(bmap2, 0xff, sizeof(arr));
+		bitmap_to_arr64(arr, exp1, nbits);
+		bitmap_from_arr64(bmap2, arr, nbits);
+		expect_eq_bitmap(bmap2, exp1, nbits);
+
+		next_bit = find_next_bit(bmap2, round_up(nbits, BITS_PER_LONG), nbits);
+		if (next_bit < round_up(nbits, BITS_PER_LONG))
+			pr_err("bitmap_copy_arr64(nbits == %d:"
+				" tail is not safely cleared: %d\n", nbits, next_bit);
+
+		if (nbits < EXP1_IN_BITS - 64)
+			expect_eq_uint(arr[DIV_ROUND_UP(nbits, 64)], 0xa5a5a5a5);
+	}
+}
+
 static void noinline __init test_mem_optimisations(void)
 {
 	DECLARE_BITMAP(bmap1, 1024);
···
 	test_copy();
 	test_replace();
 	test_bitmap_arr32();
+	test_bitmap_arr64();
 	test_bitmap_parse();
 	test_bitmap_parselist();
 	test_bitmap_printlist();

mm/vmstat.c

···
 	int node;
 
 	for_each_online_node(node) {
-		if (cpumask_weight(cpumask_of_node(node)) > 0)
+		if (!cpumask_empty(cpumask_of_node(node)))
 			node_set_state(node, N_CPU);
 	}
 }
···
 
 	refresh_zone_stat_thresholds();
 	node_cpus = cpumask_of_node(node);
-	if (cpumask_weight(node_cpus) > 0)
+	if (!cpumask_empty(node_cpus))
 		return 0;
 
 	node_clear_state(node, N_CPU);

tools/include/linux/bitmap.h

···
 		 const unsigned long *bitmap2, int bits);
 int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int bits);
-int __bitmap_equal(const unsigned long *bitmap1,
-		   const unsigned long *bitmap2, unsigned int bits);
+bool __bitmap_equal(const unsigned long *bitmap1,
+		    const unsigned long *bitmap2, unsigned int bits);
 void bitmap_clear(unsigned long *map, unsigned int start, int len);
-int __bitmap_intersects(const unsigned long *bitmap1,
-			const unsigned long *bitmap2, unsigned int bits);
+bool __bitmap_intersects(const unsigned long *bitmap1,
+			 const unsigned long *bitmap2, unsigned int bits);
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))
···
 #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1)
 #define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0)
 
-static inline int bitmap_equal(const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static inline bool bitmap_equal(const unsigned long *src1,
+				const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
···
 	return __bitmap_equal(src1, src2, nbits);
 }
 
-static inline int bitmap_intersects(const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static inline bool bitmap_intersects(const unsigned long *src1,
+				     const unsigned long *src2,
+				     unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;

tools/lib/bitmap.c

···
 	return result != 0;
 }
 
-int __bitmap_equal(const unsigned long *bitmap1,
-		const unsigned long *bitmap2, unsigned int bits)
+bool __bitmap_equal(const unsigned long *bitmap1,
+		    const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k, lim = bits/BITS_PER_LONG;
 	for (k = 0; k < lim; ++k)
 		if (bitmap1[k] != bitmap2[k])
-			return 0;
+			return false;
 
 	if (bits % BITS_PER_LONG)
 		if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
-			return 0;
+			return false;
 
-	return 1;
+	return true;
 }
 
-int __bitmap_intersects(const unsigned long *bitmap1,
-			const unsigned long *bitmap2, unsigned int bits)
+bool __bitmap_intersects(const unsigned long *bitmap1,
+			 const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k, lim = bits/BITS_PER_LONG;
 	for (k = 0; k < lim; ++k)
 		if (bitmap1[k] & bitmap2[k])
-			return 1;
+			return true;
 
 	if (bits % BITS_PER_LONG)
 		if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
-			return 1;
-	return 0;
+			return true;
+	return false;
 }