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

@@ -3533,10 +3533,14 @@ R:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 R:	Rasmus Villemoes <linux@rasmusvillemoes.dk>
 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

@@ -125,7 +125,7 @@ common_shutdown_1(void *generic_ptr)
 	/* 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

@@ -572,7 +572,7 @@ setup_arch (char **cmdline_p)
 #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

@@ -576,8 +576,6 @@ clear_cpu_sibling_map(int cpu)
 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]);
@@ -585,8 +583,6 @@ remove_siblinginfo(int 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

@@ -213,11 +213,10 @@ void __init riscv_fill_hwcap(void)
 		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

@@ -1332,8 +1332,7 @@ static int kvm_s390_set_processor_feat(struct kvm *kvm,
 		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],
@@ -1504,8 +1503,7 @@ static int kvm_s390_get_processor_feat(struct kvm *kvm,
 {
 	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",
@@ -1520,9 +1518,7 @@ static int kvm_s390_get_machine_feat(struct kvm *kvm,
 {
 	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

@@ -90,7 +90,7 @@ static void synic_update_vector(struct kvm_vcpu_hv_synic *synic,
 {
 	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;
@@ -100,16 +100,16 @@ static void synic_update_vector(struct kvm_vcpu_hv_synic *synic,
 	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)
@@ -1855,7 +1855,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 		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)
@@ -1956,7 +1956,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 		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

@@ -781,7 +781,7 @@ int smu_v11_0_set_allowed_mask(struct smu_context *smu)
 		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

@@ -837,7 +837,7 @@ int smu_v13_0_set_allowed_mask(struct smu_context *smu)
 	    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

@@ -1047,7 +1047,7 @@ static int i915_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
 	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

@@ -45,41 +45,31 @@ static irqreturn_t iio_simple_dummy_trigger_h(int irq, void *p)
 {
 	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

@@ -1603,12 +1603,8 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 		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

@@ -2180,13 +2180,9 @@ static int bcm_sysport_rule_set(struct bcm_sysport_priv *priv,
 	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

@@ -355,7 +355,7 @@ int otx2_add_macfilter(struct net_device *netdev, const u8 *mac)
 {
 	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",
@@ -438,7 +438,7 @@ int otx2_get_maxflows(struct otx2_flow_config *flow_cfg)
 		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

@@ -1120,7 +1120,7 @@ static int otx2_cgx_config_loopback(struct otx2_nic *pf, bool enable)
 	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

@@ -1994,21 +1994,16 @@ static void mlx4_allocate_port_vpps(struct mlx4_dev *dev, int port)
 
 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];
@@ -2063,19 +2058,13 @@ static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave)
 
 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

@@ -319,44 +319,27 @@ free_rdma_dev:
 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

@@ -76,7 +76,7 @@ void qed_roce_stop(struct qed_hwfn *p_hwfn)
 	 * 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

@@ -72,6 +72,8 @@ struct device;
  *  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
  *
@@ -132,8 +134,8 @@ unsigned long *devm_bitmap_zalloc(struct device *dev,
  * 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,
@@ -157,10 +159,10 @@ int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
 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);
@@ -264,8 +266,12 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst,
 }
 
 /*
- * 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,
@@ -281,6 +287,22 @@ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap,
 			(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,
 			const unsigned long *src2, unsigned int nbits)
 {
@@ -331,8 +353,8 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr
 #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));
@@ -362,8 +384,9 @@ static inline bool bitmap_or_equal(const unsigned long *src1,
 	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;
@@ -371,8 +394,8 @@ static inline int bitmap_intersects(const unsigned long *src1,
 		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));
@@ -514,10 +537,7 @@ static inline void bitmap_next_set_region(unsigned long *bitmap,
  */
 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

@@ -21,8 +21,8 @@ extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long siz
 /**
  * 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.
@@ -50,8 +50,8 @@ 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.
@@ -79,8 +79,8 @@ 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.