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
  ...

11 files changed, 48 insertions, 94 deletions

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index b87f550af26b..5f8809f6990d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/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);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index 7be4f6875a7b..ef9b56de143b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/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);
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 3e3b09588fd3..958b37123bf1 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/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;
diff --git a/drivers/iio/dummy/iio_simple_dummy_buffer.c b/drivers/iio/dummy/iio_simple_dummy_buffer.c
index d81c2b2dad82..9b2f99449a82 100644
--- a/drivers/iio/dummy/iio_simple_dummy_buffer.c
+++ b/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));
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index fbb32aa49b24..48cf344750ff 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/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,
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 3272aca496dc..47fc8e6963d5 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/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
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 54f235c216a9..2dd192b5e4e0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/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
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index fe3472e04c23..9106c359e64c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/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");
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index e10b7b04b894..c56d2194cbfc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/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];
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 23b668de4640..69b0ede75cae 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/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 };
-
-	if (!weight || !check)
+	unsigned int bit, weight, nbits;
+	unsigned long *b;
+
+	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))
+	for (bit = 0; bit < bmap->max_count; bit += 512) {
+		b =  bmap->bitmap + BITS_TO_LONGS(bit);
+		nbits = min(bmap->max_count - bit, 512U);
+
+		if (!bitmap_empty(b, nbits))
 			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]);
-
-	/* 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);
+				  "line 0x%04x: %*pb\n", bit / 512, nbits, b);
 	}
 
 end:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index 071b4aeaddf2..134ecfca96a3 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/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