[PATCH 04/54] net: mellanox: fix open-coded for_each_set_bit()

[PATCH 04/54] net: mellanox: fix open-coded for_each_set_bit()

[Yury Norov]

Mellanox driver has an open-coded for_each_set_bit(). Fix it.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c | 23 ++++++-----------------
 1 file changed, 6 insertions(+), 17 deletions(-)

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];
-- 
2.30.2

[PATCH 18/54] drivers/infiniband: replace cpumask_weight with cpumask_empty where appropriate

[Yury Norov]

drivers/infiniband/hw/hfi1/affinity.c code calls cpumask_weight() to check
if any bit of a given cpumask is set. We can do it more efficiently with
cpumask_empty() because cpumask_empty() stops traversing the cpumask as
soon as it finds first set bit, while cpumask_weight() counts all bits
unconditionally.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 drivers/infiniband/hw/hfi1/affinity.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index 98c813ba4304..38eee675369a 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -667,7 +667,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
 			 * engines, use the same CPU cores as general/control
 			 * context.
 			 */
-			if (cpumask_weight(&entry->def_intr.mask) == 0)
+			if (cpumask_empty(&entry->def_intr.mask))
 				cpumask_copy(&entry->def_intr.mask,
 					     &entry->general_intr_mask);
 		}
@@ -687,7 +687,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
 		 * vectors, use the same CPU core as the general/control
 		 * context.
 		 */
-		if (cpumask_weight(&entry->comp_vect_mask) == 0)
+		if (cpumask_empty(&entry->comp_vect_mask))
 			cpumask_copy(&entry->comp_vect_mask,
 				     &entry->general_intr_mask);
 	}
-- 
2.30.2

[PATCH 44/54] infiniband: replace cpumask_weight with cpumask_weight_{eq, ...} where appropriate

[Yury Norov]

Infiniband code uses cpumask_weight() to compare the weight of
cpumask with a given number. We can do it more efficiently with
cpumask_weight_{eq, ...} because conditional cpumask_weight may stop
traversing the cpumask earlier, as soon as condition is met.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 drivers/infiniband/hw/hfi1/affinity.c    | 9 ++++-----
 drivers/infiniband/hw/qib/qib_file_ops.c | 2 +-
 drivers/infiniband/hw/qib/qib_iba7322.c  | 2 +-
 3 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index 38eee675369a..7c5ca5c5306a 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -507,7 +507,7 @@ static int _dev_comp_vect_cpu_mask_init(struct hfi1_devdata *dd,
 	 * available CPUs divide it by the number of devices in the
 	 * local NUMA node.
 	 */
-	if (cpumask_weight(&entry->comp_vect_mask) == 1) {
+	if (cpumask_weight_eq(&entry->comp_vect_mask, 1)) {
 		possible_cpus_comp_vect = 1;
 		dd_dev_warn(dd,
 			    "Number of kernel receive queues is too large for completion vector affinity to be effective\n");
@@ -593,7 +593,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
 {
 	struct hfi1_affinity_node *entry;
 	const struct cpumask *local_mask;
-	int curr_cpu, possible, i, ret;
+	int curr_cpu, i, ret;
 	bool new_entry = false;
 
 	local_mask = cpumask_of_node(dd->node);
@@ -626,10 +626,9 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
 			    local_mask);
 
 		/* fill in the receive list */
-		possible = cpumask_weight(&entry->def_intr.mask);
 		curr_cpu = cpumask_first(&entry->def_intr.mask);
 
-		if (possible == 1) {
+		if (cpumask_weight_eq(&entry->def_intr.mask, 1)) {
 			/* only one CPU, everyone will use it */
 			cpumask_set_cpu(curr_cpu, &entry->rcv_intr.mask);
 			cpumask_set_cpu(curr_cpu, &entry->general_intr_mask);
@@ -1017,7 +1016,7 @@ int hfi1_get_proc_affinity(int node)
 		cpu = cpumask_first(proc_mask);
 		cpumask_set_cpu(cpu, &set->used);
 		goto done;
-	} else if (current->nr_cpus_allowed < cpumask_weight(&set->mask)) {
+	} else if (cpumask_weight_gt(&set->mask, current->nr_cpus_allowed)) {
 		hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %*pbl",
 			  current->pid, current->comm,
 			  cpumask_pr_args(proc_mask));
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index aa290928cf96..add89bc21b0a 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -1151,7 +1151,7 @@ static void assign_ctxt_affinity(struct file *fp, struct qib_devdata *dd)
 	 * reserve a processor for it on the local NUMA node.
 	 */
 	if ((weight >= qib_cpulist_count) &&
-		(cpumask_weight(local_mask) <= qib_cpulist_count)) {
+		(cpumask_weight_le(local_mask, qib_cpulist_count))) {
 		for_each_cpu(local_cpu, local_mask)
 			if (!test_and_set_bit(local_cpu, qib_cpulist)) {
 				fd->rec_cpu_num = local_cpu;
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index ceed302cf6a0..b17f96509d2c 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -3405,7 +3405,7 @@ static void qib_setup_7322_interrupt(struct qib_devdata *dd, int clearpend)
 	local_mask = cpumask_of_pcibus(dd->pcidev->bus);
 	firstcpu = cpumask_first(local_mask);
 	if (firstcpu >= nr_cpu_ids ||
-			cpumask_weight(local_mask) == num_online_cpus()) {
+			cpumask_weight_eq(local_mask, num_online_cpus())) {
 		local_mask = topology_core_cpumask(0);
 		firstcpu = cpumask_first(local_mask);
 	}
-- 
2.30.2

Re: [PATCH 18/54] drivers/infiniband: replace cpumask_weight with cpumask_empty where appropriate

[Leon Romanovsky]

On Sun, Jan 23, 2022 at 10:38:49AM -0800, Yury Norov wrote:
> drivers/infiniband/hw/hfi1/affinity.c code calls cpumask_weight() to check
> if any bit of a given cpumask is set. We can do it more efficiently with
> cpumask_empty() because cpumask_empty() stops traversing the cpumask as
> soon as it finds first set bit, while cpumask_weight() counts all bits
> unconditionally.
> 
> Signed-off-by: Yury Norov <yury.norov@gmail.com>
> ---
>  drivers/infiniband/hw/hfi1/affinity.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)

Except that title needs to be: "RDMA/hfi: ....", the change looks ok.

Thanks,
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>

Re: [PATCH 04/54] net: mellanox: fix open-coded for_each_set_bit()

[Tariq Toukan]

On 1/23/2022 8:38 PM, Yury Norov wrote:
> Mellanox driver has an open-coded for_each_set_bit(). Fix it.
> 
> Signed-off-by: Yury Norov <yury.norov@gmail.com>
> ---
>   drivers/net/ethernet/mellanox/mlx4/cmd.c | 23 ++++++-----------------
>   1 file changed, 6 insertions(+), 17 deletions(-)
> 

Reviewed-by: Tariq Toukan <tariqt@nvidia.com>

Thanks,
Tariq