From 47402385d0b18ba46c6bfc4cff073c9359571fe4 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 9 Dec 2021 12:09:24 +0200
Subject: devlink: Add new "io_eq_size" generic device param

Add new device generic parameter to determine the size of the
I/O completion EQs.

For example, to reduce I/O EQ size to 64, execute:
$ devlink dev param set pci/0000:06:00.0 \
              name io_eq_size value 64 cmode driverinit
$ devlink dev reload pci/0000:06:00.0

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 Documentation/networking/devlink/devlink-params.rst | 3 +++
 include/net/devlink.h                               | 4 ++++
 net/core/devlink.c                                  | 5 +++++
 3 files changed, 12 insertions(+)

diff --git a/Documentation/networking/devlink/devlink-params.rst b/Documentation/networking/devlink/devlink-params.rst
index b7dfe693a332..547c0b430c9e 100644
--- a/Documentation/networking/devlink/devlink-params.rst
+++ b/Documentation/networking/devlink/devlink-params.rst
@@ -129,3 +129,6 @@ own name.
        will NACK any attempt of other host to reset the device. This parameter
        is useful for setups where a device is shared by different hosts, such
        as multi-host setup.
+   * - ``io_eq_size``
+     - u32
+     - Control the size of I/O completion EQs.
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 3276a29f2b81..b5f4acd0e0cd 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -459,6 +459,7 @@ enum devlink_param_generic_id {
 	DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA,
 	DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET,
 	DEVLINK_PARAM_GENERIC_ID_ENABLE_IWARP,
+	DEVLINK_PARAM_GENERIC_ID_IO_EQ_SIZE,
 
 	/* add new param generic ids above here*/
 	__DEVLINK_PARAM_GENERIC_ID_MAX,
@@ -511,6 +512,9 @@ enum devlink_param_generic_id {
 #define DEVLINK_PARAM_GENERIC_ENABLE_IWARP_NAME "enable_iwarp"
 #define DEVLINK_PARAM_GENERIC_ENABLE_IWARP_TYPE DEVLINK_PARAM_TYPE_BOOL
 
+#define DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_NAME "io_eq_size"
+#define DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_TYPE DEVLINK_PARAM_TYPE_U32
+
 #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate)	\
 {									\
 	.id = DEVLINK_PARAM_GENERIC_ID_##_id,				\
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 0a9349a02cad..e2e38b8872c8 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4466,6 +4466,11 @@ static const struct devlink_param devlink_param_generic[] = {
 		.name = DEVLINK_PARAM_GENERIC_ENABLE_IWARP_NAME,
 		.type = DEVLINK_PARAM_GENERIC_ENABLE_IWARP_TYPE,
 	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_IO_EQ_SIZE,
+		.name = DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_NAME,
+		.type = DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_TYPE,
+	},
 };
 
 static int devlink_param_generic_verify(const struct devlink_param *param)
-- 
cgit v1.2.3


From 0844fa5f7b8921e730d971adb5267002b6dd66a0 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 9 Dec 2021 12:09:25 +0200
Subject: net/mlx5: Let user configure io_eq_size param

Currently, each I/O EQ is taking 128KB of memory. This size
is not needed in all use cases, and is critical with large scale.
Hence, allow user to configure the size of I/O EQs.

For example, to reduce I/O EQ size to 64, execute:
$ devlink dev param set pci/0000:00:0b.0 name io_eq_size value 64 \
              cmode driverinit
$ devlink dev reload pci/0000:00:0b.0

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 Documentation/networking/devlink/mlx5.rst         |  4 ++++
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 14 ++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/eq.c      | 18 +++++++++++++++++-
 3 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst
index 4e4b97f7971a..291e7f63af73 100644
--- a/Documentation/networking/devlink/mlx5.rst
+++ b/Documentation/networking/devlink/mlx5.rst
@@ -14,8 +14,12 @@ Parameters
 
    * - Name
      - Mode
+     - Validation
    * - ``enable_roce``
      - driverinit
+   * - ``io_eq_size``
+     - driverinit
+     - The range is between 64 and 4096.
 
 The ``mlx5`` driver also implements the following driver-specific
 parameters.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 1c98652b244a..177c6e9159f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -546,6 +546,13 @@ static int mlx5_devlink_enable_remote_dev_reset_get(struct devlink *devlink, u32
 	return 0;
 }
 
+static int mlx5_devlink_eq_depth_validate(struct devlink *devlink, u32 id,
+					  union devlink_param_value val,
+					  struct netlink_ext_ack *extack)
+{
+	return (val.vu16 >= 64 && val.vu16 <= 4096) ? 0 : -EINVAL;
+}
+
 static const struct devlink_param mlx5_devlink_params[] = {
 	DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_FLOW_STEERING_MODE,
 			     "flow_steering_mode", DEVLINK_PARAM_TYPE_STRING,
@@ -570,6 +577,8 @@ static const struct devlink_param mlx5_devlink_params[] = {
 	DEVLINK_PARAM_GENERIC(ENABLE_REMOTE_DEV_RESET, BIT(DEVLINK_PARAM_CMODE_RUNTIME),
 			      mlx5_devlink_enable_remote_dev_reset_get,
 			      mlx5_devlink_enable_remote_dev_reset_set, NULL),
+	DEVLINK_PARAM_GENERIC(IO_EQ_SIZE, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, mlx5_devlink_eq_depth_validate),
 };
 
 static void mlx5_devlink_set_params_init_values(struct devlink *devlink)
@@ -608,6 +617,11 @@ static void mlx5_devlink_set_params_init_values(struct devlink *devlink)
 						   value);
 	}
 #endif
+
+	value.vu32 = MLX5_COMP_EQ_SIZE;
+	devlink_param_driverinit_value_set(devlink,
+					   DEVLINK_PARAM_GENERIC_ID_IO_EQ_SIZE,
+					   value);
 }
 
 static const struct devlink_param enable_eth_param =
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 792e0d6aa861..7686d7c9c824 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -19,6 +19,7 @@
 #include "lib/clock.h"
 #include "diag/fw_tracer.h"
 #include "mlx5_irq.h"
+#include "devlink.h"
 
 enum {
 	MLX5_EQE_OWNER_INIT_VAL	= 0x1,
@@ -796,6 +797,21 @@ static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 	}
 }
 
+static u16 comp_eq_depth_devlink_param_get(struct mlx5_core_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	union devlink_param_value val;
+	int err;
+
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_IO_EQ_SIZE,
+						 &val);
+	if (!err)
+		return val.vu32;
+	mlx5_core_dbg(dev, "Failed to get param. using default. err = %d\n", err);
+	return MLX5_COMP_EQ_SIZE;
+}
+
 static int create_comp_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
@@ -807,7 +823,7 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 
 	INIT_LIST_HEAD(&table->comp_eqs_list);
 	ncomp_eqs = table->num_comp_eqs;
-	nent = MLX5_COMP_EQ_SIZE;
+	nent = comp_eq_depth_devlink_param_get(dev);
 	for (i = 0; i < ncomp_eqs; i++) {
 		struct mlx5_eq_param param = {};
 		int vecidx = i;
-- 
cgit v1.2.3


From 0b5705ebc355e79b71bf946058acec6820e27869 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 9 Dec 2021 12:09:26 +0200
Subject: devlink: Add new "event_eq_size" generic device param

Add new device generic parameter to determine the size of the
asynchronous control events EQ.

For example, to reduce event EQ size to 64, execute:
$ devlink dev param set pci/0000:06:00.0 \
              name event_eq_size value 64 cmode driverinit
$ devlink dev reload pci/0000:06:00.0

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 Documentation/networking/devlink/devlink-params.rst | 3 +++
 include/net/devlink.h                               | 4 ++++
 net/core/devlink.c                                  | 5 +++++
 3 files changed, 12 insertions(+)

diff --git a/Documentation/networking/devlink/devlink-params.rst b/Documentation/networking/devlink/devlink-params.rst
index 547c0b430c9e..da0b5e7f8eec 100644
--- a/Documentation/networking/devlink/devlink-params.rst
+++ b/Documentation/networking/devlink/devlink-params.rst
@@ -132,3 +132,6 @@ own name.
    * - ``io_eq_size``
      - u32
      - Control the size of I/O completion EQs.
+   * - ``event_eq_size``
+     - u32
+     - Control the size of asynchronous control events EQ.
diff --git a/include/net/devlink.h b/include/net/devlink.h
index b5f4acd0e0cd..8d5349d2fb68 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -460,6 +460,7 @@ enum devlink_param_generic_id {
 	DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET,
 	DEVLINK_PARAM_GENERIC_ID_ENABLE_IWARP,
 	DEVLINK_PARAM_GENERIC_ID_IO_EQ_SIZE,
+	DEVLINK_PARAM_GENERIC_ID_EVENT_EQ_SIZE,
 
 	/* add new param generic ids above here*/
 	__DEVLINK_PARAM_GENERIC_ID_MAX,
@@ -515,6 +516,9 @@ enum devlink_param_generic_id {
 #define DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_NAME "io_eq_size"
 #define DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_TYPE DEVLINK_PARAM_TYPE_U32
 
+#define DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_NAME "event_eq_size"
+#define DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_TYPE DEVLINK_PARAM_TYPE_U32
+
 #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate)	\
 {									\
 	.id = DEVLINK_PARAM_GENERIC_ID_##_id,				\
diff --git a/net/core/devlink.c b/net/core/devlink.c
index e2e38b8872c8..6366ce324dce 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4471,6 +4471,11 @@ static const struct devlink_param devlink_param_generic[] = {
 		.name = DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_NAME,
 		.type = DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_TYPE,
 	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_EVENT_EQ_SIZE,
+		.name = DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_NAME,
+		.type = DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_TYPE,
+	},
 };
 
 static int devlink_param_generic_verify(const struct devlink_param *param)
-- 
cgit v1.2.3


From 57ca767820ade09ee3e3c53bfeb5543ba7c00ab0 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 9 Dec 2021 12:09:27 +0200
Subject: net/mlx5: Let user configure event_eq_size param

Event EQ is an EQ which received the notification of almost all the
events generated by the NIC.
Currently, each event EQ is taking 512KB of memory. This size is not
needed in most use cases, and is critical with large scale. Hence,
allow user to configure the size of the event EQ.

For example to reduce event EQ size to 64, execute::
$ devlink dev param set pci/0000:00:0b.0 name event_eq_size value 64 \
              cmode driverinit
$ devlink dev reload pci/0000:00:0b.0

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 Documentation/networking/devlink/mlx5.rst         |  3 +++
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c |  7 +++++++
 drivers/net/ethernet/mellanox/mlx5/core/eq.c      | 16 +++++++++++++++-
 3 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst
index 291e7f63af73..38089f0aefcf 100644
--- a/Documentation/networking/devlink/mlx5.rst
+++ b/Documentation/networking/devlink/mlx5.rst
@@ -20,6 +20,9 @@ Parameters
    * - ``io_eq_size``
      - driverinit
      - The range is between 64 and 4096.
+   * - ``event_eq_size``
+     - driverinit
+     - The range is between 64 and 4096.
 
 The ``mlx5`` driver also implements the following driver-specific
 parameters.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 177c6e9159f8..37b7600c5545 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -579,6 +579,8 @@ static const struct devlink_param mlx5_devlink_params[] = {
 			      mlx5_devlink_enable_remote_dev_reset_set, NULL),
 	DEVLINK_PARAM_GENERIC(IO_EQ_SIZE, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
 			      NULL, NULL, mlx5_devlink_eq_depth_validate),
+	DEVLINK_PARAM_GENERIC(EVENT_EQ_SIZE, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, mlx5_devlink_eq_depth_validate),
 };
 
 static void mlx5_devlink_set_params_init_values(struct devlink *devlink)
@@ -622,6 +624,11 @@ static void mlx5_devlink_set_params_init_values(struct devlink *devlink)
 	devlink_param_driverinit_value_set(devlink,
 					   DEVLINK_PARAM_GENERIC_ID_IO_EQ_SIZE,
 					   value);
+
+	value.vu32 = MLX5_NUM_ASYNC_EQE;
+	devlink_param_driverinit_value_set(devlink,
+					   DEVLINK_PARAM_GENERIC_ID_EVENT_EQ_SIZE,
+					   value);
 }
 
 static const struct devlink_param enable_eth_param =
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 7686d7c9c824..b695aad71ee1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -623,6 +623,20 @@ static void cleanup_async_eq(struct mlx5_core_dev *dev,
 			      name, err);
 }
 
+static u16 async_eq_depth_devlink_param_get(struct mlx5_core_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	union devlink_param_value val;
+	int err;
+
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_EVENT_EQ_SIZE,
+						 &val);
+	if (!err)
+		return val.vu32;
+	mlx5_core_dbg(dev, "Failed to get param. using default. err = %d\n", err);
+	return MLX5_NUM_ASYNC_EQE;
+}
 static int create_async_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
@@ -647,7 +661,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 
 	param = (struct mlx5_eq_param) {
 		.irq_index = MLX5_IRQ_EQ_CTRL,
-		.nent = MLX5_NUM_ASYNC_EQE,
+		.nent = async_eq_depth_devlink_param_get(dev),
 	};
 
 	gather_async_events_mask(dev, param.mask);
-- 
cgit v1.2.3


From 0ad598d0be228aca56086ead4e164f7354cd3b57 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 9 Dec 2021 12:09:28 +0200
Subject: devlink: Clarifies max_macs generic devlink param

The generic param max_macs documentation isn't clear.
Replace it with a more descriptive documentation

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 Documentation/networking/devlink/devlink-params.rst | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/Documentation/networking/devlink/devlink-params.rst b/Documentation/networking/devlink/devlink-params.rst
index da0b5e7f8eec..4e01dc32bc08 100644
--- a/Documentation/networking/devlink/devlink-params.rst
+++ b/Documentation/networking/devlink/devlink-params.rst
@@ -118,8 +118,10 @@ own name.
        errors.
    * - ``max_macs``
      - u32
-     - Specifies the maximum number of MAC addresses per ethernet port of
-       this device.
+     - Typically macvlan, vlan net devices mac are also programmed in their
+       parent netdevice's Function rx filter. This parameter limit the
+       maximum number of unicast mac address filters to receive traffic from
+       per ethernet port of this device.
    * - ``region_snapshot_enable``
      - Boolean
      - Enable capture of ``devlink-region`` snapshots.
-- 
cgit v1.2.3


From 8680a60fc1fc19b5bcf50f6cfd9b5d08fc799926 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 9 Dec 2021 12:09:29 +0200
Subject: net/mlx5: Let user configure max_macs generic param

Currently, max_macs is taking 70Kbytes of memory per function. This
size is not needed in all use cases, and is critical with large scale.
Hence, allow user to configure the number of max_macs.

For example, to reduce the number of max_macs to 1, execute::
$ devlink dev param set pci/0000:00:0b.0 name max_macs value 1 \
              cmode driverinit
$ devlink dev reload pci/0000:00:0b.0

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 Documentation/networking/devlink/mlx5.rst         |  3 +
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 67 +++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c    | 21 +++++++
 3 files changed, 91 insertions(+)

diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst
index 38089f0aefcf..38e94ed65936 100644
--- a/Documentation/networking/devlink/mlx5.rst
+++ b/Documentation/networking/devlink/mlx5.rst
@@ -23,6 +23,9 @@ Parameters
    * - ``event_eq_size``
      - driverinit
      - The range is between 64 and 4096.
+   * - ``max_macs``
+     - driverinit
+     - The range is between 1 and 2^31. Only power of 2 values are supported.
 
 The ``mlx5`` driver also implements the following driver-specific
 parameters.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 37b7600c5545..d1093bb2d436 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -773,6 +773,66 @@ static void mlx5_devlink_auxdev_params_unregister(struct devlink *devlink)
 	mlx5_devlink_eth_param_unregister(devlink);
 }
 
+static int mlx5_devlink_max_uc_list_validate(struct devlink *devlink, u32 id,
+					     union devlink_param_value val,
+					     struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	if (val.vu32 == 0) {
+		NL_SET_ERR_MSG_MOD(extack, "max_macs value must be greater than 0");
+		return -EINVAL;
+	}
+
+	if (!is_power_of_2(val.vu32)) {
+		NL_SET_ERR_MSG_MOD(extack, "Only power of 2 values are supported for max_macs");
+		return -EINVAL;
+	}
+
+	if (ilog2(val.vu32) >
+	    MLX5_CAP_GEN_MAX(dev, log_max_current_uc_list)) {
+		NL_SET_ERR_MSG_MOD(extack, "max_macs value is out of the supported range");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct devlink_param max_uc_list_param =
+	DEVLINK_PARAM_GENERIC(MAX_MACS, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, mlx5_devlink_max_uc_list_validate);
+
+static int mlx5_devlink_max_uc_list_param_register(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	union devlink_param_value value;
+	int err;
+
+	if (!MLX5_CAP_GEN_MAX(dev, log_max_current_uc_list_wr_supported))
+		return 0;
+
+	err = devlink_param_register(devlink, &max_uc_list_param);
+	if (err)
+		return err;
+
+	value.vu32 = 1 << MLX5_CAP_GEN(dev, log_max_current_uc_list);
+	devlink_param_driverinit_value_set(devlink,
+					   DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+					   value);
+	return 0;
+}
+
+static void
+mlx5_devlink_max_uc_list_param_unregister(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	if (!MLX5_CAP_GEN_MAX(dev, log_max_current_uc_list_wr_supported))
+		return;
+
+	devlink_param_unregister(devlink, &max_uc_list_param);
+}
+
 #define MLX5_TRAP_DROP(_id, _group_id)					\
 	DEVLINK_TRAP_GENERIC(DROP, DROP, _id,				\
 			     DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \
@@ -832,6 +892,10 @@ int mlx5_devlink_register(struct devlink *devlink)
 	if (err)
 		goto auxdev_reg_err;
 
+	err = mlx5_devlink_max_uc_list_param_register(devlink);
+	if (err)
+		goto max_uc_list_err;
+
 	err = mlx5_devlink_traps_register(devlink);
 	if (err)
 		goto traps_reg_err;
@@ -842,6 +906,8 @@ int mlx5_devlink_register(struct devlink *devlink)
 	return 0;
 
 traps_reg_err:
+	mlx5_devlink_max_uc_list_param_unregister(devlink);
+max_uc_list_err:
 	mlx5_devlink_auxdev_params_unregister(devlink);
 auxdev_reg_err:
 	devlink_params_unregister(devlink, mlx5_devlink_params,
@@ -852,6 +918,7 @@ auxdev_reg_err:
 void mlx5_devlink_unregister(struct devlink *devlink)
 {
 	mlx5_devlink_traps_unregister(devlink);
+	mlx5_devlink_max_uc_list_param_unregister(devlink);
 	mlx5_devlink_auxdev_params_unregister(devlink);
 	devlink_params_unregister(devlink, mlx5_devlink_params,
 				  ARRAY_SIZE(mlx5_devlink_params));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index d97c9e86d7b3..b1a82226623c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -484,10 +484,26 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP);
 }
 
+static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	union devlink_param_value val;
+	int err;
+
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+						 &val);
+	if (!err)
+		return val.vu32;
+	mlx5_core_dbg(dev, "Failed to get param. err = %d\n", err);
+	return err;
+}
+
 static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 {
 	struct mlx5_profile *prof = &dev->profile;
 	void *set_hca_cap;
+	int max_uc_list;
 	int err;
 
 	err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL);
@@ -561,6 +577,11 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 	if (MLX5_CAP_GEN(dev, roce_rw_supported))
 		MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev));
 
+	max_uc_list = max_uc_list_get_devlink_param(dev);
+	if (max_uc_list > 0)
+		MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_current_uc_list,
+			 ilog2(max_uc_list));
+
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE);
 }
 
-- 
cgit v1.2.3


From 08ab0ff47bf72aa404e35247a48a7070b07fccbf Mon Sep 17 00:00:00 2001
From: Shaokun Zhang <zhangshaokun@hisilicon.com>
Date: Tue, 7 Dec 2021 20:35:15 +0800
Subject: net/mlx5: Remove the repeated declaration

Function 'mlx5_esw_vport_match_metadata_supported' and
'mlx5_esw_offloads_vport_metadata_set' are declared twice, so remove
the repeated declaration and blank line.

Cc: Saeed Mahameed <saeedm@nvidia.com>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 513f741d16c7..ead5e8acc8be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -343,9 +343,6 @@ void mlx5_esw_match_metadata_free(struct mlx5_eswitch *esw, u32 metadata);
 
 int mlx5_esw_qos_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32 rate_mbps);
 
-bool mlx5_esw_vport_match_metadata_supported(const struct mlx5_eswitch *esw);
-int mlx5_esw_offloads_vport_metadata_set(struct mlx5_eswitch *esw, bool enable);
-
 /* E-Switch API */
 int mlx5_eswitch_init(struct mlx5_core_dev *dev);
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw);
-- 
cgit v1.2.3


From 6c72cb05d4b877300cb23df32f7451bdc55d2940 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Sun, 5 Dec 2021 12:31:47 +0200
Subject: net/mlx5e: Use bitmap field for profile features

Use a features bitmap field in mlx5e_profile to declare profile support
state of the different features.  Let it replace the existing
rx_ptp_support boolean. It will be extended to cover more features in a
downstream patch.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h               | 9 ++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c           | 6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c       | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c          | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c           | 2 --
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c      | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c | 1 -
 7 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index e77c4159713f..a8fa7f1e5ce5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -956,6 +956,10 @@ struct mlx5e_rx_handlers {
 
 extern const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic;
 
+enum mlx5e_profile_feature {
+	MLX5E_PROFILE_FEATURE_PTP_RX,
+};
+
 struct mlx5e_profile {
 	int	(*init)(struct mlx5_core_dev *mdev,
 			struct net_device *netdev);
@@ -974,9 +978,12 @@ struct mlx5e_profile {
 	const struct mlx5e_rx_handlers *rx_handlers;
 	int	max_tc;
 	u8	rq_groups;
-	bool	rx_ptp_support;
+	u32     features;
 };
 
+#define mlx5e_profile_feature_cap(profile, feature)	\
+	((profile)->features & (MLX5E_PROFILE_FEATURE_## feature))
+
 void mlx5e_build_ptys2ethtool_map(void);
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index 18d542b1c5cb..82baafd3c00c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -768,7 +768,7 @@ int mlx5e_ptp_alloc_rx_fs(struct mlx5e_priv *priv)
 {
 	struct mlx5e_ptp_fs *ptp_fs;
 
-	if (!priv->profile->rx_ptp_support)
+	if (!mlx5e_profile_feature_cap(priv->profile, PTP_RX))
 		return 0;
 
 	ptp_fs = kzalloc(sizeof(*ptp_fs), GFP_KERNEL);
@@ -783,7 +783,7 @@ void mlx5e_ptp_free_rx_fs(struct mlx5e_priv *priv)
 {
 	struct mlx5e_ptp_fs *ptp_fs = priv->fs.ptp_fs;
 
-	if (!priv->profile->rx_ptp_support)
+	if (!mlx5e_profile_feature_cap(priv->profile, PTP_RX))
 		return;
 
 	mlx5e_ptp_rx_unset_fs(priv);
@@ -794,7 +794,7 @@ int mlx5e_ptp_rx_manage_fs(struct mlx5e_priv *priv, bool set)
 {
 	struct mlx5e_ptp *c = priv->channels.ptp;
 
-	if (!priv->profile->rx_ptp_support)
+	if (!mlx5e_profile_feature_cap(priv->profile, PTP_RX))
 		return 0;
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index c8757c5a812b..536fcb2c5e90 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1934,7 +1934,7 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val
 	if (curr_val == new_val)
 		return 0;
 
-	if (new_val && !priv->profile->rx_ptp_support && rx_filter) {
+	if (new_val && !mlx5e_profile_feature_cap(priv->profile, PTP_RX) && rx_filter) {
 		netdev_err(priv->netdev,
 			   "Profile doesn't support enabling of CQE compression while hardware time-stamping is enabled.\n");
 		return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 496977e7406e..6ca2240d7dff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4038,7 +4038,7 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
 		goto err_unlock;
 	}
 
-	if (!priv->profile->rx_ptp_support)
+	if (!mlx5e_profile_feature_cap(priv->profile, PTP_RX))
 		err = mlx5e_hwstamp_config_no_ptp_rx(priv,
 						     config.rx_filter != HWTSTAMP_FILTER_NONE);
 	else
@@ -5093,7 +5093,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
 	.rq_groups	   = MLX5E_NUM_RQ_GROUPS(XSK),
 	.stats_grps	   = mlx5e_nic_stats_grps,
 	.stats_grps_num	   = mlx5e_nic_stats_grps_num,
-	.rx_ptp_support    = true,
+	.features          = BIT(MLX5E_PROFILE_FEATURE_PTP_RX),
 };
 
 static unsigned int
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 6e0f88ea3701..17d27d45a69d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1113,7 +1113,6 @@ static const struct mlx5e_profile mlx5e_rep_profile = {
 	.rq_groups		= MLX5E_NUM_RQ_GROUPS(REGULAR),
 	.stats_grps		= mlx5e_rep_stats_grps,
 	.stats_grps_num		= mlx5e_rep_stats_grps_num,
-	.rx_ptp_support		= false,
 };
 
 static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
@@ -1134,7 +1133,6 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
 	.rq_groups		= MLX5E_NUM_RQ_GROUPS(XSK),
 	.stats_grps		= mlx5e_ul_rep_stats_grps,
 	.stats_grps_num		= mlx5e_ul_rep_stats_grps_num,
-	.rx_ptp_support		= false,
 };
 
 /* e-Switch vport representors */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 051b20ec7bdb..1b082576a63a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -449,7 +449,6 @@ static const struct mlx5e_profile mlx5i_nic_profile = {
 	.rq_groups	   = MLX5E_NUM_RQ_GROUPS(REGULAR),
 	.stats_grps        = mlx5i_stats_grps,
 	.stats_grps_num    = mlx5i_stats_grps_num,
-	.rx_ptp_support    = false,
 };
 
 /* mlx5i netdev NDos */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index 5308f23702bc..0b86e78dbc0e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -350,7 +350,6 @@ static const struct mlx5e_profile mlx5i_pkey_nic_profile = {
 	.rx_handlers       = &mlx5i_rx_handlers,
 	.max_tc		   = MLX5I_MAX_NUM_TC,
 	.rq_groups	   = MLX5E_NUM_RQ_GROUPS(REGULAR),
-	.rx_ptp_support	   = false,
 };
 
 const struct mlx5e_profile *mlx5i_pkey_get_profile(void)
-- 
cgit v1.2.3


From 1958c2bddfa260f210c59f10a8ef41e08551aab1 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Tue, 7 Dec 2021 08:38:42 +0200
Subject: net/mlx5e: Add profile indications for PTP and QOS HTB features

Let the profile indicate support of the PTP and HTB (QOS) features.
This unifies the logic that calculates the number of netdev queues needed
for the features, and allows simplification of mlx5e_create_netdev(),
which no longer requires number of rx/tx queues as parameters.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Aya Levin <ayal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  5 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 53 ++++++++++++++++-------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c  |  8 +---
 3 files changed, 42 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index a8fa7f1e5ce5..ff194c76f1c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -958,6 +958,8 @@ extern const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic;
 
 enum mlx5e_profile_feature {
 	MLX5E_PROFILE_FEATURE_PTP_RX,
+	MLX5E_PROFILE_FEATURE_PTP_TX,
+	MLX5E_PROFILE_FEATURE_QOS_HTB,
 };
 
 struct mlx5e_profile {
@@ -1195,8 +1197,7 @@ int mlx5e_priv_init(struct mlx5e_priv *priv,
 		    struct mlx5_core_dev *mdev);
 void mlx5e_priv_cleanup(struct mlx5e_priv *priv);
 struct net_device *
-mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile,
-		    unsigned int txqs, unsigned int rxqs);
+mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile);
 int mlx5e_attach_netdev(struct mlx5e_priv *priv);
 void mlx5e_detach_netdev(struct mlx5e_priv *priv);
 void mlx5e_destroy_netdev(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 6ca2240d7dff..a0d9a17aa4a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5093,7 +5093,9 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
 	.rq_groups	   = MLX5E_NUM_RQ_GROUPS(XSK),
 	.stats_grps	   = mlx5e_nic_stats_grps,
 	.stats_grps_num	   = mlx5e_nic_stats_grps_num,
-	.features          = BIT(MLX5E_PROFILE_FEATURE_PTP_RX),
+	.features          = BIT(MLX5E_PROFILE_FEATURE_PTP_RX) |
+		BIT(MLX5E_PROFILE_FEATURE_PTP_TX) |
+		BIT(MLX5E_PROFILE_FEATURE_QOS_HTB),
 };
 
 static unsigned int
@@ -5181,13 +5183,44 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv)
 	memset(priv, 0, sizeof(*priv));
 }
 
+static unsigned int mlx5e_get_max_num_txqs(struct mlx5_core_dev *mdev,
+					   const struct mlx5e_profile *profile)
+{
+	unsigned int nch, ptp_txqs, qos_txqs;
+
+	nch = mlx5e_get_max_num_channels(mdev);
+
+	ptp_txqs = MLX5_CAP_GEN(mdev, ts_cqe_to_dest_cqn) &&
+		mlx5e_profile_feature_cap(profile, PTP_TX) ?
+		profile->max_tc : 0;
+
+	qos_txqs = mlx5_qos_is_supported(mdev) &&
+		mlx5e_profile_feature_cap(profile, QOS_HTB) ?
+		mlx5e_qos_max_leaf_nodes(mdev) : 0;
+
+	return nch * profile->max_tc + ptp_txqs + qos_txqs;
+}
+
+static unsigned int mlx5e_get_max_num_rxqs(struct mlx5_core_dev *mdev,
+					   const struct mlx5e_profile *profile)
+{
+	unsigned int nch;
+
+	nch = mlx5e_get_max_num_channels(mdev);
+
+	return nch * profile->rq_groups;
+}
+
 struct net_device *
-mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile,
-		    unsigned int txqs, unsigned int rxqs)
+mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile)
 {
 	struct net_device *netdev;
+	unsigned int txqs, rxqs;
 	int err;
 
+	txqs = mlx5e_get_max_num_txqs(mdev, profile);
+	rxqs = mlx5e_get_max_num_rxqs(mdev, profile);
+
 	netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv), txqs, rxqs);
 	if (!netdev) {
 		mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n");
@@ -5432,22 +5465,10 @@ static int mlx5e_probe(struct auxiliary_device *adev,
 	struct mlx5_core_dev *mdev = edev->mdev;
 	struct net_device *netdev;
 	pm_message_t state = {};
-	unsigned int txqs, rxqs, ptp_txqs = 0;
 	struct mlx5e_priv *priv;
-	int qos_sqs = 0;
 	int err;
-	int nch;
 
-	if (MLX5_CAP_GEN(mdev, ts_cqe_to_dest_cqn))
-		ptp_txqs = profile->max_tc;
-
-	if (mlx5_qos_is_supported(mdev))
-		qos_sqs = mlx5e_qos_max_leaf_nodes(mdev);
-
-	nch = mlx5e_get_max_num_channels(mdev);
-	txqs = nch * profile->max_tc + ptp_txqs + qos_sqs;
-	rxqs = nch * profile->rq_groups;
-	netdev = mlx5e_create_netdev(mdev, profile, txqs, rxqs);
+	netdev = mlx5e_create_netdev(mdev, profile);
 	if (!netdev) {
 		mlx5_core_err(mdev, "mlx5e_create_netdev failed\n");
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 17d27d45a69d..0bd3721c9110 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1183,14 +1183,10 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	struct devlink_port *dl_port;
 	struct net_device *netdev;
 	struct mlx5e_priv *priv;
-	unsigned int txqs, rxqs;
-	int nch, err;
+	int err;
 
 	profile = &mlx5e_rep_profile;
-	nch = mlx5e_get_max_num_channels(dev);
-	txqs = nch * profile->max_tc;
-	rxqs = nch * profile->rq_groups;
-	netdev = mlx5e_create_netdev(dev, profile, txqs, rxqs);
+	netdev = mlx5e_create_netdev(dev, profile);
 	if (!netdev) {
 		mlx5_core_warn(dev,
 			       "Failed to create representor netdev for vport %d\n",
-- 
cgit v1.2.3


From 0246a57ab5174ea6fe260e946900d5d3d5483dbf Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Thu, 2 Sep 2021 10:24:06 +0300
Subject: net/mlx5e: Save memory by using dynamic allocation in netdev priv

Many arrays in priv are statically allocated with a pre-defined maximum
(for num channels, num TCs, etc...), that is in some cases significantly
larger than the actual maximum. Examples:
- The more VFs are supported, the less MSIX vectors each of them could
  have. This limits the max_nch for each.
- Systems with limited number of cores or MSIX (< 64).
- Netdev profiles that do not support: QoS (DCB / HTB), PTP TX port
  timestamping.

Here we save some amount of memory by moving several structures
and arrays to follow the actual maximum instead.
This patch also prepares the code for even more savings to follow.

For example, on a system where the maximum num of channel is 8,
the channels stats structs alone go down from 3648*64 = 228 KB to
3648*8 = 28.5 KB per interface.

This is important for environments with high number of VFs/SFs or
limited memory.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      | 11 ++---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 53 +++++++++++++++++++++--
 2 files changed, 54 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index ff194c76f1c5..14497b4adc6a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -145,7 +145,6 @@ struct page_pool;
 
 #define MLX5E_MIN_NUM_CHANNELS         0x1
 #define MLX5E_MAX_NUM_CHANNELS         (MLX5E_INDIR_RQT_SIZE / 2)
-#define MLX5E_MAX_NUM_SQS              (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
 #define MLX5E_TX_CQ_POLL_BUDGET        128
 #define MLX5E_TX_XSK_POLL_BUDGET       64
 #define MLX5E_SQ_RECOVER_MIN_INTERVAL  500 /* msecs */
@@ -875,10 +874,8 @@ struct mlx5e_trap;
 
 struct mlx5e_priv {
 	/* priv data path fields - start */
-	/* +1 for port ptp ts */
-	struct mlx5e_txqsq *txq2sq[(MLX5E_MAX_NUM_CHANNELS + 1) * MLX5E_MAX_NUM_TC +
-				   MLX5E_QOS_MAX_LEAF_NODES];
-	int channel_tc2realtxq[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
+	struct mlx5e_txqsq **txq2sq;
+	int **channel_tc2realtxq;
 	int port_ptp_tc2realtxq[MLX5E_MAX_NUM_TC];
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	struct mlx5e_dcbx_dp       dcbx_dp;
@@ -893,7 +890,7 @@ struct mlx5e_priv {
 	struct mlx5e_channels      channels;
 	u32                        tisn[MLX5_MAX_PORTS][MLX5E_MAX_NUM_TC];
 	struct mlx5e_rx_res       *rx_res;
-	u32                        tx_rates[MLX5E_MAX_NUM_SQS];
+	u32                       *tx_rates;
 
 	struct mlx5e_flow_steering fs;
 
@@ -909,7 +906,7 @@ struct mlx5e_priv {
 	struct net_device         *netdev;
 	struct mlx5e_trap         *en_trap;
 	struct mlx5e_stats         stats;
-	struct mlx5e_channel_stats channel_stats[MLX5E_MAX_NUM_CHANNELS];
+	struct mlx5e_channel_stats *channel_stats;
 	struct mlx5e_channel_stats trap_stats;
 	struct mlx5e_ptp_stats     ptp_stats;
 	u16                        stats_nch;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a0d9a17aa4a9..75984ed262dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5130,12 +5130,18 @@ int mlx5e_priv_init(struct mlx5e_priv *priv,
 		    struct net_device *netdev,
 		    struct mlx5_core_dev *mdev)
 {
+	int nch, num_txqs, node, i;
+
+	num_txqs = netdev->num_tx_queues;
+	nch = mlx5e_calc_max_nch(mdev, netdev, profile);
+	node = dev_to_node(mlx5_core_dma_dev(mdev));
+
 	/* priv init */
 	priv->mdev        = mdev;
 	priv->netdev      = netdev;
 	priv->msglevel    = MLX5E_MSG_LEVEL;
-	priv->max_nch     = mlx5e_calc_max_nch(mdev, netdev, profile);
-	priv->stats_nch   = priv->max_nch;
+	priv->max_nch     = nch;
+	priv->stats_nch   = nch;
 	priv->max_opened_tc = 1;
 
 	if (!alloc_cpumask_var(&priv->scratchpad.cpumask, GFP_KERNEL))
@@ -5152,11 +5158,46 @@ int mlx5e_priv_init(struct mlx5e_priv *priv,
 	if (!priv->wq)
 		goto err_free_cpumask;
 
+	priv->txq2sq = kcalloc_node(num_txqs, sizeof(*priv->txq2sq), GFP_KERNEL, node);
+	if (!priv->txq2sq)
+		goto err_destroy_workqueue;
+
+	priv->tx_rates = kcalloc_node(num_txqs, sizeof(*priv->tx_rates), GFP_KERNEL, node);
+	if (!priv->tx_rates)
+		goto err_free_txq2sq;
+
+	priv->channel_tc2realtxq =
+		kcalloc_node(nch, sizeof(*priv->channel_tc2realtxq), GFP_KERNEL, node);
+	if (!priv->channel_tc2realtxq)
+		goto err_free_tx_rates;
+
+	for (i = 0; i < nch; i++) {
+		priv->channel_tc2realtxq[i] =
+			kcalloc_node(profile->max_tc, sizeof(**priv->channel_tc2realtxq),
+				     GFP_KERNEL, node);
+		if (!priv->channel_tc2realtxq[i])
+			goto err_free_channel_tc2realtxq;
+	}
+
+	priv->channel_stats =
+		kcalloc_node(nch, sizeof(*priv->channel_stats), GFP_KERNEL, node);
+	if (!priv->channel_stats)
+		goto err_free_channel_tc2realtxq;
+
 	return 0;
 
+err_free_channel_tc2realtxq:
+	while (--i >= 0)
+		kfree(priv->channel_tc2realtxq[i]);
+	kfree(priv->channel_tc2realtxq);
+err_free_tx_rates:
+	kfree(priv->tx_rates);
+err_free_txq2sq:
+	kfree(priv->txq2sq);
+err_destroy_workqueue:
+	destroy_workqueue(priv->wq);
 err_free_cpumask:
 	free_cpumask_var(priv->scratchpad.cpumask);
-
 	return -ENOMEM;
 }
 
@@ -5168,6 +5209,12 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv)
 	if (!priv->mdev)
 		return;
 
+	kfree(priv->channel_stats);
+	for (i = 0; i < priv->max_nch; i++)
+		kfree(priv->channel_tc2realtxq[i]);
+	kfree(priv->channel_tc2realtxq);
+	kfree(priv->tx_rates);
+	kfree(priv->txq2sq);
 	destroy_workqueue(priv->wq);
 	free_cpumask_var(priv->scratchpad.cpumask);
 
-- 
cgit v1.2.3


From 473baf2e9e8c5b3240f443658e9b59dabba9eb9e Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Wed, 29 Sep 2021 17:29:24 +0300
Subject: net/mlx5e: Allow profile-specific limitation on max num of channels

Let SF/VF representor's netdev use profile-specific limitation on
max_nch to reduce its memory and HW resources consumption.

This is particularly important for environments with limited memory
and high number of SFs.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Vu Pham <vuhuong@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 18 +++++++++++++++---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c  |  7 +++++++
 3 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 14497b4adc6a..c2812513434a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -972,6 +972,7 @@ struct mlx5e_profile {
 	int	(*update_rx)(struct mlx5e_priv *priv);
 	void	(*update_stats)(struct mlx5e_priv *priv);
 	void	(*update_carrier)(struct mlx5e_priv *priv);
+	int	(*max_nch_limit)(struct mlx5_core_dev *mdev);
 	unsigned int (*stats_grps_num)(struct mlx5e_priv *priv);
 	mlx5e_stats_grp_t *stats_grps;
 	const struct mlx5e_rx_handlers *rx_handlers;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 75984ed262dc..e4a79ba031e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5098,6 +5098,18 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
 		BIT(MLX5E_PROFILE_FEATURE_QOS_HTB),
 };
 
+static int mlx5e_profile_max_num_channels(struct mlx5_core_dev *mdev,
+					  const struct mlx5e_profile *profile)
+{
+	int nch;
+
+	nch = mlx5e_get_max_num_channels(mdev);
+
+	if (profile->max_nch_limit)
+		nch = min_t(int, nch, profile->max_nch_limit(mdev));
+	return nch;
+}
+
 static unsigned int
 mlx5e_calc_max_nch(struct mlx5_core_dev *mdev, struct net_device *netdev,
 		   const struct mlx5e_profile *profile)
@@ -5106,7 +5118,7 @@ mlx5e_calc_max_nch(struct mlx5_core_dev *mdev, struct net_device *netdev,
 	unsigned int max_nch, tmp;
 
 	/* core resources */
-	max_nch = mlx5e_get_max_num_channels(mdev);
+	max_nch = mlx5e_profile_max_num_channels(mdev, profile);
 
 	/* netdev rx queues */
 	tmp = netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1);
@@ -5235,7 +5247,7 @@ static unsigned int mlx5e_get_max_num_txqs(struct mlx5_core_dev *mdev,
 {
 	unsigned int nch, ptp_txqs, qos_txqs;
 
-	nch = mlx5e_get_max_num_channels(mdev);
+	nch = mlx5e_profile_max_num_channels(mdev, profile);
 
 	ptp_txqs = MLX5_CAP_GEN(mdev, ts_cqe_to_dest_cqn) &&
 		mlx5e_profile_feature_cap(profile, PTP_TX) ?
@@ -5253,7 +5265,7 @@ static unsigned int mlx5e_get_max_num_rxqs(struct mlx5_core_dev *mdev,
 {
 	unsigned int nch;
 
-	nch = mlx5e_get_max_num_channels(mdev);
+	nch = mlx5e_profile_max_num_channels(mdev, profile);
 
 	return nch * profile->rq_groups;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 0bd3721c9110..8c0f4cfbe471 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -591,6 +591,12 @@ bool mlx5e_eswitch_vf_rep(const struct net_device *netdev)
 	return netdev->netdev_ops == &mlx5e_netdev_ops_rep;
 }
 
+static int mlx5e_rep_max_nch_limit(struct mlx5_core_dev *mdev)
+{
+	return (1 << MLX5_CAP_GEN(mdev, log_max_tir)) /
+		mlx5_eswitch_get_total_vports(mdev);
+}
+
 static void mlx5e_build_rep_params(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -1113,6 +1119,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = {
 	.rq_groups		= MLX5E_NUM_RQ_GROUPS(REGULAR),
 	.stats_grps		= mlx5e_rep_stats_grps,
 	.stats_grps_num		= mlx5e_rep_stats_grps_num,
+	.max_nch_limit		= mlx5e_rep_max_nch_limit,
 };
 
 static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
-- 
cgit v1.2.3


From be98737a4faa3a0dc1781ced5bbf5c47865e29d7 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Sun, 5 Dec 2021 16:04:14 +0200
Subject: net/mlx5e: Use dynamic per-channel allocations in stats

Make stats array an array of pointer. This patch comes in to prepare for
the next patch where allocations of the stats are to be performed
dynamically on first usage.

Signed-off-by: Lama Kayal <lkayal@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  2 +-
 .../ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/setup.c |  2 +-
 .../ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c  |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 28 ++++++++++++++++------
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 16 ++++++-------
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c  |  2 +-
 9 files changed, 36 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index c2812513434a..33679467c63a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -906,7 +906,7 @@ struct mlx5e_priv {
 	struct net_device         *netdev;
 	struct mlx5e_trap         *en_trap;
 	struct mlx5e_stats         stats;
-	struct mlx5e_channel_stats *channel_stats;
+	struct mlx5e_channel_stats **channel_stats;
 	struct mlx5e_channel_stats trap_stats;
 	struct mlx5e_ptp_stats     ptp_stats;
 	u16                        stats_nch;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
index d290d7276b8d..074ffa4fa5af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
@@ -20,7 +20,7 @@ mlx5e_hv_vhca_fill_ring_stats(struct mlx5e_priv *priv, int ch,
 	struct mlx5e_channel_stats *stats;
 	int tc;
 
-	stats = &priv->channel_stats[ch];
+	stats = priv->channel_stats[ch];
 	data->rx_packets = stats->rq.packets;
 	data->rx_bytes   = stats->rq.bytes;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 538bc2419bd8..5f2b67b9c189 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -67,7 +67,7 @@ static int mlx5e_init_xsk_rq(struct mlx5e_channel *c,
 	rq->hw_mtu       = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->xdpsq        = &c->rq_xdpsq;
 	rq->xsk_pool     = pool;
-	rq->stats        = &c->priv->channel_stats[c->ix].xskrq;
+	rq->stats        = &c->priv->channel_stats[c->ix]->xskrq;
 	rq->ptp_cyc2time = mlx5_rq_ts_translator(mdev);
 	rq_xdp_ix        = c->ix + params->num_channels * MLX5E_RQ_GROUP_XSK;
 	err = mlx5e_rq_set_handlers(rq, params, xsk);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index 15711814d2d2..96064a2033f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -611,7 +611,7 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk,
 	priv_rx->rxq = rxq;
 	priv_rx->sk = sk;
 
-	priv_rx->rq_stats = &priv->channel_stats[rxq].rq;
+	priv_rx->rq_stats = &priv->channel_stats[rxq]->rq;
 	priv_rx->sw_stats = &priv->tls->sw_stats;
 	mlx5e_set_ktls_rx_priv_ctx(tls_ctx, priv_rx);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index fe5d82fa6e92..49cca6bd49a1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -556,7 +556,7 @@ static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv,
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
-		priv->channel_stats[arfs_rule->rxq].rq.arfs_err++;
+		priv->channel_stats[arfs_rule->rxq]->rq.arfs_err++;
 		mlx5e_dbg(HW, priv,
 			  "%s: add rule(filter id=%d, rq idx=%d, ip proto=0x%x) failed,err=%d\n",
 			  __func__, arfs_rule->filter_id, arfs_rule->rxq,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index e4a79ba031e9..504844097d20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -479,7 +479,7 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param
 	rq->mdev         = mdev;
 	rq->hw_mtu       = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->xdpsq        = &c->rq_xdpsq;
-	rq->stats        = &c->priv->channel_stats[c->ix].rq;
+	rq->stats        = &c->priv->channel_stats[c->ix]->rq;
 	rq->ptp_cyc2time = mlx5_rq_ts_translator(mdev);
 	err = mlx5e_rq_set_handlers(rq, params, NULL);
 	if (err)
@@ -1161,10 +1161,10 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->xsk_pool  = xsk_pool;
 
 	sq->stats = sq->xsk_pool ?
-		&c->priv->channel_stats[c->ix].xsksq :
+		&c->priv->channel_stats[c->ix]->xsksq :
 		is_redirect ?
-			&c->priv->channel_stats[c->ix].xdpsq :
-			&c->priv->channel_stats[c->ix].rq_xdpsq;
+			&c->priv->channel_stats[c->ix]->xdpsq :
+			&c->priv->channel_stats[c->ix]->rq_xdpsq;
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
@@ -1928,7 +1928,7 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c,
 		err = mlx5e_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix,
 				       params, &cparam->txq_sq, &c->sq[tc], tc,
 				       qos_queue_group_id,
-				       &c->priv->channel_stats[c->ix].sq[tc]);
+				       &c->priv->channel_stats[c->ix]->sq[tc]);
 		if (err)
 			goto err_close_sqs;
 	}
@@ -2207,7 +2207,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey);
 	c->num_tc   = mlx5e_get_dcb_num_tc(params);
 	c->xdp      = !!params->xdp_prog;
-	c->stats    = &priv->channel_stats[ix].ch;
+	c->stats    = &priv->channel_stats[ix]->ch;
 	c->aff_mask = irq_get_effective_affinity_mask(irq);
 	c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix);
 
@@ -3371,7 +3371,7 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s)
 	int i;
 
 	for (i = 0; i < priv->stats_nch; i++) {
-		struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i];
+		struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i];
 		struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq;
 		struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
 		int j;
@@ -5196,8 +5196,20 @@ int mlx5e_priv_init(struct mlx5e_priv *priv,
 	if (!priv->channel_stats)
 		goto err_free_channel_tc2realtxq;
 
+	for (i = 0; i < priv->stats_nch; i++) {
+		priv->channel_stats[i] = kvzalloc_node(sizeof(**priv->channel_stats),
+						       GFP_KERNEL, node);
+		if (!priv->channel_stats[i])
+			goto err_free_channel_stats;
+	}
+
 	return 0;
 
+err_free_channel_stats:
+	while (--i >= 0)
+		kvfree(priv->channel_stats[i]);
+	kfree(priv->channel_stats);
+	i = nch;
 err_free_channel_tc2realtxq:
 	while (--i >= 0)
 		kfree(priv->channel_tc2realtxq[i]);
@@ -5221,6 +5233,8 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv)
 	if (!priv->mdev)
 		return;
 
+	for (i = 0; i < priv->stats_nch; i++)
+		kvfree(priv->channel_stats[i]);
 	kfree(priv->channel_stats);
 	for (i = 0; i < priv->max_nch; i++)
 		kfree(priv->channel_tc2realtxq[i]);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 7e05d7592bce..f09b57c31ed7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2189,7 +2189,7 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 
 	priv = mlx5i_epriv(netdev);
 	tstamp = &priv->tstamp;
-	stats = &priv->channel_stats[rq->ix].rq;
+	stats = rq->stats;
 
 	flags_rqpn = be32_to_cpu(cqe->flags_rqpn);
 	g = (flags_rqpn >> 28) & 3;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 3c91a11e27ad..73fcd9fb17dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -463,7 +463,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw)
 
 	for (i = 0; i < priv->stats_nch; i++) {
 		struct mlx5e_channel_stats *channel_stats =
-			&priv->channel_stats[i];
+			priv->channel_stats[i];
 		int j;
 
 		mlx5e_stats_grp_sw_update_stats_rq_stats(s, &channel_stats->rq);
@@ -2197,21 +2197,21 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(channels)
 	for (i = 0; i < max_nch; i++)
 		for (j = 0; j < NUM_CH_STATS; j++)
 			data[idx++] =
-				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].ch,
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->ch,
 						     ch_stats_desc, j);
 
 	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_RQ_STATS; j++)
 			data[idx++] =
-				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq,
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->rq,
 						     rq_stats_desc, j);
 		for (j = 0; j < NUM_XSKRQ_STATS * is_xsk; j++)
 			data[idx++] =
-				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xskrq,
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->xskrq,
 						     xskrq_stats_desc, j);
 		for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++)
 			data[idx++] =
-				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq_xdpsq,
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->rq_xdpsq,
 						     rq_xdpsq_stats_desc, j);
 	}
 
@@ -2219,17 +2219,17 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(channels)
 		for (i = 0; i < max_nch; i++)
 			for (j = 0; j < NUM_SQ_STATS; j++)
 				data[idx++] =
-					MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].sq[tc],
+					MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->sq[tc],
 							     sq_stats_desc, j);
 
 	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_XSKSQ_STATS * is_xsk; j++)
 			data[idx++] =
-				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xsksq,
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->xsksq,
 						     xsksq_stats_desc, j);
 		for (j = 0; j < NUM_XDPSQ_STATS; j++)
 			data[idx++] =
-				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xdpsq,
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i]->xdpsq,
 						     xdpsq_stats_desc, j);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 1b082576a63a..0a99a020a3b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -117,7 +117,7 @@ static void mlx5i_grp_sw_update_stats(struct mlx5e_priv *priv)
 		struct mlx5e_channel_stats *channel_stats;
 		struct mlx5e_rq_stats *rq_stats;
 
-		channel_stats = &priv->channel_stats[i];
+		channel_stats = priv->channel_stats[i];
 		rq_stats = &channel_stats->rq;
 
 		s.rx_packets += rq_stats->packets;
-- 
cgit v1.2.3


From fa691d0c9c0812b9045f3a9420862e47b3b92518 Mon Sep 17 00:00:00 2001
From: Lama Kayal <lkayal@nvidia.com>
Date: Wed, 22 Sep 2021 09:32:33 +0300
Subject: net/mlx5e: Allocate per-channel stats dynamically at first usage

Make stats allocation per-channel dynamic on demand, at channel open
operation.

Previously the stats array was pre-allocated for the maximum possible
number of channels. Here we defer the per-channel stats instance allocation
upon its first usage, so that it's allocated only if really needed.

Allocating stats on demand helps maintain a more memory-efficient code,
as we're saving memory when the used number of channels is smaller than
the maximum.

The stats memory instances are still freed in mlx5e_priv_arrays_free(),
so that they are persistent to channels' closure.

Memory size allocated for struct mlx5e_channel_stats is 3648 bytes.
If maximum number of channel stands for 64, the total memory space
allocated for stats is 3648x64 = 228K bytes. In scenarios where the
number of channels in use is significantly smaller than maximum number,
the memory saved can be remarkable.

Signed-off-by: Lama Kayal <lkayal@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 41 ++++++++++++++++-------
 1 file changed, 28 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 504844097d20..1a47108805fd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2176,6 +2176,30 @@ static u8 mlx5e_enumerate_lag_port(struct mlx5_core_dev *mdev, int ix)
 	return (ix + port_aff_bias) % mlx5e_get_num_lag_ports(mdev);
 }
 
+static int mlx5e_channel_stats_alloc(struct mlx5e_priv *priv, int ix, int cpu)
+{
+	if (ix > priv->stats_nch)  {
+		netdev_warn(priv->netdev, "Unexpected channel stats index %d > %d\n", ix,
+			    priv->stats_nch);
+		return -EINVAL;
+	}
+
+	if (priv->channel_stats[ix])
+		return 0;
+
+	/* Asymmetric dynamic memory allocation.
+	 * Freed in mlx5e_priv_arrays_free, not on channel closure.
+	 */
+	mlx5e_dbg(DRV, priv, "Creating channel stats %d\n", ix);
+	priv->channel_stats[ix] = kvzalloc_node(sizeof(**priv->channel_stats),
+						GFP_KERNEL, cpu_to_node(cpu));
+	if (!priv->channel_stats[ix])
+		return -ENOMEM;
+	priv->stats_nch++;
+
+	return 0;
+}
+
 static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 			      struct mlx5e_params *params,
 			      struct mlx5e_channel_param *cparam,
@@ -2193,6 +2217,10 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	if (err)
 		return err;
 
+	err = mlx5e_channel_stats_alloc(priv, ix, cpu);
+	if (err)
+		return err;
+
 	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
 		return -ENOMEM;
@@ -5153,7 +5181,6 @@ int mlx5e_priv_init(struct mlx5e_priv *priv,
 	priv->netdev      = netdev;
 	priv->msglevel    = MLX5E_MSG_LEVEL;
 	priv->max_nch     = nch;
-	priv->stats_nch   = nch;
 	priv->max_opened_tc = 1;
 
 	if (!alloc_cpumask_var(&priv->scratchpad.cpumask, GFP_KERNEL))
@@ -5196,20 +5223,8 @@ int mlx5e_priv_init(struct mlx5e_priv *priv,
 	if (!priv->channel_stats)
 		goto err_free_channel_tc2realtxq;
 
-	for (i = 0; i < priv->stats_nch; i++) {
-		priv->channel_stats[i] = kvzalloc_node(sizeof(**priv->channel_stats),
-						       GFP_KERNEL, node);
-		if (!priv->channel_stats[i])
-			goto err_free_channel_stats;
-	}
-
 	return 0;
 
-err_free_channel_stats:
-	while (--i >= 0)
-		kvfree(priv->channel_stats[i]);
-	kfree(priv->channel_stats);
-	i = nch;
 err_free_channel_tc2realtxq:
 	while (--i >= 0)
 		kfree(priv->channel_tc2realtxq[i]);
-- 
cgit v1.2.3


From 1f08917ab929a6939cb0c95d47f928db43f6d3c9 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Tue, 14 Sep 2021 14:46:05 +0300
Subject: net/mlx5e: Take packet_merge params directly from the RX res struct

As packet_merge params structure is saved on the RX resources structure, there
is no need to pass it separately.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
index 0015a81eb9a1..24c32f73040a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
@@ -37,7 +37,6 @@ struct mlx5e_rx_res {
 /* API for rx_res_rss_* */
 
 static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res,
-				     const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 				     unsigned int init_nch)
 {
 	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
@@ -52,7 +51,7 @@ static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res,
 		return -ENOMEM;
 
 	err = mlx5e_rss_init(rss, res->mdev, inner_ft_support, res->drop_rqn,
-			     init_pkt_merge_param);
+			     &res->pkt_merge_param);
 	if (err)
 		goto err_rss_free;
 
@@ -277,8 +276,7 @@ struct mlx5e_rx_res *mlx5e_rx_res_alloc(void)
 	return kvzalloc(sizeof(struct mlx5e_rx_res), GFP_KERNEL);
 }
 
-static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res,
-				      const struct mlx5e_packet_merge_param *init_pkt_merge_param)
+static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res)
 {
 	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
 	struct mlx5e_tir_builder *builder;
@@ -309,7 +307,7 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res,
 		mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn,
 					    mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt),
 					    inner_ft_support);
-		mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param);
+		mlx5e_tir_builder_build_packet_merge(builder, &res->pkt_merge_param);
 		mlx5e_tir_builder_build_direct(builder);
 
 		err = mlx5e_tir_init(&res->channels[ix].direct_tir, builder, res->mdev, true);
@@ -339,7 +337,7 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res,
 		mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn,
 					    mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
 					    inner_ft_support);
-		mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param);
+		mlx5e_tir_builder_build_packet_merge(builder, &res->pkt_merge_param);
 		mlx5e_tir_builder_build_direct(builder);
 
 		err = mlx5e_tir_init(&res->channels[ix].xsk_tir, builder, res->mdev, true);
@@ -454,11 +452,11 @@ int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev,
 	res->pkt_merge_param = *init_pkt_merge_param;
 	init_rwsem(&res->pkt_merge_param_sem);
 
-	err = mlx5e_rx_res_rss_init_def(res, init_pkt_merge_param, init_nch);
+	err = mlx5e_rx_res_rss_init_def(res, init_nch);
 	if (err)
 		goto err_out;
 
-	err = mlx5e_rx_res_channels_init(res, init_pkt_merge_param);
+	err = mlx5e_rx_res_channels_init(res);
 	if (err)
 		goto err_rss_destroy;
 
-- 
cgit v1.2.3