Linux RDMA and InfiniBand development
 help / color / mirror / Atom feed
From: Tariq Toukan <tariqt@nvidia.com>
To: Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Andrew Lunn <andrew+netdev@lunn.ch>,
	"David S. Miller" <davem@davemloft.net>
Cc: Saeed Mahameed <saeedm@nvidia.com>,
	Leon Romanovsky <leon@kernel.org>,
	Tariq Toukan <tariqt@nvidia.com>, Mark Bloch <mbloch@nvidia.com>,
	"Moshe Shemesh" <moshe@nvidia.com>,
	Akiva Goldberger <agoldberger@nvidia.com>,
	<netdev@vger.kernel.org>, <linux-rdma@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>, Gal Pressman <gal@nvidia.com>,
	Dragos Tatulea <dtatulea@nvidia.com>
Subject: [PATCH net-next 2/8] net/mlx5: Use v1 response layout for query_esw_functions
Date: Sun, 10 May 2026 08:34:42 +0300	[thread overview]
Message-ID: <20260510053448.326823-3-tariqt@nvidia.com> (raw)
In-Reply-To: <20260510053448.326823-1-tariqt@nvidia.com>

From: Moshe Shemesh <moshe@nvidia.com>

Use the v1 response layout for the query_esw_functions command when
supported by the device. When query_host_net_function_v1 capability is
set, use MLX5_QUERY_ESW_FUNC_OP_MOD_LAYOUT_V1 to retrieve parameters
for multiple network functions, allocating the output buffer according
to query_host_net_function_num_max. Validate that firmware does not
return more entries than the allocated buffer.

This change does not introduce new functionality, but enables the
existing mlx5_esw_query_functions() callers to retrieve host PF
information with the new layout as well. The mlx5_esw_get_host_pf_info()
helper abstracts parsing the command output in both legacy and new
formats, so callers do not need to handle the different layouts.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/eswitch.c | 88 +++++++++++++++++--
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |  5 +-
 .../mellanox/mlx5/core/eswitch_offloads.c     |  6 +-
 .../net/ethernet/mellanox/mlx5/core/sriov.c   |  2 +-
 4 files changed, 89 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 861e79ddb489..8b62dde7eb70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1063,11 +1063,28 @@ static int eswitch_vport_event(struct notifier_block *nb,
  */
 const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
 {
-	int outlen = MLX5_ST_SZ_BYTES(query_esw_functions_out);
+	bool net_func_v1 = MLX5_CAP_GEN(dev, query_host_net_function_v1);
 	u32 in[MLX5_ST_SZ_DW(query_esw_functions_in)] = {};
+	int alloc_entries;
+	int outlen;
 	u32 *out;
 	int err;
 
+	if (net_func_v1) {
+		alloc_entries = MLX5_CAP_GEN(dev,
+					     query_host_net_function_num_max);
+		alloc_entries = max(alloc_entries, 1);
+		MLX5_SET(query_esw_functions_in, in, op_mod,
+			 MLX5_QUERY_ESW_FUNC_OP_MOD_LAYOUT_V1);
+		outlen = MLX5_BYTE_OFF(query_esw_functions_out,
+				       net_function_params) +
+			 alloc_entries * MLX5_UN_SZ_BYTES(net_function_params);
+		outlen = max_t(int, outlen,
+			       MLX5_ST_SZ_BYTES(query_esw_functions_out));
+	} else {
+		outlen = MLX5_ST_SZ_BYTES(query_esw_functions_out);
+	}
+
 	out = kvzalloc(outlen, GFP_KERNEL);
 	if (!out)
 		return ERR_PTR(-ENOMEM);
@@ -1076,9 +1093,25 @@ const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
 		 MLX5_CMD_OP_QUERY_ESW_FUNCTIONS);
 
 	err = mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
-	if (!err)
-		return out;
+	if (err)
+		goto free;
+
+	if (net_func_v1) {
+		int num_entries;
+
+		num_entries = MLX5_GET(query_esw_functions_out, out,
+				       net_function_num);
+		if (num_entries > alloc_entries) {
+			mlx5_core_warn(dev, "Got %d entries, max expected %d\n",
+				       num_entries, alloc_entries);
+			err = -EINVAL;
+			goto free;
+		}
+	}
+
+	return out;
 
+free:
 	kvfree(out);
 	return ERR_PTR(err);
 }
@@ -1100,12 +1133,55 @@ mlx5_esw_host_pf_from_host_params(const void *entry)
 	};
 }
 
-struct mlx5_esw_pf_info mlx5_esw_get_host_pf_info(const u32 *out)
+static struct mlx5_esw_pf_info
+mlx5_esw_host_pf_from_net_func_params(const u8 *entry, int num_entries)
+{
+	int i;
+
+	for (i = 0; i < num_entries; i++) {
+		int pf_type, state;
+
+		pf_type = MLX5_GET(network_function_params, entry, pci_pf_type);
+		if (pf_type != MLX5_PCI_PF_TYPE_EXTERNAL_HOST_PF) {
+			entry += MLX5_UN_SZ_BYTES(net_function_params);
+			continue;
+		}
+
+		state = MLX5_GET(network_function_params, entry, vhca_state);
+
+		return (struct mlx5_esw_pf_info) {
+			.pf_disabled = state != MLX5_VHCA_STATE_IN_USE,
+			.num_of_vfs = MLX5_GET(network_function_params,
+					       entry, pci_num_vfs),
+			.total_vfs = MLX5_GET(network_function_params,
+					      entry, pci_total_vfs),
+			.host_number = MLX5_GET(network_function_params,
+						entry, host_number),
+		};
+	}
+
+	/* No external host PF entry found */
+	return (struct mlx5_esw_pf_info) {
+		.pf_not_exist = true,
+		.pf_disabled = true,
+	};
+}
+
+struct mlx5_esw_pf_info
+mlx5_esw_get_host_pf_info(struct mlx5_core_dev *dev, const u32 *out)
 {
 	const void *entry;
 
 	entry = MLX5_ADDR_OF(query_esw_functions_out, out, net_function_params);
 
+	if (MLX5_CAP_GEN(dev, query_host_net_function_v1)) {
+		int num_entries = MLX5_GET(query_esw_functions_out, out,
+					   net_function_num);
+
+		return mlx5_esw_host_pf_from_net_func_params(entry,
+							     num_entries);
+	}
+
 	return mlx5_esw_host_pf_from_host_params(entry);
 }
 
@@ -1121,7 +1197,7 @@ static int mlx5_esw_host_functions_enabled_query(struct mlx5_eswitch *esw)
 	if (IS_ERR(query_host_out))
 		return PTR_ERR(query_host_out);
 
-	host_pf_info = mlx5_esw_get_host_pf_info(query_host_out);
+	host_pf_info = mlx5_esw_get_host_pf_info(esw->dev, query_host_out);
 	esw->esw_funcs.host_funcs_disabled = host_pf_info.pf_not_exist;
 
 	kvfree(query_host_out);
@@ -1561,7 +1637,7 @@ mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, int num_vfs)
 	if (IS_ERR(out))
 		return;
 
-	host_pf_info = mlx5_esw_get_host_pf_info(out);
+	host_pf_info = mlx5_esw_get_host_pf_info(esw->dev, out);
 	esw->esw_funcs.num_vfs = host_pf_info.num_of_vfs;
 	if (mlx5_core_ec_sriov_enabled(esw->dev))
 		esw->esw_funcs.num_ec_vfs = num_vfs;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index cfaae59a6e7c..a5f832ed2251 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -657,7 +657,8 @@ bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
 			       struct mlx5_core_dev *dev1);
 
 const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev);
-struct mlx5_esw_pf_info mlx5_esw_get_host_pf_info(const u32 *out);
+struct mlx5_esw_pf_info mlx5_esw_get_host_pf_info(struct mlx5_core_dev *dev,
+						  const u32 *out);
 int mlx5_esw_host_pf_enable_hca(struct mlx5_core_dev *dev);
 int mlx5_esw_host_pf_disable_hca(struct mlx5_core_dev *dev);
 
@@ -986,7 +987,7 @@ static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
 }
 
 static inline struct mlx5_esw_pf_info
-mlx5_esw_get_host_pf_info(const u32 *out)
+mlx5_esw_get_host_pf_info(struct mlx5_core_dev *dev, const u32 *out)
 {
 	return (struct mlx5_esw_pf_info) {};
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 217c2fe6b690..acbc37b05308 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3716,7 +3716,7 @@ static void esw_vfs_changed_event_handler(struct mlx5_eswitch *esw)
 	if (IS_ERR(out))
 		return;
 
-	host_pf_info = mlx5_esw_get_host_pf_info(out);
+	host_pf_info = mlx5_esw_get_host_pf_info(esw->dev, out);
 	new_num_vfs = host_pf_info.num_of_vfs;
 
 	if (new_num_vfs == esw->esw_funcs.num_vfs || host_pf_info.pf_disabled)
@@ -3832,7 +3832,7 @@ static int mlx5_esw_host_number_init(struct mlx5_eswitch *esw)
 		return PTR_ERR(query_host_out);
 
 	/* Mark non local controller with non zero controller number. */
-	host_pf_info = mlx5_esw_get_host_pf_info(query_host_out);
+	host_pf_info = mlx5_esw_get_host_pf_info(esw->dev, query_host_out);
 	esw->offloads.host_number = host_pf_info.host_number;
 	kvfree(query_host_out);
 	return 0;
@@ -4988,7 +4988,7 @@ int mlx5_devlink_pf_port_fn_state_get(struct devlink_port *port,
 	if (IS_ERR(query_out))
 		return PTR_ERR(query_out);
 
-	host_pf_info = mlx5_esw_get_host_pf_info(query_out);
+	host_pf_info = mlx5_esw_get_host_pf_info(vport->dev, query_out);
 
 	*opstate = host_pf_info.pf_disabled ?
 			DEVLINK_PORT_FN_OPSTATE_DETACHED :
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 79f76c456d72..0770b5d99c5d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -285,7 +285,7 @@ static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev)
 		 */
 		if (IS_ERR(out))
 			goto done;
-		host_pf_info = mlx5_esw_get_host_pf_info(out);
+		host_pf_info = mlx5_esw_get_host_pf_info(dev, out);
 		host_total_vfs = host_pf_info.total_vfs;
 		kvfree(out);
 		return host_total_vfs;
-- 
2.44.0


  parent reply	other threads:[~2026-05-10  5:35 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-10  5:34 [PATCH net-next 0/8] net/mlx5: Prepare eswitch infrastructure for satellite PF support Tariq Toukan
2026-05-10  5:34 ` [PATCH net-next 1/8] net/mlx5: Use helper to parse host PF info Tariq Toukan
2026-05-10  5:34 ` Tariq Toukan [this message]
2026-05-10  5:34 ` [PATCH net-next 3/8] net/mlx5: Use mlx5_eswitch_is_vf_vport() for IPsec VF checks Tariq Toukan
2026-05-10  5:34 ` [PATCH net-next 4/8] net/mlx5: Switch vport HCA cap helpers to kvzalloc Tariq Toukan
2026-05-10  5:34 ` [PATCH net-next 5/8] net/mlx5: Add mlx5_vport_set_other_func_general_cap macro Tariq Toukan
2026-05-10  5:34 ` [PATCH net-next 6/8] net/mlx5: Refactor mlx5_set_msix_vec_count() SET_HCA_CAP Tariq Toukan
2026-05-10  5:34 ` [PATCH net-next 7/8] net/mlx5: Use vport helper for IPsec eswitch set caps Tariq Toukan
2026-05-10  5:34 ` [PATCH net-next 8/8] net/mlx5: Generalize enable/disable HCA for any PF vport Tariq Toukan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260510053448.326823-3-tariqt@nvidia.com \
    --to=tariqt@nvidia.com \
    --cc=agoldberger@nvidia.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=davem@davemloft.net \
    --cc=dtatulea@nvidia.com \
    --cc=edumazet@google.com \
    --cc=gal@nvidia.com \
    --cc=kuba@kernel.org \
    --cc=leon@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=mbloch@nvidia.com \
    --cc=moshe@nvidia.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=saeedm@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox