[PATCH mlx5-next 0/2] mlx5-next updates 2025-02-19

[PATCH mlx5-next 0/2] mlx5-next updates 2025-02-19

[Tariq Toukan]

Hi,

This series contains mlx5 shared updates as preparation for upcoming
features.

Regards,
Tariq

Patrisious Haddad (1):
  net/mlx5: Change POOL_NEXT_SIZE define value and make it global

Shahar Shitrit (1):
  net/mlx5: Add new health syndrome error and crr bit offset

 drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c    | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c    | 6 ++++--
 drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h    | 2 --
 drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c | 3 ++-
 include/linux/mlx5/device.h                             | 1 +
 include/linux/mlx5/fs.h                                 | 2 ++
 include/linux/mlx5/mlx5_ifc.h                           | 1 +
 7 files changed, 11 insertions(+), 6 deletions(-)


base-commit: a64dcfb451e254085a7daee5fe51bf22959d52d3
-- 
2.45.0

[PATCH mlx5-next 1/2] net/mlx5: Add new health syndrome error and crr bit offset

[Tariq Toukan]

From: Shahar Shitrit <shshitrit@nvidia.com>

Add new error value for trust lockdown in health syndrome enum.
Also, include the offset for crr bit in the health buffer layout.

These changes prepare for downstream patches that update health
event handling.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 include/linux/mlx5/device.h   | 1 +
 include/linux/mlx5/mlx5_ifc.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 0c48b20f818a..fd37f4e54d76 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -538,6 +538,7 @@ struct mlx5_cmd_layout {
 };
 
 enum mlx5_rfr_severity_bit_offsets {
+	MLX5_CRR_BIT_OFFSET = 0x6,
 	MLX5_RFR_BIT_OFFSET = 0x7,
 };
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 4f3716e124c9..cc2875e843f7 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -11119,6 +11119,7 @@ enum {
 	MLX5_INITIAL_SEG_HEALTH_SYNDROME_FFSER_ERR                    = 0xf,
 	MLX5_INITIAL_SEG_HEALTH_SYNDROME_HIGH_TEMP_ERR                = 0x10,
 	MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_PCI_POISONED_ERR         = 0x12,
+	MLX5_INITIAL_SEG_HEALTH_SYNDROME_TRUST_LOCKDOWN_ERR           = 0x13,
 };
 
 struct mlx5_ifc_initial_seg_bits {
-- 
2.45.0

[PATCH mlx5-next 2/2] net/mlx5: Change POOL_NEXT_SIZE define value and make it global

[Tariq Toukan]

From: Patrisious Haddad <phaddad@nvidia.com>

Change POOL_NEXT_SIZE define value from 0 to BIT(30), since this define
is used to request the available maximum sized flow table, and zero doesn't
make sense for it, whereas some places in the driver use zero explicitly
expecting the smallest table size possible but instead due to this
define they end up allocating the biggest table size unawarely.

In addition move the definition to "include/linux/mlx5/fs.h" to expose the
define to IB driver as well, while appropriately renaming it.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c    | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c    | 6 ++++--
 drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h    | 2 --
 drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c | 3 ++-
 include/linux/mlx5/fs.h                                 | 2 ++
 5 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
index 45183de424f3..76382626ad41 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
@@ -96,7 +96,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 	if (!flow_group_in)
 		return -ENOMEM;
 
-	ft_attr.max_fte = POOL_NEXT_SIZE;
+	ft_attr.max_fte = MLX5_FS_MAX_POOL_SIZE;
 	ft_attr.prio = LEGACY_FDB_PRIO;
 	fdb = mlx5_create_flow_table(root_ns, &ft_attr);
 	if (IS_ERR(fdb)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
index c14590acc772..f6abfd00d7e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
@@ -50,10 +50,12 @@ mlx5_ft_pool_get_avail_sz(struct mlx5_core_dev *dev, enum fs_flow_table_type tab
 	int i, found_i = -1;
 
 	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) {
-		if (dev->priv.ft_pool->ft_left[i] && FT_POOLS[i] >= desired_size &&
+		if (dev->priv.ft_pool->ft_left[i] &&
+		    (FT_POOLS[i] >= desired_size ||
+		     desired_size == MLX5_FS_MAX_POOL_SIZE) &&
 		    FT_POOLS[i] <= max_ft_size) {
 			found_i = i;
-			if (desired_size != POOL_NEXT_SIZE)
+			if (desired_size != MLX5_FS_MAX_POOL_SIZE)
 				break;
 		}
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
index 25f4274b372b..173e312db720 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
@@ -7,8 +7,6 @@
 #include <linux/mlx5/driver.h>
 #include "fs_core.h"
 
-#define POOL_NEXT_SIZE 0
-
 int mlx5_ft_pool_init(struct mlx5_core_dev *dev);
 void mlx5_ft_pool_destroy(struct mlx5_core_dev *dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index a80ecb672f33..c862dd28c466 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -161,7 +161,8 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains,
 		ft_attr.flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
 				  MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
 
-	sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ? FT_TBL_SZ : POOL_NEXT_SIZE;
+	sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ?
+		FT_TBL_SZ : MLX5_FS_MAX_POOL_SIZE;
 	ft_attr.max_fte = sz;
 
 	/* We use chains_default_ft(chains) as the table's next_ft till
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 2a69d9d71276..01cb72d68c23 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -40,6 +40,8 @@
 
 #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v)
 
+#define MLX5_FS_MAX_POOL_SIZE BIT(30)
+
 enum mlx5_flow_destination_type {
 	MLX5_FLOW_DESTINATION_TYPE_NONE,
 	MLX5_FLOW_DESTINATION_TYPE_VPORT,
-- 
2.45.0

Re: [PATCH mlx5-next 0/2] mlx5-next updates 2025-02-19

[Leon Romanovsky]

On Wed, 19 Feb 2025 10:58:06 +0200, Tariq Toukan wrote:
> This series contains mlx5 shared updates as preparation for upcoming
> features.
> 
> Regards,
> Tariq
> 
> Patrisious Haddad (1):
>   net/mlx5: Change POOL_NEXT_SIZE define value and make it global
> 
> [...]

Applied, thanks!

[1/2] net/mlx5: Add new health syndrome error and crr bit offset
      https://git.kernel.org/rdma/rdma/c/531ca2b9a215d0
[2/2] net/mlx5: Change POOL_NEXT_SIZE define value and make it global
      https://git.kernel.org/rdma/rdma/c/80df31f384b414

Best regards,
-- 
Leon Romanovsky <leon@kernel.org>