netfilter flowtable hardware offload support
Subsystems (6)
Pablo Neira Ayuso
maintainercover netfilter flowtable hardware offload support
Hi Saeed,
This patchset updates the mlx5 driver to support for the netfilter flowtable hardware offload from Paul Blakey.
Please review and apply if you're fine with this.
Thank you.
Paul Blakey (7):
net/mlx5: Simplify fdb chain and prio eswitch defines net/mlx5: Rename FDB_* tc related defines to FDB_TC_* defines net/mlx5: Define fdb tc levels per prio
net/mlx5: Accumulate levels for chains prio namespaces net/mlx5: Refactor creating fast path prio chains net/mlx5: Add new chain for netfilter flow table offload net/mlx5: TC: Offload flow table rules
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 45 ++++++- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 32 ++++- drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 3 +- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 21 ++-- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 10 +- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 129 +++++++++++++++------ include/linux/mlx5/fs.h | 3 +- 7 files changed, 185 insertions(+), 58 deletions(-)
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 1/7 net/mlx5: Simplify fdb chain and prio eswitch defines
From: Paul Blakey <[email protected]>
FDB_MAX_CHAIN and FDB_MAX_PRIO were defined differently depending on if CONFIG_MLX5_ESWITCH is enabled to save space on allocations.
This is a minor space saving, and there is no real need for it. Simplify things instead, and define them the same in both cases.
Issue: 1929510
--- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +4 -8
@@ -43,6 +43,10 @@#include <linux/mlx5/fs.h> #include "lib/mpfs.h" +#define FDB_MAX_CHAIN 3 +#define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1) +#define FDB_MAX_PRIO 16 +#ifdef CONFIG_MLX5_ESWITCH #define MLX5_MAX_UC_PER_VPORT (dev) \
@@ -59,10 +63,6 @@#define mlx5_esw_has_fwd_fdb (dev) \ MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_to_table) -#define FDB_MAX_CHAIN 3 -#define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1) -#define FDB_MAX_PRIO 16 -struct vport_ingress {struct mlx5_flow_table *acl;struct mlx5_flow_group *allow_untagged_spoofchk_grp;
@@ -613,10 +613,6 @@ static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)static inline void mlx5_eswitch_update_num_of_vfs (struct mlx5_eswitch *esw,const int num_vfs) {} -#define FDB_MAX_CHAIN 1 -#define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1) -#define FDB_MAX_PRIO 1 -#endif /* CONFIG_MLX5_ESWITCH */ #endif /* __MLX5_ESWITCH_H__ */
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 2/7 net/mlx5: Rename FDB_* tc related defines to FDB_TC_* defines
In reply to Pablo Neira AyusoFrom: Paul Blakey <[email protected]>
Rename it to prepare for next patch that will add a different type of offload to the FDB.
Issue: 1929510
--- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 8 ++++---- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 10 +++++----- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 8 ++++---- 4 files changed, 15 insertions(+), 15 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +2 -2
@@ -1074,7 +1074,7 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw,memcpy (slow_attr, flow->esw_attr,sizeof (*slow_attr)); slow_attr->action =MLX5_FLOW_CONTEXT_ACTION_FWD_DEST ; slow_attr->split_count =0 ; - slow_attr->dest_chain =FDB_SLOW_PATH_CHAIN ; + slow_attr->dest_chain =FDB_TC_SLOW_PATH_CHAIN ; rule =mlx5e_tc_offload_fdb_rules (esw, flow, spec, slow_attr);if (!IS_ERR (rule))
@@ -1091,7 +1091,7 @@ mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw,memcpy (slow_attr, flow->esw_attr,sizeof (*slow_attr)); slow_attr->action =MLX5_FLOW_CONTEXT_ACTION_FWD_DEST ; slow_attr->split_count =0 ; - slow_attr->dest_chain =FDB_SLOW_PATH_CHAIN ; + slow_attr->dest_chain =FDB_TC_SLOW_PATH_CHAIN ;mlx5e_tc_unoffload_fdb_rules (esw, flow, slow_attr);flow_flag_clear (flow,SLOW ); }
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +4 -4
@@ -43,9 +43,9 @@#include <linux/mlx5/fs.h> #include "lib/mpfs.h" -#define FDB_MAX_CHAIN 3 -#define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1) -#define FDB_MAX_PRIO 16 +#define FDB_TC_MAX_CHAIN 3 +#define FDB_TC_SLOW_PATH_CHAIN (FDB_TC_MAX_CHAIN + 1) +#define FDB_TC_MAX_PRIO 16#ifdef CONFIG_MLX5_ESWITCH
@@ -166,7 +166,7 @@ struct mlx5_eswitch_fdb {struct {struct mlx5_flow_table *fdb;u32 num_rules; - } fdb_prio[FDB_MAX_CHAIN +1 ][FDB_MAX_PRIO +1 ][PRIO_LEVELS ]; + } fdb_prio[FDB_TC_MAX_CHAIN +1 ][FDB_TC_MAX_PRIO +1 ][PRIO_LEVELS ];/* Protects fdb_prio table */ struct mutex fdb_prio_lock;
drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +5 -5
@@ -75,7 +75,7 @@ bool mlx5_eswitch_prios_supported(struct mlx5_eswitch *esw)u32 mlx5_eswitch_get_chain_range (struct mlx5_eswitch *esw) {if (esw->fdb_table.flags &ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED ) -return FDB_MAX_CHAIN ; +return FDB_TC_MAX_CHAIN ;return 0 ; }
@@ -83,7 +83,7 @@ u32 mlx5_eswitch_get_chain_range(struct mlx5_eswitch *esw)u16 mlx5_eswitch_get_prio_range (struct mlx5_eswitch *esw) {if (esw->fdb_table.flags &ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED ) -return FDB_MAX_PRIO ; +return FDB_TC_MAX_PRIO ;return 1 ; }
@@ -927,7 +927,7 @@ esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level)int table_prio, l =0 ;u32 flags =0 ; -if (chain ==FDB_SLOW_PATH_CHAIN ) +if (chain ==FDB_TC_SLOW_PATH_CHAIN )return esw->fdb_table.offloads.slow_fdb;mutex_lock (&esw->fdb_table.offloads.fdb_prio_lock);
@@ -952,7 +952,7 @@ esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level) flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |MLX5_FLOW_TABLE_TUNNEL_EN_DECAP ); - table_prio = (chain *FDB_MAX_PRIO ) + prio -1 ; + table_prio = (chain *FDB_TC_MAX_PRIO ) + prio -1 ;/* create earlier levels for correct fs_core lookup when * connecting tables
@@ -989,7 +989,7 @@ esw_put_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level) {int l; -if (chain ==FDB_SLOW_PATH_CHAIN ) +if (chain ==FDB_TC_SLOW_PATH_CHAIN )return ;mutex_lock (&esw->fdb_table.offloads.fdb_prio_lock);
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +4 -4
@@ -2606,7 +2606,7 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)return -ENOMEM ; steering->fdb_sub_ns =kzalloc (sizeof (steering->fdb_sub_ns) * - (FDB_MAX_CHAIN +1 ),GFP_KERNEL ); + (FDB_TC_MAX_CHAIN +1 ),GFP_KERNEL );if (!steering->fdb_sub_ns)return -ENOMEM ;
@@ -2617,7 +2617,7 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) goto out_err; } - levels =2 *FDB_MAX_PRIO * (FDB_MAX_CHAIN +1 ); + levels =2 *FDB_TC_MAX_PRIO * (FDB_TC_MAX_CHAIN +1 ); maj_prio =fs_create_prio_chained (&steering->fdb_root_ns->ns,FDB_FAST_PATH , levels);
@@ -2626,14 +2626,14 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) goto out_err; } -for (chain =0 ; chain <=FDB_MAX_CHAIN ; chain++) { +for (chain =0 ; chain <=FDB_TC_MAX_CHAIN ; chain++) { ns =fs_create_namespace (maj_prio,MLX5_FLOW_TABLE_MISS_ACTION_DEF );if (IS_ERR (ns)) { err =PTR_ERR (ns); goto out_err; } -for (prio =0 ; prio <FDB_MAX_PRIO * (chain +1 ); prio++) { +for (prio =0 ; prio <FDB_TC_MAX_PRIO * (chain +1 ); prio++) { min_prio =fs_create_prio (ns, prio,2 );if (IS_ERR (min_prio)) { err =PTR_ERR (min_prio);
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 3/7 net/mlx5: Define fdb tc levels per prio
In reply to Pablo Neira AyusoFrom: Paul Blakey <[email protected]>
Define FDB_TC_LEVELS_PER_PRIO instead of magic number 2. This is the number of levels used by each tc prio table in the fdb.
Issue: 1929510
--- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 6 ++++-- 2 files changed, 6 insertions(+), 4 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +2 -2
@@ -46,6 +46,7 @@#define FDB_TC_MAX_CHAIN 3#define FDB_TC_SLOW_PATH_CHAIN (FDB_TC_MAX_CHAIN + 1)#define FDB_TC_MAX_PRIO 16 +#define FDB_TC_LEVELS_PER_PRIO 2#ifdef CONFIG_MLX5_ESWITCH
@@ -139,7 +140,6 @@ enum offloads_fdb_flags {extern const unsigned int ESW_POOLS [4 ]; -#define PRIO_LEVELS 2 struct mlx5_eswitch_fdb { union { struct legacy_fdb {
@@ -166,7 +166,7 @@ struct mlx5_eswitch_fdb {struct {struct mlx5_flow_table *fdb;u32 num_rules; - } fdb_prio[FDB_TC_MAX_CHAIN +1 ][FDB_TC_MAX_PRIO +1 ][PRIO_LEVELS ]; + } fdb_prio[FDB_TC_MAX_CHAIN +1 ][FDB_TC_MAX_PRIO +1 ][FDB_TC_LEVELS_PER_PRIO ];/* Protects fdb_prio table */ struct mutex fdb_prio_lock;
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +4 -2
@@ -2617,7 +2617,8 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) goto out_err; } - levels =2 *FDB_TC_MAX_PRIO * (FDB_TC_MAX_CHAIN +1 ); + levels =FDB_TC_LEVELS_PER_PRIO * +FDB_TC_MAX_PRIO * (FDB_TC_MAX_CHAIN +1 ); maj_prio =fs_create_prio_chained (&steering->fdb_root_ns->ns,FDB_FAST_PATH , levels);
@@ -2634,7 +2635,8 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) }for (prio =0 ; prio <FDB_TC_MAX_PRIO * (chain +1 ); prio++) { - min_prio =fs_create_prio (ns, prio,2 ); + min_prio =fs_create_prio (ns, prio, +FDB_TC_LEVELS_PER_PRIO );if (IS_ERR (min_prio)) { err =PTR_ERR (min_prio); goto out_err;
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 4/7 net/mlx5: Accumulate levels for chains prio namespaces
In reply to Pablo Neira AyusoFrom: Paul Blakey <[email protected]>
Tc chains are implemented by creating a chained prio steering type, and inside it there is a namespace for each chain (FDB_TC_MAX_CHAINS). Each of those has a list of priorities.
Currently, all namespaces in a prio start at the parent prio level. But since we can jump from chain (namespace) to another chain in the same prio, we need the levels for higher chains to be higher as well. So we created unused prios to account for levels in previous namespaces.
Fix that by accumulating the namespaces levels if we are inside a chained type prio, and removing the unused prios.
Issue: 1929510
--- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 10 +++++++++- 2 files changed, 10 insertions(+), 2 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +1 -1
@@ -952,7 +952,7 @@ esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level) flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |MLX5_FLOW_TABLE_TUNNEL_EN_DECAP ); - table_prio = (chain *FDB_TC_MAX_PRIO ) + prio -1 ; + table_prio = prio -1 ;/* create earlier levels for correct fs_core lookup when * connecting tables
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +9 -1
@@ -2400,9 +2400,17 @@ static void set_prio_attrs_in_prio(struct fs_prio *prio, int acc_level)int acc_level_ns = acc_level; prio->start_level = acc_level; -fs_for_each_ns (ns, prio) +fs_for_each_ns (ns, prio) {/* This updates start_level and num_levels of ns's priority descendants */ acc_level_ns =set_prio_attrs_in_ns (ns, acc_level); + +/* If this a prio with chains, and we can jump from one chain +* (namepsace) to another, so we accumulate the levels +*/ +if (prio->node.type ==FS_TYPE_PRIO_CHAINS ) + acc_level = acc_level_ns; + } +if (!prio->num_levels) prio->num_levels = acc_level_ns - prio->start_level;WARN_ON (prio->num_levels < acc_level_ns - prio->start_level);
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 5/7 net/mlx5: Refactor creating fast path prio chains
In reply to Pablo Neira AyusoFrom: Paul Blakey <[email protected]>
Next patch will re-use this to add a new chain but in a different prio.
Issue: 1929510
--- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 118 +++++++++++++++------- 1 file changed, 82 insertions(+), 36 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +82 -36
@@ -2599,60 +2599,106 @@ static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering) steering->rdma_rx_root_ns =NULL ;return err; } -static int init_fdb_root_ns (struct mlx5_flow_steering *steering) + +/* FT and tc chains are stored in the same array so we can re-use the +* mlx5_get_fdb_sub_ns() and tc api for FT chains. +* When creating a new ns for each chain store it in the first available slot. +* Assume tc chains are created and stored first and only then the FT chain. +*/ +static void store_fdb_sub_ns_prio_chain (struct mlx5_flow_steering *steering, +struct mlx5_flow_namespace *ns) +{ +int chain =0 ; + +while (steering->fdb_sub_ns[chain]) + ++chain; + + steering->fdb_sub_ns[chain] = ns; +} + +static int create_fdb_sub_ns_prio_chain (struct mlx5_flow_steering *steering, +struct fs_prio *maj_prio) {struct mlx5_flow_namespace *ns; -struct fs_prio *maj_prio;struct fs_prio *min_prio; +int prio; + + ns =fs_create_namespace (maj_prio,MLX5_FLOW_TABLE_MISS_ACTION_DEF ); +if (IS_ERR (ns)) +return PTR_ERR (ns); + +for (prio =0 ; prio <FDB_TC_MAX_PRIO ; prio++) { + min_prio =fs_create_prio (ns, prio,FDB_TC_LEVELS_PER_PRIO ); +if (IS_ERR (min_prio)) +return PTR_ERR (min_prio); + } + +store_fdb_sub_ns_prio_chain (steering, ns); + +return 0 ; +} + +static int create_fdb_chains (struct mlx5_flow_steering *steering, +int fs_prio, +int chains) +{ +struct fs_prio *maj_prio;int levels;int chain; -int prio;int err; - steering->fdb_root_ns =create_root_ns (steering,FS_FT_FDB ); -if (!steering->fdb_root_ns) -return -ENOMEM ; + levels =FDB_TC_LEVELS_PER_PRIO *FDB_TC_MAX_PRIO * chains; + maj_prio =fs_create_prio_chained (&steering->fdb_root_ns->ns, + fs_prio, + levels); +if (IS_ERR (maj_prio)) +return PTR_ERR (maj_prio); + +for (chain =0 ; chain < chains; chain++) { + err =create_fdb_sub_ns_prio_chain (steering, maj_prio); +if (err) +return err; + } + +return 0 ; +} - steering->fdb_sub_ns =kzalloc (sizeof (steering->fdb_sub_ns) * - (FDB_TC_MAX_CHAIN +1 ),GFP_KERNEL ); +static int create_fdb_fast_path (struct mlx5_flow_steering *steering) +{ +const int total_chains =FDB_TC_MAX_CHAIN +1 ; +int err; + + steering->fdb_sub_ns =kcalloc (total_chains, +sizeof (*steering->fdb_sub_ns), +GFP_KERNEL );if (!steering->fdb_sub_ns)return -ENOMEM ; + err =create_fdb_chains (steering,FDB_FAST_PATH ,FDB_TC_MAX_CHAIN +1 ); +if (err) +return err; + +return 0 ; +} + +static int init_fdb_root_ns (struct mlx5_flow_steering *steering) +{ +struct fs_prio *maj_prio; +int err; + + steering->fdb_root_ns =create_root_ns (steering,FS_FT_FDB ); +if (!steering->fdb_root_ns) +return -ENOMEM ; + maj_prio =fs_create_prio (&steering->fdb_root_ns->ns,FDB_BYPASS_PATH ,1 );if (IS_ERR (maj_prio)) { err =PTR_ERR (maj_prio); goto out_err; } - - levels =FDB_TC_LEVELS_PER_PRIO * -FDB_TC_MAX_PRIO * (FDB_TC_MAX_CHAIN +1 ); - maj_prio =fs_create_prio_chained (&steering->fdb_root_ns->ns, -FDB_FAST_PATH , - levels); -if (IS_ERR (maj_prio)) { - err =PTR_ERR (maj_prio); + err =create_fdb_fast_path (steering); +if (err) goto out_err; - } - -for (chain =0 ; chain <=FDB_TC_MAX_CHAIN ; chain++) { - ns =fs_create_namespace (maj_prio,MLX5_FLOW_TABLE_MISS_ACTION_DEF ); -if (IS_ERR (ns)) { - err =PTR_ERR (ns); - goto out_err; - } - -for (prio =0 ; prio <FDB_TC_MAX_PRIO * (chain +1 ); prio++) { - min_prio =fs_create_prio (ns, prio, -FDB_TC_LEVELS_PER_PRIO ); -if (IS_ERR (min_prio)) { - err =PTR_ERR (min_prio); - goto out_err; - } - } - - steering->fdb_sub_ns[chain] = ns; - } maj_prio =fs_create_prio (&steering->fdb_root_ns->ns,FDB_SLOW_PATH ,1 );if (IS_ERR (maj_prio)) {
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 6/7 net/mlx5: Add new chain for netfilter flow table offload
In reply to Pablo Neira AyusoFrom: Paul Blakey <[email protected]>
Netfilter tables (nftables) implements a software datapath that comes after tc ingress datapath. The datapath supports offloading such rules via the flow table offload API.
This API is currently only used by NFT and it doesn't provide the global priority in regards to tc offload, so we assume offloading such rules must come after tc. It does provide a flow table priority parameter, so we need to provide some supported priority range.
For that, split fastpath prio to two, flow table offload and tc offload, with one dedicated priority chain for flow table offload.
Next patch will re-use the multi chain API to access this chain by allowing access to this chain by the fdb_sub_namespace.
Issue: 1929510
--- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 9 +++++++-- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 9 ++++++--- include/linux/mlx5/fs.h | 3 ++- 3 files changed, 15 insertions(+), 6 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +7 -2
@@ -44,7 +44,12 @@#include "lib/mpfs.h" #define FDB_TC_MAX_CHAIN 3 -#define FDB_TC_SLOW_PATH_CHAIN (FDB_TC_MAX_CHAIN + 1) +#define FDB_FT_CHAIN (FDB_TC_MAX_CHAIN + 1) +#define FDB_TC_SLOW_PATH_CHAIN (FDB_FT_CHAIN + 1) + +/* The index of the last real chain (FT) + 1 as chain zero is valid as well */ +#define FDB_NUM_CHAINS (FDB_FT_CHAIN + 1) +#define FDB_TC_MAX_PRIO 16#define FDB_TC_LEVELS_PER_PRIO 2
@@ -166,7 +171,7 @@ struct mlx5_eswitch_fdb {struct {struct mlx5_flow_table *fdb;u32 num_rules; - } fdb_prio[FDB_TC_MAX_CHAIN +1 ][FDB_TC_MAX_PRIO +1 ][FDB_TC_LEVELS_PER_PRIO ]; + } fdb_prio[FDB_NUM_CHAINS ][FDB_TC_MAX_PRIO +1 ][FDB_TC_LEVELS_PER_PRIO ];/* Protects fdb_prio table */ struct mutex fdb_prio_lock;
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +6 -3
@@ -2665,16 +2665,19 @@ static int create_fdb_chains(struct mlx5_flow_steering *steering,static int create_fdb_fast_path (struct mlx5_flow_steering *steering) { -const int total_chains =FDB_TC_MAX_CHAIN +1 ;int err; - steering->fdb_sub_ns =kcalloc (total_chains, + steering->fdb_sub_ns =kcalloc (FDB_NUM_CHAINS ,sizeof (*steering->fdb_sub_ns),GFP_KERNEL );if (!steering->fdb_sub_ns)return -ENOMEM ; - err =create_fdb_chains (steering,FDB_FAST_PATH ,FDB_TC_MAX_CHAIN +1 ); + err =create_fdb_chains (steering,FDB_TC_OFFLOAD ,FDB_TC_MAX_CHAIN +1 ); +if (err) +return err; + + err =create_fdb_chains (steering,FDB_FT_OFFLOAD ,1 );if (err)return err;
include/linux/mlx5/fs.h +2 -1
@@ -80,7 +80,8 @@ enum mlx5_flow_namespace_type {enum {FDB_BYPASS_PATH , -FDB_FAST_PATH , +FDB_TC_OFFLOAD , +FDB_FT_OFFLOAD ,FDB_SLOW_PATH , };
Signature · 1 line
2.11.0
Pablo Neira Ayuso
maintainerPATCH 7/7 net/mlx5: TC: Offload flow table rules
In reply to Pablo Neira AyusoFrom: Paul Blakey <[email protected]>
Since both tc rules and flow table rules are of the same format, we can re-use tc parsing for that, and move the flow table rules to their steering domain - In this case, the next chain after max tc chain.
Issue: 1929510
--- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 45 ++++++++++++++++++++++-- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 28 ++++++++++++++- drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 3 +- 3 files changed, 71 insertions(+), 5 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +42 -3
@@ -1243,21 +1243,60 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data, } } -static LIST_HEAD (mlx5e_rep_block_cb_list); +static int mlx5e_rep_setup_ft_cb (enum tc_setup_type type,void *type_data, +void *cb_priv) +{ +struct flow_cls_offload *f = type_data; +struct flow_cls_offload cls_flower; +struct mlx5e_priv *priv = cb_priv; +struct mlx5_eswitch *esw; +unsigned long flags; +int err; + + flags =MLX5_TC_FLAG (INGRESS ) | +MLX5_TC_FLAG (ESW_OFFLOAD ) | +MLX5_TC_FLAG (FT_OFFLOAD ); + esw = priv->mdev->priv.eswitch; +switch (type) { +case TC_SETUP_CLSFLOWER : +if (!mlx5_eswitch_prios_supported (esw) || f->common.chain_index) +return -EOPNOTSUPP ; + +/* Re-use tc offload path by moving the ft flow to the +* reserved ft chain. +*/ +memcpy (&cls_flower, f,sizeof (*f)); + cls_flower.common.chain_index =FDB_FT_CHAIN ; + err =mlx5e_rep_setup_tc_cls_flower (priv, &cls_flower, flags); +memcpy (&f->stats, &cls_flower.stats,sizeof (f->stats)); +return err; +default : +return -EOPNOTSUPP ; + } +} + +static LIST_HEAD (mlx5e_rep_block_tc_cb_list); +static LIST_HEAD (mlx5e_rep_block_ft_cb_list);static int mlx5e_rep_setup_tc (struct net_device *dev,enum tc_setup_type type,void *type_data) {struct mlx5e_priv *priv =netdev_priv (dev);struct flow_block_offload *f = type_data; + f->unlocked_driver_cb = true; +switch (type) {case TC_SETUP_BLOCK : - f->unlocked_driver_cb = true;return flow_block_cb_setup_simple (type_data, - &mlx5e_rep_block_cb_list, + &mlx5e_rep_block_tc_cb_list, mlx5e_rep_setup_tc_cb, priv, priv, true); +case TC_SETUP_FT : +return flow_block_cb_setup_simple (type_data, + &mlx5e_rep_block_ft_cb_list, + mlx5e_rep_setup_ft_cb, + priv, priv, true);default :return -EOPNOTSUPP ; }
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +27 -1
@@ -74,6 +74,7 @@ enum {MLX5E_TC_FLOW_FLAG_INGRESS =MLX5E_TC_FLAG_INGRESS_BIT ,MLX5E_TC_FLOW_FLAG_EGRESS =MLX5E_TC_FLAG_EGRESS_BIT ,MLX5E_TC_FLOW_FLAG_ESWITCH =MLX5E_TC_FLAG_ESW_OFFLOAD_BIT , +MLX5E_TC_FLOW_FLAG_FT =MLX5E_TC_FLAG_FT_OFFLOAD_BIT ,MLX5E_TC_FLOW_FLAG_NIC =MLX5E_TC_FLAG_NIC_OFFLOAD_BIT ,MLX5E_TC_FLOW_FLAG_OFFLOADED =MLX5E_TC_FLOW_BASE , MLX5E_TC_FLOW_FLAG_HAIRPIN = MLX5E_TC_FLOW_BASE + 1,
@@ -276,6 +277,11 @@ static bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow)return flow_flag_test (flow,ESWITCH ); } +static bool mlx5e_is_ft_flow (struct mlx5e_tc_flow *flow) +{ +return flow_flag_test (flow,FT ); +} +static bool mlx5e_is_offloaded_flow (struct mlx5e_tc_flow *flow) {return flow_flag_test (flow,OFFLOADED );
@@ -1168,7 +1174,12 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,return -EOPNOTSUPP ; } -if (attr->chain > max_chain) { +/* We check chain range only for tc flows. +* For ft flows, we checked attr->chain was originally 0 and set it to +* FDB_FT_CHAIN which is outside tc range. +* See mlx5e_rep_setup_ft_cb(). +*/ +if (!mlx5e_is_ft_flow (flow) && attr->chain > max_chain) {NL_SET_ERR_MSG (extack,"Requested chain is out of supported range" );return -EOPNOTSUPP ; }
@@ -3217,6 +3228,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;struct mlx5e_rep_priv *rpriv = priv->ppriv;const struct ip_tunnel_info *info =NULL ; +bool ft_flow =mlx5e_is_ft_flow (flow);const struct flow_action_entry *act;bool encap = false;u32 action =0 ;
@@ -3261,6 +3273,14 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,return -EINVAL ; } +if (ft_flow && out_dev == priv->netdev) { +/* Ignore forward to self rules generated +* by adding both mlx5 devs to the flow table +* block on a normal nft offload setup. +*/ +return -EOPNOTSUPP ; + } +if (attr->out_count >=MLX5_MAX_FLOW_FWD_VPORTS ) {NL_SET_ERR_MSG_MOD (extack,"can't support more output ports, can't offload forwarding" );
@@ -3385,6 +3405,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,u32 dest_chain = act->chain_index;u32 max_chain =mlx5_eswitch_get_chain_range (esw); +if (ft_flow) { +NL_SET_ERR_MSG_MOD (extack,"Goto action is not supported" ); +return -EOPNOTSUPP ; + }if (dest_chain <= attr->chain) {NL_SET_ERR_MSG (extack,"Goto earlier chain isn't supported" );return -EOPNOTSUPP ;
@@ -3475,6 +3499,8 @@ static void get_flags(int flags, unsigned long *flow_flags) __flow_flags |=BIT (MLX5E_TC_FLOW_FLAG_ESWITCH );if (flags &MLX5_TC_FLAG (NIC_OFFLOAD )) __flow_flags |=BIT (MLX5E_TC_FLOW_FLAG_NIC ); +if (flags &MLX5_TC_FLAG (FT_OFFLOAD )) + __flow_flags |=BIT (MLX5E_TC_FLOW_FLAG_FT ); *flow_flags = __flow_flags; }
drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +2 -1
@@ -44,7 +44,8 @@ enum {MLX5E_TC_FLAG_EGRESS_BIT ,MLX5E_TC_FLAG_NIC_OFFLOAD_BIT ,MLX5E_TC_FLAG_ESW_OFFLOAD_BIT , - MLX5E_TC_FLAG_LAST_EXPORTED_BIT = MLX5E_TC_FLAG_ESW_OFFLOAD_BIT, +MLX5E_TC_FLAG_FT_OFFLOAD_BIT , + MLX5E_TC_FLAG_LAST_EXPORTED_BIT = MLX5E_TC_FLAG_FT_OFFLOAD_BIT, };#define MLX5_TC_FLAG (flag) BIT(MLX5E_TC_FLAG_##flag##_BIT)
Signature · 1 line
2.11.0
Re: [PATCH mlx5-next 7/7] net/mlx5: TC: Offload flow table rules
Quoted 7 lines · Pablo Neira Ayuso
From: Paul Blakey <[email protected]>
Since both tc rules and flow table rules are of the same format, we can re-use tc parsing for that, and move the flow table rules to their steering domain - In this case, the next chain after max tc chain.
Quoted 5 lines
Issue: 1929510
Change-Id I68bf14d5398b91cf26cc7c7f19dab64ba8757c01Signed-off-by Paul Blakey <[email protected]>Reviewed-by Mark Bloch <[email protected]>
Series LGTM,
couple of things:
1) Paul should have removed Issue and change-Id tags I can do this myself when i apply those to my trees.
2) patches #1..#6 can perfectly go mlx5-next,
already tried and i had to resolve some trivial conflicts, but all good.
3) this patch needs to be on top of net-next, due to dependency with TC_SETUP_FT, I will resubmit it through my normal pull request procedure after applying all other patches in this series to mlx5-next shared branch.
All patches will land in net-next in couple of days, i guess there is no rush to have them there immediately ?
Thanks,
saeed.
Pablo Neira Ayuso
maintainerRe: [PATCH mlx5-next 7/7] net/mlx5: TC: Offload flow table rules
Hi Saeed,
Quoted 16 lines · Saeed Mahameed
Quoted 7 lines · Pablo Neira Ayuso
From: Paul Blakey <[email protected]>
Since both tc rules and flow table rules are of the same format, we can re-use tc parsing for that, and move the flow table rules to their steering domain - In this case, the next chain after max tc chain.
Quoted 5 lines
Issue: 1929510
Change-Id I68bf14d5398b91cf26cc7c7f19dab64ba8757c01Signed-off-by Paul Blakey <[email protected]>Reviewed-by Mark Bloch <[email protected]>Series LGTM,
Quoted 8 lines
couple of things:
1) Paul should have removed Issue and change-Id tags I can do this myself when i apply those to my trees.
2) patches #1..#6 can perfectly go mlx5-next,
already tried and i had to resolve some trivial conflicts, but all good.
Thanks.
Quoted 7 lines
3) this patch needs to be on top of net-next, due to dependency with
TC_SETUP_FT, I will resubmit it through my normal pull request procedure after applying all other patches in this series to mlx5-next shared branch.All patches will land in net-next in couple of days, i guess there is no rush to have them there immediately ?
No rush on my side.
We have to wait for David to tell us if he is fine to apply this patchset into net-next, then pull from your tree the first client for this code in a couple of days as you suggest.
Quoted 9 lines · Pablo Neira Ayuso
Hi Saeed,
This patchset updates the mlx5 driver to support for the netfilter flowtable hardware offload from Paul Blakey.
Please review and apply if you're fine with this.
Thank you.
Quoted 9 lines
Paul Blakey (7):
net/mlx5: Simplify fdb chain and prio eswitch defines net/mlx5: Rename FDB_* tc related defines to FDB_TC_* defines net/mlx5: Define fdb tc levels per prio
net/mlx5: Accumulate levels for chains prio namespaces net/mlx5: Refactor creating fast path prio chains net/mlx5: Add new chain for netfilter flow table offload net/mlx5: TC: Offload flow table rules
patches #1..#6 applied to mlx5-next.
patch #7 will be re-submitted on top of net-next when mlx5-next gets merged on my next pull request.
Thanks,
Saeed.