diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c')
-rw-r--r-- | drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 1517 |
1 files changed, 1230 insertions, 287 deletions
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index bd8de6b9be71..33cec1cc1642 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -41,14 +41,184 @@ #include <linux/in6.h> #include <linux/notifier.h> #include <linux/inetdevice.h> +#include <linux/netdevice.h> #include <net/netevent.h> #include <net/neighbour.h> #include <net/arp.h> #include <net/ip_fib.h> +#include <net/fib_rules.h> +#include <net/l3mdev.h> #include "spectrum.h" #include "core.h" #include "reg.h" +#include "spectrum_cnt.h" +#include "spectrum_dpipe.h" +#include "spectrum_router.h" + +struct mlxsw_sp_rif { + struct list_head nexthop_list; + struct list_head neigh_list; + struct net_device *dev; + struct mlxsw_sp_fid *f; + unsigned char addr[ETH_ALEN]; + int mtu; + u16 rif_index; + u16 vr_id; + unsigned int counter_ingress; + bool counter_ingress_valid; + unsigned int counter_egress; + bool counter_egress_valid; +}; + +static unsigned int * +mlxsw_sp_rif_p_counter_get(struct mlxsw_sp_rif *rif, + enum mlxsw_sp_rif_counter_dir dir) +{ + switch (dir) { + case MLXSW_SP_RIF_COUNTER_EGRESS: + return &rif->counter_egress; + case MLXSW_SP_RIF_COUNTER_INGRESS: + return &rif->counter_ingress; + } + return NULL; +} + +static bool +mlxsw_sp_rif_counter_valid_get(struct mlxsw_sp_rif *rif, + enum mlxsw_sp_rif_counter_dir dir) +{ + switch (dir) { + case MLXSW_SP_RIF_COUNTER_EGRESS: + return rif->counter_egress_valid; + case MLXSW_SP_RIF_COUNTER_INGRESS: + return rif->counter_ingress_valid; + } + return false; +} + +static void +mlxsw_sp_rif_counter_valid_set(struct mlxsw_sp_rif *rif, + enum mlxsw_sp_rif_counter_dir dir, + bool valid) +{ + switch (dir) { + case MLXSW_SP_RIF_COUNTER_EGRESS: + rif->counter_egress_valid = valid; + break; + case MLXSW_SP_RIF_COUNTER_INGRESS: + rif->counter_ingress_valid = valid; + break; + } +} + +static int mlxsw_sp_rif_counter_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index, + unsigned int counter_index, bool enable, + enum mlxsw_sp_rif_counter_dir dir) +{ + char ritr_pl[MLXSW_REG_RITR_LEN]; + bool is_egress = false; + int err; + + if (dir == MLXSW_SP_RIF_COUNTER_EGRESS) + is_egress = true; + mlxsw_reg_ritr_rif_pack(ritr_pl, rif_index); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); + if (err) + return err; + + mlxsw_reg_ritr_counter_pack(ritr_pl, counter_index, enable, + is_egress); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *rif, + enum mlxsw_sp_rif_counter_dir dir, u64 *cnt) +{ + char ricnt_pl[MLXSW_REG_RICNT_LEN]; + unsigned int *p_counter_index; + bool valid; + int err; + + valid = mlxsw_sp_rif_counter_valid_get(rif, dir); + if (!valid) + return -EINVAL; + + p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir); + if (!p_counter_index) + return -EINVAL; + mlxsw_reg_ricnt_pack(ricnt_pl, *p_counter_index, + MLXSW_REG_RICNT_OPCODE_NOP); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ricnt), ricnt_pl); + if (err) + return err; + *cnt = mlxsw_reg_ricnt_good_unicast_packets_get(ricnt_pl); + return 0; +} + +static int mlxsw_sp_rif_counter_clear(struct mlxsw_sp *mlxsw_sp, + unsigned int counter_index) +{ + char ricnt_pl[MLXSW_REG_RICNT_LEN]; + + mlxsw_reg_ricnt_pack(ricnt_pl, counter_index, + MLXSW_REG_RICNT_OPCODE_CLEAR); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ricnt), ricnt_pl); +} + +int mlxsw_sp_rif_counter_alloc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *rif, + enum mlxsw_sp_rif_counter_dir dir) +{ + unsigned int *p_counter_index; + int err; + + p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir); + if (!p_counter_index) + return -EINVAL; + err = mlxsw_sp_counter_alloc(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_RIF, + p_counter_index); + if (err) + return err; + + err = mlxsw_sp_rif_counter_clear(mlxsw_sp, *p_counter_index); + if (err) + goto err_counter_clear; + + err = mlxsw_sp_rif_counter_edit(mlxsw_sp, rif->rif_index, + *p_counter_index, true, dir); + if (err) + goto err_counter_edit; + mlxsw_sp_rif_counter_valid_set(rif, dir, true); + return 0; + +err_counter_edit: +err_counter_clear: + mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_RIF, + *p_counter_index); + return err; +} + +void mlxsw_sp_rif_counter_free(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *rif, + enum mlxsw_sp_rif_counter_dir dir) +{ + unsigned int *p_counter_index; + + p_counter_index = mlxsw_sp_rif_p_counter_get(rif, dir); + if (WARN_ON(!p_counter_index)) + return; + mlxsw_sp_rif_counter_edit(mlxsw_sp, rif->rif_index, + *p_counter_index, false, dir); + mlxsw_sp_counter_free(mlxsw_sp, MLXSW_SP_COUNTER_SUB_POOL_RIF, + *p_counter_index); + mlxsw_sp_rif_counter_valid_set(rif, dir, false); +} + +static struct mlxsw_sp_rif * +mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev); #define mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) \ for_each_set_bit(prefix, (prefix_usage)->b, MLXSW_SP_PREFIX_COUNT) @@ -89,12 +259,6 @@ mlxsw_sp_prefix_usage_cpy(struct mlxsw_sp_prefix_usage *prefix_usage1, } static void -mlxsw_sp_prefix_usage_zero(struct mlxsw_sp_prefix_usage *prefix_usage) -{ - memset(prefix_usage, 0, sizeof(*prefix_usage)); -} - -static void mlxsw_sp_prefix_usage_set(struct mlxsw_sp_prefix_usage *prefix_usage, unsigned char prefix_len) { @@ -125,7 +289,7 @@ struct mlxsw_sp_fib_node { struct list_head entry_list; struct list_head list; struct rhash_head ht_node; - struct mlxsw_sp_vr *vr; + struct mlxsw_sp_fib *fib; struct mlxsw_sp_fib_key key; }; @@ -149,13 +313,17 @@ struct mlxsw_sp_fib_entry { struct mlxsw_sp_fib { struct rhashtable ht; struct list_head node_list; + struct mlxsw_sp_vr *vr; + struct mlxsw_sp_lpm_tree *lpm_tree; unsigned long prefix_ref_count[MLXSW_SP_PREFIX_COUNT]; struct mlxsw_sp_prefix_usage prefix_usage; + enum mlxsw_sp_l3proto proto; }; static const struct rhashtable_params mlxsw_sp_fib_ht_params; -static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void) +static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp_vr *vr, + enum mlxsw_sp_l3proto proto) { struct mlxsw_sp_fib *fib; int err; @@ -167,6 +335,8 @@ static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void) if (err) goto err_rhashtable_init; INIT_LIST_HEAD(&fib->node_list); + fib->proto = proto; + fib->vr = vr; return fib; err_rhashtable_init: @@ -177,24 +347,21 @@ err_rhashtable_init: static void mlxsw_sp_fib_destroy(struct mlxsw_sp_fib *fib) { WARN_ON(!list_empty(&fib->node_list)); + WARN_ON(fib->lpm_tree); rhashtable_destroy(&fib->ht); kfree(fib); } static struct mlxsw_sp_lpm_tree * -mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp, bool one_reserved) +mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp) { static struct mlxsw_sp_lpm_tree *lpm_tree; int i; - for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) { - lpm_tree = &mlxsw_sp->router.lpm_trees[i]; - if (lpm_tree->ref_count == 0) { - if (one_reserved) - one_reserved = false; - else - return lpm_tree; - } + for (i = 0; i < mlxsw_sp->router.lpm.tree_count; i++) { + lpm_tree = &mlxsw_sp->router.lpm.trees[i]; + if (lpm_tree->ref_count == 0) + return lpm_tree; } return NULL; } @@ -248,12 +415,12 @@ mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_lpm_tree * mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_prefix_usage *prefix_usage, - enum mlxsw_sp_l3proto proto, bool one_reserved) + enum mlxsw_sp_l3proto proto) { struct mlxsw_sp_lpm_tree *lpm_tree; int err; - lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp, one_reserved); + lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp); if (!lpm_tree) return ERR_PTR(-EBUSY); lpm_tree->proto = proto; @@ -283,13 +450,13 @@ static int mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_lpm_tree * mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_prefix_usage *prefix_usage, - enum mlxsw_sp_l3proto proto, bool one_reserved) + enum mlxsw_sp_l3proto proto) { struct mlxsw_sp_lpm_tree *lpm_tree; int i; - for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) { - lpm_tree = &mlxsw_sp->router.lpm_trees[i]; + for (i = 0; i < mlxsw_sp->router.lpm.tree_count; i++) { + lpm_tree = &mlxsw_sp->router.lpm.trees[i]; if (lpm_tree->ref_count != 0 && lpm_tree->proto == proto && mlxsw_sp_prefix_usage_eq(&lpm_tree->prefix_usage, @@ -297,7 +464,7 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, goto inc_ref_count; } lpm_tree = mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage, - proto, one_reserved); + proto); if (IS_ERR(lpm_tree)) return lpm_tree; @@ -314,15 +481,41 @@ static int mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp, return 0; } -static void mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp) +#define MLXSW_SP_LPM_TREE_MIN 2 /* trees 0 and 1 are reserved */ + +static int mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_lpm_tree *lpm_tree; + u64 max_trees; int i; - for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) { - lpm_tree = &mlxsw_sp->router.lpm_trees[i]; + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_LPM_TREES)) + return -EIO; + + max_trees = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_LPM_TREES); + mlxsw_sp->router.lpm.tree_count = max_trees - MLXSW_SP_LPM_TREE_MIN; + mlxsw_sp->router.lpm.trees = kcalloc(mlxsw_sp->router.lpm.tree_count, + sizeof(struct mlxsw_sp_lpm_tree), + GFP_KERNEL); + if (!mlxsw_sp->router.lpm.trees) + return -ENOMEM; + + for (i = 0; i < mlxsw_sp->router.lpm.tree_count; i++) { + lpm_tree = &mlxsw_sp->router.lpm.trees[i]; lpm_tree->id = i + MLXSW_SP_LPM_TREE_MIN; } + + return 0; +} + +static void mlxsw_sp_lpm_fini(struct mlxsw_sp *mlxsw_sp) +{ + kfree(mlxsw_sp->router.lpm.trees); +} + +static bool mlxsw_sp_vr_is_used(const struct mlxsw_sp_vr *vr) +{ + return !!vr->fib4; } static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) @@ -332,31 +525,31 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { vr = &mlxsw_sp->router.vrs[i]; - if (!vr->used) + if (!mlxsw_sp_vr_is_used(vr)) return vr; } return NULL; } static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vr *vr) + const struct mlxsw_sp_fib *fib) { char raltb_pl[MLXSW_REG_RALTB_LEN]; - mlxsw_reg_raltb_pack(raltb_pl, vr->id, - (enum mlxsw_reg_ralxx_protocol) vr->proto, - vr->lpm_tree->id); + mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id, + (enum mlxsw_reg_ralxx_protocol) fib->proto, + fib->lpm_tree->id); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); } static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vr *vr) + const struct mlxsw_sp_fib *fib) { char raltb_pl[MLXSW_REG_RALTB_LEN]; /* Bind to tree 0 which is default */ - mlxsw_reg_raltb_pack(raltb_pl, vr->id, - (enum mlxsw_reg_ralxx_protocol) vr->proto, 0); + mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id, + (enum mlxsw_reg_ralxx_protocol) fib->proto, 0); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); } @@ -369,8 +562,7 @@ static u32 mlxsw_sp_fix_tb_id(u32 tb_id) } static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp, - u32 tb_id, - enum mlxsw_sp_l3proto proto) + u32 tb_id) { struct mlxsw_sp_vr *vr; int i; @@ -379,69 +571,50 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp, for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { vr = &mlxsw_sp->router.vrs[i]; - if (vr->used && vr->proto == proto && vr->tb_id == tb_id) + if (mlxsw_sp_vr_is_used(vr) && vr->tb_id == tb_id) return vr; } return NULL; } +static struct mlxsw_sp_fib *mlxsw_sp_vr_fib(const struct mlxsw_sp_vr *vr, + enum mlxsw_sp_l3proto proto) +{ + switch (proto) { + case MLXSW_SP_L3_PROTO_IPV4: + return vr->fib4; + case MLXSW_SP_L3_PROTO_IPV6: + BUG_ON(1); + } + return NULL; +} + static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, - unsigned char prefix_len, - u32 tb_id, - enum mlxsw_sp_l3proto proto) + u32 tb_id) { - struct mlxsw_sp_prefix_usage req_prefix_usage; - struct mlxsw_sp_lpm_tree *lpm_tree; struct mlxsw_sp_vr *vr; - int err; vr = mlxsw_sp_vr_find_unused(mlxsw_sp); if (!vr) return ERR_PTR(-EBUSY); - vr->fib = mlxsw_sp_fib_create(); - if (IS_ERR(vr->fib)) - return ERR_CAST(vr->fib); - - vr->proto = proto; + vr->fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4); + if (IS_ERR(vr->fib4)) + return ERR_CAST(vr->fib4); vr->tb_id = tb_id; - mlxsw_sp_prefix_usage_zero(&req_prefix_usage); - mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len); - lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, - proto, true); - if (IS_ERR(lpm_tree)) { - err = PTR_ERR(lpm_tree); - goto err_tree_get; - } - vr->lpm_tree = lpm_tree; - err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); - if (err) - goto err_tree_bind; - - vr->used = true; return vr; - -err_tree_bind: - mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree); -err_tree_get: - mlxsw_sp_fib_destroy(vr->fib); - - return ERR_PTR(err); } -static void mlxsw_sp_vr_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vr *vr) +static void mlxsw_sp_vr_destroy(struct mlxsw_sp_vr *vr) { - mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr); - mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree); - mlxsw_sp_fib_destroy(vr->fib); - vr->used = false; + mlxsw_sp_fib_destroy(vr->fib4); + vr->fib4 = NULL; } static int -mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, +mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib *fib, struct mlxsw_sp_prefix_usage *req_prefix_usage) { - struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree; + struct mlxsw_sp_lpm_tree *lpm_tree = fib->lpm_tree; struct mlxsw_sp_lpm_tree *new_tree; int err; @@ -449,7 +622,7 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, return 0; new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage, - vr->proto, false); + fib->proto); if (IS_ERR(new_tree)) { /* We failed to get a tree according to the required * prefix usage. However, the current tree might be still good @@ -463,8 +636,8 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, } /* Prevent packet loss by overwriting existing binding */ - vr->lpm_tree = new_tree; - err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr); + fib->lpm_tree = new_tree; + err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib); if (err) goto err_tree_bind; mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); @@ -472,53 +645,26 @@ mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, return 0; err_tree_bind: - vr->lpm_tree = lpm_tree; + fib->lpm_tree = lpm_tree; mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree); return err; } -static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, - unsigned char prefix_len, - u32 tb_id, - enum mlxsw_sp_l3proto proto) +static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id) { struct mlxsw_sp_vr *vr; - int err; tb_id = mlxsw_sp_fix_tb_id(tb_id); - vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id, proto); - if (!vr) { - vr = mlxsw_sp_vr_create(mlxsw_sp, prefix_len, tb_id, proto); - if (IS_ERR(vr)) - return vr; - } else { - struct mlxsw_sp_prefix_usage req_prefix_usage; - - mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, - &vr->fib->prefix_usage); - mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len); - /* Need to replace LPM tree in case new prefix is required. */ - err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr, - &req_prefix_usage); - if (err) - return ERR_PTR(err); - } + vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id); + if (!vr) + vr = mlxsw_sp_vr_create(mlxsw_sp, tb_id); return vr; } -static void mlxsw_sp_vr_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr) +static void mlxsw_sp_vr_put(struct mlxsw_sp_vr *vr) { - /* Destroy virtual router entity in case the associated FIB is empty - * and allow it to be used for other tables in future. Otherwise, - * check if some prefix usage did not disappear and change tree if - * that is the case. Note that in case new, smaller tree cannot be - * allocated, the original one will be kept being used. - */ - if (mlxsw_sp_prefix_usage_none(&vr->fib->prefix_usage)) - mlxsw_sp_vr_destroy(mlxsw_sp, vr); - else - mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr, - &vr->fib->prefix_usage); + if (!vr->rif_count && list_empty(&vr->fib4->node_list)) + mlxsw_sp_vr_destroy(vr); } static int mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp) @@ -627,14 +773,14 @@ static struct mlxsw_sp_neigh_entry * mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n) { struct mlxsw_sp_neigh_entry *neigh_entry; - struct mlxsw_sp_rif *r; + struct mlxsw_sp_rif *rif; int err; - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev); - if (!r) + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev); + if (!rif) return ERR_PTR(-EINVAL); - neigh_entry = mlxsw_sp_neigh_entry_alloc(mlxsw_sp, n, r->rif); + neigh_entry = mlxsw_sp_neigh_entry_alloc(mlxsw_sp, n, rif->rif_index); if (!neigh_entry) return ERR_PTR(-ENOMEM); @@ -642,7 +788,7 @@ mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n) if (err) goto err_neigh_entry_insert; - list_add(&neigh_entry->rif_list_node, &r->neigh_list); + list_add(&neigh_entry->rif_list_node, &rif->neigh_list); return neigh_entry; @@ -1050,22 +1196,22 @@ static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp) } static int mlxsw_sp_neigh_rif_flush(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_rif *r) + const struct mlxsw_sp_rif *rif) { char rauht_pl[MLXSW_REG_RAUHT_LEN]; mlxsw_reg_rauht_pack(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_DELETE_ALL, - r->rif, r->addr); + rif->rif_index, rif->addr); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl); } static void mlxsw_sp_neigh_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r) + struct mlxsw_sp_rif *rif) { struct mlxsw_sp_neigh_entry *neigh_entry, *tmp; - mlxsw_sp_neigh_rif_flush(mlxsw_sp, r); - list_for_each_entry_safe(neigh_entry, tmp, &r->neigh_list, + mlxsw_sp_neigh_rif_flush(mlxsw_sp, rif); + list_for_each_entry_safe(neigh_entry, tmp, &rif->neigh_list, rif_list_node) mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry); } @@ -1082,7 +1228,7 @@ struct mlxsw_sp_nexthop { */ struct rhash_head ht_node; struct mlxsw_sp_nexthop_key key; - struct mlxsw_sp_rif *r; + struct mlxsw_sp_rif *rif; u8 should_offload:1, /* set indicates this neigh is connected and * should be put to KVD linear area of this group. */ @@ -1109,7 +1255,7 @@ struct mlxsw_sp_nexthop_group { u16 ecmp_size; u16 count; struct mlxsw_sp_nexthop nexthops[0]; -#define nh_rif nexthops[0].r +#define nh_rif nexthops[0].rif }; static const struct rhashtable_params mlxsw_sp_nexthop_group_ht_params = { @@ -1171,7 +1317,7 @@ mlxsw_sp_nexthop_lookup(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_vr *vr, + const struct mlxsw_sp_fib *fib, u32 adj_index, u16 ecmp_size, u32 new_adj_index, u16 new_ecmp_size) @@ -1179,8 +1325,8 @@ static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp, char raleu_pl[MLXSW_REG_RALEU_LEN]; mlxsw_reg_raleu_pack(raleu_pl, - (enum mlxsw_reg_ralxx_protocol) vr->proto, vr->id, - adj_index, ecmp_size, new_adj_index, + (enum mlxsw_reg_ralxx_protocol) fib->proto, + fib->vr->id, adj_index, ecmp_size, new_adj_index, new_ecmp_size); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raleu), raleu_pl); } @@ -1190,14 +1336,14 @@ static int mlxsw_sp_adj_index_mass_update(struct mlxsw_sp *mlxsw_sp, u32 old_adj_index, u16 old_ecmp_size) { struct mlxsw_sp_fib_entry *fib_entry; - struct mlxsw_sp_vr *vr = NULL; + struct mlxsw_sp_fib *fib = NULL; int err; list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) { - if (vr == fib_entry->fib_node->vr) + if (fib == fib_entry->fib_node->fib) continue; - vr = fib_entry->fib_node->vr; - err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, vr, + fib = fib_entry->fib_node->fib; + err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, fib, old_adj_index, old_ecmp_size, nh_grp->adj_index, @@ -1280,7 +1426,6 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, bool old_adj_index_valid; u32 old_adj_index; u16 old_ecmp_size; - int ret; int i; int err; @@ -1318,15 +1463,14 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, */ goto set_trap; - ret = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size); - if (ret < 0) { + err = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size, &adj_index); + if (err) { /* We ran out of KVD linear space, just set the * trap and let everything flow through kernel. */ dev_warn(mlxsw_sp->bus_info->dev, "Failed to allocate KVD linear area for nexthop group.\n"); goto set_trap; } - adj_index = ret; old_adj_index_valid = nh_grp->adj_index_valid; old_adj_index = nh_grp->adj_index; old_ecmp_size = nh_grp->ecmp_size; @@ -1399,22 +1543,22 @@ mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp, } static void mlxsw_sp_nexthop_rif_init(struct mlxsw_sp_nexthop *nh, - struct mlxsw_sp_rif *r) + struct mlxsw_sp_rif *rif) { - if (nh->r) + if (nh->rif) return; - nh->r = r; - list_add(&nh->rif_list_node, &r->nexthop_list); + nh->rif = rif; + list_add(&nh->rif_list_node, &rif->nexthop_list); } static void mlxsw_sp_nexthop_rif_fini(struct mlxsw_sp_nexthop *nh) { - if (!nh->r) + if (!nh->rif) return; list_del(&nh->rif_list_node); - nh->r = NULL; + nh->rif = NULL; } static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp, @@ -1505,7 +1649,7 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp, { struct net_device *dev = fib_nh->nh_dev; struct in_device *in_dev; - struct mlxsw_sp_rif *r; + struct mlxsw_sp_rif *rif; int err; nh->nh_grp = nh_grp; @@ -1514,15 +1658,18 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp, if (err) return err; + if (!dev) + return 0; + in_dev = __in_dev_get_rtnl(dev); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && fib_nh->nh_flags & RTNH_F_LINKDOWN) return 0; - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); - if (!r) + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!rif) return 0; - mlxsw_sp_nexthop_rif_init(nh, r); + mlxsw_sp_nexthop_rif_init(nh, rif); err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh); if (err) @@ -1548,7 +1695,7 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_nexthop_key key; struct mlxsw_sp_nexthop *nh; - struct mlxsw_sp_rif *r; + struct mlxsw_sp_rif *rif; if (mlxsw_sp->router.aborted) return; @@ -1558,13 +1705,13 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp, if (WARN_ON_ONCE(!nh)) return; - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fib_nh->nh_dev); - if (!r) + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fib_nh->nh_dev); + if (!rif) return; switch (event) { case FIB_EVENT_NH_ADD: - mlxsw_sp_nexthop_rif_init(nh, r); + mlxsw_sp_nexthop_rif_init(nh, rif); mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh); break; case FIB_EVENT_NH_DEL: @@ -1577,11 +1724,11 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp, } static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r) + struct mlxsw_sp_rif *rif) { struct mlxsw_sp_nexthop *nh, *tmp; - list_for_each_entry_safe(nh, tmp, &r->nexthop_list, rif_list_node) { + list_for_each_entry_safe(nh, tmp, &rif->nexthop_list, rif_list_node) { mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh); mlxsw_sp_nexthop_rif_fini(nh); mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp); @@ -1699,7 +1846,7 @@ static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) { fib_entry->offloaded = true; - switch (fib_entry->fib_node->vr->proto) { + switch (fib_entry->fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: fib_info_offload_inc(fib_entry->nh_group->key.fi); break; @@ -1711,7 +1858,7 @@ static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) static void mlxsw_sp_fib_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry) { - switch (fib_entry->fib_node->vr->proto) { + switch (fib_entry->fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: fib_info_offload_dec(fib_entry->nh_group->key.fi); break; @@ -1751,8 +1898,8 @@ static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp, enum mlxsw_reg_ralue_op op) { char ralue_pl[MLXSW_REG_RALUE_LEN]; + struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr; - struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr; enum mlxsw_reg_ralue_trap_action trap_action; u16 trap_id = 0; u32 adjacency_index = 0; @@ -1772,8 +1919,8 @@ static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp, } mlxsw_reg_ralue_pack4(ralue_pl, - (enum mlxsw_reg_ralxx_protocol) vr->proto, op, - vr->id, fib_entry->fib_node->key.prefix_len, + (enum mlxsw_reg_ralxx_protocol) fib->proto, op, + fib->vr->id, fib_entry->fib_node->key.prefix_len, *p_dip); mlxsw_reg_ralue_act_remote_pack(ralue_pl, trap_action, trap_id, adjacency_index, ecmp_size); @@ -1784,27 +1931,28 @@ static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, enum mlxsw_reg_ralue_op op) { - struct mlxsw_sp_rif *r = fib_entry->nh_group->nh_rif; + struct mlxsw_sp_rif *rif = fib_entry->nh_group->nh_rif; + struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; enum mlxsw_reg_ralue_trap_action trap_action; char ralue_pl[MLXSW_REG_RALUE_LEN]; u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr; - struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr; u16 trap_id = 0; - u16 rif = 0; + u16 rif_index = 0; if (mlxsw_sp_fib_entry_should_offload(fib_entry)) { trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP; - rif = r->rif; + rif_index = rif->rif_index; } else { trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP; trap_id = MLXSW_TRAP_ID_RTR_INGRESS0; } mlxsw_reg_ralue_pack4(ralue_pl, - (enum mlxsw_reg_ralxx_protocol) vr->proto, op, - vr->id, fib_entry->fib_node->key.prefix_len, + (enum mlxsw_reg_ralxx_protocol) fib->proto, op, + fib->vr->id, fib_entry->fib_node->key.prefix_len, *p_dip); - mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, rif); + mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, + rif_index); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } @@ -1812,13 +1960,13 @@ static int mlxsw_sp_fib_entry_op4_trap(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, enum mlxsw_reg_ralue_op op) { + struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; char ralue_pl[MLXSW_REG_RALUE_LEN]; u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr; - struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr; mlxsw_reg_ralue_pack4(ralue_pl, - (enum mlxsw_reg_ralxx_protocol) vr->proto, op, - vr->id, fib_entry->fib_node->key.prefix_len, + (enum mlxsw_reg_ralxx_protocol) fib->proto, op, + fib->vr->id, fib_entry->fib_node->key.prefix_len, *p_dip); mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); @@ -1845,7 +1993,7 @@ static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, { int err = -EINVAL; - switch (fib_entry->fib_node->vr->proto) { + switch (fib_entry->fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: err = mlxsw_sp_fib_entry_op4(mlxsw_sp, fib_entry, op); break; @@ -1877,17 +2025,29 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, { struct fib_info *fi = fen_info->fi; - if (fen_info->type == RTN_LOCAL || fen_info->type == RTN_BROADCAST) { + switch (fen_info->type) { + case RTN_BROADCAST: /* fall through */ + case RTN_LOCAL: fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; return 0; - } - if (fen_info->type != RTN_UNICAST) - return -EINVAL; - if (fi->fib_nh->nh_scope != RT_SCOPE_LINK) + case RTN_UNREACHABLE: /* fall through */ + case RTN_BLACKHOLE: /* fall through */ + case RTN_PROHIBIT: + /* Packets hitting these routes need to be trapped, but + * can do so with a lower priority than packets directed + * at the host, so use action type local instead of trap. + */ fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; - else - fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; - return 0; + return 0; + case RTN_UNICAST: + if (fi->fib_nh->nh_scope != RT_SCOPE_LINK) + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; + else + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; + return 0; + default: + return -EINVAL; + } } static struct mlxsw_sp_fib_entry * @@ -1996,7 +2156,7 @@ mlxsw_sp_fib_node_lookup(struct mlxsw_sp_fib *fib, const void *addr, } static struct mlxsw_sp_fib_node * -mlxsw_sp_fib_node_create(struct mlxsw_sp_vr *vr, const void *addr, +mlxsw_sp_fib_node_create(struct mlxsw_sp_fib *fib, const void *addr, size_t addr_len, unsigned char prefix_len) { struct mlxsw_sp_fib_node *fib_node; @@ -2006,18 +2166,15 @@ mlxsw_sp_fib_node_create(struct mlxsw_sp_vr *vr, const void *addr, return NULL; INIT_LIST_HEAD(&fib_node->entry_list); - list_add(&fib_node->list, &vr->fib->node_list); + list_add(&fib_node->list, &fib->node_list); memcpy(fib_node->key.addr, addr, addr_len); fib_node->key.prefix_len = prefix_len; - mlxsw_sp_fib_node_insert(vr->fib, fib_node); - fib_node->vr = vr; return fib_node; } static void mlxsw_sp_fib_node_destroy(struct mlxsw_sp_fib_node *fib_node) { - mlxsw_sp_fib_node_remove(fib_node->vr->fib, fib_node); list_del(&fib_node->list); WARN_ON(!list_empty(&fib_node->entry_list)); kfree(fib_node); @@ -2034,7 +2191,7 @@ mlxsw_sp_fib_node_entry_is_first(const struct mlxsw_sp_fib_node *fib_node, static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node) { unsigned char prefix_len = fib_node->key.prefix_len; - struct mlxsw_sp_fib *fib = fib_node->vr->fib; + struct mlxsw_sp_fib *fib = fib_node->fib; if (fib->prefix_ref_count[prefix_len]++ == 0) mlxsw_sp_prefix_usage_set(&fib->prefix_usage, prefix_len); @@ -2043,32 +2200,98 @@ static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node) static void mlxsw_sp_fib_node_prefix_dec(struct mlxsw_sp_fib_node *fib_node) { unsigned char prefix_len = fib_node->key.prefix_len; - struct mlxsw_sp_fib *fib = fib_node->vr->fib; + struct mlxsw_sp_fib *fib = fib_node->fib; if (--fib->prefix_ref_count[prefix_len] == 0) mlxsw_sp_prefix_usage_clear(&fib->prefix_usage, prefix_len); } +static int mlxsw_sp_fib_node_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_node *fib_node, + struct mlxsw_sp_fib *fib) +{ + struct mlxsw_sp_prefix_usage req_prefix_usage; + struct mlxsw_sp_lpm_tree *lpm_tree; + int err; + + err = mlxsw_sp_fib_node_insert(fib, fib_node); + if (err) + return err; + fib_node->fib = fib; + + mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, &fib->prefix_usage); + mlxsw_sp_prefix_usage_set(&req_prefix_usage, fib_node->key.prefix_len); + + if (!mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) { + err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib, + &req_prefix_usage); + if (err) + goto err_tree_check; + } else { + lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, + fib->proto); + if (IS_ERR(lpm_tree)) + return PTR_ERR(lpm_tree); + fib->lpm_tree = lpm_tree; + err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib); + if (err) + goto err_tree_bind; + } + + mlxsw_sp_fib_node_prefix_inc(fib_node); + + return 0; + +err_tree_bind: + fib->lpm_tree = NULL; + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); +err_tree_check: + fib_node->fib = NULL; + mlxsw_sp_fib_node_remove(fib, fib_node); + return err; +} + +static void mlxsw_sp_fib_node_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_node *fib_node) +{ + struct mlxsw_sp_lpm_tree *lpm_tree = fib_node->fib->lpm_tree; + struct mlxsw_sp_fib *fib = fib_node->fib; + + mlxsw_sp_fib_node_prefix_dec(fib_node); + + if (mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) { + mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib); + fib->lpm_tree = NULL; + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); + } else { + mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib, &fib->prefix_usage); + } + + fib_node->fib = NULL; + mlxsw_sp_fib_node_remove(fib, fib_node); +} + static struct mlxsw_sp_fib_node * mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp, const struct fib_entry_notifier_info *fen_info) { struct mlxsw_sp_fib_node *fib_node; + struct mlxsw_sp_fib *fib; struct mlxsw_sp_vr *vr; int err; - vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->dst_len, fen_info->tb_id, - MLXSW_SP_L3_PROTO_IPV4); + vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->tb_id); if (IS_ERR(vr)) return ERR_CAST(vr); + fib = mlxsw_sp_vr_fib(vr, MLXSW_SP_L3_PROTO_IPV4); - fib_node = mlxsw_sp_fib_node_lookup(vr->fib, &fen_info->dst, + fib_node = mlxsw_sp_fib_node_lookup(fib, &fen_info->dst, sizeof(fen_info->dst), fen_info->dst_len); if (fib_node) return fib_node; - fib_node = mlxsw_sp_fib_node_create(vr, &fen_info->dst, + fib_node = mlxsw_sp_fib_node_create(fib, &fen_info->dst, sizeof(fen_info->dst), fen_info->dst_len); if (!fib_node) { @@ -2076,22 +2299,29 @@ mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp, goto err_fib_node_create; } + err = mlxsw_sp_fib_node_init(mlxsw_sp, fib_node, fib); + if (err) + goto err_fib_node_init; + return fib_node; +err_fib_node_init: + mlxsw_sp_fib_node_destroy(fib_node); err_fib_node_create: - mlxsw_sp_vr_put(mlxsw_sp, vr); + mlxsw_sp_vr_put(vr); return ERR_PTR(err); } static void mlxsw_sp_fib4_node_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node) { - struct mlxsw_sp_vr *vr = fib_node->vr; + struct mlxsw_sp_vr *vr = fib_node->fib->vr; if (!list_empty(&fib_node->entry_list)) return; + mlxsw_sp_fib_node_fini(mlxsw_sp, fib_node); mlxsw_sp_fib_node_destroy(fib_node); - mlxsw_sp_vr_put(mlxsw_sp, vr); + mlxsw_sp_vr_put(vr); } static struct mlxsw_sp_fib_entry * @@ -2236,8 +2466,6 @@ static int mlxsw_sp_fib4_node_entry_link(struct mlxsw_sp *mlxsw_sp, if (err) goto err_fib4_node_entry_add; - mlxsw_sp_fib_node_prefix_inc(fib_node); - return 0; err_fib4_node_entry_add: @@ -2251,7 +2479,6 @@ mlxsw_sp_fib4_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node; - mlxsw_sp_fib_node_prefix_dec(fib_node); mlxsw_sp_fib4_node_entry_del(mlxsw_sp, fib_node, fib_entry); mlxsw_sp_fib4_node_list_remove(fib_entry); } @@ -2340,9 +2567,7 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) { char ralta_pl[MLXSW_REG_RALTA_LEN]; char ralst_pl[MLXSW_REG_RALST_LEN]; - char raltb_pl[MLXSW_REG_RALTB_LEN]; - char ralue_pl[MLXSW_REG_RALUE_LEN]; - int err; + int i, err; mlxsw_reg_ralta_pack(ralta_pl, true, MLXSW_REG_RALXX_PROTOCOL_IPV4, MLXSW_SP_LPM_TREE_MIN); @@ -2355,16 +2580,33 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) if (err) return err; - mlxsw_reg_raltb_pack(raltb_pl, 0, MLXSW_REG_RALXX_PROTOCOL_IPV4, - MLXSW_SP_LPM_TREE_MIN); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); - if (err) - return err; + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[i]; + char raltb_pl[MLXSW_REG_RALTB_LEN]; + char ralue_pl[MLXSW_REG_RALUE_LEN]; - mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4, - MLXSW_REG_RALUE_OP_WRITE_WRITE, 0, 0, 0); - mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); + if (!mlxsw_sp_vr_is_used(vr)) + continue; + + mlxsw_reg_raltb_pack(raltb_pl, vr->id, + MLXSW_REG_RALXX_PROTOCOL_IPV4, + MLXSW_SP_LPM_TREE_MIN); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), + raltb_pl); + if (err) + return err; + + mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4, + MLXSW_REG_RALUE_OP_WRITE_WRITE, vr->id, 0, + 0); + mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), + ralue_pl); + if (err) + return err; + } + + return 0; } static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp, @@ -2390,7 +2632,7 @@ static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node) { - switch (fib_node->vr->proto) { + switch (fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: mlxsw_sp_fib4_node_flush(mlxsw_sp, fib_node); break; @@ -2400,26 +2642,32 @@ static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp, } } -static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) +static void mlxsw_sp_vr_fib_flush(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_vr *vr, + enum mlxsw_sp_l3proto proto) { + struct mlxsw_sp_fib *fib = mlxsw_sp_vr_fib(vr, proto); struct mlxsw_sp_fib_node *fib_node, *tmp; - struct mlxsw_sp_vr *vr; + + list_for_each_entry_safe(fib_node, tmp, &fib->node_list, list) { + bool do_break = &tmp->list == &fib->node_list; + + mlxsw_sp_fib_node_flush(mlxsw_sp, fib_node); + if (do_break) + break; + } +} + +static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) +{ int i; for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { - vr = &mlxsw_sp->router.vrs[i]; + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[i]; - if (!vr->used) + if (!mlxsw_sp_vr_is_used(vr)) continue; - - list_for_each_entry_safe(fib_node, tmp, &vr->fib->node_list, - list) { - bool do_break = &tmp->list == &vr->fib->node_list; - - mlxsw_sp_fib_node_flush(mlxsw_sp, fib_node); - if (do_break) - break; - } + mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4); } } @@ -2437,74 +2685,11 @@ static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp) dev_warn(mlxsw_sp->bus_info->dev, "Failed to set abort trap.\n"); } -static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif) -{ - char ritr_pl[MLXSW_REG_RITR_LEN]; - int err; - - mlxsw_reg_ritr_rif_pack(ritr_pl, rif); - err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); - if (WARN_ON_ONCE(err)) - return err; - - mlxsw_reg_ritr_enable_set(ritr_pl, false); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); -} - -void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_rif *r) -{ - mlxsw_sp_router_rif_disable(mlxsw_sp, r->rif); - mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, r); - mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, r); -} - -static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) -{ - char rgcr_pl[MLXSW_REG_RGCR_LEN]; - u64 max_rifs; - int err; - - if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS)) - return -EIO; - - max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); - mlxsw_sp->rifs = kcalloc(max_rifs, sizeof(struct mlxsw_sp_rif *), - GFP_KERNEL); - if (!mlxsw_sp->rifs) - return -ENOMEM; - - mlxsw_reg_rgcr_pack(rgcr_pl, true); - mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); - if (err) - goto err_rgcr_fail; - - return 0; - -err_rgcr_fail: - kfree(mlxsw_sp->rifs); - return err; -} - -static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) -{ - char rgcr_pl[MLXSW_REG_RGCR_LEN]; - int i; - - mlxsw_reg_rgcr_pack(rgcr_pl, false); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); - - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) - WARN_ON_ONCE(mlxsw_sp->rifs[i]); - - kfree(mlxsw_sp->rifs); -} - struct mlxsw_sp_fib_event_work { struct work_struct work; union { struct fib_entry_notifier_info fen_info; + struct fib_rule_notifier_info fr_info; struct fib_nh_notifier_info fnh_info; }; struct mlxsw_sp *mlxsw_sp; @@ -2516,6 +2701,7 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work) struct mlxsw_sp_fib_event_work *fib_work = container_of(work, struct mlxsw_sp_fib_event_work, work); struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; + struct fib_rule *rule; bool replace, append; int err; @@ -2539,7 +2725,10 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work) break; case FIB_EVENT_RULE_ADD: /* fall through */ case FIB_EVENT_RULE_DEL: - mlxsw_sp_router_fib4_abort(mlxsw_sp); + rule = fib_work->fr_info.rule; + if (!fib4_rule_default(rule) && !rule->l3mdev) + mlxsw_sp_router_fib4_abort(mlxsw_sp); + fib_rule_put(rule); break; case FIB_EVENT_NH_ADD: /* fall through */ case FIB_EVENT_NH_DEL: @@ -2582,6 +2771,11 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, */ fib_info_hold(fib_work->fen_info.fi); break; + case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_DEL: + memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info)); + fib_rule_get(fib_work->fr_info.rule); + break; case FIB_EVENT_NH_ADD: /* fall through */ case FIB_EVENT_NH_DEL: memcpy(&fib_work->fnh_info, ptr, sizeof(fib_work->fnh_info)); @@ -2594,6 +2788,707 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, return NOTIFY_DONE; } +static struct mlxsw_sp_rif * +mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev) +{ + int i; + + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) + if (mlxsw_sp->rifs[i] && mlxsw_sp->rifs[i]->dev == dev) + return mlxsw_sp->rifs[i]; + + return NULL; +} + +static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif) +{ + char ritr_pl[MLXSW_REG_RITR_LEN]; + int err; + + mlxsw_reg_ritr_rif_pack(ritr_pl, rif); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); + if (WARN_ON_ONCE(err)) + return err; + + mlxsw_reg_ritr_enable_set(ritr_pl, false); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +static void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *rif) +{ + mlxsw_sp_router_rif_disable(mlxsw_sp, rif->rif_index); + mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, rif); + mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, rif); +} + +static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *rif, + const struct in_device *in_dev, + unsigned long event) +{ + switch (event) { + case NETDEV_UP: + if (!rif) + return true; + return false; + case NETDEV_DOWN: + if (rif && !in_dev->ifa_list && + !netif_is_l3_slave(rif->dev)) + return true; + /* It is possible we already removed the RIF ourselves + * if it was assigned to a netdev that is now a bridge + * or LAG slave. + */ + return false; + } + + return false; +} + +#define MLXSW_SP_INVALID_INDEX_RIF 0xffff +static int mlxsw_sp_avail_rif_get(struct mlxsw_sp *mlxsw_sp) +{ + int i; + + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) + if (!mlxsw_sp->rifs[i]) + return i; + + return MLXSW_SP_INVALID_INDEX_RIF; +} + +static void mlxsw_sp_vport_rif_sp_attr_get(struct mlxsw_sp_port *mlxsw_sp_vport, + bool *p_lagged, u16 *p_system_port) +{ + u8 local_port = mlxsw_sp_vport->local_port; + + *p_lagged = mlxsw_sp_vport->lagged; + *p_system_port = *p_lagged ? mlxsw_sp_vport->lag_id : local_port; +} + +static int mlxsw_sp_vport_rif_sp_op(struct mlxsw_sp_port *mlxsw_sp_vport, + u16 vr_id, struct net_device *l3_dev, + u16 rif_index, bool create) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + bool lagged = mlxsw_sp_vport->lagged; + char ritr_pl[MLXSW_REG_RITR_LEN]; + u16 system_port; + + mlxsw_reg_ritr_pack(ritr_pl, create, MLXSW_REG_RITR_SP_IF, rif_index, + vr_id, l3_dev->mtu, l3_dev->dev_addr); + + mlxsw_sp_vport_rif_sp_attr_get(mlxsw_sp_vport, &lagged, &system_port); + mlxsw_reg_ritr_sp_if_pack(ritr_pl, lagged, system_port, + mlxsw_sp_vport_vid_get(mlxsw_sp_vport)); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport); + +static u16 mlxsw_sp_rif_sp_to_fid(u16 rif_index) +{ + return MLXSW_SP_RFID_BASE + rif_index; +} + +static struct mlxsw_sp_fid * +mlxsw_sp_rfid_alloc(u16 fid, struct net_device *l3_dev) +{ + struct mlxsw_sp_fid *f; + + f = kzalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + f->leave = mlxsw_sp_vport_rif_sp_leave; + f->ref_count = 0; + f->dev = l3_dev; + f->fid = fid; + + return f; +} + +static struct mlxsw_sp_rif * +mlxsw_sp_rif_alloc(u16 rif_index, u16 vr_id, struct net_device *l3_dev, + struct mlxsw_sp_fid *f) +{ + struct mlxsw_sp_rif *rif; + + rif = kzalloc(sizeof(*rif), GFP_KERNEL); + if (!rif) + return NULL; + + INIT_LIST_HEAD(&rif->nexthop_list); + INIT_LIST_HEAD(&rif->neigh_list); + ether_addr_copy(rif->addr, l3_dev->dev_addr); + rif->mtu = l3_dev->mtu; + rif->vr_id = vr_id; + rif->dev = l3_dev; + rif->rif_index = rif_index; + rif->f = f; + + return rif; +} + +u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif) +{ + return rif->rif_index; +} + +int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif) +{ + return rif->dev->ifindex; +} + +static struct mlxsw_sp_rif * +mlxsw_sp_vport_rif_sp_create(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *l3_dev) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + u32 tb_id = l3mdev_fib_table(l3_dev); + struct mlxsw_sp_vr *vr; + struct mlxsw_sp_fid *f; + struct mlxsw_sp_rif *rif; + u16 fid, rif_index; + int err; + + rif_index = mlxsw_sp_avail_rif_get(mlxsw_sp); + if (rif_index == MLXSW_SP_INVALID_INDEX_RIF) + return ERR_PTR(-ERANGE); + + vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN); + if (IS_ERR(vr)) + return ERR_CAST(vr); + + err = mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, + rif_index, true); + if (err) + goto err_vport_rif_sp_op; + + fid = mlxsw_sp_rif_sp_to_fid(rif_index); + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, true); + if (err) + goto err_rif_fdb_op; + + f = mlxsw_sp_rfid_alloc(fid, l3_dev); + if (!f) { + err = -ENOMEM; + goto err_rfid_alloc; + } + + rif = mlxsw_sp_rif_alloc(rif_index, vr->id, l3_dev, f); + if (!rif) { + err = -ENOMEM; + goto err_rif_alloc; + } + + if (devlink_dpipe_table_counter_enabled(priv_to_devlink(mlxsw_sp->core), + MLXSW_SP_DPIPE_TABLE_NAME_ERIF)) { + err = mlxsw_sp_rif_counter_alloc(mlxsw_sp, rif, + MLXSW_SP_RIF_COUNTER_EGRESS); + if (err) + netdev_dbg(mlxsw_sp_vport->dev, + "Counter alloc Failed err=%d\n", err); + } + + f->rif = rif; + mlxsw_sp->rifs[rif_index] = rif; + vr->rif_count++; + + return rif; + +err_rif_alloc: + kfree(f); +err_rfid_alloc: + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); +err_rif_fdb_op: + mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif_index, + false); +err_vport_rif_sp_op: + mlxsw_sp_vr_put(vr); + return ERR_PTR(err); +} + +static void mlxsw_sp_vport_rif_sp_destroy(struct mlxsw_sp_port *mlxsw_sp_vport, + struct mlxsw_sp_rif *rif) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[rif->vr_id]; + struct net_device *l3_dev = rif->dev; + struct mlxsw_sp_fid *f = rif->f; + u16 rif_index = rif->rif_index; + u16 fid = f->fid; + + mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif); + + mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_EGRESS); + mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_INGRESS); + + vr->rif_count--; + mlxsw_sp->rifs[rif_index] = NULL; + f->rif = NULL; + + kfree(rif); + + kfree(f); + + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, fid, false); + + mlxsw_sp_vport_rif_sp_op(mlxsw_sp_vport, vr->id, l3_dev, rif_index, + false); + mlxsw_sp_vr_put(vr); +} + +static int mlxsw_sp_vport_rif_sp_join(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *l3_dev) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; + struct mlxsw_sp_rif *rif; + + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev); + if (!rif) { + rif = mlxsw_sp_vport_rif_sp_create(mlxsw_sp_vport, l3_dev); + if (IS_ERR(rif)) + return PTR_ERR(rif); + } + + mlxsw_sp_vport_fid_set(mlxsw_sp_vport, rif->f); + rif->f->ref_count++; + + netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", rif->f->fid); + + return 0; +} + +static void mlxsw_sp_vport_rif_sp_leave(struct mlxsw_sp_port *mlxsw_sp_vport) +{ + struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport); + + netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid); + + mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL); + if (--f->ref_count == 0) + mlxsw_sp_vport_rif_sp_destroy(mlxsw_sp_vport, f->rif); +} + +static int mlxsw_sp_inetaddr_vport_event(struct net_device *l3_dev, + struct net_device *port_dev, + unsigned long event, u16 vid) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(port_dev); + struct mlxsw_sp_port *mlxsw_sp_vport; + + mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); + if (WARN_ON(!mlxsw_sp_vport)) + return -EINVAL; + + switch (event) { + case NETDEV_UP: + return mlxsw_sp_vport_rif_sp_join(mlxsw_sp_vport, l3_dev); + case NETDEV_DOWN: + mlxsw_sp_vport_rif_sp_leave(mlxsw_sp_vport); + break; + } + + return 0; +} + +static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev, + unsigned long event) +{ + if (netif_is_bridge_port(port_dev) || + netif_is_lag_port(port_dev) || + netif_is_ovs_port(port_dev)) + return 0; + + return mlxsw_sp_inetaddr_vport_event(port_dev, port_dev, event, 1); +} + +static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev, + struct net_device *lag_dev, + unsigned long event, u16 vid) +{ + struct net_device *port_dev; + struct list_head *iter; + int err; + + netdev_for_each_lower_dev(lag_dev, port_dev, iter) { + if (mlxsw_sp_port_dev_check(port_dev)) { + err = mlxsw_sp_inetaddr_vport_event(l3_dev, port_dev, + event, vid); + if (err) + return err; + } + } + + return 0; +} + +static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev, + unsigned long event) +{ + if (netif_is_bridge_port(lag_dev)) + return 0; + + return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1); +} + +static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev) +{ + u16 fid; + + if (is_vlan_dev(l3_dev)) + fid = vlan_dev_vlan_id(l3_dev); + else if (mlxsw_sp->master_bridge.dev == l3_dev) + fid = 1; + else + return mlxsw_sp_vfid_find(mlxsw_sp, l3_dev); + + return mlxsw_sp_fid_find(mlxsw_sp, fid); +} + +static u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp) +{ + return mlxsw_core_max_ports(mlxsw_sp->core) + 1; +} + +static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid) +{ + return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID : + MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST; +} + +static u16 mlxsw_sp_flood_table_index_get(u16 fid) +{ + return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid; +} + +static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid, + bool set) +{ + u8 router_port = mlxsw_sp_router_port(mlxsw_sp); + enum mlxsw_flood_table_type table_type; + char *sftr_pl; + u16 index; + int err; + + sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); + if (!sftr_pl) + return -ENOMEM; + + table_type = mlxsw_sp_flood_table_type_get(fid); + index = mlxsw_sp_flood_table_index_get(fid); + mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BC, index, table_type, + 1, router_port, set); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); + + kfree(sftr_pl); + return err; +} + +static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid) +{ + if (mlxsw_sp_fid_is_vfid(fid)) + return MLXSW_REG_RITR_FID_IF; + else + return MLXSW_REG_RITR_VLAN_IF; +} + +static int mlxsw_sp_rif_bridge_op(struct mlxsw_sp *mlxsw_sp, u16 vr_id, + struct net_device *l3_dev, + u16 fid, u16 rif, + bool create) +{ + enum mlxsw_reg_ritr_if_type rif_type; + char ritr_pl[MLXSW_REG_RITR_LEN]; + + rif_type = mlxsw_sp_rif_type_get(fid); + mlxsw_reg_ritr_pack(ritr_pl, create, rif_type, rif, vr_id, l3_dev->mtu, + l3_dev->dev_addr); + mlxsw_reg_ritr_fid_set(ritr_pl, rif_type, fid); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev, + struct mlxsw_sp_fid *f) +{ + u32 tb_id = l3mdev_fib_table(l3_dev); + struct mlxsw_sp_rif *rif; + struct mlxsw_sp_vr *vr; + u16 rif_index; + int err; + + rif_index = mlxsw_sp_avail_rif_get(mlxsw_sp); + if (rif_index == MLXSW_SP_INVALID_INDEX_RIF) + return -ERANGE; + + vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN); + if (IS_ERR(vr)) + return PTR_ERR(vr); + + err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true); + if (err) + goto err_port_flood_set; + + err = mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, + rif_index, true); + if (err) + goto err_rif_bridge_op; + + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true); + if (err) + goto err_rif_fdb_op; + + rif = mlxsw_sp_rif_alloc(rif_index, vr->id, l3_dev, f); + if (!rif) { + err = -ENOMEM; + goto err_rif_alloc; + } + + f->rif = rif; + mlxsw_sp->rifs[rif_index] = rif; + vr->rif_count++; + + netdev_dbg(l3_dev, "RIF=%d created\n", rif_index); + + return 0; + +err_rif_alloc: + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); +err_rif_fdb_op: + mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif_index, + false); +err_rif_bridge_op: + mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); +err_port_flood_set: + mlxsw_sp_vr_put(vr); + return err; +} + +void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_rif *rif) +{ + struct mlxsw_sp_vr *vr = &mlxsw_sp->router.vrs[rif->vr_id]; + struct net_device *l3_dev = rif->dev; + struct mlxsw_sp_fid *f = rif->f; + u16 rif_index = rif->rif_index; + + mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif); + + vr->rif_count--; + mlxsw_sp->rifs[rif_index] = NULL; + f->rif = NULL; + + kfree(rif); + + mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); + + mlxsw_sp_rif_bridge_op(mlxsw_sp, vr->id, l3_dev, f->fid, rif_index, + false); + + mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); + + mlxsw_sp_vr_put(vr); + + netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif_index); +} + +static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev, + struct net_device *br_dev, + unsigned long event) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev); + struct mlxsw_sp_fid *f; + + /* FID can either be an actual FID if the L3 device is the + * VLAN-aware bridge or a VLAN device on top. Otherwise, the + * L3 device is a VLAN-unaware bridge and we get a vFID. + */ + f = mlxsw_sp_bridge_fid_get(mlxsw_sp, l3_dev); + if (WARN_ON(!f)) + return -EINVAL; + + switch (event) { + case NETDEV_UP: + return mlxsw_sp_rif_bridge_create(mlxsw_sp, l3_dev, f); + case NETDEV_DOWN: + mlxsw_sp_rif_bridge_destroy(mlxsw_sp, f->rif); + break; + } + + return 0; +} + +static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev, + unsigned long event) +{ + struct net_device *real_dev = vlan_dev_real_dev(vlan_dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev); + u16 vid = vlan_dev_vlan_id(vlan_dev); + + if (mlxsw_sp_port_dev_check(real_dev)) + return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event, + vid); + else if (netif_is_lag_master(real_dev)) + return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event, + vid); + else if (netif_is_bridge_master(real_dev) && + mlxsw_sp->master_bridge.dev == real_dev) + return mlxsw_sp_inetaddr_bridge_event(vlan_dev, real_dev, + event); + + return 0; +} + +static int __mlxsw_sp_inetaddr_event(struct net_device *dev, + unsigned long event) +{ + if (mlxsw_sp_port_dev_check(dev)) + return mlxsw_sp_inetaddr_port_event(dev, event); + else if (netif_is_lag_master(dev)) + return mlxsw_sp_inetaddr_lag_event(dev, event); + else if (netif_is_bridge_master(dev)) + return mlxsw_sp_inetaddr_bridge_event(dev, dev, event); + else if (is_vlan_dev(dev)) + return mlxsw_sp_inetaddr_vlan_event(dev, event); + else + return 0; +} + +int mlxsw_sp_inetaddr_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct in_ifaddr *ifa = (struct in_ifaddr *) ptr; + struct net_device *dev = ifa->ifa_dev->dev; + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_rif *rif; + int err = 0; + + mlxsw_sp = mlxsw_sp_lower_get(dev); + if (!mlxsw_sp) + goto out; + + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!mlxsw_sp_rif_should_config(rif, ifa->ifa_dev, event)) + goto out; + + err = __mlxsw_sp_inetaddr_event(dev, event); +out: + return notifier_from_errno(err); +} + +static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index, + const char *mac, int mtu) +{ + char ritr_pl[MLXSW_REG_RITR_LEN]; + int err; + + mlxsw_reg_ritr_rif_pack(ritr_pl, rif_index); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); + if (err) + return err; + + mlxsw_reg_ritr_mtu_set(ritr_pl, mtu); + mlxsw_reg_ritr_if_mac_memcpy_to(ritr_pl, mac); + mlxsw_reg_ritr_op_set(ritr_pl, MLXSW_REG_RITR_RIF_CREATE); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +int mlxsw_sp_netdevice_router_port_event(struct net_device *dev) +{ + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_rif *rif; + int err; + + mlxsw_sp = mlxsw_sp_lower_get(dev); + if (!mlxsw_sp) + return 0; + + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!rif) + return 0; + + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->addr, rif->f->fid, false); + if (err) + return err; + + err = mlxsw_sp_rif_edit(mlxsw_sp, rif->rif_index, dev->dev_addr, + dev->mtu); + if (err) + goto err_rif_edit; + + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, dev->dev_addr, rif->f->fid, true); + if (err) + goto err_rif_fdb_op; + + ether_addr_copy(rif->addr, dev->dev_addr); + rif->mtu = dev->mtu; + + netdev_dbg(dev, "Updated RIF=%d\n", rif->rif_index); + + return 0; + +err_rif_fdb_op: + mlxsw_sp_rif_edit(mlxsw_sp, rif->rif_index, rif->addr, rif->mtu); +err_rif_edit: + mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->addr, rif->f->fid, true); + return err; +} + +static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev) +{ + struct mlxsw_sp_rif *rif; + + /* If netdev is already associated with a RIF, then we need to + * destroy it and create a new one with the new virtual router ID. + */ + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev); + if (rif) + __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN); + + return __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_UP); +} + +static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev) +{ + struct mlxsw_sp_rif *rif; + + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev); + if (!rif) + return; + __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN); +} + +int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, + struct netdev_notifier_changeupper_info *info) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev); + int err = 0; + + if (!mlxsw_sp) + return 0; + + switch (event) { + case NETDEV_PRECHANGEUPPER: + return 0; + case NETDEV_CHANGEUPPER: + if (info->linking) + err = mlxsw_sp_port_vrf_join(mlxsw_sp, l3_dev); + else + mlxsw_sp_port_vrf_leave(mlxsw_sp, l3_dev); + break; + } + + return err; +} + static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb) { struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb); @@ -2606,6 +3501,48 @@ static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb) mlxsw_sp_router_fib_flush(mlxsw_sp); } +static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) +{ + char rgcr_pl[MLXSW_REG_RGCR_LEN]; + u64 max_rifs; + int err; + + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS)) + return -EIO; + + max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); + mlxsw_sp->rifs = kcalloc(max_rifs, sizeof(struct mlxsw_sp_rif *), + GFP_KERNEL); + if (!mlxsw_sp->rifs) + return -ENOMEM; + + mlxsw_reg_rgcr_pack(rgcr_pl, true); + mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); + if (err) + goto err_rgcr_fail; + + return 0; + +err_rgcr_fail: + kfree(mlxsw_sp->rifs); + return err; +} + +static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) +{ + char rgcr_pl[MLXSW_REG_RGCR_LEN]; + int i; + + mlxsw_reg_rgcr_pack(rgcr_pl, false); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); + + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) + WARN_ON_ONCE(mlxsw_sp->rifs[i]); + + kfree(mlxsw_sp->rifs); +} + int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) { int err; @@ -2625,7 +3562,10 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) if (err) goto err_nexthop_group_ht_init; - mlxsw_sp_lpm_init(mlxsw_sp); + err = mlxsw_sp_lpm_init(mlxsw_sp); + if (err) + goto err_lpm_init; + err = mlxsw_sp_vrs_init(mlxsw_sp); if (err) goto err_vrs_init; @@ -2647,6 +3587,8 @@ err_register_fib_notifier: err_neigh_init: mlxsw_sp_vrs_fini(mlxsw_sp); err_vrs_init: + mlxsw_sp_lpm_fini(mlxsw_sp); +err_lpm_init: rhashtable_destroy(&mlxsw_sp->router.nexthop_group_ht); err_nexthop_group_ht_init: rhashtable_destroy(&mlxsw_sp->router.nexthop_ht); @@ -2660,6 +3602,7 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) unregister_fib_notifier(&mlxsw_sp->fib_nb); mlxsw_sp_neigh_fini(mlxsw_sp); mlxsw_sp_vrs_fini(mlxsw_sp); + mlxsw_sp_lpm_fini(mlxsw_sp); rhashtable_destroy(&mlxsw_sp->router.nexthop_group_ht); rhashtable_destroy(&mlxsw_sp->router.nexthop_ht); __mlxsw_sp_router_fini(mlxsw_sp); |