@@ -154,7 +154,8 @@ mlx5_core-$(CONFIG_MLX5_HW_STEERING) += steering/hws/cmd.o \
steering/hws/vport.o \
steering/hws/bwc_complex.o \
steering/hws/fs_hws_pools.o \
- steering/hws/fs_hws.o
+ steering/hws/fs_hws.o \
+ steering/hws/action_ste_pool.o
#
# SF device
new file mode 100644
@@ -0,0 +1,387 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#include "internal.h"
+
+static const char *
+hws_pool_opt_to_str(enum mlx5hws_pool_optimize opt)
+{
+ switch (opt) {
+ case MLX5HWS_POOL_OPTIMIZE_NONE:
+ return "rx-and-tx";
+ case MLX5HWS_POOL_OPTIMIZE_ORIG:
+ return "rx-only";
+ case MLX5HWS_POOL_OPTIMIZE_MIRROR:
+ return "tx-only";
+ default:
+ return "unknown";
+ }
+}
+
+static int
+hws_action_ste_table_create_pool(struct mlx5hws_context *ctx,
+ struct mlx5hws_action_ste_table *action_tbl,
+ enum mlx5hws_pool_optimize opt, size_t log_sz)
+{
+ struct mlx5hws_pool_attr pool_attr = { 0 };
+
+ pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
+ pool_attr.table_type = MLX5HWS_TABLE_TYPE_FDB;
+ pool_attr.flags = MLX5HWS_POOL_FLAG_BUDDY;
+ pool_attr.opt_type = opt;
+ pool_attr.alloc_log_sz = log_sz;
+
+ action_tbl->pool = mlx5hws_pool_create(ctx, &pool_attr);
+ if (!action_tbl->pool) {
+ mlx5hws_err(ctx, "Failed to allocate STE pool\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int hws_action_ste_table_create_single_rtc(
+ struct mlx5hws_context *ctx,
+ struct mlx5hws_action_ste_table *action_tbl,
+ enum mlx5hws_pool_optimize opt, size_t log_sz, bool tx)
+{
+ struct mlx5hws_cmd_rtc_create_attr rtc_attr = { 0 };
+ u32 *rtc_id;
+
+ rtc_attr.log_depth = 0;
+ rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
+ /* Action STEs use the default always hit definer. */
+ rtc_attr.match_definer_0 = ctx->caps->trivial_match_definer;
+ rtc_attr.is_frst_jumbo = false;
+ rtc_attr.miss_ft_id = 0;
+ rtc_attr.pd = ctx->pd_num;
+ rtc_attr.reparse_mode = mlx5hws_context_get_reparse_mode(ctx);
+
+ if (tx) {
+ rtc_attr.table_type = FS_FT_FDB_TX;
+ rtc_attr.ste_base =
+ mlx5hws_pool_get_base_mirror_id(action_tbl->pool);
+ rtc_attr.stc_base =
+ mlx5hws_pool_get_base_mirror_id(ctx->stc_pool);
+ rtc_attr.log_size =
+ opt == MLX5HWS_POOL_OPTIMIZE_ORIG ? 0 : log_sz;
+ rtc_id = &action_tbl->rtc_1_id;
+ } else {
+ rtc_attr.table_type = FS_FT_FDB_RX;
+ rtc_attr.ste_base = mlx5hws_pool_get_base_id(action_tbl->pool);
+ rtc_attr.stc_base = mlx5hws_pool_get_base_id(ctx->stc_pool);
+ rtc_attr.log_size =
+ opt == MLX5HWS_POOL_OPTIMIZE_MIRROR ? 0 : log_sz;
+ rtc_id = &action_tbl->rtc_0_id;
+ }
+
+ return mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_id);
+}
+
+static int
+hws_action_ste_table_create_rtcs(struct mlx5hws_context *ctx,
+ struct mlx5hws_action_ste_table *action_tbl,
+ enum mlx5hws_pool_optimize opt, size_t log_sz)
+{
+ int err;
+
+ err = hws_action_ste_table_create_single_rtc(ctx, action_tbl, opt,
+ log_sz, false);
+ if (err)
+ return err;
+
+ err = hws_action_ste_table_create_single_rtc(ctx, action_tbl, opt,
+ log_sz, true);
+ if (err) {
+ mlx5hws_cmd_rtc_destroy(ctx->mdev, action_tbl->rtc_0_id);
+ return err;
+ }
+
+ return 0;
+}
+
+static void
+hws_action_ste_table_destroy_rtcs(struct mlx5hws_action_ste_table *action_tbl)
+{
+ mlx5hws_cmd_rtc_destroy(action_tbl->pool->ctx->mdev,
+ action_tbl->rtc_1_id);
+ mlx5hws_cmd_rtc_destroy(action_tbl->pool->ctx->mdev,
+ action_tbl->rtc_0_id);
+}
+
+static int
+hws_action_ste_table_create_stc(struct mlx5hws_context *ctx,
+ struct mlx5hws_action_ste_table *action_tbl)
+{
+ struct mlx5hws_cmd_stc_modify_attr stc_attr = { 0 };
+
+ stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+ stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE;
+ stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
+ stc_attr.ste_table.ste_pool = action_tbl->pool;
+ stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer;
+
+ return mlx5hws_action_alloc_single_stc(ctx, &stc_attr,
+ MLX5HWS_TABLE_TYPE_FDB,
+ &action_tbl->stc);
+}
+
+static struct mlx5hws_action_ste_table *
+hws_action_ste_table_alloc(struct mlx5hws_action_ste_pool_element *parent_elem)
+{
+ enum mlx5hws_pool_optimize opt = parent_elem->opt;
+ struct mlx5hws_context *ctx = parent_elem->ctx;
+ struct mlx5hws_action_ste_table *action_tbl;
+ size_t log_sz;
+ int err;
+
+ log_sz = min(parent_elem->log_sz ?
+ parent_elem->log_sz +
+ MLX5HWS_ACTION_STE_TABLE_STEP_LOG_SZ :
+ MLX5HWS_ACTION_STE_TABLE_INIT_LOG_SZ,
+ MLX5HWS_ACTION_STE_TABLE_MAX_LOG_SZ);
+
+ action_tbl = kzalloc(sizeof(*action_tbl), GFP_KERNEL);
+ if (!action_tbl)
+ return ERR_PTR(-ENOMEM);
+
+ err = hws_action_ste_table_create_pool(ctx, action_tbl, opt, log_sz);
+ if (err)
+ goto free_tbl;
+
+ err = hws_action_ste_table_create_rtcs(ctx, action_tbl, opt, log_sz);
+ if (err)
+ goto destroy_pool;
+
+ err = hws_action_ste_table_create_stc(ctx, action_tbl);
+ if (err)
+ goto destroy_rtcs;
+
+ action_tbl->parent_elem = parent_elem;
+ INIT_LIST_HEAD(&action_tbl->list_node);
+ list_add(&action_tbl->list_node, &parent_elem->available);
+ parent_elem->log_sz = log_sz;
+
+ mlx5hws_dbg(ctx,
+ "Allocated %s action STE table log_sz %zu; STEs (%d, %d); RTCs (%d, %d); STC %d\n",
+ hws_pool_opt_to_str(opt), log_sz,
+ mlx5hws_pool_get_base_id(action_tbl->pool),
+ mlx5hws_pool_get_base_mirror_id(action_tbl->pool),
+ action_tbl->rtc_0_id, action_tbl->rtc_1_id,
+ action_tbl->stc.offset);
+
+ return action_tbl;
+
+destroy_rtcs:
+ hws_action_ste_table_destroy_rtcs(action_tbl);
+destroy_pool:
+ mlx5hws_pool_destroy(action_tbl->pool);
+free_tbl:
+ kfree(action_tbl);
+
+ return ERR_PTR(err);
+}
+
+static void
+hws_action_ste_table_destroy(struct mlx5hws_action_ste_table *action_tbl)
+{
+ struct mlx5hws_context *ctx = action_tbl->parent_elem->ctx;
+
+ mlx5hws_dbg(ctx,
+ "Destroying %s action STE table: STEs (%d, %d); RTCs (%d, %d); STC %d\n",
+ hws_pool_opt_to_str(action_tbl->parent_elem->opt),
+ mlx5hws_pool_get_base_id(action_tbl->pool),
+ mlx5hws_pool_get_base_mirror_id(action_tbl->pool),
+ action_tbl->rtc_0_id, action_tbl->rtc_1_id,
+ action_tbl->stc.offset);
+
+ mlx5hws_action_free_single_stc(ctx, MLX5HWS_TABLE_TYPE_FDB,
+ &action_tbl->stc);
+ hws_action_ste_table_destroy_rtcs(action_tbl);
+ mlx5hws_pool_destroy(action_tbl->pool);
+
+ list_del(&action_tbl->list_node);
+ kfree(action_tbl);
+}
+
+static int
+hws_action_ste_pool_element_init(struct mlx5hws_context *ctx,
+ struct mlx5hws_action_ste_pool_element *elem,
+ enum mlx5hws_pool_optimize opt)
+{
+ elem->ctx = ctx;
+ elem->opt = opt;
+ INIT_LIST_HEAD(&elem->available);
+ INIT_LIST_HEAD(&elem->full);
+
+ return 0;
+}
+
+static void hws_action_ste_pool_element_destroy(
+ struct mlx5hws_action_ste_pool_element *elem)
+{
+ struct mlx5hws_action_ste_table *action_tbl, *p;
+
+ /* This should be empty, but attempt to free its elements anyway. */
+ list_for_each_entry_safe(action_tbl, p, &elem->full, list_node)
+ hws_action_ste_table_destroy(action_tbl);
+
+ list_for_each_entry_safe(action_tbl, p, &elem->available, list_node)
+ hws_action_ste_table_destroy(action_tbl);
+}
+
+static int hws_action_ste_pool_init(struct mlx5hws_context *ctx,
+ struct mlx5hws_action_ste_pool *pool)
+{
+ enum mlx5hws_pool_optimize opt;
+ int err;
+
+ /* Rules which are added for both RX and TX must use the same action STE
+ * indices for both. If we were to use a single table, then RX-only and
+ * TX-only rules would waste the unused entries. Thus, we use separate
+ * table sets for the three cases.
+ */
+ for (opt = MLX5HWS_POOL_OPTIMIZE_NONE; opt < MLX5HWS_POOL_OPTIMIZE_MAX;
+ opt++) {
+ err = hws_action_ste_pool_element_init(ctx, &pool->elems[opt],
+ opt);
+ if (err)
+ goto destroy_elems;
+ }
+
+ return 0;
+
+destroy_elems:
+ while (opt-- > MLX5HWS_POOL_OPTIMIZE_NONE)
+ hws_action_ste_pool_element_destroy(&pool->elems[opt]);
+
+ return err;
+}
+
+static void hws_action_ste_pool_destroy(struct mlx5hws_action_ste_pool *pool)
+{
+ int opt;
+
+ for (opt = MLX5HWS_POOL_OPTIMIZE_MAX - 1;
+ opt >= MLX5HWS_POOL_OPTIMIZE_NONE; opt--)
+ hws_action_ste_pool_element_destroy(&pool->elems[opt]);
+}
+
+int mlx5hws_action_ste_pool_init(struct mlx5hws_context *ctx)
+{
+ struct mlx5hws_action_ste_pool *pool;
+ size_t queues = ctx->queues;
+ int i, err;
+
+ pool = kcalloc(queues, sizeof(*pool), GFP_KERNEL);
+ if (!pool)
+ return -ENOMEM;
+
+ for (i = 0; i < queues; i++) {
+ err = hws_action_ste_pool_init(ctx, &pool[i]);
+ if (err)
+ goto free_pool;
+ }
+
+ ctx->action_ste_pool = pool;
+
+ return 0;
+
+free_pool:
+ while (i--)
+ hws_action_ste_pool_destroy(&pool[i]);
+ kfree(pool);
+
+ return err;
+}
+
+void mlx5hws_action_ste_pool_uninit(struct mlx5hws_context *ctx)
+{
+ size_t queues = ctx->queues;
+ int i;
+
+ for (i = 0; i < queues; i++)
+ hws_action_ste_pool_destroy(&ctx->action_ste_pool[i]);
+
+ kfree(ctx->action_ste_pool);
+}
+
+static struct mlx5hws_action_ste_pool_element *
+hws_action_ste_choose_elem(struct mlx5hws_action_ste_pool *pool,
+ bool skip_rx, bool skip_tx)
+{
+ if (skip_rx)
+ return &pool->elems[MLX5HWS_POOL_OPTIMIZE_MIRROR];
+
+ if (skip_tx)
+ return &pool->elems[MLX5HWS_POOL_OPTIMIZE_ORIG];
+
+ return &pool->elems[MLX5HWS_POOL_OPTIMIZE_NONE];
+}
+
+static int
+hws_action_ste_table_chunk_alloc(struct mlx5hws_action_ste_table *action_tbl,
+ struct mlx5hws_action_ste_chunk *chunk)
+{
+ int err;
+
+ err = mlx5hws_pool_chunk_alloc(action_tbl->pool, &chunk->ste);
+ if (err)
+ return err;
+
+ chunk->action_tbl = action_tbl;
+
+ return 0;
+}
+
+int mlx5hws_action_ste_chunk_alloc(struct mlx5hws_action_ste_pool *pool,
+ bool skip_rx, bool skip_tx,
+ struct mlx5hws_action_ste_chunk *chunk)
+{
+ struct mlx5hws_action_ste_pool_element *elem;
+ struct mlx5hws_action_ste_table *action_tbl;
+ bool found;
+ int err;
+
+ if (skip_rx && skip_tx)
+ return -EINVAL;
+
+ elem = hws_action_ste_choose_elem(pool, skip_rx, skip_tx);
+
+ mlx5hws_dbg(elem->ctx,
+ "Allocating action STEs skip_rx %d skip_tx %d order %d\n",
+ skip_rx, skip_tx, chunk->ste.order);
+
+ found = false;
+ list_for_each_entry(action_tbl, &elem->available, list_node) {
+ if (!hws_action_ste_table_chunk_alloc(action_tbl, chunk)) {
+ found = true;
+ break;
+ }
+ }
+
+ if (!found) {
+ action_tbl = hws_action_ste_table_alloc(elem);
+ if (IS_ERR(action_tbl))
+ return PTR_ERR(action_tbl);
+
+ err = hws_action_ste_table_chunk_alloc(action_tbl, chunk);
+ if (err)
+ return err;
+ }
+
+ if (mlx5hws_pool_empty(action_tbl->pool))
+ list_move(&action_tbl->list_node, &elem->full);
+
+ return 0;
+}
+
+void mlx5hws_action_ste_chunk_free(struct mlx5hws_action_ste_chunk *chunk)
+{
+ mlx5hws_dbg(chunk->action_tbl->pool->ctx,
+ "Freeing action STEs offset %d order %d\n",
+ chunk->ste.offset, chunk->ste.order);
+ mlx5hws_pool_chunk_free(chunk->action_tbl->pool, &chunk->ste);
+ list_move(&chunk->action_tbl->list_node,
+ &chunk->action_tbl->parent_elem->available);
+}
new file mode 100644
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */
+
+#ifndef ACTION_STE_POOL_H_
+#define ACTION_STE_POOL_H_
+
+#define MLX5HWS_ACTION_STE_TABLE_INIT_LOG_SZ 10
+#define MLX5HWS_ACTION_STE_TABLE_STEP_LOG_SZ 1
+#define MLX5HWS_ACTION_STE_TABLE_MAX_LOG_SZ 20
+
+struct mlx5hws_action_ste_pool_element;
+
+struct mlx5hws_action_ste_table {
+ struct mlx5hws_action_ste_pool_element *parent_elem;
+ /* Wraps the RTC and STE range for this given action. */
+ struct mlx5hws_pool *pool;
+ /* Match STEs use this STC to jump to this pool's RTC. */
+ struct mlx5hws_pool_chunk stc;
+ u32 rtc_0_id;
+ u32 rtc_1_id;
+ struct list_head list_node;
+};
+
+struct mlx5hws_action_ste_pool_element {
+ struct mlx5hws_context *ctx;
+ size_t log_sz; /* Size of the largest table so far. */
+ enum mlx5hws_pool_optimize opt;
+ struct list_head available;
+ struct list_head full;
+};
+
+/* Central repository of action STEs. The context contains one of these pools
+ * per queue.
+ */
+struct mlx5hws_action_ste_pool {
+ struct mlx5hws_action_ste_pool_element elems[MLX5HWS_POOL_OPTIMIZE_MAX];
+};
+
+/* A chunk of STEs and the table it was allocated from. Used by rules. */
+struct mlx5hws_action_ste_chunk {
+ struct mlx5hws_action_ste_table *action_tbl;
+ struct mlx5hws_pool_chunk ste;
+};
+
+int mlx5hws_action_ste_pool_init(struct mlx5hws_context *ctx);
+
+void mlx5hws_action_ste_pool_uninit(struct mlx5hws_context *ctx);
+
+/* Callers are expected to fill chunk->ste.order. On success, this function
+ * populates chunk->tbl and chunk->ste.offset.
+ */
+int mlx5hws_action_ste_chunk_alloc(struct mlx5hws_action_ste_pool *pool,
+ bool skip_rx, bool skip_tx,
+ struct mlx5hws_action_ste_chunk *chunk);
+
+void mlx5hws_action_ste_chunk_free(struct mlx5hws_action_ste_chunk *chunk);
+
+#endif /* ACTION_STE_POOL_H_ */
@@ -158,10 +158,16 @@ static int hws_context_init_hws(struct mlx5hws_context *ctx,
if (ret)
goto pools_uninit;
+ ret = mlx5hws_action_ste_pool_init(ctx);
+ if (ret)
+ goto close_queues;
+
INIT_LIST_HEAD(&ctx->tbl_list);
return 0;
+close_queues:
+ mlx5hws_send_queues_close(ctx);
pools_uninit:
hws_context_pools_uninit(ctx);
uninit_pd:
@@ -174,6 +180,7 @@ static void hws_context_uninit_hws(struct mlx5hws_context *ctx)
if (!(ctx->flags & MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT))
return;
+ mlx5hws_action_ste_pool_uninit(ctx);
mlx5hws_send_queues_close(ctx);
hws_context_pools_uninit(ctx);
hws_context_uninit_pd(ctx);
@@ -39,6 +39,7 @@ struct mlx5hws_context {
struct mlx5hws_cmd_query_caps *caps;
u32 pd_num;
struct mlx5hws_pool *stc_pool;
+ struct mlx5hws_action_ste_pool *action_ste_pool; /* One per queue */
struct mlx5hws_context_common_res common_res;
struct mlx5hws_pattern_cache *pattern_cache;
struct mlx5hws_definer_cache *definer_cache;
@@ -17,6 +17,7 @@
#include "context.h"
#include "table.h"
#include "send.h"
+#include "action_ste_pool.h"
#include "rule.h"
#include "cmd.h"
#include "action.h"
@@ -33,6 +33,7 @@ enum mlx5hws_pool_optimize {
MLX5HWS_POOL_OPTIMIZE_NONE = 0x0,
MLX5HWS_POOL_OPTIMIZE_ORIG = 0x1,
MLX5HWS_POOL_OPTIMIZE_MIRROR = 0x2,
+ MLX5HWS_POOL_OPTIMIZE_MAX = 0x3,
};
struct mlx5hws_pool_attr {