diff options
Diffstat (limited to 'drivers/net/ethernet/google')
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve.h | 105 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_adminq.c | 84 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_adminq.h | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c | 45 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_ethtool.c | 100 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_main.c | 463 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_rx.c | 30 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_rx_dqo.c | 110 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_tx.c | 87 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_tx_dqo.c | 48 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_utils.c | 6 |
11 files changed, 619 insertions, 460 deletions
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index dd92949bb214..2fab38c8ee78 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -59,6 +59,8 @@ #define GVE_MAX_RX_BUFFER_SIZE 4096 +#define GVE_XDP_RX_BUFFER_SIZE_DQO 4096 + #define GVE_DEFAULT_RX_BUFFER_OFFSET 2048 #define GVE_PAGE_POOL_SIZE_MULTIPLIER 4 @@ -68,6 +70,9 @@ #define GVE_FLOW_RULE_IDS_CACHE_SIZE \ (GVE_ADMINQ_BUFFER_SIZE / sizeof(((struct gve_adminq_queried_flow_rule *)0)->location)) +#define GVE_RSS_KEY_SIZE 40 +#define GVE_RSS_INDIR_SIZE 128 + #define GVE_XDP_ACTIONS 5 #define GVE_GQ_TX_MIN_PKT_DESC_BYTES 182 @@ -102,7 +107,13 @@ struct gve_rx_desc_queue { /* The page info for a single slot in the RX data queue */ struct gve_rx_slot_page_info { - struct page *page; + /* netmem is used for DQO RDA mode + * page is used in all other modes + */ + union { + struct page *page; + netmem_ref netmem; + }; void *page_address; u32 page_offset; /* offset to write to in page */ unsigned int buf_size; @@ -218,6 +229,11 @@ struct gve_rx_cnts { /* Contains datapath state used to represent an RX queue. */ struct gve_rx_ring { struct gve_priv *gve; + + u16 packet_buffer_size; /* Size of buffer posted to NIC */ + u16 packet_buffer_truesize; /* Total size of RX buffer */ + u16 rx_headroom; + union { /* GQI fields */ struct { @@ -226,7 +242,6 @@ struct gve_rx_ring { /* threshold for posting new buffs and descs */ u32 db_threshold; - u16 packet_buffer_size; u32 qpl_copy_pool_mask; u32 qpl_copy_pool_head; @@ -604,8 +619,6 @@ struct gve_tx_ring { dma_addr_t complq_bus_dqo; /* dma address of the dqo.compl_ring */ struct u64_stats_sync statss; /* sync stats for 32bit archs */ struct xsk_buff_pool *xsk_pool; - u32 xdp_xsk_wakeup; - u32 xdp_xsk_done; u64 xdp_xsk_sent; u64 xdp_xmit; u64 xdp_xmit_errors; @@ -624,10 +637,18 @@ struct gve_notify_block { u32 irq; }; -/* Tracks allowed and current queue settings */ -struct gve_queue_config { +/* Tracks allowed and current rx queue settings */ +struct gve_rx_queue_config { u16 max_queues; - u16 num_queues; /* current */ + u16 num_queues; + u16 packet_buffer_size; +}; + +/* Tracks allowed and current tx queue settings */ +struct gve_tx_queue_config { + u16 max_queues; + u16 num_queues; /* number of TX queues, excluding XDP queues */ + u16 num_xdp_queues; }; /* Tracks the available and used qpl IDs */ @@ -651,11 +672,11 @@ struct gve_ptype_lut { /* Parameters for allocating resources for tx queues */ struct gve_tx_alloc_rings_cfg { - struct gve_queue_config *qcfg; + struct gve_tx_queue_config *qcfg; + + u16 num_xdp_rings; u16 ring_size; - u16 start_idx; - u16 num_rings; bool raw_addressing; /* Allocated resources are returned here */ @@ -665,13 +686,15 @@ struct gve_tx_alloc_rings_cfg { /* Parameters for allocating resources for rx queues */ struct gve_rx_alloc_rings_cfg { /* tx config is also needed to determine QPL ids */ - struct gve_queue_config *qcfg; - struct gve_queue_config *qcfg_tx; + struct gve_rx_queue_config *qcfg_rx; + struct gve_tx_queue_config *qcfg_tx; u16 ring_size; u16 packet_buffer_size; bool raw_addressing; bool enable_header_split; + bool reset_rss; + bool xdp; /* Allocated resources are returned here */ struct gve_rx_ring *rx; @@ -722,6 +745,11 @@ struct gve_flow_rules_cache { u32 rule_ids_cache_num; }; +struct gve_rss_config { + u8 *hash_key; + u32 *hash_lut; +}; + struct gve_priv { struct net_device *dev; struct gve_tx_ring *tx; /* array of tx_cfg.num_queues */ @@ -751,9 +779,8 @@ struct gve_priv { u32 rx_copybreak; /* copy packets smaller than this */ u16 default_num_queues; /* default num queues to set up */ - u16 num_xdp_queues; - struct gve_queue_config tx_cfg; - struct gve_queue_config rx_cfg; + struct gve_tx_queue_config tx_cfg; + struct gve_rx_queue_config rx_cfg; u32 num_ntfy_blks; /* spilt between TX and RX so must be even */ struct gve_registers __iomem *reg_bar0; /* see gve_register.h */ @@ -823,7 +850,6 @@ struct gve_priv { struct gve_ptype_lut *ptype_lut_dqo; /* Must be a power of two. */ - u16 data_buffer_size_dqo; u16 max_rx_buffer_size; /* device limit */ enum gve_queue_format queue_format; @@ -842,6 +868,8 @@ struct gve_priv { u16 rss_key_size; u16 rss_lut_size; + bool cache_rss_config; + struct gve_rss_config rss_config; }; enum gve_service_task_flags_bit { @@ -1024,27 +1052,16 @@ static inline bool gve_is_qpl(struct gve_priv *priv) } /* Returns the number of tx queue page lists */ -static inline u32 gve_num_tx_qpls(const struct gve_queue_config *tx_cfg, - int num_xdp_queues, +static inline u32 gve_num_tx_qpls(const struct gve_tx_queue_config *tx_cfg, bool is_qpl) { if (!is_qpl) return 0; - return tx_cfg->num_queues + num_xdp_queues; -} - -/* Returns the number of XDP tx queue page lists - */ -static inline u32 gve_num_xdp_qpls(struct gve_priv *priv) -{ - if (priv->queue_format != GVE_GQI_QPL_FORMAT) - return 0; - - return priv->num_xdp_queues; + return tx_cfg->num_queues + tx_cfg->num_xdp_queues; } /* Returns the number of rx queue page lists */ -static inline u32 gve_num_rx_qpls(const struct gve_queue_config *rx_cfg, +static inline u32 gve_num_rx_qpls(const struct gve_rx_queue_config *rx_cfg, bool is_qpl) { if (!is_qpl) @@ -1062,7 +1079,8 @@ static inline u32 gve_rx_qpl_id(struct gve_priv *priv, int rx_qid) return priv->tx_cfg.max_queues + rx_qid; } -static inline u32 gve_get_rx_qpl_id(const struct gve_queue_config *tx_cfg, int rx_qid) +static inline u32 gve_get_rx_qpl_id(const struct gve_tx_queue_config *tx_cfg, + int rx_qid) { return tx_cfg->max_queues + rx_qid; } @@ -1072,7 +1090,7 @@ static inline u32 gve_tx_start_qpl_id(struct gve_priv *priv) return gve_tx_qpl_id(priv, 0); } -static inline u32 gve_rx_start_qpl_id(const struct gve_queue_config *tx_cfg) +static inline u32 gve_rx_start_qpl_id(const struct gve_tx_queue_config *tx_cfg) { return gve_get_rx_qpl_id(tx_cfg, 0); } @@ -1103,7 +1121,7 @@ static inline bool gve_is_gqi(struct gve_priv *priv) static inline u32 gve_num_tx_queues(struct gve_priv *priv) { - return priv->tx_cfg.num_queues + priv->num_xdp_queues; + return priv->tx_cfg.num_queues + priv->tx_cfg.num_xdp_queues; } static inline u32 gve_xdp_tx_queue_id(struct gve_priv *priv, u32 queue_id) @@ -1116,6 +1134,16 @@ static inline u32 gve_xdp_tx_start_queue_id(struct gve_priv *priv) return gve_xdp_tx_queue_id(priv, 0); } +static inline bool gve_supports_xdp_xmit(struct gve_priv *priv) +{ + switch (priv->queue_format) { + case GVE_GQI_QPL_FORMAT: + return true; + default: + return false; + } +} + /* gqi napi handler defined in gve_main.c */ int gve_napi_poll(struct napi_struct *napi, int budget); @@ -1140,6 +1168,7 @@ int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx, void gve_xdp_tx_flush(struct gve_priv *priv, u32 xdp_qid); bool gve_tx_poll(struct gve_notify_block *block, int budget); bool gve_xdp_poll(struct gve_notify_block *block, int budget); +int gve_xsk_tx_poll(struct gve_notify_block *block, int budget); int gve_tx_alloc_rings_gqi(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *cfg); void gve_tx_free_rings_gqi(struct gve_priv *priv, @@ -1196,7 +1225,8 @@ void gve_free_buffer(struct gve_rx_ring *rx, struct gve_rx_buf_state_dqo *buf_state); int gve_alloc_buffer(struct gve_rx_ring *rx, struct gve_rx_desc_dqo *desc); struct page_pool *gve_rx_create_page_pool(struct gve_priv *priv, - struct gve_rx_ring *rx); + struct gve_rx_ring *rx, + bool xdp); /* Reset */ void gve_schedule_reset(struct gve_priv *priv); @@ -1208,14 +1238,17 @@ int gve_adjust_config(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *tx_alloc_cfg, struct gve_rx_alloc_rings_cfg *rx_alloc_cfg); int gve_adjust_queues(struct gve_priv *priv, - struct gve_queue_config new_rx_config, - struct gve_queue_config new_tx_config); + struct gve_rx_queue_config new_rx_config, + struct gve_tx_queue_config new_tx_config, + bool reset_rss); /* flow steering rule */ int gve_get_flow_rule_entry(struct gve_priv *priv, struct ethtool_rxnfc *cmd); int gve_get_flow_rule_ids(struct gve_priv *priv, struct ethtool_rxnfc *cmd, u32 *rule_locs); int gve_add_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd); int gve_del_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd); int gve_flow_rules_reset(struct gve_priv *priv); +/* RSS config */ +int gve_init_rss_config(struct gve_priv *priv, u16 num_queues); /* report stats handling */ void gve_handle_report_stats(struct gve_priv *priv); /* exported by ethtool.c */ diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index 060e0e674938..3e8fc33cc11f 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -731,6 +731,7 @@ static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv, .ntfy_id = cpu_to_be32(rx->ntfy_id), .queue_resources_addr = cpu_to_be64(rx->q_resources_bus), .rx_ring_size = cpu_to_be16(priv->rx_desc_cnt), + .packet_buffer_size = cpu_to_be16(rx->packet_buffer_size), }; if (gve_is_gqi(priv)) { @@ -743,7 +744,6 @@ static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv, cpu_to_be64(rx->data.data_bus); cmd->create_rx_queue.index = cpu_to_be32(queue_index); cmd->create_rx_queue.queue_page_list_id = cpu_to_be32(qpl_id); - cmd->create_rx_queue.packet_buffer_size = cpu_to_be16(rx->packet_buffer_size); } else { u32 qpl_id = 0; @@ -756,8 +756,6 @@ static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv, cpu_to_be64(rx->dqo.complq.bus); cmd->create_rx_queue.rx_data_ring_addr = cpu_to_be64(rx->dqo.bufq.bus); - cmd->create_rx_queue.packet_buffer_size = - cpu_to_be16(priv->data_buffer_size_dqo); cmd->create_rx_queue.rx_buff_ring_size = cpu_to_be16(priv->rx_desc_cnt); cmd->create_rx_queue.enable_rsc = @@ -885,6 +883,15 @@ static void gve_set_default_desc_cnt(struct gve_priv *priv, priv->min_rx_desc_cnt = priv->rx_desc_cnt; } +static void gve_set_default_rss_sizes(struct gve_priv *priv) +{ + if (!gve_is_gqi(priv)) { + priv->rss_key_size = GVE_RSS_KEY_SIZE; + priv->rss_lut_size = GVE_RSS_INDIR_SIZE; + priv->cache_rss_config = true; + } +} + static void gve_enable_supported_features(struct gve_priv *priv, u32 supported_features_mask, const struct gve_device_option_jumbo_frames @@ -968,6 +975,10 @@ static void gve_enable_supported_features(struct gve_priv *priv, be16_to_cpu(dev_op_rss_config->hash_key_size); priv->rss_lut_size = be16_to_cpu(dev_op_rss_config->hash_lut_size); + priv->cache_rss_config = false; + dev_dbg(&priv->pdev->dev, + "RSS device option enabled with key size of %u, lut size of %u.\n", + priv->rss_key_size, priv->rss_lut_size); } } @@ -1052,6 +1063,8 @@ int gve_adminq_describe_device(struct gve_priv *priv) /* set default descriptor counts */ gve_set_default_desc_cnt(priv, descriptor); + gve_set_default_rss_sizes(priv); + /* DQO supports LRO. */ if (!gve_is_gqi(priv)) priv->dev->hw_features |= NETIF_F_LRO; @@ -1128,20 +1141,6 @@ int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id) return gve_adminq_execute_cmd(priv, &cmd); } -int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu) -{ - union gve_adminq_command cmd; - - memset(&cmd, 0, sizeof(cmd)); - cmd.opcode = cpu_to_be32(GVE_ADMINQ_SET_DRIVER_PARAMETER); - cmd.set_driver_param = (struct gve_adminq_set_driver_parameter) { - .parameter_type = cpu_to_be32(GVE_SET_PARAM_MTU), - .parameter_value = cpu_to_be64(mtu), - }; - - return gve_adminq_execute_cmd(priv, &cmd); -} - int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len, dma_addr_t stats_report_addr, u64 interval) { @@ -1290,8 +1289,9 @@ int gve_adminq_reset_flow_rules(struct gve_priv *priv) int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh) { + const u32 *hash_lut_to_config = NULL; + const u8 *hash_key_to_config = NULL; dma_addr_t lut_bus = 0, key_bus = 0; - u16 key_size = 0, lut_size = 0; union gve_adminq_command cmd; __be32 *lut = NULL; u8 hash_alg = 0; @@ -1301,7 +1301,7 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r switch (rxfh->hfunc) { case ETH_RSS_HASH_NO_CHANGE: - break; + fallthrough; case ETH_RSS_HASH_TOP: hash_alg = ETH_RSS_HASH_TOP; break; @@ -1310,27 +1310,46 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r } if (rxfh->indir) { - lut_size = priv->rss_lut_size; + if (rxfh->indir_size != priv->rss_lut_size) + return -EINVAL; + + hash_lut_to_config = rxfh->indir; + } else if (priv->cache_rss_config) { + hash_lut_to_config = priv->rss_config.hash_lut; + } + + if (hash_lut_to_config) { lut = dma_alloc_coherent(&priv->pdev->dev, - lut_size * sizeof(*lut), + priv->rss_lut_size * sizeof(*lut), &lut_bus, GFP_KERNEL); if (!lut) return -ENOMEM; for (i = 0; i < priv->rss_lut_size; i++) - lut[i] = cpu_to_be32(rxfh->indir[i]); + lut[i] = cpu_to_be32(hash_lut_to_config[i]); } if (rxfh->key) { - key_size = priv->rss_key_size; + if (rxfh->key_size != priv->rss_key_size) { + err = -EINVAL; + goto out; + } + + hash_key_to_config = rxfh->key; + } else if (priv->cache_rss_config) { + hash_key_to_config = priv->rss_config.hash_key; + } + + if (hash_key_to_config) { key = dma_alloc_coherent(&priv->pdev->dev, - key_size, &key_bus, GFP_KERNEL); + priv->rss_key_size, + &key_bus, GFP_KERNEL); if (!key) { err = -ENOMEM; goto out; } - memcpy(key, rxfh->key, key_size); + memcpy(key, hash_key_to_config, priv->rss_key_size); } /* Zero-valued fields in the cmd.configure_rss instruct the device to @@ -1344,8 +1363,10 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r BIT(GVE_RSS_HASH_TCPV6) | BIT(GVE_RSS_HASH_UDPV6)), .hash_alg = hash_alg, - .hash_key_size = cpu_to_be16(key_size), - .hash_lut_size = cpu_to_be16(lut_size), + .hash_key_size = + cpu_to_be16((key_bus) ? priv->rss_key_size : 0), + .hash_lut_size = + cpu_to_be16((lut_bus) ? priv->rss_lut_size : 0), .hash_key_addr = cpu_to_be64(key_bus), .hash_lut_addr = cpu_to_be64(lut_bus), }; @@ -1355,11 +1376,11 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r out: if (lut) dma_free_coherent(&priv->pdev->dev, - lut_size * sizeof(*lut), + priv->rss_lut_size * sizeof(*lut), lut, lut_bus); if (key) dma_free_coherent(&priv->pdev->dev, - key_size, key, key_bus); + priv->rss_key_size, key, key_bus); return err; } @@ -1463,12 +1484,15 @@ static int gve_adminq_process_rss_query(struct gve_priv *priv, rxfh->hfunc = descriptor->hash_alg; rss_info_addr = (void *)(descriptor + 1); - if (rxfh->key) + if (rxfh->key) { + rxfh->key_size = priv->rss_key_size; memcpy(rxfh->key, rss_info_addr, priv->rss_key_size); + } rss_info_addr += priv->rss_key_size; lut = (__be32 *)rss_info_addr; if (rxfh->indir) { + rxfh->indir_size = priv->rss_lut_size; for (i = 0; i < priv->rss_lut_size; i++) rxfh->indir[i] = be32_to_cpu(lut[i]); } diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index 863683de9694..228217458275 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -612,7 +612,6 @@ int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 queue_id); int gve_adminq_register_page_list(struct gve_priv *priv, struct gve_queue_page_list *qpl); int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id); -int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu); int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len, dma_addr_t stats_report_addr, u64 interval); int gve_adminq_verify_driver_compatibility(struct gve_priv *priv, diff --git a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c index 403f0f335ba6..a71883e1d920 100644 --- a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c @@ -139,7 +139,8 @@ int gve_alloc_qpl_page_dqo(struct gve_rx_ring *rx, buf_state->page_info.page_offset = 0; buf_state->page_info.page_address = page_address(buf_state->page_info.page); - buf_state->page_info.buf_size = priv->data_buffer_size_dqo; + buf_state->page_info.buf_size = rx->packet_buffer_truesize; + buf_state->page_info.pad = rx->rx_headroom; buf_state->last_single_ref_offset = 0; /* The page already has 1 ref. */ @@ -162,7 +163,7 @@ void gve_free_qpl_page_dqo(struct gve_rx_buf_state_dqo *buf_state) void gve_try_recycle_buf(struct gve_priv *priv, struct gve_rx_ring *rx, struct gve_rx_buf_state_dqo *buf_state) { - const u16 data_buffer_size = priv->data_buffer_size_dqo; + const u16 data_buffer_size = rx->packet_buffer_truesize; int pagecount; /* Can't reuse if we only fit one buffer per page */ @@ -205,38 +206,40 @@ void gve_free_to_page_pool(struct gve_rx_ring *rx, struct gve_rx_buf_state_dqo *buf_state, bool allow_direct) { - struct page *page = buf_state->page_info.page; + netmem_ref netmem = buf_state->page_info.netmem; - if (!page) + if (!netmem) return; - page_pool_put_full_page(page->pp, page, allow_direct); - buf_state->page_info.page = NULL; + page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, allow_direct); + buf_state->page_info.netmem = 0; } static int gve_alloc_from_page_pool(struct gve_rx_ring *rx, struct gve_rx_buf_state_dqo *buf_state) { - struct gve_priv *priv = rx->gve; - struct page *page; + netmem_ref netmem; - buf_state->page_info.buf_size = priv->data_buffer_size_dqo; - page = page_pool_alloc(rx->dqo.page_pool, - &buf_state->page_info.page_offset, - &buf_state->page_info.buf_size, GFP_ATOMIC); + buf_state->page_info.buf_size = rx->packet_buffer_truesize; + netmem = page_pool_alloc_netmem(rx->dqo.page_pool, + &buf_state->page_info.page_offset, + &buf_state->page_info.buf_size, + GFP_ATOMIC); - if (!page) + if (!netmem) return -ENOMEM; - buf_state->page_info.page = page; - buf_state->page_info.page_address = page_address(page); - buf_state->addr = page_pool_get_dma_addr(page); + buf_state->page_info.netmem = netmem; + buf_state->page_info.page_address = netmem_address(netmem); + buf_state->addr = page_pool_get_dma_addr_netmem(netmem); + buf_state->page_info.pad = rx->dqo.page_pool->p.offset; return 0; } struct page_pool *gve_rx_create_page_pool(struct gve_priv *priv, - struct gve_rx_ring *rx) + struct gve_rx_ring *rx, + bool xdp) { u32 ntfy_id = gve_rx_idx_to_ntfy(priv, rx->q_num); struct page_pool_params pp = { @@ -247,7 +250,8 @@ struct page_pool *gve_rx_create_page_pool(struct gve_priv *priv, .netdev = priv->dev, .napi = &priv->ntfy_blocks[ntfy_id].napi, .max_len = PAGE_SIZE, - .dma_dir = DMA_FROM_DEVICE, + .dma_dir = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE, + .offset = xdp ? XDP_PACKET_HEADROOM : 0, }; return page_pool_create(&pp); @@ -269,7 +273,7 @@ void gve_reuse_buffer(struct gve_rx_ring *rx, struct gve_rx_buf_state_dqo *buf_state) { if (rx->dqo.page_pool) { - buf_state->page_info.page = NULL; + buf_state->page_info.netmem = 0; gve_free_buf_state(rx, buf_state); } else { gve_dec_pagecnt_bias(&buf_state->page_info); @@ -301,7 +305,8 @@ int gve_alloc_buffer(struct gve_rx_ring *rx, struct gve_rx_desc_dqo *desc) } desc->buf_id = cpu_to_le16(buf_state - rx->dqo.buf_states); desc->buf_addr = cpu_to_le64(buf_state->addr + - buf_state->page_info.page_offset); + buf_state->page_info.page_offset + + buf_state->page_info.pad); return 0; diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index bdfc6e77b2af..3c1da0cf3f61 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -63,11 +63,11 @@ static const char gve_gstrings_rx_stats[][ETH_GSTRING_LEN] = { static const char gve_gstrings_tx_stats[][ETH_GSTRING_LEN] = { "tx_posted_desc[%u]", "tx_completed_desc[%u]", "tx_consumed_desc[%u]", "tx_bytes[%u]", "tx_wake[%u]", "tx_stop[%u]", "tx_event_counter[%u]", - "tx_dma_mapping_error[%u]", "tx_xsk_wakeup[%u]", - "tx_xsk_done[%u]", "tx_xsk_sent[%u]", "tx_xdp_xmit[%u]", "tx_xdp_xmit_errors[%u]" + "tx_dma_mapping_error[%u]", + "tx_xsk_sent[%u]", "tx_xdp_xmit[%u]", "tx_xdp_xmit_errors[%u]" }; -static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = { +static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] __nonstring_array = { "adminq_prod_cnt", "adminq_cmd_fail", "adminq_timeouts", "adminq_describe_device_cnt", "adminq_cfg_device_resources_cnt", "adminq_register_page_list_cnt", "adminq_unregister_page_list_cnt", @@ -113,7 +113,7 @@ static void gve_get_strings(struct net_device *netdev, u32 stringset, u8 *data) i); for (i = 0; i < ARRAY_SIZE(gve_gstrings_adminq_stats); i++) - ethtool_puts(&s, gve_gstrings_adminq_stats[i]); + ethtool_cpy(&s, gve_gstrings_adminq_stats[i]); break; @@ -392,7 +392,9 @@ gve_get_ethtool_stats(struct net_device *netdev, */ data[i++] = 0; data[i++] = 0; - data[i++] = tx->dqo_tx.tail - tx->dqo_tx.head; + data[i++] = + (tx->dqo_tx.tail - tx->dqo_tx.head) & + tx->mask; } do { start = @@ -417,9 +419,7 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = value; } } - /* XDP xsk counters */ - data[i++] = tx->xdp_xsk_wakeup; - data[i++] = tx->xdp_xsk_done; + /* XDP counters */ do { start = u64_stats_fetch_begin(&priv->tx[ring].statss); data[i] = tx->xdp_xsk_sent; @@ -477,11 +477,12 @@ static int gve_set_channels(struct net_device *netdev, struct ethtool_channels *cmd) { struct gve_priv *priv = netdev_priv(netdev); - struct gve_queue_config new_tx_cfg = priv->tx_cfg; - struct gve_queue_config new_rx_cfg = priv->rx_cfg; + struct gve_tx_queue_config new_tx_cfg = priv->tx_cfg; + struct gve_rx_queue_config new_rx_cfg = priv->rx_cfg; struct ethtool_channels old_settings; int new_tx = cmd->tx_count; int new_rx = cmd->rx_count; + bool reset_rss = false; gve_get_channels(netdev, &old_settings); @@ -492,22 +493,27 @@ static int gve_set_channels(struct net_device *netdev, if (!new_rx || !new_tx) return -EINVAL; - if (priv->num_xdp_queues && - (new_tx != new_rx || (2 * new_tx > priv->tx_cfg.max_queues))) { - dev_err(&priv->pdev->dev, "XDP load failed: The number of configured RX queues should be equal to the number of configured TX queues and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues"); - return -EINVAL; - } + if (priv->xdp_prog) { + if (new_tx != new_rx || + (2 * new_tx > priv->tx_cfg.max_queues)) { + dev_err(&priv->pdev->dev, "The number of configured RX queues should be equal to the number of configured TX queues and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues when XDP program is installed"); + return -EINVAL; + } - if (!netif_running(netdev)) { - priv->tx_cfg.num_queues = new_tx; - priv->rx_cfg.num_queues = new_rx; - return 0; + /* One XDP TX queue per RX queue. */ + new_tx_cfg.num_xdp_queues = new_rx; + } else { + new_tx_cfg.num_xdp_queues = 0; } + if (new_rx != priv->rx_cfg.num_queues && + priv->cache_rss_config && !netif_is_rxfh_configured(netdev)) + reset_rss = true; + new_tx_cfg.num_queues = new_tx; new_rx_cfg.num_queues = new_rx; - return gve_adjust_queues(priv, new_rx_cfg, new_tx_cfg); + return gve_adjust_queues(priv, new_rx_cfg, new_tx_cfg, reset_rss); } static void gve_get_ringparam(struct net_device *netdev, @@ -643,8 +649,7 @@ static int gve_set_tunable(struct net_device *netdev, switch (etuna->id) { case ETHTOOL_RX_COPYBREAK: { - u32 max_copybreak = gve_is_gqi(priv) ? - GVE_DEFAULT_RX_BUFFER_SIZE : priv->data_buffer_size_dqo; + u32 max_copybreak = priv->rx_cfg.packet_buffer_size; len = *(u32 *)value; if (len > max_copybreak) @@ -700,7 +705,7 @@ static int gve_set_priv_flags(struct net_device *netdev, u32 flags) memset(priv->stats_report->stats, 0, (tx_stats_num + rx_stats_num) * sizeof(struct stats)); - del_timer_sync(&priv->stats_report_timer); + timer_delete_sync(&priv->stats_report_timer); } return 0; } @@ -855,6 +860,25 @@ static u32 gve_get_rxfh_indir_size(struct net_device *netdev) return priv->rss_lut_size; } +static void gve_get_rss_config_cache(struct gve_priv *priv, + struct ethtool_rxfh_param *rxfh) +{ + struct gve_rss_config *rss_config = &priv->rss_config; + + rxfh->hfunc = ETH_RSS_HASH_TOP; + + if (rxfh->key) { + rxfh->key_size = priv->rss_key_size; + memcpy(rxfh->key, rss_config->hash_key, priv->rss_key_size); + } + + if (rxfh->indir) { + rxfh->indir_size = priv->rss_lut_size; + memcpy(rxfh->indir, rss_config->hash_lut, + priv->rss_lut_size * sizeof(*rxfh->indir)); + } +} + static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh) { struct gve_priv *priv = netdev_priv(netdev); @@ -862,18 +886,46 @@ static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rx if (!priv->rss_key_size || !priv->rss_lut_size) return -EOPNOTSUPP; + if (priv->cache_rss_config) { + gve_get_rss_config_cache(priv, rxfh); + return 0; + } + return gve_adminq_query_rss_config(priv, rxfh); } +static void gve_set_rss_config_cache(struct gve_priv *priv, + struct ethtool_rxfh_param *rxfh) +{ + struct gve_rss_config *rss_config = &priv->rss_config; + + if (rxfh->key) + memcpy(rss_config->hash_key, rxfh->key, priv->rss_key_size); + + if (rxfh->indir) + memcpy(rss_config->hash_lut, rxfh->indir, + priv->rss_lut_size * sizeof(*rxfh->indir)); +} + static int gve_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh, struct netlink_ext_ack *extack) { struct gve_priv *priv = netdev_priv(netdev); + int err; if (!priv->rss_key_size || !priv->rss_lut_size) return -EOPNOTSUPP; - return gve_adminq_configure_rss(priv, rxfh); + err = gve_adminq_configure_rss(priv, rxfh); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Fail to configure RSS config"); + return err; + } + + if (priv->cache_rss_config) + gve_set_rss_config_cache(priv, rxfh); + + return 0; } const struct ethtool_ops gve_ethtool_ops = { diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index e171ca248f9a..dc35a23ec47f 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -184,6 +184,43 @@ static void gve_free_flow_rule_caches(struct gve_priv *priv) flow_rules_cache->rules_cache = NULL; } +static int gve_alloc_rss_config_cache(struct gve_priv *priv) +{ + struct gve_rss_config *rss_config = &priv->rss_config; + + if (!priv->cache_rss_config) + return 0; + + rss_config->hash_key = kcalloc(priv->rss_key_size, + sizeof(rss_config->hash_key[0]), + GFP_KERNEL); + if (!rss_config->hash_key) + return -ENOMEM; + + rss_config->hash_lut = kcalloc(priv->rss_lut_size, + sizeof(rss_config->hash_lut[0]), + GFP_KERNEL); + if (!rss_config->hash_lut) + goto free_rss_key_cache; + + return 0; + +free_rss_key_cache: + kfree(rss_config->hash_key); + rss_config->hash_key = NULL; + return -ENOMEM; +} + +static void gve_free_rss_config_cache(struct gve_priv *priv) +{ + struct gve_rss_config *rss_config = &priv->rss_config; + + kfree(rss_config->hash_key); + kfree(rss_config->hash_lut); + + memset(rss_config, 0, sizeof(*rss_config)); +} + static int gve_alloc_counter_array(struct gve_priv *priv) { priv->counter_array = @@ -231,7 +268,8 @@ static void gve_stats_report_schedule(struct gve_priv *priv) static void gve_stats_report_timer(struct timer_list *t) { - struct gve_priv *priv = from_timer(priv, t, stats_report_timer); + struct gve_priv *priv = timer_container_of(priv, t, + stats_report_timer); mod_timer(&priv->stats_report_timer, round_jiffies(jiffies + @@ -265,7 +303,7 @@ static void gve_free_stats_report(struct gve_priv *priv) if (!priv->stats_report) return; - del_timer_sync(&priv->stats_report_timer); + timer_delete_sync(&priv->stats_report_timer); dma_free_coherent(&priv->pdev->dev, priv->stats_report_len, priv->stats_report, priv->stats_report_bus); priv->stats_report = NULL; @@ -333,6 +371,14 @@ int gve_napi_poll(struct napi_struct *napi, int budget) if (block->rx) { work_done = gve_rx_poll(block, budget); + + /* Poll XSK TX as part of RX NAPI. Setup re-poll based on max of + * TX and RX work done. + */ + if (priv->xdp_prog) + work_done = max_t(int, work_done, + gve_xsk_tx_poll(block, budget)); + reschedule |= work_done == budget; } @@ -567,9 +613,12 @@ static int gve_setup_device_resources(struct gve_priv *priv) err = gve_alloc_flow_rule_caches(priv); if (err) return err; - err = gve_alloc_counter_array(priv); + err = gve_alloc_rss_config_cache(priv); if (err) goto abort_with_flow_rule_caches; + err = gve_alloc_counter_array(priv); + if (err) + goto abort_with_rss_config_cache; err = gve_alloc_notify_blocks(priv); if (err) goto abort_with_counter; @@ -603,6 +652,12 @@ static int gve_setup_device_resources(struct gve_priv *priv) } } + err = gve_init_rss_config(priv, priv->rx_cfg.num_queues); + if (err) { + dev_err(&priv->pdev->dev, "Failed to init RSS config"); + goto abort_with_ptype_lut; + } + err = gve_adminq_report_stats(priv, priv->stats_report_len, priv->stats_report_bus, GVE_STATS_REPORT_TIMER_PERIOD); @@ -621,6 +676,8 @@ abort_with_ntfy_blocks: gve_free_notify_blocks(priv); abort_with_counter: gve_free_counter_array(priv); +abort_with_rss_config_cache: + gve_free_rss_config_cache(priv); abort_with_flow_rule_caches: gve_free_flow_rule_caches(priv); @@ -661,6 +718,7 @@ static void gve_teardown_device_resources(struct gve_priv *priv) priv->ptype_lut_dqo = NULL; gve_free_flow_rule_caches(priv); + gve_free_rss_config_cache(priv); gve_free_counter_array(priv); gve_free_notify_blocks(priv); gve_free_stats_report(priv); @@ -738,30 +796,13 @@ static struct gve_queue_page_list *gve_rx_get_qpl(struct gve_priv *priv, int idx return rx->dqo.qpl; } -static int gve_register_xdp_qpls(struct gve_priv *priv) -{ - int start_id; - int err; - int i; - - start_id = gve_xdp_tx_start_queue_id(priv); - for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) { - err = gve_register_qpl(priv, gve_tx_get_qpl(priv, i)); - /* This failure will trigger a reset - no need to clean up */ - if (err) - return err; - } - return 0; -} - static int gve_register_qpls(struct gve_priv *priv) { int num_tx_qpls, num_rx_qpls; int err; int i; - num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_num_xdp_qpls(priv), - gve_is_qpl(priv)); + num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_is_qpl(priv)); num_rx_qpls = gve_num_rx_qpls(&priv->rx_cfg, gve_is_qpl(priv)); for (i = 0; i < num_tx_qpls; i++) { @@ -779,30 +820,13 @@ static int gve_register_qpls(struct gve_priv *priv) return 0; } -static int gve_unregister_xdp_qpls(struct gve_priv *priv) -{ - int start_id; - int err; - int i; - - start_id = gve_xdp_tx_start_queue_id(priv); - for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) { - err = gve_unregister_qpl(priv, gve_tx_get_qpl(priv, i)); - /* This failure will trigger a reset - no need to clean */ - if (err) - return err; - } - return 0; -} - static int gve_unregister_qpls(struct gve_priv *priv) { int num_tx_qpls, num_rx_qpls; int err; int i; - num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_num_xdp_qpls(priv), - gve_is_qpl(priv)); + num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_is_qpl(priv)); num_rx_qpls = gve_num_rx_qpls(&priv->rx_cfg, gve_is_qpl(priv)); for (i = 0; i < num_tx_qpls; i++) { @@ -821,27 +845,6 @@ static int gve_unregister_qpls(struct gve_priv *priv) return 0; } -static int gve_create_xdp_rings(struct gve_priv *priv) -{ - int err; - - err = gve_adminq_create_tx_queues(priv, - gve_xdp_tx_start_queue_id(priv), - priv->num_xdp_queues); - if (err) { - netif_err(priv, drv, priv->dev, "failed to create %d XDP tx queues\n", - priv->num_xdp_queues); - /* This failure will trigger a reset - no need to clean - * up - */ - return err; - } - netif_dbg(priv, drv, priv->dev, "created %d XDP tx queues\n", - priv->num_xdp_queues); - - return 0; -} - static int gve_create_rings(struct gve_priv *priv) { int num_tx_queues = gve_num_tx_queues(priv); @@ -897,7 +900,7 @@ static void init_xdp_sync_stats(struct gve_priv *priv) int i; /* Init stats */ - for (i = start_id; i < start_id + priv->num_xdp_queues; i++) { + for (i = start_id; i < start_id + priv->tx_cfg.num_xdp_queues; i++) { int ntfy_idx = gve_tx_idx_to_ntfy(priv, i); u64_stats_init(&priv->tx[i].statss); @@ -925,19 +928,18 @@ static void gve_tx_get_curr_alloc_cfg(struct gve_priv *priv, cfg->qcfg = &priv->tx_cfg; cfg->raw_addressing = !gve_is_qpl(priv); cfg->ring_size = priv->tx_desc_cnt; - cfg->start_idx = 0; - cfg->num_rings = gve_num_tx_queues(priv); + cfg->num_xdp_rings = cfg->qcfg->num_xdp_queues; cfg->tx = priv->tx; } -static void gve_tx_stop_rings(struct gve_priv *priv, int start_id, int num_rings) +static void gve_tx_stop_rings(struct gve_priv *priv, int num_rings) { int i; if (!priv->tx) return; - for (i = start_id; i < start_id + num_rings; i++) { + for (i = 0; i < num_rings; i++) { if (gve_is_gqi(priv)) gve_tx_stop_ring_gqi(priv, i); else @@ -945,12 +947,11 @@ static void gve_tx_stop_rings(struct gve_priv *priv, int start_id, int num_rings } } -static void gve_tx_start_rings(struct gve_priv *priv, int start_id, - int num_rings) +static void gve_tx_start_rings(struct gve_priv *priv, int num_rings) { int i; - for (i = start_id; i < start_id + num_rings; i++) { + for (i = 0; i < num_rings; i++) { if (gve_is_gqi(priv)) gve_tx_start_ring_gqi(priv, i); else @@ -958,28 +959,6 @@ static void gve_tx_start_rings(struct gve_priv *priv, int start_id, } } -static int gve_alloc_xdp_rings(struct gve_priv *priv) -{ - struct gve_tx_alloc_rings_cfg cfg = {0}; - int err = 0; - - if (!priv->num_xdp_queues) - return 0; - - gve_tx_get_curr_alloc_cfg(priv, &cfg); - cfg.start_idx = gve_xdp_tx_start_queue_id(priv); - cfg.num_rings = priv->num_xdp_queues; - - err = gve_tx_alloc_rings_gqi(priv, &cfg); - if (err) - return err; - - gve_tx_start_rings(priv, cfg.start_idx, cfg.num_rings); - init_xdp_sync_stats(priv); - - return 0; -} - static int gve_queues_mem_alloc(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *tx_alloc_cfg, struct gve_rx_alloc_rings_cfg *rx_alloc_cfg) @@ -1010,26 +989,6 @@ free_tx: return err; } -static int gve_destroy_xdp_rings(struct gve_priv *priv) -{ - int start_id; - int err; - - start_id = gve_xdp_tx_start_queue_id(priv); - err = gve_adminq_destroy_tx_queues(priv, - start_id, - priv->num_xdp_queues); - if (err) { - netif_err(priv, drv, priv->dev, - "failed to destroy XDP queues\n"); - /* This failure will trigger a reset - no need to clean up */ - return err; - } - netif_dbg(priv, drv, priv->dev, "destroyed XDP queues\n"); - - return 0; -} - static int gve_destroy_rings(struct gve_priv *priv) { int num_tx_queues = gve_num_tx_queues(priv); @@ -1054,20 +1013,6 @@ static int gve_destroy_rings(struct gve_priv *priv) return 0; } -static void gve_free_xdp_rings(struct gve_priv *priv) -{ - struct gve_tx_alloc_rings_cfg cfg = {0}; - - gve_tx_get_curr_alloc_cfg(priv, &cfg); - cfg.start_idx = gve_xdp_tx_start_queue_id(priv); - cfg.num_rings = priv->num_xdp_queues; - - if (priv->tx) { - gve_tx_stop_rings(priv, cfg.start_idx, cfg.num_rings); - gve_tx_free_rings_gqi(priv, &cfg); - } -} - static void gve_queues_mem_free(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *tx_cfg, struct gve_rx_alloc_rings_cfg *rx_cfg) @@ -1194,7 +1139,7 @@ static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev) int i, j; u32 tx_qid; - if (!priv->num_xdp_queues) + if (!priv->tx_cfg.num_xdp_queues) return 0; for (i = 0; i < priv->rx_cfg.num_queues; i++) { @@ -1205,8 +1150,14 @@ static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev) napi->napi_id); if (err) goto err; - err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL); + if (gve_is_qpl(priv)) + err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq, + MEM_TYPE_PAGE_SHARED, + NULL); + else + err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq, + MEM_TYPE_PAGE_POOL, + rx->dqo.page_pool); if (err) goto err; rx->xsk_pool = xsk_get_pool_from_qid(dev, i); @@ -1224,7 +1175,7 @@ static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev) } } - for (i = 0; i < priv->num_xdp_queues; i++) { + for (i = 0; i < priv->tx_cfg.num_xdp_queues; i++) { tx_qid = gve_xdp_tx_queue_id(priv, i); priv->tx[tx_qid].xsk_pool = xsk_get_pool_from_qid(dev, i); } @@ -1245,7 +1196,7 @@ static void gve_unreg_xdp_info(struct gve_priv *priv) { int i, tx_qid; - if (!priv->num_xdp_queues) + if (!priv->tx_cfg.num_xdp_queues || !priv->rx || !priv->tx) return; for (i = 0; i < priv->rx_cfg.num_queues; i++) { @@ -1258,7 +1209,7 @@ static void gve_unreg_xdp_info(struct gve_priv *priv) } } - for (i = 0; i < priv->num_xdp_queues; i++) { + for (i = 0; i < priv->tx_cfg.num_xdp_queues; i++) { tx_qid = gve_xdp_tx_queue_id(priv, i); priv->tx[tx_qid].xsk_pool = NULL; } @@ -1275,15 +1226,14 @@ static void gve_drain_page_cache(struct gve_priv *priv) static void gve_rx_get_curr_alloc_cfg(struct gve_priv *priv, struct gve_rx_alloc_rings_cfg *cfg) { - cfg->qcfg = &priv->rx_cfg; + cfg->qcfg_rx = &priv->rx_cfg; cfg->qcfg_tx = &priv->tx_cfg; cfg->raw_addressing = !gve_is_qpl(priv); cfg->enable_header_split = priv->header_split_enabled; cfg->ring_size = priv->rx_desc_cnt; - cfg->packet_buffer_size = gve_is_gqi(priv) ? - GVE_DEFAULT_RX_BUFFER_SIZE : - priv->data_buffer_size_dqo; + cfg->packet_buffer_size = priv->rx_cfg.packet_buffer_size; cfg->rx = priv->rx; + cfg->xdp = !!cfg->qcfg_tx->num_xdp_queues; } void gve_get_curr_alloc_cfgs(struct gve_priv *priv, @@ -1356,17 +1306,13 @@ static int gve_queues_start(struct gve_priv *priv, /* Record new configs into priv */ priv->tx_cfg = *tx_alloc_cfg->qcfg; - priv->rx_cfg = *rx_alloc_cfg->qcfg; + priv->tx_cfg.num_xdp_queues = tx_alloc_cfg->num_xdp_rings; + priv->rx_cfg = *rx_alloc_cfg->qcfg_rx; priv->tx_desc_cnt = tx_alloc_cfg->ring_size; priv->rx_desc_cnt = rx_alloc_cfg->ring_size; - if (priv->xdp_prog) - priv->num_xdp_queues = priv->rx_cfg.num_queues; - else - priv->num_xdp_queues = 0; - - gve_tx_start_rings(priv, 0, tx_alloc_cfg->num_rings); - gve_rx_start_rings(priv, rx_alloc_cfg->qcfg->num_queues); + gve_tx_start_rings(priv, gve_num_tx_queues(priv)); + gve_rx_start_rings(priv, rx_alloc_cfg->qcfg_rx->num_queues); gve_init_sync_stats(priv); err = netif_set_real_num_tx_queues(dev, priv->tx_cfg.num_queues); @@ -1380,12 +1326,18 @@ static int gve_queues_start(struct gve_priv *priv, if (err) goto stop_and_free_rings; + if (rx_alloc_cfg->reset_rss) { + err = gve_init_rss_config(priv, priv->rx_cfg.num_queues); + if (err) + goto reset; + } + err = gve_register_qpls(priv); if (err) goto reset; priv->header_split_enabled = rx_alloc_cfg->enable_header_split; - priv->data_buffer_size_dqo = rx_alloc_cfg->packet_buffer_size; + priv->rx_cfg.packet_buffer_size = rx_alloc_cfg->packet_buffer_size; err = gve_create_rings(priv); if (err) @@ -1412,7 +1364,7 @@ reset: /* return the original error */ return err; stop_and_free_rings: - gve_tx_stop_rings(priv, 0, gve_num_tx_queues(priv)); + gve_tx_stop_rings(priv, gve_num_tx_queues(priv)); gve_rx_stop_rings(priv, priv->rx_cfg.num_queues); gve_queues_mem_remove(priv); return err; @@ -1457,11 +1409,11 @@ static int gve_queues_stop(struct gve_priv *priv) goto err; gve_clear_device_rings_ok(priv); } - del_timer_sync(&priv->stats_report_timer); + timer_delete_sync(&priv->stats_report_timer); gve_unreg_xdp_info(priv); - gve_tx_stop_rings(priv, 0, gve_num_tx_queues(priv)); + gve_tx_stop_rings(priv, gve_num_tx_queues(priv)); gve_rx_stop_rings(priv, priv->rx_cfg.num_queues); priv->interface_down_cnt++; @@ -1491,56 +1443,6 @@ static int gve_close(struct net_device *dev) return 0; } -static int gve_remove_xdp_queues(struct gve_priv *priv) -{ - int err; - - err = gve_destroy_xdp_rings(priv); - if (err) - return err; - - err = gve_unregister_xdp_qpls(priv); - if (err) - return err; - - gve_unreg_xdp_info(priv); - gve_free_xdp_rings(priv); - - priv->num_xdp_queues = 0; - return 0; -} - -static int gve_add_xdp_queues(struct gve_priv *priv) -{ - int err; - - priv->num_xdp_queues = priv->rx_cfg.num_queues; - - err = gve_alloc_xdp_rings(priv); - if (err) - goto err; - - err = gve_reg_xdp_info(priv, priv->dev); - if (err) - goto free_xdp_rings; - - err = gve_register_xdp_qpls(priv); - if (err) - goto free_xdp_rings; - - err = gve_create_xdp_rings(priv); - if (err) - goto free_xdp_rings; - - return 0; - -free_xdp_rings: - gve_free_xdp_rings(priv); -err: - priv->num_xdp_queues = 0; - return err; -} - static void gve_handle_link_status(struct gve_priv *priv, bool link_status) { if (!gve_get_napi_enabled(priv)) @@ -1558,6 +1460,19 @@ static void gve_handle_link_status(struct gve_priv *priv, bool link_status) } } +static int gve_configure_rings_xdp(struct gve_priv *priv, + u16 num_xdp_rings) +{ + struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0}; + struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0}; + + gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg); + tx_alloc_cfg.num_xdp_rings = num_xdp_rings; + + rx_alloc_cfg.xdp = !!num_xdp_rings; + return gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg); +} + static int gve_set_xdp(struct gve_priv *priv, struct bpf_prog *prog, struct netlink_ext_ack *extack) { @@ -1570,29 +1485,26 @@ static int gve_set_xdp(struct gve_priv *priv, struct bpf_prog *prog, WRITE_ONCE(priv->xdp_prog, prog); if (old_prog) bpf_prog_put(old_prog); + + /* Update priv XDP queue configuration */ + priv->tx_cfg.num_xdp_queues = priv->xdp_prog ? + priv->rx_cfg.num_queues : 0; return 0; } - gve_turndown(priv); - if (!old_prog && prog) { - // Allocate XDP TX queues if an XDP program is - // being installed - err = gve_add_xdp_queues(priv); - if (err) - goto out; - } else if (old_prog && !prog) { - // Remove XDP TX queues if an XDP program is - // being uninstalled - err = gve_remove_xdp_queues(priv); - if (err) - goto out; - } + if (!old_prog && prog) + err = gve_configure_rings_xdp(priv, priv->rx_cfg.num_queues); + else if (old_prog && !prog) + err = gve_configure_rings_xdp(priv, 0); + + if (err) + goto out; + WRITE_ONCE(priv->xdp_prog, prog); if (old_prog) bpf_prog_put(old_prog); out: - gve_turnup(priv); status = ioread32be(&priv->reg_bar0->device_status); gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status); return err; @@ -1623,8 +1535,8 @@ static int gve_xsk_pool_enable(struct net_device *dev, if (err) return err; - /* If XDP prog is not installed, return */ - if (!priv->xdp_prog) + /* If XDP prog is not installed or interface is down, return. */ + if (!priv->xdp_prog || !netif_running(dev)) return 0; rx = &priv->rx[qid]; @@ -1669,21 +1581,16 @@ static int gve_xsk_pool_disable(struct net_device *dev, if (qid >= priv->rx_cfg.num_queues) return -EINVAL; - /* If XDP prog is not installed, unmap DMA and return */ - if (!priv->xdp_prog) - goto done; - - tx_qid = gve_xdp_tx_queue_id(priv, qid); - if (!netif_running(dev)) { - priv->rx[qid].xsk_pool = NULL; - xdp_rxq_info_unreg(&priv->rx[qid].xsk_rxq); - priv->tx[tx_qid].xsk_pool = NULL; + /* If XDP prog is not installed or interface is down, unmap DMA and + * return. + */ + if (!priv->xdp_prog || !netif_running(dev)) goto done; - } napi_rx = &priv->ntfy_blocks[priv->rx[qid].ntfy_id].napi; napi_disable(napi_rx); /* make sure current rx poll is done */ + tx_qid = gve_xdp_tx_queue_id(priv, qid); napi_tx = &priv->ntfy_blocks[priv->tx[tx_qid].ntfy_id].napi; napi_disable(napi_tx); /* make sure current tx poll is done */ @@ -1709,24 +1616,20 @@ done: static int gve_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) { struct gve_priv *priv = netdev_priv(dev); - int tx_queue_id = gve_xdp_tx_queue_id(priv, queue_id); + struct napi_struct *napi; + + if (!gve_get_napi_enabled(priv)) + return -ENETDOWN; if (queue_id >= priv->rx_cfg.num_queues || !priv->xdp_prog) return -EINVAL; - if (flags & XDP_WAKEUP_TX) { - struct gve_tx_ring *tx = &priv->tx[tx_queue_id]; - struct napi_struct *napi = - &priv->ntfy_blocks[tx->ntfy_id].napi; - - if (!napi_if_scheduled_mark_missed(napi)) { - /* Call local_bh_enable to trigger SoftIRQ processing */ - local_bh_disable(); - napi_schedule(napi); - local_bh_enable(); - } - - tx->xdp_xsk_wakeup++; + napi = &priv->ntfy_blocks[gve_rx_idx_to_ntfy(priv, queue_id)].napi; + if (!napi_if_scheduled_mark_missed(napi)) { + /* Call local_bh_enable to trigger SoftIRQ processing */ + local_bh_disable(); + napi_schedule(napi); + local_bh_enable(); } return 0; @@ -1735,6 +1638,7 @@ static int gve_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) static int verify_xdp_configuration(struct net_device *dev) { struct gve_priv *priv = netdev_priv(dev); + u16 max_xdp_mtu; if (dev->features & NETIF_F_LRO) { netdev_warn(dev, "XDP is not supported when LRO is on.\n"); @@ -1747,7 +1651,11 @@ static int verify_xdp_configuration(struct net_device *dev) return -EOPNOTSUPP; } - if (dev->mtu > GVE_DEFAULT_RX_BUFFER_SIZE - sizeof(struct ethhdr) - GVE_RX_PAD) { + max_xdp_mtu = priv->rx_cfg.packet_buffer_size - sizeof(struct ethhdr); + if (priv->queue_format == GVE_GQI_QPL_FORMAT) + max_xdp_mtu -= GVE_RX_PAD; + + if (dev->mtu > max_xdp_mtu) { netdev_warn(dev, "XDP is not supported for mtu %d.\n", dev->mtu); return -EOPNOTSUPP; @@ -1785,6 +1693,26 @@ static int gve_xdp(struct net_device *dev, struct netdev_bpf *xdp) } } +int gve_init_rss_config(struct gve_priv *priv, u16 num_queues) +{ + struct gve_rss_config *rss_config = &priv->rss_config; + struct ethtool_rxfh_param rxfh = {0}; + u16 i; + + if (!priv->cache_rss_config) + return 0; + + for (i = 0; i < priv->rss_lut_size; i++) + rss_config->hash_lut[i] = + ethtool_rxfh_indir_default(i, num_queues); + + netdev_rss_key_fill(rss_config->hash_key, priv->rss_key_size); + + rxfh.hfunc = ETH_RSS_HASH_TOP; + + return gve_adminq_configure_rss(priv, &rxfh); +} + int gve_flow_rules_reset(struct gve_priv *priv) { if (!priv->max_flow_rules) @@ -1832,8 +1760,9 @@ int gve_adjust_config(struct gve_priv *priv, } int gve_adjust_queues(struct gve_priv *priv, - struct gve_queue_config new_rx_config, - struct gve_queue_config new_tx_config) + struct gve_rx_queue_config new_rx_config, + struct gve_tx_queue_config new_tx_config, + bool reset_rss) { struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0}; struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0}; @@ -1844,14 +1773,19 @@ int gve_adjust_queues(struct gve_priv *priv, /* Relay the new config from ethtool */ tx_alloc_cfg.qcfg = &new_tx_config; rx_alloc_cfg.qcfg_tx = &new_tx_config; - rx_alloc_cfg.qcfg = &new_rx_config; - tx_alloc_cfg.num_rings = new_tx_config.num_queues; + rx_alloc_cfg.qcfg_rx = &new_rx_config; + rx_alloc_cfg.reset_rss = reset_rss; if (netif_running(priv->dev)) { err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg); return err; } /* Set the config for the next up. */ + if (reset_rss) { + err = gve_init_rss_config(priv, new_rx_config.num_queues); + if (err) + return err; + } priv->tx_cfg = new_tx_config; priv->rx_cfg = new_rx_config; @@ -1880,7 +1814,7 @@ static void gve_turndown(struct gve_priv *priv) netif_queue_set_napi(priv->dev, idx, NETDEV_QUEUE_TYPE_TX, NULL); - napi_disable(&block->napi); + napi_disable_locked(&block->napi); } for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) { int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx); @@ -1891,14 +1825,19 @@ static void gve_turndown(struct gve_priv *priv) netif_queue_set_napi(priv->dev, idx, NETDEV_QUEUE_TYPE_RX, NULL); - napi_disable(&block->napi); + napi_disable_locked(&block->napi); } /* Stop tx queues */ netif_tx_disable(priv->dev); + xdp_features_clear_redirect_target_locked(priv->dev); + gve_clear_napi_enabled(priv); gve_clear_report_stats(priv); + + /* Make sure that all traffic is finished processing. */ + synchronize_net(); } static void gve_turnup(struct gve_priv *priv) @@ -1916,7 +1855,7 @@ static void gve_turnup(struct gve_priv *priv) if (!gve_tx_was_added_to_block(priv, idx)) continue; - napi_enable(&block->napi); + napi_enable_locked(&block->napi); if (idx < priv->tx_cfg.num_queues) netif_queue_set_napi(priv->dev, idx, @@ -1944,7 +1883,7 @@ static void gve_turnup(struct gve_priv *priv) if (!gve_rx_was_added_to_block(priv, idx)) continue; - napi_enable(&block->napi); + napi_enable_locked(&block->napi); netif_queue_set_napi(priv->dev, idx, NETDEV_QUEUE_TYPE_RX, &block->napi); @@ -1963,6 +1902,9 @@ static void gve_turnup(struct gve_priv *priv) napi_schedule(&block->napi); } + if (priv->tx_cfg.num_xdp_queues && gve_supports_xdp_xmit(priv)) + xdp_features_set_redirect_target_locked(priv->dev, false); + gve_set_napi_enabled(priv); } @@ -2136,7 +2078,9 @@ static void gve_handle_reset(struct gve_priv *priv) if (gve_get_do_reset(priv)) { rtnl_lock(); + netdev_lock(priv->dev); gve_reset(priv, false); + netdev_unlock(priv->dev); rtnl_unlock(); } } @@ -2210,7 +2154,7 @@ void gve_handle_report_stats(struct gve_priv *priv) }; stats[stats_idx++] = (struct stats) { .stat_name = cpu_to_be32(RX_BUFFERS_POSTED), - .value = cpu_to_be64(priv->rx[0].fill_cnt), + .value = cpu_to_be64(priv->rx[idx].fill_cnt), .queue_id = cpu_to_be32(idx), }; } @@ -2232,14 +2176,17 @@ static void gve_service_task(struct work_struct *work) static void gve_set_netdev_xdp_features(struct gve_priv *priv) { + xdp_features_t xdp_features; + if (priv->queue_format == GVE_GQI_QPL_FORMAT) { - priv->dev->xdp_features = NETDEV_XDP_ACT_BASIC; - priv->dev->xdp_features |= NETDEV_XDP_ACT_REDIRECT; - priv->dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; - priv->dev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; + xdp_features = NETDEV_XDP_ACT_BASIC; + xdp_features |= NETDEV_XDP_ACT_REDIRECT; + xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; } else { - priv->dev->xdp_features = 0; + xdp_features = 0; } + + xdp_set_features_flag_locked(priv->dev, xdp_features); } static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) @@ -2313,6 +2260,7 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) priv->rx_cfg.num_queues = min_t(int, priv->default_num_queues, priv->rx_cfg.num_queues); } + priv->tx_cfg.num_xdp_queues = 0; dev_info(&priv->pdev->dev, "TX queues %d, RX queues %d\n", priv->tx_cfg.num_queues, priv->rx_cfg.num_queues); @@ -2693,7 +2641,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) priv->service_task_flags = 0x0; priv->state_flags = 0x0; priv->ethtool_flags = 0x0; - priv->data_buffer_size_dqo = GVE_DEFAULT_RX_BUFFER_SIZE; + priv->rx_cfg.packet_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE; priv->max_rx_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE; gve_set_probe_in_progress(priv); @@ -2712,6 +2660,9 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto abort_with_wq; + if (!gve_is_gqi(priv) && !gve_is_qpl(priv)) + dev->netmem_tx = true; + err = register_netdev(dev); if (err) goto abort_with_gve_init; @@ -2769,6 +2720,7 @@ static void gve_shutdown(struct pci_dev *pdev) bool was_up = netif_running(priv->dev); rtnl_lock(); + netdev_lock(netdev); if (was_up && gve_close(priv->dev)) { /* If the dev was up, attempt to close, if close fails, reset */ gve_reset_and_teardown(priv, was_up); @@ -2776,6 +2728,7 @@ static void gve_shutdown(struct pci_dev *pdev) /* If the dev wasn't up or close worked, finish tearing down */ gve_teardown_priv_resources(priv); } + netdev_unlock(netdev); rtnl_unlock(); } @@ -2788,6 +2741,7 @@ static int gve_suspend(struct pci_dev *pdev, pm_message_t state) priv->suspend_cnt++; rtnl_lock(); + netdev_lock(netdev); if (was_up && gve_close(priv->dev)) { /* If the dev was up, attempt to close, if close fails, reset */ gve_reset_and_teardown(priv, was_up); @@ -2796,6 +2750,7 @@ static int gve_suspend(struct pci_dev *pdev, pm_message_t state) gve_teardown_priv_resources(priv); } priv->up_before_suspend = was_up; + netdev_unlock(netdev); rtnl_unlock(); return 0; } @@ -2808,7 +2763,9 @@ static int gve_resume(struct pci_dev *pdev) priv->resume_cnt++; rtnl_lock(); + netdev_lock(netdev); err = gve_reset_recovery(priv, priv->up_before_suspend); + netdev_unlock(netdev); rtnl_unlock(); return err; } diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index acb73d4d0de6..90e875c1832f 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -141,12 +141,15 @@ void gve_rx_free_ring_gqi(struct gve_priv *priv, struct gve_rx_ring *rx, netif_dbg(priv, drv, priv->dev, "freed rx ring %d\n", idx); } -static void gve_setup_rx_buffer(struct gve_rx_slot_page_info *page_info, - dma_addr_t addr, struct page *page, __be64 *slot_addr) +static void gve_setup_rx_buffer(struct gve_rx_ring *rx, + struct gve_rx_slot_page_info *page_info, + dma_addr_t addr, struct page *page, + __be64 *slot_addr) { page_info->page = page; page_info->page_offset = 0; page_info->page_address = page_address(page); + page_info->buf_size = rx->packet_buffer_size; *slot_addr = cpu_to_be64(addr); /* The page already has 1 ref */ page_ref_add(page, INT_MAX - 1); @@ -171,7 +174,7 @@ static int gve_rx_alloc_buffer(struct gve_priv *priv, struct device *dev, return err; } - gve_setup_rx_buffer(page_info, dma, page, &data_slot->addr); + gve_setup_rx_buffer(rx, page_info, dma, page, &data_slot->addr); return 0; } @@ -199,7 +202,8 @@ static int gve_rx_prefill_pages(struct gve_rx_ring *rx, struct page *page = rx->data.qpl->pages[i]; dma_addr_t addr = i * PAGE_SIZE; - gve_setup_rx_buffer(&rx->data.page_info[i], addr, page, + gve_setup_rx_buffer(rx, &rx->data.page_info[i], addr, + page, &rx->data.data_ring[i].qpl_offset); continue; } @@ -222,6 +226,7 @@ static int gve_rx_prefill_pages(struct gve_rx_ring *rx, rx->qpl_copy_pool[j].page = page; rx->qpl_copy_pool[j].page_offset = 0; rx->qpl_copy_pool[j].page_address = page_address(page); + rx->qpl_copy_pool[j].buf_size = rx->packet_buffer_size; /* The page already has 1 ref. */ page_ref_add(page, INT_MAX - 1); @@ -283,6 +288,7 @@ int gve_rx_alloc_ring_gqi(struct gve_priv *priv, rx->gve = priv; rx->q_num = idx; + rx->packet_buffer_size = cfg->packet_buffer_size; rx->mask = slots - 1; rx->data.raw_addressing = cfg->raw_addressing; @@ -351,7 +357,6 @@ int gve_rx_alloc_ring_gqi(struct gve_priv *priv, rx->db_threshold = slots / 2; gve_rx_init_ring_state_gqi(rx); - rx->packet_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE; gve_rx_ctx_clear(&rx->ctx); return 0; @@ -385,12 +390,12 @@ int gve_rx_alloc_rings_gqi(struct gve_priv *priv, int err = 0; int i, j; - rx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_rx_ring), + rx = kvcalloc(cfg->qcfg_rx->max_queues, sizeof(struct gve_rx_ring), GFP_KERNEL); if (!rx) return -ENOMEM; - for (i = 0; i < cfg->qcfg->num_queues; i++) { + for (i = 0; i < cfg->qcfg_rx->num_queues; i++) { err = gve_rx_alloc_ring_gqi(priv, cfg, &rx[i], i); if (err) { netif_err(priv, drv, priv->dev, @@ -419,7 +424,7 @@ void gve_rx_free_rings_gqi(struct gve_priv *priv, if (!rx) return; - for (i = 0; i < cfg->qcfg->num_queues; i++) + for (i = 0; i < cfg->qcfg_rx->num_queues; i++) gve_rx_free_ring_gqi(priv, &rx[i], cfg); kvfree(rx); @@ -590,7 +595,7 @@ static struct sk_buff *gve_rx_copy_to_pool(struct gve_rx_ring *rx, copy_page_info->pad = page_info->pad; skb = gve_rx_add_frags(napi, copy_page_info, - rx->packet_buffer_size, len, ctx); + copy_page_info->buf_size, len, ctx); if (unlikely(!skb)) return NULL; @@ -630,7 +635,8 @@ gve_rx_qpl(struct device *dev, struct net_device *netdev, * device. */ if (page_info->can_flip) { - skb = gve_rx_add_frags(napi, page_info, rx->packet_buffer_size, len, ctx); + skb = gve_rx_add_frags(napi, page_info, page_info->buf_size, + len, ctx); /* No point in recycling if we didn't get the skb */ if (skb) { /* Make sure that the page isn't freed. */ @@ -680,7 +686,7 @@ static struct sk_buff *gve_rx_skb(struct gve_priv *priv, struct gve_rx_ring *rx, skb = gve_rx_raw_addressing(&priv->pdev->dev, netdev, page_info, len, napi, data_slot, - rx->packet_buffer_size, ctx); + page_info->buf_size, ctx); } else { skb = gve_rx_qpl(&priv->pdev->dev, netdev, rx, page_info, len, napi, data_slot); @@ -855,7 +861,7 @@ static void gve_rx(struct gve_rx_ring *rx, netdev_features_t feat, void *old_data; int xdp_act; - xdp_init_buff(&xdp, rx->packet_buffer_size, &rx->xdp_rxq); + xdp_init_buff(&xdp, page_info->buf_size, &rx->xdp_rxq); xdp_prepare_buff(&xdp, page_info->page_address + page_info->page_offset, GVE_RX_PAD, len, false); diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 8ac0047f1ada..dcb0545baa50 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -109,10 +109,13 @@ static void gve_rx_reset_ring_dqo(struct gve_priv *priv, int idx) void gve_rx_stop_ring_dqo(struct gve_priv *priv, int idx) { int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx); + struct gve_rx_ring *rx = &priv->rx[idx]; if (!gve_rx_was_added_to_block(priv, idx)) return; + if (rx->dqo.page_pool) + page_pool_disable_direct_recycling(rx->dqo.page_pool); gve_remove_napi(priv, ntfy_idx); gve_rx_remove_from_block(priv, idx); gve_rx_reset_ring_dqo(priv, idx); @@ -221,6 +224,15 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv, memset(rx, 0, sizeof(*rx)); rx->gve = priv; rx->q_num = idx; + rx->packet_buffer_size = cfg->packet_buffer_size; + + if (cfg->xdp) { + rx->packet_buffer_truesize = GVE_XDP_RX_BUFFER_SIZE_DQO; + rx->rx_headroom = XDP_PACKET_HEADROOM; + } else { + rx->packet_buffer_truesize = rx->packet_buffer_size; + rx->rx_headroom = 0; + } rx->dqo.num_buf_states = cfg->raw_addressing ? buffer_queue_slots : gve_get_rx_pages_per_qpl_dqo(cfg->ring_size); @@ -251,7 +263,7 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv, goto err; if (cfg->raw_addressing) { - pool = gve_rx_create_page_pool(priv, rx); + pool = gve_rx_create_page_pool(priv, rx, cfg->xdp); if (IS_ERR(pool)) goto err; @@ -297,12 +309,12 @@ int gve_rx_alloc_rings_dqo(struct gve_priv *priv, int err; int i; - rx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_rx_ring), + rx = kvcalloc(cfg->qcfg_rx->max_queues, sizeof(struct gve_rx_ring), GFP_KERNEL); if (!rx) return -ENOMEM; - for (i = 0; i < cfg->qcfg->num_queues; i++) { + for (i = 0; i < cfg->qcfg_rx->num_queues; i++) { err = gve_rx_alloc_ring_dqo(priv, cfg, &rx[i], i); if (err) { netif_err(priv, drv, priv->dev, @@ -331,7 +343,7 @@ void gve_rx_free_rings_dqo(struct gve_priv *priv, if (!rx) return; - for (i = 0; i < cfg->qcfg->num_queues; i++) + for (i = 0; i < cfg->qcfg_rx->num_queues; i++) gve_rx_free_ring_dqo(priv, &rx[i], cfg); kvfree(rx); @@ -474,6 +486,25 @@ static int gve_rx_copy_ondemand(struct gve_rx_ring *rx, return 0; } +static void gve_skb_add_rx_frag(struct gve_rx_ring *rx, + struct gve_rx_buf_state_dqo *buf_state, + int num_frags, u16 buf_len) +{ + if (rx->dqo.page_pool) { + skb_add_rx_frag_netmem(rx->ctx.skb_tail, num_frags, + buf_state->page_info.netmem, + buf_state->page_info.page_offset + + buf_state->page_info.pad, buf_len, + buf_state->page_info.buf_size); + } else { + skb_add_rx_frag(rx->ctx.skb_tail, num_frags, + buf_state->page_info.page, + buf_state->page_info.page_offset + + buf_state->page_info.pad, buf_len, + buf_state->page_info.buf_size); + } +} + /* Chains multi skbs for single rx packet. * Returns 0 if buffer is appended, -1 otherwise. */ @@ -511,14 +542,34 @@ static int gve_rx_append_frags(struct napi_struct *napi, if (gve_rx_should_trigger_copy_ondemand(rx)) return gve_rx_copy_ondemand(rx, buf_state, buf_len); - skb_add_rx_frag(rx->ctx.skb_tail, num_frags, - buf_state->page_info.page, - buf_state->page_info.page_offset, - buf_len, buf_state->page_info.buf_size); + gve_skb_add_rx_frag(rx, buf_state, num_frags, buf_len); gve_reuse_buffer(rx, buf_state); return 0; } +static void gve_xdp_done_dqo(struct gve_priv *priv, struct gve_rx_ring *rx, + struct xdp_buff *xdp, struct bpf_prog *xprog, + int xdp_act, + struct gve_rx_buf_state_dqo *buf_state) +{ + u64_stats_update_begin(&rx->statss); + switch (xdp_act) { + case XDP_ABORTED: + case XDP_DROP: + default: + rx->xdp_actions[xdp_act]++; + break; + case XDP_TX: + rx->xdp_tx_errors++; + break; + case XDP_REDIRECT: + rx->xdp_redirect_errors++; + break; + } + u64_stats_update_end(&rx->statss); + gve_free_buffer(rx, buf_state); +} + /* Returns 0 if descriptor is completed successfully. * Returns -EINVAL if descriptor is invalid. * Returns -ENOMEM if data cannot be copied to skb. @@ -533,6 +584,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, const bool hsplit = compl_desc->split_header; struct gve_rx_buf_state_dqo *buf_state; struct gve_priv *priv = rx->gve; + struct bpf_prog *xprog; u16 buf_len; u16 hdr_len; @@ -559,7 +611,12 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, /* Page might have not been used for awhile and was likely last written * by a different thread. */ - prefetch(buf_state->page_info.page); + if (rx->dqo.page_pool) { + if (!netmem_is_net_iov(buf_state->page_info.netmem)) + prefetch(netmem_to_page(buf_state->page_info.netmem)); + } else { + prefetch(buf_state->page_info.page); + } /* Copy the header into the skb in the case of header split */ if (hsplit) { @@ -588,7 +645,8 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, /* Sync the portion of dma buffer for CPU to read. */ dma_sync_single_range_for_cpu(&priv->pdev->dev, buf_state->addr, - buf_state->page_info.page_offset, + buf_state->page_info.page_offset + + buf_state->page_info.pad, buf_len, DMA_FROM_DEVICE); /* Append to current skb if one exists. */ @@ -600,6 +658,34 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, return 0; } + xprog = READ_ONCE(priv->xdp_prog); + if (xprog) { + struct xdp_buff xdp; + void *old_data; + int xdp_act; + + xdp_init_buff(&xdp, buf_state->page_info.buf_size, + &rx->xdp_rxq); + xdp_prepare_buff(&xdp, + buf_state->page_info.page_address + + buf_state->page_info.page_offset, + buf_state->page_info.pad, + buf_len, false); + old_data = xdp.data; + xdp_act = bpf_prog_run_xdp(xprog, &xdp); + buf_state->page_info.pad += xdp.data - old_data; + buf_len = xdp.data_end - xdp.data; + if (xdp_act != XDP_PASS) { + gve_xdp_done_dqo(priv, rx, &xdp, xprog, xdp_act, + buf_state); + return 0; + } + + u64_stats_update_begin(&rx->statss); + rx->xdp_actions[XDP_PASS]++; + u64_stats_update_end(&rx->statss); + } + if (eop && buf_len <= priv->rx_copybreak) { rx->ctx.skb_head = gve_rx_copy(priv->dev, napi, &buf_state->page_info, buf_len); @@ -630,9 +716,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, if (rx->dqo.page_pool) skb_mark_for_recycle(rx->ctx.skb_head); - skb_add_rx_frag(rx->ctx.skb_head, 0, buf_state->page_info.page, - buf_state->page_info.page_offset, buf_len, - buf_state->page_info.buf_size); + gve_skb_add_rx_frag(rx, buf_state, 0, buf_len); gve_reuse_buffer(rx, buf_state); return 0; diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index e7fb7d6d283d..1b40bf0c811a 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -206,7 +206,10 @@ void gve_tx_stop_ring_gqi(struct gve_priv *priv, int idx) return; gve_remove_napi(priv, ntfy_idx); - gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false); + if (tx->q_num < priv->tx_cfg.num_queues) + gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false); + else + gve_clean_xdp_done(priv, tx, priv->tx_desc_cnt); netdev_tx_reset_queue(tx->netdev_txq); gve_tx_remove_from_block(priv, idx); } @@ -331,27 +334,23 @@ int gve_tx_alloc_rings_gqi(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *cfg) { struct gve_tx_ring *tx = cfg->tx; + int total_queues; int err = 0; int i, j; - if (cfg->start_idx + cfg->num_rings > cfg->qcfg->max_queues) { + total_queues = cfg->qcfg->num_queues + cfg->num_xdp_rings; + if (total_queues > cfg->qcfg->max_queues) { netif_err(priv, drv, priv->dev, "Cannot alloc more than the max num of Tx rings\n"); return -EINVAL; } - if (cfg->start_idx == 0) { - tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring), - GFP_KERNEL); - if (!tx) - return -ENOMEM; - } else if (!tx) { - netif_err(priv, drv, priv->dev, - "Cannot alloc tx rings from a nonzero start idx without tx array\n"); - return -EINVAL; - } + tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring), + GFP_KERNEL); + if (!tx) + return -ENOMEM; - for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++) { + for (i = 0; i < total_queues; i++) { err = gve_tx_alloc_ring_gqi(priv, cfg, &tx[i], i); if (err) { netif_err(priv, drv, priv->dev, @@ -367,8 +366,7 @@ int gve_tx_alloc_rings_gqi(struct gve_priv *priv, cleanup: for (j = 0; j < i; j++) gve_tx_free_ring_gqi(priv, &tx[j], cfg); - if (cfg->start_idx == 0) - kvfree(tx); + kvfree(tx); return err; } @@ -381,13 +379,11 @@ void gve_tx_free_rings_gqi(struct gve_priv *priv, if (!tx) return; - for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++) + for (i = 0; i < cfg->qcfg->num_queues + cfg->qcfg->num_xdp_queues; i++) gve_tx_free_ring_gqi(priv, &tx[i], cfg); - if (cfg->start_idx == 0) { - kvfree(tx); - cfg->tx = NULL; - } + kvfree(tx); + cfg->tx = NULL; } /* gve_tx_avail - Calculates the number of slots available in the ring @@ -834,11 +830,14 @@ int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, struct gve_tx_ring *tx; int i, err = 0, qid; - if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK) || !priv->xdp_prog) return -EINVAL; + if (!gve_get_napi_enabled(priv)) + return -ENETDOWN; + qid = gve_xdp_tx_queue_id(priv, - smp_processor_id() % priv->num_xdp_queues); + smp_processor_id() % priv->tx_cfg.num_xdp_queues); tx = &priv->tx[qid]; @@ -953,13 +952,9 @@ static int gve_xsk_tx(struct gve_priv *priv, struct gve_tx_ring *tx, spin_lock(&tx->xdp_lock); while (sent < budget) { - if (!gve_can_tx(tx, GVE_TX_START_THRESH)) - goto out; - - if (!xsk_tx_peek_desc(tx->xsk_pool, &desc)) { - tx->xdp_xsk_done = tx->xdp_xsk_wakeup; + if (!gve_can_tx(tx, GVE_TX_START_THRESH) || + !xsk_tx_peek_desc(tx->xsk_pool, &desc)) goto out; - } data = xsk_buff_raw_get_data(tx->xsk_pool, desc.addr); nsegs = gve_tx_fill_xdp(priv, tx, data, desc.len, NULL, true); @@ -975,33 +970,41 @@ out: return sent; } +int gve_xsk_tx_poll(struct gve_notify_block *rx_block, int budget) +{ + struct gve_rx_ring *rx = rx_block->rx; + struct gve_priv *priv = rx->gve; + struct gve_tx_ring *tx; + int sent = 0; + + tx = &priv->tx[gve_xdp_tx_queue_id(priv, rx->q_num)]; + if (tx->xsk_pool) { + sent = gve_xsk_tx(priv, tx, budget); + + u64_stats_update_begin(&tx->statss); + tx->xdp_xsk_sent += sent; + u64_stats_update_end(&tx->statss); + if (xsk_uses_need_wakeup(tx->xsk_pool)) + xsk_set_tx_need_wakeup(tx->xsk_pool); + } + + return sent; +} + bool gve_xdp_poll(struct gve_notify_block *block, int budget) { struct gve_priv *priv = block->priv; struct gve_tx_ring *tx = block->tx; u32 nic_done; - bool repoll; u32 to_do; /* Find out how much work there is to be done */ nic_done = gve_tx_load_event_counter(priv, tx); to_do = min_t(u32, (nic_done - tx->done), budget); gve_clean_xdp_done(priv, tx, to_do); - repoll = nic_done != tx->done; - - if (tx->xsk_pool) { - int sent = gve_xsk_tx(priv, tx, budget); - - u64_stats_update_begin(&tx->statss); - tx->xdp_xsk_sent += sent; - u64_stats_update_end(&tx->statss); - repoll |= (sent == budget); - if (xsk_uses_need_wakeup(tx->xsk_pool)) - xsk_set_tx_need_wakeup(tx->xsk_pool); - } /* If we still have work we want to repoll */ - return repoll; + return nic_done != tx->done; } bool gve_tx_poll(struct gve_notify_block *block, int budget) diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c index f879426cb552..9d705d94b065 100644 --- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c @@ -379,27 +379,23 @@ int gve_tx_alloc_rings_dqo(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *cfg) { struct gve_tx_ring *tx = cfg->tx; + int total_queues; int err = 0; int i, j; - if (cfg->start_idx + cfg->num_rings > cfg->qcfg->max_queues) { + total_queues = cfg->qcfg->num_queues + cfg->num_xdp_rings; + if (total_queues > cfg->qcfg->max_queues) { netif_err(priv, drv, priv->dev, "Cannot alloc more than the max num of Tx rings\n"); return -EINVAL; } - if (cfg->start_idx == 0) { - tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring), - GFP_KERNEL); - if (!tx) - return -ENOMEM; - } else if (!tx) { - netif_err(priv, drv, priv->dev, - "Cannot alloc tx rings from a nonzero start idx without tx array\n"); - return -EINVAL; - } + tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring), + GFP_KERNEL); + if (!tx) + return -ENOMEM; - for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++) { + for (i = 0; i < total_queues; i++) { err = gve_tx_alloc_ring_dqo(priv, cfg, &tx[i], i); if (err) { netif_err(priv, drv, priv->dev, @@ -415,8 +411,7 @@ int gve_tx_alloc_rings_dqo(struct gve_priv *priv, err: for (j = 0; j < i; j++) gve_tx_free_ring_dqo(priv, &tx[j], cfg); - if (cfg->start_idx == 0) - kvfree(tx); + kvfree(tx); return err; } @@ -429,13 +424,11 @@ void gve_tx_free_rings_dqo(struct gve_priv *priv, if (!tx) return; - for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++) + for (i = 0; i < cfg->qcfg->num_queues + cfg->qcfg->num_xdp_queues; i++) gve_tx_free_ring_dqo(priv, &tx[i], cfg); - if (cfg->start_idx == 0) { - kvfree(tx); - cfg->tx = NULL; - } + kvfree(tx); + cfg->tx = NULL; } /* Returns the number of slots available in the ring */ @@ -667,7 +660,8 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx, goto err; dma_unmap_len_set(pkt, len[pkt->num_bufs], len); - dma_unmap_addr_set(pkt, dma[pkt->num_bufs], addr); + netmem_dma_unmap_addr_set(skb_frag_netmem(frag), pkt, + dma[pkt->num_bufs], addr); ++pkt->num_bufs; gve_tx_fill_pkt_desc_dqo(tx, desc_idx, skb, len, addr, @@ -770,6 +764,9 @@ static int gve_tx_add_skb_dqo(struct gve_tx_ring *tx, s16 completion_tag; pkt = gve_alloc_pending_packet(tx); + if (!pkt) + return -ENOMEM; + pkt->skb = skb; completion_tag = pkt - tx->dqo.pending_packets; @@ -1045,8 +1042,9 @@ static void gve_unmap_packet(struct device *dev, dma_unmap_single(dev, dma_unmap_addr(pkt, dma[0]), dma_unmap_len(pkt, len[0]), DMA_TO_DEVICE); for (i = 1; i < pkt->num_bufs; i++) { - dma_unmap_page(dev, dma_unmap_addr(pkt, dma[i]), - dma_unmap_len(pkt, len[i]), DMA_TO_DEVICE); + netmem_dma_unmap_page_attrs(dev, dma_unmap_addr(pkt, dma[i]), + dma_unmap_len(pkt, len[i]), + DMA_TO_DEVICE, 0); } pkt->num_bufs = 0; } @@ -1146,8 +1144,7 @@ static void gve_handle_miss_completion(struct gve_priv *priv, /* jiffies can wraparound but time comparisons can handle overflows. */ pending_packet->timeout_jiffies = jiffies + - msecs_to_jiffies(GVE_REINJECT_COMPL_TIMEOUT * - MSEC_PER_SEC); + secs_to_jiffies(GVE_REINJECT_COMPL_TIMEOUT); add_to_list(tx, &tx->dqo_compl.miss_completions, pending_packet); *bytes += pending_packet->skb->len; @@ -1191,8 +1188,7 @@ static void remove_miss_completions(struct gve_priv *priv, pending_packet->state = GVE_PACKET_STATE_TIMED_OUT_COMPL; pending_packet->timeout_jiffies = jiffies + - msecs_to_jiffies(GVE_DEALLOCATE_COMPL_TIMEOUT * - MSEC_PER_SEC); + secs_to_jiffies(GVE_DEALLOCATE_COMPL_TIMEOUT); /* Maintain pending packet in another list so the packet can be * unallocated at a later time. */ diff --git a/drivers/net/ethernet/google/gve/gve_utils.c b/drivers/net/ethernet/google/gve/gve_utils.c index 30fef100257e..ace9b8698021 100644 --- a/drivers/net/ethernet/google/gve/gve_utils.c +++ b/drivers/net/ethernet/google/gve/gve_utils.c @@ -110,13 +110,13 @@ void gve_add_napi(struct gve_priv *priv, int ntfy_idx, { struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; - netif_napi_add(priv->dev, &block->napi, gve_poll); - netif_napi_set_irq(&block->napi, block->irq); + netif_napi_add_locked(priv->dev, &block->napi, gve_poll); + netif_napi_set_irq_locked(&block->napi, block->irq); } void gve_remove_napi(struct gve_priv *priv, int ntfy_idx) { struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; - netif_napi_del(&block->napi); + netif_napi_del_locked(&block->napi); } |