From 9d73cf4ebe65bb601f0d3bea6100860dd33e27f6 Mon Sep 17 00:00:00 2001 From: Praveen Kaligineedi Date: Wed, 15 Mar 2023 16:33:08 -0700 Subject: [PATCH] gve: Add XDP support for GQI-QPL format Adding support for XDP DROP, PASS, TX, REDIRECT for GQI QPL format. Add AF_XDP zero-copy support. When an XDP program is installed, dedicated TX queues are created to handle XDP traffic. The user needs to ensure that the number of configured TX queues is equal to the number of configured RX queues; and the number of TX/RX queues is less than or equal to half the maximum number of TX/RX queues. The XDP traffic from AF_XDP sockets and from other NICs (arriving via XDP_REDIRECT) will also egress through the dedicated XDP TX queues. Although these changes support AF_XDP socket in zero-copy mode, there is still a copy happening within the driver between XSK buffer pool and QPL bounce buffers in GQI-QPL format. The following example demonstrates how the XDP packets are mapped to TX queues: Example configuration: Max RX queues : 2N, Max TX queues : 2N Configured RX queues : N, Configured TX queues : N TX queue mapping: TX queues with queue id 0,...,N-1 will handle traffic from the stack. TX queues with queue id N,...,2N-1 will handle XDP traffic. For the XDP packets transmitted using XDP_TX action: = N + For the XDP packets that arrive from other NICs via XDP_REDIRECT action: = N + ( smp_processor_id % N ) For AF_XDP zero-copy mode: = N + --- Updated version to 1.4.0rc1 --- google/gve/gve.h | 112 +++++- google/gve/gve_adminq.c | 8 +- google/gve/gve_adminq.h | 4 +- google/gve/gve_ethtool.c | 91 +++-- google/gve/gve_main.c | 721 ++++++++++++++++++++++++++++++++++++--- google/gve/gve_rx.c | 147 +++++++- google/gve/gve_rx_dqo.c | 2 +- google/gve/gve_tx.c | 298 ++++++++++++++-- google/gve/gve_utils.c | 6 +- google/gve/gve_utils.h | 3 +- patches/patch_xdp1.cocci | 307 +++++++++++++++++ patches/patch_xdp2.cocci | 107 ++++++ 12 files changed, 1667 insertions(+), 139 deletions(-) create mode 100644 patches/patch_xdp1.cocci create mode 100644 patches/patch_xdp2.cocci diff --git a/google/gve/gve.h b/google/gve/gve.h index 64eb044..e214b51 100644 --- a/google/gve/gve.h +++ b/google/gve/gve.h @@ -47,6 +47,10 @@ #define GVE_RX_BUFFER_SIZE_DQO 2048 +#define GVE_XDP_ACTIONS 5 + +#define GVE_TX_MAX_HEADER_SIZE 182 + /* Each slot in the desc ring has a 1:1 mapping to a slot in the data ring */ struct gve_rx_desc_queue { struct gve_rx_desc *desc_ring; /* the descriptor ring */ @@ -230,7 +234,10 @@ struct gve_rx_ring { u64 rx_frag_flip_cnt; /* free-running count of rx segments where page_flip was used */ u64 rx_frag_copy_cnt; /* free-running count of rx segments copied */ u64 rx_frag_alloc_cnt; /* free-running count of rx page allocations */ - + u64 xdp_tx_errors; + u64 xdp_redirect_errors; + u64 xdp_alloc_fails; + u64 xdp_actions[GVE_XDP_ACTIONS]; u32 q_num; /* queue index */ u32 ntfy_id; /* notification block index */ struct gve_queue_resources *q_resources; /* head and tail pointer idx */ @@ -238,6 +245,12 @@ struct gve_rx_ring { struct u64_stats_sync statss; /* sync stats for 32bit archs */ struct gve_rx_ctx ctx; /* Info for packet currently being processed in this ring. */ + + /* XDP stuff */ + struct xdp_rxq_info xdp_rxq; + struct xdp_rxq_info xsk_rxq; + struct xsk_buff_pool *xsk_pool; + struct page_frag_cache page_cache; /* Page cache to allocate XDP frames */ }; /* A TX desc ring entry */ @@ -258,7 +271,14 @@ struct gve_tx_iovec { * ring entry but only used for a pkt_desc not a seg_desc */ struct gve_tx_buffer_state { - struct sk_buff *skb; /* skb for this pkt */ + union { + struct sk_buff *skb; /* skb for this pkt */ + struct xdp_frame *xdp_frame; /* xdp_frame */ + }; + struct { + u16 size; /* size of xmitted xdp pkt */ + u8 is_xsk; /* xsk buff */ + } xdp; union { struct gve_tx_iovec iov[GVE_TX_MAX_IOVEC]; /* segments of this pkt */ struct { @@ -373,6 +393,8 @@ struct gve_tx_ring { struct { /* Spinlock for when cleanup in progress */ spinlock_t clean_lock; + /* Spinlock for XDP tx traffic */ + spinlock_t xdp_lock; }; /* DQO fields. */ @@ -450,6 +472,12 @@ struct gve_tx_ring { dma_addr_t q_resources_bus; /* dma address of the queue resources */ 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; } ____cacheline_aligned; /* Wraps the info for one irq including the napi struct and the queues @@ -526,9 +554,11 @@ struct gve_priv { u16 rx_data_slot_cnt; /* rx buffer length */ u64 max_registered_pages; u64 num_registered_pages; /* num pages registered with NIC */ + struct bpf_prog *xdp_prog; /* XDP BPF program */ 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_qpl_config qpl_cfg; /* map used QPL ids */ @@ -785,7 +815,17 @@ static inline u32 gve_num_tx_qpls(struct gve_priv *priv) if (priv->queue_format != GVE_GQI_QPL_FORMAT) return 0; - return priv->tx_cfg.num_queues; + return priv->tx_cfg.num_queues + priv->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; } /* Returns the number of rx queue page lists @@ -798,16 +838,35 @@ static inline u32 gve_num_rx_qpls(struct gve_priv *priv) return priv->rx_cfg.num_queues; } +static inline u32 gve_tx_qpl_id(struct gve_priv *priv, int tx_qid) +{ + return tx_qid; +} + +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_tx_start_qpl_id(struct gve_priv *priv) +{ + return gve_tx_qpl_id(priv, 0); +} + +static inline u32 gve_rx_start_qpl_id(struct gve_priv *priv) +{ + return gve_rx_qpl_id(priv, 0); +} + /* Returns a pointer to the next available tx qpl in the list of qpls */ static inline -struct gve_queue_page_list *gve_assign_tx_qpl(struct gve_priv *priv) +struct gve_queue_page_list *gve_assign_tx_qpl(struct gve_priv *priv, int tx_qid) { - int id = find_first_zero_bit(priv->qpl_cfg.qpl_id_map, - priv->qpl_cfg.qpl_map_size); + int id = gve_tx_qpl_id(priv, tx_qid); - /* we are out of tx qpls */ - if (id >= gve_num_tx_qpls(priv)) + /* QPL already in use */ + if (test_bit(id, priv->qpl_cfg.qpl_id_map)) return NULL; set_bit(id, priv->qpl_cfg.qpl_id_map); @@ -817,14 +876,12 @@ struct gve_queue_page_list *gve_assign_tx_qpl(struct gve_priv *priv) /* Returns a pointer to the next available rx qpl in the list of qpls */ static inline -struct gve_queue_page_list *gve_assign_rx_qpl(struct gve_priv *priv) +struct gve_queue_page_list *gve_assign_rx_qpl(struct gve_priv *priv, int rx_qid) { - int id = find_next_zero_bit(priv->qpl_cfg.qpl_id_map, - priv->qpl_cfg.qpl_map_size, - gve_num_tx_qpls(priv)); + int id = gve_rx_qpl_id(priv, rx_qid); - /* we are out of rx qpls */ - if (id == gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv)) + /* QPL already in use */ + if (test_bit(id, priv->qpl_cfg.qpl_id_map)) return NULL; set_bit(id, priv->qpl_cfg.qpl_id_map); @@ -843,7 +900,7 @@ static inline void gve_unassign_qpl(struct gve_priv *priv, int id) static inline enum dma_data_direction gve_qpl_dma_dir(struct gve_priv *priv, int id) { - if (id < gve_num_tx_qpls(priv)) + if (id < gve_rx_start_qpl_id(priv)) return DMA_TO_DEVICE; else return DMA_FROM_DEVICE; @@ -855,6 +912,21 @@ static inline bool gve_is_gqi(struct gve_priv *priv) priv->queue_format == GVE_GQI_QPL_FORMAT; } +static inline u32 gve_num_tx_queues(struct gve_priv *priv) +{ + return priv->tx_cfg.num_queues + priv->num_xdp_queues; +} + +static inline u32 gve_xdp_tx_queue_id(struct gve_priv *priv, u32 queue_id) +{ + return priv->tx_cfg.num_queues + queue_id; +} + +static inline u32 gve_xdp_tx_start_queue_id(struct gve_priv *priv) +{ + return gve_xdp_tx_queue_id(priv, 0); +} + /* buffers */ int gve_alloc_page(struct gve_priv *priv, struct device *dev, struct page **page, dma_addr_t *dma, @@ -863,9 +935,15 @@ void gve_free_page(struct device *dev, struct page *page, dma_addr_t dma, enum dma_data_direction); /* tx handling */ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev); +int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, + u32 flags); +int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx, + void *data, int len, void *frame_p); +void gve_xdp_tx_flush(struct gve_priv *priv, u32 xdp_qid); bool gve_tx_poll(struct gve_notify_block *block, int budget); -int gve_tx_alloc_rings(struct gve_priv *priv); -void gve_tx_free_rings_gqi(struct gve_priv *priv); +bool gve_xdp_poll(struct gve_notify_block *block, int budget); +int gve_tx_alloc_rings(struct gve_priv *priv, int start_id, int num_rings); +void gve_tx_free_rings_gqi(struct gve_priv *priv, int start_id, int num_rings); u32 gve_tx_load_event_counter(struct gve_priv *priv, struct gve_tx_ring *tx); bool gve_tx_clean_pending(struct gve_priv *priv, struct gve_tx_ring *tx); diff --git a/google/gve/gve_adminq.c b/google/gve/gve_adminq.c index 11725c7..1a122ef 100644 --- a/google/gve/gve_adminq.c +++ b/google/gve/gve_adminq.c @@ -516,12 +516,12 @@ static int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_index) return gve_adminq_issue_cmd(priv, &cmd); } -int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 num_queues) +int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_queues) { int err; int i; - for (i = 0; i < num_queues; i++) { + for (i = start_id; i < start_id + num_queues; i++) { err = gve_adminq_create_tx_queue(priv, i); if (err) return err; @@ -604,12 +604,12 @@ static int gve_adminq_destroy_tx_queue(struct gve_priv *priv, u32 queue_index) return 0; } -int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 num_queues) +int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_queues) { int err; int i; - for (i = 0; i < num_queues; i++) { + for (i = start_id; i < start_id + num_queues; i++) { err = gve_adminq_destroy_tx_queue(priv, i); if (err) return err; diff --git a/google/gve/gve_adminq.h b/google/gve/gve_adminq.h index cf29662..f894beb 100644 --- a/google/gve/gve_adminq.h +++ b/google/gve/gve_adminq.h @@ -410,8 +410,8 @@ int gve_adminq_configure_device_resources(struct gve_priv *priv, dma_addr_t db_array_bus_addr, u32 num_ntfy_blks); int gve_adminq_deconfigure_device_resources(struct gve_priv *priv); -int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 num_queues); -int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 queue_id); +int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_queues); +int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_queues); int gve_adminq_create_rx_queues(struct gve_priv *priv, u32 num_queues); int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 queue_id); int gve_adminq_register_page_list(struct gve_priv *priv, diff --git a/google/gve/gve_ethtool.c b/google/gve/gve_ethtool.c index 5f81470..cfd4b8d 100644 --- a/google/gve/gve_ethtool.c +++ b/google/gve/gve_ethtool.c @@ -34,6 +34,11 @@ static u32 gve_get_msglevel(struct net_device *netdev) return priv->msg_enable; } +/* For the following stats column string names, make sure the order + * matches how it is filled in the code. For xdp_aborted, xdp_drop, + * xdp_pass, xdp_tx, xdp_redirect, make sure it also matches the order + * as declared in enum xdp_action inside file uapi/linux/bpf.h . + */ static const char gve_gstrings_main_stats[][ETH_GSTRING_LEN] = { "rx_packets", "tx_packets", "rx_bytes", "tx_bytes", "rx_dropped", "tx_dropped", "tx_timeouts", @@ -49,12 +54,16 @@ static const char gve_gstrings_rx_stats[][ETH_GSTRING_LEN] = { "rx_dropped_pkt[%u]", "rx_copybreak_pkt[%u]", "rx_copied_pkt[%u]", "rx_queue_drop_cnt[%u]", "rx_no_buffers_posted[%u]", "rx_drops_packet_over_mru[%u]", "rx_drops_invalid_checksum[%u]", + "rx_xdp_aborted[%u]", "rx_xdp_drop[%u]", "rx_xdp_pass[%u]", + "rx_xdp_tx[%u]", "rx_xdp_redirect[%u]", + "rx_xdp_tx_errors[%u]", "rx_xdp_redirect_errors[%u]", "rx_xdp_alloc_fails[%u]", }; 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_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]" }; static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = { @@ -81,8 +90,10 @@ static void gve_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { struct gve_priv *priv = netdev_priv(netdev); char *s = (char *)data; + int num_tx_queues; int i, j; + num_tx_queues = gve_num_tx_queues(priv); switch (stringset) { case ETH_SS_STATS: memcpy(s, *gve_gstrings_main_stats, @@ -97,7 +108,7 @@ static void gve_get_strings(struct net_device *netdev, u32 stringset, u8 *data) } } - for (i = 0; i < priv->tx_cfg.num_queues; i++) { + for (i = 0; i < num_tx_queues; i++) { for (j = 0; j < NUM_GVE_TX_CNTS; j++) { snprintf(s, ETH_GSTRING_LEN, gve_gstrings_tx_stats[j], i); @@ -124,12 +135,14 @@ static void gve_get_strings(struct net_device *netdev, u32 stringset, u8 *data) static int gve_get_sset_count(struct net_device *netdev, int sset) { struct gve_priv *priv = netdev_priv(netdev); + int num_tx_queues; + num_tx_queues = gve_num_tx_queues(priv); switch (sset) { case ETH_SS_STATS: return GVE_MAIN_STATS_LEN + GVE_ADMINQ_STATS_LEN + (priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS) + - (priv->tx_cfg.num_queues * NUM_GVE_TX_CNTS); + (num_tx_queues * NUM_GVE_TX_CNTS); case ETH_SS_PRIV_FLAGS: return GVE_PRIV_FLAGS_STR_LEN; default: @@ -153,18 +166,20 @@ gve_get_ethtool_stats(struct net_device *netdev, struct gve_priv *priv; bool skip_nic_stats; unsigned int start; + int num_tx_queues; int ring; int i, j; ASSERT_RTNL(); priv = netdev_priv(netdev); + num_tx_queues = gve_num_tx_queues(priv); report_stats = priv->stats_report->stats; rx_qid_to_stats_idx = kmalloc_array(priv->rx_cfg.num_queues, sizeof(int), GFP_KERNEL); if (!rx_qid_to_stats_idx) return; - tx_qid_to_stats_idx = kmalloc_array(priv->tx_cfg.num_queues, + tx_qid_to_stats_idx = kmalloc_array(num_tx_queues, sizeof(int), GFP_KERNEL); if (!tx_qid_to_stats_idx) { kfree(rx_qid_to_stats_idx); @@ -195,7 +210,7 @@ gve_get_ethtool_stats(struct net_device *netdev, } } for (tx_pkts = 0, tx_bytes = 0, tx_dropped = 0, ring = 0; - ring < priv->tx_cfg.num_queues; ring++) { + ring < num_tx_queues; ring++) { if (priv->tx) { do { start = @@ -232,7 +247,7 @@ gve_get_ethtool_stats(struct net_device *netdev, i = GVE_MAIN_STATS_LEN; /* For rx cross-reporting stats, start from nic rx stats in report */ - base_stats_idx = GVE_TX_STATS_REPORT_NUM * priv->tx_cfg.num_queues + + base_stats_idx = GVE_TX_STATS_REPORT_NUM * num_tx_queues + GVE_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues; max_stats_idx = NIC_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues + base_stats_idx; @@ -283,14 +298,26 @@ gve_get_ethtool_stats(struct net_device *netdev, if (skip_nic_stats) { /* skip NIC rx stats */ i += NIC_RX_STATS_REPORT_NUM; - continue; - } - for (j = 0; j < NIC_RX_STATS_REPORT_NUM; j++) { - u64 value = - be64_to_cpu(report_stats[rx_qid_to_stats_idx[ring] + j].value); + } else { + stats_idx = rx_qid_to_stats_idx[ring]; + for (j = 0; j < NIC_RX_STATS_REPORT_NUM; j++) { + u64 value = + be64_to_cpu(report_stats[stats_idx + j].value); - data[i++] = value; + data[i++] = value; + } } + /* XDP rx counters */ + do { + start = u64_stats_fetch_begin(&priv->rx[ring].statss); + for (j = 0; j < GVE_XDP_ACTIONS; j++) + data[i + j] = rx->xdp_actions[j]; + data[i + j++] = rx->xdp_tx_errors; + data[i + j++] = rx->xdp_redirect_errors; + data[i + j++] = rx->xdp_alloc_fails; + } while (u64_stats_fetch_retry(&priv->rx[ring].statss, + start)); + i += GVE_XDP_ACTIONS + 3; /* XDP rx counters */ } } else { i += priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS; @@ -298,7 +325,7 @@ gve_get_ethtool_stats(struct net_device *netdev, /* For tx cross-reporting stats, start from nic tx stats in report */ base_stats_idx = max_stats_idx; - max_stats_idx = NIC_TX_STATS_REPORT_NUM * priv->tx_cfg.num_queues + + max_stats_idx = NIC_TX_STATS_REPORT_NUM * num_tx_queues + max_stats_idx; /* Preprocess the stats report for tx, map queue id to start index */ skip_nic_stats = false; @@ -316,7 +343,7 @@ gve_get_ethtool_stats(struct net_device *netdev, } /* walk TX rings */ if (priv->tx) { - for (ring = 0; ring < priv->tx_cfg.num_queues; ring++) { + for (ring = 0; ring < num_tx_queues; ring++) { struct gve_tx_ring *tx = &priv->tx[ring]; if (gve_is_gqi(priv)) { @@ -346,16 +373,28 @@ gve_get_ethtool_stats(struct net_device *netdev, if (skip_nic_stats) { /* skip NIC tx stats */ i += NIC_TX_STATS_REPORT_NUM; - continue; - } - for (j = 0; j < NIC_TX_STATS_REPORT_NUM; j++) { - u64 value = - be64_to_cpu(report_stats[tx_qid_to_stats_idx[ring] + j].value); - data[i++] = value; + } else { + stats_idx = tx_qid_to_stats_idx[ring]; + for (j = 0; j < NIC_TX_STATS_REPORT_NUM; j++) { + u64 value = + be64_to_cpu(report_stats[stats_idx + j].value); + data[i++] = value; + } } + /* XDP xsk counters */ + data[i++] = tx->xdp_xsk_wakeup; + data[i++] = tx->xdp_xsk_done; + do { + start = u64_stats_fetch_begin(&priv->tx[ring].statss); + data[i] = tx->xdp_xsk_sent; + data[i + 1] = tx->xdp_xmit; + data[i + 2] = tx->xdp_xmit_errors; + } while (u64_stats_fetch_retry(&priv->tx[ring].statss, + start)); + i += 3; /* XDP tx counters */ } } else { - i += priv->tx_cfg.num_queues * NUM_GVE_TX_CNTS; + i += num_tx_queues * NUM_GVE_TX_CNTS; } kfree(rx_qid_to_stats_idx); @@ -412,6 +451,12 @@ 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 (!netif_carrier_ok(netdev)) { priv->tx_cfg.num_queues = new_tx; priv->rx_cfg.num_queues = new_rx; @@ -502,7 +547,9 @@ static int gve_set_priv_flags(struct net_device *netdev, u32 flags) { struct gve_priv *priv = netdev_priv(netdev); u64 ori_flags, new_flags; + int num_tx_queues; + num_tx_queues = gve_num_tx_queues(priv); ori_flags = READ_ONCE(priv->ethtool_flags); new_flags = ori_flags; @@ -522,7 +569,7 @@ static int gve_set_priv_flags(struct net_device *netdev, u32 flags) /* delete report stats timer. */ if (!(flags & BIT(0)) && (ori_flags & BIT(0))) { int tx_stats_num = GVE_TX_STATS_REPORT_NUM * - priv->tx_cfg.num_queues; + num_tx_queues; int rx_stats_num = GVE_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues; diff --git a/google/gve/gve_main.c b/google/gve/gve_main.c index 8437133..19994f2 100644 --- a/google/gve/gve_main.c +++ b/google/gve/gve_main.c @@ -4,8 +4,10 @@ * Copyright (C) 2015-2021 Google, Inc. */ +#include #include #include +#include #include #include #include @@ -15,6 +17,7 @@ #include #include #include +#include #include "gve.h" #include "gve_dqo.h" #include "gve_adminq.h" @@ -23,7 +26,7 @@ #define GVE_DEFAULT_RX_COPYBREAK (256) #define DEFAULT_MSG_LEVEL (NETIF_MSG_DRV | NETIF_MSG_LINK) -#define GVE_VERSION "1.3.3" +#define GVE_VERSION "1.4.0rc1" #define GVE_VERSION_PREFIX "GVE-" // Minimum amount of time between queue kicks in msec (10 seconds) @@ -90,8 +93,10 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s) struct gve_priv *priv = netdev_priv(dev); unsigned int start; u64 packets, bytes; + int num_tx_queues; int ring; + num_tx_queues = gve_num_tx_queues(priv); if (priv->rx) { for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) { do { @@ -106,7 +111,7 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s) } } if (priv->tx) { - for (ring = 0; ring < priv->tx_cfg.num_queues; ring++) { + for (ring = 0; ring < num_tx_queues; ring++) { do { start = u64_stats_fetch_begin(&priv->tx[ring].statss); @@ -180,7 +185,7 @@ static int gve_alloc_stats_report(struct gve_priv *priv) int tx_stats_num, rx_stats_num; tx_stats_num = (GVE_TX_STATS_REPORT_NUM + NIC_TX_STATS_REPORT_NUM) * - priv->tx_cfg.num_queues; + gve_num_tx_queues(priv); rx_stats_num = (GVE_RX_STATS_REPORT_NUM + NIC_RX_STATS_REPORT_NUM) * priv->rx_cfg.num_queues; priv->stats_report_len = struct_size(priv->stats_report, stats, @@ -245,8 +250,13 @@ static int gve_napi_poll(struct napi_struct *napi, int budget) block = container_of(napi, struct gve_notify_block, napi); priv = block->priv; - if (block->tx) - reschedule |= gve_tx_poll(block, budget); + if (block->tx) { + if (block->tx->q_num < priv->tx_cfg.num_queues) + reschedule |= gve_tx_poll(block, budget); + else + reschedule |= gve_xdp_poll(block, budget); + } + if (block->rx) { work_done = gve_rx_poll(block, budget); reschedule |= work_done == budget; @@ -580,13 +590,36 @@ static void gve_remove_napi(struct gve_priv *priv, int ntfy_idx) netif_napi_del(&block->napi); } +static int gve_register_xdp_qpls(struct gve_priv *priv) +{ + int start_id; + int err; + int i; + + start_id = gve_tx_qpl_id(priv, gve_xdp_tx_start_queue_id(priv)); + for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) { + err = gve_adminq_register_page_list(priv, &priv->qpls[i]); + if (err) { + netif_err(priv, drv, priv->dev, + "failed to register queue page list %d\n", + priv->qpls[i].id); + /* This failure will trigger a reset - no need to clean + * up + */ + return err; + } + } + return 0; +} + static int gve_register_qpls(struct gve_priv *priv) { - int num_qpls = gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv); + int start_id; int err; int i; - for (i = 0; i < num_qpls; i++) { + start_id = gve_tx_start_qpl_id(priv); + for (i = start_id; i < start_id + gve_num_tx_qpls(priv); i++) { err = gve_adminq_register_page_list(priv, &priv->qpls[i]); if (err) { netif_err(priv, drv, priv->dev, @@ -598,16 +631,63 @@ static int gve_register_qpls(struct gve_priv *priv) return err; } } + + start_id = gve_rx_start_qpl_id(priv); + for (i = start_id; i < start_id + gve_num_rx_qpls(priv); i++) { + err = gve_adminq_register_page_list(priv, &priv->qpls[i]); + if (err) { + netif_err(priv, drv, priv->dev, + "failed to register queue page list %d\n", + priv->qpls[i].id); + /* This failure will trigger a reset - no need to clean + * up + */ + return err; + } + } + return 0; +} + +static int gve_unregister_xdp_qpls(struct gve_priv *priv) +{ + int start_id; + int err; + int i; + + start_id = gve_tx_qpl_id(priv, gve_xdp_tx_start_queue_id(priv)); + for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) { + err = gve_adminq_unregister_page_list(priv, priv->qpls[i].id); + /* This failure will trigger a reset - no need to clean up */ + if (err) { + netif_err(priv, drv, priv->dev, + "Failed to unregister queue page list %d\n", + priv->qpls[i].id); + return err; + } + } return 0; } static int gve_unregister_qpls(struct gve_priv *priv) { - int num_qpls = gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv); + int start_id; int err; int i; - for (i = 0; i < num_qpls; i++) { + start_id = gve_tx_start_qpl_id(priv); + for (i = start_id; i < start_id + gve_num_tx_qpls(priv); i++) { + err = gve_adminq_unregister_page_list(priv, priv->qpls[i].id); + /* This failure will trigger a reset - no need to clean up */ + if (err) { + netif_err(priv, drv, priv->dev, + "Failed to unregister queue page list %d\n", + priv->qpls[i].id); + return err; + } + } + + start_id = gve_rx_start_qpl_id(priv); + for (i = start_id; i < start_id + gve_num_rx_qpls(priv); i++) { err = gve_adminq_unregister_page_list(priv, priv->qpls[i].id); /* This failure will trigger a reset - no need to clean up */ if (err) { @@ -620,22 +700,44 @@ 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); int err; int i; - err = gve_adminq_create_tx_queues(priv, priv->tx_cfg.num_queues); + err = gve_adminq_create_tx_queues(priv, 0, num_tx_queues); if (err) { netif_err(priv, drv, priv->dev, "failed to create %d tx queues\n", - priv->tx_cfg.num_queues); + num_tx_queues); /* This failure will trigger a reset - no need to clean * up */ return err; } netif_dbg(priv, drv, priv->dev, "created %d tx queues\n", - priv->tx_cfg.num_queues); + num_tx_queues); err = gve_adminq_create_rx_queues(priv, priv->rx_cfg.num_queues); if (err) { @@ -668,6 +770,23 @@ static int gve_create_rings(struct gve_priv *priv) return 0; } +static void add_napi_init_xdp_sync_stats(struct gve_priv *priv, + int (*napi_poll)(struct napi_struct *napi, + int budget)) +{ + int start_id = gve_xdp_tx_start_queue_id(priv); + int i; + + /* Add xdp tx napi & init sync stats*/ + for (i = start_id; i < start_id + priv->num_xdp_queues; i++) { + int ntfy_idx = gve_tx_idx_to_ntfy(priv, i); + + u64_stats_init(&priv->tx[i].statss); + priv->tx[i].ntfy_id = ntfy_idx; + gve_add_napi(priv, ntfy_idx, napi_poll); + } +} + static void add_napi_init_sync_stats(struct gve_priv *priv, int (*napi_poll)(struct napi_struct *napi, int budget)) @@ -675,7 +794,7 @@ static void add_napi_init_sync_stats(struct gve_priv *priv, int i; /* Add tx napi & init sync stats*/ - for (i = 0; i < priv->tx_cfg.num_queues; i++) { + for (i = 0; i < gve_num_tx_queues(priv); i++) { int ntfy_idx = gve_tx_idx_to_ntfy(priv, i); u64_stats_init(&priv->tx[i].statss); @@ -692,34 +811,51 @@ static void add_napi_init_sync_stats(struct gve_priv *priv, } } -static void gve_tx_free_rings(struct gve_priv *priv) +static void gve_tx_free_rings(struct gve_priv *priv, int start_id, int num_rings) { if (gve_is_gqi(priv)) { - gve_tx_free_rings_gqi(priv); + gve_tx_free_rings_gqi(priv, start_id, num_rings); } else { gve_tx_free_rings_dqo(priv); } } +static int gve_alloc_xdp_rings(struct gve_priv *priv) +{ + int start_id; + int err = 0; + + if (!priv->num_xdp_queues) + return 0; + + start_id = gve_xdp_tx_start_queue_id(priv); + err = gve_tx_alloc_rings(priv, start_id, priv->num_xdp_queues); + if (err) + return err; + add_napi_init_xdp_sync_stats(priv, gve_napi_poll); + + return 0; +} + static int gve_alloc_rings(struct gve_priv *priv) { int err; /* Setup tx rings */ - priv->tx = kvcalloc(priv->tx_cfg.num_queues, sizeof(*priv->tx), + priv->tx = kvcalloc(priv->tx_cfg.max_queues, sizeof(*priv->tx), GFP_KERNEL); if (!priv->tx) return -ENOMEM; if (gve_is_gqi(priv)) - err = gve_tx_alloc_rings(priv); + err = gve_tx_alloc_rings(priv, 0, gve_num_tx_queues(priv)); else err = gve_tx_alloc_rings_dqo(priv); if (err) goto free_tx; /* Setup rx rings */ - priv->rx = kvcalloc(priv->rx_cfg.num_queues, sizeof(*priv->rx), + priv->rx = kvcalloc(priv->rx_cfg.max_queues, sizeof(*priv->rx), GFP_KERNEL); if (!priv->rx) { err = -ENOMEM; @@ -744,18 +880,39 @@ static int gve_alloc_rings(struct gve_priv *priv) kvfree(priv->rx); priv->rx = NULL; free_tx_queue: - gve_tx_free_rings(priv); + gve_tx_free_rings(priv, 0, gve_num_tx_queues(priv)); free_tx: kvfree(priv->tx); priv->tx = NULL; 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); int err; - err = gve_adminq_destroy_tx_queues(priv, priv->tx_cfg.num_queues); + err = gve_adminq_destroy_tx_queues(priv, 0, num_tx_queues); if (err) { netif_err(priv, drv, priv->dev, "failed to destroy tx queues\n"); @@ -782,17 +939,33 @@ static void gve_rx_free_rings(struct gve_priv *priv) gve_rx_free_rings_dqo(priv); } +static void gve_free_xdp_rings(struct gve_priv *priv) +{ + int ntfy_idx, start_id; + int i; + + start_id = gve_xdp_tx_start_queue_id(priv); + if (priv->tx) { + for (i = start_id; i < start_id + priv->num_xdp_queues; i++) { + ntfy_idx = gve_tx_idx_to_ntfy(priv, i); + gve_remove_napi(priv, ntfy_idx); + } + gve_tx_free_rings(priv, start_id, priv->num_xdp_queues); + } +} + static void gve_free_rings(struct gve_priv *priv) { + int num_tx_queues = gve_num_tx_queues(priv); int ntfy_idx; int i; if (priv->tx) { - for (i = 0; i < priv->tx_cfg.num_queues; i++) { + for (i = 0; i < num_tx_queues; i++) { ntfy_idx = gve_tx_idx_to_ntfy(priv, i); gve_remove_napi(priv, ntfy_idx); } - gve_tx_free_rings(priv); + gve_tx_free_rings(priv, 0, num_tx_queues); kvfree(priv->tx); priv->tx = NULL; } @@ -889,40 +1062,68 @@ static void gve_free_queue_page_list(struct gve_priv *priv, u32 id) qpl->page_buses[i], gve_qpl_dma_dir(priv, id)); kvfree(qpl->page_buses); + qpl->page_buses = NULL; free_pages: kvfree(qpl->pages); + qpl->pages = NULL; priv->num_registered_pages -= qpl->num_entries; } +static int gve_alloc_xdp_qpls(struct gve_priv *priv) +{ + int start_id; + int i, j; + int err; + + start_id = gve_tx_qpl_id(priv, gve_xdp_tx_start_queue_id(priv)); + for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) { + err = gve_alloc_queue_page_list(priv, i, + priv->tx_pages_per_qpl); + if (err) + goto free_qpls; + } + + return 0; + +free_qpls: + for (j = start_id; j <= i; j++) + gve_free_queue_page_list(priv, j); + return err; +} + static int gve_alloc_qpls(struct gve_priv *priv) { - int num_qpls = gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv); + int max_queues = priv->tx_cfg.max_queues + priv->rx_cfg.max_queues; + int start_id; int i, j; int err; - if (num_qpls == 0) + if (priv->queue_format != GVE_GQI_QPL_FORMAT) return 0; - priv->qpls = kvcalloc(num_qpls, sizeof(*priv->qpls), GFP_KERNEL); + priv->qpls = kvcalloc(max_queues, sizeof(*priv->qpls), GFP_KERNEL); if (!priv->qpls) return -ENOMEM; - for (i = 0; i < gve_num_tx_qpls(priv); i++) { + start_id = gve_tx_start_qpl_id(priv); + for (i = start_id; i < start_id + gve_num_tx_qpls(priv); i++) { err = gve_alloc_queue_page_list(priv, i, priv->tx_pages_per_qpl); if (err) goto free_qpls; } - for (; i < num_qpls; i++) { + + start_id = gve_rx_start_qpl_id(priv); + for (i = start_id; i < start_id + gve_num_rx_qpls(priv); i++) { err = gve_alloc_queue_page_list(priv, i, priv->rx_data_slot_cnt); if (err) goto free_qpls; } - priv->qpl_cfg.qpl_map_size = BITS_TO_LONGS(num_qpls) * + priv->qpl_cfg.qpl_map_size = BITS_TO_LONGS(max_queues) * sizeof(unsigned long) * BITS_PER_BYTE; - priv->qpl_cfg.qpl_id_map = kvcalloc(BITS_TO_LONGS(num_qpls), + priv->qpl_cfg.qpl_id_map = kvcalloc(BITS_TO_LONGS(max_queues), sizeof(unsigned long), GFP_KERNEL); if (!priv->qpl_cfg.qpl_id_map) { err = -ENOMEM; @@ -935,23 +1136,36 @@ static int gve_alloc_qpls(struct gve_priv *priv) for (j = 0; j <= i; j++) gve_free_queue_page_list(priv, j); kvfree(priv->qpls); + priv->qpls = NULL; return err; } +static void gve_free_xdp_qpls(struct gve_priv *priv) +{ + int start_id; + int i; + + start_id = gve_tx_qpl_id(priv, gve_xdp_tx_start_queue_id(priv)); + for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) + gve_free_queue_page_list(priv, i); +} + static void gve_free_qpls(struct gve_priv *priv) { - int num_qpls = gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv); + int max_queues = priv->tx_cfg.max_queues + priv->rx_cfg.max_queues; int i; - if (num_qpls == 0) + if (!priv->qpls) return; kvfree(priv->qpl_cfg.qpl_id_map); + priv->qpl_cfg.qpl_id_map = NULL; - for (i = 0; i < num_qpls; i++) + for (i = 0; i < max_queues; i++) gve_free_queue_page_list(priv, i); kvfree(priv->qpls); + priv->qpls = NULL; } /* Use this to schedule a reset when the device is capable of continuing @@ -969,11 +1183,109 @@ static int gve_reset_recovery(struct gve_priv *priv, bool was_up); static void gve_turndown(struct gve_priv *priv); static void gve_turnup(struct gve_priv *priv); +static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev) +{ + struct napi_struct *napi; + struct gve_rx_ring *rx; + int err = 0; + int i, j; + u32 tx_qid; + + if (!priv->num_xdp_queues) + return 0; + + for (i = 0; i < priv->rx_cfg.num_queues; i++) { + rx = &priv->rx[i]; + napi = &priv->ntfy_blocks[rx->ntfy_id].napi; + + err = xdp_rxq_info_reg(&rx->xdp_rxq, dev, i, + napi->napi_id); + if (err) + goto err; + err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL); + if (err) + goto err; + rx->xsk_pool = xsk_get_pool_from_qid(dev, i); + if (rx->xsk_pool) { + err = xdp_rxq_info_reg(&rx->xsk_rxq, dev, i, + napi->napi_id); + if (err) + goto err; + err = xdp_rxq_info_reg_mem_model(&rx->xsk_rxq, + MEM_TYPE_XSK_BUFF_POOL, NULL); + if (err) + goto err; + xsk_pool_set_rxq_info(rx->xsk_pool, + &rx->xsk_rxq); + } + } + + for (i = 0; i < priv->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); + } + return 0; + +err: + for (j = i; j >= 0; j--) { + rx = &priv->rx[j]; + if (xdp_rxq_info_is_reg(&rx->xdp_rxq)) + xdp_rxq_info_unreg(&rx->xdp_rxq); + if (xdp_rxq_info_is_reg(&rx->xsk_rxq)) + xdp_rxq_info_unreg(&rx->xsk_rxq); + } + return err; +} + +static void gve_unreg_xdp_info(struct gve_priv *priv) +{ + int i, tx_qid; + + if (!priv->num_xdp_queues) + return; + + for (i = 0; i < priv->rx_cfg.num_queues; i++) { + struct gve_rx_ring *rx = &priv->rx[i]; + + xdp_rxq_info_unreg(&rx->xdp_rxq); + if (rx->xsk_pool) { + xdp_rxq_info_unreg(&rx->xsk_rxq); + rx->xsk_pool = NULL; + } + } + + for (i = 0; i < priv->num_xdp_queues; i++) { + tx_qid = gve_xdp_tx_queue_id(priv, i); + priv->tx[tx_qid].xsk_pool = NULL; + } +} + +static void gve_drain_page_cache(struct gve_priv *priv) +{ + struct page_frag_cache *nc; + int i; + + for (i = 0; i < priv->rx_cfg.num_queues; i++) { + nc = &priv->rx[i].page_cache; + if (nc->va) { + __page_frag_cache_drain(virt_to_page(nc->va), + nc->pagecnt_bias); + nc->va = NULL; + } + } +} + static int gve_open(struct net_device *dev) { struct gve_priv *priv = netdev_priv(dev); int err; + if (priv->xdp_prog) + priv->num_xdp_queues = priv->rx_cfg.num_queues; + else + priv->num_xdp_queues = 0; + err = gve_alloc_qpls(priv); if (err) return err; @@ -989,6 +1301,10 @@ static int gve_open(struct net_device *dev) if (err) goto free_rings; + err = gve_reg_xdp_info(priv, dev); + if (err) + goto free_rings; + err = gve_register_qpls(priv); if (err) goto reset; @@ -1043,6 +1359,7 @@ static int gve_close(struct net_device *dev) netif_carrier_off(dev); if (gve_get_device_rings_ok(priv)) { gve_turndown(priv); + gve_drain_page_cache(priv); err = gve_destroy_rings(priv); if (err) goto err; @@ -1053,6 +1370,7 @@ static int gve_close(struct net_device *dev) } del_timer_sync(&priv->stats_report_timer); + gve_unreg_xdp_info(priv); gve_free_rings(priv); gve_free_qpls(priv); priv->interface_down_cnt++; @@ -1069,6 +1387,306 @@ static int gve_close(struct net_device *dev) return gve_reset_recovery(priv, false); } +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); + gve_free_xdp_qpls(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->tx_cfg.num_queues; + + err = gve_alloc_xdp_qpls(priv); + if (err) + goto err; + + err = gve_alloc_xdp_rings(priv); + if (err) + goto free_xdp_qpls; + + 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); +free_xdp_qpls: + gve_free_xdp_qpls(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)) + return; + + if (link_status == netif_carrier_ok(priv->dev)) + return; + + if (link_status) { + netdev_info(priv->dev, "Device link is up.\n"); + netif_carrier_on(priv->dev); + } else { + netdev_info(priv->dev, "Device link is down.\n"); + netif_carrier_off(priv->dev); + } +} + +static int gve_set_xdp(struct gve_priv *priv, struct bpf_prog *prog, + struct netlink_ext_ack *extack) +{ + struct bpf_prog *old_prog; + int err = 0; + u32 status; + + old_prog = READ_ONCE(priv->xdp_prog); + if (!netif_carrier_ok(priv->dev)) { + WRITE_ONCE(priv->xdp_prog, prog); + if (old_prog) + bpf_prog_put(old_prog); + 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; + } + 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; +} + +static int gve_xsk_pool_enable(struct net_device *dev, + struct xsk_buff_pool *pool, + u16 qid) +{ + struct gve_priv *priv = netdev_priv(dev); + struct napi_struct *napi; + struct gve_rx_ring *rx; + int tx_qid; + int err; + + if (qid >= priv->rx_cfg.num_queues) { + dev_err(&priv->pdev->dev, "xsk pool invalid qid %d", qid); + return -EINVAL; + } + if (xsk_pool_get_rx_frame_size(pool) < + priv->dev->max_mtu + sizeof(struct ethhdr)) { + dev_err(&priv->pdev->dev, "xsk pool frame_len too small"); + return -EINVAL; + } + + err = xsk_pool_dma_map(pool, &priv->pdev->dev, + DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING); + if (err) + return err; + + /* If XDP prog is not installed, return */ + if (!priv->xdp_prog) + return 0; + + rx = &priv->rx[qid]; + napi = &priv->ntfy_blocks[rx->ntfy_id].napi; + err = xdp_rxq_info_reg(&rx->xsk_rxq, dev, qid, napi->napi_id); + if (err) + goto err; + + err = xdp_rxq_info_reg_mem_model(&rx->xsk_rxq, + MEM_TYPE_XSK_BUFF_POOL, NULL); + if (err) + goto err; + + xsk_pool_set_rxq_info(pool, &rx->xsk_rxq); + rx->xsk_pool = pool; + + tx_qid = gve_xdp_tx_queue_id(priv, qid); + priv->tx[tx_qid].xsk_pool = pool; + + return 0; +err: + if (xdp_rxq_info_is_reg(&rx->xsk_rxq)) + xdp_rxq_info_unreg(&rx->xsk_rxq); + + xsk_pool_dma_unmap(pool, + DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING); + return err; +} + +static int gve_xsk_pool_disable(struct net_device *dev, + u16 qid) +{ + struct gve_priv *priv = netdev_priv(dev); + struct napi_struct *napi_rx; + struct napi_struct *napi_tx; + struct xsk_buff_pool *pool; + int tx_qid; + + pool = xsk_get_pool_from_qid(dev, qid); + if (!pool) + return -EINVAL; + 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; + goto done; + } + + napi_rx = &priv->ntfy_blocks[priv->rx[qid].ntfy_id].napi; + napi_disable(napi_rx); /* make sure current rx poll is done */ + + napi_tx = &priv->ntfy_blocks[priv->tx[tx_qid].ntfy_id].napi; + napi_disable(napi_tx); /* make sure current tx poll is done */ + + priv->rx[qid].xsk_pool = NULL; + xdp_rxq_info_unreg(&priv->rx[qid].xsk_rxq); + priv->tx[tx_qid].xsk_pool = NULL; + smp_mb(); /* Make sure it is visible to the workers on datapath */ + + napi_enable(napi_rx); + if (gve_rx_work_pending(&priv->rx[qid])) + napi_schedule(napi_rx); + + napi_enable(napi_tx); + if (gve_tx_clean_pending(priv, &priv->tx[tx_qid])) + napi_schedule(napi_tx); + +done: + xsk_pool_dma_unmap(pool, + DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING); + return 0; +} + +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); + + 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++; + } + + return 0; +} + +static int verify_xdp_configuration(struct net_device *dev) +{ + struct gve_priv *priv = netdev_priv(dev); + + if (dev->features & NETIF_F_LRO) { + netdev_warn(dev, "XDP is not supported when LRO is on.\n"); + return -EOPNOTSUPP; + } + + if (priv->queue_format != GVE_GQI_QPL_FORMAT) { + netdev_warn(dev, "XDP is not supported in mode %d.\n", + priv->queue_format); + return -EOPNOTSUPP; + } + + if (dev->mtu > (PAGE_SIZE / 2) - sizeof(struct ethhdr) - GVE_RX_PAD) { + netdev_warn(dev, "XDP is not supported for mtu %d.\n", + dev->mtu); + return -EOPNOTSUPP; + } + + if (priv->rx_cfg.num_queues != priv->tx_cfg.num_queues || + (2 * priv->tx_cfg.num_queues > priv->tx_cfg.max_queues)) { + netdev_warn(dev, "XDP load failed: The number of configured RX queues %d should be equal to the number of configured TX queues %d and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues %d", + priv->rx_cfg.num_queues, + priv->tx_cfg.num_queues, + priv->tx_cfg.max_queues); + return -EINVAL; + } + return 0; +} + +static int gve_xdp(struct net_device *dev, struct netdev_bpf *xdp) +{ + struct gve_priv *priv = netdev_priv(dev); + int err; + + err = verify_xdp_configuration(dev); + if (err) + return err; + switch (xdp->command) { + case XDP_SETUP_PROG: + return gve_set_xdp(priv, xdp->prog, xdp->extack); + case XDP_SETUP_XSK_POOL: + if (xdp->xsk.pool) + return gve_xsk_pool_enable(dev, xdp->xsk.pool, xdp->xsk.queue_id); + else + return gve_xsk_pool_disable(dev, xdp->xsk.queue_id); + default: + return -EINVAL; + } +} + int gve_adjust_queues(struct gve_priv *priv, struct gve_queue_config new_rx_config, struct gve_queue_config new_tx_config) @@ -1118,7 +1736,7 @@ static void gve_turndown(struct gve_priv *priv) return; /* Disable napi to prevent more work from coming in */ - for (idx = 0; idx < priv->tx_cfg.num_queues; idx++) { + for (idx = 0; idx < gve_num_tx_queues(priv); idx++) { int ntfy_idx = gve_tx_idx_to_ntfy(priv, idx); struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; @@ -1146,7 +1764,7 @@ static void gve_turnup(struct gve_priv *priv) netif_tx_start_all_queues(priv->dev); /* Enable napi and unmask interrupts for all queues */ - for (idx = 0; idx < priv->tx_cfg.num_queues; idx++) { + for (idx = 0; idx < gve_num_tx_queues(priv); idx++) { int ntfy_idx = gve_tx_idx_to_ntfy(priv, idx); struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; @@ -1263,6 +1881,9 @@ static const struct net_device_ops gve_netdev_ops = { .ndo_get_stats64 = gve_get_stats, .ndo_tx_timeout = gve_tx_timeout, .ndo_set_features = gve_set_features, + .ndo_bpf = gve_xdp, + .ndo_xdp_xmit = gve_xdp_xmit, + .ndo_xsk_wakeup = gve_xsk_wakeup, }; static void gve_handle_status(struct gve_priv *priv, u32 status) @@ -1306,7 +1927,7 @@ void gve_handle_report_stats(struct gve_priv *priv) be64_add_cpu(&priv->stats_report->written_count, 1); /* tx stats */ if (priv->tx) { - for (idx = 0; idx < priv->tx_cfg.num_queues; idx++) { + for (idx = 0; idx < gve_num_tx_queues(priv); idx++) { u32 last_completion = 0; u32 tx_frames = 0; @@ -1369,23 +1990,6 @@ void gve_handle_report_stats(struct gve_priv *priv) } } -static void gve_handle_link_status(struct gve_priv *priv, bool link_status) -{ - if (!gve_get_napi_enabled(priv)) - return; - - if (link_status == netif_carrier_ok(priv->dev)) - return; - - if (link_status) { - netdev_info(priv->dev, "Device link is up.\n"); - netif_carrier_on(priv->dev); - } else { - netdev_info(priv->dev, "Device link is down.\n"); - netif_carrier_off(priv->dev); - } -} - /* Handle NIC status register changes, reset requests and report stats */ static void gve_service_task(struct work_struct *work) { @@ -1399,6 +2003,18 @@ static void gve_service_task(struct work_struct *work) gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status); } +static void gve_set_netdev_xdp_features(struct gve_priv *priv) +{ + 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; + } else { + priv->dev->xdp_features = 0; + } +} + static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) { int num_ntfy; @@ -1477,6 +2093,7 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) } setup_device: + gve_set_netdev_xdp_features(priv); err = gve_setup_device_resources(priv); if (!err) return 0; diff --git a/google/gve/gve_rx.c b/google/gve/gve_rx.c index 1f55137..d1da741 100644 --- a/google/gve/gve_rx.c +++ b/google/gve/gve_rx.c @@ -8,6 +8,9 @@ #include "gve_adminq.h" #include "gve_utils.h" #include +#include +#include +#include static void gve_rx_free_buffer(struct device *dev, struct gve_rx_slot_page_info *page_info, @@ -124,7 +127,7 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx) return -ENOMEM; if (!rx->data.raw_addressing) { - rx->data.qpl = gve_assign_rx_qpl(priv); + rx->data.qpl = gve_assign_rx_qpl(priv, rx->q_num); if (!rx->data.qpl) { kvfree(rx->data.page_info); rx->data.page_info = NULL; @@ -556,7 +559,7 @@ static struct sk_buff *gve_rx_skb(struct gve_priv *priv, struct gve_rx_ring *rx, if (len <= priv->rx_copybreak && is_only_frag) { /* Just copy small packets */ - skb = gve_rx_copy(netdev, napi, page_info, len, GVE_RX_PAD); + skb = gve_rx_copy(netdev, napi, page_info, len); if (skb) { u64_stats_update_begin(&rx->statss); rx->rx_copied_pkt++; @@ -591,6 +594,107 @@ static struct sk_buff *gve_rx_skb(struct gve_priv *priv, struct gve_rx_ring *rx, return skb; } +static int gve_xsk_pool_redirect(struct net_device *dev, + struct gve_rx_ring *rx, + void *data, int len, + struct bpf_prog *xdp_prog) +{ + struct xdp_buff *xdp; + int err; + + if (rx->xsk_pool->frame_len < len) + return -E2BIG; + xdp = xsk_buff_alloc(rx->xsk_pool); + if (!xdp) { + u64_stats_update_begin(&rx->statss); + rx->xdp_alloc_fails++; + u64_stats_update_end(&rx->statss); + return -ENOMEM; + } + xdp->data_end = xdp->data + len; + memcpy(xdp->data, data, len); + err = xdp_do_redirect(dev, xdp, xdp_prog); + if (err) + xsk_buff_free(xdp); + return err; +} + +static int gve_xdp_redirect(struct net_device *dev, struct gve_rx_ring *rx, + struct xdp_buff *orig, struct bpf_prog *xdp_prog) +{ + int total_len, len = orig->data_end - orig->data; + int headroom = XDP_PACKET_HEADROOM; + struct xdp_buff new; + void *frame; + int err; + + if (rx->xsk_pool) + return gve_xsk_pool_redirect(dev, rx, orig->data, + len, xdp_prog); + + total_len = headroom + SKB_DATA_ALIGN(len) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + frame = page_frag_alloc(&rx->page_cache, total_len, GFP_ATOMIC); + if (!frame) { + u64_stats_update_begin(&rx->statss); + rx->xdp_alloc_fails++; + u64_stats_update_end(&rx->statss); + return -ENOMEM; + } + xdp_init_buff(&new, total_len, &rx->xdp_rxq); + xdp_prepare_buff(&new, frame, headroom, len, false); + memcpy(new.data, orig->data, len); + + err = xdp_do_redirect(dev, &new, xdp_prog); + if (err) + page_frag_free(frame); + + return err; +} + +static void gve_xdp_done(struct gve_priv *priv, struct gve_rx_ring *rx, + struct xdp_buff *xdp, struct bpf_prog *xprog, + int xdp_act) +{ + struct gve_tx_ring *tx; + int tx_qid; + int err; + + switch (xdp_act) { + case XDP_ABORTED: + case XDP_DROP: + default: + break; + case XDP_TX: + tx_qid = gve_xdp_tx_queue_id(priv, rx->q_num); + tx = &priv->tx[tx_qid]; + spin_lock(&tx->xdp_lock); + err = gve_xdp_xmit_one(priv, tx, xdp->data, + xdp->data_end - xdp->data, NULL); + spin_unlock(&tx->xdp_lock); + + if (unlikely(err)) { + u64_stats_update_begin(&rx->statss); + rx->xdp_tx_errors++; + u64_stats_update_end(&rx->statss); + } + break; + case XDP_REDIRECT: + err = gve_xdp_redirect(priv->dev, rx, xdp, xprog); + + if (unlikely(err)) { + u64_stats_update_begin(&rx->statss); + rx->xdp_redirect_errors++; + u64_stats_update_end(&rx->statss); + } + break; + } + u64_stats_update_begin(&rx->statss); + if ((u32)xdp_act < GVE_XDP_ACTIONS) + rx->xdp_actions[xdp_act]++; + u64_stats_update_end(&rx->statss); +} + #define GVE_PKTCONT_BIT_IS_SET(x) (GVE_RXF_PKT_CONT & (x)) static void gve_rx(struct gve_rx_ring *rx, netdev_features_t feat, struct gve_rx_desc *desc, u32 idx, @@ -603,9 +707,12 @@ static void gve_rx(struct gve_rx_ring *rx, netdev_features_t feat, union gve_rx_data_slot *data_slot; struct gve_priv *priv = rx->gve; struct sk_buff *skb = NULL; + struct bpf_prog *xprog; + struct xdp_buff xdp; dma_addr_t page_bus; void *va; + u16 len = frag_size; struct napi_struct *napi = &priv->ntfy_blocks[rx->ntfy_id].napi; bool is_first_frag = ctx->frag_cnt == 0; @@ -645,9 +752,35 @@ static void gve_rx(struct gve_rx_ring *rx, netdev_features_t feat, dma_sync_single_for_cpu(&priv->pdev->dev, page_bus, PAGE_SIZE, DMA_FROM_DEVICE); page_info->pad = is_first_frag ? GVE_RX_PAD : 0; + len -= page_info->pad; frag_size -= page_info->pad; - skb = gve_rx_skb(priv, rx, page_info, napi, frag_size, + xprog = READ_ONCE(priv->xdp_prog); + if (xprog && is_only_frag) { + void *old_data; + int xdp_act; + + xdp_init_buff(&xdp, rx->packet_buffer_size, &rx->xdp_rxq); + xdp_prepare_buff(&xdp, page_info->page_address + + page_info->page_offset, GVE_RX_PAD, + len, false); + old_data = xdp.data; + xdp_act = bpf_prog_run_xdp(xprog, &xdp); + if (xdp_act != XDP_PASS) { + gve_xdp_done(priv, rx, &xdp, xprog, xdp_act); + ctx->total_size += frag_size; + goto finish_ok_pkt; + } + + page_info->pad += xdp.data - old_data; + len = xdp.data_end - xdp.data; + + u64_stats_update_begin(&rx->statss); + rx->xdp_actions[XDP_PASS]++; + u64_stats_update_end(&rx->statss); + } + + skb = gve_rx_skb(priv, rx, page_info, napi, len, data_slot, is_only_frag); if (!skb) { u64_stats_update_begin(&rx->statss); @@ -773,6 +906,8 @@ static bool gve_rx_refill_buffers(struct gve_priv *priv, struct gve_rx_ring *rx) static int gve_clean_rx_done(struct gve_rx_ring *rx, int budget, netdev_features_t feat) { + u64 xdp_redirects = rx->xdp_actions[XDP_REDIRECT]; + u64 xdp_txs = rx->xdp_actions[XDP_TX]; struct gve_rx_ctx *ctx = &rx->ctx; struct gve_priv *priv = rx->gve; struct gve_rx_cnts cnts = {0}; @@ -820,6 +955,12 @@ static int gve_clean_rx_done(struct gve_rx_ring *rx, int budget, u64_stats_update_end(&rx->statss); } + if (xdp_txs != rx->xdp_actions[XDP_TX]) + gve_xdp_tx_flush(priv, rx->q_num); + + if (xdp_redirects != rx->xdp_actions[XDP_REDIRECT]) + xdp_do_flush(); + /* restock ring slots */ if (!rx->data.raw_addressing) { /* In QPL mode buffs are refilled as the desc are processed */ diff --git a/google/gve/gve_rx_dqo.c b/google/gve/gve_rx_dqo.c index 630f42a..e57b73e 100644 --- a/google/gve/gve_rx_dqo.c +++ b/google/gve/gve_rx_dqo.c @@ -568,7 +568,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, if (eop && buf_len <= priv->rx_copybreak) { rx->ctx.skb_head = gve_rx_copy(priv->dev, napi, - &buf_state->page_info, buf_len, 0); + &buf_state->page_info, buf_len); if (unlikely(!rx->ctx.skb_head)) goto error; rx->ctx.skb_tail = rx->ctx.skb_head; diff --git a/google/gve/gve_tx.c b/google/gve/gve_tx.c index 4888bf0..e50510b 100644 --- a/google/gve/gve_tx.c +++ b/google/gve/gve_tx.c @@ -11,6 +11,7 @@ #include #include #include +#include static inline void gve_tx_put_doorbell(struct gve_priv *priv, struct gve_queue_resources *q_resources, @@ -19,6 +20,14 @@ static inline void gve_tx_put_doorbell(struct gve_priv *priv, iowrite32be(val, &priv->db_bar2[be32_to_cpu(q_resources->db_index)]); } +void gve_xdp_tx_flush(struct gve_priv *priv, u32 xdp_qid) +{ + u32 tx_qid = gve_xdp_tx_queue_id(priv, xdp_qid); + struct gve_tx_ring *tx = &priv->tx[tx_qid]; + + gve_tx_put_doorbell(priv, tx->q_resources, tx->req); +} + /* gvnic can only transmit from a Registered Segment. * We copy skb payloads into the registered segment before writing Tx * descriptors and ringing the Tx doorbell. @@ -132,6 +141,58 @@ static void gve_tx_free_fifo(struct gve_tx_fifo *fifo, size_t bytes) atomic_add(bytes, &fifo->available); } +static size_t gve_tx_clear_buffer_state(struct gve_tx_buffer_state *info) +{ + size_t space_freed = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(info->iov); i++) { + space_freed += info->iov[i].iov_len + info->iov[i].iov_padding; + info->iov[i].iov_len = 0; + info->iov[i].iov_padding = 0; + } + return space_freed; +} + +static int gve_clean_xdp_done(struct gve_priv *priv, struct gve_tx_ring *tx, + u32 to_do) +{ + struct gve_tx_buffer_state *info; + u32 clean_end = tx->done + to_do; + u64 pkts = 0, bytes = 0; + size_t space_freed = 0; + u32 xsk_complete = 0; + u32 idx; + + for (; tx->done < clean_end; tx->done++) { + idx = tx->done & tx->mask; + info = &tx->info[idx]; + + if (unlikely(!info->xdp.size)) + continue; + + bytes += info->xdp.size; + pkts++; + xsk_complete += info->xdp.is_xsk; + + info->xdp.size = 0; + if (info->xdp_frame) { + xdp_return_frame(info->xdp_frame); + info->xdp_frame = NULL; + } + space_freed += gve_tx_clear_buffer_state(info); + } + + gve_tx_free_fifo(&tx->tx_fifo, space_freed); + if (xsk_complete > 0 && tx->xsk_pool) + xsk_tx_completed(tx->xsk_pool, xsk_complete); + u64_stats_update_begin(&tx->statss); + tx->bytes_done += bytes; + tx->pkt_done += pkts; + u64_stats_update_end(&tx->statss); + return pkts; +} + static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx, u32 to_do, bool try_to_wake); @@ -144,8 +205,12 @@ static void gve_tx_free_ring(struct gve_priv *priv, int idx) gve_tx_remove_from_block(priv, idx); slots = tx->mask + 1; - gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false); - netdev_tx_reset_queue(tx->netdev_txq); + if (tx->q_num < priv->tx_cfg.num_queues) { + gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false); + netdev_tx_reset_queue(tx->netdev_txq); + } else { + gve_clean_xdp_done(priv, tx, priv->tx_desc_cnt); + } dma_free_coherent(hdev, sizeof(*tx->q_resources), tx->q_resources, tx->q_resources_bus); @@ -177,6 +242,7 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) /* Make sure everything is zeroed to start */ memset(tx, 0, sizeof(*tx)); spin_lock_init(&tx->clean_lock); + spin_lock_init(&tx->xdp_lock); tx->q_num = idx; tx->mask = slots - 1; @@ -195,7 +261,7 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) tx->raw_addressing = priv->queue_format == GVE_GQI_RDA_FORMAT; tx->dev = &priv->pdev->dev; if (!tx->raw_addressing) { - tx->tx_fifo.qpl = gve_assign_tx_qpl(priv); + tx->tx_fifo.qpl = gve_assign_tx_qpl(priv, idx); if (!tx->tx_fifo.qpl) goto abort_with_desc; /* map Tx FIFO */ @@ -213,7 +279,8 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) netif_dbg(priv, drv, priv->dev, "tx[%d]->bus=%lx\n", idx, (unsigned long)tx->bus); - tx->netdev_txq = netdev_get_tx_queue(priv->dev, idx); + if (idx < priv->tx_cfg.num_queues) + tx->netdev_txq = netdev_get_tx_queue(priv->dev, idx); gve_tx_add_to_block(priv, idx); return 0; @@ -233,12 +300,12 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) return -ENOMEM; } -int gve_tx_alloc_rings(struct gve_priv *priv) +int gve_tx_alloc_rings(struct gve_priv *priv, int start_id, int num_rings) { int err = 0; int i; - for (i = 0; i < priv->tx_cfg.num_queues; i++) { + for (i = start_id; i < start_id + num_rings; i++) { err = gve_tx_alloc_ring(priv, i); if (err) { netif_err(priv, drv, priv->dev, @@ -251,17 +318,17 @@ int gve_tx_alloc_rings(struct gve_priv *priv) if (err) { int j; - for (j = 0; j < i; j++) + for (j = start_id; j < i; j++) gve_tx_free_ring(priv, j); } return err; } -void gve_tx_free_rings_gqi(struct gve_priv *priv) +void gve_tx_free_rings_gqi(struct gve_priv *priv, int start_id, int num_rings) { int i; - for (i = 0; i < priv->tx_cfg.num_queues; i++) + for (i = start_id; i < start_id + num_rings; i++) gve_tx_free_ring(priv, i); } @@ -374,18 +441,18 @@ static int gve_maybe_stop_tx(struct gve_priv *priv, struct gve_tx_ring *tx, } static void gve_tx_fill_pkt_desc(union gve_tx_desc *pkt_desc, - struct sk_buff *skb, bool is_gso, + u16 csum_offset, u8 ip_summed, bool is_gso, int l4_hdr_offset, u32 desc_cnt, - u16 hlen, u64 addr) + u16 hlen, u64 addr, u16 pkt_len) { /* l4_hdr_offset and csum_offset are in units of 16-bit words */ if (is_gso) { pkt_desc->pkt.type_flags = GVE_TXD_TSO | GVE_TXF_L4CSUM; - pkt_desc->pkt.l4_csum_offset = skb->csum_offset >> 1; + pkt_desc->pkt.l4_csum_offset = csum_offset >> 1; pkt_desc->pkt.l4_hdr_offset = l4_hdr_offset >> 1; - } else if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { + } else if (likely(ip_summed == CHECKSUM_PARTIAL)) { pkt_desc->pkt.type_flags = GVE_TXD_STD | GVE_TXF_L4CSUM; - pkt_desc->pkt.l4_csum_offset = skb->csum_offset >> 1; + pkt_desc->pkt.l4_csum_offset = csum_offset >> 1; pkt_desc->pkt.l4_hdr_offset = l4_hdr_offset >> 1; } else { pkt_desc->pkt.type_flags = GVE_TXD_STD; @@ -393,7 +460,7 @@ static void gve_tx_fill_pkt_desc(union gve_tx_desc *pkt_desc, pkt_desc->pkt.l4_hdr_offset = 0; } pkt_desc->pkt.desc_cnt = desc_cnt; - pkt_desc->pkt.len = cpu_to_be16(skb->len); + pkt_desc->pkt.len = cpu_to_be16(pkt_len); pkt_desc->pkt.seg_len = cpu_to_be16(hlen); pkt_desc->pkt.seg_addr = cpu_to_be64(addr); } @@ -412,15 +479,16 @@ static void gve_tx_fill_mtd_desc(union gve_tx_desc *mtd_desc, } static void gve_tx_fill_seg_desc(union gve_tx_desc *seg_desc, - struct sk_buff *skb, bool is_gso, + u16 l3_offset, u16 gso_size, + bool is_gso_v6, bool is_gso, u16 len, u64 addr) { seg_desc->seg.type_flags = GVE_TXD_SEG; if (is_gso) { - if (skb_is_gso_v6(skb)) + if (is_gso_v6) seg_desc->seg.type_flags |= GVE_TXSF_IPV6; - seg_desc->seg.l3_offset = skb_network_offset(skb) >> 1; - seg_desc->seg.mss = cpu_to_be16(skb_shinfo(skb)->gso_size); + seg_desc->seg.l3_offset = l3_offset >> 1; + seg_desc->seg.mss = cpu_to_be16(gso_size); } seg_desc->seg.seg_len = cpu_to_be16(len); seg_desc->seg.seg_addr = cpu_to_be64(addr); @@ -473,9 +541,10 @@ static int gve_tx_add_skb_copy(struct gve_priv *priv, struct gve_tx_ring *tx, st payload_nfrags = gve_tx_alloc_fifo(&tx->tx_fifo, skb->len - hlen, &info->iov[payload_iov]); - gve_tx_fill_pkt_desc(pkt_desc, skb, is_gso, l4_hdr_offset, + gve_tx_fill_pkt_desc(pkt_desc, skb->csum_offset, skb->ip_summed, + is_gso, l4_hdr_offset, 1 + mtd_desc_nr + payload_nfrags, hlen, - info->iov[hdr_nfrags - 1].iov_offset); + info->iov[hdr_nfrags - 1].iov_offset, skb->len); skb_copy_bits(skb, 0, tx->tx_fifo.base + info->iov[hdr_nfrags - 1].iov_offset, @@ -494,7 +563,9 @@ static int gve_tx_add_skb_copy(struct gve_priv *priv, struct gve_tx_ring *tx, st next_idx = (tx->req + 1 + mtd_desc_nr + i - payload_iov) & tx->mask; seg_desc = &tx->desc[next_idx]; - gve_tx_fill_seg_desc(seg_desc, skb, is_gso, + gve_tx_fill_seg_desc(seg_desc, skb_network_offset(skb), + skb_shinfo(skb)->gso_size, + skb_is_gso_v6(skb), is_gso, info->iov[i].iov_len, info->iov[i].iov_offset); @@ -552,8 +623,9 @@ static int gve_tx_add_skb_no_copy(struct gve_priv *priv, struct gve_tx_ring *tx, if (mtd_desc_nr) num_descriptors++; - gve_tx_fill_pkt_desc(pkt_desc, skb, is_gso, l4_hdr_offset, - num_descriptors, hlen, addr); + gve_tx_fill_pkt_desc(pkt_desc, skb->csum_offset, skb->ip_summed, + is_gso, l4_hdr_offset, + num_descriptors, hlen, addr, skb->len); if (mtd_desc_nr) { idx = (idx + 1) & tx->mask; @@ -569,7 +641,9 @@ static int gve_tx_add_skb_no_copy(struct gve_priv *priv, struct gve_tx_ring *tx, addr += hlen; idx = (idx + 1) & tx->mask; seg_desc = &tx->desc[idx]; - gve_tx_fill_seg_desc(seg_desc, skb, is_gso, len, addr); + gve_tx_fill_seg_desc(seg_desc, skb_network_offset(skb), + skb_shinfo(skb)->gso_size, + skb_is_gso_v6(skb), is_gso, len, addr); } for (i = 0; i < shinfo->nr_frags; i++) { @@ -587,7 +661,9 @@ static int gve_tx_add_skb_no_copy(struct gve_priv *priv, struct gve_tx_ring *tx, dma_unmap_len_set(&tx->info[idx], len, len); dma_unmap_addr_set(&tx->info[idx], dma, addr); - gve_tx_fill_seg_desc(seg_desc, skb, is_gso, len, addr); + gve_tx_fill_seg_desc(seg_desc, skb_network_offset(skb), + skb_shinfo(skb)->gso_size, + skb_is_gso_v6(skb), is_gso, len, addr); } return num_descriptors; @@ -648,6 +724,103 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } +static int gve_tx_fill_xdp(struct gve_priv *priv, struct gve_tx_ring *tx, + void *data, int len, void *frame_p, bool is_xsk) +{ + int pad, nfrags, ndescs, iovi, offset; + struct gve_tx_buffer_state *info; + u32 reqi = tx->req; + + pad = gve_tx_fifo_pad_alloc_one_frag(&tx->tx_fifo, len); + if (pad >= GVE_TX_MAX_HEADER_SIZE) + pad = 0; + info = &tx->info[reqi & tx->mask]; + info->xdp_frame = frame_p; + info->xdp.size = len; + info->xdp.is_xsk = is_xsk; + + nfrags = gve_tx_alloc_fifo(&tx->tx_fifo, pad + len, + &info->iov[0]); + iovi = pad > 0; + ndescs = nfrags - iovi; + offset = 0; + + while (iovi < nfrags) { + if (!offset) + gve_tx_fill_pkt_desc(&tx->desc[reqi & tx->mask], 0, + CHECKSUM_NONE, false, 0, ndescs, + info->iov[iovi].iov_len, + info->iov[iovi].iov_offset, len); + else + gve_tx_fill_seg_desc(&tx->desc[reqi & tx->mask], + 0, 0, false, false, + info->iov[iovi].iov_len, + info->iov[iovi].iov_offset); + + memcpy(tx->tx_fifo.base + info->iov[iovi].iov_offset, + data + offset, info->iov[iovi].iov_len); + gve_dma_sync_for_device(&priv->pdev->dev, + tx->tx_fifo.qpl->page_buses, + info->iov[iovi].iov_offset, + info->iov[iovi].iov_len); + offset += info->iov[iovi].iov_len; + iovi++; + reqi++; + } + + return ndescs; +} + +int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, + u32 flags) +{ + struct gve_priv *priv = netdev_priv(dev); + struct gve_tx_ring *tx; + int i, err = 0, qid; + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + return -EINVAL; + + qid = gve_xdp_tx_queue_id(priv, + smp_processor_id() % priv->num_xdp_queues); + + tx = &priv->tx[qid]; + + spin_lock(&tx->xdp_lock); + for (i = 0; i < n; i++) { + err = gve_xdp_xmit_one(priv, tx, frames[i]->data, + frames[i]->len, frames[i]); + if (err) + break; + } + + if (flags & XDP_XMIT_FLUSH) + gve_tx_put_doorbell(priv, tx->q_resources, tx->req); + + spin_unlock(&tx->xdp_lock); + + u64_stats_update_begin(&tx->statss); + tx->xdp_xmit += n; + tx->xdp_xmit_errors += n - i; + u64_stats_update_end(&tx->statss); + + return i ? i : err; +} + +int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx, + void *data, int len, void *frame_p) +{ + int nsegs; + + if (!gve_can_tx(tx, len + GVE_TX_MAX_HEADER_SIZE - 1)) + return -EBUSY; + + nsegs = gve_tx_fill_xdp(priv, tx, data, len, frame_p, false); + tx->req += nsegs; + + return 0; +} + #define GVE_TX_START_THRESH PAGE_SIZE static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx, @@ -657,8 +830,8 @@ static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx, u64 pkts = 0, bytes = 0; size_t space_freed = 0; struct sk_buff *skb; - int i, j; u32 idx; + int j; for (j = 0; j < to_do; j++) { idx = tx->done & tx->mask; @@ -680,12 +853,7 @@ static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx, dev_consume_skb_any(skb); if (tx->raw_addressing) continue; - /* FIFO free */ - for (i = 0; i < ARRAY_SIZE(info->iov); i++) { - space_freed += info->iov[i].iov_len + info->iov[i].iov_padding; - info->iov[i].iov_len = 0; - info->iov[i].iov_padding = 0; - } + space_freed += gve_tx_clear_buffer_state(info); } } @@ -720,6 +888,70 @@ u32 gve_tx_load_event_counter(struct gve_priv *priv, return be32_to_cpu(counter); } +static int gve_xsk_tx(struct gve_priv *priv, struct gve_tx_ring *tx, + int budget) +{ + struct xdp_desc desc; + int sent = 0, nsegs; + void *data; + + 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; + 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); + tx->req += nsegs; + sent++; + } +out: + if (sent > 0) { + gve_tx_put_doorbell(priv, tx->q_resources, tx->req); + xsk_tx_release(tx->xsk_pool); + } + spin_unlock(&tx->xdp_lock); + 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; + + /* If budget is 0, do all the work */ + if (budget == 0) + budget = INT_MAX; + + /* 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; +} + bool gve_tx_poll(struct gve_notify_block *block, int budget) { struct gve_priv *priv = block->priv; diff --git a/google/gve/gve_utils.c b/google/gve/gve_utils.c index 6ba46ad..26e08d7 100644 --- a/google/gve/gve_utils.c +++ b/google/gve/gve_utils.c @@ -49,10 +49,10 @@ void gve_rx_add_to_block(struct gve_priv *priv, int queue_idx) } struct sk_buff *gve_rx_copy(struct net_device *dev, struct napi_struct *napi, - struct gve_rx_slot_page_info *page_info, u16 len, - u16 padding) + struct gve_rx_slot_page_info *page_info, u16 len) { - void *va = page_info->page_address + padding + page_info->page_offset; + void *va = page_info->page_address + page_info->page_offset + + page_info->pad; struct sk_buff *skb; skb = napi_alloc_skb(napi, len); diff --git a/google/gve/gve_utils.h b/google/gve/gve_utils.h index 7959594..324fd98 100644 --- a/google/gve/gve_utils.h +++ b/google/gve/gve_utils.h @@ -18,8 +18,7 @@ void gve_rx_remove_from_block(struct gve_priv *priv, int queue_idx); void gve_rx_add_to_block(struct gve_priv *priv, int queue_idx); struct sk_buff *gve_rx_copy(struct net_device *dev, struct napi_struct *napi, - struct gve_rx_slot_page_info *page_info, u16 len, - u16 pad); + struct gve_rx_slot_page_info *page_info, u16 len); /* Decrement pagecnt_bias. Set it back to INT_MAX if it reached zero. */ void gve_dec_pagecnt_bias(struct gve_rx_slot_page_info *page_info); diff --git a/patches/patch_xdp1.cocci b/patches/patch_xdp1.cocci new file mode 100644 index 0000000..8bde91d --- /dev/null +++ b/patches/patch_xdp1.cocci @@ -0,0 +1,307 @@ +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +#include ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +#include ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +#include ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +#include ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ +static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev) +{ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +... ++#else /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ ++ return 0; ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ +} + +@@ +@@ +static void gve_unreg_xdp_info(struct gve_priv *priv) +{ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +... ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ +} + +@@ +@@ +static void gve_drain_page_cache(struct gve_priv *priv) +{ ++#if LINUX_VERSION_CODE >= KERNEL_VERSION(4,10,0) + ... ++#endif /* LINUX_VERSION_CODE >= KERNEL_VERSION(4,10,0) */ +} + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_set_xdp(struct gve_priv *priv, struct bpf_prog *prog, + struct netlink_ext_ack *extack) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_xsk_pool_enable(struct net_device *dev, + struct xsk_buff_pool *pool, + u16 qid) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_xsk_pool_disable(struct net_device *dev, + u16 qid) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int verify_xdp_configuration(struct net_device *dev) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_xdp(struct net_device *dev, struct netdev_bpf *xdp) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +identifier gve_netdev_ops; +identifier gve_xdp, gve_xdp_xmit, gve_xsk_wakeup; +@@ +struct net_device_ops gve_netdev_ops = { ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) + .ndo_bpf = gve_xdp, + .ndo_xdp_xmit = gve_xdp_xmit, + .ndo_xsk_wakeup = gve_xsk_wakeup, ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ +}; + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_xsk_tx(struct gve_priv *priv, struct gve_tx_ring *tx, + int budget) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +type bool; +identifier gve_xdp_poll, block, budget; +identifier tx, repoll; +@@ +bool gve_xdp_poll(struct gve_notify_block *block, int budget) +{ +... ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) + if (tx->xsk_pool) { + ... + } + ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + /* If we still have work we want to repoll */ + return repoll; +} + + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) + if (xsk_complete > 0 && tx->xsk_pool) + xsk_tx_completed(tx->xsk_pool, xsk_complete); ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, + u32 flags) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx, + void *data, int len, void *frame_p) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_tx_fill_xdp(struct gve_priv *priv, struct gve_tx_ring *tx, + void *data, int len, void *frame_p, bool is_xsk) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_remove_xdp_queues(struct gve_priv *priv) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_add_xdp_queues(struct gve_priv *priv) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static void gve_free_xdp_qpls(struct gve_priv *priv) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_alloc_xdp_qpls(struct gve_priv *priv) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static void gve_free_xdp_rings(struct gve_priv *priv) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_destroy_xdp_rings(struct gve_priv *priv) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_alloc_xdp_rings(struct gve_priv *priv) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_create_xdp_rings(struct gve_priv *priv) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_unregister_xdp_qpls(struct gve_priv *priv) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_register_xdp_qpls(struct gve_priv *priv) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static void add_napi_init_xdp_sync_stats(struct gve_priv *priv, + int (*napi_poll)(struct napi_struct *napi, + int budget)) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) + xdp_return_frame(info->xdp_frame); ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ +static void gve_set_netdev_xdp_features(struct gve_priv *priv) +{ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(6,3,0)) || defined(KUNIT_KERNEL) +... ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(6,3,0)) || defined(KUNIT_KERNEL) */ +} diff --git a/patches/patch_xdp2.cocci b/patches/patch_xdp2.cocci new file mode 100644 index 0000000..dae4cd5 --- /dev/null +++ b/patches/patch_xdp2.cocci @@ -0,0 +1,107 @@ +@@ +@@ +struct gve_rx_ring { + ... ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) + /* XDP stuff */ + struct xdp_rxq_info xdp_rxq; + struct xdp_rxq_info xsk_rxq; + struct xsk_buff_pool *xsk_pool; ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + ... +}; + +@@ +@@ +struct gve_tx_ring { + ... ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) + struct xsk_buff_pool *xsk_pool; ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + ... +}; + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_xsk_pool_redirect(struct net_device *dev, + struct gve_rx_ring *rx, + void *data, int len, + struct bpf_prog *xdp_prog) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static int gve_xdp_redirect(struct net_device *dev, struct gve_rx_ring *rx, + struct xdp_buff *orig, struct bpf_prog *xdp_prog) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + + +@@ +type bool; +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +static bool gve_xdp_done(struct gve_priv *priv, struct gve_rx_ring *rx, + struct xdp_buff *xdp, struct bpf_prog *xprog, + int xdp_act) +{ +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@ assign @ +identifier xprog, xdp; +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) + struct bpf_prog *xprog; + struct xdp_buff xdp; ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@ gve_rx @ +identifier assign.xprog, assign.xdp; +identifier READ_ONCE; +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) +xprog = READ_ONCE(priv->xdp_prog); +if (xprog && is_only_frag) { +... +} ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + + +@ assign2 @ +identifier xdp_redirects, rx; +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) + u64 xdp_redirects = rx->xdp_actions[XDP_REDIRECT]; ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +identifier assign2.xdp_redirects, assign2.rx; +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) + if (xdp_redirects != rx->xdp_actions[XDP_REDIRECT]) + xdp_do_flush(); ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@ assign3 @ +identifier xdp_txs, rx; +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) + u64 xdp_txs = rx->xdp_actions[XDP_TX]; ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */ + +@@ +identifier assign3.xdp_txs, assign3.rx; +@@ ++#if (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) + if (xdp_txs != rx->xdp_actions[XDP_TX]) + gve_xdp_tx_flush(priv, rx->q_num); ++#endif /* (LINUX_VERSION_CODE >= KERNEL_VERSION(5,14,0)) || defined(KUNIT_KERNEL) */