diff options
Diffstat (limited to 'drivers/net/ethernet/google')
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve.h | 39 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_adminq.c | 89 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_adminq.h | 15 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_desc.h | 19 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_ethtool.c | 3 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_main.c | 11 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_rx.c | 364 | ||||
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_tx.c | 197 |
8 files changed, 575 insertions, 162 deletions
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index f5c80229ea96..daf07c0f790b 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -38,6 +38,8 @@ #define NIC_TX_STATS_REPORT_NUM 0 #define NIC_RX_STATS_REPORT_NUM 4 +#define GVE_DATA_SLOT_ADDR_PAGE_MASK (~(PAGE_SIZE - 1)) + /* 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 */ @@ -49,7 +51,8 @@ struct gve_rx_desc_queue { struct gve_rx_slot_page_info { struct page *page; void *page_address; - u32 page_offset; /* offset to write to in page */ + u8 page_offset; /* flipped to second half? */ + u8 can_flip; }; /* A list of pages registered with the device during setup and used by a queue @@ -64,10 +67,11 @@ struct gve_queue_page_list { /* Each slot in the data ring has a 1:1 mapping to a slot in the desc ring */ struct gve_rx_data_queue { - struct gve_rx_data_slot *data_ring; /* read by NIC */ + union gve_rx_data_slot *data_ring; /* read by NIC */ dma_addr_t data_bus; /* dma mapping of the slots */ struct gve_rx_slot_page_info *page_info; /* page info of the buffers */ struct gve_queue_page_list *qpl; /* qpl assigned to this queue */ + u8 raw_addressing; /* use raw_addressing? */ }; struct gve_priv; @@ -82,6 +86,7 @@ struct gve_rx_ring { u32 cnt; /* free-running total number of completed packets */ u32 fill_cnt; /* free-running total number of descs and buffs posted */ u32 mask; /* masks the cnt and fill_cnt to the size of the ring */ + u32 db_threshold; /* threshold for posting new buffs and descs */ u64 rx_copybreak_pkt; /* free-running count of copybreak packets */ u64 rx_copied_pkt; /* free-running total number of copied packets */ u64 rx_skb_alloc_fail; /* free-running count of skb alloc fails */ @@ -107,12 +112,20 @@ struct gve_tx_iovec { u32 iov_padding; /* padding associated with this segment */ }; +struct gve_tx_dma_buf { + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); +}; + /* Tracks the memory in the fifo occupied by the skb. Mapped 1:1 to a desc * 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 */ - struct gve_tx_iovec iov[GVE_TX_MAX_IOVEC]; /* segments of this pkt */ + union { + struct gve_tx_iovec iov[GVE_TX_MAX_IOVEC]; /* segments of this pkt */ + struct gve_tx_dma_buf buf; + }; }; /* A TX buffer - each queue has one */ @@ -135,13 +148,17 @@ struct gve_tx_ring { __be32 last_nic_done ____cacheline_aligned; /* NIC tail pointer */ u64 pkt_done; /* free-running - total packets completed */ u64 bytes_done; /* free-running - total bytes completed */ + u64 dropped_pkt; /* free-running - total packets dropped */ + u64 dma_mapping_error; /* count of dma mapping errors */ /* Cacheline 2 -- Read-mostly fields */ union gve_tx_desc *desc ____cacheline_aligned; struct gve_tx_buffer_state *info; /* Maps 1:1 to a desc */ struct netdev_queue *netdev_txq; struct gve_queue_resources *q_resources; /* head and tail pointer idx */ + struct device *dev; u32 mask; /* masks req and done down to queue size */ + u8 raw_addressing; /* use raw_addressing? */ /* Slow-path fields */ u32 q_num ____cacheline_aligned; /* queue idx */ @@ -194,11 +211,12 @@ struct gve_priv { u16 tx_desc_cnt; /* num desc per ring */ u16 rx_desc_cnt; /* num desc per ring */ u16 tx_pages_per_qpl; /* tx buffer length */ - u16 rx_pages_per_qpl; /* rx buffer length */ + u16 rx_data_slot_cnt; /* rx buffer length */ u64 max_registered_pages; u64 num_registered_pages; /* num pages registered with NIC */ u32 rx_copybreak; /* copy packets smaller than this */ u16 default_num_queues; /* default num queues to set up */ + u8 raw_addressing; /* 1 if this dev supports raw addressing, 0 otherwise */ struct gve_queue_config tx_cfg; struct gve_queue_config rx_cfg; @@ -436,14 +454,14 @@ static inline u32 gve_rx_idx_to_ntfy(struct gve_priv *priv, u32 queue_idx) */ static inline u32 gve_num_tx_qpls(struct gve_priv *priv) { - return priv->tx_cfg.num_queues; + return priv->raw_addressing ? 0 : priv->tx_cfg.num_queues; } /* Returns the number of rx queue page lists */ static inline u32 gve_num_rx_qpls(struct gve_priv *priv) { - return priv->rx_cfg.num_queues; + return priv->raw_addressing ? 0 : priv->rx_cfg.num_queues; } /* Returns a pointer to the next available tx qpl in the list of qpls @@ -497,15 +515,6 @@ static inline enum dma_data_direction gve_qpl_dma_dir(struct gve_priv *priv, return DMA_FROM_DEVICE; } -/* Returns true if the max mtu allows page recycling */ -static inline bool gve_can_recycle_pages(struct net_device *dev) -{ - /* We can't recycle the pages if we can't fit a packet into half a - * page. - */ - return dev->max_mtu <= PAGE_SIZE / 2; -} - /* buffers */ int gve_alloc_page(struct gve_priv *priv, struct device *dev, struct page **page, dma_addr_t *dma, diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index 24ae6a28a806..53864f200599 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -14,6 +14,57 @@ #define GVE_ADMINQ_SLEEP_LEN 20 #define GVE_MAX_ADMINQ_EVENT_COUNTER_CHECK 100 +#define GVE_DEVICE_OPTION_ERROR_FMT "%s option error:\n" \ +"Expected: length=%d, feature_mask=%x.\n" \ +"Actual: length=%d, feature_mask=%x.\n" + +static +struct gve_device_option *gve_get_next_option(struct gve_device_descriptor *descriptor, + struct gve_device_option *option) +{ + void *option_end, *descriptor_end; + + option_end = (void *)(option + 1) + be16_to_cpu(option->option_length); + descriptor_end = (void *)descriptor + be16_to_cpu(descriptor->total_length); + + return option_end > descriptor_end ? NULL : (struct gve_device_option *)option_end; +} + +static +void gve_parse_device_option(struct gve_priv *priv, + struct gve_device_descriptor *device_descriptor, + struct gve_device_option *option) +{ + u16 option_length = be16_to_cpu(option->option_length); + u16 option_id = be16_to_cpu(option->option_id); + + switch (option_id) { + case GVE_DEV_OPT_ID_RAW_ADDRESSING: + /* If the length or feature mask doesn't match, + * continue without enabling the feature. + */ + if (option_length != GVE_DEV_OPT_LEN_RAW_ADDRESSING || + option->feat_mask != cpu_to_be32(GVE_DEV_OPT_FEAT_MASK_RAW_ADDRESSING)) { + dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT, "Raw Addressing", + GVE_DEV_OPT_LEN_RAW_ADDRESSING, + cpu_to_be32(GVE_DEV_OPT_FEAT_MASK_RAW_ADDRESSING), + option_length, option->feat_mask); + priv->raw_addressing = 0; + } else { + dev_info(&priv->pdev->dev, + "Raw addressing device option enabled.\n"); + priv->raw_addressing = 1; + } + break; + default: + /* If we don't recognize the option just continue + * without doing anything. + */ + dev_dbg(&priv->pdev->dev, "Unrecognized device option 0x%hx not enabled.\n", + option_id); + } +} + int gve_adminq_alloc(struct device *dev, struct gve_priv *priv) { priv->adminq = dma_alloc_coherent(dev, PAGE_SIZE, @@ -318,8 +369,10 @@ static int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_index) { struct gve_tx_ring *tx = &priv->tx[queue_index]; union gve_adminq_command cmd; + u32 qpl_id; int err; + qpl_id = priv->raw_addressing ? GVE_RAW_ADDRESSING_QPL_ID : tx->tx_fifo.qpl->id; memset(&cmd, 0, sizeof(cmd)); cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_TX_QUEUE); cmd.create_tx_queue = (struct gve_adminq_create_tx_queue) { @@ -328,7 +381,7 @@ static int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_index) .queue_resources_addr = cpu_to_be64(tx->q_resources_bus), .tx_ring_addr = cpu_to_be64(tx->bus), - .queue_page_list_id = cpu_to_be32(tx->tx_fifo.qpl->id), + .queue_page_list_id = cpu_to_be32(qpl_id), .ntfy_id = cpu_to_be32(tx->ntfy_id), }; @@ -357,8 +410,10 @@ static int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index) { struct gve_rx_ring *rx = &priv->rx[queue_index]; union gve_adminq_command cmd; + u32 qpl_id; int err; + qpl_id = priv->raw_addressing ? GVE_RAW_ADDRESSING_QPL_ID : rx->data.qpl->id; memset(&cmd, 0, sizeof(cmd)); cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_RX_QUEUE); cmd.create_rx_queue = (struct gve_adminq_create_rx_queue) { @@ -369,7 +424,7 @@ static int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index) .queue_resources_addr = cpu_to_be64(rx->q_resources_bus), .rx_desc_ring_addr = cpu_to_be64(rx->desc.bus), .rx_data_ring_addr = cpu_to_be64(rx->data.data_bus), - .queue_page_list_id = cpu_to_be32(rx->data.qpl->id), + .queue_page_list_id = cpu_to_be32(qpl_id), }; err = gve_adminq_issue_cmd(priv, &cmd); @@ -460,11 +515,14 @@ int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 num_queues) int gve_adminq_describe_device(struct gve_priv *priv) { struct gve_device_descriptor *descriptor; + struct gve_device_option *dev_opt; union gve_adminq_command cmd; dma_addr_t descriptor_bus; + u16 num_options; int err = 0; u8 *mac; u16 mtu; + int i; memset(&cmd, 0, sizeof(cmd)); descriptor = dma_alloc_coherent(&priv->pdev->dev, PAGE_SIZE, @@ -511,13 +569,30 @@ int gve_adminq_describe_device(struct gve_priv *priv) mac = descriptor->mac; dev_info(&priv->pdev->dev, "MAC addr: %pM\n", mac); priv->tx_pages_per_qpl = be16_to_cpu(descriptor->tx_pages_per_qpl); - priv->rx_pages_per_qpl = be16_to_cpu(descriptor->rx_pages_per_qpl); - if (priv->rx_pages_per_qpl < priv->rx_desc_cnt) { - dev_err(&priv->pdev->dev, "rx_pages_per_qpl cannot be smaller than rx_desc_cnt, setting rx_desc_cnt down to %d.\n", - priv->rx_pages_per_qpl); - priv->rx_desc_cnt = priv->rx_pages_per_qpl; + priv->rx_data_slot_cnt = be16_to_cpu(descriptor->rx_pages_per_qpl); + if (priv->rx_data_slot_cnt < priv->rx_desc_cnt) { + dev_err(&priv->pdev->dev, "rx_data_slot_cnt cannot be smaller than rx_desc_cnt, setting rx_desc_cnt down to %d.\n", + priv->rx_data_slot_cnt); + priv->rx_desc_cnt = priv->rx_data_slot_cnt; } priv->default_num_queues = be16_to_cpu(descriptor->default_num_queues); + dev_opt = (void *)(descriptor + 1); + + num_options = be16_to_cpu(descriptor->num_device_options); + for (i = 0; i < num_options; i++) { + struct gve_device_option *next_opt; + + next_opt = gve_get_next_option(descriptor, dev_opt); + if (!next_opt) { + dev_err(&priv->dev->dev, + "options exceed device_descriptor's total length.\n"); + err = -EINVAL; + goto free_device_descriptor; + } + + gve_parse_device_option(priv, descriptor, dev_opt); + dev_opt = next_opt; + } free_device_descriptor: dma_free_coherent(&priv->pdev->dev, sizeof(*descriptor), descriptor, diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index 015796a20118..d320c2ffd87c 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -79,12 +79,17 @@ struct gve_device_descriptor { static_assert(sizeof(struct gve_device_descriptor) == 40); -struct device_option { - __be32 option_id; - __be32 option_length; +struct gve_device_option { + __be16 option_id; + __be16 option_length; + __be32 feat_mask; }; -static_assert(sizeof(struct device_option) == 8); +static_assert(sizeof(struct gve_device_option) == 8); + +#define GVE_DEV_OPT_ID_RAW_ADDRESSING 0x1 +#define GVE_DEV_OPT_LEN_RAW_ADDRESSING 0x0 +#define GVE_DEV_OPT_FEAT_MASK_RAW_ADDRESSING 0x0 struct gve_adminq_configure_device_resources { __be64 counter_array; @@ -111,6 +116,8 @@ struct gve_adminq_unregister_page_list { static_assert(sizeof(struct gve_adminq_unregister_page_list) == 4); +#define GVE_RAW_ADDRESSING_QPL_ID 0xFFFFFFFF + struct gve_adminq_create_tx_queue { __be32 queue_id; __be32 reserved; diff --git a/drivers/net/ethernet/google/gve/gve_desc.h b/drivers/net/ethernet/google/gve/gve_desc.h index 54779871d52e..05ae6300e984 100644 --- a/drivers/net/ethernet/google/gve/gve_desc.h +++ b/drivers/net/ethernet/google/gve/gve_desc.h @@ -16,9 +16,11 @@ * Base addresses encoded in seg_addr are not assumed to be physical * addresses. The ring format assumes these come from some linear address * space. This could be physical memory, kernel virtual memory, user virtual - * memory. gVNIC uses lists of registered pages. Each queue is assumed - * to be associated with a single such linear address space to ensure a - * consistent meaning for seg_addrs posted to its rings. + * memory. + * If raw dma addressing is not supported then gVNIC uses lists of registered + * pages. Each queue is assumed to be associated with a single such linear + * address space to ensure a consistent meaning for seg_addrs posted to its + * rings. */ struct gve_tx_pkt_desc { @@ -72,12 +74,15 @@ struct gve_rx_desc { } __packed; static_assert(sizeof(struct gve_rx_desc) == 64); -/* As with the Tx ring format, the qpl_offset entries below are offsets into an - * ordered list of registered pages. +/* If the device supports raw dma addressing then the addr in data slot is + * the dma address of the buffer. + * If the device only supports registered segments then the addr is a byte + * offset into the registered segment (an ordered list of pages) where the + * buffer is. */ -struct gve_rx_data_slot { - /* byte offset into the rx registered segment of this slot */ +union gve_rx_data_slot { __be64 qpl_offset; + __be64 addr; }; /* GVE Recive Packet Descriptor Seq No */ diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 7b44769bd87c..0901fa6853ca 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -4,6 +4,7 @@ * Copyright (C) 2015-2019 Google, Inc. */ +#include <linux/ethtool.h> #include <linux/rtnetlink.h> #include "gve.h" #include "gve_adminq.h" @@ -50,6 +51,7 @@ 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_bytes[%u]", "tx_wake[%u]", "tx_stop[%u]", "tx_event_counter[%u]", + "tx_dma_mapping_error[%u]", }; static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = { @@ -322,6 +324,7 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = tx->stop_queue; data[i++] = be32_to_cpu(gve_tx_load_event_counter(priv, tx)); + data[i++] = tx->dma_mapping_error; /* stats from NIC */ if (skip_nic_stats) { /* skip NIC tx stats */ diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 02e7d74779f4..7302498c6df3 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -677,6 +677,10 @@ static int gve_alloc_qpls(struct gve_priv *priv) int i, j; int err; + /* Raw addressing means no QPLs */ + if (priv->raw_addressing) + return 0; + priv->qpls = kvzalloc(num_qpls * sizeof(*priv->qpls), GFP_KERNEL); if (!priv->qpls) return -ENOMEM; @@ -689,7 +693,7 @@ static int gve_alloc_qpls(struct gve_priv *priv) } for (; i < num_qpls; i++) { err = gve_alloc_queue_page_list(priv, i, - priv->rx_pages_per_qpl); + priv->rx_data_slot_cnt); if (err) goto free_qpls; } @@ -717,6 +721,10 @@ static void gve_free_qpls(struct gve_priv *priv) int num_qpls = gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv); int i; + /* Raw addressing means no QPLs */ + if (priv->raw_addressing) + return; + kvfree(priv->qpl_cfg.qpl_id_map); for (i = 0; i < num_qpls; i++) @@ -1077,6 +1085,7 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) if (skip_describe_device) goto setup_device; + priv->raw_addressing = false; /* Get the initial information we need from the device */ err = gve_adminq_describe_device(priv); if (err) { diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 008fa897a3e6..bf123fe524c4 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -16,12 +16,39 @@ static void gve_rx_remove_from_block(struct gve_priv *priv, int queue_idx) block->rx = NULL; } +static void gve_rx_free_buffer(struct device *dev, + struct gve_rx_slot_page_info *page_info, + union gve_rx_data_slot *data_slot) +{ + dma_addr_t dma = (dma_addr_t)(be64_to_cpu(data_slot->addr) & + GVE_DATA_SLOT_ADDR_PAGE_MASK); + + gve_free_page(dev, page_info->page, dma, DMA_FROM_DEVICE); +} + +static void gve_rx_unfill_pages(struct gve_priv *priv, struct gve_rx_ring *rx) +{ + if (rx->data.raw_addressing) { + u32 slots = rx->mask + 1; + int i; + + for (i = 0; i < slots; i++) + gve_rx_free_buffer(&priv->pdev->dev, &rx->data.page_info[i], + &rx->data.data_ring[i]); + } else { + gve_unassign_qpl(priv, rx->data.qpl->id); + rx->data.qpl = NULL; + } + kvfree(rx->data.page_info); + rx->data.page_info = NULL; +} + static void gve_rx_free_ring(struct gve_priv *priv, int idx) { struct gve_rx_ring *rx = &priv->rx[idx]; struct device *dev = &priv->pdev->dev; + u32 slots = rx->mask + 1; size_t bytes; - u32 slots; gve_rx_remove_from_block(priv, idx); @@ -33,11 +60,8 @@ static void gve_rx_free_ring(struct gve_priv *priv, int idx) rx->q_resources, rx->q_resources_bus); rx->q_resources = NULL; - gve_unassign_qpl(priv, rx->data.qpl->id); - rx->data.qpl = NULL; - kvfree(rx->data.page_info); + gve_rx_unfill_pages(priv, rx); - slots = rx->mask + 1; bytes = sizeof(*rx->data.data_ring) * slots; dma_free_coherent(dev, bytes, rx->data.data_ring, rx->data.data_bus); @@ -46,19 +70,35 @@ static void gve_rx_free_ring(struct gve_priv *priv, int idx) } static void gve_setup_rx_buffer(struct gve_rx_slot_page_info *page_info, - struct gve_rx_data_slot *slot, - dma_addr_t addr, struct page *page) + 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); - slot->qpl_offset = cpu_to_be64(addr); + *slot_addr = cpu_to_be64(addr); +} + +static int gve_rx_alloc_buffer(struct gve_priv *priv, struct device *dev, + struct gve_rx_slot_page_info *page_info, + union gve_rx_data_slot *data_slot) +{ + struct page *page; + dma_addr_t dma; + int err; + + err = gve_alloc_page(priv, dev, &page, &dma, DMA_FROM_DEVICE); + if (err) + return err; + + gve_setup_rx_buffer(page_info, dma, page, &data_slot->addr); + return 0; } static int gve_prefill_rx_pages(struct gve_rx_ring *rx) { struct gve_priv *priv = rx->gve; u32 slots; + int err; int i; /* Allocate one page per Rx queue slot. Each page is split into two @@ -71,17 +111,30 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx) if (!rx->data.page_info) return -ENOMEM; - rx->data.qpl = gve_assign_rx_qpl(priv); - + if (!rx->data.raw_addressing) + rx->data.qpl = gve_assign_rx_qpl(priv); for (i = 0; i < slots; i++) { - struct page *page = rx->data.qpl->pages[i]; - dma_addr_t addr = i * PAGE_SIZE; + if (!rx->data.raw_addressing) { + struct page *page = rx->data.qpl->pages[i]; + dma_addr_t addr = i * PAGE_SIZE; - gve_setup_rx_buffer(&rx->data.page_info[i], - &rx->data.data_ring[i], addr, page); + gve_setup_rx_buffer(&rx->data.page_info[i], addr, page, + &rx->data.data_ring[i].qpl_offset); + continue; + } + err = gve_rx_alloc_buffer(priv, &priv->pdev->dev, &rx->data.page_info[i], + &rx->data.data_ring[i]); + if (err) + goto alloc_err; } return slots; +alloc_err: + while (i--) + gve_rx_free_buffer(&priv->pdev->dev, + &rx->data.page_info[i], + &rx->data.data_ring[i]); + return err; } static void gve_rx_add_to_block(struct gve_priv *priv, int queue_idx) @@ -110,8 +163,9 @@ static int gve_rx_alloc_ring(struct gve_priv *priv, int idx) rx->gve = priv; rx->q_num = idx; - slots = priv->rx_pages_per_qpl; + slots = priv->rx_data_slot_cnt; rx->mask = slots - 1; + rx->data.raw_addressing = priv->raw_addressing; /* alloc rx data ring */ bytes = sizeof(*rx->data.data_ring) * slots; @@ -156,8 +210,8 @@ static int gve_rx_alloc_ring(struct gve_priv *priv, int idx) err = -ENOMEM; goto abort_with_q_resources; } - rx->mask = slots - 1; rx->cnt = 0; + rx->db_threshold = priv->rx_desc_cnt / 2; rx->desc.seqno = 1; gve_rx_add_to_block(priv, idx); @@ -168,7 +222,7 @@ abort_with_q_resources: rx->q_resources, rx->q_resources_bus); rx->q_resources = NULL; abort_filled: - kvfree(rx->data.page_info); + gve_rx_unfill_pages(priv, rx); abort_with_slots: bytes = sizeof(*rx->data.data_ring) * slots; dma_free_coherent(hdev, bytes, rx->data.data_ring, rx->data.data_bus); @@ -225,15 +279,14 @@ static enum pkt_hash_types gve_rss_type(__be16 pkt_flags) return PKT_HASH_TYPE_L2; } -static struct sk_buff *gve_rx_copy(struct gve_rx_ring *rx, - struct net_device *dev, +static struct sk_buff *gve_rx_copy(struct net_device *dev, struct napi_struct *napi, struct gve_rx_slot_page_info *page_info, u16 len) { struct sk_buff *skb = napi_alloc_skb(napi, len); void *va = page_info->page_address + GVE_RX_PAD + - page_info->page_offset; + (page_info->page_offset ? PAGE_SIZE / 2 : 0); if (unlikely(!skb)) return NULL; @@ -244,15 +297,10 @@ static struct sk_buff *gve_rx_copy(struct gve_rx_ring *rx, skb->protocol = eth_type_trans(skb, dev); - u64_stats_update_begin(&rx->statss); - rx->rx_copied_pkt++; - u64_stats_update_end(&rx->statss); - return skb; } -static struct sk_buff *gve_rx_add_frags(struct net_device *dev, - struct napi_struct *napi, +static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi, struct gve_rx_slot_page_info *page_info, u16 len) { @@ -262,20 +310,92 @@ static struct sk_buff *gve_rx_add_frags(struct net_device *dev, return NULL; skb_add_rx_frag(skb, 0, page_info->page, - page_info->page_offset + + (page_info->page_offset ? PAGE_SIZE / 2 : 0) + GVE_RX_PAD, len, PAGE_SIZE / 2); return skb; } -static void gve_rx_flip_buff(struct gve_rx_slot_page_info *page_info, - struct gve_rx_data_slot *data_ring) +static void gve_rx_flip_buff(struct gve_rx_slot_page_info *page_info, __be64 *slot_addr) +{ + const __be64 offset = cpu_to_be64(PAGE_SIZE / 2); + + /* "flip" to other packet buffer on this page */ + page_info->page_offset ^= 0x1; + *(slot_addr) ^= offset; +} + +static bool gve_rx_can_flip_buffers(struct net_device *netdev) +{ + return PAGE_SIZE == 4096 + ? netdev->mtu + GVE_RX_PAD + ETH_HLEN <= PAGE_SIZE / 2 : false; +} + +static int gve_rx_can_recycle_buffer(struct page *page) +{ + int pagecount = page_count(page); + + /* This page is not being used by any SKBs - reuse */ + if (pagecount == 1) + return 1; + /* This page is still being used by an SKB - we can't reuse */ + else if (pagecount >= 2) + return 0; + WARN(pagecount < 1, "Pagecount should never be < 1"); + return -1; +} + +static struct sk_buff * +gve_rx_raw_addressing(struct device *dev, struct net_device *netdev, + struct gve_rx_slot_page_info *page_info, u16 len, + struct napi_struct *napi, + union gve_rx_data_slot *data_slot) { - u64 addr = be64_to_cpu(data_ring->qpl_offset); + struct sk_buff *skb; + + skb = gve_rx_add_frags(napi, page_info, len); + if (!skb) + return NULL; - page_info->page_offset ^= PAGE_SIZE / 2; - addr ^= PAGE_SIZE / 2; - data_ring->qpl_offset = cpu_to_be64(addr); + /* Optimistically stop the kernel from freeing the page by increasing + * the page bias. We will check the refcount in refill to determine if + * we need to alloc a new page. + */ + get_page(page_info->page); + + return skb; +} + +static struct sk_buff * +gve_rx_qpl(struct device *dev, struct net_device *netdev, + struct gve_rx_ring *rx, struct gve_rx_slot_page_info *page_info, + u16 len, struct napi_struct *napi, + union gve_rx_data_slot *data_slot) +{ + struct sk_buff *skb; + + /* if raw_addressing mode is not enabled gvnic can only receive into + * registered segments. If the buffer can't be recycled, our only + * choice is to copy the data out of it so that we can return it to the + * device. + */ + if (page_info->can_flip) { + skb = gve_rx_add_frags(napi, page_info, len); + /* No point in recycling if we didn't get the skb */ + if (skb) { + /* Make sure that the page isn't freed. */ + get_page(page_info->page); + gve_rx_flip_buff(page_info, &data_slot->qpl_offset); + } + } else { + skb = gve_rx_copy(netdev, napi, page_info, len); + if (skb) { + u64_stats_update_begin(&rx->statss); + rx->rx_copied_pkt++; + u64_stats_update_end(&rx->statss); + } + } + return skb; } static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, @@ -285,8 +405,9 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, struct gve_priv *priv = rx->gve; struct napi_struct *napi = &priv->ntfy_blocks[rx->ntfy_id].napi; struct net_device *dev = priv->dev; - struct sk_buff *skb; - int pagecount; + union gve_rx_data_slot *data_slot; + struct sk_buff *skb = NULL; + dma_addr_t page_bus; u16 len; /* drop this packet */ @@ -294,71 +415,55 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, u64_stats_update_begin(&rx->statss); rx->rx_desc_err_dropped_pkt++; u64_stats_update_end(&rx->statss); - return true; + return false; } len = be16_to_cpu(rx_desc->len) - GVE_RX_PAD; page_info = &rx->data.page_info[idx]; - dma_sync_single_for_cpu(&priv->pdev->dev, rx->data.qpl->page_buses[idx], - PAGE_SIZE, DMA_FROM_DEVICE); - /* gvnic can only receive into registered segments. If the buffer - * can't be recycled, our only choice is to copy the data out of - * it so that we can return it to the device. - */ + data_slot = &rx->data.data_ring[idx]; + page_bus = (rx->data.raw_addressing) ? + be64_to_cpu(data_slot->addr) & GVE_DATA_SLOT_ADDR_PAGE_MASK : + rx->data.qpl->page_buses[idx]; + dma_sync_single_for_cpu(&priv->pdev->dev, page_bus, + PAGE_SIZE, DMA_FROM_DEVICE); - if (PAGE_SIZE == 4096) { - if (len <= priv->rx_copybreak) { - /* Just copy small packets */ - skb = gve_rx_copy(rx, dev, napi, page_info, len); - u64_stats_update_begin(&rx->statss); - rx->rx_copybreak_pkt++; - u64_stats_update_end(&rx->statss); - goto have_skb; - } - if (unlikely(!gve_can_recycle_pages(dev))) { - skb = gve_rx_copy(rx, dev, napi, page_info, len); - goto have_skb; - } - pagecount = page_count(page_info->page); - if (pagecount == 1) { - /* No part of this page is used by any SKBs; we attach - * the page fragment to a new SKB and pass it up the - * stack. - */ - skb = gve_rx_add_frags(dev, napi, page_info, len); - if (!skb) { - u64_stats_update_begin(&rx->statss); - rx->rx_skb_alloc_fail++; - u64_stats_update_end(&rx->statss); - return true; + if (len <= priv->rx_copybreak) { + /* Just copy small packets */ + skb = gve_rx_copy(dev, napi, page_info, len); + u64_stats_update_begin(&rx->statss); + rx->rx_copied_pkt++; + rx->rx_copybreak_pkt++; + u64_stats_update_end(&rx->statss); + } else { + u8 can_flip = gve_rx_can_flip_buffers(dev); + int recycle = 0; + + if (can_flip) { + recycle = gve_rx_can_recycle_buffer(page_info->page); + if (recycle < 0) { + if (!rx->data.raw_addressing) + gve_schedule_reset(priv); + return false; } - /* Make sure the kernel stack can't release the page */ - get_page(page_info->page); - /* "flip" to other packet buffer on this page */ - gve_rx_flip_buff(page_info, &rx->data.data_ring[idx]); - } else if (pagecount >= 2) { - /* We have previously passed the other half of this - * page up the stack, but it has not yet been freed. - */ - skb = gve_rx_copy(rx, dev, napi, page_info, len); + } + + page_info->can_flip = can_flip && recycle; + if (rx->data.raw_addressing) { + skb = gve_rx_raw_addressing(&priv->pdev->dev, dev, + page_info, len, napi, + data_slot); } else { - WARN(pagecount < 1, "Pagecount should never be < 1"); - return false; + skb = gve_rx_qpl(&priv->pdev->dev, dev, rx, + page_info, len, napi, data_slot); } - } else { - skb = gve_rx_copy(rx, dev, napi, page_info, len); } -have_skb: - /* We didn't manage to allocate an skb but we haven't had any - * reset worthy failures. - */ if (!skb) { u64_stats_update_begin(&rx->statss); rx->rx_skb_alloc_fail++; u64_stats_update_end(&rx->statss); - return true; + return false; } if (likely(feat & NETIF_F_RXCSUM)) { @@ -399,19 +504,73 @@ static bool gve_rx_work_pending(struct gve_rx_ring *rx) return (GVE_SEQNO(flags_seq) == rx->desc.seqno); } +static bool gve_rx_refill_buffers(struct gve_priv *priv, struct gve_rx_ring *rx) +{ + int refill_target = rx->mask + 1; + u32 fill_cnt = rx->fill_cnt; + + while (fill_cnt - rx->cnt < refill_target) { + struct gve_rx_slot_page_info *page_info; + u32 idx = fill_cnt & rx->mask; + + page_info = &rx->data.page_info[idx]; + if (page_info->can_flip) { + /* The other half of the page is free because it was + * free when we processed the descriptor. Flip to it. + */ + union gve_rx_data_slot *data_slot = + &rx->data.data_ring[idx]; + + gve_rx_flip_buff(page_info, &data_slot->addr); + page_info->can_flip = 0; + } else { + /* It is possible that the networking stack has already + * finished processing all outstanding packets in the buffer + * and it can be reused. + * Flipping is unnecessary here - if the networking stack still + * owns half the page it is impossible to tell which half. Either + * the whole page is free or it needs to be replaced. + */ + int recycle = gve_rx_can_recycle_buffer(page_info->page); + + if (recycle < 0) { + if (!rx->data.raw_addressing) + gve_schedule_reset(priv); + return false; + } + if (!recycle) { + /* We can't reuse the buffer - alloc a new one*/ + union gve_rx_data_slot *data_slot = + &rx->data.data_ring[idx]; + struct device *dev = &priv->pdev->dev; + + gve_rx_free_buffer(dev, page_info, data_slot); + page_info->page = NULL; + if (gve_rx_alloc_buffer(priv, dev, page_info, data_slot)) + break; + } + } + fill_cnt++; + } + rx->fill_cnt = fill_cnt; + return true; +} + bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, netdev_features_t feat) { struct gve_priv *priv = rx->gve; + u32 work_done = 0, packets = 0; struct gve_rx_desc *desc; u32 cnt = rx->cnt; u32 idx = cnt & rx->mask; - u32 work_done = 0; u64 bytes = 0; desc = rx->desc.desc_ring + idx; while ((GVE_SEQNO(desc->flags_seq) == rx->desc.seqno) && work_done < budget) { + bool dropped; + netif_info(priv, rx_status, priv->dev, "[%d] idx=%d desc=%p desc->flags_seq=0x%x\n", rx->q_num, idx, desc, desc->flags_seq); @@ -419,9 +578,11 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, "[%d] seqno=%d rx->desc.seqno=%d\n", rx->q_num, GVE_SEQNO(desc->flags_seq), rx->desc.seqno); - bytes += be16_to_cpu(desc->len) - GVE_RX_PAD; - if (!gve_rx(rx, desc, feat, idx)) - gve_schedule_reset(priv); + dropped = !gve_rx(rx, desc, feat, idx); + if (!dropped) { + bytes += be16_to_cpu(desc->len) - GVE_RX_PAD; + packets++; + } cnt++; idx = cnt & rx->mask; desc = rx->desc.desc_ring + idx; @@ -429,15 +590,34 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, work_done++; } - if (!work_done) + if (!work_done && rx->fill_cnt - cnt > rx->db_threshold) return false; u64_stats_update_begin(&rx->statss); - rx->rpackets += work_done; + rx->rpackets += packets; rx->rbytes += bytes; u64_stats_update_end(&rx->statss); rx->cnt = cnt; - rx->fill_cnt += work_done; + + /* restock ring slots */ + if (!rx->data.raw_addressing) { + /* In QPL mode buffs are refilled as the desc are processed */ + rx->fill_cnt += work_done; + } else if (rx->fill_cnt - cnt <= rx->db_threshold) { + /* In raw addressing mode buffs are only refilled if the avail + * falls below a threshold. + */ + if (!gve_rx_refill_buffers(priv, rx)) + return false; + + /* If we were not able to completely refill buffers, we'll want + * to schedule this queue for work again to refill buffers. + */ + if (rx->fill_cnt - cnt <= rx->db_threshold) { + gve_rx_write_doorbell(priv, rx); + return true; + } + } gve_rx_write_doorbell(priv, rx); return gve_rx_work_pending(rx); diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index d0244feb0301..6938f3a939d6 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -158,9 +158,11 @@ static void gve_tx_free_ring(struct gve_priv *priv, int idx) tx->q_resources, tx->q_resources_bus); tx->q_resources = NULL; - gve_tx_fifo_release(priv, &tx->tx_fifo); - gve_unassign_qpl(priv, tx->tx_fifo.qpl->id); - tx->tx_fifo.qpl = NULL; + if (!tx->raw_addressing) { + gve_tx_fifo_release(priv, &tx->tx_fifo); + gve_unassign_qpl(priv, tx->tx_fifo.qpl->id); + tx->tx_fifo.qpl = NULL; + } bytes = sizeof(*tx->desc) * slots; dma_free_coherent(hdev, bytes, tx->desc, tx->bus); @@ -206,11 +208,15 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) if (!tx->desc) goto abort_with_info; - tx->tx_fifo.qpl = gve_assign_tx_qpl(priv); + tx->raw_addressing = priv->raw_addressing; + tx->dev = &priv->pdev->dev; + if (!tx->raw_addressing) { + tx->tx_fifo.qpl = gve_assign_tx_qpl(priv); - /* map Tx FIFO */ - if (gve_tx_fifo_init(priv, &tx->tx_fifo)) - goto abort_with_desc; + /* map Tx FIFO */ + if (gve_tx_fifo_init(priv, &tx->tx_fifo)) + goto abort_with_desc; + } tx->q_resources = dma_alloc_coherent(hdev, @@ -228,7 +234,8 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) return 0; abort_with_fifo: - gve_tx_fifo_release(priv, &tx->tx_fifo); + if (!tx->raw_addressing) + gve_tx_fifo_release(priv, &tx->tx_fifo); abort_with_desc: dma_free_coherent(hdev, bytes, tx->desc, tx->bus); tx->desc = NULL; @@ -301,27 +308,47 @@ static inline int gve_skb_fifo_bytes_required(struct gve_tx_ring *tx, return bytes; } -/* The most descriptors we could need are 3 - 1 for the headers, 1 for - * the beginning of the payload at the end of the FIFO, and 1 if the - * payload wraps to the beginning of the FIFO. +/* The most descriptors we could need is MAX_SKB_FRAGS + 3 : 1 for each skb frag, + * +1 for the skb linear portion, +1 for when tcp hdr needs to be in separate descriptor, + * and +1 if the payload wraps to the beginning of the FIFO. */ -#define MAX_TX_DESC_NEEDED 3 +#define MAX_TX_DESC_NEEDED (MAX_SKB_FRAGS + 3) +static void gve_tx_unmap_buf(struct device *dev, struct gve_tx_buffer_state *info) +{ + if (info->skb) { + dma_unmap_single(dev, dma_unmap_addr(&info->buf, dma), + dma_unmap_len(&info->buf, len), + DMA_TO_DEVICE); + dma_unmap_len_set(&info->buf, len, 0); + } else { + dma_unmap_page(dev, dma_unmap_addr(&info->buf, dma), + dma_unmap_len(&info->buf, len), + DMA_TO_DEVICE); + dma_unmap_len_set(&info->buf, len, 0); + } +} /* Check if sufficient resources (descriptor ring space, FIFO space) are * available to transmit the given number of bytes. */ static inline bool gve_can_tx(struct gve_tx_ring *tx, int bytes_required) { - return (gve_tx_avail(tx) >= MAX_TX_DESC_NEEDED && - gve_tx_fifo_can_alloc(&tx->tx_fifo, bytes_required)); + bool can_alloc = true; + + if (!tx->raw_addressing) + can_alloc = gve_tx_fifo_can_alloc(&tx->tx_fifo, bytes_required); + + return (gve_tx_avail(tx) >= MAX_TX_DESC_NEEDED && can_alloc); } /* Stops the queue if the skb cannot be transmitted. */ static int gve_maybe_stop_tx(struct gve_tx_ring *tx, struct sk_buff *skb) { - int bytes_required; + int bytes_required = 0; + + if (!tx->raw_addressing) + bytes_required = gve_skb_fifo_bytes_required(tx, skb); - bytes_required = gve_skb_fifo_bytes_required(tx, skb); if (likely(gve_can_tx(tx, bytes_required))) return 0; @@ -395,17 +422,13 @@ static void gve_dma_sync_for_device(struct device *dev, dma_addr_t *page_buses, { u64 last_page = (iov_offset + iov_len - 1) / PAGE_SIZE; u64 first_page = iov_offset / PAGE_SIZE; - dma_addr_t dma; u64 page; - for (page = first_page; page <= last_page; page++) { - dma = page_buses[page]; - dma_sync_single_for_device(dev, dma, PAGE_SIZE, DMA_TO_DEVICE); - } + for (page = first_page; page <= last_page; page++) + dma_sync_single_for_device(dev, page_buses[page], PAGE_SIZE, DMA_TO_DEVICE); } -static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb, - struct device *dev) +static int gve_tx_add_skb_copy(struct gve_priv *priv, struct gve_tx_ring *tx, struct sk_buff *skb) { int pad_bytes, hlen, hdr_nfrags, payload_nfrags, l4_hdr_offset; union gve_tx_desc *pkt_desc, *seg_desc; @@ -447,7 +470,7 @@ static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb, skb_copy_bits(skb, 0, tx->tx_fifo.base + info->iov[hdr_nfrags - 1].iov_offset, hlen); - gve_dma_sync_for_device(dev, tx->tx_fifo.qpl->page_buses, + gve_dma_sync_for_device(&priv->pdev->dev, tx->tx_fifo.qpl->page_buses, info->iov[hdr_nfrags - 1].iov_offset, info->iov[hdr_nfrags - 1].iov_len); copy_offset = hlen; @@ -463,7 +486,7 @@ static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb, skb_copy_bits(skb, copy_offset, tx->tx_fifo.base + info->iov[i].iov_offset, info->iov[i].iov_len); - gve_dma_sync_for_device(dev, tx->tx_fifo.qpl->page_buses, + gve_dma_sync_for_device(&priv->pdev->dev, tx->tx_fifo.qpl->page_buses, info->iov[i].iov_offset, info->iov[i].iov_len); copy_offset += info->iov[i].iov_len; @@ -472,6 +495,94 @@ static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb, return 1 + payload_nfrags; } +static int gve_tx_add_skb_no_copy(struct gve_priv *priv, struct gve_tx_ring *tx, + struct sk_buff *skb) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + int hlen, payload_nfrags, l4_hdr_offset; + union gve_tx_desc *pkt_desc, *seg_desc; + struct gve_tx_buffer_state *info; + bool is_gso = skb_is_gso(skb); + u32 idx = tx->req & tx->mask; + struct gve_tx_dma_buf *buf; + u64 addr; + u32 len; + int i; + + info = &tx->info[idx]; + pkt_desc = &tx->desc[idx]; + + l4_hdr_offset = skb_checksum_start_offset(skb); + /* If the skb is gso, then we want only up to the tcp header in the first segment + * to efficiently replicate on each segment otherwise we want the linear portion + * of the skb (which will contain the checksum because skb->csum_start and + * skb->csum_offset are given relative to skb->head) in the first segment. + */ + hlen = is_gso ? l4_hdr_offset + tcp_hdrlen(skb) : skb_headlen(skb); + len = skb_headlen(skb); + + info->skb = skb; + + addr = dma_map_single(tx->dev, skb->data, len, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(tx->dev, addr))) { + tx->dma_mapping_error++; + goto drop; + } + buf = &info->buf; + dma_unmap_len_set(buf, len, len); + dma_unmap_addr_set(buf, dma, addr); + + payload_nfrags = shinfo->nr_frags; + if (hlen < len) { + /* For gso the rest of the linear portion of the skb needs to + * be in its own descriptor. + */ + payload_nfrags++; + gve_tx_fill_pkt_desc(pkt_desc, skb, is_gso, l4_hdr_offset, + 1 + payload_nfrags, hlen, addr); + + len -= hlen; + addr += hlen; + idx = (tx->req + 1) & tx->mask; + seg_desc = &tx->desc[idx]; + gve_tx_fill_seg_desc(seg_desc, skb, is_gso, len, addr); + } else { + gve_tx_fill_pkt_desc(pkt_desc, skb, is_gso, l4_hdr_offset, + 1 + payload_nfrags, hlen, addr); + } + + for (i = 0; i < shinfo->nr_frags; i++) { + const skb_frag_t *frag = &shinfo->frags[i]; + + idx = (idx + 1) & tx->mask; + seg_desc = &tx->desc[idx]; + len = skb_frag_size(frag); + addr = skb_frag_dma_map(tx->dev, frag, 0, len, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(tx->dev, addr))) { + tx->dma_mapping_error++; + goto unmap_drop; + } + buf = &tx->info[idx].buf; + tx->info[idx].skb = NULL; + dma_unmap_len_set(buf, len, len); + dma_unmap_addr_set(buf, dma, addr); + + gve_tx_fill_seg_desc(seg_desc, skb, is_gso, len, addr); + } + + return 1 + payload_nfrags; + +unmap_drop: + i += (payload_nfrags == shinfo->nr_frags ? 1 : 2); + while (i--) { + idx--; + gve_tx_unmap_buf(tx->dev, &tx->info[idx & tx->mask]); + } +drop: + tx->dropped_pkt++; + return 0; +} + netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev) { struct gve_priv *priv = netdev_priv(dev); @@ -490,17 +601,26 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev) gve_tx_put_doorbell(priv, tx->q_resources, tx->req); return NETDEV_TX_BUSY; } - nsegs = gve_tx_add_skb(tx, skb, &priv->pdev->dev); - - netdev_tx_sent_queue(tx->netdev_txq, skb->len); - skb_tx_timestamp(skb); - - /* give packets to NIC */ - tx->req += nsegs; + if (tx->raw_addressing) + nsegs = gve_tx_add_skb_no_copy(priv, tx, skb); + else + nsegs = gve_tx_add_skb_copy(priv, tx, skb); + + /* If the packet is getting sent, we need to update the skb */ + if (nsegs) { + netdev_tx_sent_queue(tx->netdev_txq, skb->len); + skb_tx_timestamp(skb); + tx->req += nsegs; + } else { + dev_kfree_skb_any(skb); + } if (!netif_xmit_stopped(tx->netdev_txq) && netdev_xmit_more()) return NETDEV_TX_OK; + /* Give packets to NIC. Even if this packet failed to send the doorbell + * might need to be rung because of xmit_more. + */ gve_tx_put_doorbell(priv, tx->q_resources, tx->req); return NETDEV_TX_OK; } @@ -525,24 +645,29 @@ static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx, info = &tx->info[idx]; skb = info->skb; + /* Unmap the buffer */ + if (tx->raw_addressing) + gve_tx_unmap_buf(tx->dev, info); + tx->done++; /* Mark as free */ if (skb) { info->skb = NULL; bytes += skb->len; pkts++; 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; + space_freed += info->iov[i].iov_len + info->iov[i].iov_padding; info->iov[i].iov_len = 0; info->iov[i].iov_padding = 0; } } - tx->done++; } - gve_tx_free_fifo(&tx->tx_fifo, space_freed); + if (!tx->raw_addressing) + gve_tx_free_fifo(&tx->tx_fifo, space_freed); u64_stats_update_begin(&tx->statss); tx->bytes_done += bytes; tx->pkt_done += pkts; |