From: Jakub Kicinski kuba@kernel.org

Releasing the DMA mapping will be useful for other types of pages, so factor it out. Make sure compiler inlines it, to avoid any regressions.

Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Mina Almasry almasrymina@google.com

---

This is implemented by Jakub in his RFC:

https://lore.kernel.org/netdev/f8270765-a27b-6ccf-33ea-cda097168d79@redhat.c...

I take no credit for the idea or implementation. This is a critical dependency of device memory TCP and thus I'm pulling it into this series to make it revewable and mergable.

--- net/core/page_pool.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/net/core/page_pool.c b/net/core/page_pool.c index c2e7c9a6efbe..ca1b3b65c9b5 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -548,21 +548,16 @@ s32 page_pool_inflight(const struct page_pool *pool, bool strict) return inflight; }

-/* Disconnects a page (from a page_pool). API users can have a need - * to disconnect a page (from a page_pool), to allow it to be used as - * a regular page (that will eventually be returned to the normal - * page-allocator via put_page). - */ -static void page_pool_return_page(struct page_pool *pool, struct page *page) +static __always_inline +void __page_pool_release_page_dma(struct page_pool *pool, struct page *page) { dma_addr_t dma; - int count;

if (!(pool->p.flags & PP_FLAG_DMA_MAP)) /* Always account for inflight pages, even if we didn't * map them */ - goto skip_dma_unmap; + return;

dma = page_pool_get_dma_addr(page);

@@ -571,7 +566,19 @@ static void page_pool_return_page(struct page_pool *pool, struct page *page) PAGE_SIZE << pool->p.order, pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING); page_pool_set_dma_addr(page, 0); -skip_dma_unmap: +} + +/* Disconnects a page (from a page_pool). API users can have a need + * to disconnect a page (from a page_pool), to allow it to be used as + * a regular page (that will eventually be returned to the normal + * page-allocator via put_page). + */ +void page_pool_return_page(struct page_pool *pool, struct page *page) +{ + int count; + + __page_pool_release_page_dma(pool, page); + page_pool_clear_pp_info(page);

/* This may be the last page returned, releasing the pool, so

This API enables the net stack to reset the queues used for devmem.

Signed-off-by: Mina Almasry almasrymina@google.com

--- include/linux/netdevice.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1b935ee341b4..316f7dee86ce 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1432,6 +1432,20 @@ struct netdev_net_notifier { * struct kernel_hwtstamp_config *kernel_config, * struct netlink_ext_ack *extack); * Change the hardware timestamping parameters for NIC device. + * + * void *(*ndo_queue_mem_alloc)(struct net_device *dev, int idx); + * Allocate memory for an RX queue. The memory returned in the form of + * a void * can be passed to ndo_queue_mem_free() for freeing or to + * ndo_queue_start to create an RX queue with this memory. + * + * void (*ndo_queue_mem_free)(struct net_device *dev, void *); + * Free memory from an RX queue. + * + * int (*ndo_queue_start)(struct net_device *dev, int idx, void *); + * Start an RX queue at the specified index. + * + * int (*ndo_queue_stop)(struct net_device *dev, int idx, void **); + * Stop the RX queue at the specified index. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1673,6 +1687,16 @@ struct net_device_ops { int (*ndo_hwtstamp_set)(struct net_device *dev, struct kernel_hwtstamp_config *kernel_config, struct netlink_ext_ack *extack); + void * (*ndo_queue_mem_alloc)(struct net_device *dev, + int idx); + void (*ndo_queue_mem_free)(struct net_device *dev, + void *queue_mem); + int (*ndo_queue_start)(struct net_device *dev, + int idx, + void *queue_mem); + int (*ndo_queue_stop)(struct net_device *dev, + int idx, + void **out_queue_mem); };

/**

Define a struct that contains all of the memory needed for an RX queue to function.

Implement the queue-api in GVE using this struct.

Currently the only memory is allocated at the time of queue start are the RX pages in gve_rx_post_buffers_dqo(). That can be moved up to queue_mem_alloc() time in the future.

For simplicity the queue API is only supported by the diorite queue out-of-order (DQO) format without queue-page-lists (QPL). Support for other GVE formats can be added in the future as well.

Signed-off-by: Mina Almasry almasrymina@google.com

--- drivers/net/ethernet/google/gve/gve_adminq.c | 6 +- drivers/net/ethernet/google/gve/gve_adminq.h | 3 + drivers/net/ethernet/google/gve/gve_dqo.h | 2 + drivers/net/ethernet/google/gve/gve_main.c | 286 +++++++++++++++++++ drivers/net/ethernet/google/gve/gve_rx_dqo.c | 5 +- 5 files changed, 296 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index 12fbd723ecc6..e515b7278295 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -348,7 +348,7 @@ static int gve_adminq_parse_err(struct gve_priv *priv, u32 status) /* Flushes all AQ commands currently queued and waits for them to complete. * If there are failures, it will return the first error. */ -static int gve_adminq_kick_and_wait(struct gve_priv *priv) +int gve_adminq_kick_and_wait(struct gve_priv *priv) { int tail, head; int i; @@ -591,7 +591,7 @@ int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_que return gve_adminq_kick_and_wait(priv); }

-static int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index) +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; @@ -691,7 +691,7 @@ int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 start_id, u32 num_qu return gve_adminq_kick_and_wait(priv); }

-static int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_index) +int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_index) { union gve_adminq_command cmd; int err; diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index 5865ccdccbd0..265beed965dc 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -411,6 +411,7 @@ union gve_adminq_command {

static_assert(sizeof(union gve_adminq_command) == 64);

+int gve_adminq_kick_and_wait(struct gve_priv *priv); int gve_adminq_alloc(struct device *dev, struct gve_priv *priv); void gve_adminq_free(struct device *dev, struct gve_priv *priv); void gve_adminq_release(struct gve_priv *priv); @@ -424,7 +425,9 @@ int gve_adminq_deconfigure_device_resources(struct gve_priv *priv); 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_create_rx_queue(struct gve_priv *priv, u32 queue_index); int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 queue_id); +int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_id); int gve_adminq_register_page_list(struct gve_priv *priv, struct gve_queue_page_list *qpl); int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id); diff --git a/drivers/net/ethernet/google/gve/gve_dqo.h b/drivers/net/ethernet/google/gve/gve_dqo.h index c36b93f0de15..3eed26a0ed7d 100644 --- a/drivers/net/ethernet/google/gve/gve_dqo.h +++ b/drivers/net/ethernet/google/gve/gve_dqo.h @@ -46,6 +46,8 @@ int gve_clean_tx_done_dqo(struct gve_priv *priv, struct gve_tx_ring *tx, struct napi_struct *napi); void gve_rx_post_buffers_dqo(struct gve_rx_ring *rx); void gve_rx_write_doorbell_dqo(const struct gve_priv *priv, int queue_idx); +void gve_free_page_dqo(struct gve_priv *priv, struct gve_rx_buf_state_dqo *bs, + bool free_page);

static inline void gve_tx_put_doorbell_dqo(const struct gve_priv *priv, diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 619bf63ec935..5b23d811afd3 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -22,6 +22,7 @@ #include "gve_dqo.h" #include "gve_adminq.h" #include "gve_register.h" +#include "gve_utils.h"

#define GVE_DEFAULT_RX_COPYBREAK (256)

@@ -1702,6 +1703,287 @@ static int gve_xdp(struct net_device *dev, struct netdev_bpf *xdp) } }

+struct gve_per_rx_queue_mem_dqo { + struct gve_rx_buf_state_dqo *buf_states; + u32 num_buf_states; + + struct gve_rx_compl_desc_dqo *complq_desc_ring; + dma_addr_t complq_bus; + + struct gve_rx_desc_dqo *bufq_desc_ring; + dma_addr_t bufq_bus; + + struct gve_queue_resources *q_resources; + dma_addr_t q_resources_bus; + + size_t completion_queue_slots; + size_t buffer_queue_slots; +}; + +static int gve_rx_queue_stop(struct net_device *dev, int idx, + void **out_per_q_mem) +{ + struct gve_per_rx_queue_mem_dqo *per_q_mem; + struct gve_priv *priv = netdev_priv(dev); + struct gve_notify_block *block; + struct gve_rx_ring *rx; + int ntfy_idx; + int err; + + rx = &priv->rx[idx]; + ntfy_idx = gve_rx_idx_to_ntfy(priv, idx); + block = &priv->ntfy_blocks[ntfy_idx]; + + if (priv->queue_format != GVE_DQO_RDA_FORMAT) + return -EOPNOTSUPP; + + if (!out_per_q_mem) + return -EINVAL; + + /* Stopping queue 0 while other queues are running is unfortunately + * fails silently for GVE at the moment. Disable the queue-api for + * queue 0 until this is resolved. + */ + if (idx == 0) + return -ERANGE; + + per_q_mem = kvcalloc(1, sizeof(*per_q_mem), GFP_KERNEL); + if (!per_q_mem) + return -ENOMEM; + + napi_disable(&block->napi); + err = gve_adminq_destroy_rx_queue(priv, idx); + if (err) + goto err_napi_enable; + + err = gve_adminq_kick_and_wait(priv); + if (err) + goto err_create_rx_queue; + + gve_remove_napi(priv, ntfy_idx); + + per_q_mem->buf_states = rx->dqo.buf_states; + per_q_mem->num_buf_states = rx->dqo.num_buf_states; + + per_q_mem->complq_desc_ring = rx->dqo.complq.desc_ring; + per_q_mem->complq_bus = rx->dqo.complq.bus; + + per_q_mem->bufq_desc_ring = rx->dqo.bufq.desc_ring; + per_q_mem->bufq_bus = rx->dqo.bufq.bus; + + per_q_mem->q_resources = rx->q_resources; + per_q_mem->q_resources_bus = rx->q_resources_bus; + + per_q_mem->buffer_queue_slots = rx->dqo.bufq.mask + 1; + per_q_mem->completion_queue_slots = rx->dqo.complq.mask + 1; + + *out_per_q_mem = per_q_mem; + + return 0; + +err_create_rx_queue: + /* There is nothing we can do here if these fail. */ + gve_adminq_create_rx_queue(priv, idx); + gve_adminq_kick_and_wait(priv); + +err_napi_enable: + napi_enable(&block->napi); + kvfree(per_q_mem); + + return err; +} + +static void gve_rx_queue_mem_free(struct net_device *dev, void *per_q_mem) +{ + struct gve_per_rx_queue_mem_dqo *gve_q_mem; + struct gve_priv *priv = netdev_priv(dev); + struct gve_rx_buf_state_dqo *bs; + struct device *hdev; + size_t size; + int i; + + priv = netdev_priv(dev); + gve_q_mem = (struct gve_per_rx_queue_mem_dqo *)per_q_mem; + hdev = &priv->pdev->dev; + + if (!gve_q_mem) + return; + + if (priv->queue_format != GVE_DQO_RDA_FORMAT) + return; + + for (i = 0; i < gve_q_mem->num_buf_states; i++) { + bs = &gve_q_mem->buf_states[i]; + if (bs->page_info.page) + gve_free_page_dqo(priv, bs, true); + } + + if (gve_q_mem->q_resources) + dma_free_coherent(hdev, sizeof(*gve_q_mem->q_resources), + gve_q_mem->q_resources, + gve_q_mem->q_resources_bus); + + if (gve_q_mem->bufq_desc_ring) { + size = sizeof(gve_q_mem->bufq_desc_ring[0]) * + gve_q_mem->buffer_queue_slots; + dma_free_coherent(hdev, size, gve_q_mem->bufq_desc_ring, + gve_q_mem->bufq_bus); + } + + if (gve_q_mem->complq_desc_ring) { + size = sizeof(gve_q_mem->complq_desc_ring[0]) * + gve_q_mem->completion_queue_slots; + dma_free_coherent(hdev, size, gve_q_mem->complq_desc_ring, + gve_q_mem->complq_bus); + } + + kvfree(gve_q_mem->buf_states); + + kvfree(per_q_mem); +} + +static void *gve_rx_queue_mem_alloc(struct net_device *dev, int idx) +{ + struct gve_per_rx_queue_mem_dqo *gve_q_mem; + struct gve_priv *priv = netdev_priv(dev); + struct device *hdev = &priv->pdev->dev; + size_t size; + + if (priv->queue_format != GVE_DQO_RDA_FORMAT) + return NULL; + + /* See comment in gve_rx_queue_stop() */ + if (idx == 0) + return NULL; + + gve_q_mem = kvcalloc(1, sizeof(*gve_q_mem), GFP_KERNEL); + if (!gve_q_mem) + goto err; + + gve_q_mem->buffer_queue_slots = + priv->options_dqo_rda.rx_buff_ring_entries; + gve_q_mem->completion_queue_slots = priv->rx_desc_cnt; + + gve_q_mem->num_buf_states = + min_t(s16, S16_MAX, gve_q_mem->buffer_queue_slots * 4); + + gve_q_mem->buf_states = kvcalloc(gve_q_mem->num_buf_states, + sizeof(gve_q_mem->buf_states[0]), + GFP_KERNEL); + if (!gve_q_mem->buf_states) + goto err; + + size = sizeof(struct gve_rx_compl_desc_dqo) * + gve_q_mem->completion_queue_slots; + gve_q_mem->complq_desc_ring = dma_alloc_coherent(hdev, size, + &gve_q_mem->complq_bus, + GFP_KERNEL); + if (!gve_q_mem->complq_desc_ring) + goto err; + + size = sizeof(struct gve_rx_desc_dqo) * gve_q_mem->buffer_queue_slots; + gve_q_mem->bufq_desc_ring = dma_alloc_coherent(hdev, size, + &gve_q_mem->bufq_bus, + GFP_KERNEL); + if (!gve_q_mem->bufq_desc_ring) + goto err; + + gve_q_mem->q_resources = dma_alloc_coherent(hdev, + sizeof(*gve_q_mem->q_resources), + &gve_q_mem->q_resources_bus, + GFP_KERNEL); + if (!gve_q_mem->q_resources) + goto err; + + return gve_q_mem; + +err: + gve_rx_queue_mem_free(dev, gve_q_mem); + return NULL; +} + +static int gve_rx_queue_start(struct net_device *dev, int idx, void *per_q_mem) +{ + struct gve_per_rx_queue_mem_dqo *gve_q_mem; + struct gve_priv *priv = netdev_priv(dev); + struct gve_rx_ring *rx = &priv->rx[idx]; + struct gve_notify_block *block; + int ntfy_idx; + int err; + int i; + + if (priv->queue_format != GVE_DQO_RDA_FORMAT) + return -EOPNOTSUPP; + + /* See comment in gve_rx_queue_stop() */ + if (idx == 0) + return -ERANGE; + + gve_q_mem = (struct gve_per_rx_queue_mem_dqo *)per_q_mem; + ntfy_idx = gve_rx_idx_to_ntfy(priv, idx); + block = &priv->ntfy_blocks[ntfy_idx]; + + netif_dbg(priv, drv, priv->dev, "starting rx ring DQO\n"); + + memset(rx, 0, sizeof(*rx)); + rx->gve = priv; + rx->q_num = idx; + rx->dqo.bufq.mask = gve_q_mem->buffer_queue_slots - 1; + rx->dqo.complq.num_free_slots = gve_q_mem->completion_queue_slots; + rx->dqo.complq.mask = gve_q_mem->completion_queue_slots - 1; + rx->ctx.skb_head = NULL; + rx->ctx.skb_tail = NULL; + + rx->dqo.num_buf_states = gve_q_mem->num_buf_states; + + rx->dqo.buf_states = gve_q_mem->buf_states; + + /* Set up linked list of buffer IDs */ + for (i = 0; i < rx->dqo.num_buf_states - 1; i++) + rx->dqo.buf_states[i].next = i + 1; + + rx->dqo.buf_states[rx->dqo.num_buf_states - 1].next = -1; + rx->dqo.recycled_buf_states.head = -1; + rx->dqo.recycled_buf_states.tail = -1; + rx->dqo.used_buf_states.head = -1; + rx->dqo.used_buf_states.tail = -1; + + rx->dqo.complq.desc_ring = gve_q_mem->complq_desc_ring; + rx->dqo.complq.bus = gve_q_mem->complq_bus; + + rx->dqo.bufq.desc_ring = gve_q_mem->bufq_desc_ring; + rx->dqo.bufq.bus = gve_q_mem->bufq_bus; + + rx->q_resources = gve_q_mem->q_resources; + rx->q_resources_bus = gve_q_mem->q_resources_bus; + + gve_rx_add_to_block(priv, idx); + + err = gve_adminq_create_rx_queue(priv, idx); + if (err) + return err; + + err = gve_adminq_kick_and_wait(priv); + if (err) + goto err_destroy_rx_queue; + + /* TODO, pull the memory allocations in this to gve_rx_queue_mem_alloc() + */ + gve_rx_post_buffers_dqo(&priv->rx[idx]); + + napi_enable(&block->napi); + gve_set_itr_coalesce_usecs_dqo(priv, block, priv->rx_coalesce_usecs); + + return 0; + +err_destroy_rx_queue: + /* There is nothing we can do if these fail. */ + gve_adminq_destroy_rx_queue(priv, idx); + gve_adminq_kick_and_wait(priv); + + return err; +} + int gve_adjust_queues(struct gve_priv *priv, struct gve_queue_config new_rx_config, struct gve_queue_config new_tx_config) @@ -1900,6 +2182,10 @@ static const struct net_device_ops gve_netdev_ops = { .ndo_bpf = gve_xdp, .ndo_xdp_xmit = gve_xdp_xmit, .ndo_xsk_wakeup = gve_xsk_wakeup, + .ndo_queue_mem_alloc = gve_rx_queue_mem_alloc, + .ndo_queue_mem_free = gve_rx_queue_mem_free, + .ndo_queue_start = gve_rx_queue_start, + .ndo_queue_stop = gve_rx_queue_stop, };

static void gve_handle_status(struct gve_priv *priv, u32 status) diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index f281e42a7ef9..e729f04d3f60 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -21,9 +21,8 @@ static int gve_buf_ref_cnt(struct gve_rx_buf_state_dqo *bs) return page_count(bs->page_info.page) - bs->page_info.pagecnt_bias; }

-static void gve_free_page_dqo(struct gve_priv *priv, - struct gve_rx_buf_state_dqo *bs, - bool free_page) +void gve_free_page_dqo(struct gve_priv *priv, struct gve_rx_buf_state_dqo *bs, + bool free_page) { page_ref_sub(bs->page_info.page, bs->page_info.pagecnt_bias - 1); if (free_page)

API takes the dma-buf fd as input, and binds it to the netdevice. The user can specify the rx queues to bind the dma-buf to.

Suggested-by: Stanislav Fomichev sdf@google.com Signed-off-by: Mina Almasry almasrymina@google.com

---

Changes in v1: - Add rx-queue-type to distingish rx from tx (Jakub) - Return dma-buf ID from netlink API (David, Stan)

Changes in RFC-v3: - Support binding multiple rx rx-queues

--- Documentation/netlink/specs/netdev.yaml | 52 +++++++++++++++++++++++++ include/uapi/linux/netdev.h | 19 +++++++++ net/core/netdev-genl-gen.c | 19 +++++++++ net/core/netdev-genl-gen.h | 2 + net/core/netdev-genl.c | 6 +++ tools/include/uapi/linux/netdev.h | 19 +++++++++ 6 files changed, 117 insertions(+)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index f2c76d103bd8..df6a11d47006 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -260,6 +260,45 @@ attribute-sets: name: napi-id doc: ID of the NAPI instance which services this queue. type: u32 + - + name: queue-dmabuf + attributes: + - + name: type + doc: rx or tx queue + type: u8 + enum: queue-type + - + name: idx + doc: queue index + type: u32 + + - + name: bind-dmabuf + attributes: + - + name: ifindex + doc: netdev ifindex to bind the dma-buf to. + type: u32 + checks: + min: 1 + - + name: queues + doc: receive queues to bind the dma-buf to. + type: nest + nested-attributes: queue-dmabuf + multi-attr: true + - + name: dmabuf-fd + doc: dmabuf file descriptor to bind. + type: u32 + - + name: dmabuf-id + doc: id of the dmabuf binding + type: u32 + checks: + min: 1 +

operations: list: @@ -382,6 +421,19 @@ operations: attributes: - ifindex reply: *queue-get-op + - + name: bind-rx + doc: Bind dmabuf to netdev + attribute-set: bind-dmabuf + do: + request: + attributes: + - ifindex + - dmabuf-fd + - queues + reply: + attributes: + - dmabuf-id - name: napi-get doc: Get information about NAPI instances configured on the system. diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 424c5e28f495..35d201dc4b05 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -129,6 +129,24 @@ enum { NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) };

+enum { + NETDEV_A_QUEUE_DMABUF_TYPE = 1, + NETDEV_A_QUEUE_DMABUF_IDX, + + __NETDEV_A_QUEUE_DMABUF_MAX, + NETDEV_A_QUEUE_DMABUF_MAX = (__NETDEV_A_QUEUE_DMABUF_MAX - 1) +}; + +enum { + NETDEV_A_BIND_DMABUF_IFINDEX = 1, + NETDEV_A_BIND_DMABUF_QUEUES, + NETDEV_A_BIND_DMABUF_DMABUF_FD, + NETDEV_A_BIND_DMABUF_DMABUF_ID, + + __NETDEV_A_BIND_DMABUF_MAX, + NETDEV_A_BIND_DMABUF_MAX = (__NETDEV_A_BIND_DMABUF_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, @@ -140,6 +158,7 @@ enum { NETDEV_CMD_PAGE_POOL_CHANGE_NTF, NETDEV_CMD_PAGE_POOL_STATS_GET, NETDEV_CMD_QUEUE_GET, + NETDEV_CMD_BIND_RX, NETDEV_CMD_NAPI_GET,

__NETDEV_CMD_MAX, diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index be7f2ebd61b2..3384b1ae3f40 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -27,6 +27,11 @@ const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFIND [NETDEV_A_PAGE_POOL_IFINDEX] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_page_pool_ifindex_range), };

+const struct nla_policy netdev_queue_dmabuf_nl_policy[NETDEV_A_QUEUE_DMABUF_IDX + 1] = { + [NETDEV_A_QUEUE_DMABUF_TYPE] = NLA_POLICY_MAX(NLA_U8, 1), + [NETDEV_A_QUEUE_DMABUF_IDX] = { .type = NLA_U32, }, +}; + /* NETDEV_CMD_DEV_GET - do */ static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = { [NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), @@ -58,6 +63,13 @@ static const struct nla_policy netdev_queue_get_dump_nl_policy[NETDEV_A_QUEUE_IF [NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), };

+/* NETDEV_CMD_BIND_RX - do */ +static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_BIND_DMABUF_DMABUF_FD + 1] = { + [NETDEV_A_BIND_DMABUF_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), + [NETDEV_A_BIND_DMABUF_DMABUF_FD] = { .type = NLA_U32, }, + [NETDEV_A_BIND_DMABUF_QUEUES] = NLA_POLICY_NESTED(netdev_queue_dmabuf_nl_policy), +}; + /* NETDEV_CMD_NAPI_GET - do */ static const struct nla_policy netdev_napi_get_do_nl_policy[NETDEV_A_NAPI_ID + 1] = { [NETDEV_A_NAPI_ID] = { .type = NLA_U32, }, @@ -124,6 +136,13 @@ static const struct genl_split_ops netdev_nl_ops[] = { .maxattr = NETDEV_A_QUEUE_IFINDEX, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = NETDEV_CMD_BIND_RX, + .doit = netdev_nl_bind_rx_doit, + .policy = netdev_bind_rx_nl_policy, + .maxattr = NETDEV_A_BIND_DMABUF_DMABUF_FD, + .flags = GENL_CMD_CAP_DO, + }, { .cmd = NETDEV_CMD_NAPI_GET, .doit = netdev_nl_napi_get_doit, diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index a47f2bcbe4fa..a7ede514eccd 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -13,6 +13,7 @@

/* Common nested types */ extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1]; +extern const struct nla_policy netdev_queue_dmabuf_nl_policy[NETDEV_A_QUEUE_DMABUF_IDX + 1];

int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); @@ -26,6 +27,7 @@ int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb, int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);

diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index fd98936da3ae..0ed292d87ae0 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -469,6 +469,12 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; }

+/* Stub */ +int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) +{ + return 0; +} + static int netdev_genl_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 424c5e28f495..35d201dc4b05 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -129,6 +129,24 @@ enum { NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) };

+enum { + NETDEV_A_QUEUE_DMABUF_TYPE = 1, + NETDEV_A_QUEUE_DMABUF_IDX, + + __NETDEV_A_QUEUE_DMABUF_MAX, + NETDEV_A_QUEUE_DMABUF_MAX = (__NETDEV_A_QUEUE_DMABUF_MAX - 1) +}; + +enum { + NETDEV_A_BIND_DMABUF_IFINDEX = 1, + NETDEV_A_BIND_DMABUF_QUEUES, + NETDEV_A_BIND_DMABUF_DMABUF_FD, + NETDEV_A_BIND_DMABUF_DMABUF_ID, + + __NETDEV_A_BIND_DMABUF_MAX, + NETDEV_A_BIND_DMABUF_MAX = (__NETDEV_A_BIND_DMABUF_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, @@ -140,6 +158,7 @@ enum { NETDEV_CMD_PAGE_POOL_CHANGE_NTF, NETDEV_CMD_PAGE_POOL_STATS_GET, NETDEV_CMD_QUEUE_GET, + NETDEV_CMD_BIND_RX, NETDEV_CMD_NAPI_GET,

__NETDEV_CMD_MAX,

Add a netdev_dmabuf_binding struct which represents the dma-buf-to-netdevice binding. The netlink API will bind the dma-buf to rx queues on the netdevice. On the binding, the dma_buf_attach & dma_buf_map_attachment will occur. The entries in the sg_table from mapping will be inserted into a genpool to make it ready for allocation.

The chunks in the genpool are owned by a dmabuf_chunk_owner struct which holds the dma-buf offset of the base of the chunk and the dma_addr of the chunk. Both are needed to use allocations that come from this chunk.

We create a new type that represents an allocation from the genpool: page_pool_iov. We setup the page_pool_iov allocation size in the genpool to PAGE_SIZE for simplicity: to match the PAGE_SIZE normally allocated by the page pool and given to the drivers.

The user can unbind the dmabuf from the netdevice by closing the netlink socket that established the binding. We do this so that the binding is automatically unbound even if the userspace process crashes.

The binding and unbinding leaves an indicator in struct netdev_rx_queue that the given queue is bound, but the binding doesn't take effect until the driver actually reconfigures its queues, and re-initializes its page pool.

The netdev_dmabuf_binding struct is refcounted, and releases its resources only when all the refs are released.

Signed-off-by: Willem de Bruijn willemb@google.com Signed-off-by: Kaiyuan Zhang kaiyuanz@google.com Signed-off-by: Mina Almasry almasrymina@google.com

---

v1:

- Introduce devmem.h instead of bloating netdevice.h (Jakub) - ENOTSUPP -> EOPNOTSUPP (checkpatch.pl I think) - Remove unneeded rcu protection for binding->list (rtnl protected) - Removed extraneous err_binding_put: label. - Removed dma_addr += len (Paolo). - Don't override err on netdev_bind_dmabuf_to_queue failure. - Rename devmem -> dmabuf (David). - Add id to dmabuf binding (David/Stan). - Fix missing xa_destroy bound_rq_list. - Use queue api to reset bound RX queues (Jakub). - Update netlink API for rx-queue type (tx/re) (Jakub).

RFC v3: - Support multi rx-queue binding

--- include/net/devmem.h | 96 ++++++++++++ include/net/netdev_rx_queue.h | 1 + include/net/page_pool/types.h | 27 ++++ net/core/dev.c | 276 ++++++++++++++++++++++++++++++++++ net/core/netdev-genl.c | 122 ++++++++++++++- 5 files changed, 520 insertions(+), 2 deletions(-) create mode 100644 include/net/devmem.h

diff --git a/include/net/devmem.h b/include/net/devmem.h new file mode 100644 index 000000000000..29ff125f9815 --- /dev/null +++ b/include/net/devmem.h @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Device memory TCP support + * + * Authors: Mina Almasry almasrymina@google.com + * Willem de Bruijn willemb@google.com + * Kaiyuan Zhang kaiyuanz@google.com + * + */ +#ifndef _NET_DEVMEM_H +#define _NET_DEVMEM_H + +struct netdev_dmabuf_binding { + struct dma_buf *dmabuf; + struct dma_buf_attachment *attachment; + struct sg_table *sgt; + struct net_device *dev; + struct gen_pool *chunk_pool; + + /* The user holds a ref (via the netlink API) for as long as they want + * the binding to remain alive. Each page pool using this binding holds + * a ref to keep the binding alive. Each allocated page_pool_iov holds a + * ref. + * + * The binding undos itself and unmaps the underlying dmabuf once all + * those refs are dropped and the binding is no longer desired or in + * use. + */ + refcount_t ref; + + /* The portid of the user that owns this binding. Used for netlink to + * notify us of the user dropping the bind. + */ + u32 owner_nlportid; + + /* The list of bindings currently active. Used for netlink to notify us + * of the user dropping the bind. + */ + struct list_head list; + + /* rxq's this binding is active on. */ + struct xarray bound_rxq_list; + + /* ID of this binding. Globally unique to all bindings currently + * active. + */ + u32 id; +}; + +#ifdef CONFIG_DMA_SHARED_BUFFER +void __netdev_dmabuf_binding_free(struct netdev_dmabuf_binding *binding); +int netdev_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, + struct netdev_dmabuf_binding **out); +void netdev_unbind_dmabuf(struct netdev_dmabuf_binding *binding); +int netdev_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct netdev_dmabuf_binding *binding); +#else +static inline void +__netdev_dmabuf_binding_free(struct netdev_dmabuf_binding *binding) +{ +} + +static inline int netdev_bind_dmabuf(struct net_device *dev, + unsigned int dmabuf_fd, + struct netdev_dmabuf_binding **out) +{ + return -EOPNOTSUPP; +} +static inline void netdev_unbind_dmabuf(struct netdev_dmabuf_binding *binding) +{ +} + +static inline int +netdev_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct netdev_dmabuf_binding *binding) +{ + return -EOPNOTSUPP; +} +#endif + +static inline void +netdev_dmabuf_binding_get(struct netdev_dmabuf_binding *binding) +{ + refcount_inc(&binding->ref); +} + +static inline void +netdev_dmabuf_binding_put(struct netdev_dmabuf_binding *binding) +{ + if (!refcount_dec_and_test(&binding->ref)) + return; + + __netdev_dmabuf_binding_free(binding); +} + +#endif /* _NET_DEVMEM_H */ diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index aa1716fb0e53..5dc35628633a 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -25,6 +25,7 @@ struct netdev_rx_queue { * Readers and writers must hold RTNL */ struct napi_struct *napi; + struct netdev_dmabuf_binding *binding; } ____cacheline_aligned_in_smp;

/* diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 0e9fa79a5ef1..44faee7a7b02 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -134,6 +134,33 @@ struct memory_provider_ops { bool (*release_page)(struct page_pool *pool, struct page *page); };

+/* page_pool_iov support */ + +/* Owner of the dma-buf chunks inserted into the gen pool. Each scatterlist + * entry from the dmabuf is inserted into the genpool as a chunk, and needs + * this owner struct to keep track of some metadata necessary to create + * allocations from this chunk. + */ +struct dmabuf_genpool_chunk_owner { + /* Offset into the dma-buf where this chunk starts. */ + unsigned long base_virtual; + + /* dma_addr of the start of the chunk. */ + dma_addr_t base_dma_addr; + + /* Array of page_pool_iovs for this chunk. */ + struct page_pool_iov *ppiovs; + size_t num_ppiovs; + + struct netdev_dmabuf_binding *binding; +}; + +struct page_pool_iov { + struct dmabuf_genpool_chunk_owner *owner; + + refcount_t refcount; +}; + struct page_pool { struct page_pool_params_fast p;

diff --git a/net/core/dev.c b/net/core/dev.c index 0432b04cf9b0..b8c8be5a912e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -153,6 +153,10 @@ #include <linux/prandom.h> #include <linux/once_lite.h> #include <net/netdev_rx_queue.h> +#include <linux/genalloc.h> +#include <linux/dma-buf.h> +#include <net/page_pool/types.h> +#include <net/devmem.h>

#include "dev.h" #include "net-sysfs.h" @@ -2041,6 +2045,278 @@ static int call_netdevice_notifiers_mtu(unsigned long val, return call_netdevice_notifiers_info(val, &info.info); }

+/* Device memory support */ + +#ifdef CONFIG_DMA_SHARED_BUFFER +static void netdev_dmabuf_free_chunk_owner(struct gen_pool *genpool, + struct gen_pool_chunk *chunk, + void *not_used) +{ + struct dmabuf_genpool_chunk_owner *owner = chunk->owner; + + kvfree(owner->ppiovs); + kfree(owner); +} + +void __netdev_dmabuf_binding_free(struct netdev_dmabuf_binding *binding) +{ + size_t size, avail; + + gen_pool_for_each_chunk(binding->chunk_pool, + netdev_dmabuf_free_chunk_owner, NULL); + + size = gen_pool_size(binding->chunk_pool); + avail = gen_pool_avail(binding->chunk_pool); + + if (!WARN(size != avail, "can't destroy genpool. size=%lu, avail=%lu", + size, avail)) + gen_pool_destroy(binding->chunk_pool); + + dma_buf_unmap_attachment(binding->attachment, binding->sgt, + DMA_BIDIRECTIONAL); + dma_buf_detach(binding->dmabuf, binding->attachment); + dma_buf_put(binding->dmabuf); + xa_destroy(&binding->bound_rxq_list); + kfree(binding); +} + +static int netdev_restart_rx_queue(struct net_device *dev, int rxq_idx) +{ + void *new_mem; + void *old_mem; + int err; + + if (!dev || !dev->netdev_ops) + return -EINVAL; + + if (!dev->netdev_ops->ndo_queue_stop || + !dev->netdev_ops->ndo_queue_mem_free || + !dev->netdev_ops->ndo_queue_mem_alloc || + !dev->netdev_ops->ndo_queue_start) + return -EOPNOTSUPP; + + new_mem = dev->netdev_ops->ndo_queue_mem_alloc(dev, rxq_idx); + if (!new_mem) + return -ENOMEM; + + err = dev->netdev_ops->ndo_queue_stop(dev, rxq_idx, &old_mem); + if (err) + goto err_free_new_mem; + + err = dev->netdev_ops->ndo_queue_start(dev, rxq_idx, new_mem); + if (err) + goto err_start_queue; + + dev->netdev_ops->ndo_queue_mem_free(dev, old_mem); + + return 0; + +err_start_queue: + dev->netdev_ops->ndo_queue_start(dev, rxq_idx, old_mem); + +err_free_new_mem: + dev->netdev_ops->ndo_queue_mem_free(dev, new_mem); + + return err; +} + +/* Protected by rtnl_lock() */ +static DEFINE_XARRAY_FLAGS(netdev_dmabuf_bindings, XA_FLAGS_ALLOC1); + +void netdev_unbind_dmabuf(struct netdev_dmabuf_binding *binding) +{ + struct netdev_rx_queue *rxq; + unsigned long xa_idx; + unsigned int rxq_idx; + + if (!binding) + return; + + if (binding->list.next) + list_del(&binding->list); + + xa_for_each(&binding->bound_rxq_list, xa_idx, rxq) { + if (rxq->binding == binding) { + /* We hold the rtnl_lock while binding/unbinding + * dma-buf, so we can't race with another thread that + * is also modifying this value. However, the driver + * may read this config while it's creating its + * rx-queues. WRITE_ONCE() here to match the + * READ_ONCE() in the driver. + */ + WRITE_ONCE(rxq->binding, NULL); + + rxq_idx = get_netdev_rx_queue_index(rxq); + + netdev_restart_rx_queue(binding->dev, rxq_idx); + } + } + + xa_erase(&netdev_dmabuf_bindings, binding->id); + + netdev_dmabuf_binding_put(binding); +} + +int netdev_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct netdev_dmabuf_binding *binding) +{ + struct netdev_rx_queue *rxq; + u32 xa_idx; + int err; + + rxq = __netif_get_rx_queue(dev, rxq_idx); + + if (rxq->binding) + return -EEXIST; + + err = xa_alloc(&binding->bound_rxq_list, &xa_idx, rxq, xa_limit_32b, + GFP_KERNEL); + if (err) + return err; + + /* We hold the rtnl_lock while binding/unbinding dma-buf, so we can't + * race with another thread that is also modifying this value. However, + * the driver may read this config while it's creating its * rx-queues. + * WRITE_ONCE() here to match the READ_ONCE() in the driver. + */ + WRITE_ONCE(rxq->binding, binding); + + err = netdev_restart_rx_queue(dev, rxq_idx); + if (err) + goto err_xa_erase; + + return 0; + +err_xa_erase: + xa_erase(&binding->bound_rxq_list, xa_idx); + WRITE_ONCE(rxq->binding, NULL); + + return err; +} + +int netdev_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, + struct netdev_dmabuf_binding **out) +{ + struct netdev_dmabuf_binding *binding; + static u32 id_alloc_next; + struct scatterlist *sg; + struct dma_buf *dmabuf; + unsigned int sg_idx, i; + unsigned long virtual; + int err; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + dmabuf = dma_buf_get(dmabuf_fd); + if (IS_ERR_OR_NULL(dmabuf)) + return -EBADFD; + + binding = kzalloc_node(sizeof(*binding), GFP_KERNEL, + dev_to_node(&dev->dev)); + if (!binding) { + err = -ENOMEM; + goto err_put_dmabuf; + } + binding->dev = dev; + + err = xa_alloc_cyclic(&netdev_dmabuf_bindings, &binding->id, binding, + xa_limit_32b, &id_alloc_next, GFP_KERNEL); + if (err < 0) + goto err_free_binding; + + xa_init_flags(&binding->bound_rxq_list, XA_FLAGS_ALLOC); + + refcount_set(&binding->ref, 1); + + binding->dmabuf = dmabuf; + + binding->attachment = dma_buf_attach(binding->dmabuf, dev->dev.parent); + if (IS_ERR(binding->attachment)) { + err = PTR_ERR(binding->attachment); + goto err_free_id; + } + + binding->sgt = dma_buf_map_attachment(binding->attachment, + DMA_BIDIRECTIONAL); + if (IS_ERR(binding->sgt)) { + err = PTR_ERR(binding->sgt); + goto err_detach; + } + + /* For simplicity we expect to make PAGE_SIZE allocations, but the + * binding can be much more flexible than that. We may be able to + * allocate MTU sized chunks here. Leave that for future work... + */ + binding->chunk_pool = gen_pool_create(PAGE_SHIFT, + dev_to_node(&dev->dev)); + if (!binding->chunk_pool) { + err = -ENOMEM; + goto err_unmap; + } + + virtual = 0; + for_each_sgtable_dma_sg(binding->sgt, sg, sg_idx) { + dma_addr_t dma_addr = sg_dma_address(sg); + struct dmabuf_genpool_chunk_owner *owner; + size_t len = sg_dma_len(sg); + struct page_pool_iov *ppiov; + + owner = kzalloc_node(sizeof(*owner), GFP_KERNEL, + dev_to_node(&dev->dev)); + owner->base_virtual = virtual; + owner->base_dma_addr = dma_addr; + owner->num_ppiovs = len / PAGE_SIZE; + owner->binding = binding; + + err = gen_pool_add_owner(binding->chunk_pool, dma_addr, + dma_addr, len, dev_to_node(&dev->dev), + owner); + if (err) { + err = -EINVAL; + goto err_free_chunks; + } + + owner->ppiovs = kvmalloc_array(owner->num_ppiovs, + sizeof(*owner->ppiovs), + GFP_KERNEL); + if (!owner->ppiovs) { + err = -ENOMEM; + goto err_free_chunks; + } + + for (i = 0; i < owner->num_ppiovs; i++) { + ppiov = &owner->ppiovs[i]; + ppiov->owner = owner; + refcount_set(&ppiov->refcount, 1); + } + + virtual += len; + } + + *out = binding; + + return 0; + +err_free_chunks: + gen_pool_for_each_chunk(binding->chunk_pool, + netdev_dmabuf_free_chunk_owner, NULL); + gen_pool_destroy(binding->chunk_pool); +err_unmap: + dma_buf_unmap_attachment(binding->attachment, binding->sgt, + DMA_BIDIRECTIONAL); +err_detach: + dma_buf_detach(dmabuf, binding->attachment); +err_free_id: + xa_erase(&netdev_dmabuf_bindings, binding->id); +err_free_binding: + kfree(binding); +err_put_dmabuf: + dma_buf_put(dmabuf); + return err; +} +#endif + #ifdef CONFIG_NET_INGRESS static DEFINE_STATIC_KEY_FALSE(ingress_needed_key);

diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 0ed292d87ae0..b3323812d0b0 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -9,6 +9,7 @@ #include <net/xdp_sock.h> #include <net/netdev_rx_queue.h> #include <net/busy_poll.h> +#include <net/devmem.h>

#include "netdev-genl-gen.h" #include "dev.h" @@ -469,10 +470,94 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; }

-/* Stub */ +static LIST_HEAD(netdev_rbinding_list); + int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) { - return 0; + struct nlattr *tb[ARRAY_SIZE(netdev_queue_dmabuf_nl_policy)]; + struct netdev_dmabuf_binding *out_binding; + u32 ifindex, dmabuf_fd, rxq_idx; + struct net_device *netdev; + struct sk_buff *rsp; + struct nlattr *attr; + int rem, err = 0; + void *hdr; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_BIND_DMABUF_DMABUF_FD) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_BIND_DMABUF_QUEUES)) + return -EINVAL; + + ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); + dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_BIND_DMABUF_DMABUF_FD]); + + rtnl_lock(); + + netdev = __dev_get_by_index(genl_info_net(info), ifindex); + if (!netdev) { + err = -ENODEV; + goto err_unlock; + } + + err = netdev_bind_dmabuf(netdev, dmabuf_fd, &out_binding); + if (err) + goto err_unlock; + + nla_for_each_attr(attr, genlmsg_data(info->genlhdr), + genlmsg_len(info->genlhdr), rem) { + if (nla_type(attr) != NETDEV_A_BIND_DMABUF_QUEUES) + continue; + + err = nla_parse_nested(tb, + ARRAY_SIZE(netdev_queue_dmabuf_nl_policy) - 1, + attr, netdev_queue_dmabuf_nl_policy, + info->extack); + + if (err < 0) + goto err_unbind; + + rxq_idx = nla_get_u32(tb[NETDEV_A_QUEUE_DMABUF_IDX]); + + if (rxq_idx >= netdev->num_rx_queues) { + err = -ERANGE; + goto err_unbind; + } + + err = netdev_bind_dmabuf_to_queue(netdev, rxq_idx, out_binding); + if (err) + goto err_unbind; + } + + out_binding->owner_nlportid = info->snd_portid; + list_add(&out_binding->list, &netdev_rbinding_list); + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) { + err = -ENOMEM; + goto err_unbind; + } + + hdr = genlmsg_put(rsp, info->snd_portid, info->snd_seq, + &netdev_nl_family, 0, info->genlhdr->cmd); + if (!hdr) { + err = -EMSGSIZE; + goto err_genlmsg_free; + } + + nla_put_u32(rsp, NETDEV_A_BIND_DMABUF_DMABUF_ID, out_binding->id); + genlmsg_end(rsp, hdr); + + rtnl_unlock(); + + return genlmsg_reply(rsp, info); + +err_genlmsg_free: + nlmsg_free(rsp); +err_unbind: + netdev_unbind_dmabuf(out_binding); +err_unlock: + rtnl_unlock(); + return err; }

static int netdev_genl_netdevice_event(struct notifier_block *nb, @@ -495,10 +580,37 @@ static int netdev_genl_netdevice_event(struct notifier_block *nb, return NOTIFY_OK; }

+static int netdev_netlink_notify(struct notifier_block *nb, unsigned long state, + void *_notify) +{ + struct netlink_notify *notify = _notify; + struct netdev_dmabuf_binding *rbinding; + + if (state != NETLINK_URELEASE || notify->protocol != NETLINK_GENERIC) + return NOTIFY_DONE; + + rtnl_lock(); + + list_for_each_entry(rbinding, &netdev_rbinding_list, list) { + if (rbinding->owner_nlportid == notify->portid) { + netdev_unbind_dmabuf(rbinding); + break; + } + } + + rtnl_unlock(); + + return NOTIFY_OK; +} + static struct notifier_block netdev_genl_nb = { .notifier_call = netdev_genl_netdevice_event, };

+static struct notifier_block netdev_netlink_notifier = { + .notifier_call = netdev_netlink_notify, +}; + static int __init netdev_genl_init(void) { int err; @@ -511,8 +623,14 @@ static int __init netdev_genl_init(void) if (err) goto err_unreg_ntf;

+ err = netlink_register_notifier(&netdev_netlink_notifier); + if (err) + goto err_unreg_family; + return 0;

+err_unreg_family: + genl_unregister_family(&netdev_nl_family); err_unreg_ntf: unregister_netdevice_notifier(&netdev_genl_nb); return err;

Implement netdev devmem allocator. The allocator takes a given struct netdev_dmabuf_binding as input and allocates page_pool_iov from that binding.

The allocation simply delegates to the binding's genpool for the allocation logic and wraps the returned memory region in a page_pool_iov struct.

page_pool_iov are refcounted and are freed back to the binding when the refcount drops to 0.

Signed-off-by: Willem de Bruijn willemb@google.com Signed-off-by: Kaiyuan Zhang kaiyuanz@google.com Signed-off-by: Mina Almasry almasrymina@google.com

---

v1: - Rename devmem -> dmabuf (David).

--- include/net/devmem.h | 13 ++++++++++++ include/net/page_pool/helpers.h | 28 +++++++++++++++++++++++++ net/core/dev.c | 37 ++++++++++++++++++++++++++++++++- 3 files changed, 77 insertions(+), 1 deletion(-)

diff --git a/include/net/devmem.h b/include/net/devmem.h index 29ff125f9815..29bc337c7743 100644 --- a/include/net/devmem.h +++ b/include/net/devmem.h @@ -48,6 +48,9 @@ struct netdev_dmabuf_binding { };

#ifdef CONFIG_DMA_SHARED_BUFFER +struct page_pool_iov * +netdev_alloc_dmabuf(struct netdev_dmabuf_binding *binding); +void netdev_free_dmabuf(struct page_pool_iov *ppiov); void __netdev_dmabuf_binding_free(struct netdev_dmabuf_binding *binding); int netdev_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, struct netdev_dmabuf_binding **out); @@ -55,6 +58,16 @@ void netdev_unbind_dmabuf(struct netdev_dmabuf_binding *binding); int netdev_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, struct netdev_dmabuf_binding *binding); #else +static inline struct page_pool_iov * +netdev_alloc_dmabuf(struct netdev_dmabuf_binding *binding) +{ + return NULL; +} + +static inline void netdev_free_dmabuf(struct page_pool_iov *ppiov) +{ +} + static inline void __netdev_dmabuf_binding_free(struct netdev_dmabuf_binding *binding) { diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 7dc65774cde5..8bfc2d43efd4 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -79,6 +79,34 @@ static inline u64 *page_pool_ethtool_stats_get(u64 *data, void *stats) } #endif

+/* page_pool_iov support */ + +static inline struct dmabuf_genpool_chunk_owner * +page_pool_iov_owner(const struct page_pool_iov *ppiov) +{ + return ppiov->owner; +} + +static inline unsigned int page_pool_iov_idx(const struct page_pool_iov *ppiov) +{ + return ppiov - page_pool_iov_owner(ppiov)->ppiovs; +} + +static inline dma_addr_t +page_pool_iov_dma_addr(const struct page_pool_iov *ppiov) +{ + struct dmabuf_genpool_chunk_owner *owner = page_pool_iov_owner(ppiov); + + return owner->base_dma_addr + + ((dma_addr_t)page_pool_iov_idx(ppiov) << PAGE_SHIFT); +} + +static inline struct netdev_dmabuf_binding * +page_pool_iov_binding(const struct page_pool_iov *ppiov) +{ + return page_pool_iov_owner(ppiov)->binding; +} + /** * page_pool_dev_alloc_pages() - allocate a page. * @pool: pool from which to allocate diff --git a/net/core/dev.c b/net/core/dev.c index b8c8be5a912e..30667e4c3b95 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -155,8 +155,8 @@ #include <net/netdev_rx_queue.h> #include <linux/genalloc.h> #include <linux/dma-buf.h> -#include <net/page_pool/types.h> #include <net/devmem.h> +#include <net/page_pool/helpers.h>

#include "dev.h" #include "net-sysfs.h" @@ -2120,6 +2120,41 @@ static int netdev_restart_rx_queue(struct net_device *dev, int rxq_idx) return err; }

+struct page_pool_iov *netdev_alloc_dmabuf(struct netdev_dmabuf_binding *binding) +{ + struct dmabuf_genpool_chunk_owner *owner; + struct page_pool_iov *ppiov; + unsigned long dma_addr; + ssize_t offset; + ssize_t index; + + dma_addr = gen_pool_alloc_owner(binding->chunk_pool, PAGE_SIZE, + (void **)&owner); + if (!dma_addr) + return NULL; + + offset = dma_addr - owner->base_dma_addr; + index = offset / PAGE_SIZE; + ppiov = &owner->ppiovs[index]; + + netdev_dmabuf_binding_get(binding); + + return ppiov; +} + +void netdev_free_dmabuf(struct page_pool_iov *ppiov) +{ + struct netdev_dmabuf_binding *binding = page_pool_iov_binding(ppiov); + unsigned long dma_addr = page_pool_iov_dma_addr(ppiov); + + refcount_set(&ppiov->refcount, 1); + + if (gen_pool_has_addr(binding->chunk_pool, dma_addr, PAGE_SIZE)) + gen_pool_free(binding->chunk_pool, dma_addr, PAGE_SIZE); + + netdev_dmabuf_binding_put(binding); +} + /* Protected by rtnl_lock() */ static DEFINE_XARRAY_FLAGS(netdev_dmabuf_bindings, XA_FLAGS_ALLOC1);

Make skb_frag_page() fail in the case where the frag is not backed by a page, and fix its relevant callers to handle this case.

Correctly handle skb_frag refcounting in the page_pool_iovs case.

Signed-off-by: Mina Almasry almasrymina@google.com

---

Changes in v1: - Fix illegal_highdma() (Yunsheng). - Rework napi_pp_put_page() slightly to reduce code churn (Willem).

--- include/linux/skbuff.h | 42 +++++++++++++++++++++++++++++++++++------- net/core/dev.c | 3 ++- net/core/gro.c | 2 +- net/core/skbuff.c | 3 +++ net/ipv4/tcp.c | 3 +++ 5 files changed, 44 insertions(+), 9 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b370eb8d70f7..851f448d2181 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -37,6 +37,8 @@ #endif #include <net/net_debug.h> #include <net/dropreason-core.h> +#include <net/page_pool/types.h> +#include <net/page_pool/helpers.h>

/** * DOC: skb checksums @@ -3414,15 +3416,38 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto, fragto->bv_offset = fragfrom->bv_offset; }

+/* Returns true if the skb_frag contains a page_pool_iov. */ +static inline bool skb_frag_is_page_pool_iov(const skb_frag_t *frag) +{ + return page_is_page_pool_iov(frag->bv_page); +} + /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * - * Returns the &struct page associated with @frag. + * Returns the &struct page associated with @frag. Returns NULL if this frag + * has no associated page. */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { - return frag->bv_page; + if (!page_is_page_pool_iov(frag->bv_page)) + return frag->bv_page; + + return NULL; +} + +/** + * skb_frag_page_pool_iov - retrieve the page_pool_iov referred to by fragment + * @frag: the fragment + * + * Returns the &struct page_pool_iov associated with @frag. Returns NULL if this + * frag has no associated page_pool_iov. + */ +static inline struct page_pool_iov * +skb_frag_page_pool_iov(const skb_frag_t *frag) +{ + return page_to_page_pool_iov(frag->bv_page); }

/** @@ -3433,7 +3458,7 @@ static inline struct page *skb_frag_page(const skb_frag_t *frag) */ static inline void __skb_frag_ref(skb_frag_t *frag) { - get_page(skb_frag_page(frag)); + page_pool_page_get_many(frag->bv_page, 1); }

/** @@ -3453,13 +3478,13 @@ bool napi_pp_put_page(struct page *page, bool napi_safe); static inline void napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) { - struct page *page = skb_frag_page(frag); - #ifdef CONFIG_PAGE_POOL - if (recycle && napi_pp_put_page(page, napi_safe)) + if (recycle && napi_pp_put_page(frag->bv_page, napi_safe)) return; + page_pool_page_put_many(frag->bv_page, 1); +#else + put_page(skb_frag_page(frag)); #endif - put_page(page); }

/** @@ -3499,6 +3524,9 @@ static inline void skb_frag_unref(struct sk_buff *skb, int f) */ static inline void *skb_frag_address(const skb_frag_t *frag) { + if (!skb_frag_page(frag)) + return NULL; + return page_address(skb_frag_page(frag)) + skb_frag_off(frag); }

diff --git a/net/core/dev.c b/net/core/dev.c index 30667e4c3b95..1ae9257df441 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3709,8 +3709,9 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) if (!(dev->features & NETIF_F_HIGHDMA)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct page *page = skb_frag_page(frag);

- if (PageHighMem(skb_frag_page(frag))) + if (page && PageHighMem(page)) return 1; } } diff --git a/net/core/gro.c b/net/core/gro.c index 0759277dc14e..42d7f6755f32 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -376,7 +376,7 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) NAPI_GRO_CB(skb)->frag0 = NULL; NAPI_GRO_CB(skb)->frag0_len = 0;

- if (!skb_headlen(skb) && pinfo->nr_frags && + if (!skb_headlen(skb) && pinfo->nr_frags && skb_frag_page(frag0) && !PageHighMem(skb_frag_page(frag0)) && (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 07f802f1adf1..2ce64f57a0f6 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2999,6 +2999,9 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];

+ if (WARN_ON_ONCE(!skb_frag_page(f))) + return false; + if (__splice_segment(skb_frag_page(f), skb_frag_off(f), skb_frag_size(f), offset, len, spd, false, sk, pipe)) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 70a1bafbefba..e22681c4bfac 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2157,6 +2157,9 @@ static int tcp_zerocopy_receive(struct sock *sk, break; } page = skb_frag_page(frags); + if (WARN_ON_ONCE(!page)) + break; + prefetchw(page); pages[pages_to_map++] = page; length += PAGE_SIZE;

In tcp_recvmsg_locked(), detect if the skb being received by the user is a devmem skb. In this case - if the user provided the MSG_SOCK_DEVMEM flag - pass it to tcp_recvmsg_devmem() for custom handling.

tcp_recvmsg_devmem() copies any data in the skb header to the linear buffer, and returns a cmsg to the user indicating the number of bytes returned in the linear buffer.

tcp_recvmsg_devmem() then loops over the unaccessible devmem skb frags, and returns to the user a cmsg_devmem indicating the location of the data in the dmabuf device memory. cmsg_devmem contains this information:

1. the offset into the dmabuf where the payload starts. 'frag_offset'. 2. the size of the frag. 'frag_size'. 3. an opaque token 'frag_token' to return to the kernel when the buffer is to be released.

The pages awaiting freeing are stored in the newly added sk->sk_user_pages, and each page passed to userspace is get_page()'d. This reference is dropped once the userspace indicates that it is done reading this page. All pages are released when the socket is destroyed.

Signed-off-by: Willem de Bruijn willemb@google.com Signed-off-by: Kaiyuan Zhang kaiyuanz@google.com Signed-off-by: Mina Almasry almasrymina@google.com

---

Changes in v1: - Added dmabuf_id to dmabuf_cmsg (David/Stan). - Devmem -> dmabuf (David). - Change tcp_recvmsg_dmabuf() check to skb->dmabuf (Paolo). - Use __skb_frag_ref() & napi_pp_put_page() for refcounting (Yunsheng).

RFC v3: - Fixed issue with put_cmsg() failing silently.

--- include/linux/socket.h | 1 + include/net/page_pool/helpers.h | 9 ++ include/net/sock.h | 2 + include/uapi/asm-generic/socket.h | 5 + include/uapi/linux/uio.h | 10 ++ net/ipv4/tcp.c | 190 +++++++++++++++++++++++++++++- net/ipv4/tcp_ipv4.c | 8 ++ 7 files changed, 220 insertions(+), 5 deletions(-)

diff --git a/include/linux/socket.h b/include/linux/socket.h index cfcb7e2c3813..fe2b9e2081bb 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -326,6 +326,7 @@ struct ucred { * plain text and require encryption */

+#define MSG_SOCK_DEVMEM 0x2000000 /* Receive devmem skbs as cmsg */ #define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 2d4e0a2c5620..e7e2e89d3663 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -108,6 +108,15 @@ page_pool_iov_dma_addr(const struct page_pool_iov *ppiov) ((dma_addr_t)page_pool_iov_idx(ppiov) << PAGE_SHIFT); }

+static inline unsigned long +page_pool_iov_virtual_addr(const struct page_pool_iov *ppiov) +{ + struct dmabuf_genpool_chunk_owner *owner = page_pool_iov_owner(ppiov); + + return owner->base_virtual + + ((unsigned long)page_pool_iov_idx(ppiov) << PAGE_SHIFT); +} + static inline struct netdev_dmabuf_binding * page_pool_iov_binding(const struct page_pool_iov *ppiov) { diff --git a/include/net/sock.h b/include/net/sock.h index 1d6931caf0c3..01029c855c1b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -353,6 +353,7 @@ struct sk_filter; * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference * @sk_bind2_node: bind node in the bhash2 table + * @sk_user_pages: xarray of pages the user is holding a reference on. */ struct sock { /* @@ -545,6 +546,7 @@ struct sock { struct rcu_head sk_rcu; netns_tracker ns_tracker; struct hlist_node sk_bind2_node; + struct xarray sk_user_pages; };

enum sk_pacing { diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 8ce8a39a1e5f..25a2f5255f52 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -135,6 +135,11 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77

+#define SO_DEVMEM_LINEAR 98 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 99 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__)

#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h index 059b1a9147f4..ad92e37699da 100644 --- a/include/uapi/linux/uio.h +++ b/include/uapi/linux/uio.h @@ -20,6 +20,16 @@ struct iovec __kernel_size_t iov_len; /* Must be size_t (1003.1g) */ };

+struct dmabuf_cmsg { + __u64 frag_offset; /* offset into the dmabuf where the frag starts. + */ + __u32 frag_size; /* size of the frag. */ + __u32 frag_token; /* token representing this frag for + * DEVMEM_DONTNEED. + */ + __u32 dmabuf_id; /* dmabuf id this frag belongs to. */ +}; + /* * UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1) */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5a3135e93d3d..088b2b48bee0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -461,6 +461,7 @@ void tcp_init_sock(struct sock *sk)

set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); + xa_init_flags(&sk->sk_user_pages, XA_FLAGS_ALLOC1); } EXPORT_SYMBOL(tcp_init_sock);

@@ -2303,6 +2304,155 @@ static int tcp_inq_hint(struct sock *sk) return inq; }

+/* On error, returns the -errno. On success, returns number of bytes sent to the + * user. May not consume all of @remaining_len. + */ +static int tcp_recvmsg_dmabuf(const struct sock *sk, const struct sk_buff *skb, + unsigned int offset, struct msghdr *msg, + int remaining_len) +{ + struct dmabuf_cmsg dmabuf_cmsg = { 0 }; + unsigned int start; + int i, copy, n; + int sent = 0; + int err = 0; + + do { + start = skb_headlen(skb); + + if (!skb->dmabuf) { + err = -ENODEV; + goto out; + } + + /* Copy header. */ + copy = start - offset; + if (copy > 0) { + copy = min(copy, remaining_len); + + n = copy_to_iter(skb->data + offset, copy, + &msg->msg_iter); + if (n != copy) { + err = -EFAULT; + goto out; + } + + offset += copy; + remaining_len -= copy; + + /* First a dmabuf_cmsg for # bytes copied to user + * buffer. + */ + memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); + dmabuf_cmsg.frag_size = copy; + err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, + sizeof(dmabuf_cmsg), &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + if (!err) + err = -ETOOSMALL; + goto out; + } + + sent += copy; + + if (remaining_len == 0) + goto out; + } + + /* after that, send information of dmabuf pages through a + * sequence of cmsg + */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct page_pool_iov *ppiov; + u64 frag_offset; + u32 user_token; + int end; + + /* skb->dmabuf should indicate that ALL the frags in + * this skb are dmabuf page_pool_iovs. We're checking + * for that flag above, but also check individual frags + * here. If the tcp stack is not setting skb->dmabuf + * correctly, we still don't want to crash here when + * accessing pgmap or priv below. + */ + if (!skb_frag_page_pool_iov(frag)) { + net_err_ratelimited("Found non-dmabuf skb with page_pool_iov"); + err = -ENODEV; + goto out; + } + + ppiov = skb_frag_page_pool_iov(frag); + end = start + skb_frag_size(frag); + copy = end - offset; + + if (copy > 0) { + copy = min(copy, remaining_len); + + frag_offset = page_pool_iov_virtual_addr(ppiov) + + skb_frag_off(frag) + offset - + start; + dmabuf_cmsg.frag_offset = frag_offset; + dmabuf_cmsg.frag_size = copy; + err = xa_alloc((struct xarray *)&sk->sk_user_pages, + &user_token, frag->bv_page, + xa_limit_31b, GFP_KERNEL); + if (err) + goto out; + + dmabuf_cmsg.frag_token = user_token; + dmabuf_cmsg.dmabuf_id = page_pool_iov_binding_id(ppiov); + + offset += copy; + remaining_len -= copy; + + err = put_cmsg(msg, SOL_SOCKET, + SO_DEVMEM_DMABUF, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + xa_erase((struct xarray *)&sk->sk_user_pages, + user_token); + if (!err) + err = -ETOOSMALL; + goto out; + } + + __skb_frag_ref(frag); + + sent += copy; + + if (remaining_len == 0) + goto out; + } + start = end; + } + + if (!remaining_len) + goto out; + + /* if remaining_len is not satisfied yet, we need to go to the + * next frag in the frag_list to satisfy remaining_len. + */ + skb = skb_shinfo(skb)->frag_list ?: skb->next; + + offset = offset - start; + } while (skb); + + if (remaining_len) { + err = -EFAULT; + goto out; + } + +out: + if (!sent) + sent = err; + + return sent; +} + /* * This routine copies from a sock struct into the user buffer. * @@ -2316,6 +2466,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int *cmsg_flags) { struct tcp_sock *tp = tcp_sk(sk); + int last_copied_dmabuf = -1; /* uninitialized */ int copied = 0; u32 peek_seq; u32 *seq; @@ -2493,15 +2644,44 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, }

if (!(flags & MSG_TRUNC)) { - err = skb_copy_datagram_msg(skb, offset, msg, used); - if (err) { - /* Exception. Bailout! */ - if (!copied) - copied = -EFAULT; + if (last_copied_dmabuf != -1 && + last_copied_dmabuf != skb->dmabuf) break; + + if (!skb->dmabuf) { + err = skb_copy_datagram_msg(skb, offset, msg, + used); + if (err) { + /* Exception. Bailout! */ + if (!copied) + copied = -EFAULT; + break; + } + } else { + if (!(flags & MSG_SOCK_DEVMEM)) { + /* skb->dmabuf skbs can only be received + * with the MSG_SOCK_DEVMEM flag. + */ + if (!copied) + copied = -EFAULT; + + break; + } + + err = tcp_recvmsg_dmabuf(sk, skb, offset, msg, + used); + if (err <= 0) { + if (!copied) + copied = -EFAULT; + + break; + } + used = err; } }

+ last_copied_dmabuf = skb->dmabuf; + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 86cc6d36f818..986398cc2f65 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2501,6 +2501,14 @@ static void tcp_md5sig_info_free_rcu(struct rcu_head *head) void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + struct page *page; + unsigned long index; + + xa_for_each(&sk->sk_user_pages, index, page) + if (WARN_ON_ONCE(!napi_pp_put_page(page, false))) + page_pool_page_put_many(page, 1); + + xa_destroy(&sk->sk_user_pages);

trace_tcp_destroy_sock(sk);

Add an interface for the user to notify the kernel that it is done reading the devmem dmabuf frags returned as cmsg. The kernel will drop the reference on the frags to make them available for re-use.

Signed-off-by: Willem de Bruijn willemb@google.com Signed-off-by: Kaiyuan Zhang kaiyuanz@google.com Signed-off-by: Mina Almasry almasrymina@google.com

---

Changes in v1: - devmemtoken -> dmabuf_token (David). - Use napi_pp_put_page() for refcounting (Yunsheng).

--- include/uapi/asm-generic/socket.h | 1 + include/uapi/linux/uio.h | 4 ++++ net/core/sock.c | 38 +++++++++++++++++++++++++++++++ 3 files changed, 43 insertions(+)

diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 25a2f5255f52..1acb77780f10 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -135,6 +135,7 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77

+#define SO_DEVMEM_DONTNEED 97 #define SO_DEVMEM_LINEAR 98 #define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR #define SO_DEVMEM_DMABUF 99 diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h index ad92e37699da..65f33178a601 100644 --- a/include/uapi/linux/uio.h +++ b/include/uapi/linux/uio.h @@ -30,6 +30,10 @@ struct dmabuf_cmsg { __u32 dmabuf_id; /* dmabuf id this frag belongs to. */ };

+struct dmabuf_token { + __u32 token_start; + __u32 token_count; +}; /* * UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1) */ diff --git a/net/core/sock.c b/net/core/sock.c index fef349dd72fa..521bdc4ff260 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1051,6 +1051,41 @@ static int sock_reserve_memory(struct sock *sk, int bytes) return 0; }

+static noinline_for_stack int +sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen) +{ + struct dmabuf_token tokens[128]; + unsigned int num_tokens, i, j; + int ret; + + if (sk->sk_type != SOCK_STREAM || sk->sk_protocol != IPPROTO_TCP) + return -EBADF; + + if (optlen % sizeof(struct dmabuf_token) || optlen > sizeof(tokens)) + return -EINVAL; + + num_tokens = optlen / sizeof(struct dmabuf_token); + if (copy_from_sockptr(tokens, optval, optlen)) + return -EFAULT; + + ret = 0; + for (i = 0; i < num_tokens; i++) { + for (j = 0; j < tokens[i].token_count; j++) { + struct page *page = xa_erase(&sk->sk_user_pages, + tokens[i].token_start + j); + + if (page) { + if (WARN_ON_ONCE(!napi_pp_put_page(page, + false))) + page_pool_page_put_many(page, 1); + ret++; + } + } + } + + return ret; +} + void sockopt_lock_sock(struct sock *sk) { /* When current->bpf_ctx is set, the setsockopt is called from @@ -1538,6 +1573,9 @@ int sk_setsockopt(struct sock *sk, int level, int optname, break; }

+ case SO_DEVMEM_DONTNEED: + ret = sock_devmem_dontneed(sk, optval, optlen); + break; default: ret = -ENOPROTOOPT; break;

Signed-off-by: Mina Almasry almasrymina@google.com --- Documentation/networking/devmem.rst | 270 ++++++++++++++++++++++++++++ 1 file changed, 270 insertions(+) create mode 100644 Documentation/networking/devmem.rst

diff --git a/Documentation/networking/devmem.rst b/Documentation/networking/devmem.rst new file mode 100644 index 000000000000..ed0d9c88b708 --- /dev/null +++ b/Documentation/networking/devmem.rst @@ -0,0 +1,270 @@ + +================= +Device Memory TCP +================= + + +Intro +===== + +Device memory TCP (devmem TCP) enables receiving data directly into device +memory (dmabuf). The feature is currently implemented for TCP sockets. + + +Opportunity +----------- + +A large amount of data transfers have device memory as the source and/or +destination. Accelerators drastically increased the volume of such transfers. +Some examples include: + +- Distributed training, where ML accelerators, such as GPUs on different hosts, + exchange data among them. + +- Distributed raw block storage applications transfer large amounts of data with + remote SSDs, much of this data does not require host processing. + +Today, the majority of the Device-to-Device data transfers the network are +implemented as the following low level operations: Device-to-Host copy, +Host-to-Host network transfer, and Host-to-Device copy. + +The implementation is suboptimal, especially for bulk data transfers, and can +put significant strains on system resources such as host memory bandwidth and +PCIe bandwidth. + +Devmem TCP optimizes this use case by implementing socket APIs that enable +the user to receive incoming network packets directly into device memory. + +Packet payloads go directly from the NIC to device memory. + +Packet headers go to host memory and are processed by the TCP/IP stack +normally. The NIC must support header split to achieve this. + +Advantages: + +- Alleviate host memory bandwidth pressure, compared to existing + network-transfer + device-copy semantics. + +- Alleviate PCIe bandwidth pressure, by limiting data transfer to the lowest + level of the PCIe tree, compared to traditional path which sends data through + the root complex. + + +More Info +--------- + + slides, video + https://netdevconf.org/0x17/sessions/talk/device-memory-tcp.html + + patchset + [RFC PATCH v3 00/12] Device Memory TCP + https://lore.kernel.org/lkml/20231106024413.2801438-1-almasrymina@google.com... + + +Interface +========= + +Example +------- + +tools/testing/selftests/net/ncdevmem.c:do_server shows an example of setting up +the RX path of this API. + +NIC Setup +--------- + +Header split, flow steering, & RSS are required features for devmem TCP. + +Header split is used to split incoming packets into a header buffer in host +memory, and a payload buffer in device memory. + +Flow steering & RSS are used to ensure that only flows targeting devmem land on +RX queue bound to devmem. + +Enable header split & flow steering: + +:: + + # enable header split (assuming priv-flag) + ethtool --set-priv-flags eth1 enable-header-split on + + # enable flow steering + ethtool -K eth1 ntuple on + +Configure RSS to steer all traffic away from the target RX queue (queue 15 in +this example): + +:: + + ethtool --set-rxfh-indir eth1 equal 15 + + +The user must bind a dmabuf to any number of RX queues on a given NIC using +netlink API: + +:: + + /* Bind dmabuf to NIC RX queue 15 */ + struct netdev_queue *queues; + queues = malloc(sizeof(*queues) * 1); + + queues[0]._present.type = 1; + queues[0]._present.idx = 1; + queues[0].type = NETDEV_RX_QUEUE_TYPE_RX; + queues[0].idx = 15; + + *ys = ynl_sock_create(&ynl_netdev_family, &yerr); + + req = netdev_bind_rx_req_alloc(); + netdev_bind_rx_req_set_ifindex(req, 1 /* ifindex */); + netdev_bind_rx_req_set_dmabuf_fd(req, dmabuf_fd); + __netdev_bind_rx_req_set_queues(req, queues, n_queue_index); + + rsp = netdev_bind_rx(*ys, req); + + dmabuf_id = rsp->dmabuf_id; + + +The netlink API returns a dmabuf_id: a unique ID that refers to this dmabuf +that has been bound. + +Socket Setup +------------ + +The socket must be flow steering to the dmabuf bound RX queue: + +:: + + ethtool -N eth1 flow-type tcp4 ... queue 15, + + +Receiving data +-------------- + +The user application must signal to the kernel that it is capable of receiving +devmem data by passing the MSG_SOCK_DEVMEM flag to recvmsg: + +:: + + ret = recvmsg(fd, &msg, MSG_SOCK_DEVMEM); + +Applications that do not specify the MSG_SOCK_DEVMEM flag will receive an EFAULT +on devmem data. + +Devmem data is received directly into the dmabuf bound to the NIC in 'NIC +Setup', and the kernel signals such to the user via the SCM_DEVMEM_* cmsgs: + +:: + + for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) { + if (cm->cmsg_level != SOL_SOCKET || + (cm->cmsg_type != SCM_DEVMEM_DMABUF && + cm->cmsg_type != SCM_DEVMEM_LINEAR)) + continue; + + dmabuf_cmsg = (struct dmabuf_cmsg *)CMSG_DATA(cm); + + if (cm->cmsg_type == SCM_DEVMEM_DMABUF) { + /* Frag landed in dmabuf. + * + * dmabuf_cmsg->dmabuf_id is the dmabuf the + * frag landed on. + * + * dmabuf_cmsg->frag_offset is the offset into + * the dmabuf where the frag starts. + * + * dmabuf_cmsg->frag_size is the size of the + * frag. + * + * dmabuf_cmsg->frag_token is a token used to + * refer to this frag for later freeing. + */ + + struct dmabuf_token token; + token.token_start = dmabuf_cmsg->frag_token; + token.token_count = 1; + continue; + } + + if (cm->cmsg_type == SCM_DEVMEM_LINEAR) + /* Frag landed in linear buffer. + * + * dmabuf_cmsg->frag_size is the size of the + * frag. + */ + continue; + + } + +Applications may receive 2 cmsgs: + +- SCM_DEVMEM_DMABUF: this indicates the fragment landed in the dmabuf indicated + by dmabuf_id. + +- SCM_DEVMEM_LINEAR: this indicates the fragment landed in the linear buffer. + This typically happens when the NIC is unable to split the packet at the + header boundary, such that part (or all) of the payload landed in host + memory. + +Applications may receive no SO_DEVMEM_* cmsgs. That indicates non-devmem, +regular TCP data that landed on an RX queue not bound to a dmabuf. + + +Freeing frags +------------- + +Frags received via SCM_DEVMEM_DMABUF are pinned by the kernel while the user +processes the frag. The user must return the frag to the kernel via +SO_DEVMEM_DONTNEED: + +:: + + ret = setsockopt(client_fd, SOL_SOCKET, SO_DEVMEM_DONTNEED, &token, + sizeof(token)); + +The user must ensure the tokens are returned to the kernel in a timely manner. +Failure to do so will exhaust the limited dmabuf that is bound to the RX queue +and will lead to packet drops. + + +Implementation & Caveats +======================== + +Unreadable skbs +--------------- + +Devmem payloads are inaccessible to the kernel processing the packets. This +results in a few quirks for payloads of devmem skbs: + +- Loopback is not functional. Loopback relies on copying the payload, which is + not possible with devmem skbs. + +- Software checksum calculation fails. + +- TCP Dump and bpf can't access devmem packet payloads. + + +Testing +======= + +More realistic example code can be found in the kernel source under +tools/testing/selftests/net/ncdevmem.c + +ncdevmem is a devmem TCP netcat. It works very similarly to netcat, but +receives data directly into a udmabuf. + +To run ncdevmem, you need to run it a server on the machine under test, and you +need to run netcat on a peer to provide the TX data. + +ncdevmem has a validation mode as well that expects a repeating pattern of +incoming data and validates it as such: + +:: + + # On server: + ncdevmem -s <server IP> -c <client IP> -f eth1 -d 3 -n 0000:06:00.0 -l \ + -p 5201 -v 7 + + # On client: + yes $(echo -e \x01\x02\x03\x04\x05\x06) | \ + tr \n \0 | head -c 5G | nc <server IP> 5201 -p 5201

ncdevmem is a devmem TCP netcat. It works similarly to netcat, but it sends and receives data using the devmem TCP APIs. It uses udmabuf as the dmabuf provider. It is compatible with a regular netcat running on a peer, or a ncdevmem running on a peer.

In addition to normal netcat support, ncdevmem has a validation mode, where it sends a specific pattern and validates this pattern on the receiver side to ensure data integrity.

Suggested-by: Stanislav Fomichev sdf@google.com Signed-off-by: Mina Almasry almasrymina@google.com

---

Changes in v1: - Many more general cleanups (Willem). - Removed driver reset (Jakub). - Removed hardcoded if index (Paolo).

RFC v2: - General cleanups (Willem).

--- tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 5 + tools/testing/selftests/net/ncdevmem.c | 489 +++++++++++++++++++++++++ 3 files changed, 495 insertions(+) create mode 100644 tools/testing/selftests/net/ncdevmem.c

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 2f9d378edec3..b644dbae58b7 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -17,6 +17,7 @@ ipv6_flowlabel ipv6_flowlabel_mgr log.txt msg_zerocopy +ncdevmem nettest psock_fanout psock_snd diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 14bd68da7466..d7a66563ffe7 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,6 +5,10 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ $(KHDR_INCLUDES) # Additional include paths needed by kselftest.h CFLAGS += -I../ +CFLAGS += -I../../../net/ynl/generated/ +CFLAGS += -I../../../net/ynl/lib/ + +LDLIBS += ../../../net/ynl/lib/ynl.a ../../../net/ynl/generated/protos.a

TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \ rtnetlink.sh xfrm_policy.sh test_blackhole_dev.sh @@ -92,6 +96,7 @@ TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh TEST_PROGS += fdb_flush.sh TEST_PROGS += fq_band_pktlimit.sh +TEST_GEN_FILES += ncdevmem

TEST_FILES := settings

diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c new file mode 100644 index 000000000000..7fbeee02b9a2 --- /dev/null +++ b/tools/testing/selftests/net/ncdevmem.c @@ -0,0 +1,489 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#define __EXPORTED_HEADERS__ + +#include <linux/uio.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <stdbool.h> +#include <string.h> +#include <errno.h> +#define __iovec_defined +#include <fcntl.h> +#include <malloc.h> +#include <error.h> + +#include <arpa/inet.h> +#include <sys/socket.h> +#include <sys/mman.h> +#include <sys/ioctl.h> +#include <sys/syscall.h> + +#include <linux/memfd.h> +#include <linux/if.h> +#include <linux/dma-buf.h> +#include <linux/udmabuf.h> +#include <libmnl/libmnl.h> +#include <linux/types.h> +#include <linux/netlink.h> +#include <linux/genetlink.h> +#include <linux/netdev.h> +#include <time.h> + +#include "netdev-user.h" +#include <ynl.h> + +#define PAGE_SHIFT 12 +#define TEST_PREFIX "ncdevmem" +#define NUM_PAGES 16000 + +#ifndef MSG_SOCK_DEVMEM +#define MSG_SOCK_DEVMEM 0x2000000 +#endif + +/* + * tcpdevmem netcat. Works similarly to netcat but does device memory TCP + * instead of regular TCP. Uses udmabuf to mock a dmabuf provider. + * + * Usage: + * + * On server: + * ncdevmem -s <server IP> -c <client IP> -f eth1 -d 3 -n 0000:06:00.0 -l \ + * -p 5201 -v 7 + * + * On client: + * yes $(echo -e \x01\x02\x03\x04\x05\x06) | \ + * tr \n \0 | \ + * head -c 5G | \ + * nc <server IP> 5201 -p 5201 + * + * Note this is compatible with regular netcat. i.e. the sender or receiver can + * be replaced with regular netcat to test the RX or TX path in isolation. + */ + +static char *server_ip = "192.168.1.4"; +static char *client_ip = "192.168.1.2"; +static char *port = "5201"; +static size_t do_validation; +static int queue_num = 15; +static char *ifname = "eth1"; +static unsigned int ifindex = 3; +static char *nic_pci_addr = "0000:06:00.0"; +static unsigned int iterations; +static unsigned int dmabuf_id; + +void print_bytes(void *ptr, size_t size) +{ + unsigned char *p = ptr; + int i; + + for (i = 0; i < size; i++) + printf("%02hhX ", p[i]); + printf("\n"); +} + +void print_nonzero_bytes(void *ptr, size_t size) +{ + unsigned char *p = ptr; + unsigned int i; + + for (i = 0; i < size; i++) + putchar(p[i]); + printf("\n"); +} + +void validate_buffer(void *line, size_t size) +{ + static unsigned char seed = 1; + unsigned char *ptr = line; + int errors = 0; + size_t i; + + for (i = 0; i < size; i++) { + if (ptr[i] != seed) { + fprintf(stderr, + "Failed validation: expected=%u, actual=%u, index=%lu\n", + seed, ptr[i], i); + errors++; + if (errors > 20) + error(1, 0, "validation failed."); + } + seed++; + if (seed == do_validation) + seed = 0; + } + + fprintf(stdout, "Validated buffer\n"); +} + +static void reset_flow_steering(void) +{ + char command[256]; + + memset(command, 0, sizeof(command)); + snprintf(command, sizeof(command), "sudo ethtool -K %s ntuple off", + "eth1"); + system(command); + + memset(command, 0, sizeof(command)); + snprintf(command, sizeof(command), "sudo ethtool -K %s ntuple on", + "eth1"); + system(command); +} + +static void configure_flow_steering(void) +{ + char command[256]; + + memset(command, 0, sizeof(command)); + snprintf(command, sizeof(command), + "sudo ethtool -N %s flow-type tcp4 src-ip %s dst-ip %s src-port %s dst-port %s queue %d", + ifname, client_ip, server_ip, port, port, queue_num); + system(command); +} + +static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd, + struct netdev_queue_dmabuf *queues, + unsigned int n_queue_index, struct ynl_sock **ys) +{ + struct netdev_bind_rx_req *req = NULL; + struct netdev_bind_rx_rsp *rsp = NULL; + struct ynl_error yerr; + + *ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!*ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return -1; + } + + req = netdev_bind_rx_req_alloc(); + netdev_bind_rx_req_set_ifindex(req, ifindex); + netdev_bind_rx_req_set_dmabuf_fd(req, dmabuf_fd); + __netdev_bind_rx_req_set_queues(req, queues, n_queue_index); + + rsp = netdev_bind_rx(*ys, req); + if (!rsp) { + perror("netdev_bind_rx"); + goto err_close; + } + + if (!rsp->_present.dmabuf_id) { + perror("dmabuf_id not present"); + goto err_close; + } + + printf("got dmabuf id=%d\n", rsp->dmabuf_id); + dmabuf_id = rsp->dmabuf_id; + + netdev_bind_rx_req_free(req); + netdev_bind_rx_rsp_free(rsp); + + return 0; + +err_close: + fprintf(stderr, "YNL failed: %s\n", (*ys)->err.msg); + netdev_bind_rx_req_free(req); + ynl_sock_destroy(*ys); + return -1; +} + +static void create_udmabuf(int *devfd, int *memfd, int *buf, size_t dmabuf_size) +{ + struct udmabuf_create create; + int ret; + + *devfd = open("/dev/udmabuf", O_RDWR); + if (*devfd < 0) { + error(70, 0, + "%s: [skip,no-udmabuf: Unable to access DMA buffer device file]\n", + TEST_PREFIX); + } + + *memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING); + if (*memfd < 0) + error(70, 0, "%s: [skip,no-memfd]\n", TEST_PREFIX); + + /* Required for udmabuf */ + ret = fcntl(*memfd, F_ADD_SEALS, F_SEAL_SHRINK); + if (ret < 0) + error(73, 0, "%s: [skip,fcntl-add-seals]\n", TEST_PREFIX); + + ret = ftruncate(*memfd, dmabuf_size); + if (ret == -1) + error(74, 0, "%s: [FAIL,memfd-truncate]\n", TEST_PREFIX); + + memset(&create, 0, sizeof(create)); + + create.memfd = *memfd; + create.offset = 0; + create.size = dmabuf_size; + *buf = ioctl(*devfd, UDMABUF_CREATE, &create); + if (*buf < 0) + error(75, 0, "%s: [FAIL, create udmabuf]\n", TEST_PREFIX); +} + +int do_server(void) +{ + char ctrl_data[sizeof(int) * 20000]; + struct netdev_queue_dmabuf *queues; + size_t non_page_aligned_frags = 0; + struct sockaddr_in client_addr; + struct sockaddr_in server_sin; + size_t page_aligned_frags = 0; + int devfd, memfd, buf, ret; + size_t total_received = 0; + socklen_t client_addr_len; + bool is_devmem = false; + char *buf_mem = NULL; + struct ynl_sock *ys; + size_t dmabuf_size; + char iobuf[819200]; + char buffer[256]; + int socket_fd; + int client_fd; + size_t i = 0; + int opt = 1; + + dmabuf_size = getpagesize() * NUM_PAGES; + + create_udmabuf(&devfd, &memfd, &buf, dmabuf_size); + + reset_flow_steering(); + configure_flow_steering(); + + sleep(1); + + queues = malloc(sizeof(*queues) * 1); + + queues[0]._present.type = 1; + queues[0]._present.idx = 1; + queues[0].type = NETDEV_QUEUE_TYPE_RX; + queues[0].idx = queue_num; + if (bind_rx_queue(ifindex, buf, queues, 1, &ys)) + error(1, 0, "Failed to bind\n"); + + buf_mem = mmap(NULL, dmabuf_size, PROT_READ | PROT_WRITE, MAP_SHARED, + buf, 0); + if (buf_mem == MAP_FAILED) + error(1, 0, "mmap()"); + + server_sin.sin_family = AF_INET; + server_sin.sin_port = htons(atoi(port)); + + ret = inet_pton(server_sin.sin_family, server_ip, &server_sin.sin_addr); + if (socket < 0) + error(79, 0, "%s: [FAIL, create socket]\n", TEST_PREFIX); + + socket_fd = socket(server_sin.sin_family, SOCK_STREAM, 0); + if (socket < 0) + error(errno, errno, "%s: [FAIL, create socket]\n", TEST_PREFIX); + + ret = setsockopt(socket_fd, SOL_SOCKET, SO_REUSEPORT, &opt, + sizeof(opt)); + if (ret) + error(errno, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX); + + ret = setsockopt(socket_fd, SOL_SOCKET, SO_REUSEADDR, &opt, + sizeof(opt)); + if (ret) + error(errno, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX); + + printf("binding to address %s:%d\n", server_ip, + ntohs(server_sin.sin_port)); + + ret = bind(socket_fd, &server_sin, sizeof(server_sin)); + if (ret) + error(errno, errno, "%s: [FAIL, bind]\n", TEST_PREFIX); + + ret = listen(socket_fd, 1); + if (ret) + error(errno, errno, "%s: [FAIL, listen]\n", TEST_PREFIX); + + client_addr_len = sizeof(client_addr); + + inet_ntop(server_sin.sin_family, &server_sin.sin_addr, buffer, + sizeof(buffer)); + printf("Waiting or connection on %s:%d\n", buffer, + ntohs(server_sin.sin_port)); + client_fd = accept(socket_fd, &client_addr, &client_addr_len); + + inet_ntop(client_addr.sin_family, &client_addr.sin_addr, buffer, + sizeof(buffer)); + printf("Got connection from %s:%d\n", buffer, + ntohs(client_addr.sin_port)); + + while (1) { + struct iovec iov = { .iov_base = iobuf, + .iov_len = sizeof(iobuf) }; + struct dmabuf_cmsg *dmabuf_cmsg = NULL; + struct dma_buf_sync sync = { 0 }; + struct cmsghdr *cm = NULL; + struct msghdr msg = { 0 }; + struct dmabuf_token token; + ssize_t ret; + + is_devmem = false; + printf("\n\n"); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = ctrl_data; + msg.msg_controllen = sizeof(ctrl_data); + ret = recvmsg(client_fd, &msg, MSG_SOCK_DEVMEM); + printf("recvmsg ret=%ld\n", ret); + if (ret < 0 && (errno == EAGAIN || errno == EWOULDBLOCK)) + continue; + if (ret < 0) { + perror("recvmsg"); + continue; + } + if (ret == 0) { + printf("client exited\n"); + goto cleanup; + } + + i++; + for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) { + if (cm->cmsg_level != SOL_SOCKET || + (cm->cmsg_type != SCM_DEVMEM_DMABUF && + cm->cmsg_type != SCM_DEVMEM_LINEAR)) { + fprintf(stdout, "skipping non-devmem cmsg\n"); + continue; + } + + dmabuf_cmsg = (struct dmabuf_cmsg *)CMSG_DATA(cm); + is_devmem = true; + + if (cm->cmsg_type == SCM_DEVMEM_LINEAR) { + /* TODO: process data copied from skb's linear + * buffer. + */ + fprintf(stdout, + "SCM_DEVMEM_LINEAR. dmabuf_cmsg->frag_size=%u\n", + dmabuf_cmsg->frag_size); + + continue; + } + + token.token_start = dmabuf_cmsg->frag_token; + token.token_count = 1; + + total_received += dmabuf_cmsg->frag_size; + printf("received frag_page=%llu, in_page_offset=%llu, frag_offset=%llu, frag_size=%u, token=%u, total_received=%lu, dmabuf_id=%u\n", + dmabuf_cmsg->frag_offset >> PAGE_SHIFT, + dmabuf_cmsg->frag_offset % getpagesize(), + dmabuf_cmsg->frag_offset, dmabuf_cmsg->frag_size, + dmabuf_cmsg->frag_token, total_received, + dmabuf_cmsg->dmabuf_id); + + if (dmabuf_cmsg->dmabuf_id != dmabuf_id) + error(1, 0, + "received on wrong dmabuf_id: flow steering error\n"); + + if (dmabuf_cmsg->frag_size % getpagesize()) + non_page_aligned_frags++; + else + page_aligned_frags++; + + sync.flags = DMA_BUF_SYNC_READ | DMA_BUF_SYNC_START; + ioctl(buf, DMA_BUF_IOCTL_SYNC, &sync); + + if (do_validation) + validate_buffer( + ((unsigned char *)buf_mem) + + dmabuf_cmsg->frag_offset, + dmabuf_cmsg->frag_size); + else + print_nonzero_bytes( + ((unsigned char *)buf_mem) + + dmabuf_cmsg->frag_offset, + dmabuf_cmsg->frag_size); + + sync.flags = DMA_BUF_SYNC_READ | DMA_BUF_SYNC_END; + ioctl(buf, DMA_BUF_IOCTL_SYNC, &sync); + + ret = setsockopt(client_fd, SOL_SOCKET, + SO_DEVMEM_DONTNEED, &token, + sizeof(token)); + if (ret != 1) + error(1, 0, + "SO_DEVMEM_DONTNEED not enough tokens"); + } + if (!is_devmem) + error(1, 0, "flow steering error\n"); + + printf("total_received=%lu\n", total_received); + } + + fprintf(stdout, "%s: ok\n", TEST_PREFIX); + + fprintf(stdout, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n", + page_aligned_frags, non_page_aligned_frags); + + fprintf(stdout, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n", + page_aligned_frags, non_page_aligned_frags); + +cleanup: + + munmap(buf_mem, dmabuf_size); + close(client_fd); + close(socket_fd); + close(buf); + close(memfd); + close(devfd); + ynl_sock_destroy(ys); + + return 0; +} + +int main(int argc, char *argv[]) +{ + int is_server = 0, opt; + + while ((opt = getopt(argc, argv, "ls:c:p:v:q:f:n:i:d:")) != -1) { + switch (opt) { + case 'l': + is_server = 1; + break; + case 's': + server_ip = optarg; + break; + case 'c': + client_ip = optarg; + break; + case 'p': + port = optarg; + break; + case 'v': + do_validation = atoll(optarg); + break; + case 'q': + queue_num = atoi(optarg); + break; + case 'f': + ifname = optarg; + break; + case 'd': + ifindex = atoi(optarg); + break; + case 'n': + nic_pci_addr = optarg; + break; + case 'i': + iterations = atoll(optarg); + break; + case '?': + printf("unknown option: %c\n", optopt); + break; + } + } + + for (; optind < argc; optind++) + printf("extra arguments: %s\n", argv[optind]); + + if (is_server) + return do_server(); + + return 0; +}