Add netdev_rx_queue_restart(), which resets an rx queue using the queue API recently merged[1].

The queue API was merged to enable the core net stack to reset individual rx queues to actuate changes in the rx queue's configuration. In later patches in this series, we will use netdev_rx_queue_restart() to reset rx queues after binding or unbinding dmabuf configuration, which will cause reallocation of the page_pool to repopulate its memory using the new configuration.

[1] https://lore.kernel.org/netdev/20240430231420.699177-1-shailend@google.com/T...

Signed-off-by: David Wei dw@davidwei.uk Signed-off-by: Mina Almasry almasrymina@google.com Reviewed-by: Pavel Begunkov asml.silence@gmail.com Reviewed-by: Jakub Kicinski kuba@kernel.org

---

v18: - Add more color to commit message (Xuan Zhuo).

v17: - Use ASSERT_RTNL() (Jakub).

v13: - Add reviewed-by from Pavel (thanks!) - Fixed comment (Pavel)

v11: - Fix not checking dev->queue_mgmt_ops (Pavel). - Fix ndo_queue_mem_free call that passed the wrong pointer (David).

v9: https://lore.kernel.org/all/20240502045410.3524155-4-dw@davidwei.uk/ (submitted by David). - fixed SPDX license identifier (Simon). - Rebased on top of merged queue API definition, and changed implementation to match that. - Replace rtnl_lock() with rtnl_is_locked() to make it useable from my netlink code where rtnl is already locked.

--- include/net/netdev_rx_queue.h | 3 ++ net/core/Makefile | 1 + net/core/netdev_rx_queue.c | 74 +++++++++++++++++++++++++++++++++++ 3 files changed, 78 insertions(+) create mode 100644 net/core/netdev_rx_queue.c

diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index aa1716fb0e53c..e78ca52d67fbf 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -54,4 +54,7 @@ get_netdev_rx_queue_index(struct netdev_rx_queue *queue) return index; } #endif + +int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq); + #endif diff --git a/net/core/Makefile b/net/core/Makefile index 62be9aef25285..f82232b358a2c 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o

obj-y += net-sysfs.o obj-y += hotdata.o +obj-y += netdev_rx_queue.o obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c new file mode 100644 index 0000000000000..da11720a59830 --- /dev/null +++ b/net/core/netdev_rx_queue.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/netdevice.h> +#include <net/netdev_queues.h> +#include <net/netdev_rx_queue.h> + +int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx) +{ + void *new_mem, *old_mem; + int err; + + if (!dev->queue_mgmt_ops || !dev->queue_mgmt_ops->ndo_queue_stop || + !dev->queue_mgmt_ops->ndo_queue_mem_free || + !dev->queue_mgmt_ops->ndo_queue_mem_alloc || + !dev->queue_mgmt_ops->ndo_queue_start) + return -EOPNOTSUPP; + + ASSERT_RTNL(); + + new_mem = kvzalloc(dev->queue_mgmt_ops->ndo_queue_mem_size, GFP_KERNEL); + if (!new_mem) + return -ENOMEM; + + old_mem = kvzalloc(dev->queue_mgmt_ops->ndo_queue_mem_size, GFP_KERNEL); + if (!old_mem) { + err = -ENOMEM; + goto err_free_new_mem; + } + + err = dev->queue_mgmt_ops->ndo_queue_mem_alloc(dev, new_mem, rxq_idx); + if (err) + goto err_free_old_mem; + + err = dev->queue_mgmt_ops->ndo_queue_stop(dev, old_mem, rxq_idx); + if (err) + goto err_free_new_queue_mem; + + err = dev->queue_mgmt_ops->ndo_queue_start(dev, new_mem, rxq_idx); + if (err) + goto err_start_queue; + + dev->queue_mgmt_ops->ndo_queue_mem_free(dev, old_mem); + + kvfree(old_mem); + kvfree(new_mem); + + return 0; + +err_start_queue: + /* Restarting the queue with old_mem should be successful as we haven't + * changed any of the queue configuration, and there is not much we can + * do to recover from a failure here. + * + * WARN if we fail to recover the old rx queue, and at least free + * old_mem so we don't also leak that. + */ + if (dev->queue_mgmt_ops->ndo_queue_start(dev, old_mem, rxq_idx)) { + WARN(1, + "Failed to restart old queue in error path. RX queue %d may be unhealthy.", + rxq_idx); + dev->queue_mgmt_ops->ndo_queue_mem_free(dev, old_mem); + } + +err_free_new_queue_mem: + dev->queue_mgmt_ops->ndo_queue_mem_free(dev, new_mem); + +err_free_old_mem: + kvfree(old_mem); + +err_free_new_mem: + kvfree(new_mem); + + return err; +}

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: net_iov. We setup the net_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, and the binding is actuated by resetting the rx queue using the queue API.

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 Reviewed-by: Pavel Begunkov asml.silence@gmail.com # excluding netlink Acked-by: Daniel Vetter daniel.vetter@ffwll.ch

---

v17: - Add missing kfree(owner) (Jakub) - Fix issue found by Taehee, where may access an rxq that has already been freed if the driver has been unloaded in the meantime (thanks!)

v16: - Fix rtnl_lock() not being acquired on unbind path (Reported by Taehee). - Use unlocked versions of dma_buf_[un]map_attachment (Reported by Taehee). - Use real_num_rx_queues instead of num_rx_queues (Taehee). - bound_rxq_list -> bound_rxqs (Jakub). - Removed READ_ONCE/WRITE_ONCE infavor of rtnl_lock() sync. (Jakub). - Use ERR_CAST instead of out param (Jakub). - Add NULL Check for kzalloc_node() call (Paolo). - Move genl_sk_priv_get, genlmsg_new, genlmsg_input outside of the lock acquisition (Jakub). - Add netif_device_present() check (Jakub). - Use nla_for_each_attr_type(Jakub).

v13: - Fixed a couple of places that still listed DMA_BIDIRECTIONAL (Pavel). - Added reviewed-by from Pavel.

v11: - Fix build error with CONFIG_DMA_SHARED_BUFFER && !CONFIG_GENERIC_ALLOCATOR - Rebased on top of no memory provider ops.

v10: - Moved net_iov_dma_addr() to devmem.h and made it devmem specific helper (David).

v9: https://lore.kernel.org/all/20240403002053.2376017-5-almasrymina@google.com/ - Removed net_devmem_restart_rx_queues and put it in its own patch (David).

v8: - move dmabuf_devmem_ops usage to later patch to avoid patch-by-patch build error.

v7: - Use IS_ERR() instead of IS_ERR_OR_NULL() for the dma_buf_get() return value. - Changes netdev_* naming in devmem.c to net_devmem_* (Yunsheng). - DMA_BIDIRECTIONAL -> DMA_FROM_DEVICE (Yunsheng). - Added a comment around recovering of the old rx queue in net_devmem_restart_rx_queue(), and added freeing of old_mem if the restart of the old queue fails. (Yunsheng). - Use kernel-family sock-priv (Jakub). - Put pp_memory_provider_params in netdev_rx_queue instead of the dma-buf specific binding (Pavel & David). - Move queue management ops to queue_mgmt_ops instead of netdev_ops (Jakub). - Remove excess whitespaces (Jakub). - Use genlmsg_iput (Jakub).

v6: - Validate rx queue index - Refactor new functions into devmem.c (Pavel)

v5: - Renamed page_pool_iov to net_iov, and moved that support to devmem.h or netmem.h.

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

--- Documentation/netlink/specs/netdev.yaml | 4 + include/net/devmem.h | 115 +++++++++++ include/net/netdev_rx_queue.h | 2 + include/net/netmem.h | 10 + include/net/page_pool/types.h | 6 + net/core/Makefile | 2 +- net/core/dev.c | 4 + net/core/devmem.c | 257 ++++++++++++++++++++++++ net/core/netdev-genl-gen.c | 4 + net/core/netdev-genl-gen.h | 4 + net/core/netdev-genl.c | 99 ++++++++- 11 files changed, 504 insertions(+), 3 deletions(-) create mode 100644 include/net/devmem.h create mode 100644 net/core/devmem.c

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 4930e8142aa63..0c747530c275e 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -667,6 +667,10 @@ operations: attributes: - id

+kernel-family: + headers: [ "linux/list.h"] + sock-priv: struct list_head + mcast-groups: list: - diff --git a/include/net/devmem.h b/include/net/devmem.h new file mode 100644 index 0000000000000..c7bd6a0a6b9e9 --- /dev/null +++ b/include/net/devmem.h @@ -0,0 +1,115 @@ +/* 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 net_devmem_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 net_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 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_rxqs; + + /* ID of this binding. Globally unique to all bindings currently + * active. + */ + u32 id; +}; + +/* 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 net_iovs for this chunk. */ + struct net_iov *niovs; + size_t num_niovs; + + struct net_devmem_dmabuf_binding *binding; +}; + +#if defined(CONFIG_DMA_SHARED_BUFFER) && defined(CONFIG_GENERIC_ALLOCATOR) +void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding); +struct net_devmem_dmabuf_binding * +net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd); +void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding); +int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct net_devmem_dmabuf_binding *binding); +void dev_dmabuf_uninstall(struct net_device *dev); +#else +static inline void +__net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) +{ +} + +static inline struct net_devmem_dmabuf_binding * +net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd) +{ + return ERR_PTR(-EOPNOTSUPP); +} +static inline void +net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ +} + +static inline int +net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct net_devmem_dmabuf_binding *binding) +{ + return -EOPNOTSUPP; +} + +static inline void dev_dmabuf_uninstall(struct net_device *dev) +{ +} +#endif + +static inline void +net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding) +{ + refcount_inc(&binding->ref); +} + +static inline void +net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding) +{ + if (!refcount_dec_and_test(&binding->ref)) + return; + + __net_devmem_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 e78ca52d67fbf..ac34f5fb4f71d 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -6,6 +6,7 @@ #include <linux/netdevice.h> #include <linux/sysfs.h> #include <net/xdp.h> +#include <net/page_pool/types.h>

/* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { @@ -25,6 +26,7 @@ struct netdev_rx_queue { * Readers and writers must hold RTNL */ struct napi_struct *napi; + struct pp_memory_provider_params mp_params; } ____cacheline_aligned_in_smp;

/* diff --git a/include/net/netmem.h b/include/net/netmem.h index 46cc9b89ac79f..41e96c2f94b5c 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -8,6 +8,16 @@ #ifndef _NET_NETMEM_H #define _NET_NETMEM_H

+#include <net/devmem.h> + +/* net_iov */ + +struct net_iov { + struct dmabuf_genpool_chunk_owner *owner; +}; + +/* netmem */ + /** * typedef netmem_ref - a nonexistent type marking a reference to generic * network memory. diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 50569fed7868e..4afd6dd56351a 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -139,6 +139,10 @@ struct page_pool_stats { */ #define PAGE_POOL_FRAG_GROUP_ALIGN (4 * sizeof(long))

+struct pp_memory_provider_params { + void *mp_priv; +}; + struct page_pool { struct page_pool_params_fast p;

@@ -197,6 +201,8 @@ struct page_pool { */ struct ptr_ring ring;

+ void *mp_priv; + #ifdef CONFIG_PAGE_POOL_STATS /* recycle stats are per-cpu to avoid locking */ struct page_pool_recycle_stats __percpu *recycle_stats; diff --git a/net/core/Makefile b/net/core/Makefile index f82232b358a2c..6b43611fb4a43 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -13,7 +13,7 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ fib_notifier.o xdp.o flow_offload.o gro.o \ - netdev-genl.o netdev-genl-gen.o gso.o + netdev-genl.o netdev-genl-gen.o gso.o devmem.o

obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o

diff --git a/net/core/dev.c b/net/core/dev.c index 751d9b70e6ad7..b6c21d1a6452b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -158,6 +158,9 @@ #include <net/page_pool/types.h> #include <net/page_pool/helpers.h> #include <net/rps.h> +#include <linux/genalloc.h> +#include <linux/dma-buf.h> +#include <net/devmem.h>

#include "dev.h" #include "net-sysfs.h" @@ -11335,6 +11338,7 @@ void unregister_netdevice_many_notify(struct list_head *head, dev_tcx_uninstall(dev); dev_xdp_uninstall(dev); bpf_dev_bound_netdev_unregister(dev); + dev_dmabuf_uninstall(dev);

netdev_offload_xstats_disable_all(dev);

diff --git a/net/core/devmem.c b/net/core/devmem.c new file mode 100644 index 0000000000000..9a357235bde8f --- /dev/null +++ b/net/core/devmem.c @@ -0,0 +1,257 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Devmem TCP + * + * Authors: Mina Almasry almasrymina@google.com + * Willem de Bruijn willemdebruijn.kernel@gmail.com + * Kaiyuan Zhang <kaiyuanz@google.com + */ + +#include <linux/types.h> +#include <linux/mm.h> +#include <linux/netdevice.h> +#include <trace/events/page_pool.h> +#include <net/netdev_rx_queue.h> +#include <net/page_pool/types.h> +#include <net/page_pool/helpers.h> +#include <linux/genalloc.h> +#include <linux/dma-buf.h> +#include <net/devmem.h> +#include <net/netdev_queues.h> + +/* Device memory support */ + +#if defined(CONFIG_DMA_SHARED_BUFFER) && defined(CONFIG_GENERIC_ALLOCATOR) +static void net_devmem_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->niovs); + kfree(owner); +} + +void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) +{ + size_t size, avail; + + gen_pool_for_each_chunk(binding->chunk_pool, + net_devmem_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=%zu, avail=%zu", + size, avail)) + gen_pool_destroy(binding->chunk_pool); + + dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt, + DMA_FROM_DEVICE); + dma_buf_detach(binding->dmabuf, binding->attachment); + dma_buf_put(binding->dmabuf); + xa_destroy(&binding->bound_rxqs); + kfree(binding); +} + +/* Protected by rtnl_lock() */ +static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1); + +void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ + struct netdev_rx_queue *rxq; + unsigned long xa_idx; + unsigned int rxq_idx; + + if (binding->list.next) + list_del(&binding->list); + + xa_for_each(&binding->bound_rxqs, xa_idx, rxq) { + if (rxq->mp_params.mp_priv == binding) { + rxq->mp_params.mp_priv = NULL; + + rxq_idx = get_netdev_rx_queue_index(rxq); + + netdev_rx_queue_restart(binding->dev, rxq_idx); + } + } + + xa_erase(&net_devmem_dmabuf_bindings, binding->id); + + net_devmem_dmabuf_binding_put(binding); +} + +int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct net_devmem_dmabuf_binding *binding) +{ + struct netdev_rx_queue *rxq; + u32 xa_idx; + int err; + + if (rxq_idx >= dev->real_num_rx_queues) + return -ERANGE; + + rxq = __netif_get_rx_queue(dev, rxq_idx); + if (rxq->mp_params.mp_priv) + return -EEXIST; + + err = xa_alloc(&binding->bound_rxqs, &xa_idx, rxq, xa_limit_32b, + GFP_KERNEL); + if (err) + return err; + + rxq->mp_params.mp_priv = binding; + + err = netdev_rx_queue_restart(dev, rxq_idx); + if (err) + goto err_xa_erase; + + return 0; + +err_xa_erase: + rxq->mp_params.mp_priv = NULL; + xa_erase(&binding->bound_rxqs, xa_idx); + + return err; +} + +struct net_devmem_dmabuf_binding *net_devmem_bind_dmabuf(struct net_device *dev, + unsigned int dmabuf_fd) +{ + struct net_devmem_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; + + dmabuf = dma_buf_get(dmabuf_fd); + if (IS_ERR(dmabuf)) + return ERR_CAST(dmabuf); + + 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(&net_devmem_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_rxqs, 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_unlocked(binding->attachment, + DMA_FROM_DEVICE); + 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 net_iov *niov; + + owner = kzalloc_node(sizeof(*owner), GFP_KERNEL, + dev_to_node(&dev->dev)); + if (!owner) { + err = -ENOMEM; + goto err_free_chunks; + } + + owner->base_virtual = virtual; + owner->base_dma_addr = dma_addr; + owner->num_niovs = 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) { + kfree(owner); + err = -EINVAL; + goto err_free_chunks; + } + + owner->niovs = kvmalloc_array(owner->num_niovs, + sizeof(*owner->niovs), + GFP_KERNEL); + if (!owner->niovs) { + err = -ENOMEM; + goto err_free_chunks; + } + + for (i = 0; i < owner->num_niovs; i++) { + niov = &owner->niovs[i]; + niov->owner = owner; + } + + virtual += len; + } + + return binding; + +err_free_chunks: + gen_pool_for_each_chunk(binding->chunk_pool, + net_devmem_dmabuf_free_chunk_owner, NULL); + gen_pool_destroy(binding->chunk_pool); +err_unmap: + dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt, + DMA_FROM_DEVICE); +err_detach: + dma_buf_detach(dmabuf, binding->attachment); +err_free_id: + xa_erase(&net_devmem_dmabuf_bindings, binding->id); +err_free_binding: + kfree(binding); +err_put_dmabuf: + dma_buf_put(dmabuf); + return ERR_PTR(err); +} + +void dev_dmabuf_uninstall(struct net_device *dev) +{ + unsigned int i, count = dev->num_rx_queues; + struct net_devmem_dmabuf_binding *binding; + struct netdev_rx_queue *rxq; + unsigned long xa_idx; + + for (i = 0; i < count; i++) { + binding = dev->_rx[i].mp_params.mp_priv; + if (binding) + xa_for_each(&binding->bound_rxqs, xa_idx, rxq) + if (rxq == &dev->_rx[i]) + xa_erase(&binding->bound_rxqs, xa_idx); + } +} +#endif diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 6b7fe6035067b..b28424ae06d5f 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -9,6 +9,7 @@ #include "netdev-genl-gen.h"

#include <uapi/linux/netdev.h> +#include <linux/list.h>

/* Integer value ranges */ static const struct netlink_range_validation netdev_a_page_pool_id_range = { @@ -187,4 +188,7 @@ struct genl_family netdev_nl_family __ro_after_init = { .n_split_ops = ARRAY_SIZE(netdev_nl_ops), .mcgrps = netdev_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(netdev_nl_mcgrps), + .sock_priv_size = sizeof(struct list_head), + .sock_priv_init = (void *)netdev_nl_sock_priv_init, + .sock_priv_destroy = (void *)netdev_nl_sock_priv_destroy, }; diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index 67c34005750c3..8cda334fd0429 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -10,6 +10,7 @@ #include <net/genetlink.h>

#include <uapi/linux/netdev.h> +#include <linux/list.h>

/* Common nested types */ extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1]; @@ -40,4 +41,7 @@ enum {

extern struct genl_family netdev_nl_family;

+void netdev_nl_sock_priv_init(struct list_head *priv); +void netdev_nl_sock_priv_destroy(struct list_head *priv); + #endif /* _LINUX_NETDEV_GEN_H */ diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 2d726e65211dd..bd54cf50b658a 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -10,6 +10,7 @@ #include <net/netdev_rx_queue.h> #include <net/netdev_queues.h> #include <net/busy_poll.h> +#include <net/devmem.h>

#include "netdev-genl-gen.h" #include "dev.h" @@ -721,10 +722,87 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, return err; }

-/* Stub */ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) { - return 0; + struct nlattr *tb[ARRAY_SIZE(netdev_queue_id_nl_policy)]; + struct net_devmem_dmabuf_binding *binding; + struct list_head *sock_binding_list; + 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_DMABUF_FD) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_QUEUES)) + return -EINVAL; + + ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); + dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]); + + sock_binding_list = genl_sk_priv_get(&netdev_nl_family, + NETLINK_CB(skb).sk); + if (IS_ERR(sock_binding_list)) + return PTR_ERR(sock_binding_list); + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) { + err = -EMSGSIZE; + goto err_genlmsg_free; + } + + rtnl_lock(); + + netdev = __dev_get_by_index(genl_info_net(info), ifindex); + if (!netdev || !netif_device_present(netdev)) { + err = -ENODEV; + goto err_unlock; + } + + binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd); + if (IS_ERR(binding)) { + err = PTR_ERR(binding); + goto err_unlock; + } + + nla_for_each_attr_type(attr, NETDEV_A_DMABUF_QUEUES, + genlmsg_data(info->genlhdr), + genlmsg_len(info->genlhdr), rem) { + err = nla_parse_nested( + tb, ARRAY_SIZE(netdev_queue_id_nl_policy) - 1, attr, + netdev_queue_id_nl_policy, info->extack); + if (err < 0) + goto err_unbind; + + rxq_idx = nla_get_u32(tb[NETDEV_A_QUEUE_ID]); + + err = net_devmem_bind_dmabuf_to_queue(netdev, rxq_idx, binding); + if (err) + goto err_unbind; + } + + list_add(&binding->list, sock_binding_list); + + nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id); + genlmsg_end(rsp, hdr); + + rtnl_unlock(); + + return genlmsg_reply(rsp, info); + +err_unbind: + net_devmem_unbind_dmabuf(binding); +err_unlock: + rtnl_unlock(); +err_genlmsg_free: + nlmsg_free(rsp); + return err; }

static int netdev_genl_netdevice_event(struct notifier_block *nb, @@ -771,3 +849,20 @@ static int __init netdev_genl_init(void) }

subsys_initcall(netdev_genl_init); + +void netdev_nl_sock_priv_init(struct list_head *priv) +{ + INIT_LIST_HEAD(priv); +} + +void netdev_nl_sock_priv_destroy(struct list_head *priv) +{ + struct net_devmem_dmabuf_binding *binding; + struct net_devmem_dmabuf_binding *temp; + + list_for_each_entry_safe(binding, temp, priv, list) { + rtnl_lock(); + net_devmem_unbind_dmabuf(binding); + rtnl_unlock(); + } +}

Implement netdev devmem allocator. The allocator takes a given struct netdev_dmabuf_binding as input and allocates net_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 net_iov struct.

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 Reviewed-by: Pavel Begunkov asml.silence@gmail.com

---

v17: - Don't acquire a binding ref for every allocation (Jakub).

v11: - Fix extraneous inline directive (Paolo)

v8: - Rename netdev_dmabuf_binding -> net_devmem_dmabuf_binding to avoid patch-by-patch build error. - Move niov->pp_magic/pp/pp_ref_counter usage to later patch to avoid patch-by-patch build error.

v7: - netdev_ -> net_devmem_* naming (Yunsheng).

v6: - Add comment on net_iov_dma_addr to explain why we don't use niov->dma_addr (Pavel) - Refactor new functions into net/core/devmem.c (Pavel)

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

--- include/net/devmem.h | 13 +++++++++++++ include/net/netmem.h | 18 ++++++++++++++++++ net/core/devmem.c | 40 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 71 insertions(+)

diff --git a/include/net/devmem.h b/include/net/devmem.h index c7bd6a0a6b9e9..2e7cc46d4d3ca 100644 --- a/include/net/devmem.h +++ b/include/net/devmem.h @@ -69,7 +69,20 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding); int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, struct net_devmem_dmabuf_binding *binding); void dev_dmabuf_uninstall(struct net_device *dev); +struct net_iov * +net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding); +void net_devmem_free_dmabuf(struct net_iov *ppiov); #else +static inline struct net_iov * +net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ + return NULL; +} + +static inline void net_devmem_free_dmabuf(struct net_iov *ppiov) +{ +} + static inline void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) { diff --git a/include/net/netmem.h b/include/net/netmem.h index 41e96c2f94b5c..664df8325ece5 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -14,8 +14,26 @@

struct net_iov { struct dmabuf_genpool_chunk_owner *owner; + unsigned long dma_addr; };

+static inline struct dmabuf_genpool_chunk_owner * +net_iov_owner(const struct net_iov *niov) +{ + return niov->owner; +} + +static inline unsigned int net_iov_idx(const struct net_iov *niov) +{ + return niov - net_iov_owner(niov)->niovs; +} + +static inline struct net_devmem_dmabuf_binding * +net_iov_binding(const struct net_iov *niov) +{ + return net_iov_owner(niov)->binding; +} + /* netmem */

/** diff --git a/net/core/devmem.c b/net/core/devmem.c index 9a357235bde8f..3f73d0bda023f 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -32,6 +32,14 @@ static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool, kfree(owner); }

+static dma_addr_t net_devmem_get_dma_addr(const struct net_iov *niov) +{ + struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov); + + return owner->base_dma_addr + + ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT); +} + void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) { size_t size, avail; @@ -54,6 +62,38 @@ void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) kfree(binding); }

+struct net_iov * +net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ + struct dmabuf_genpool_chunk_owner *owner; + unsigned long dma_addr; + struct net_iov *niov; + 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; + niov = &owner->niovs[index]; + + niov->dma_addr = 0; + + return niov; +} + +void net_devmem_free_dmabuf(struct net_iov *niov) +{ + struct net_devmem_dmabuf_binding *binding = net_iov_binding(niov); + unsigned long dma_addr = net_devmem_get_dma_addr(niov); + + if (gen_pool_has_addr(binding->chunk_pool, dma_addr, PAGE_SIZE)) + gen_pool_free(binding->chunk_pool, dma_addr, PAGE_SIZE); +} + /* Protected by rtnl_lock() */ static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1);

These helpers are used for setup and init of buffers, and their implementation need not be static inline in the header file.

Moving the implementation to the .c file allows us to hide netmem implementation details in internal header files rather than the public file.

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

--- include/net/page_pool/helpers.h | 30 ++---------------------------- net/core/page_pool.c | 31 +++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+), 28 deletions(-)

diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 2b43a893c619d..8f27ecc00bb16 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -399,17 +399,7 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va, page_pool_put_page(pool, virt_to_head_page(va), -1, allow_direct); }

-static inline dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem) -{ - struct page *page = netmem_to_page(netmem); - - dma_addr_t ret = page->dma_addr; - - if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) - ret <<= PAGE_SHIFT; - - return ret; -} +dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem);

/** * page_pool_get_dma_addr() - Retrieve the stored DMA address. @@ -423,23 +413,7 @@ static inline dma_addr_t page_pool_get_dma_addr(const struct page *page) return page_pool_get_dma_addr_netmem(page_to_netmem((struct page *)page)); }

-static inline bool page_pool_set_dma_addr_netmem(netmem_ref netmem, - dma_addr_t addr) -{ - struct page *page = netmem_to_page(netmem); - - if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) { - page->dma_addr = addr >> PAGE_SHIFT; - - /* We assume page alignment to shave off bottom bits, - * if this "compression" doesn't work we need to drop. - */ - return addr != (dma_addr_t)page->dma_addr << PAGE_SHIFT; - } - - page->dma_addr = addr; - return false; -} +bool page_pool_set_dma_addr_netmem(netmem_ref netmem, dma_addr_t addr);

/** * page_pool_dma_sync_for_cpu - sync Rx page for CPU after it's written by HW diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 2abe6e919224d..a032f731d4146 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -1099,3 +1099,34 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid) } } EXPORT_SYMBOL(page_pool_update_nid); + +dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem) +{ + struct page *page = netmem_to_page(netmem); + + dma_addr_t ret = page->dma_addr; + + if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) + ret <<= PAGE_SHIFT; + + return ret; +} +EXPORT_SYMBOL(page_pool_get_dma_addr_netmem); + +bool page_pool_set_dma_addr_netmem(netmem_ref netmem, dma_addr_t addr) +{ + struct page *page = netmem_to_page(netmem); + + if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) { + page->dma_addr = addr >> PAGE_SHIFT; + + /* We assume page alignment to shave off bottom bits, + * if this "compression" doesn't work we need to drop. + */ + return addr != (dma_addr_t)page->dma_addr << PAGE_SHIFT; + } + + page->dma_addr = addr; + return false; +} +EXPORT_SYMBOL(page_pool_set_dma_addr_netmem);

Convert netmem to be a union of struct page and struct netmem. Overload the LSB of struct netmem* to indicate that it's a net_iov, otherwise it's a page.

Currently these entries in struct page are rented by the page_pool and used exclusively by the net stack:

struct { unsigned long pp_magic; struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; atomic_long_t pp_ref_count; };

Mirror these (and only these) entries into struct net_iov and implement netmem helpers that can access these common fields regardless of whether the underlying type is page or net_iov.

Implement checks for net_iov in netmem helpers which delegate to mm APIs, to ensure net_iov are never passed to the mm stack.

Signed-off-by: Mina Almasry almasrymina@google.com Reviewed-by: Pavel Begunkov asml.silence@gmail.com

---

v17: - Rename netmem_to_pfn to netmem_pfn_trace (Jakub) - Move some low level netmem helpers to netmem_priv.h (Jakub).

v13: - Move NET_IOV dependent changes to this patch. - Fixed comment (Pavel) - Applied Reviewed-by from Pavel.

v9: https://lore.kernel.org/netdev/20240403002053.2376017-8-almasrymina@google.c... - Remove CONFIG checks in netmem_is_net_iov() (Pavel/David/Jens)

v7: - Remove static_branch_unlikely from netmem_to_net_iov(). We're getting better results from the fast path in bench_page_pool_simple tests without the static_branch_unlikely, and the addition of static_branch_unlikely doesn't improve performance of devmem TCP.

Additionally only check netmem_to_net_iov() if CONFIG_DMA_SHARED_BUFFER is enabled, otherwise dmabuf net_iovs cannot exist anyway.

net-next base: 8 cycle fast path. with static_branch_unlikely: 10 cycle fast path. without static_branch_unlikely: 9 cycle fast path. CONFIG_DMA_SHARED_BUFFER disabled: 8 cycle fast path as baseline.

Performance of devmem TCP is at 95% line rate is regardless of static_branch_unlikely or not.

v6: - Rebased on top of the merged netmem_ref type. - Rebased on top of the merged skb_pp_frag_ref() changes.

v5: - Use netmem instead of page* with LSB set. - Use pp_ref_count for refcounting net_iov. - Removed many of the custom checks for netmem.

v1: - Disable fragmentation support for iov properly. - fix napi_pp_put_page() path (Yunsheng). - Use pp_frag_count for devmem refcounting.

Cc: linux-mm@kvack.org Cc: Matthew Wilcox willy@infradead.org

--- include/net/netmem.h | 108 +++++++++++++++++++++++++++++-- include/net/page_pool/helpers.h | 12 ++-- include/trace/events/page_pool.h | 12 ++-- net/core/devmem.c | 3 + net/core/netmem_priv.h | 36 +++++++++++ net/core/page_pool.c | 38 ++++++----- net/core/skbuff.c | 23 ++++--- 7 files changed, 181 insertions(+), 51 deletions(-) create mode 100644 net/core/netmem_priv.h

diff --git a/include/net/netmem.h b/include/net/netmem.h index 664df8325ece5..99531780e53af 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -9,14 +9,51 @@ #define _NET_NETMEM_H

#include <net/devmem.h> +#include <net/net_debug.h>

/* net_iov */

+DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers); + +/* We overload the LSB of the struct page pointer to indicate whether it's + * a page or net_iov. + */ +#define NET_IOV 0x01UL + struct net_iov { + unsigned long __unused_padding; + unsigned long pp_magic; + struct page_pool *pp; struct dmabuf_genpool_chunk_owner *owner; unsigned long dma_addr; + atomic_long_t pp_ref_count; };

+/* These fields in struct page are used by the page_pool and net stack: + * + * struct { + * unsigned long pp_magic; + * struct page_pool *pp; + * unsigned long _pp_mapping_pad; + * unsigned long dma_addr; + * atomic_long_t pp_ref_count; + * }; + * + * We mirror the page_pool fields here so the page_pool can access these fields + * without worrying whether the underlying fields belong to a page or net_iov. + * + * The non-net stack fields of struct page are private to the mm stack and must + * never be mirrored to net_iov. + */ +#define NET_IOV_ASSERT_OFFSET(pg, iov) \ + static_assert(offsetof(struct page, pg) == \ + offsetof(struct net_iov, iov)) +NET_IOV_ASSERT_OFFSET(pp_magic, pp_magic); +NET_IOV_ASSERT_OFFSET(pp, pp); +NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr); +NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count); +#undef NET_IOV_ASSERT_OFFSET + static inline struct dmabuf_genpool_chunk_owner * net_iov_owner(const struct net_iov *niov) { @@ -47,20 +84,22 @@ net_iov_binding(const struct net_iov *niov) */ typedef unsigned long __bitwise netmem_ref;

+static inline bool netmem_is_net_iov(const netmem_ref netmem) +{ + return (__force unsigned long)netmem & NET_IOV; +} + /* This conversion fails (returns NULL) if the netmem_ref is not struct page * backed. - * - * Currently struct page is the only possible netmem, and this helper never - * fails. */ static inline struct page *netmem_to_page(netmem_ref netmem) { + if (WARN_ON_ONCE(netmem_is_net_iov(netmem))) + return NULL; + return (__force struct page *)netmem; }

-/* Converting from page to netmem is always safe, because a page can always be - * a netmem. - */ static inline netmem_ref page_to_netmem(struct page *page) { return (__force netmem_ref)page; @@ -68,17 +107,72 @@ static inline netmem_ref page_to_netmem(struct page *page)

static inline int netmem_ref_count(netmem_ref netmem) { + /* The non-pp refcount of net_iov is always 1. On net_iov, we only + * support pp refcounting which uses the pp_ref_count field. + */ + if (netmem_is_net_iov(netmem)) + return 1; + return page_ref_count(netmem_to_page(netmem)); }

-static inline unsigned long netmem_to_pfn(netmem_ref netmem) +static inline unsigned long netmem_pfn_trace(netmem_ref netmem) { + if (netmem_is_net_iov(netmem)) + return 0; + return page_to_pfn(netmem_to_page(netmem)); }

+static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem) +{ + return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV); +} + +static inline struct page_pool *netmem_get_pp(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->pp; +} + +static inline atomic_long_t *netmem_get_pp_ref_count_ref(netmem_ref netmem) +{ + return &__netmem_clear_lsb(netmem)->pp_ref_count; +} + +static inline bool netmem_is_pref_nid(netmem_ref netmem, int pref_nid) +{ + /* Assume net_iov are on the preferred node without actually + * checking... + * + * This check is only used to check for recycling memory in the page + * pool's fast paths. Currently the only implementation of net_iov + * is dmabuf device memory. It's a deliberate decision by the user to + * bind a certain dmabuf to a certain netdev, and the netdev rx queue + * would not be able to reallocate memory from another dmabuf that + * exists on the preferred node, so, this check doesn't make much sense + * in this case. Assume all net_iovs can be recycled for now. + */ + if (netmem_is_net_iov(netmem)) + return true; + + return page_to_nid(netmem_to_page(netmem)) == pref_nid; +} + static inline netmem_ref netmem_compound_head(netmem_ref netmem) { + /* niov are never compounded */ + if (netmem_is_net_iov(netmem)) + return netmem; + return page_to_netmem(compound_head(netmem_to_page(netmem))); }

+static inline void *netmem_address(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + return NULL; + + return page_address(netmem_to_page(netmem)); +} + #endif /* _NET_NETMEM_H */ diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 8f27ecc00bb16..50c1efd4018fd 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -216,7 +216,7 @@ page_pool_get_dma_dir(const struct page_pool *pool)

static inline void page_pool_fragment_netmem(netmem_ref netmem, long nr) { - atomic_long_set(&netmem_to_page(netmem)->pp_ref_count, nr); + atomic_long_set(netmem_get_pp_ref_count_ref(netmem), nr); }

/** @@ -244,7 +244,7 @@ static inline void page_pool_fragment_page(struct page *page, long nr)

static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) { - struct page *page = netmem_to_page(netmem); + atomic_long_t *pp_ref_count = netmem_get_pp_ref_count_ref(netmem); long ret;

/* If nr == pp_ref_count then we have cleared all remaining @@ -261,19 +261,19 @@ static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) * initially, and only overwrite it when the page is partitioned into * more than one piece. */ - if (atomic_long_read(&page->pp_ref_count) == nr) { + if (atomic_long_read(pp_ref_count) == nr) { /* As we have ensured nr is always one for constant case using * the BUILD_BUG_ON(), only need to handle the non-constant case * here for pp_ref_count draining, which is a rare case. */ BUILD_BUG_ON(__builtin_constant_p(nr) && nr != 1); if (!__builtin_constant_p(nr)) - atomic_long_set(&page->pp_ref_count, 1); + atomic_long_set(pp_ref_count, 1);

return 0; }

- ret = atomic_long_sub_return(nr, &page->pp_ref_count); + ret = atomic_long_sub_return(nr, pp_ref_count); WARN_ON(ret < 0);

/* We are the last user here too, reset pp_ref_count back to 1 to @@ -282,7 +282,7 @@ static inline long page_pool_unref_netmem(netmem_ref netmem, long nr) * page_pool_unref_page() currently. */ if (unlikely(!ret)) - atomic_long_set(&page->pp_ref_count, 1); + atomic_long_set(pp_ref_count, 1);

return ret; } diff --git a/include/trace/events/page_pool.h b/include/trace/events/page_pool.h index 543e54e432a18..31825ed300324 100644 --- a/include/trace/events/page_pool.h +++ b/include/trace/events/page_pool.h @@ -57,12 +57,12 @@ TRACE_EVENT(page_pool_state_release, __entry->pool = pool; __entry->netmem = (__force unsigned long)netmem; __entry->release = release; - __entry->pfn = netmem_to_pfn(netmem); + __entry->pfn = netmem_pfn_trace(netmem); ),

- TP_printk("page_pool=%p netmem=%p pfn=0x%lx release=%u", + TP_printk("page_pool=%p netmem=%p is_net_iov=%lu pfn=0x%lx release=%u", __entry->pool, (void *)__entry->netmem, - __entry->pfn, __entry->release) + __entry->netmem & NET_IOV, __entry->pfn, __entry->release) );

TRACE_EVENT(page_pool_state_hold, @@ -83,12 +83,12 @@ TRACE_EVENT(page_pool_state_hold, __entry->pool = pool; __entry->netmem = (__force unsigned long)netmem; __entry->hold = hold; - __entry->pfn = netmem_to_pfn(netmem); + __entry->pfn = netmem_pfn_trace(netmem); ),

- TP_printk("page_pool=%p netmem=%p pfn=0x%lx hold=%u", + TP_printk("page_pool=%p netmem=%p is_net_iov=%lu, pfn=0x%lx hold=%u", __entry->pool, (void *)__entry->netmem, - __entry->pfn, __entry->hold) + __entry->netmem & NET_IOV, __entry->pfn, __entry->hold) );

TRACE_EVENT(page_pool_update_nid, diff --git a/net/core/devmem.c b/net/core/devmem.c index 3f73d0bda023f..befff59a2ee64 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -80,7 +80,10 @@ net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding) index = offset / PAGE_SIZE; niov = &owner->niovs[index];

+ niov->pp_magic = 0; + niov->pp = NULL; niov->dma_addr = 0; + atomic_long_set(&niov->pp_ref_count, 0);

return niov; } diff --git a/net/core/netmem_priv.h b/net/core/netmem_priv.h new file mode 100644 index 0000000000000..d18eaca38cdaa --- /dev/null +++ b/net/core/netmem_priv.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __NETMEM_PRIV_H +#define __NETMEM_PRIV_H + +static inline unsigned long netmem_get_pp_magic(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->pp_magic; +} + +static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic) +{ + __netmem_clear_lsb(netmem)->pp_magic |= pp_magic; +} + +static inline void netmem_clear_pp_magic(netmem_ref netmem) +{ + __netmem_clear_lsb(netmem)->pp_magic = 0; +} + +static inline void netmem_set_pp(netmem_ref netmem, struct page_pool *pool) +{ + __netmem_clear_lsb(netmem)->pp = pool; +} + +static inline unsigned long netmem_get_dma_addr(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->dma_addr; +} + +static inline void netmem_set_dma_addr(netmem_ref netmem, + unsigned long dma_addr) +{ + __netmem_clear_lsb(netmem)->dma_addr = dma_addr; +} +#endif diff --git a/net/core/page_pool.c b/net/core/page_pool.c index a032f731d4146..c5c303746d494 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -25,6 +25,9 @@ #include <trace/events/page_pool.h>

#include "page_pool_priv.h" +#include "netmem_priv.h" + +DEFINE_STATIC_KEY_FALSE(page_pool_mem_providers);

#define DEFER_TIME (msecs_to_jiffies(1000)) #define DEFER_WARN_INTERVAL (60 * HZ) @@ -358,7 +361,7 @@ static noinline netmem_ref page_pool_refill_alloc_cache(struct page_pool *pool) if (unlikely(!netmem)) break;

- if (likely(page_to_nid(netmem_to_page(netmem)) == pref_nid)) { + if (likely(netmem_is_pref_nid(netmem, pref_nid))) { pool->alloc.cache[pool->alloc.count++] = netmem; } else { /* NUMA mismatch; @@ -454,10 +457,8 @@ static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem)

static void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem) { - struct page *page = netmem_to_page(netmem); - - page->pp = pool; - page->pp_magic |= PP_SIGNATURE; + netmem_set_pp(netmem, pool); + netmem_or_pp_magic(netmem, PP_SIGNATURE);

/* Ensuring all pages have been split into one fragment initially: * page_pool_set_pp_info() is only called once for every page when it @@ -472,10 +473,8 @@ static void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)

static void page_pool_clear_pp_info(netmem_ref netmem) { - struct page *page = netmem_to_page(netmem); - - page->pp_magic = 0; - page->pp = NULL; + netmem_clear_pp_magic(netmem); + netmem_set_pp(netmem, NULL); }

static struct page *__page_pool_alloc_page_order(struct page_pool *pool, @@ -692,8 +691,9 @@ static bool page_pool_recycle_in_cache(netmem_ref netmem,

static bool __page_pool_page_can_be_recycled(netmem_ref netmem) { - return page_ref_count(netmem_to_page(netmem)) == 1 && - !page_is_pfmemalloc(netmem_to_page(netmem)); + return netmem_is_net_iov(netmem) || + (page_ref_count(netmem_to_page(netmem)) == 1 && + !page_is_pfmemalloc(netmem_to_page(netmem))); }

/* If the page refcnt == 1, this will try to recycle the page. @@ -728,6 +728,7 @@ __page_pool_put_page(struct page_pool *pool, netmem_ref netmem, /* Page found as candidate for recycling */ return netmem; } + /* Fallback/non-XDP mode: API user have elevated refcnt. * * Many drivers split up the page into fragments, and some @@ -949,7 +950,7 @@ static void page_pool_empty_ring(struct page_pool *pool) /* Empty recycle ring */ while ((netmem = (__force netmem_ref)ptr_ring_consume_bh(&pool->ring))) { /* Verify the refcnt invariant of cached pages */ - if (!(page_ref_count(netmem_to_page(netmem)) == 1)) + if (!(netmem_ref_count(netmem) == 1)) pr_crit("%s() page_pool refcnt %d violation\n", __func__, netmem_ref_count(netmem));

@@ -1102,9 +1103,7 @@ EXPORT_SYMBOL(page_pool_update_nid);

dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem) { - struct page *page = netmem_to_page(netmem); - - dma_addr_t ret = page->dma_addr; + dma_addr_t ret = netmem_get_dma_addr(netmem);

if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) ret <<= PAGE_SHIFT; @@ -1115,18 +1114,17 @@ EXPORT_SYMBOL(page_pool_get_dma_addr_netmem);

bool page_pool_set_dma_addr_netmem(netmem_ref netmem, dma_addr_t addr) { - struct page *page = netmem_to_page(netmem); - if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) { - page->dma_addr = addr >> PAGE_SHIFT; + netmem_set_dma_addr(netmem, addr >> PAGE_SHIFT);

/* We assume page alignment to shave off bottom bits, * if this "compression" doesn't work we need to drop. */ - return addr != (dma_addr_t)page->dma_addr << PAGE_SHIFT; + return addr != (dma_addr_t)netmem_get_dma_addr(netmem) + << PAGE_SHIFT; }

- page->dma_addr = addr; + netmem_set_dma_addr(netmem, addr); return false; } EXPORT_SYMBOL(page_pool_set_dma_addr_netmem); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index de2a044cc6656..9e2b283427934 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -89,6 +89,7 @@

#include "dev.h" #include "sock_destructor.h" +#include "netmem_priv.h"

#ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; @@ -920,9 +921,9 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); }

-static bool is_pp_page(struct page *page) +static bool is_pp_netmem(netmem_ref netmem) { - return (page->pp_magic & ~0x3UL) == PP_SIGNATURE; + return (netmem_get_pp_magic(netmem) & ~0x3UL) == PP_SIGNATURE; }

int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, @@ -1020,9 +1021,7 @@ EXPORT_SYMBOL(skb_cow_data_for_xdp); #if IS_ENABLED(CONFIG_PAGE_POOL) bool napi_pp_put_page(netmem_ref netmem) { - struct page *page = netmem_to_page(netmem); - - page = compound_head(page); + netmem = netmem_compound_head(netmem);

/* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation * in order to preserve any existing bits, such as bit 0 for the @@ -1031,10 +1030,10 @@ bool napi_pp_put_page(netmem_ref netmem) * and page_is_pfmemalloc() is checked in __page_pool_put_page() * to avoid recycling the pfmemalloc page. */ - if (unlikely(!is_pp_page(page))) + if (unlikely(!is_pp_netmem(netmem))) return false;

- page_pool_put_full_netmem(page->pp, page_to_netmem(page), false); + page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false);

return true; } @@ -1061,7 +1060,7 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data) static int skb_pp_frag_ref(struct sk_buff *skb) { struct skb_shared_info *shinfo; - struct page *head_page; + netmem_ref head_netmem; int i;

if (!skb->pp_recycle) @@ -1070,11 +1069,11 @@ static int skb_pp_frag_ref(struct sk_buff *skb) shinfo = skb_shinfo(skb);

for (i = 0; i < shinfo->nr_frags; i++) { - head_page = compound_head(skb_frag_page(&shinfo->frags[i])); - if (likely(is_pp_page(head_page))) - page_pool_ref_page(head_page); + head_netmem = netmem_compound_head(shinfo->frags[i].netmem); + if (likely(is_pp_netmem(head_netmem))) + page_pool_ref_netmem(head_netmem); else - page_ref_inc(head_page); + page_ref_inc(netmem_to_page(head_netmem)); } return 0; }

For device memory TCP, we expect the skb headers to be available in host memory for access, and we expect the skb frags to be in device memory and unaccessible to the host. We expect there to be no mixing and matching of device memory frags (unaccessible) with host memory frags (accessible) in the same skb.

Add a skb->devmem flag which indicates whether the frags in this skb are device memory frags or not.

__skb_fill_netmem_desc() now checks frags added to skbs for net_iov, and marks the skb as skb->devmem accordingly.

Add checks through the network stack to avoid accessing the frags of devmem skbs and avoid coalescing devmem skbs with non devmem skbs.

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 Reviewed-by: Eric Dumazet edumazet@google.com

---

v16: - Fix unreadable handling in skb_split_no_header() (Eric).

v11: - drop excessive checks for frag 0 pull (Paolo)

v9: https://lore.kernel.org/netdev/20240403002053.2376017-11-almasrymina@google.... - change skb->readable to skb->unreadable (Pavel/David).

skb->readable was very complicated, because by default skbs are readable so the flag needed to be set to true in all code paths where new skbs were created or cloned. Forgetting to set skb->readable=true in some paths caused crashes.

Flip it to skb->unreadable so that the default 0 value works well, and we only need to set it to true when we add unreadable frags.

v6 - skb->dmabuf -> skb->readable (Pavel). Pavel's original suggestion was to remove the skb->dmabuf flag entirely, but when I looked into it closely, I found the issue that if we remove the flag we have to dereference the shinfo(skb) pointer to obtain the first frag, which can cause a performance regression if it dirties the cache line when the shinfo(skb) was not really needed. Instead, I converted the skb->dmabuf flag into a generic skb->readable flag which can be re-used by io_uring.

Changes in v1: - Rename devmem -> dmabuf (David). - Flip skb_frags_not_readable (Jakub).

--- include/linux/skbuff.h | 19 +++++++++++++++++-- include/net/tcp.h | 5 +++-- net/core/datagram.c | 6 ++++++ net/core/skbuff.c | 43 ++++++++++++++++++++++++++++++++++++++++-- net/ipv4/tcp.c | 3 +++ net/ipv4/tcp_input.c | 13 ++++++++++--- net/ipv4/tcp_output.c | 5 ++++- net/packet/af_packet.c | 4 ++-- 8 files changed, 86 insertions(+), 12 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dbadf2dd6b353..d02a88bad953b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -827,6 +827,8 @@ enum skb_tstamp_type { * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) + * @unreadable: indicates that at least 1 of the fragments in this skb is + * unreadable. * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required @@ -1008,7 +1010,7 @@ struct sk_buff { #if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; #endif - + __u8 unreadable:1; #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif @@ -1823,6 +1825,12 @@ static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) __skb_zcopy_downgrade_managed(skb); }

+/* Return true if frags in this skb are readable by the host. */ +static inline bool skb_frags_readable(const struct sk_buff *skb) +{ + return !skb->unreadable; +} + static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; @@ -2539,10 +2547,17 @@ static inline void skb_len_add(struct sk_buff *skb, int delta) static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { - struct page *page = netmem_to_page(netmem); + struct page *page;

__skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size);

+ if (netmem_is_net_iov(netmem)) { + skb->unreadable = true; + return; + } + + page = netmem_to_page(netmem); + /* Propagate page pfmemalloc to the skb if we can. The problem is * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). diff --git a/include/net/tcp.h b/include/net/tcp.h index 2aac11e7e1cc5..e8f6e602c2ad4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1060,7 +1060,7 @@ static inline int tcp_skb_mss(const struct sk_buff *skb)

static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb) { - return likely(!TCP_SKB_CB(skb)->eor); + return likely(!TCP_SKB_CB(skb)->eor && skb_frags_readable(skb)); }

static inline bool tcp_skb_can_collapse(const struct sk_buff *to, @@ -1069,7 +1069,8 @@ static inline bool tcp_skb_can_collapse(const struct sk_buff *to, /* skb_cmp_decrypted() not needed, use tcp_write_collapse_fence() */ return likely(tcp_skb_can_collapse_to(to) && mptcp_skb_can_collapse(to, from) && - skb_pure_zcopy_same(to, from)); + skb_pure_zcopy_same(to, from) && + skb_frags_readable(to) == skb_frags_readable(from)); }

static inline bool tcp_skb_can_collapse_rx(const struct sk_buff *to, diff --git a/net/core/datagram.c b/net/core/datagram.c index a40f733b37d70..f0693707aece4 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -407,6 +407,9 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset, return 0; }

+ if (!skb_frags_readable(skb)) + goto short_copy; + /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; @@ -623,6 +626,9 @@ int zerocopy_fill_skb_from_iter(struct sk_buff *skb, { int frag = skb_shinfo(skb)->nr_frags;

+ if (!skb_frags_readable(skb)) + return -EFAULT; + while (length && iov_iter_count(from)) { struct page *head, *last_head = NULL; struct page *pages[MAX_SKB_FRAGS]; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 91c7def737001..ea60dae051682 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1972,6 +1972,9 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) return -EINVAL;

+ if (!skb_frags_readable(skb)) + return -EFAULT; + if (!num_frags) goto release;

@@ -2145,6 +2148,9 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) unsigned int size; int headerlen;

+ if (!skb_frags_readable(skb)) + return NULL; + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL;

@@ -2483,6 +2489,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, struct sk_buff *n; int oldheadroom;

+ if (!skb_frags_readable(skb)) + return NULL; + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL;

@@ -2827,6 +2836,9 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta) */ int i, k, eat = (skb->tail + delta) - skb->end;

+ if (!skb_frags_readable(skb)) + return NULL; + if (eat > 0 || skb_cloned(skb)) { if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0, GFP_ATOMIC)) @@ -2980,6 +2992,9 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) to += copy; }

+ if (!skb_frags_readable(skb)) + goto fault; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *f = &skb_shinfo(skb)->frags[i]; @@ -3168,6 +3183,9 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, /* * then map the fragments */ + if (!skb_frags_readable(skb)) + return false; + for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];

@@ -3391,6 +3409,9 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) from += copy; }

+ if (!skb_frags_readable(skb)) + goto fault; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int end; @@ -3470,6 +3491,9 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, pos = copy; }

+ if (!skb_frags_readable(skb)) + return 0; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; @@ -3570,6 +3594,9 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, pos = copy; }

+ if (!skb_frags_readable(skb)) + return 0; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end;

@@ -4061,6 +4088,7 @@ static inline void skb_split_inside_header(struct sk_buff *skb, skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i];

skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags; + skb1->unreadable = skb->unreadable; skb_shinfo(skb)->nr_frags = 0; skb1->data_len = skb->data_len; skb1->len += skb1->data_len; @@ -4108,6 +4136,8 @@ static inline void skb_split_no_header(struct sk_buff *skb, pos += size; } skb_shinfo(skb1)->nr_frags = k; + + skb1->unreadable = skb->unreadable; }

/** @@ -4346,6 +4376,9 @@ unsigned int skb_seq_read(unsigned int consumed, const u8 **data, return block_limit - abs_offset; }

+ if (!skb_frags_readable(st->cur_skb)) + return 0; + if (st->frag_idx == 0 && !st->frag_data) st->stepped_offset += skb_headlen(st->cur_skb);

@@ -5958,7 +5991,10 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (to->pp_recycle != from->pp_recycle) return false;

- if (len <= skb_tailroom(to)) { + if (skb_frags_readable(from) != skb_frags_readable(to)) + return false; + + if (len <= skb_tailroom(to) && skb_frags_readable(from)) { if (len) BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); *delta_truesize = 0; @@ -6135,6 +6171,9 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len) if (!pskb_may_pull(skb, write_len)) return -ENOMEM;

+ if (!skb_frags_readable(skb)) + return -EFAULT; + if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0;

@@ -6814,7 +6853,7 @@ void skb_condense(struct sk_buff *skb) { if (skb->data_len) { if (skb->data_len > skb->end - skb->tail || - skb_cloned(skb)) + skb_cloned(skb) || !skb_frags_readable(skb)) return;

/* Nice, we can free page frag(s) right now */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8050148d302b1..adc0eb9a9b5c3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2160,6 +2160,9 @@ static int tcp_zerocopy_receive(struct sock *sk, skb = tcp_recv_skb(sk, seq, &offset); }

+ if (!skb_frags_readable(skb)) + break; + if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e2b9583ed96ab..01cbc317fd71e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5395,6 +5395,9 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root, for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) { n = tcp_skb_next(skb, list);

+ if (!skb_frags_readable(skb)) + goto skip_this; + /* No new bits? It is possible on ofo queue. */ if (!before(start, TCP_SKB_CB(skb)->end_seq)) { skb = tcp_collapse_one(sk, skb, list, root); @@ -5415,17 +5418,20 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root, break; }

- if (n && n != tail && tcp_skb_can_collapse_rx(skb, n) && + if (n && n != tail && skb_frags_readable(n) && + tcp_skb_can_collapse_rx(skb, n) && TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) { end_of_skbs = false; break; }

+skip_this: /* Decided to skip this, advance start seq. */ start = TCP_SKB_CB(skb)->end_seq; } if (end_of_skbs || - (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) + (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) || + !skb_frags_readable(skb)) return;

__skb_queue_head_init(&tmp); @@ -5467,7 +5473,8 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root, if (!skb || skb == tail || !tcp_skb_can_collapse_rx(nskb, skb) || - (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) + (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) || + !skb_frags_readable(skb)) goto end; } } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 16c48df8df4cc..3678255e94ec2 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2344,7 +2344,8 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)

if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb) || - !skb_pure_zcopy_same(skb, next)) + !skb_pure_zcopy_same(skb, next) || + skb_frags_readable(skb) != skb_frags_readable(next)) return false;

len -= skb->len; @@ -3264,6 +3265,8 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) return false; if (skb_cloned(skb)) return false; + if (!skb_frags_readable(skb)) + return false; /* Some heuristics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return false; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 4a364cdd445e8..a705ec2142540 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2216,7 +2216,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, } }

- snaplen = skb->len; + snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb);

res = run_filter(skb, sk, snaplen); if (!res) @@ -2336,7 +2336,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } }

- snaplen = skb->len; + snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb);

res = run_filter(skb, sk, snaplen); if (!res)

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 reuse.

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 Reviewed-by: Pavel Begunkov asml.silence@gmail.com Reviewed-by: Eric Dumazet edumazet@google.com

---

v16: - Use sk_is_tcp(). - Fix unnamed 128 DONTNEED limit (David). - Fix kernel allocating for 128 tokens even if the user didn't ask for that much (Eric). - Fix number assignement (Arnd).

v10: - Fix leak of tokens (Nikolay).

v7: - Updated SO_DEVMEM_* uapi to use the next available entry (Arnd).

v6: - Squash in locking optimizations from edumazet@google.com. With his changes we lock the xarray once per sock_devmem_dontneed operation rather than once per frag.

Changes in v1: - devmemtoken -> dmabuf_token (David). - Use napi_pp_put_page() for refcounting (Yunsheng). - Fix build error with missing socket options on other asms.

--- arch/alpha/include/uapi/asm/socket.h | 1 + arch/mips/include/uapi/asm/socket.h | 1 + arch/parisc/include/uapi/asm/socket.h | 1 + arch/sparc/include/uapi/asm/socket.h | 1 + include/uapi/asm-generic/socket.h | 1 + include/uapi/linux/uio.h | 4 ++ net/core/sock.c | 68 +++++++++++++++++++++++++++ 7 files changed, 77 insertions(+)

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index ef4656a41058a..251b73c5481ea 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -144,6 +144,7 @@ #define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR #define SO_DEVMEM_DMABUF 79 #define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF +#define SO_DEVMEM_DONTNEED 80

#if !defined(__KERNEL__)

diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 414807d55e33f..8ab7582291abf 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -155,6 +155,7 @@ #define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR #define SO_DEVMEM_DMABUF 79 #define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF +#define SO_DEVMEM_DONTNEED 80

#if !defined(__KERNEL__)

diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 2b817efd45444..38fc0b188e084 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -136,6 +136,7 @@ #define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR #define SO_DEVMEM_DMABUF 79 #define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF +#define SO_DEVMEM_DONTNEED 80

#if !defined(__KERNEL__)

diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 00248fc689773..57084ed2f3c4e 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -137,6 +137,7 @@ #define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR #define SO_DEVMEM_DMABUF 0x0058 #define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF +#define SO_DEVMEM_DONTNEED 0x0059

#if !defined(__KERNEL__)

diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index e993edc9c0ee6..3b4e3e8156025 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -139,6 +139,7 @@ #define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR #define SO_DEVMEM_DMABUF 79 #define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF +#define SO_DEVMEM_DONTNEED 80

#if !defined(__KERNEL__)

diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h index 3a22ddae376a2..d17f8fcd93ec9 100644 --- a/include/uapi/linux/uio.h +++ b/include/uapi/linux/uio.h @@ -33,6 +33,10 @@ struct dmabuf_cmsg { */ };

+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 9abc4fe259535..df2a2dd6409da 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -124,6 +124,7 @@ #include <linux/netdevice.h> #include <net/protocol.h> #include <linux/skbuff.h> +#include <linux/skbuff_ref.h> #include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.h> @@ -1049,6 +1050,69 @@ static int sock_reserve_memory(struct sock *sk, int bytes) return 0; }

+#ifdef CONFIG_PAGE_POOL + +/* This is the number of tokens that the user can SO_DEVMEM_DONTNEED in + * 1 syscall. The limit exists to limit the amount of memory the kernel + * allocates to copy these tokens. + */ +#define MAX_DONTNEED_TOKENS 128 + +static noinline_for_stack int +sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen) +{ + unsigned int num_tokens, i, j, k, netmem_num = 0; + struct dmabuf_token *tokens; + netmem_ref netmems[16]; + int ret = 0; + + if (!sk_is_tcp(sk)) + return -EBADF; + + if (optlen % sizeof(struct dmabuf_token) || + optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS) + return -EINVAL; + + tokens = kvmalloc_array(optlen, sizeof(*tokens), GFP_KERNEL); + if (!tokens) + return -ENOMEM; + + num_tokens = optlen / sizeof(struct dmabuf_token); + if (copy_from_sockptr(tokens, optval, optlen)) { + kvfree(tokens); + return -EFAULT; + } + + xa_lock_bh(&sk->sk_user_frags); + for (i = 0; i < num_tokens; i++) { + for (j = 0; j < tokens[i].token_count; j++) { + netmem_ref netmem = (__force netmem_ref)__xa_erase( + &sk->sk_user_frags, tokens[i].token_start + j); + + if (netmem && + !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) { + netmems[netmem_num++] = netmem; + if (netmem_num == ARRAY_SIZE(netmems)) { + xa_unlock_bh(&sk->sk_user_frags); + for (k = 0; k < netmem_num; k++) + WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); + netmem_num = 0; + xa_lock_bh(&sk->sk_user_frags); + } + ret++; + } + } + } + + xa_unlock_bh(&sk->sk_user_frags); + for (k = 0; k < netmem_num; k++) + WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); + + kvfree(tokens); + return ret; +} +#endif + void sockopt_lock_sock(struct sock *sk) { /* When current->bpf_ctx is set, the setsockopt is called from @@ -1211,6 +1275,10 @@ int sk_setsockopt(struct sock *sk, int level, int optname, ret = -EOPNOTSUPP; return ret; } +#ifdef CONFIG_PAGE_POOL + case SO_DEVMEM_DONTNEED: + return sock_devmem_dontneed(sk, optval, optlen); +#endif }

sockopt_lock_sock(sk);

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

---

v16: - Remove outdated -n option (Taehee). - Use 'ifname' instead of accidentally hardcoded 'eth1'. (Taehee) - Remove dead code 'iterations' (Taehee). - Use if_nametoindex() instead of passing device index (Taehee).

v15: - Fix linking against libynl. (Jakub)

v9: https://lore.kernel.org/netdev/20240403002053.2376017-15-almasrymina@google.... - Remove unused nic_pci_addr entry (Cong).

v6: - Updated to bind 8 queues. - Added RSS configuration. - Added some more tests for the netlink API.

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 | 9 + tools/testing/selftests/net/ncdevmem.c | 536 +++++++++++++++++++++++++ 3 files changed, 546 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 666ab7d9390b1..fe770903118c5 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 8eaffd7a641c5..e4708975ef428 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -95,6 +95,11 @@ TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh TEST_PROGS += bpf_offload.py

+# YNL files, must be before "include ..lib.mk" +EXTRA_CLEAN += $(OUTPUT)/libynl.a +YNL_GEN_FILES := ncdevmem +TEST_GEN_FILES += $(YNL_GEN_FILES) + TEST_FILES := settings TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh

@@ -104,6 +109,10 @@ TEST_INCLUDES := forwarding/lib.sh

include ../lib.mk

+# YNL build +YNL_GENS := netdev +include ynl.mk + $(OUTPUT)/epoll_busy_poll: LDLIBS += -lcap $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread -lcrypto diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c new file mode 100644 index 0000000000000..92c4fda346821 --- /dev/null +++ b/tools/testing/selftests/net/ncdevmem.c @@ -0,0 +1,536 @@ +// 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/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 <net/if.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 -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 start_queue = 8; +static int num_queues = 8; +static char *ifname = "eth1"; +static unsigned int ifindex; +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", + ifname); + system(command); + + memset(command, 0, sizeof(command)); + snprintf(command, sizeof(command), "sudo ethtool -K %s ntuple on", + ifname); + system(command); +} + +static void configure_rss(void) +{ + char command[256]; + + memset(command, 0, sizeof(command)); + snprintf(command, sizeof(command), "sudo ethtool -X %s equal %d", + ifname, start_queue); + 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, start_queue); + system(command); +} + +static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd, + struct netdev_queue_id *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_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.id) { + perror("id not present"); + goto err_close; + } + + printf("got dmabuf id=%d\n", rsp->id); + dmabuf_id = rsp->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_id *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 RSS to divert all traffic from our devmem queues */ + configure_rss(); + + /* Flow steer our devmem flows to start_queue */ + configure_flow_steering(); + + sleep(1); + + queues = malloc(sizeof(*queues) * num_queues); + + for (i = 0; i < num_queues; i++) { + queues[i]._present.type = 1; + queues[i]._present.id = 1; + queues[i].type = NETDEV_QUEUE_TYPE_RX; + queues[i].id = start_queue + i; + } + + if (bind_rx_queue(ifindex, buf, queues, num_queues, &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; +} + +void run_devmem_tests(void) +{ + struct netdev_queue_id *queues; + int devfd, memfd, buf; + struct ynl_sock *ys; + size_t dmabuf_size; + size_t i = 0; + + dmabuf_size = getpagesize() * NUM_PAGES; + + create_udmabuf(&devfd, &memfd, &buf, dmabuf_size); + + /* Configure RSS to divert all traffic from our devmem queues */ + configure_rss(); + + sleep(1); + + queues = malloc(sizeof(*queues) * num_queues); + + for (i = 0; i < num_queues; i++) { + queues[i]._present.type = 1; + queues[i]._present.id = 1; + queues[i].type = NETDEV_QUEUE_TYPE_RX; + queues[i].id = start_queue + i; + } + + if (bind_rx_queue(ifindex, buf, queues, num_queues, &ys)) + error(1, 0, "Failed to bind\n"); + + /* Closing the netlink socket does an implicit unbind */ + ynl_sock_destroy(ys); +} + +int main(int argc, char *argv[]) +{ + int is_server = 0, opt; + + while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:")) != -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': + num_queues = atoi(optarg); + break; + case 't': + start_queue = atoi(optarg); + break; + case 'f': + ifname = optarg; + break; + case '?': + printf("unknown option: %c\n", optopt); + break; + } + } + + ifindex = if_nametoindex(ifname); + + for (; optind < argc; optind++) + printf("extra arguments: %s\n", argv[optind]); + + run_devmem_tests(); + + if (is_server) + return do_server(); + + return 0; +}