diff options
30 files changed, 1007 insertions, 86 deletions
diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index f5e0750ab71d..c0ef6d0d7786 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -743,6 +743,18 @@ operations: - defer-hard-irqs - gro-flush-timeout - irq-suspend-timeout + - + name: bind-tx + doc: Bind dmabuf to netdev for TX + attribute-set: dmabuf + do: + request: + attributes: + - ifindex + - fd + reply: + attributes: + - id kernel-family: headers: [ "net/netdev_netlink.h"] diff --git a/Documentation/networking/devmem.rst b/Documentation/networking/devmem.rst index eb678ca45496..a6cd7236bfbd 100644 --- a/Documentation/networking/devmem.rst +++ b/Documentation/networking/devmem.rst @@ -62,15 +62,15 @@ More Info https://lore.kernel.org/netdev/20240831004313.3713467-1-almasrymina@google.com/ -Interface -========= +RX Interface +============ Example ------- -tools/testing/selftests/net/ncdevmem.c:do_server shows an example of setting up -the RX path of this API. +./tools/testing/selftests/drivers/net/hw/ncdevmem:do_server shows an example of +setting up the RX path of this API. NIC Setup @@ -235,6 +235,148 @@ can be less than the tokens provided by the user in case of: (a) an internal kernel leak bug. (b) the user passed more than 1024 frags. +TX Interface +============ + + +Example +------- + +./tools/testing/selftests/drivers/net/hw/ncdevmem:do_client shows an example of +setting up the TX path of this API. + + +NIC Setup +--------- + +The user must bind a TX dmabuf to a given NIC using the netlink API:: + + struct netdev_bind_tx_req *req = NULL; + struct netdev_bind_tx_rsp *rsp = NULL; + struct ynl_error yerr; + + *ys = ynl_sock_create(&ynl_netdev_family, &yerr); + + req = netdev_bind_tx_req_alloc(); + netdev_bind_tx_req_set_ifindex(req, ifindex); + netdev_bind_tx_req_set_fd(req, dmabuf_fd); + + rsp = netdev_bind_tx(*ys, req); + + tx_dmabuf_id = rsp->id; + + +The netlink API returns a dmabuf_id: a unique ID that refers to this dmabuf +that has been bound. + +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. + +Note that any reasonably well-behaved dmabuf from any exporter should work with +devmem TCP, even if the dmabuf is not actually backed by devmem. An example of +this is udmabuf, which wraps user memory (non-devmem) in a dmabuf. + +Socket Setup +------------ + +The user application must use MSG_ZEROCOPY flag when sending devmem TCP. Devmem +cannot be copied by the kernel, so the semantics of the devmem TX are similar +to the semantics of MSG_ZEROCOPY:: + + setsockopt(socket_fd, SOL_SOCKET, SO_ZEROCOPY, &opt, sizeof(opt)); + +It is also recommended that the user binds the TX socket to the same interface +the dma-buf has been bound to via SO_BINDTODEVICE:: + + setsockopt(socket_fd, SOL_SOCKET, SO_BINDTODEVICE, ifname, strlen(ifname) + 1); + + +Sending data +------------ + +Devmem data is sent using the SCM_DEVMEM_DMABUF cmsg. + +The user should create a msghdr where, + +* iov_base is set to the offset into the dmabuf to start sending from +* iov_len is set to the number of bytes to be sent from the dmabuf + +The user passes the dma-buf id to send from via the dmabuf_tx_cmsg.dmabuf_id. + +The example below sends 1024 bytes from offset 100 into the dmabuf, and 2048 +from offset 2000 into the dmabuf. The dmabuf to send from is tx_dmabuf_id:: + + char ctrl_data[CMSG_SPACE(sizeof(struct dmabuf_tx_cmsg))]; + struct dmabuf_tx_cmsg ddmabuf; + struct msghdr msg = {}; + struct cmsghdr *cmsg; + struct iovec iov[2]; + + iov[0].iov_base = (void*)100; + iov[0].iov_len = 1024; + iov[1].iov_base = (void*)2000; + iov[1].iov_len = 2048; + + msg.msg_iov = iov; + msg.msg_iovlen = 2; + + msg.msg_control = ctrl_data; + msg.msg_controllen = sizeof(ctrl_data); + + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_DEVMEM_DMABUF; + cmsg->cmsg_len = CMSG_LEN(sizeof(struct dmabuf_tx_cmsg)); + + ddmabuf.dmabuf_id = tx_dmabuf_id; + + *((struct dmabuf_tx_cmsg *)CMSG_DATA(cmsg)) = ddmabuf; + + sendmsg(socket_fd, &msg, MSG_ZEROCOPY); + + +Reusing TX dmabufs +------------------ + +Similar to MSG_ZEROCOPY with regular memory, the user should not modify the +contents of the dma-buf while a send operation is in progress. This is because +the kernel does not keep a copy of the dmabuf contents. Instead, the kernel +will pin and send data from the buffer available to the userspace. + +Just as in MSG_ZEROCOPY, the kernel notifies the userspace of send completions +using MSG_ERRQUEUE:: + + int64_t tstop = gettimeofday_ms() + waittime_ms; + char control[CMSG_SPACE(100)] = {}; + struct sock_extended_err *serr; + struct msghdr msg = {}; + struct cmsghdr *cm; + int retries = 10; + __u32 hi, lo; + + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + while (gettimeofday_ms() < tstop) { + if (!do_poll(fd)) continue; + + ret = recvmsg(fd, &msg, MSG_ERRQUEUE); + + for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) { + serr = (void *)CMSG_DATA(cm); + + hi = serr->ee_data; + lo = serr->ee_info; + + fprintf(stdout, "tx complete [%d,%d]\n", lo, hi); + } + } + +After the associated sendmsg has been completed, the dmabuf can be reused by +the userspace. + + Implementation & Caveats ======================== diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst index ca8605eb82ff..c69cc89c958e 100644 --- a/Documentation/networking/net_cachelines/net_device.rst +++ b/Documentation/networking/net_cachelines/net_device.rst @@ -10,6 +10,7 @@ Type Name fastpath_tx_acce =================================== =========================== =================== =================== =================================================================================== unsigned_long:32 priv_flags read_mostly __dev_queue_xmit(tx) unsigned_long:1 lltx read_mostly HARD_TX_LOCK,HARD_TX_TRYLOCK,HARD_TX_UNLOCK(tx) +unsigned long:1 netmem_tx:1; read_mostly char name[16] struct netdev_name_node* name_node struct dev_ifalias* ifalias diff --git a/Documentation/networking/netdev-features.rst b/Documentation/networking/netdev-features.rst index 5014f7cc1398..02bd7536fc0c 100644 --- a/Documentation/networking/netdev-features.rst +++ b/Documentation/networking/netdev-features.rst @@ -188,3 +188,8 @@ Redundancy) frames from one port to another in hardware. This should be set for devices which duplicate outgoing HSR (High-availability Seamless Redundancy) or PRP (Parallel Redundancy Protocol) tags automatically frames in hardware. + +* netmem-tx + +This should be set for devices which support netmem TX. See +Documentation/networking/netmem.rst diff --git a/Documentation/networking/netmem.rst b/Documentation/networking/netmem.rst index 7de21ddb5412..b63aded46337 100644 --- a/Documentation/networking/netmem.rst +++ b/Documentation/networking/netmem.rst @@ -19,8 +19,8 @@ Benefits of Netmem : * Simplified Development: Drivers interact with a consistent API, regardless of the underlying memory implementation. -Driver Requirements -=================== +Driver RX Requirements +====================== 1. The driver must support page_pool. @@ -77,3 +77,22 @@ Driver Requirements that purpose, but be mindful that some netmem types might have longer circulation times, such as when userspace holds a reference in zerocopy scenarios. + +Driver TX Requirements +====================== + +1. The Driver must not pass the netmem dma_addr to any of the dma-mapping APIs + directly. This is because netmem dma_addrs may come from a source like + dma-buf that is not compatible with the dma-mapping APIs. + + Helpers like netmem_dma_unmap_page_attrs() & netmem_dma_unmap_addr_set() + should be used in lieu of dma_unmap_page[_attrs](), dma_unmap_addr_set(). + The netmem variants will handle netmem dma_addrs correctly regardless of the + source, delegating to the dma-mapping APIs when appropriate. + + Not all dma-mapping APIs have netmem equivalents at the moment. If your + driver relies on a missing netmem API, feel free to add and propose to + netdev@, or reach out to the maintainers and/or almasrymina@google.com for + help adding the netmem API. + +2. Driver should declare support by setting `netdev->netmem_tx = true` diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 446e4b6fd3f1..e1ffbd561fac 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -2659,6 +2659,9 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto abort_with_wq; + if (!gve_is_gqi(priv) && !gve_is_qpl(priv)) + dev->netmem_tx = true; + err = register_netdev(dev); if (err) goto abort_with_gve_init; diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c index 2eba868d8037..a27f1574a733 100644 --- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c @@ -660,7 +660,8 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx, goto err; dma_unmap_len_set(pkt, len[pkt->num_bufs], len); - dma_unmap_addr_set(pkt, dma[pkt->num_bufs], addr); + netmem_dma_unmap_addr_set(skb_frag_netmem(frag), pkt, + dma[pkt->num_bufs], addr); ++pkt->num_bufs; gve_tx_fill_pkt_desc_dqo(tx, desc_idx, skb, len, addr, @@ -1038,8 +1039,9 @@ static void gve_unmap_packet(struct device *dev, dma_unmap_single(dev, dma_unmap_addr(pkt, dma[0]), dma_unmap_len(pkt, len[0]), DMA_TO_DEVICE); for (i = 1; i < pkt->num_bufs; i++) { - dma_unmap_page(dev, dma_unmap_addr(pkt, dma[i]), - dma_unmap_len(pkt, len[i]), DMA_TO_DEVICE); + netmem_dma_unmap_page_attrs(dev, dma_unmap_addr(pkt, dma[i]), + dma_unmap_len(pkt, len[i]), + DMA_TO_DEVICE, 0); } pkt->num_bufs = 0; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 773167508c82..32a1e41636a9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1772,6 +1772,7 @@ enum netdev_reg_state { * @lltx: device supports lockless Tx. Deprecated for real HW * drivers. Mainly used by logical interfaces, such as * bonding and tunnels + * @netmem_tx: device support netmem_tx. * * @name: This is the first field of the "visible" part of this structure * (i.e. as seen by users in the "Space.c" file). It is the name @@ -2087,6 +2088,7 @@ struct net_device { struct_group(priv_flags_fast, unsigned long priv_flags:32; unsigned long lltx:1; + unsigned long netmem_tx:1; ); const struct net_device_ops *netdev_ops; const struct header_ops *header_ops; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f3e72be6f634..c7397b17bb08 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1707,13 +1707,16 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, - struct ubuf_info *uarg); + struct ubuf_info *uarg, bool devmem); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); +struct net_devmem_dmabuf_binding; + int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, - size_t length); + size_t length, + struct net_devmem_dmabuf_binding *binding); int zerocopy_fill_skb_from_iter(struct sk_buff *skb, struct iov_iter *from, size_t length); @@ -1721,12 +1724,14 @@ int zerocopy_fill_skb_from_iter(struct sk_buff *skb, static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { - return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len); + return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len, + NULL); } int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, - struct ubuf_info *uarg); + struct ubuf_info *uarg, + struct net_devmem_dmabuf_binding *binding); /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) @@ -3697,6 +3702,10 @@ static inline dma_addr_t __skb_frag_dma_map(struct device *dev, size_t offset, size_t size, enum dma_data_direction dir) { + if (skb_frag_is_net_iov(frag)) { + return netmem_to_net_iov(frag->netmem)->dma_addr + offset + + frag->offset; + } return dma_map_page(dev, skb_frag_page(frag), skb_frag_off(frag) + offset, size, dir); } diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h index 0f3c58007488..9e49372ef1a0 100644 --- a/include/linux/skbuff_ref.h +++ b/include/linux/skbuff_ref.h @@ -17,7 +17,7 @@ */ static inline void __skb_frag_ref(skb_frag_t *frag) { - get_page(skb_frag_page(frag)); + get_netmem(skb_frag_netmem(frag)); } /** @@ -40,7 +40,7 @@ static inline void skb_page_unref(netmem_ref netmem, bool recycle) if (recycle && napi_pp_put_page(netmem)) return; #endif - put_page(netmem_to_page(netmem)); + put_netmem(netmem); } /** diff --git a/include/net/netmem.h b/include/net/netmem.h index c61d5b21e7b4..386164fb9c18 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -8,6 +8,7 @@ #ifndef _NET_NETMEM_H #define _NET_NETMEM_H +#include <linux/dma-mapping.h> #include <linux/mm.h> #include <net/net_debug.h> @@ -20,8 +21,17 @@ DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers); */ #define NET_IOV 0x01UL +enum net_iov_type { + NET_IOV_DMABUF, + NET_IOV_IOURING, + + /* Force size to unsigned long to make the NET_IOV_ASSERTS below pass. + */ + NET_IOV_MAX = ULONG_MAX +}; + struct net_iov { - unsigned long __unused_padding; + enum net_iov_type type; unsigned long pp_magic; struct page_pool *pp; struct net_iov_area *owner; @@ -264,4 +274,26 @@ static inline unsigned long netmem_get_dma_addr(netmem_ref netmem) return __netmem_clear_lsb(netmem)->dma_addr; } +void get_netmem(netmem_ref netmem); +void put_netmem(netmem_ref netmem); + +#define netmem_dma_unmap_addr_set(NETMEM, PTR, ADDR_NAME, VAL) \ + do { \ + if (!netmem_is_net_iov(NETMEM)) \ + dma_unmap_addr_set(PTR, ADDR_NAME, VAL); \ + else \ + dma_unmap_addr_set(PTR, ADDR_NAME, 0); \ + } while (0) + +static inline void netmem_dma_unmap_page_attrs(struct device *dev, + dma_addr_t addr, size_t size, + enum dma_data_direction dir, + unsigned long attrs) +{ + if (!addr) + return; + + dma_unmap_page_attrs(dev, addr, size, dir, attrs); +} + #endif /* _NET_NETMEM_H */ diff --git a/include/net/sock.h b/include/net/sock.h index f0fabb9fd28a..3e15d7105ad2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1851,6 +1851,7 @@ struct sockcm_cookie { u32 tsflags; u32 ts_opt_id; u32 priority; + u32 dmabuf_id; }; static inline void sockcm_init(struct sockcm_cookie *sockc, diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 7600bf62dbdf..7eb9571786b8 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -219,6 +219,7 @@ enum { NETDEV_CMD_QSTATS_GET, NETDEV_CMD_BIND_RX, NETDEV_CMD_NAPI_SET, + NETDEV_CMD_BIND_TX, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index fe86606b9f30..0c64129f5d50 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -259,6 +259,7 @@ static int io_zcrx_create_area(struct io_zcrx_ifq *ifq, niov->owner = &area->nia; area->freelist[i] = i; atomic_set(&area->user_refs[i], 0); + niov->type = NET_IOV_IOURING; } area->free_count = nr_iovs; @@ -809,7 +810,7 @@ static int io_zcrx_recv_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq, return io_zcrx_copy_frag(req, ifq, frag, off, len); niov = netmem_to_net_iov(frag->netmem); - if (niov->pp->mp_ops != &io_uring_pp_zc_ops || + if (!niov->pp || niov->pp->mp_ops != &io_uring_pp_zc_ops || io_pp_to_ifq(niov->pp) != ifq) return -EFAULT; diff --git a/net/core/datagram.c b/net/core/datagram.c index f0634f0cb834..9ef5442536f5 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -63,6 +63,8 @@ #include <net/busy_poll.h> #include <crypto/hash.h> +#include "devmem.h" + /* * Is a socket 'connection oriented' ? */ @@ -691,9 +693,49 @@ int zerocopy_fill_skb_from_iter(struct sk_buff *skb, return 0; } +static int +zerocopy_fill_skb_from_devmem(struct sk_buff *skb, struct iov_iter *from, + int length, + struct net_devmem_dmabuf_binding *binding) +{ + int i = skb_shinfo(skb)->nr_frags; + size_t virt_addr, size, off; + struct net_iov *niov; + + /* Devmem filling works by taking an IOVEC from the user where the + * iov_addrs are interpreted as an offset in bytes into the dma-buf to + * send from. We do not support other iter types. + */ + if (iov_iter_type(from) != ITER_IOVEC) + return -EFAULT; + + while (length && iov_iter_count(from)) { + if (i == MAX_SKB_FRAGS) + return -EMSGSIZE; + + virt_addr = (size_t)iter_iov_addr(from); + niov = net_devmem_get_niov_at(binding, virt_addr, &off, &size); + if (!niov) + return -EFAULT; + + size = min_t(size_t, size, length); + size = min_t(size_t, size, iter_iov_len(from)); + + get_netmem(net_iov_to_netmem(niov)); + skb_add_rx_frag_netmem(skb, i, net_iov_to_netmem(niov), off, + size, PAGE_SIZE); + iov_iter_advance(from, size); + length -= size; + i++; + } + + return 0; +} + int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, - size_t length) + size_t length, + struct net_devmem_dmabuf_binding *binding) { unsigned long orig_size = skb->truesize; unsigned long truesize; @@ -701,6 +743,8 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, if (msg && msg->msg_ubuf && msg->sg_from_iter) ret = msg->sg_from_iter(skb, from, length); + else if (binding) + ret = zerocopy_fill_skb_from_devmem(skb, from, length, binding); else ret = zerocopy_fill_skb_from_iter(skb, from, length); @@ -734,7 +778,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) if (skb_copy_datagram_from_iter(skb, 0, from, copy)) return -EFAULT; - return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U); + return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U, NULL); } EXPORT_SYMBOL(zerocopy_sg_from_iter); diff --git a/net/core/dev.c b/net/core/dev.c index c9013632296f..33d5e95209cb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3896,12 +3896,42 @@ sw_checksum: } EXPORT_SYMBOL(skb_csum_hwoffload_help); +static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb, + struct net_device *dev) +{ + struct skb_shared_info *shinfo; + struct net_iov *niov; + + if (likely(skb_frags_readable(skb))) + goto out; + + if (!dev->netmem_tx) + goto out_free; + + shinfo = skb_shinfo(skb); + + if (shinfo->nr_frags > 0) { + niov = netmem_to_net_iov(skb_frag_netmem(&shinfo->frags[0])); + if (net_is_devmem_iov(niov) && + net_devmem_iov_binding(niov)->dev != dev) + goto out_free; + } + +out: + return skb; + +out_free: + kfree_skb(skb); + return NULL; +} + static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again) { netdev_features_t features; - if (!skb_frags_readable(skb)) - goto out_kfree_skb; + skb = validate_xmit_unreadable_skb(skb, dev); + if (unlikely(!skb)) + goto out_null; features = netif_skb_features(skb); skb = validate_xmit_vlan(skb, features); diff --git a/net/core/devmem.c b/net/core/devmem.c index 6e27a47d0493..88065e5ef651 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -16,6 +16,7 @@ #include <net/netdev_rx_queue.h> #include <net/page_pool/helpers.h> #include <net/page_pool/memory_provider.h> +#include <net/sock.h> #include <trace/events/page_pool.h> #include "devmem.h" @@ -30,7 +31,7 @@ static const struct memory_provider_ops dmabuf_devmem_ops; bool net_is_devmem_iov(struct net_iov *niov) { - return niov->pp->mp_ops == &dmabuf_devmem_ops; + return niov->type == NET_IOV_DMABUF; } static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool, @@ -52,8 +53,10 @@ static dma_addr_t net_devmem_get_dma_addr(const struct net_iov *niov) ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT); } -void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) +void __net_devmem_dmabuf_binding_free(struct work_struct *wq) { + struct net_devmem_dmabuf_binding *binding = container_of(wq, typeof(*binding), unbind_w); + size_t size, avail; gen_pool_for_each_chunk(binding->chunk_pool, @@ -71,8 +74,10 @@ void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) dma_buf_detach(binding->dmabuf, binding->attachment); dma_buf_put(binding->dmabuf); xa_destroy(&binding->bound_rxqs); + kvfree(binding->tx_vec); kfree(binding); } +EXPORT_SYMBOL(__net_devmem_dmabuf_binding_free); struct net_iov * net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding) @@ -117,6 +122,13 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) unsigned long xa_idx; unsigned int rxq_idx; + xa_erase(&net_devmem_dmabuf_bindings, binding->id); + + /* Ensure no tx net_devmem_lookup_dmabuf() are in flight after the + * erase. + */ + synchronize_net(); + if (binding->list.next) list_del(&binding->list); @@ -131,8 +143,6 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) __net_mp_close_rxq(binding->dev, rxq_idx, &mp_params); } - xa_erase(&net_devmem_dmabuf_bindings, binding->id); - net_devmem_dmabuf_binding_put(binding); } @@ -166,8 +176,9 @@ err_close_rxq: } struct net_devmem_dmabuf_binding * -net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, - struct netlink_ext_ack *extack) +net_devmem_bind_dmabuf(struct net_device *dev, + enum dma_data_direction direction, + unsigned int dmabuf_fd, struct netlink_ext_ack *extack) { struct net_devmem_dmabuf_binding *binding; static u32 id_alloc_next; @@ -189,13 +200,6 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, } 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); @@ -206,26 +210,36 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, if (IS_ERR(binding->attachment)) { err = PTR_ERR(binding->attachment); NL_SET_ERR_MSG(extack, "Failed to bind dmabuf to device"); - goto err_free_id; + goto err_free_binding; } binding->sgt = dma_buf_map_attachment_unlocked(binding->attachment, - DMA_FROM_DEVICE); + direction); if (IS_ERR(binding->sgt)) { err = PTR_ERR(binding->sgt); NL_SET_ERR_MSG(extack, "Failed to map dmabuf attachment"); goto err_detach; } + if (direction == DMA_TO_DEVICE) { + binding->tx_vec = kvmalloc_array(dmabuf->size / PAGE_SIZE, + sizeof(struct net_iov *), + GFP_KERNEL); + if (!binding->tx_vec) { + err = -ENOMEM; + goto err_unmap; + } + } + /* 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)); + binding->chunk_pool = gen_pool_create(PAGE_SHIFT, + dev_to_node(&dev->dev)); if (!binding->chunk_pool) { err = -ENOMEM; - goto err_unmap; + goto err_tx_vec; } virtual = 0; @@ -266,27 +280,36 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, for (i = 0; i < owner->area.num_niovs; i++) { niov = &owner->area.niovs[i]; + niov->type = NET_IOV_DMABUF; niov->owner = &owner->area; page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov), net_devmem_get_dma_addr(niov)); + if (direction == DMA_TO_DEVICE) + binding->tx_vec[owner->area.base_virtual / PAGE_SIZE + i] = niov; } virtual += len; } + 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_chunks; + 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_tx_vec: + kvfree(binding->tx_vec); 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: @@ -294,6 +317,74 @@ err_put_dmabuf: return ERR_PTR(err); } +struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id) +{ + struct net_devmem_dmabuf_binding *binding; + + rcu_read_lock(); + binding = xa_load(&net_devmem_dmabuf_bindings, id); + if (binding) { + if (!net_devmem_dmabuf_binding_get(binding)) + binding = NULL; + } + rcu_read_unlock(); + + return binding; +} + +void net_devmem_get_net_iov(struct net_iov *niov) +{ + net_devmem_dmabuf_binding_get(net_devmem_iov_binding(niov)); +} + +void net_devmem_put_net_iov(struct net_iov *niov) +{ + net_devmem_dmabuf_binding_put(net_devmem_iov_binding(niov)); +} + +struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk, + unsigned int dmabuf_id) +{ + struct net_devmem_dmabuf_binding *binding; + struct dst_entry *dst = __sk_dst_get(sk); + int err = 0; + + binding = net_devmem_lookup_dmabuf(dmabuf_id); + if (!binding || !binding->tx_vec) { + err = -EINVAL; + goto out_err; + } + + /* The dma-addrs in this binding are only reachable to the corresponding + * net_device. + */ + if (!dst || !dst->dev || dst->dev->ifindex != binding->dev->ifindex) { + err = -ENODEV; + goto out_err; + } + + return binding; + +out_err: + if (binding) + net_devmem_dmabuf_binding_put(binding); + + return ERR_PTR(err); +} + +struct net_iov * +net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding, + size_t virt_addr, size_t *off, size_t *size) +{ + if (virt_addr >= binding->dmabuf->size) + return NULL; + + *off = virt_addr % PAGE_SIZE; + *size = PAGE_SIZE - *off; + + return binding->tx_vec[virt_addr / PAGE_SIZE]; +} + /*** "Dmabuf devmem memory provider" ***/ int mp_dmabuf_devmem_init(struct page_pool *pool) diff --git a/net/core/devmem.h b/net/core/devmem.h index 7fc158d52729..919e6ed28fdc 100644 --- a/net/core/devmem.h +++ b/net/core/devmem.h @@ -23,12 +23,20 @@ struct net_devmem_dmabuf_binding { /* 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. + * a ref to keep the binding alive. The page_pool does not release the + * ref until all the net_iovs allocated from this binding are released + * back to the page_pool. * * 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. + * + * net_devmem_get_net_iov() on dmabuf net_iovs will increment this + * reference, making sure that the binding remains alive until all the + * net_iovs are no longer used. net_iovs allocated from this binding + * that are stuck in the TX path for any reason (such as awaiting + * retransmits) hold a reference to the binding until the skb holding + * them is freed. */ refcount_t ref; @@ -44,6 +52,14 @@ struct net_devmem_dmabuf_binding { * active. */ u32 id; + + /* Array of net_iov pointers for this binding, sorted by virtual + * address. This array is convenient to map the virtual addresses to + * net_iovs in the TX path. + */ + struct net_iov **tx_vec; + + struct work_struct unbind_w; }; #if defined(CONFIG_NET_DEVMEM) @@ -60,14 +76,17 @@ struct dmabuf_genpool_chunk_owner { dma_addr_t base_dma_addr; }; -void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding); +void __net_devmem_dmabuf_binding_free(struct work_struct *wq); struct net_devmem_dmabuf_binding * -net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, - struct netlink_ext_ack *extack); +net_devmem_bind_dmabuf(struct net_device *dev, + enum dma_data_direction direction, + unsigned int dmabuf_fd, struct netlink_ext_ack *extack); +struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id); 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, struct netlink_ext_ack *extack); +void net_devmem_bind_tx_release(struct sock *sk); static inline struct dmabuf_genpool_chunk_owner * net_devmem_iov_to_chunk_owner(const struct net_iov *niov) @@ -96,10 +115,10 @@ static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov) ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT); } -static inline void +static inline bool net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding) { - refcount_inc(&binding->ref); + return refcount_inc_not_zero(&binding->ref); } static inline void @@ -108,30 +127,57 @@ 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); + INIT_WORK(&binding->unbind_w, __net_devmem_dmabuf_binding_free); + schedule_work(&binding->unbind_w); } +void net_devmem_get_net_iov(struct net_iov *niov); +void net_devmem_put_net_iov(struct net_iov *niov); + struct net_iov * net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding); void net_devmem_free_dmabuf(struct net_iov *ppiov); bool net_is_devmem_iov(struct net_iov *niov); +struct net_devmem_dmabuf_binding * +net_devmem_get_binding(struct sock *sk, unsigned int dmabuf_id); +struct net_iov * +net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding, size_t addr, + size_t *off, size_t *size); #else struct net_devmem_dmabuf_binding; static inline void -__net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) +net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding) +{ +} + +static inline void net_devmem_get_net_iov(struct net_iov *niov) +{ +} + +static inline void net_devmem_put_net_iov(struct net_iov *niov) +{ +} + +static inline void __net_devmem_dmabuf_binding_free(struct work_struct *wq) { } static inline struct net_devmem_dmabuf_binding * net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, + enum dma_data_direction direction, struct netlink_ext_ack *extack) { return ERR_PTR(-EOPNOTSUPP); } +static inline struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id) +{ + return NULL; +} + static inline void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) { @@ -170,6 +216,25 @@ static inline bool net_is_devmem_iov(struct net_iov *niov) { return false; } + +static inline struct net_devmem_dmabuf_binding * +net_devmem_get_binding(struct sock *sk, unsigned int dmabuf_id) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline struct net_iov * +net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding, size_t addr, + size_t *off, size_t *size) +{ + return NULL; +} + +static inline struct net_devmem_dmabuf_binding * +net_devmem_iov_binding(const struct net_iov *niov) +{ + return NULL; +} #endif #endif /* _NET_DEVMEM_H */ diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 739f7b6506a6..4fc44587f493 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -99,6 +99,12 @@ static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_IRQ_SUSPE [NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT] = { .type = NLA_UINT, }, }; +/* NETDEV_CMD_BIND_TX - do */ +static const struct nla_policy netdev_bind_tx_nl_policy[NETDEV_A_DMABUF_FD + 1] = { + [NETDEV_A_DMABUF_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), + [NETDEV_A_DMABUF_FD] = { .type = NLA_U32, }, +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -190,6 +196,13 @@ static const struct genl_split_ops netdev_nl_ops[] = { .maxattr = NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, + { + .cmd = NETDEV_CMD_BIND_TX, + .doit = netdev_nl_bind_tx_doit, + .policy = netdev_bind_tx_nl_policy, + .maxattr = NETDEV_A_DMABUF_FD, + .flags = GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index 17d39fd64c94..cf3fad74511f 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -34,6 +34,7 @@ int netdev_nl_qstats_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_set_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 17aa9e42e8d5..cfcf1654d4fb 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -907,7 +907,8 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) goto err_unlock; } - binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, info->extack); + binding = net_devmem_bind_dmabuf(netdev, DMA_FROM_DEVICE, dmabuf_fd, + info->extack); if (IS_ERR(binding)) { err = PTR_ERR(binding); goto err_unlock; @@ -968,6 +969,83 @@ err_genlmsg_free: return err; } +int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct net_devmem_dmabuf_binding *binding; + struct netdev_nl_sock *priv; + struct net_device *netdev; + u32 ifindex, dmabuf_fd; + struct sk_buff *rsp; + int err = 0; + void *hdr; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_FD)) + return -EINVAL; + + ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); + dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]); + + priv = genl_sk_priv_get(&netdev_nl_family, NETLINK_CB(skb).sk); + if (IS_ERR(priv)) + return PTR_ERR(priv); + + 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; + } + + mutex_lock(&priv->lock); + + netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex); + if (!netdev) { + err = -ENODEV; + goto err_unlock_sock; + } + + if (!netif_device_present(netdev)) { + err = -ENODEV; + goto err_unlock_netdev; + } + + if (!netdev->netmem_tx) { + err = -EOPNOTSUPP; + NL_SET_ERR_MSG(info->extack, + "Driver does not support netmem TX"); + goto err_unlock_netdev; + } + + binding = net_devmem_bind_dmabuf(netdev, DMA_TO_DEVICE, dmabuf_fd, + info->extack); + if (IS_ERR(binding)) { + err = PTR_ERR(binding); + goto err_unlock_netdev; + } + + list_add(&binding->list, &priv->bindings); + + nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id); + genlmsg_end(rsp, hdr); + + netdev_unlock(netdev); + mutex_unlock(&priv->lock); + + return genlmsg_reply(rsp, info); + +err_unlock_netdev: + netdev_unlock(netdev); +err_unlock_sock: + mutex_unlock(&priv->lock); +err_genlmsg_free: + nlmsg_free(rsp); + return err; +} + void netdev_nl_sock_priv_init(struct netdev_nl_sock *priv) { INIT_LIST_HEAD(&priv->bindings); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d73ad79fe739..4159107f1666 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -89,6 +89,7 @@ #include <linux/textsearch.h> #include "dev.h" +#include "devmem.h" #include "netmem_priv.h" #include "sock_destructor.h" @@ -1654,7 +1655,8 @@ void mm_unaccount_pinned_pages(struct mmpin *mmp) } EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages); -static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) +static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size, + bool devmem) { struct ubuf_info_msgzc *uarg; struct sk_buff *skb; @@ -1669,7 +1671,7 @@ static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) uarg = (void *)skb->cb; uarg->mmp.user = NULL; - if (mm_account_pinned_pages(&uarg->mmp, size)) { + if (likely(!devmem) && mm_account_pinned_pages(&uarg->mmp, size)) { kfree_skb(skb); return NULL; } @@ -1692,7 +1694,7 @@ static inline struct sk_buff *skb_from_uarg(struct ubuf_info_msgzc *uarg) } struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, - struct ubuf_info *uarg) + struct ubuf_info *uarg, bool devmem) { if (uarg) { struct ubuf_info_msgzc *uarg_zc; @@ -1722,7 +1724,8 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, next = (u32)atomic_read(&sk->sk_zckey); if ((u32)(uarg_zc->id + uarg_zc->len) == next) { - if (mm_account_pinned_pages(&uarg_zc->mmp, size)) + if (likely(!devmem) && + mm_account_pinned_pages(&uarg_zc->mmp, size)) return NULL; uarg_zc->len++; uarg_zc->bytelen = bytelen; @@ -1737,7 +1740,7 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, } new_alloc: - return msg_zerocopy_alloc(sk, size); + return msg_zerocopy_alloc(sk, size, devmem); } EXPORT_SYMBOL_GPL(msg_zerocopy_realloc); @@ -1841,7 +1844,8 @@ EXPORT_SYMBOL_GPL(msg_zerocopy_ubuf_ops); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, - struct ubuf_info *uarg) + struct ubuf_info *uarg, + struct net_devmem_dmabuf_binding *binding) { int err, orig_len = skb->len; @@ -1860,7 +1864,8 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, return -EEXIST; } - err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len); + err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len, + binding); if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { struct sock *save_sk = skb->sk; @@ -7313,3 +7318,32 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, return false; } EXPORT_SYMBOL(csum_and_copy_from_iter_full); + +void get_netmem(netmem_ref netmem) +{ + struct net_iov *niov; + + if (netmem_is_net_iov(netmem)) { + niov = netmem_to_net_iov(netmem); + if (net_is_devmem_iov(niov)) + net_devmem_get_net_iov(netmem_to_net_iov(netmem)); + return; + } + get_page(netmem_to_page(netmem)); +} +EXPORT_SYMBOL(get_netmem); + +void put_netmem(netmem_ref netmem) +{ + struct net_iov *niov; + + if (netmem_is_net_iov(netmem)) { + niov = netmem_to_net_iov(netmem); + if (net_is_devmem_iov(niov)) + net_devmem_put_net_iov(netmem_to_net_iov(netmem)); + return; + } + + put_page(netmem_to_page(netmem)); +} +EXPORT_SYMBOL(put_netmem); diff --git a/net/core/sock.c b/net/core/sock.c index b64df2463300..347ce75482f5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3018,6 +3018,11 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, return -EPERM; sockc->priority = *(u32 *)CMSG_DATA(cmsg); break; + case SCM_DEVMEM_DMABUF: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) + return -EINVAL; + sockc->dmabuf_id = *(u32 *)CMSG_DATA(cmsg); + break; default: return -EINVAL; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 6e18d7ec5062..a2705d454fd6 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1014,7 +1014,8 @@ static int __ip_append_data(struct sock *sk, uarg = msg->msg_ubuf; } } else if (sock_flag(sk, SOCK_ZEROCOPY)) { - uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); + uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb), + false); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 86c427f16636..0ae265d39184 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1059,6 +1059,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) { + struct net_devmem_dmabuf_binding *binding = NULL; struct tcp_sock *tp = tcp_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; @@ -1066,11 +1067,23 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; int process_backlog = 0; + bool sockc_valid = true; int zc = 0; long timeo; flags = msg->msg_flags; + sockc = (struct sockcm_cookie){ .tsflags = READ_ONCE(sk->sk_tsflags) }; + if (msg->msg_controllen) { + err = sock_cmsg_send(sk, msg, &sockc); + if (unlikely(err)) + /* Don't return error until MSG_FASTOPEN has been + * processed; that may succeed even if the cmsg is + * invalid. + */ + sockc_valid = false; + } + if ((flags & MSG_ZEROCOPY) && size) { if (msg->msg_ubuf) { uarg = msg->msg_ubuf; @@ -1078,7 +1091,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) zc = MSG_ZEROCOPY; } else if (sock_flag(sk, SOCK_ZEROCOPY)) { skb = tcp_write_queue_tail(sk); - uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb)); + uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb), + sockc_valid && !!sockc.dmabuf_id); if (!uarg) { err = -ENOBUFS; goto out_err; @@ -1087,12 +1101,27 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) zc = MSG_ZEROCOPY; else uarg_to_msgzc(uarg)->zerocopy = 0; + + if (sockc_valid && sockc.dmabuf_id) { + binding = net_devmem_get_binding(sk, sockc.dmabuf_id); + if (IS_ERR(binding)) { + err = PTR_ERR(binding); + binding = NULL; + goto out_err; + } + } } } else if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES) && size) { if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_SPLICE_PAGES; } + if (sockc_valid && sockc.dmabuf_id && + (!(flags & MSG_ZEROCOPY) || !sock_flag(sk, SOCK_ZEROCOPY))) { + err = -EINVAL; + goto out_err; + } + if (unlikely(flags & MSG_FASTOPEN || inet_test_bit(DEFER_CONNECT, sk)) && !tp->repair) { @@ -1131,13 +1160,10 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) /* 'common' sending to sendq */ } - sockc = (struct sockcm_cookie) { .tsflags = READ_ONCE(sk->sk_tsflags)}; - if (msg->msg_controllen) { - err = sock_cmsg_send(sk, msg, &sockc); - if (unlikely(err)) { + if (!sockc_valid) { + if (!err) err = -EINVAL; - goto out_err; - } + goto out_err; } /* This should be in poll */ @@ -1258,7 +1284,8 @@ new_segment: goto wait_for_space; } - err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); + err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg, + binding); if (err == -EMSGSIZE || err == -EEXIST) { tcp_mark_push(tp, skb); goto new_segment; @@ -1339,6 +1366,8 @@ out_nopush: /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */ if (uarg && !msg->msg_ubuf) net_zcopy_put(uarg); + if (binding) + net_devmem_dmabuf_binding_put(binding); return copied + copied_syn; do_error: @@ -1356,6 +1385,9 @@ out_err: sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } + if (binding) + net_devmem_dmabuf_binding_put(binding); + return err; } EXPORT_SYMBOL_GPL(tcp_sendmsg_locked); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ef052ccd9380..7bd29a9ff0db 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1524,7 +1524,8 @@ emsgsize: uarg = msg->msg_ubuf; } } else if (sock_flag(sk, SOCK_ZEROCOPY)) { - uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); + uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb), + false); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 7f7de6d88096..6e7b727c781c 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -87,7 +87,7 @@ static int virtio_transport_init_zcopy_skb(struct vsock_sock *vsk, uarg = msg_zerocopy_realloc(sk_vsock(vsk), iter->count, - NULL); + NULL, false); if (!uarg) return -1; @@ -107,8 +107,7 @@ static int virtio_transport_fill_skb(struct sk_buff *skb, { if (zcopy) return __zerocopy_sg_from_iter(info->msg, NULL, skb, - &info->msg->msg_iter, - len); + &info->msg->msg_iter, len, NULL); return memcpy_from_msg(skb_put(skb, len), info->msg, len); } diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 7600bf62dbdf..7eb9571786b8 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -219,6 +219,7 @@ enum { NETDEV_CMD_QSTATS_GET, NETDEV_CMD_BIND_RX, NETDEV_CMD_NAPI_SET, + NETDEV_CMD_BIND_TX, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py index 3947e9157115..7fc686cf47a2 100755 --- a/tools/testing/selftests/drivers/net/hw/devmem.py +++ b/tools/testing/selftests/drivers/net/hw/devmem.py @@ -1,6 +1,7 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 +from os import path from lib.py import ksft_run, ksft_exit from lib.py import ksft_eq, KsftSkipEx from lib.py import NetDrvEpEnv @@ -10,8 +11,7 @@ from lib.py import ksft_disruptive def require_devmem(cfg): if not hasattr(cfg, "_devmem_probed"): - port = rand_port() - probe_command = f"./ncdevmem -f {cfg.ifname}" + probe_command = f"{cfg.bin_local} -f {cfg.ifname}" cfg._devmem_supported = cmd(probe_command, fail=False, shell=True).ret == 0 cfg._devmem_probed = True @@ -25,7 +25,7 @@ def check_rx(cfg) -> None: require_devmem(cfg) port = rand_port() - listen_cmd = f"./ncdevmem -l -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port}" + listen_cmd = f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port}" with bkg(listen_cmd) as socat: wait_port_listen(port) @@ -34,9 +34,27 @@ def check_rx(cfg) -> None: ksft_eq(socat.stdout.strip(), "hello\nworld") +@ksft_disruptive +def check_tx(cfg) -> None: + cfg.require_ipver("6") + require_devmem(cfg) + + port = rand_port() + listen_cmd = f"socat -U - TCP6-LISTEN:{port}" + + with bkg(listen_cmd, exit_wait=True) as socat: + wait_port_listen(port) + cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_remote} -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port}", host=cfg.remote, shell=True) + + ksft_eq(socat.stdout.strip(), "hello\nworld") + + def main() -> None: with NetDrvEpEnv(__file__) as cfg: - ksft_run([check_rx], + cfg.bin_local = path.abspath(path.dirname(__file__) + "/ncdevmem") + cfg.bin_remote = cfg.remote.deploy(cfg.bin_local) + + ksft_run([check_rx, check_tx], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index 2bf14ac2b8c6..f801a1b3545f 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -9,22 +9,31 @@ * ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201 * * On client: - * echo -n "hello\nworld" | nc -s <server IP> 5201 -p 5201 + * echo -n "hello\nworld" | \ + * ncdevmem -s <server IP> [-c <client IP>] -p 5201 -f eth1 * - * Test data validation: + * 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. + * + * Test data validation (devmem TCP on RX only): * * 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 | \ + * head -c 1G | \ * nc <server IP> 5201 -p 5201 * + * Test data validation (devmem TCP on RX and TX, validation happens on RX): * - * 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. + * On server: + * ncdevmem -s <server IP> [-c <client IP>] -l -p 5201 -v 8 -f eth1 + * + * On client: + * yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06\\x07) | \ + * head -c 1M | \ + * ncdevmem -s <server IP> [-c <client IP>] -p 5201 -f eth1 */ #define _GNU_SOURCE #define __EXPORTED_HEADERS__ @@ -40,15 +49,18 @@ #include <fcntl.h> #include <malloc.h> #include <error.h> +#include <poll.h> #include <arpa/inet.h> #include <sys/socket.h> #include <sys/mman.h> #include <sys/ioctl.h> #include <sys/syscall.h> +#include <sys/time.h> #include <linux/memfd.h> #include <linux/dma-buf.h> +#include <linux/errqueue.h> #include <linux/udmabuf.h> #include <linux/types.h> #include <linux/netlink.h> @@ -79,6 +91,8 @@ static int num_queues = -1; static char *ifname; static unsigned int ifindex; static unsigned int dmabuf_id; +static uint32_t tx_dmabuf_id; +static int waittime_ms = 500; struct memory_buffer { int fd; @@ -92,6 +106,8 @@ struct memory_buffer { struct memory_provider { struct memory_buffer *(*alloc)(size_t size); void (*free)(struct memory_buffer *ctx); + void (*memcpy_to_device)(struct memory_buffer *dst, size_t off, + void *src, int n); void (*memcpy_from_device)(void *dst, struct memory_buffer *src, size_t off, int n); }; @@ -152,6 +168,20 @@ static void udmabuf_free(struct memory_buffer *ctx) free(ctx); } +static void udmabuf_memcpy_to_device(struct memory_buffer *dst, size_t off, + void *src, int n) +{ + struct dma_buf_sync sync = {}; + + sync.flags = DMA_BUF_SYNC_START | DMA_BUF_SYNC_WRITE; + ioctl(dst->fd, DMA_BUF_IOCTL_SYNC, &sync); + + memcpy(dst->buf_mem + off, src, n); + + sync.flags = DMA_BUF_SYNC_END | DMA_BUF_SYNC_WRITE; + ioctl(dst->fd, DMA_BUF_IOCTL_SYNC, &sync); +} + static void udmabuf_memcpy_from_device(void *dst, struct memory_buffer *src, size_t off, int n) { @@ -169,6 +199,7 @@ static void udmabuf_memcpy_from_device(void *dst, struct memory_buffer *src, static struct memory_provider udmabuf_memory_provider = { .alloc = udmabuf_alloc, .free = udmabuf_free, + .memcpy_to_device = udmabuf_memcpy_to_device, .memcpy_from_device = udmabuf_memcpy_from_device, }; @@ -187,14 +218,16 @@ void validate_buffer(void *line, size_t size) { static unsigned char seed = 1; unsigned char *ptr = line; - int errors = 0; + unsigned char expected; + static int errors; size_t i; for (i = 0; i < size; i++) { - if (ptr[i] != seed) { + expected = seed ? seed : '\n'; + if (ptr[i] != expected) { fprintf(stderr, "Failed validation: expected=%u, actual=%u, index=%lu\n", - seed, ptr[i], i); + expected, ptr[i], i); errors++; if (errors > 20) error(1, 0, "validation failed."); @@ -393,6 +426,49 @@ err_close: return -1; } +static int bind_tx_queue(unsigned int ifindex, unsigned int dmabuf_fd, + struct ynl_sock **ys) +{ + struct netdev_bind_tx_req *req = NULL; + struct netdev_bind_tx_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_tx_req_alloc(); + netdev_bind_tx_req_set_ifindex(req, ifindex); + netdev_bind_tx_req_set_fd(req, dmabuf_fd); + + rsp = netdev_bind_tx(*ys, req); + if (!rsp) { + perror("netdev_bind_tx"); + goto err_close; + } + + if (!rsp->_present.id) { + perror("id not present"); + goto err_close; + } + + fprintf(stderr, "got tx dmabuf id=%d\n", rsp->id); + tx_dmabuf_id = rsp->id; + + netdev_bind_tx_req_free(req); + netdev_bind_tx_rsp_free(rsp); + + return 0; + +err_close: + fprintf(stderr, "YNL failed: %s\n", (*ys)->err.msg); + netdev_bind_tx_req_free(req); + ynl_sock_destroy(*ys); + return -1; +} + static void enable_reuseaddr(int fd) { int opt = 1; @@ -431,7 +507,7 @@ static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6) return 0; } -int do_server(struct memory_buffer *mem) +static int do_server(struct memory_buffer *mem) { char ctrl_data[sizeof(int) * 20000]; struct netdev_queue_id *queues; @@ -685,6 +761,206 @@ void run_devmem_tests(void) provider->free(mem); } +static uint64_t gettimeofday_ms(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return (tv.tv_sec * 1000ULL) + (tv.tv_usec / 1000ULL); +} + +static int do_poll(int fd) +{ + struct pollfd pfd; + int ret; + + pfd.revents = 0; + pfd.fd = fd; + + ret = poll(&pfd, 1, waittime_ms); + if (ret == -1) + error(1, errno, "poll"); + + return ret && (pfd.revents & POLLERR); +} + +static void wait_compl(int fd) +{ + int64_t tstop = gettimeofday_ms() + waittime_ms; + char control[CMSG_SPACE(100)] = {}; + struct sock_extended_err *serr; + struct msghdr msg = {}; + struct cmsghdr *cm; + __u32 hi, lo; + int ret; + + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + while (gettimeofday_ms() < tstop) { + if (!do_poll(fd)) + continue; + + ret = recvmsg(fd, &msg, MSG_ERRQUEUE); + if (ret < 0) { + if (errno == EAGAIN) + continue; + error(1, errno, "recvmsg(MSG_ERRQUEUE)"); + return; + } + if (msg.msg_flags & MSG_CTRUNC) + error(1, 0, "MSG_CTRUNC\n"); + + for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) { + if (cm->cmsg_level != SOL_IP && + cm->cmsg_level != SOL_IPV6) + continue; + if (cm->cmsg_level == SOL_IP && + cm->cmsg_type != IP_RECVERR) + continue; + if (cm->cmsg_level == SOL_IPV6 && + cm->cmsg_type != IPV6_RECVERR) + continue; + + serr = (void *)CMSG_DATA(cm); + if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY) + error(1, 0, "wrong origin %u", serr->ee_origin); + if (serr->ee_errno != 0) + error(1, 0, "wrong errno %d", serr->ee_errno); + + hi = serr->ee_data; + lo = serr->ee_info; + + fprintf(stderr, "tx complete [%d,%d]\n", lo, hi); + return; + } + } + + error(1, 0, "did not receive tx completion"); +} + +static int do_client(struct memory_buffer *mem) +{ + char ctrl_data[CMSG_SPACE(sizeof(__u32))]; + struct sockaddr_in6 server_sin; + struct sockaddr_in6 client_sin; + struct ynl_sock *ys = NULL; + struct msghdr msg = {}; + ssize_t line_size = 0; + struct cmsghdr *cmsg; + struct iovec iov[2]; + char *line = NULL; + unsigned long mid; + size_t len = 0; + int socket_fd; + __u32 ddmabuf; + int opt = 1; + int ret; + + ret = parse_address(server_ip, atoi(port), &server_sin); + if (ret < 0) + error(1, 0, "parse server address"); + + socket_fd = socket(AF_INET6, SOCK_STREAM, 0); + if (socket_fd < 0) + error(1, socket_fd, "create socket"); + + enable_reuseaddr(socket_fd); + + ret = setsockopt(socket_fd, SOL_SOCKET, SO_BINDTODEVICE, ifname, + strlen(ifname) + 1); + if (ret) + error(1, errno, "bindtodevice"); + + if (bind_tx_queue(ifindex, mem->fd, &ys)) + error(1, 0, "Failed to bind\n"); + + if (client_ip) { + ret = parse_address(client_ip, atoi(port), &client_sin); + if (ret < 0) + error(1, 0, "parse client address"); + + ret = bind(socket_fd, &client_sin, sizeof(client_sin)); + if (ret) + error(1, errno, "bind"); + } + + ret = setsockopt(socket_fd, SOL_SOCKET, SO_ZEROCOPY, &opt, sizeof(opt)); + if (ret) + error(1, errno, "set sock opt"); + + fprintf(stderr, "Connect to %s %d (via %s)\n", server_ip, + ntohs(server_sin.sin6_port), ifname); + + ret = connect(socket_fd, &server_sin, sizeof(server_sin)); + if (ret) + error(1, errno, "connect"); + + while (1) { + free(line); + line = NULL; + line_size = getline(&line, &len, stdin); + + if (line_size < 0) + break; + + mid = (line_size / 2) + 1; + + iov[0].iov_base = (void *)1; + iov[0].iov_len = mid; + iov[1].iov_base = (void *)(mid + 2); + iov[1].iov_len = line_size - mid; + + provider->memcpy_to_device(mem, (size_t)iov[0].iov_base, line, + iov[0].iov_len); + provider->memcpy_to_device(mem, (size_t)iov[1].iov_base, + line + iov[0].iov_len, + iov[1].iov_len); + + fprintf(stderr, + "read line_size=%ld iov[0].iov_base=%lu, iov[0].iov_len=%lu, iov[1].iov_base=%lu, iov[1].iov_len=%lu\n", + line_size, (unsigned long)iov[0].iov_base, + iov[0].iov_len, (unsigned long)iov[1].iov_base, + iov[1].iov_len); + + msg.msg_iov = iov; + msg.msg_iovlen = 2; + + msg.msg_control = ctrl_data; + msg.msg_controllen = sizeof(ctrl_data); + + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_DEVMEM_DMABUF; + cmsg->cmsg_len = CMSG_LEN(sizeof(__u32)); + + ddmabuf = tx_dmabuf_id; + + *((__u32 *)CMSG_DATA(cmsg)) = ddmabuf; + + ret = sendmsg(socket_fd, &msg, MSG_ZEROCOPY); + if (ret < 0) + error(1, errno, "Failed sendmsg"); + + fprintf(stderr, "sendmsg_ret=%d\n", ret); + + if (ret != line_size) + error(1, errno, "Did not send all bytes"); + + wait_compl(socket_fd); + } + + fprintf(stderr, "%s: tx ok\n", TEST_PREFIX); + + free(line); + close(socket_fd); + + if (ys) + ynl_sock_destroy(ys); + + return 0; +} + int main(int argc, char *argv[]) { struct memory_buffer *mem; @@ -728,6 +1004,8 @@ int main(int argc, char *argv[]) ifindex = if_nametoindex(ifname); + fprintf(stderr, "using ifindex=%u\n", ifindex); + if (!server_ip && !client_ip) { if (start_queue < 0 && num_queues < 0) { num_queues = rxq_num(ifindex); @@ -778,7 +1056,7 @@ int main(int argc, char *argv[]) error(1, 0, "Missing -p argument\n"); mem = provider->alloc(getpagesize() * NUM_PAGES); - ret = is_server ? do_server(mem) : 1; + ret = is_server ? do_server(mem) : do_client(mem); provider->free(mem); return ret; |