diff options
54 files changed, 2757 insertions, 124 deletions
diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 959755be4d7f..08412c279297 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -167,6 +167,10 @@ attribute-sets: "re-attached", they are just waiting to disappear. Attribute is absent if Page Pool has not been detached, and can still be used to allocate new memory. + - + name: dmabuf + doc: ID of the dmabuf this page-pool is attached to. + type: u32 - name: page-pool-info subset-of: page-pool @@ -268,6 +272,10 @@ attribute-sets: name: napi-id doc: ID of the NAPI instance which services this queue. type: u32 + - + name: dmabuf + doc: ID of the dmabuf attached to this queue, if any. + type: u32 - name: qstats @@ -457,6 +465,39 @@ attribute-sets: Number of times driver re-started accepting send requests to this queue from the stack. type: uint + - + name: queue-id + subset-of: queue + attributes: + - + name: id + - + name: type + - + name: dmabuf + attributes: + - + name: ifindex + doc: netdev ifindex to bind the dmabuf to. + type: u32 + checks: + min: 1 + - + name: queues + doc: receive queues to bind the dmabuf to. + type: nest + nested-attributes: queue-id + multi-attr: true + - + name: fd + doc: dmabuf file descriptor to bind. + type: u32 + - + name: id + doc: id of the dmabuf binding + type: u32 + checks: + min: 1 operations: list: @@ -510,6 +551,7 @@ operations: - inflight - inflight-mem - detach-time + - dmabuf dump: reply: *pp-reply config-cond: page-pool @@ -574,6 +616,7 @@ operations: - type - napi-id - ifindex + - dmabuf dump: request: attributes: @@ -619,6 +662,24 @@ operations: - rx-bytes - tx-packets - tx-bytes + - + name: bind-rx + doc: Bind dmabuf to netdev + attribute-set: dmabuf + flags: [ admin-perm ] + do: + request: + attributes: + - ifindex + - fd + - queues + reply: + attributes: + - id + +kernel-family: + headers: [ "linux/list.h"] + sock-priv: struct list_head mcast-groups: list: diff --git a/Documentation/networking/devmem.rst b/Documentation/networking/devmem.rst new file mode 100644 index 000000000000..a55bf21f671c --- /dev/null +++ b/Documentation/networking/devmem.rst @@ -0,0 +1,269 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================= +Device Memory TCP +================= + + +Intro +===== + +Device memory TCP (devmem TCP) enables receiving data directly into device +memory (dmabuf). The feature is currently implemented for TCP sockets. + + +Opportunity +----------- + +A large number of data transfers have device memory as the source and/or +destination. Accelerators drastically increased the prevalence of such +transfers. Some examples include: + +- Distributed training, where ML accelerators, such as GPUs on different hosts, + exchange data. + +- Distributed raw block storage applications transfer large amounts of data with + remote SSDs. Much of this data does not require host processing. + +Typically the Device-to-Device data transfers in the network are implemented as +the following low-level operations: Device-to-Host copy, Host-to-Host network +transfer, and Host-to-Device copy. + +The flow involving host copies is suboptimal, especially for bulk data transfers, +and can put significant strains on system resources such as host memory +bandwidth and PCIe bandwidth. + +Devmem TCP optimizes this use case by implementing socket APIs that enable +the user to receive incoming network packets directly into device memory. + +Packet payloads go directly from the NIC to device memory. + +Packet headers go to host memory and are processed by the TCP/IP stack +normally. The NIC must support header split to achieve this. + +Advantages: + +- Alleviate host memory bandwidth pressure, compared to existing + network-transfer + device-copy semantics. + +- Alleviate PCIe bandwidth pressure, by limiting data transfer to the lowest + level of the PCIe tree, compared to the traditional path which sends data + through the root complex. + + +More Info +--------- + + slides, video + https://netdevconf.org/0x17/sessions/talk/device-memory-tcp.html + + patchset + [PATCH net-next v24 00/13] Device Memory TCP + https://lore.kernel.org/netdev/[email protected]/ + + +Interface +========= + + +Example +------- + +tools/testing/selftests/net/ncdevmem.c:do_server shows an example of setting up +the RX path of this API. + + +NIC Setup +--------- + +Header split, flow steering, & RSS are required features for devmem TCP. + +Header split is used to split incoming packets into a header buffer in host +memory, and a payload buffer in device memory. + +Flow steering & RSS are used to ensure that only flows targeting devmem land on +an RX queue bound to devmem. + +Enable header split & flow steering:: + + # enable header split + ethtool -G eth1 tcp-data-split on + + + # enable flow steering + ethtool -K eth1 ntuple on + +Configure RSS to steer all traffic away from the target RX queue (queue 15 in +this example):: + + ethtool --set-rxfh-indir eth1 equal 15 + + +The user must bind a dmabuf to any number of RX queues on a given NIC using +the netlink API:: + + /* Bind dmabuf to NIC RX queue 15 */ + struct netdev_queue *queues; + queues = malloc(sizeof(*queues) * 1); + + queues[0]._present.type = 1; + queues[0]._present.idx = 1; + queues[0].type = NETDEV_RX_QUEUE_TYPE_RX; + queues[0].idx = 15; + + *ys = ynl_sock_create(&ynl_netdev_family, &yerr); + + req = netdev_bind_rx_req_alloc(); + netdev_bind_rx_req_set_ifindex(req, 1 /* ifindex */); + netdev_bind_rx_req_set_dmabuf_fd(req, dmabuf_fd); + __netdev_bind_rx_req_set_queues(req, queues, n_queue_index); + + rsp = netdev_bind_rx(*ys, req); + + dmabuf_id = rsp->dmabuf_id; + + +The netlink API returns a dmabuf_id: a unique ID that refers to this dmabuf +that has been bound. + +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 socket must be flow steered to the dmabuf bound RX queue:: + + ethtool -N eth1 flow-type tcp4 ... queue 15 + + +Receiving data +-------------- + +The user application must signal to the kernel that it is capable of receiving +devmem data by passing the MSG_SOCK_DEVMEM flag to recvmsg:: + + ret = recvmsg(fd, &msg, MSG_SOCK_DEVMEM); + +Applications that do not specify the MSG_SOCK_DEVMEM flag will receive an EFAULT +on devmem data. + +Devmem data is received directly into the dmabuf bound to the NIC in 'NIC +Setup', and the kernel signals such to the user via the SCM_DEVMEM_* cmsgs:: + + for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) { + if (cm->cmsg_level != SOL_SOCKET || + (cm->cmsg_type != SCM_DEVMEM_DMABUF && + cm->cmsg_type != SCM_DEVMEM_LINEAR)) + continue; + + dmabuf_cmsg = (struct dmabuf_cmsg *)CMSG_DATA(cm); + + if (cm->cmsg_type == SCM_DEVMEM_DMABUF) { + /* Frag landed in dmabuf. + * + * dmabuf_cmsg->dmabuf_id is the dmabuf the + * frag landed on. + * + * dmabuf_cmsg->frag_offset is the offset into + * the dmabuf where the frag starts. + * + * dmabuf_cmsg->frag_size is the size of the + * frag. + * + * dmabuf_cmsg->frag_token is a token used to + * refer to this frag for later freeing. + */ + + struct dmabuf_token token; + token.token_start = dmabuf_cmsg->frag_token; + token.token_count = 1; + continue; + } + + if (cm->cmsg_type == SCM_DEVMEM_LINEAR) + /* Frag landed in linear buffer. + * + * dmabuf_cmsg->frag_size is the size of the + * frag. + */ + continue; + + } + +Applications may receive 2 cmsgs: + +- SCM_DEVMEM_DMABUF: this indicates the fragment landed in the dmabuf indicated + by dmabuf_id. + +- SCM_DEVMEM_LINEAR: this indicates the fragment landed in the linear buffer. + This typically happens when the NIC is unable to split the packet at the + header boundary, such that part (or all) of the payload landed in host + memory. + +Applications may receive no SO_DEVMEM_* cmsgs. That indicates non-devmem, +regular TCP data that landed on an RX queue not bound to a dmabuf. + + +Freeing frags +------------- + +Frags received via SCM_DEVMEM_DMABUF are pinned by the kernel while the user +processes the frag. The user must return the frag to the kernel via +SO_DEVMEM_DONTNEED:: + + ret = setsockopt(client_fd, SOL_SOCKET, SO_DEVMEM_DONTNEED, &token, + sizeof(token)); + +The user must ensure the tokens are returned to the kernel in a timely manner. +Failure to do so will exhaust the limited dmabuf that is bound to the RX queue +and will lead to packet drops. + + +Implementation & Caveats +======================== + +Unreadable skbs +--------------- + +Devmem payloads are inaccessible to the kernel processing the packets. This +results in a few quirks for payloads of devmem skbs: + +- Loopback is not functional. Loopback relies on copying the payload, which is + not possible with devmem skbs. + +- Software checksum calculation fails. + +- TCP Dump and bpf can't access devmem packet payloads. + + +Testing +======= + +More realistic example code can be found in the kernel source under +``tools/testing/selftests/net/ncdevmem.c`` + +ncdevmem is a devmem TCP netcat. It works very similarly to netcat, but +receives data directly into a udmabuf. + +To run ncdevmem, you need to run it on a server on the machine under test, and +you need to run netcat on a peer to provide the TX data. + +ncdevmem has a validation mode as well that expects a repeating pattern of +incoming data and validates it as such. For example, you can launch +ncdevmem on the server by:: + + ncdevmem -s <server IP> -c <client IP> -f eth1 -d 3 -n 0000:06:00.0 -l \ + -p 5201 -v 7 + +On client side, use regular netcat to send TX data to ncdevmem process +on the server:: + + yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06) | \ + tr \\n \\0 | head -c 5G | nc <server IP> 5201 -p 5201 diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index c71b87346178..08f437c326ab 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -49,6 +49,7 @@ Contents: cdc_mbim dccp dctcp + devmem dns_resolver driver eql diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index e94f621903fe..251b73c5481e 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -140,6 +140,12 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SO_DEVMEM_LINEAR 78 +#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__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 60ebaed28a4c..8ab7582291ab 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -151,6 +151,12 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SO_DEVMEM_LINEAR 78 +#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__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index be264c2b1a11..38fc0b188e08 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -132,6 +132,12 @@ #define SO_PASSPIDFD 0x404A #define SO_PEERPIDFD 0x404B +#define SO_DEVMEM_LINEAR 78 +#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__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 682da3714686..57084ed2f3c4 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -133,6 +133,12 @@ #define SO_PASSPIDFD 0x0055 #define SO_PEERPIDFD 0x0056 +#define SO_DEVMEM_LINEAR 0x0057 +#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/linux/netdevice.h b/include/linux/netdevice.h index 2465bdb6037f..e87b5e488325 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3953,6 +3953,8 @@ u8 dev_xdp_prog_count(struct net_device *dev); int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); +u32 dev_get_min_mp_channel_count(const struct net_device *dev); + int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5803eb8a157d..39f1d16f3628 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 @@ -1824,6 +1826,12 @@ 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; @@ -2540,10 +2548,17 @@ 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). @@ -3524,21 +3539,58 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto, fragto->offset = fragfrom->offset; } +/* Return: true if the skb_frag contains a net_iov. */ +static inline bool skb_frag_is_net_iov(const skb_frag_t *frag) +{ + return netmem_is_net_iov(frag->netmem); +} + +/** + * skb_frag_net_iov - retrieve the net_iov referred to by fragment + * @frag: the fragment + * + * Return: the &struct net_iov associated with @frag. Returns NULL if this + * frag has no associated net_iov. + */ +static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag) +{ + if (!skb_frag_is_net_iov(frag)) + return NULL; + + return netmem_to_net_iov(frag->netmem); +} + /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * - * Returns the &struct page associated with @frag. + * Return: the &struct page associated with @frag. Returns NULL if this frag + * has no associated page. */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { + if (skb_frag_is_net_iov(frag)) + return NULL; + return netmem_to_page(frag->netmem); } +/** + * skb_frag_netmem - retrieve the netmem referred to by a fragment + * @frag: the fragment + * + * Return: the &netmem_ref associated with @frag. + */ +static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag) +{ + return frag->netmem; +} + int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog); + /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer @@ -3548,6 +3600,9 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, */ static inline void *skb_frag_address(const skb_frag_t *frag) { + if (!skb_frag_page(frag)) + return NULL; + return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h index 16c241a23472..0f3c58007488 100644 --- a/include/linux/skbuff_ref.h +++ b/include/linux/skbuff_ref.h @@ -34,14 +34,13 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) bool napi_pp_put_page(netmem_ref netmem); -static inline void -skb_page_unref(struct page *page, bool recycle) +static inline void skb_page_unref(netmem_ref netmem, bool recycle) { #ifdef CONFIG_PAGE_POOL - if (recycle && napi_pp_put_page(page_to_netmem(page))) + if (recycle && napi_pp_put_page(netmem)) return; #endif - put_page(page); + put_page(netmem_to_page(netmem)); } /** @@ -54,7 +53,7 @@ skb_page_unref(struct page *page, bool recycle) */ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { - skb_page_unref(skb_frag_page(frag), recycle); + skb_page_unref(skb_frag_netmem(frag), recycle); } /** diff --git a/include/linux/socket.h b/include/linux/socket.h index df9cdb8bbfb8..d18cc47e89bd 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -327,6 +327,7 @@ struct ucred { * plain text and require encryption */ +#define MSG_SOCK_DEVMEM 0x2000000 /* Receive devmem skbs as cmsg */ #define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index aa1716fb0e53..ac34f5fb4f71 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; /* @@ -54,4 +56,7 @@ 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/include/net/netmem.h b/include/net/netmem.h index 46cc9b89ac79..8a6e20be4b9d 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -8,6 +8,54 @@ #ifndef _NET_NETMEM_H #define _NET_NETMEM_H +#include <linux/mm.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 + +/* netmem */ + /** * typedef netmem_ref - a nonexistent type marking a reference to generic * network memory. @@ -19,20 +67,37 @@ */ 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 struct net_iov *netmem_to_net_iov(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + return (struct net_iov *)((__force unsigned long)netmem & + ~NET_IOV); + + DEBUG_NET_WARN_ON_ONCE(true); + return NULL; +} + +static inline netmem_ref net_iov_to_netmem(struct net_iov *niov) +{ + return (__force netmem_ref)((unsigned long)niov | NET_IOV); +} + static inline netmem_ref page_to_netmem(struct page *page) { return (__force netmem_ref)page; @@ -40,17 +105,70 @@ 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) +{ + /* NUMA node preference only makes sense if we're allocating + * system memory. Memory providers (which give us net_iovs) + * choose for us. + */ + 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)); +} + +static inline unsigned long netmem_get_dma_addr(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->dma_addr; +} + #endif /* _NET_NETMEM_H */ diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 2b43a893c619..793e6fd78bc5 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; } @@ -401,9 +401,7 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va, 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; + dma_addr_t ret = netmem_get_dma_addr(netmem); if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) ret <<= PAGE_SHIFT; @@ -423,24 +421,6 @@ 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; -} - /** * page_pool_dma_sync_for_cpu - sync Rx page for CPU after it's written by HW * @pool: &page_pool the @page belongs to @@ -463,11 +443,6 @@ static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool, page_pool_get_dma_dir(pool)); } -static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr) -{ - return page_pool_set_dma_addr_netmem(page_to_netmem(page), addr); -} - static inline bool page_pool_put(struct page_pool *pool) { return refcount_dec_and_test(&pool->user_cnt); diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 50569fed7868..c022c410abe3 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -20,8 +20,18 @@ * device driver responsibility */ #define PP_FLAG_SYSTEM_POOL BIT(2) /* Global system page_pool */ + +/* Allow unreadable (net_iov backed) netmem in this page_pool. Drivers setting + * this must be able to support unreadable netmem, where netmem_address() would + * return NULL. This flag should not be set for header page_pools. + * + * If the driver sets PP_FLAG_ALLOW_UNREADABLE_NETMEM, it should also set + * page_pool_params.slow.queue_idx. + */ +#define PP_FLAG_ALLOW_UNREADABLE_NETMEM BIT(3) + #define PP_FLAG_ALL (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV | \ - PP_FLAG_SYSTEM_POOL) + PP_FLAG_SYSTEM_POOL | PP_FLAG_ALLOW_UNREADABLE_NETMEM) /* * Fast allocation side cache array/stack @@ -57,7 +67,9 @@ struct pp_alloc_cache { * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV * @slow: params with slowpath access only (initialization and Netlink) * @netdev: netdev this pool will serve (leave as NULL if none or multiple) - * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL + * @queue_idx: queue idx this page_pool is being created for. + * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL, + * PP_FLAG_ALLOW_UNREADABLE_NETMEM. */ struct page_pool_params { struct_group_tagged(page_pool_params_fast, fast, @@ -72,6 +84,7 @@ struct page_pool_params { ); struct_group_tagged(page_pool_params_slow, slow, struct net_device *netdev; + unsigned int queue_idx; unsigned int flags; /* private: used by test code only */ void (*init_callback)(netmem_ref netmem, void *arg); @@ -139,6 +152,10 @@ 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 +214,8 @@ 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/include/net/sock.h b/include/net/sock.h index f51d61fab059..c58ca8dd561b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -337,6 +337,7 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference + * @sk_user_frags: xarray of pages the user is holding a reference on. */ struct sock { /* @@ -542,6 +543,7 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; + struct xarray sk_user_frags; }; struct sock_bh_locked { diff --git a/include/net/tcp.h b/include/net/tcp.h index 2aac11e7e1cc..f77f812bfbe7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -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/include/trace/events/page_pool.h b/include/trace/events/page_pool.h index 543e54e432a1..31825ed30032 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/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 8ce8a39a1e5f..3b4e3e815602 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -135,6 +135,12 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SO_DEVMEM_LINEAR 78 +#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__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 43742ac5b00d..7c308f04e7a0 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -93,6 +93,7 @@ enum { NETDEV_A_PAGE_POOL_INFLIGHT, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, NETDEV_A_PAGE_POOL_DETACH_TIME, + NETDEV_A_PAGE_POOL_DMABUF, __NETDEV_A_PAGE_POOL_MAX, NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1) @@ -131,6 +132,7 @@ enum { NETDEV_A_QUEUE_IFINDEX, NETDEV_A_QUEUE_TYPE, NETDEV_A_QUEUE_NAPI_ID, + NETDEV_A_QUEUE_DMABUF, __NETDEV_A_QUEUE_MAX, NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) @@ -174,6 +176,16 @@ enum { }; enum { + NETDEV_A_DMABUF_IFINDEX = 1, + NETDEV_A_DMABUF_QUEUES, + NETDEV_A_DMABUF_FD, + NETDEV_A_DMABUF_ID, + + __NETDEV_A_DMABUF_MAX, + NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1) +}; + +enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, NETDEV_CMD_DEV_DEL_NTF, @@ -186,6 +198,7 @@ enum { NETDEV_CMD_QUEUE_GET, NETDEV_CMD_NAPI_GET, NETDEV_CMD_QSTATS_GET, + NETDEV_CMD_BIND_RX, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h index 059b1a9147f4..649739e0c404 100644 --- a/include/uapi/linux/uio.h +++ b/include/uapi/linux/uio.h @@ -20,6 +20,24 @@ struct iovec __kernel_size_t iov_len; /* Must be size_t (1003.1g) */ }; +struct dmabuf_cmsg { + __u64 frag_offset; /* offset into the dmabuf where the frag starts. + */ + __u32 frag_size; /* size of the frag. */ + __u32 frag_token; /* token representing this frag for + * DEVMEM_DONTNEED. + */ + __u32 dmabuf_id; /* dmabuf id this frag belongs to. */ + __u32 flags; /* Currently unused. Reserved for future + * uses. + */ +}; + +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/Kconfig b/net/Kconfig index d27d0deac0bf..7574b066d7cd 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -66,6 +66,11 @@ config SKB_DECRYPTED config SKB_EXTENSIONS bool +config NET_DEVMEM + def_bool y + depends on DMA_SHARED_BUFFER + depends on GENERIC_ALLOCATOR + menu "Networking options" source "net/packet/Kconfig" diff --git a/net/core/Makefile b/net/core/Makefile index 62be9aef2528..c3ebbaf9c81e 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-$(CONFIG_NET_PKTGEN) += pktgen.o @@ -43,3 +44,4 @@ obj-$(CONFIG_BPF_SYSCALL) += sock_map.o obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o obj-$(CONFIG_OF) += of_net.o obj-$(CONFIG_NET_TEST) += net_test.o +obj-$(CONFIG_NET_DEVMEM) += devmem.o diff --git a/net/core/datagram.c b/net/core/datagram.c index a40f733b37d7..f0693707aece 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/dev.c b/net/core/dev.c index 8f4dead64284..1e740faf9e78 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -161,6 +161,7 @@ #include <linux/phy_link_topology.h> #include "dev.h" +#include "devmem.h" #include "net-sysfs.h" static DEFINE_SPINLOCK(ptype_lock); @@ -3311,6 +3312,10 @@ int skb_checksum_help(struct sk_buff *skb) return -EINVAL; } + if (!skb_frags_readable(skb)) { + return -EFAULT; + } + /* Before computing a checksum, we should make sure no frag could * be modified by an external entity : checksum could be wrong. */ @@ -3433,8 +3438,9 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) if (!(dev->features & NETIF_F_HIGHDMA)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct page *page = skb_frag_page(frag); - if (PageHighMem(skb_frag_page(frag))) + if (page && PageHighMem(page)) return 1; } } @@ -9367,6 +9373,11 @@ int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) if (!dev->netdev_ops->ndo_bpf) return -EOPNOTSUPP; + if (dev_get_min_mp_channel_count(dev)) { + NL_SET_ERR_MSG(bpf->extack, "unable to propagate XDP to device using memory provider"); + return -EBUSY; + } + return dev->netdev_ops->ndo_bpf(dev, bpf); } EXPORT_SYMBOL_GPL(dev_xdp_propagate); @@ -9399,6 +9410,11 @@ static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode, struct netdev_bpf xdp; int err; + if (dev_get_min_mp_channel_count(dev)) { + NL_SET_ERR_MSG(extack, "unable to install XDP to device using memory provider"); + return -EBUSY; + } + memset(&xdp, 0, sizeof(xdp)); xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG; xdp.extack = extack; @@ -9823,6 +9839,20 @@ err_out: return err; } +u32 dev_get_min_mp_channel_count(const struct net_device *dev) +{ + int i; + + ASSERT_RTNL(); + + for (i = dev->real_num_rx_queues - 1; i >= 0; i--) + if (dev->_rx[i].mp_params.mp_priv) + /* The channel count is the idx plus 1. */ + return i + 1; + + return 0; +} + /** * dev_index_reserve() - allocate an ifindex in a namespace * @net: the applicable net namespace @@ -11359,6 +11389,7 @@ 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 000000000000..11b91c12ee11 --- /dev/null +++ b/net/core/devmem.c @@ -0,0 +1,389 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Devmem TCP + * + * Authors: Mina Almasry <[email protected]> + * Willem de Bruijn <[email protected]> + * Kaiyuan Zhang <[email protected] + */ + +#include <linux/dma-buf.h> +#include <linux/genalloc.h> +#include <linux/mm.h> +#include <linux/netdevice.h> +#include <linux/types.h> +#include <net/netdev_queues.h> +#include <net/netdev_rx_queue.h> +#include <net/page_pool/helpers.h> +#include <trace/events/page_pool.h> + +#include "devmem.h" +#include "mp_dmabuf_devmem.h" +#include "page_pool_priv.h" + +/* Device memory support */ + +/* Protected by rtnl_lock() */ +static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1); + +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); +} + +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; + + 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); +} + +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->pp_magic = 0; + niov->pp = NULL; + atomic_long_set(&niov->pp_ref_count, 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 (WARN_ON(!gen_pool_has_addr(binding->chunk_pool, dma_addr, + PAGE_SIZE))) + return; + + gen_pool_free(binding->chunk_pool, dma_addr, PAGE_SIZE); +} + +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) { + WARN_ON(rxq->mp_params.mp_priv != binding); + + rxq->mp_params.mp_priv = NULL; + + rxq_idx = get_netdev_rx_queue_index(rxq); + + WARN_ON(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 netlink_ext_ack *extack) +{ + struct netdev_rx_queue *rxq; + u32 xa_idx; + int err; + + if (rxq_idx >= dev->real_num_rx_queues) { + NL_SET_ERR_MSG(extack, "rx queue index out of range"); + return -ERANGE; + } + + rxq = __netif_get_rx_queue(dev, rxq_idx); + if (rxq->mp_params.mp_priv) { + NL_SET_ERR_MSG(extack, "designated queue already memory provider bound"); + return -EEXIST; + } + +#ifdef CONFIG_XDP_SOCKETS + if (rxq->pool) { + NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP"); + return -EBUSY; + } +#endif + + 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 netlink_ext_ack *extack) +{ + 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); + NL_SET_ERR_MSG(extack, "Failed to bind dmabuf to device"); + 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); + NL_SET_ERR_MSG(extack, "Failed to map dmabuf attachment"); + 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; + page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov), + net_devmem_get_dma_addr(niov)); + } + + 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) +{ + struct net_devmem_dmabuf_binding *binding; + struct netdev_rx_queue *rxq; + unsigned long xa_idx; + unsigned int i; + + for (i = 0; i < dev->real_num_rx_queues; i++) { + binding = dev->_rx[i].mp_params.mp_priv; + if (!binding) + continue; + + xa_for_each(&binding->bound_rxqs, xa_idx, rxq) + if (rxq == &dev->_rx[i]) { + xa_erase(&binding->bound_rxqs, xa_idx); + break; + } + } +} + +/*** "Dmabuf devmem memory provider" ***/ + +int mp_dmabuf_devmem_init(struct page_pool *pool) +{ + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; + + if (!binding) + return -EINVAL; + + if (!pool->dma_map) + return -EOPNOTSUPP; + + if (pool->dma_sync) + return -EOPNOTSUPP; + + if (pool->p.order != 0) + return -E2BIG; + + net_devmem_dmabuf_binding_get(binding); + return 0; +} + +netmem_ref mp_dmabuf_devmem_alloc_netmems(struct page_pool *pool, gfp_t gfp) +{ + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; + struct net_iov *niov; + netmem_ref netmem; + + niov = net_devmem_alloc_dmabuf(binding); + if (!niov) + return 0; + + netmem = net_iov_to_netmem(niov); + + page_pool_set_pp_info(pool, netmem); + + pool->pages_state_hold_cnt++; + trace_page_pool_state_hold(pool, netmem, pool->pages_state_hold_cnt); + return netmem; +} + +void mp_dmabuf_devmem_destroy(struct page_pool *pool) +{ + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; + + net_devmem_dmabuf_binding_put(binding); +} + +bool mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem) +{ + long refcount = atomic_long_read(netmem_get_pp_ref_count_ref(netmem)); + + if (WARN_ON_ONCE(!netmem_is_net_iov(netmem))) + return false; + + if (WARN_ON_ONCE(refcount != 1)) + return false; + + page_pool_clear_pp_info(netmem); + + net_devmem_free_dmabuf(netmem_to_net_iov(netmem)); + + /* We don't want the page pool put_page()ing our net_iovs. */ + return false; +} diff --git a/net/core/devmem.h b/net/core/devmem.h new file mode 100644 index 000000000000..76099ef9c482 --- /dev/null +++ b/net/core/devmem.h @@ -0,0 +1,180 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Device memory TCP support + * + * Authors: Mina Almasry <[email protected]> + * Willem de Bruijn <[email protected]> + * Kaiyuan Zhang <[email protected]> + * + */ +#ifndef _NET_DEVMEM_H +#define _NET_DEVMEM_H + +struct netlink_ext_ack; + +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; +}; + +#if defined(CONFIG_NET_DEVMEM) +/* 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; +}; + +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, + struct netlink_ext_ack *extack); +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 dev_dmabuf_uninstall(struct net_device *dev); + +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; +} + +static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov) +{ + struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov); + + return owner->base_virtual + + ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT); +} + +static inline u32 net_iov_binding_id(const struct net_iov *niov) +{ + return net_iov_owner(niov)->binding->id; +} + +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); +} + +struct net_iov * +net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding); +void net_devmem_free_dmabuf(struct net_iov *ppiov); + +#else +struct net_devmem_dmabuf_binding; + +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, + struct netlink_ext_ack *extack) +{ + 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, + struct netlink_ext_ack *extack) + +{ + return -EOPNOTSUPP; +} + +static inline void dev_dmabuf_uninstall(struct net_device *dev) +{ +} + +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 unsigned long net_iov_virtual_addr(const struct net_iov *niov) +{ + return 0; +} + +static inline u32 net_iov_binding_id(const struct net_iov *niov) +{ + return 0; +} +#endif + +#endif /* _NET_DEVMEM_H */ diff --git a/net/core/gro.c b/net/core/gro.c index 3abad1b567dd..802b4a062400 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -408,7 +408,8 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) pinfo = skb_shinfo(skb); frag0 = &pinfo->frags[0]; - if (pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0)) && + if (pinfo->nr_frags && skb_frag_page(frag0) && + !PageHighMem(skb_frag_page(frag0)) && (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, diff --git a/net/core/mp_dmabuf_devmem.h b/net/core/mp_dmabuf_devmem.h new file mode 100644 index 000000000000..67cd0dd7319c --- /dev/null +++ b/net/core/mp_dmabuf_devmem.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Dmabuf device memory provider. + * + * Authors: Mina Almasry <[email protected]> + * + */ +#ifndef _NET_MP_DMABUF_DEVMEM_H +#define _NET_MP_DMABUF_DEVMEM_H + +#include <net/netmem.h> + +#if defined(CONFIG_NET_DEVMEM) +int mp_dmabuf_devmem_init(struct page_pool *pool); + +netmem_ref mp_dmabuf_devmem_alloc_netmems(struct page_pool *pool, gfp_t gfp); + +void mp_dmabuf_devmem_destroy(struct page_pool *pool); + +bool mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem); +#else +static inline int mp_dmabuf_devmem_init(struct page_pool *pool) +{ + return -EOPNOTSUPP; +} + +static inline netmem_ref +mp_dmabuf_devmem_alloc_netmems(struct page_pool *pool, gfp_t gfp) +{ + return 0; +} + +static inline void mp_dmabuf_devmem_destroy(struct page_pool *pool) +{ +} + +static inline bool +mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem) +{ + return false; +} +#endif + +#endif /* _NET_MP_DMABUF_DEVMEM_H */ diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 8350a0afa9ec..b28424ae06d5 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 = { @@ -27,6 +28,11 @@ const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFIND [NETDEV_A_PAGE_POOL_IFINDEX] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_page_pool_ifindex_range), }; +const struct nla_policy netdev_queue_id_nl_policy[NETDEV_A_QUEUE_TYPE + 1] = { + [NETDEV_A_QUEUE_ID] = { .type = NLA_U32, }, + [NETDEV_A_QUEUE_TYPE] = NLA_POLICY_MAX(NLA_U32, 1), +}; + /* NETDEV_CMD_DEV_GET - do */ static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = { [NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), @@ -74,6 +80,13 @@ static const struct nla_policy netdev_qstats_get_nl_policy[NETDEV_A_QSTATS_SCOPE [NETDEV_A_QSTATS_SCOPE] = NLA_POLICY_MASK(NLA_UINT, 0x1), }; +/* NETDEV_CMD_BIND_RX - do */ +static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1] = { + [NETDEV_A_DMABUF_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), + [NETDEV_A_DMABUF_FD] = { .type = NLA_U32, }, + [NETDEV_A_DMABUF_QUEUES] = NLA_POLICY_NESTED(netdev_queue_id_nl_policy), +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -151,6 +164,13 @@ static const struct genl_split_ops netdev_nl_ops[] = { .maxattr = NETDEV_A_QSTATS_SCOPE, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = NETDEV_CMD_BIND_RX, + .doit = netdev_nl_bind_rx_doit, + .policy = netdev_bind_rx_nl_policy, + .maxattr = NETDEV_A_DMABUF_FD, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { @@ -168,4 +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 4db40fd5b4a9..8cda334fd042 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -10,9 +10,11 @@ #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]; +extern const struct nla_policy netdev_queue_id_nl_policy[NETDEV_A_QUEUE_TYPE + 1]; int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); @@ -30,6 +32,7 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); 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); enum { NETDEV_NLGRP_MGMT, @@ -38,4 +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 a17d7eaeb001..1cb954f2d39e 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -3,16 +3,17 @@ #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/rtnetlink.h> +#include <net/busy_poll.h> #include <net/net_namespace.h> +#include <net/netdev_queues.h> +#include <net/netdev_rx_queue.h> #include <net/sock.h> #include <net/xdp.h> #include <net/xdp_sock.h> -#include <net/netdev_rx_queue.h> -#include <net/netdev_queues.h> -#include <net/busy_poll.h> -#include "netdev-genl-gen.h" #include "dev.h" +#include "devmem.h" +#include "netdev-genl-gen.h" struct netdev_nl_dump_ctx { unsigned long ifindex; @@ -294,6 +295,7 @@ static int netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) { + struct net_devmem_dmabuf_binding *binding; struct netdev_rx_queue *rxq; struct netdev_queue *txq; void *hdr; @@ -313,6 +315,12 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID, rxq->napi->napi_id)) goto nla_put_failure; + + binding = rxq->mp_params.mp_priv; + if (binding && + nla_put_u32(rsp, NETDEV_A_QUEUE_DMABUF, binding->id)) + goto nla_put_failure; + break; case NETDEV_QUEUE_TYPE_TX: txq = netdev_get_tx_queue(netdev, q_idx); @@ -723,6 +731,129 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, return err; } +int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) +{ + 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; + } + + if (dev_xdp_prog_count(netdev)) { + NL_SET_ERR_MSG(info->extack, "unable to bind dmabuf to device with XDP program attached"); + err = -EEXIST; + goto err_unlock; + } + + binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, info->extack); + 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; + + if (NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_ID) || + NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_TYPE)) { + err = -EINVAL; + goto err_unbind; + } + + if (nla_get_u32(tb[NETDEV_A_QUEUE_TYPE]) != NETDEV_QUEUE_TYPE_RX) { + NL_SET_BAD_ATTR(info->extack, tb[NETDEV_A_QUEUE_TYPE]); + err = -EINVAL; + goto err_unbind; + } + + rxq_idx = nla_get_u32(tb[NETDEV_A_QUEUE_ID]); + + err = net_devmem_bind_dmabuf_to_queue(netdev, rxq_idx, binding, + info->extack); + 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); + + err = genlmsg_reply(rsp, info); + if (err) + goto err_unbind; + + rtnl_unlock(); + + return 0; + +err_unbind: + net_devmem_unbind_dmabuf(binding); +err_unlock: + rtnl_unlock(); +err_genlmsg_free: + nlmsg_free(rsp); + return err; +} + +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(); + } +} + static int netdev_genl_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c new file mode 100644 index 000000000000..e217a5838c87 --- /dev/null +++ b/net/core/netdev_rx_queue.c @@ -0,0 +1,81 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/netdevice.h> +#include <net/netdev_queues.h> +#include <net/netdev_rx_queue.h> + +#include "page_pool_priv.h" + +int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx) +{ + struct netdev_rx_queue *rxq = __netif_get_rx_queue(dev, 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 = page_pool_check_memory_provider(dev, rxq); + if (err) + goto err_free_new_queue_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; +} diff --git a/net/core/netmem_priv.h b/net/core/netmem_priv.h new file mode 100644 index 000000000000..7eadb8393e00 --- /dev/null +++ b/net/core/netmem_priv.h @@ -0,0 +1,31 @@ +/* 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 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 2abe6e919224..a813d30d2135 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -11,6 +11,7 @@ #include <linux/slab.h> #include <linux/device.h> +#include <net/netdev_rx_queue.h> #include <net/page_pool/helpers.h> #include <net/xdp.h> @@ -24,8 +25,12 @@ #include <trace/events/page_pool.h> +#include "mp_dmabuf_devmem.h" +#include "netmem_priv.h" #include "page_pool_priv.h" +DEFINE_STATIC_KEY_FALSE(page_pool_mem_providers); + #define DEFER_TIME (msecs_to_jiffies(1000)) #define DEFER_WARN_INTERVAL (60 * HZ) @@ -187,6 +192,8 @@ static int page_pool_init(struct page_pool *pool, int cpuid) { unsigned int ring_qsize = 1024; /* Default */ + struct netdev_rx_queue *rxq; + int err; page_pool_struct_check(); @@ -268,7 +275,37 @@ static int page_pool_init(struct page_pool *pool, if (pool->dma_map) get_device(pool->p.dev); + if (pool->slow.flags & PP_FLAG_ALLOW_UNREADABLE_NETMEM) { + /* We rely on rtnl_lock()ing to make sure netdev_rx_queue + * configuration doesn't change while we're initializing + * the page_pool. + */ + ASSERT_RTNL(); + rxq = __netif_get_rx_queue(pool->slow.netdev, + pool->slow.queue_idx); + pool->mp_priv = rxq->mp_params.mp_priv; + } + + if (pool->mp_priv) { + err = mp_dmabuf_devmem_init(pool); + if (err) { + pr_warn("%s() mem-provider init failed %d\n", __func__, + err); + goto free_ptr_ring; + } + + static_branch_inc(&page_pool_mem_providers); + } + return 0; + +free_ptr_ring: + ptr_ring_cleanup(&pool->ring, NULL); +#ifdef CONFIG_PAGE_POOL_STATS + if (!pool->system) + free_percpu(pool->recycle_stats); +#endif + return err; } static void page_pool_uninit(struct page_pool *pool) @@ -358,7 +395,7 @@ 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; @@ -452,32 +489,6 @@ unmap_failed: return false; } -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; - - /* Ensuring all pages have been split into one fragment initially: - * page_pool_set_pp_info() is only called once for every page when it - * is allocated from the page allocator and page_pool_fragment_page() - * is dirtying the same cache line as the page->pp_magic above, so - * the overhead is negligible. - */ - page_pool_fragment_netmem(netmem, 1); - if (pool->has_init_callback) - pool->slow.init_callback(netmem, pool->slow.init_arg); -} - -static void page_pool_clear_pp_info(netmem_ref netmem) -{ - struct page *page = netmem_to_page(netmem); - - page->pp_magic = 0; - page->pp = NULL; -} - static struct page *__page_pool_alloc_page_order(struct page_pool *pool, gfp_t gfp) { @@ -573,7 +584,10 @@ netmem_ref page_pool_alloc_netmem(struct page_pool *pool, gfp_t gfp) return netmem; /* Slow-path: cache empty, do real allocation */ - netmem = __page_pool_alloc_pages_slow(pool, gfp); + if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv) + netmem = mp_dmabuf_devmem_alloc_netmems(pool, gfp); + else + netmem = __page_pool_alloc_pages_slow(pool, gfp); return netmem; } EXPORT_SYMBOL(page_pool_alloc_netmem); @@ -609,6 +623,28 @@ s32 page_pool_inflight(const struct page_pool *pool, bool strict) return inflight; } +void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem) +{ + 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 + * is allocated from the page allocator and page_pool_fragment_page() + * is dirtying the same cache line as the page->pp_magic above, so + * the overhead is negligible. + */ + page_pool_fragment_netmem(netmem, 1); + if (pool->has_init_callback) + pool->slow.init_callback(netmem, pool->slow.init_arg); +} + +void page_pool_clear_pp_info(netmem_ref netmem) +{ + netmem_clear_pp_magic(netmem); + netmem_set_pp(netmem, NULL); +} + static __always_inline void __page_pool_release_page_dma(struct page_pool *pool, netmem_ref netmem) { @@ -637,8 +673,13 @@ static __always_inline void __page_pool_release_page_dma(struct page_pool *pool, void page_pool_return_page(struct page_pool *pool, netmem_ref netmem) { int count; + bool put; - __page_pool_release_page_dma(pool, netmem); + put = true; + if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv) + put = mp_dmabuf_devmem_release_page(pool, netmem); + else + __page_pool_release_page_dma(pool, netmem); /* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. @@ -646,8 +687,10 @@ void page_pool_return_page(struct page_pool *pool, netmem_ref netmem) count = atomic_inc_return_relaxed(&pool->pages_state_release_cnt); trace_page_pool_state_release(pool, netmem, count); - page_pool_clear_pp_info(netmem); - put_page(netmem_to_page(netmem)); + if (put) { + page_pool_clear_pp_info(netmem); + put_page(netmem_to_page(netmem)); + } /* An optimization would be to call __free_pages(page, pool->p.order) * knowing page is not part of page-cache (thus avoiding a * __page_cache_release() call). @@ -692,8 +735,9 @@ 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 +772,7 @@ __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 +994,7 @@ 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)); @@ -964,6 +1009,12 @@ static void __page_pool_destroy(struct page_pool *pool) page_pool_unlist(pool); page_pool_uninit(pool); + + if (pool->mp_priv) { + mp_dmabuf_devmem_destroy(pool); + static_branch_dec(&page_pool_mem_providers); + } + kfree(pool); } diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h index 90665d40f1eb..57439787b9c2 100644 --- a/net/core/page_pool_priv.h +++ b/net/core/page_pool_priv.h @@ -3,10 +3,56 @@ #ifndef __PAGE_POOL_PRIV_H #define __PAGE_POOL_PRIV_H +#include <net/page_pool/helpers.h> + +#include "netmem_priv.h" + s32 page_pool_inflight(const struct page_pool *pool, bool strict); int page_pool_list(struct page_pool *pool); void page_pool_detached(struct page_pool *pool); void page_pool_unlist(struct page_pool *pool); +static inline bool +page_pool_set_dma_addr_netmem(netmem_ref netmem, dma_addr_t addr) +{ + if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) { + 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)netmem_get_dma_addr(netmem) + << PAGE_SHIFT; + } + + netmem_set_dma_addr(netmem, addr); + return false; +} + +static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr) +{ + return page_pool_set_dma_addr_netmem(page_to_netmem(page), addr); +} + +#if defined(CONFIG_PAGE_POOL) +void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem); +void page_pool_clear_pp_info(netmem_ref netmem); +int page_pool_check_memory_provider(struct net_device *dev, + struct netdev_rx_queue *rxq); +#else +static inline void page_pool_set_pp_info(struct page_pool *pool, + netmem_ref netmem) +{ +} +static inline void page_pool_clear_pp_info(netmem_ref netmem) +{ +} +static inline int page_pool_check_memory_provider(struct net_device *dev, + struct netdev_rx_queue *rxq) +{ + return 0; +} +#endif + #endif diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 3a3277ba167b..48335766c1bf 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -4,10 +4,12 @@ #include <linux/netdevice.h> #include <linux/xarray.h> #include <net/net_debug.h> -#include <net/page_pool/types.h> +#include <net/netdev_rx_queue.h> #include <net/page_pool/helpers.h> +#include <net/page_pool/types.h> #include <net/sock.h> +#include "devmem.h" #include "page_pool_priv.h" #include "netdev-genl-gen.h" @@ -212,6 +214,7 @@ static int page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info) { + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; size_t inflight, refsz; void *hdr; @@ -241,6 +244,9 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, pool->user.detach_time)) goto err_cancel; + if (binding && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_DMABUF, binding->id)) + goto err_cancel; + genlmsg_end(rsp, hdr); return 0; @@ -344,6 +350,30 @@ void page_pool_unlist(struct page_pool *pool) mutex_unlock(&page_pools_lock); } +int page_pool_check_memory_provider(struct net_device *dev, + struct netdev_rx_queue *rxq) +{ + struct net_devmem_dmabuf_binding *binding = rxq->mp_params.mp_priv; + struct page_pool *pool; + struct hlist_node *n; + + if (!binding) + return 0; + + mutex_lock(&page_pools_lock); + hlist_for_each_entry_safe(pool, n, &dev->page_pools, user.list) { + if (pool->mp_priv != binding) + continue; + + if (pool->slow.queue_idx == get_netdev_rx_queue_index(rxq)) { + mutex_unlock(&page_pools_lock); + return 0; + } + } + mutex_unlock(&page_pools_lock); + return -ENODATA; +} + static void page_pool_unreg_netdev_wipe(struct net_device *netdev) { struct page_pool *pool; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 038a059b5924..74149dc4ee31 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -88,6 +88,7 @@ #include <linux/textsearch.h> #include "dev.h" +#include "netmem_priv.h" #include "sock_destructor.h" #ifdef CONFIG_SKB_EXTENSIONS @@ -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; } @@ -1372,6 +1371,14 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) struct page *p; u8 *vaddr; + if (skb_frag_is_net_iov(frag)) { + printk("%sskb frag %d: not readable\n", level, i); + len -= skb_frag_size(frag); + if (!len) + break; + continue; + } + skb_frag_foreach_page(frag, skb_frag_off(frag), skb_frag_size(frag), p, p_off, p_len, copied) { @@ -1965,6 +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; @@ -2138,6 +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; @@ -2476,6 +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; @@ -2820,6 +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)) @@ -2973,6 +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]; @@ -3161,9 +3183,15 @@ 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]; + if (WARN_ON_ONCE(!skb_frag_page(f))) + return false; + if (__splice_segment(skb_frag_page(f), skb_frag_off(f), skb_frag_size(f), offset, len, spd, false, sk, pipe)) @@ -3381,6 +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; @@ -3460,6 +3491,9 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, pos = copy; } + if (WARN_ON_ONCE(!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]; @@ -3560,6 +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; @@ -4051,6 +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; @@ -4098,6 +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; } /** @@ -4335,6 +4375,9 @@ next_skb: 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); @@ -5982,7 +6025,10 @@ 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; @@ -6159,6 +6205,9 @@ 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; @@ -6838,7 +6887,7 @@ 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/core/sock.c b/net/core/sock.c index 468b1239606c..bbb57b5af0b1 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); diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 6c245e59bbc1..dd345efa114b 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -655,6 +655,7 @@ int ethtool_check_max_channel(struct net_device *dev, { u64 max_rxnfc_in_use; u32 max_rxfh_in_use; + int max_mp_in_use; /* ensure the new Rx count fits within the configured Rx flow * indirection table/rxnfc settings @@ -673,6 +674,13 @@ int ethtool_check_max_channel(struct net_device *dev, return -EINVAL; } + max_mp_in_use = dev_get_min_mp_channel_count(dev); + if (channels.combined_count + channels.rx_count <= max_mp_in_use) { + if (info) + GENL_SET_ERR_MSG_FMT(info, "requested channel counts are too low for existing memory provider setting (%d)", max_mp_in_use); + return -EINVAL; + } + return 0; } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 47378ca41904..f3281312eb5e 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -115,7 +115,8 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - skb_page_unref(sg_page(sg), skb->pp_recycle); + skb_page_unref(page_to_netmem(sg_page(sg)), + skb->pp_recycle); } #ifdef CONFIG_INET_ESPINTCP diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e359a9161445..4f77bd862e95 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -285,6 +285,8 @@ #include <trace/events/tcp.h> #include <net/rps.h> +#include "../core/devmem.h" + /* Track pending CMSGs. */ enum { TCP_CMSG_INQ = 1, @@ -471,6 +473,7 @@ void tcp_init_sock(struct sock *sk) set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); + xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1); } EXPORT_SYMBOL(tcp_init_sock); @@ -2160,6 +2163,9 @@ 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; @@ -2177,6 +2183,9 @@ static int tcp_zerocopy_receive(struct sock *sk, break; } page = skb_frag_page(frags); + if (WARN_ON_ONCE(!page)) + break; + prefetchw(page); pages[pages_to_map++] = page; length += PAGE_SIZE; @@ -2322,6 +2331,220 @@ static int tcp_inq_hint(struct sock *sk) return inq; } +/* batch __xa_alloc() calls and reduce xa_lock()/xa_unlock() overhead. */ +struct tcp_xa_pool { + u8 max; /* max <= MAX_SKB_FRAGS */ + u8 idx; /* idx <= max */ + __u32 tokens[MAX_SKB_FRAGS]; + netmem_ref netmems[MAX_SKB_FRAGS]; +}; + +static void tcp_xa_pool_commit_locked(struct sock *sk, struct tcp_xa_pool *p) +{ + int i; + + /* Commit part that has been copied to user space. */ + for (i = 0; i < p->idx; i++) + __xa_cmpxchg(&sk->sk_user_frags, p->tokens[i], XA_ZERO_ENTRY, + (__force void *)p->netmems[i], GFP_KERNEL); + /* Rollback what has been pre-allocated and is no longer needed. */ + for (; i < p->max; i++) + __xa_erase(&sk->sk_user_frags, p->tokens[i]); + + p->max = 0; + p->idx = 0; +} + +static void tcp_xa_pool_commit(struct sock *sk, struct tcp_xa_pool *p) +{ + if (!p->max) + return; + + xa_lock_bh(&sk->sk_user_frags); + + tcp_xa_pool_commit_locked(sk, p); + + xa_unlock_bh(&sk->sk_user_frags); +} + +static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p, + unsigned int max_frags) +{ + int err, k; + + if (p->idx < p->max) + return 0; + + xa_lock_bh(&sk->sk_user_frags); + + tcp_xa_pool_commit_locked(sk, p); + + for (k = 0; k < max_frags; k++) { + err = __xa_alloc(&sk->sk_user_frags, &p->tokens[k], + XA_ZERO_ENTRY, xa_limit_31b, GFP_KERNEL); + if (err) + break; + } + + xa_unlock_bh(&sk->sk_user_frags); + + p->max = k; + p->idx = 0; + return k ? 0 : err; +} + +/* On error, returns the -errno. On success, returns number of bytes sent to the + * user. May not consume all of @remaining_len. + */ +static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, + unsigned int offset, struct msghdr *msg, + int remaining_len) +{ + struct dmabuf_cmsg dmabuf_cmsg = { 0 }; + struct tcp_xa_pool tcp_xa_pool; + unsigned int start; + int i, copy, n; + int sent = 0; + int err = 0; + + tcp_xa_pool.max = 0; + tcp_xa_pool.idx = 0; + do { + start = skb_headlen(skb); + + if (skb_frags_readable(skb)) { + err = -ENODEV; + goto out; + } + + /* Copy header. */ + copy = start - offset; + if (copy > 0) { + copy = min(copy, remaining_len); + + n = copy_to_iter(skb->data + offset, copy, + &msg->msg_iter); + if (n != copy) { + err = -EFAULT; + goto out; + } + + offset += copy; + remaining_len -= copy; + + /* First a dmabuf_cmsg for # bytes copied to user + * buffer. + */ + memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); + dmabuf_cmsg.frag_size = copy; + err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, + sizeof(dmabuf_cmsg), &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + if (!err) + err = -ETOOSMALL; + goto out; + } + + sent += copy; + + if (remaining_len == 0) + goto out; + } + + /* after that, send information of dmabuf pages through a + * sequence of cmsg + */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct net_iov *niov; + u64 frag_offset; + int end; + + /* !skb_frags_readable() should indicate that ALL the + * frags in this skb are dmabuf net_iovs. We're checking + * for that flag above, but also check individual frags + * here. If the tcp stack is not setting + * skb_frags_readable() correctly, we still don't want + * to crash here. + */ + if (!skb_frag_net_iov(frag)) { + net_err_ratelimited("Found non-dmabuf skb with net_iov"); + err = -ENODEV; + goto out; + } + + niov = skb_frag_net_iov(frag); + end = start + skb_frag_size(frag); + copy = end - offset; + + if (copy > 0) { + copy = min(copy, remaining_len); + + frag_offset = net_iov_virtual_addr(niov) + + skb_frag_off(frag) + offset - + start; + dmabuf_cmsg.frag_offset = frag_offset; + dmabuf_cmsg.frag_size = copy; + err = tcp_xa_pool_refill(sk, &tcp_xa_pool, + skb_shinfo(skb)->nr_frags - i); + if (err) + goto out; + + /* Will perform the exchange later */ + dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx]; + dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov); + + offset += copy; + remaining_len -= copy; + + err = put_cmsg(msg, SOL_SOCKET, + SO_DEVMEM_DMABUF, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + if (!err) + err = -ETOOSMALL; + goto out; + } + + atomic_long_inc(&niov->pp_ref_count); + tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); + + sent += copy; + + if (remaining_len == 0) + goto out; + } + start = end; + } + + tcp_xa_pool_commit(sk, &tcp_xa_pool); + if (!remaining_len) + goto out; + + /* if remaining_len is not satisfied yet, we need to go to the + * next frag in the frag_list to satisfy remaining_len. + */ + skb = skb_shinfo(skb)->frag_list ?: skb->next; + + offset = offset - start; + } while (skb); + + if (remaining_len) { + err = -EFAULT; + goto out; + } + +out: + tcp_xa_pool_commit(sk, &tcp_xa_pool); + if (!sent) + sent = err; + + return sent; +} + /* * This routine copies from a sock struct into the user buffer. * @@ -2335,6 +2558,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int *cmsg_flags) { struct tcp_sock *tp = tcp_sk(sk); + int last_copied_dmabuf = -1; /* uninitialized */ int copied = 0; u32 peek_seq; u32 *seq; @@ -2514,15 +2738,44 @@ found_ok_skb: } if (!(flags & MSG_TRUNC)) { - err = skb_copy_datagram_msg(skb, offset, msg, used); - if (err) { - /* Exception. Bailout! */ - if (!copied) - copied = -EFAULT; + if (last_copied_dmabuf != -1 && + last_copied_dmabuf != !skb_frags_readable(skb)) break; + + if (skb_frags_readable(skb)) { + err = skb_copy_datagram_msg(skb, offset, msg, + used); + if (err) { + /* Exception. Bailout! */ + if (!copied) + copied = -EFAULT; + break; + } + } else { + if (!(flags & MSG_SOCK_DEVMEM)) { + /* dmabuf skbs can only be received + * with the MSG_SOCK_DEVMEM flag. + */ + if (!copied) + copied = -EFAULT; + + break; + } + + err = tcp_recvmsg_dmabuf(sk, skb, offset, msg, + used); + if (err <= 0) { + if (!copied) + copied = -EFAULT; + + break; + } + used = err; } } + last_copied_dmabuf = !skb_frags_readable(skb); + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e37488d3453f..9f314dfa1490 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5391,6 +5391,9 @@ restart: 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); @@ -5411,17 +5414,20 @@ restart: 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); @@ -5463,7 +5469,8 @@ restart: 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_ipv4.c b/net/ipv4/tcp_ipv4.c index eb631e66ee03..5afe5e57c89b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -79,6 +79,7 @@ #include <linux/seq_file.h> #include <linux/inetdevice.h> #include <linux/btf_ids.h> +#include <linux/skbuff_ref.h> #include <crypto/hash.h> #include <linux/scatterlist.h> @@ -2512,10 +2513,25 @@ static void tcp_md5sig_info_free_rcu(struct rcu_head *head) } #endif +static void tcp_release_user_frags(struct sock *sk) +{ +#ifdef CONFIG_PAGE_POOL + unsigned long index; + void *netmem; + + xa_for_each(&sk->sk_user_frags, index, netmem) + WARN_ON_ONCE(!napi_pp_put_page((__force netmem_ref)netmem)); +#endif +} + void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + tcp_release_user_frags(sk); + + xa_destroy(&sk->sk_user_frags); + trace_tcp_destroy_sock(sk); tcp_clear_xmit_timers(sk); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ad562272db2e..bb1fe1ba867a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -628,6 +628,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); + xa_init_flags(&newsk->sk_user_frags, XA_FLAGS_ALLOC1); + return newsk; } EXPORT_SYMBOL(tcp_create_openreq_child); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index cdd0def14427..4fd746bd4d54 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/ipv6/esp6.c b/net/ipv6/esp6.c index 3920e8aa1031..b2400c226a32 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -132,7 +132,8 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - skb_page_unref(sg_page(sg), skb->pp_recycle); + skb_page_unref(page_to_netmem(sg_page(sg)), + skb->pp_recycle); } #ifdef CONFIG_INET6_ESPINTCP diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 4a364cdd445e..a705ec214254 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) diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index c0e0204b9630..6b2756f95629 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -211,6 +211,11 @@ int xp_assign_dev(struct xsk_buff_pool *pool, goto err_unreg_pool; } + if (dev_get_min_mp_channel_count(netdev)) { + err = -EBUSY; + goto err_unreg_pool; + } + bpf.command = XDP_SETUP_XSK_POOL; bpf.xsk.pool = pool; bpf.xsk.queue_id = queue_id; diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 43742ac5b00d..7c308f04e7a0 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -93,6 +93,7 @@ enum { NETDEV_A_PAGE_POOL_INFLIGHT, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, NETDEV_A_PAGE_POOL_DETACH_TIME, + NETDEV_A_PAGE_POOL_DMABUF, __NETDEV_A_PAGE_POOL_MAX, NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1) @@ -131,6 +132,7 @@ enum { NETDEV_A_QUEUE_IFINDEX, NETDEV_A_QUEUE_TYPE, NETDEV_A_QUEUE_NAPI_ID, + NETDEV_A_QUEUE_DMABUF, __NETDEV_A_QUEUE_MAX, NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) @@ -174,6 +176,16 @@ enum { }; enum { + NETDEV_A_DMABUF_IFINDEX = 1, + NETDEV_A_DMABUF_QUEUES, + NETDEV_A_DMABUF_FD, + NETDEV_A_DMABUF_ID, + + __NETDEV_A_DMABUF_MAX, + NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1) +}; + +enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, NETDEV_CMD_DEV_DEL_NTF, @@ -186,6 +198,7 @@ enum { NETDEV_CMD_QUEUE_GET, NETDEV_CMD_NAPI_GET, NETDEV_CMD_QSTATS_GET, + NETDEV_CMD_BIND_RX, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/tools/net/ynl/lib/.gitignore b/tools/net/ynl/lib/.gitignore index c18dd8d83cee..296c4035dbf2 100644 --- a/tools/net/ynl/lib/.gitignore +++ b/tools/net/ynl/lib/.gitignore @@ -1 +1,2 @@ __pycache__/ +*.d diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 923bf098e2eb..1c04c780db66 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 22a5d6a7c3f3..649f1fe0dc46 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -97,6 +97,11 @@ 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 @@ -106,6 +111,10 @@ 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 000000000000..64d6805381c5 --- /dev/null +++ b/tools/testing/selftests/net/ncdevmem.c @@ -0,0 +1,570 @@ +// 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"); +} + +#define run_command(cmd, ...) \ + ({ \ + char command[256]; \ + memset(command, 0, sizeof(command)); \ + snprintf(command, sizeof(command), cmd, ##__VA_ARGS__); \ + printf("Running: %s\n", command); \ + system(command); \ + }) + +static int reset_flow_steering(void) +{ + int ret = 0; + + ret = run_command("sudo ethtool -K %s ntuple off", ifname); + if (ret) + return ret; + + return run_command("sudo ethtool -K %s ntuple on", ifname); +} + +static int configure_headersplit(bool on) +{ + return run_command("sudo ethtool -G %s tcp-data-split %s", ifname, + on ? "on" : "off"); +} + +static int configure_rss(void) +{ + return run_command("sudo ethtool -X %s equal %d", ifname, start_queue); +} + +static int configure_channels(unsigned int rx, unsigned int tx) +{ + return run_command("sudo ethtool -L %s rx %u tx %u", ifname, rx, tx); +} + +static int configure_flow_steering(void) +{ + return run_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); +} + +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); + + if (reset_flow_steering()) + error(1, 0, "Failed to reset flow steering\n"); + + /* Configure RSS to divert all traffic from our devmem queues */ + if (configure_rss()) + error(1, 0, "Failed to configure rss\n"); + + /* Flow steer our devmem flows to start_queue */ + if (configure_flow_steering()) + error(1, 0, "Failed to configure flow steering\n"); + + 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 */ + if (configure_rss()) + error(1, 0, "rss error\n"); + + queues = calloc(num_queues, sizeof(*queues)); + + if (configure_headersplit(1)) + error(1, 0, "Failed to configure header split\n"); + + if (!bind_rx_queue(ifindex, buf, queues, num_queues, &ys)) + error(1, 0, "Binding empty queues array should have failed\n"); + + 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 (configure_headersplit(0)) + error(1, 0, "Failed to configure header split\n"); + + if (!bind_rx_queue(ifindex, buf, queues, num_queues, &ys)) + error(1, 0, "Configure dmabuf with header split off should have failed\n"); + + if (configure_headersplit(1)) + error(1, 0, "Failed to configure header split\n"); + + 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"); + + /* Deactivating a bound queue should not be legal */ + if (!configure_channels(num_queues, num_queues - 1)) + error(1, 0, "Deactivating a bound queue should be illegal.\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; +} |