diff options
Diffstat (limited to 'drivers/net/ethernet/intel/libeth')
| -rw-r--r-- | drivers/net/ethernet/intel/libeth/Kconfig | 15 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/libeth/Makefile | 12 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/libeth/priv.h | 37 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/libeth/rx.c | 273 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/libeth/tx.c | 41 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/libeth/xdp.c | 451 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/libeth/xsk.c | 271 |
7 files changed, 1100 insertions, 0 deletions
diff --git a/drivers/net/ethernet/intel/libeth/Kconfig b/drivers/net/ethernet/intel/libeth/Kconfig new file mode 100644 index 000000000000..2445b979c499 --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/Kconfig @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2024-2025 Intel Corporation + +config LIBETH + tristate "Common Ethernet library (libeth)" if COMPILE_TEST + select PAGE_POOL + help + libeth is a common library containing routines shared between several + drivers, but not yet promoted to the generic kernel API. + +config LIBETH_XDP + tristate "Common XDP library (libeth_xdp)" if COMPILE_TEST + select LIBETH + help + XDP and XSk helpers based on libeth hotpath management. diff --git a/drivers/net/ethernet/intel/libeth/Makefile b/drivers/net/ethernet/intel/libeth/Makefile new file mode 100644 index 000000000000..350bc0b38bad --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2024-2025 Intel Corporation + +obj-$(CONFIG_LIBETH) += libeth.o + +libeth-y := rx.o +libeth-y += tx.o + +obj-$(CONFIG_LIBETH_XDP) += libeth_xdp.o + +libeth_xdp-y += xdp.o +libeth_xdp-y += xsk.o diff --git a/drivers/net/ethernet/intel/libeth/priv.h b/drivers/net/ethernet/intel/libeth/priv.h new file mode 100644 index 000000000000..9b811d31015c --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/priv.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2025 Intel Corporation */ + +#ifndef __LIBETH_PRIV_H +#define __LIBETH_PRIV_H + +#include <linux/types.h> + +/* XDP */ + +enum xdp_action; +struct libeth_xdp_buff; +struct libeth_xdp_tx_frame; +struct skb_shared_info; +struct xdp_frame_bulk; + +extern const struct xsk_tx_metadata_ops libeth_xsktmo_slow; + +void libeth_xsk_tx_return_bulk(const struct libeth_xdp_tx_frame *bq, + u32 count); +u32 libeth_xsk_prog_exception(struct libeth_xdp_buff *xdp, enum xdp_action act, + int ret); + +struct libeth_xdp_ops { + void (*bulk)(const struct skb_shared_info *sinfo, + struct xdp_frame_bulk *bq, bool frags); + void (*xsk)(struct libeth_xdp_buff *xdp); +}; + +void libeth_attach_xdp(const struct libeth_xdp_ops *ops); + +static inline void libeth_detach_xdp(void) +{ + libeth_attach_xdp(NULL); +} + +#endif /* __LIBETH_PRIV_H */ diff --git a/drivers/net/ethernet/intel/libeth/rx.c b/drivers/net/ethernet/intel/libeth/rx.c new file mode 100644 index 000000000000..62521a1f4ec9 --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/rx.c @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2024-2025 Intel Corporation */ + +#define DEFAULT_SYMBOL_NAMESPACE "LIBETH" + +#include <linux/export.h> + +#include <net/libeth/rx.h> + +/* Rx buffer management */ + +/** + * libeth_rx_hw_len_mtu - get the actual buffer size to be passed to HW + * @pp: &page_pool_params of the netdev to calculate the size for + * @max_len: maximum buffer size for a single descriptor + * + * Return: HW-writeable length per one buffer to pass it to the HW accounting: + * MTU the @dev has, HW required alignment, minimum and maximum allowed values, + * and system's page size. + */ +static u32 libeth_rx_hw_len_mtu(const struct page_pool_params *pp, u32 max_len) +{ + u32 len; + + len = READ_ONCE(pp->netdev->mtu) + LIBETH_RX_LL_LEN; + len = ALIGN(len, LIBETH_RX_BUF_STRIDE); + len = min3(len, ALIGN_DOWN(max_len ? : U32_MAX, LIBETH_RX_BUF_STRIDE), + pp->max_len); + + return len; +} + +/** + * libeth_rx_hw_len_truesize - get the short buffer size to be passed to HW + * @pp: &page_pool_params of the netdev to calculate the size for + * @max_len: maximum buffer size for a single descriptor + * @truesize: desired truesize for the buffers + * + * Return: HW-writeable length per one buffer to pass it to the HW ignoring the + * MTU and closest to the passed truesize. Can be used for "short" buffer + * queues to fragment pages more efficiently. + */ +static u32 libeth_rx_hw_len_truesize(const struct page_pool_params *pp, + u32 max_len, u32 truesize) +{ + u32 min, len; + + min = SKB_HEAD_ALIGN(pp->offset + LIBETH_RX_BUF_STRIDE); + truesize = clamp(roundup_pow_of_two(truesize), roundup_pow_of_two(min), + PAGE_SIZE << LIBETH_RX_PAGE_ORDER); + + len = SKB_WITH_OVERHEAD(truesize - pp->offset); + len = ALIGN_DOWN(len, LIBETH_RX_BUF_STRIDE) ? : LIBETH_RX_BUF_STRIDE; + len = min3(len, ALIGN_DOWN(max_len ? : U32_MAX, LIBETH_RX_BUF_STRIDE), + pp->max_len); + + return len; +} + +/** + * libeth_rx_page_pool_params - calculate params with the stack overhead + * @fq: buffer queue to calculate the size for + * @pp: &page_pool_params of the netdev + * + * Set the PP params to will all needed stack overhead (headroom, tailroom) and + * both the HW buffer length and the truesize for all types of buffers. For + * "short" buffers, truesize never exceeds the "wanted" one; for the rest, + * it can be up to the page size. + * + * Return: true on success, false on invalid input params. + */ +static bool libeth_rx_page_pool_params(struct libeth_fq *fq, + struct page_pool_params *pp) +{ + pp->offset = fq->xdp ? LIBETH_XDP_HEADROOM : LIBETH_SKB_HEADROOM; + /* HW-writeable / syncable length per one page */ + pp->max_len = LIBETH_RX_PAGE_LEN(pp->offset); + + /* HW-writeable length per buffer */ + switch (fq->type) { + case LIBETH_FQE_MTU: + fq->buf_len = libeth_rx_hw_len_mtu(pp, fq->buf_len); + break; + case LIBETH_FQE_SHORT: + fq->buf_len = libeth_rx_hw_len_truesize(pp, fq->buf_len, + fq->truesize); + break; + case LIBETH_FQE_HDR: + fq->buf_len = ALIGN(LIBETH_MAX_HEAD, LIBETH_RX_BUF_STRIDE); + break; + default: + return false; + } + + /* Buffer size to allocate */ + fq->truesize = roundup_pow_of_two(SKB_HEAD_ALIGN(pp->offset + + fq->buf_len)); + + return true; +} + +/** + * libeth_rx_page_pool_params_zc - calculate params without the stack overhead + * @fq: buffer queue to calculate the size for + * @pp: &page_pool_params of the netdev + * + * Set the PP params to exclude the stack overhead and both the buffer length + * and the truesize, which are equal for the data buffers. Note that this + * requires separate header buffers to be always active and account the + * overhead. + * With the MTU == ``PAGE_SIZE``, this allows the kernel to enable the zerocopy + * mode. + * + * Return: true on success, false on invalid input params. + */ +static bool libeth_rx_page_pool_params_zc(struct libeth_fq *fq, + struct page_pool_params *pp) +{ + u32 mtu, max; + + pp->offset = 0; + pp->max_len = PAGE_SIZE << LIBETH_RX_PAGE_ORDER; + + switch (fq->type) { + case LIBETH_FQE_MTU: + mtu = READ_ONCE(pp->netdev->mtu); + break; + case LIBETH_FQE_SHORT: + mtu = fq->truesize; + break; + default: + return false; + } + + mtu = roundup_pow_of_two(mtu); + max = min(rounddown_pow_of_two(fq->buf_len ? : U32_MAX), + pp->max_len); + + fq->buf_len = clamp(mtu, LIBETH_RX_BUF_STRIDE, max); + fq->truesize = fq->buf_len; + + return true; +} + +/** + * libeth_rx_fq_create - create a PP with the default libeth settings + * @fq: buffer queue struct to fill + * @napi: &napi_struct covering this PP (no usage outside its poll loops) + * + * Return: %0 on success, -%errno on failure. + */ +int libeth_rx_fq_create(struct libeth_fq *fq, struct napi_struct *napi) +{ + struct page_pool_params pp = { + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .order = LIBETH_RX_PAGE_ORDER, + .pool_size = fq->count, + .nid = fq->nid, + .dev = napi->dev->dev.parent, + .netdev = napi->dev, + .napi = napi, + }; + struct libeth_fqe *fqes; + struct page_pool *pool; + int ret; + + pp.dma_dir = fq->xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; + + if (!fq->hsplit) + ret = libeth_rx_page_pool_params(fq, &pp); + else + ret = libeth_rx_page_pool_params_zc(fq, &pp); + if (!ret) + return -EINVAL; + + pool = page_pool_create(&pp); + if (IS_ERR(pool)) + return PTR_ERR(pool); + + fqes = kvcalloc_node(fq->count, sizeof(*fqes), GFP_KERNEL, fq->nid); + if (!fqes) { + ret = -ENOMEM; + goto err_buf; + } + + ret = xdp_reg_page_pool(pool); + if (ret) + goto err_mem; + + fq->fqes = fqes; + fq->pp = pool; + + return 0; + +err_mem: + kvfree(fqes); +err_buf: + page_pool_destroy(pool); + + return ret; +} +EXPORT_SYMBOL_GPL(libeth_rx_fq_create); + +/** + * libeth_rx_fq_destroy - destroy a &page_pool created by libeth + * @fq: buffer queue to process + */ +void libeth_rx_fq_destroy(struct libeth_fq *fq) +{ + xdp_unreg_page_pool(fq->pp); + kvfree(fq->fqes); + page_pool_destroy(fq->pp); +} +EXPORT_SYMBOL_GPL(libeth_rx_fq_destroy); + +/** + * libeth_rx_recycle_slow - recycle libeth netmem + * @netmem: network memory to recycle + * + * To be used on exceptions or rare cases not requiring fast inline recycling. + */ +void __cold libeth_rx_recycle_slow(netmem_ref netmem) +{ + page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false); +} +EXPORT_SYMBOL_GPL(libeth_rx_recycle_slow); + +/* Converting abstract packet type numbers into a software structure with + * the packet parameters to do O(1) lookup on Rx. + */ + +static const u16 libeth_rx_pt_xdp_oip[] = { + [LIBETH_RX_PT_OUTER_L2] = XDP_RSS_TYPE_NONE, + [LIBETH_RX_PT_OUTER_IPV4] = XDP_RSS_L3_IPV4, + [LIBETH_RX_PT_OUTER_IPV6] = XDP_RSS_L3_IPV6, +}; + +static const u16 libeth_rx_pt_xdp_iprot[] = { + [LIBETH_RX_PT_INNER_NONE] = XDP_RSS_TYPE_NONE, + [LIBETH_RX_PT_INNER_UDP] = XDP_RSS_L4_UDP, + [LIBETH_RX_PT_INNER_TCP] = XDP_RSS_L4_TCP, + [LIBETH_RX_PT_INNER_SCTP] = XDP_RSS_L4_SCTP, + [LIBETH_RX_PT_INNER_ICMP] = XDP_RSS_L4_ICMP, + [LIBETH_RX_PT_INNER_TIMESYNC] = XDP_RSS_TYPE_NONE, +}; + +static const u16 libeth_rx_pt_xdp_pl[] = { + [LIBETH_RX_PT_PAYLOAD_NONE] = XDP_RSS_TYPE_NONE, + [LIBETH_RX_PT_PAYLOAD_L2] = XDP_RSS_TYPE_NONE, + [LIBETH_RX_PT_PAYLOAD_L3] = XDP_RSS_TYPE_NONE, + [LIBETH_RX_PT_PAYLOAD_L4] = XDP_RSS_L4, +}; + +/** + * libeth_rx_pt_gen_hash_type - generate an XDP RSS hash type for a PT + * @pt: PT structure to evaluate + * + * Generates ```hash_type``` field with XDP RSS type values from the parsed + * packet parameters if they're obtained dynamically at runtime. + */ +void libeth_rx_pt_gen_hash_type(struct libeth_rx_pt *pt) +{ + pt->hash_type = 0; + pt->hash_type |= libeth_rx_pt_xdp_oip[pt->outer_ip]; + pt->hash_type |= libeth_rx_pt_xdp_iprot[pt->inner_prot]; + pt->hash_type |= libeth_rx_pt_xdp_pl[pt->payload_layer]; +} +EXPORT_SYMBOL_GPL(libeth_rx_pt_gen_hash_type); + +/* Module */ + +MODULE_DESCRIPTION("Common Ethernet library"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/intel/libeth/tx.c b/drivers/net/ethernet/intel/libeth/tx.c new file mode 100644 index 000000000000..e0167f43d2a8 --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/tx.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2025 Intel Corporation */ + +#define DEFAULT_SYMBOL_NAMESPACE "LIBETH" + +#include <net/libeth/xdp.h> + +#include "priv.h" + +/* Tx buffer completion */ + +DEFINE_STATIC_CALL_NULL(bulk, libeth_xdp_return_buff_bulk); +DEFINE_STATIC_CALL_NULL(xsk, libeth_xsk_buff_free_slow); + +/** + * libeth_tx_complete_any - perform Tx completion for one SQE of any type + * @sqe: Tx buffer to complete + * @cp: polling params + * + * Can be used to complete both regular and XDP SQEs, for example when + * destroying queues. + * When libeth_xdp is not loaded, XDPSQEs won't be handled. + */ +void libeth_tx_complete_any(struct libeth_sqe *sqe, struct libeth_cq_pp *cp) +{ + if (sqe->type >= __LIBETH_SQE_XDP_START) + __libeth_xdp_complete_tx(sqe, cp, static_call(bulk), + static_call(xsk)); + else + libeth_tx_complete(sqe, cp); +} +EXPORT_SYMBOL_GPL(libeth_tx_complete_any); + +/* Module */ + +void libeth_attach_xdp(const struct libeth_xdp_ops *ops) +{ + static_call_update(bulk, ops ? ops->bulk : NULL); + static_call_update(xsk, ops ? ops->xsk : NULL); +} +EXPORT_SYMBOL_GPL(libeth_attach_xdp); diff --git a/drivers/net/ethernet/intel/libeth/xdp.c b/drivers/net/ethernet/intel/libeth/xdp.c new file mode 100644 index 000000000000..d4ac027d9584 --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/xdp.c @@ -0,0 +1,451 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2025 Intel Corporation */ + +#define DEFAULT_SYMBOL_NAMESPACE "LIBETH_XDP" + +#include <linux/export.h> + +#include <net/libeth/xdp.h> + +#include "priv.h" + +/* XDPSQ sharing */ + +DEFINE_STATIC_KEY_FALSE(libeth_xdpsq_share); +EXPORT_SYMBOL_GPL(libeth_xdpsq_share); + +void __libeth_xdpsq_get(struct libeth_xdpsq_lock *lock, + const struct net_device *dev) +{ + bool warn; + + spin_lock_init(&lock->lock); + lock->share = true; + + warn = !static_key_enabled(&libeth_xdpsq_share); + static_branch_inc(&libeth_xdpsq_share); + + if (warn && net_ratelimit()) + netdev_warn(dev, "XDPSQ sharing enabled, possible XDP Tx slowdown\n"); +} +EXPORT_SYMBOL_GPL(__libeth_xdpsq_get); + +void __libeth_xdpsq_put(struct libeth_xdpsq_lock *lock, + const struct net_device *dev) +{ + static_branch_dec(&libeth_xdpsq_share); + + if (!static_key_enabled(&libeth_xdpsq_share) && net_ratelimit()) + netdev_notice(dev, "XDPSQ sharing disabled\n"); + + lock->share = false; +} +EXPORT_SYMBOL_GPL(__libeth_xdpsq_put); + +void __acquires(&lock->lock) +__libeth_xdpsq_lock(struct libeth_xdpsq_lock *lock) +{ + spin_lock(&lock->lock); +} +EXPORT_SYMBOL_GPL(__libeth_xdpsq_lock); + +void __releases(&lock->lock) +__libeth_xdpsq_unlock(struct libeth_xdpsq_lock *lock) +{ + spin_unlock(&lock->lock); +} +EXPORT_SYMBOL_GPL(__libeth_xdpsq_unlock); + +/* XDPSQ clean-up timers */ + +/** + * libeth_xdpsq_init_timer - initialize an XDPSQ clean-up timer + * @timer: timer to initialize + * @xdpsq: queue this timer belongs to + * @lock: corresponding XDPSQ lock + * @poll: queue polling/completion function + * + * XDPSQ clean-up timers must be set up before using at the queue configuration + * time. Set the required pointers and the cleaning callback. + */ +void libeth_xdpsq_init_timer(struct libeth_xdpsq_timer *timer, void *xdpsq, + struct libeth_xdpsq_lock *lock, + void (*poll)(struct work_struct *work)) +{ + timer->xdpsq = xdpsq; + timer->lock = lock; + + INIT_DELAYED_WORK(&timer->dwork, poll); +} +EXPORT_SYMBOL_GPL(libeth_xdpsq_init_timer); + +/* ``XDP_TX`` bulking */ + +static void __cold +libeth_xdp_tx_return_one(const struct libeth_xdp_tx_frame *frm) +{ + if (frm->len_fl & LIBETH_XDP_TX_MULTI) + libeth_xdp_return_frags(frm->data + frm->soff, true); + + libeth_xdp_return_va(frm->data, true); +} + +static void __cold +libeth_xdp_tx_return_bulk(const struct libeth_xdp_tx_frame *bq, u32 count) +{ + for (u32 i = 0; i < count; i++) { + const struct libeth_xdp_tx_frame *frm = &bq[i]; + + if (!(frm->len_fl & LIBETH_XDP_TX_FIRST)) + continue; + + libeth_xdp_tx_return_one(frm); + } +} + +static void __cold libeth_trace_xdp_exception(const struct net_device *dev, + const struct bpf_prog *prog, + u32 act) +{ + trace_xdp_exception(dev, prog, act); +} + +/** + * libeth_xdp_tx_exception - handle Tx exceptions of XDP frames + * @bq: XDP Tx frame bulk + * @sent: number of frames sent successfully (from this bulk) + * @flags: internal libeth_xdp flags (XSk, .ndo_xdp_xmit etc.) + * + * Cold helper used by __libeth_xdp_tx_flush_bulk(), do not call directly. + * Reports XDP Tx exceptions, frees the frames that won't be sent or adjust + * the Tx bulk to try again later. + */ +void __cold libeth_xdp_tx_exception(struct libeth_xdp_tx_bulk *bq, u32 sent, + u32 flags) +{ + const struct libeth_xdp_tx_frame *pos = &bq->bulk[sent]; + u32 left = bq->count - sent; + + if (!(flags & LIBETH_XDP_TX_NDO)) + libeth_trace_xdp_exception(bq->dev, bq->prog, XDP_TX); + + if (!(flags & LIBETH_XDP_TX_DROP)) { + memmove(bq->bulk, pos, left * sizeof(*bq->bulk)); + bq->count = left; + + return; + } + + if (flags & LIBETH_XDP_TX_XSK) + libeth_xsk_tx_return_bulk(pos, left); + else if (!(flags & LIBETH_XDP_TX_NDO)) + libeth_xdp_tx_return_bulk(pos, left); + else + libeth_xdp_xmit_return_bulk(pos, left, bq->dev); + + bq->count = 0; +} +EXPORT_SYMBOL_GPL(libeth_xdp_tx_exception); + +/* .ndo_xdp_xmit() implementation */ + +u32 __cold libeth_xdp_xmit_return_bulk(const struct libeth_xdp_tx_frame *bq, + u32 count, const struct net_device *dev) +{ + u32 n = 0; + + for (u32 i = 0; i < count; i++) { + const struct libeth_xdp_tx_frame *frm = &bq[i]; + dma_addr_t dma; + + if (frm->flags & LIBETH_XDP_TX_FIRST) + dma = *libeth_xdp_xmit_frame_dma(frm->xdpf); + else + dma = dma_unmap_addr(frm, dma); + + dma_unmap_page(dev->dev.parent, dma, dma_unmap_len(frm, len), + DMA_TO_DEVICE); + + /* Actual xdp_frames are freed by the core */ + n += !!(frm->flags & LIBETH_XDP_TX_FIRST); + } + + return n; +} +EXPORT_SYMBOL_GPL(libeth_xdp_xmit_return_bulk); + +/* Rx polling path */ + +/** + * libeth_xdp_load_stash - recreate an &xdp_buff from libeth_xdp buffer stash + * @dst: target &libeth_xdp_buff to initialize + * @src: source stash + * + * External helper used by libeth_xdp_init_buff(), do not call directly. + * Recreate an onstack &libeth_xdp_buff using the stash saved earlier. + * The only field untouched (rxq) is initialized later in the + * abovementioned function. + */ +void libeth_xdp_load_stash(struct libeth_xdp_buff *dst, + const struct libeth_xdp_buff_stash *src) +{ + dst->data = src->data; + dst->base.data_end = src->data + src->len; + dst->base.data_meta = src->data; + dst->base.data_hard_start = src->data - src->headroom; + + dst->base.frame_sz = src->frame_sz; + dst->base.flags = src->flags; +} +EXPORT_SYMBOL_GPL(libeth_xdp_load_stash); + +/** + * libeth_xdp_save_stash - convert &xdp_buff to a libeth_xdp buffer stash + * @dst: target &libeth_xdp_buff_stash to initialize + * @src: source XDP buffer + * + * External helper used by libeth_xdp_save_buff(), do not call directly. + * Use the fields from the passed XDP buffer to initialize the stash on the + * queue, so that a partially received frame can be finished later during + * the next NAPI poll. + */ +void libeth_xdp_save_stash(struct libeth_xdp_buff_stash *dst, + const struct libeth_xdp_buff *src) +{ + dst->data = src->data; + dst->headroom = src->data - src->base.data_hard_start; + dst->len = src->base.data_end - src->data; + + dst->frame_sz = src->base.frame_sz; + dst->flags = src->base.flags; + + WARN_ON_ONCE(dst->flags != src->base.flags); +} +EXPORT_SYMBOL_GPL(libeth_xdp_save_stash); + +void __libeth_xdp_return_stash(struct libeth_xdp_buff_stash *stash) +{ + LIBETH_XDP_ONSTACK_BUFF(xdp); + + libeth_xdp_load_stash(xdp, stash); + libeth_xdp_return_buff_slow(xdp); + + stash->data = NULL; +} +EXPORT_SYMBOL_GPL(__libeth_xdp_return_stash); + +/** + * libeth_xdp_return_buff_slow - free &libeth_xdp_buff + * @xdp: buffer to free/return + * + * Slowpath version of libeth_xdp_return_buff() to be called on exceptions, + * queue clean-ups etc., without unwanted inlining. + */ +void __cold libeth_xdp_return_buff_slow(struct libeth_xdp_buff *xdp) +{ + __libeth_xdp_return_buff(xdp, false); +} +EXPORT_SYMBOL_GPL(libeth_xdp_return_buff_slow); + +/** + * libeth_xdp_buff_add_frag - add frag to XDP buffer + * @xdp: head XDP buffer + * @fqe: Rx buffer containing the frag + * @len: frag length reported by HW + * + * External helper used by libeth_xdp_process_buff(), do not call directly. + * Frees both head and frag buffers on error. + * + * Return: true success, false on error (no space for a new frag). + */ +bool libeth_xdp_buff_add_frag(struct libeth_xdp_buff *xdp, + const struct libeth_fqe *fqe, + u32 len) +{ + netmem_ref netmem = fqe->netmem; + + if (!xdp_buff_add_frag(&xdp->base, netmem, + fqe->offset + netmem_get_pp(netmem)->p.offset, + len, fqe->truesize)) + goto recycle; + + return true; + +recycle: + libeth_rx_recycle_slow(netmem); + libeth_xdp_return_buff_slow(xdp); + + return false; +} +EXPORT_SYMBOL_GPL(libeth_xdp_buff_add_frag); + +/** + * libeth_xdp_prog_exception - handle XDP prog exceptions + * @bq: XDP Tx bulk + * @xdp: buffer to process + * @act: original XDP prog verdict + * @ret: error code if redirect failed + * + * External helper used by __libeth_xdp_run_prog() and + * __libeth_xsk_run_prog_slow(), do not call directly. + * Reports invalid @act, XDP exception trace event and frees the buffer. + * + * Return: libeth_xdp XDP prog verdict. + */ +u32 __cold libeth_xdp_prog_exception(const struct libeth_xdp_tx_bulk *bq, + struct libeth_xdp_buff *xdp, + enum xdp_action act, int ret) +{ + if (act > XDP_REDIRECT) + bpf_warn_invalid_xdp_action(bq->dev, bq->prog, act); + + libeth_trace_xdp_exception(bq->dev, bq->prog, act); + + if (xdp->base.rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) + return libeth_xsk_prog_exception(xdp, act, ret); + + libeth_xdp_return_buff_slow(xdp); + + return LIBETH_XDP_DROP; +} +EXPORT_SYMBOL_GPL(libeth_xdp_prog_exception); + +/* Tx buffer completion */ + +static void libeth_xdp_put_netmem_bulk(netmem_ref netmem, + struct xdp_frame_bulk *bq) +{ + if (unlikely(bq->count == XDP_BULK_QUEUE_SIZE)) + xdp_flush_frame_bulk(bq); + + bq->q[bq->count++] = netmem; +} + +/** + * libeth_xdp_return_buff_bulk - free &xdp_buff as part of a bulk + * @sinfo: shared info corresponding to the buffer + * @bq: XDP frame bulk to store the buffer + * @frags: whether the buffer has frags + * + * Same as xdp_return_frame_bulk(), but for &libeth_xdp_buff, speeds up Tx + * completion of ``XDP_TX`` buffers and allows to free them in same bulks + * with &xdp_frame buffers. + */ +void libeth_xdp_return_buff_bulk(const struct skb_shared_info *sinfo, + struct xdp_frame_bulk *bq, bool frags) +{ + if (!frags) + goto head; + + for (u32 i = 0; i < sinfo->nr_frags; i++) + libeth_xdp_put_netmem_bulk(skb_frag_netmem(&sinfo->frags[i]), + bq); + +head: + libeth_xdp_put_netmem_bulk(virt_to_netmem(sinfo), bq); +} +EXPORT_SYMBOL_GPL(libeth_xdp_return_buff_bulk); + +/* Misc */ + +/** + * libeth_xdp_queue_threshold - calculate XDP queue clean/refill threshold + * @count: number of descriptors in the queue + * + * The threshold is the limit at which RQs start to refill (when the number of + * empty buffers exceeds it) and SQs get cleaned up (when the number of free + * descriptors goes below it). To speed up hotpath processing, threshold is + * always pow-2, closest to 1/4 of the queue length. + * Don't call it on hotpath, calculate and cache the threshold during the + * queue initialization. + * + * Return: the calculated threshold. + */ +u32 libeth_xdp_queue_threshold(u32 count) +{ + u32 quarter, low, high; + + if (likely(is_power_of_2(count))) + return count >> 2; + + quarter = DIV_ROUND_CLOSEST(count, 4); + low = rounddown_pow_of_two(quarter); + high = roundup_pow_of_two(quarter); + + return high - quarter <= quarter - low ? high : low; +} +EXPORT_SYMBOL_GPL(libeth_xdp_queue_threshold); + +/** + * __libeth_xdp_set_features - set XDP features for netdev + * @dev: &net_device to configure + * @xmo: XDP metadata ops (Rx hints) + * @zc_segs: maximum number of S/G frags the HW can transmit + * @tmo: XSk Tx metadata ops (Tx hints) + * + * Set all the features libeth_xdp supports. Only the first argument is + * necessary; without the third one (zero), XSk support won't be advertised. + * Use the non-underscored versions in drivers instead. + */ +void __libeth_xdp_set_features(struct net_device *dev, + const struct xdp_metadata_ops *xmo, + u32 zc_segs, + const struct xsk_tx_metadata_ops *tmo) +{ + xdp_set_features_flag(dev, + NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | + (zc_segs ? NETDEV_XDP_ACT_XSK_ZEROCOPY : 0) | + NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG); + dev->xdp_metadata_ops = xmo; + + tmo = tmo == libeth_xsktmo ? &libeth_xsktmo_slow : tmo; + + dev->xdp_zc_max_segs = zc_segs ? : 1; + dev->xsk_tx_metadata_ops = zc_segs ? tmo : NULL; +} +EXPORT_SYMBOL_GPL(__libeth_xdp_set_features); + +/** + * libeth_xdp_set_redirect - toggle the XDP redirect feature + * @dev: &net_device to configure + * @enable: whether XDP is enabled + * + * Use this when XDPSQs are not always available to dynamically enable + * and disable redirect feature. + */ +void libeth_xdp_set_redirect(struct net_device *dev, bool enable) +{ + if (enable) + xdp_features_set_redirect_target(dev, true); + else + xdp_features_clear_redirect_target(dev); +} +EXPORT_SYMBOL_GPL(libeth_xdp_set_redirect); + +/* Module */ + +static const struct libeth_xdp_ops xdp_ops __initconst = { + .bulk = libeth_xdp_return_buff_bulk, + .xsk = libeth_xsk_buff_free_slow, +}; + +static int __init libeth_xdp_module_init(void) +{ + libeth_attach_xdp(&xdp_ops); + + return 0; +} +module_init(libeth_xdp_module_init); + +static void __exit libeth_xdp_module_exit(void) +{ + libeth_detach_xdp(); +} +module_exit(libeth_xdp_module_exit); + +MODULE_DESCRIPTION("Common Ethernet library - XDP infra"); +MODULE_IMPORT_NS("LIBETH"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/intel/libeth/xsk.c b/drivers/net/ethernet/intel/libeth/xsk.c new file mode 100644 index 000000000000..846e902e31b6 --- /dev/null +++ b/drivers/net/ethernet/intel/libeth/xsk.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2025 Intel Corporation */ + +#define DEFAULT_SYMBOL_NAMESPACE "LIBETH_XDP" + +#include <linux/export.h> + +#include <net/libeth/xsk.h> + +#include "priv.h" + +/* ``XDP_TX`` bulking */ + +void __cold libeth_xsk_tx_return_bulk(const struct libeth_xdp_tx_frame *bq, + u32 count) +{ + for (u32 i = 0; i < count; i++) + libeth_xsk_buff_free_slow(bq[i].xsk); +} + +/* XSk TMO */ + +const struct xsk_tx_metadata_ops libeth_xsktmo_slow = { + .tmo_request_checksum = libeth_xsktmo_req_csum, +}; + +/* Rx polling path */ + +/** + * libeth_xsk_buff_free_slow - free an XSk Rx buffer + * @xdp: buffer to free + * + * Slowpath version of xsk_buff_free() to be used on exceptions, cleanups etc. + * to avoid unwanted inlining. + */ +void libeth_xsk_buff_free_slow(struct libeth_xdp_buff *xdp) +{ + xsk_buff_free(&xdp->base); +} +EXPORT_SYMBOL_GPL(libeth_xsk_buff_free_slow); + +/** + * libeth_xsk_buff_add_frag - add frag to XSk Rx buffer + * @head: head buffer + * @xdp: frag buffer + * + * External helper used by libeth_xsk_process_buff(), do not call directly. + * Frees both main and frag buffers on error. + * + * Return: main buffer with attached frag on success, %NULL on error (no space + * for a new frag). + */ +struct libeth_xdp_buff *libeth_xsk_buff_add_frag(struct libeth_xdp_buff *head, + struct libeth_xdp_buff *xdp) +{ + if (!xsk_buff_add_frag(&head->base, &xdp->base)) + goto free; + + return head; + +free: + libeth_xsk_buff_free_slow(xdp); + libeth_xsk_buff_free_slow(head); + + return NULL; +} +EXPORT_SYMBOL_GPL(libeth_xsk_buff_add_frag); + +/** + * libeth_xsk_buff_stats_frags - update onstack RQ stats with XSk frags info + * @rs: onstack stats to update + * @xdp: buffer to account + * + * External helper used by __libeth_xsk_run_pass(), do not call directly. + * Adds buffer's frags count and total len to the onstack stats. + */ +void libeth_xsk_buff_stats_frags(struct libeth_rq_napi_stats *rs, + const struct libeth_xdp_buff *xdp) +{ + libeth_xdp_buff_stats_frags(rs, xdp); +} +EXPORT_SYMBOL_GPL(libeth_xsk_buff_stats_frags); + +/** + * __libeth_xsk_run_prog_slow - process the non-``XDP_REDIRECT`` verdicts + * @xdp: buffer to process + * @bq: Tx bulk for queueing on ``XDP_TX`` + * @act: verdict to process + * @ret: error code if ``XDP_REDIRECT`` failed + * + * External helper used by __libeth_xsk_run_prog(), do not call directly. + * ``XDP_REDIRECT`` is the most common and hottest verdict on XSk, thus + * it is processed inline. The rest goes here for out-of-line processing, + * together with redirect errors. + * + * Return: libeth_xdp XDP prog verdict. + */ +u32 __libeth_xsk_run_prog_slow(struct libeth_xdp_buff *xdp, + const struct libeth_xdp_tx_bulk *bq, + enum xdp_action act, int ret) +{ + switch (act) { + case XDP_DROP: + xsk_buff_free(&xdp->base); + + return LIBETH_XDP_DROP; + case XDP_TX: + return LIBETH_XDP_TX; + case XDP_PASS: + return LIBETH_XDP_PASS; + default: + break; + } + + return libeth_xdp_prog_exception(bq, xdp, act, ret); +} +EXPORT_SYMBOL_GPL(__libeth_xsk_run_prog_slow); + +/** + * libeth_xsk_prog_exception - handle XDP prog exceptions on XSk + * @xdp: buffer to process + * @act: verdict returned by the prog + * @ret: error code if ``XDP_REDIRECT`` failed + * + * Internal. Frees the buffer and, if the queue uses XSk wakeups, stop the + * current NAPI poll when there are no free buffers left. + * + * Return: libeth_xdp's XDP prog verdict. + */ +u32 __cold libeth_xsk_prog_exception(struct libeth_xdp_buff *xdp, + enum xdp_action act, int ret) +{ + const struct xdp_buff_xsk *xsk; + u32 __ret = LIBETH_XDP_DROP; + + if (act != XDP_REDIRECT) + goto drop; + + xsk = container_of(&xdp->base, typeof(*xsk), xdp); + if (xsk_uses_need_wakeup(xsk->pool) && ret == -ENOBUFS) + __ret = LIBETH_XDP_ABORTED; + +drop: + libeth_xsk_buff_free_slow(xdp); + + return __ret; +} + +/* Refill */ + +/** + * libeth_xskfq_create - create an XSkFQ + * @fq: fill queue to initialize + * + * Allocates the FQEs and initializes the fields used by libeth_xdp: number + * of buffers to refill, refill threshold and buffer len. + * + * Return: %0 on success, -errno otherwise. + */ +int libeth_xskfq_create(struct libeth_xskfq *fq) +{ + fq->fqes = kvcalloc_node(fq->count, sizeof(*fq->fqes), GFP_KERNEL, + fq->nid); + if (!fq->fqes) + return -ENOMEM; + + fq->pending = fq->count; + fq->thresh = libeth_xdp_queue_threshold(fq->count); + fq->buf_len = xsk_pool_get_rx_frame_size(fq->pool); + + return 0; +} +EXPORT_SYMBOL_GPL(libeth_xskfq_create); + +/** + * libeth_xskfq_destroy - destroy an XSkFQ + * @fq: fill queue to destroy + * + * Zeroes the used fields and frees the FQEs array. + */ +void libeth_xskfq_destroy(struct libeth_xskfq *fq) +{ + fq->buf_len = 0; + fq->thresh = 0; + fq->pending = 0; + + kvfree(fq->fqes); +} +EXPORT_SYMBOL_GPL(libeth_xskfq_destroy); + +/* .ndo_xsk_wakeup */ + +static void libeth_xsk_napi_sched(void *info) +{ + __napi_schedule_irqoff(info); +} + +/** + * libeth_xsk_init_wakeup - initialize libeth XSk wakeup structure + * @csd: struct to initialize + * @napi: NAPI corresponding to this queue + * + * libeth_xdp uses inter-processor interrupts to perform XSk wakeups. In order + * to do that, the corresponding CSDs must be initialized when creating the + * queues. + */ +void libeth_xsk_init_wakeup(call_single_data_t *csd, struct napi_struct *napi) +{ + INIT_CSD(csd, libeth_xsk_napi_sched, napi); +} +EXPORT_SYMBOL_GPL(libeth_xsk_init_wakeup); + +/** + * libeth_xsk_wakeup - perform an XSk wakeup + * @csd: CSD corresponding to the queue + * @qid: the stack queue index + * + * Try to mark the NAPI as missed first, so that it could be rescheduled. + * If it's not, schedule it on the corresponding CPU using IPIs (or directly + * if already running on it). + */ +void libeth_xsk_wakeup(call_single_data_t *csd, u32 qid) +{ + struct napi_struct *napi = csd->info; + + if (napi_if_scheduled_mark_missed(napi) || + unlikely(!napi_schedule_prep(napi))) + return; + + if (unlikely(qid >= nr_cpu_ids)) + qid %= nr_cpu_ids; + + if (qid != raw_smp_processor_id() && cpu_online(qid)) + smp_call_function_single_async(qid, csd); + else + __napi_schedule(napi); +} +EXPORT_SYMBOL_GPL(libeth_xsk_wakeup); + +/* Pool setup */ + +#define LIBETH_XSK_DMA_ATTR \ + (DMA_ATTR_WEAK_ORDERING | DMA_ATTR_SKIP_CPU_SYNC) + +/** + * libeth_xsk_setup_pool - setup or destroy an XSk pool for a queue + * @dev: target &net_device + * @qid: stack queue index to configure + * @enable: whether to enable or disable the pool + * + * Check that @qid is valid and then map or unmap the pool. + * + * Return: %0 on success, -errno otherwise. + */ +int libeth_xsk_setup_pool(struct net_device *dev, u32 qid, bool enable) +{ + struct xsk_buff_pool *pool; + + pool = xsk_get_pool_from_qid(dev, qid); + if (!pool) + return -EINVAL; + + if (enable) + return xsk_pool_dma_map(pool, dev->dev.parent, + LIBETH_XSK_DMA_ATTR); + else + xsk_pool_dma_unmap(pool, LIBETH_XSK_DMA_ATTR); + + return 0; +} +EXPORT_SYMBOL_GPL(libeth_xsk_setup_pool); |