include/net/xdp_sock_drv.h

/* SPDX-License-Identifier: GPL-2.0 */
/* Interface for implementing AF_XDP zero-copy support in drivers.
 * Copyright(c) 2020 Intel Corporation.
 */

#ifndef _LINUX_XDP_SOCK_DRV_H
#define _LINUX_XDP_SOCK_DRV_H

#include <net/xdp_sock.h>
#include <net/xsk_buff_pool.h>

#define XDP_UMEM_MIN_CHUNK_SHIFT 11
#define XDP_UMEM_MIN_CHUNK_SIZE (1 << XDP_UMEM_MIN_CHUNK_SHIFT)

#define NETDEV_XDP_ACT_XSK	(NETDEV_XDP_ACT_BASIC |		\
				 NETDEV_XDP_ACT_REDIRECT |	\
				 NETDEV_XDP_ACT_XSK_ZEROCOPY)

struct xsk_cb_desc {
	void *src;
	u8 off;
	u8 bytes;
};

#ifdef CONFIG_XDP_SOCKETS

void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries);
bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc);
u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max);
void xsk_tx_release(struct xsk_buff_pool *pool);
struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
					    u16 queue_id);
void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool);
void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool);
void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool);
void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool);
bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool);

static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool)
{
	return XDP_PACKET_HEADROOM + pool->headroom;
}

static inline u32 xsk_pool_get_tailroom(bool mbuf)
{
	return mbuf ? SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : 0;
}

static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool)
{
	return pool->chunk_size;
}

static inline u32 __xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
{
	return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool);
}

static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
{
	u32 frame_size =  __xsk_pool_get_rx_frame_size(pool);
	struct xdp_umem *umem = pool->umem;
	bool mbuf;

	/* Reserve tailroom only for zero-copy pools that opted into
	 * multi-buffer. The reserved area is used for skb_shared_info,
	 * matching the XDP core's xdp_data_hard_end() layout.
	 */
	mbuf = pool->dev && (umem->flags & XDP_UMEM_SG_FLAG);
	frame_size -= xsk_pool_get_tailroom(mbuf);

	return ALIGN_DOWN(frame_size, 128);
}

static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool)
{
	return pool->unaligned ? 0 : xsk_pool_get_chunk_size(pool);
}

static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
					 struct xdp_rxq_info *rxq)
{
	xp_set_rxq_info(pool, rxq);
}

static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
				    struct xsk_cb_desc *desc)
{
	xp_fill_cb(pool, desc);
}

static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
				      unsigned long attrs)
{
	xp_dma_unmap(pool, attrs);
}

static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool,
				   struct device *dev, unsigned long attrs)
{
	struct xdp_umem *umem = pool->umem;

	return xp_dma_map(pool, dev, attrs, umem->pgs, umem->npgs);
}

static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp)
{
	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);

	return xp_get_dma(xskb);
}

static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp)
{
	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);

	return xp_get_frame_dma(xskb);
}

static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
{
	return xp_alloc(pool);
}

static inline bool xsk_is_eop_desc(const struct xdp_desc *desc)
{
	return !xp_mb_desc(desc);
}

/* Returns as many entries as possible up to max. 0 <= N <= max. */
static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
{
	return xp_alloc_batch(pool, xdp, max);
}

static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
{
	return xp_can_alloc(pool, count);
}

static inline void xsk_buff_free(struct xdp_buff *xdp)
{
	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
	struct list_head *xskb_list = &xskb->pool->xskb_list;
	struct xdp_buff_xsk *pos, *tmp;

	if (likely(!xdp_buff_has_frags(xdp)))
		goto out;

	list_for_each_entry_safe(pos, tmp, xskb_list, list_node) {
		list_del_init(&pos->list_node);
		xp_free(pos);
	}

	xdp_get_shared_info_from_buff(xdp)->nr_frags = 0;
out:
	xp_free(xskb);
}

static inline bool xsk_buff_add_frag(struct xdp_buff *head,
				     struct xdp_buff *xdp)
{
	const void *data = xdp->data;
	struct xdp_buff_xsk *frag;

	if (!__xdp_buff_add_frag(head, virt_to_netmem(data),
				 offset_in_page(data), xdp->data_end - data,
				 xdp->frame_sz, false))
		return false;

	frag = container_of(xdp, struct xdp_buff_xsk, xdp);
	list_add_tail(&frag->list_node, &frag->pool->xskb_list);

	return true;
}

static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
{
	struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
	struct xdp_buff *ret = NULL;
	struct xdp_buff_xsk *frag;

	frag = list_first_entry_or_null(&xskb->pool->xskb_list,
					struct xdp_buff_xsk, list_node);
	if (frag) {
		list_del_init(&frag->list_node);
		ret = &frag->xdp;
	}

	return ret;
}

static inline void xsk_buff_del_frag(struct xdp_buff *xdp)
{
	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);

	list_del_init(&xskb->list_node);
}

static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first)
{
	struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
	struct xdp_buff_xsk *frag;

	frag = list_first_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk,
				list_node);
	return &frag->xdp;
}

static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
{
	struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
	struct xdp_buff_xsk *frag;

	frag = list_last_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk,
			       list_node);
	return &frag->xdp;
}

static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
{
	xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM;
	xdp->data_meta = xdp->data;
	xdp->data_end = xdp->data + size;
	xdp->flags = 0;
}

static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
					      u64 addr)
{
	return xp_raw_get_dma(pool, addr);
}

static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
{
	return xp_raw_get_data(pool, addr);
}

/**
 * xsk_buff_raw_get_ctx - get &xdp_desc context
 * @pool: XSk buff pool desc address belongs to
 * @addr: desc address (from userspace)
 * @options: desc options (from userspace)
 *
 * Wrapper for xp_raw_get_ctx() to be used in drivers, see its kdoc for
 * details.
 *
 * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata
 * pointer, if it is present (initialized to %NULL otherwise).
 */
static inline struct xdp_desc_ctx
xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr, u32 options)
{
	return xp_raw_get_ctx(pool, addr, options);
}

#define XDP_TXMD_FLAGS_VALID ( \
		XDP_TXMD_FLAGS_TIMESTAMP | \
		XDP_TXMD_FLAGS_CHECKSUM | \
		XDP_TXMD_FLAGS_LAUNCH_TIME | \
	0)

static inline bool
xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool,
			   const struct xsk_tx_metadata *meta, u64 *flags)
{
	*flags = READ_ONCE(meta->flags);
	if (*flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
		if (pool->tx_metadata_len <
		    offsetofend(struct xsk_tx_metadata, request.launch_time))
			return false;
	return !(*flags & ~XDP_TXMD_FLAGS_VALID);
}

/**
 *  xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission
 *  and call appropriate xsk_tx_metadata_ops operation.
 *  @pool: pointer to AF_XDP buffer pool, used to validate the metadata
 *  @pmeta: pointer to pointer to AF_XDP metadata area
 *  @ops: pointer to struct xsk_tx_metadata_ops
 *  @priv: pointer to driver-private area
 *
 *  This function should be called by the networking device when
 *  it prepares AF_XDP egress packet.
 */
static inline void
xsk_tx_metadata_request(const struct xsk_buff_pool *pool,
			struct xsk_tx_metadata **pmeta,
			const struct xsk_tx_metadata_ops *ops, void *priv)
{
	const struct xsk_tx_metadata *meta = *pmeta;
	u64 flags;

	if (!meta)
		return;

	if (unlikely(!xsk_buff_valid_tx_metadata(pool, meta, &flags))) {
		*pmeta = NULL;
		return; /* no way to signal the error to the user */
	}

	if (ops->tmo_request_launch_time)
		if (flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
			ops->tmo_request_launch_time(
				READ_ONCE(meta->request.launch_time), priv);

	if (ops->tmo_request_timestamp)
		if (flags & XDP_TXMD_FLAGS_TIMESTAMP)
			ops->tmo_request_timestamp(priv);

	if (ops->tmo_request_checksum)
		if (flags & XDP_TXMD_FLAGS_CHECKSUM)
			ops->tmo_request_checksum(
				READ_ONCE(meta->request.csum_start),
				READ_ONCE(meta->request.csum_offset), priv);

	if (!(flags & XDP_TXMD_FLAGS_TIMESTAMP))
		*pmeta = NULL;
}

static inline struct xsk_tx_metadata *
__xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data,
			unsigned int options)
{
	if (!pool->tx_metadata_len || !(options & XDP_TX_METADATA))
		return NULL;

	return data - pool->tx_metadata_len;
}

static inline struct xsk_tx_metadata *
xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr, u32 options)
{
	return __xsk_buff_get_metadata(pool, xp_raw_get_data(pool, addr),
				       options);
}

static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
{
	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);

	xp_dma_sync_for_cpu(xskb);
}

static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool,
						    dma_addr_t dma,
						    size_t size)
{
	xp_dma_sync_for_device(pool, dma, size);
}

#else

static inline void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries)
{
}

static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool,
				    struct xdp_desc *desc)
{
	return false;
}

static inline u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max)
{
	return 0;
}

static inline void xsk_tx_release(struct xsk_buff_pool *pool)
{
}

static inline struct xsk_buff_pool *
xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id)
{
	return NULL;
}

static inline void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
{
}

static inline void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool)
{
}

static inline void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool)
{
}

static inline void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool)
{
}

static inline bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool)
{
	return false;
}

static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool)
{
	return 0;
}

static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool)
{
	return 0;
}

static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
{
	return 0;
}

static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool)
{
	return 0;
}

static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
					 struct xdp_rxq_info *rxq)
{
}

static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
				    struct xsk_cb_desc *desc)
{
}

static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
				      unsigned long attrs)
{
}

static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool,
				   struct device *dev, unsigned long attrs)
{
	return 0;
}

static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp)
{
	return 0;
}

static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp)
{
	return 0;
}

static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
{
	return NULL;
}

static inline bool xsk_is_eop_desc(const struct xdp_desc *desc)
{
	return false;
}

static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
{
	return 0;
}

static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
{
	return false;
}

static inline void xsk_buff_free(struct xdp_buff *xdp)
{
}

static inline bool xsk_buff_add_frag(struct xdp_buff *head,
				     struct xdp_buff *xdp)
{
	return false;
}

static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
{
	return NULL;
}

static inline void xsk_buff_del_frag(struct xdp_buff *xdp)
{
}

static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first)
{
	return NULL;
}

static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
{
	return NULL;
}

static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
{
}

static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
					      u64 addr)
{
	return 0;
}

static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
{
	return NULL;
}

static inline struct xdp_desc_ctx
xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr, u32 options)
{
	return (struct xdp_desc_ctx){ };
}

static inline bool
xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool,
			   const struct xsk_tx_metadata *meta, u64 *flags)
{
	return false;
}

static inline void
xsk_tx_metadata_request(const struct xsk_buff_pool *pool,
			struct xsk_tx_metadata **pmeta,
			const struct xsk_tx_metadata_ops *ops, void *priv)
{
}

static inline struct xsk_tx_metadata *
__xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data,
			unsigned int options)
{
	return NULL;
}

static inline struct xsk_tx_metadata *
xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr, u32 options)
{
	return NULL;
}

static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
{
}

static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool,
						    dma_addr_t dma,
						    size_t size)
{
}

#endif /* CONFIG_XDP_SOCKETS */

#endif /* _LINUX_XDP_SOCK_DRV_H */