libeth: xdp: add helpers for preparing/processing &libeth_xdp_buff

Add convenience helpers to build an &xdp_buff. This means: general
initialization before the NAPI loop, adding head, adding frags etc.
libeth_xdp_process_buff() is the same what everybody have in their
drivers:

dma_sync_for_cpu();

if (!frag) {
	add_head();
	prefetch();
} else {
	add_frag();
}

Note that I don't use net_prefetch(), sticking to the original
prefetch(). In none of my tests prefetching 128 bytes yielded better
perf than 64 bytes. That might differ if the headers are huge enough,
but then additional tunneling etc. overhead takes place, you either
way won't win a lot.

&libeth_xdp_stash is for cases when you exit the polling loop without
finishing building the buff. If that happens, you need to store the
buffer in the queue structure until the next loop and then restore it.
It makes no sense to place a whole full &xdp_buff there. Define a
minimal structure, which would store only the fields essential to
restore it.
I was able to pack it into 16 bytes, which is only 8 bytes bigger
than `struct sk_buff *skb` on x64.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

1 files changed, 151 insertions, 0 deletions

diff --git a/include/net/libeth/xdp.h b/include/net/libeth/xdp.h
index 22bd038decb6..780447cdabc1 100644
--- a/include/net/libeth/xdp.h
+++ b/include/net/libeth/xdp.h
@@ -60,6 +60,42 @@ static_assert(offsetof(struct libeth_xdp_buff, desc) ==
 static_assert(IS_ALIGNED(sizeof(struct xdp_buff_xsk),
 			 __alignof(struct libeth_xdp_buff)));
 
+/**
+ * __LIBETH_XDP_ONSTACK_BUFF - declare a &libeth_xdp_buff on the stack
+ * @name: name of the variable to declare
+ * @...: sizeof() of the driver-private data
+ */
+#define __LIBETH_XDP_ONSTACK_BUFF(name, ...)				      \
+	___LIBETH_XDP_ONSTACK_BUFF(name, ##__VA_ARGS__)
+/**
+ * LIBETH_XDP_ONSTACK_BUFF - declare a &libeth_xdp_buff on the stack
+ * @name: name of the variable to declare
+ * @...: type or variable name of the driver-private data
+ */
+#define LIBETH_XDP_ONSTACK_BUFF(name, ...)				      \
+	__LIBETH_XDP_ONSTACK_BUFF(name, __libeth_xdp_priv_sz(__VA_ARGS__))
+
+#define ___LIBETH_XDP_ONSTACK_BUFF(name, ...)				      \
+	__DEFINE_FLEX(struct libeth_xdp_buff, name, priv,		      \
+		      LIBETH_XDP_PRIV_SZ(__VA_ARGS__ + 0),		      \
+		      __uninitialized);					      \
+	LIBETH_XDP_ASSERT_PRIV_SZ(__VA_ARGS__ + 0)
+
+#define __libeth_xdp_priv_sz(...)					      \
+	CONCATENATE(__libeth_xdp_psz, COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__)
+
+#define __libeth_xdp_psz0(...)
+#define __libeth_xdp_psz1(...)		sizeof(__VA_ARGS__)
+
+#define LIBETH_XDP_PRIV_SZ(sz)						      \
+	(ALIGN(sz, __alignof(struct libeth_xdp_buff)) / sizeof(long))
+
+/* Performs XSK_CHECK_PRIV_TYPE() */
+#define LIBETH_XDP_ASSERT_PRIV_SZ(sz)					      \
+	static_assert(offsetofend(struct xdp_buff_xsk, cb) >=		      \
+		      struct_size_t(struct libeth_xdp_buff, priv,	      \
+				    LIBETH_XDP_PRIV_SZ(sz)))
+
 /* XDPSQ sharing */
 
 DECLARE_STATIC_KEY_FALSE(libeth_xdpsq_share);
@@ -963,6 +999,65 @@ __libeth_xdp_xmit_do_bulk(struct libeth_xdp_tx_bulk *bq,
 
 /* Rx polling path */
 
+void libeth_xdp_load_stash(struct libeth_xdp_buff *dst,
+			   const struct libeth_xdp_buff_stash *src);
+void libeth_xdp_save_stash(struct libeth_xdp_buff_stash *dst,
+			   const struct libeth_xdp_buff *src);
+void __libeth_xdp_return_stash(struct libeth_xdp_buff_stash *stash);
+
+/**
+ * libeth_xdp_init_buff - initialize a &libeth_xdp_buff for Rx NAPI poll
+ * @dst: onstack buffer to initialize
+ * @src: XDP buffer stash placed on the queue
+ * @rxq: registered &xdp_rxq_info corresponding to this queue
+ *
+ * Should be called before the main NAPI polling loop. Loads the content of
+ * the previously saved stash or initializes the buffer from scratch.
+ */
+static inline void
+libeth_xdp_init_buff(struct libeth_xdp_buff *dst,
+		     const struct libeth_xdp_buff_stash *src,
+		     struct xdp_rxq_info *rxq)
+{
+	if (likely(!src->data))
+		dst->data = NULL;
+	else
+		libeth_xdp_load_stash(dst, src);
+
+	dst->base.rxq = rxq;
+}
+
+/**
+ * libeth_xdp_save_buff - save a partially built buffer on a queue
+ * @dst: XDP buffer stash placed on the queue
+ * @src: onstack buffer to save
+ *
+ * Should be called after the main NAPI polling loop. If the loop exited before
+ * the buffer was finished, saves its content on the queue, so that it can be
+ * completed during the next poll. Otherwise, clears the stash.
+ */
+static inline void libeth_xdp_save_buff(struct libeth_xdp_buff_stash *dst,
+					const struct libeth_xdp_buff *src)
+{
+	if (likely(!src->data))
+		dst->data = NULL;
+	else
+		libeth_xdp_save_stash(dst, src);
+}
+
+/**
+ * libeth_xdp_return_stash - free an XDP buffer stash from a queue
+ * @stash: stash to free
+ *
+ * If the queue is about to be destroyed, but it still has an incompleted
+ * buffer stash, this helper should be called to free it.
+ */
+static inline void libeth_xdp_return_stash(struct libeth_xdp_buff_stash *stash)
+{
+	if (stash->data)
+		__libeth_xdp_return_stash(stash);
+}
+
 static inline void libeth_xdp_return_va(const void *data, bool napi)
 {
 	netmem_ref netmem = virt_to_netmem(data);
@@ -1004,6 +1099,62 @@ out:
 	xdp->data = NULL;
 }
 
+bool libeth_xdp_buff_add_frag(struct libeth_xdp_buff *xdp,
+			      const struct libeth_fqe *fqe,
+			      u32 len);
+
+/**
+ * libeth_xdp_prepare_buff - fill &libeth_xdp_buff with head FQE data
+ * @xdp: XDP buffer to attach the head to
+ * @fqe: FQE containing the head buffer
+ * @len: buffer len passed from HW
+ *
+ * Internal, use libeth_xdp_process_buff() instead. Initializes XDP buffer
+ * head with the Rx buffer data: data pointer, length, headroom, and
+ * truesize/tailroom. Zeroes the flags.
+ */
+static inline void libeth_xdp_prepare_buff(struct libeth_xdp_buff *xdp,
+					   const struct libeth_fqe *fqe,
+					   u32 len)
+{
+	const struct page *page = __netmem_to_page(fqe->netmem);
+
+	xdp_init_buff(&xdp->base, fqe->truesize, xdp->base.rxq);
+	xdp_prepare_buff(&xdp->base, page_address(page) + fqe->offset,
+			 page->pp->p.offset, len, true);
+}
+
+/**
+ * libeth_xdp_process_buff - attach Rx buffer to &libeth_xdp_buff
+ * @xdp: XDP buffer to attach the Rx buffer to
+ * @fqe: Rx buffer to process
+ * @len: received data length from the descriptor
+ *
+ * If the XDP buffer is empty, attaches the Rx buffer as head and initializes
+ * the required fields. Otherwise, attaches the buffer as a frag.
+ * Already performs DMA sync-for-CPU and frame start prefetch
+ * (for head buffers only).
+ *
+ * Return: true on success, false if the descriptor must be skipped (empty or
+ * no space for a new frag).
+ */
+static inline bool libeth_xdp_process_buff(struct libeth_xdp_buff *xdp,
+					   const struct libeth_fqe *fqe,
+					   u32 len)
+{
+	if (!libeth_rx_sync_for_cpu(fqe, len))
+		return false;
+
+	if (xdp->data)
+		return libeth_xdp_buff_add_frag(xdp, fqe, len);
+
+	libeth_xdp_prepare_buff(xdp, fqe, len);
+
+	prefetch(xdp->data);
+
+	return true;
+}
+
 /* Tx buffer completion */
 
 void libeth_xdp_return_buff_bulk(const struct skb_shared_info *sinfo,