libeth: add Rx buffer management

Add a couple intuitive helpers to hide Rx buffer implementation details
in the library and not multiplicate it between drivers. The settings are
sorta optimized for 100G+ NICs, but nothing really HW-specific here.
Use the new page_pool_dev_alloc() to dynamically switch between
split-page and full-page modes depending on MTU, page size, required
headroom etc. For example, on x86_64 with the default driver settings
each page is shared between 2 buffers. Turning on XDP (not in this
series) -> increasing headroom requirement pushes truesize out of 2048
boundary, leading to that each buffer starts getting a full page.
The "ceiling" limit is %PAGE_SIZE, as only order-0 pages are used to
avoid compound overhead. For the above architecture, this means maximum
linear frame size of 3712 w/o XDP.
Not that &libeth_buf_queue is not a complete queue/ring structure for
now, rather a shim, but eventually the libeth-enabled drivers will move
to it, with iavf being the first one.

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

2 files changed, 99 insertions, 0 deletions

diff --git a/drivers/net/ethernet/intel/libeth/Kconfig b/drivers/net/ethernet/intel/libeth/Kconfig
index af970a63c227..480293b71dbc 100644
--- a/drivers/net/ethernet/intel/libeth/Kconfig
+++ b/drivers/net/ethernet/intel/libeth/Kconfig
@@ -3,6 +3,7 @@
 
 config LIBETH
 	tristate
+	select PAGE_POOL
 	help
 	  libeth is a common library containing routines shared between several
 	  drivers, but not yet promoted to the generic kernel API.
diff --git a/drivers/net/ethernet/intel/libeth/rx.c b/drivers/net/ethernet/intel/libeth/rx.c
index 879c4dfd6a4e..6221b88c34ac 100644
--- a/drivers/net/ethernet/intel/libeth/rx.c
+++ b/drivers/net/ethernet/intel/libeth/rx.c
@@ -3,6 +3,104 @@
 
 #include <net/libeth/rx.h>
 
+/* Rx buffer management */
+
+/**
+ * libeth_rx_hw_len - 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(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_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,
+		.dma_dir	= DMA_FROM_DEVICE,
+		.offset		= LIBETH_SKB_HEADROOM,
+	};
+	struct libeth_fqe *fqes;
+	struct page_pool *pool;
+
+	/* HW-writeable / syncable length per one page */
+	pp.max_len = LIBETH_RX_PAGE_LEN(pp.offset);
+
+	/* HW-writeable length per buffer */
+	fq->buf_len = libeth_rx_hw_len(&pp, fq->buf_len);
+	/* Buffer size to allocate */
+	fq->truesize = roundup_pow_of_two(SKB_HEAD_ALIGN(pp.offset +
+							 fq->buf_len));
+
+	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)
+		goto err_buf;
+
+	fq->fqes = fqes;
+	fq->pp = pool;
+
+	return 0;
+
+err_buf:
+	page_pool_destroy(pool);
+
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_create, LIBETH);
+
+/**
+ * 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)
+{
+	kvfree(fq->fqes);
+	page_pool_destroy(fq->pp);
+}
+EXPORT_SYMBOL_NS_GPL(libeth_rx_fq_destroy, LIBETH);
+
+/**
+ * libeth_rx_recycle_slow - recycle a libeth page from the NAPI context
+ * @page: page to recycle
+ *
+ * To be used on exceptions or rare cases not requiring fast inline recycling.
+ */
+void libeth_rx_recycle_slow(struct page *page)
+{
+	page_pool_recycle_direct(page->pp, page);
+}
+EXPORT_SYMBOL_NS_GPL(libeth_rx_recycle_slow, LIBETH);
+
 /* Converting abstract packet type numbers into a software structure with
  * the packet parameters to do O(1) lookup on Rx.
  */