Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue

Tony Nguyen says:

====================
net: intel: start The Great Code Dedup + Page Pool for iavf

Alexander Lobakin says:

Here's a two-shot: introduce {,Intel} Ethernet common library (libeth and
libie) and switch iavf to Page Pool. Details are in the commit messages;
here's a summary:

Not a secret there's a ton of code duplication between two and more Intel
ethernet modules. Before introducing new changes, which would need to be
copied over again, start decoupling the already existing duplicate
functionality into a new module, which will be shared between several
Intel Ethernet drivers. The first name that came to my mind was
"libie" -- "Intel Ethernet common library". Also this sounds like
"lovelie" (-> one word, no "lib I E" pls) and can be expanded as
"lib Internet Explorer" :P
The "generic", pure-software part is placed separately, so that it can be
easily reused in any driver by any vendor without linking to the Intel
pre-200G guts. In a few words, it's something any modern driver does the
same way, but nobody moved it level up (yet).
The series is only the beginning. From now on, adding every new feature
or doing any good driver refactoring will remove much more lines than add
for quite some time. There's a basic roadmap with some deduplications
planned already, not speaking of that touching every line now asks:
"can I share this?". The final destination is very ambitious: have only
one unified driver for at least i40e, ice, iavf, and idpf with a struct
ops for each generation. That's never gonna happen, right? But you still
can at least try.
PP conversion for iavf lands within the same series as these two are tied
closely. libie will support Page Pool model only, so that a driver can't
use much of the lib until it's converted. iavf is only the example, the
rest will eventually be converted soon on a per-driver basis. That is
when it gets really interesting. Stay tech.

* '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
  MAINTAINERS: add entry for libeth and libie
  iavf: switch to Page Pool
  iavf: pack iavf_ring more efficiently
  libeth: add Rx buffer management
  page_pool: add DMA-sync-for-CPU inline helper
  page_pool: constify some read-only function arguments
  slab: introduce kvmalloc_array_node() and kvcalloc_node()
  iavf: drop page splitting and recycling
  iavf: kill "legacy-rx" for good
  net: intel: introduce {, Intel} Ethernet common library
====================

Link: https://lore.kernel.org/r/20240424203559.3420468-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 338 insertions, 9 deletions

diff --git a/include/linux/net/intel/libie/rx.h b/include/linux/net/intel/libie/rx.h
new file mode 100644
index 00000000000000..8e97775f1d6632
--- /dev/null
+++ b/include/linux/net/intel/libie/rx.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2024 Intel Corporation */
+
+#ifndef __LIBIE_RX_H
+#define __LIBIE_RX_H
+
+#include <net/libeth/rx.h>
+
+/* Rx buffer management */
+
+/* The largest size for a single descriptor as per HW */
+#define LIBIE_MAX_RX_BUF_LEN	9728U
+/* "True" HW-writeable space: minimum from SW and HW values */
+#define LIBIE_RX_BUF_LEN(hr)	min_t(u32, LIBETH_RX_PAGE_LEN(hr),	\
+				      LIBIE_MAX_RX_BUF_LEN)
+
+/* The maximum frame size as per HW (S/G) */
+#define __LIBIE_MAX_RX_FRM_LEN	16382U
+/* ATST, HW can chain up to 5 Rx descriptors */
+#define LIBIE_MAX_RX_FRM_LEN(hr)					\
+	min_t(u32, __LIBIE_MAX_RX_FRM_LEN, LIBIE_RX_BUF_LEN(hr) * 5)
+/* Maximum frame size minus LL overhead */
+#define LIBIE_MAX_MTU							\
+	(LIBIE_MAX_RX_FRM_LEN(LIBETH_MAX_HEADROOM) - LIBETH_RX_LL_LEN)
+
+/* O(1) converting i40e/ice/iavf's 8/10-bit hardware packet type to a parsed
+ * bitfield struct.
+ */
+
+#define LIBIE_RX_PT_NUM		154
+
+extern const struct libeth_rx_pt libie_rx_pt_lut[LIBIE_RX_PT_NUM];
+
+/**
+ * libie_rx_pt_parse - convert HW packet type to software bitfield structure
+ * @pt: 10-bit hardware packet type value from the descriptor
+ *
+ * ```libie_rx_pt_lut``` must be accessed only using this wrapper.
+ *
+ * Return: parsed bitfield struct corresponding to the provided ptype.
+ */
+static inline struct libeth_rx_pt libie_rx_pt_parse(u32 pt)
+{
+	if (unlikely(pt >= LIBIE_RX_PT_NUM))
+		pt = 0;
+
+	return libie_rx_pt_lut[pt];
+}
+
+#endif /* __LIBIE_RX_H */
diff --git a/include/linux/slab.h b/include/linux/slab.h
index e53cbfa1832558..d1d1fa5e798306 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -774,14 +774,27 @@ static inline __alloc_size(1) void *kvzalloc(size_t size, gfp_t flags)
 	return kvmalloc(size, flags | __GFP_ZERO);
 }
 
-static inline __alloc_size(1, 2) void *kvmalloc_array(size_t n, size_t size, gfp_t flags)
+static inline __alloc_size(1, 2) void *
+kvmalloc_array_node(size_t n, size_t size, gfp_t flags, int node)
 {
 	size_t bytes;
 
 	if (unlikely(check_mul_overflow(n, size, &bytes)))
 		return NULL;
 
-	return kvmalloc(bytes, flags);
+	return kvmalloc_node(bytes, flags, node);
+}
+
+static inline __alloc_size(1, 2) void *
+kvmalloc_array(size_t n, size_t size, gfp_t flags)
+{
+	return kvmalloc_array_node(n, size, flags, NUMA_NO_NODE);
+}
+
+static inline __alloc_size(1, 2) void *
+kvcalloc_node(size_t n, size_t size, gfp_t flags, int node)
+{
+	return kvmalloc_array_node(n, size, flags | __GFP_ZERO, node);
 }
 
 static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t flags)
diff --git a/include/net/libeth/rx.h b/include/net/libeth/rx.h
new file mode 100644
index 00000000000000..f29ea3e34c6cae
--- /dev/null
+++ b/include/net/libeth/rx.h
@@ -0,0 +1,242 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2024 Intel Corporation */
+
+#ifndef __LIBETH_RX_H
+#define __LIBETH_RX_H
+
+#include <linux/if_vlan.h>
+
+#include <net/page_pool/helpers.h>
+#include <net/xdp.h>
+
+/* Rx buffer management */
+
+/* Space reserved in front of each frame */
+#define LIBETH_SKB_HEADROOM	(NET_SKB_PAD + NET_IP_ALIGN)
+/* Maximum headroom for worst-case calculations */
+#define LIBETH_MAX_HEADROOM	LIBETH_SKB_HEADROOM
+/* Link layer / L2 overhead: Ethernet, 2 VLAN tags (C + S), FCS */
+#define LIBETH_RX_LL_LEN	(ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN)
+
+/* Always use order-0 pages */
+#define LIBETH_RX_PAGE_ORDER	0
+/* Pick a sane buffer stride and align to a cacheline boundary */
+#define LIBETH_RX_BUF_STRIDE	SKB_DATA_ALIGN(128)
+/* HW-writeable space in one buffer: truesize - headroom/tailroom, aligned */
+#define LIBETH_RX_PAGE_LEN(hr)						  \
+	ALIGN_DOWN(SKB_MAX_ORDER(hr, LIBETH_RX_PAGE_ORDER),		  \
+		   LIBETH_RX_BUF_STRIDE)
+
+/**
+ * struct libeth_fqe - structure representing an Rx buffer (fill queue element)
+ * @page: page holding the buffer
+ * @offset: offset from the page start (to the headroom)
+ * @truesize: total space occupied by the buffer (w/ headroom and tailroom)
+ *
+ * Depending on the MTU, API switches between one-page-per-frame and shared
+ * page model (to conserve memory on bigger-page platforms). In case of the
+ * former, @offset is always 0 and @truesize is always ```PAGE_SIZE```.
+ */
+struct libeth_fqe {
+	struct page		*page;
+	u32			offset;
+	u32			truesize;
+} __aligned_largest;
+
+/**
+ * struct libeth_fq - structure representing a buffer (fill) queue
+ * @fp: hotpath part of the structure
+ * @pp: &page_pool for buffer management
+ * @fqes: array of Rx buffers
+ * @truesize: size to allocate per buffer, w/overhead
+ * @count: number of descriptors/buffers the queue has
+ * @buf_len: HW-writeable length per each buffer
+ * @nid: ID of the closest NUMA node with memory
+ */
+struct libeth_fq {
+	struct_group_tagged(libeth_fq_fp, fp,
+		struct page_pool	*pp;
+		struct libeth_fqe	*fqes;
+
+		u32			truesize;
+		u32			count;
+	);
+
+	/* Cold fields */
+	u32			buf_len;
+	int			nid;
+};
+
+int libeth_rx_fq_create(struct libeth_fq *fq, struct napi_struct *napi);
+void libeth_rx_fq_destroy(struct libeth_fq *fq);
+
+/**
+ * libeth_rx_alloc - allocate a new Rx buffer
+ * @fq: fill queue to allocate for
+ * @i: index of the buffer within the queue
+ *
+ * Return: DMA address to be passed to HW for Rx on successful allocation,
+ * ```DMA_MAPPING_ERROR``` otherwise.
+ */
+static inline dma_addr_t libeth_rx_alloc(const struct libeth_fq_fp *fq, u32 i)
+{
+	struct libeth_fqe *buf = &fq->fqes[i];
+
+	buf->truesize = fq->truesize;
+	buf->page = page_pool_dev_alloc(fq->pp, &buf->offset, &buf->truesize);
+	if (unlikely(!buf->page))
+		return DMA_MAPPING_ERROR;
+
+	return page_pool_get_dma_addr(buf->page) + buf->offset +
+	       fq->pp->p.offset;
+}
+
+void libeth_rx_recycle_slow(struct page *page);
+
+/**
+ * libeth_rx_sync_for_cpu - synchronize or recycle buffer post DMA
+ * @fqe: buffer to process
+ * @len: frame length from the descriptor
+ *
+ * Process the buffer after it's written by HW. The regular path is to
+ * synchronize DMA for CPU, but in case of no data it will be immediately
+ * recycled back to its PP.
+ *
+ * Return: true when there's data to process, false otherwise.
+ */
+static inline bool libeth_rx_sync_for_cpu(const struct libeth_fqe *fqe,
+					  u32 len)
+{
+	struct page *page = fqe->page;
+
+	/* Very rare, but possible case. The most common reason:
+	 * the last fragment contained FCS only, which was then
+	 * stripped by the HW.
+	 */
+	if (unlikely(!len)) {
+		libeth_rx_recycle_slow(page);
+		return false;
+	}
+
+	page_pool_dma_sync_for_cpu(page->pp, page, fqe->offset, len);
+
+	return true;
+}
+
+/* Converting abstract packet type numbers into a software structure with
+ * the packet parameters to do O(1) lookup on Rx.
+ */
+
+enum {
+	LIBETH_RX_PT_OUTER_L2			= 0U,
+	LIBETH_RX_PT_OUTER_IPV4,
+	LIBETH_RX_PT_OUTER_IPV6,
+};
+
+enum {
+	LIBETH_RX_PT_NOT_FRAG			= 0U,
+	LIBETH_RX_PT_FRAG,
+};
+
+enum {
+	LIBETH_RX_PT_TUNNEL_IP_NONE		= 0U,
+	LIBETH_RX_PT_TUNNEL_IP_IP,
+	LIBETH_RX_PT_TUNNEL_IP_GRENAT,
+	LIBETH_RX_PT_TUNNEL_IP_GRENAT_MAC,
+	LIBETH_RX_PT_TUNNEL_IP_GRENAT_MAC_VLAN,
+};
+
+enum {
+	LIBETH_RX_PT_TUNNEL_END_NONE		= 0U,
+	LIBETH_RX_PT_TUNNEL_END_IPV4,
+	LIBETH_RX_PT_TUNNEL_END_IPV6,
+};
+
+enum {
+	LIBETH_RX_PT_INNER_NONE			= 0U,
+	LIBETH_RX_PT_INNER_UDP,
+	LIBETH_RX_PT_INNER_TCP,
+	LIBETH_RX_PT_INNER_SCTP,
+	LIBETH_RX_PT_INNER_ICMP,
+	LIBETH_RX_PT_INNER_TIMESYNC,
+};
+
+#define LIBETH_RX_PT_PAYLOAD_NONE		PKT_HASH_TYPE_NONE
+#define LIBETH_RX_PT_PAYLOAD_L2			PKT_HASH_TYPE_L2
+#define LIBETH_RX_PT_PAYLOAD_L3			PKT_HASH_TYPE_L3
+#define LIBETH_RX_PT_PAYLOAD_L4			PKT_HASH_TYPE_L4
+
+struct libeth_rx_pt {
+	u32					outer_ip:2;
+	u32					outer_frag:1;
+	u32					tunnel_type:3;
+	u32					tunnel_end_prot:2;
+	u32					tunnel_end_frag:1;
+	u32					inner_prot:3;
+	enum pkt_hash_types			payload_layer:2;
+
+	u32					pad:2;
+	enum xdp_rss_hash_type			hash_type:16;
+};
+
+void libeth_rx_pt_gen_hash_type(struct libeth_rx_pt *pt);
+
+/**
+ * libeth_rx_pt_get_ip_ver - get IP version from a packet type structure
+ * @pt: packet type params
+ *
+ * Wrapper to compile out the IPv6 code from the drivers when not supported
+ * by the kernel.
+ *
+ * Return: @pt.outer_ip or stub for IPv6 when not compiled-in.
+ */
+static inline u32 libeth_rx_pt_get_ip_ver(struct libeth_rx_pt pt)
+{
+#if !IS_ENABLED(CONFIG_IPV6)
+	switch (pt.outer_ip) {
+	case LIBETH_RX_PT_OUTER_IPV4:
+		return LIBETH_RX_PT_OUTER_IPV4;
+	default:
+		return LIBETH_RX_PT_OUTER_L2;
+	}
+#else
+	return pt.outer_ip;
+#endif
+}
+
+/* libeth_has_*() can be used to quickly check whether the HW metadata is
+ * available to avoid further expensive processing such as descriptor reads.
+ * They already check for the corresponding netdev feature to be enabled,
+ * thus can be used as drop-in replacements.
+ */
+
+static inline bool libeth_rx_pt_has_checksum(const struct net_device *dev,
+					     struct libeth_rx_pt pt)
+{
+	/* Non-zero _INNER* is only possible when _OUTER_IPV* is set,
+	 * it is enough to check only for the L4 type.
+	 */
+	return likely(pt.inner_prot > LIBETH_RX_PT_INNER_NONE &&
+		      (dev->features & NETIF_F_RXCSUM));
+}
+
+static inline bool libeth_rx_pt_has_hash(const struct net_device *dev,
+					 struct libeth_rx_pt pt)
+{
+	return likely(pt.payload_layer > LIBETH_RX_PT_PAYLOAD_NONE &&
+		      (dev->features & NETIF_F_RXHASH));
+}
+
+/**
+ * libeth_rx_pt_set_hash - fill in skb hash value basing on the PT
+ * @skb: skb to fill the hash in
+ * @hash: 32-bit hash value from the descriptor
+ * @pt: packet type
+ */
+static inline void libeth_rx_pt_set_hash(struct sk_buff *skb, u32 hash,
+					 struct libeth_rx_pt pt)
+{
+	skb_set_hash(skb, hash, pt.payload_layer);
+}
+
+#endif /* __LIBETH_RX_H */
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 1d397c1a004318..873631c79ab166 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -52,13 +52,15 @@
 #ifndef _NET_PAGE_POOL_HELPERS_H
 #define _NET_PAGE_POOL_HELPERS_H
 
+#include <linux/dma-mapping.h>
+
 #include <net/page_pool/types.h>
 
 #ifdef CONFIG_PAGE_POOL_STATS
 /* Deprecated driver-facing API, use netlink instead */
 int page_pool_ethtool_stats_get_count(void);
 u8 *page_pool_ethtool_stats_get_strings(u8 *data);
-u64 *page_pool_ethtool_stats_get(u64 *data, void *stats);
+u64 *page_pool_ethtool_stats_get(u64 *data, const void *stats);
 
 bool page_pool_get_stats(const struct page_pool *pool,
 			 struct page_pool_stats *stats);
@@ -73,7 +75,7 @@ static inline u8 *page_pool_ethtool_stats_get_strings(u8 *data)
 	return data;
 }
 
-static inline u64 *page_pool_ethtool_stats_get(u64 *data, void *stats)
+static inline u64 *page_pool_ethtool_stats_get(u64 *data, const void *stats)
 {
 	return data;
 }
@@ -204,8 +206,8 @@ static inline void *page_pool_dev_alloc_va(struct page_pool *pool,
  * Get the stored dma direction. A driver might decide to store this locally
  * and avoid the extra cache line from page_pool to determine the direction.
  */
-static
-inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
+static inline enum dma_data_direction
+page_pool_get_dma_dir(const struct page_pool *pool)
 {
 	return pool->p.dma_dir;
 }
@@ -370,7 +372,7 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va,
  * Fetch the DMA address of the page. The page pool to which the page belongs
  * must had been created with PP_FLAG_DMA_MAP.
  */
-static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
+static inline dma_addr_t page_pool_get_dma_addr(const struct page *page)
 {
 	dma_addr_t ret = page->dma_addr;
 
@@ -395,6 +397,28 @@ static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t 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
+ * @page: page to sync
+ * @offset: offset from page start to "hard" start if using PP frags
+ * @dma_sync_size: size of the data written to the page
+ *
+ * Can be used as a shorthand to sync Rx pages before accessing them in the
+ * driver. Caller must ensure the pool was created with ``PP_FLAG_DMA_MAP``.
+ * Note that this version performs DMA sync unconditionally, even if the
+ * associated PP doesn't perform sync-for-device.
+ */
+static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool,
+					      const struct page *page,
+					      u32 offset, u32 dma_sync_size)
+{
+	dma_sync_single_range_for_cpu(pool->p.dev,
+				      page_pool_get_dma_addr(page),
+				      offset + pool->p.offset, dma_sync_size,
+				      page_pool_get_dma_dir(pool));
+}
+
 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 5e43a08d3231c1..a6ebed0022160f 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -213,7 +213,7 @@ struct xdp_mem_info;
 #ifdef CONFIG_PAGE_POOL
 void page_pool_destroy(struct page_pool *pool);
 void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
-			   struct xdp_mem_info *mem);
+			   const struct xdp_mem_info *mem);
 void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 			     int count);
 #else
@@ -223,7 +223,7 @@ static inline void page_pool_destroy(struct page_pool *pool)
 
 static inline void page_pool_use_xdp_mem(struct page_pool *pool,
 					 void (*disconnect)(void *),
-					 struct xdp_mem_info *mem)
+					 const struct xdp_mem_info *mem)
 {
 }