BPF sample with helper for accessing meta

drivers/net/ethernet/intel/ice/ice.h

@@ -424,6 +424,9 @@ struct ice_vsi {
 
 	struct ice_channel *ch;
 
+	u8 xdp_metadata_support:1;	 /* true if VSI should support xdp meta */
+	struct xdp_meta_tail xdp_meta_tail;
+
 	/* setup back reference, to which aggregator node this VSI
 	 * corresponds to
 	 */

drivers/net/ethernet/intel/ice/ice_main.c

@@ -2607,6 +2607,21 @@ static void ice_vsi_assign_bpf_prog(struct ice_vsi *vsi, struct bpf_prog *prog)
 		WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog);
 }
 
+static void ice_xdp_rings_set_metadata(const struct ice_vsi *vsi)
+{
+	int i;
+
+	ice_for_each_rxq(vsi, i) {
+		vsi->rx_rings[i]->xdp_metadata_support = vsi->xdp_metadata_support;
+		vsi->rx_rings[i]->xdp_meta_tail = vsi->xdp_meta_tail;
+	}
+
+	for (i = 0; i < vsi->num_xdp_txq; i++) {
+		vsi->xdp_rings[i]->xdp_metadata_support = vsi->xdp_metadata_support;
+		vsi->xdp_rings[i]->xdp_meta_tail = vsi->xdp_meta_tail;
+	}
+}
+
 /**
  * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP
  * @vsi: VSI to bring up Tx rings used by XDP
@@ -2650,6 +2665,8 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog)
 	if (ice_xdp_alloc_setup_rings(vsi))
 		goto clear_xdp_rings;
 
+	ice_xdp_rings_set_metadata(vsi);
+
 	/* follow the logic from ice_vsi_map_rings_to_vectors */
 	ice_for_each_q_vector(vsi, v_idx) {
 		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
@@ -2842,7 +2859,7 @@ int ice_vsi_determine_xdp_res(struct ice_vsi *vsi)
  */
 static int
 ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
-		   struct netlink_ext_ack *extack)
+		   struct netlink_ext_ack *extack, u32 flags)
 {
 	int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD;
 	bool if_running = netif_running(vsi->netdev);
@@ -2862,6 +2879,18 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 		}
 	}
 
+	if (flags & XDP_FLAGS_USE_METADATA) {
+		vsi->xdp_metadata_support = true;
+		ret = xdp_meta_fill_id_magic(&vsi->xdp_meta_tail, THIS_MODULE,
+					     "xdp_meta_generic");
+		if (ret) {
+			NL_SET_ERR_MSG_MOD(extack, "Could not fill in xdp meta tail");
+			vsi->xdp_metadata_support = false;
+		}
+	} else {
+		vsi->xdp_metadata_support = false;
+	}
+
 	if (!ice_is_xdp_ena_vsi(vsi) && prog) {
 		xdp_ring_err = ice_vsi_determine_xdp_res(vsi);
 		if (xdp_ring_err) {
@@ -2924,7 +2953,7 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
-		return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
+		return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack, xdp->flags);
 	case XDP_SETUP_XSK_POOL:
 		return ice_xsk_pool_setup(vsi, xdp->xsk.pool,
 					  xdp->xsk.queue_id);

drivers/net/ethernet/intel/ice/ice_txrx.c

@@ -1184,6 +1184,10 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		hard_start = page_address(rx_buf->page) + rx_buf->page_offset -
 			     offset;
 		xdp_prepare_buff(&xdp, hard_start, offset, size, true);
+
+		if (likely(rx_ring->xdp_metadata_support))
+			ice_xdp_set_meta(&xdp, rx_desc, rx_ring->xdp_meta_tail);
+
 #if (PAGE_SIZE > 4096)
 		/* At larger PAGE_SIZE, frame_sz depend on len size */
 		xdp.frame_sz = ice_rx_frame_truesize(rx_ring, size);

drivers/net/ethernet/intel/ice/ice_txrx.h

@@ -294,6 +294,10 @@ struct ice_rx_ring {
 	struct xsk_buff_pool *xsk_pool;
 	struct sk_buff *skb;
 	dma_addr_t dma;			/* physical address of ring */
+
+	u8 xdp_metadata_support:1;	/* is xdp metadata supported */
+	struct xdp_meta_tail xdp_meta_tail;
+
 #define ICE_RX_FLAGS_RING_BUILD_SKB	BIT(1)
 	u64 cached_phctime;
 	u8 dcb_tc;			/* Traffic class of ring */
@@ -322,6 +326,7 @@ struct ice_tx_ring {
 	u16 reg_idx;			/* HW register index of the ring */
 	u16 count;			/* Number of descriptors */
 	u16 q_index;			/* Queue number of ring */
+
 	/* stats structs */
 	struct ice_txq_stats tx_stats;
 	/* CL3 - 3rd cacheline starts here */
@@ -335,6 +340,10 @@ struct ice_tx_ring {
 	u32 txq_teid;			/* Added Tx queue TEID */
 	/* CL4 - 4th cacheline starts here */
 	u16 xdp_tx_active;
+
+	u8 xdp_metadata_support:1;	/* is xdp metadata supported */
+	struct xdp_meta_tail xdp_meta_tail;
+
 #define ICE_TX_FLAGS_RING_XDP		BIT(0)
 #define ICE_TX_FLAGS_RING_VLAN_L2TAG1	BIT(1)
 #define ICE_TX_FLAGS_RING_VLAN_L2TAG2	BIT(2)

drivers/net/ethernet/intel/ice/ice_txrx_lib.h

@@ -70,6 +70,32 @@ static inline void ice_xdp_ring_update_tail(struct ice_tx_ring *xdp_ring)
 	writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail);
 }
 
+static inline void ice_xdp_set_meta(struct xdp_buff *xdp, const union ice_32b_rx_flex_desc *desc,
+				    const struct xdp_meta_tail tail)
+{
+	const struct ice_32b_rx_flex_desc_nic *flex = (struct ice_32b_rx_flex_desc_nic *)desc;
+	struct xdp_meta_generic *md = xdp->data - sizeof(struct xdp_meta_generic);
+
+	/* Fields are already in little endian*/
+	md->rx_vid = flex->flex_ts.flex.vlan_id;
+	md->rx_hash = flex->rss_hash;
+
+	md->rx_flags = 0;
+	md->rx_qid = 0;
+	md->rx_csum = 0;
+	md->rx_tstamp = 0;
+
+	md->tx_flags = 0;
+	md->tx_csum_off = 0;
+	md->tx_vid = 0;
+
+	md->btf_id = tail.btf_id;
+	md->type_id = tail.type_id;
+	md->magic = tail.magic;
+
+	xdp->data_meta = md;
+}
+
 void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res);
 int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring);
 int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring);

include/linux/btf.h

@@ -117,6 +117,7 @@ u32 btf_obj_id(const struct btf *btf);
 bool btf_is_kernel(const struct btf *btf);
 bool btf_is_module(const struct btf *btf);
 struct module *btf_try_get_module(const struct btf *btf);
+struct btf *btf_get_module_btf(const struct module *module);
 u32 btf_nr_types(const struct btf *btf);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,

include/net/xdp.h

@@ -245,6 +245,15 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp);
 struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf);
 
+struct xdp_meta_tail {
+	__le32 btf_id;
+	__le32 type_id;
+	__le32 magic;
+};
+
+int xdp_meta_fill_id_magic(struct xdp_meta_tail *tail, const struct module *mod,
+			   const char *type_name);
+
 static inline
 void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
 {

include/uapi/linux/bpf.h

@@ -8,6 +8,7 @@
 #ifndef _UAPI__LINUX_BPF_H__
 #define _UAPI__LINUX_BPF_H__
 
+#include <asm/byteorder.h>
 #include <linux/types.h>
 #include <linux/bpf_common.h>
 
@@ -6634,4 +6635,170 @@ struct bpf_core_relo {
 	enum bpf_core_relo_kind kind;
 };
 
+/* Definitions being used to work with &xdp_meta_generic, declared as an enum
+ * so they are visible for BPF programs via vmlinux.h.
+ */
+enum xdp_meta_generic_defs {
+	/* xdp_meta_generic::tx_flags */
+
+	/* Metadata carries valid Tx timestamp */
+	XDP_META_TX_TSTAMP_PRESENT	= (0x1 << 4),
+	/* Mask of the bits containing Tx VLAN action */
+	XDP_META_TX_VLAN_TYPE		= (0x3 << 2),
+	/* No action is needed */
+	XDP_META_TX_VLAN_NONE		= 0x0,
+	/* NIC must push C-VLAN tag */
+	XDP_META_TX_CVID		= 0x1,
+	/* NIC must push S-VLAN tag */
+	XDP_META_TX_SVID		= 0x2,
+	/* Mask of the bits containing Tx checksum action */
+	XDP_META_TX_CSUM_ACT		= (0x3 << 0),
+	/* No action for checksum */
+	XDP_META_TX_CSUM_ASIS		= 0x0,
+	/* NIC must compute checksum, no start/offset are provided */
+	XDP_META_TX_CSUM_AUTO		= 0x1,
+	/* NIC must compute checksum using the provided start and offset */
+	XDP_META_TX_CSUM_HELP		= 0x2,
+
+	/* xdp_meta_generic::rx_flags */
+
+	/* Metadata contains valid Rx queue ID */
+	XDP_META_RX_QID_PRESENT		= (0x1 << 9),
+	/* Metadata contains valid Rx timestamp */
+	XDP_META_RX_TSTAMP_PRESENT	= (0x1 << 8),
+	/* Mask of the bits containing Rx VLAN status */
+	XDP_META_RX_VLAN_TYPE		= (0x3 << 6),
+	/* Metadata does not have any VLAN tags */
+	XDP_META_RX_VLAN_NONE		= 0x0,
+	/* Metadata carries valid C-VLAN tag */
+	XDP_META_RX_CVID		= 0x1,
+	/* Metadata carries valid S-VLAN tag */
+	XDP_META_RX_SVID		= 0x2,
+	/* Mask of the bits containing Rx hash status */
+	XDP_META_RX_HASH_TYPE		= (0x3 << 4),
+	/* Metadata has no RSS hash */
+	XDP_META_RX_HASH_NONE		= 0x0,
+	/* Metadata has valid L2 hash */
+	XDP_META_RX_HASH_L2		= 0x1,
+	/* Metadata has valid L3 hash */
+	XDP_META_RX_HASH_L3		= 0x2,
+	/* Metadata has valid L4 hash */
+	XDP_META_RX_HASH_L4		= 0x3,
+	/* Mask of the field containing checksum level (if there's encap) */
+	XDP_META_RX_CSUM_LEVEL		= (0x3 << 2),
+	/* Mask of the bits containing Rx checksum status */
+	XDP_META_RX_CSUM_STATUS		= (0x3 << 0),
+	/* Metadata has no checksum info */
+	XDP_META_RX_CSUM_NONE		= 0x0,
+	/* Checksum has been verified by NIC */
+	XDP_META_RX_CSUM_OK		= 0x1,
+	/* Metadata carries valid checksum */
+	XDP_META_RX_CSUM_COMP		= 0x2,
+
+	/* xdp_meta_generic::magic_id indicates that the metadata is either
+	 * struct xdp_meta_generic itself or contains it at the end -> can be
+	 * used to get/set HW hints.
+	 * Direct btf_id comparison is not enough here as a custom structure
+	 * caring xdp_meta_generic at the end will have a different ID.
+	 */
+	XDP_META_GENERIC_MAGIC	= 0xeda6,
+};
+
+/* Generic metadata can be composed directly by HW, plus it should always
+ * have the first field as __le16 to account the 2 bytes of "IP align", so
+ * we pack it to avoid unexpected paddings. Also, it should be aligned to
+ * sizeof(__be16) as any other Ethernet data, and to optimize access on the
+ * 32-bit platforms.
+ */
+#define __xdp_meta_generic_attrs			\
+	__attribute__((__packed__))			\
+	__attribute__((aligned(sizeof(__be16))))
+
+/* Depending on the field layout inside the structure, it might or might not
+ * emit a "packed attribute is unnecessary" warning (when enabled, e.g. in
+ * libbpf). To not add and remove the attributes on each field addition,
+ * just suppress it.
+ */
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wpacked"
+
+/* All fields have explicit endianness, as it might be composed by HW.
+ * Byteswaps are needed for the Big Endian architectures to access the
+ * fields.
+ */
+struct xdp_meta_generic {
+	/* Add new fields here */
+
+	/* Egress part */
+	__struct_group(/* no tag */, tx, __xdp_meta_generic_attrs,
+		/* Offset from the start of the frame to the L4 header
+		 * to compute checksum for
+		 */
+		__le16 tx_csum_start;
+		/* Offset inside the L4 header to the checksum field */
+		__le16 tx_csum_off;
+		/* ID for hardware VLAN push */
+		__le16 tx_vid;
+		/* Flags indicating which Tx metadata is used */
+		__le32 tx_flags;
+		/* Tx timestamp value */
+		__le64 tx_tstamp;
+	);
+
+	/* Shortcut for the half relevant on ingress: Rx + IDs */
+	__struct_group(xdp_meta_generic_rx, rx_full, __xdp_meta_generic_attrs,
+		/* Ingress part */
+		__struct_group(/* no tag */, rx, __xdp_meta_generic_attrs,
+			/* Rx timestamp value */
+			__le64 rx_tstamp;
+			/* Rx hash value */
+			__le32 rx_hash;
+			/* Rx checksum value */
+			__le32 rx_csum;
+			/* VLAN ID popped on Rx */
+			__le16 rx_vid;
+			/* Rx queue ID on which the frame has arrived */
+			__le16 rx_qid;
+			/* Flags indicating which Rx metadata is used */
+			__le32 rx_flags;
+		);
+
+		/* Unique metadata identifiers */
+		__struct_group(/* no tag */, id, __xdp_meta_generic_attrs,
+			union {
+				struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+					/* Indicates the ID of the BTF which
+					 * the below type ID comes from, as
+					 * several kernel modules may have
+					 * identical type IDs
+					 */
+					__le32 btf_id;
+					/* Indicates the ID of the actual
+					 * structure passed as metadata,
+					 * within the above BTF ID
+					 */
+					__le32 type_id;
+#else /* __LITTLE_ENDIAN_BITFIELD */
+					__le32 type_id;
+					__le32 btf_id;
+#endif /* __LITTLE_ENDIAN_BITFIELD */
+				};
+				/* BPF program gets IDs coded as one __u64:
+				 * `btf_id << 32 | type_id`, allow direct
+				 * comparison
+				 */
+				__le64 full_id;
+			};
+			/* If set to the correct value, indicates that the
+			 * meta is generic-compatible and can be used by
+			 * the consumers of generic metadata
+			 */
+			__le16 magic;
+		);
+	);
+} __xdp_meta_generic_attrs;
+
+#pragma GCC diagnostic pop
+
 #endif /* _UAPI__LINUX_BPF_H__ */

include/uapi/linux/if_link.h

@@ -1275,11 +1275,13 @@ enum {
 #define XDP_FLAGS_DRV_MODE		(1U << 2)
 #define XDP_FLAGS_HW_MODE		(1U << 3)
 #define XDP_FLAGS_REPLACE		(1U << 4)
+#define XDP_FLAGS_USE_METADATA		(1U << 5)
 #define XDP_FLAGS_MODES			(XDP_FLAGS_SKB_MODE | \
 					 XDP_FLAGS_DRV_MODE | \
 					 XDP_FLAGS_HW_MODE)
 #define XDP_FLAGS_MASK			(XDP_FLAGS_UPDATE_IF_NOEXIST | \
-					 XDP_FLAGS_MODES | XDP_FLAGS_REPLACE)
+					 XDP_FLAGS_MODES | XDP_FLAGS_REPLACE | \
+					 XDP_FLAGS_USE_METADATA)
 
 /* These are stored into IFLA_XDP_ATTACHED on dump. */
 enum {

kernel/bpf/btf.c

@@ -6576,7 +6576,7 @@ struct module *btf_try_get_module(const struct btf *btf)
 /* Returns struct btf corresponding to the struct module.
  * This function can return NULL or ERR_PTR.
  */
-static struct btf *btf_get_module_btf(const struct module *module)
+struct btf *btf_get_module_btf(const struct module *module)
 {
 #ifdef CONFIG_DEBUG_INFO_BTF_MODULES
 	struct btf_module *btf_mod, *tmp;

kernel/bpf/cpumap.c

@@ -215,6 +215,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 {
 	struct xdp_rxq_info rxq;
 	struct xdp_buff xdp;
+	volatile struct xdp_meta_generic xdp_meta_generic;
 	int i, nframes = 0;
 
 	xdp_set_return_frame_no_direct();