Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2023-05-16

We've added 57 non-merge commits during the last 19 day(s) which contain
a total of 63 files changed, 3293 insertions(+), 690 deletions(-).

The main changes are:

1) Add precision propagation to verifier for subprogs and callbacks,
   from Andrii Nakryiko.

2) Improve BPF's {g,s}setsockopt() handling with wrong option lengths,
   from Stanislav Fomichev.

3) Utilize pahole v1.25 for the kernel's BTF generation to filter out
   inconsistent function prototypes, from Alan Maguire.

4) Various dyn-pointer verifier improvements to relax restrictions,
   from Daniel Rosenberg.

5) Add a new bpf_task_under_cgroup() kfunc for designated task,
   from Feng Zhou.

6) Unblock tests for arm64 BPF CI after ftrace supporting direct call,
   from Florent Revest.

7) Add XDP hint kfunc metadata for RX hash/timestamp for igc,
   from Jesper Dangaard Brouer.

8) Add several new dyn-pointer kfuncs to ease their usability,
   from Joanne Koong.

9) Add in-depth LRU internals description and dot function graph,
   from Joe Stringer.

10) Fix KCSAN report on bpf_lru_list when accessing node->ref,
    from Martin KaFai Lau.

11) Only dump unprivileged_bpf_disabled log warning upon write,
    from Kui-Feng Lee.

12) Extend test_progs to directly passing allow/denylist file,
    from Stephen Veiss.

13) Fix BPF trampoline memleak upon failure attaching to fentry,
    from Yafang Shao.

14) Fix emitting struct bpf_tcp_sock type in vmlinux BTF,
    from Yonghong Song.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (57 commits)
  bpf: Fix memleak due to fentry attach failure
  bpf: Remove bpf trampoline selector
  bpf, arm64: Support struct arguments in the BPF trampoline
  bpftool: JIT limited misreported as negative value on aarch64
  bpf: fix calculation of subseq_idx during precision backtracking
  bpf: Remove anonymous union in bpf_kfunc_call_arg_meta
  bpf: Document EFAULT changes for sockopt
  selftests/bpf: Correctly handle optlen > 4096
  selftests/bpf: Update EFAULT {g,s}etsockopt selftests
  bpf: Don't EFAULT for {g,s}setsockopt with wrong optlen
  libbpf: fix offsetof() and container_of() to work with CO-RE
  bpf: Address KCSAN report on bpf_lru_list
  bpf: Add --skip_encoding_btf_inconsistent_proto, --btf_gen_optimized to pahole flags for v1.25
  selftests/bpf: Accept mem from dynptr in helper funcs
  bpf: verifier: Accept dynptr mem as mem in helpers
  selftests/bpf: Check overflow in optional buffer
  selftests/bpf: Test allowing NULL buffer in dynptr slice
  bpf: Allow NULL buffers in bpf_dynptr_slice(_rw)
  selftests/bpf: Add testcase for bpf_task_under_cgroup
  bpf: Add bpf_task_under_cgroup() kfunc
  ...
====================

Link: https://lore.kernel.org/r/20230515225603.27027-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 105 insertions, 11 deletions

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 1c4676882082..38d113b48111 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1690,14 +1690,36 @@ static void igc_rx_checksum(struct igc_ring *ring,
 		   le32_to_cpu(rx_desc->wb.upper.status_error));
 }
 
+/* Mapping HW RSS Type to enum pkt_hash_types */
+static const enum pkt_hash_types igc_rss_type_table[IGC_RSS_TYPE_MAX_TABLE] = {
+	[IGC_RSS_TYPE_NO_HASH]		= PKT_HASH_TYPE_L2,
+	[IGC_RSS_TYPE_HASH_TCP_IPV4]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_IPV4]	= PKT_HASH_TYPE_L3,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_IPV6_EX]	= PKT_HASH_TYPE_L3,
+	[IGC_RSS_TYPE_HASH_IPV6]	= PKT_HASH_TYPE_L3,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6_EX] = PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_UDP_IPV4]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6_EX] = PKT_HASH_TYPE_L4,
+	[10] = PKT_HASH_TYPE_NONE, /* RSS Type above 9 "Reserved" by HW  */
+	[11] = PKT_HASH_TYPE_NONE, /* keep array sized for SW bit-mask   */
+	[12] = PKT_HASH_TYPE_NONE, /* to handle future HW revisons       */
+	[13] = PKT_HASH_TYPE_NONE,
+	[14] = PKT_HASH_TYPE_NONE,
+	[15] = PKT_HASH_TYPE_NONE,
+};
+
 static inline void igc_rx_hash(struct igc_ring *ring,
 			       union igc_adv_rx_desc *rx_desc,
 			       struct sk_buff *skb)
 {
-	if (ring->netdev->features & NETIF_F_RXHASH)
-		skb_set_hash(skb,
-			     le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
-			     PKT_HASH_TYPE_L3);
+	if (ring->netdev->features & NETIF_F_RXHASH) {
+		u32 rss_hash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
+		u32 rss_type = igc_rss_type(rx_desc);
+
+		skb_set_hash(skb, rss_hash, igc_rss_type_table[rss_type]);
+	}
 }
 
 static void igc_rx_vlan(struct igc_ring *rx_ring,
@@ -2214,6 +2236,8 @@ static bool igc_alloc_rx_buffers_zc(struct igc_ring *ring, u16 count)
 	if (!count)
 		return ok;
 
+	XSK_CHECK_PRIV_TYPE(struct igc_xdp_buff);
+
 	desc = IGC_RX_DESC(ring, i);
 	bi = &ring->rx_buffer_info[i];
 	i -= ring->count;
@@ -2498,8 +2522,8 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 		union igc_adv_rx_desc *rx_desc;
 		struct igc_rx_buffer *rx_buffer;
 		unsigned int size, truesize;
+		struct igc_xdp_buff ctx;
 		ktime_t timestamp = 0;
-		struct xdp_buff xdp;
 		int pkt_offset = 0;
 		void *pktbuf;
 
@@ -2528,18 +2552,20 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 		if (igc_test_staterr(rx_desc, IGC_RXDADV_STAT_TSIP)) {
 			timestamp = igc_ptp_rx_pktstamp(q_vector->adapter,
 							pktbuf);
+			ctx.rx_ts = timestamp;
 			pkt_offset = IGC_TS_HDR_LEN;
 			size -= IGC_TS_HDR_LEN;
 		}
 
 		if (!skb) {
-			xdp_init_buff(&xdp, truesize, &rx_ring->xdp_rxq);
-			xdp_prepare_buff(&xdp, pktbuf - igc_rx_offset(rx_ring),
+			xdp_init_buff(&ctx.xdp, truesize, &rx_ring->xdp_rxq);
+			xdp_prepare_buff(&ctx.xdp, pktbuf - igc_rx_offset(rx_ring),
 					 igc_rx_offset(rx_ring) + pkt_offset,
 					 size, true);
-			xdp_buff_clear_frags_flag(&xdp);
+			xdp_buff_clear_frags_flag(&ctx.xdp);
+			ctx.rx_desc = rx_desc;
 
-			skb = igc_xdp_run_prog(adapter, &xdp);
+			skb = igc_xdp_run_prog(adapter, &ctx.xdp);
 		}
 
 		if (IS_ERR(skb)) {
@@ -2561,9 +2587,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 		} else if (skb)
 			igc_add_rx_frag(rx_ring, rx_buffer, skb, size);
 		else if (ring_uses_build_skb(rx_ring))
-			skb = igc_build_skb(rx_ring, rx_buffer, &xdp);
+			skb = igc_build_skb(rx_ring, rx_buffer, &ctx.xdp);
 		else
-			skb = igc_construct_skb(rx_ring, rx_buffer, &xdp,
+			skb = igc_construct_skb(rx_ring, rx_buffer, &ctx.xdp,
 						timestamp);
 
 		/* exit if we failed to retrieve a buffer */
@@ -2664,6 +2690,15 @@ static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector,
 	napi_gro_receive(&q_vector->napi, skb);
 }
 
+static struct igc_xdp_buff *xsk_buff_to_igc_ctx(struct xdp_buff *xdp)
+{
+	/* xdp_buff pointer used by ZC code path is alloc as xdp_buff_xsk. The
+	 * igc_xdp_buff shares its layout with xdp_buff_xsk and private
+	 * igc_xdp_buff fields fall into xdp_buff_xsk->cb
+	 */
+       return (struct igc_xdp_buff *)xdp;
+}
+
 static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 {
 	struct igc_adapter *adapter = q_vector->adapter;
@@ -2682,6 +2717,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 	while (likely(total_packets < budget)) {
 		union igc_adv_rx_desc *desc;
 		struct igc_rx_buffer *bi;
+		struct igc_xdp_buff *ctx;
 		ktime_t timestamp = 0;
 		unsigned int size;
 		int res;
@@ -2699,9 +2735,13 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 
 		bi = &ring->rx_buffer_info[ntc];
 
+		ctx = xsk_buff_to_igc_ctx(bi->xdp);
+		ctx->rx_desc = desc;
+
 		if (igc_test_staterr(desc, IGC_RXDADV_STAT_TSIP)) {
 			timestamp = igc_ptp_rx_pktstamp(q_vector->adapter,
 							bi->xdp->data);
+			ctx->rx_ts = timestamp;
 
 			bi->xdp->data += IGC_TS_HDR_LEN;
 
@@ -6454,6 +6494,58 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg)
 	return value;
 }
 
+/* Mapping HW RSS Type to enum xdp_rss_hash_type */
+static enum xdp_rss_hash_type igc_xdp_rss_type[IGC_RSS_TYPE_MAX_TABLE] = {
+	[IGC_RSS_TYPE_NO_HASH]		= XDP_RSS_TYPE_L2,
+	[IGC_RSS_TYPE_HASH_TCP_IPV4]	= XDP_RSS_TYPE_L4_IPV4_TCP,
+	[IGC_RSS_TYPE_HASH_IPV4]	= XDP_RSS_TYPE_L3_IPV4,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6]	= XDP_RSS_TYPE_L4_IPV6_TCP,
+	[IGC_RSS_TYPE_HASH_IPV6_EX]	= XDP_RSS_TYPE_L3_IPV6_EX,
+	[IGC_RSS_TYPE_HASH_IPV6]	= XDP_RSS_TYPE_L3_IPV6,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6_EX] = XDP_RSS_TYPE_L4_IPV6_TCP_EX,
+	[IGC_RSS_TYPE_HASH_UDP_IPV4]	= XDP_RSS_TYPE_L4_IPV4_UDP,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6]	= XDP_RSS_TYPE_L4_IPV6_UDP,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6_EX] = XDP_RSS_TYPE_L4_IPV6_UDP_EX,
+	[10] = XDP_RSS_TYPE_NONE, /* RSS Type above 9 "Reserved" by HW  */
+	[11] = XDP_RSS_TYPE_NONE, /* keep array sized for SW bit-mask   */
+	[12] = XDP_RSS_TYPE_NONE, /* to handle future HW revisons       */
+	[13] = XDP_RSS_TYPE_NONE,
+	[14] = XDP_RSS_TYPE_NONE,
+	[15] = XDP_RSS_TYPE_NONE,
+};
+
+static int igc_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash,
+			   enum xdp_rss_hash_type *rss_type)
+{
+	const struct igc_xdp_buff *ctx = (void *)_ctx;
+
+	if (!(ctx->xdp.rxq->dev->features & NETIF_F_RXHASH))
+		return -ENODATA;
+
+	*hash = le32_to_cpu(ctx->rx_desc->wb.lower.hi_dword.rss);
+	*rss_type = igc_xdp_rss_type[igc_rss_type(ctx->rx_desc)];
+
+	return 0;
+}
+
+static int igc_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp)
+{
+	const struct igc_xdp_buff *ctx = (void *)_ctx;
+
+	if (igc_test_staterr(ctx->rx_desc, IGC_RXDADV_STAT_TSIP)) {
+		*timestamp = ctx->rx_ts;
+
+		return 0;
+	}
+
+	return -ENODATA;
+}
+
+static const struct xdp_metadata_ops igc_xdp_metadata_ops = {
+	.xmo_rx_hash			= igc_xdp_rx_hash,
+	.xmo_rx_timestamp		= igc_xdp_rx_timestamp,
+};
+
 /**
  * igc_probe - Device Initialization Routine
  * @pdev: PCI device information struct
@@ -6527,6 +6619,7 @@ static int igc_probe(struct pci_dev *pdev,
 	hw->hw_addr = adapter->io_addr;
 
 	netdev->netdev_ops = &igc_netdev_ops;
+	netdev->xdp_metadata_ops = &igc_xdp_metadata_ops;
 	igc_ethtool_set_ops(netdev);
 	netdev->watchdog_timeo = 5 * HZ;
 
@@ -6554,6 +6647,7 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->features |= NETIF_F_TSO;
 	netdev->features |= NETIF_F_TSO6;
 	netdev->features |= NETIF_F_TSO_ECN;
+	netdev->features |= NETIF_F_RXHASH;
 	netdev->features |= NETIF_F_RXCSUM;
 	netdev->features |= NETIF_F_HW_CSUM;
 	netdev->features |= NETIF_F_SCTP_CRC;