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

Daniel Borkmann says:

====================
bpf-next 2023-01-28

We've added 124 non-merge commits during the last 22 day(s) which contain
a total of 124 files changed, 6386 insertions(+), 1827 deletions(-).

The main changes are:

1) Implement XDP hints via kfuncs with initial support for RX hash and
   timestamp metadata kfuncs, from Stanislav Fomichev and
   Toke Høiland-Jørgensen.
   Measurements on overhead: https://lore.kernel.org/bpf/875yellcx6.fsf@toke.dk

2) Extend libbpf's bpf_tracing.h support for tracing arguments of
   kprobes/uprobes and syscall as a special case, from Andrii Nakryiko.

3) Significantly reduce the search time for module symbols by livepatch
   and BPF, from Jiri Olsa and Zhen Lei.

4) Enable cpumasks to be used as kptrs, which is useful for tracing
   programs tracking which tasks end up running on which CPUs
   in different time intervals, from David Vernet.

5) Fix several issues in the dynptr processing such as stack slot liveness
   propagation, missing checks for PTR_TO_STACK variable offset, etc,
   from Kumar Kartikeya Dwivedi.

6) Various performance improvements, fixes, and introduction of more
   than just one XDP program to XSK selftests, from Magnus Karlsson.

7) Big batch to BPF samples to reduce deprecated functionality,
   from Daniel T. Lee.

8) Enable struct_ops programs to be sleepable in verifier,
   from David Vernet.

9) Reduce pr_warn() noise on BTF mismatches when they are expected under
   the CONFIG_MODULE_ALLOW_BTF_MISMATCH config anyway, from Connor O'Brien.

10) Describe modulo and division by zero behavior of the BPF runtime
    in BPF's instruction specification document, from Dave Thaler.

11) Several improvements to libbpf API documentation in libbpf.h,
    from Grant Seltzer.

12) Improve resolve_btfids header dependencies related to subcmd and add
    proper support for HOSTCC, from Ian Rogers.

13) Add ipip6 and ip6ip decapsulation support for bpf_skb_adjust_room()
    helper along with BPF selftests, from Ziyang Xuan.

14) Simplify the parsing logic of structure parameters for BPF trampoline
    in the x86-64 JIT compiler, from Pu Lehui.

15) Get BTF working for kernels with CONFIG_RUST enabled by excluding
    Rust compilation units with pahole, from Martin Rodriguez Reboredo.

16) Get bpf_setsockopt() working for kTLS on top of TCP sockets,
    from Kui-Feng Lee.

17) Disable stack protection for BPF objects in bpftool given BPF backends
    don't support it, from Holger Hoffstätte.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (124 commits)
  selftest/bpf: Make crashes more debuggable in test_progs
  libbpf: Add documentation to map pinning API functions
  libbpf: Fix malformed documentation formatting
  selftests/bpf: Properly enable hwtstamp in xdp_hw_metadata
  selftests/bpf: Calls bpf_setsockopt() on a ktls enabled socket.
  bpf: Check the protocol of a sock to agree the calls to bpf_setsockopt().
  bpf/selftests: Verify struct_ops prog sleepable behavior
  bpf: Pass const struct bpf_prog * to .check_member
  libbpf: Support sleepable struct_ops.s section
  bpf: Allow BPF_PROG_TYPE_STRUCT_OPS programs to be sleepable
  selftests/bpf: Fix vmtest static compilation error
  tools/resolve_btfids: Alter how HOSTCC is forced
  tools/resolve_btfids: Install subcmd headers
  bpf/docs: Document the nocast aliasing behavior of ___init
  bpf/docs: Document how nested trusted fields may be defined
  bpf/docs: Document cpumask kfuncs in a new file
  selftests/bpf: Add selftest suite for cpumask kfuncs
  selftests/bpf: Add nested trust selftests suite
  bpf: Enable cpumasks to be queried and used as kptrs
  bpf: Disallow NULLable pointers for trusted kfuncs
  ...
====================

Link: https://lore.kernel.org/r/20230128004827.21371-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 69 insertions, 18 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index 98b5ffb4d729..9e3b76182088 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -58,9 +58,7 @@ u64 mlx4_en_get_cqe_ts(struct mlx4_cqe *cqe)
 	return hi | lo;
 }
 
-void mlx4_en_fill_hwtstamps(struct mlx4_en_dev *mdev,
-			    struct skb_shared_hwtstamps *hwts,
-			    u64 timestamp)
+u64 mlx4_en_get_hwtstamp(struct mlx4_en_dev *mdev, u64 timestamp)
 {
 	unsigned int seq;
 	u64 nsec;
@@ -70,8 +68,15 @@ void mlx4_en_fill_hwtstamps(struct mlx4_en_dev *mdev,
 		nsec = timecounter_cyc2time(&mdev->clock, timestamp);
 	} while (read_seqretry(&mdev->clock_lock, seq));
 
+	return ns_to_ktime(nsec);
+}
+
+void mlx4_en_fill_hwtstamps(struct mlx4_en_dev *mdev,
+			    struct skb_shared_hwtstamps *hwts,
+			    u64 timestamp)
+{
 	memset(hwts, 0, sizeof(struct skb_shared_hwtstamps));
-	hwts->hwtstamp = ns_to_ktime(nsec);
+	hwts->hwtstamp = mlx4_en_get_hwtstamp(mdev, timestamp);
 }
 
 /**
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 8800d3f1f55c..af4c4858f397 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2889,6 +2889,11 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
 	.ndo_bpf		= mlx4_xdp,
 };
 
+static const struct xdp_metadata_ops mlx4_xdp_metadata_ops = {
+	.xmo_rx_timestamp		= mlx4_en_xdp_rx_timestamp,
+	.xmo_rx_hash			= mlx4_en_xdp_rx_hash,
+};
+
 struct mlx4_en_bond {
 	struct work_struct work;
 	struct mlx4_en_priv *priv;
@@ -3310,6 +3315,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		dev->netdev_ops = &mlx4_netdev_ops_master;
 	else
 		dev->netdev_ops = &mlx4_netdev_ops;
+	dev->xdp_metadata_ops = &mlx4_xdp_metadata_ops;
 	dev->watchdog_timeo = MLX4_EN_WATCHDOG_TIMEOUT;
 	netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]);
 	netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 8f762fc170b3..0869d4fff17b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -661,9 +661,41 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 #define MLX4_CQE_STATUS_IP_ANY (MLX4_CQE_STATUS_IPV4)
 #endif
 
+struct mlx4_en_xdp_buff {
+	struct xdp_buff xdp;
+	struct mlx4_cqe *cqe;
+	struct mlx4_en_dev *mdev;
+	struct mlx4_en_rx_ring *ring;
+	struct net_device *dev;
+};
+
+int mlx4_en_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
+{
+	struct mlx4_en_xdp_buff *_ctx = (void *)ctx;
+
+	if (unlikely(_ctx->ring->hwtstamp_rx_filter != HWTSTAMP_FILTER_ALL))
+		return -EOPNOTSUPP;
+
+	*timestamp = mlx4_en_get_hwtstamp(_ctx->mdev,
+					  mlx4_en_get_cqe_ts(_ctx->cqe));
+	return 0;
+}
+
+int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash)
+{
+	struct mlx4_en_xdp_buff *_ctx = (void *)ctx;
+
+	if (unlikely(!(_ctx->dev->features & NETIF_F_RXHASH)))
+		return -EOPNOTSUPP;
+
+	*hash = be32_to_cpu(_ctx->cqe->immed_rss_invalid);
+	return 0;
+}
+
 int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int budget)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_xdp_buff mxbuf = {};
 	int factor = priv->cqe_factor;
 	struct mlx4_en_rx_ring *ring;
 	struct bpf_prog *xdp_prog;
@@ -671,7 +703,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	bool doorbell_pending;
 	bool xdp_redir_flush;
 	struct mlx4_cqe *cqe;
-	struct xdp_buff xdp;
 	int polled = 0;
 	int index;
 
@@ -681,7 +712,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	ring = priv->rx_ring[cq_ring];
 
 	xdp_prog = rcu_dereference_bh(ring->xdp_prog);
-	xdp_init_buff(&xdp, priv->frag_info[0].frag_stride, &ring->xdp_rxq);
+	xdp_init_buff(&mxbuf.xdp, priv->frag_info[0].frag_stride, &ring->xdp_rxq);
 	doorbell_pending = false;
 	xdp_redir_flush = false;
 
@@ -776,24 +807,28 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 						priv->frag_info[0].frag_size,
 						DMA_FROM_DEVICE);
 
-			xdp_prepare_buff(&xdp, va - frags[0].page_offset,
-					 frags[0].page_offset, length, false);
-			orig_data = xdp.data;
-
-			act = bpf_prog_run_xdp(xdp_prog, &xdp);
-
-			length = xdp.data_end - xdp.data;
-			if (xdp.data != orig_data) {
-				frags[0].page_offset = xdp.data -
-					xdp.data_hard_start;
-				va = xdp.data;
+			xdp_prepare_buff(&mxbuf.xdp, va - frags[0].page_offset,
+					 frags[0].page_offset, length, true);
+			orig_data = mxbuf.xdp.data;
+			mxbuf.cqe = cqe;
+			mxbuf.mdev = priv->mdev;
+			mxbuf.ring = ring;
+			mxbuf.dev = dev;
+
+			act = bpf_prog_run_xdp(xdp_prog, &mxbuf.xdp);
+
+			length = mxbuf.xdp.data_end - mxbuf.xdp.data;
+			if (mxbuf.xdp.data != orig_data) {
+				frags[0].page_offset = mxbuf.xdp.data -
+					mxbuf.xdp.data_hard_start;
+				va = mxbuf.xdp.data;
 			}
 
 			switch (act) {
 			case XDP_PASS:
 				break;
 			case XDP_REDIRECT:
-				if (likely(!xdp_do_redirect(dev, &xdp, xdp_prog))) {
+				if (likely(!xdp_do_redirect(dev, &mxbuf.xdp, xdp_prog))) {
 					ring->xdp_redirect++;
 					xdp_redir_flush = true;
 					frags[0].page = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 3d4226ddba5e..544e09b97483 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -796,10 +796,15 @@ void mlx4_en_update_pfc_stats_bitmap(struct mlx4_dev *dev,
 int mlx4_en_netdev_event(struct notifier_block *this,
 			 unsigned long event, void *ptr);
 
+struct xdp_md;
+int mlx4_en_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp);
+int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash);
+
 /*
  * Functions for time stamping
  */
 u64 mlx4_en_get_cqe_ts(struct mlx4_cqe *cqe);
+u64 mlx4_en_get_hwtstamp(struct mlx4_en_dev *mdev, u64 timestamp);
 void mlx4_en_fill_hwtstamps(struct mlx4_en_dev *mdev,
 			    struct skb_shared_hwtstamps *hwts,
 			    u64 timestamp);